From 6198221fa0df0298513b35796f63f242ea97134e Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 29 May 2013 15:59:39 -0600 Subject: NVMe: Disk IO statistics Add io stats accounting for bio requests so nvme block devices show useful disk stats. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f451c8d6e231..5d7c07946fbe 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -572,6 +572,7 @@ struct nvme_iod { int offset; /* Of PRP list */ int nents; /* Used in scatterlist */ int length; /* Of data, in bytes */ + unsigned long start_time; dma_addr_t first_dma; struct scatterlist sg[0]; }; -- cgit v1.2.3 From faef31b482549640e2d0095afdf3dedb992cfa80 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 21 Feb 2013 15:04:08 -0800 Subject: clocksource: time-armada-370-xp: Fix sparse warning drivers/clocksource/time-armada-370-xp.c:217:13: warning: symbol 'armada_370_xp_timer_init' was not declared. Should it be static? Also remove the __init marking in the prototype as it's unnecessary and drop the init.h file. Acked-by: Gregory CLEMENT Acked-by: Marc Zyngier Signed-off-by: Stephen Boyd --- include/linux/time-armada-370-xp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time-armada-370-xp.h b/include/linux/time-armada-370-xp.h index dfdfdc03115b..6fb0856b9405 100644 --- a/include/linux/time-armada-370-xp.h +++ b/include/linux/time-armada-370-xp.h @@ -11,8 +11,6 @@ #ifndef __TIME_ARMADA_370_XPPRCMU_H #define __TIME_ARMADA_370_XPPRCMU_H -#include - -void __init armada_370_xp_timer_init(void); +void armada_370_xp_timer_init(void); #endif -- cgit v1.2.3 From f825c736e75b11adb59ec52a4a1096efddd2ec97 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 2 Jul 2013 11:15:15 +0530 Subject: mm/cma: Move dma contiguous changes into a seperate config We want to use CMA for allocating hash page table and real mode area for PPC64. Hence move DMA contiguous related changes into a seperate config so that ppc64 can enable CMA without requiring DMA contiguous. Acked-by: Michal Nazarewicz Acked-by: Paul Mackerras Signed-off-by: Aneesh Kumar K.V [removed defconfig changes] Signed-off-by: Marek Szyprowski --- include/linux/dma-contiguous.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 01b5c84be828..00141d3325fe 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -57,7 +57,7 @@ struct cma; struct page; struct device; -#ifdef CONFIG_CMA +#ifdef CONFIG_DMA_CMA /* * There is always at least global CMA area and a few optional device -- cgit v1.2.3 From 7d11965ddb9b9b1e0a5d13c58345ada1ccbc663b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 16 May 2013 17:20:32 +0200 Subject: lib/raid6: add ARM-NEON accelerated syndrome calculation Rebased/reworked a patch contributed by Rob Herring that uses NEON intrinsics to perform the RAID-6 syndrome calculations. It uses the existing unroll.awk code to generate several unrolled versions of which the best performing one is selected at boot time. Signed-off-by: Ard Biesheuvel Acked-by: Nicolas Pitre Cc: hpa@linux.intel.com --- include/linux/raid/pq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 8dfaa2ce2e95..0f424698064f 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -114,6 +114,11 @@ extern const struct raid6_recov_calls raid6_recov_intx1; extern const struct raid6_recov_calls raid6_recov_ssse3; extern const struct raid6_recov_calls raid6_recov_avx2; +extern const struct raid6_calls raid6_neonx1; +extern const struct raid6_calls raid6_neonx2; +extern const struct raid6_calls raid6_neonx4; +extern const struct raid6_calls raid6_neonx8; + /* Algorithm list */ extern const struct raid6_calls * const raid6_algos[]; extern const struct raid6_recov_calls *const raid6_recov_algos[]; -- cgit v1.2.3 From a8855990e382fc81c04187c5fdb48743307baf32 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 9 Jul 2013 22:36:45 +0800 Subject: writeback: Do not sort b_io list only because of block device inode It is very likely that block device inode will be part of BDI dirty list as well. However it doesn't make sence to sort inodes on the b_io list just because of this inode (as it contains buffers all over the device anyway). So save some CPU cycles which is valuable since we hold relatively contented wb->list_lock. Signed-off-by: Jan Kara --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 65c2be22b601..61da2f1c8056 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2058,6 +2058,7 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); +extern int sb_is_blkdev_sb(struct super_block *sb); #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } @@ -2077,6 +2078,11 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } + +static inline int sb_is_blkdev_sb(struct super_block *sb) +{ + return 0; +} #endif extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; -- cgit v1.2.3 From cf870c70a194443f8fc654ddc9d6cfd02c58003b Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Wed, 10 Jul 2013 14:57:01 +0530 Subject: mce: acpi/apei: Soft-offline a page on firmware GHES notification If the firmware indicates in GHES error data entry that the error threshold has exceeded for a corrected error event, then we try to soft-offline the page. This could be called in interrupt context, so we queue this up similar to how we handle memory failure scenarios. Signed-off-by: Naveen N. Rao Acked-by: Borislav Petkov Signed-off-by: Tony Luck --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e0c8528a41a4..958e9efd02a7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1784,6 +1784,7 @@ enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, + MF_SOFT_OFFLINE = 1 << 3, }; extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); -- cgit v1.2.3 From a51805efae5dda0da66f79268ffcf0715f9dbea4 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jul 2013 14:23:49 -0700 Subject: lockdep: Introduce lock_acquire_exclusive()/shared() helper macros In lockdep.h, the spinlock/mutex/rwsem/rwlock/lock_map acquire macros have different definitions based on the value of CONFIG_PROVE_LOCKING. We have separate ifdefs for each of these definitions, which seems redundant. Introduce lock_acquire_{exclusive,shared,shared_recursive} helpers which will have different definitions based on CONFIG_PROVE_LOCKING. Then all other helper macros can be defined based on the above ones, which reduces the amount of ifdefined code. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Lai Jiangshan Cc: "Srivatsa S. Bhat" Cc: Rusty Russell Cc: Andi Kleen Cc: "Paul E. McKenney" Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20130708212350.6DD1931C15E@corp2gmr1-1.hot.corp.google.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 92 +++++++++++++------------------------------------ 1 file changed, 23 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f1e877b79ed8..cfc2f119779a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -365,7 +365,7 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) -#else /* !LOCKDEP */ +#else /* !CONFIG_LOCKDEP */ static inline void lockdep_off(void) { @@ -479,82 +479,36 @@ static inline void print_irqtrace_events(struct task_struct *curr) * on the per lock-class debug mode: */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# endif -# define spin_release(l, n, i) lock_release(l, n, i) +#ifdef CONFIG_PROVE_LOCKING + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 2, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 2, n, i) #else -# define spin_acquire(l, s, t, i) do { } while (0) -# define spin_release(l, n, i) do { } while (0) + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, NULL, i) -# else -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, NULL, i) -# endif -# define rwlock_release(l, n, i) lock_release(l, n, i) -#else -# define rwlock_acquire(l, s, t, i) do { } while (0) -# define rwlock_acquire_read(l, s, t, i) do { } while (0) -# define rwlock_release(l, n, i) do { } while (0) -#endif +#define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define spin_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# endif -# define mutex_release(l, n, i) lock_release(l, n, i) -#else -# define mutex_acquire(l, s, t, i) do { } while (0) -# define mutex_acquire_nest(l, s, t, n, i) do { } while (0) -# define mutex_release(l, n, i) do { } while (0) -#endif +#define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) +#define rwlock_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, NULL, i) -# else -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, NULL, i) -# endif +#define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define mutex_release(l, n, i) lock_release(l, n, i) + +#define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) # define rwsem_release(l, n, i) lock_release(l, n, i) -#else -# define rwsem_acquire(l, s, t, i) do { } while (0) -# define rwsem_acquire_nest(l, s, t, n, i) do { } while (0) -# define rwsem_acquire_read(l, s, t, i) do { } while (0) -# define rwsem_release(l, n, i) do { } while (0) -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 2, NULL, _THIS_IP_) -# else -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 1, NULL, _THIS_IP_) -# endif +#define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) # define lock_map_release(l) lock_release(l, 1, _THIS_IP_) -#else -# define lock_map_acquire(l) do { } while (0) -# define lock_map_acquire_read(l) do { } while (0) -# define lock_map_release(l) do { } while (0) -#endif #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ -- cgit v1.2.3 From 728ce22b696f9f1404a74d7b2279a65933553a1b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:51 +0200 Subject: cpuidle: Make cpuidle's sysfs directory dynamically allocated The cpuidle sysfs code is designed to have a single instance of per CPU cpuidle directory. It is not possible to remove the sysfs entry and create it again. This is not a problem with the current code but future changes will add CPU hotplug support to enable/disable the device, so it will need to remove the sysfs entry like other subsystems do. That won't be possible without this change, because the kobj is a static object which can't be reused for kobj_init_and_add(). Add cpuidle_device_kobj to be allocated dynamically when adding/removing a sysfs entry which is consistent with the other cpuidle's sysfs entries. An added benefit is that the sysfs code is now more self-contained and the includes needed for sysfs can be moved from cpuidle.h directly into sysfs.c so as to reduce the total number of headers dragged along with cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 0bc4b74668e9..b922db53b7ab 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -13,8 +13,6 @@ #include #include -#include -#include #include #define CPUIDLE_STATE_MAX 10 @@ -61,6 +59,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) +struct cpuidle_device_kobj; + struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; @@ -71,9 +71,8 @@ struct cpuidle_device { struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; + struct cpuidle_device_kobj *kobj_dev; struct list_head device_list; - struct kobject kobj; - struct completion kobj_unregister; #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED int safe_state_index; -- cgit v1.2.3 From 1a7064380e6639e1cc5ed609ceb1ed46f3f188e3 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:52 +0200 Subject: cpuidle: Add missing forward declarations of structures Add missing forward declarations of struct cpuidle_state_kobj and struct cpuidle_driver_kobj in cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b922db53b7ab..781addc66f03 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -60,6 +60,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) struct cpuidle_device_kobj; +struct cpuidle_state_kobj; +struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; -- cgit v1.2.3 From 6e8b8726ad503214ba66e34aed69aff41de33489 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 15 Jul 2013 11:19:32 +0930 Subject: PTR_RET is now PTR_ERR_OR_ZERO True, it's often used in return statements, but after much bikeshedding it's probably better to have an explicit name. (I tried just putting the IS_ERR check inside PTR_ERR itself and gcc usually generated no more code. But that clashes current expectations of how PTR_ERR behaves, so having a separate function is better). Suggested-by: Julia Lawall Suggested-by: "Michael S. Tsirkin" Cc: Julia Lawall Cc: "Michael S. Tsirkin" Signed-off-by: Rusty Russell --- include/linux/err.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/err.h b/include/linux/err.h index 221fcfb676c4..15f92e072450 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -52,7 +52,7 @@ static inline void * __must_check ERR_CAST(__force const void *ptr) return (void *) ptr; } -static inline int __must_check PTR_RET(__force const void *ptr) +static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); @@ -60,6 +60,9 @@ static inline int __must_check PTR_RET(__force const void *ptr) return 0; } +/* Deprecated */ +#define PTR_RET(p) PTR_ERR_OR_ZERO(p) + #endif #endif /* _LINUX_ERR_H */ -- cgit v1.2.3 From 326c29b6bedb7440b4232631686027af84a62cf5 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 4 Jul 2013 08:56:27 +0100 Subject: mfd: arizona: Add GPIO control register bit definitions Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/mfd/arizona/gpio.h | 96 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 include/linux/mfd/arizona/gpio.h (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/gpio.h b/include/linux/mfd/arizona/gpio.h new file mode 100644 index 000000000000..d2146bb74f89 --- /dev/null +++ b/include/linux/mfd/arizona/gpio.h @@ -0,0 +1,96 @@ +/* + * GPIO configuration for Arizona devices + * + * Copyright 2013 Wolfson Microelectronics. PLC. + * + * Author: Charles Keepax + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARIZONA_GPIO_H +#define _ARIZONA_GPIO_H + +#define ARIZONA_GP_FN_TXLRCLK 0x00 +#define ARIZONA_GP_FN_GPIO 0x01 +#define ARIZONA_GP_FN_IRQ1 0x02 +#define ARIZONA_GP_FN_IRQ2 0x03 +#define ARIZONA_GP_FN_OPCLK 0x04 +#define ARIZONA_GP_FN_FLL1_OUT 0x05 +#define ARIZONA_GP_FN_FLL2_OUT 0x06 +#define ARIZONA_GP_FN_PWM1 0x08 +#define ARIZONA_GP_FN_PWM2 0x09 +#define ARIZONA_GP_FN_SYSCLK_UNDERCLOCKED 0x0A +#define ARIZONA_GP_FN_ASYNCCLK_UNDERCLOCKED 0x0B +#define ARIZONA_GP_FN_FLL1_LOCK 0x0C +#define ARIZONA_GP_FN_FLL2_LOCK 0x0D +#define ARIZONA_GP_FN_FLL1_CLOCK_OK 0x0F +#define ARIZONA_GP_FN_FLL2_CLOCK_OK 0x10 +#define ARIZONA_GP_FN_HEADPHONE_DET 0x12 +#define ARIZONA_GP_FN_MIC_DET 0x13 +#define ARIZONA_GP_FN_WSEQ_STATUS 0x15 +#define ARIZONA_GP_FN_CIF_ADDRESS_ERROR 0x16 +#define ARIZONA_GP_FN_ASRC1_LOCK 0x1A +#define ARIZONA_GP_FN_ASRC2_LOCK 0x1B +#define ARIZONA_GP_FN_ASRC_CONFIG_ERROR 0x1C +#define ARIZONA_GP_FN_DRC1_SIGNAL_DETECT 0x1D +#define ARIZONA_GP_FN_DRC1_ANTICLIP 0x1E +#define ARIZONA_GP_FN_DRC1_DECAY 0x1F +#define ARIZONA_GP_FN_DRC1_NOISE 0x20 +#define ARIZONA_GP_FN_DRC1_QUICK_RELEASE 0x21 +#define ARIZONA_GP_FN_DRC2_SIGNAL_DETECT 0x22 +#define ARIZONA_GP_FN_DRC2_ANTICLIP 0x23 +#define ARIZONA_GP_FN_DRC2_DECAY 0x24 +#define ARIZONA_GP_FN_DRC2_NOISE 0x25 +#define ARIZONA_GP_FN_DRC2_QUICK_RELEASE 0x26 +#define ARIZONA_GP_FN_MIXER_DROPPED_SAMPLE 0x27 +#define ARIZONA_GP_FN_AIF1_CONFIG_ERROR 0x28 +#define ARIZONA_GP_FN_AIF2_CONFIG_ERROR 0x29 +#define ARIZONA_GP_FN_AIF3_CONFIG_ERROR 0x2A +#define ARIZONA_GP_FN_SPK_TEMP_SHUTDOWN 0x2B +#define ARIZONA_GP_FN_SPK_TEMP_WARNING 0x2C +#define ARIZONA_GP_FN_UNDERCLOCKED 0x2D +#define ARIZONA_GP_FN_OVERCLOCKED 0x2E +#define ARIZONA_GP_FN_DSP_IRQ1 0x35 +#define ARIZONA_GP_FN_DSP_IRQ2 0x36 +#define ARIZONA_GP_FN_ASYNC_OPCLK 0x3D +#define ARIZONA_GP_FN_BOOT_DONE 0x44 +#define ARIZONA_GP_FN_DSP1_RAM_READY 0x45 +#define ARIZONA_GP_FN_SYSCLK_ENA_STATUS 0x4B +#define ARIZONA_GP_FN_ASYNCCLK_ENA_STATUS 0x4C + +#define ARIZONA_GPN_DIR 0x8000 /* GPN_DIR */ +#define ARIZONA_GPN_DIR_MASK 0x8000 /* GPN_DIR */ +#define ARIZONA_GPN_DIR_SHIFT 15 /* GPN_DIR */ +#define ARIZONA_GPN_DIR_WIDTH 1 /* GPN_DIR */ +#define ARIZONA_GPN_PU 0x4000 /* GPN_PU */ +#define ARIZONA_GPN_PU_MASK 0x4000 /* GPN_PU */ +#define ARIZONA_GPN_PU_SHIFT 14 /* GPN_PU */ +#define ARIZONA_GPN_PU_WIDTH 1 /* GPN_PU */ +#define ARIZONA_GPN_PD 0x2000 /* GPN_PD */ +#define ARIZONA_GPN_PD_MASK 0x2000 /* GPN_PD */ +#define ARIZONA_GPN_PD_SHIFT 13 /* GPN_PD */ +#define ARIZONA_GPN_PD_WIDTH 1 /* GPN_PD */ +#define ARIZONA_GPN_LVL 0x0800 /* GPN_LVL */ +#define ARIZONA_GPN_LVL_MASK 0x0800 /* GPN_LVL */ +#define ARIZONA_GPN_LVL_SHIFT 11 /* GPN_LVL */ +#define ARIZONA_GPN_LVL_WIDTH 1 /* GPN_LVL */ +#define ARIZONA_GPN_POL 0x0400 /* GPN_POL */ +#define ARIZONA_GPN_POL_MASK 0x0400 /* GPN_POL */ +#define ARIZONA_GPN_POL_SHIFT 10 /* GPN_POL */ +#define ARIZONA_GPN_POL_WIDTH 1 /* GPN_POL */ +#define ARIZONA_GPN_OP_CFG 0x0200 /* GPN_OP_CFG */ +#define ARIZONA_GPN_OP_CFG_MASK 0x0200 /* GPN_OP_CFG */ +#define ARIZONA_GPN_OP_CFG_SHIFT 9 /* GPN_OP_CFG */ +#define ARIZONA_GPN_OP_CFG_WIDTH 1 /* GPN_OP_CFG */ +#define ARIZONA_GPN_DB 0x0100 /* GPN_DB */ +#define ARIZONA_GPN_DB_MASK 0x0100 /* GPN_DB */ +#define ARIZONA_GPN_DB_SHIFT 8 /* GPN_DB */ +#define ARIZONA_GPN_DB_WIDTH 1 /* GPN_DB */ +#define ARIZONA_GPN_FN_MASK 0x007F /* GPN_DB */ +#define ARIZONA_GPN_FN_SHIFT 0 /* GPN_DB */ +#define ARIZONA_GPN_FN_WIDTH 7 /* GPN_DB */ + +#endif -- cgit v1.2.3 From 10175b3b2fdd287515db4c103d96b323bb4cd690 Mon Sep 17 00:00:00 2001 From: Bo Shen Date: Wed, 3 Jul 2013 16:37:59 +0800 Subject: ARM: atmel-ssc: change phybase type to dma_addr_t as the phybase paramter only used for DMA operation, change it's type from resource_size_t to dma_addr_t Signed-off-by: Bo Shen Reviewed-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- include/linux/atmel-ssc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h index deb0ae58b99b..66a0e5384edd 100644 --- a/include/linux/atmel-ssc.h +++ b/include/linux/atmel-ssc.h @@ -11,7 +11,7 @@ struct atmel_ssc_platform_data { struct ssc_device { struct list_head list; - resource_size_t phybase; + dma_addr_t phybase; void __iomem *regs; struct platform_device *pdev; struct atmel_ssc_platform_data *pdata; -- cgit v1.2.3 From dc9ceed6a12aff627c81e01ada191e8a23fcbe3e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 4 Jul 2013 17:27:14 +0100 Subject: regulator: core: Make set_voltage_tol() try for mid-range first The expected semantic for something expressed as a tolerance is that it should deliver the specified value with some deviation allowed but this is not what set_voltage_tol() currently does. Instead it just passes the maximum possible range to set_voltage() which will typically result in a voltage aimed at lower than the target voltage. Instead first try to set a voltage between the target voltage and the upper limit, then fall back on the full range. This will be much more robust against physical variation in systems and makes the API behave more like users would expect. Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..3610df8dd229 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -369,8 +369,11 @@ static inline int regulator_count_voltages(struct regulator *regulator) static inline int regulator_set_voltage_tol(struct regulator *regulator, int new_uV, int tol_uV) { - return regulator_set_voltage(regulator, - new_uV - tol_uV, new_uV + tol_uV); + if (regulator_set_voltage(regulator, new_uV, new_uV + tol_uV) == 0) + return 0; + else + return regulator_set_voltage(regulator, + new_uV - tol_uV, new_uV + tol_uV); } static inline int regulator_is_supported_voltage_tol(struct regulator *regulator, -- cgit v1.2.3 From 94d33c02c7186b69849c292e1216a08ad1c0d99d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 2 Jul 2013 22:52:41 +0100 Subject: regulator: core: Add helpers for multiple linear ranges Many regulators have several linear ranges of selector with different step sizes, for example offering better resolution at lower voltages. Provide regulator_{map,list}_voltage_linear_range() allowing these regulators to use generic code. To do so a table of regulator_linear_range structs needs to be pointed to from the descriptor. This was inspired by similar code included in a driver submission from Chao Xie and Yi Zhang at Marvell. Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6700cc94bdd1..67e13aa5a478 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -39,6 +39,24 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; +/** + * Specify a range of voltages for regulator_map_linar_range() and + * regulator_list_linear_range(). + * + * @min_uV: Lowest voltage in range + * @max_uV: Highest voltage in range + * @min_sel: Lowest selector for range + * @max_sel: Highest selector for range + * @uV_step: Step size + */ +struct regulator_linear_range { + unsigned int min_uV; + unsigned int max_uV; + unsigned int min_sel; + unsigned int max_sel; + unsigned int uV_step; +}; + /** * struct regulator_ops - regulator operations. * @@ -223,6 +241,9 @@ struct regulator_desc { unsigned int linear_min_sel; unsigned int ramp_delay; + const struct regulator_linear_range *linear_ranges; + int n_linear_ranges; + const unsigned int *volt_table; unsigned int vsel_reg; @@ -326,10 +347,14 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_linear_range(struct regulator_dev *rdev, + unsigned int selector); int regulator_list_voltage_table(struct regulator_dev *rdev, unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_ascend(struct regulator_dev *rdev, -- cgit v1.2.3 From 1653ccf4c52df6a4abe8ec2f33f2cb2896d129ea Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:15 +0530 Subject: regulator: core: Add support for disabling ramp delay Some hardwares support disabling ramp delay, so adding ramp_disable flag to constraints. It will be used to figure out whether ramp_delay in constraints is explicitly set to zero or its unintialized (zero by default). And we don't need to call set_voltage_time_sel() for regulators for whom ramp delay is disabled in constraints. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 36adbc82de6a..999b20ce06cf 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -134,6 +134,7 @@ struct regulation_constraints { unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ unsigned apply_uV:1; /* apply uV constraint if min == max */ + unsigned ramp_disable:1; /* disable ramp delay */ }; /** -- cgit v1.2.3 From 874b31585650afa6745de5133849365e7e6af418 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 11:44:49 +0100 Subject: spi/bitbang: Unexport spi_bitbang_transfer() Currently no drivers use the ability to override spi_bitbang_transfer() and if any started this would make it harder to convert the bitbang code to use transfer_one_message() so remove the export in order to prevent anyone starting. Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index f987a2bee16a..b5aa215493f6 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -41,7 +41,6 @@ struct spi_bitbang { */ extern int spi_bitbang_setup(struct spi_device *spi); extern void spi_bitbang_cleanup(struct spi_device *spi); -extern int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m); extern int spi_bitbang_setup_transfer(struct spi_device *spi, struct spi_transfer *t); -- cgit v1.2.3 From a2fd4f9fa3b9f051550b36c4dfa74bc32bda24ee Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 10 Jul 2013 14:57:26 +0100 Subject: spi: Support transfer speed checking in the core Allow drivers to avoid implementing their own checks for simple rates by specifying the limits in the master structure. Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..cdf668156154 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -233,6 +233,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * suported. If set, the SPI core will reject any transfer with an * unsupported bits_per_word. If not set, this value is simply ignored, * and it's up to the individual driver to perform any validation. + * @min_speed_hz: Lowest supported transfer speed + * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for SPI bus locking @@ -312,6 +314,10 @@ struct spi_master { #define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) + /* limits on transfer speed */ + u32 min_speed_hz; + u32 max_speed_hz; + /* other constraints relevant to this driver */ u16 flags; #define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -- cgit v1.2.3 From 221a27c76033a3a4196b3da09848bc5f237f3f94 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 8 Jul 2013 14:15:25 +0530 Subject: dmaengine: add dma_slave_get_caps api add new device callback .device_slave_caps api which can be used by clients to query the dma channel capablties before they program the channel. This can help is removing errors during the channel programming. Also add helper dma_slave_get_caps API This patch folds the work done by Matt earlier https://patchwork.kernel.org/patch/2094891/ Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cb286b1acdb6..5692bc3afd39 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -370,6 +370,33 @@ struct dma_slave_config { unsigned int slave_id; }; +/* struct dma_slave_caps - expose capabilities of a slave channel only + * + * @src_addr_widths: bit mask of src addr widths the channel supports + * @dstn_addr_widths: bit mask of dstn addr widths the channel supports + * @directions: bit mask of slave direction the channel supported + * since the enum dma_transfer_direction is not defined as bits for each + * type of direction, the dma controller should fill (1 << ) and same + * should be checked by controller as well + * @cmd_pause: true, if pause and thereby resume is supported + * @cmd_terminate: true, if terminate cmd is supported + * + * @max_sg_nr: maximum number of SG segments supported + * 0 for no maximum + * @max_sg_len: maximum length of a SG segment supported + * 0 for no maximum + */ +struct dma_slave_caps { + u32 src_addr_widths; + u32 dstn_addr_widths; + u32 directions; + bool cmd_pause; + bool cmd_terminate; + + u32 max_sg_nr; + u32 max_sg_len; +}; + static inline const char *dma_chan_name(struct dma_chan *chan) { return dev_name(&chan->dev->device); @@ -532,6 +559,7 @@ struct dma_tx_state { * struct with auxiliary transfer status information, otherwise the call * will just return a simple status code * @device_issue_pending: push pending transactions to hardware + * @device_slave_caps: return the slave channel capabilities */ struct dma_device { @@ -597,6 +625,7 @@ struct dma_device { dma_cookie_t cookie, struct dma_tx_state *txstate); void (*device_issue_pending)(struct dma_chan *chan); + int (*device_slave_caps)(struct dma_chan *chan, struct dma_slave_caps *caps); }; static inline int dmaengine_device_control(struct dma_chan *chan, @@ -670,6 +699,21 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps) +{ + if (!chan || !caps) + return -EINVAL; + + /* check if the channel supports slave transactions */ + if (!test_bit(DMA_SLAVE, chan->device->cap_mask.bits)) + return -ENXIO; + + if (chan->device->device_slave_caps) + return chan->device->device_slave_caps(chan, caps); + + return -ENXIO; +} + static inline int dmaengine_terminate_all(struct dma_chan *chan) { return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0); -- cgit v1.2.3 From 939c02777a27ea7915764ecca5263dbb60c664f3 Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:16 +0530 Subject: regulator: s2mps11: Implement set_ramp_rate callback for bucks Implementing set_ramp_rate() and using standard constraints for getting ramp_delay and ramp_disable, instead of getting it as s2mps11 specific data through platform data, makes driver more compliant with framework and reduces the complexity for adding DT support. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- include/linux/mfd/samsung/s2mps11.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 4e94dc65f987..d0d52ea60074 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -191,6 +191,17 @@ enum s2mps11_regulators { #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1) #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ + +#define S2MPS11_BUCK2_RAMP_SHIFT 6 +#define S2MPS11_BUCK34_RAMP_SHIFT 4 +#define S2MPS11_BUCK5_RAMP_SHIFT 6 +#define S2MPS11_BUCK16_RAMP_SHIFT 4 +#define S2MPS11_BUCK7810_RAMP_SHIFT 2 +#define S2MPS11_BUCK9_RAMP_SHIFT 0 +#define S2MPS11_BUCK2_RAMP_EN_SHIFT 3 +#define S2MPS11_BUCK3_RAMP_EN_SHIFT 2 +#define S2MPS11_BUCK4_RAMP_EN_SHIFT 1 +#define S2MPS11_BUCK6_RAMP_EN_SHIFT 0 #define S2MPS11_PMIC_EN_SHIFT 6 #define S2MPS11_REGULATOR_MAX (S2MPS11_REG_MAX - 3) -- cgit v1.2.3 From 8b770e3c9824c98eafe67950ad6e41e09ec9c98a Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 4 Jul 2013 21:13:24 +0200 Subject: backlight: Add GPIO-based backlight driver The GPIO backlight driver controls the backlight in on/off mode through a single GPIO. Signed-off-by: Laurent Pinchart Acked-by: Jingoo Han Signed-off-by: Simon Horman --- include/linux/platform_data/gpio_backlight.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/platform_data/gpio_backlight.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio_backlight.h b/include/linux/platform_data/gpio_backlight.h new file mode 100644 index 000000000000..5ae0d9c80d4d --- /dev/null +++ b/include/linux/platform_data/gpio_backlight.h @@ -0,0 +1,21 @@ +/* + * gpio_backlight.h - Simple GPIO-controlled backlight + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __GPIO_BACKLIGHT_H__ +#define __GPIO_BACKLIGHT_H__ + +struct device; + +struct gpio_backlight_platform_data { + struct device *fbdev; + int gpio; + int def_value; + bool active_low; + const char *name; +}; + +#endif -- cgit v1.2.3 From 82e5c40d88f928afffe7bd4027719d3184433908 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 4 Jul 2013 21:13:25 +0200 Subject: backlight: Add Sanyo LV5207LP backlight driver The LV5207LP is a multi-purpose 7 LEDs driver for the mobile market. Only the main LED is supported by this driver. Signed-off-by: Laurent Pinchart Acked-by: Jingoo Han Signed-off-by: Simon Horman --- include/linux/platform_data/lv5207lp.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/platform_data/lv5207lp.h (limited to 'include/linux') diff --git a/include/linux/platform_data/lv5207lp.h b/include/linux/platform_data/lv5207lp.h new file mode 100644 index 000000000000..7dc4d9a219a6 --- /dev/null +++ b/include/linux/platform_data/lv5207lp.h @@ -0,0 +1,19 @@ +/* + * lv5207lp.h - Sanyo LV5207LP LEDs Driver + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __LV5207LP_H__ +#define __LV5207LP_H__ + +struct device; + +struct lv5207lp_platform_data { + struct device *fbdev; + unsigned int max_value; + unsigned int def_value; +}; + +#endif -- cgit v1.2.3 From 67b43e590415866649e5ba8a6421bb84ecb74f72 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 4 Jul 2013 21:13:26 +0200 Subject: backlight: Add ROHM BD6107 backlight driver The BD6107 is a multi-purpose 10 channels LED driver for the mobile market. Only the main channel is supported by this driver. Signed-off-by: Laurent Pinchart Acked-by: Jingoo Han Signed-off-by: Simon Horman --- include/linux/platform_data/bd6107.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/platform_data/bd6107.h (limited to 'include/linux') diff --git a/include/linux/platform_data/bd6107.h b/include/linux/platform_data/bd6107.h new file mode 100644 index 000000000000..671d6502d241 --- /dev/null +++ b/include/linux/platform_data/bd6107.h @@ -0,0 +1,19 @@ +/* + * bd6107.h - Rohm BD6107 LEDs Driver + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __BD6107_H__ +#define __BD6107_H__ + +struct device; + +struct bd6107_platform_data { + struct device *fbdev; + int reset; /* Reset GPIO */ + unsigned int def_value; +}; + +#endif -- cgit v1.2.3 From dc34e7e1a701134c2639dc7af78dc91055616477 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Mon, 1 Jul 2013 00:01:32 +0400 Subject: libata: move 'struct ata_taskfile' and friends from ata.h to libata.h Move 'struct ata_taskfile', ata_prot_flags() and their friends from to . They were misplaced from the beginning, as should cover ATA/ATAPI and related standards only -- to which the aforementioned structure and function have only remote relation. I would have moved 'enum ata_tf_protocols' closely related to 'struct ata_taskfile' but it unfortunately gets used by 'drivers/ide/ide-ioctls.c'... Signed-off-by: Sergei Shtylyov Signed-off-by: Tejun Heo --- include/linux/ata.h | 102 ------------------------------------------------- include/linux/libata.h | 102 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ee0bd9524055..f63fb1afc5cc 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -446,22 +446,6 @@ enum { SERR_TRANS_ST_ERROR = (1 << 24), /* Transport state trans. error */ SERR_UNRECOG_FIS = (1 << 25), /* Unrecognized FIS */ SERR_DEV_XCHG = (1 << 26), /* device exchanged */ - - /* struct ata_taskfile flags */ - ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ - ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ - ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ - ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ - ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ - ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ - ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ - - /* protocol flags */ - ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ - ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ - ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, - ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ - ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ }; enum ata_tf_protocols { @@ -488,83 +472,6 @@ struct ata_bmdma_prd { __le32 flags_len; }; -struct ata_taskfile { - unsigned long flags; /* ATA_TFLAG_xxx */ - u8 protocol; /* ATA_PROT_xxx */ - - u8 ctl; /* control reg */ - - u8 hob_feature; /* additional data */ - u8 hob_nsect; /* to support LBA48 */ - u8 hob_lbal; - u8 hob_lbam; - u8 hob_lbah; - - u8 feature; - u8 nsect; - u8 lbal; - u8 lbam; - u8 lbah; - - u8 device; - - u8 command; /* IO operation */ -}; - -/* - * protocol tests - */ -static inline unsigned int ata_prot_flags(u8 prot) -{ - switch (prot) { - case ATA_PROT_NODATA: - return 0; - case ATA_PROT_PIO: - return ATA_PROT_FLAG_PIO; - case ATA_PROT_DMA: - return ATA_PROT_FLAG_DMA; - case ATA_PROT_NCQ: - return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; - case ATAPI_PROT_NODATA: - return ATA_PROT_FLAG_ATAPI; - case ATAPI_PROT_PIO: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; - case ATAPI_PROT_DMA: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; - } - return 0; -} - -static inline int ata_is_atapi(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; -} - -static inline int ata_is_nodata(u8 prot) -{ - return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); -} - -static inline int ata_is_pio(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; -} - -static inline int ata_is_dma(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; -} - -static inline int ata_is_ncq(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; -} - -static inline int ata_is_data(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; -} - /* * id tests */ @@ -1060,15 +967,6 @@ static inline unsigned ata_set_lba_range_entries(void *_buffer, return used_bytes; } -static inline int is_multi_taskfile(struct ata_taskfile *tf) -{ - return (tf->command == ATA_CMD_READ_MULTI) || - (tf->command == ATA_CMD_WRITE_MULTI) || - (tf->command == ATA_CMD_READ_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) diff --git a/include/linux/libata.h b/include/linux/libata.h index 4ea55bb45deb..283d66bc603c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -138,6 +138,22 @@ enum { ATA_SHT_THIS_ID = -1, ATA_SHT_USE_CLUSTERING = 1, + /* struct ata_taskfile flags */ + ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ + ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ + ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ + ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ + ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ + ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ + ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ + + /* protocol flags */ + ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ + ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ + ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, + ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ + ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ + /* struct ata_device stuff */ ATA_DFLAG_LBA = (1 << 0), /* device supports LBA */ ATA_DFLAG_LBA48 = (1 << 1), /* device supports LBA48 */ @@ -518,6 +534,29 @@ enum sw_activity { BLINK_OFF, }; +struct ata_taskfile { + unsigned long flags; /* ATA_TFLAG_xxx */ + u8 protocol; /* ATA_PROT_xxx */ + + u8 ctl; /* control reg */ + + u8 hob_feature; /* additional data */ + u8 hob_nsect; /* to support LBA48 */ + u8 hob_lbal; + u8 hob_lbam; + u8 hob_lbah; + + u8 feature; + u8 nsect; + u8 lbal; + u8 lbam; + u8 lbah; + + u8 device; + + u8 command; /* IO operation */ +}; + #ifdef CONFIG_ATA_SFF struct ata_ioports { void __iomem *cmd_addr; @@ -959,6 +998,69 @@ extern const unsigned long sata_deb_timing_long[]; extern struct ata_port_operations ata_dummy_port_ops; extern const struct ata_port_info ata_dummy_port_info; +/* + * protocol tests + */ +static inline unsigned int ata_prot_flags(u8 prot) +{ + switch (prot) { + case ATA_PROT_NODATA: + return 0; + case ATA_PROT_PIO: + return ATA_PROT_FLAG_PIO; + case ATA_PROT_DMA: + return ATA_PROT_FLAG_DMA; + case ATA_PROT_NCQ: + return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; + case ATAPI_PROT_NODATA: + return ATA_PROT_FLAG_ATAPI; + case ATAPI_PROT_PIO: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; + case ATAPI_PROT_DMA: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; + } + return 0; +} + +static inline int ata_is_atapi(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; +} + +static inline int ata_is_nodata(u8 prot) +{ + return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); +} + +static inline int ata_is_pio(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; +} + +static inline int ata_is_dma(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; +} + +static inline int ata_is_ncq(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; +} + +static inline int ata_is_data(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; +} + +static inline int is_multi_taskfile(struct ata_taskfile *tf) +{ + return (tf->command == ATA_CMD_READ_MULTI) || + (tf->command == ATA_CMD_WRITE_MULTI) || + (tf->command == ATA_CMD_READ_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); +} + static inline const unsigned long * sata_ehc_deb_timing(struct ata_eh_context *ehc) { -- cgit v1.2.3 From 55708698c5f153f4e390175cdfc395333b2eafbd Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Tue, 16 Jul 2013 17:56:12 +0800 Subject: fs/anon_inode: Introduce a new lib function anon_inode_getfile_private() Introduce a new lib function anon_inode_getfile_private(), it creates a new file instance by hooking it up to an anonymous inode, and a dentry that describe the "class" of the file, similar to anon_inode_getfile(), but each file holds a single inode. Furthermore, anyone who wants to create a private anon file will benefit from this change. Signed-off-by: Gu Zheng Signed-off-by: Benjamin LaHaise --- include/linux/anon_inodes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 8013a45242fe..cf573c22b81e 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -13,6 +13,9 @@ struct file_operations; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_private(const char *name, + const struct file_operations *fops, + void *priv, int flags); int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags); -- cgit v1.2.3 From 36bc08cc01709b4a9bb563b35aa530241ddc63e3 Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Tue, 16 Jul 2013 17:56:16 +0800 Subject: fs/aio: Add support to aio ring pages migration As the aio job will pin the ring pages, that will lead to mem migrated failed. In order to fix this problem we use an anon inode to manage the aio ring pages, and setup the migratepage callback in the anon inode's address space, so that when mem migrating the aio ring pages will be moved to other mem node safely. Signed-off-by: Gu Zheng Signed-off-by: Benjamin LaHaise --- include/linux/migrate.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index a405d3dc0f61..c407d88f5979 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -55,6 +55,9 @@ extern int migrate_vmas(struct mm_struct *mm, extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); +extern int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page, + struct buffer_head *head, enum migrate_mode mode); #else static inline void putback_lru_pages(struct list_head *l) {} -- cgit v1.2.3 From 2025172e32808a327b00f968c72baa79adc594c2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 20:07:27 +0100 Subject: spi/bitbang: Use core message pump Convert drivers using bitbang to use the core mesasge pump infrastructure, saving some code and meaning that these drivers get to take advantage of work done on improving the core implementation. Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b5aa215493f6..daebaba886aa 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -4,11 +4,7 @@ #include struct spi_bitbang { - struct workqueue_struct *workqueue; - struct work_struct work; - spinlock_t lock; - struct list_head queue; u8 busy; u8 use_dma; u8 flags; /* extra spi->mode support */ -- cgit v1.2.3 From 126a5af520eff9b99a0bb1ca4bb4a0b7973f7d5a Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 3 Jul 2013 16:30:53 +0200 Subject: KVM: kvm-io: support cookies Add new functions kvm_io_bus_{read,write}_cookie() that allows users of the kvm io infrastructure to use a cookie value to speed up lookup of a device on an io bus. Signed-off-by: Cornelia Huck Signed-off-by: Paolo Bonzini Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a63d83ebd151..ec590aece366 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -160,8 +160,12 @@ enum kvm_bus { int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); +int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, const void *val, long cookie); int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); +int kvm_io_bus_read_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, void *val, long cookie); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, -- cgit v1.2.3 From e59dbe09f8e6fb8f6ee19dc79d1a2f14299e4cd2 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 4 Jul 2013 13:40:29 +0900 Subject: KVM: Introduce kvm_arch_memslots_updated() This is called right after the memslots is updated, i.e. when the result of update_memslots() gets installed in install_new_memslots(). Since the memslots needs to be updated twice when we delete or move a memslot, kvm_arch_commit_memory_region() does not correspond to this exactly. In the following patch, x86 will use this new API to check if the mmio generation has reached its maximum value, in which case mmio sptes need to be flushed out. Signed-off-by: Takuya Yoshikawa Acked-by: Alexander Graf Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ec590aece366..c11c7686ae5f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); +void kvm_arch_memslots_updated(struct kvm *kvm); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, -- cgit v1.2.3 From e04c5d76b0cfb66cadd900cf147526f2271884b8 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 10 Jul 2013 22:21:57 -0300 Subject: remove sched notifier for cross-cpu migrations Linux as a guest on KVM hypervisor, the only user of the pvclock vsyscall interface, does not require notification on task migration because: 1. cpu ID number maps 1:1 to per-CPU pvclock time info. 2. per-CPU pvclock time info is updated if the underlying CPU changes. 3. that version is increased whenever underlying CPU changes. Which is sufficient to guarantee nanoseconds counter is calculated properly. Signed-off-by: Marcelo Tosatti Acked-by: Peter Zijlstra Signed-off-by: Gleb Natapov --- include/linux/sched.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..bfc809d51745 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -107,14 +107,6 @@ extern unsigned long this_cpu_load(void); extern void calc_global_load(unsigned long ticks); extern void update_cpu_load_nohz(void); -/* Notifier for when a task gets migrated to a new CPU */ -struct task_migration_notifier { - struct task_struct *task; - int from_cpu; - int to_cpu; -}; -extern void register_task_migration_notifier(struct notifier_block *n); - extern unsigned long get_parent_ip(unsigned long addr); extern void dump_cpu_task(int cpu); -- cgit v1.2.3 From 078726ce6d56a767533064e0f2f2100d7cb6fc22 Mon Sep 17 00:00:00 2001 From: Sourav Poddar Date: Thu, 18 Jul 2013 15:31:25 +0530 Subject: driver: spi: Modify core to compute the message length Make spi core calculate the message length while populating the other transfer parameters. Usecase, driver can use it to populate framelength filed in their controller. Signed-off-by: Sourav Poddar Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..aadd0a885a0f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -578,6 +578,7 @@ struct spi_message { /* completion is reported through a callback */ void (*complete)(void *context); void *context; + unsigned frame_length; unsigned actual_length; int status; -- cgit v1.2.3 From 640efa08cb635ae43d5ceae302b20c2c3f2035e5 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 3 Jul 2013 13:14:32 +0900 Subject: gpio: em: Add pinctrl support Register the GPIO pin range, and request and free GPIO pins using the pinctrl API. The pctl_name platform data member should be used by platform devices to point out which pinctrl device to use. Follows same style as "dc3465a gpio-rcar: Add pinctrl support", by Laurent Pinchart, thanks to him. Signed-off-by: Magnus Damm Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-em.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-em.h b/include/linux/platform_data/gpio-em.h index 573edfb046c4..7c5a519d2dcd 100644 --- a/include/linux/platform_data/gpio-em.h +++ b/include/linux/platform_data/gpio-em.h @@ -5,6 +5,7 @@ struct gpio_em_config { unsigned int gpio_base; unsigned int irq_base; unsigned int number_of_pins; + const char *pctl_name; }; #endif /* __GPIO_EM_H__ */ -- cgit v1.2.3 From ae3e4c277669e16093f0e71ca927cf33e7dde053 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 16 Jul 2013 12:32:08 +0200 Subject: leds: Remove leds-renesas-tpu driver The driver is superseded by the generic pwm-renesas-tpu driver used with leds-pwm. Signed-off-by: Laurent Pinchart Acked-by: Bryan Wu Signed-off-by: Simon Horman --- include/linux/platform_data/leds-renesas-tpu.h | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100644 include/linux/platform_data/leds-renesas-tpu.h (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-renesas-tpu.h b/include/linux/platform_data/leds-renesas-tpu.h deleted file mode 100644 index 055387086fc1..000000000000 --- a/include/linux/platform_data/leds-renesas-tpu.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __LEDS_RENESAS_TPU_H__ -#define __LEDS_RENESAS_TPU_H__ - -struct led_renesas_tpu_config { - char *name; - unsigned pin_gpio_fn; - unsigned pin_gpio; - unsigned int channel_offset; - unsigned int timer_bit; - unsigned int max_brightness; - unsigned int refresh_rate; -}; - -#endif /* __LEDS_RENESAS_TPU_H__ */ -- cgit v1.2.3 From 75b9222556ede41b9bd9d2d0dcb998f668b49b5f Mon Sep 17 00:00:00 2001 From: Nathaniel Yazdani Date: Wed, 3 Jul 2013 13:52:21 -0700 Subject: jbd: remove unneeded semicolon This patch removes an unnecessary semicolon that was placed after the closing bracket of an inline JBD wrapper function. Signed-off-by: Nathaniel Yazdani Signed-off-by: Jan Kara --- include/linux/jbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 8685d1be12c7..bc3e57d367fc 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -77,7 +77,7 @@ static inline void *jbd_alloc(size_t size, gfp_t flags) static inline void jbd_free(void *ptr, size_t size) { free_pages((unsigned long)ptr, get_order(size)); -}; +} #define JFS_MIN_JOURNAL_BLOCKS 1024 -- cgit v1.2.3 From 27ce405039bfe6d3f4143415c638f56a3df77dca Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 10 Jul 2013 19:56:27 +0200 Subject: HID: fix data access in implement() implement() is setting bytes in LE data stream. In case the data is not aligned to 64bits, it reads past the allocated buffer. It doesn't really change any value there (it's properly bitmasked), but in case that this read past the boundary hits a page boundary, pagefault happens when accessing 64bits of 'x' in implement(), and kernel oopses. This happens much more often when numbered reports are in use, as the initial 8bit skip in the buffer makes the whole process work on values which are not aligned to 64bits. This problem dates back to attempts in 2005 and 2006 to make implement() and extract() as generic as possible, and even back then the problem was realized by Adam Kroperlin, but falsely assumed to be impossible to cause any harm: http://www.mail-archive.com/linux-usb-devel@lists.sourceforge.net/msg47690.html I have made several attempts at fixing it "on the spot" directly in implement(), but the results were horrible; the special casing for processing last 64bit chunk and switching to different math makes it unreadable mess. I therefore took a path to allocate a few bytes more which will never make it into final report, but are there as a cushion for all the 64bit math operations happening in implement() and extract(). All callers of hid_output_report() are converted at the same time to allocate the buffer by newly introduced hid_alloc_report_buf() helper. Bruno noticed that the whole raw_size test can be dropped as well, as hid_alloc_report_buf() makes sure that the buffer is always of a proper size. Reviewed-by: Benjamin Tissoires Acked-by: Gustavo Padovan Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0c48991b0402..acccdf4eb485 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -744,6 +744,7 @@ struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); void hid_output_report(struct hid_report *report, __u8 *data); +u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); -- cgit v1.2.3 From bb4997a1afbff61084b243d62aaaf23ea38a290e Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 15 Jul 2013 13:15:04 +0200 Subject: bcma: add some more core names These cores were found on a BCM4708 (chipid 53010), this is a ARM SoC with two Cortex A9 cores. bcma: bus0: Found chip with id 0xCF12, rev 0x00 and package 0x02 bcma: bus0: Core 0 found: ChipCommon (manuf 0x4BF, id 0x800, rev 0x2A, class 0x0) bcma: bus0: Core 1 found: DMA (manuf 0x4BF, id 0x502, rev 0x01, class 0x0) bcma: bus0: Core 2 found: GBit MAC (manuf 0x4BF, id 0x82D, rev 0x04, class 0x0) bcma: bus0: Core 3 found: GBit MAC (manuf 0x4BF, id 0x82D, rev 0x04, class 0x0) bcma: bus0: Core 4 found: GBit MAC (manuf 0x4BF, id 0x82D, rev 0x04, class 0x0) bcma: bus0: Core 5 found: GBit MAC (manuf 0x4BF, id 0x82D, rev 0x04, class 0x0) bcma: bus0: Core 6 found: PCIe Gen 2 (manuf 0x4BF, id 0x501, rev 0x01, class 0x0) bcma: bus0: Core 7 found: PCIe Gen 2 (manuf 0x4BF, id 0x501, rev 0x01, class 0x0) bcma: bus0: Core 8 found: ARM Cortex A9 core (ihost) (manuf 0x4BF, id 0x510, rev 0x01, class 0x0) bcma: bus0: Core 9 found: USB 2.0 (manuf 0x4BF, id 0x504, rev 0x01, class 0x0) bcma: bus0: Core 10 found: USB 3.0 (manuf 0x4BF, id 0x505, rev 0x01, class 0x0) bcma: bus0: Core 11 found: SDIO3 (manuf 0x4BF, id 0x503, rev 0x01, class 0x0) bcma: bus0: Core 12 found: ARM Cortex A9 JTAG (manuf 0x4BF, id 0x506, rev 0x01, class 0x0) bcma: bus0: Core 13 found: Denali DDR2/DDR3 memory controller (manuf 0x4BF, id 0x507, rev 0x01, class 0x0) bcma: bus0: Core 14 found: ROM (manuf 0x4BF, id 0x508, rev 0x01, class 0x0) bcma: bus0: Core 15 found: NAND flash controller (manuf 0x4BF, id 0x509, rev 0x01, class 0x0) bcma: bus0: Core 16 found: SPI flash controller (manuf 0x4BF, id 0x50A, rev 0x01, class 0x0) Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 622fc505d3e1..8fee02807204 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -72,7 +72,19 @@ struct bcma_host_ops { /* Core-ID values. */ #define BCMA_CORE_OOB_ROUTER 0x367 /* Out of band */ #define BCMA_CORE_4706_CHIPCOMMON 0x500 +#define BCMA_CORE_PCIEG2 0x501 +#define BCMA_CORE_DMA 0x502 +#define BCMA_CORE_SDIO3 0x503 +#define BCMA_CORE_USB20 0x504 +#define BCMA_CORE_USB30 0x505 +#define BCMA_CORE_A9JTAG 0x506 +#define BCMA_CORE_DDR23 0x507 +#define BCMA_CORE_ROM 0x508 +#define BCMA_CORE_NAND 0x509 +#define BCMA_CORE_QSPI 0x50A +#define BCMA_CORE_CHIPCOMMON_B 0x50B #define BCMA_CORE_4706_SOC_RAM 0x50E +#define BCMA_CORE_ARMCA9 0x510 #define BCMA_CORE_4706_MAC_GBIT 0x52D #define BCMA_CORE_AMEMC 0x52E /* DDR1/2 memory controller core */ #define BCMA_CORE_ALTA 0x534 /* I2S core */ -- cgit v1.2.3 From 16041990d1c75efb4408d19413cf4fd27aa148dd Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 15 Jul 2013 13:15:06 +0200 Subject: bcma: add constants for new ARM based SoCs These are the chipIDs of some ARM based SoCs from the BCM47xx line. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 8fee02807204..4d043c30216f 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -189,6 +189,11 @@ struct bcma_host_ops { #define BCMA_PKG_ID_BCM5357 11 #define BCMA_CHIP_ID_BCM53572 53572 #define BCMA_PKG_ID_BCM47188 9 +#define BCMA_CHIP_ID_BCM4707 53010 +#define BCMA_PKG_ID_BCM4707 1 +#define BCMA_PKG_ID_BCM4708 2 +#define BCMA_PKG_ID_BCM4709 0 +#define BCMA_CHIP_ID_BCM53018 53018 /* Board types (on PCI usually equals to the subsystem dev id) */ /* BCM4313 */ -- cgit v1.2.3 From be1c9de98d8904c75a5ab8b2a0d97bea0f7c07cc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 13 Jul 2013 23:27:23 +0200 Subject: ACPI / PCI: Make bus registration and unregistration symmetric Since acpi_pci_slot_enumerate() and acpiphp_enumerate_slots() can get the ACPI device handle they need from bus->bridge, it is not necessary to pass that handle to them as an argument. Drop the second argument of acpi_pci_slot_enumerate() and acpiphp_enumerate_slots(), rework them to obtain the ACPI handle from bus->bridge and make acpi_pci_add_bus() and acpi_pci_remove_bus() entirely symmetrical. Tested-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki Acked-by: Yinghai Lu --- include/linux/pci-acpi.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 170447977278..d006f0ca60f4 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -47,24 +47,22 @@ void acpi_pci_remove_bus(struct pci_bus *bus); #ifdef CONFIG_ACPI_PCI_SLOT void acpi_pci_slot_init(void); -void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle); +void acpi_pci_slot_enumerate(struct pci_bus *bus); void acpi_pci_slot_remove(struct pci_bus *bus); #else static inline void acpi_pci_slot_init(void) { } -static inline void acpi_pci_slot_enumerate(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpi_pci_slot_enumerate(struct pci_bus *bus) { } static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } #endif #ifdef CONFIG_HOTPLUG_PCI_ACPI void acpiphp_init(void); -void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); +void acpiphp_enumerate_slots(struct pci_bus *bus); void acpiphp_remove_slots(struct pci_bus *bus); void acpiphp_check_host_bridge(acpi_handle handle); #else static inline void acpiphp_init(void) { } -static inline void acpiphp_enumerate_slots(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpiphp_enumerate_slots(struct pci_bus *bus) { } static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(acpi_handle handle) { } #endif -- cgit v1.2.3 From 62470419e993f8d9d93db0effd3af4296ecb79a5 Mon Sep 17 00:00:00 2001 From: Michael Wang Date: Thu, 4 Jul 2013 12:55:51 +0800 Subject: sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang Cc: Mike Galbraith Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..4f163a8ffabf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1034,6 +1034,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; + struct task_struct *last_wakee; + unsigned long wakee_flips; + unsigned long wakee_flip_decay_ts; #endif int on_rq; -- cgit v1.2.3 From 2753e6f8207355ab72574d48287cec187272a151 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 22 Jul 2013 17:15:52 +0200 Subject: regmap: irq: Allow to acknowledge masked interrupts during initialization In case the hardware interrupt mask register does not prevent the chip level irq from being asserted by the corresponding interrupt status bit, already set interrupt bits should to be cleared once after masking them during initialization. Add a flag to let drivers enable this behavior. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 75981d0b57dc..34ebe7778033 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -470,6 +470,7 @@ struct regmap_irq { * @ack_base: Base ack address. If zero then the chip is clear on read. * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. + * @init_ack_masked: Ack all masked interrupts once during initalization. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. @@ -485,6 +486,7 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; + bool init_ack_masked; unsigned int mask_invert; unsigned int wake_invert; bool runtime_pm; -- cgit v1.2.3 From 36697529b5bbe36911e39a6309e7a7c9250d280a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 07:04:48 -0400 Subject: tty: Replace ldisc locking with ldisc_sem Line discipline locking was performed with a combination of a mutex, a status bit, a count, and a waitqueue -- basically, a rw semaphore. Replace the existing combination with an ld_semaphore. Fixes: 1) the 'reference acquire after ldisc locked' bug 2) the over-complicated halt mechanism 3) lock order wrt. tty_lock() 4) dropping locks while changing ldisc 5) previously unidentified deadlock while locking ldisc from both linked ttys concurrently 6) previously unidentified recursive deadlocks Adds much-needed lockdep diagnostics. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 +--- include/linux/tty_ldisc.h | 3 +-- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 01ac30efd6a6..7269daf7632b 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -238,7 +238,7 @@ struct tty_struct { int index; /* Protects ldisc changes: Lock tty not pty */ - struct mutex ldisc_mutex; + struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; struct mutex atomic_write_lock; @@ -305,8 +305,6 @@ struct tty_file_private { #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ #define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ -#define TTY_LDISC 9 /* Line discipline attached */ -#define TTY_LDISC_CHANGING 10 /* Line discipline changing */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index a1b048999821..23bdd9debb84 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -203,8 +203,7 @@ struct tty_ldisc_ops { struct tty_ldisc { struct tty_ldisc_ops *ops; - atomic_t users; - wait_queue_head_t wq_idle; + struct tty_struct *tty; }; #define TTY_LDISC_MAGIC 0x5403 -- cgit v1.2.3 From 24a89d1cb69b6c488cf16d98dd02e7820f62b40c Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:15 -0400 Subject: tty: Make ldisc input flow control concurrency-friendly Although line discipline receiving is single-producer/single-consumer, using tty->receive_room to manage flow control creates unnecessary critical regions requiring additional lock use. Instead, introduce the optional .receive_buf2() ldisc method which returns the # of bytes actually received. Serialization is guaranteed by the caller. In turn, the line discipline should schedule the buffer work item whenever space becomes available; ie., when there is room to receive data and receive_room() previously returned 0 (the buffer work item stops processing if receive_buf2() returns 0). Note the 'no room' state need not be atomic despite concurrent use by two threads because only the buffer work thread can set the state and only the read() thread can clear the state. Add n_tty_receive_buf2() as the receive_buf2() method for N_TTY. Provide a public helper function, tty_ldisc_receive_buf(), to use when directly accessing the receive_buf() methods. Line disciplines not using input flow control can continue to set tty->receive_room to a fixed value and only provide the receive_buf() method. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 13 +++++++++++++ include/linux/tty_ldisc.h | 13 +++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7269daf7632b..8323ee4f95b9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -557,6 +557,19 @@ extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); extern void tty_ldisc_begin(void); +static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, + char *f, int count) +{ + if (ld->ops->receive_buf2) + count = ld->ops->receive_buf2(ld->tty, p, f, count); + else { + count = min_t(int, count, ld->tty->receive_room); + if (count) + ld->ops->receive_buf(ld->tty, p, f, count); + } + return count; +} + /* n_tty.c */ extern struct tty_ldisc_ops tty_ldisc_N_TTY; diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 23bdd9debb84..f15c898ff462 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -109,6 +109,17 @@ * * Tells the discipline that the DCD pin has changed its status. * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. + * + * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + * char *fp, int count); + * + * This function is called by the low-level tty driver to send + * characters received by the hardware to the line discpline for + * processing. is a pointer to the buffer of input + * character received by the device. is a pointer to a + * pointer of flag bytes which indicate whether a character was + * received with a parity error, etc. + * If assigned, prefer this function for automatic flow control. */ #include @@ -195,6 +206,8 @@ struct tty_ldisc_ops { void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int); void (*fasync)(struct tty_struct *tty, int on); + int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + char *fp, int count); struct module *owner; -- cgit v1.2.3 From 6a1c0680cf3ba94356ecd58833e1540c93472a57 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:23 -0400 Subject: tty: Convert termios_mutex to termios_rwsem termios is commonly accessed unsafely (especially by N_TTY) because the existing mutex forces exclusive access. Convert existing usage. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 8323ee4f95b9..d3042076d163 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -10,6 +10,7 @@ #include #include #include +#include @@ -243,9 +244,9 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; - struct mutex termios_mutex; + struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; - /* Termios values are protected by the termios mutex */ + /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; @@ -253,7 +254,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios mutex */ + struct winsize winsize; /* termios rwsem */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3 From d8c1f929aa8164cd8eaa830068d2fa3159c0764a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:31 -0400 Subject: tty: Only guarantee termios read safety for throttle/unthrottle No tty driver modifies termios during throttle() or unthrottle(). Therefore, only read safety is required. However, tty_throttle_safe and tty_unthrottle_safe must still be mutually exclusive; introduce throttle_mutex for that purpose. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d3042076d163..57a70d1d0412 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -244,6 +244,7 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; + struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ -- cgit v1.2.3 From 1fc359fc3ea72314cc3ebdfa94c60e020c152cd2 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:01 -0400 Subject: tty: Compute flip buffer ptrs The char_buf_ptr and flag_buf_ptr values are trivially derived from the .data field offset; compute values as needed. Fixes a long-standing type-mismatch with the char and flag ptrs. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 12 ++++++++++-- include/linux/tty_flip.h | 4 ++-- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 57a70d1d0412..87bbaa31ebf5 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -31,8 +31,6 @@ struct tty_buffer { struct tty_buffer *next; - char *char_buf_ptr; - unsigned char *flag_buf_ptr; int used; int size; int commit; @@ -41,6 +39,16 @@ struct tty_buffer { unsigned long data[0]; }; +static inline unsigned char *char_buf_ptr(struct tty_buffer *b, int ofs) +{ + return ((unsigned char *)b->data) + ofs; +} + +static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) +{ + return (char *)char_buf_ptr(b, ofs) + b->size; +} + /* * We default to dicing tty buffer allocations to this many characters * in order to avoid multiple page allocations. We know the size of diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index e0f252633b47..ad0303994c32 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -18,8 +18,8 @@ static inline int tty_insert_flip_char(struct tty_port *port, { struct tty_buffer *tb = port->buf.tail; if (tb && tb->used < tb->size) { - tb->flag_buf_ptr[tb->used] = flag; - tb->char_buf_ptr[tb->used++] = ch; + *flag_buf_ptr(tb, tb->used) = flag; + *char_buf_ptr(tb, tb->used++) = ch; return 1; } return tty_insert_flip_string_flags(port, &ch, &flag, 1); -- cgit v1.2.3 From 809850b7a5fcc0a96d023e1171a7944c60fd5a71 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:06 -0400 Subject: tty: Use lockless flip buffer free list In preparation for lockless flip buffers, make the flip buffer free list lockless. NB: using llist is not the optimal solution, as the driver and buffer work may contend over the llist head unnecessarily. However, test measurements indicate this contention is low. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/llist.h | 23 +++++++++++++++++++++++ include/linux/tty.h | 8 ++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index cdaa7f023899..8828a78dec9a 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -124,6 +124,29 @@ static inline void init_llist_head(struct llist_head *list) &(pos)->member != NULL; \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) +/** + * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type + * safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @node: the first entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry_safe(pos, n, node, member) \ + for (pos = llist_entry((node), typeof(*pos), member); \ + &pos->member != NULL && \ + (n = llist_entry(pos->member.next, typeof(*n), member), true); \ + pos = n) + /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test diff --git a/include/linux/tty.h b/include/linux/tty.h index 87bbaa31ebf5..5043b12f23ea 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -11,6 +11,7 @@ #include #include #include +#include @@ -30,7 +31,10 @@ #define __DISABLED_CHAR '\0' struct tty_buffer { - struct tty_buffer *next; + union { + struct tty_buffer *next; + struct llist_node free; + }; int used; int size; int commit; @@ -65,7 +69,7 @@ struct tty_bufhead { spinlock_t lock; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ - struct tty_buffer *free; /* Free queue head */ + struct llist_head free; /* Free queue head */ int memory_used; /* Buffer space used excluding free queue */ }; -- cgit v1.2.3 From 7391ee16950e772076d321792d9fbf030f921345 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:07 -0400 Subject: tty: Simplify flip buffer list with 0-sized sentinel Use a 0-sized sentinel to avoid assigning the head ptr from the driver side thread. This also eliminates testing head/tail for NULL. When the sentinel is first 'consumed' by the buffer work (or by tty_buffer_flush()), it is detached from the list but not freed nor added to the free list. Both buffer work and tty_buffer_flush() continue to preserve at least 1 flip buffer to which head & tail is pointed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5043b12f23ea..2e93eb831c61 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,6 +67,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; spinlock_t lock; + struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ -- cgit v1.2.3 From 7bfe0b7116be207cf2204ae06335cc89d8f8ee02 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:08 -0400 Subject: tty: Track flip buffer memory limit atomically Lockless flip buffers require atomically updating the bytes-in-use watermark. The pty driver also peeks at the watermark value to limit memory consumption to a much lower value than the default; query the watermark with new fn, tty_buffer_space_avail(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- include/linux/tty_flip.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 2e93eb831c61..7c124541f011 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -71,8 +71,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ - int memory_used; /* Buffer space used excluding - free queue */ + atomic_t memory_used; /* In-use buffers excluding free list */ }; /* * When a break, frame error, or parity error happens, these codes are diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index ad0303994c32..6944ed2ce692 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -1,6 +1,7 @@ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H +extern int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); extern int tty_insert_flip_string_flags(struct tty_port *port, const unsigned char *chars, const char *flags, size_t size); -- cgit v1.2.3 From e9975fdec0138f1b2a85b9624e41660abd9865d4 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:10 -0400 Subject: tty: Ensure single-threaded flip buffer consumer with mutex The buffer work may race with parallel tty_buffer_flush. Use a mutex to guarantee exclusive modify access to the head flip buffer. Remove the unneeded spin lock. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7c124541f011..1c8fef0e3ff6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; - spinlock_t lock; + struct mutex flush_mutex; struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ -- cgit v1.2.3 From d7a68be4f265be10e24be931c257af30ca55566b Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:11 -0400 Subject: tty: Only perform flip buffer flush from tty_buffer_flush() Now that dropping the buffer lock is not necessary (as result of converting the spin lock to a mutex), the flip buffer flush no longer needs to be handled by the buffer work. Simply signal a flush is required; the buffer work will exit the i/o loop, which allows tty_buffer_flush() to proceed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1c8fef0e3ff6..1d5bacca3652 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -213,7 +213,6 @@ struct tty_port { wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHING 1 /* Flushing to ldisc in progress */ #define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ -- cgit v1.2.3 From 8c1fb49ba107c7db9441ef6ec0ab5830d112cc2a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:12 -0400 Subject: tty: Avoid false-sharing flip buffer ptrs Separate the head and tail ptrs to avoid cache-line contention (so called 'false-sharing') between concurrent threads. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1d5bacca3652..b8e8adf95bf3 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -65,13 +65,13 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { + struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; struct tty_buffer sentinel; - struct tty_buffer *head; /* Queue head */ - struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ + struct tty_buffer *tail; /* Active buffer */ }; /* * When a break, frame error, or parity error happens, these codes are -- cgit v1.2.3 From 0f56bd2f6a97d8b0eb5c8f9bc04b83a6c16d1d48 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:13 -0400 Subject: tty: Use non-atomic state to signal flip buffer flush pending Atomic bit ops are no longer required to indicate a flip buffer flush is pending, as the flush_mutex is sufficient barrier. Remove the unnecessary port .iflags field and localize flip buffer state to struct tty_bufhead. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index b8e8adf95bf3..991575fe3451 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -68,6 +68,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; + unsigned int flushpending:1; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ @@ -212,8 +213,6 @@ struct tty_port { wait_queue_head_t close_wait; /* Close waiters */ wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ - unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ struct mutex mutex; /* Locking */ -- cgit v1.2.3 From a7c8d58c79853adeebf0a1ddc9c63e433b4d97f1 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:15 -0400 Subject: tty: Fix unsafe vt paste_selection() Convert the tty_buffer_flush() exclusion mechanism to a public interface - tty_buffer_lock/unlock_exclusive() - and use the interface to safely write the paste selection to the line discipline. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- include/linux/tty_flip.h | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 991575fe3451..7a9a3b0a6b5a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,8 +67,8 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; - struct mutex flush_mutex; - unsigned int flushpending:1; + struct mutex lock; + atomic_t priority; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 6944ed2ce692..21ddd7d9ea1f 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -32,4 +32,7 @@ static inline int tty_insert_flip_string(struct tty_port *port, return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } +extern void tty_buffer_lock_exclusive(struct tty_port *port); +extern void tty_buffer_unlock_exclusive(struct tty_port *port); + #endif /* _LINUX_TTY_FLIP_H */ -- cgit v1.2.3 From 9114fe8ccf1871f630d2c14cd60e5f455b015459 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:16 -0400 Subject: tty: Remove private constant from global namespace TTY_BUFFER_PAGE is only used within drivers/tty/tty_buffer.c; relocate to that file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7a9a3b0a6b5a..5fd5d6f1ebc4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -53,17 +53,6 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) return (char *)char_buf_ptr(b, ofs) + b->size; } -/* - * We default to dicing tty buffer allocations to this many characters - * in order to avoid multiple page allocations. We know the size of - * tty_buffer itself but it must also be taken into account that the - * the buffer is 256 byte aligned. See tty_buffer_find for the allocation - * logic this must match - */ - -#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) - - struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; -- cgit v1.2.3 From fc423ff00df3a19554414eed80aef9de9b50313e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 20 Jul 2013 12:13:52 +0200 Subject: team: add peer notification When port is enabled or disabled, allow to notify peers by unsolicitated NAs or gratuitous ARPs. Disabled by default. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index f6156f91eb1c..b0b83683461e 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -10,9 +10,9 @@ #ifndef _LINUX_IF_TEAM_H_ #define _LINUX_IF_TEAM_H_ - #include #include +#include #include struct team_pcpu_stats { @@ -194,6 +194,12 @@ struct team { bool user_carrier_enabled; bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ + struct { + unsigned int count; + unsigned int interval; /* in ms */ + atomic_t count_pending; + struct delayed_work dw; + } notify_peers; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; -- cgit v1.2.3 From 4aa5dee4d9997879adff858514844efab5a15a01 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 20 Jul 2013 12:13:53 +0200 Subject: net: convert resend IGMP to notifier event Until now, bond_resend_igmp_join_requests() looks for vlans attached to bonding device, bridge where bonding act as port manually. It does not care of other scenarios, like stacked bonds or team device above. Make this more generic and use netdev notifier to propagate the event to upper devices and to actually call ip_mc_rejoin_groups(). Signed-off-by: Jiri Pirko Acked-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/linux/netdevice.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index e3362b5f13e8..f47550d75f85 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -129,6 +129,5 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -extern void ip_mc_rejoin_groups(struct in_device *in_dev); #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0741a1e919a5..2bb2357d83bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1633,6 +1633,7 @@ struct packet_offload { #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 #define NETDEV_CHANGEUPPER 0x0015 +#define NETDEV_RESEND_IGMP 0x0016 extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 492b200efdd20b8fcfdac873f3cd8d4902386581 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 20 Jul 2013 12:13:54 +0200 Subject: team: add support for sending multicast rejoins Similar to what is implemented in bonding. User is able to ask team driver to send IGMP rejoins in case port is enabled or disabled. Using previously introduced netdev notifier. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index b0b83683461e..a899dc24be15 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -200,6 +200,12 @@ struct team { atomic_t count_pending; struct delayed_work dw; } notify_peers; + struct { + unsigned int count; + unsigned int interval; /* in ms */ + atomic_t count_pending; + struct delayed_work dw; + } mcast_rejoin; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; -- cgit v1.2.3 From 40d5e0905a03601d40cd4e46b8690093c2355d03 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 10:21:17 -0400 Subject: n_tty: Fix EOF push handling In canonical mode, an EOF which is not the first character of the line causes read() to complete and return the number of characters read so far (commonly referred to as EOF push). However, if the previous read() returned because the user buffer was full _and_ the next character is an EOF not at the beginning of the line, read() must not return 0, thus mistakenly indicating the end-of-file condition. The TTY_PUSH flag is used to indicate an EOF was received which is not at the beginning of the line. Because the EOF push condition is evaluated by a thread other than the read(), multiple EOF pushes can cause a premature end-of-file to be indicated. Instead, discover the 'EOF push as first read character' condition from the read() thread itself, and restart the i/o loop if detected. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5fd5d6f1ebc4..554b732d8b55 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -304,7 +304,6 @@ struct tty_file_private { #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ #define TTY_DEBUG 4 /* Debugging */ #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ -- cgit v1.2.3 From 2adfffa223500b739b17dcf3d710cec344f7608f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 17 Jun 2013 16:48:13 +0200 Subject: OF: make of_property_for_each_{u32|string}() use parameters if OF is not enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I am getting a few |warning: unused variable ‘p’ [-Wunused-variable] |warning: unused variable ‘prop’ [-Wunused-variable] in the case where CONFIG_OF is not defined and the parameters are only used in the loop macro. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Grant Likely --- include/linux/of.h | 39 ++++++++++++++++++++++++--------------- 1 file changed, 24 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..90a8811e9e48 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -323,12 +323,6 @@ extern int of_detach_node(struct device_node *); */ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, u32 *pu); -#define of_property_for_each_u32(np, propname, prop, p, u) \ - for (prop = of_find_property(np, propname, NULL), \ - p = of_prop_next_u32(prop, NULL, &u); \ - p; \ - p = of_prop_next_u32(prop, p, &u)) - /* * struct property *prop; * const char *s; @@ -337,11 +331,6 @@ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, * printk("String value: %s\n", s); */ const char *of_prop_next_string(struct property *prop, const char *cur); -#define of_property_for_each_string(np, propname, prop, s) \ - for (prop = of_find_property(np, propname, NULL), \ - s = of_prop_next_string(prop, NULL); \ - s; \ - s = of_prop_next_string(prop, s)) #else /* CONFIG_OF */ @@ -505,12 +494,20 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline const __be32 *of_prop_next_u32(struct property *prop, + const __be32 *cur, u32 *pu) +{ + return NULL; +} + +static inline const char *of_prop_next_string(struct property *prop, + const char *cur) +{ + return NULL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL -#define of_property_for_each_u32(np, propname, prop, p, u) \ - while (0) -#define of_property_for_each_string(np, propname, prop, s) \ - while (0) #endif /* CONFIG_OF */ #ifndef of_node_to_nid @@ -559,6 +556,18 @@ static inline int of_property_read_u32(const struct device_node *np, return of_property_read_u32_array(np, propname, out_value, 1); } +#define of_property_for_each_u32(np, propname, prop, p, u) \ + for (prop = of_find_property(np, propname, NULL), \ + p = of_prop_next_u32(prop, NULL, &u); \ + p; \ + p = of_prop_next_u32(prop, p, &u)) + +#define of_property_for_each_string(np, propname, prop, s) \ + for (prop = of_find_property(np, propname, NULL), \ + s = of_prop_next_string(prop, NULL); \ + s; \ + s = of_prop_next_string(prop, s)) + #if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE) extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); -- cgit v1.2.3 From 374d5c9964c10373ba39bbe934f4262eb87d7114 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Mon, 1 Jul 2013 14:20:35 -0400 Subject: of: Specify initrd location using 64-bit On some PAE architectures, the entire range of physical memory could reside outside the 32-bit limit. These systems need the ability to specify the initrd location using 64-bit numbers. This patch globally modifies the early_init_dt_setup_initrd_arch() function to use 64-bit numbers instead of the current unsigned long. There has been quite a bit of debate about whether to use u64 or phys_addr_t. It was concluded to stick to u64 to be consistent with rest of the device tree code. As summarized by Geert, "The address to load the initrd is decided by the bootloader/user and set at that point later in time. The dtb should not be tied to the kernel you are booting" More details on the discussion can be found here: https://lkml.org/lkml/2013/6/20/690 https://lkml.org/lkml/2012/9/13/544 Signed-off-by: Santosh Shilimkar Acked-by: Rob Herring Acked-by: Vineet Gupta Acked-by: Jean-Christophe PLAGNIOL-VILLARD Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index ed136ad698ce..4a17939b95cc 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -106,8 +106,7 @@ extern u64 dt_mem_next_cell(int s, __be32 **cellp); * physical addresses. */ #ifdef CONFIG_BLK_DEV_INITRD -extern void early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end); +extern void early_init_dt_setup_initrd_arch(u64 start, u64 end); #endif /* Early flat tree scan hooks */ -- cgit v1.2.3 From f484f7a6bc6f0f871627cc1f83f56077a5dc6e47 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:42 +0200 Subject: regmap: irq: make flags bool and put them in a bitfield This patch makes mask/wake_invert bool and puts all flags into a bitfield for consistency and to save some space. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 34ebe7778033..99b0f7cad75c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -486,10 +486,10 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; - bool init_ack_masked; - unsigned int mask_invert; - unsigned int wake_invert; - bool runtime_pm; + bool init_ack_masked:1; + bool mask_invert:1; + bool wake_invert:1; + bool runtime_pm:1; int num_regs; -- cgit v1.2.3 From 68622bdfefb969fd7cf710545d7e758a732ab01d Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:48 +0200 Subject: regmap: irq: document mask/wake_invert flags Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 99b0f7cad75c..a3c68aad2381 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -471,6 +471,8 @@ struct regmap_irq { * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. + * @mask_invert: Inverted mask register: cleared bits are masked out. + * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. -- cgit v1.2.3 From 5ff9d8a65ce80efb509ce4e8051394e9ed2cd942 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Mar 2013 21:04:39 -0700 Subject: vfs: Lock in place mounts from more privileged users When creating a less privileged mount namespace or propogating mounts from a more privileged to a less privileged mount namespace lock the submounts so they may not be unmounted individually in the child mount namespace revealing what is under them. This enforces the reasonable expectation that it is not possible to see under a mount point. Most of the time mounts are on empty directories and revealing that does not matter, however I have seen an occassionaly sloppy configuration where there were interesting things concealed under a mount point that probably should not be revealed. Expirable submounts are not locked because they will eventually unmount automatically so whatever is under them already needs to be safe for unprivileged users to access. From a practical standpoint these restrictions do not appear to be significant for unprivileged users of the mount namespace. Recursive bind mounts and pivot_root continues to work, and mounts that are created in a mount namespace may be unmounted there. All of which means that the common idiom of keeping a directory of interesting files and using pivot_root to throw everything else away continues to work just fine. Acked-by: Serge Hallyn Acked-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- include/linux/mount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 73005f9957ea..38cd98f112a0 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -48,6 +48,7 @@ struct mnt_namespace; #define MNT_INTERNAL 0x4000 #define MNT_LOCK_READONLY 0x400000 +#define MNT_LOCKED 0x800000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ -- cgit v1.2.3 From dee4a0be69c0e2996188e0c46478eadc280a8954 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 24 Jul 2013 16:43:51 -0400 Subject: tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [] lock_acquire+0x92/0x1f0 [] down_read+0x47/0x5c [] __blocking_notifier_call_chain+0x56/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [] lock_acquire+0x92/0x1f0 [] console_lock+0x77/0x80 [] con_flush_chars+0x31/0x50 [] n_tty_write+0x1ec/0x4d0 [] tty_write+0x159/0x2e0 [] redirected_tty_write+0xb5/0xc0 [] vfs_write+0xc5/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [] __lock_acquire+0x1c43/0x1d30 [] lock_acquire+0x92/0x1f0 [] down_write+0x44/0x70 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [] dump_stack+0x19/0x1b [] print_circular_bug+0x1fb/0x20c [] __lock_acquire+0x1c43/0x1d30 [] ? mark_held_locks+0xae/0x120 [] ? trace_hardirqs_on_caller+0x105/0x1d0 [] lock_acquire+0x92/0x1f0 [] ? tty_do_resize+0x36/0xe0 [] down_write+0x44/0x70 [] ? tty_do_resize+0x36/0xe0 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] ? kmemleak_alloc+0x5b/0xc0 [] ? kmem_cache_alloc_trace+0x104/0x290 [] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] ? _raw_spin_unlock_irqrestore+0x42/0x80 [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] ? driver_probe_device+0x3a0/0x3a0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] ? 0xffffffffa0229fff [] driver_register+0x77/0x170 [] ? 0xffffffffa0229fff [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] ? 0xffffffffa0229fff [] ? 0xffffffffa0229fff [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] ? ddebug_proc_open+0xb0/0xb0 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 554b732d8b55..64f864651d86 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -245,6 +245,7 @@ struct tty_struct { struct mutex legacy_mutex; struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; + struct mutex winsize_mutex; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; @@ -254,7 +255,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios rwsem */ + struct winsize winsize; /* winsize_mutex */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3 From 10e232c597ac757e7f8600649f7e872e86de190f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 28 Jun 2013 09:38:12 +0800 Subject: USB: check sg buffer size in usb_submit_urb USB spec stats that short packet can only appear at the end of transfer. Because lost of HC(EHCI/UHCI/OHCI/...) can't build a full packet from discontinuous buffers, we introduce the limit in usb_submit_urb() to avoid such kind of bad sg buffers coming from driver. The limit might be a bit strict: - platform has iommu to do sg list mapping - some host controllers may support to build full packet from discontinuous buffers. But considered that most of HCs don't support that, and driver need work well or keep consistent on different HCs and ARCHs, we have to introduce the limit. Currently, only usbtest is reported to pass such sg buffers to HC, and other users(mass storage, usbfs) don't have the problem. We don't check it on USB wireless device, because: - wireless devices can't be attached to common USB bus(EHCI/UHCI/OHCI/...) - the max packet size of endpoint may be odd, and often can't devide 4KB which is a typical usage in usb mass storage application Reported-by: Konstantin Filatov Reported-by: Denis V. Lunev Cc: Felipe Balbi Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index a232b7ece1f6..e99b2a114af4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1258,7 +1258,9 @@ typedef void (*usb_complete_t)(struct urb *); * the device driver is saying that it provided this DMA address, * which the host controller driver should use in preference to the * transfer_buffer. - * @sg: scatter gather buffer list + * @sg: scatter gather buffer list, the buffer size of each element in + * the list (except the last) must be divisible by the endpoint's + * max packet size * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3 From c9bee3b7fdecb0c1d070c7b54113b3bdfb9a3d36 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Jul 2013 20:27:07 -0700 Subject: tcp: TCP_NOTSENT_LOWAT socket option Idea of this patch is to add optional limitation of number of unsent bytes in TCP sockets, to reduce usage of kernel memory. TCP receiver might announce a big window, and TCP sender autotuning might allow a large amount of bytes in write queue, but this has little performance impact if a large part of this buffering is wasted : Write queue needs to be large only to deal with large BDP, not necessarily to cope with scheduling delays (incoming ACKS make room for the application to queue more bytes) For most workloads, using a value of 128 KB or less is OK to give applications enough time to react to POLLOUT events in time (or being awaken in a blocking sendmsg()) This patch adds two ways to set the limit : 1) Per socket option TCP_NOTSENT_LOWAT 2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets not using TCP_NOTSENT_LOWAT socket option (or setting a zero value) Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect. This changes poll()/select()/epoll() to report POLLOUT only if number of unsent bytes is below tp->nosent_lowat Note this might increase number of sendmsg()/sendfile() calls when using non blocking sockets, and increase number of context switches for blocking sockets. Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is defined as : Specify the minimum number of bytes in the buffer until the socket layer will pass the data to the protocol) Tested: netperf sessions, and watching /proc/net/protocols "memory" column for TCP With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458) lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y Using 128KB has no bad effect on the throughput or cpu usage of a single flow, although there is an increase of context switches. A bonus is that we hold socket lock for a shorter amount of time and should improve latencies of ACK processing. lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 412,514 context-switches 200.034645535 seconds time elapsed lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 2,675,818 context-switches 200.029651391 seconds time elapsed Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Yuchung Cheng Acked-By: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 472120b4fac5..9640803a17a7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -238,6 +238,7 @@ struct tcp_sock { u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ -- cgit v1.2.3 From 18afa4b028b46f8b45ca64f94aefe717c297b07d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 23 Jul 2013 16:13:17 +0200 Subject: net: Make devnet_rename_seq static No users outside net/core/dev.c. Signed-off-by: Thomas Gleixner Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2bb2357d83bb..3ca60b070ef0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1666,9 +1666,6 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ -extern seqcount_t devnet_rename_seq; /* Device rename seq */ - - #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ -- cgit v1.2.3 From 9548906b2bb7ff09e12c013a55d669bef2c8e121 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 25 Jul 2013 05:44:02 +0900 Subject: xattr: Constify ->name member of "struct xattr". Since everybody sets kstrdup()ed constant string to "struct xattr"->name but nobody modifies "struct xattr"->name , we can omit kstrdup() and its failure checking by constifying ->name member of "struct xattr". Signed-off-by: Tetsuo Handa Reviewed-by: Joel Becker [ocfs2] Acked-by: Serge E. Hallyn Acked-by: Casey Schaufler Acked-by: Mimi Zohar Reviewed-by: Paul Moore Tested-by: Paul Moore Acked-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 8 ++++---- include/linux/xattr.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 7ce53ae1266b..9d37e2b9d3ec 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1492,7 +1492,7 @@ struct security_operations { int (*inode_alloc_security) (struct inode *inode); void (*inode_free_security) (struct inode *inode); int (*inode_init_security) (struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, + const struct qstr *qstr, const char **name, void **value, size_t *len); int (*inode_create) (struct inode *dir, struct dentry *dentry, umode_t mode); @@ -1770,7 +1770,7 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, initxattrs initxattrs, void *fs_data); int security_old_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, + const struct qstr *qstr, const char **name, void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, @@ -2094,8 +2094,8 @@ static inline int security_inode_init_security(struct inode *inode, static inline int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, - char **name, void **value, - size_t *len) + const char **name, + void **value, size_t *len) { return -EOPNOTSUPP; } diff --git a/include/linux/xattr.h b/include/linux/xattr.h index fdbafc6841cf..91b0a68d38dc 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -31,7 +31,7 @@ struct xattr_handler { }; struct xattr { - char *name; + const char *name; void *value; size_t value_len; }; -- cgit v1.2.3 From 3784b6d64dc52ed3fbebad61a85ab9b7a687a167 Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Thu, 25 Jul 2013 11:33:18 +0800 Subject: regulator: pfuze100: add pfuze100 regulator driver Add pfuze100 regulator driver. Signed-off-by: Robin Gong Tested-by: Steffen Trumtrar Signed-off-by: Mark Brown --- include/linux/regulator/pfuze100.h | 44 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/regulator/pfuze100.h (limited to 'include/linux') diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h new file mode 100644 index 000000000000..65d550bf3954 --- /dev/null +++ b/include/linux/regulator/pfuze100.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ +#ifndef __LINUX_REG_PFUZE100_H +#define __LINUX_REG_PFUZE100_H + +#define PFUZE100_SW1AB 0 +#define PFUZE100_SW1C 1 +#define PFUZE100_SW2 2 +#define PFUZE100_SW3A 3 +#define PFUZE100_SW3B 4 +#define PFUZE100_SW4 5 +#define PFUZE100_SWBST 6 +#define PFUZE100_VSNVS 7 +#define PFUZE100_VREFDDR 8 +#define PFUZE100_VGEN1 9 +#define PFUZE100_VGEN2 10 +#define PFUZE100_VGEN3 11 +#define PFUZE100_VGEN4 12 +#define PFUZE100_VGEN5 13 +#define PFUZE100_VGEN6 14 +#define PFUZE100_MAX_REGULATOR 15 + +struct regulator_init_data; + +struct pfuze_regulator_platform_data { + struct regulator_init_data *init_data[PFUZE100_MAX_REGULATOR]; +}; + +#endif /* __LINUX_REG_PFUZE100_H */ -- cgit v1.2.3 From 36019265cf81cdb2d366b28016bb00b936efc751 Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Wed, 24 Jul 2013 23:11:53 -0700 Subject: ktime: fix some scripts/kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the following type of warnings: Warning(include/linux/ktime.h:75): No description found for return value of 'ktime_set' Fix them by using a "Return:" section to describe the return values. (Also apply some minor reformatting along the way.) Signed-off-by: Yacine Belkadi Acked-by: Rob Landley Signed-off-by: Jiri Kosina --- include/linux/ktime.h | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index debf208b7611..31c0cd1c941a 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -69,7 +69,7 @@ typedef union ktime ktime_t; /* Kill this */ * @secs: seconds to set * @nsecs: nanoseconds to set * - * Return the ktime_t representation of the value + * Return: The ktime_t representation of the value. */ static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) { @@ -151,7 +151,7 @@ static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) * @lhs: minuend * @rhs: subtrahend * - * Returns the remainder of the subtraction + * Return: The remainder of the subtraction. */ static inline ktime_t ktime_sub(const ktime_t lhs, const ktime_t rhs) { @@ -169,7 +169,7 @@ static inline ktime_t ktime_sub(const ktime_t lhs, const ktime_t rhs) * @add1: addend1 * @add2: addend2 * - * Returns the sum of @add1 and @add2. + * Return: The sum of @add1 and @add2. */ static inline ktime_t ktime_add(const ktime_t add1, const ktime_t add2) { @@ -195,7 +195,7 @@ static inline ktime_t ktime_add(const ktime_t add1, const ktime_t add2) * @kt: addend * @nsec: the scalar nsec value to add * - * Returns the sum of @kt and @nsec in ktime_t format + * Return: The sum of @kt and @nsec in ktime_t format. */ extern ktime_t ktime_add_ns(const ktime_t kt, u64 nsec); @@ -204,7 +204,7 @@ extern ktime_t ktime_add_ns(const ktime_t kt, u64 nsec); * @kt: minuend * @nsec: the scalar nsec value to subtract * - * Returns the subtraction of @nsec from @kt in ktime_t format + * Return: The subtraction of @nsec from @kt in ktime_t format. */ extern ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec); @@ -212,7 +212,7 @@ extern ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec); * timespec_to_ktime - convert a timespec to ktime_t format * @ts: the timespec variable to convert * - * Returns a ktime_t variable with the converted timespec value + * Return: A ktime_t variable with the converted timespec value. */ static inline ktime_t timespec_to_ktime(const struct timespec ts) { @@ -224,7 +224,7 @@ static inline ktime_t timespec_to_ktime(const struct timespec ts) * timeval_to_ktime - convert a timeval to ktime_t format * @tv: the timeval variable to convert * - * Returns a ktime_t variable with the converted timeval value + * Return: A ktime_t variable with the converted timeval value. */ static inline ktime_t timeval_to_ktime(const struct timeval tv) { @@ -237,7 +237,7 @@ static inline ktime_t timeval_to_ktime(const struct timeval tv) * ktime_to_timespec - convert a ktime_t variable to timespec format * @kt: the ktime_t variable to convert * - * Returns the timespec representation of the ktime value + * Return: The timespec representation of the ktime value. */ static inline struct timespec ktime_to_timespec(const ktime_t kt) { @@ -249,7 +249,7 @@ static inline struct timespec ktime_to_timespec(const ktime_t kt) * ktime_to_timeval - convert a ktime_t variable to timeval format * @kt: the ktime_t variable to convert * - * Returns the timeval representation of the ktime value + * Return: The timeval representation of the ktime value. */ static inline struct timeval ktime_to_timeval(const ktime_t kt) { @@ -262,7 +262,7 @@ static inline struct timeval ktime_to_timeval(const ktime_t kt) * ktime_to_ns - convert a ktime_t variable to scalar nanoseconds * @kt: the ktime_t variable to convert * - * Returns the scalar nanoseconds representation of @kt + * Return: The scalar nanoseconds representation of @kt. */ static inline s64 ktime_to_ns(const ktime_t kt) { @@ -276,7 +276,9 @@ static inline s64 ktime_to_ns(const ktime_t kt) * @cmp1: comparable1 * @cmp2: comparable2 * - * Compare two ktime_t variables, returns 1 if equal + * Compare two ktime_t variables. + * + * Return: 1 if equal. */ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2) { @@ -288,7 +290,7 @@ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2) * @cmp1: comparable1 * @cmp2: comparable2 * - * Returns ... + * Return: ... * cmp1 < cmp2: return <0 * cmp1 == cmp2: return 0 * cmp1 > cmp2: return >0 @@ -342,7 +344,7 @@ extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); * @kt: the ktime_t variable to convert * @ts: the timespec variable to store the result in * - * Returns true if there was a successful conversion, false if kt was 0. + * Return: %true if there was a successful conversion, %false if kt was 0. */ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts) -- cgit v1.2.3 From 928bea964827d7824b548c1f8e06eccbbc4d0d7d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:17 -0700 Subject: PCI: Delay enabling bridges until they're needed We currently enable PCI bridges after scanning a bus and assigning resources. This is often done in arch code. This patch changes this so we don't enable a bridge until necessary, i.e., until we enable a PCI device behind the bridge. We do this in the generic pci_enable_device() path, so this also removes the arch-specific code to enable bridges. [bhelgaas: changelog] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..8cd1e6f30acd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1043,7 +1043,6 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, resource_size_t, resource_size_t), void *alignf_data); -void pci_enable_bridges(struct pci_bus *bus); /* Proper probing supporting hot-pluggable devices */ int __must_check __pci_register_driver(struct pci_driver *, struct module *, -- cgit v1.2.3 From 39772038ea93e85ea4f1307ec9c1f48a063d89a0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:18 -0700 Subject: PCI: Assign resources for hot-added host bridge more aggressively When hot-adding an ACPI host bridge, use pci_assign_unassigned_root_bus_resources() instead of pci_assign_unassigned_bus_resources(). The former is more aggressive and will release and reassign existing resources if necessary. This is safe at hot-add time because no drivers are bound to devices below the new host bridge yet. [bhelgaas: changelog, split __init changes out for reviewability] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8cd1e6f30acd..e494c90a00d1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1003,6 +1003,7 @@ int pci_claim_resource(struct pci_dev *, int); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); +void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus); void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), -- cgit v1.2.3 From 42189d854f174e7b29e0fdb4da9984ba63126a92 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 2 Jul 2013 10:50:15 +0300 Subject: usb: clamp bInterval to allowed range bInterval must be within the range 1 - 16 when running at High/Super speed, and within the range 1 - 255 when running at Full/Low speed. In order to catch drivers passing a too large bInterval on Super/High speed scenarios (thus overflowing urb->interval), let's clamp() the argument to the allowed ranges. Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e99b2a114af4..eb4252a0da7e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1547,10 +1547,16 @@ static inline void usb_fill_int_urb(struct urb *urb, urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; - if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) + + if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) { + /* make sure interval is within allowed range */ + interval = clamp(interval, 1, 16); + urb->interval = 1 << (interval - 1); - else + } else { urb->interval = interval; + } + urb->start_frame = -1; } -- cgit v1.2.3 From 323f54ed0f3ce20e9946c961fc928ccdb80d9345 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Thu, 25 Jul 2013 14:26:10 -0400 Subject: numa: Mark __node_set() as __always_inline It is posible for some compilers to decide that __node_set() does not need to be made turned into an inline function. When the compiler does this on an __init function calling it on __initdata we get a section mismatch warning now. Use __always_inline to ensure that we will be inlined. Reported-by: Paul Bolle Cc: Jianpeng Ma Cc: Rusty Russell Cc: Lai Jiangshan Cc: Yasuaki Ishimatsu Cc: Wen Congyang Cc: Jiang Liu Cc: KOSAKI Motohiro Cc: Minchan Kim Cc: Mel Gorman Cc: David Rientjes Cc: Yinghai Lu Cc: Greg KH Signed-off-by: Tom Rini Link: http://lkml.kernel.org/r/1374776770-32361-1-git-send-email-trini@ti.com Signed-off-by: Ingo Molnar --- include/linux/nodemask.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4e2cbfa640b7..58b9a02c38d2 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -98,8 +98,17 @@ typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; +/* + * The inline keyword gives the compiler room to decide to inline, or + * not inline a function as it sees best. However, as these functions + * are called in both __init and non-__init functions, if they are not + * inlined we will end up with a section mis-match error (of the type of + * freeable items not being freed). So we must use __always_inline here + * to fix the problem. If other functions in the future also end up in + * this situation they will also need to be annotated as __always_inline + */ #define node_set(node, dst) __node_set((node), &(dst)) -static inline void __node_set(int node, volatile nodemask_t *dstp) +static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } -- cgit v1.2.3 From c817a67ecba7c3c2aaa104796d78f160af60920d Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 27 Jun 2013 15:06:14 +0100 Subject: kobject: delayed kobject release: help find buggy drivers Implement debugging for kobject release functions. kobjects are reference counted, so the drop of the last reference to them is not predictable. However, the common case is for the last reference to be the kobject's removal from a subsystem, which results in the release function being immediately called. This can hide subtle bugs, which can occur when another thread holds a reference to the kobject at the same time that a kobject is removed. This results in the release method being delayed. In order to make these kinds of problems more visible, the following patch implements a delayed release; this has the effect that the release function will be out of order with respect to the removal of the kobject in the same manner that it would be if a reference was being held. This provides us with an easy way to allow driver writers to debug their drivers and fix otherwise hidden problems. Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 939b11268c86..de6dcbcc6ef7 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -26,6 +26,7 @@ #include #include #include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ @@ -65,6 +66,9 @@ struct kobject { struct kobj_type *ktype; struct sysfs_dirent *sd; struct kref kref; +#ifdef CONFIG_DEBUG_KOBJECT_RELEASE + struct delayed_work release; +#endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; -- cgit v1.2.3 From cffe4e0e7413eb29fb8bd035c8b12b33a4b8522a Mon Sep 17 00:00:00 2001 From: Stratos Karafotis Date: Wed, 5 Jun 2013 19:01:50 +0300 Subject: cpufreq: Remove unused function __cpufreq_driver_getavg() The target frequency calculation method in the ondemand governor has changed and it is now independent of the measured average frequency. Consequently, the __cpufreq_driver_getavg() function and getavg member of struct cpufreq_driver are not used any more, so drop them. [rjw: Changelog] Signed-off-by: Stratos Karafotis Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 90d5a15120d5..e1fd215e16c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -216,10 +216,6 @@ extern int cpufreq_driver_target(struct cpufreq_policy *policy, extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); - -extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy, - unsigned int cpu); - int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -258,8 +254,6 @@ struct cpufreq_driver { unsigned int (*get) (unsigned int cpu); /* optional */ - unsigned int (*getavg) (struct cpufreq_policy *policy, - unsigned int cpu); int (*bios_limit) (int cpu, unsigned int *limit); int (*exit) (struct cpufreq_policy *policy); -- cgit v1.2.3 From 102c9323c35a83789ad5ebd3c45fa8fb389add88 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 17:07:27 -0400 Subject: tracing: Add __tracepoint_string() to export string pointers There are several tracepoints (mostly in RCU), that reference a string pointer and uses the print format of "%s" to display the string that exists in the kernel, instead of copying the actual string to the ring buffer (saves time and ring buffer space). But this has an issue with userspace tools that read the binary buffers that has the address of the string but has no access to what the string itself is. The end result is just output that looks like: rcu_dyntick: ffffffff818adeaa 1 0 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_utilization: ffffffff8184333b rcu_utilization: ffffffff8184333b The above is pretty useless when read by the userspace tools. Ideally we would want something that looks like this: rcu_dyntick: Start 1 0 rcu_dyntick: End 0 140000000000000 rcu_dyntick: Start 140000000000000 0 rcu_callback: rcu_preempt rhp=0xffff880037aff710 func=put_cred_rcu 0/4 rcu_callback: rcu_preempt rhp=0xffff880078961980 func=file_free_rcu 0/5 rcu_dyntick: End 0 1 The trace_printk() which also only stores the address of the string format instead of recording the string into the buffer itself, exports the mapping of kernel addresses to format strings via the printk_format file in the debugfs tracing directory. The tracepoint strings can use this same method and output the format to the same file and the userspace tools will be able to decipher the address without any modification. The tracepoint strings need its own section to save the strings because the trace_printk section will cause the trace_printk() buffers to be allocated if anything exists within the section. trace_printk() is only used for debugging and should never exist in the kernel, we can not use the trace_printk sections. Add a new tracepoint_str section that will also be examined by the output of the printk_format file. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4372658c73ae..81af18a75f4d 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -357,6 +357,40 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) +/** + * tracepoint_string - register constant persistent string to trace system + * @str - a constant persistent string that will be referenced in tracepoints + * + * If constant strings are being used in tracepoints, it is faster and + * more efficient to just save the pointer to the string and reference + * that with a printf "%s" instead of saving the string in the ring buffer + * and wasting space and time. + * + * The problem with the above approach is that userspace tools that read + * the binary output of the trace buffers do not have access to the string. + * Instead they just show the address of the string which is not very + * useful to users. + * + * With tracepoint_string(), the string will be registered to the tracing + * system and exported to userspace via the debugfs/tracing/printk_formats + * file that maps the string address to the string text. This way userspace + * tools that read the binary buffers have a way to map the pointers to + * the ASCII strings they represent. + * + * The @str used must be a constant string and persistent as it would not + * make sense to show a string that no longer exists. But it is still fine + * to be used with modules, because when modules are unloaded, if they + * had tracepoints, the ring buffers are cleared too. As long as the string + * does not change during the life of the module, it is fine to use + * tracepoint_string() within a module. + */ +#define tracepoint_string(str) \ + ({ \ + static const char *___tp_str __tracepoint_string = str; \ + ___tp_str; \ + }) +#define __tracepoint_string __attribute__((section("__tracepoint_str"))) + #ifdef CONFIG_PERF_EVENTS struct perf_event; -- cgit v1.2.3 From 10d8b34a421716d55a4ff7c2d427c35e88b8fd60 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:17 +0400 Subject: serial: max310x: Driver rework This patch rework max310x driver. Major changes have been made: - Prepare driver to support ICs with more than one UART. - Prepare driver to support work with I2C-bus. The patch changes almost every function and can not be divided into parts. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 91648bf5fc5c..1aec0b620ac3 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -42,9 +42,8 @@ /* MAX310X platform data structure */ struct max310x_pdata { /* Flags global to driver */ - const u8 driver_flags:2; + const u8 driver_flags; #define MAX310X_EXT_CLK (0x00000001) /* External clock enable */ -#define MAX310X_AUTOSLEEP (0x00000002) /* Enable AutoSleep mode */ /* Flags global to UART port */ const u8 uart_flags[MAX310X_MAX_UARTS]; #define MAX310X_LOOPBACK (0x00000001) /* Loopback mode enable */ @@ -60,8 +59,6 @@ struct max310x_pdata { void (*init)(void); /* Called before finish */ void (*exit)(void); - /* Suspend callback */ - void (*suspend)(int do_suspend); }; #endif -- cgit v1.2.3 From 21fc509f1194c2fa06eff4c72238210089c29453 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:18 +0400 Subject: serial: max310x: Add MAX3109 support This patch adds support for MAX3109 (advanced dual universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 1aec0b620ac3..4c128eda26ba 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8 serial driver + * Maxim (Dallas) MAX3107/8/9 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 1 +#define MAX310X_MAX_UARTS 2 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3 From 003236d9ac4d02721867e47f7ad4371ab7f74689 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:19 +0400 Subject: serial: max310x: Add MAX14830 support This patch adds support for MAX14830 (advanced quad universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 4c128eda26ba..dd11dcd1a184 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8/9 serial driver + * Maxim (Dallas) MAX3107/8/9, MAX14830 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 2 +#define MAX310X_MAX_UARTS 4 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3 From 12197de2cdb2ded83db7b5a3a06f4b275fb8e62c Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:38 +0100 Subject: pci_ids.h: move PCI_VENDOR_ID_AMCC here PCI_VENDOR_ID_AMCC is defined locally in "drivers/staging/comedi/comedidev.h" for a few comedi hardware drivers, namely "adl_pci9118", "addi_apci_1500" and "addi_apci_3120" (also "addi_apci_1710" but that is not currently built and will probably be removed soon). Move the define into "include/linux/pci_ids.h" as it is shared by several drivers (albeit all comedi drivers currently). PCI_VENDOR_ID_AMCC happens to have the same value (0x10e8) as PCI_VENDOR_ID_ADDIDATA_OLD. The vendor ID is actually assigned to Applied Micro Circuits Corporation and Addi-Data were using device IDs assigned by AMCC on some of their earlier PCI boards. The PCI_VENDOR_ID_ADDIDATA_OLD define is still being used by the "8250_pci" PCI serial board driver. Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bed2e89611b..9d9911926598 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1311,6 +1311,8 @@ #define PCI_DEVICE_ID_IMS_TT128 0x9128 #define PCI_DEVICE_ID_IMS_TT3D 0x9135 +#define PCI_VENDOR_ID_AMCC 0x10e8 + #define PCI_VENDOR_ID_INTERG 0x10ea #define PCI_DEVICE_ID_INTERG_1682 0x1682 #define PCI_DEVICE_ID_INTERG_2000 0x2000 @@ -2256,7 +2258,7 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 +#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 -- cgit v1.2.3 From fee8bf4b74e37bfeb8998a349cb788680eb3f634 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:41 +0100 Subject: pci_ids.h: remove PCI_VENDOR_ID_ADDIDATA_OLD and PCI_DEVICE_ID_ADDIDATA_APCI7800 These two defines are no longer used. They were only used by the PCI serial driver "8250_pci" to support the original ADDI-DATA APCI-7800 card. In that driver, PCI_VENDOR_ID_ADDIDATA_OLD has been replaced with PCI_VENDOR_ID_AMCC which has the same value (0x10e8), and PCI_DEVICE_ID_ADDIDATA_APCI7800 has been replaced with a local #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 with the same value (0x818e). Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 9d9911926598..6dec3d6abe0b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2258,12 +2258,10 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 #define PCI_DEVICE_ID_ADDIDATA_APCI7300 0x7002 -#define PCI_DEVICE_ID_ADDIDATA_APCI7800 0x818E #define PCI_DEVICE_ID_ADDIDATA_APCI7500_2 0x7009 #define PCI_DEVICE_ID_ADDIDATA_APCI7420_2 0x700A #define PCI_DEVICE_ID_ADDIDATA_APCI7300_2 0x700B -- cgit v1.2.3 From cf940ebe98e693aec2d10f9af2fb84eb55234e3c Mon Sep 17 00:00:00 2001 From: Andreas Platschek Date: Fri, 26 Jul 2013 06:46:37 +0200 Subject: tty: Remove dead code -> The ledptrs[] array is never initialized. -> There is no place where kbd->ledmode is set to LED_SHOW_MEM therefore the if statement does not make much sense. -> Since LED_SHOW_MEM is not used, it can be removed from the header file as well. Signed-off-by: Andreas Platschek Signed-off-by: Greg Kroah-Hartman --- include/linux/kbd_kern.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index b7c8cdc1d422..cbfb171bbcba 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -36,10 +36,9 @@ struct kbd_struct { #define VC_CTRLRLOCK KG_CTRLR /* ctrlr lock mode */ unsigned char slockstate; /* for `sticky' Shift, Ctrl, etc. */ - unsigned char ledmode:2; /* one 2-bit value */ + unsigned char ledmode:1; #define LED_SHOW_FLAGS 0 /* traditional state */ #define LED_SHOW_IOCTL 1 /* only change leds upon ioctl */ -#define LED_SHOW_MEM 2 /* `heartbeat': peek into memory */ unsigned char ledflagstate:4; /* flags, not lights */ unsigned char default_ledflagstate:4; -- cgit v1.2.3 From 6741335bc7294548ac95cb1f4671991ff30da193 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Tue, 2 Jul 2013 10:31:30 -0700 Subject: Drivers: hv: util: Fix a bug in version negotiation code for util services The current code picked the highest version advertised by the host. WS2012 R2 has implemented a protocol version for KVP that is not compatible with prior protocol versions of KVP. Fix the bug in the current code by explicitly specifying the protocol version that the guest can support. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fae8bac907ef..49949079cf47 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -27,6 +27,14 @@ #include +/* + * Framework version for util services. + */ + +#define UTIL_FW_MAJOR 3 +#define UTIL_FW_MINOR 0 +#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) + /* * Implementation of host controlled snapshot of the guest. @@ -1494,7 +1502,7 @@ struct hyperv_service_callback { }; #define MAX_SRV_VER 0x7ffffff -extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -- cgit v1.2.3 From a88c32ae15f25fcf0a3c9fadd92f840a1abf0e43 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 25 Jul 2013 13:47:53 +0800 Subject: USBNET: centralize computing of max rx/tx qlen This patch centralizes computing of max rx/tx qlen, because: - RX_QLEN()/TX_QLEN() is called in hot path - computing depends on device's usb speed, now we have ls/fs, hs, ss, so more checks need to be involved - in fact, max rx/tx qlen should not only depend on device USB speed, but also depend on ethernet link speed, so we need to consider that in future. - if SG support is done, max tx qlen may need change too Generally, hard_mtu and rx_urb_size are changed in bind(), reset() and link_reset() callback, and change mtu network operation, this patches introduces the API of usbnet_update_max_qlen(), and calls it in above path. Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index f18d64129f99..8fbc008e183e 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -34,6 +34,7 @@ struct usbnet { struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; + unsigned short rx_qlen, tx_qlen; /* i/o info: pipes etc */ unsigned in, out; @@ -253,4 +254,6 @@ extern void usbnet_link_change(struct usbnet *, bool, bool); extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags); extern void usbnet_status_stop(struct usbnet *dev); +extern void usbnet_update_max_qlen(struct usbnet *dev); + #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.2.3 From bf640876e21fe603f7f52b0c27d66b7716da0384 Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Fri, 26 Jul 2013 15:04:07 +0200 Subject: KVM: s390: Make KVM_HVA_ERR_BAD usable on s390 Current common code uses PAGE_OFFSET to indicate a bad host virtual address. As this check won't work on architectures that don't map kernel and user memory into the same address space (e.g. s390), such architectures can now provide their own KVM_HVA_ERR_BAD defines. Signed-off-by: Dominik Dingel Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c11c7686ae5f..ca645a01d37a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -85,6 +85,12 @@ static inline bool is_noslot_pfn(pfn_t pfn) return pfn == KVM_PFN_NOSLOT; } +/* + * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) + * provide own defines and kvm_is_error_hva + */ +#ifndef KVM_HVA_ERR_BAD + #define KVM_HVA_ERR_BAD (PAGE_OFFSET) #define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE) @@ -93,6 +99,8 @@ static inline bool kvm_is_error_hva(unsigned long addr) return addr >= PAGE_OFFSET; } +#endif + #define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) static inline bool is_error_page(struct page *page) -- cgit v1.2.3 From fe6f700d6cbb7e8a61711e325f53d9c9e0a42a4c Mon Sep 17 00:00:00 2001 From: Yevgeny Petrilin Date: Sun, 28 Jul 2013 18:54:21 +0300 Subject: net/mlx4_core: Respond to operation request by firmware This commit adds new firmware command and new firmware event. The firmware raises the MLX4_EVENT_TYPE_OP_REQUIRED event in order to signal the driver it needs to perform an administrative operation throughout the MLX4_CMD_GET_OP_REQ command. At the moment the supported operation is adding/removing multicast entries which are used by the firmware for handling NCSI traffic in B0 steering mode. Also, had to swap the order of mlx4_init_mcg_table() and mlx4_init_eq_table() to make sure that driver will get events only after resources are initialized to handle it. Signed-off-by: Yevgeny Petrilin Signed-off-by: Jack Morgenstein Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index bb1c8096a7eb..cd1fdf75103b 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -69,6 +69,7 @@ enum { MLX4_CMD_SET_ICM_SIZE = 0xffd, /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, + MLX4_CMD_GET_OP_REQ = 0x59, /* TPT commands */ MLX4_CMD_SW2HW_MPT = 0xd, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 52c23a892bab..6aebdfe0ed8b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -207,6 +207,7 @@ enum mlx4_event { MLX4_EVENT_TYPE_CMD = 0x0a, MLX4_EVENT_TYPE_VEP_UPDATE = 0x19, MLX4_EVENT_TYPE_COMM_CHANNEL = 0x18, + MLX4_EVENT_TYPE_OP_REQUIRED = 0x1a, MLX4_EVENT_TYPE_FATAL_WARNING = 0x1b, MLX4_EVENT_TYPE_FLR_EVENT = 0x1c, MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d, -- cgit v1.2.3 From 410aee70f06da60dd8f78c3ec3346cc74c9bed46 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 15:27:26 +0300 Subject: usb: phy: protect against NULL phy pointers In order to decrease the amount of work done by PHY users, allow NULL phy pointers to be passed. Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 44036808bf0f..6c0b1c513db7 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -142,7 +142,7 @@ extern void usb_remove_phy(struct usb_phy *); /* helpers for direct access thru low-level io interface */ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) { - if (x->io_ops && x->io_ops->read) + if (x && x->io_ops && x->io_ops->read) return x->io_ops->read(x, reg); return -EINVAL; @@ -150,7 +150,7 @@ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) { - if (x->io_ops && x->io_ops->write) + if (x && x->io_ops && x->io_ops->write) return x->io_ops->write(x, val, reg); return -EINVAL; @@ -159,7 +159,7 @@ static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) static inline int usb_phy_init(struct usb_phy *x) { - if (x->init) + if (x && x->init) return x->init(x); return 0; @@ -168,14 +168,14 @@ usb_phy_init(struct usb_phy *x) static inline void usb_phy_shutdown(struct usb_phy *x) { - if (x->shutdown) + if (x && x->shutdown) x->shutdown(x); } static inline int usb_phy_vbus_on(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, true); @@ -184,7 +184,7 @@ usb_phy_vbus_on(struct usb_phy *x) static inline int usb_phy_vbus_off(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, false); @@ -258,7 +258,7 @@ usb_phy_set_power(struct usb_phy *x, unsigned mA) static inline int usb_phy_set_suspend(struct usb_phy *x, int suspend) { - if (x->set_suspend != NULL) + if (x && x->set_suspend != NULL) return x->set_suspend(x, suspend); else return 0; @@ -267,7 +267,7 @@ usb_phy_set_suspend(struct usb_phy *x, int suspend) static inline int usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_connect) + if (x && x->notify_connect) return x->notify_connect(x, speed); else return 0; @@ -276,7 +276,7 @@ usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) static inline int usb_phy_notify_disconnect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_disconnect) + if (x && x->notify_disconnect) return x->notify_disconnect(x, speed); else return 0; -- cgit v1.2.3 From 1494a1f62bf7cf57345e9282c8189fe2a21fab64 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 13:56:45 +0300 Subject: usb: common: introduce of_usb_get_maximum_speed() this helper will be used for controllers which want to work at a lower speed even though they support higher USB transfer rates. One such case is Texas Instruments' AM437x SoC where it uses a USB3 controller without a USB3 PHY, rendering the controller USB2-only. Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index a0ef405368b8..5a7cb9ebf0ef 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -7,16 +7,24 @@ #ifndef __LINUX_USB_OF_H #define __LINUX_USB_OF_H +#include #include #include #if IS_ENABLED(CONFIG_OF) enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np); +enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np); #else static inline enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np) { return USB_DR_MODE_UNKNOWN; } + +static inline enum usb_device_speed +of_usb_get_maximum_speed(struct device_node *np) +{ + return USB_SPEED_UNKNOWN; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) -- cgit v1.2.3 From 5702f75375aa9ecf8ad3431aef3fe6ce8c8dbd15 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 17 Jul 2013 11:09:49 +0300 Subject: usb: gadget: udc-core: move sysfs_notify() to a workqueue usb_gadget_set_state() will call sysfs_notify() which might sleep. Some users might want to call usb_gadget_set_state() from the very IRQ handler which actually changes the gadget state. Instead of having every UDC driver add their own workqueue for such a simple notification, we're adding it generically to our struct usb_gadget, so the details are hidden from all UDC drivers. Acked-by: Alan Stern Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index f1b0dca60f12..942ef5e053bf 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -22,6 +22,7 @@ #include #include #include +#include #include struct usb_ep; @@ -475,6 +476,7 @@ struct usb_gadget_ops { /** * struct usb_gadget - represents a usb slave device + * @work: (internal use) Workqueue to be used for sysfs_notify() * @ops: Function pointers used to access hardware-specific operations. * @ep0: Endpoint zero, used when reading or writing responses to * driver setup() requests @@ -520,6 +522,7 @@ struct usb_gadget_ops { * device is acting as a B-Peripheral (so is_a_peripheral is false). */ struct usb_gadget { + struct work_struct work; /* readonly to gadget driver */ const struct usb_gadget_ops *ops; struct usb_ep *ep0; @@ -538,6 +541,7 @@ struct usb_gadget { unsigned out_epnum; unsigned in_epnum; }; +#define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) static inline void set_gadget_data(struct usb_gadget *gadget, void *data) { dev_set_drvdata(&gadget->dev, data); } -- cgit v1.2.3 From f5b8c8b6d3b4697f28b818d8784e3e4b2a290022 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Wed, 17 Jul 2013 10:37:49 +0300 Subject: usb: tegra: Use regulators instead of GPIOs for USB PHY VBUS The tegra ehci driver has enabled USB vbus regulators directly using GPIOs and the device tree attribute nvidia,vbus-gpio. This is ugly and causes error messages on boot when both the regulator driver and the ehci driver want access to the same GPIO. After this patch, usb vbus regulators for tegra usb phy devices are specified with the device tree attribute vbus-supply = <&x> where x is a regulator defined in the device tree. The old nvidia,vbus-gpio property is no longer supported. Signed-off-by: Mikko Perttunen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d2ca919a5b73..2b5fa947980a 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -55,6 +55,7 @@ struct tegra_usb_phy { struct clk *clk; struct clk *pll_u; struct clk *pad_clk; + struct regulator *vbus; enum tegra_usb_phy_mode mode; void *config; struct usb_phy *ulpi; -- cgit v1.2.3 From 185d0fd570c121c0c3d4527842a097e50e3e7a79 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:01 +0300 Subject: usb: phy: tegra: Remove unnecessary 'dev' field struct usb_phy already has a field for the device pointer, so this unnecessary field can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 2b5fa947980a..c2bc7106aaa8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,7 +60,6 @@ struct tegra_usb_phy { void *config; struct usb_phy *ulpi; struct usb_phy u_phy; - struct device *dev; bool is_legacy_phy; bool is_ulpi_phy; int reset_gpio; -- cgit v1.2.3 From 5fed6828318119656e243c4f0a11955cefc8eebd Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:04 +0300 Subject: ARM: tegra: Remove USB platform data USB-related platform data is not used anymore in the Tegra USB drivers, so remove all of it. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Acked-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/platform_data/tegra_usb.h | 32 -------------------------------- include/linux/usb/tegra_usb_phy.h | 5 ----- 2 files changed, 37 deletions(-) delete mode 100644 include/linux/platform_data/tegra_usb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tegra_usb.h b/include/linux/platform_data/tegra_usb.h deleted file mode 100644 index 66c673fef408..000000000000 --- a/include/linux/platform_data/tegra_usb.h +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef _TEGRA_USB_H_ -#define _TEGRA_USB_H_ - -enum tegra_usb_operating_modes { - TEGRA_USB_DEVICE, - TEGRA_USB_HOST, - TEGRA_USB_OTG, -}; - -struct tegra_ehci_platform_data { - enum tegra_usb_operating_modes operating_mode; - /* power down the phy on bus suspend */ - int power_down_on_bus_suspend; - void *phy_config; - int vbus_gpio; -}; - -#endif /* _TEGRA_USB_H_ */ diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index c2bc7106aaa8..847415313ad2 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -28,11 +28,6 @@ struct tegra_utmip_config { u8 xcvr_lsrslew; }; -struct tegra_ulpi_config { - int reset_gpio; - const char *clk; -}; - enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_FULL = 0, TEGRA_USB_PHY_PORT_SPEED_LOW, -- cgit v1.2.3 From 3b102e8bc0e49d417c7d376af857537080335dbf Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:07 +0300 Subject: usb: phy: tegra: Remove custom PHY locating APIs The Tegra EHCI driver is no longer using these custom functions, so they can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 847415313ad2..a095c98184d0 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,8 +60,6 @@ struct tegra_usb_phy { int reset_gpio; }; -struct usb_phy *tegra_usb_get_phy(struct device_node *dn); - void tegra_usb_phy_preresume(struct usb_phy *phy); void tegra_usb_phy_postresume(struct usb_phy *phy); -- cgit v1.2.3 From 6558d7edbe069df1220b525362d4aa854a65a8bc Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:09 +0300 Subject: usb: phy: tegra: Use DT helpers for dr_mode Use the new of_usb_get_dr_mode helper function for parsing dr_mode from the device tree. Also replace the usage of the custom tegra_usb_phy_mode enum with the standard enum. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index a095c98184d0..d3db274610a1 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -34,12 +34,6 @@ enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_HIGH, }; -enum tegra_usb_phy_mode { - TEGRA_USB_PHY_MODE_DEVICE, - TEGRA_USB_PHY_MODE_HOST, - TEGRA_USB_PHY_MODE_OTG, -}; - struct tegra_xtal_freq; struct tegra_usb_phy { @@ -51,7 +45,7 @@ struct tegra_usb_phy { struct clk *pll_u; struct clk *pad_clk; struct regulator *vbus; - enum tegra_usb_phy_mode mode; + enum usb_dr_mode mode; void *config; struct usb_phy *ulpi; struct usb_phy u_phy; -- cgit v1.2.3 From 49834de234f3cf592c3d242c889ca603db8e7050 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 28 Jul 2013 14:47:02 +0100 Subject: spi: Provide core support for runtime PM during transfers Most SPI drivers that implement runtime PM support use identical code to do so: they acquire a runtime PM lock in prepare_transfer_hardware() and then they release it in unprepare_transfer_hardware(). The variations in this are mostly missing error checking and the choice to use autosuspend. Since these runtime PM calls are normally the only thing in the prepare and unprepare callbacks and the autosuspend API transparently does the right thing on devices with autosuspend disabled factor all of this out into the core with a flag to enable the behaviour. Signed-off-by: Mark Brown Reviewed-by: Stephen Warren Acked-by: Linus Walleij --- include/linux/spi/spi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..bf0204c00053 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -254,6 +254,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @busy: message pump is busy * @running: message pump is running * @rt: whether this queue is set to run as a realtime task + * @auto_runtime_pm: the core should ensure a runtime PM reference is held + * while the hardware is prepared, using the parent + * device for the spidev * @prepare_transfer_hardware: a message will soon arrive from the queue * so the subsystem requests the driver to prepare the transfer hardware * by issuing this call @@ -374,11 +377,13 @@ struct spi_master { bool busy; bool running; bool rt; + bool auto_runtime_pm; int (*prepare_transfer_hardware)(struct spi_master *master); int (*transfer_one_message)(struct spi_master *master, struct spi_message *mesg); int (*unprepare_transfer_hardware)(struct spi_master *master); + /* gpio chip select */ int *cs_gpios; }; -- cgit v1.2.3 From 055560b04a8cd063aea916fd083b7aec02c2adb8 Mon Sep 17 00:00:00 2001 From: Elen Song Date: Mon, 22 Jul 2013 16:30:29 +0800 Subject: serial: at91: distinguish usart and uart Distinguish usart and uart by read ip name register, The usart read name is "USAR", The uart and dbgu read name is "DBGU". Signed-off-by: Elen Song Signed-off-by: Greg Kroah-Hartman --- include/linux/atmel_serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h index fd6833764d72..be201ca2990c 100644 --- a/include/linux/atmel_serial.h +++ b/include/linux/atmel_serial.h @@ -124,4 +124,6 @@ #define ATMEL_US_NER 0x44 /* Number of Errors Register */ #define ATMEL_US_IF 0x4c /* IrDA Filter Register */ +#define ATMEL_US_NAME 0xf0 /* Ip Name */ + #endif -- cgit v1.2.3 From e66c33d579ea566d10e8c8695a7168aae3e02992 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 16:50:28 -0400 Subject: rcu: Add const annotation to char * for RCU tracepoints and functions All the RCU tracepoints and functions that reference char pointers do so with just 'char *' even though they do not modify the contents of the string itself. This will cause warnings if a const char * is used in one of these functions. The RCU tracepoints store the pointer to the string to refer back to them when the trace output is displayed. As this can be minutes, hours or even days later, those strings had better be constant. This change also opens the door to allow the RCU tracepoint strings and their addresses to be exported so that userspace tracing tools can translate the contents of the pointers of the RCU tracepoints. Signed-off-by: Steven Rostedt --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4b14bdc911d7..0c38abbe6e35 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,7 +52,7 @@ extern int rcutorture_runnable; /* for sysctl */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) extern void rcutorture_record_test_transition(void); extern void rcutorture_record_progress(unsigned long vernum); -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, @@ -65,7 +65,7 @@ static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, -- cgit v1.2.3 From 9cf7b244187bba5964d4bf7438946baa2a974466 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 30 Jul 2013 09:09:15 +0300 Subject: usb: of: fix build breakage caused by recent patches commit 052a11d (usb: phy: make PHY driver selection possible by controller drivers) changed the rules on how drivers/usb/phy/of.c would be compiled and failed to update include/linux/usb/of.h accordingly. Because of that, we can fall into situations where of_usb_get_phy_mode() is redefined. In order to fix the error, we update the IS_ENABLED() check in include/linux/usb/of.h to reflect the condition where of.c is built. Reported-by: Stephen Rothwell Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 5a7cb9ebf0ef..8c38aa26b3bb 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -27,7 +27,7 @@ of_usb_get_maximum_speed(struct device_node *np) } #endif -#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np); #else static inline enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np) -- cgit v1.2.3 From a24a4b9f3f7a4cfba3af0e8079e25972b88a5afa Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Tue, 30 Jul 2013 15:30:05 +0800 Subject: include/linux/coda.h: remove useless '#else' '#else' is useless, need remove. Signed-off-by: Chen Gang Signed-off-by: Jiri Kosina --- include/linux/coda.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coda.h b/include/linux/coda.h index cff544f81105..d30209b9cef8 100644 --- a/include/linux/coda.h +++ b/include/linux/coda.h @@ -60,7 +60,6 @@ Mellon the rights to redistribute these changes without encumbrance. #if defined(__linux__) typedef unsigned long long u_quad_t; -#else #endif #include #endif -- cgit v1.2.3 From 1207637304990374231fe4e9aeb527904f4ec1e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Jul 2013 08:30:16 -0400 Subject: workqueue: mark WQ_NON_REENTRANT deprecated dbf2576e37 ("workqueue: make all workqueues non-reentrant") made WQ_NON_REENTRANT no-op but the following patches didn't remove the flag or update the documentation. Let's mark the flag deprecated and update the documentation accordingly. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a0ed78ab54d7..594521ba0d43 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,7 +295,12 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * Documentation/workqueue.txt. */ enum { - WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ + /* + * All wqs are now non-reentrant making the following flag + * meaningless. Will be removed. + */ + WQ_NON_REENTRANT = 1 << 0, /* DEPRECATED */ + WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ -- cgit v1.2.3 From bec68faaf3ba74ed0dcd5dc3a881b30aec542973 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 13 May 2013 14:45:08 -0700 Subject: aio: io_cancel() no longer returns the io_event Originally, io_event() was documented to return the io_event if cancellation succeeded - the io_event wouldn't be delivered via the ring buffer like it normally would. But this isn't what the implementation was actually doing; the only driver implementing cancellation, the usb gadget code, never returned an io_event in its cancel function. And aio_complete() was recently changed to no longer suppress event delivery if the kiocb had been cancelled. This gets rid of the unused io_event argument to kiocb_cancel() and kiocb->ki_cancel(), and changes io_cancel() to return -EINPROGRESS if kiocb->ki_cancel() returned success. Also tweak the refcounting in kiocb_cancel() to make more sense. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Signed-off-by: Benjamin LaHaise --- include/linux/aio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 1bdf965339f9..8c8dd1d84d2e 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -27,7 +27,7 @@ struct kiocb; */ #define KIOCB_CANCELLED ((void *) (~0ULL)) -typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); +typedef int (kiocb_cancel_fn)(struct kiocb *); struct kiocb { atomic_t ki_users; -- cgit v1.2.3 From 73a7075e3f6ec63dc359064eea6fd84f406cf2a5 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 9 May 2013 15:03:42 -0700 Subject: aio: Kill aio_rw_vect_retry() This code doesn't serve any purpose anymore, since the aio retry infrastructure has been removed. This change should be safe because aio_read/write are also used for synchronous IO, and called from do_sync_read()/do_sync_write() - and there's no looping done in the sync case (the read and write syscalls). Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Signed-off-by: Benjamin LaHaise --- include/linux/aio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 8c8dd1d84d2e..7bb766e73968 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -50,11 +50,9 @@ struct kiocb { unsigned short ki_opcode; size_t ki_nbytes; /* copy of iocb->aio_nbytes */ char __user *ki_buf; /* remaining iocb->aio_buf */ - size_t ki_left; /* remaining bytes */ struct iovec ki_inline_vec; /* inline vector */ struct iovec *ki_iovec; unsigned long ki_nr_segs; - unsigned long ki_cur_seg; struct list_head ki_list; /* the aio core uses this * for cancellation */ -- cgit v1.2.3 From 8bc92afcf7f5c598001dd04e62d88f57f6e89e51 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 25 Feb 2013 16:36:27 -0800 Subject: aio: Kill unneeded kiocb members The old aio retry infrastucture needed to save the various arguments to to aio operations. But with the retry infrastructure gone, we can trim struct kiocb quite a bit. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Cc: Theodore Ts'o Signed-off-by: Benjamin LaHaise --- include/linux/aio.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7bb766e73968..b570472355d1 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -36,6 +36,7 @@ struct kiocb { struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; void (*ki_dtor)(struct kiocb *); + void *private; union { void __user *user; @@ -44,15 +45,7 @@ struct kiocb { __u64 ki_user_data; /* user's data for completion */ loff_t ki_pos; - - void *private; - /* State that we remember to be able to restart/retry */ - unsigned short ki_opcode; - size_t ki_nbytes; /* copy of iocb->aio_nbytes */ - char __user *ki_buf; /* remaining iocb->aio_buf */ - struct iovec ki_inline_vec; /* inline vector */ - struct iovec *ki_iovec; - unsigned long ki_nr_segs; + size_t ki_nbytes; /* copy of iocb->aio_nbytes */ struct list_head ki_list; /* the aio core uses this * for cancellation */ -- cgit v1.2.3 From 57282d8fd744072d6d6f18fa6ebe3cc1149015bf Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 13 May 2013 13:42:52 -0700 Subject: aio: Kill ki_users The kiocb refcount is only needed for cancellation - to ensure a kiocb isn't freed while a ki_cancel callback is running. But if we restrict ki_cancel callbacks to not block (which they currently don't), we can simply drop the refcount. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Cc: Theodore Ts'o Signed-off-by: Benjamin LaHaise --- include/linux/aio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index b570472355d1..c4f07ffa1cbb 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -30,8 +30,6 @@ struct kiocb; typedef int (kiocb_cancel_fn)(struct kiocb *); struct kiocb { - atomic_t ki_users; - struct file *ki_filp; struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; @@ -65,7 +63,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_users = ATOMIC_INIT(1), .ki_ctx = NULL, .ki_filp = filp, .ki_obj.tsk = current, @@ -75,7 +72,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) /* prototypes */ #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -extern void aio_put_req(struct kiocb *iocb); extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); @@ -84,7 +80,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr, void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } -static inline void aio_put_req(struct kiocb *iocb) { } static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } -- cgit v1.2.3 From d29c445b635b3a03cf683cafcbae58a4ec1e1125 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 18 Mar 2013 11:09:26 -0700 Subject: aio: Kill ki_dtor sock_aio_dtor() is dead code - and stuff that does need to do cleanup can simply do it before calling aio_complete(). Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Cc: Theodore Ts'o Signed-off-by: Benjamin LaHaise --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index c4f07ffa1cbb..d9c92daa3944 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -33,7 +33,6 @@ struct kiocb { struct file *ki_filp; struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; - void (*ki_dtor)(struct kiocb *); void *private; union { -- cgit v1.2.3 From db446a08c23d5475e6b08c87acca79ebb20f283c Mon Sep 17 00:00:00 2001 From: Benjamin LaHaise Date: Tue, 30 Jul 2013 12:54:40 -0400 Subject: aio: convert the ioctx list to table lookup v3 On Wed, Jun 12, 2013 at 11:14:40AM -0700, Kent Overstreet wrote: > On Mon, Apr 15, 2013 at 02:40:55PM +0300, Octavian Purdila wrote: > > When using a large number of threads performing AIO operations the > > IOCTX list may get a significant number of entries which will cause > > significant overhead. For example, when running this fio script: > > > > rw=randrw; size=256k ;directory=/mnt/fio; ioengine=libaio; iodepth=1 > > blocksize=1024; numjobs=512; thread; loops=100 > > > > on an EXT2 filesystem mounted on top of a ramdisk we can observe up to > > 30% CPU time spent by lookup_ioctx: > > > > 32.51% [guest.kernel] [g] lookup_ioctx > > 9.19% [guest.kernel] [g] __lock_acquire.isra.28 > > 4.40% [guest.kernel] [g] lock_release > > 4.19% [guest.kernel] [g] sched_clock_local > > 3.86% [guest.kernel] [g] local_clock > > 3.68% [guest.kernel] [g] native_sched_clock > > 3.08% [guest.kernel] [g] sched_clock_cpu > > 2.64% [guest.kernel] [g] lock_release_holdtime.part.11 > > 2.60% [guest.kernel] [g] memcpy > > 2.33% [guest.kernel] [g] lock_acquired > > 2.25% [guest.kernel] [g] lock_acquire > > 1.84% [guest.kernel] [g] do_io_submit > > > > This patchs converts the ioctx list to a radix tree. For a performance > > comparison the above FIO script was run on a 2 sockets 8 core > > machine. This are the results (average and %rsd of 10 runs) for the > > original list based implementation and for the radix tree based > > implementation: > > > > cores 1 2 4 8 16 32 > > list 109376 ms 69119 ms 35682 ms 22671 ms 19724 ms 16408 ms > > %rsd 0.69% 1.15% 1.17% 1.21% 1.71% 1.43% > > radix 73651 ms 41748 ms 23028 ms 16766 ms 15232 ms 13787 ms > > %rsd 1.19% 0.98% 0.69% 1.13% 0.72% 0.75% > > % of radix > > relative 66.12% 65.59% 66.63% 72.31% 77.26% 83.66% > > to list > > > > To consider the impact of the patch on the typical case of having > > only one ctx per process the following FIO script was run: > > > > rw=randrw; size=100m ;directory=/mnt/fio; ioengine=libaio; iodepth=1 > > blocksize=1024; numjobs=1; thread; loops=100 > > > > on the same system and the results are the following: > > > > list 58892 ms > > %rsd 0.91% > > radix 59404 ms > > %rsd 0.81% > > % of radix > > relative 100.87% > > to list > > So, I was just doing some benchmarking/profiling to get ready to send > out the aio patches I've got for 3.11 - and it looks like your patch is > causing a ~1.5% throughput regression in my testing :/ ... I've got an alternate approach for fixing this wart in lookup_ioctx()... Instead of using an rbtree, just use the reserved id in the ring buffer header to index an array pointing the ioctx. It's not finished yet, and it needs to be tidied up, but is most of the way there. -ben -- "Thought is the essence of where you are now." -- kmo> And, a rework of Ben's code, but this was entirely his idea kmo> -Kent bcrl> And fix the code to use the right mm_struct in kill_ioctx(), actually free memory. Signed-off-by: Benjamin LaHaise --- include/linux/mm_types.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index fb425aa16c01..da8cf5cc1aa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -322,6 +322,7 @@ struct mm_rss_stat { atomic_long_t count[NR_MM_COUNTERS]; }; +struct kioctx_table; struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -382,8 +383,8 @@ struct mm_struct { struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_AIO - spinlock_t ioctx_lock; - struct hlist_head ioctx_list; + spinlock_t ioctx_lock; + struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MM_OWNER /* -- cgit v1.2.3 From df04b6242a584ab3dcfe89221775085f60ba83dd Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 12 Jul 2013 13:32:02 +0200 Subject: mfd: twl6040: Remove support for legacy (pdata) mode TWL6040 is used only with OMAP4/5 SoCs and they can only boot in in DT mode. The support for pdata/legacy boot can be removed. Add TODO comment to the header file that all pdata struct can be removed in the next merge window (after the sub driver updates are in). Signed-off-by: Peter Ujfalusi Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/twl6040.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index 7e7fbce7a308..6dd8893b2a56 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -185,6 +185,7 @@ #define TWL6040_GPO_MAX 3 +/* TODO: All platform data struct can be removed */ struct twl6040_codec_data { u16 hs_left_step; u16 hs_right_step; -- cgit v1.2.3 From 08ad7b7f542bad5d1476573ddecefc1899da21e4 Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sun, 7 Jul 2013 17:14:22 +0530 Subject: mfd: s2mps11: Remove clocks from regulators list Since these are fixed rate clocks which are registered with common clock framework so remove these from list of regulators which were unnecessarily incrementing the count(S2MPS11_REGULATOR_MAX) of regulators. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/samsung/s2mps11.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 4e94dc65f987..179e10ca095b 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -167,11 +167,8 @@ enum s2mps11_regulators { S2MPS11_BUCK8, S2MPS11_BUCK9, S2MPS11_BUCK10, - S2MPS11_AP_EN32KHZ, - S2MPS11_CP_EN32KHZ, - S2MPS11_BT_EN32KHZ, - S2MPS11_REG_MAX, + S2MPS11_REGULATOR_MAX, }; #define S2MPS11_BUCK_MIN1 600000 @@ -192,6 +189,5 @@ enum s2mps11_regulators { #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ #define S2MPS11_PMIC_EN_SHIFT 6 -#define S2MPS11_REGULATOR_MAX (S2MPS11_REG_MAX - 3) #endif /* __LINUX_MFD_S2MPS11_H */ -- cgit v1.2.3 From efe3126afce32e3100af3029a80701d47e1b6999 Mon Sep 17 00:00:00 2001 From: "Patil, Rachna" Date: Sat, 20 Jul 2013 17:27:35 +0100 Subject: MFD: ti_tscadc: ADC Clock check not required ADC is ideally expected to work at a frequency of 3MHz. The present code had a check, which returned error if the frequency went below the threshold value. But since AM335x supports various working frequencies, this check is not required. Now the code just uses the internal ADC clock divider to set the ADC frequency w.r.t the sys clock. Signed-off-by: Patil, Rachna Signed-off-by: Zubair Lutfullah Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/ti_am335x_tscadc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 8d73fe29796a..71bb41c32a64 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -114,7 +114,6 @@ #define CNTRLREG_TSCENB BIT(7) #define ADC_CLK 3000000 -#define MAX_CLK_DIV 7 #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 -- cgit v1.2.3 From 62480dc8b4bd951057c0712c8547e6c3fa12008a Mon Sep 17 00:00:00 2001 From: Andrea Adami Date: Sun, 21 Jul 2013 01:07:42 +0200 Subject: mfd: mcp: Add missing linux/device.h header Fixes this compilation error: linux/include/linux/mfd/mcp.h:22:16: error: field 'attached_device' has incomplete type linux/include/linux/mfd/mcp.h:48:23: error: field 'drv' has incomplete type Signed-off-by: Andrea Adami Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/mcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mcp.h b/include/linux/mfd/mcp.h index a9e8bd157673..f682953043ba 100644 --- a/include/linux/mfd/mcp.h +++ b/include/linux/mfd/mcp.h @@ -10,6 +10,8 @@ #ifndef MCP_H #define MCP_H +#include + struct mcp_ops; struct mcp { -- cgit v1.2.3 From 38c4faaea4ca71c69584ef71cca8d0735d5361c1 Mon Sep 17 00:00:00 2001 From: Andrea Adami Date: Sun, 21 Jul 2013 01:07:39 +0200 Subject: mfd: ucb1x00: Explicitely include linux/device.h Fixes this compilation error: linux/include/linux/mfd/ucb1x00.h:137:17: error: field 'dev' has incomplete type Signed-off-by: Andrea Adami Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/ucb1x00.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ucb1x00.h b/include/linux/mfd/ucb1x00.h index 28af41756360..88f90cbf8e6a 100644 --- a/include/linux/mfd/ucb1x00.h +++ b/include/linux/mfd/ucb1x00.h @@ -10,6 +10,7 @@ #ifndef UCB1200_H #define UCB1200_H +#include #include #include #include -- cgit v1.2.3 From 66b52b0dc82c5c88d769dc1c7d44cf45d0deb07c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 29 Jul 2013 18:16:49 +0200 Subject: net: add ndo to get id of physical port of the device This patch adds a ndo for getting physical port of the device. Driver which is aware of being virtual function of some physical port should implement this ndo. This is applicable not only for IOV, but for other solutions (NPAR, multichannel) as well. Basically if there is possible to have multiple netdevs on the single hw port. Signed-off-by: Jiri Pirko Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ca60b070ef0..875f869dc38a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -728,6 +728,16 @@ struct netdev_fcoe_hbainfo { }; #endif +#define MAX_PHYS_PORT_ID_LEN 32 + +/* This structure holds a unique identifier to identify the + * physical port used by a netdevice. + */ +struct netdev_phys_port_id { + unsigned char id[MAX_PHYS_PORT_ID_LEN]; + unsigned char id_len; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -932,6 +942,12 @@ struct netdev_fcoe_hbainfo { * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. + * + * int (*ndo_get_phys_port_id)(struct net_device *dev, + * struct netdev_phys_port_id *ppid); + * Called to get ID of physical port of this device. If driver does + * not implement this, it is assumed that the hw is not able to have + * multiple net devices on single physical port. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1060,6 +1076,8 @@ struct net_device_ops { struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); + int (*ndo_get_phys_port_id)(struct net_device *dev, + struct netdev_phys_port_id *ppid); }; /* @@ -2315,6 +2333,8 @@ extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_change_carrier(struct net_device *, bool new_carrier); +extern int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid); extern int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); -- cgit v1.2.3 From 59da381ee2afc806f85becf3aa64ffc952355552 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 31 Jul 2013 06:53:21 +0000 Subject: PCI: move enum pcie_link_width into pci.h pcie_link_width is the enum used to define the link width values for a pcie device. This enum should not be contained solely in pci_hotplug.h, and this patch moves it next to pci_bus_speed in pci.h Signed-off-by: Jacob Keller Tested-by: Phil Schmitt Acked-by: Bjorn Helgaas Signed-off-by: Jeff Kirsher --- include/linux/pci.h | 13 +++++++++++++ include/linux/pci_hotplug.h | 13 ------------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..a0bf22d816cf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -183,6 +183,19 @@ enum pci_bus_flags { PCI_BUS_FLAGS_NO_MMRBC = (__force pci_bus_flags_t) 2, }; +/* These values come from the PCI Express Spec */ +enum pcie_link_width { + PCIE_LNK_WIDTH_RESRV = 0x00, + PCIE_LNK_X1 = 0x01, + PCIE_LNK_X2 = 0x02, + PCIE_LNK_X4 = 0x04, + PCIE_LNK_X8 = 0x08, + PCIE_LNK_X12 = 0x0C, + PCIE_LNK_X16 = 0x10, + PCIE_LNK_X32 = 0x20, + PCIE_LNK_WIDTH_UNKNOWN = 0xFF, +}; + /* Based on the PCI Hotplug Spec, but some values are made up by us */ enum pci_bus_speed { PCI_SPEED_33MHz = 0x00, diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8db71dcd6337..64e61e05d9a0 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -28,19 +28,6 @@ #ifndef _PCI_HOTPLUG_H #define _PCI_HOTPLUG_H -/* These values come from the PCI Express Spec */ -enum pcie_link_width { - PCIE_LNK_WIDTH_RESRV = 0x00, - PCIE_LNK_X1 = 0x01, - PCIE_LNK_X2 = 0x02, - PCIE_LNK_X4 = 0x04, - PCIE_LNK_X8 = 0x08, - PCIE_LNK_X12 = 0x0C, - PCIE_LNK_X16 = 0x10, - PCIE_LNK_X32 = 0x20, - PCIE_LNK_WIDTH_UNKNOWN = 0xFF, -}; - /** * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use * @owner: The module owner of this structure -- cgit v1.2.3 From 81377c8d3563e7aec5c8baaaacacb48034f430a0 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 31 Jul 2013 06:53:26 +0000 Subject: PCI: Add function to obtain minimum link width and speed A PCI Express device can potentially report a link width and speed which it will not properly fulfill due to being plugged into a slower link higher in the chain. This function walks up the PCI bus chain and calculates the minimum link width and speed of this entire chain. This can be useful to enable a device to determine if it has enough bandwidth for optimum functionality. Signed-off-by: Jacob Keller Tested-by: Phil Schmitt Acked-by: Bjorn Helgaas Signed-off-by: Jeff Kirsher --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a0bf22d816cf..2edbee64aeba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -934,6 +934,8 @@ int pcie_get_readrq(struct pci_dev *dev); int pcie_set_readrq(struct pci_dev *dev, int rq); int pcie_get_mps(struct pci_dev *dev); int pcie_set_mps(struct pci_dev *dev, int mps); +int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, + enum pcie_link_width *width); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); -- cgit v1.2.3 From ddf64a3c03d4d68431146a0f1622844cc6cb6c22 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Mon, 15 Jul 2013 19:10:10 +0200 Subject: HID: usbhid: make usbhid_set_leds() static usbhid_set_leds() is only used inside of usbhid/hid-core.c so no need to export it. Signed-off-by: David Herrmann Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0c48991b0402..b8058c5c5594 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -989,7 +989,6 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size, u32 usbhid_lookup_quirk(const u16 idVendor, const u16 idProduct); int usbhid_quirks_init(char **quirks_param); void usbhid_quirks_exit(void); -void usbhid_set_leds(struct hid_device *hid); #ifdef CONFIG_HID_PID int hid_pidff_init(struct hid_device *hid); -- cgit v1.2.3 From 4bdfb2729c3a396fe7400c9332c49aee2b971bd8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:00:53 +0100 Subject: regulator: core: Add missing stub for regulator_get_exclusive() Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..60da4a62c402 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -211,6 +211,13 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +regulator_get_exclusive(struct device *dev, const char *id) +{ + return NULL; +} + + static inline struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id) { -- cgit v1.2.3 From de1dd9fd2156874b45803299b3b27e65d5defdd9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:42:42 +0100 Subject: regulator: core: Provide hints to the core about optional supplies While the majority of supplies on devices are mandatory and can't be physically omitted for electrical reasons some devices do have optional supplies and need to know if they are missing, MMC being the most common of these. Currently the core accurately reports all errors when regulators are requested since it does not know if the supply is one that must be provided even if by a regulator software does not know about or if it is one that may genuinely be disconnected. In order to allow this behaviour to be changed and stub regulators to be provided in the former case add a new regulator request function regulator_get_optional() which provides a hint to the core that the regulator may genuinely not be connected. Currently the implementation is identical to the current behaviour, future patches will add support in the core for returning stub regulators in the case where normal regulator_get() fails and the board has requested it. Signed-off-by: Mark Brown Acked-by: Chris Ball --- include/linux/regulator/consumer.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 60da4a62c402..e2bac6db4abc 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,10 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check regulator_get_optional(struct device *dev, + const char *id); +struct regulator *__must_check devm_regulator_get_optional(struct device *dev, + const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -211,15 +215,27 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +devm_regulator_get(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id) { return NULL; } +static inline struct regulator *__must_check +regulator_get_optional(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check -devm_regulator_get(struct device *dev, const char *id) +devm_regulator_get_optional(struct device *dev, const char *id) { return NULL; } -- cgit v1.2.3 From 50c9d75b6f01a337aab728511bc1d2a0a3d7b800 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Mon, 15 Jul 2013 19:10:12 +0200 Subject: HID: input: generic hidinput_input_event handler The hidinput_input_event() callback converts input events written from userspace into HID reports and sends them to the device. We currently implement this in every HID transport driver, even though most of them do the same. This provides a generic hidinput_input_event() implementation which is mostly copied from usbhid. It uses a delayed worker to allow multiple LED events to be collected into a single output event. We use the custom ->request() transport driver callback to allow drivers to adjust the outgoing report and handle the request asynchronously. If no custom ->request() callback is available, we fall back to the generic raw output report handler (which is synchronous). Drivers can still provide custom hidinput_input_event() handlers (see logitech-dj) if the generic implementation doesn't fit their needs. Signed-off-by: David Herrmann Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b8058c5c5594..ea4b828cb9cd 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -456,6 +456,7 @@ struct hid_device { /* device report descriptor */ enum hid_type type; /* device type (mouse, kbd, ...) */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; + struct work_struct led_work; /* delayed LED worker */ struct semaphore driver_lock; /* protects the current driver, except during input */ struct semaphore driver_input_lock; /* protects the current driver */ -- cgit v1.2.3 From 3d7d248cf484fe37595698e0ca31a9bcecc85a42 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 13 Jun 2013 09:50:35 +0200 Subject: HID: i2c-hid: add DT bindings Add device tree based support for HID over I2C devices. Tested on an Odroid-X board with a Synaptics touchpad. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/i2c/i2c-hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c/i2c-hid.h b/include/linux/i2c/i2c-hid.h index 60e411d764d4..7aa901d92058 100644 --- a/include/linux/i2c/i2c-hid.h +++ b/include/linux/i2c/i2c-hid.h @@ -19,7 +19,8 @@ * @hid_descriptor_address: i2c register where the HID descriptor is stored. * * Note that it is the responsibility of the platform driver (or the acpi 5.0 - * driver) to setup the irq related to the gpio in the struct i2c_board_info. + * driver, or the flattened device tree) to setup the irq related to the gpio in + * the struct i2c_board_info. * The platform driver should also setup the gpio according to the device: * * A typical example is the following: -- cgit v1.2.3 From 6f4b7e632d78c2d91502211c430722cc66428492 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 16:18:36 +0800 Subject: cgroup: more naming cleanups Constantly use @cset for css_set variables and use @cgrp as cgroup variables. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 297462b9f41a..00a7e07a1567 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -394,8 +394,8 @@ struct cgroup_map_cb { /* cftype->flags */ enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cg */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cg */ + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ }; @@ -513,7 +513,7 @@ struct cftype_set { }; struct cgroup_scanner { - struct cgroup *cg; + struct cgroup *cgrp; int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); -- cgit v1.2.3 From 4e96ee8e981b5140a2bcc5fff0d5c0eef39a62ee Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:50:50 +0800 Subject: cgroup: convert cgroup_ida to cgroup_idr This enables us to lookup a cgroup by its id. v4: - add a comment for idr_remove() in cgroup_offline_fn(). v3: - on success, idr_alloc() returns the id but not 0, so fix the BUG_ON() in cgroup_init(). - pass the right value to idr_alloc() so that the id for dummy cgroup is 0. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 00a7e07a1567..cca570e188fb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,7 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* ida allocated in-hierarchy ID */ + int id; /* idr allocated in-hierarchy ID */ /* * We link our 'sibling' struct into our parent's 'children'. @@ -322,7 +322,7 @@ struct cgroupfs_root { unsigned long flags; /* IDs for cgroups in this hierarchy */ - struct ida cgroup_ida; + struct idr cgroup_idr; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; -- cgit v1.2.3 From b414dc09a31d41d696093a4cce9fb2853a5ecd4e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:06 +0800 Subject: cgroup: document how cgroup IDs are assigned As cgroup id has been used in netprio cgroup and will be used in memcg, it's important to make it clear how a cgroup id is allocated. For example, in netprio cgroup, the id is used as index of anarray. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cca570e188fb..4dfcd0e1b73e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,13 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* idr allocated in-hierarchy ID */ + /* + * idr allocated in-hierarchy ID. + * + * The ID of the root cgroup is always 0, and a new cgroup + * will be assigned with a smallest available ID. + */ + int id; /* * We link our 'sibling' struct into our parent's 'children'. -- cgit v1.2.3 From e14880f7bb7e0dc0933af304998371dd543ceb40 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:31 +0800 Subject: cgroup: implement cgroup_from_id() This will be used as a replacement for css_lookup(). There's a difference with cgroup id and css id. cgroup id starts with 0, while css id starts with 1. v4: - also check if cggroup_mutex is held. - make it an inline function. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4dfcd0e1b73e..bbf4d89b56a8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -720,6 +720,24 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } +/** + * cgroup_from_id - lookup cgroup by id + * @ss: cgroup subsys to be looked into + * @id: the cgroup id + * + * Returns the cgroup if there's valid one with @id, otherwise returns NULL. + * Should be called under rcu_read_lock(). + */ +static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) +{ +#ifdef CONFIG_PROVE_RCU + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&cgroup_mutex), + "cgroup_from_id() needs proper protection"); +#endif + return idr_find(&ss->root->cgroup_idr, id); +} + struct cgroup *cgroup_next_sibling(struct cgroup *pos); /** -- cgit v1.2.3 From d6b47b122473885abc882e337ac2d321bbcfb378 Mon Sep 17 00:00:00 2001 From: Ben Guthro Date: Tue, 30 Jul 2013 08:24:52 -0400 Subject: ACPI / sleep: Introduce acpi_os_prepare_extended_sleep() for extended sleep path Like acpi_os_prepare_sleep(), register a callback for use in systems like tboot, and xen, which have system specific requirements outside of ACPICA. This mirrors the functionality in acpi_os_prepare_sleep(), called from acpi_hw_sleep() Signed-off-by: Ben Guthro Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 353ba256f368..a5db4aeefa36 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -481,6 +481,13 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); + +void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, + u32 val_a, u32 val_b)); + +acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, + u32 val_a, u32 val_b); + #ifdef CONFIG_X86 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else -- cgit v1.2.3 From 312a0c16c1fa9dd7cb5af413cf73b2fe2806c962 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:08 +0200 Subject: netfilter: nf_conntrack: constify sk_buff argument to nf_ct_attach() Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index de70f7b45b68..f4bbf2cd22d8 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -314,8 +314,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; -extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; +extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; struct nf_conn; -- cgit v1.2.3 From 2d89c68ac78ae432038ef23371d2fa949d725d43 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:10 +0200 Subject: netfilter: nf_nat: change sequence number adjustments to 32 bits Using 16 bits is too small, when many adjustments happen the offsets might overflow and break the connection. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f4bbf2cd22d8..655d5d198d49 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -330,7 +330,7 @@ extern struct nfq_ct_hook __rcu *nfq_ct_hook; struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off); + u32 ctinfo, s32 off); }; extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; #else -- cgit v1.2.3 From 8fe120b5a665fc869c23f86e4964b801f6e53486 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 31 Jul 2013 19:00:32 +0200 Subject: ASoC: omap-abe-twl6040: Remove support for pdata (legacy boot) Just recently OMAP4 legacy boot support has been removed. No reason to keep the code used by the legacy boot (pdata based) since neither OMAP4 or OMAP5 can boot in this mode. Signed-off-by: Peter Ujfalusi Signed-off-by: Mark Brown --- include/linux/platform_data/omap-abe-twl6040.h | 49 -------------------------- 1 file changed, 49 deletions(-) delete mode 100644 include/linux/platform_data/omap-abe-twl6040.h (limited to 'include/linux') diff --git a/include/linux/platform_data/omap-abe-twl6040.h b/include/linux/platform_data/omap-abe-twl6040.h deleted file mode 100644 index 5d298ac10fc2..000000000000 --- a/include/linux/platform_data/omap-abe-twl6040.h +++ /dev/null @@ -1,49 +0,0 @@ -/** - * omap-abe-twl6040.h - ASoC machine driver OMAP4+ devices, header. - * - * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com - * All rights reserved. - * - * Author: Peter Ujfalusi - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - */ - -#ifndef _OMAP_ABE_TWL6040_H_ -#define _OMAP_ABE_TWL6040_H_ - -/* To select if only one channel is connected in a stereo port */ -#define ABE_TWL6040_LEFT (1 << 0) -#define ABE_TWL6040_RIGHT (1 << 1) - -struct omap_abe_twl6040_data { - char *card_name; - /* Feature flags for connected audio pins */ - u8 has_hs; - u8 has_hf; - bool has_ep; - u8 has_aux; - u8 has_vibra; - bool has_dmic; - bool has_hsmic; - bool has_mainmic; - bool has_submic; - u8 has_afm; - /* Other features */ - bool jack_detection; /* board can detect jack events */ - int mclk_freq; /* MCLK frequency speed for twl6040 */ -}; - -#endif /* _OMAP_ABE_TWL6040_H_ */ -- cgit v1.2.3 From c0155b2da4cd6583b1b729451249ca346e1c05a2 Mon Sep 17 00:00:00 2001 From: Dmitry Popov Date: Wed, 31 Jul 2013 13:39:45 +0400 Subject: tcp: Remove unused tcpct declarations and comments Remove declaration, 4 defines and confusing comment that are no longer used since 1a2c6181c4 ("tcp: Remove TCPCT"). Signed-off-by: Dmitry Popov Acked-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9640803a17a7..d68633452d9b 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -107,7 +107,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) * only four options will fit in a standard TCP header */ #define TCP_NUM_SACKS 4 -struct tcp_cookie_values; struct tcp_request_sock_ops; struct tcp_request_sock { -- cgit v1.2.3 From c34a761231b56dea4bd205cb9c29ffe37475d232 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Jul 2013 16:11:15 -0700 Subject: net: skb_orphan() changes It is illegal to set skb->sk without corresponding destructor. Its therefore safe for skb_orphan() to not clear skb->sk if skb->destructor is not set. Also avoid clearing skb->destructor if already NULL. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5afefa01a13c..a95547adff25 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1805,10 +1805,11 @@ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) */ static inline void skb_orphan(struct sk_buff *skb) { - if (skb->destructor) + if (skb->destructor) { skb->destructor(skb); - skb->destructor = NULL; - skb->sk = NULL; + skb->destructor = NULL; + skb->sk = NULL; + } } /** -- cgit v1.2.3 From 674349f365ce7ac2b826edc619907a19c7136822 Mon Sep 17 00:00:00 2001 From: Andreas Robinson Date: Thu, 1 Aug 2013 10:55:34 +1000 Subject: modules: add support for soft module dependencies Additional and optional dependencies not found while building the kernel and modules, can now be declared explicitly. Signed-off-by: Andreas Robinson Acked-by: Herbert Xu Signed-off-by: Rusty Russell Signed-off-by: Herbert Xu --- include/linux/module.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 46f1ea01e6f6..504035f3ece1 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -97,6 +97,11 @@ extern const struct gtype##_id __mod_##gtype##_table \ /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) +/* Soft module dependencies. See man modprobe.d for details. + * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") + */ +#define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) + /* * The following license idents are currently accepted as indicating free * software modules -- cgit v1.2.3 From 90efa75f7ab0be5677f0cca155dbf0b39eacdd03 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:56:30 +0400 Subject: serial: sccnxp: Using CLK API for getting UART clock This patch removes "frequency" parameter from SCCNXP platform_data and uses CLK API for getting clock. If CLK ommited, default IC frequency will be used instead. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index bdc510d03245..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -60,7 +60,6 @@ * }; * * static struct sccnxp_pdata sc2892_info = { - * .frequency = 3686400, * .mctrl_cfg[0] = MCTRL_SIG(DIR_OP, LINE_OP0), * .mctrl_cfg[1] = MCTRL_SIG(DIR_OP, LINE_OP1), * }; @@ -78,8 +77,6 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { - /* Frequency (extrenal clock or crystal) */ - int frequency; /* Shift for A0 line */ const u8 reg_shift; /* Modem control lines configuration */ -- cgit v1.2.3 From 85c996907473e4ef824774b97b26499adf66521f Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:55:45 +0400 Subject: serial: sccnxp: Add DT support Add DT support to the SCCNCP serial driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index af0c8c3b89ae..98373d6add27 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - const u8 reg_shift; + u32 reg_shift; /* Modem control lines configuration */ - const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - const unsigned int poll_time_us; + u32 poll_time_us; }; #endif -- cgit v1.2.3 From dcb7a6ce0a08012a17cca34711a02017abed554b Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Fri, 26 Jul 2013 17:02:29 -0700 Subject: ieee80211: add definition for interworking support IEEE802.11u interworking support is advertised via extended capabilities IE bit 31. This is 7th bit of 4th byte of extended capabilities. Signed-off-by: Avinash Patil Signed-off-by: Bing Zhao Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b0dc87a2a376..22c909413d32 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1860,6 +1860,11 @@ enum ieee80211_tdls_actioncode { WLAN_TDLS_DISCOVERY_REQUEST = 10, }; +/* Interworking capabilities are set in 7th bit of 4th byte of the + * @WLAN_EID_EXT_CAPABILITY information element + */ +#define WLAN_EXT_CAPA4_INTERWORKING_ENABLED BIT(7) + /* * TDLS capabililites to be enabled in the 5th byte of the * @WLAN_EID_EXT_CAPABILITY information element -- cgit v1.2.3 From 9e2bc79bce58a1ce0005015c9351b3bcaaa02e5c Mon Sep 17 00:00:00 2001 From: Fred Zhou Date: Thu, 1 Aug 2013 14:16:28 +0800 Subject: ieee80211: add definition for 802.11ac information elements Add element IDs for Extended BSS Load, VHT TX Power Envelope, AID, and Quiet Channel. Signed-off-by: Fred Zhou Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 22c909413d32..b3ce299782af 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1709,6 +1709,10 @@ enum ieee80211_eid { WLAN_EID_OPMODE_NOTIF = 199, WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, + WLAN_EID_EXTENDED_BSS_LOAD = 193, + WLAN_EID_VHT_TX_POWER_ENVELOPE = 195, + WLAN_EID_AID = 197, + WLAN_EID_QUIET_CHANNEL = 198, /* 802.11ad */ WLAN_EID_NON_TX_BSSID_CAP = 83, -- cgit v1.2.3 From 376c7311bdb6efea3322310333576a04d73fbe4c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Aug 2013 11:43:08 -0700 Subject: net: add a temporary sanity check in skb_orphan() David suggested to add a BUG_ON() to catch if some layer sets skb->sk pointer without a corresponding destructor. As skb can sit in a queue, it's mandatory to make sure the socket cannot disappear, and it's usually done by taking a reference on the socket, then releasing it from the skb destructor. This patch is a follow-up to commit c34a761231b5 ("net: skb_orphan() changes") and will be reverted after catching all possible offenders if any. Suggested-by: David Miller Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a95547adff25..d48de687c21f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1809,6 +1809,8 @@ static inline void skb_orphan(struct sk_buff *skb) skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; + } else { + BUG_ON(skb->sk); } } -- cgit v1.2.3 From cfc25993e81f3fa68481d062be634d33184d5eae Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Wed, 29 May 2013 11:29:07 +0200 Subject: Drivers: hv: remove HV_DRV_VERSION Remove HV_DRV_VERSION, it has no meaning for upstream drivers. Initially it was supposed to show the "Linux Integration Services" version, now it is not in sync anymore with the out-of-tree drivers available from the MSFT website. The only place where a version string is still required is the KVP command "IntegrationServicesVersion" which is handled by tools/hv/hv_kvp_daemon.c. To satisfy such KVP request from the host pass the current string to the daemon during KVP userland registration. Signed-off-by: Olaf Hering Acked-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 49949079cf47..a3b8b2e2d244 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -463,27 +463,6 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, *read = dsize - *write; } - -/* - * We use the same version numbering for all Hyper-V modules. - * - * Definition of versioning is as follows; - * - * Major Number Changes for these scenarios; - * 1. When a new version of Windows Hyper-V - * is released. - * 2. A Major change has occurred in the - * Linux IC's. - * (For example the merge for the first time - * into the kernel) Every time the Major Number - * changes, the Revision number is reset to 0. - * Minor Number Changes when new functionality is added - * to the Linux IC's that is not a bug fix. - * - * 3.1 - Added completed hv_utils driver. Shutdown/Heartbeat/Timesync - */ -#define HV_DRV_VERSION "3.1" - /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. -- cgit v1.2.3 From 461a8ecb2d76fb6f3ac1a90eb886697db869d387 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Aug 2013 15:25:19 +0800 Subject: Revert "serial: sccnxp: Add DT support" This reverts commit 85c996907473e4ef824774b97b26499adf66521f. Alexander wishes to remove this patch as it is incorrect. Reported-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index 98373d6add27..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - u32 reg_shift; + const u8 reg_shift; /* Modem control lines configuration */ - u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - u32 poll_time_us; + const unsigned int poll_time_us; }; #endif -- cgit v1.2.3 From b6aa23ccaea1548cfb404b41129717f13443bccf Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 1 Aug 2013 16:08:57 -0600 Subject: spi: fix SPI_BIT_MASK so it always fits into 32-bits On a 64-bit platform, ~0UL fills 64-bits, which causes SPI_BIT_MASK(32) not to fit into 32 bits. This causes a warning when the result is assigned to a 32-bit variable. Use ~0U instead to prevent this. This fixes: drivers/spi/spi-gpio.c: In function 'spi_gpio_probe': drivers/spi/spi-gpio.c:446:2: warning: large integer implicitly truncated to unsigned type [-Woverflow] Reported-by: kbuild test robot Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..c920c2f4dad5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -309,7 +309,7 @@ struct spi_master { /* bitmask of supported bits_per_word for transfers */ u32 bits_per_word_mask; #define SPI_BPW_MASK(bits) BIT((bits) - 1) -#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) +#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0U : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) /* other constraints relevant to this driver */ -- cgit v1.2.3 From abe4c51afda02423c81da6f1eaaa50b733f1ecc2 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 2 Aug 2013 12:59:44 +0200 Subject: regulators: max8660: add DT bindings This patch adds devicetree bindings for max8660, along with some documentation. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/linux/regulator/max8660.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/max8660.h b/include/linux/regulator/max8660.h index 9936763621c7..f8a6a4844864 100644 --- a/include/linux/regulator/max8660.h +++ b/include/linux/regulator/max8660.h @@ -39,7 +39,7 @@ enum { */ struct max8660_subdev_data { int id; - char *name; + const char *name; struct regulator_init_data *platform_data; }; -- cgit v1.2.3 From 574e2af7c0af3273836def5e66f236521bb433c9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 1 Aug 2013 16:17:48 -0700 Subject: include: Convert ethernet mac address declarations to use ETH_ALEN It's convenient to have ethernet mac addresses use ETH_ALEN to be able to grep for them a bit easier and also to ensure that the addresses are __aligned(2). Add #include as necessary. Signed-off-by: Joe Perches Acked-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- include/linux/dm9000.h | 4 ++- include/linux/fs_enet_pd.h | 3 ++- include/linux/ieee80211.h | 59 +++++++++++++++++++++++---------------------- include/linux/mlx4/device.h | 11 +++++---- include/linux/mlx4/qp.h | 5 ++-- include/linux/mv643xx_eth.h | 3 ++- include/linux/sh_eth.h | 3 ++- include/linux/smsc911x.h | 3 ++- include/linux/uwb/spec.h | 5 ++-- 9 files changed, 53 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm9000.h b/include/linux/dm9000.h index 96e87693d933..841925fbfe8a 100644 --- a/include/linux/dm9000.h +++ b/include/linux/dm9000.h @@ -14,6 +14,8 @@ #ifndef __DM9000_PLATFORM_DATA #define __DM9000_PLATFORM_DATA __FILE__ +#include + /* IO control flags */ #define DM9000_PLATF_8BITONLY (0x0001) @@ -27,7 +29,7 @@ struct dm9000_plat_data { unsigned int flags; - unsigned char dev_addr[6]; + unsigned char dev_addr[ETH_ALEN]; /* allow replacement IO routines */ diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 51b793466ff3..343d82a54468 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -18,6 +18,7 @@ #include #include +#include #include #define FS_ENET_NAME "fs_enet" @@ -135,7 +136,7 @@ struct fs_platform_info { const struct fs_mii_bus_info *bus_info; int rx_ring, tx_ring; /* number of buffers on rx */ - __u8 macaddr[6]; /* mac address */ + __u8 macaddr[ETH_ALEN]; /* mac address */ int rx_copybreak; /* limit we copy small frames */ int use_napi; /* use NAPI */ int napi_weight; /* NAPI weight */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b0dc87a2a376..4e101af9c1ff 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -16,6 +16,7 @@ #define LINUX_IEEE80211_H #include +#include #include /* @@ -209,28 +210,28 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; - u8 addr4[6]; + u8 addr4[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; __le16 qos_ctrl; } __packed __aligned(2); @@ -608,8 +609,8 @@ struct ieee80211s_hdr { u8 flags; u8 ttl; __le32 seqnum; - u8 eaddr1[6]; - u8 eaddr2[6]; + u8 eaddr1[ETH_ALEN]; + u8 eaddr2[ETH_ALEN]; } __packed __aligned(2); /* Mesh flags */ @@ -758,7 +759,7 @@ struct ieee80211_rann_ie { u8 rann_flags; u8 rann_hopcount; u8 rann_ttl; - u8 rann_addr[6]; + u8 rann_addr[ETH_ALEN]; __le32 rann_seq; __le32 rann_interval; __le32 rann_metric; @@ -802,9 +803,9 @@ enum ieee80211_vht_opmode_bits { struct ieee80211_mgmt { __le16 frame_control; __le16 duration; - u8 da[6]; - u8 sa[6]; - u8 bssid[6]; + u8 da[ETH_ALEN]; + u8 sa[ETH_ALEN]; + u8 bssid[ETH_ALEN]; __le16 seq_ctrl; union { struct { @@ -833,7 +834,7 @@ struct ieee80211_mgmt { struct { __le16 capab_info; __le16 listen_interval; - u8 current_ap[6]; + u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ u8 variable[0]; } __packed reassoc_req; @@ -966,21 +967,21 @@ struct ieee80211_vendor_ie { struct ieee80211_rts { __le16 frame_control; __le16 duration; - u8 ra[6]; - u8 ta[6]; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; - u8 ra[6]; + u8 ra[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; - u8 bssid[6]; - u8 ta[6]; + u8 bssid[ETH_ALEN]; + u8 ta[ETH_ALEN]; } __packed __aligned(2); /* TDLS */ @@ -989,14 +990,14 @@ struct ieee80211_pspoll { struct ieee80211_tdls_lnkie { u8 ie_type; /* Link Identifier IE */ u8 ie_len; - u8 bssid[6]; - u8 init_sta[6]; - u8 resp_sta[6]; + u8 bssid[ETH_ALEN]; + u8 init_sta[ETH_ALEN]; + u8 resp_sta[ETH_ALEN]; } __packed; struct ieee80211_tdls_data { - u8 da[6]; - u8 sa[6]; + u8 da[ETH_ALEN]; + u8 sa[ETH_ALEN]; __be16 ether_type; u8 payload_type; u8 category; @@ -1090,8 +1091,8 @@ struct ieee80211_p2p_noa_attr { struct ieee80211_bar { __le16 frame_control; __le16 duration; - __u8 ra[6]; - __u8 ta[6]; + __u8 ra[ETH_ALEN]; + __u8 ta[ETH_ALEN]; __le16 control; __le16 start_seq_num; } __packed; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6aebdfe0ed8b..09ef2f448a00 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -33,6 +33,7 @@ #ifndef MLX4_DEVICE_H #define MLX4_DEVICE_H +#include #include #include #include @@ -620,7 +621,7 @@ struct mlx4_eth_av { u8 dgid[16]; u32 reserved4[2]; __be16 vlan; - u8 mac[6]; + u8 mac[ETH_ALEN]; }; union mlx4_ext_av { @@ -914,10 +915,10 @@ enum mlx4_net_trans_promisc_mode { }; struct mlx4_spec_eth { - u8 dst_mac[6]; - u8 dst_mac_msk[6]; - u8 src_mac[6]; - u8 src_mac_msk[6]; + u8 dst_mac[ETH_ALEN]; + u8 dst_mac_msk[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + u8 src_mac_msk[ETH_ALEN]; u8 ether_type_enable; __be16 ether_type; __be16 vlan_id_msk; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 262deac02c9e..6d351473c292 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -34,6 +34,7 @@ #define MLX4_QP_H #include +#include #include @@ -143,7 +144,7 @@ struct mlx4_qp_path { u8 feup; u8 fvl_rx; u8 reserved4[2]; - u8 dmac[6]; + u8 dmac[ETH_ALEN]; }; enum { /* fl */ @@ -318,7 +319,7 @@ struct mlx4_wqe_datagram_seg { __be32 dqpn; __be32 qkey; __be16 vlan; - u8 mac[6]; + u8 mac[ETH_ALEN]; }; struct mlx4_wqe_lso_seg { diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 6e8215b15998..61a0da38d0cb 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -6,6 +6,7 @@ #define __LINUX_MV643XX_ETH_H #include +#include #define MV643XX_ETH_SHARED_NAME "mv643xx_eth" #define MV643XX_ETH_NAME "mv643xx_eth_port" @@ -48,7 +49,7 @@ struct mv643xx_eth_platform_data { * Use this MAC address if it is valid, overriding the * address that is already in the hardware. */ - u8 mac_addr[6]; + u8 mac_addr[ETH_ALEN]; /* * If speed is 0, autonegotiation is enabled. diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index fc305713fc6d..6205eeba392b 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -2,6 +2,7 @@ #define __ASM_SH_ETH_H__ #include +#include enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; enum { @@ -18,7 +19,7 @@ struct sh_eth_plat_data { phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr); - unsigned char mac_addr[6]; + unsigned char mac_addr[ETH_ALEN]; unsigned no_ether_link:1; unsigned ether_link_active_low:1; unsigned needs_init:1; diff --git a/include/linux/smsc911x.h b/include/linux/smsc911x.h index 4dde70e74822..eec3efd19beb 100644 --- a/include/linux/smsc911x.h +++ b/include/linux/smsc911x.h @@ -22,6 +22,7 @@ #define __LINUX_SMSC911X_H__ #include +#include /* platform_device configuration data, should be assigned to * the platform_device's dev.platform_data */ @@ -31,7 +32,7 @@ struct smsc911x_platform_config { unsigned int flags; unsigned int shift; phy_interface_t phy_interface; - unsigned char mac[6]; + unsigned char mac[ETH_ALEN]; }; /* Constants for platform_device irq polarity configuration */ diff --git a/include/linux/uwb/spec.h b/include/linux/uwb/spec.h index b52e44f1bd33..0df24bfcdb38 100644 --- a/include/linux/uwb/spec.h +++ b/include/linux/uwb/spec.h @@ -32,6 +32,7 @@ #include #include +#include #define i1480_FW 0x00000303 /* #define i1480_FW 0x00000302 */ @@ -130,7 +131,7 @@ enum { UWB_DRP_BACKOFF_WIN_MAX = 16 }; * it is also used to define headers sent down and up the wire/radio). */ struct uwb_mac_addr { - u8 data[6]; + u8 data[ETH_ALEN]; } __attribute__((packed)); @@ -568,7 +569,7 @@ struct uwb_rc_evt_confirm { /* Device Address Management event. [WHCI] section 3.1.3.2. */ struct uwb_rc_evt_dev_addr_mgmt { struct uwb_rceb rceb; - u8 baAddr[6]; + u8 baAddr[ETH_ALEN]; u8 bResultCode; } __attribute__((packed)); -- cgit v1.2.3 From 5ef76da644bf346d29200007d8d3779e7009dabb Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:20 +0200 Subject: fbdev: simplefb: add init through platform_data If we create proper platform-devices in x86 boot-code, we can use simplefb for VBE or EFI framebuffers, too. However, there is normally no OF support so we introduce a platform_data object so x86 boot-code can pass the parameters via plain old platform-data. This also removes the OF dependency as it is not needed. The headers provide proper dummies for the case OF is disabled. Furthermore, we move the FORMAT-definitions to the common platform header so initialization code can use it to transform "struct screen_info" to the right format-name. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-2-git-send-email-dh.herrmann@gmail.com Reviewed-by: Stephen Warren Signed-off-by: H. Peter Anvin --- include/linux/platform_data/simplefb.h | 56 ++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/platform_data/simplefb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h new file mode 100644 index 000000000000..5fa2c5e02ab8 --- /dev/null +++ b/include/linux/platform_data/simplefb.h @@ -0,0 +1,56 @@ +/* + * simplefb.h - Simple Framebuffer Device + * + * Copyright (C) 2013 David Herrmann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __PLATFORM_DATA_SIMPLEFB_H__ +#define __PLATFORM_DATA_SIMPLEFB_H__ + +#include +#include +#include + +/* format array, use it to initialize a "struct simplefb_format" array */ +#define SIMPLEFB_FORMATS \ +{ \ + { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ +} + +/* + * Data-Format for Simple-Framebuffers + * @name: unique 0-terminated name that can be used to identify the mode + * @red,green,blue: Offsets and sizes of the single RGB parts + * @transp: Offset and size of the alpha bits. length=0 means no alpha + * @fourcc: 32bit DRM four-CC code (see drm_fourcc.h) + */ +struct simplefb_format { + const char *name; + u32 bits_per_pixel; + struct fb_bitfield red; + struct fb_bitfield green; + struct fb_bitfield blue; + struct fb_bitfield transp; + u32 fourcc; +}; + +/* + * Simple-Framebuffer description + * If the arch-boot code creates simple-framebuffers without DT support, it + * can pass the width, height, stride and format via this platform-data object. + * The framebuffer location must be given as IORESOURCE_MEM resource. + * @format must be a format as described in "struct simplefb_format" above. + */ +struct simplefb_platform_data { + u32 width; + u32 height; + u32 stride; + const char *format; +}; + +#endif /* __PLATFORM_DATA_SIMPLEFB_H__ */ -- cgit v1.2.3 From 9a6a36d19c9d24479300511e23933876a4a9cf82 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:24 +0200 Subject: fbdev: simplefb: add common x86 RGB formats 32bit XRGB and ARGB are used by modern x86 systems for EFI and VESA framebuffers. The other formats were reported by hpa to be most common. Add these so simplefb works on most common x86 systems. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-6-git-send-email-dh.herrmann@gmail.com Signed-off-by: H. Peter Anvin --- include/linux/platform_data/simplefb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h index 5fa2c5e02ab8..53774b0cd8e9 100644 --- a/include/linux/platform_data/simplefb.h +++ b/include/linux/platform_data/simplefb.h @@ -20,6 +20,13 @@ #define SIMPLEFB_FORMATS \ { \ { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ + { "x1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {0, 0}, DRM_FORMAT_XRGB1555 }, \ + { "a1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {15, 1}, DRM_FORMAT_ARGB1555 }, \ + { "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 }, \ + { "x8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_XRGB8888 }, \ + { "a8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {24, 8}, DRM_FORMAT_ARGB8888 }, \ + { "x2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {0, 0}, DRM_FORMAT_XRGB2101010 }, \ + { "a2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {30, 2}, DRM_FORMAT_ARGB2101010 }, \ } /* -- cgit v1.2.3 From 626f090c5cbbe557379978c7a9525011ad7fbbf6 Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Fri, 2 Aug 2013 20:10:04 +0200 Subject: usb: fix some scripts/kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the following type of warnings: Warning(drivers/usb/core/usb.c:76): No description found for return value of 'usb_find_alt_setting' Fix them by: - adding some missing descriptions of return values - using "Return" sections for those descriptions Signed-off-by: Yacine Belkadi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 6efdab089014..acb1b0aa77d8 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -708,7 +708,10 @@ extern int usb_driver_claim_interface(struct usb_driver *driver, * usb_interface_claimed - returns true iff an interface is claimed * @iface: the interface being checked * - * Returns true (nonzero) iff the interface is claimed, else false (zero). + * Return: %true (nonzero) iff the interface is claimed, else %false + * (zero). + * + * Note: * Callers must own the driver model's usb bus readlock. So driver * probe() entries don't need extra locking, but other call contexts * may need to explicitly claim that lock. @@ -745,8 +748,9 @@ extern struct usb_host_interface *usb_find_alt_setting( * @buf: where to put the string * @size: how big is "buf"? * - * Returns length of the string (> 0) or negative if size was too small. + * Return: Length of the string (> 0) or negative if size was too small. * + * Note: * This identifier is intended to be "stable", reflecting physical paths in * hardware such as physical bus addresses for host controllers or ports on * USB hubs. That makes it stay the same until systems are physically @@ -1578,7 +1582,7 @@ extern int usb_anchor_empty(struct usb_anchor *anchor); * usb_urb_dir_in - check if an URB describes an IN transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an IN transfer (device-to-host), + * Return: 1 if @urb describes an IN transfer (device-to-host), * otherwise 0. */ static inline int usb_urb_dir_in(struct urb *urb) @@ -1590,7 +1594,7 @@ static inline int usb_urb_dir_in(struct urb *urb) * usb_urb_dir_out - check if an URB describes an OUT transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an OUT transfer (host-to-device), + * Return: 1 if @urb describes an OUT transfer (host-to-device), * otherwise 0. */ static inline int usb_urb_dir_out(struct urb *urb) -- cgit v1.2.3 From 23cde4d65cc7d11e2048d2b240cdf13927ac50d0 Mon Sep 17 00:00:00 2001 From: Denis CIOCCA Date: Wed, 19 Jun 2013 09:28:00 +0100 Subject: iio: Added ST-sensors platform data to select the DRDY interrupt pin This patch add support to redirect the DRDY interrupt on INT1 or INT2 on accelerometer and pressure sensors. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 14 +++++++++++--- include/linux/platform_data/st_sensors_pdata.h | 24 ++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 3 deletions(-) create mode 100644 include/linux/platform_data/st_sensors_pdata.h (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 72b26940730d..e51f65480ea5 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -17,6 +17,8 @@ #include #include +#include + #define ST_SENSORS_TX_MAX_LENGTH 2 #define ST_SENSORS_RX_MAX_LENGTH 6 @@ -118,14 +120,16 @@ struct st_sensor_bdu { /** * struct st_sensor_data_ready_irq - ST sensor device data-ready interrupt * @addr: address of the register. - * @mask: mask to write the on/off value. + * @mask_int1: mask to enable/disable IRQ on INT1 pin. + * @mask_int2: mask to enable/disable IRQ on INT2 pin. * struct ig1 - represents the Interrupt Generator 1 of sensors. * @en_addr: address of the enable ig1 register. * @en_mask: mask to write the on/off value for enable. */ struct st_sensor_data_ready_irq { u8 addr; - u8 mask; + u8 mask_int1; + u8 mask_int2; struct { u8 en_addr; u8 en_mask; @@ -201,6 +205,7 @@ struct st_sensors { * @buffer_data: Data used by buffer part. * @odr: Output data rate of the sensor [Hz]. * num_data_channels: Number of data channels used in buffer. + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). * @get_irq_data_ready: Function to get the IRQ used for data ready signal. * @tf: Transfer function structure used by I/O operations. * @tb: Transfer buffers and mutex used by I/O operations. @@ -219,6 +224,8 @@ struct st_sensor_data { unsigned int odr; unsigned int num_data_channels; + u8 drdy_int_pin; + unsigned int (*get_irq_data_ready) (struct iio_dev *indio_dev); const struct st_sensor_transfer_function *tf; @@ -249,7 +256,8 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) } #endif -int st_sensors_init_sensor(struct iio_dev *indio_dev); +int st_sensors_init_sensor(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); int st_sensors_set_enable(struct iio_dev *indio_dev, bool enable); diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h new file mode 100644 index 000000000000..753839187ba0 --- /dev/null +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -0,0 +1,24 @@ +/* + * STMicroelectronics sensors platform-data driver + * + * Copyright 2013 STMicroelectronics Inc. + * + * Denis Ciocca + * + * Licensed under the GPL-2. + */ + +#ifndef ST_SENSORS_PDATA_H +#define ST_SENSORS_PDATA_H + +/** + * struct st_sensors_platform_data - Platform data for the ST sensors + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). + * Available only for accelerometer and pressure sensors. + * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). + */ +struct st_sensors_platform_data { + u8 drdy_int_pin; +}; + +#endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3 From 60b188f0d679656a1a2603d3bc1fa005373f4b9c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 16 Jul 2013 16:08:00 +0100 Subject: iio: Remove IIO_DEV_ATTR_RESET macro There are no users of this macro left and we have come to the conclusion that it is not a good idea to expose the raw chip reset to userspace so the macro is very unlikely to be used in new drivers. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/sysfs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/sysfs.h b/include/linux/iio/sysfs.h index b7a934b9431b..2958c960003a 100644 --- a/include/linux/iio/sysfs.h +++ b/include/linux/iio/sysfs.h @@ -73,11 +73,6 @@ struct iio_const_attr { .dev_attr = __ATTR(_name, S_IRUGO, iio_read_const_attr, NULL)} /* Generic attributes of onetype or another */ -/** - * IIO_DEV_ATTR_RESET: resets the device - **/ -#define IIO_DEV_ATTR_RESET(_store) \ - IIO_DEVICE_ATTR(reset, S_IWUSR, NULL, _store, 0) /** * IIO_DEV_ATTR_SAMP_FREQ - sets any internal clock frequency -- cgit v1.2.3 From 9dabaf5eddbafa21aded7c063cb38d2e8936c237 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 18 Jul 2013 11:19:00 +0100 Subject: iio: core: implement devm_iio_device_alloc/devm_iio_device_free Add a resource managed devm_iio_device_alloc()/devm_iio_device_free() to automatically clean up any allocations made by IIO drivers, thus leading to simplified IIO drivers code. In addition, this will allow IIO drivers to use other devm_*() API (like devm_request_irq) and don't care about the race between iio_device_free() and the release of resources by Device core during driver removing. Signed-off-by: Grygorii Strashko Signed-off-by: Oleksandr Kravchenko Tested-by: Oleksandr Kravchenko Reviewed-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3d35b7023591..61d220f89aca 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -531,6 +531,31 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) **/ void iio_device_free(struct iio_dev *indio_dev); +/** + * devm_iio_device_alloc - Resource-managed iio_device_alloc() + * @dev: Device to allocate iio_dev for + * @sizeof_priv: Space to allocate for private structure. + * + * Managed iio_device_alloc. iio_dev allocated with this function is + * automatically freed on driver detach. + * + * If an iio_dev allocated with this function needs to be freed separately, + * devm_iio_device_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_dev on success, NULL on failure. + */ +struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); + +/** + * devm_iio_device_free - Resource-managed iio_device_free() + * @dev: Device this iio_dev belongs to + * @indio_dev: the iio_dev associated with the device + * + * Free indio_dev allocated with devm_iio_device_alloc(). + */ +void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From 9bc541028b2b93962e0bebce62ce6e295aab2086 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Mon, 29 Jul 2013 22:35:00 +0100 Subject: iio: Fix documentation of devm_iio_device_free() Signed-off-by: Peter Meerwald Cc: Grygorii Strashko Cc: Oleksandr Kravchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 61d220f89aca..09ebe0a4d8e6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -552,9 +552,9 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); * @dev: Device this iio_dev belongs to * @indio_dev: the iio_dev associated with the device * - * Free indio_dev allocated with devm_iio_device_alloc(). + * Free iio_dev allocated with devm_iio_device_alloc(). */ -void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); +void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); /** * iio_buffer_enabled() - helper function to test if the buffer is enabled -- cgit v1.2.3 From 6eee5b3b493824731ed34ade0299241f91f04096 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 11 Jun 2013 20:48:02 +0900 Subject: extcon: Add an API to get extcon device from dt node Added an API of_extcon_get_extcon_dev() to be used by drivers to get extcon device in the case of dt boot (this can be used instead of extcon_get_extcon_dev()). Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/extcon/of_extcon.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/extcon/of_extcon.h (limited to 'include/linux') diff --git a/include/linux/extcon/of_extcon.h b/include/linux/extcon/of_extcon.h new file mode 100644 index 000000000000..0ebfeff1b55d --- /dev/null +++ b/include/linux/extcon/of_extcon.h @@ -0,0 +1,31 @@ +/* + * OF helpers for External connector (extcon) framework + * + * Copyright (C) 2013 Texas Instruments, Inc. + * Kishon Vijay Abraham I + * + * Copyright (C) 2013 Samsung Electronics + * Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_OF_EXTCON_H +#define __LINUX_OF_EXTCON_H + +#include + +#if IS_ENABLED(CONFIG_OF_EXTCON) +extern struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index); +#else +static inline struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index) +{ + return ERR_PTR(-ENOSYS); +} +#endif /* CONFIG_OF_EXTCON */ +#endif /* __LINUX_OF_EXTCON_H */ -- cgit v1.2.3 From 8061ad7239f3f97b477984660e95134ca684578c Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 8 Jul 2013 09:54:43 +0900 Subject: usb: dwc3: use extcon fwrk to receive connect/disconnect Modified dwc3-omap to receive connect and disconnect notification using extcon framework. Also did the necessary cleanups required after adapting to extcon framework. Signed-off-by: Kishon Vijay Abraham I Acked-by: Felipe Balbi Signed-off-by: Chanwoo Choi --- include/linux/usb/dwc3-omap.h | 30 ------------------------------ 1 file changed, 30 deletions(-) delete mode 100644 include/linux/usb/dwc3-omap.h (limited to 'include/linux') diff --git a/include/linux/usb/dwc3-omap.h b/include/linux/usb/dwc3-omap.h deleted file mode 100644 index 5615f4d82724..000000000000 --- a/include/linux/usb/dwc3-omap.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Copyright (C) 2013 by Texas Instruments - * - * The Inventra Controller Driver for Linux is free software; you - * can redistribute it and/or modify it under the terms of the GNU - * General Public License version 2 as published by the Free Software - * Foundation. - */ - -#ifndef __DWC3_OMAP_H__ -#define __DWC3_OMAP_H__ - -enum omap_dwc3_vbus_id_status { - OMAP_DWC3_UNKNOWN = 0, - OMAP_DWC3_ID_GROUND, - OMAP_DWC3_ID_FLOAT, - OMAP_DWC3_VBUS_VALID, - OMAP_DWC3_VBUS_OFF, -}; - -#if (defined(CONFIG_USB_DWC3) || defined(CONFIG_USB_DWC3_MODULE)) -extern int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status); -#else -static inline int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) -{ - return -ENODEV; -} -#endif - -#endif /* __DWC3_OMAP_H__ */ -- cgit v1.2.3 From 43e3f38892a6a521ff5901cdb97cf6985101badd Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 9 Jul 2013 18:34:21 +0530 Subject: extcon: palmas: remove unused member from palams_usb structure Remove unused member vbus_enable and set_vbus_work from palmas_usb as these members are not used in drivers. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/palmas.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..03c22ca55446 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -371,16 +371,11 @@ struct palmas_usb { struct extcon_dev edev; - /* used to set vbus, in atomic path */ - struct work_struct set_vbus_work; - int id_otg_irq; int id_irq; int vbus_otg_irq; int vbus_irq; - int vbus_enable; - enum palmas_usb_state linkstat; }; -- cgit v1.2.3 From 7281e05aabee7484624d448da208932690ed62b3 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 10 Jul 2013 14:59:06 +0530 Subject: extcon: palmas: Option to disable ID/VBUS detection based on platform Based on system design, platform needs to detect the VBUS or ID or both. Provide option to select this through platform data to disable part of cable detection through palmas-usb. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/palmas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 03c22ca55446..cfc678ceb570 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -377,6 +377,9 @@ struct palmas_usb { int vbus_irq; enum palmas_usb_state linkstat; + int wakeup; + bool enable_vbus_detection; + bool enable_id_detection; }; #define comparator_to_palmas(x) container_of((x), struct palmas_usb, comparator) -- cgit v1.2.3 From 6cdd97821322352b94bb92f271b4466ad38a2468 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 5 Aug 2013 10:52:36 -0600 Subject: vfio: add external user support VFIO is designed to be used via ioctls on file descriptors returned by VFIO. However in some situations support for an external user is required. The first user is KVM on PPC64 (SPAPR TCE protocol) which is going to use the existing VFIO groups for exclusive access in real/virtual mode on a host to avoid passing map/unmap requests to the user space which would made things pretty slow. The protocol includes: 1. do normal VFIO init operation: - opening a new container; - attaching group(s) to it; - setting an IOMMU driver for a container. When IOMMU is set for a container, all groups in it are considered ready to use by an external user. 2. User space passes a group fd to an external user. The external user calls vfio_group_get_external_user() to verify that: - the group is initialized; - IOMMU is set for it. If both checks passed, vfio_group_get_external_user() increments the container user counter to prevent the VFIO group from disposal before KVM exits. 3. The external user calls vfio_external_user_iommu_id() to know an IOMMU ID. PPC64 KVM uses it to link logical bus number (LIOBN) with IOMMU ID. 4. When the external KVM finishes, it calls vfio_group_put_external_user() to release the VFIO group. This call decrements the container user counter. Everything gets released. The "vfio: Limit group opens" patch is also required for the consistency. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Alex Williamson --- include/linux/vfio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ac8d488e4372..24579a0312a0 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -90,4 +90,11 @@ extern void vfio_unregister_iommu_driver( TYPE tmp; \ offsetof(TYPE, MEMBER) + sizeof(tmp.MEMBER); }) \ +/* + * External user API + */ +extern struct vfio_group *vfio_group_get_external_user(struct file *filep); +extern void vfio_group_put_external_user(struct vfio_group *group); +extern int vfio_external_user_iommu_id(struct vfio_group *group); + #endif /* VFIO_H */ -- cgit v1.2.3 From c57acd14ac2d53e40f5c17701c3cc3a092a07b35 Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Tue, 23 Jul 2013 01:49:18 +0200 Subject: clk: mux: Add support for read-only muxes. Some platforms have read-only clock muxes that are preconfigured at reset and cannot be changed at runtime. This patch extends mux clock driver to allow handling such read-only muxes by adding new CLK_MUX_READ_ONLY mux flag. Signed-off-by: Tomasz Figa Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1ec14a732176..9487b96939e8 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -327,8 +327,10 @@ struct clk_mux { #define CLK_MUX_INDEX_ONE BIT(0) #define CLK_MUX_INDEX_BIT BIT(1) #define CLK_MUX_HIWORD_MASK BIT(2) +#define CLK_MUX_READ_ONLY BIT(3) /* mux setting cannot be changed */ extern const struct clk_ops clk_mux_ops; +extern const struct clk_ops clk_mux_ro_ops; struct clk *clk_register_mux(struct device *dev, const char *name, const char **parent_names, u8 num_parents, unsigned long flags, -- cgit v1.2.3 From ce157510eb886feb996a7a13354973bdf4aae1a1 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Thu, 11 Apr 2013 01:34:59 -0700 Subject: mtd: nand: reword nand_chip bad block interface comments This remedies a few problems: (1) The use of "the" vs. "a" is a little confusing, IMO. (2) nand_chip.block_bad is used exclusively for checking the OOB bad block markers of a NAND. Any BBT functionality is handled in nand_bbt.c, so this description should differentiate itself from nand_bbt.c. Signed-off-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ab6363443ce8..50c5ea02c81a 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -390,8 +390,8 @@ struct nand_buffers { * @write_buf: [REPLACEABLE] write data from the buffer to the chip * @read_buf: [REPLACEABLE] read data from the chip into the buffer * @select_chip: [REPLACEABLE] select chip nr - * @block_bad: [REPLACEABLE] check, if the block is bad - * @block_markbad: [REPLACEABLE] mark the block bad + * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers + * @block_markbad: [REPLACEABLE] mark a block bad * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling * ALE/CLE/nCE. Also used to write command and address * @init_size: [BOARDSPECIFIC] hardwarespecific function for setting -- cgit v1.2.3 From 52778b2e9fcb66c8f1c9d5b1ae435815c19e7ae3 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Wed, 15 May 2013 16:40:25 +0800 Subject: mtd: increase max OOB size to 744 The oob size of Micron's MT29F64G08CBABAWP is 744 bytes. So increase the NAND_MAX_OOBSIZE to 744. Signed-off-by: Huang Shijie Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 50c5ea02c81a..38535eb453db 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -56,7 +56,7 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); * is supported now. If you add a chip with bigger oobsize/page * adjust this accordingly. */ -#define NAND_MAX_OOBSIZE 640 +#define NAND_MAX_OOBSIZE 744 #define NAND_MAX_PAGESIZE 8192 /* -- cgit v1.2.3 From 64ddba4d8a381b65bebee24c8da4eb80080c64a4 Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Mon, 29 Apr 2013 14:07:48 +0200 Subject: mtd: nand: fsmc: update of OF support Add nand bank selection and timings to the device tree bindings. Signed-off-by: Mian Yousaf Kaukab [Added some documentation] Signed-off-by: Linus Walleij Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/fsmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h index d6ed61ef451d..c8be32e9fc49 100644 --- a/include/linux/mtd/fsmc.h +++ b/include/linux/mtd/fsmc.h @@ -137,6 +137,7 @@ enum access_mode { /** * fsmc_nand_platform_data - platform specific NAND controller config + * @nand_timings: timing setup for the physical NAND interface * @partitions: partition table for the platform, use a default fallback * if this is NULL * @nr_partitions: the number of partitions in the previous entry -- cgit v1.2.3 From d914c932d7764bf9633af974940aee9390adf20d Mon Sep 17 00:00:00 2001 From: David Mosberger Date: Wed, 29 May 2013 15:30:13 +0300 Subject: mtd: nand_base: Only use GET/SET FEATURES command on chips that support them. Spansion's S34MLx chips support ONFI but not the GET/SET FEATURES calls. Signed-off-by: David Mosberger Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 38535eb453db..0745a42f1acd 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -217,6 +217,9 @@ struct nand_chip; /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 +/* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) + struct nand_onfi_params { /* rev info and features block */ /* 'O' 'N' 'F' 'I' */ -- cgit v1.2.3 From 71b94e2e866aa35f40945d9e820fc3214b792d1f Mon Sep 17 00:00:00 2001 From: Josh Wu Date: Thu, 9 May 2013 15:34:54 +0800 Subject: mtd: atmel_nand: replace cpu_is_at32ap7000() with a nand platform data The nand driver use cpu_is_at32ap7000() macro for a workaround. For the multi-platform support, we will remove this cpu_is_xxx() macro. This patch adds a boolean variable need_reset_workaround in structure atmel_nand_data. Using this variable we can remove cpu_is_at32ap7000() macro. Hans-Christian: Feel free to push this through the mtd tree, if they won't accept it I'm working on getting my workflow up on the linux-avr32.git tree. Signed-off-by: Josh Wu Acked-by: Hans-Christian Egtvedt Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/platform_data/atmel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 6a293b7fff3b..59f558d9b81e 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -71,6 +71,9 @@ struct atmel_nand_data { u8 on_flash_bbt; /* bbt on flash */ struct mtd_partition *parts; unsigned int num_parts; + + /* default is false, only for at32ap7000 chip is true */ + bool need_reset_workaround; }; /* Serial */ -- cgit v1.2.3 From 1b7192658a08f70df0f290634fd7cd2ecb629fc9 Mon Sep 17 00:00:00 2001 From: Josh Wu Date: Thu, 9 May 2013 15:34:55 +0800 Subject: mtd: atmel_nand: add a new dt binding item for nand dma support This patch will set the nand dma support in dts. Since we will not use cpu_is_xxx() in nand driver. We needn't include the mach/cpu.h any more. Signed-off-by: Josh Wu Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/platform_data/atmel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 59f558d9b81e..cea9f70133c5 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -71,6 +71,7 @@ struct atmel_nand_data { u8 on_flash_bbt; /* bbt on flash */ struct mtd_partition *parts; unsigned int num_parts; + bool has_dma; /* support dma transfer */ /* default is false, only for at32ap7000 chip is true */ bool need_reset_workaround; -- cgit v1.2.3 From e7f1935c11269bc53cd52425b1025657adddb839 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Jul 2013 21:45:17 +0200 Subject: wireless: make TU conversion macros available A few places in the code (mac80211 and iwlmvm) use the same TU_TO_JIFFIES() macro and could use TU_TO_EXP_TIME() that mac80211 has. Make these available to everyone and use them. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b3ce299782af..23a8877f4ded 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2288,4 +2288,8 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, return !!(tim->virtual_map[index] & mask); } +/* convert time units */ +#define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) +#define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) + #endif /* LINUX_IEEE80211_H */ -- cgit v1.2.3 From 6a63b098f0ea34a2cdfea11a5c5f89e723c862c7 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 26 Jul 2013 10:17:39 -0300 Subject: bus: mvebu-mbus: Add new API for window creation We add an API to create MBus address decoding windows from the target ID and attribute. This function will be used later and deprecate the current name based scheme. Signed-off-by: Thomas Petazzoni Tested-by: Andrew Lunn Tested-by: Sebastian Hesselbarth Signed-off-by: Jason Cooper --- include/linux/mbus.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index dba482e31a13..9245b663e720 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -62,8 +62,14 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base, size_t size, phys_addr_t remap, unsigned int flags); +int mvebu_mbus_add_window_remap_by_id(unsigned int target, + unsigned int attribute, + phys_addr_t base, size_t size, + phys_addr_t remap); int mvebu_mbus_add_window(const char *devname, phys_addr_t base, size_t size); +int mvebu_mbus_add_window_by_id(unsigned int target, unsigned int attribute, + phys_addr_t base, size_t size); int mvebu_mbus_del_window(phys_addr_t base, size_t size); int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, size_t mbus_size, phys_addr_t sdram_phys_base, -- cgit v1.2.3 From 6839cfa82f99fd098ea486e7f9df78344c8e091f Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Fri, 26 Jul 2013 10:17:45 -0300 Subject: bus: mvebu-mbus: Introduce device tree binding This patch adds the most fundamental device-tree initialization. We only introduce what's required to be able to probe the mvebu-mbus driver from the DT. Follow-up patches will extend the device tree binding, allowing to describe static address decoding windows. Signed-off-by: Thomas Petazzoni Signed-off-by: Ezequiel Garcia Tested-by: Andrew Lunn Tested-by: Sebastian Hesselbarth Signed-off-by: Jason Cooper --- include/linux/mbus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 9245b663e720..eadefd687a0b 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -74,5 +74,6 @@ int mvebu_mbus_del_window(phys_addr_t base, size_t size); int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, size_t mbus_size, phys_addr_t sdram_phys_base, size_t sdram_size); +int mvebu_mbus_dt_init(void); #endif /* __LINUX_MBUS_H */ -- cgit v1.2.3 From 79d946837c042fba3e9ba2726f3cfa56aa408e16 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Fri, 26 Jul 2013 10:17:47 -0300 Subject: bus: mvebu-mbus: Add new API for the PCIe memory and IO aperture We add two optional properties to the MBus DT binding, to encode the PCIe memory and IO aperture. This allows such information to be retrieved by -for instance- the pci driver to allocate the MBus decoding windows. Correspondingly, and in order to retrieve this information, we add two new APIs. Signed-off-by: Ezequiel Garcia Tested-by: Andrew Lunn Tested-by: Sebastian Hesselbarth Signed-off-by: Jason Cooper --- include/linux/mbus.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index eadefd687a0b..650bc154a86e 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -11,6 +11,8 @@ #ifndef __LINUX_MBUS_H #define __LINUX_MBUS_H +struct resource; + struct mbus_dram_target_info { /* @@ -59,6 +61,8 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) } #endif +void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); +void mvebu_mbus_get_pcie_io_aperture(struct resource *res); int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base, size_t size, phys_addr_t remap, unsigned int flags); -- cgit v1.2.3 From 124e5427f59877cd9dde5fa2ea90c413765e77ef Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 26 Jul 2013 10:17:50 -0300 Subject: bus: mvebu-mbus: Remove the no longer used name-based API Now that every user of the deprecated name-based API has been converted to using the ID-based API, let's remove the former one. Signed-off-by: Thomas Petazzoni Tested-by: Andrew Lunn Tested-by: Sebastian Hesselbarth Signed-off-by: Jason Cooper --- include/linux/mbus.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 650bc154a86e..345b8c53b897 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -63,15 +63,10 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); void mvebu_mbus_get_pcie_io_aperture(struct resource *res); -int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base, - size_t size, phys_addr_t remap, - unsigned int flags); int mvebu_mbus_add_window_remap_by_id(unsigned int target, unsigned int attribute, phys_addr_t base, size_t size, phys_addr_t remap); -int mvebu_mbus_add_window(const char *devname, phys_addr_t base, - size_t size); int mvebu_mbus_add_window_by_id(unsigned int target, unsigned int attribute, phys_addr_t base, size_t size); int mvebu_mbus_del_window(phys_addr_t base, size_t size); -- cgit v1.2.3 From b6c035d04e80b4244a143e34e51c84cf2181bd94 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 5 Aug 2013 15:02:48 -0700 Subject: x86, asmlinkage: Make dump_stack visible dump_stack is used from assembler code, so make it visible. Signed-off-by: Andi Kleen Link: http://lkml.kernel.org/r/1375740170-7446-15-git-send-email-andi@firstfloor.org Signed-off-by: H. Peter Anvin --- include/linux/printk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 22c7052e9372..e6131a782481 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -200,7 +200,7 @@ static inline void show_regs_print_info(const char *log_lvl) } #endif -extern void dump_stack(void) __cold; +extern asmlinkage void dump_stack(void) __cold; #ifndef pr_fmt #define pr_fmt(fmt) fmt -- cgit v1.2.3 From 36f8250e4d478429a393c20910dcd02772bd0839 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 7 Aug 2013 08:56:10 +0800 Subject: regulator: fan53555: Prevent multiple include of fan53555.h Add define for __FAN53555_H__ to prevent multiple include of the header file. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/fan53555.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/fan53555.h b/include/linux/regulator/fan53555.h index 5c45c85d52ca..f13880e84d85 100644 --- a/include/linux/regulator/fan53555.h +++ b/include/linux/regulator/fan53555.h @@ -11,6 +11,7 @@ */ #ifndef __FAN53555_H__ +#define __FAN53555_H__ /* VSEL ID */ enum { -- cgit v1.2.3 From 9d3dda5c0d092d6bc9911bf24de81350d47c6be6 Mon Sep 17 00:00:00 2001 From: Leilei Shang Date: Fri, 7 Jun 2013 14:38:17 +0800 Subject: i2c: pxa: enable high speed mode for i2c bus To enter high speed mode, following steps should be done: 1. When running in high speed mode, i2c clock rate is different from standard mode. Clock rate must be set according to specification first. 2. When i2c controller sends a master code and wins arbitration, high speed mode is entered. If you want to enable high speed mode, the following members of platform data should be set to proper value: 1. "high_mode" should be set to "1". 2. "master_code" should be set to "8'b 0000_1xxx"(x is 0 or 1). If no master_code is set, set to default value 0xe. 3. "rate" should be set according to specification. Signed-off-by: Leilei Shang Signed-off-by: Wolfram Sang --- include/linux/i2c/pxa-i2c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/pxa-i2c.h b/include/linux/i2c/pxa-i2c.h index 1a9f65e6ec0f..53aab243cbd8 100644 --- a/include/linux/i2c/pxa-i2c.h +++ b/include/linux/i2c/pxa-i2c.h @@ -67,6 +67,9 @@ struct i2c_pxa_platform_data { unsigned int class; unsigned int use_pio :1; unsigned int fast_mode :1; + unsigned int high_mode:1; + unsigned char master_code; + unsigned long rate; }; extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info); -- cgit v1.2.3 From 3923172b3d700486c1ca24df9c4c5405a83e2309 Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Wed, 26 Jun 2013 10:56:35 +0300 Subject: i2c: reduce parent checking to a NOOP in non-I2C_MUX case In 0826374 - i2c: Multiplexed I2C bus core support core i2c code increased in size and complexity even when I2C_MUX wasn't selected. Turning this check into a constant NULL in the n case lets the client functions in be simplified too, not needing to include never-called calls to the mux-specific helpers. Signed-off-by: Phil Carmody Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e988fa935b3c..b3c4b8dac1ce 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -447,11 +447,13 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data) static inline struct i2c_adapter * i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter) { +#if IS_ENABLED(I2C_MUX) struct device *parent = adapter->dev.parent; if (parent != NULL && parent->type == &i2c_adapter_type) return to_i2c_adapter(parent); else +#endif return NULL; } -- cgit v1.2.3 From f8407299f61681e9733f06c7214e81002cb459b3 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 24 Jul 2013 11:59:49 -0400 Subject: NFS Remove unused authflavour parameter from init_client Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 8651574a305b..ddc3e32178c3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1442,7 +1442,7 @@ struct nfs_rpc_ops { struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); struct nfs_client * (*init_client) (struct nfs_client *, const struct rpc_timeout *, - const char *, rpc_authflavor_t); + const char *); void (*free_client) (struct nfs_client *); struct nfs_server *(*create_server)(struct nfs_mount_info *, struct nfs_subversion *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, -- cgit v1.2.3 From bf4dae5ce1b95a5932e43036edcf3f1b324758c6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 7 Aug 2013 22:21:57 +0200 Subject: pinctrl: nomadik: delete ancient pin control API The pin control subsystem was created to do away with custom pin control APIs such as this one. It was kept for backward-compatibility but is completely unused in the current kernel, so let's delete it. Signed-off-by: Linus Walleij --- include/linux/platform_data/pinctrl-nomadik.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/pinctrl-nomadik.h b/include/linux/platform_data/pinctrl-nomadik.h index f73b2f0c55b7..abf5bed84df3 100644 --- a/include/linux/platform_data/pinctrl-nomadik.h +++ b/include/linux/platform_data/pinctrl-nomadik.h @@ -226,30 +226,6 @@ enum nmk_gpio_slpm { NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE, }; -/* Older deprecated pin config API that should go away soon */ -extern int nmk_config_pin(pin_cfg_t cfg, bool sleep); -extern int nmk_config_pins(pin_cfg_t *cfgs, int num); -extern int nmk_config_pins_sleep(pin_cfg_t *cfgs, int num); -extern int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode); -extern int nmk_gpio_set_pull(int gpio, enum nmk_gpio_pull pull); -#ifdef CONFIG_PINCTRL_NOMADIK -extern int nmk_gpio_set_mode(int gpio, int gpio_mode); -#else -static inline int nmk_gpio_set_mode(int gpio, int gpio_mode) -{ - return -ENODEV; -} -#endif -extern int nmk_gpio_get_mode(int gpio); - -extern void nmk_gpio_wakeups_suspend(void); -extern void nmk_gpio_wakeups_resume(void); - -extern void nmk_gpio_clocks_enable(void); -extern void nmk_gpio_clocks_disable(void); - -extern void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up); - /* * Platform data to register a block: only the initial gpio/irq number. */ -- cgit v1.2.3 From 5ff0a268037d344f86df690ccb994d8bc015d2d9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:03 +0530 Subject: cpufreq: Clean up header files included in the core This patch addresses the following issues in the header files in the cpufreq core: - Include headers in ascending order, so that we don't add same many times by mistake. - must be included after , so that they override whatever they need to. - Remove unnecessary includes. - Don't include files already included by cpufreq.h or cpufreq_governor.h. [rjw: Changelog] Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e1fd215e16c9..97627bbbca82 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -11,16 +11,11 @@ #ifndef _LINUX_CPUFREQ_H #define _LINUX_CPUFREQ_H -#include -#include -#include -#include +#include +#include #include +#include #include -#include -#include -#include -#include #define CPUFREQ_NAME_LEN 16 /* Print length for names. Extra 1 space for accomodating '\n' in prints */ -- cgit v1.2.3 From 74aca95da74836a6807118f6590d8df8232c74a9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:04 +0530 Subject: cpufreq: Re-arrange declarations in cpufreq.h They are pretty much mixed up. Although generic headers are present, definitions/declarations are present outside of them too ... This patch just moves stuff up and down to make it look better and consistent. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 373 +++++++++++++++++++++++------------------------- 1 file changed, 177 insertions(+), 196 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 97627bbbca82..0d3b0266bc98 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -17,60 +17,30 @@ #include #include -#define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ -#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) - /********************************************************************* - * CPUFREQ NOTIFIER INTERFACE * + * CPUFREQ INTERFACE * *********************************************************************/ - -#define CPUFREQ_TRANSITION_NOTIFIER (0) -#define CPUFREQ_POLICY_NOTIFIER (1) - -#ifdef CONFIG_CPU_FREQ -int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); -int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -extern void disable_cpufreq(void); -#else /* CONFIG_CPU_FREQ */ -static inline int cpufreq_register_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline int cpufreq_unregister_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline void disable_cpufreq(void) { } -#endif /* CONFIG_CPU_FREQ */ - -/* if (cpufreq_driver->target) exists, the ->governor decides what frequency - * within the limits is used. If (cpufreq_driver->setpolicy> exists, these - * two generic policies are available: - */ - -#define CPUFREQ_POLICY_POWERSAVE (1) -#define CPUFREQ_POLICY_PERFORMANCE (2) - -/* Frequency values here are CPU kHz so that hardware which doesn't run - * with some frequencies can complain without having to guess what per - * cent / per mille means. +/* + * Frequency values here are CPU kHz + * * Maximum transition latency is in nanoseconds - if it's unknown, * CPUFREQ_ETERNAL shall be used. */ +#define CPUFREQ_ETERNAL (-1) +#define CPUFREQ_NAME_LEN 16 +/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) + struct cpufreq_governor; -/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ -extern struct kobject *cpufreq_global_kobject; -int cpufreq_get_global_kobject(void); -void cpufreq_put_global_kobject(void); -int cpufreq_sysfs_create_file(const struct attribute *attr); -void cpufreq_sysfs_remove_file(const struct attribute *attr); +struct cpufreq_freqs { + unsigned int cpu; /* cpu nr */ + unsigned int old; + unsigned int new; + u8 flags; /* flags of cpufreq_driver, see below. */ +}; -#define CPUFREQ_ETERNAL (-1) struct cpufreq_cpuinfo { unsigned int max_freq; unsigned int min_freq; @@ -117,111 +87,95 @@ struct cpufreq_policy { int transition_ongoing; /* Tracks transition status */ }; -#define CPUFREQ_ADJUST (0) -#define CPUFREQ_INCOMPATIBLE (1) -#define CPUFREQ_NOTIFY (2) -#define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) - /* Only for ACPI */ #define CPUFREQ_SHARED_TYPE_NONE (0) /* None */ #define CPUFREQ_SHARED_TYPE_HW (1) /* HW does needed coordination */ #define CPUFREQ_SHARED_TYPE_ALL (2) /* All dependent CPUs should set freq */ #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); +void cpufreq_cpu_put(struct cpufreq_policy *data); + static inline bool policy_is_shared(struct cpufreq_policy *policy) { return cpumask_weight(policy->cpus) > 1; } -/******************** cpufreq transition notifiers *******************/ - -#define CPUFREQ_PRECHANGE (0) -#define CPUFREQ_POSTCHANGE (1) -#define CPUFREQ_RESUMECHANGE (8) -#define CPUFREQ_SUSPENDCHANGE (9) +/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ +extern struct kobject *cpufreq_global_kobject; +int cpufreq_get_global_kobject(void); +void cpufreq_put_global_kobject(void); +int cpufreq_sysfs_create_file(const struct attribute *attr); +void cpufreq_sysfs_remove_file(const struct attribute *attr); -struct cpufreq_freqs { - unsigned int cpu; /* cpu nr */ - unsigned int old; - unsigned int new; - u8 flags; /* flags of cpufreq_driver, see below. */ -}; +#ifdef CONFIG_CPU_FREQ +unsigned int cpufreq_get(unsigned int cpu); +unsigned int cpufreq_quick_get(unsigned int cpu); +unsigned int cpufreq_quick_get_max(unsigned int cpu); +void disable_cpufreq(void); -/** - * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch - * safe) - * @old: old value - * @div: divisor - * @mult: multiplier - * - * - * new = old * mult / div - */ -static inline unsigned long cpufreq_scale(unsigned long old, u_int div, - u_int mult) +u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); +int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); +int cpufreq_update_policy(unsigned int cpu); +bool have_governor_per_policy(void); +struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +#else +static inline unsigned int cpufreq_get(unsigned int cpu) { -#if BITS_PER_LONG == 32 - - u64 result = ((u64) old) * ((u64) mult); - do_div(result, div); - return (unsigned long) result; - -#elif BITS_PER_LONG == 64 - - unsigned long result = old * ((u64) mult); - result /= div; - return result; - + return 0; +} +static inline unsigned int cpufreq_quick_get(unsigned int cpu) +{ + return 0; +} +static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +{ + return 0; +} +static inline void disable_cpufreq(void) { } #endif -}; /********************************************************************* - * CPUFREQ GOVERNORS * + * CPUFREQ DRIVER INTERFACE * *********************************************************************/ -#define CPUFREQ_GOV_START 1 -#define CPUFREQ_GOV_STOP 2 -#define CPUFREQ_GOV_LIMITS 3 -#define CPUFREQ_GOV_POLICY_INIT 4 -#define CPUFREQ_GOV_POLICY_EXIT 5 +#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ +#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ -struct cpufreq_governor { - char name[CPUFREQ_NAME_LEN]; - int initialized; - int (*governor) (struct cpufreq_policy *policy, - unsigned int event); - ssize_t (*show_setspeed) (struct cpufreq_policy *policy, - char *buf); - int (*store_setspeed) (struct cpufreq_policy *policy, - unsigned int freq); - unsigned int max_transition_latency; /* HW must be able to switch to - next freq faster than this value in nano secs or we - will fallback to performance governor */ - struct list_head governor_list; - struct module *owner; +struct freq_attr { + struct attribute attr; + ssize_t (*show)(struct cpufreq_policy *, char *); + ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); }; -/* - * Pass a target to the cpufreq driver. - */ -extern int cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -extern int __cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -int cpufreq_register_governor(struct cpufreq_governor *governor); -void cpufreq_unregister_governor(struct cpufreq_governor *governor); +#define cpufreq_freq_attr_ro(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) -/********************************************************************* - * CPUFREQ DRIVER INTERFACE * - *********************************************************************/ +#define cpufreq_freq_attr_ro_perm(_name, _perm) \ +static struct freq_attr _name = \ +__ATTR(_name, _perm, show_##_name, NULL) -#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ -#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ +#define cpufreq_freq_attr_rw(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) + +struct global_attr { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, + struct attribute *attr, char *buf); + ssize_t (*store)(struct kobject *a, struct attribute *b, + const char *c, size_t count); +}; + +#define define_one_global_ro(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) + +#define define_one_global_rw(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) -struct freq_attr; struct cpufreq_driver { struct module *owner; @@ -258,7 +212,6 @@ struct cpufreq_driver { }; /* flags */ - #define CPUFREQ_STICKY 0x01 /* the driver isn't removed even if * all ->init() calls failed */ #define CPUFREQ_CONST_LOOPS 0x02 /* loops_per_jiffy or other kernel @@ -270,8 +223,7 @@ struct cpufreq_driver { int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -void cpufreq_notify_transition(struct cpufreq_policy *policy, - struct cpufreq_freqs *freqs, unsigned int state); +const char *cpufreq_get_current_driver(void); static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) @@ -289,86 +241,117 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, return; } -struct freq_attr { - struct attribute attr; - ssize_t (*show)(struct cpufreq_policy *, char *); - ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); -}; - -#define cpufreq_freq_attr_ro(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) - -#define cpufreq_freq_attr_ro_perm(_name, _perm) \ -static struct freq_attr _name = \ -__ATTR(_name, _perm, show_##_name, NULL) - -#define cpufreq_freq_attr_rw(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/********************************************************************* + * CPUFREQ NOTIFIER INTERFACE * + *********************************************************************/ -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; +#define CPUFREQ_TRANSITION_NOTIFIER (0) +#define CPUFREQ_POLICY_NOTIFIER (1) -#define define_one_global_ro(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) +/* Transition notifiers */ +#define CPUFREQ_PRECHANGE (0) +#define CPUFREQ_POSTCHANGE (1) +#define CPUFREQ_RESUMECHANGE (8) +#define CPUFREQ_SUSPENDCHANGE (9) -#define define_one_global_rw(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/* Policy Notifiers */ +#define CPUFREQ_ADJUST (0) +#define CPUFREQ_INCOMPATIBLE (1) +#define CPUFREQ_NOTIFY (2) +#define CPUFREQ_START (3) +#define CPUFREQ_UPDATE_POLICY_CPU (4) -struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); -const char *cpufreq_get_current_driver(void); +#ifdef CONFIG_CPU_FREQ +int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); +int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -/********************************************************************* - * CPUFREQ 2.6. INTERFACE * - *********************************************************************/ -u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); -int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); -bool have_governor_per_policy(void); -struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +void cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state); -#ifdef CONFIG_CPU_FREQ -/* - * query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it - */ -unsigned int cpufreq_get(unsigned int cpu); -#else -static inline unsigned int cpufreq_get(unsigned int cpu) +#else /* CONFIG_CPU_FREQ */ +static inline int cpufreq_register_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -#endif - -/* - * query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it - */ -#ifdef CONFIG_CPU_FREQ -unsigned int cpufreq_quick_get(unsigned int cpu); -unsigned int cpufreq_quick_get_max(unsigned int cpu); -#else -static inline unsigned int cpufreq_quick_get(unsigned int cpu) +static inline int cpufreq_unregister_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +#endif /* !CONFIG_CPU_FREQ */ + +/** + * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch + * safe) + * @old: old value + * @div: divisor + * @mult: multiplier + * + * + * new = old * mult / div + */ +static inline unsigned long cpufreq_scale(unsigned long old, u_int div, + u_int mult) { - return 0; -} +#if BITS_PER_LONG == 32 + u64 result = ((u64) old) * ((u64) mult); + do_div(result, div); + return (unsigned long) result; + +#elif BITS_PER_LONG == 64 + unsigned long result = old * ((u64) mult); + result /= div; + return result; #endif +} /********************************************************************* - * CPUFREQ DEFAULT GOVERNOR * + * CPUFREQ GOVERNORS * *********************************************************************/ +/* + * If (cpufreq_driver->target) exists, the ->governor decides what frequency + * within the limits is used. If (cpufreq_driver->setpolicy> exists, these + * two generic policies are available: + */ +#define CPUFREQ_POLICY_POWERSAVE (1) +#define CPUFREQ_POLICY_PERFORMANCE (2) + +/* Governor Events */ +#define CPUFREQ_GOV_START 1 +#define CPUFREQ_GOV_STOP 2 +#define CPUFREQ_GOV_LIMITS 3 +#define CPUFREQ_GOV_POLICY_INIT 4 +#define CPUFREQ_GOV_POLICY_EXIT 5 + +struct cpufreq_governor { + char name[CPUFREQ_NAME_LEN]; + int initialized; + int (*governor) (struct cpufreq_policy *policy, + unsigned int event); + ssize_t (*show_setspeed) (struct cpufreq_policy *policy, + char *buf); + int (*store_setspeed) (struct cpufreq_policy *policy, + unsigned int freq); + unsigned int max_transition_latency; /* HW must be able to switch to + next freq faster than this value in nano secs or we + will fallback to performance governor */ + struct list_head governor_list; + struct module *owner; +}; + +/* Pass a target to the cpufreq driver */ +int cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int __cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int cpufreq_register_governor(struct cpufreq_governor *governor); +void cpufreq_unregister_governor(struct cpufreq_governor *governor); + +/* CPUFREQ DEFAULT GOVERNOR */ /* * Performance governor is fallback governor if any other gov failed to auto * load due latency restrictions @@ -417,18 +400,16 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int relation, unsigned int *index); -/* the following 3 funtions are for cpufreq core use only */ +void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); +ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); + +/* the following funtion is for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; - void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, unsigned int cpu); -void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); - void cpufreq_frequency_table_put_attr(unsigned int cpu); -ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); - #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 3a3e9e06d0c11b8efa95933a88c9e67209fa4330 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:05 +0530 Subject: cpufreq: Give consistent names to cpufreq_policy objects They are called policy, cur_policy, new_policy, data, etc. Just call them policy wherever possible. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 0d3b0266bc98..29208923c9d3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -94,7 +94,7 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); +void cpufreq_cpu_put(struct cpufreq_policy *policy); static inline bool policy_is_shared(struct cpufreq_policy *policy) { -- cgit v1.2.3 From b4bf07771faaf959b0a916d35b1b930c030e30a8 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 6 Aug 2013 17:45:03 +0800 Subject: net: move iov_pages() to net/core/iovec.c To let it be reused and reduce code duplication. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 230c04bda3e2..445ef7519dc2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -313,6 +313,8 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, unsigned int len, __wsum *csump); +extern unsigned long iov_pages(const struct iovec *iov, int offset, + unsigned long nr_segs); extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, -- cgit v1.2.3 From c3bdeb5c7cc073ccf5ff9624642022a8613a956e Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 6 Aug 2013 17:45:04 +0800 Subject: net: move zerocopy_sg_from_iovec() to net/core/datagram.c To let it be reused and reduce code duplication. Also document this function. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ae46475d4568..5ac96f31d546 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2359,6 +2359,10 @@ extern int skb_copy_datagram_from_iovec(struct sk_buff *skb, const struct iovec *from, int from_offset, int len); +extern int zerocopy_sg_from_iovec(struct sk_buff *skb, + const struct iovec *frm, + int offset, + size_t count); extern int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset, const struct iovec *to, -- cgit v1.2.3 From 72b098964d3c3fb030dcac2d4c869c9851a0d17a Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Tue, 6 Aug 2013 20:32:14 +0100 Subject: video/hdmi: Introduce a generic hdmi_infoframe union MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit And a way to pack hdmi_infoframe generically. Cc: Thierry Reding Reviewed-by: Ville Syrjälä Signed-off-by: Damien Lespiau Acked-by: Dave Airlie Reviewed-by: Alex Deucher Signed-off-by: Daniel Vetter --- include/linux/hdmi.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 3b589440ecfe..0f3f82eadef7 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -23,6 +23,12 @@ enum hdmi_infoframe_type { #define HDMI_SPD_INFOFRAME_SIZE 25 #define HDMI_AUDIO_INFOFRAME_SIZE 10 +struct hdmi_any_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; +}; + enum hdmi_colorspace { HDMI_COLORSPACE_RGB, HDMI_COLORSPACE_YUV422, @@ -228,4 +234,15 @@ struct hdmi_vendor_infoframe { ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, void *buffer, size_t size); +union hdmi_infoframe { + struct hdmi_any_infoframe any; + struct hdmi_avi_infoframe avi; + struct hdmi_spd_infoframe spd; + struct hdmi_vendor_infoframe vendor; + struct hdmi_audio_infoframe audio; +}; + +ssize_t +hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size); + #endif /* _DRM_HDMI_H */ -- cgit v1.2.3 From 61177b0e12ba162d5de206914e8703d8eb90ad19 Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Tue, 6 Aug 2013 20:32:15 +0100 Subject: video/hdmi: Add a macro to return the size of a full infoframe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cc: Thierry Reding Reviewed-by: Ville Syrjälä Signed-off-by: Damien Lespiau Acked-by: Dave Airlie Reviewed-by: Alex Deucher Signed-off-by: Daniel Vetter --- include/linux/hdmi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 0f3f82eadef7..bc6743e76e37 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -23,6 +23,9 @@ enum hdmi_infoframe_type { #define HDMI_SPD_INFOFRAME_SIZE 25 #define HDMI_AUDIO_INFOFRAME_SIZE 10 +#define HDMI_INFOFRAME_SIZE(type) \ + (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) + struct hdmi_any_infoframe { enum hdmi_infoframe_type type; unsigned char version; -- cgit v1.2.3 From 8af01f56a03e9cbd91a55d688fce1315021efba8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: s/cgroup_subsys_state/cgroup_css/ s/task_subsys_state/task_css/ The names of the two struct cgroup_subsys_state accessors - cgroup_subsys_state() and task_subsys_state() - are somewhat awkward. The former clashes with the type name and the latter doesn't even indicate it's somehow related to cgroup. We're about to revamp large portion of cgroup API, so, let's rename them so that they're less awkward. Most per-controller usages of the accessors are localized in accessor wrappers and given the amount of scheduled changes, this isn't gonna add any noticeable headache. Rename cgroup_subsys_state() to cgroup_css() and task_subsys_state() to task_css(). This patch is pure rename. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 44dd422d7e9b..552c5feef733 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -647,8 +647,15 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS -static inline struct cgroup_subsys_state *cgroup_subsys_state( - struct cgroup *cgrp, int subsys_id) +/** + * cgroup_css - obtain a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @subsys_id: the subsystem of interest + * + * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. + */ +static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, + int subsys_id) { return cgrp->subsys[subsys_id]; } @@ -678,7 +685,7 @@ extern struct mutex cgroup_mutex; #endif /** - * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds + * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() @@ -686,7 +693,7 @@ extern struct mutex cgroup_mutex; * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ -#define task_subsys_state_check(task, subsys_id, __c) \ +#define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** @@ -701,22 +708,22 @@ static inline struct css_set *task_css_set(struct task_struct *task) } /** - * task_subsys_state - obtain css for (task, subsys) + * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * - * See task_subsys_state_check(). + * See task_css_check(). */ -static inline struct cgroup_subsys_state * -task_subsys_state(struct task_struct *task, int subsys_id) +static inline struct cgroup_subsys_state *task_css(struct task_struct *task, + int subsys_id) { - return task_subsys_state_check(task, subsys_id, false); + return task_css_check(task, subsys_id, false); } -static inline struct cgroup* task_cgroup(struct task_struct *task, - int subsys_id) +static inline struct cgroup *task_cgroup(struct task_struct *task, + int subsys_id) { - return task_subsys_state(task, subsys_id)->cgroup; + return task_css(task, subsys_id)->cgroup; } /** -- cgit v1.2.3 From 72c97e54e0f043d33b246d7460ae0a36c4b8c643 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: add subsystem pointer to cgroup_subsys_state Currently, given a cgroup_subsys_state, there's no way to find out which subsystem the css is for, which we'll need to convert the cgroup controller API to primarily use @css instead of @cgroup. This patch adds cgroup_subsys_state->ss which points to the subsystem the @css belongs to. While at it, remove the comment about accessing @css->cgroup to determine the hierarchy. cgroup core will provide API to traverse hierarchy of css'es and we don't want subsystems to directly walk cgroup hierarchies anymore. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 552c5feef733..821678aae4db 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -66,13 +66,12 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* - * The cgroup that this subsystem is attached to. Useful - * for subsystems that want to know about the cgroup - * hierarchy structure - */ + /* the cgroup that this css is attached to */ struct cgroup *cgroup; + /* the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; -- cgit v1.2.3 From 6387698699afd72d6304566fb6ccf84bffe07c56 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add css_parent() Currently, controllers have to explicitly follow the cgroup hierarchy to find the parent of a given css. cgroup is moving towards using cgroup_subsys_state as the main controller interface construct, so let's provide a way to climb the hierarchy using just csses. This patch implements css_parent() which, given a css, returns its parent. The function is guarnateed to valid non-NULL parent css as long as the target css is not at the top of the hierarchy. freezer, cpuset, cpu, cpuacct, hugetlb, memory, net_cls and devices are converted to use css_parent() instead of accessing cgroup->parent directly. * __parent_ca() is dropped from cpuacct and its usage is replaced with parent_ca(). The only difference between the two was NULL test on cgroup->parent which is now embedded in css_parent() making the distinction moot. Note that eventually a css->parent field will be added to css and the NULL check in css_parent() will go away. This patch shouldn't cause any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 821678aae4db..18112a3bb12b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -646,6 +646,21 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS +/** + * css_parent - find the parent css + * @css: the target cgroup_subsys_state + * + * Return the parent css of @css. This function is guaranteed to return + * non-NULL parent as long as @css isn't the root. + */ +static inline +struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) +{ + struct cgroup *parent_cgrp = css->cgroup->parent; + + return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; +} + /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest -- cgit v1.2.3 From eb95419b023abacb415e2a18fea899023ce7624d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- include/linux/cgroup.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 18112a3bb12b..9c2b9dd9121d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -579,18 +579,22 @@ int cgroup_taskset_size(struct cgroup_taskset *tset); */ struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp); - int (*css_online)(struct cgroup *cgrp); - void (*css_offline)(struct cgroup *cgrp); - void (*css_free)(struct cgroup *cgrp); - - int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, struct task_struct *task); - void (*bind)(struct cgroup *root); + void (*bind)(struct cgroup_subsys_state *root_css); int subsys_id; int disabled; -- cgit v1.2.3 From 2bb566cb68dfafad328af666ebadf0e49accd6ca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add subsys backlink pointer to cftype cgroup is transitioning to using css (cgroup_subsys_state) instead of cgroup as the primary subsystem handle. The cgroupfs file interface will be converted to use css's which requires finding out the subsystem from cftype so that the matching css can be determined from the cgroup. This patch adds cftype->ss which points to the subsystem the file belongs to. The field is initialized while a cftype is being registered. This makes it unnecessary to explicitly specify the subsystem for other cftype handling functions. @ss argument dropped from various cftype handling functions. This patch shouldn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Cc: Jens Axboe --- include/linux/cgroup.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9c2b9dd9121d..5db8138a0482 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -429,6 +429,12 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; + /* + * The subsys this file belongs to. Initialized automatically + * during registration. NULL for cgroup core files. + */ + struct cgroup_subsys *ss; + int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -542,7 +548,7 @@ static inline const char *cgroup_name(const struct cgroup *cgrp) } int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); -- cgit v1.2.3 From 67f4c36f83455b253445b2cb28ac9a2c4f85d99a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: add cgroup->dummy_css cgroup subsystem API is being converted to use css (cgroup_subsys_state) as the main handle, which makes things a bit awkward for subsystem agnostic core features - the "cgroup.*" interface files and various iterations - a bit awkward as they don't have a css to use. This patch adds cgroup->dummy_css which has NULL ->ss and whose only role is pointing back to the cgroup. This will be used to support subsystem agnostic features on the coming css based API. css_parent() is updated to handle dummy_css's. Note that css will soon grow its own ->parent field and css_parent() will be made trivial. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5db8138a0482..b0d5f53ae5e1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -225,6 +225,9 @@ struct cgroup { struct list_head pidlists; struct mutex pidlist_mutex; + /* dummy css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state dummy_css; + /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -668,7 +671,13 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { struct cgroup *parent_cgrp = css->cgroup->parent; - return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; + if (!parent_cgrp) + return NULL; + + if (css->ss) + return parent_cgrp->subsys[css->ss->subsys_id]; + else + return &parent_cgrp->dummy_css; } /** -- cgit v1.2.3 From 182446d087906de40e514573a92a97b203695f71 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in file methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup. Please see the previous commit which converts the subsystem methods for rationale. This patch converts all cftype file operations to take @css instead of @cgroup. cftypes for the cgroup core files don't have their subsytem pointer set. These will automatically use the dummy_css added by the previous patch and can be converted the same way. Most subsystem conversions are straight forwards but there are some interesting ones. * freezer: update_if_frozen() is also converted to take @css instead of @cgroup for consistency. This will make the code look simpler too once iterators are converted to use css. * memory/vmpressure: mem_cgroup_from_css() needs to be exported to vmpressure while mem_cgroup_from_cont() can be made static. Updated accordingly. * cpu: cgroup_tg() doesn't have any user left. Removed. * cpuacct: cgroup_ca() doesn't have any user left. Removed. * hugetlb: hugetlb_cgroup_form_cgroup() doesn't have any user left. Removed. * net_cls: cgrp_cls_state() doesn't have any user left. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- include/linux/cgroup.h | 24 +++++++++++++----------- include/linux/memcontrol.h | 2 +- 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0d5f53ae5e1..0b91436c68ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -439,34 +439,34 @@ struct cftype { struct cgroup_subsys *ss; int (*open)(struct inode *inode, struct file *file); - ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*read)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes, loff_t *ppos); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ - u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ - s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_map() is used for defining a map of key/value * pairs. It should call cb->fill(cb, key, value) for each * entry. The key/value pairs (and their ordering) should not * change between reboots. */ - int (*read_map)(struct cgroup *cgrp, struct cftype *cft, + int (*read_map)(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb); /* * read_seq_string() is used for outputting a simple sequence * using seqfile. */ - int (*read_seq_string)(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *m); + int (*read_seq_string)(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m); - ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos); @@ -475,18 +475,20 @@ struct cftype { * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); /* * write_s64() is a signed version of write_u64() */ - int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); /* * write_string() is passed a nul-terminated kernelspace * buffer of maximum length determined by max_write_len. * Returns 0 or -ve error code. */ - int (*write_string)(struct cgroup *cgrp, struct cftype *cft, + int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer); /* * trigger() callback can be used to get some kick from the @@ -494,7 +496,7 @@ struct cftype { * at all. The private field can be used to determine the * kick type for multiplexing. */ - int (*trigger)(struct cgroup *cgrp, unsigned int event); + int (*trigger)(struct cgroup_subsys_state *css, unsigned int event); int (*release)(struct inode *inode, struct file *file); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7b4d9d79570b..6c416092e324 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,7 +85,7 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont); +extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); static inline bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) -- cgit v1.2.3 From 3b287a505ef4024634beb12a93773254909d5dae Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: convert cgroup_next_sibling() to cgroup_next_child() cgroup is transitioning to using css (cgroup_subsys_state) as the main subsys interface handle instead of cgroup and the iterators will be updated to use css too. The iterators need to walk the cgroup hierarchy and return the css's matching the origin css, which is a bit cumbersome to open code. This patch converts cgroup_next_sibling() to cgroup_next_child() so that it can handle all steps of direct child iteration. This will be used to update iterators to take @css instead of @cgrp. In addition to the new iteration init handling, cgroup_next_child() is restructured so that the different branches share the end of iteration condition check. This patch doesn't change any behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0b91436c68ef..5f9ba5881717 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,7 +779,7 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_sibling(struct cgroup *pos); +struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); /** * cgroup_for_each_child - iterate through children of a cgroup @@ -802,7 +802,7 @@ struct cgroup *cgroup_next_sibling(struct cgroup *pos); #define cgroup_for_each_child(pos, cgrp) \ for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_sibling((pos))) + (pos); (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); -- cgit v1.2.3 From f48e3924dca268c677c4e338e5d91ad9e6fe6b9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: always use cgroup_next_child() to walk the children list There are several places where the children list is accessed directly. This patch converts those places to use cgroup_next_child(). This will help updating the hierarchy iterators to use @css instead of @cgrp. While cgroup_next_child() can be heavy in pathological cases - e.g. a lot of dead children, this shouldn't cause any noticeable behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5f9ba5881717..c288bce428f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -800,9 +800,8 @@ struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); * the start of the next iteration by, for example, bumping the css refcnt. */ #define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ - struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_child((pos), (cgrp))) + for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ + (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); -- cgit v1.2.3 From 492eb21b98f88e411a8bb43d6edcd7d7022add10 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:25 -0400 Subject: cgroup: make hierarchy iterators deal with cgroup_subsys_state instead of cgroup cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because * In most cases, css is the only thing subsystems care about anyway. * On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem * For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier. Most subsystem conversions are straight-forward. Noteworthy changes are * blkio: cgroup_to_blkcg() is no longer used. Removed. * freezer: cgroup_freezer() is no longer used. Removed. * devices: cgroup_to_devcgroup() is no longer used. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe --- include/linux/cgroup.h | 88 ++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c288bce428f8..4bc22f4a1abb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,68 +779,72 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); /** - * cgroup_for_each_child - iterate through children of a cgroup - * @pos: the cgroup * to use as the loop cursor - * @cgrp: cgroup whose children to walk + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Walk @cgrp's children. Must be called under rcu_read_lock(). A child - * cgroup which hasn't finished ->css_online() or already has finished + * Walk @parent's children. Must be called under rcu_read_lock(). A child + * css which hasn't finished ->css_online() or already has finished * ->css_offline() may show up during traversal and it's each subsystem's * responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and - * before starting iterating, a cgroup which finished ->css_online() is + * before starting iterating, a css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ - (pos) = cgroup_next_child((pos), (cgrp))) +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, - struct cgroup *cgroup); -struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos); /** - * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk * - * Walk @cgroup's descendants. Must be called under rcu_read_lock(). A - * descendant cgroup which hasn't finished ->css_online() or already has + * Walk @root's descendants. Must be called under rcu_read_lock(). A + * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_online() is + * iteration, any descendant css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape * state updates of its ancestors. * - * my_online(@cgrp) + * my_online(@css) * { - * Lock @cgrp->parent and @cgrp; - * Inherit state from @cgrp->parent; + * Lock @css's parent and @css; + * Inherit state from the parent; * Unlock both. * } * - * my_update_state(@cgrp) + * my_update_state(@css) * { - * Lock @cgrp; - * Update @cgrp's state; - * Unlock @cgrp; + * Lock @css; + * Update @css's state; + * Unlock @css; * - * cgroup_for_each_descendant_pre(@pos, @cgrp) { + * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos->parent; + * Verify @pos is alive and inherit state from @pos's parent; * Unlock @pos; * } * } @@ -851,8 +855,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any cgroup after the latest update to its - * parent. + * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. @@ -865,25 +868,26 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_descendant_pre(pos, cgroup) \ - for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_pre((pos), (cgroup))) +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) -struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, - struct cgroup *cgroup); +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); /** - * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk * - * Similar to cgroup_for_each_descendant_pre() but performs post-order + * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. Note that the walk visibility guarantee described in * pre-order walk doesn't apply the same to post-order walks. */ -#define cgroup_for_each_descendant_post(pos, cgroup) \ - for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_post((pos), (cgroup))) +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { -- cgit v1.2.3 From 0942eeeef68f9493c1bcb1a52baf612b73fcf9fb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: rename cgroup_iter to cgroup_task_iter cgroup now has multiple iterators and it's quite confusing to have something which walks over tasks of a single cgroup named cgroup_iter. Let's rename it to cgroup_task_iter. While at it, reformat / update comments and replace the overview comment above the interface function decls with proper function comments. Such overview can be useful but function comments should be more than enough here. This is pure rename and doesn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 31 ++++++++----------------------- 1 file changed, 8 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4bc22f4a1abb..ea439794bd9b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -889,31 +889,16 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_iter should be treated as an opaque object */ -struct cgroup_iter { - struct list_head *cset_link; - struct list_head *task; +/* A cgroup_task_iter should be treated as an opaque object */ +struct cgroup_task_iter { + struct list_head *cset_link; + struct list_head *task; }; -/* - * To iterate across the tasks in a cgroup: - * - * 1) call cgroup_iter_start to initialize an iterator - * - * 2) call cgroup_iter_next() to retrieve member tasks until it - * returns NULL or until you want to end the iteration - * - * 3) call cgroup_iter_end() to destroy the iterator. - * - * Or, call cgroup_scan_tasks() to iterate through every task in a - * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling - * the test_task() callback, but not while calling the process_task() - * callback. - */ -void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); -struct task_struct *cgroup_iter_next(struct cgroup *cgrp, - struct cgroup_iter *it); -void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); +void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, + struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From c59cd3d840b1b0a8f996cbbd9132128dcaabbeb9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cgroup_task_iter remember the cgroup being iterated Currently all cgroup_task_iter functions require @cgrp to be passed in, which is superflous and increases chance of usage error. Make cgroup_task_iter remember the cgroup being iterated and drop @cgrp argument from next and end functions. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ea439794bd9b..0287fccd0f54 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -891,14 +891,14 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, /* A cgroup_task_iter should be treated as an opaque object */ struct cgroup_task_iter { + struct cgroup *origin_cgrp; struct list_head *cset_link; struct list_head *task; }; void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, - struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From e535837b1dae17b5a2d76ea1bc22ac1a79354624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: remove struct cgroup_scanner cgroup_scan_tasks() takes a pointer to struct cgroup_scanner as its sole argument and the only function of that struct is packing the arguments of the function call which are consisted of five fields. It's not too unusual to pack parameters into a struct when the number of arguments gets excessive or the whole set needs to be passed around a lot, but neither holds here making it just weird. Drop struct cgroup_scanner and pass the params directly to cgroup_scan_tasks(). Note that struct cpuset_change_nodemask_arg was added to cpuset.c to pass both ->cs and ->newmems pointer to cpuset_change_nodemask() using single data pointer. This doesn't make any functional differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0287fccd0f54..8472ed576b64 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -528,15 +528,6 @@ struct cftype_set { struct cftype *cfts; }; -struct cgroup_scanner { - struct cgroup *cgrp; - int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); - void (*process_task)(struct task_struct *p, - struct cgroup_scanner *scan); - struct ptr_heap *heap; - void *data; -}; - /* * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This * function can be called as long as @cgrp is accessible. @@ -899,7 +890,12 @@ struct cgroup_task_iter { void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); void cgroup_task_iter_end(struct cgroup_task_iter *it); -int cgroup_scan_tasks(struct cgroup_scanner *scan); + +int cgroup_scan_tasks(struct cgroup *cgrp, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); + int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 72ec7029937f0518eff21b8762743c31591684f5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make task iterators deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. This patch converts task iterators to deal with css instead of cgroup. Note that under unified hierarchy, different sets of tasks will be considered belonging to a given cgroup depending on the subsystem in question and making the iterators deal with css instead cgroup provides them with enough information about the iteration. While at it, fix several function comment formats in cpuset.c. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley --- include/linux/cgroup.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8472ed576b64..cd105fce089c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -880,21 +880,22 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_task_iter should be treated as an opaque object */ -struct cgroup_task_iter { - struct cgroup *origin_cgrp; +/* A css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys_state *origin_css; struct list_head *cset_link; struct list_head *task; }; -void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup_task_iter *it); +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); -int cgroup_scan_tasks(struct cgroup *cgrp, - bool (*test)(struct task_struct *, void *), - void (*process)(struct task_struct *, void *), - void *data, struct ptr_heap *heap); +int css_scan_tasks(struct cgroup_subsys_state *css, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 81eeaf0411204f52af8ef78ff107cfca2fcfec1d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cftype->[un]register_event() deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cftype->[un]register_event() is among the remaining couple interfaces which still use struct cgroup. Convert it to cgroup_subsys_state. The conversion is mostly mechanical and removes the last users of mem_cgroup_from_cont() and cg_to_vmpressure(), which are removed. v2: indentation update as suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 10 ++++++---- include/linux/vmpressure.h | 6 ++++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cd105fce089c..b065d24486e6 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -506,16 +506,18 @@ struct cftype { * you want to provide this functionality. Use eventfd_signal() * on eventfd to send notification to userspace. */ - int (*register_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd, const char *args); + int (*register_event)(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, + const char *args); /* * unregister_event() callback will be called when userspace * closes the eventfd or on cgroup removing. * This callback must be implemented, if you want provide * notification functionality. */ - void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd); + void (*unregister_event)(struct cgroup_subsys_state *css, + struct cftype *cft, + struct eventfd_ctx *eventfd); }; /* diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 76be077340ea..b239482bd39d 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -33,10 +33,12 @@ extern void vmpressure_init(struct vmpressure *vmpr); extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css); -extern int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, +extern int vmpressure_register_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, const char *args); -extern void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, +extern void vmpressure_unregister_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd); #else static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, -- cgit v1.2.3 From d99c8727e7bbc01b70e2c57e6127bfab26b868fd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make cgroup_taskset deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cgroup_taskset which is used by the subsystem attach methods is the last cgroup subsystem API which isn't using css as the handle. Update cgroup_taskset_cur_cgroup() to cgroup_taskset_cur_css() and cgroup_taskset_for_each() to take @skip_css instead of @skip_cgrp. The conversions are pretty mechanical. One exception is cpuset::cgroup_cs(), which lost its last user and got removed. This patch shouldn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Daniel Wagner Cc: Ingo Molnar Cc: Matt Helsley Cc: Steven Rostedt --- include/linux/cgroup.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b065d24486e6..d9a970568be9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -562,20 +562,22 @@ int cgroup_task_count(const struct cgroup *cgrp); struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); -struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset); +struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, + int subsys_id); int cgroup_taskset_size(struct cgroup_taskset *tset); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor - * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all + * @skip_css: skip if task's css matches this, %NULL to iterate through all * @tset: taskset to iterate */ -#define cgroup_taskset_for_each(task, skip_cgrp, tset) \ +#define cgroup_taskset_for_each(task, skip_css, tset) \ for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) \ - if (!(skip_cgrp) || \ - cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp)) + if (!(skip_css) || \ + cgroup_taskset_cur_css((tset), \ + (skip_css)->ss->subsys_id) != (skip_css)) /* * Control Group subsystem type. -- cgit v1.2.3 From 95109b627ba6a043c181fa5fa45d1c754dd44fbc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: unexport cgroup_css() cgroup_css() no longer has any user left outside cgroup.c proper and we don't want subsystems to grow new usages of the function. cgroup core should always provide the css to use to the subsystems, which will make dynamic creation and destruction of css's across the lifetime of a cgroup much more manageable than exposing the cgroup directly to subsystems and let them dereference css's from it. Make cgroup_css() a static function in cgroup.c. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d9a970568be9..c40e508d54e9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -677,19 +677,6 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) return &parent_cgrp->dummy_css; } -/** - * cgroup_css - obtain a cgroup's css for the specified subsystem - * @cgrp: the cgroup of interest - * @subsys_id: the subsystem of interest - * - * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. - */ -static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, - int subsys_id) -{ - return cgrp->subsys[subsys_id]; -} - /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for -- cgit v1.2.3 From bd8815a6d802fc16a7a106e170593aa05dc17e72 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make css_for_each_descendant() and friends include the origin css in the iteration Previously, all css descendant iterators didn't include the origin (root of subtree) css in the iteration. The reasons were maintaining consistency with css_for_each_child() and that at the time of introduction more use cases needed skipping the origin anyway; however, given that css_is_descendant() considers self to be a descendant, omitting the origin css has become more confusing and looking at the accumulated use cases rather clearly indicates that including origin would result in simpler code overall. While this is a change which can easily lead to subtle bugs, cgroup API including the iterators has recently gone through major restructuring and no out-of-tree changes will be applicable without adjustments making this a relatively acceptable opportunity for this type of change. The conversions are mostly straight-forward. If the iteration block had explicit origin handling before or after, it's moved inside the iteration. If not, if (pos == origin) continue; is added. Some conversions add extra reference get/put around origin handling by consolidating origin handling and the rest. While the extra ref operations aren't strictly necessary, this shouldn't cause any noticeable difference. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Michal Hocko Cc: Jens Axboe Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c40e508d54e9..8ec5b0f38292 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -798,7 +798,8 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * - * Walk @root's descendants. Must be called under rcu_read_lock(). A + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). A * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. @@ -820,13 +821,12 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * * my_update_state(@css) * { - * Lock @css; - * Update @css's state; - * Unlock @css; - * * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos's parent; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } @@ -864,8 +864,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. Note that the walk visibility guarantee described in - * pre-order walk doesn't apply the same to post-order walks. + * traversal instead. @root is included in the iteration and the last + * node to be visited. Note that the walk visibility guarantee described + * in pre-order walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ -- cgit v1.2.3 From e99a03c6f50a699d63b5751e3e88f84e43b037a7 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 1 Aug 2013 15:01:08 -0400 Subject: jbd: use a single printk for jbd_debug() Backport of jbd2 commit 169f1a2a87aae44034da4b9f81be1683d33de6d0 ("jbd2: use a single printk for jbd_debug()") Since the jbd_debug() is implemented with two separate printk() calls, it can lead to corrupted and misleading debug output like the following (see lines marked with "*"): [ 290.339362] (fs/jbd2/journal.c, 203): kjournald2: kjournald2 wakes [ 290.339365] (fs/jbd2/journal.c, 155): kjournald2: commit_sequence=42103, commit_request=42104 [ 290.339369] (fs/jbd2/journal.c, 158): kjournald2: OK, requests differ [* 290.339376] (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: [* 290.339379] (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: want 42104, j_commit_sequence=42103 [* 290.339382] JBD2: starting commit of transaction 42104 [ 290.339410] (fs/jbd2/revoke.c, 566): jbd2_journal_write_revoke_records: Wrote 0 revoke records [ 290.376555] (fs/jbd2/commit.c, 1088): jbd2_journal_commit_transaction: JBD2: commit 42104 complete, head 42079 i.e. the debug output from log_wait_commit and journal_commit_transaction have become interleaved. The output should have been: (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: JBD2: want 42104, j_commit_sequence=42103 (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: starting commit of transaction 42104 It is expected that this is not easy to replicate -- I was only able to cause it on preempt-rt kernels, and even then only under heavy I/O load. Signed-off-by: Paul Gortmaker Signed-off-by: Jan Kara --- include/linux/jbd.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index bc3e57d367fc..31229e0be90b 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -57,16 +57,13 @@ #define JBD_EXPENSIVE_CHECKING extern u8 journal_enable_debug; -#define jbd_debug(n, f, a...) \ - do { \ - if ((n) <= journal_enable_debug) { \ - printk (KERN_DEBUG "(%s, %d): %s: ", \ - __FILE__, __LINE__, __func__); \ - printk (f, ## a); \ - } \ - } while (0) +void __jbd_debug(int level, const char *file, const char *func, + unsigned int line, const char *fmt, ...); + +#define jbd_debug(n, fmt, a...) \ + __jbd_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else -#define jbd_debug(f, a...) /**/ +#define jbd_debug(n, fmt, a...) /**/ #endif static inline void *jbd_alloc(size_t size, gfp_t flags) -- cgit v1.2.3 From 3fa4d7344be0afebd80382ffeea6b1787cccf971 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 26 Jul 2013 12:16:42 +0200 Subject: usb: phy: rename nop_usb_xceiv => usb_phy_gen_xceiv The "nop" driver isn't a do-nothing-stub but supports a couple functions like clock on/off or is able to use a voltage regulator. This patch simply renames the driver to "generic" since it is easy possible to extend it by a simple function istead of writing a complete driver. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi --- include/linux/usb/nop-usb-xceiv.h | 29 ----------------------------- include/linux/usb/usb_phy_gen_xceiv.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 29 deletions(-) delete mode 100644 include/linux/usb/nop-usb-xceiv.h create mode 100644 include/linux/usb/usb_phy_gen_xceiv.h (limited to 'include/linux') diff --git a/include/linux/usb/nop-usb-xceiv.h b/include/linux/usb/nop-usb-xceiv.h deleted file mode 100644 index 148d35171aac..000000000000 --- a/include/linux/usb/nop-usb-xceiv.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __LINUX_USB_NOP_XCEIV_H -#define __LINUX_USB_NOP_XCEIV_H - -#include - -struct nop_usb_xceiv_platform_data { - enum usb_phy_type type; - unsigned long clk_rate; - - /* if set fails with -EPROBE_DEFER if can't get regulator */ - unsigned int needs_vcc:1; - unsigned int needs_reset:1; -}; - -#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) -/* sometimes transceivers are accessed only through e.g. ULPI */ -extern void usb_nop_xceiv_register(void); -extern void usb_nop_xceiv_unregister(void); -#else -static inline void usb_nop_xceiv_register(void) -{ -} - -static inline void usb_nop_xceiv_unregister(void) -{ -} -#endif - -#endif /* __LINUX_USB_NOP_XCEIV_H */ diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h new file mode 100644 index 000000000000..f9a7e7bc925b --- /dev/null +++ b/include/linux/usb/usb_phy_gen_xceiv.h @@ -0,0 +1,29 @@ +#ifndef __LINUX_USB_NOP_XCEIV_H +#define __LINUX_USB_NOP_XCEIV_H + +#include + +struct usb_phy_gen_xceiv_platform_data { + enum usb_phy_type type; + unsigned long clk_rate; + + /* if set fails with -EPROBE_DEFER if can't get regulator */ + unsigned int needs_vcc:1; + unsigned int needs_reset:1; +}; + +#if IS_ENABLED(CONFIG_NOP_USB_XCEIV) +/* sometimes transceivers are accessed only through e.g. ULPI */ +extern void usb_nop_xceiv_register(void); +extern void usb_nop_xceiv_unregister(void); +#else +static inline void usb_nop_xceiv_register(void) +{ +} + +static inline void usb_nop_xceiv_unregister(void) +{ +} +#endif + +#endif /* __LINUX_USB_NOP_XCEIV_H */ -- cgit v1.2.3 From 851cf6e7d6366195d4ee033cdc7787df1a649a14 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 9 Aug 2013 19:51:57 +0530 Subject: jump_label: Split jumplabel ratelimit Commit b202952075f62603bea9bfb6ebc6b0420db11949 ("perf, core: Rate limit perf_sched_events jump_label patching") introduced rate limiting for jump label disabling. The changes were made in the jump label code in order to be more widely available and to keep things tidier. This is all fine, except now jump_label.h includes linux/workqueue.h, which makes it impossible to include jump_label.h from anything that workqueue.h needs. For example, it's now impossible to include jump_label.h from asm/spinlock.h, which is done in proposed pv-ticketlock patches. This patch splits out the rate limiting related changes from jump_label.h into a new file, jump_label_ratelimit.h, to resolve the issue. Signed-off-by: Andrew Jones Link: http://lkml.kernel.org/r/1376058122-8248-10-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- include/linux/jump_label.h | 28 +--------------------------- include/linux/jump_label_ratelimit.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/perf_event.h | 1 + 3 files changed, 36 insertions(+), 27 deletions(-) create mode 100644 include/linux/jump_label_ratelimit.h (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0976fc46d1e0..a5079072da66 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -48,7 +48,6 @@ #include #include -#include #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) @@ -61,12 +60,6 @@ struct static_key { #endif }; -struct static_key_deferred { - struct static_key key; - unsigned long timeout; - struct delayed_work work; -}; - # include # define HAVE_JUMP_LABEL #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ @@ -78,6 +71,7 @@ enum jump_label_type { struct module; +#include #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TRUE_BRANCH 1UL @@ -119,10 +113,7 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry, extern int jump_label_text_reserved(void *start, void *end); extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); -extern void static_key_slow_dec_deferred(struct static_key_deferred *key); extern void jump_label_apply_nops(struct module *mod); -extern void -jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); #define STATIC_KEY_INIT_TRUE ((struct static_key) \ { .enabled = ATOMIC_INIT(1), .entries = (void *)1 }) @@ -131,8 +122,6 @@ jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); #else /* !HAVE_JUMP_LABEL */ -#include - struct static_key { atomic_t enabled; }; @@ -141,10 +130,6 @@ static __always_inline void jump_label_init(void) { } -struct static_key_deferred { - struct static_key key; -}; - static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(atomic_read(&key->enabled)) > 0) @@ -169,11 +154,6 @@ static inline void static_key_slow_dec(struct static_key *key) atomic_dec(&key->enabled); } -static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) -{ - static_key_slow_dec(&key->key); -} - static inline int jump_label_text_reserved(void *start, void *end) { return 0; @@ -187,12 +167,6 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -static inline void -jump_label_rate_limit(struct static_key_deferred *key, - unsigned long rl) -{ -} - #define STATIC_KEY_INIT_TRUE ((struct static_key) \ { .enabled = ATOMIC_INIT(1) }) #define STATIC_KEY_INIT_FALSE ((struct static_key) \ diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h new file mode 100644 index 000000000000..113788389b3d --- /dev/null +++ b/include/linux/jump_label_ratelimit.h @@ -0,0 +1,34 @@ +#ifndef _LINUX_JUMP_LABEL_RATELIMIT_H +#define _LINUX_JUMP_LABEL_RATELIMIT_H + +#include +#include + +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +struct static_key_deferred { + struct static_key key; + unsigned long timeout; + struct delayed_work work; +}; +#endif + +#ifdef HAVE_JUMP_LABEL +extern void static_key_slow_dec_deferred(struct static_key_deferred *key); +extern void +jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); + +#else /* !HAVE_JUMP_LABEL */ +struct static_key_deferred { + struct static_key key; +}; +static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) +{ + static_key_slow_dec(&key->key); +} +static inline void +jump_label_rate_limit(struct static_key_deferred *key, + unsigned long rl) +{ +} +#endif /* HAVE_JUMP_LABEL */ +#endif /* _LINUX_JUMP_LABEL_RATELIMIT_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c43f6eabad5b..226be8da3f85 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -48,6 +48,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include #include #include -- cgit v1.2.3 From 86f8973c1053cb03e1b1b45989a4e144e05b1735 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 8 Aug 2013 16:09:50 +0200 Subject: spi: new controller driver for efm32 SoCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown --- include/linux/platform_data/efm32-spi.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/platform_data/efm32-spi.h (limited to 'include/linux') diff --git a/include/linux/platform_data/efm32-spi.h b/include/linux/platform_data/efm32-spi.h new file mode 100644 index 000000000000..31b19ca1d73a --- /dev/null +++ b/include/linux/platform_data/efm32-spi.h @@ -0,0 +1,14 @@ +#ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ +#define __LINUX_PLATFORM_DATA_EFM32_SPI_H__ + +#include + +/** + * struct efm32_spi_pdata + * @location: pinmux location for the I/O pins (to be written to the ROUTE + * register) + */ +struct efm32_spi_pdata { + u8 location; +}; +#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ */ -- cgit v1.2.3 From 5c6fe01c1fe3140a8fb088d2a9c32548b731c35e Mon Sep 17 00:00:00 2001 From: William Manley Date: Tue, 6 Aug 2013 19:03:14 +0100 Subject: net: igmp: Don't flush routing cache when force_igmp_version is modified The procfs knob /proc/sys/net/ipv4/conf/*/force_igmp_version allows the IGMP protocol version to use to be explicitly set. As a side effect this caused the routing cache to be flushed as it was declared as a DEVINET_SYSCTL_FLUSHING_ENTRY. Flushing is unnecessary and this patch makes it so flushing does not occur. Requested by Hannes Frederic Sowa as he was reviewing other patches adding procfs entries. Suggested-by: Hannes Frederic Sowa Signed-off-by: William Manley Acked-by: Hannes Frederic Sowa Acked-by: Benjamin LaHaise Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index b99cd23f3474..0a4a6cb35338 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -27,9 +27,9 @@ enum IPV4_DEVCONF_TAG, IPV4_DEVCONF_ARPFILTER, IPV4_DEVCONF_MEDIUM_ID, + IPV4_DEVCONF_FORCE_IGMP_VERSION, IPV4_DEVCONF_NOXFRM, IPV4_DEVCONF_NOPOLICY, - IPV4_DEVCONF_FORCE_IGMP_VERSION, IPV4_DEVCONF_ARP_ANNOUNCE, IPV4_DEVCONF_ARP_IGNORE, IPV4_DEVCONF_PROMOTE_SECONDARIES, -- cgit v1.2.3 From 2690048c01f32bf45d1c1e1ab3079bc10ad2aea7 Mon Sep 17 00:00:00 2001 From: William Manley Date: Tue, 6 Aug 2013 19:03:15 +0100 Subject: net: igmp: Allow user-space configuration of igmp unsolicited report interval Adds the new procfs knobs: /proc/sys/net/ipv4/conf/*/igmpv2_unsolicited_report_interval /proc/sys/net/ipv4/conf/*/igmpv3_unsolicited_report_interval Which will allow userspace configuration of the IGMP unsolicited report interval (see below) in milliseconds. The defaults are 10000ms for IGMPv2 and 1000ms for IGMPv3 in accordance with RFC2236 and RFC3376. Background: If an IGMP join packet is lost you will not receive data sent to the multicast group so if no data arrives from that multicast group in a period of time after the IGMP join a second IGMP join will be sent. The delay between joins is the "IGMP Unsolicited Report Interval". Prior to this patch this value was hard coded in the kernel to 10s for IGMPv2 and 1s for IGMPv3. 10s is unsuitable for some use-cases, such as IPTV as it can cause channel change to be slow in the presence of packet loss. This patch allows the value to be overridden from userspace for both IGMPv2 and IGMPv3 such that it can be tuned accoding to the network. Tested with Wireshark and a simple program to join a (non-existent) multicast group. The distribution of timings for the second join differ based upon setting the procfs knobs. igmpvX_unsolicited_report_interval is intended to follow the pattern established by force_igmp_version, and while a procfs entry has been added a corresponding sysctl knob has not as it is my understanding that sysctl is deprecated[1]. [1]: http://lwn.net/Articles/247243/ Signed-off-by: William Manley Acked-by: Hannes Frederic Sowa Acked-by: Benjamin LaHaise Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 0a4a6cb35338..c796ce26c7c0 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -28,6 +28,8 @@ enum IPV4_DEVCONF_ARPFILTER, IPV4_DEVCONF_MEDIUM_ID, IPV4_DEVCONF_FORCE_IGMP_VERSION, + IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL, + IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL, IPV4_DEVCONF_NOXFRM, IPV4_DEVCONF_NOPOLICY, IPV4_DEVCONF_ARP_ANNOUNCE, -- cgit v1.2.3 From 9194731c5f9b2664c882a515b3398a29384a6864 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 16 Jun 2013 16:25:35 +0200 Subject: drm/rcar-du: Rename platform data fields to match what they describe The struct rcar_du_encoder_data encoder::field describes the encoder type, and the rcar_du_encoder_lvds_data and rcar_du_encoder_vga_data structures describe connector properties. Rename them accordingly. Signed-off-by: Laurent Pinchart --- include/linux/platform_data/rcar-du.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/rcar-du.h b/include/linux/platform_data/rcar-du.h index 80587fdbba3e..64cd8635e6e6 100644 --- a/include/linux/platform_data/rcar-du.h +++ b/include/linux/platform_data/rcar-du.h @@ -28,22 +28,29 @@ struct rcar_du_panel_data { struct drm_mode_modeinfo mode; }; -struct rcar_du_encoder_lvds_data { +struct rcar_du_connector_lvds_data { struct rcar_du_panel_data panel; }; -struct rcar_du_encoder_vga_data { +struct rcar_du_connector_vga_data { /* TODO: Add DDC information for EDID retrieval */ }; +/* + * struct rcar_du_encoder_data - Encoder platform data + * @type: the encoder type (RCAR_DU_ENCODER_*) + * @output: the DU output the connector is connected to + * @connector.lvds: platform data for LVDS connectors + * @connector.vga: platform data for VGA connectors + */ struct rcar_du_encoder_data { - enum rcar_du_encoder_type encoder; + enum rcar_du_encoder_type type; unsigned int output; union { - struct rcar_du_encoder_lvds_data lvds; - struct rcar_du_encoder_vga_data vga; - } u; + struct rcar_du_connector_lvds_data lvds; + struct rcar_du_connector_vga_data vga; + } connector; }; struct rcar_du_platform_data { -- cgit v1.2.3 From ef67a902e946ad1ef51040cf287a45cc4714e2b5 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 17 Jun 2013 03:13:11 +0200 Subject: drm/rcar-du: Rework output routing support Split the output routing specification between SoC-internal data, specified in the rcar_du_device_info structure, and board data, passed through platform data. The DU has 5 possible outputs (DPAD0/1, LVDS0/1, TCON). SoC-internal output routing data specify which output are valid, which CRTCs can be connected to the valid outputs, and the type of in-SoC encoder for the output. Platform data then specifies external encoders and the output they are connected to. Signed-off-by: Laurent Pinchart --- include/linux/platform_data/rcar-du.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/rcar-du.h b/include/linux/platform_data/rcar-du.h index 64cd8635e6e6..1a2e9901a22e 100644 --- a/include/linux/platform_data/rcar-du.h +++ b/include/linux/platform_data/rcar-du.h @@ -16,8 +16,18 @@ #include +enum rcar_du_output { + RCAR_DU_OUTPUT_DPAD0, + RCAR_DU_OUTPUT_DPAD1, + RCAR_DU_OUTPUT_LVDS0, + RCAR_DU_OUTPUT_LVDS1, + RCAR_DU_OUTPUT_TCON, + RCAR_DU_OUTPUT_MAX, +}; + enum rcar_du_encoder_type { RCAR_DU_ENCODER_UNUSED = 0, + RCAR_DU_ENCODER_NONE, RCAR_DU_ENCODER_VGA, RCAR_DU_ENCODER_LVDS, }; @@ -39,13 +49,16 @@ struct rcar_du_connector_vga_data { /* * struct rcar_du_encoder_data - Encoder platform data * @type: the encoder type (RCAR_DU_ENCODER_*) - * @output: the DU output the connector is connected to + * @output: the DU output the connector is connected to (RCAR_DU_OUTPUT_*) * @connector.lvds: platform data for LVDS connectors * @connector.vga: platform data for VGA connectors + * + * Encoder platform data describes an on-board encoder, its associated DU SoC + * output, and the connector. */ struct rcar_du_encoder_data { enum rcar_du_encoder_type type; - unsigned int output; + enum rcar_du_output output; union { struct rcar_du_connector_lvds_data lvds; -- cgit v1.2.3 From 64e8674fbe6bc848333a9b7e19f8cc019dde9eab Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:24 -0600 Subject: PCI: Add pci_reset_bridge_secondary_bus() Move the secondary bus reset code from pci_parent_bus_reset() into its own function. Export it as we'll later be calling it from hotplug controllers and elsewhere. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..35c1bc4909f3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); -- cgit v1.2.3 From c88a1f8b96e7384627b918dfabbfc0c615a4a914 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Tue, 6 Aug 2013 22:53:08 +0530 Subject: cpufreq: Store cpufreq policies in a list Policies available in the cpufreq framework are now linked together. They are accessible via cpufreq_policy_list defined in the cpufreq core. [rjw: Fix from Yinghai Lu folded in] Signed-off-by: Lukasz Majewski Signed-off-by: Myungjoo Ham Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 29208923c9d3..431a05d4b4c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -82,6 +82,7 @@ struct cpufreq_policy { struct cpufreq_real_policy user_policy; + struct list_head policy_list; struct kobject kobj; struct completion kobj_unregister; int transition_ongoing; /* Tracks transition status */ -- cgit v1.2.3 From adc97d6a735dbb1e94cb4f1bf0b55f258b349941 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:12 +0530 Subject: cpufreq: Drop the owner field from struct cpufreq_driver We don't need to set .owner = THIS_MODULE any more in cpufreq drivers as this field isn't used any more by the cpufreq core. This patch removes it and updates all dependent drivers accordingly. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 431a05d4b4c9..d568f3975eeb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -179,7 +179,6 @@ __ATTR(_name, 0644, show_##_name, store_##_name) struct cpufreq_driver { - struct module *owner; char name[CPUFREQ_NAME_LEN]; u8 flags; /* -- cgit v1.2.3 From 77409d9bcc0ee3fc309a3d6fd18553f6ec5a9aa6 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 12 Aug 2013 14:21:14 +0530 Subject: regulator: palmas: model SMPS10 as two regulators SMPS10 has two outputs OUT1 and OUT2 and have one input IN1. SMPS10-OUT2 is connected to SMPS10-IN1 and can be configured either in BOOST mode or BYPASS mode. regulator_enable of SMPS10-OUT2 configures it in BOOST mode. For BYPASS mode regulator_allow_bypass() API can be used. SMPS10-OUT1 is connected to SMPS10-OUT2 and can be enabled using regulator_enable(). [ axel.lin@ingics.com : Simplify regulator_desc setting for SMPS10_[OUT1|OUT2] Signed-off-by: J Keerthy Signed-off-by: Laxman Dewangan Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..c06d78af3342 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -160,7 +160,8 @@ enum palmas_regulators { PALMAS_REG_SMPS7, PALMAS_REG_SMPS8, PALMAS_REG_SMPS9, - PALMAS_REG_SMPS10, + PALMAS_REG_SMPS10_OUT2, + PALMAS_REG_SMPS10_OUT1, /* LDO regulators */ PALMAS_REG_LDO1, PALMAS_REG_LDO2, @@ -355,9 +356,9 @@ struct palmas_pmic { int smps123; int smps457; - int range[PALMAS_REG_SMPS10]; - unsigned int ramp_delay[PALMAS_REG_SMPS10]; - unsigned int current_reg_mode[PALMAS_REG_SMPS10]; + int range[PALMAS_REG_SMPS10_OUT1]; + unsigned int ramp_delay[PALMAS_REG_SMPS10_OUT1]; + unsigned int current_reg_mode[PALMAS_REG_SMPS10_OUT1]; }; struct palmas_resource { -- cgit v1.2.3 From 6bdaa63c2957ac04e8d596880f732b79f9c06c3c Mon Sep 17 00:00:00 2001 From: Aravind Gopalakrishnan Date: Fri, 2 Aug 2013 17:43:02 -0500 Subject: pci_ids: Add PCI device ID functions 3 and 4 for newer F15h models. Add PCI device IDs for AMD F15h, model 30h. They will be used in amd_nb.c and amd64_edac.c Signed-off-by: Aravind Gopalakrishnan Signed-off-by: Borislav Petkov --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bed2e89611b..d1fe5d00140a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -518,6 +518,8 @@ #define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303 #define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304 #define PCI_DEVICE_ID_AMD_15H_M10H_F3 0x1403 +#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F3 0x141d +#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F4 0x141e #define PCI_DEVICE_ID_AMD_15H_NB_F0 0x1600 #define PCI_DEVICE_ID_AMD_15H_NB_F1 0x1601 #define PCI_DEVICE_ID_AMD_15H_NB_F2 0x1602 -- cgit v1.2.3 From 4287d824f265451cd10f6d20266b27a207a6cdd7 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 9 Aug 2013 22:27:06 +0200 Subject: PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni Acked-by: Bjorn Helgaas Acked-by: Benjamin Herrenschmidt Tested-by: Daniel Price Tested-by: Thierry Reding Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: x86@kernel.org Cc: Russell King Cc: Tony Luck Cc: Fenghua Yu Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: David S. Miller Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf Signed-off-by: Jason Cooper --- include/linux/msi.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index ee66f3a12fb6..271dfd14a05f 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -51,12 +51,18 @@ struct msi_desc { }; /* - * The arch hook for setup up msi irqs + * The arch hooks to setup up msi irqs. Those functions are + * implemented as weak symbols so that they /can/ be overriden by + * architecture specific code if needed. */ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); int arch_msi_check_device(struct pci_dev* dev, int nvec, int type); +void arch_restore_msi_irqs(struct pci_dev *dev, int irq); + +void default_teardown_msi_irqs(struct pci_dev *dev); +void default_restore_msi_irqs(struct pci_dev *dev, int irq); #endif /* LINUX_MSI_H */ -- cgit v1.2.3 From 0cbdcfcf427b63b9670e56760ef5e67cd7081b35 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 9 Aug 2013 22:27:08 +0200 Subject: PCI: Introduce new MSI chip infrastructure The new struct msi_chip is used to associated an MSI controller with a PCI bus. It is automatically handed down from the root to its children during bus enumeration. This patch provides default (weak) implementations for the architecture- specific MSI functions (arch_setup_msi_irq(), arch_teardown_msi_irq() and arch_msi_check_device()) which check if a PCI device's bus has an attached MSI chip and forward the call appropriately. Signed-off-by: Thierry Reding Signed-off-by: Thomas Petazzoni Acked-by: Bjorn Helgaas Tested-by: Daniel Price Tested-by: Thierry Reding Signed-off-by: Jason Cooper --- include/linux/msi.h | 11 +++++++++++ include/linux/pci.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 271dfd14a05f..090ddadbc838 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -65,4 +65,15 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq); void default_teardown_msi_irqs(struct pci_dev *dev); void default_restore_msi_irqs(struct pci_dev *dev, int irq); +struct msi_chip { + struct module *owner; + struct device *dev; + + int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev, + struct msi_desc *desc); + void (*teardown_irq)(struct msi_chip *chip, unsigned int irq); + int (*check_device)(struct msi_chip *chip, struct pci_dev *dev, + int nvec, int type); +}; + #endif /* LINUX_MSI_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..4044e3c00609 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -433,6 +433,7 @@ struct pci_bus { struct resource busn_res; /* bus numbers routed to this bus */ struct pci_ops *ops; /* configuration access functions */ + struct msi_chip *msi; /* MSI controller */ void *sysdata; /* hook for sys-specific extension */ struct proc_dir_entry *procdir; /* directory entry in /proc/bus/pci */ -- cgit v1.2.3 From 0d5a6db3aa46faafd0212650bfd709d51240d9da Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 9 Aug 2013 22:27:09 +0200 Subject: of: pci: add registry of MSI chips This commit adds a very basic registry of msi_chip structures, so that an IRQ controller driver can register an msi_chip, and a PCIe host controller can find it, based on a 'struct device_node'. Signed-off-by: Thomas Petazzoni Acked-by: Benjamin Herrenschmidt Acked-by: Rob Herring Signed-off-by: Jason Cooper --- include/linux/msi.h | 2 ++ include/linux/of_pci.h | 12 ++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 090ddadbc838..b17ead818aec 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -68,6 +68,8 @@ void default_restore_msi_irqs(struct pci_dev *dev, int irq); struct msi_chip { struct module *owner; struct device *dev; + struct device_node *of_node; + struct list_head list; int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev, struct msi_desc *desc); diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 7a04826018c0..fd9c408631a0 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -2,6 +2,7 @@ #define __OF_PCI_H #include +#include struct pci_dev; struct of_irq; @@ -13,4 +14,15 @@ struct device_node *of_pci_find_child_device(struct device_node *parent, int of_pci_get_devfn(struct device_node *np); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); +#if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI) +int of_pci_msi_chip_add(struct msi_chip *chip); +void of_pci_msi_chip_remove(struct msi_chip *chip); +struct msi_chip *of_pci_find_msi_chip_by_node(struct device_node *of_node); +#else +static inline int of_pci_msi_chip_add(struct msi_chip *chip) { return -EINVAL; } +static inline void of_pci_msi_chip_remove(struct msi_chip *chip) { } +static inline struct msi_chip * +of_pci_find_msi_chip_by_node(struct device_node *of_node) { return NULL; } +#endif + #endif -- cgit v1.2.3 From 5c19e95216b93b0d29c6a4887e69a980edc6fc81 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 5 Aug 2013 14:40:44 +0200 Subject: OF: Add helper for matching against linux,stdout-path devicetrees may have a linux,stdout-path property in the chosen node describing the console device. This adds a helper function to match a device against this property so a driver can call add_preferred_console for a matching device. Signed-off-by: Sascha Hauer Acked-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..429e16801858 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -343,6 +343,8 @@ const char *of_prop_next_string(struct property *prop, const char *cur); s; \ s = of_prop_next_string(prop, s)) +int of_device_is_stdout_path(struct device_node *dn); + #else /* CONFIG_OF */ static inline const char* of_node_full_name(struct device_node *np) @@ -505,6 +507,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_device_is_stdout_path(struct device_node *dn) +{ + return 0; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #define of_property_for_each_u32(np, propname, prop, p, u) \ -- cgit v1.2.3 From 3e635202ce40e4d7ff3fafc18db70c5d28cc6622 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:51 +0300 Subject: usb: phy: tegra: Tegra30 support The Tegra30 USB PHY is a bit different than the Tegra20 PHY: - The EHCI controller supports the HOSTPC register extension, and some of the fields that the PHY needs to modify (PHCD and PTS) have moved to the new HOSTPC register. - Some of the UTMI PLL configuration registers have moved from the USB register space to the Clock-And-Reset controller space. In Tegra30 the clock driver is responsible for configuring the UTMI PLL. - The USBMODE register must be explicitly written to enter host mode. - Certain PHY parameters need to be programmed for optimal signal quality. Support for this will be added in the next patch. The new tegra_phy_soc_config structure is added to describe the differences between the SoCs. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3db274610a1..d3a63c354db9 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -18,6 +18,24 @@ #include #include +/* + * utmi_pll_config_in_car_module: true if the UTMI PLL configuration registers + * should be set up by clk-tegra, false if by the PHY code + * has_hostpc: true if the USB controller has the HOSTPC extension, which + * changes the location of the PHCD and PTS fields + * requires_usbmode_setup: true if the USBMODE register needs to be set to + * enter host mode + * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level + * and hsdiscon_level should be set for adequate signal quality + */ + +struct tegra_phy_soc_config { + bool utmi_pll_config_in_car_module; + bool has_hostpc; + bool requires_usbmode_setup; + bool requires_extra_tuning_parameters; +}; + struct tegra_utmip_config { u8 hssync_start_delay; u8 elastic_limit; @@ -47,6 +65,7 @@ struct tegra_usb_phy { struct regulator *vbus; enum usb_dr_mode mode; void *config; + const struct tegra_phy_soc_config *soc_config; struct usb_phy *ulpi; struct usb_phy u_phy; bool is_legacy_phy; -- cgit v1.2.3 From e497a24d8e18af510879b2ae059ee20a4a58eae8 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:53 +0300 Subject: usb: phy: tegra: Program new PHY parameters The Tegra30 TRM recommends configuration of certain PHY parameters for optimal quality. Program the following registers based on device tree parameters: - UTMIP_XCVR_HSSLEW: HS slew rate control. - UTMIP_HSSQUELCH_LEVEL: HS squelch detector level - UTMIP_HSDISCON_LEVEL: HS disconnect detector level. These registers exist in Tegra20, but programming them hasn't been necessary, so these parameters won't be set on Tegra20 to keep the device trees backward compatible. Additionally, the UTMIP_XCVR_SETUP parameter can be set from fuses instead of a software-programmed value, as the optimal value can vary between invidual boards. The boolean property nvidia,xcvr-setup-use-fuses can be used to enable this behaviour. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3a63c354db9..1de16c324ec8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -41,9 +41,13 @@ struct tegra_utmip_config { u8 elastic_limit; u8 idle_wait_delay; u8 term_range_adj; + bool xcvr_setup_use_fuses; u8 xcvr_setup; u8 xcvr_lsfslew; u8 xcvr_lsrslew; + u8 xcvr_hsslew; + u8 hssquelch_level; + u8 hsdiscon_level; }; enum tegra_usb_phy_port_speed { -- cgit v1.2.3 From 94dfd7edfd5c9b605caf7b562de7a813d216e011 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 3 Jul 2013 22:53:07 +0800 Subject: USB: HCD: support giveback of URB in tasklet context This patch implements the mechanism of giveback of URB in tasklet context, so that hardware interrupt handling time for usb host controller can be saved much, and HCD interrupt handling can be simplified. Motivations: 1), on some arch(such as ARM), DMA mapping/unmapping is a bit time-consuming, for example: when accessing usb mass storage via EHCI on pandaboard, the common length of transfer buffer is 120KB, the time consumed on DMA unmapping may reach hundreds of microseconds; even on A15 based box, the time is still about scores of microseconds 2), on some arch, reading DMA coherent memoery is very time-consuming, the most common example is usb video class driver[1] 3), driver's complete() callback may do much things which is driver specific, so the time is consumed unnecessarily in hardware irq context. 4), running driver's complete() callback in hardware irq context causes that host controller driver has to release its lock in interrupt handler, so reacquiring the lock after return may busy wait a while and increase interrupt handling time. More seriously, releasing the HCD lock makes HCD becoming quite complicated to deal with introduced races. So the patch proposes to run giveback of URB in tasklet context, then time consumed in HCD irq handling doesn't depend on drivers' complete and DMA mapping/unmapping any more, also we can simplify HCD since the HCD lock isn't needed to be released during irq handling. The patch should be reasonable and doable: 1), for drivers, they don't care if the complete() is called in hard irq context or softirq context 2), the biggest change is the situation in which usb_submit_urb() is called in complete() callback, so the introduced tasklet schedule delay might be a con, but it shouldn't be a big deal: - control/bulk asynchronous transfer isn't sensitive to schedule delay - the patch schedules giveback of periodic URBs using tasklet_hi_schedule, so the introduced delay should be very small - for ISOC transfer, generally, drivers submit several URBs concurrently to avoid interrupt delay, so it is OK with the little schedule delay. - for interrupt transfer, generally, drivers only submit one URB at the same time, but interrupt transfer is often used in event report, polling, ... situations, and a little delay should be OK. Considered that HCDs may optimize on submitting URB in complete(), the patch may cause the optimization not working, so introduces one flag to mark if the HCD supports to run giveback URB in tasklet context. When all HCDs are ready, the flag can be removed. [1], http://marc.info/?t=136438111600010&r=1&w=2 Cc: Oliver Neukum Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 1e88377e22f4..a9c7d44bd2ed 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -22,6 +22,7 @@ #ifdef __KERNEL__ #include +#include #define MAX_TOPO_LEVEL 6 @@ -67,6 +68,13 @@ /*-------------------------------------------------------------------------*/ +struct giveback_urb_bh { + bool running; + spinlock_t lock; + struct list_head head; + struct tasklet_struct bh; +}; + struct usb_hcd { /* @@ -139,6 +147,9 @@ struct usb_hcd { resource_size_t rsrc_len; /* memory/io resource length */ unsigned power_budget; /* in mA, 0 = no limit */ + struct giveback_urb_bh high_prio_bh; + struct giveback_urb_bh low_prio_bh; + /* bandwidth_mutex should be taken before adding or removing * any new bus bandwidth constraints: * 1. Before adding a configuration for a new device. @@ -221,6 +232,7 @@ struct hc_driver { #define HCD_USB25 0x0030 /* Wireless USB 1.0 (USB 2.5)*/ #define HCD_USB3 0x0040 /* USB 3.0 */ #define HCD_MASK 0x0070 +#define HCD_BH 0x0100 /* URB complete in BH context */ /* called to init HCD and root hub */ int (*reset) (struct usb_hcd *hcd); @@ -361,6 +373,11 @@ struct hc_driver { int (*find_raw_port_number)(struct usb_hcd *, int); }; +static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) +{ + return hcd->driver->flags & HCD_BH; +} + extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb, int status); -- cgit v1.2.3 From bcc48f1a7a0d40ae2e5a26aff72c2b674fd8b596 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:22 +0800 Subject: USB: introduce usb_device_no_sg_constraint() helper Some host controllers(such as xHCI) can support building packet from discontinuous buffers, so introduce one flag and helper for this kind of host controllers, then the feature can help some applications(such as usbnet) by supporting arbitrary length of sg buffers. Acked-by: Alan Stern Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index acb1b0aa77d8..001629cd1a97 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -337,6 +337,7 @@ struct usb_bus { * the ep queue on a short transfer * with the URB_SHORT_NOT_OK flag set. */ + unsigned no_sg_constraint:1; /* no sg constraint */ unsigned sg_tablesize; /* 0 or largest number of sg list entries */ int devnum_next; /* Next open device number in @@ -684,6 +685,11 @@ static inline bool usb_device_supports_ltm(struct usb_device *udev) return udev->bos->ss_cap->bmAttributes & USB_LTM_SUPPORT; } +static inline bool usb_device_no_sg_constraint(struct usb_device *udev) +{ + return udev && udev->bus && udev->bus->no_sg_constraint; +} + /*-------------------------------------------------------------------------*/ @@ -1253,7 +1259,7 @@ typedef void (*usb_complete_t)(struct urb *); * transfer_buffer. * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's - * max packet size + * max packet size if no_sg_constraint isn't set in 'struct usb_bus' * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3 From 638c5115a794981441246fa8fa5d95c1875af5ba Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:24 +0800 Subject: USBNET: support DMA SG This patch introduces support of DMA SG if the USB host controller which usbnet device is attached to is capable of building packet from discontinuous buffers. The patch supports passing the skb fragment buffers to usb stack directly via urb->sg. Cc: Ben Hutchings Cc: Grant Grundler Cc: Freddy Xin Cc: Alan Stern Acked-by: Oliver Neukum Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index f18d64129f99..2b47e6364e36 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -34,6 +34,7 @@ struct usbnet { struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; + unsigned can_dma_sg:1; /* i/o info: pipes etc */ unsigned in, out; -- cgit v1.2.3 From 3775a209d38aa3a0c7ed89a7d0f529e0230f280e Mon Sep 17 00:00:00 2001 From: Casey Leedom Date: Tue, 6 Aug 2013 15:48:36 +0530 Subject: PCI: Add pci_wait_for_pending_transaction() New routine to avoid duplication of code to wait for pending PCI transactions to complete. Signed-off-by: Casey Leedom Signed-off-by: Vipul Pandya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..e6470016c718 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -914,6 +914,7 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev); void pci_msi_off(struct pci_dev *dev); int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); +int pci_wait_for_pending_transaction(struct pci_dev *dev); int pcix_get_max_mmrbc(struct pci_dev *dev); int pcix_get_mmrbc(struct pci_dev *dev); int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc); -- cgit v1.2.3 From fa6fdb33b486a8afc5439c504da8d581e142c77d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:55 -0700 Subject: driver core: bus_type: add dev_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add dev_groups to struct bus_type which should be used instead of dev_attrs. dev_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..3aec4a68b1d4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @dev_groups: Default attributes of the devices on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -104,8 +105,9 @@ struct bus_type { const char *dev_name; struct device *dev_root; struct bus_attribute *bus_attrs; - struct device_attribute *dev_attrs; + struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; + const struct attribute_group **dev_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3 From ed0617b5c0bcd7fd04053568aa0cc19a977a1f26 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:56 -0700 Subject: driver core: bus_type: add drv_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add drv_groups to struct bus_type which should be used instead of drv_attrs. drv_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3aec4a68b1d4..94d987f128bb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -67,6 +67,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. * @dev_groups: Default attributes of the devices on the bus. + * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -106,8 +107,9 @@ struct bus_type { struct device *dev_root; struct bus_attribute *bus_attrs; struct device_attribute *dev_attrs; /* use dev_groups instead */ - struct driver_attribute *drv_attrs; + struct driver_attribute *drv_attrs; /* use drv_groups instead */ const struct attribute_group **dev_groups; + const struct attribute_group **drv_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3 From 12478ba077adf8b53be6101b80dd8a65e4df9ea6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:57 -0700 Subject: driver core: bus_type: add bus_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add bus_groups to struct bus_type which should be used instead of bus_attrs. bus_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 94d987f128bb..26e23b22ed0a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver @@ -105,9 +106,10 @@ struct bus_type { const char *name; const char *dev_name; struct device *dev_root; - struct bus_attribute *bus_attrs; + struct bus_attribute *bus_attrs; /* use bus_groups instead */ struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; /* use drv_groups instead */ + const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; -- cgit v1.2.3 From 2d854e5738cded368a0759f85b1197f5c044513d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:02:30 +0200 Subject: context_tracing: Fix guest accounting with native vtime 1) If context tracking is enabled with native vtime accounting (which combo is useless except for dev testing), we call vtime_guest_enter() and vtime_guest_exit() on host <-> guest switches. But those are stubs in this configurations. As a result, cputime is not correctly flushed on kvm context switches. 2) If context tracking runs but is disabled on some CPUs, those CPUs end up calling __guest_enter/__guest_exit which in turn call vtime_account_system(). We don't want to call this because we run in tick based accounting for these CPUs. Refactor the guest_enter/guest_exit code such that all combinations finally work. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 52 +++++++++++++++++----------------------- 1 file changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index fc09d7b0dacf..5984f2556d13 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -20,25 +20,6 @@ struct context_tracking { } state; }; -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -56,9 +37,6 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); -extern void guest_enter(void); -extern void guest_exit(void); - static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -81,21 +59,35 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline enum ctx_state exception_enter(void) { return 0; } +static inline void exception_exit(enum ctx_state prev_ctx) { } +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) { } +#endif /* !CONFIG_CONTEXT_TRACKING */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void guest_enter(void); +extern void guest_exit(void); +#else static inline void guest_enter(void) { - __guest_enter(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; } static inline void guest_exit(void) { - __guest_exit(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; } - -static inline enum ctx_state exception_enter(void) { return 0; } -static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) { } -#endif /* !CONFIG_CONTEXT_TRACKING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #endif -- cgit v1.2.3 From 5b206d48e58204e84d249c4eb18651a1ff7a1274 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:05:14 +0200 Subject: vtime: Update a few comments Update a stale comment from the old vtime era and document some locking that might be non obvious. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 5984f2556d13..d883ff0dd8fc 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -72,8 +72,9 @@ extern void guest_exit(void); static inline void guest_enter(void) { /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. + * This is running in ioctl context so its safe + * to assume that it's the stime pending cputime + * to flush. */ vtime_account_system(current); current->flags |= PF_VCPU; @@ -81,10 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ + /* Flush the guest cputime we spent on the guest */ vtime_account_system(current); current->flags &= ~PF_VCPU; } -- cgit v1.2.3 From 2e70933866ace52091a3c11a5c104c063ab0c445 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 00:55:25 +0200 Subject: nohz: Only enable context tracking on full dynticks CPUs The context tracking subsystem has the ability to selectively enable the tracking on any defined subset of CPU. This means that we can define a CPU range that doesn't run the context tracking and another range that does. Now what we want in practice is to enable the tracking on full dynticks CPUs only. In order to perform this, we just need to pass our full dynticks CPU range selection from the full dynticks subsystem to the context tracking. This way we can spare the overhead of RCU user extended quiescent state and vtime maintainance on the CPUs that are outside the full dynticks range. Just keep in mind the raw context tracking itself is still necessary everywhere. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d883ff0dd8fc..1ae37c708c63 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -34,6 +34,8 @@ static inline bool context_tracking_active(void) return __this_cpu_read(context_tracking.active); } +extern void context_tracking_cpu_set(int cpu); + extern void user_enter(void); extern void user_exit(void); -- cgit v1.2.3 From b9d10be7a8e88fdcb12540387c219cdde87b0795 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Mon, 12 Aug 2013 09:45:53 -0600 Subject: ACPI / processor: Acquire writer lock to update CPU maps CPU system maps are protected with reader/writer locks. The reader lock, get_online_cpus(), assures that the maps are not updated while holding the lock. The writer lock, cpu_hotplug_begin(), is used to udpate the cpu maps along with cpu_maps_update_begin(). However, the ACPI processor handler updates the cpu maps without holding the the writer lock. acpi_map_lsapic() is called from acpi_processor_hotadd_init() to update cpu_possible_mask and cpu_present_mask. acpi_unmap_lsapic() is called from acpi_processor_remove() to update cpu_possible_mask. Currently, they are either unprotected or protected with the reader lock, which is not correct. For example, the get_online_cpus() below is supposed to assure that cpu_possible_mask is not changed while the code is iterating with for_each_possible_cpu(). get_online_cpus(); for_each_possible_cpu(cpu) { : } put_online_cpus(); However, this lock has no protection with CPU hotplug since the ACPI processor handler does not use the writer lock when it updates cpu_possible_mask. The reader lock does not serialize within the readers. This patch protects them with the writer lock with cpu_hotplug_begin() along with cpu_maps_update_begin(), which must be held before calling cpu_hotplug_begin(). It also protects arch_register_cpu() / arch_unregister_cpu(), which creates / deletes a sysfs cpu device interface. For this purpose it changes cpu_hotplug_begin() and cpu_hotplug_done() to global and exports them in cpu.h. Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- include/linux/cpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..956c0a16566f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -172,6 +172,8 @@ extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ +extern void cpu_hotplug_begin(void); +extern void cpu_hotplug_done(void); extern void get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); @@ -197,6 +199,8 @@ static inline void cpu_hotplug_driver_unlock(void) #else /* CONFIG_HOTPLUG_CPU */ +static inline void cpu_hotplug_begin(void) {} +static inline void cpu_hotplug_done(void) {} #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) -- cgit v1.2.3 From 7bb587f4eef8f71ce589f360ab99bb54ab0fc85d Mon Sep 17 00:00:00 2001 From: Zhangfei Gao Date: Fri, 28 Jun 2013 20:39:12 +0800 Subject: dmaengine: add interface of dma_get_slave_channel Suggested by Arnd, add dma_get_slave_channel interface Dma host driver could get specific channel specificied by request line, rather than filter. host example: static struct dma_chan *xx_of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { struct xx_dma_dev *d = ofdma->of_dma_data; unsigned int request = dma_spec->args[0]; if (request > d->dma_requests) return NULL; return dma_get_slave_channel(&(d->chans[request].vc.chan)); } probe: of_dma_controller_register((&op->dev)->of_node, xx_of_dma_simple_xlate, d); Signed-off-by: Zhangfei Gao Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cb286b1acdb6..c271608e862e 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -995,6 +995,7 @@ int dma_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); +struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); struct dma_chan *net_dma_find_channel(void); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) #define dma_request_slave_channel_compat(mask, x, y, dev, name) \ -- cgit v1.2.3 From 4ca0c0d4784fa82d68733f7793e3487023e12282 Mon Sep 17 00:00:00 2001 From: Padmavathi Venna Date: Mon, 12 Aug 2013 15:19:52 +0530 Subject: ASoC: Samsung: I2S: Modify the I2S driver to support I2S on Exynos5420 Exynos5420 added support for I2S TDM mode. For this, there are some register changes in the I2S controller. This patch adds the relevant register changes to support I2S in normal mode. This patch adds a quirk for TDM mode and if TDM mode is present all the relevent changes will be applied. Signed-off-by: Padmavathi Venna Reviewed-by: Tomasz Figa Signed-off-by: Mark Brown --- include/linux/platform_data/asoc-s3c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h index 88272591a895..9efc04dd255a 100644 --- a/include/linux/platform_data/asoc-s3c.h +++ b/include/linux/platform_data/asoc-s3c.h @@ -36,6 +36,7 @@ struct samsung_i2s { */ #define QUIRK_NO_MUXPSR (1 << 2) #define QUIRK_NEED_RSTCLR (1 << 3) +#define QUIRK_SUPPORTS_TDM (1 << 4) /* Quirks of the I2S controller */ u32 quirks; dma_addr_t idma_addr; -- cgit v1.2.3 From 0c1836a6563decc6de8622b2ed71523b3bdceb65 Mon Sep 17 00:00:00 2001 From: Amit Daniel Kachhap Date: Mon, 24 Jun 2013 16:20:27 +0530 Subject: thermal: exynos: Move exynos_thermal.h from include/* to driver/* folder This patch renames and moves include/linux/platform_data/exynos_thermal.h to drivers/thermal/samsung/exynos_tmu.h. This file movement is needed as exynos SOC's are not supporting non-DT based platforms and this file now just contains exynos tmu driver related definations. Also struct freq_clip_table is now moved to exynos_thermal_common.c as it fixes the compilation issue occuring because now this new tmu header file is included in tmu driver c file and not in the common thermal header file. Acked-by: Kukjin Kim Acked-by: Jonghwa Lee Acked-by: Eduardo Valentin Signed-off-by: Amit Daniel Kachhap Signed-off-by: Eduardo Valentin --- include/linux/platform_data/exynos_thermal.h | 119 --------------------------- 1 file changed, 119 deletions(-) delete mode 100644 include/linux/platform_data/exynos_thermal.h (limited to 'include/linux') diff --git a/include/linux/platform_data/exynos_thermal.h b/include/linux/platform_data/exynos_thermal.h deleted file mode 100644 index da7e6274b175..000000000000 --- a/include/linux/platform_data/exynos_thermal.h +++ /dev/null @@ -1,119 +0,0 @@ -/* - * exynos_thermal.h - Samsung EXYNOS TMU (Thermal Management Unit) - * - * Copyright (C) 2011 Samsung Electronics - * Donggeun Kim - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _LINUX_EXYNOS_THERMAL_H -#define _LINUX_EXYNOS_THERMAL_H -#include - -enum calibration_type { - TYPE_ONE_POINT_TRIMMING, - TYPE_TWO_POINT_TRIMMING, - TYPE_NONE, -}; - -enum soc_type { - SOC_ARCH_EXYNOS4210 = 1, - SOC_ARCH_EXYNOS, -}; -/** - * struct freq_clip_table - * @freq_clip_max: maximum frequency allowed for this cooling state. - * @temp_level: Temperature level at which the temperature clipping will - * happen. - * @mask_val: cpumask of the allowed cpu's where the clipping will take place. - * - * This structure is required to be filled and passed to the - * cpufreq_cooling_unregister function. - */ -struct freq_clip_table { - unsigned int freq_clip_max; - unsigned int temp_level; - const struct cpumask *mask_val; -}; - -/** - * struct exynos_tmu_platform_data - * @threshold: basic temperature for generating interrupt - * 25 <= threshold <= 125 [unit: degree Celsius] - * @threshold_falling: differntial value for setting threshold - * of temperature falling interrupt. - * @trigger_levels: array for each interrupt levels - * [unit: degree Celsius] - * 0: temperature for trigger_level0 interrupt - * condition for trigger_level0 interrupt: - * current temperature > threshold + trigger_levels[0] - * 1: temperature for trigger_level1 interrupt - * condition for trigger_level1 interrupt: - * current temperature > threshold + trigger_levels[1] - * 2: temperature for trigger_level2 interrupt - * condition for trigger_level2 interrupt: - * current temperature > threshold + trigger_levels[2] - * 3: temperature for trigger_level3 interrupt - * condition for trigger_level3 interrupt: - * current temperature > threshold + trigger_levels[3] - * @trigger_level0_en: - * 1 = enable trigger_level0 interrupt, - * 0 = disable trigger_level0 interrupt - * @trigger_level1_en: - * 1 = enable trigger_level1 interrupt, - * 0 = disable trigger_level1 interrupt - * @trigger_level2_en: - * 1 = enable trigger_level2 interrupt, - * 0 = disable trigger_level2 interrupt - * @trigger_level3_en: - * 1 = enable trigger_level3 interrupt, - * 0 = disable trigger_level3 interrupt - * @gain: gain of amplifier in the positive-TC generator block - * 0 <= gain <= 15 - * @reference_voltage: reference voltage of amplifier - * in the positive-TC generator block - * 0 <= reference_voltage <= 31 - * @noise_cancel_mode: noise cancellation mode - * 000, 100, 101, 110 and 111 can be different modes - * @type: determines the type of SOC - * @efuse_value: platform defined fuse value - * @cal_type: calibration type for temperature - * @freq_clip_table: Table representing frequency reduction percentage. - * @freq_tab_count: Count of the above table as frequency reduction may - * applicable to only some of the trigger levels. - * - * This structure is required for configuration of exynos_tmu driver. - */ -struct exynos_tmu_platform_data { - u8 threshold; - u8 threshold_falling; - u8 trigger_levels[4]; - bool trigger_level0_en; - bool trigger_level1_en; - bool trigger_level2_en; - bool trigger_level3_en; - - u8 gain; - u8 reference_voltage; - u8 noise_cancel_mode; - u32 efuse_value; - - enum calibration_type cal_type; - enum soc_type type; - struct freq_clip_table freq_tab[4]; - unsigned int freq_tab_count; -}; -#endif /* _LINUX_EXYNOS_THERMAL_H */ -- cgit v1.2.3 From bd0779370588386e4a67ba5d0b176cfded8e6a53 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Aug 2013 18:13:20 +0200 Subject: netfilter: nfnetlink_queue: allow to attach expectations to conntracks This patch adds the capability to attach expectations via nfnetlink_queue. This is required by conntrack helpers that trigger expectations based on the first packet seen like the TFTP and the DHCPv6 user-space helpers. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 655d5d198d49..e2cf786be22f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -325,6 +325,8 @@ struct nfq_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); + int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report); }; extern struct nfq_ct_hook __rcu *nfq_ct_hook; -- cgit v1.2.3 From 35ef10da65d43211f4cd7e7822cbb3becdfc0ae1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: rename cgroup_subsys_state->dput_work and its callback function css (cgroup_subsys_state) will become RCU protected and there will be two stages which require punting to work item during release. To prepare for using the work item for multiple times, rename css->dput_work to css->destroy_work and css_dput_fn() to css_free_work_fn() and move work item initialization from css init to right before the actual usage. This reorganization doesn't introduce any behavior change. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8ec5b0f38292..12d66fee26f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -80,7 +80,7 @@ struct cgroup_subsys_state { struct css_id __rcu *id; /* Used to put @cgroup->dentry on the last css_put() */ - struct work_struct dput_work; + struct work_struct destroy_work; }; /* bits in struct cgroup_subsys_state flags field */ -- cgit v1.2.3 From 0ae78e0bf10ac38ab53548e18383afc9997eca22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: add cgroup_subsys_state->parent With the planned unified hierarchy, css's (cgroup_subsys_state) will be RCU protected and allowed to be attached and detached dynamically over the course of a cgroup's lifetime. This means that css's will stay accessible after being detached from its cgroup - the matching pointer in cgroup->subsys[] cleared - for ref draining and RCU grace period. cgroup core still wants to guarantee that the parent css is never destroyed before its children and css_parent() always returns the parent regardless of the state of the child css as long as it's accessible. This patch makes css's hold onto their parents and adds css->parent so that the parent css is never detroyed before its children and can be determined without consulting the cgroups. cgroup->dummy_css is also updated to point to the parent dummy_css; however, it doesn't need to worry about object lifetime as the parent cgroup is already pinned by the child. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 12d66fee26f8..8a5dc91fbaad 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -75,6 +75,9 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; + /* the parent css */ + struct cgroup_subsys_state *parent; + unsigned long flags; /* ID for this css, if possible */ struct css_id __rcu *id; @@ -666,15 +669,7 @@ struct cgroup_subsys { static inline struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { - struct cgroup *parent_cgrp = css->cgroup->parent; - - if (!parent_cgrp) - return NULL; - - if (css->ss) - return parent_cgrp->subsys[css->ss->subsys_id]; - else - return &parent_cgrp->dummy_css; + return css->parent; } /** -- cgit v1.2.3 From 73e80ed8007fc48a6deeb295ba37159fad274bd2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:55 -0400 Subject: cgroup: add __rcu modifier to cgroup->subsys[] For the planned unified hierarchy, each css (cgroup_subsys_state) will be RCU protected so that it can be created and destroyed individually while allowing RCU accesses. Previous changes ensured that all cgroup->subsys[] accesses use the cgroup_css() accessor. This patch adds __rcu modifier to cgroup->subsys[], add matching RCU dereference in cgroup_css() and convert all assignments to either rcu_assign_pointer() or RCU_INIT_POINTER(). This change prepares for the actual RCUfication of css's and doesn't introduce any visible behavior change. The conversion is verified with sparse and all accesses are properly RCU annotated. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8a5dc91fbaad..eb200b5794e7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -204,7 +204,7 @@ struct cgroup { struct cgroup_name __rcu *name; /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; -- cgit v1.2.3 From b4f173752a56187bd55752b0474429202f2ab1d3 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Mon, 6 May 2013 14:19:19 -0600 Subject: ARM: tegra: disable LP2 cpuidle state if PCIe is enabled Tegra20 HW appears to have a bug such that PCIe device interrupts, whether they are legacy IRQs or MSI, are lost when LP2 is enabled. To work around this, simply disable LP2 if any PCIe devices with interrupts are present. Detect this via the IRQ domain map operation. This is slightly over-conservative; if a device with an interrupt is present but the driver does not actually use them, LP2 will still be disabled. However, this is a reasonable trade-off which enables a simpler workaround. Signed-off-by: Stephen Warren Tested-by: Thierry Reding Acked-by: Thierry Reding --- include/linux/tegra-cpuidle.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/tegra-cpuidle.h (limited to 'include/linux') diff --git a/include/linux/tegra-cpuidle.h b/include/linux/tegra-cpuidle.h new file mode 100644 index 000000000000..dda3647242a4 --- /dev/null +++ b/include/linux/tegra-cpuidle.h @@ -0,0 +1,19 @@ +/* + * Copyright (c) 2013, NVIDIA CORPORATION. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __LINUX_TEGRA_CPUIDLE_H__ +#define __LINUX_TEGRA_CPUIDLE_H__ + +void tegra_cpuidle_pcie_irqs_in_use(void); + +#endif -- cgit v1.2.3 From fc4eba58b4c1462ff3d6247b66fb47d6928db6d2 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 14 Aug 2013 01:03:46 +0200 Subject: ipv6: make unsolicited report intervals configurable for mld Commit cab70040dfd95ee32144f02fade64f0cb94f31a0 ("net: igmp: Reduce Unsolicited report interval to 1s when using IGMPv3") and 2690048c01f32bf45d1c1e1ab3079bc10ad2aea7 ("net: igmp: Allow user-space configuration of igmp unsolicited report interval") by William Manley made igmp unsolicited report intervals configurable per interface and corrected the interval of unsolicited igmpv3 report messages resendings to 1s. Same needs to be done for IPv6: MLDv1 (RFC2710 7.10.): 10 seconds MLDv2 (RFC3810 9.11.): 1 second Both intervals are configurable via new procfs knobs mldv1_unsolicited_report_interval and mldv2_unsolicited_report_interval. (also added .force_mld_version to ipv6_devconf_dflt to bring structs in line without semantic changes) v2: a) Joined documentation update for IPv4 and IPv6 MLD/IGMP unsolicited_report_interval procfs knobs. b) incorporate stylistic feedback from William Manley v3: a) add new DEVCONF_* values to the end of the enum (thanks to David Miller) Cc: Cong Wang Cc: William Manley Cc: Benjamin LaHaise Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 850e95bc766c..77a478462d8e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -19,6 +19,8 @@ struct ipv6_devconf { __s32 rtr_solicit_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; + __s32 mldv1_unsolicited_report_interval; + __s32 mldv2_unsolicited_report_interval; #ifdef CONFIG_IPV6_PRIVACY __s32 use_tempaddr; __s32 temp_valid_lft; -- cgit v1.2.3 From f20104de55a212a9742d8df1807f1f29dc95b748 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: replace cgroup->css_kill_cnt with ->nr_css Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. With the planned unified hierarchy, css's will be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, css's will be individually RCU protected instead of being tied to the cgroup. cgroup->css_kill_cnt is used during cgroup destruction to wait for css reference count disable; however, this model doesn't work once css's lifetimes are managed separately from cgroup's. This patch replaces it with cgroup->nr_css which is an cgroup_mutex protected integer counting the number of attached css's. The count is incremented from online_css() and decremented after refcnt kill is confirmed. If the count reaches zero and the cgroup is marked dead, the second stage of cgroup destruction is kicked off. If a cgroup doesn't have any css attached at the time of rmdir, cgroup_destroy_locked() now invokes the second stage directly as no css kill confirmation would happen. cgroup_offline_fn() - the second step of cgroup destruction - is renamed to cgroup_destroy_css_killed() and now expects to be called with cgroup_mutex held. While this patch changes how css destruction is punted to work items, it shouldn't change any visible behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index eb200b5794e7..80dca872f4d4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -171,6 +171,9 @@ struct cgroup { */ int id; + /* the number of attached css's */ + int nr_css; + /* * We link our 'sibling' struct into our parent's 'children'. * Our children link their 'sibling' into our 'children'. @@ -234,7 +237,6 @@ struct cgroup { /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; - atomic_t css_kill_cnt; /* List of events which userspace want to receive */ struct list_head event_list; -- cgit v1.2.3 From 09a503ea3a816b285b0b402b7f785eaec0c7a7e1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: decouple cgroup_subsys_state destruction from cgroup destruction Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. css's are created when the associated cgroup is created and destroyed when it gets destroyed. Also, individual css's aren't RCU protected but the whole cgroup is. With the planned unified hierarchy, css's will need to be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, this patch decouples css destruction from cgroup destruction - offline_css() invocation and the final css_put() are moved from cgroup_destroy_css_killed() to css_killed_work_fn(). Now each css is individually offlined and put as its reference count is killed instead of waiting for all css's attached to the cgroup to finish refcnt killing and then proceeding to offlining and putting them together. While this changes the order of destruction operations, the changes shouldn't be noticeable to cgroup subsystems or userland. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 80dca872f4d4..71e77e7cdb6f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,7 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* Used to put @cgroup->dentry on the last css_put() */ + /* percpu_ref killing and putting dentry on the last css_put() */ struct work_struct destroy_work; }; -- cgit v1.2.3 From 0c21ead136a900c36f1ab74fd7d09a306dc31324 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:51 -0400 Subject: cgroup: RCU protect each cgroup_subsys_state release With the planned unified hierarchy, individual css's will be created and destroyed dynamically across the lifetime of a cgroup. To enable such usages, css destruction is being decoupled from cgroup destruction. Most of the destruction path has been decoupled but the actual free of css still depends on cgroup free path. When all css refs are drained, css_release() kicks off css_free_work_fn() which puts the cgroup. When the cgroup refcnt reaches zero, cgroup_diput() is invoked which in turn schedules RCU free of the cgroup. After a grace period, all css's are freed along with the cgroup itself. This patch moves the RCU grace period and css freeing from cgroup release path to css release path. css_release(), instead of kicking off css_free_work_fn() directly, schedules RCU callback css_free_rcu_fn() which in turn kicks off css_free_work_fn() after a RCU grace period. css_free_work_fn() is updated to free the css directly. The five-way punting - percpu ref kill confirmation, a work item, percpu ref release, RCU grace period, and again a work item - is quite hairy but the work items are there only to provide process context and the actual sequence is kill confirm -> release -> RCU free, which isn't simple but not too crazy. This removes cgroup_css() usage after offline_css() allowing clearing cgroup->subsys[] from offline_css(), which makes it consistent with online_css() and brings it closer to proper lifetime management for individual css's. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 71e77e7cdb6f..c24bd0b9f93a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,8 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* percpu_ref killing and putting dentry on the last css_put() */ + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; struct work_struct destroy_work; }; -- cgit v1.2.3 From 13b3006b8ebd60926a60fc378ff6fe8affa9a194 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Sat, 10 Aug 2013 18:52:18 +0200 Subject: dma: mmp_pdma: add filter function PXA peripherals need to obtain specific DMA request ids which will eventually be stored in the DRCMR register. Currently, clients are expected to store that number inside the slave config block as slave_id, which is unfortunately incompatible with the way DMA resources are handled in DT environments. This patch adds a filter function which stores the filter parameter passed in by of-dma.c into the channel's drcmr register. For backward compatability, cfg->slave_id is still used if set to a non-zero value. Signed-off-by: Daniel Mack Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/dma/mmp-pdma.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/dma/mmp-pdma.h (limited to 'include/linux') diff --git a/include/linux/dma/mmp-pdma.h b/include/linux/dma/mmp-pdma.h new file mode 100644 index 000000000000..2dc9b2bc18fc --- /dev/null +++ b/include/linux/dma/mmp-pdma.h @@ -0,0 +1,15 @@ +#ifndef _MMP_PDMA_H_ +#define _MMP_PDMA_H_ + +struct dma_chan; + +#ifdef CONFIG_MMP_PDMA +bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param); +#else +static inline bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param) +{ + return false; +} +#endif + +#endif /* _MMP_PDMA_H_ */ -- cgit v1.2.3 From f0c03956ac40fdc4fbce7bed262ae74ac372e765 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 13 Aug 2013 15:05:38 +0200 Subject: netfilter: export xt_rpfilter.h to userland This file contains the API for the match "rpfilter", hence it should be exported to userland. Signed-off-by: Nicolas Dichtel Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_rpfilter.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/netfilter/xt_rpfilter.h (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_rpfilter.h b/include/linux/netfilter/xt_rpfilter.h deleted file mode 100644 index 8358d4f71952..000000000000 --- a/include/linux/netfilter/xt_rpfilter.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _XT_RPATH_H -#define _XT_RPATH_H - -#include - -enum { - XT_RPFILTER_LOOSE = 1 << 0, - XT_RPFILTER_VALID_MARK = 1 << 1, - XT_RPFILTER_ACCEPT_LOCAL = 1 << 2, - XT_RPFILTER_INVERT = 1 << 3, -#ifdef __KERNEL__ - XT_RPFILTER_OPTION_MASK = XT_RPFILTER_LOOSE | - XT_RPFILTER_VALID_MARK | - XT_RPFILTER_ACCEPT_LOCAL | - XT_RPFILTER_INVERT, -#endif -}; - -struct xt_rpfilter_info { - __u8 flags; -}; - -#endif -- cgit v1.2.3 From 38c67328ac79cb9eaf61b5d4750fe3b9cff0dd15 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 13 Aug 2013 15:05:39 +0200 Subject: netfilter: export xt_HMARK.h to userland This file contains the API for the target "HMARK", hence it should be exported to userland. Signed-off-by: Nicolas Dichtel Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_HMARK.h | 50 -------------------------------------- 1 file changed, 50 deletions(-) delete mode 100644 include/linux/netfilter/xt_HMARK.h (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_HMARK.h b/include/linux/netfilter/xt_HMARK.h deleted file mode 100644 index 826fc5807577..000000000000 --- a/include/linux/netfilter/xt_HMARK.h +++ /dev/null @@ -1,50 +0,0 @@ -#ifndef XT_HMARK_H_ -#define XT_HMARK_H_ - -#include - -enum { - XT_HMARK_SADDR_MASK, - XT_HMARK_DADDR_MASK, - XT_HMARK_SPI, - XT_HMARK_SPI_MASK, - XT_HMARK_SPORT, - XT_HMARK_DPORT, - XT_HMARK_SPORT_MASK, - XT_HMARK_DPORT_MASK, - XT_HMARK_PROTO_MASK, - XT_HMARK_RND, - XT_HMARK_MODULUS, - XT_HMARK_OFFSET, - XT_HMARK_CT, - XT_HMARK_METHOD_L3, - XT_HMARK_METHOD_L3_4, -}; -#define XT_HMARK_FLAG(flag) (1 << flag) - -union hmark_ports { - struct { - __u16 src; - __u16 dst; - } p16; - struct { - __be16 src; - __be16 dst; - } b16; - __u32 v32; - __be32 b32; -}; - -struct xt_hmark_info { - union nf_inet_addr src_mask; - union nf_inet_addr dst_mask; - union hmark_ports port_mask; - union hmark_ports port_set; - __u32 flags; - __u16 proto_mask; - __u32 hashrnd; - __u32 hmodulus; - __u32 hoffset; /* Mark offset to start from */ -}; - -#endif /* XT_HMARK_H_ */ -- cgit v1.2.3 From 7cabf491eb6d52ea7f166b287702890cae0c803d Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Mon, 15 Jul 2013 10:20:56 +0530 Subject: iommu/fsl: Add additional iommu attributes required by the PAMU driver. Added the following domain attributes for the FSL PAMU driver: 1. Added new iommu stash attribute, which allows setting of the LIODN specific stash id parameter through IOMMU API. 2. Added an attribute for enabling/disabling DMA to a particular memory window. 3. Added domain attribute to check for PAMUV1 specific constraints. Signed-off-by: Varun Sethi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 3aeb7305e2f5..7ea319e95b47 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -58,10 +58,26 @@ struct iommu_domain { #define IOMMU_CAP_CACHE_COHERENCY 0x1 #define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ +/* + * Following constraints are specifc to FSL_PAMUV1: + * -aperture must be power of 2, and naturally aligned + * -number of windows must be power of 2, and address space size + * of each window is determined by aperture size / # of windows + * -the actual size of the mapped region of a window must be power + * of 2 starting with 4KB and physical address must be naturally + * aligned. + * DOMAIN_ATTR_FSL_PAMUV1 corresponds to the above mentioned contraints. + * The caller can invoke iommu_domain_get_attr to check if the underlying + * iommu implementation supports these constraints. + */ + enum iommu_attr { DOMAIN_ATTR_GEOMETRY, DOMAIN_ATTR_PAGING, DOMAIN_ATTR_WINDOWS, + DOMAIN_ATTR_FSL_PAMU_STASH, + DOMAIN_ATTR_FSL_PAMU_ENABLE, + DOMAIN_ATTR_FSL_PAMUV1, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From 65f382fd0c8fa483713c0971de9f1dfb4cf1ad9c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:12:32 +0200 Subject: context_tracking: Ground setup for static key use Prepare for using a static key in the context tracking subsystem. This will help optimizing the off case on its many users: * user_enter, user_exit, exception_enter, exception_exit, guest_enter, guest_exit, vtime_*() Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 1ae37c708c63..c138c24bad1a 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct context_tracking { @@ -22,6 +23,7 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_in_user(void) @@ -67,6 +69,14 @@ static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ + +#ifdef CONFIG_CONTEXT_TRACKING_FORCE +extern void context_tracking_init(void); +#else +static inline void context_tracking_init(void) { } +#endif /* CONFIG_CONTEXT_TRACKING_FORCE */ + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void guest_enter(void); extern void guest_exit(void); -- cgit v1.2.3 From ad65782fba507d91a0a98f519b59e79cac1b474c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize main APIs off case with static key Optimize user and exception entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes to be nopped (at least we hope so...). If this proves not be enough in the long term, we'll need to bring an exception slow path by re-routing the exception handlers. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index c138c24bad1a..38ab60b3f3a6 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -38,23 +38,40 @@ static inline bool context_tracking_active(void) extern void context_tracking_cpu_set(int cpu); -extern void user_enter(void); -extern void user_exit(void); +extern void context_tracking_user_enter(void); +extern void context_tracking_user_exit(void); + +static inline void user_enter(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_enter(); + +} +static inline void user_exit(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_exit(); +} static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; + if (!static_key_false(&context_tracking_enabled)) + return 0; + prev_ctx = this_cpu_read(context_tracking.state); - user_exit(); + context_tracking_user_exit(); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { - if (prev_ctx == IN_USER) - user_enter(); + if (static_key_false(&context_tracking_enabled)) { + if (prev_ctx == IN_USER) + context_tracking_user_enter(); + } } extern void context_tracking_task_switch(struct task_struct *prev, -- cgit v1.2.3 From 48d6a816a8bf36e2a197c322697323003bdc1cfe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize guest APIs off case with static key Optimize guest entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes overhead to be minimized. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 38ab60b3f3a6..8854eadb2142 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -95,8 +95,23 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void guest_enter(void); -extern void guest_exit(void); +static inline void guest_enter(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_enter(current); + else + current->flags |= PF_VCPU; +} + +static inline void guest_exit(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_exit(current); + else + current->flags &= ~PF_VCPU; +} #else static inline void guest_enter(void) { -- cgit v1.2.3 From 73d424f9af7b571276e6284617cb59726d47bf12 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:42:13 +0200 Subject: context_tracking: Optimize context switch off case with static keys No need for syscall slowpath if no CPU is full dynticks, rather nop this in this case. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8854eadb2142..e070ea5dadac 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -40,6 +40,8 @@ extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); extern void context_tracking_user_exit(void); +extern void __context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next); static inline void user_enter(void) { @@ -74,8 +76,12 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } -extern void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next); +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) +{ + if (static_key_false(&context_tracking_enabled)) + __context_tracking_task_switch(prev, next); +} #else static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } @@ -112,6 +118,7 @@ static inline void guest_exit(void) else current->flags &= ~PF_VCPU; } + #else static inline void guest_enter(void) { -- cgit v1.2.3 From e7358b3bc0d7fcec0e7a724477f06db2b0c68e21 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 02:15:49 +0200 Subject: context_tracking: Split low level state headers We plan to use the context tracking static key on inline vtime APIs. For this we need to include the context tracking headers from those of vtime. However vtime headers need to stay low level because they are included in hardirq.h that mostly contains standalone definitions. But context_tracking.h includes sched.h for a few task_struct references, therefore it wouldn't be sensible to include it from vtime.h To solve this, lets split the context tracking headers and move out the pure state definitions that only require a few low level headers. We can safely include that small part in vtime.h later. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 31 +-------------------------- include/linux/context_tracking_state.h | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 30 deletions(-) create mode 100644 include/linux/context_tracking_state.h (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index e070ea5dadac..82ec4870e064 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -2,40 +2,12 @@ #define _LINUX_CONTEXT_TRACKING_H #include -#include #include -#include +#include #include -struct context_tracking { - /* - * When active is false, probes are unset in order - * to minimize overhead: TIF flags are cleared - * and calls to user_enter/exit are ignored. This - * may be further optimized using static keys. - */ - bool active; - enum ctx_state { - IN_KERNEL = 0, - IN_USER, - } state; -}; - #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; -DECLARE_PER_CPU(struct context_tracking, context_tracking); - -static inline bool context_tracking_in_user(void) -{ - return __this_cpu_read(context_tracking.state) == IN_USER; -} - -static inline bool context_tracking_active(void) -{ - return __this_cpu_read(context_tracking.active); -} - extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); @@ -83,7 +55,6 @@ static inline void context_tracking_task_switch(struct task_struct *prev, __context_tracking_task_switch(prev, next); } #else -static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } static inline enum ctx_state exception_enter(void) { return 0; } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h new file mode 100644 index 000000000000..0f1979d0674f --- /dev/null +++ b/include/linux/context_tracking_state.h @@ -0,0 +1,39 @@ +#ifndef _LINUX_CONTEXT_TRACKING_STATE_H +#define _LINUX_CONTEXT_TRACKING_STATE_H + +#include +#include + +struct context_tracking { + /* + * When active is false, probes are unset in order + * to minimize overhead: TIF flags are cleared + * and calls to user_enter/exit are ignored. This + * may be further optimized using static keys. + */ + bool active; + enum ctx_state { + IN_KERNEL = 0, + IN_USER, + } state; +}; + +#ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; +DECLARE_PER_CPU(struct context_tracking, context_tracking); + +static inline bool context_tracking_in_user(void) +{ + return __this_cpu_read(context_tracking.state) == IN_USER; +} + +static inline bool context_tracking_active(void) +{ + return __this_cpu_read(context_tracking.active); +} +#else +static inline bool context_tracking_in_user(void) { return false; } +static inline bool context_tracking_active(void) { return false; } +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif -- cgit v1.2.3 From 2d4b84739f0acf61f37267b4e80c5bd85fb90a7e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Jul 2013 20:29:43 +0200 Subject: hardirq: Split preempt count mask definitions In order to use static keys with vtime APIs, we'll need to add static keys headers to vtime.h hardirq.h then becomes a problem because it needs vtime.h for irqtime accounting in irq_enter/irq_exit, but it's often included just to get the irq mask definitions in the task preempt_count field and the APIs that come along: in_interrupt(), in_hardirq(), etc... Some very low level arch headers sometimes need these masks and APIs such as arch/m68k/include/asm/irqflags.h for example. But they don't want to include hardirq.h if vtime.h, jump_label.h and even workqueue.h come along. Including such bloated high level header from arch headers can quickly result in circular headers dependency that crash the build. So let's split hardirq.h in two parts: * preempt_mask.h that gathers all the preempt_count definitions and the APIs associated. This one is considered low level and can be safely included anywhere. * hardirq.h that includes the previous one. It defines the irq entry/exit APIs. To avoid future circular headers dependencies, the preempt_mask.h inclusion can replace hardirq.h on files that don't implement irq low level handlers but just need the atomic/context check APIs. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/hardirq.h | 117 +---------------------------------------- include/linux/preempt_mask.h | 122 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 123 insertions(+), 116 deletions(-) create mode 100644 include/linux/preempt_mask.h (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 05bcc0903766..ccfe17c5c8da 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -1,126 +1,11 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H -#include +#include #include #include #include -#include -/* - * We put the hardirq and softirq counter into the preemption - * counter. The bitmask has the following meaning: - * - * - bits 0-7 are the preemption count (max preemption depth: 256) - * - bits 8-15 are the softirq count (max # of softirqs: 256) - * - * The hardirq count can in theory reach the same as NR_IRQS. - * In reality, the number of nested IRQS is limited to the stack - * size as well. For archs with over 1000 IRQS it is not practical - * to expect that they will all nest. We give a max of 10 bits for - * hardirq nesting. An arch may choose to give less than 10 bits. - * m68k expects it to be 8. - * - * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) - * - bit 26 is the NMI_MASK - * - bit 27 is the PREEMPT_ACTIVE flag - * - * PREEMPT_MASK: 0x000000ff - * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x03ff0000 - * NMI_MASK: 0x04000000 - */ -#define PREEMPT_BITS 8 -#define SOFTIRQ_BITS 8 -#define NMI_BITS 1 - -#define MAX_HARDIRQ_BITS 10 - -#ifndef HARDIRQ_BITS -# define HARDIRQ_BITS MAX_HARDIRQ_BITS -#endif - -#if HARDIRQ_BITS > MAX_HARDIRQ_BITS -#error HARDIRQ_BITS too high! -#endif - -#define PREEMPT_SHIFT 0 -#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) -#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) - -#define __IRQ_MASK(x) ((1UL << (x))-1) - -#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) -#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) -#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) -#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) - -#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) -#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) -#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) -#define NMI_OFFSET (1UL << NMI_SHIFT) - -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) - -#ifndef PREEMPT_ACTIVE -#define PREEMPT_ACTIVE_BITS 1 -#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) -#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) -#endif - -#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) -#error PREEMPT_ACTIVE is too low! -#endif - -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) - -/* - * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? - */ -#define in_irq() (hardirq_count()) -#define in_softirq() (softirq_count()) -#define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) - -#if defined(CONFIG_PREEMPT_COUNT) -# define PREEMPT_CHECK_OFFSET 1 -#else -# define PREEMPT_CHECK_OFFSET 0 -#endif - -/* - * Are we running in atomic context? WARNING: this macro cannot - * always detect atomic context; in particular, it cannot know about - * held spinlocks in non-preemptible kernels. Thus it should not be - * used in the general case to determine whether sleeping is possible. - * Do not use in_atomic() in driver code. - */ -#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) - -/* - * Check whether we were atomic before we did preempt_disable(): - * (used by the scheduler, *after* releasing the kernel lock) - */ -#define in_atomic_preempt_off() \ - ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) - -#ifdef CONFIG_PREEMPT_COUNT -# define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#else -# define preemptible() 0 -#endif #if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h new file mode 100644 index 000000000000..931bc616219f --- /dev/null +++ b/include/linux/preempt_mask.h @@ -0,0 +1,122 @@ +#ifndef LINUX_PREEMPT_MASK_H +#define LINUX_PREEMPT_MASK_H + +#include +#include + +/* + * We put the hardirq and softirq counter into the preemption + * counter. The bitmask has the following meaning: + * + * - bits 0-7 are the preemption count (max preemption depth: 256) + * - bits 8-15 are the softirq count (max # of softirqs: 256) + * + * The hardirq count can in theory reach the same as NR_IRQS. + * In reality, the number of nested IRQS is limited to the stack + * size as well. For archs with over 1000 IRQS it is not practical + * to expect that they will all nest. We give a max of 10 bits for + * hardirq nesting. An arch may choose to give less than 10 bits. + * m68k expects it to be 8. + * + * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) + * - bit 26 is the NMI_MASK + * - bit 27 is the PREEMPT_ACTIVE flag + * + * PREEMPT_MASK: 0x000000ff + * SOFTIRQ_MASK: 0x0000ff00 + * HARDIRQ_MASK: 0x03ff0000 + * NMI_MASK: 0x04000000 + */ +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define NMI_BITS 1 + +#define MAX_HARDIRQ_BITS 10 + +#ifndef HARDIRQ_BITS +# define HARDIRQ_BITS MAX_HARDIRQ_BITS +#endif + +#if HARDIRQ_BITS > MAX_HARDIRQ_BITS +#error HARDIRQ_BITS too high! +#endif + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) +#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) + +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + +#ifndef PREEMPT_ACTIVE +#define PREEMPT_ACTIVE_BITS 1 +#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) +#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) +#endif + +#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) +#error PREEMPT_ACTIVE is too low! +#endif + +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) + +/* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? + */ +#define in_irq() (hardirq_count()) +#define in_softirq() (softirq_count()) +#define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + +#if defined(CONFIG_PREEMPT_COUNT) +# define PREEMPT_CHECK_OFFSET 1 +#else +# define PREEMPT_CHECK_OFFSET 0 +#endif + +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ +#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) + +/* + * Check whether we were atomic before we did preempt_disable(): + * (used by the scheduler, *after* releasing the kernel lock) + */ +#define in_atomic_preempt_off() \ + ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) + +#ifdef CONFIG_PREEMPT_COUNT +# define preemptible() (preempt_count() == 0 && !irqs_disabled()) +#else +# define preemptible() 0 +#endif + +#endif /* LINUX_PREEMPT_MASK_H */ -- cgit v1.2.3 From a5725ac23bf4ff79656ac2c317c323e261327fb3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 16 Jul 2013 18:50:52 +0200 Subject: vtime: Describe overriden functions in dedicated arch headers If the arch overrides some generic vtime APIs, let it describe these on a dedicated and standalone header. This way it becomes convenient to include it in vtime generic headers without irrelevant stuff in such a low level header. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman Cc: Martin Schwidefsky Cc: Heiko Carstens --- include/linux/vtime.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index b1dd2db80076..2ad073915e8c 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,6 +1,10 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#include +#endif + struct task_struct; #ifdef CONFIG_VIRT_CPU_ACCOUNTING -- cgit v1.2.3 From b04934061330a4a449cfce703c97d887c3e11cd7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 03:10:15 +0200 Subject: vtime: Optimize full dynticks accounting off case with static keys If no CPU is in the full dynticks range, we can avoid the full dynticks cputime accounting through generic vtime along with its overhead and use the traditional tick based accounting instead. Let's do this and nope the off case with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 6 ++-- include/linux/vtime.h | 70 ++++++++++++++++++++++++++++++++++------ 2 files changed, 63 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 82ec4870e064..158158704c30 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -74,8 +74,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -83,8 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 2ad073915e8c..f5b72b364bda 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,22 +1,68 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#include #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include #endif + struct task_struct; +/* + * vtime_accounting_enabled() definitions/declarations + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +static inline bool vtime_accounting_enabled(void) { return true; } +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static inline bool vtime_accounting_enabled(void) +{ + if (static_key_false(&context_tracking_enabled)) { + if (context_tracking_active()) + return true; + } + + return false; +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +static inline bool vtime_accounting_enabled(void) { return false; } +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ + + +/* + * Common vtime APIs + */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifdef __ARCH_HAS_VTIME_TASK_SWITCH extern void vtime_task_switch(struct task_struct *prev); +#else +extern void vtime_common_task_switch(struct task_struct *prev); +static inline void vtime_task_switch(struct task_struct *prev) +{ + if (vtime_accounting_enabled()) + vtime_common_task_switch(prev); +} +#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ + extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); extern void vtime_account_user(struct task_struct *tsk); -extern void vtime_account_irq_enter(struct task_struct *tsk); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } -#endif +#ifdef __ARCH_HAS_VTIME_ACCOUNT +extern void vtime_account_irq_enter(struct task_struct *tsk); +#else +extern void vtime_common_account_irq_enter(struct task_struct *tsk); +static inline void vtime_account_irq_enter(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_common_account_irq_enter(tsk); +} +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -24,14 +70,20 @@ static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } static inline void vtime_account_user(struct task_struct *tsk) { } static inline void vtime_account_irq_enter(struct task_struct *tsk) { } -static inline bool vtime_accounting_enabled(void) { return false; } -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_account_irq_exit(struct task_struct *tsk); -extern bool vtime_accounting_enabled(void); +extern void vtime_gen_account_irq_exit(struct task_struct *tsk); + +static inline void vtime_account_irq_exit(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_gen_account_irq_exit(tsk); +} + extern void vtime_user_enter(struct task_struct *tsk); + static inline void vtime_user_exit(struct task_struct *tsk) { vtime_account_user(tsk); @@ -39,7 +91,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); -#else +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_account_irq_exit(struct task_struct *tsk) { /* On hard|softirq exit we always account to hard|softirq cputime */ -- cgit v1.2.3 From 460775df4680b4593d8449bc171008578625a850 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks state checks with static keys These APIs are frequenctly accessed and priority is given to optimize the full dynticks off-case in order to let distros enable this feature without suffering from significant performance regressions. Let's inline these APIs and optimize them with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 9180f4b85e6d..c60b079e1b37 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -10,6 +10,8 @@ #include #include #include +#include +#include #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -158,15 +160,34 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL +extern bool tick_nohz_full_running; +extern cpumask_var_t tick_nohz_full_mask; + +static inline bool tick_nohz_full_enabled(void) +{ + if (!static_key_false(&context_tracking_enabled)) + return false; + + return tick_nohz_full_running; +} + +static inline bool tick_nohz_full_cpu(int cpu) +{ + if (!tick_nohz_full_enabled()) + return false; + + return cpumask_test_cpu(cpu, tick_nohz_full_mask); +} + extern void tick_nohz_init(void); -extern int tick_nohz_full_cpu(int cpu); extern void tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); extern void tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } -static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline bool tick_nohz_full_enabled(void) { return false; } +static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -- cgit v1.2.3 From d13508f9440e46dccac6a2dd48d51a73b2207482 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks's sched hooks with static keys Scheduler IPIs and task context switches are serious fast path. Let's try to hide as much as we can the impact of full dynticks APIs' off case that are called on these sites through the use of static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index c60b079e1b37..a7ef1d6fceb6 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -180,20 +180,32 @@ static inline bool tick_nohz_full_cpu(int cpu) } extern void tick_nohz_init(void); -extern void tick_nohz_full_check(void); +extern void __tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); -extern void tick_nohz_task_switch(struct task_struct *tsk); +extern void __tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } -static inline void tick_nohz_full_check(void) { } +static inline void __tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -static inline void tick_nohz_task_switch(struct task_struct *tsk) { } +static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } #endif +static inline void tick_nohz_full_check(void) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_full_check(); +} + +static inline void tick_nohz_task_switch(struct task_struct *tsk) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_task_switch(tsk); +} + # ifdef CONFIG_CPU_IDLE_GOV_MENU extern void menu_hrtimer_cancel(void); -- cgit v1.2.3 From b81eec09a484c588ead035003ce7555ca8a9963a Mon Sep 17 00:00:00 2001 From: Bill Huang Date: Thu, 8 Aug 2013 04:45:05 -0700 Subject: mfd: palmas: Add power off control Hook up "pm_power_off" to palmas power off routine if there is DT property "ti,system-power-controller" defined, so platform which is powered by this regulator can be powered off properly. Acked-by: Nishanth Menon Signed-off-by: Mallikarjun Kasoju Signed-off-by: Bill Huang Signed-off-by: Lee Jones --- include/linux/mfd/palmas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..061cce0b119a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -258,6 +258,7 @@ struct palmas_platform_data { */ int mux_from_pdata; u8 pad1, pad2; + bool pm_off; struct palmas_pmic_platform_data *pmic_pdata; struct palmas_gpadc_platform_data *gpadc_pdata; -- cgit v1.2.3 From 6446221c14ef3bf58754cf1948631128dbe62700 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 12 Aug 2013 10:37:18 +0200 Subject: ARM: pxa: ssp: add pxa_ssp_request_of() Add a function to lookup ssp devices from device tree. This way, users can reference the ssp devices in order to register to them. Signed-off-by: Daniel Mack Acked-by: Haojian Zhuang Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 467cc6307b62..49444203328a 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -21,6 +21,8 @@ #include #include +#include + /* * SSP Serial Port Registers @@ -190,6 +192,8 @@ struct ssp_device { int irq; int drcmr_rx; int drcmr_tx; + + struct device_node *of_node; }; /** @@ -218,11 +222,18 @@ static inline u32 pxa_ssp_read_reg(struct ssp_device *dev, u32 reg) #ifdef CONFIG_ARCH_PXA struct ssp_device *pxa_ssp_request(int port, const char *label); void pxa_ssp_free(struct ssp_device *); +struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node, + const char *label); #else static inline struct ssp_device *pxa_ssp_request(int port, const char *label) { return NULL; } +static inline struct ssp_device *pxa_ssp_request_of(const struct device_node *n, + const char *name) +{ + return NULL; +} static inline void pxa_ssp_free(struct ssp_device *ssp) {} #endif -- cgit v1.2.3 From e81c8f18afc4fdd6e34d8c83814b8b5134dbb30f Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 6 Aug 2013 18:42:34 +0530 Subject: pinctrl: pinconf-generic: add generic APIs for mapping pinctrl node Add generic APIs to map the DT node and its sub node in pinconf generic driver. These APIs can be used from driver to parse the DT node who uses the pinconf generic APIs for defining their nodes. Changes from V1: - Add generic property for pins and functions in pinconf-generic. - Add APIs to map the DT and subnode. - Move common utils APIs to the pinctrl-utils from this file. - Update the binding document accordingly. Changes from V2: - Rebased the pinctrl binding doc on top of Stephen's cleanup. - Rename properties "pinctrl-pins" and "pinctrl-function" to "pins" and "function". Signed-off-by: Laxman Dewangan Reviewed-by: Stephen Warren Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index bf7e989abcb5..a472b93292a3 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -137,6 +137,12 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param return PIN_CONF_PACKED(param, argument); } +int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, + struct device_node *np, struct pinctrl_map **map, + unsigned *reserved_maps, unsigned *num_maps); +int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *np_config, struct pinctrl_map **map, + unsigned *num_maps); #endif /* CONFIG_GENERIC_PINCONF */ #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */ -- cgit v1.2.3 From 0a8d3e2412841c6b1dab1006fd5f7ab5b689db21 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 6 Aug 2013 18:42:35 +0530 Subject: pinctrl: palmas: add pincontrol driver TI Palmas series Power Management IC have multiple pins which can be configured for different functionality. This pins can be configured for different function. Also their properties like pull up/down, open drain enable/disable are configurable. Add support for pincontrol driver Palmas series device like TPS65913, TPS80036. The driver supports to be register from DT only. Changes from V1: - Add generic property for pins and functions in pinconf-generic. - Add APIs to map the DT and subnode. - Move common utils APIs to the pinctrl-utils from this file. - Update the binding document accordingly. Changes from V2: - Add ack by Lee. - Correct the binding docs. Signed-off-by: Laxman Dewangan Acked-by: Lee Jones Reviewed-by: Stephen Warren Signed-off-by: Linus Walleij --- include/linux/mfd/palmas.h | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..2891f7cd902e 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -449,7 +449,7 @@ enum usb_irq_events { #define PALMAS_DVFS_BASE 0x180 #define PALMAS_PMU_CONTROL_BASE 0x1A0 #define PALMAS_RESOURCE_BASE 0x1D4 -#define PALMAS_PU_PD_OD_BASE 0x1F4 +#define PALMAS_PU_PD_OD_BASE 0x1F0 #define PALMAS_LED_BASE 0x200 #define PALMAS_INTERRUPT_BASE 0x210 #define PALMAS_USB_OTG_BASE 0x250 @@ -1734,16 +1734,20 @@ enum usb_irq_events { #define PALMAS_REGEN3_CTRL_MODE_ACTIVE_SHIFT 0 /* Registers for function PAD_CONTROL */ -#define PALMAS_PU_PD_INPUT_CTRL1 0x0 -#define PALMAS_PU_PD_INPUT_CTRL2 0x1 -#define PALMAS_PU_PD_INPUT_CTRL3 0x2 -#define PALMAS_OD_OUTPUT_CTRL 0x4 -#define PALMAS_POLARITY_CTRL 0x5 -#define PALMAS_PRIMARY_SECONDARY_PAD1 0x6 -#define PALMAS_PRIMARY_SECONDARY_PAD2 0x7 -#define PALMAS_I2C_SPI 0x8 -#define PALMAS_PU_PD_INPUT_CTRL4 0x9 -#define PALMAS_PRIMARY_SECONDARY_PAD3 0xA +#define PALMAS_OD_OUTPUT_CTRL2 0x2 +#define PALMAS_POLARITY_CTRL2 0x3 +#define PALMAS_PU_PD_INPUT_CTRL1 0x4 +#define PALMAS_PU_PD_INPUT_CTRL2 0x5 +#define PALMAS_PU_PD_INPUT_CTRL3 0x6 +#define PALMAS_PU_PD_INPUT_CTRL5 0x7 +#define PALMAS_OD_OUTPUT_CTRL 0x8 +#define PALMAS_POLARITY_CTRL 0x9 +#define PALMAS_PRIMARY_SECONDARY_PAD1 0xA +#define PALMAS_PRIMARY_SECONDARY_PAD2 0xB +#define PALMAS_I2C_SPI 0xC +#define PALMAS_PU_PD_INPUT_CTRL4 0xD +#define PALMAS_PRIMARY_SECONDARY_PAD3 0xE +#define PALMAS_PRIMARY_SECONDARY_PAD4 0xF /* Bit definitions for PU_PD_INPUT_CTRL1 */ #define PALMAS_PU_PD_INPUT_CTRL1_RESET_IN_PD 0x40 @@ -2501,6 +2505,15 @@ enum usb_irq_events { #define PALMAS_PU_PD_GPIO_CTRL1 0x6 #define PALMAS_PU_PD_GPIO_CTRL2 0x7 #define PALMAS_OD_OUTPUT_GPIO_CTRL 0x8 +#define PALMAS_GPIO_DATA_IN2 0x9 +#define PALMAS_GPIO_DATA_DIR2 0x0A +#define PALMAS_GPIO_DATA_OUT2 0x0B +#define PALMAS_GPIO_DEBOUNCE_EN2 0x0C +#define PALMAS_GPIO_CLEAR_DATA_OUT2 0x0D +#define PALMAS_GPIO_SET_DATA_OUT2 0x0E +#define PALMAS_PU_PD_GPIO_CTRL3 0x0F +#define PALMAS_PU_PD_GPIO_CTRL4 0x10 +#define PALMAS_OD_OUTPUT_GPIO_CTRL2 0x11 /* Bit definitions for GPIO_DATA_IN */ #define PALMAS_GPIO_DATA_IN_GPIO_7_IN 0x80 -- cgit v1.2.3 From 1542d9c35d8166c54e0616574954a0f48449f331 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:03 +0300 Subject: usb: chipidea: move vbus regulator operation to core The vbus regulator is a common element for USB vbus operation, So, move it from glue layer to core. Tested-by: Marek Vasut Signed-off-by: Michael Grzeschik Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 25629948c842..ce4e1aa071b3 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -24,6 +24,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 void (*notify_event) (struct ci_hdrc *ci, unsigned event); + struct regulator *reg_vbus; }; /* Default offset of capability registers */ -- cgit v1.2.3 From 577b232fc9caba1b6f7a3bb9901c00b10e0ca1ba Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:08 +0300 Subject: usb: chipidea: add flag CI_HDRC_DUAL_ROLE_NOT_OTG Since we need otgsc to know vbus's status at some chipidea controllers even it is peripheral-only mode. Besides, some SoCs (eg, AR9331 SoC) don't have otgsc register even the DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS. We inroduce flag CI_HDRC_DUAL_ROLE_NOT_OTG to indicate if the controller is dual role, but not supports OTG. If this flag is not set, we follow the rule that if DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS, then this controller is otg capable. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index ce4e1aa071b3..10a607ce9090 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -20,6 +20,11 @@ struct ci_hdrc_platform_data { #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) #define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) + /* + * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, + * but otg is not supported (no register otgsc). + */ +#define CI_HDRC_DUAL_ROLE_NOT_OTG BIT(4) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 -- cgit v1.2.3 From d268e9bc23f5df4a2f4167da246d277c2a468d3d Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:14 +0300 Subject: usb: chipidea: retire flag CI_HDRC_PULLUP_ON_VBUS Currently, the controller only runs when the ci->vbus_active is true. So the flag CI_HDRC_PULLUP_ON_VBUS is useless no longer. If the user doesn't have otgsc, he/she needs to change ci_handle_vbus_change to update ci->vbus_active. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 10a607ce9090..7d399671a566 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -18,7 +18,6 @@ struct ci_hdrc_platform_data { unsigned long flags; #define CI_HDRC_REGS_SHARED BIT(0) #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) -#define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) /* * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, -- cgit v1.2.3 From 5c32b35b004f5ef70dcf62bbc42b8bed1e50b471 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:31 -0600 Subject: PCI: Add hotplug_slot_ops.reset_slot() This optional callback allows hotplug controllers to perform slot specific resets. These may be necessary in cases where a normal secondary bus reset can interact with controller logic and expose spurious hotplugs. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci_hotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8db71dcd6337..bd32109e607e 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -63,6 +63,9 @@ enum pcie_link_width { * @get_adapter_status: Called to get see if an adapter is present in the slot or not. * If this field is NULL, the value passed in the struct hotplug_slot_info * will be used when this value is requested by a user. + * @reset_slot: Optional interface to allow override of a bus reset for the + * slot for cases where a secondary bus reset can result in spurious + * hotplug events or where a slot can be reset independent of the bus. * * The table of function pointers that is passed to the hotplug pci core by a * hotplug pci driver. These functions are called by the hotplug pci core when @@ -80,6 +83,7 @@ struct hotplug_slot_ops { int (*get_attention_status) (struct hotplug_slot *slot, u8 *value); int (*get_latch_status) (struct hotplug_slot *slot, u8 *value); int (*get_adapter_status) (struct hotplug_slot *slot, u8 *value); + int (*reset_slot) (struct hotplug_slot *slot, int probe); }; /** -- cgit v1.2.3 From 090a3c5322e900f468b3205b76d0837003ad57b2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:55 -0600 Subject: PCI: Add pci_reset_slot() and pci_reset_bus() Sometimes pci_reset_function() is not sufficient. We have cases where devices do not support any kind of reset, but there might be multiple functions on the bus preventing pci_reset_function() from doing a secondary bus reset. We also have cases where a device will advertise that it supports a PM reset, but really does nothing on D3hot->D0 (graphics cards are notorious for this). These devices often also have more than one function, so even blacklisting PM reset for them wouldn't allow a secondary bus reset through pci_reset_function(). If a driver supports multiple devices it should have the ability to induce a bus reset when it needs to. This patch provides that ability through pci_reset_slot() and pci_reset_bus(). It's the caller's responsibility when using these interfaces to understand that all of the devices in or below the slot (or on or below the bus) will be reset and therefore should be under control of the caller. PCI state of all the affected devices is saved and restored around these resets, but internal state of all of the affected devices is reset (which should be the intention). Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 35c1bc4909f3..1a8fd3464daf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,8 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_slot(struct pci_slot *slot); +int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); -- cgit v1.2.3 From 9a3d2b9beefd5b07c1d8f70ded01b88f203ee304 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 14 Aug 2013 14:06:05 -0600 Subject: PCI: Add pci_probe_reset_slot() and pci_probe_reset_bus() Users of pci_reset_bus() and pci_reset_slot() need a way to probe whether the bus or slot supports reset. Add trivial helper functions and export them as vfio-pci will make use of these. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1a8fd3464daf..daf40cd851df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,7 +924,9 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); +int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From b05e92545d9582be15699e4a33d0f93ac00b37dd Mon Sep 17 00:00:00 2001 From: Franky Lin Date: Sat, 10 Aug 2013 12:27:26 +0200 Subject: brcmfmac: abstract tx packet processing functions Abstract brcmf_sdio_txpkt_prep and brcmf_sdio_txpkt_postp as a preparation of chained tx packets for host side tx glomming. Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Arend van Spriel Signed-off-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/platform_data/brcmfmac-sdio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h index b7174998c24a..e75dcbf2b230 100644 --- a/include/linux/platform_data/brcmfmac-sdio.h +++ b/include/linux/platform_data/brcmfmac-sdio.h @@ -94,6 +94,10 @@ void __init brcmfmac_init_pdata(void) * Set this to true if the SDIO host controller has higher align requirement * than 32 bytes for each scatterlist item. * + * sd_head_align: alignment requirement for start of data buffer + * + * sd_sgentry_align: length alignment requirement for each sg entry + * * power_on: This function is called by the brcmfmac when the module gets * loaded. This can be particularly useful for low power devices. The platform * spcific routine may for example decide to power up the complete device. @@ -121,6 +125,8 @@ struct brcmfmac_sdio_platform_data { unsigned int oob_irq_nr; unsigned long oob_irq_flags; bool broken_sg_support; + unsigned short sd_head_align; + unsigned short sd_sgentry_align; void (*power_on)(void); void (*power_off)(void); void (*reset)(void); -- cgit v1.2.3 From 0d74d4a161c9f9870039af414b712552c0ed6dfb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 15 Aug 2013 21:38:49 +0200 Subject: pinctrl: add includes and ifdefs for non-DT builds Commit e81c8f18afc4fdd6e34d8c83814b8b5134dbb30f "pinctrl: pinconf-generic: add generic APIs for mapping pinctrl node" Added function prototypes with implicit dependencies on other header files causing build warnings like this: In file included from arch/arm/mach-ux500/board-mop500-pins.c:12:0: include/linux/pinctrl/pinconf-generic.h:142:3: warning: 'struct device_node' declared inside parameter list [enabled by default] unsigned *reserved_maps, unsigned *num_maps); ^ include/linux/pinctrl/pinconf-generic.h:142:3: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] include/linux/pinctrl/pinconf-generic.h:142:3: warning: 'struct pinctrl_dev' declared inside parameter list [enabled by default] include/linux/pinctrl/pinconf-generic.h:145:3: warning: 'struct device_node' declared inside parameter list [enabled by default] unsigned *num_maps); ^ Let's just add ifdefs for non-DT systems (the actual code is already ifdefed) and #include to get the most important structs and forward-declare the pinctrl core structs. Reported-by: Olof Johansson Cc: Laxman Dewangan Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index a472b93292a3..83f5179ea0c5 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -137,12 +137,21 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param return PIN_CONF_PACKED(param, argument); } +#ifdef CONFIG_OF + +#include +struct pinctrl_dev; +struct pinctrl_map; + int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, struct pinctrl_map **map, unsigned *reserved_maps, unsigned *num_maps); int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev, struct device_node *np_config, struct pinctrl_map **map, unsigned *num_maps); + +#endif + #endif /* CONFIG_GENERIC_PINCONF */ #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */ -- cgit v1.2.3 From 98d4f93c79b002f85480320fe63fefaa31d58b6c Mon Sep 17 00:00:00 2001 From: Jens Frederich Date: Thu, 15 Aug 2013 21:34:55 +0200 Subject: Staging: olpc_dcon: replace some magic numbers This patch replace some magic numbers. I believe it makes the driver more readable. The magic number 0x26 is the XO system embedded controller (EC) command 'DCON power enable/disable'. Number 0x41, and 0x42 are special memory controller settings register. The 0x41 initialize bit sequence 0x101 means: enable memory power down function and special SDRAM clock delay for synchronize SDRAM output and clock signal. The 0x42 initialize squence 0x101 is wrong. According to the specification Bit 8 is reserved, thus not in use. I removed it. Signed-off-by: Jens Frederich Signed-off-by: Greg Kroah-Hartman --- include/linux/olpc-ec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index 5bb6e760aa61..2925df3ce78a 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -6,6 +6,7 @@ #define EC_WRITE_SCI_MASK 0x1b #define EC_WAKE_UP_WLAN 0x24 #define EC_WLAN_LEAVE_RESET 0x25 +#define EC_DCON_POWER_MODE 0x26 #define EC_READ_EB_MODE 0x2a #define EC_SET_SCI_INHIBIT 0x32 #define EC_SET_SCI_INHIBIT_RELEASE 0x34 -- cgit v1.2.3 From 6d33f7bb8c3863e54f8bdede0a2bf97a3585ac20 Mon Sep 17 00:00:00 2001 From: Thomas Pugliese Date: Thu, 15 Aug 2013 12:21:30 -0500 Subject: USB: WUSBCORE: clear RPIPE stall for control endpoints When the HWA encounters a STALL on a control endpoint, it should clear the RPIPE_STALL feature on the RPIPE before processing the next transfer request. Otherwise, all transfer requests on that endpoint after the first STALL will fail because the RPIPE is still in the halted state. This also removes the unneccessary call to spin_lock_irqsave for a nested lock that was present in the first patch. Signed-off-by: Thomas Pugliese Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/wusb-wa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h index 6be985b2a434..4ff744e2b678 100644 --- a/include/linux/usb/wusb-wa.h +++ b/include/linux/usb/wusb-wa.h @@ -66,6 +66,7 @@ enum { WA_ENABLE = 0x01, WA_RESET = 0x02, RPIPE_PAUSE = 0x1, + RPIPE_STALL = 0x2, }; /* Responses from Get Status request ([WUSB] section 8.3.1.6) */ -- cgit v1.2.3 From 1c8924eb106c1ac755d5d35ce9b3ff42e89e2511 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sat, 17 Aug 2013 09:32:32 -0400 Subject: quota: provide interface for readding allocated space into reserved space ext4 needs to convert allocated (metadata) blocks back into blocks reserved for delayed allocation. Add functions into quota code for supporting such operation. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/fs.h | 1 + include/linux/quotaops.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 981874773e85..e7893523f81f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2503,6 +2503,7 @@ extern void generic_fillattr(struct inode *, struct kstat *); extern int vfs_getattr(struct path *, struct kstat *); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); +void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 1c50093ae656..6965fe394c3b 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -41,6 +41,7 @@ void __quota_error(struct super_block *sb, const char *func, void inode_add_rsv_space(struct inode *inode, qsize_t number); void inode_claim_rsv_space(struct inode *inode, qsize_t number); void inode_sub_rsv_space(struct inode *inode, qsize_t number); +void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); void dquot_initialize(struct inode *inode); void dquot_drop(struct inode *inode); @@ -59,6 +60,7 @@ int dquot_alloc_inode(const struct inode *inode); int dquot_claim_space_nodirty(struct inode *inode, qsize_t number); void dquot_free_inode(const struct inode *inode); +void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number); int dquot_disable(struct super_block *sb, int type, unsigned int flags); /* Suspend quotas on remount RO */ @@ -238,6 +240,13 @@ static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) return 0; } +static inline int dquot_reclaim_space_nodirty(struct inode *inode, + qsize_t number) +{ + inode_sub_bytes(inode, number); + return 0; +} + static inline int dquot_disable(struct super_block *sb, int type, unsigned int flags) { @@ -336,6 +345,12 @@ static inline int dquot_claim_block(struct inode *inode, qsize_t nr) return ret; } +static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr) +{ + dquot_reclaim_space_nodirty(inode, nr << inode->i_blkbits); + mark_inode_dirty_sync(inode); +} + static inline void dquot_free_space_nodirty(struct inode *inode, qsize_t nr) { __dquot_free_space(inode, nr, 0); -- cgit v1.2.3 From d536321df392ee0db6a5e92d98f0303020315f40 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Fri, 16 Aug 2013 14:11:00 +0100 Subject: iio: trigger: implement devm_iio_trigger_alloc/devm_iio_triger_free Add a resource managed devm_iio_trigger_alloc()/devm_iio_triger_free() to automatically clean up triggers allocated by IIO drivers, thus leading to simplified IIO drivers code. Signed-off-by: Jacek Anaszewski Signed-off-by: Kyunmin Park Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 09ebe0a4d8e6..2103cc32a5fb 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -556,6 +556,35 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); */ void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); +/** + * devm_iio_trigger_alloc - Resource-managed iio_trigger_alloc() + * @dev: Device to allocate iio_trigger for + * @fmt: trigger name format. If it includes format + * specifiers, the additional arguments following + * format are formatted and inserted in the resulting + * string replacing their respective specifiers. + * + * Managed iio_trigger_alloc. iio_trigger allocated with this function is + * automatically freed on driver detach. + * + * If an iio_trigger allocated with this function needs to be freed separately, + * devm_iio_trigger_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_trigger on success, NULL on failure. + */ +struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, + const char *fmt, ...); + +/** + * devm_iio_trigger_free - Resource-managed iio_trigger_free() + * @dev: Device this iio_dev belongs to + * @iio_trig: the iio_trigger associated with the device + * + * Free iio_trigger allocated with devm_iio_trigger_alloc(). + */ +void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From 26e0ca22c3b85b04f693dd0422f13a61846ccfa9 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 4 Jun 2013 11:22:30 -0300 Subject: [media] v4l: Renesas R-Car VSP1 driver The VSP1 is a video processing engine that includes a blender, scalers, filters and statistics computation. Configurable data path routing logic allows ordering the internal blocks in a flexible way. Due to the configurable nature of the pipeline the driver implements the media controller API and doesn't use the V4L2 mem-to-mem framework, even though the device usually operates in memory to memory mode. Only the read pixel formatters, up/down scalers, write pixel formatters and LCDC interface are supported at this stage. Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/vsp1.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/platform_data/vsp1.h (limited to 'include/linux') diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h new file mode 100644 index 000000000000..a73a456d7f11 --- /dev/null +++ b/include/linux/platform_data/vsp1.h @@ -0,0 +1,25 @@ +/* + * vsp1.h -- R-Car VSP1 Platform Data + * + * Copyright (C) 2013 Renesas Corporation + * + * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef __PLATFORM_VSP1_H__ +#define __PLATFORM_VSP1_H__ + +#define VSP1_HAS_LIF (1 << 0) + +struct vsp1_platform_data { + unsigned int features; + unsigned int rpf_count; + unsigned int uds_count; + unsigned int wpf_count; +}; + +#endif /* __PLATFORM_VSP1_H__ */ -- cgit v1.2.3 From 73135e969970304a474c18c9f732fa3e36d88514 Mon Sep 17 00:00:00 2001 From: Vladimir Barinov Date: Thu, 25 Jul 2013 17:23:10 -0300 Subject: [media] V4L2: soc_camera: Renesas R-Car VIN driver Add Renesas R-Car VIN (Video In) V4L2 driver. Based on the patch by Phil Edworthy . [Sergei: removed deprecated IRQF_DISABLED flag, reordered/renamed 'enum chip_id' values, reordered rcar_vin_id_table[] entries, removed senseless parens from to_buf_list() macro, used ALIGN() macro in rcar_vin_setup(), added {} to the *if* statement and used 'bool' values instead of 0/1 where necessary, removed unused macros, done some reformatting and clarified some comments.] Signed-off-by: Vladimir Barinov Signed-off-by: Sergei Shtylyov Signed-off-by: Guennadi Liakhovetski Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/camera-rcar.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/platform_data/camera-rcar.h (limited to 'include/linux') diff --git a/include/linux/platform_data/camera-rcar.h b/include/linux/platform_data/camera-rcar.h new file mode 100644 index 000000000000..dfc83c581593 --- /dev/null +++ b/include/linux/platform_data/camera-rcar.h @@ -0,0 +1,25 @@ +/* + * Platform data for Renesas R-Car VIN soc-camera driver + * + * Copyright (C) 2011-2013 Renesas Solutions Corp. + * Copyright (C) 2013 Cogent Embedded, Inc., + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __CAMERA_RCAR_H_ +#define __CAMERA_RCAR_H_ + +#define RCAR_VIN_HSYNC_ACTIVE_LOW (1 << 0) +#define RCAR_VIN_VSYNC_ACTIVE_LOW (1 << 1) +#define RCAR_VIN_BT601 (1 << 2) +#define RCAR_VIN_BT656 (1 << 3) + +struct rcar_vin_platform_data { + unsigned int flags; +}; + +#endif /* __CAMERA_RCAR_H_ */ -- cgit v1.2.3 From 4dbfd040757b8bf22f4ac17e80b39c068061a16c Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Tue, 30 Jul 2013 02:59:49 -0300 Subject: [media] V4L2: mx3_camera: add support for asynchronous subdevice registration The soc-camera core does all the work on supporting asynchronous subdevice probing, host drivers only have to pass a subdevice list to soc-camera. Typically this list is provided by the platform. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/camera-mx3.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/camera-mx3.h b/include/linux/platform_data/camera-mx3.h index f226ee3777e1..a910dadc8258 100644 --- a/include/linux/platform_data/camera-mx3.h +++ b/include/linux/platform_data/camera-mx3.h @@ -33,6 +33,8 @@ #define MX3_CAMERA_DATAWIDTH_MASK (MX3_CAMERA_DATAWIDTH_4 | MX3_CAMERA_DATAWIDTH_8 | \ MX3_CAMERA_DATAWIDTH_10 | MX3_CAMERA_DATAWIDTH_15) +struct v4l2_async_subdev; + /** * struct mx3_camera_pdata - i.MX3x camera platform data * @flags: MX3_CAMERA_* flags @@ -43,6 +45,8 @@ struct mx3_camera_pdata { unsigned long flags; unsigned long mclk_10khz; struct device *dma_dev; + struct v4l2_async_subdev **asd; /* Flat array, arranged in groups */ + int *asd_sizes; /* 0-terminated array of asd group sizes */ }; #endif -- cgit v1.2.3 From b778ae25366e6f3891fe51306f56a3bca211975d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 23 Apr 2013 12:51:11 -0700 Subject: debugobjects: Make debug_object_activate() return status In order to better respond to things like duplicate invocations of call_rcu(), RCU needs to see the status of a call to debug_object_activate(). This would allow RCU to leak the callback in order to avoid adding freelist-reuse mischief to the duplicate invoations. This commit therefore makes debug_object_activate() return status, zero for success and -EINVAL for failure. Signed-off-by: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Sedat Dilek Cc: Davidlohr Bueso Cc: Rik van Riel Cc: Thomas Gleixner Cc: Linus Torvalds Tested-by: Sedat Dilek Reviewed-by: Josh Triplett --- include/linux/debugobjects.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 0e5f5785d9f2..98ffcbd4888e 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -63,7 +63,7 @@ struct debug_obj_descr { extern void debug_object_init (void *addr, struct debug_obj_descr *descr); extern void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr); -extern void debug_object_activate (void *addr, struct debug_obj_descr *descr); +extern int debug_object_activate (void *addr, struct debug_obj_descr *descr); extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); extern void debug_object_free (void *addr, struct debug_obj_descr *descr); @@ -85,8 +85,8 @@ static inline void debug_object_init (void *addr, struct debug_obj_descr *descr) { } static inline void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { } -static inline void -debug_object_activate (void *addr, struct debug_obj_descr *descr) { } +static inline int +debug_object_activate (void *addr, struct debug_obj_descr *descr) { return 0; } static inline void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { } static inline void -- cgit v1.2.3 From c34ac00caefbe49d40058ae7200bd58725cebb45 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 28 Jun 2013 10:34:48 -0700 Subject: rculist: list_first_or_null_rcu() should use list_entry_rcu() list_first_or_null() should test whether the list is empty and return pointer to the first entry if not in a RCU safe manner. It's broken in several ways. * It compares __kernel @__ptr with __rcu @__next triggering the following sparse warning. net/core/dev.c:4331:17: error: incompatible types in comparison expression (different address spaces) * It doesn't perform rcu_dereference*() and computes the entry address using container_of() directly from the __rcu pointer which is inconsitent with other rculist interface. As a result, all three in-kernel users - net/core/dev.c, macvlan, cgroup - are buggy. They dereference the pointer w/o going through read barrier. * While ->next dereference passes through list_next_rcu(), the compiler is still free to fetch ->next more than once and thus nullify the "__ptr != __next" condition check. Fix it by making list_first_or_null_rcu() dereference ->next directly using ACCESS_ONCE() and then use list_entry_rcu() on it like other rculist accessors. v2: Paul pointed out that the compiler may fetch the pointer more than once nullifying the condition check. ACCESS_ONCE() added on ->next dereference. v3: Restored () around macro param which was accidentally removed. Spotted by Paul. Signed-off-by: Tejun Heo Reported-by: Fengguang Wu Cc: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Cc: Li Zefan Cc: Patrick McHardy Cc: stable@vger.kernel.org Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rculist.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f4b1001a4676..4106721c4e5e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -267,8 +267,9 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_first_or_null_rcu(ptr, type, member) \ ({struct list_head *__ptr = (ptr); \ - struct list_head __rcu *__next = list_next_rcu(__ptr); \ - likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \ + struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + likely(__ptr != __next) ? \ + list_entry_rcu(__next, type, member) : NULL; \ }) /** -- cgit v1.2.3 From feed66ed26a53e700ca02ce1744fed7d0c647292 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 May 2013 08:55:54 -0700 Subject: rcu: Eliminate unused APIs intended for adaptive ticks The rcu_user_enter_after_irq() and rcu_user_exit_after_irq() functions were intended for use by adaptive ticks, but changes in implementation have rendered them unnecessary. This commit therefore removes them. Reported-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0c38abbe6e35..30bea9c25735 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -229,13 +229,9 @@ extern void rcu_irq_exit(void); #ifdef CONFIG_RCU_USER_QS extern void rcu_user_enter(void); extern void rcu_user_exit(void); -extern void rcu_user_enter_after_irq(void); -extern void rcu_user_exit_after_irq(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } -static inline void rcu_user_enter_after_irq(void) { } -static inline void rcu_user_exit_after_irq(void) { } static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* CONFIG_RCU_USER_QS */ -- cgit v1.2.3 From b1baec525e75bcf4dd8c8824cfde476a98b13bab Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 16 Jul 2013 17:28:46 +0800 Subject: dma: mxs-dma: remove code left from generic DMA binding conversion With all mxs-dma clients moved to use generic DMA helper, the code left from generic DMA binding conversion can be removed now. Signed-off-by: Shawn Guo Reviewed-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/fsl/mxs-dma.h | 20 -------------------- 1 file changed, 20 deletions(-) delete mode 100644 include/linux/fsl/mxs-dma.h (limited to 'include/linux') diff --git a/include/linux/fsl/mxs-dma.h b/include/linux/fsl/mxs-dma.h deleted file mode 100644 index 55d870238399..000000000000 --- a/include/linux/fsl/mxs-dma.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright 2011 Freescale Semiconductor, Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __MACH_MXS_DMA_H__ -#define __MACH_MXS_DMA_H__ - -#include - -struct mxs_dma_data { - int chan_irq; -}; - -extern int mxs_dma_is_apbh(struct dma_chan *chan); -extern int mxs_dma_is_apbx(struct dma_chan *chan); -#endif /* __MACH_MXS_DMA_H__ */ -- cgit v1.2.3 From 1cb650b91ba582f6737457b7d22e368585596d2c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 19 Aug 2013 10:05:24 +0800 Subject: cgroup: change cgroup_from_id() to css_from_id() Now we want cgroup core to always provide the css to use to the subsystems, so change this API to css_from_id(). Uninline css_from_id(), because it's getting bigger and cgroup_css() has been unexported. While at it, remove the #ifdef, and shuffle the order of the args. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c24bd0b9f93a..b685955d4b29 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -741,27 +741,11 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } -/** - * cgroup_from_id - lookup cgroup by id - * @ss: cgroup subsys to be looked into - * @id: the cgroup id - * - * Returns the cgroup if there's valid one with @id, otherwise returns NULL. - * Should be called under rcu_read_lock(). - */ -static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) -{ -#ifdef CONFIG_PROVE_RCU - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&cgroup_mutex), - "cgroup_from_id() needs proper protection"); -#endif - return idr_find(&ss->root->cgroup_idr, id); -} - struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); + /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor -- cgit v1.2.3 From 2f74f972d4cc7d83408ea0c32d424edcb44887bf Mon Sep 17 00:00:00 2001 From: Harshula Jayasuriya Date: Fri, 16 Aug 2013 03:46:40 +1000 Subject: sunrpc: prepare NFS for 2038 1) The kernel sunrpc code needs to handle seconds since epoch greater than 2147483647. This means functions that parse time as an int need to handle it as time_t. 2) The kernel changes must be accompanied by userspace changes in nfs-utils. Signed-off-by: Harshula Jayasuriya Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6ce690de447f..437ddb6c4aef 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -264,12 +264,30 @@ static inline int get_uint(char **bpp, unsigned int *anint) return 0; } +static inline int get_time(char **bpp, time_t *time) +{ + char buf[50]; + long long ll; + int len = qword_get(bpp, buf, sizeof(buf)); + + if (len < 0) + return -EINVAL; + if (len == 0) + return -ENOENT; + + if (kstrtoll(buf, 0, &ll)) + return -EINVAL; + + *time = (time_t)ll; + return 0; +} + static inline time_t get_expiry(char **bpp) { - int rv; + time_t rv; struct timespec boot; - if (get_int(bpp, &rv)) + if (get_time(bpp, &rv)) return 0; if (rv < 0) return 0; -- cgit v1.2.3 From b3b515bbd689ba3937cac2dd3fc55057f8c50329 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:52:47 -0700 Subject: pstore: Add new argument 'compressed' in pstore write callback Addition of new argument 'compressed' in the write call back will help the backend to know if the data passed from pstore is compressed or not (In case where compression fails.). If compressed, the backend can add a tag indicating the data is compressed while writing to persistent store. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 4aa80ba830a2..abfca4f59422 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -58,11 +58,11 @@ struct pstore_info { struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t hsize, + unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi); int (*write_buf)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char *buf, size_t hsize, + unsigned int part, const char *buf, bool compressed, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, int count, struct timespec time, -- cgit v1.2.3 From 9a4e1398208d147a9240731a1f8cfe7d8cc4c553 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:53:19 -0700 Subject: pstore: Introduce new argument 'compressed' in the read callback Backends will set the flag 'compressed' after reading the log from persistent store to indicate the data being returned to pstore is compressed or not. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index abfca4f59422..abd437d0a8a7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -55,7 +55,7 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi); + bool *compressed, struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, bool compressed, -- cgit v1.2.3 From 7ef3dcc8145263cb5a8c7059f82d44c948eb46a8 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 29 Jul 2013 12:24:58 +0100 Subject: clk: abstract parent cache Abstract access to the clock parent cache by defining clk_get_parent_by_index(clk, index). This allows access to parent clocks from clock drivers. Signed-off-by: James Hogan Reviewed-by: Stephen Boyd Cc: Mike Turquette Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9487b96939e8..a83409285a7f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -420,6 +420,7 @@ const char *__clk_get_name(struct clk *clk); struct clk_hw *__clk_get_hw(struct clk *clk); u8 __clk_get_num_parents(struct clk *clk); struct clk *__clk_get_parent(struct clk *clk); +struct clk *clk_get_parent_by_index(struct clk *clk, u8 index); unsigned int __clk_get_enable_count(struct clk *clk); unsigned int __clk_get_prepare_count(struct clk *clk); unsigned long __clk_get_rate(struct clk *clk); -- cgit v1.2.3 From 71472c0c06cf9a3d1540762ea205654c584e3bc4 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 29 Jul 2013 12:25:00 +0100 Subject: clk: add support for clock reparent on set_rate Add core support to allow clock implementations to select the best parent clock when rounding a rate, e.g. the one which can provide the closest clock rate to that requested. This is by way of adding a new clock op, determine_rate(), which is like round_rate() but has an extra parameter to allow the clock implementation to optionally select a different parent clock. The core then takes care of reparenting the clock when setting the rate. The parent change takes place with the help of some new private data members. struct clk::new_parent specifies a clock's new parent (NULL indicates no change), and struct clk::new_child specifies a clock's new child (whose new_parent member points back to it). The purpose of these are to allow correct walking of the future tree for notifications prior to actually reparenting any clocks, specifically to skip child clocks who are being reparented to another clock (they will be notified via the new parent), and to include any new child clock. These pointers are set by clk_calc_subtree(), and the new_child pointer gets cleared when a child is actually reparented to avoid duplicate POST_RATE_CHANGE notifications. Each place where round_rate() is called, determine_rate() is checked first and called in preference. This restructures a few of the call sites to simplify the logic into if/else blocks. Signed-off-by: James Hogan Reviewed-by: Stephen Boyd Cc: Mike Turquette Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Mike Turquette --- include/linux/clk-private.h | 3 +++ include/linux/clk-provider.h | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h index dd7adff76e81..8138c94409f3 100644 --- a/include/linux/clk-private.h +++ b/include/linux/clk-private.h @@ -33,8 +33,11 @@ struct clk { const char **parent_names; struct clk **parents; u8 num_parents; + u8 new_parent_index; unsigned long rate; unsigned long new_rate; + struct clk *new_parent; + struct clk *new_child; unsigned long flags; unsigned int enable_count; unsigned int prepare_count; diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index a83409285a7f..4f525b37c6fd 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -79,6 +79,10 @@ struct clk_hw; * @round_rate: Given a target rate as input, returns the closest rate actually * supported by the clock. * + * @determine_rate: Given a target rate as input, returns the closest rate + * actually supported by the clock, and optionally the parent clock + * that should be used to provide the clock rate. + * * @get_parent: Queries the hardware to determine the parent of a clock. The * return value is a u8 which specifies the index corresponding to * the parent clock. This index can be applied to either the @@ -126,6 +130,9 @@ struct clk_ops { unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long, unsigned long *); + long (*determine_rate)(struct clk_hw *hw, unsigned long rate, + unsigned long *best_parent_rate, + struct clk **best_parent_clk); int (*set_parent)(struct clk_hw *hw, u8 index); u8 (*get_parent)(struct clk_hw *hw); int (*set_rate)(struct clk_hw *hw, unsigned long, -- cgit v1.2.3 From 819c1de344c5b8350bffd35be9a0fa74541292d3 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 29 Jul 2013 12:25:01 +0100 Subject: clk: add CLK_SET_RATE_NO_REPARENT flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a CLK_SET_RATE_NO_REPARENT clock flag, which will prevent muxes being reparented during clk_set_rate. To avoid breaking existing platforms, all callers of clk_register_mux() are adjusted to pass the new flag. Platform maintainers are encouraged to remove the flag if they wish to allow mux reparenting on set_rate. Signed-off-by: James Hogan Reviewed-by: Stephen Boyd Cc: Mike Turquette Cc: Russell King Cc: Sascha Hauer Cc: Stephen Warren Cc: Viresh Kumar Cc: Kukjin Kim Cc: Haojian Zhuang Cc: Chao Xie Cc: Arnd Bergmann Cc: "Emilio López" Cc: Gregory CLEMENT Cc: Maxime Ripard Cc: Prashant Gaikwad Cc: Thierry Reding Cc: Peter De Schrijver Cc: Pawel Moll Cc: Catalin Marinas Cc: Andrew Chew Cc: Doug Anderson Cc: Heiko Stuebner Cc: Paul Walmsley Cc: Sylwester Nawrocki Cc: Thomas Abraham Cc: Tomasz Figa Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: spear-devel@list.st.com Cc: linux-tegra@vger.kernel.org Tested-by: Haojian Zhuang Acked-by: Stephen Warren [tegra] Acked-by: Maxime Ripard [sunxi] Acked-by: Sören Brinkmann [Zynq] Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 4f525b37c6fd..5c0bc3904c9b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -27,6 +27,7 @@ #define CLK_IS_ROOT BIT(4) /* root clk, has no parent */ #define CLK_IS_BASIC BIT(5) /* Basic clk, can't do a to_clk_foo() */ #define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */ +#define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */ struct clk_hw; -- cgit v1.2.3 From e366fdd72529c545ccf327569ee250c1673be221 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 29 Jul 2013 12:25:02 +0100 Subject: clk: clk-mux: implement remuxing on set_rate Implement clk-mux remuxing if the CLK_SET_RATE_NO_REPARENT flag isn't set. This implements determine_rate for clk-mux to propagate to each parent and to choose the best one (like clk-divider this chooses the parent which provides the fastest rate <= the requested rate). The determine_rate op is implemented as a core helper function so that it can be easily used by more complex clocks which incorporate muxes. Signed-off-by: James Hogan Reviewed-by: Stephen Boyd Cc: Mike Turquette Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 5c0bc3904c9b..1f0285b2f422 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -436,6 +436,9 @@ unsigned long __clk_get_flags(struct clk *clk); bool __clk_is_prepared(struct clk *clk); bool __clk_is_enabled(struct clk *clk); struct clk *__clk_lookup(const char *name); +long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *best_parent_rate, + struct clk **best_parent_p); /* * FIXME clock api without lock protection -- cgit v1.2.3 From 36ec66e0333355112148549f9846adcc0909482e Mon Sep 17 00:00:00 2001 From: Krystian Garbaciak Date: Mon, 29 Jul 2013 19:00:42 +0200 Subject: mfd: da9063: Add register definitions for DA9063 driver This patch adds register definitions for the DA9063 PMIC. They will be used by the following DA9063 mfd core driver and functional module drivers. Signed-off-by: Krystian Garbaciak Signed-off-by: Philipp Zabel Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/da9063/registers.h | 1028 ++++++++++++++++++++++++++++++++++ 1 file changed, 1028 insertions(+) create mode 100644 include/linux/mfd/da9063/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h new file mode 100644 index 000000000000..5834813fb5f3 --- /dev/null +++ b/include/linux/mfd/da9063/registers.h @@ -0,0 +1,1028 @@ +/* + * Registers definition for DA9063 modules + * + * Copyright 2012 Dialog Semiconductor Ltd. + * + * Author: Michal Hajduk + * Krystian Garbaciak + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef _DA9063_REG_H +#define _DA9063_REG_H + +#define DA9063_I2C_PAGE_SEL_SHIFT 1 + +#define DA9063_EVENT_REG_NUM 4 +#define DA9210_EVENT_REG_NUM 2 +#define DA9063_EXT_EVENT_REG_NUM (DA9063_EVENT_REG_NUM + \ + DA9210_EVENT_REG_NUM) + +/* Page selection I2C or SPI always in the begining of any page. */ +/* Page 0 : I2C access 0x000 - 0x0FF SPI access 0x000 - 0x07F */ +/* Page 1 : SPI access 0x080 - 0x0FF */ +/* Page 2 : I2C access 0x100 - 0x1FF SPI access 0x100 - 0x17F */ +/* Page 3 : SPI access 0x180 - 0x1FF */ +#define DA9063_REG_PAGE_CON 0x00 + +/* System Control and Event Registers */ +#define DA9063_REG_STATUS_A 0x01 +#define DA9063_REG_STATUS_B 0x02 +#define DA9063_REG_STATUS_C 0x03 +#define DA9063_REG_STATUS_D 0x04 +#define DA9063_REG_FAULT_LOG 0x05 +#define DA9063_REG_EVENT_A 0x06 +#define DA9063_REG_EVENT_B 0x07 +#define DA9063_REG_EVENT_C 0x08 +#define DA9063_REG_EVENT_D 0x09 +#define DA9063_REG_IRQ_MASK_A 0x0A +#define DA9063_REG_IRQ_MASK_B 0x0B +#define DA9063_REG_IRQ_MASK_C 0x0C +#define DA9063_REG_IRQ_MASK_D 0x0D +#define DA9063_REG_CONTROL_A 0x0E +#define DA9063_REG_CONTROL_B 0x0F +#define DA9063_REG_CONTROL_C 0x10 +#define DA9063_REG_CONTROL_D 0x11 +#define DA9063_REG_CONTROL_E 0x12 +#define DA9063_REG_CONTROL_F 0x13 +#define DA9063_REG_PD_DIS 0x14 + +/* GPIO Control Registers */ +#define DA9063_REG_GPIO_0_1 0x15 +#define DA9063_REG_GPIO_2_3 0x16 +#define DA9063_REG_GPIO_4_5 0x17 +#define DA9063_REG_GPIO_6_7 0x18 +#define DA9063_REG_GPIO_8_9 0x19 +#define DA9063_REG_GPIO_10_11 0x1A +#define DA9063_REG_GPIO_12_13 0x1B +#define DA9063_REG_GPIO_14_15 0x1C +#define DA9063_REG_GPIO_MODE_0_7 0x1D +#define DA9063_REG_GPIO_MODE_8_15 0x1E +#define DA9063_REG_GPIO_SWITCH_CONT 0x1F + +/* Regulator Control Registers */ +#define DA9063_REG_BCORE2_CONT 0x20 +#define DA9063_REG_BCORE1_CONT 0x21 +#define DA9063_REG_BPRO_CONT 0x22 +#define DA9063_REG_BMEM_CONT 0x23 +#define DA9063_REG_BIO_CONT 0x24 +#define DA9063_REG_BPERI_CONT 0x25 +#define DA9063_REG_LDO1_CONT 0x26 +#define DA9063_REG_LDO2_CONT 0x27 +#define DA9063_REG_LDO3_CONT 0x28 +#define DA9063_REG_LDO4_CONT 0x29 +#define DA9063_REG_LDO5_CONT 0x2A +#define DA9063_REG_LDO6_CONT 0x2B +#define DA9063_REG_LDO7_CONT 0x2C +#define DA9063_REG_LDO8_CONT 0x2D +#define DA9063_REG_LDO9_CONT 0x2E +#define DA9063_REG_LDO10_CONT 0x2F +#define DA9063_REG_LDO11_CONT 0x30 +#define DA9063_REG_VIB 0x31 +#define DA9063_REG_DVC_1 0x32 +#define DA9063_REG_DVC_2 0x33 + +/* GP-ADC Control Registers */ +#define DA9063_REG_ADC_MAN 0x34 +#define DA9063_REG_ADC_CONT 0x35 +#define DA9063_REG_VSYS_MON 0x36 +#define DA9063_REG_ADC_RES_L 0x37 +#define DA9063_REG_ADC_RES_H 0x38 +#define DA9063_REG_VSYS_RES 0x39 +#define DA9063_REG_ADCIN1_RES 0x3A +#define DA9063_REG_ADCIN2_RES 0x3B +#define DA9063_REG_ADCIN3_RES 0x3C +#define DA9063_REG_MON1_RES 0x3D +#define DA9063_REG_MON2_RES 0x3E +#define DA9063_REG_MON3_RES 0x3F + +/* RTC Calendar and Alarm Registers */ +#define DA9063_REG_COUNT_S 0x40 +#define DA9063_REG_COUNT_MI 0x41 +#define DA9063_REG_COUNT_H 0x42 +#define DA9063_REG_COUNT_D 0x43 +#define DA9063_REG_COUNT_MO 0x44 +#define DA9063_REG_COUNT_Y 0x45 +#define DA9063_REG_ALARM_MI 0x46 +#define DA9063_REG_ALARM_H 0x47 +#define DA9063_REG_ALARM_D 0x48 +#define DA9063_REG_ALARM_MO 0x49 +#define DA9063_REG_ALARM_Y 0x4A +#define DA9063_REG_SECOND_A 0x4B +#define DA9063_REG_SECOND_B 0x4C +#define DA9063_REG_SECOND_C 0x4D +#define DA9063_REG_SECOND_D 0x4E + +/* Sequencer Control Registers */ +#define DA9063_REG_SEQ 0x81 +#define DA9063_REG_SEQ_TIMER 0x82 +#define DA9063_REG_ID_2_1 0x83 +#define DA9063_REG_ID_4_3 0x84 +#define DA9063_REG_ID_6_5 0x85 +#define DA9063_REG_ID_8_7 0x86 +#define DA9063_REG_ID_10_9 0x87 +#define DA9063_REG_ID_12_11 0x88 +#define DA9063_REG_ID_14_13 0x89 +#define DA9063_REG_ID_16_15 0x8A +#define DA9063_REG_ID_18_17 0x8B +#define DA9063_REG_ID_20_19 0x8C +#define DA9063_REG_ID_22_21 0x8D +#define DA9063_REG_ID_24_23 0x8E +#define DA9063_REG_ID_26_25 0x8F +#define DA9063_REG_ID_28_27 0x90 +#define DA9063_REG_ID_30_29 0x91 +#define DA9063_REG_ID_32_31 0x92 +#define DA9063_REG_SEQ_A 0x95 +#define DA9063_REG_SEQ_B 0x96 +#define DA9063_REG_WAIT 0x97 +#define DA9063_REG_EN_32K 0x98 +#define DA9063_REG_RESET 0x99 + +/* Regulator Setting Registers */ +#define DA9063_REG_BUCK_ILIM_A 0x9A +#define DA9063_REG_BUCK_ILIM_B 0x9B +#define DA9063_REG_BUCK_ILIM_C 0x9C +#define DA9063_REG_BCORE2_CFG 0x9D +#define DA9063_REG_BCORE1_CFG 0x9E +#define DA9063_REG_BPRO_CFG 0x9F +#define DA9063_REG_BIO_CFG 0xA0 +#define DA9063_REG_BMEM_CFG 0xA1 +#define DA9063_REG_BPERI_CFG 0xA2 +#define DA9063_REG_VBCORE2_A 0xA3 +#define DA9063_REG_VBCORE1_A 0xA4 +#define DA9063_REG_VBPRO_A 0xA5 +#define DA9063_REG_VBMEM_A 0xA6 +#define DA9063_REG_VBIO_A 0xA7 +#define DA9063_REG_VBPERI_A 0xA8 +#define DA9063_REG_VLDO1_A 0xA9 +#define DA9063_REG_VLDO2_A 0xAA +#define DA9063_REG_VLDO3_A 0xAB +#define DA9063_REG_VLDO4_A 0xAC +#define DA9063_REG_VLDO5_A 0xAD +#define DA9063_REG_VLDO6_A 0xAE +#define DA9063_REG_VLDO7_A 0xAF +#define DA9063_REG_VLDO8_A 0xB0 +#define DA9063_REG_VLDO9_A 0xB1 +#define DA9063_REG_VLDO10_A 0xB2 +#define DA9063_REG_VLDO11_A 0xB3 +#define DA9063_REG_VBCORE2_B 0xB4 +#define DA9063_REG_VBCORE1_B 0xB5 +#define DA9063_REG_VBPRO_B 0xB6 +#define DA9063_REG_VBMEM_B 0xB7 +#define DA9063_REG_VBIO_B 0xB8 +#define DA9063_REG_VBPERI_B 0xB9 +#define DA9063_REG_VLDO1_B 0xBA +#define DA9063_REG_VLDO2_B 0xBB +#define DA9063_REG_VLDO3_B 0xBC +#define DA9063_REG_VLDO4_B 0xBD +#define DA9063_REG_VLDO5_B 0xBE +#define DA9063_REG_VLDO6_B 0xBF +#define DA9063_REG_VLDO7_B 0xC0 +#define DA9063_REG_VLDO8_B 0xC1 +#define DA9063_REG_VLDO9_B 0xC2 +#define DA9063_REG_VLDO10_B 0xC3 +#define DA9063_REG_VLDO11_B 0xC4 + +/* Backup Battery Charger Control Register */ +#define DA9063_REG_BBAT_CONT 0xC5 + +/* GPIO PWM (LED) */ +#define DA9063_REG_GPO11_LED 0xC6 +#define DA9063_REG_GPO14_LED 0xC7 +#define DA9063_REG_GPO15_LED 0xC8 + +/* GP-ADC Threshold Registers */ +#define DA9063_REG_ADC_CFG 0xC9 +#define DA9063_REG_AUTO1_HIGH 0xCA +#define DA9063_REG_AUTO1_LOW 0xCB +#define DA9063_REG_AUTO2_HIGH 0xCC +#define DA9063_REG_AUTO2_LOW 0xCD +#define DA9063_REG_AUTO3_HIGH 0xCE +#define DA9063_REG_AUTO3_LOW 0xCF + +/* DA9063 Configuration registers */ +/* OTP */ +#define DA9063_REG_OPT_COUNT 0x101 +#define DA9063_REG_OPT_ADDR 0x102 +#define DA9063_REG_OPT_DATA 0x103 + +/* Customer Trim and Configuration */ +#define DA9063_REG_T_OFFSET 0x104 +#define DA9063_REG_INTERFACE 0x105 +#define DA9063_REG_CONFIG_A 0x106 +#define DA9063_REG_CONFIG_B 0x107 +#define DA9063_REG_CONFIG_C 0x108 +#define DA9063_REG_CONFIG_D 0x109 +#define DA9063_REG_CONFIG_E 0x10A +#define DA9063_REG_CONFIG_F 0x10B +#define DA9063_REG_CONFIG_G 0x10C +#define DA9063_REG_CONFIG_H 0x10D +#define DA9063_REG_CONFIG_I 0x10E +#define DA9063_REG_CONFIG_J 0x10F +#define DA9063_REG_CONFIG_K 0x110 +#define DA9063_REG_CONFIG_L 0x111 +#define DA9063_REG_MON_REG_1 0x112 +#define DA9063_REG_MON_REG_2 0x113 +#define DA9063_REG_MON_REG_3 0x114 +#define DA9063_REG_MON_REG_4 0x115 +#define DA9063_REG_MON_REG_5 0x116 +#define DA9063_REG_MON_REG_6 0x117 +#define DA9063_REG_TRIM_CLDR 0x118 + +/* General Purpose Registers */ +#define DA9063_REG_GP_ID_0 0x119 +#define DA9063_REG_GP_ID_1 0x11A +#define DA9063_REG_GP_ID_2 0x11B +#define DA9063_REG_GP_ID_3 0x11C +#define DA9063_REG_GP_ID_4 0x11D +#define DA9063_REG_GP_ID_5 0x11E +#define DA9063_REG_GP_ID_6 0x11F +#define DA9063_REG_GP_ID_7 0x120 +#define DA9063_REG_GP_ID_8 0x121 +#define DA9063_REG_GP_ID_9 0x122 +#define DA9063_REG_GP_ID_10 0x123 +#define DA9063_REG_GP_ID_11 0x124 +#define DA9063_REG_GP_ID_12 0x125 +#define DA9063_REG_GP_ID_13 0x126 +#define DA9063_REG_GP_ID_14 0x127 +#define DA9063_REG_GP_ID_15 0x128 +#define DA9063_REG_GP_ID_16 0x129 +#define DA9063_REG_GP_ID_17 0x12A +#define DA9063_REG_GP_ID_18 0x12B +#define DA9063_REG_GP_ID_19 0x12C + +/* Chip ID and variant */ +#define DA9063_REG_CHIP_ID 0x181 +#define DA9063_REG_CHIP_VARIANT 0x182 + +/* + * PMIC registers bits + */ +/* DA9063_REG_PAGE_CON (addr=0x00) */ +#define DA9063_PEG_PAGE_SHIFT 0 +#define DA9063_REG_PAGE_MASK 0x07 +#define DA9063_REG_PAGE0 0x00 +#define DA9063_REG_PAGE2 0x02 +#define DA9063_PAGE_WRITE_MODE 0x00 +#define DA9063_REPEAT_WRITE_MODE 0x40 +#define DA9063_PAGE_REVERT 0x80 + +/* DA9063_REG_STATUS_A (addr=0x01) */ +#define DA9063_NONKEY 0x01 +#define DA9063_WAKE 0x02 +#define DA9063_DVC_BUSY 0x04 +#define DA9063_COMP_1V2 0x08 + +/* DA9063_REG_STATUS_B (addr=0x02) */ +#define DA9063_GPI0 0x01 +#define DA9063_GPI1 0x02 +#define DA9063_GPI2 0x04 +#define DA9063_GPI3 0x08 +#define DA9063_GPI4 0x10 +#define DA9063_GPI5 0x20 +#define DA9063_GPI6 0x40 +#define DA9063_GPI7 0x80 + +/* DA9063_REG_STATUS_C (addr=0x03) */ +#define DA9063_GPI8 0x01 +#define DA9063_GPI9 0x02 +#define DA9063_GPI10 0x04 +#define DA9063_GPI11 0x08 +#define DA9063_GPI12 0x10 +#define DA9063_GPI13 0x20 +#define DA9063_GPI14 0x40 +#define DA9063_GPI15 0x80 + +/* DA9063_REG_STATUS_D (addr=0x04) */ +#define DA9063_LDO3_LIM 0x08 +#define DA9063_LDO4_LIM 0x10 +#define DA9063_LDO7_LIM 0x20 +#define DA9063_LDO8_LIM 0x40 +#define DA9063_LDO11_LIM 0x80 + +/* DA9063_REG_FAULT_LOG (addr=0x05) */ +#define DA9063_TWD_ERROR 0x01 +#define DA9063_POR 0x02 +#define DA9063_VDD_FAULT 0x04 +#define DA9063_VDD_START 0x08 +#define DA9063_TEMP_CRIT 0x10 +#define DA9063_KEY_RESET 0x20 +#define DA9063_NSHUTDOWN 0x40 +#define DA9063_WAIT_SHUT 0x80 + +/* DA9063_REG_EVENT_A (addr=0x06) */ +#define DA9063_E_NONKEY 0x01 +#define DA9063_E_ALARM 0x02 +#define DA9063_E_TICK 0x04 +#define DA9063_E_ADC_RDY 0x08 +#define DA9063_E_SEQ_RDY 0x10 +#define DA9063_EVENTS_B 0x20 +#define DA9063_EVENTS_C 0x40 +#define DA9063_EVENTS_D 0x80 + +/* DA9063_REG_EVENT_B (addr=0x07) */ +#define DA9063_E_WAKE 0x01 +#define DA9063_E_TEMP 0x02 +#define DA9063_E_COMP_1V2 0x04 +#define DA9063_E_LDO_LIM 0x08 +#define DA9063_E_REG_UVOV 0x10 +#define DA9063_E_DVC_RDY 0x20 +#define DA9063_E_VDD_MON 0x40 +#define DA9063_E_VDD_WARN 0x80 + +/* DA9063_REG_EVENT_C (addr=0x08) */ +#define DA9063_E_GPI0 0x01 +#define DA9063_E_GPI1 0x02 +#define DA9063_E_GPI2 0x04 +#define DA9063_E_GPI3 0x08 +#define DA9063_E_GPI4 0x10 +#define DA9063_E_GPI5 0x20 +#define DA9063_E_GPI6 0x40 +#define DA9063_E_GPI7 0x80 + +/* DA9063_REG_EVENT_D (addr=0x09) */ +#define DA9063_E_GPI8 0x01 +#define DA9063_E_GPI9 0x02 +#define DA9063_E_GPI10 0x04 +#define DA9063_E_GPI11 0x08 +#define DA9063_E_GPI12 0x10 +#define DA9063_E_GPI13 0x20 +#define DA9063_E_GPI14 0x40 +#define DA9063_E_GPI15 0x80 + +/* DA9063_REG_IRQ_MASK_A (addr=0x0A) */ +#define DA9063_M_ONKEY 0x01 +#define DA9063_M_ALARM 0x02 +#define DA9063_M_TICK 0x04 +#define DA9063_M_ADC_RDY 0x08 +#define DA9063_M_SEQ_RDY 0x10 + +/* DA9063_REG_IRQ_MASK_B (addr=0x0B) */ +#define DA9063_M_WAKE 0x01 +#define DA9063_M_TEMP 0x02 +#define DA9063_M_COMP_1V2 0x04 +#define DA9063_M_LDO_LIM 0x08 +#define DA9063_M_UVOV 0x10 +#define DA9063_M_DVC_RDY 0x20 +#define DA9063_M_VDD_MON 0x40 +#define DA9063_M_VDD_WARN 0x80 + +/* DA9063_REG_IRQ_MASK_C (addr=0x0C) */ +#define DA9063_M_GPI0 0x01 +#define DA9063_M_GPI1 0x02 +#define DA9063_M_GPI2 0x04 +#define DA9063_M_GPI3 0x08 +#define DA9063_M_GPI4 0x10 +#define DA9063_M_GPI5 0x20 +#define DA9063_M_GPI6 0x40 +#define DA9063_M_GPI7 0x80 + +/* DA9063_REG_IRQ_MASK_D (addr=0x0D) */ +#define DA9063_M_GPI8 0x01 +#define DA9063_M_GPI9 0x02 +#define DA9063_M_GPI10 0x04 +#define DA9063_M_GPI11 0x08 +#define DA9063_M_GPI12 0x10 +#define DA9063_M_GPI13 0x20 +#define DA9063_M_GPI14 0x40 +#define DA9063_M_GPI15 0x80 + +/* DA9063_REG_CONTROL_A (addr=0x0E) */ +#define DA9063_SYSTEM_EN 0x01 +#define DA9063_POWER_EN 0x02 +#define DA9063_POWER1_EN 0x04 +#define DA9063_STANDBY 0x08 +#define DA9063_M_SYSTEM_EN 0x10 +#define DA9063_M_POWER_EN 0x20 +#define DA9063_M_POWER1_EN 0x40 +#define DA9063_CP_EN 0x80 + +/* DA9063_REG_CONTROL_B (addr=0x0F) */ +#define DA9063_CHG_SEL 0x01 +#define DA9063_WATCHDOG_PD 0x02 +#define DA9063_NRES_MODE 0x08 +#define DA9063_NONKEY_LOCK 0x10 + +/* DA9063_REG_CONTROL_C (addr=0x10) */ +#define DA9063_DEBOUNCING_MASK 0x07 +#define DA9063_DEBOUNCING_OFF 0x0 +#define DA9063_DEBOUNCING_0MS1 0x1 +#define DA9063_DEBOUNCING_1MS 0x2 +#define DA9063_DEBOUNCING_10MS24 0x3 +#define DA9063_DEBOUNCING_51MS2 0x4 +#define DA9063_DEBOUNCING_256MS 0x5 +#define DA9063_DEBOUNCING_512MS 0x6 +#define DA9063_DEBOUNCING_1024MS 0x7 + +#define DA9063_AUTO_BOOT 0x08 +#define DA9063_OTPREAD_EN 0x10 +#define DA9063_SLEW_RATE_MASK 0x60 +#define DA9063_SLEW_RATE_4US 0x00 +#define DA9063_SLEW_RATE_3US 0x20 +#define DA9063_SLEW_RATE_1US 0x40 +#define DA9063_SLEW_RATE_0US5 0x60 +#define DA9063_DEF_SUPPLY 0x80 + +/* DA9063_REG_CONTROL_D (addr=0x11) */ +#define DA9063_TWDSCALE_MASK 0x07 +#define DA9063_BLINK_FRQ_MASK 0x38 +#define DA9063_BLINK_FRQ_OFF 0x00 +#define DA9063_BLINK_FRQ_1S0 0x08 +#define DA9063_BLINK_FRQ_2S0 0x10 +#define DA9063_BLINK_FRQ_4S0 0x18 +#define DA9063_BLINK_FRQ_0S18 0x20 +#define DA9063_BLINK_FRQ_2S0_VDD 0x28 +#define DA9063_BLINK_FRQ_4S0_VDD 0x30 +#define DA9063_BLINK_FRQ_0S18_VDD 0x38 + +#define DA9063_BLINK_DUR_MASK 0xC0 +#define DA9063_BLINK_DUR_10MS 0x00 +#define DA9063_BLINK_DUR_20MS 0x40 +#define DA9063_BLINK_DUR_40MS 0x80 +#define DA9063_BLINK_DUR_20MSDBL 0xC0 + +/* DA9063_REG_CONTROL_E (addr=0x12) */ +#define DA9063_RTC_MODE_PD 0x01 +#define DA9063_RTC_MODE_SD 0x02 +#define DA9063_RTC_EN 0x04 +#define DA9063_ECO_MODE 0x08 +#define DA9063_PM_FB1_PIN 0x10 +#define DA9063_PM_FB2_PIN 0x20 +#define DA9063_PM_FB3_PIN 0x40 +#define DA9063_V_LOCK 0x80 + +/* DA9063_REG_CONTROL_F (addr=0x13) */ +#define DA9063_WATCHDOG 0x01 +#define DA9063_SHUTDOWN 0x02 +#define DA9063_WAKE_UP 0x04 + +/* DA9063_REG_PD_DIS (addr=0x14) */ +#define DA9063_GPI_DIS 0x01 +#define DA9063_GPADC_PAUSE 0x02 +#define DA9063_PMIF_DIS 0x04 +#define DA9063_HS2WIRE_DIS 0x08 +#define DA9063_BBAT_DIS 0x20 +#define DA9063_OUT_32K_PAUSE 0x40 +#define DA9063_PMCONT_DIS 0x80 + +/* DA9063_REG_GPIO_0_1 (addr=0x15) */ +#define DA9063_GPIO0_PIN_MASK 0x03 +#define DA9063_GPIO0_PIN_ADCIN1 0x00 +#define DA9063_GPIO0_PIN_GPI 0x01 +#define DA9063_GPIO0_PIN_GPO_OD 0x02 +#define DA9063_GPIO0_PIN_GPO 0x03 +#define DA9063_GPIO0_TYPE 0x04 +#define DA9063_GPIO0_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO0_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO0_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO0_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO0_NO_WAKEUP 0x08 +#define DA9063_GPIO1_PIN_MASK 0x30 +#define DA9063_GPIO1_PIN_ADCIN2_COMP 0x00 +#define DA9063_GPIO1_PIN_GPI 0x10 +#define DA9063_GPIO1_PIN_GPO_OD 0x20 +#define DA9063_GPIO1_PIN_GPO 0x30 +#define DA9063_GPIO1_TYPE 0x40 +#define DA9063_GPIO1_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO1_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO1_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO1_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO1_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_2_3 (addr=0x16) */ +#define DA9063_GPIO2_PIN_MASK 0x03 +#define DA9063_GPIO2_PIN_ADCIN3 0x00 +#define DA9063_GPIO2_PIN_GPI 0x01 +#define DA9063_GPIO2_PIN_GPO_PSS 0x02 +#define DA9063_GPIO2_PIN_GPO 0x03 +#define DA9063_GPIO2_TYPE 0x04 +#define DA9063_GPIO2_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO2_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO2_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO2_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO2_NO_WAKEUP 0x08 +#define DA9063_GPIO3_PIN_MASK 0x30 +#define DA9063_GPIO3_PIN_CORE_SW_G 0x00 +#define DA9063_GPIO3_PIN_GPI 0x10 +#define DA9063_GPIO3_PIN_GPO_OD 0x20 +#define DA9063_GPIO3_PIN_GPO 0x30 +#define DA9063_GPIO3_TYPE 0x40 +#define DA9063_GPIO3_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO3_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO3_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO3_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO3_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_4_5 (addr=0x17) */ +#define DA9063_GPIO4_PIN_MASK 0x03 +#define DA9063_GPIO4_PIN_CORE_SW_S 0x00 +#define DA9063_GPIO4_PIN_GPI 0x01 +#define DA9063_GPIO4_PIN_GPO_OD 0x02 +#define DA9063_GPIO4_PIN_GPO 0x03 +#define DA9063_GPIO4_TYPE 0x04 +#define DA9063_GPIO4_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO4_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO4_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO4_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO4_NO_WAKEUP 0x08 +#define DA9063_GPIO5_PIN_MASK 0x30 +#define DA9063_GPIO5_PIN_PERI_SW_G 0x00 +#define DA9063_GPIO5_PIN_GPI 0x10 +#define DA9063_GPIO5_PIN_GPO_OD 0x20 +#define DA9063_GPIO5_PIN_GPO 0x30 +#define DA9063_GPIO5_TYPE 0x40 +#define DA9063_GPIO5_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO5_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO5_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO5_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO5_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_6_7 (addr=0x18) */ +#define DA9063_GPIO6_PIN_MASK 0x03 +#define DA9063_GPIO6_PIN_PERI_SW_S 0x00 +#define DA9063_GPIO6_PIN_GPI 0x01 +#define DA9063_GPIO6_PIN_GPO_OD 0x02 +#define DA9063_GPIO6_PIN_GPO 0x03 +#define DA9063_GPIO6_TYPE 0x04 +#define DA9063_GPIO6_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO6_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO6_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO6_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO6_NO_WAKEUP 0x08 +#define DA9063_GPIO7_PIN_MASK 0x30 +#define DA9063_GPIO7_PIN_GPI 0x10 +#define DA9063_GPIO7_PIN_GPO_PSS 0x20 +#define DA9063_GPIO7_PIN_GPO 0x30 +#define DA9063_GPIO7_TYPE 0x40 +#define DA9063_GPIO7_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO7_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO7_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO7_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO7_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_8_9 (addr=0x19) */ +#define DA9063_GPIO8_PIN_MASK 0x03 +#define DA9063_GPIO8_PIN_GPI_SYS_EN 0x00 +#define DA9063_GPIO8_PIN_GPI 0x01 +#define DA9063_GPIO8_PIN_GPO_PSS 0x02 +#define DA9063_GPIO8_PIN_GPO 0x03 +#define DA9063_GPIO8_TYPE 0x04 +#define DA9063_GPIO8_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO8_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO8_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO8_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO8_NO_WAKEUP 0x08 +#define DA9063_GPIO9_PIN_MASK 0x30 +#define DA9063_GPIO9_PIN_GPI_PWR_EN 0x00 +#define DA9063_GPIO9_PIN_GPI 0x10 +#define DA9063_GPIO9_PIN_GPO_PSS 0x20 +#define DA9063_GPIO9_PIN_GPO 0x30 +#define DA9063_GPIO9_TYPE 0x40 +#define DA9063_GPIO9_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO9_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO9_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO9_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO9_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_10_11 (addr=0x1A) */ +#define DA9063_GPIO10_PIN_MASK 0x03 +#define DA9063_GPIO10_PIN_GPI_PWR1_EN 0x00 +#define DA9063_GPIO10_PIN_GPI 0x01 +#define DA9063_GPIO10_PIN_GPO_OD 0x02 +#define DA9063_GPIO10_PIN_GPO 0x03 +#define DA9063_GPIO10_TYPE 0x04 +#define DA9063_GPIO10_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO10_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO10_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO10_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO10_NO_WAKEUP 0x08 +#define DA9063_GPIO11_PIN_MASK 0x30 +#define DA9063_GPIO11_PIN_GPO_OD 0x00 +#define DA9063_GPIO11_PIN_GPI 0x10 +#define DA9063_GPIO11_PIN_GPO_PSS 0x20 +#define DA9063_GPIO11_PIN_GPO 0x30 +#define DA9063_GPIO11_TYPE 0x40 +#define DA9063_GPIO11_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO11_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO11_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO11_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO11_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_12_13 (addr=0x1B) */ +#define DA9063_GPIO12_PIN_MASK 0x03 +#define DA9063_GPIO12_PIN_NVDDFLT_OUT 0x00 +#define DA9063_GPIO12_PIN_GPI 0x01 +#define DA9063_GPIO12_PIN_VSYSMON_OUT 0x02 +#define DA9063_GPIO12_PIN_GPO 0x03 +#define DA9063_GPIO12_TYPE 0x04 +#define DA9063_GPIO12_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO12_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO12_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO12_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO12_NO_WAKEUP 0x08 +#define DA9063_GPIO13_PIN_MASK 0x30 +#define DA9063_GPIO13_PIN_GPFB1_OUT 0x00 +#define DA9063_GPIO13_PIN_GPI 0x10 +#define DA9063_GPIO13_PIN_GPFB1_OUTOD 0x20 +#define DA9063_GPIO13_PIN_GPO 0x30 +#define DA9063_GPIO13_TYPE 0x40 +#define DA9063_GPIO13_TYPE_GPFB1_OUT 0x00 +#define DA9063_GPIO13_TYPE_GPI 0x00 +#define DA9063_GPIO13_TYPE_GPFB1_OUTOD 0x04 +#define DA9063_GPIO13_TYPE_GPO 0x04 +#define DA9063_GPIO13_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_14_15 (addr=0x1C) */ +#define DA9063_GPIO14_PIN_MASK 0x03 +#define DA9063_GPIO14_PIN_GPO_OD 0x00 +#define DA9063_GPIO14_PIN_GPI 0x01 +#define DA9063_GPIO14_PIN_HS2DATA 0x02 +#define DA9063_GPIO14_PIN_GPO 0x03 +#define DA9063_GPIO14_TYPE 0x04 +#define DA9063_GPIO14_TYPE_GPI_ACT_LOW 0x00 +#define DA9063_GPIO14_TYPE_GPO_VDD_IO1 0x00 +#define DA9063_GPIO14_TYPE_GPI_ACT_HIGH 0x04 +#define DA9063_GPIO14_TYPE_GPO_VDD_IO2 0x04 +#define DA9063_GPIO14_NO_WAKEUP 0x08 +#define DA9063_GPIO15_PIN_MASK 0x30 +#define DA9063_GPIO15_PIN_GPO_OD 0x00 +#define DA9063_GPIO15_PIN_GPI 0x10 +#define DA9063_GPIO15_PIN_GPO 0x30 +#define DA9063_GPIO15_TYPE 0x40 +#define DA9063_GPIO15_TYPE_GPFB1_OUT 0x00 +#define DA9063_GPIO15_TYPE_GPI 0x00 +#define DA9063_GPIO15_TYPE_GPFB1_OUTOD 0x04 +#define DA9063_GPIO15_TYPE_GPO 0x04 +#define DA9063_GPIO15_NO_WAKEUP 0x80 + +/* DA9063_REG_GPIO_MODE_0_7 (addr=0x1D) */ +#define DA9063_GPIO0_MODE 0x01 +#define DA9063_GPIO1_MODE 0x02 +#define DA9063_GPIO2_MODE 0x04 +#define DA9063_GPIO3_MODE 0x08 +#define DA9063_GPIO4_MODE 0x10 +#define DA9063_GPIO5_MODE 0x20 +#define DA9063_GPIO6_MODE 0x40 +#define DA9063_GPIO7_MODE 0x80 + +/* DA9063_REG_GPIO_MODE_8_15 (addr=0x1E) */ +#define DA9063_GPIO8_MODE 0x01 +#define DA9063_GPIO9_MODE 0x02 +#define DA9063_GPIO10_MODE 0x04 +#define DA9063_GPIO11_MODE 0x08 +#define DA9063_GPIO11_MODE_LED_ACT_HIGH 0x00 +#define DA9063_GPIO11_MODE_LED_ACT_LOW 0x08 +#define DA9063_GPIO12_MODE 0x10 +#define DA9063_GPIO13_MODE 0x20 +#define DA9063_GPIO14_MODE 0x40 +#define DA9063_GPIO14_MODE_LED_ACT_HIGH 0x00 +#define DA9063_GPIO14_MODE_LED_ACT_LOW 0x40 +#define DA9063_GPIO15_MODE 0x80 +#define DA9063_GPIO15_MODE_LED_ACT_HIGH 0x00 +#define DA9063_GPIO15_MODE_LED_ACT_LOW 0x80 + +/* DA9063_REG_SWITCH_CONT (addr=0x1F) */ +#define DA9063_CORE_SW_GPI_MASK 0x03 +#define DA9063_CORE_SW_GPI_OFF 0x00 +#define DA9063_CORE_SW_GPI_GPIO1 0x01 +#define DA9063_CORE_SW_GPI_GPIO2 0x02 +#define DA9063_CORE_SW_GPI_GPIO13 0x03 +#define DA9063_PERI_SW_GPI_MASK 0x0C +#define DA9063_PERI_SW_GPI_OFF 0x00 +#define DA9063_PERI_SW_GPI_GPIO1 0x04 +#define DA9063_PERI_SW_GPI_GPIO2 0x08 +#define DA9063_PERI_SW_GPI_GPIO13 0x0C +#define DA9063_SWITCH_SR_MASK 0x30 +#define DA9063_SWITCH_SR_1MV 0x00 +#define DA9063_SWITCH_SR_5MV 0x10 +#define DA9063_SWITCH_SR_10MV 0x20 +#define DA9063_SWITCH_SR_50MV 0x30 +#define DA9063_SWITCH_SR_DIS 0x40 +#define DA9063_CP_EN_MODE 0x80 + +/* DA9063_REGL_Bxxxx_CONT common bits (addr=0x20-0x25) */ +#define DA9063_BUCK_EN 0x01 +#define DA9063_BUCK_GPI_MASK 0x06 +#define DA9063_BUCK_GPI_OFF 0x00 +#define DA9063_BUCK_GPI_GPIO1 0x02 +#define DA9063_BUCK_GPI_GPIO2 0x04 +#define DA9063_BUCK_GPI_GPIO13 0x06 +#define DA9063_BUCK_CONF 0x08 +#define DA9063_VBUCK_GPI_MASK 0x60 +#define DA9063_VBUCK_GPI_OFF 0x00 +#define DA9063_VBUCK_GPI_GPIO1 0x20 +#define DA9063_VBUCK_GPI_GPIO2 0x40 +#define DA9063_VBUCK_GPI_GPIO13 0x60 + +/* DA9063_REG_BCORE1_CONT specific bits (addr=0x21) */ +#define DA9063_CORE_SW_EN 0x10 +#define DA9063_CORE_SW_CONF 0x80 + +/* DA9063_REG_BPERI_CONT specific bits (addr=0x25) */ +#define DA9063_PERI_SW_EN 0x10 +#define DA9063_PERI_SW_CONF 0x80 + +/* DA9063_REG_LDOx_CONT common bits (addr=0x26-0x30) */ +#define DA9063_LDO_EN 0x01 +#define DA9063_LDO_GPI_MASK 0x06 +#define DA9063_LDO_GPI_OFF 0x00 +#define DA9063_LDO_GPI_GPIO1 0x02 +#define DA9063_LDO_GPI_GPIO2 0x04 +#define DA9063_LDO_GPI_GPIO13 0x06 +#define DA9063_LDO_PD_DIS 0x08 +#define DA9063_VLDO_GPI_MASK 0x60 +#define DA9063_VLDO_GPI_OFF 0x00 +#define DA9063_VLDO_GPI_GPIO1 0x20 +#define DA9063_VLDO_GPI_GPIO2 0x40 +#define DA9063_VLDO_GPI_GPIO13 0x60 +#define DA9063_LDO_CONF 0x80 + +/* DA9063_REG_LDO5_CONT specific bits (addr=0x2A) */ +#define DA9063_VLDO5_SEL 0x10 + +/* DA9063_REG_LDO6_CONT specific bits (addr=0x2B) */ +#define DA9063_VLDO6_SEL 0x10 + +/* DA9063_REG_LDO7_CONT specific bits (addr=0x2C) */ +#define DA9063_VLDO7_SEL 0x10 + +/* DA9063_REG_LDO8_CONT specific bits (addr=0x2D) */ +#define DA9063_VLDO8_SEL 0x10 + +/* DA9063_REG_LDO9_CONT specific bits (addr=0x2E) */ +#define DA9063_VLDO9_SEL 0x10 + +/* DA9063_REG_LDO10_CONT specific bits (addr=0x2F) */ +#define DA9063_VLDO10_SEL 0x10 + +/* DA9063_REG_LDO11_CONT specific bits (addr=0x30) */ +#define DA9063_VLDO11_SEL 0x10 + +/* DA9063_REG_VIB (addr=0x31) */ +#define DA9063_VIB_SET_MASK 0x3F +#define DA9063_VIB_SET_OFF 0 +#define DA9063_VIB_SET_MAX 0x3F + +/* DA9063_REG_DVC_1 (addr=0x32) */ +#define DA9063_VBCORE1_SEL 0x01 +#define DA9063_VBCORE2_SEL 0x02 +#define DA9063_VBPRO_SEL 0x04 +#define DA9063_VBMEM_SEL 0x08 +#define DA9063_VBPERI_SEL 0x10 +#define DA9063_VLDO1_SEL 0x20 +#define DA9063_VLDO2_SEL 0x40 +#define DA9063_VLDO3_SEL 0x80 + +/* DA9063_REG_DVC_2 (addr=0x33) */ +#define DA9063_VBIO_SEL 0x01 +#define DA9063_VLDO4_SEL 0x80 + +/* DA9063_REG_ADC_MAN (addr=0x34) */ +#define DA9063_ADC_MUX_MASK 0x0F +#define DA9063_ADC_MUX_VSYS 0x00 +#define DA9063_ADC_MUX_ADCIN1 0x01 +#define DA9063_ADC_MUX_ADCIN2 0x02 +#define DA9063_ADC_MUX_ADCIN3 0x03 +#define DA9063_ADC_MUX_T_SENSE 0x04 +#define DA9063_ADC_MUX_VBBAT 0x05 +#define DA9063_ADC_MUX_LDO_G1 0x08 +#define DA9063_ADC_MUX_LDO_G2 0x09 +#define DA9063_ADC_MUX_LDO_G3 0x0A +#define DA9063_ADC_MAN 0x10 +#define DA9063_ADC_MODE 0x20 + +/* DA9063_REG_ADC_CONT (addr=0x35) */ +#define DA9063_ADC_AUTO_VSYS_EN 0x01 +#define DA9063_ADC_AUTO_AD1_EN 0x02 +#define DA9063_ADC_AUTO_AD2_EN 0x04 +#define DA9063_ADC_AUTO_AD3_EN 0x08 +#define DA9063_ADC_AD1_ISRC_EN 0x10 +#define DA9063_ADC_AD2_ISRC_EN 0x20 +#define DA9063_ADC_AD3_ISRC_EN 0x40 +#define DA9063_COMP1V2_EN 0x80 + +/* DA9063_REG_VSYS_MON (addr=0x36) */ +#define DA9063_VSYS_VAL_MASK 0xFF +#define DA9063_VSYS_VAL_BASE 0x00 + +/* DA9063_REG_ADC_RES_L (addr=0x37) */ +#define DA9063_ADC_RES_L_BITS 2 +#define DA9063_ADC_RES_L_MASK 0xC0 + +/* DA9063_REG_ADC_RES_H (addr=0x38) */ +#define DA9063_ADC_RES_M_BITS 8 +#define DA9063_ADC_RES_M_MASK 0xFF + +/* DA9063_REG_(xxx_RES/ADC_RES_H) (addr=0x39-0x3F) */ +#define DA9063_ADC_VAL_MASK 0xFF + +/* DA9063_REG_COUNT_S (addr=0x40) */ +#define DA9063_RTC_READ 0x80 +#define DA9063_COUNT_SEC_MASK 0x3F + +/* DA9063_REG_COUNT_MI (addr=0x41) */ +#define DA9063_COUNT_MIN_MASK 0x3F + +/* DA9063_REG_COUNT_H (addr=0x42) */ +#define DA9063_COUNT_HOUR_MASK 0x1F + +/* DA9063_REG_COUNT_D (addr=0x43) */ +#define DA9063_COUNT_DAY_MASK 0x1F + +/* DA9063_REG_COUNT_MO (addr=0x44) */ +#define DA9063_COUNT_MONTH_MASK 0x0F + +/* DA9063_REG_COUNT_Y (addr=0x45) */ +#define DA9063_COUNT_YEAR_MASK 0x3F +#define DA9063_MONITOR 0x40 + +/* DA9063_REG_ALARM_MI (addr=0x46) */ +#define DA9063_ALARM_STATUS_ALARM 0x80 +#define DA9063_ALARM_STATUS_TICK 0x40 +#define DA9063_ALARM_MIN_MASK 0x3F + +/* DA9063_REG_ALARM_H (addr=0x47) */ +#define DA9063_ALARM_HOUR_MASK 0x1F + +/* DA9063_REG_ALARM_D (addr=0x48) */ +#define DA9063_ALARM_DAY_MASK 0x1F + +/* DA9063_REG_ALARM_MO (addr=0x49) */ +#define DA9063_TICK_WAKE 0x20 +#define DA9063_TICK_TYPE 0x10 +#define DA9063_TICK_TYPE_SEC 0x00 +#define DA9063_TICK_TYPE_MIN 0x10 +#define DA9063_ALARM_MONTH_MASK 0x0F + +/* DA9063_REG_ALARM_Y (addr=0x4A) */ +#define DA9063_TICK_ON 0x80 +#define DA9063_ALARM_ON 0x40 +#define DA9063_ALARM_YEAR_MASK 0x3F + +/* DA9063_REG_WAIT (addr=0x97)*/ +#define DA9063_REG_WAIT_TIME_MASK 0xF +#define DA9063_WAIT_TIME_0_US 0x0 +#define DA9063_WAIT_TIME_512_US 0x1 +#define DA9063_WAIT_TIME_1_MS 0x2 +#define DA9063_WAIT_TIME_2_MS 0x3 +#define DA9063_WAIT_TIME_4_1_MS 0x4 +#define DA9063_WAIT_TIME_8_2_MS 0x5 +#define DA9063_WAIT_TIME_16_4_MS 0x6 +#define DA9063_WAIT_TIME_32_8_MS 0x7 +#define DA9063_WAIT_TIME_65_5_MS 0x8 +#define DA9063_WAIT_TIME_128_MS 0x9 +#define DA9063_WAIT_TIME_256_MS 0xA +#define DA9063_WAIT_TIME_512_MS 0xB +#define DA9063_WAIT_TIME_1_S 0xC +#define DA9063_WAIT_TIME_2_1_S 0xD + +/* DA9063_REG_EN_32K (addr=0x98)*/ +#define DA9063_STABILIZ_TIME_MASK 0x7 +#define DA9063_CRYSTAL 0x08 +#define DA9063_DELAY_MODE 0x10 +#define DA9063_OUT_CLOCK 0x20 +#define DA9063_RTC_CLOCK 0x40 +#define DA9063_OUT_32K_EN 0x80 + +/* DA9063_REG_CHIP_VARIANT */ +#define DA9063_CHIP_VARIANT_SHIFT 4 + +/* DA9063_REG_BUCK_ILIM_A (addr=0x9A) */ +#define DA9063_BIO_ILIM_MASK 0x0F +#define DA9063_BMEM_ILIM_MASK 0xF0 + +/* DA9063_REG_BUCK_ILIM_B (addr=0x9B) */ +#define DA9063_BPRO_ILIM_MASK 0x0F +#define DA9063_BPERI_ILIM_MASK 0xF0 + +/* DA9063_REG_BUCK_ILIM_C (addr=0x9C) */ +#define DA9063_BCORE1_ILIM_MASK 0x0F +#define DA9063_BCORE2_ILIM_MASK 0xF0 + +/* DA9063_REG_Bxxxx_CFG common bits (addr=0x9D-0xA2) */ +#define DA9063_BUCK_FB_MASK 0x07 +#define DA9063_BUCK_PD_DIS_SHIFT 5 +#define DA9063_BUCK_MODE_MASK 0xC0 +#define DA9063_BUCK_MODE_MANUAL 0x00 +#define DA9063_BUCK_MODE_SLEEP 0x40 +#define DA9063_BUCK_MODE_SYNC 0x80 +#define DA9063_BUCK_MODE_AUTO 0xC0 + +/* DA9063_REG_BPRO_CFG (addr=0x9F) */ +#define DA9063_BPRO_VTTR_EN 0x08 +#define DA9063_BPRO_VTT_EN 0x10 + +/* DA9063_REG_VBxxxx_A/B (addr=0xA3-0xA8, 0xB4-0xB9) */ +#define DA9063_VBUCK_MASK 0x7F +#define DA9063_VBUCK_BIAS 0 +#define DA9063_BUCK_SL 0x80 + +/* DA9063_REG_VLDOx_A/B (addr=0xA9-0x3, 0xBA-0xC4) */ +#define DA9063_LDO_SL 0x80 + +/* DA9063_REG_VLDO1_A/B (addr=0xA9, 0xBA) */ +#define DA9063_VLDO1_MASK 0x3F +#define DA9063_VLDO1_BIAS 0 + +/* DA9063_REG_VLDO2_A/B (addr=0xAA, 0xBB) */ +#define DA9063_VLDO2_MASK 0x3F +#define DA9063_VLDO2_BIAS 0 + +/* DA9063_REG_VLDO3_A/B (addr=0xAB, 0xBC) */ +#define DA9063_VLDO3_MASK 0x7F +#define DA9063_VLDO3_BIAS 0 + +/* DA9063_REG_VLDO4_A/B (addr=0xAC, 0xBD) */ +#define DA9063_VLDO4_MASK 0x7F +#define DA9063_VLDO4_BIAS 0 + +/* DA9063_REG_VLDO5_A/B (addr=0xAD, 0xBE) */ +#define DA9063_VLDO5_MASK 0x3F +#define DA9063_VLDO5_BIAS 2 + +/* DA9063_REG_VLDO6_A/B (addr=0xAE, 0xBF) */ +#define DA9063_VLDO6_MASK 0x3F +#define DA9063_VLDO6_BIAS 2 + +/* DA9063_REG_VLDO7_A/B (addr=0xAF, 0xC0) */ +#define DA9063_VLDO7_MASK 0x3F +#define DA9063_VLDO7_BIAS 2 + +/* DA9063_REG_VLDO8_A/B (addr=0xB0, 0xC1) */ +#define DA9063_VLDO8_MASK 0x3F +#define DA9063_VLDO8_BIAS 2 + +/* DA9063_REG_VLDO9_A/B (addr=0xB1, 0xC2) */ +#define DA9063_VLDO9_MASK 0x3F +#define DA9063_VLDO9_BIAS 3 + +/* DA9063_REG_VLDO10_A/B (addr=0xB2, 0xC3) */ +#define DA9063_VLDO10_MASK 0x3F +#define DA9063_VLDO10_BIAS 2 + +/* DA9063_REG_VLDO11_A/B (addr=0xB3, 0xC4) */ +#define DA9063_VLDO11_MASK 0x3F +#define DA9063_VLDO11_BIAS 2 + +/* DA9063_REG_GPO11_LED (addr=0xC6) */ +/* DA9063_REG_GPO14_LED (addr=0xC7) */ +/* DA9063_REG_GPO15_LED (addr=0xC8) */ +#define DA9063_GPIO_DIM 0x80 +#define DA9063_GPIO_PWM_MASK 0x7F + +/* DA9063_REG_CONFIG_H (addr=0x10D) */ +#define DA9063_PWM_CLK_MASK 0x01 +#define DA9063_PWM_CLK_PWM2MHZ 0x00 +#define DA9063_PWM_CLK_PWM1MHZ 0x01 +#define DA9063_LDO8_MODE_MASK 0x02 +#define DA9063_LDO8_MODE_LDO 0 +#define DA9063_LDO8_MODE_VIBR 0x02 +#define DA9063_MERGE_SENSE_MASK 0x04 +#define DA9063_MERGE_SENSE_GP_FB2 0x00 +#define DA9063_MERGE_SENSE_GPIO4 0x04 +#define DA9063_BCORE_MERGE 0x08 +#define DA9063_BPRO_OD 0x10 +#define DA9063_BCORE2_OD 0x20 +#define DA9063_BCORE1_OD 0x40 +#define DA9063_BUCK_MERGE 0x80 + +/* DA9063_REG_CONFIG_I (addr=0x10E) */ +#define DA9063_NONKEY_PIN_MASK 0x03 +#define DA9063_NONKEY_PIN_PORT 0x00 +#define DA9063_NONKEY_PIN_SWDOWN 0x01 +#define DA9063_NONKEY_PIN_AUTODOWN 0x02 +#define DA9063_NONKEY_PIN_AUTOFLPRT 0x03 + +/* DA9063_REG_MON_REG_5 (addr=0x116) */ +#define DA9063_MON_A8_IDX_MASK 0x07 +#define DA9063_MON_A8_IDX_NONE 0x00 +#define DA9063_MON_A8_IDX_BCORE1 0x01 +#define DA9063_MON_A8_IDX_BCORE2 0x02 +#define DA9063_MON_A8_IDX_BPRO 0x03 +#define DA9063_MON_A8_IDX_LDO3 0x04 +#define DA9063_MON_A8_IDX_LDO4 0x05 +#define DA9063_MON_A8_IDX_LDO11 0x06 +#define DA9063_MON_A9_IDX_MASK 0x70 +#define DA9063_MON_A9_IDX_NONE 0x00 +#define DA9063_MON_A9_IDX_BIO 0x01 +#define DA9063_MON_A9_IDX_BMEM 0x02 +#define DA9063_MON_A9_IDX_BPERI 0x03 +#define DA9063_MON_A9_IDX_LDO1 0x04 +#define DA9063_MON_A9_IDX_LDO2 0x05 +#define DA9063_MON_A9_IDX_LDO5 0x06 + +/* DA9063_REG_MON_REG_6 (addr=0x117) */ +#define DA9063_MON_A10_IDX_MASK 0x07 +#define DA9063_MON_A10_IDX_NONE 0x00 +#define DA9063_MON_A10_IDX_LDO6 0x01 +#define DA9063_MON_A10_IDX_LDO7 0x02 +#define DA9063_MON_A10_IDX_LDO8 0x03 +#define DA9063_MON_A10_IDX_LDO9 0x04 +#define DA9063_MON_A10_IDX_LDO10 0x05 + +#endif /* _DA9063_REG_H */ -- cgit v1.2.3 From 8e685483b0ba17fe08cfc36fb86b3688a24b2090 Mon Sep 17 00:00:00 2001 From: Krystian Garbaciak Date: Mon, 29 Jul 2013 19:00:43 +0200 Subject: mfd: da9063: Add Dialog DA9063 core driver This is MFD module providing access to registers and interrupts of DA906x series PMIC. It is used by other functional modules, registered as MFD cells. Driver uses regmap with paging to access extended register list. Register map is divided into two pages, where the second page is used during initialisation. This module provides support to following functional cells: - Regulators - RTC - HWMON - OnKey (power key misc input device) - Vibration (force-feedback input device) - Watchdog - LEDs Signed-off-by: Krystian Garbaciak Signed-off-by: Philipp Zabel Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/da9063/core.h | 55 +++++++++++++++++++ include/linux/mfd/da9063/pdata.h | 111 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 166 insertions(+) create mode 100644 include/linux/mfd/da9063/core.h create mode 100644 include/linux/mfd/da9063/pdata.h (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h new file mode 100644 index 000000000000..ec2fd2aa24ae --- /dev/null +++ b/include/linux/mfd/da9063/core.h @@ -0,0 +1,55 @@ +/* + * Definitions for DA9063 MFD driver + * + * Copyright 2012 Dialog Semiconductor Ltd. + * + * Author: Michal Hajduk + * Krystian Garbaciak + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __MFD_DA9063_CORE_H__ +#define __MFD_DA9063_CORE_H__ + +#include +#include + +/* DA9063 modules */ +#define DA9063_DRVNAME_CORE "da9063-core" +#define DA9063_DRVNAME_REGULATORS "da9063-regulators" +#define DA9063_DRVNAME_LEDS "da9063-leds" +#define DA9063_DRVNAME_WATCHDOG "da9063-watchdog" +#define DA9063_DRVNAME_HWMON "da9063-hwmon" +#define DA9063_DRVNAME_ONKEY "da9063-onkey" +#define DA9063_DRVNAME_RTC "da9063-rtc" +#define DA9063_DRVNAME_VIBRATION "da9063-vibration" + +enum da9063_models { + PMIC_DA9063 = 0x61, +}; + +struct da9063 { + /* Device */ + struct device *dev; + unsigned short model; + unsigned short revision; + unsigned int flags; + + /* Control interface */ + struct regmap *regmap; + + /* Interrupts */ + int chip_irq; + unsigned int irq_base; +}; + +int da9063_device_init(struct da9063 *da9063, unsigned int irq); + +void da9063_device_exit(struct da9063 *da9063); + +#endif /* __MFD_DA9063_CORE_H__ */ diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h new file mode 100644 index 000000000000..95c8742215a7 --- /dev/null +++ b/include/linux/mfd/da9063/pdata.h @@ -0,0 +1,111 @@ +/* + * Platform configuration options for DA9063 + * + * Copyright 2012 Dialog Semiconductor Ltd. + * + * Author: Michal Hajduk + * Author: Krystian Garbaciak + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __MFD_DA9063_PDATA_H__ +#define __MFD_DA9063_PDATA_H__ + +#include + +/* + * Regulator configuration + */ +/* DA9063 regulator IDs */ +enum { + /* BUCKs */ + DA9063_ID_BCORE1, + DA9063_ID_BCORE2, + DA9063_ID_BPRO, + DA9063_ID_BMEM, + DA9063_ID_BIO, + DA9063_ID_BPERI, + + /* BCORE1 and BCORE2 in merged mode */ + DA9063_ID_BCORES_MERGED, + /* BMEM and BIO in merged mode */ + DA9063_ID_BMEM_BIO_MERGED, + /* When two BUCKs are merged, they cannot be reused separately */ + + /* LDOs */ + DA9063_ID_LDO1, + DA9063_ID_LDO2, + DA9063_ID_LDO3, + DA9063_ID_LDO4, + DA9063_ID_LDO5, + DA9063_ID_LDO6, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO10, + DA9063_ID_LDO11, +}; + +/* Regulators platform data */ +struct da9063_regulator_data { + int id; + struct regulator_init_data *initdata; +}; + +struct da9063_regulators_pdata { + unsigned n_regulators; + struct da9063_regulator_data *regulator_data; +}; + + +/* + * RGB LED configuration + */ +/* LED IDs for flags in struct led_info. */ +enum { + DA9063_GPIO11_LED, + DA9063_GPIO14_LED, + DA9063_GPIO15_LED, + + DA9063_LED_NUM +}; +#define DA9063_LED_ID_MASK 0x3 + +/* LED polarity for flags in struct led_info. */ +#define DA9063_LED_HIGH_LEVEL_ACTIVE 0x0 +#define DA9063_LED_LOW_LEVEL_ACTIVE 0x4 + + +/* + * General PMIC configuration + */ +/* HWMON ADC channels configuration */ +#define DA9063_FLG_FORCE_IN0_MANUAL_MODE 0x0010 +#define DA9063_FLG_FORCE_IN0_AUTO_MODE 0x0020 +#define DA9063_FLG_FORCE_IN1_MANUAL_MODE 0x0040 +#define DA9063_FLG_FORCE_IN1_AUTO_MODE 0x0080 +#define DA9063_FLG_FORCE_IN2_MANUAL_MODE 0x0100 +#define DA9063_FLG_FORCE_IN2_AUTO_MODE 0x0200 +#define DA9063_FLG_FORCE_IN3_MANUAL_MODE 0x0400 +#define DA9063_FLG_FORCE_IN3_AUTO_MODE 0x0800 + +/* Disable register caching. */ +#define DA9063_FLG_NO_CACHE 0x0008 + +struct da9063; + +/* DA9063 platform data */ +struct da9063_pdata { + int (*init)(struct da9063 *da9063); + int irq_base; + unsigned flags; + struct da9063_regulators_pdata *regulators_pdata; + struct led_platform_data *leds_pdata; +}; + +#endif /* __MFD_DA9063_PDATA_H__ */ -- cgit v1.2.3 From a0e08b8606f3c0722b235a09b537264e5b14f748 Mon Sep 17 00:00:00 2001 From: Krystian Garbaciak Date: Mon, 29 Jul 2013 19:00:44 +0200 Subject: mfd: da9063: Add IRQ support This patch adds a regmap irqchip for DA9063 IRQs. It depends on git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git tags/regmap-irq-ack-mask Signed-off-by: Krystian Garbaciak Signed-off-by: Philipp Zabel Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/da9063/core.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index ec2fd2aa24ae..2d2a0af675fd 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -33,6 +33,41 @@ enum da9063_models { PMIC_DA9063 = 0x61, }; +/* Interrupts */ +enum da9063_irqs { + DA9063_IRQ_ONKEY = 0, + DA9063_IRQ_ALARM, + DA9063_IRQ_TICK, + DA9063_IRQ_ADC_RDY, + DA9063_IRQ_SEQ_RDY, + DA9063_IRQ_WAKE, + DA9063_IRQ_TEMP, + DA9063_IRQ_COMP_1V2, + DA9063_IRQ_LDO_LIM, + DA9063_IRQ_REG_UVOV, + DA9063_IRQ_VDD_MON, + DA9063_IRQ_WARN, + DA9063_IRQ_GPI0, + DA9063_IRQ_GPI1, + DA9063_IRQ_GPI2, + DA9063_IRQ_GPI3, + DA9063_IRQ_GPI4, + DA9063_IRQ_GPI5, + DA9063_IRQ_GPI6, + DA9063_IRQ_GPI7, + DA9063_IRQ_GPI8, + DA9063_IRQ_GPI9, + DA9063_IRQ_GPI10, + DA9063_IRQ_GPI11, + DA9063_IRQ_GPI12, + DA9063_IRQ_GPI13, + DA9063_IRQ_GPI14, + DA9063_IRQ_GPI15, +}; + +#define DA9063_IRQ_BASE_OFFSET 0 +#define DA9063_NUM_IRQ (DA9063_IRQ_GPI15 + 1 - DA9063_IRQ_BASE_OFFSET) + struct da9063 { /* Device */ struct device *dev; @@ -46,10 +81,13 @@ struct da9063 { /* Interrupts */ int chip_irq; unsigned int irq_base; + struct regmap_irq_chip_data *regmap_irq; }; int da9063_device_init(struct da9063 *da9063, unsigned int irq); +int da9063_irq_init(struct da9063 *da9063); void da9063_device_exit(struct da9063 *da9063); +void da9063_irq_exit(struct da9063 *da9063); #endif /* __MFD_DA9063_CORE_H__ */ -- cgit v1.2.3 From cc01b4639c94b1732995a9909a8973bfed67db2b Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 13 Aug 2013 13:23:11 +0530 Subject: mfd: palmas: Add support for external control configuration Some of Palmas resources like clock, SMPSs, LDOs etc can be controlled by external pins ENABLE1, ENABLE2 or NSLEEP. Add support to configure these resources to externally controlled. Signed-off-by: Laxman Dewangan Acked-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/palmas.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..d2fca1c6f7df 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -183,6 +183,50 @@ enum palmas_regulators { PALMAS_NUM_REGS, }; +/* External controll signal name */ +enum { + PALMAS_EXT_CONTROL_ENABLE1 = 0x1, + PALMAS_EXT_CONTROL_ENABLE2 = 0x2, + PALMAS_EXT_CONTROL_NSLEEP = 0x4, +}; + +/* + * Palmas device resources can be controlled externally for + * enabling/disabling it rather than register write through i2c. + * Add the external controlled requestor ID for different resources. + */ +enum palmas_external_requestor_id { + PALMAS_EXTERNAL_REQSTR_ID_REGEN1, + PALMAS_EXTERNAL_REQSTR_ID_REGEN2, + PALMAS_EXTERNAL_REQSTR_ID_SYSEN1, + PALMAS_EXTERNAL_REQSTR_ID_SYSEN2, + PALMAS_EXTERNAL_REQSTR_ID_CLK32KG, + PALMAS_EXTERNAL_REQSTR_ID_CLK32KGAUDIO, + PALMAS_EXTERNAL_REQSTR_ID_REGEN3, + PALMAS_EXTERNAL_REQSTR_ID_SMPS12, + PALMAS_EXTERNAL_REQSTR_ID_SMPS3, + PALMAS_EXTERNAL_REQSTR_ID_SMPS45, + PALMAS_EXTERNAL_REQSTR_ID_SMPS6, + PALMAS_EXTERNAL_REQSTR_ID_SMPS7, + PALMAS_EXTERNAL_REQSTR_ID_SMPS8, + PALMAS_EXTERNAL_REQSTR_ID_SMPS9, + PALMAS_EXTERNAL_REQSTR_ID_SMPS10, + PALMAS_EXTERNAL_REQSTR_ID_LDO1, + PALMAS_EXTERNAL_REQSTR_ID_LDO2, + PALMAS_EXTERNAL_REQSTR_ID_LDO3, + PALMAS_EXTERNAL_REQSTR_ID_LDO4, + PALMAS_EXTERNAL_REQSTR_ID_LDO5, + PALMAS_EXTERNAL_REQSTR_ID_LDO6, + PALMAS_EXTERNAL_REQSTR_ID_LDO7, + PALMAS_EXTERNAL_REQSTR_ID_LDO8, + PALMAS_EXTERNAL_REQSTR_ID_LDO9, + PALMAS_EXTERNAL_REQSTR_ID_LDOLN, + PALMAS_EXTERNAL_REQSTR_ID_LDOUSB, + + /* Last entry */ + PALMAS_EXTERNAL_REQSTR_ID_MAX, +}; + struct palmas_pmic_platform_data { /* An array of pointers to regulator init data indexed by regulator * ID @@ -2866,4 +2910,9 @@ static inline int palmas_irq_get_virq(struct palmas *palmas, int irq) return regmap_irq_get_virq(palmas->irq_data, irq); } + +int palmas_ext_control_req_config(struct palmas *palmas, + enum palmas_external_requestor_id ext_control_req_id, + int ext_ctrl, bool enable); + #endif /* __LINUX_MFD_PALMAS_H */ -- cgit v1.2.3 From bd0eae4e1cd5c4ff7c2a9ebcb3e78ea4631251ef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 24 Jul 2013 15:05:19 -0700 Subject: PPS: convert class code to use dev_groups The dev_attrs field of struct class is going away soon, dev_groups should be used instead. This converts the pps class code to use the correct field. Cc: Rodolfo Giometti Signed-off-by: Greg Kroah-Hartman --- include/linux/pps_kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 7db3eb93a079..1d2cd21242e8 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -80,7 +80,7 @@ struct pps_device { * Global variables */ -extern struct device_attribute pps_attrs[]; +extern const struct attribute_group *pps_groups[]; /* * Internal functions. -- cgit v1.2.3 From 7cb14ba75d57910cc4b62115dd5db7bd83c93684 Mon Sep 17 00:00:00 2001 From: Andreas Robinson Date: Tue, 20 Aug 2013 15:33:19 +0930 Subject: modules: add support for soft module dependencies Additional and optional dependencies not found while building the kernel and modules, can now be declared explicitly. Signed-off-by: Andreas Robinson Acked-by: Herbert Xu Signed-off-by: Rusty Russell --- include/linux/module.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 46f1ea01e6f6..504035f3ece1 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -97,6 +97,11 @@ extern const struct gtype##_id __mod_##gtype##_table \ /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) +/* Soft module dependencies. See man modprobe.d for details. + * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") + */ +#define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) + /* * The following license idents are currently accepted as indicating free * software modules -- cgit v1.2.3 From ab013c5f60b7ead254863c75b9adc2a47992d01b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Aug 2013 15:33:19 +0930 Subject: module: Add flag to allow mod params to have no arguments Currently the params.c code allows only two "set" functions to have no arguments. If a parameter does not have an argument, then it looks at the set function and tests if it is either param_set_bool() or param_set_bint(). If it is not one of these functions, then it fails the loading of the module. But there may be module parameters that have different set functions and still allow no arguments. But unless each of these cases adds their function to the if statement, it wont be allowed to have no arguments. This method gets rather messing and does not scale. Instead, introduce a flags field to the kernel_param_ops, where if the flag KERNEL_PARAM_FL_NOARG is set, the parameter will not fail if it does not contain an argument. It will be expected that the corresponding set function can handle a NULL pointer as "val". Signed-off-by: Steven Rostedt Signed-off-by: Rusty Russell --- include/linux/moduleparam.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 27d9da3f86ff..c3eb102a9cc8 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -36,7 +36,18 @@ static const char __UNIQUE_ID(name)[] \ struct kernel_param; +/* + * Flags available for kernel_param_ops + * + * NOARG - the parameter allows for no argument (foo instead of foo=1) + */ +enum { + KERNEL_PARAM_FL_NOARG = (1 << 0) +}; + struct kernel_param_ops { + /* How the ops should behave */ + unsigned int flags; /* Returns 0, or -errno. arg is in kp->arg. */ int (*set)(const char *val, const struct kernel_param *kp); /* Returns length written or -errno. Buffer is 4k (ie. be short!) */ @@ -187,7 +198,7 @@ struct kparam_array /* Obsolete - use module_param_cb() */ #define module_param_call(name, set, get, arg, perm) \ static struct kernel_param_ops __param_ops_##name = \ - { (void *)set, (void *)get }; \ + { 0, (void *)set, (void *)get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ name, &__param_ops_##name, arg, \ (perm) + sizeof(__check_old_set_param(set))*0, -1) -- cgit v1.2.3 From 773ccdfd9cc6f9bf8ec75a59fa742d7a663a5903 Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 20 Aug 2013 14:18:51 +0800 Subject: mfd: rtsx: Read vendor setting from config space Normally OEMs will set vendor setting to the config space of Realtek card reader in BIOS stage. This patch reads the setting at the first, and configure the internal registers according to it, to improve card reader's compatibility condition. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 7a9f7089435d..9cba73703704 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -184,11 +184,26 @@ #define CARD_SHARE_BAROSSA_SD 0x01 #define CARD_SHARE_BAROSSA_MS 0x02 +/* CARD_DRIVE_SEL */ +#define MS_DRIVE_8mA (0x01 << 6) +#define MMC_DRIVE_8mA (0x01 << 4) +#define XD_DRIVE_8mA (0x01 << 2) +#define GPIO_DRIVE_8mA 0x01 +#define RTS5209_CARD_DRIVE_DEFAULT (MS_DRIVE_8mA | MMC_DRIVE_8mA |\ + XD_DRIVE_8mA | GPIO_DRIVE_8mA) +#define RTL8411_CARD_DRIVE_DEFAULT (MS_DRIVE_8mA | MMC_DRIVE_8mA |\ + XD_DRIVE_8mA) +#define RTSX_CARD_DRIVE_DEFAULT (MS_DRIVE_8mA | GPIO_DRIVE_8mA) + /* SD30_DRIVE_SEL */ #define DRIVER_TYPE_A 0x05 #define DRIVER_TYPE_B 0x03 #define DRIVER_TYPE_C 0x02 #define DRIVER_TYPE_D 0x01 +#define CFG_DRIVER_TYPE_A 0x02 +#define CFG_DRIVER_TYPE_B 0x03 +#define CFG_DRIVER_TYPE_C 0x01 +#define CFG_DRIVER_TYPE_D 0x00 /* FPDCTL */ #define SSC_POWER_DOWN 0x01 @@ -684,6 +699,8 @@ #define DUMMY_REG_RESET_0 0xFE90 +#define AUTOLOAD_CFG_BASE 0xFF00 + /* Memory mapping */ #define SRAM_BASE 0xE600 #define RBUF_BASE 0xF400 @@ -726,6 +743,11 @@ #define PHY_FLD4 0x1E #define PHY_DUM_REG 0x1F +#define LCTLR 0x80 +#define PCR_SETTING_REG1 0x724 +#define PCR_SETTING_REG2 0x814 +#define PCR_SETTING_REG3 0x747 + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) struct rtsx_pcr; @@ -747,6 +769,7 @@ struct pcr_ops { u8 voltage); unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); + void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); }; enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; @@ -788,7 +811,6 @@ struct rtsx_pcr { struct completion *finish_me; unsigned int cur_clock; - bool ms_pmos; bool remove_pci; bool msi_en; @@ -806,6 +828,16 @@ struct rtsx_pcr { #define IC_VER_D 3 u8 ic_version; + u8 sd30_drive_sel_1v8; + u8 sd30_drive_sel_3v3; + u8 card_drive_sel; +#define ASPM_L1_EN 0x02 + u8 aspm_en; + +#define PCR_MS_PMOS (1 << 0) +#define PCR_REVERSE_SOCKET (1 << 1) + u32 flags; + const u32 *sd_pull_ctl_enable_tbl; const u32 *sd_pull_ctl_disable_tbl; const u32 *ms_pull_ctl_enable_tbl; -- cgit v1.2.3 From 5947c167d145f32d4475d647a87e2af2699efe45 Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 20 Aug 2013 14:18:52 +0800 Subject: mfd: rtsx: Add shutdown callback in rtsx_pci_driver Some actions to clear power state should be handled in .shutdown callback in rtsx_pci_driver. This patch adopts the following measures to catch this goal: 1. Add a function rtsx_pci_power_off to abstract the common ops in .shutdown and .suspend 2. Add pcr->ops->force_power_down to fulfill the individual action for each reader model Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 9cba73703704..11ab786fdc83 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -25,8 +25,7 @@ #include #include - -#include "rtsx_common.h" +#include #define MAX_RW_REG_CNT 1024 @@ -536,6 +535,10 @@ #define SAMPLE_VAR_CLK0 (0x01 << 4) #define SAMPLE_VAR_CLK1 (0x02 << 4) +/* HOST_SLEEP_STATE */ +#define HOST_ENTER_S1 1 +#define HOST_ENTER_S3 2 + #define MS_CFG 0xFD40 #define MS_TPC 0xFD41 #define MS_TRANS_CFG 0xFD42 @@ -701,6 +704,11 @@ #define AUTOLOAD_CFG_BASE 0xFF00 +#define PM_CTRL1 0xFF44 +#define PM_CTRL2 0xFF45 +#define PM_CTRL3 0xFF46 +#define PM_CTRL4 0xFF47 + /* Memory mapping */ #define SRAM_BASE 0xE600 #define RBUF_BASE 0xF400 @@ -770,6 +778,7 @@ struct pcr_ops { unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); + void (*force_power_down)(struct rtsx_pcr *pcr); }; enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; -- cgit v1.2.3 From 0ccc0065c90284f283314e52a96e76ae8a8dce0a Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 20 Aug 2013 14:18:54 +0800 Subject: mfd: rtsx: Clear hardware PFM mode in rtl8411b Clear hw_pfm_en to disable hardware PFM mode, to fix a bug that in some situation registers in 0xFDxx domain can't be accessed. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 11ab786fdc83..9a16276bc080 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -687,6 +687,7 @@ #define PME_FORCE_CTL 0xFE56 #define ASPM_FORCE_CTL 0xFE57 #define PM_CLK_FORCE_CTL 0xFE58 +#define FUNC_FORCE_CTL 0xFE59 #define PERST_GLITCH_WIDTH 0xFE5C #define CHANGE_LINK_STATE 0xFE5B #define RESET_LOAD_REG 0xFE5E -- cgit v1.2.3 From eb891c65c9c87e55f728d95bcc514dea337aed12 Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 20 Aug 2013 14:18:55 +0800 Subject: mfd: rtsx: Configure to enter a deeper power-saving mode in S3 Set a bit to enable rts5227 and rts5249 to enter a deeper internal power-saving mode in S3, and recover it after resuming. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 9a16276bc080..dd0bd5806adc 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -779,7 +779,7 @@ struct pcr_ops { unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); - void (*force_power_down)(struct rtsx_pcr *pcr); + void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state); }; enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; -- cgit v1.2.3 From 09fd86780bb4603df1886e17127f5beb97f70ffb Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 20 Aug 2013 14:18:56 +0800 Subject: mfd: rtsx: Copyright modifications Update copyright date, remove author address and add Roger Tseng. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_common.h | 3 +-- include/linux/mfd/rtsx_pci.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h index 2b13970596f5..443176ee1ab0 100644 --- a/include/linux/mfd/rtsx_common.h +++ b/include/linux/mfd/rtsx_common.h @@ -1,6 +1,6 @@ /* Driver for Realtek driver-based card reader * - * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved. + * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -17,7 +17,6 @@ * * Author: * Wei WANG - * No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China */ #ifndef __RTSX_COMMON_H diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index dd0bd5806adc..daefca1bafb3 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -1,6 +1,6 @@ /* Driver for Realtek PCI-Express card reader * - * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved. + * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -17,7 +17,6 @@ * * Author: * Wei WANG - * No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China */ #ifndef __RTSX_PCI_H -- cgit v1.2.3 From 5a581b367b5df0531265311fc681c2abd377e5e6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Jul 2013 03:53:54 -0700 Subject: jiffies: Avoid undefined behavior from signed overflow According to the C standard 3.4.3p3, overflow of a signed integer results in undefined behavior. This commit therefore changes the definitions of time_after(), time_after_eq(), time_after64(), and time_after_eq64() to avoid this undefined behavior. The trick is that the subtraction is done using unsigned arithmetic, which according to 6.2.5p9 cannot overflow because it is defined as modulo arithmetic. This has the added (though admittedly quite small) benefit of shortening four lines of code by four characters each. Note that the C standard considers the cast from unsigned to signed to be implementation-defined, see 6.3.1.3p3. However, on a two's-complement system, an implementation that defines anything other than a reinterpretation of the bits is free to come to me, and I will be happy to act as a witness for its being committed to an insane asylum. (Although I have nothing against saturating arithmetic or signals in some cases, these things really should not be the default when compiling an operating-system kernel.) Signed-off-by: Paul E. McKenney Cc: John Stultz Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Linus Torvalds Cc: Eric Dumazet Cc: Kevin Easton [ paulmck: Included time_after64() and time_after_eq64(), as suggested by Eric Dumazet, also fixed commit message.] Reviewed-by: Josh Triplett --- include/linux/jiffies.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 97ba4e78a37e..d235e88cfd7c 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void) #define time_after(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(b) - (long)(a) < 0)) + ((long)((b) - (a)) < 0)) #define time_before(a,b) time_after(b,a) #define time_after_eq(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(a) - (long)(b) >= 0)) + ((long)((a) - (b)) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) /* @@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void) #define time_after64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(b) - (__s64)(a) < 0)) + ((__s64)((b) - (a)) < 0)) #define time_before64(a,b) time_after64(b,a) #define time_after_eq64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(a) - (__s64)(b) >= 0)) + ((__s64)((a) - (b)) >= 0)) #define time_before_eq64(a,b) time_after_eq64(b,a) #define time_in_range64(a, b, c) \ -- cgit v1.2.3 From af30cb446dd5f4ad5b93d7d4188c49a864c0d643 Mon Sep 17 00:00:00 2001 From: Chandra Seetharaman Date: Tue, 6 Aug 2013 17:27:07 -0500 Subject: quota: Add a new quotactl command Q_XGETQSTATV XFS now supports three types of quotas (user, group and project). Current version of Q_XGETSTAT has support for only two types of quotas. In order to support three types of quotas, the interface, specifically struct fs_quota_stat, need to be expanded. Current version of fs_quota_stat does not allow expansion without breaking backward compatibility. So, a quotactl command and new fs_quota_stat structure need to be added. This patch adds a new command Q_XGETQSTATV to quotactl() which takes a new data structure fs_quota_statv. This new data structure provides support for future expansion and backward compatibility. Callers of the new quotactl command have to set the version of the data structure being passed, and kernel will fill as much data as requested. If the kernel does not support the user-space provided version, EINVAL will be returned. User-space can reduce the version number and call the same quotactl again. Signed-off-by: Chandra Seetharaman Reviewed-by: Jan Kara Reviewed-by: Rich Johnston Signed-off-by: Ben Myers [v2: Applied rjohnston's suggestions as per Chandra's request. -bpm] --- include/linux/quota.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index d13371134c59..cc7494a35429 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -328,6 +328,7 @@ struct quotactl_ops { int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); int (*set_xstate)(struct super_block *, unsigned int, int); + int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); }; struct quota_format_type { -- cgit v1.2.3 From 6853152689d47b4a1eb9f38a25a18f3f8b7a60de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Aug 2013 16:48:54 -0700 Subject: sysfs.h: fix __BIN_ATTR_RW() __BIN_ATTR_RW() wasn't passing in the _size field. As it would break the build if this macro was ever used, it's obvious no one had ever tried to use it before. Fix it so that it can be used. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 9e8a9b555ad6..0f04958623d7 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -153,7 +153,7 @@ struct bin_attribute { #define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name, \ (S_IWUSR | S_IRUGO), _name##_read, \ - _name##_write) + _name##_write, _size) #define __BIN_ATTR_NULL __ATTR_NULL -- cgit v1.2.3 From 8d3214c4e8c8be6efd8ec7a172239ebbd4deb04b Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 18 Aug 2013 03:13:26 +0400 Subject: sh_eth: remove 'register_type' field from 'struct sh_eth_plat_data' Now that the 'register_type' field of the 'sh_eth' driver's platform data is not used by the driver anymore, it's time to remove it and its initializers from the SH platform code. Also move *enum* declaring values for this field from to the local driver's header file as they're only needed by the driver itself now... Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- include/linux/sh_eth.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 6205eeba392b..90b5e30c2f22 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -5,17 +5,10 @@ #include enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; -enum { - SH_ETH_REG_GIGABIT, - SH_ETH_REG_FAST_RCAR, - SH_ETH_REG_FAST_SH4, - SH_ETH_REG_FAST_SH3_SH2 -}; struct sh_eth_plat_data { int phy; int edmac_endian; - int register_type; phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr); -- cgit v1.2.3 From dbe34724c08ea25d39d31735120077013fbbb6fb Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 19 Aug 2013 17:47:40 +0530 Subject: drivers: net: cpsw: remove platform data header file of cpsw CPSW driver no longer supports platform register as all the SoCs which has CPSW are supporting DT only booting, so moving cpsw.h header file from platform include to drivers/net/ethernet/ti Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- include/linux/platform_data/cpsw.h | 44 -------------------------------------- 1 file changed, 44 deletions(-) delete mode 100644 include/linux/platform_data/cpsw.h (limited to 'include/linux') diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h deleted file mode 100644 index bb3cd58d71e3..000000000000 --- a/include/linux/platform_data/cpsw.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - * Texas Instruments Ethernet Switch Driver - * - * Copyright (C) 2012 Texas Instruments - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ -#ifndef __CPSW_H__ -#define __CPSW_H__ - -#include - -struct cpsw_slave_data { - char phy_id[MII_BUS_ID_SIZE]; - int phy_if; - u8 mac_addr[ETH_ALEN]; - u16 dual_emac_res_vlan; /* Reserved VLAN for DualEMAC */ - -}; - -struct cpsw_platform_data { - u32 ss_reg_ofs; /* Subsystem control register offset */ - u32 channels; /* number of cpdma channels (symmetric) */ - u32 slaves; /* number of slave cpgmac ports */ - struct cpsw_slave_data *slave_data; - u32 active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */ - u32 cpts_clock_mult; /* convert input clock ticks to nanoseconds */ - u32 cpts_clock_shift; /* convert input clock ticks to nanoseconds */ - u32 ale_entries; /* ale table size */ - u32 bd_ram_size; /*buffer descriptor ram size */ - u32 rx_descs; /* Number of Rx Descriptios */ - u32 mac_control; /* Mac control register */ - u16 default_vlan; /* Def VLAN for ALE lookup in VLAN aware mode*/ - bool dual_emac; /* Enable Dual EMAC mode */ -}; - -#endif /* __CPSW_H__ */ -- cgit v1.2.3 From 1ddff7da0faecffdcdeab3d981fb8241453cea44 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Mon, 19 Aug 2013 15:39:19 +0400 Subject: can: mcp251x: Replace power callbacks with regulator API This patch replaces power callbacks to the regulator API. To improve the readability of the code, helper for the regulator enable/disable was added. Acked-by: Haojian Zhuang Signed-off-by: Alexander Shiyan Signed-off-by: Marc Kleine-Budde --- include/linux/can/platform/mcp251x.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 089fe43211a4..8a2725676d8b 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -9,26 +9,15 @@ #include -/** +/* * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data * @oscillator_frequency: - oscillator frequency in Hz * @irq_flags: - IRQF configuration flags - * @board_specific_setup: - called before probing the chip (power,reset) - * @transceiver_enable: - called to power on/off the transceiver - * @power_enable: - called to power on/off the mcp *and* the - * transceiver - * - * Please note that you should define power_enable or transceiver_enable or - * none of them. Defining both of them is no use. - * */ struct mcp251x_platform_data { unsigned long oscillator_frequency; unsigned long irq_flags; - int (*board_specific_setup)(struct spi_device *spi); - int (*transceiver_enable)(int enable); - int (*power_enable) (int enable); }; #endif /* __CAN_PLATFORM_MCP251X_H__ */ -- cgit v1.2.3 From ae5d589e5f9f3217656ada632869968178886ac6 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Mon, 19 Aug 2013 15:39:20 +0400 Subject: can: mcp251x: Eliminate irq_flags from driver platform_data Flags is not used by boards, so remove this field from the driver platform_data. Signed-off-by: Alexander Shiyan Signed-off-by: Marc Kleine-Budde --- include/linux/can/platform/mcp251x.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 8a2725676d8b..dc029dba7a03 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -12,12 +12,10 @@ /* * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data * @oscillator_frequency: - oscillator frequency in Hz - * @irq_flags: - IRQF configuration flags */ struct mcp251x_platform_data { unsigned long oscillator_frequency; - unsigned long irq_flags; }; #endif /* __CAN_PLATFORM_MCP251X_H__ */ -- cgit v1.2.3 From 183912d352a242a276a7877852f107459a13aff9 Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 15 Aug 2013 14:01:40 +0100 Subject: of: move of_get_cpu_node implementation to DT core library This patch moves the generalized implementation of of_get_cpu_node from PowerPC to DT core library, thereby adding support for retrieving cpu node for a given logical cpu index on any architecture. The CPU subsystem can now use this function to assign of_node in the cpu device while registering CPUs. It is recommended to use these helper function only in pre-SMP/early initialisation stages to retrieve CPU device node pointers in logical ordering. Once the cpu devices are registered, it can be retrieved easily from cpu device of_node which avoids unnecessary parsing and matching. Cc: Benjamin Herrenschmidt Cc: Grant Likely Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- include/linux/cpu.h | 1 + include/linux/of.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..3dfed2b9ae2e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -28,6 +28,7 @@ struct cpu { extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); +extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id); extern int cpu_add_dev_attr(struct device_attribute *attr); extern void cpu_remove_dev_attr(struct device_attribute *attr); diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..c0bb2f188048 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -266,6 +266,7 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); +extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -459,6 +460,12 @@ static inline const void *of_get_property(const struct device_node *node, return NULL; } +static inline struct device_node *of_get_cpu_node(int cpu, + unsigned int *thread) +{ + return NULL; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { -- cgit v1.2.3 From bd00860e960e52658cebfd65eeb4748ed6ff039f Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 18 Jul 2013 11:22:04 +0100 Subject: of/device: add helper to get cpu device node from logical cpu index Multiple drivers need to get the cpu device node from the cpu logical index and then access the of_node. This patch adds helper function to fetch the device node directly. Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- include/linux/of_device.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 9d27475feec1..82ce324fdce7 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,6 +1,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H +#include #include #include /* temporary until merge */ @@ -43,6 +44,15 @@ static inline void of_device_node_put(struct device *dev) of_node_put(dev->of_node); } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + struct device *cpu_dev; + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return NULL; + return of_node_get(cpu_dev->of_node); +} + #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -67,6 +77,11 @@ static inline const struct of_device_id *of_match_device( { return NULL; } + +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} #endif /* CONFIG_OF */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From 37a7bd6255b415afe197489b5cd1f9568a7ae058 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 20 Aug 2013 12:13:01 -0500 Subject: drivers: base: reduce add_memory_section() for boot-time only Now that add_memory_section() is only called from boot time, reduce the logic and remove the enum. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 85c31a8e2904..4c89fb0c8f4c 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -125,7 +125,6 @@ extern struct memory_block *find_memory_block_hinted(struct mem_section *, struct memory_block *); extern struct memory_block *find_memory_block(struct mem_section *); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Tue, 20 Aug 2013 16:05:05 -0500 Subject: drivers: base: use standard device online/offline for state change There are two ways to set the online/offline state for a memory block: echo 0|1 > online and echo online|online_kernel|online_movable|offline > state. The state attribute can online a memory block with extra data, the "online type", where the online attribute uses a default online type of ONLINE_KEEP, same as echo online > state. Currently there is a state_mutex that provides consistency between the memory block state and the underlying memory. The problem is that this code does a lot of things that the common device layer can do for us, such as the serialization of the online/offline handlers using the device lock, setting the dev->offline field, and calling kobject_uevent(). This patch refactors the online/offline code to allow the common device_[online|offline] functions to be used. The result is a simpler and more common code path for the two state setting mechanisms. It also removes the state_mutex from the struct memory_block as the memory block device lock provides the state consistency. No functional change is intended by this patch. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- include/linux/memory.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 4c89fb0c8f4c..9a6bbf76452d 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -25,16 +25,9 @@ struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; - unsigned long state; - int section_count; - - /* - * This serializes all state change requests. It isn't - * held during creation because the control files are - * created long after the critical areas during - * initialization. - */ - struct mutex state_mutex; + unsigned long state; /* serialized by the dev->lock */ + int section_count; /* serialized by mem_sysfs_mutex */ + int online_type; /* for passing data to online routine */ int phys_device; /* to which fru does this belong? */ void *hw; /* optional pointer to fw/hw data */ int (*phys_callback)(struct memory_block *); -- cgit v1.2.3 From 3e9b2bae8369661070622d05570cbcdfa01770e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 13:47:50 -0700 Subject: sysfs: add sysfs_create/remove_groups() These functions are being open-coded in 3 different places in the driver core, and other driver subsystems will want to start doing this as well, so move it to the sysfs core to keep it all in one place, where we know it is written properly. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 0f04958623d7..4dbb9d31daa8 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -215,10 +215,14 @@ void sysfs_delete_link(struct kobject *dir, struct kobject *targ, int __must_check sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp); +int __must_check sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp); void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp); +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group); void sysfs_remove_file_from_group(struct kobject *kobj, -- cgit v1.2.3 From 5da5c9c899dc456d6eb43aae3e8d4e853b7f5306 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 17:47:05 -0700 Subject: sysfs: fix up minor coding style issues in sysfs.h As long as we are cleaning up sysfs coding style issues, don't forget the main sysfs.h file, so fix up the space issues there as well. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 4dbb9d31daa8..a864b8d918ee 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -51,9 +51,9 @@ do { \ static struct lock_class_key __key; \ \ (attr)->key = &__key; \ -} while(0) +} while (0) #else -#define sysfs_attr_init(attr) do {} while(0) +#define sysfs_attr_init(attr) do {} while (0) #endif struct attribute_group { @@ -69,7 +69,7 @@ struct attribute_group { * for examples.. */ -#define __ATTR(_name,_mode,_show,_store) { \ +#define __ATTR(_name, _mode, _show, _store) { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ @@ -119,7 +119,7 @@ struct bin_attribute { void *private; ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); @@ -168,8 +168,8 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size) struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size) struct sysfs_ops { - ssize_t (*show)(struct kobject *, struct attribute *,char *); - ssize_t (*store)(struct kobject *,struct attribute *,const char *, size_t); + ssize_t (*show)(struct kobject *, struct attribute *, char *); + ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); const void *(*namespace)(struct kobject *, const struct attribute *); }; -- cgit v1.2.3 From f477b7fb13df2b843997559ff34e87d054ba6538 Mon Sep 17 00:00:00 2001 From: wangyuhang Date: Sun, 11 Aug 2013 18:15:17 +0800 Subject: spi: DUAL and QUAD support fix the previous patch some mistake below: 1. DT in slave node, use "spi-tx-nbits = <1/2/4>" in place of using "spi-tx-dual, spi-tx-quad" directly, same to rx. So correct the previous way to get the property in @of_register_spi_devices(). 2. Change the value of transfer bit macro(SPI_NBITS_SINGLE, SPI_NBITS_DUAL SPI_NBITS_QUAD) to 0x01, 0x02 and 0x04 to match the actual wires. 3. Add the following check (1)keep the tx_nbits and rx_nbits in spi_transfer is not beyond the single, dual and quad. (2)keep tx_nbits and rx_nbits are contained by @spi_device->mode example: if @spi_device->mode = DUAL, then tx/rx_nbits can not be set to QUAD(SPI_NBITS_QUAD) (3)if "@spi_device->mode & SPI_3WIRE", then tx/rx_nbits should be in single(SPI_NBITS_SINGLE) Signed-off-by: wangyuhang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cdf668156154..ccd7840c4507 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -74,7 +74,7 @@ struct spi_device { struct spi_master *master; u32 max_speed_hz; u8 chip_select; - u8 mode; + u16 mode; #define SPI_CPHA 0x01 /* clock phase */ #define SPI_CPOL 0x02 /* clock polarity */ #define SPI_MODE_0 (0|0) /* (original MicroWire) */ @@ -87,6 +87,10 @@ struct spi_device { #define SPI_LOOP 0x20 /* loopback mode */ #define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ #define SPI_READY 0x80 /* slave pulls low to pause */ +#define SPI_TX_DUAL 0x100 /* transmit with 2 wires */ +#define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ +#define SPI_RX_DUAL 0x400 /* receive with 2 wires */ +#define SPI_RX_QUAD 0x800 /* receive with 4 wires */ u8 bits_per_word; int irq; void *controller_state; @@ -454,6 +458,10 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * @rx_buf: data to be read (dma-safe memory), or NULL * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_nbits: number of bits used for writting. If 0 the default + * (SPI_NBITS_SINGLE) is used. + * @rx_nbits: number of bits used for reading. If 0 the default + * (SPI_NBITS_SINGLE) is used. * @len: size of rx and tx buffers (in bytes) * @speed_hz: Select a speed other than the device default for this * transfer. If 0 the default (from @spi_device) is used. @@ -508,6 +516,11 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * by the results of previous messages and where the whole transaction * ends when the chipselect goes intactive. * + * When SPI can transfer in 1x,2x or 4x. It can get this tranfer information + * from device through @tx_nbits and @rx_nbits. In Bi-direction, these + * two should both be set. User can set transfer mode with SPI_NBITS_SINGLE(1x) + * SPI_NBITS_DUAL(2x) and SPI_NBITS_QUAD(4x) to support these three transfer. + * * The code that submits an spi_message (and its spi_transfers) * to the lower layers is responsible for managing its memory. * Zero-initialize every field you don't set up explicitly, to @@ -528,6 +541,11 @@ struct spi_transfer { dma_addr_t rx_dma; unsigned cs_change:1; + u8 tx_nbits; + u8 rx_nbits; +#define SPI_NBITS_SINGLE 0x01 /* 1bit transfer */ +#define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ +#define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; u16 delay_usecs; u32 speed_hz; @@ -875,7 +893,7 @@ struct spi_board_info { /* mode becomes spi_device.mode, and is essential for chips * where the default of SPI_CS_HIGH = 0 is wrong. */ - u8 mode; + u16 mode; /* ... may need additional spi_device chip config data here. * avoid stuff protocol drivers can set; but include stuff -- cgit v1.2.3 From dc76a1adfa12ad11957bdeec565dbccf37205d04 Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Tue, 13 Aug 2013 09:59:00 -0500 Subject: phy: micrel: Add definitions for common Micrel PHY registers Add defines for common Micrel PHY setups so that other platforms can use them. Update imx61 and sama5 hardware to use the micrel_phy.h PHY defines. Also add support for the KSZ9021RLRN PHY. Signed-off-by: Dinh Nguyen Acked-by: Nicolas Ferre Acked-by: David S. Miller CC: Andrew Victor CC: Jean-Christophe Plagniol-Villard Cc: netdev@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Shawn Guo --- include/linux/micrel_phy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 8752dbbc6135..ad05ce60c1c9 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -17,6 +17,7 @@ #define PHY_ID_KSZ8873MLL 0x000e7237 #define PHY_ID_KSZ9021 0x00221610 +#define PHY_ID_KSZ9021RLRN 0x00221611 #define PHY_ID_KS8737 0x00221720 #define PHY_ID_KSZ8021 0x00221555 #define PHY_ID_KSZ8031 0x00221556 @@ -35,4 +36,9 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 +#define MICREL_KSZ9021_EXTREG_CTRL 0xB +#define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC +#define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104 +#define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105 + #endif /* _MICREL_PHY_H */ -- cgit v1.2.3 From a58674ff8383f5b8f6a77f03c48f6a47840b9325 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 22 Aug 2013 11:24:44 +0800 Subject: PCI: Simplify pcie_bus_configure_settings() interface Based on a patch by Jon Mason (see URL below). All users of pcie_bus_configure_settings() pass arguments of the form "bus, bus->self->pcie_mpss". The "mpss" argument is redundant since we can easily look it up internally. In addition, all callers check "bus->self" for NULL, which we can also do internally. This patch simplifies the interface and the callers. No functional change. Reference: http://lkml.kernel.org/r/1317048850-30728-2-git-send-email-mason@myri.com Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..57062b7a20ba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -675,7 +675,7 @@ struct pci_driver { /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI -void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); +void pcie_bus_configure_settings(struct pci_bus *bus); enum pcie_bus_config_types { PCIE_BUS_TUNE_OFF, -- cgit v1.2.3 From 3e1026b3fa2f61d33ce6a9e42a22398cc4ab8e58 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 22 Aug 2013 10:25:34 -0700 Subject: sysfs.h: remove attr_name() macro Gotta love a macro that doesn't reduce the typing you have to do. Also, only the driver core, and one network driver uses this. The driver core functions will be going away soon, and I'll convert the network driver soon to not need this as well, so delete it for now before anyone else gets some bright ideas and wants to use it. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a864b8d918ee..b5a9d9b26bd4 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -108,8 +108,6 @@ static const struct attribute_group _name##_group = { \ }; \ __ATTRIBUTE_GROUPS(_name) -#define attr_name(_attr) (_attr).attr.name - struct file; struct vm_area_struct; -- cgit v1.2.3 From 699c1985587aad3432c5ae19801efb4186db8b7a Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 20 Aug 2013 16:41:02 +0200 Subject: PCI: Add pcibios_pm_ops for optional arch-specific hibernate functionality Platforms may want to provide architecture-specific functionality when a PCI device is doing a hibernate transition. Add a weak symbol pcibios_pm_ops that architectures can override to do so. [bhelgaas: fold in return value checks from v2 patch] Signed-off-by: Sebastian Ott Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..89ed12379f2f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1648,6 +1648,10 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, int pcibios_add_device(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); +#ifdef CONFIG_HIBERNATE_CALLBACKS +extern struct dev_pm_ops pcibios_pm_ops; +#endif + #ifdef CONFIG_PCI_MMCONFIG void __init pci_mmcfg_early_init(void); void __init pci_mmcfg_late_init(void); -- cgit v1.2.3 From 2771399ac9986c75437a83b1c723493cfcdfa439 Mon Sep 17 00:00:00 2001 From: Gerhard Sittig Date: Thu, 22 Aug 2013 21:55:13 +0200 Subject: fs_enet: cleanup clock API use make the Freescale ethernet driver get, prepare and enable the FEC clock during probe(); disable and unprepare the clock upon remove(), put is done by the devm approach; hold a reference to the clock over the period of use. clock lookup is non-fatal as not all platforms provide clock specs in their device tree; failure to enable specified clocks is fatal. Signed-off-by: Gerhard Sittig Signed-off-by: Anatolij Gustschin Signed-off-by: David S. Miller --- include/linux/fs_enet_pd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 343d82a54468..efb05961bdd8 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -16,6 +16,7 @@ #ifndef FS_ENET_PD_H #define FS_ENET_PD_H +#include #include #include #include @@ -143,6 +144,8 @@ struct fs_platform_info { int use_rmii; /* use RMII mode */ int has_phy; /* if the network is phy container as well...*/ + + struct clk *clk_per; /* 'per' clock for register access */ }; struct fs_mii_fec_platform_info { u32 irq[32]; -- cgit v1.2.3 From 71ea148370f8b6c745a8a42f6fd983cf5ebade18 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 10 Aug 2013 10:46:50 +0300 Subject: dmaengine: make dma_submit_error() return an error code The problem here is that the dma_xfer() functions in drivers/ata/pata_arasan_cf.c and drivers/mtd/nand/fsmc_nand.c expect dma_submit_error() to return an error code so they return 1 when they intended to return a negative. So far as I can tell, none of the ->tx_submit() functions ever do return error codes so this patch should have no effect in the current code. I also changed it from a define to an inline. Signed-off-by: Dan Carpenter Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cb286b1acdb6..b3ba7e410943 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -38,7 +38,10 @@ typedef s32 dma_cookie_t; #define DMA_MIN_COOKIE 1 #define DMA_MAX_COOKIE INT_MAX -#define dma_submit_error(cookie) ((cookie) < 0 ? 1 : 0) +static inline int dma_submit_error(dma_cookie_t cookie) +{ + return cookie < 0 ? cookie : 0; +} /** * enum dma_status - DMA transaction status -- cgit v1.2.3 From 3287c24088abded9f111ca797fdd36f86912d199 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 21 Aug 2013 16:53:37 +0530 Subject: pinctrl: utils : add support to pass config type in generic util APIs Add support to pass the config type like GROUP or PIN when using the utils or generic pin configuration APIs. This will make the APIs more generic. Added additional inline APIs such that it can be use directly as callback for the pinctrl_ops. Changes from V1: - Remove separate implementation for pins and group for pinctrl_utils_dt_free_map and improve this function to support both i.e. PINS and GROUPs. Signed-off-by: Laxman Dewangan Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 83f5179ea0c5..fb90ef5eb038 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -140,15 +140,33 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param #ifdef CONFIG_OF #include +#include struct pinctrl_dev; struct pinctrl_map; int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, struct pinctrl_map **map, - unsigned *reserved_maps, unsigned *num_maps); + unsigned *reserved_maps, unsigned *num_maps, + enum pinctrl_map_type type); int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev, struct device_node *np_config, struct pinctrl_map **map, - unsigned *num_maps); + unsigned *num_maps, enum pinctrl_map_type type); + +static inline int pinconf_generic_dt_node_to_map_group( + struct pinctrl_dev *pctldev, struct device_node *np_config, + struct pinctrl_map **map, unsigned *num_maps) +{ + return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, + PIN_MAP_TYPE_CONFIGS_GROUP); +} + +static inline int pinconf_generic_dt_node_to_map_pin( + struct pinctrl_dev *pctldev, struct device_node *np_config, + struct pinctrl_map **map, unsigned *num_maps) +{ + return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, + PIN_MAP_TYPE_CONFIGS_PIN); +} #endif -- cgit v1.2.3 From 687b81d083c082bc1e853032e3a2a54f8c251d27 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 11 Jul 2013 12:56:15 +0100 Subject: i2c: move OF helpers into the core I2C of helpers used to live in of_i2c.c but experience (from SPI) shows that it is much cleaner to have this in the core. This also removes a circular dependency between the helpers and the core, and so we can finally register child nodes in the core instead of doing this manually in each driver. So, fix the drivers and documentation, too. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 20 ++++++++++++++++++++ include/linux/of_i2c.h | 46 ---------------------------------------------- 2 files changed, 20 insertions(+), 46 deletions(-) delete mode 100644 include/linux/of_i2c.h (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b3c4b8dac1ce..ed53696e31a6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -544,6 +544,26 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) #endif /* I2C */ +#if IS_ENABLED(CONFIG_OF) +/* must call put_device() when done with returned i2c_client device */ +extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); + +/* must call put_device() when done with returned i2c_adapter device */ +extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); + +#else + +static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) +{ + return NULL; +} + +static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) +{ + return NULL; +} +#endif /* CONFIG_OF */ + #if IS_ENABLED(CONFIG_ACPI_I2C) extern void acpi_i2c_register_devices(struct i2c_adapter *adap); #else diff --git a/include/linux/of_i2c.h b/include/linux/of_i2c.h deleted file mode 100644 index cfb545cd86b5..000000000000 --- a/include/linux/of_i2c.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * Generic I2C API implementation for PowerPC. - * - * Copyright (c) 2008 Jochen Friedrich - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __LINUX_OF_I2C_H -#define __LINUX_OF_I2C_H - -#if defined(CONFIG_OF_I2C) || defined(CONFIG_OF_I2C_MODULE) -#include - -extern void of_i2c_register_devices(struct i2c_adapter *adap); - -/* must call put_device() when done with returned i2c_client device */ -extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); - -/* must call put_device() when done with returned i2c_adapter device */ -extern struct i2c_adapter *of_find_i2c_adapter_by_node( - struct device_node *node); - -#else -static inline void of_i2c_register_devices(struct i2c_adapter *adap) -{ - return; -} - -static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) -{ - return NULL; -} - -/* must call put_device() when done with returned i2c_adapter device */ -static inline struct i2c_adapter *of_find_i2c_adapter_by_node( - struct device_node *node) -{ - return NULL; -} -#endif /* CONFIG_OF_I2C */ - -#endif /* __LINUX_OF_I2C_H */ -- cgit v1.2.3 From 55e71edb81b2b45273e7b284cce13ff24bde846f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 21 Aug 2013 17:28:23 +0300 Subject: i2c: move ACPI helpers into the core This follows what has already been done for the DeviceTree helpers. Move the ACPI helpers from drivers/acpi/acpi_i2c.c to the I2C core and update documentation accordingly. This also solves a problem reported by Jerry Snitselaar that we can't build the ACPI I2C helpers as a module. Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index ed53696e31a6..2ab11dc38077 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -564,10 +564,4 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node } #endif /* CONFIG_OF */ -#if IS_ENABLED(CONFIG_ACPI_I2C) -extern void acpi_i2c_register_devices(struct i2c_adapter *adap); -#else -static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) {} -#endif - #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From eb18cba78c2b9250663021e17e1e9cc34630e92a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 20 Aug 2013 15:05:17 -0400 Subject: math64: New separate div64_u64_rem helper Commit f792685006274a850e6cc0ea9ade275ccdfc90bc ("math64: New div64_u64_rem helper") implemented div64_u64 in terms of div64_u64_rem. But div64_u64_rem was removed because it slowed down div64_u64 (and there were no other users of div64_u64_rem). Device Mapper's I/O statistics support has a need for div64_u64_rem; reintroduce this helper as a separate method that doesn't slow down div64_u64, especially on 32-bit systems. Signed-off-by: Mike Snitzer Cc: Stanislaw Gruszka Cc: Ingo Molnar Cc: Frederic Weisbecker Cc: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/math64.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 2913b86eb12a..69ed5f5e9f6e 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -30,6 +30,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) return dividend / divisor; } +/** + * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder + */ +static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) +{ + *remainder = dividend % divisor; + return dividend / divisor; +} + /** * div64_u64 - unsigned 64bit divide with 64bit divisor */ @@ -63,6 +72,10 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif +#ifndef div64_u64_rem +extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); +#endif + #ifndef div64_u64 extern u64 div64_u64(u64 dividend, u64 divisor); #endif -- cgit v1.2.3 From f1bc1e4c44b1b78fe34431936c60759b5aad5e3f Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Fri, 23 Aug 2013 10:17:54 +0800 Subject: ata: acpi: rework the ata acpi bind support Binding ACPI handle to SCSI device has several drawbacks, namely: 1 During ATA device initialization time, ACPI handle will be needed while SCSI devices are not created yet. So each time ACPI handle is needed, instead of retrieving the handle by ACPI_HANDLE macro, a namespace scan is performed to find the handle for the corresponding ATA device. This is inefficient, and also expose a restriction on calling path not holding any lock. 2 The binding to SCSI device tree makes code complex, while at the same time doesn't bring us any benefit. All ACPI handlings are still done in ATA module, not in SCSI. Rework the ATA ACPI binding code to bind ACPI handle to ATA transport devices(ATA port and ATA device). The binding needs to be done only once, since the ATA transport devices do not go away with hotplug. And due to this, the flush_work call in hotplug handler for ATA bay is no longer needed. Tested on an Intel test platform for binding and runtime power off for ODD(ZPODD) and hard disk; on an ASUS S400C for binding and normal boot and S3, where its SATA port node has _SDD and _GTF control methods when configured as an AHCI controller and its PATA device node has _GTF control method when configured as an IDE controller. SATA PMP binding and ATA hotplug is not tested. Signed-off-by: Aaron Lu Tested-by: Dirk Griesbach Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 283d66bc603c..3198617905e1 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1244,8 +1244,6 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, const struct ata_acpi_gtm *gtm); -acpi_handle ata_ap_acpi_handle(struct ata_port *ap); -acpi_handle ata_dev_acpi_handle(struct ata_device *dev); int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm); #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) -- cgit v1.2.3 From abec1a806e0c3cf168999667d5fb6218398ef12a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Aug 2013 19:01:58 +0000 Subject: percpu: Make __verify_pcu_ptr handle per cpu pointers to arrays __verify_pcpu_ptr() will cause a compilation failure if the type of the pointer is a pointer to a fixed array of objects. Adding zero to the pointer converts the type of pointer to that pointing to a single object of the array. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu-defs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 27ef6b190ea6..57e890abe1f0 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -22,9 +22,12 @@ * Macro which verifies @ptr is a percpu pointer without evaluating * @ptr. This is to be used in percpu accessors to verify that the * input parameter is a percpu pointer. + * + * + 0 is required in order to convert the pointer type from a + * potential array type to a pointer to a single item of the array. */ #define __verify_pcpu_ptr(ptr) do { \ - const void __percpu *__vpp_verify = (typeof(ptr))NULL; \ + const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ (void)__vpp_verify; \ } while (0) -- cgit v1.2.3 From a65fcce75a75c0d41b938f86d09d42b6f1733309 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:01 -0700 Subject: sysfs: create __ATTR_WO() This creates the macro __ATTR_WO() for write-only attributes, instead of having to "open define" them. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b5a9d9b26bd4..69c1ff003628 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -80,6 +80,11 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_WO(_name) { \ + .attr = { .name = __stringify(_name), .mode = S_IWUSR }, \ + .store = _name##_store, \ +} + #define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO), \ _name##_show, _name##_store) -- cgit v1.2.3 From 1130c55c757660ac83bd2de220f08580c56b6855 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:56 -0700 Subject: driver core: create write-only attribute macros for devices and drivers This creates the macros DRIVER_ATTR_WO() and DEVICE_ATTR_WO() for write-only attributes for drivers and devices. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 26e23b22ed0a..0ed94b5f67fc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -277,6 +277,8 @@ struct driver_attribute { struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RO(_name) +#define DRIVER_ATTR_WO(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) extern int __must_check driver_create_file(struct device_driver *driver, const struct driver_attribute *attr); @@ -534,6 +536,8 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct device_attribute dev_attr_##_name = __ATTR_RW(_name) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_WO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } -- cgit v1.2.3 From 0f102b6ccec15c057d4d82f9731e6b780c9f8132 Mon Sep 17 00:00:00 2001 From: Haojian Zhuang Date: Mon, 3 Jun 2013 10:02:59 +0800 Subject: ARM: mmp: avoid to include head file in mach-mmp pxa910_set_wake() & mmp2_set_wake() are both declared in head files of arch/arm/mach-mmp/include/mach directory. If we include these head files in irq-mmp driver, it blocks the multiplatform build. So adjust the code. Signed-off-by: Haojian Zhuang --- include/linux/irqchip/mmp.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/irqchip/mmp.h (limited to 'include/linux') diff --git a/include/linux/irqchip/mmp.h b/include/linux/irqchip/mmp.h new file mode 100644 index 000000000000..c78a8921185d --- /dev/null +++ b/include/linux/irqchip/mmp.h @@ -0,0 +1,6 @@ +#ifndef __IRQCHIP_MMP_H +#define __IRQCHIP_MMP_H + +extern struct irq_chip icu_irq_chip; + +#endif /* __IRQCHIP_MMP_H */ -- cgit v1.2.3 From 214fc309d1387e822d606a33a10e31cacfe83520 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:31 +0200 Subject: mmc: slot-gpio: Add debouncing capability to mmc_gpio_request_cd() Add a debounce parameter to the mmc_gpio_request_cd() function that enables GPIO debouncing when set to a non-zero value. This can be used by MMC host drivers to enable debouncing on the card detect signal. Signed-off-by: Laurent Pinchart Reviewed-by: H Hartley Sweeten Signed-off-by: Chris Ball --- include/linux/mmc/slot-gpio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 7d88d27bfafa..b0c73e4cacea 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -18,7 +18,8 @@ int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio); void mmc_gpio_free_ro(struct mmc_host *host); int mmc_gpio_get_cd(struct mmc_host *host); -int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio); +int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio, + unsigned int debounce); void mmc_gpio_free_cd(struct mmc_host *host); #endif -- cgit v1.2.3 From bf287a90ceedf86e3313ba0dcff606ac5399b39a Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:32 +0200 Subject: mmc: mmc_spi: Support CD/RO GPIOs Add support for passing CD/RO GPIO numbers directly to the mmc_spi driver instead of relying solely on board code callbacks to retrieve the CD/RO signals values. The driver will enable debouncing on the card detect GPIO if the cd_debounce field is set to a non-zero value. Signed-off-by: Laurent Pinchart Reviewed-by: H Hartley Sweeten Signed-off-by: Chris Ball --- include/linux/spi/mmc_spi.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/mmc_spi.h b/include/linux/spi/mmc_spi.h index 32be8dbdf191..87cdb35bedda 100644 --- a/include/linux/spi/mmc_spi.h +++ b/include/linux/spi/mmc_spi.h @@ -7,6 +7,11 @@ struct device; struct mmc_host; +#define MMC_SPI_USE_CD_GPIO (1 << 0) +#define MMC_SPI_USE_RO_GPIO (1 << 1) +#define MMC_SPI_CD_GPIO_ACTIVE_LOW (1 << 2) +#define MMC_SPI_RO_GPIO_ACTIVE_LOW (1 << 3) + /* Put this in platform_data of a device being used to manage an MMC/SD * card slot. (Modeled after PXA mmc glue; see that for usage examples.) * @@ -30,8 +35,19 @@ struct mmc_spi_platform_data { */ int (*get_cd)(struct device *); + /* + * Card Detect and Read Only GPIOs. To enable debouncing on the card + * detect GPIO, set the cd_debounce to the debounce time in + * microseconds. + */ + unsigned int flags; + unsigned int cd_gpio; + unsigned int cd_debounce; + unsigned int ro_gpio; + /* Capabilities to pass into mmc core (e.g. MMC_CAP_NEEDS_POLL). */ unsigned long caps; + unsigned long caps2; /* how long to debounce card detect, in msecs */ u16 detect_delay; -- cgit v1.2.3 From 62b6af5c7ee28a3faf9638e509fd2da85a97229d Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:38 +0200 Subject: mmc: mmc_spi: Remove platform data .get_cd() and .get_ro() callbacks All platforms now pass the CD and RO GPIOs to the MMC SPI driver, those callbacks are not used anymore. Remove them. Signed-off-by: Laurent Pinchart Reviewed-by: H Hartley Sweeten Signed-off-by: Chris Ball --- include/linux/spi/mmc_spi.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/mmc_spi.h b/include/linux/spi/mmc_spi.h index 87cdb35bedda..274bc0fa00af 100644 --- a/include/linux/spi/mmc_spi.h +++ b/include/linux/spi/mmc_spi.h @@ -26,15 +26,6 @@ struct mmc_spi_platform_data { void *); void (*exit)(struct device *, void *); - /* sense switch on sd cards */ - int (*get_ro)(struct device *); - - /* - * If board does not use CD interrupts, driver can optimize polling - * using this function. - */ - int (*get_cd)(struct device *); - /* * Card Detect and Read Only GPIOs. To enable debouncing on the card * detect GPIO, set the cd_debounce to the debounce time in -- cgit v1.2.3 From dcbfaf36c1933d88565501ff13feb0f4b2d38735 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:39 +0200 Subject: mmc: sh_mmcif: Remove .down_pwr() callback from platform data The callback isn't used by the driver and isn't initialized by board code. Remove it. Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mmcif.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index e7d5dd67bb74..39011eb42930 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -34,7 +34,6 @@ struct sh_mmcif_plat_data { void (*set_pwr)(struct platform_device *pdev, int state); - void (*down_pwr)(struct platform_device *pdev); int (*get_cd)(struct platform_device *pdef); unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ unsigned int slave_id_rx; -- cgit v1.2.3 From 83a0c7797e96e103bb3b6fcf8afb7b65dc7fc68e Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:40 +0200 Subject: mmc: sh_mmcif: Remove .set_pwr() callback from platform data The .set_pwr() callback isn't used anymore as all platforms register GPIO-controlled regulators. Remove it. Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mmcif.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 39011eb42930..767fac5a7d93 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -33,7 +33,6 @@ */ struct sh_mmcif_plat_data { - void (*set_pwr)(struct platform_device *pdev, int state); int (*get_cd)(struct platform_device *pdef); unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ unsigned int slave_id_rx; -- cgit v1.2.3 From 57fcb523e5fce1c24e9c28b64f6e6dc3edf55073 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:41 +0200 Subject: mmc: sh_mobile_sdhi: Remove .get_cd() callback from platform data All platforms pass the CD GPIO number to the driver in the .cd_gpio field. The .get_cd() callback isn't used anymore, remove it. Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mobile_sdhi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index b76bcf0621f6..f31c69262232 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -26,7 +26,6 @@ struct sh_mobile_sdhi_info { u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; void (*set_pwr)(struct platform_device *pdev, int state); - int (*get_cd)(struct platform_device *pdev); /* callbacks for board specific setup code */ int (*init)(struct platform_device *pdev, -- cgit v1.2.3 From 1036563e1417c050993bbd48f20a84ff7c7cef99 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:42 +0200 Subject: mmc: sh_mobile_sdhi: Remove .set_pwr() callback from platform data The .set_pwr() callback isn't used anymore as all platforms register GPIO-controlled regulators. Remove it. Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mobile_sdhi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index f31c69262232..68927ae50845 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -25,7 +25,6 @@ struct sh_mobile_sdhi_info { unsigned long tmio_caps2; u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; - void (*set_pwr)(struct platform_device *pdev, int state); /* callbacks for board specific setup code */ int (*init)(struct platform_device *pdev, -- cgit v1.2.3 From 2b63b341d42cd64ff40062447320d46cf3e7f0bb Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:43 +0200 Subject: mmc: tmio-mmc: Remove .get_cd() callback from platform data All platforms pass the CD GPIO number to the driver in the .cd_gpio field. The .get_cd() callback isn't used anymore, remove it Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index ce3511326f80..b22883d60500 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -108,7 +108,6 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - int (*get_cd)(struct platform_device *host); int (*write16_hook)(struct tmio_mmc_host *host, int addr); /* clock management callbacks */ int (*clk_enable)(struct platform_device *pdev, unsigned int *f); -- cgit v1.2.3 From 3af9d15c719017feb63fa99f89ac6009a5a3d467 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 8 Aug 2013 12:38:44 +0200 Subject: mmc: tmio-mmc: Remove .set_pwr() callback from platform data The .set_pwr() callback isn't used anymore as all platforms register GPIO-controlled regulators. Remove it. Signed-off-by: Laurent Pinchart Acked-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index b22883d60500..baa23464a1e6 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -106,7 +106,6 @@ struct tmio_mmc_data { struct tmio_mmc_dma *dma; struct device *dev; unsigned int cd_gpio; - void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); int (*write16_hook)(struct tmio_mmc_host *host, int addr); /* clock management callbacks */ -- cgit v1.2.3 From d00cadacbe47d4883b0d5e38aa73a3f4e171d37e Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 2 Aug 2013 14:48:02 +0200 Subject: mmc: sh_mmcif: move header include from header into .c sh_dma.h isn't needed in sh_mmcif.h, move it into sh_mmcif.c. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mmcif.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 767fac5a7d93..c4880ffb6cce 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -16,7 +16,6 @@ #include #include -#include /* * MMCIF : CE_CLK_CTRL [19:16] -- cgit v1.2.3 From 967bcb77177cda1a426fdb2350e6ec61bcf5b5eb Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 10 Jul 2013 21:21:12 +0200 Subject: mmc: sh_mmcif: revision-specific Command Completion Signal handling Some earlier MMCIF IP revisions contained Command Completion Signal support, which has been dropped again in modern versions. Sopport for this feature is added in a way to preserve the current behaviour by default, i.e. when it is not enabled in platform data. Patch is based on work by Nobuyuki HIRAI. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mmcif.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index c4880ffb6cce..197ed91f6a0c 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -36,6 +36,7 @@ struct sh_mmcif_plat_data { unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ unsigned int slave_id_rx; bool use_cd_gpio : 1; + bool ccs_unsupported : 1; unsigned int cd_gpio; u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ unsigned long caps; -- cgit v1.2.3 From 6d6fd3674259d16b735c961743ff28870c46cedc Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 10 Jul 2013 21:21:13 +0200 Subject: mmc: sh_mmcif: revision-specific CLK_CTRL2 handling Some newer MMCIF IP revisions contain a CE_CLK_CTRL2 register, that has to be set for proper operation. Support for this feature is added in a way to preserve the current behaviour by default, i.e. when it is not enabled in platform data. Patch is based on work by Nobuyuki HIRAI. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mmcif.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 197ed91f6a0c..ccd8fb2cad52 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -37,6 +37,7 @@ struct sh_mmcif_plat_data { unsigned int slave_id_rx; bool use_cd_gpio : 1; bool ccs_unsupported : 1; + bool clk_ctrl2_present : 1; unsigned int cd_gpio; u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ unsigned long caps; @@ -60,6 +61,7 @@ struct sh_mmcif_plat_data { #define MMCIF_CE_INT_MASK 0x00000044 #define MMCIF_CE_HOST_STS1 0x00000048 #define MMCIF_CE_HOST_STS2 0x0000004C +#define MMCIF_CE_CLK_CTRL2 0x00000070 #define MMCIF_CE_VERSION 0x0000007C /* CE_BUF_ACC */ -- cgit v1.2.3 From 8be5ad9acb7c11b9d717bcdbe3d6de0dab081a39 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:48 -0700 Subject: libata: Populate host-to-device FIS "auxiliary" field SATA 3.1 added an "auxiliary" field to the host-to-device FIS. Populate the host-to-device FIS with the new field via the taskfile struct. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 3198617905e1..9b6ba196179f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -555,6 +555,10 @@ struct ata_taskfile { u8 device; u8 command; /* IO operation */ + + u32 auxiliary; /* auxiliary field */ + /* from SATA 3.1 and */ + /* ATA-8 ACS-3 */ }; #ifdef CONFIG_ATA_SFF -- cgit v1.2.3 From 40fb59e75ad197a1c4ca2fbccef85432d8d103f8 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:49 -0700 Subject: libata: Add H2D FIS "auxiliary" port flag Add a new port flag, ATA_FLAG_FPDMA_AUX, used to indicate support for transmission of the H2D FIS 'auxiliary' field. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b6ba196179f..578f98c3ff57 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -223,6 +223,7 @@ enum { ATA_FLAG_ACPI_SATA = (1 << 17), /* need native SATA ACPI layout */ ATA_FLAG_AN = (1 << 18), /* controller supports AN */ ATA_FLAG_PMP = (1 << 19), /* controller supports PMP */ + ATA_FLAG_FPDMA_AUX = (1 << 20), /* controller supports H2DFIS aux field */ ATA_FLAG_EM = (1 << 21), /* driver supports enclosure * management */ ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity -- cgit v1.2.3 From ed36911c747c18525691c0aa0fbe6b918c8eac19 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:50 -0700 Subject: libata: Add support for SEND/RECEIVE FPDMA QUEUED Add support for the following ATA opcodes, which are present in SATA 3.1 and T13 ATA ACS-3: SEND FPDMA QUEUED RECEIVE FPDMA QUEUED Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/ata.h | 21 +++++++++++++++++++++ include/linux/libata.h | 4 ++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index f63fb1afc5cc..bf4c69ca76df 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -239,6 +239,8 @@ enum { ATA_CMD_WRITE_QUEUED_FUA_EXT = 0x3E, ATA_CMD_FPDMA_READ = 0x60, ATA_CMD_FPDMA_WRITE = 0x61, + ATA_CMD_FPDMA_SEND = 0x64, + ATA_CMD_FPDMA_RECV = 0x65, ATA_CMD_PIO_READ = 0x20, ATA_CMD_PIO_READ_EXT = 0x24, ATA_CMD_PIO_WRITE = 0x30, @@ -293,8 +295,13 @@ enum { /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, + /* Subcmds for ATA_CMD_FPDMA_SEND */ + ATA_SUBCMD_FPDMA_SEND_DSM = 0x00, + ATA_SUBCMD_FPDMA_SEND_WR_LOG_DMA_EXT = 0x02, + /* READ_LOG_EXT pages */ ATA_LOG_SATA_NCQ = 0x10, + ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_SATA_ID_DEV_DATA = 0x30, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_DEVSLP_OFFSET = 0x30, @@ -305,6 +312,15 @@ enum { ATA_LOG_DEVSLP_VALID = 0x07, ATA_LOG_DEVSLP_VALID_MASK = 0x80, + /* NCQ send and receive log */ + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_OFFSET = 0x00, + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_DSM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET = 0x04, + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_RD_LOG_OFFSET = 0x08, + ATA_LOG_NCQ_SEND_RECV_WR_LOG_OFFSET = 0x0C, + ATA_LOG_NCQ_SEND_RECV_SIZE = 0x10, + /* READ/WRITE LONG (obsolete) */ ATA_CMD_READ_LONG = 0x22, ATA_CMD_READ_LONG_ONCE = 0x23, @@ -772,6 +788,11 @@ static inline int ata_id_rotation_rate(const u16 *id) return val; } +static inline bool ata_id_has_ncq_send_and_recv(const u16 *id) +{ + return id[ATA_ID_SATA_CAPABILITY_2] & BIT(6); +} + static inline bool ata_id_has_trim(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/libata.h b/include/linux/libata.h index 578f98c3ff57..a988c2d7d0e8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -172,6 +172,7 @@ enum { ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ + ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -704,6 +705,9 @@ struct ata_device { /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; + /* NCQ send and receive log subcommand support */ + u8 ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_SIZE]; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ -- cgit v1.2.3 From 87fb6c31b9ef9ccab9a822b01fc3911f026a29bb Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:51 -0700 Subject: libata: Add support for queued DSM TRIM Some new SSDs support the queued version of the DSM TRIM command. Let the driver use the new command if supported. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a988c2d7d0e8..0e23c26485f4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1606,6 +1606,13 @@ static inline int ata_ncq_enabled(struct ata_device *dev) ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ; } +static inline bool ata_fpdma_dsm_supported(struct ata_device *dev) +{ + return (dev->flags & ATA_DFLAG_NCQ_SEND_RECV) && + (dev->ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] & + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM); +} + static inline void ata_qc_set_polling(struct ata_queued_cmd *qc) { qc->tf.ctl |= ATA_NIEN; -- cgit v1.2.3 From 444c580f7e9ad29927a5d5269d576bd7cdccebb8 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 8 Aug 2013 15:16:22 +0900 Subject: f2fs: add flags for inline xattrs This patch adds basic inode flags for inline xattrs, F2FS_INLINE_XATTR, and add a mount option, inline_xattr, which is enabled when xattr is set. If the mount option is enabled, all the files are marked with the inline_xattrs flag. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 383d5e39b280..10ab11f8f99d 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -144,10 +144,12 @@ struct f2fs_extent { #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ +#define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */ + struct f2fs_inode { __le16 i_mode; /* file mode */ __u8 i_advise; /* file hints */ - __u8 i_reserved; /* reserved */ + __u8 i_inline; /* file inline flags */ __le32 i_uid; /* user ID */ __le32 i_gid; /* group ID */ __le32 i_links; /* links count */ -- cgit v1.2.3 From de93653fe31fc9439971296842dcd0280f8ab5f4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 12 Aug 2013 21:08:03 +0900 Subject: f2fs: reserve the xattr space dynamically This patch enables the number of direct pointers inside on-disk inode block to be changed dynamically according to the size of inline xattr space. The number of direct pointers, ADDRS_PER_INODE, can be changed only if the file has inline xattr flag. The number of direct pointers that will be used by inline xattrs is defined as F2FS_INLINE_XATTR_ADDRS. Current patch assigns F2FS_INLINE_XATTR_ADDRS to 0 temporarily. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 10ab11f8f99d..93e7020fb7a8 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -140,9 +140,17 @@ struct f2fs_extent { } __packed; #define F2FS_NAME_LEN 255 -#define ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ -#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ -#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ +#define F2FS_INLINE_XATTR_ADDRS 0 /* 0 bytes for inline xattrs */ +#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ +#define ADDRS_PER_INODE(fi) addrs_per_inode(fi) +#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ +#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ + +#define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) +#define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) +#define NODE_IND1_BLOCK (DEF_ADDRS_PER_INODE + 3) +#define NODE_IND2_BLOCK (DEF_ADDRS_PER_INODE + 4) +#define NODE_DIND_BLOCK (DEF_ADDRS_PER_INODE + 5) #define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */ @@ -172,7 +180,7 @@ struct f2fs_inode { struct f2fs_extent i_ext; /* caching a largest extent */ - __le32 i_addr[ADDRS_PER_INODE]; /* Pointers to data blocks */ + __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ __le32 i_nid[5]; /* direct(2), indirect(2), double_indirect(1) node id */ -- cgit v1.2.3 From 65985d935ddd5657c66a8bb3ae9752ed842549b8 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 14 Aug 2013 21:57:27 +0900 Subject: f2fs: support the inline xattrs 0. modified inode structure -------------------------------------- metadata (e.g., i_mtime, i_ctime, etc) -------------------------------------- direct pointers [0 ~ 873] inline xattrs (200 bytes by default) indirect pointers [0 ~ 4] -------------------------------------- node footer -------------------------------------- 1. setxattr flow - read_all_xattrs copies all the xattrs from inline and xattr node block. - handle xattr entries - write_all_xattrs copies modified xattrs into inline and xattr node block. 2. getxattr flow - read_all_xattrs copies all the xattrs from inline and xattr node block. - check target entries 3. Usage # mount -t f2fs -o inline_xattr $DEV $MNT Once mounted with the inline_xattr option, f2fs marks all the newly created files to reserve an amount of inline xattr space explicitly inside the inode block. Without the mount option, f2fs will not touch any existing files and newly created files as well. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 93e7020fb7a8..bb942f6d5702 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -140,7 +140,7 @@ struct f2fs_extent { } __packed; #define F2FS_NAME_LEN 255 -#define F2FS_INLINE_XATTR_ADDRS 0 /* 0 bytes for inline xattrs */ +#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define ADDRS_PER_INODE(fi) addrs_per_inode(fi) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ -- cgit v1.2.3 From 15261f6d8d032b30f6eb7dbf1dbb9e4095df84c0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 14 Aug 2013 11:07:08 +0300 Subject: HID: hid-sensor-hub: fix style of comments This patch fixes the style of the comments to be like following /* The commentary */ There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: Jiri Kosina --- include/linux/hid-sensor-hub.h | 2 +- include/linux/hid-sensor-ids.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index ecefb7311dd6..32ba45158d39 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -172,7 +172,7 @@ struct hid_sensor_common { struct hid_sensor_hub_attribute_info sensitivity; }; -/*Convert from hid unit expo to regular exponent*/ +/* Convert from hid unit expo to regular exponent */ static inline int hid_sensor_convert_exponent(int unit_expo) { if (unit_expo < 0x08) diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 6f24446e7669..4f945d3ed49f 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -37,7 +37,7 @@ #define HID_USAGE_SENSOR_ANGL_VELOCITY_Y_AXIS 0x200458 #define HID_USAGE_SENSOR_ANGL_VELOCITY_Z_AXIS 0x200459 -/*ORIENTATION: Compass 3D: (200083) */ +/* ORIENTATION: Compass 3D: (200083) */ #define HID_USAGE_SENSOR_COMPASS_3D 0x200083 #define HID_USAGE_SENSOR_ORIENT_MAGN_HEADING 0x200471 #define HID_USAGE_SENSOR_ORIENT_MAGN_HEADING_X 0x200472 -- cgit v1.2.3 From 6e9e318b304fd7373a0754805a76a02ddbc69a41 Mon Sep 17 00:00:00 2001 From: Haijun Zhang Date: Mon, 26 Aug 2013 09:19:22 +0800 Subject: mmc: core: parse voltage from device-tree Add function to support getting voltage from device-tree. If voltage-range is specified in device-tree node, this function will parse it and return the available voltage mask. Signed-off-by: Haijun Zhang Acked-by: Anton Vorontsov Signed-off-by: Chris Ball --- include/linux/mmc/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 443243b241d5..da51bec578c3 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -208,6 +208,8 @@ static inline void mmc_claim_host(struct mmc_host *host) __mmc_claim_host(host, NULL); } +struct device_node; extern u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max); +extern int mmc_of_parse_voltage(struct device_node *np, u32 *mask); #endif /* LINUX_MMC_CORE_H */ -- cgit v1.2.3 From c0b887b66c95fe5abaac071b8332b8c21113d84b Mon Sep 17 00:00:00 2001 From: Haijun Zhang Date: Mon, 26 Aug 2013 09:19:23 +0800 Subject: mmc: sdhci: get voltage from sdhc host We use host->ocr_mask to hold the voltage get from device-tree node, In case host->ocr_mask was available, we use host->ocr_mask as the final available voltage can be used by MMC/SD/SDIO card. Signed-off-by: Haijun Zhang Reviewed-by: Anton Vorontsov Signed-off-by: Chris Ball --- include/linux/mmc/sdhci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index e3c6a74d980a..3e781b8c0be7 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -171,6 +171,7 @@ struct sdhci_host { unsigned int ocr_avail_sdio; /* OCR bit masks */ unsigned int ocr_avail_sd; unsigned int ocr_avail_mmc; + u32 ocr_mask; /* available voltages */ wait_queue_head_t buf_ready_int; /* Waitqueue for Buffer Read Ready interrupt */ unsigned int tuning_done; /* Condition flag set when CMD19 succeeds */ -- cgit v1.2.3 From 1ea4c16120f529d811de0a35db6b252352268e95 Mon Sep 17 00:00:00 2001 From: Andrey Moiseev Date: Sun, 25 Aug 2013 22:51:15 -0700 Subject: Input: add driver for slidebar on Lenovo IdeaPad laptops This driver adds support for slidebars found on some Lenovo IdeaPad laptops (the slidebars work with SlideNav/Desktop Navigator under Windows). Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=16004 Registers 'IdeaPad Slidebar' input device and /sys/devices/platform/ideapad_slidebar/slidebar_mode for switching slidebar's modes. Now works on: IdeaPad Y550, Y550P. May work on (testing and adding new models is needed): Ideapad Y560, Y460, Y450, Y650, and, probably, some others. Signed-off-by: Andrey Moiseev Signed-off-by: Dmitry Torokhov --- include/linux/i8042.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i8042.h b/include/linux/i8042.h index a986ff588944..0f9bafa17a02 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -31,6 +31,30 @@ #define I8042_CMD_MUX_PFX 0x0090 #define I8042_CMD_MUX_SEND 0x1090 +/* + * Status register bits. + */ + +#define I8042_STR_PARITY 0x80 +#define I8042_STR_TIMEOUT 0x40 +#define I8042_STR_AUXDATA 0x20 +#define I8042_STR_KEYLOCK 0x10 +#define I8042_STR_CMDDAT 0x08 +#define I8042_STR_MUXERR 0x04 +#define I8042_STR_IBF 0x02 +#define I8042_STR_OBF 0x01 + +/* + * Control register bits. + */ + +#define I8042_CTR_KBDINT 0x01 +#define I8042_CTR_AUXINT 0x02 +#define I8042_CTR_IGNKEYLOCK 0x08 +#define I8042_CTR_KBDDIS 0x10 +#define I8042_CTR_AUXDIS 0x20 +#define I8042_CTR_XLATE 0x40 + struct serio; #if defined(CONFIG_SERIO_I8042) || defined(CONFIG_SERIO_I8042_MODULE) -- cgit v1.2.3 From cfe51ec1ae427ec0be5a7670eae815ce5eb30e1c Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 24 Aug 2013 00:32:30 +0200 Subject: bcma: add method to power up and down the PCIe core by wifi driver The wifi driver should tell the PCIe core that it is now in operation so that some workarounds can be applied and the power state is changed. This should replace the call to bcma_core_pci_extend_L1timer by the brcmsmac driver. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 424760f01b9d..27f9ceb68b42 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -185,6 +185,7 @@ struct pci_dev; #define BCMA_CORE_PCI_RC_CRS_VISIBILITY 0x0001 struct bcma_drv_pci; +struct bcma_bus; #ifdef CONFIG_BCMA_DRIVER_PCI_HOSTMODE struct bcma_drv_pci_host { @@ -220,6 +221,8 @@ extern void bcma_core_pci_init(struct bcma_drv_pci *pc); extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable); extern void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend); +extern void bcma_core_pci_up(struct bcma_bus *bus); +extern void bcma_core_pci_down(struct bcma_bus *bus); extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); extern int bcma_core_pci_plat_dev_init(struct pci_dev *dev); -- cgit v1.2.3 From 780335acc815802dcee63d75f5589d43c3ccb402 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 24 Aug 2013 00:32:32 +0200 Subject: bcma: do not export bcma_core_pci_extend_L1timer() This is not called any more, do not export it. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 27f9ceb68b42..0234955aa9c7 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -220,7 +220,6 @@ struct bcma_drv_pci { extern void bcma_core_pci_init(struct bcma_drv_pci *pc); extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable); -extern void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend); extern void bcma_core_pci_up(struct bcma_bus *bus); extern void bcma_core_pci_down(struct bcma_bus *bus); -- cgit v1.2.3 From 521deea64088bc885a76bd174241eaa3d3a6876f Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 24 Aug 2013 00:32:33 +0200 Subject: bcma: add bcma_core_pci_power_save() This enables or disables power saving on the PCIe bus when the wifi is in operation or not. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_pci.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 0234955aa9c7..d66033f418c9 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -181,6 +181,26 @@ struct pci_dev; #define BCMA_CORE_PCI_CFG_DEVCTRL 0xd8 +#define BCMA_CORE_PCI_ + +/* MDIO devices (SERDES modules) */ +#define BCMA_CORE_PCI_MDIO_IEEE0 0x000 +#define BCMA_CORE_PCI_MDIO_IEEE1 0x001 +#define BCMA_CORE_PCI_MDIO_BLK0 0x800 +#define BCMA_CORE_PCI_MDIO_BLK1 0x801 +#define BCMA_CORE_PCI_MDIO_BLK1_MGMT0 0x16 +#define BCMA_CORE_PCI_MDIO_BLK1_MGMT1 0x17 +#define BCMA_CORE_PCI_MDIO_BLK1_MGMT2 0x18 +#define BCMA_CORE_PCI_MDIO_BLK1_MGMT3 0x19 +#define BCMA_CORE_PCI_MDIO_BLK1_MGMT4 0x1A +#define BCMA_CORE_PCI_MDIO_BLK2 0x802 +#define BCMA_CORE_PCI_MDIO_BLK3 0x803 +#define BCMA_CORE_PCI_MDIO_BLK4 0x804 +#define BCMA_CORE_PCI_MDIO_TXPLL 0x808 /* TXPLL register block idx */ +#define BCMA_CORE_PCI_MDIO_TXCTRL0 0x820 +#define BCMA_CORE_PCI_MDIO_SERDESID 0x831 +#define BCMA_CORE_PCI_MDIO_RXCTRL0 0x840 + /* PCIE Root Capability Register bits (Host mode only) */ #define BCMA_CORE_PCI_RC_CRS_VISIBILITY 0x0001 -- cgit v1.2.3 From 277fe44dd862412ee034470ad1c13a79d24e533b Mon Sep 17 00:00:00 2001 From: Yonghua Zheng Date: Mon, 26 Aug 2013 23:38:35 +0800 Subject: HID: hidraw: Add spinlock in struct hidraw to protect list It is unsafe to call list_for_each_entry in hidraw_report_event to traverse each hidraw_list node without a lock protection, the list could be modified if someone calls hidraw_release and list_del to remove itself from the list, this can cause hidraw_report_event to touch a deleted list struct and panic. To prevent this, introduce a spinlock in struct hidraw to protect list from concurrent access. Signed-off-by: Yonghua Zheng Signed-off-by: Jiri Kosina --- include/linux/hidraw.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h index 2451662c728a..ddf52612eed8 100644 --- a/include/linux/hidraw.h +++ b/include/linux/hidraw.h @@ -23,6 +23,7 @@ struct hidraw { wait_queue_head_t wait; struct hid_device *hid; struct device *dev; + spinlock_t list_lock; struct list_head list; }; -- cgit v1.2.3 From 35cf083619da5677f83e9a8eae813f0b413d7082 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: rename cgroup_css_from_dir() to css_from_dir() and update its syntax cgroup_css_from_dir() will grow another user. In preparation, make the following changes. * All css functions are prefixed with just "css_", rename it to css_from_dir(). * Take dentry * instead of file * as dentry is what ultimately identifies a cgroup and file may not always be available. Note that the function now checkes whether @dentry->d_inode is NULL as the caller now may specify a negative dentry. * Make it take cgroup_subsys * instead of integer subsys_id. This simplifies the function and allows specifying no subsystem for cgroup->dummy_css. * Make return section a bit less verbose. This patch doesn't introduce any behavior changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar --- include/linux/cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b685955d4b29..21ba29869eb8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -903,7 +903,8 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg, /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); -struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); +struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); #else /* !CONFIG_CGROUPS */ -- cgit v1.2.3 From 9fa4db334c7d9570aec7a5121e84fae99aae1d04 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: implement CFTYPE_NO_PREFIX When cgroup files are created, cgroup core automatically prepends the name of the subsystem as prefix. This patch adds CFTYPE_NO_ which disables the automatic prefix. This is to work around historical baggages and shouldn't be used for new files. This will be used to move "cgroup.event_control" from cgroup core to memcg. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Glauber Costa --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 21ba29869eb8..3561d305b1e0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -411,6 +411,7 @@ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ }; #define MAX_CFTYPE_NAME 64 -- cgit v1.2.3 From 33b3a561f417ec3e1013999ce8bdb6c055abb1ce Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Tue, 9 Jul 2013 02:11:37 -0700 Subject: leds: support new LP8501 device - another LP55xx common LP8501 can drive up to 9 channels like LP5523. LEDs can be controlled directly via the I2C and programmable engines are supported. LP55xx common driver LP8501 is one of LP55xx family device, so LP55xx common code are used. Chip specific data is defined in the structure, 'lp55xx_device_config'. Differences between LP8501 and LP5523 Different register layout for LED output control and others. LP8501 specific feature for separate output power selection. LP8501 doesn't support external clock detection. Different programming engine data. LP8501 specific feature - output power selection Output channels are selected by power selection - Vout or Vdd. Separate power for VDD1-6 and VDD7-9 are available. It is configurable in the platform data. To support this feature, LP55xx DT structure and header are changed. Device tree binding is updated as well. LED pattern data Example pattern data is updated in the driver documentation. Signed-off-by: Milo Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 202e290faea8..51a2ff579d60 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -36,6 +36,13 @@ struct lp55xx_predef_pattern { u8 size_b; }; +enum lp8501_pwr_sel { + LP8501_ALL_VDD, /* D1~9 are connected to VDD */ + LP8501_6VDD_3VOUT, /* D1~6 with VDD, D7~9 with VOUT */ + LP8501_3VDD_6VOUT, /* D1~6 with VOUT, D7~9 with VDD */ + LP8501_ALL_VOUT, /* D1~9 are connected to VOUT */ +}; + /* * struct lp55xx_platform_data * @led_config : Configurable led class device @@ -67,6 +74,9 @@ struct lp55xx_platform_data { /* Predefined pattern data */ struct lp55xx_predef_pattern *patterns; unsigned int num_patterns; + + /* LP8501 specific */ + enum lp8501_pwr_sel pwr_sel; }; #endif /* _LEDS_LP55XX_H */ -- cgit v1.2.3 From 8465b01827b7a1e0e2464b0a300618bf7add25d8 Mon Sep 17 00:00:00 2001 From: "Mark A. Greer" Date: Thu, 25 Jul 2013 10:16:41 -0700 Subject: leds: pca9633: Add hardware blink support Add hardware blinking support to the pca9633 driver. NOTE: Hardware blinking violates the leds infrastructure driver interface since the hardware only supports blinking all LEDs with the same delay_on/delay_off rates. That is, only the LEDs that are set to blink will actually blink but all LEDs that are set to blink will blink in identical fashion. The delay_on/delay_off values of the last LED that is set to blink will be used for all of the blinking LEDs. If the hardware doesn't support the requested blinking pattern, a default of 500ms on and off will be used. Hardware blinking is disabled by default but can be enabled by setting the 'blink_type' member in the platform_data struct to 'PCA9633_HW_BLINK' or by adding the 'nxp,hw-blink' property to the DTS. (fengguang.wu@intel.com: Removes unneeded semicolon.) Signed-off-by: Mark A. Greer Reported-by: Fengguang Wu Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-pca9633.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-pca9633.h b/include/linux/platform_data/leds-pca9633.h index c5bf29b6fa7f..3c1037a81d34 100644 --- a/include/linux/platform_data/leds-pca9633.h +++ b/include/linux/platform_data/leds-pca9633.h @@ -27,9 +27,15 @@ enum pca9633_outdrv { PCA9633_TOTEM_POLE, /* aka push-pull */ }; +enum pca9633_blink_type { + PCA9633_SW_BLINK, + PCA9633_HW_BLINK, +}; + struct pca9633_platform_data { struct led_platform_data leds; enum pca9633_outdrv outdrv; + enum pca9633_blink_type blink_type; }; #endif /* __LINUX_PCA9633_H*/ -- cgit v1.2.3 From 56a1740c21e4396164265c3ec80e29990ddcdc36 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Wed, 14 Aug 2013 14:23:50 -0700 Subject: leds-pca9633: Rename to leds-pca963x The driver now supports the chips pca9633 and pca9634, therefore we rename the files to more generic and meaningul names Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-pca9633.h | 41 ----------------------------- include/linux/platform_data/leds-pca963x.h | 42 ++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 41 deletions(-) delete mode 100644 include/linux/platform_data/leds-pca9633.h create mode 100644 include/linux/platform_data/leds-pca963x.h (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-pca9633.h b/include/linux/platform_data/leds-pca9633.h deleted file mode 100644 index 3c1037a81d34..000000000000 --- a/include/linux/platform_data/leds-pca9633.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * PCA9633 LED chip driver. - * - * Copyright 2012 bct electronic GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - */ - -#ifndef __LINUX_PCA9633_H -#define __LINUX_PCA9633_H -#include - -enum pca9633_outdrv { - PCA9633_OPEN_DRAIN, - PCA9633_TOTEM_POLE, /* aka push-pull */ -}; - -enum pca9633_blink_type { - PCA9633_SW_BLINK, - PCA9633_HW_BLINK, -}; - -struct pca9633_platform_data { - struct led_platform_data leds; - enum pca9633_outdrv outdrv; - enum pca9633_blink_type blink_type; -}; - -#endif /* __LINUX_PCA9633_H*/ diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h new file mode 100644 index 000000000000..e731f0036329 --- /dev/null +++ b/include/linux/platform_data/leds-pca963x.h @@ -0,0 +1,42 @@ +/* + * PCA963X LED chip driver. + * + * Copyright 2012 bct electronic GmbH + * Copyright 2013 Qtechnology A/S + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + */ + +#ifndef __LINUX_PCA963X_H +#define __LINUX_PCA963X_H +#include + +enum pca963x_outdrv { + PCA963X_OPEN_DRAIN, + PCA963X_TOTEM_POLE, /* aka push-pull */ +}; + +enum pca963x_blink_type { + PCA963X_SW_BLINK, + PCA963X_HW_BLINK, +}; + +struct pca963x_platform_data { + struct led_platform_data leds; + enum pca963x_outdrv outdrv; + enum pca963x_blink_type blink_type; +}; + +#endif /* __LINUX_PCA963X_H*/ -- cgit v1.2.3 From e51db73532955dc5eaba4235e62b74b460709d5b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 30 Mar 2013 19:57:41 -0700 Subject: userns: Better restrictions on when proc and sysfs can be mounted Rely on the fact that another flavor of the filesystem is already mounted and do not rely on state in the user namespace. Verify that the mounted filesystem is not covered in any significant way. I would love to verify that the previously mounted filesystem has no mounts on top but there are at least the directories /proc/sys/fs/binfmt_misc and /sys/fs/cgroup/ that exist explicitly for other filesystems to mount on top of. Refactor the test into a function named fs_fully_visible and call that function from the mount routines of proc and sysfs. This makes this test local to the filesystems involved and the results current of when the mounts take place, removing a weird threading of the user namespace, the mount namespace and the filesystems themselves. Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 1 + include/linux/user_namespace.h | 4 ---- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 981874773e85..3050c620f062 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1897,6 +1897,7 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); +extern bool fs_fully_visible(struct file_system_type *); extern int current_umask(void); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b6b215f13b45..4ce009324933 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -26,8 +26,6 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; - bool may_mount_sysfs; - bool may_mount_proc; }; extern struct user_namespace init_user_ns; @@ -84,6 +82,4 @@ static inline void put_user_ns(struct user_namespace *ns) #endif -void update_mnt_policy(struct user_namespace *userns); - #endif /* _LINUX_USER_H */ -- cgit v1.2.3 From ae77cbc1e7b90473a2b0963bce0e1eb163873214 Mon Sep 17 00:00:00 2001 From: Ken Steele Date: Wed, 7 Aug 2013 12:39:56 -0400 Subject: RAID: add tilegx SIMD implementation of raid6 This change adds TILE-Gx SIMD instructions to the software raid (md), modeling the Altivec implementation. This is only for Syndrome generation; there is more that could be done to improve recovery, as in the recent Intel SSE3 recovery implementation. The code unrolls 8 times; this turns out to be the best on tilegx hardware among the set 1, 2, 4, 8 or 16. The code reads one cache-line of data from each disk, stores P and Q then goes to the next cache-line. The test code in sys/linux/lib/raid6/test reports 2008 MB/s data read rate for syndrome generation using 18 disks (16 data and 2 parity). It was 1512 MB/s before this SIMD optimizations. This is running on 1 core with all the data in cache. This is based on the paper The Mathematics of RAID-6. (http://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf). Signed-off-by: Ken Steele Signed-off-by: Chris Metcalf Signed-off-by: NeilBrown --- include/linux/raid/pq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 8dfaa2ce2e95..6d5df8adb53a 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -101,6 +101,7 @@ extern const struct raid6_calls raid6_altivec8; extern const struct raid6_calls raid6_avx2x1; extern const struct raid6_calls raid6_avx2x2; extern const struct raid6_calls raid6_avx2x4; +extern const struct raid6_calls raid6_tilegx8; struct raid6_recov_calls { void (*data2)(int, size_t, int, int, void **); -- cgit v1.2.3 From a2547380393ac82c659b40182b0da8d05a8365f3 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 29 Jul 2013 14:31:45 +0200 Subject: drivers: dma-contiguous: clean source code and prepare for device tree This patch cleans the initialization of dma contiguous framework. The all-in-one dma_declare_contiguous() function is now separated into dma_contiguous_reserve_area() which only steals the the memory from memblock allocator and dma_contiguous_add_device() function, which assigns given device to the specified reserved memory area. This improves the flexibility in defining contiguous memory areas and assigning device to them, because now it is possible to assign more than one device to the given contiguous memory area. Such split in initialization procedure is also required for upcoming device tree support. Signed-off-by: Marek Szyprowski Acked-by: Kyungmin Park Acked-by: Michal Nazarewicz Acked-by: Tomasz Figa --- include/linux/device.h | 2 +- include/linux/dma-contiguous.h | 62 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 61 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index bcf8c0d4cd98..9200cfd75f15 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -711,7 +711,7 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ -#ifdef CONFIG_CMA +#ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 00141d3325fe..3b28f937d959 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -67,9 +67,53 @@ struct device; extern struct cma *dma_contiguous_default_area; +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; +} + +static inline void dma_contiguous_set_default(struct cma *cma) +{ + dma_contiguous_default_area = cma; +} + void dma_contiguous_reserve(phys_addr_t addr_limit); -int dma_declare_contiguous(struct device *dev, phys_addr_t size, - phys_addr_t base, phys_addr_t limit); + +int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, + phys_addr_t limit, struct cma **res_cma); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @base: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ + +static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma *cma; + int ret; + ret = dma_contiguous_reserve_area(size, base, limit, &cma); + if (ret == 0) + dev_set_cma_area(dev, cma); + + return ret; +} struct page *dma_alloc_from_contiguous(struct device *dev, int count, unsigned int order); @@ -80,8 +124,22 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages, #define MAX_CMA_AREAS (0) +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + return NULL; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { } + +static inline void dma_contiguous_set_default(struct cma *cma) { } + static inline void dma_contiguous_reserve(phys_addr_t limit) { } +static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, + phys_addr_t limit, struct cma **res_cma) { + return -ENOSYS; +} + static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, phys_addr_t base, phys_addr_t limit) -- cgit v1.2.3 From 57d74bcf3072b65bde5aa540cedc976a75c48e5c Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 26 Aug 2013 14:41:56 +0200 Subject: drivers: of: add function to scan fdt nodes given by path Add a function to scan the flattened device-tree starting from the node given by the path. It is used to extract information (like reserved memory), which is required on early boot before we can unflatten the tree. Signed-off-by: Marek Szyprowski Acked-by: Michal Nazarewicz Acked-by: Tomasz Figa Reviewed-by: Rob Herring --- include/linux/of_fdt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index ed136ad698ce..19f26f8d2202 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -90,6 +90,9 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern int of_flat_dt_match(unsigned long node, const char *const *matches); extern unsigned long of_get_flat_dt_root(void); +extern int of_scan_flat_dt_by_path(const char *path, + int (*it)(unsigned long node, const char *name, int depth, void *data), + void *data); extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data); -- cgit v1.2.3 From f961bd3516e4f699bbacff5d7f5247d6d87c59f0 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 22 Aug 2013 14:51:08 +0200 Subject: HID: detect Win 8 multitouch devices in core Detecting Win 8 multitouch devices in core allows us to set quirks before the device is parsed through hid_hw_start(). It also simplifies the detection of those devices in hid-multitouch and makes the handling of those devices cleaner. As Win 8 multitouch panels are in the group multitouch and rely on a special feature to be detected, this patch adds a bitfield in the parser. Signed-off-by: Benjamin Tissoires Reviewed-by: Henrik Rydberg Tested-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0c48991b0402..cef1e9b86cc4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -295,6 +295,7 @@ struct hid_item { #define HID_GROUP_GENERIC 0x0001 #define HID_GROUP_MULTITOUCH 0x0002 #define HID_GROUP_SENSOR_HUB 0x0003 +#define HID_GROUP_MULTITOUCH_WIN_8 0x0004 /* * This is the global environment of the parser. This information is @@ -532,6 +533,8 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 +#define HID_SCAN_FLAG_MT_WIN_8 0x00000001 + struct hid_parser { struct hid_global global; struct hid_global global_stack[HID_GLOBAL_STACK_SIZE]; @@ -540,6 +543,7 @@ struct hid_parser { unsigned collection_stack[HID_COLLECTION_STACK_SIZE]; unsigned collection_stack_ptr; struct hid_device *device; + unsigned scan_flags; }; struct hid_class_descriptor { -- cgit v1.2.3 From 595e9276ce68791317484ec7f0f9f2e0457c3b34 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 22 Aug 2013 14:51:09 +0200 Subject: HID: do not init input reports for Win 8 multitouch devices Some multitouch screens do not like to be polled for input reports. However, the Win8 spec says that all touches should be sent during each report, making the initialization of reports unnecessary. The Win7 spec is less precise, so do not use this for those devices. Add the quirk HID_QUIRK_NO_INIT_INPUT_REPORTS so that we do not have to introduce a quirk for each problematic device. This quirk makes the driver behave the same way the Win 8 does. It actually retrieves the features, but not the inputs. Signed-off-by: Benjamin Tissoires Reviewed-by: Henrik Rydberg Tested-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index cef1e9b86cc4..bc132d2a20aa 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -283,6 +283,7 @@ struct hid_item { #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 +#define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 -- cgit v1.2.3 From 9d8eab7af79cb4ce2de5de39f82c455b1f796963 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 26 Aug 2013 14:43:10 +0200 Subject: drivers: of: add initialization code for dma reserved memory This patch adds device tree support for contiguous and reserved memory regions defined in device tree. Large memory blocks can be reliably reserved only during early boot. This must happen before the whole memory management subsystem is initialized, because we need to ensure that the given contiguous blocks are not yet allocated by kernel. Also it must happen before kernel mappings for the whole low memory are created, to ensure that there will be no mappings (for reserved blocks) or mapping with special properties can be created (for CMA blocks). This all happens before device tree structures are unflattened, so we need to get reserved memory layout directly from fdt. Later, those reserved memory regions are assigned to devices on each device structure initialization. Signed-off-by: Marek Szyprowski Acked-by: Kyungmin Park Acked-by: Michal Nazarewicz Acked-by: Tomasz Figa Acked-by: Stephen Warren Reviewed-by: Rob Herring --- include/linux/of_reserved_mem.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/of_reserved_mem.h (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h new file mode 100644 index 000000000000..c84128255814 --- /dev/null +++ b/include/linux/of_reserved_mem.h @@ -0,0 +1,14 @@ +#ifndef __OF_RESERVED_MEM_H +#define __OF_RESERVED_MEM_H + +#ifdef CONFIG_OF_RESERVED_MEM +void of_reserved_mem_device_init(struct device *dev); +void of_reserved_mem_device_release(struct device *dev); +void early_init_dt_scan_reserved_mem(void); +#else +static inline void of_reserved_mem_device_init(struct device *dev) { } +static inline void of_reserved_mem_device_release(struct device *dev) { } +static inline void early_init_dt_scan_reserved_mem(void) { } +#endif + +#endif /* __OF_RESERVED_MEM_H */ -- cgit v1.2.3 From ca8b387803072a16baf6d8090591b10bfdf4e253 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 10 Jul 2013 12:09:47 +0200 Subject: DMA: shdma: support the new CHCLR register layout On newer r-car SoCs the CHCLR register only contains one bit per channel, to which a 1 has to be written to reset the channel. Older SoC versions had one CHCLR register per channel, to which a 0 must be written to reset the channel and clear its buffers. This patch adds support for the newer layout. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Vinod Koul --- include/linux/sh_dma.h | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 4e83f3e034f3..776ed9d682f4 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -33,13 +33,44 @@ struct sh_dmae_slave_config { char mid_rid; }; +/** + * struct sh_dmae_channel - DMAC channel platform data + * @offset: register offset within the main IOMEM resource + * @dmars: channel DMARS register offset + * @chclr_offset: channel CHCLR register offset + * @dmars_bit: channel DMARS field offset within the register + * @chclr_bit: bit position, to be set to reset the channel + */ struct sh_dmae_channel { unsigned int offset; unsigned int dmars; - unsigned int dmars_bit; unsigned int chclr_offset; + unsigned char dmars_bit; + unsigned char chclr_bit; }; +/** + * struct sh_dmae_pdata - DMAC platform data + * @slave: array of slaves + * @slave_num: number of slaves in the above array + * @channel: array of DMA channels + * @channel_num: number of channels in the above array + * @ts_low_shift: shift of the low part of the TS field + * @ts_low_mask: low TS field mask + * @ts_high_shift: additional shift of the high part of the TS field + * @ts_high_mask: high TS field mask + * @ts_shift: array of Transfer Size shifts, indexed by TS value + * @ts_shift_num: number of shifts in the above array + * @dmaor_init: DMAOR initialisation value + * @chcr_offset: CHCR address offset + * @chcr_ie_bit: CHCR Interrupt Enable bit + * @dmaor_is_32bit: DMAOR is a 32-bit register + * @needs_tend_set: the TEND register has to be set + * @no_dmars: DMAC has no DMARS registers + * @chclr_present: DMAC has one or several CHCLR registers + * @chclr_bitwise: channel CHCLR registers are bitwise + * @slave_only: DMAC cannot be used for MEMCPY + */ struct sh_dmae_pdata { const struct sh_dmae_slave_config *slave; int slave_num; @@ -59,6 +90,7 @@ struct sh_dmae_pdata { unsigned int needs_tend_set:1; unsigned int no_dmars:1; unsigned int chclr_present:1; + unsigned int chclr_bitwise:1; unsigned int slave_only:1; }; -- cgit v1.2.3 From c1c63a14f4f2419d093acd7164eccdff315baa86 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Tue, 2 Jul 2013 17:45:55 +0200 Subject: DMA: shdma: switch to managed resource allocation Switch shdma to using devm_* managed functions for allocation of memory, requesting IRQs, mapping IO resources etc. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Vinod Koul --- include/linux/shdma-base.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h index 5b1c9848124c..31cf89fb1d5b 100644 --- a/include/linux/shdma-base.h +++ b/include/linux/shdma-base.h @@ -116,7 +116,6 @@ struct shdma_dev { int shdma_request_irq(struct shdma_chan *, int, unsigned long, const char *); -void shdma_free_irq(struct shdma_chan *); bool shdma_reset(struct shdma_dev *sdev); void shdma_chan_probe(struct shdma_dev *sdev, struct shdma_chan *schan, int id); -- cgit v1.2.3 From 4981c4dc194efb18f0e9a02f1b43e926f2f0d2bb Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 2 Aug 2013 16:50:36 +0200 Subject: DMA: shdma: switch DT mode to use configuration data from a match table This facilitates DMAC DT support by eliminating the need in AUXDATA and avoiding creating complex DT data. This also fits well with DMAC devices, of which SoCs often have multiple identical copies and it is perfectly valid to use a single configuration data set for all of them. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Vinod Koul --- include/linux/shdma-base.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h index 31cf89fb1d5b..f92c0a43c54c 100644 --- a/include/linux/shdma-base.h +++ b/include/linux/shdma-base.h @@ -96,7 +96,7 @@ struct shdma_ops { dma_addr_t (*slave_addr)(struct shdma_chan *); int (*desc_setup)(struct shdma_chan *, struct shdma_desc *, dma_addr_t, dma_addr_t, size_t *); - int (*set_slave)(struct shdma_chan *, int, bool); + int (*set_slave)(struct shdma_chan *, int, dma_addr_t, bool); void (*setup_xfer)(struct shdma_chan *, int); void (*start_xfer)(struct shdma_chan *, struct shdma_desc *); struct shdma_desc *(*embedded_desc)(void *, int); -- cgit v1.2.3 From 4620ad5419612fcd9ab412410440d3a7e8a9a90a Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 2 Aug 2013 16:50:37 +0200 Subject: DMA: shdma: remove private and unused defines from a global header Macros, named like TEND or SAR lack a namespace and are too broadly named for a global header. Besides, they aren't needed globally. Move them to where they belong - into the driver. Some other macros aren't used at all, remove them. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Vinod Koul --- include/linux/sh_dma.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 776ed9d682f4..b7b43b82231e 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -94,39 +94,18 @@ struct sh_dmae_pdata { unsigned int slave_only:1; }; -/* DMA register */ -#define SAR 0x00 -#define DAR 0x04 -#define TCR 0x08 -#define CHCR 0x0C -#define DMAOR 0x40 - -#define TEND 0x18 /* USB-DMAC */ - /* DMAOR definitions */ #define DMAOR_AE 0x00000004 #define DMAOR_NMIF 0x00000002 #define DMAOR_DME 0x00000001 /* Definitions for the SuperH DMAC */ -#define REQ_L 0x00000000 -#define REQ_E 0x00080000 -#define RACK_H 0x00000000 -#define RACK_L 0x00040000 -#define ACK_R 0x00000000 -#define ACK_W 0x00020000 -#define ACK_H 0x00000000 -#define ACK_L 0x00010000 #define DM_INC 0x00004000 #define DM_DEC 0x00008000 #define DM_FIX 0x0000c000 #define SM_INC 0x00001000 #define SM_DEC 0x00002000 #define SM_FIX 0x00003000 -#define RS_IN 0x00000200 -#define RS_OUT 0x00000300 -#define TS_BLK 0x00000040 -#define TM_BUR 0x00000020 #define CHCR_DE 0x00000001 #define CHCR_TE 0x00000002 #define CHCR_IE 0x00000004 -- cgit v1.2.3 From 41d73ec053d2424599c4ed8452b889374d523ade Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 27 Aug 2013 08:50:12 +0200 Subject: netfilter: nf_conntrack: make sequence number adjustments usuable without NAT Split out sequence number adjustments from NAT and move them to the conntrack core to make them usable for SYN proxying. The sequence number adjustment information is moved to a seperate extend. The extend is added to new conntracks when a NAT mapping is set up for a connection using a helper. As a side effect, this saves 24 bytes per connection with NAT in the common case that a connection does not have a helper assigned. Signed-off-by: Patrick McHardy Tested-by: Martin Topholm Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e2cf786be22f..708fe72ab913 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -319,6 +319,7 @@ extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; struct nf_conn; +enum ip_conntrack_info; struct nlattr; struct nfq_ct_hook { @@ -327,14 +328,10 @@ struct nfq_ct_hook { int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); -}; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; - -struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, s32 off); + enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; +extern struct nfq_ct_hook __rcu *nfq_ct_hook; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif -- cgit v1.2.3 From f799878000c5a9a1e6a311dfd4faa50601dcb1f8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Aug 2013 17:24:49 -0700 Subject: sysfs: add sysfs_create/remove_groups for when SYSFS is not enabled We need these functions for when CONFIG_SYSFS=n. Reported-by: Fengguang Wu Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 69c1ff003628..e647a1aa0723 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -350,6 +350,11 @@ static inline int sysfs_create_group(struct kobject *kobj, return 0; } +static inline int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { @@ -361,6 +366,11 @@ static inline void sysfs_remove_group(struct kobject *kobj, { } +static inline void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { -- cgit v1.2.3 From aa514ce34b65e3dc01f95a0b470b39bbb7e09998 Mon Sep 17 00:00:00 2001 From: Gerhard Sittig Date: Mon, 22 Jul 2013 14:14:40 +0200 Subject: clk: wrap I/O access for improved portability the common clock drivers were motivated/initiated by ARM development and apparently assume little endian peripherals wrap register/peripherals access in the common code (div, gate, mux) in preparation of adding COMMON_CLK support for other platforms Signed-off-by: Gerhard Sittig Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1f0285b2f422..73bdb69f0c08 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -12,6 +12,7 @@ #define __LINUX_CLK_PROVIDER_H #include +#include #ifdef CONFIG_COMMON_CLK @@ -504,5 +505,21 @@ static inline const char *of_clk_get_parent_name(struct device_node *np, #define of_clk_init(matches) \ { while (0); } #endif /* CONFIG_OF */ + +/* + * wrap access to peripherals in accessor routines + * for improved portability across platforms + */ + +static inline u32 clk_readl(u32 __iomem *reg) +{ + return readl(reg); +} + +static inline void clk_writel(u32 val, u32 __iomem *reg) +{ + writel(val, reg); +} + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From d7bf353fd0aa3e12060ce64c8a7b4aaf4336145c Mon Sep 17 00:00:00 2001 From: "Mark A. Greer" Date: Fri, 23 Aug 2013 19:21:03 -0700 Subject: bq24190_charger: Add support for TI BQ24190 Battery Charger Add driver support for the Texas Instruments BQ24190 battery charger. Some of the information provided by the device is about the charger and other information is about the battery so create two power_supply objects (one for each) and provide the appropriate information for each one. The device has many fields that go beyond what is reasonable to report or modify using the existing 'POWER_SUPPLY_PROP_*' properties so the driver exports the register fields via sysfs. They are prefixed by 'f_' (for 'field') to make it easier to distinguish between a register field and a "normal" sysfs file exported by the power_supply infrastructure. Signed-off-by: Mark A. Greer Signed-off-by: Anton Vorontsov --- include/linux/power/bq24190_charger.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/power/bq24190_charger.h (limited to 'include/linux') diff --git a/include/linux/power/bq24190_charger.h b/include/linux/power/bq24190_charger.h new file mode 100644 index 000000000000..9f0283721cbc --- /dev/null +++ b/include/linux/power/bq24190_charger.h @@ -0,0 +1,16 @@ +/* + * Platform data for the TI bq24190 battery charger driver. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _BQ24190_CHARGER_H_ +#define _BQ24190_CHARGER_H_ + +struct bq24190_platform_data { + unsigned int gpio_int; /* GPIO pin that's connected to INT# */ +}; + +#endif -- cgit v1.2.3 From 948dcf96622814d2a850a12851d27824530a9747 Mon Sep 17 00:00:00 2001 From: Zoran Markovic Date: Fri, 2 Aug 2013 13:38:02 -0700 Subject: power_supply: Prevent suspend until power supply events are processed This patch, originally authored by Arve Hjonnevag and Todd Poynor, prevents the system from entering suspend mode until the power supply plug, unplug, or any other change of state event is fully processed. This guarantees that the screen lights up and displays the battery charging state. The implementation uses the power supply wakeup_source object. Cc: David Woodhouse Cc: Arve Hjonnevag Cc: Todd Poynor Cc: John Stultz Signed-off-by: Zoran Markovic Signed-off-by: Anton Vorontsov --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 804b90643a85..5c2600630dc9 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -15,6 +15,7 @@ #include #include +#include struct device; @@ -194,6 +195,8 @@ struct power_supply { /* private */ struct device *dev; struct work_struct changed_work; + spinlock_t changed_lock; + bool changed; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; -- cgit v1.2.3 From 3159269ef484954985cbbf1ff89976f090a18b24 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 26 Aug 2013 09:58:30 +0200 Subject: debugfs: provide debugfs_create_x64() when disabled commit 15b0beaa332b3923cc ("Add x64 support to debugfs") added debugfs_create_x64(), but forgot to provide it when debugfs is disabled, causing problems when code tries to use it even then. Provide the appropriate static inline. Cc: Huang Ying Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index d68b4ea7343c..263489d0788d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -192,6 +192,13 @@ static inline struct dentry *debugfs_create_x32(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, + struct dentry *parent, + u64 *value) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) -- cgit v1.2.3 From 03b054e9696c3cbd3d5905ec96da15acd0a2fe8d Mon Sep 17 00:00:00 2001 From: Sherman Yin Date: Tue, 27 Aug 2013 11:32:12 -0700 Subject: pinctrl: Pass all configs to driver on pin_config_set() When setting pin configuration in the pinctrl framework, pin_config_set() or pin_config_group_set() is called in a loop to set one configuration at a time for the specified pin or group. This patch 1) removes the loop and 2) changes the API to pass the whole pin config array to the driver. It is now up to the driver to loop through the configs. This allows the driver to potentially combine configs and reduce the number of writes to pin config registers. All c files changed have been build-tested to verify the change compiles and that the corresponding .o is successfully generated. Signed-off-by: Sherman Yin Reviewed-by: Christian Daudt Reviewed-by: Matt Porter Tested-by: Stephen Warren Acked-by: Laurent Pinchart Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index f6998692bdc9..09eb80f2574a 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -47,13 +47,15 @@ struct pinconf_ops { unsigned long *config); int (*pin_config_set) (struct pinctrl_dev *pctldev, unsigned pin, - unsigned long config); + unsigned long *configs, + unsigned num_configs); int (*pin_config_group_get) (struct pinctrl_dev *pctldev, unsigned selector, unsigned long *config); int (*pin_config_group_set) (struct pinctrl_dev *pctldev, unsigned selector, - unsigned long config); + unsigned long *configs, + unsigned num_configs); int (*pin_config_dbg_parse_modify) (struct pinctrl_dev *pctldev, const char *arg, unsigned long *config); -- cgit v1.2.3 From 574979c617eb9593f8dfbb804da3f0e00f8bf28e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Aug 2013 09:51:41 -0700 Subject: sysfs: sysfs_create_groups returns a value. When I included the "empty" function for sysfs_create_groups() when CONFIG_SYSFS=n, I forgot to return a value for it, so things blew up the build. This patch fixes that, stupid me. Reported-by: kbuild test robot Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index e647a1aa0723..11baec7c9b26 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -353,6 +353,7 @@ static inline int sysfs_create_group(struct kobject *kobj, static inline int sysfs_create_groups(struct kobject *kobj, const struct attribute_group **groups) { + return 0; } static inline int sysfs_update_group(struct kobject *kobj, -- cgit v1.2.3 From f77c0162a339400ad16f657603fdc3bf11654fd3 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 14 Aug 2013 13:58:31 +0300 Subject: IB/mlx4: Add receive flow steering support Implement ib_create_flow() and ib_destroy_flow(). Translate the verbs structures provided by the user to HW structures and call the MLX4_QP_FLOW_STEERING_ATTACH/DETACH firmware commands. On the ATTACH command completion, the firmware provides a 64-bit registration ID, which is placed into struct mlx4_ib_flow that wraps the instance of struct ib_flow which is retuned to caller. Later, this reg ID is used for detaching that flow from the firmware. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 52c23a892bab..d73423c37c25 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1052,11 +1052,6 @@ struct _rule_hw { }; }; -/* translating DMFS verbs sniffer rule to the FW API would need two reg IDs */ -struct mlx4_flow_handle { - u64 reg_id[2]; -}; - int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, -- cgit v1.2.3 From 8ef2d6511f7eba89ef5fe41cc83008ae63368aa2 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Tue, 27 Aug 2013 17:47:34 +0300 Subject: dev-core: fix build break when DEBUG is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When DEBUG is defined, dev_dbg_ratelimited uses dynamic debug data structures even when CONFIG_DYNAMIC_DEBUG is not defined. It leads to build break. For example, when I try to use dev_dbg_ratelimited in USB code and CONFIG_USB_DEBUG is enabled, but CONFIG_DYNAMIC_DEBUG is not, I get: CC [M] drivers/usb/host/xhci-ring.o drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_intr_tx’: drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘DEFINE_DYNAMIC_DEBUG_METADATA’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c:3059:3: error: ‘descriptor’ undeclared (first use in this function) drivers/usb/host/xhci-ring.c:3059:3: note: each undeclared identifier is reported only once for each function it appears in drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘__dynamic_pr_debug’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_isoc_tx_prepare’: drivers/usb/host/xhci-ring.c:3847:3: error: ‘descriptor’ undeclared (first use in this function) cc1: some warnings being treated as errors make[2]: *** [drivers/usb/host/xhci-ring.o] Error 1 make[1]: *** [drivers/usb/host] Error 2 make: *** [drivers/usb/] Error 2 This patch separates definition for CONFIG_DYNAMIC_DEBUG and DEBUG cases. [Note, Sarah moved the comment above the macro to avoid checkpatch warnings.] Signed-off-by: Dmitry Kasatkin Signed-off-by: Sarah Sharp Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..7d960d581e9c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1099,7 +1099,8 @@ do { \ dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) #define dev_info_ratelimited(dev, fmt, ...) \ dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) +/* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ @@ -1108,8 +1109,17 @@ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ - ##__VA_ARGS__); \ + __dynamic_dev_dbg(&descriptor, dev, fmt, \ + ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -- cgit v1.2.3 From 10d9eb8a17cfb697967928bde06f3e7e530b03ac Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 19 Mar 2013 23:59:04 -0400 Subject: drivers: irq-chip: irq-gic: introduce gic_cpu_if_down() When processors are about to hit low power states, the assertion of standbywfi signal, triggered by the wfi instruction, is essential to entering low power modes. If an IRQ is pending on the processor at the time wfi is issued, the wfi instruction completes and the processor restarts execution without asserting the standbywfi signal. Depending on the platform power controller HW this behaviour can be acceptable or not; if this behaviour must be prevented software should be provided with a way to disable the routing of interrupts to the core IRQ pins. On systems where raw GIC distributor interrupts are connected to the power controller as wake-up events (hence the power controller still senses IRQs and can wake up cores upon IRQ pending), the GIC CPU interface can be disabled on power down, so that the GIC CPU IF output is gated and wfi cannot complete, thereby preventing the standbywfi issue. This patch adds a simple function to the GIC driver that allows to disable the GIC CPU IF from power down procedures. Signed-off-by: Nicolas Pitre Signed-off-by: Lorenzo Pieralisi [rewrote commit log] Signed-off-by: Olof Johansson --- include/linux/irqchip/arm-gic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 3e203eb23cc7..0e5d9ecdb2b6 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -66,6 +66,7 @@ extern struct irq_chip gic_arch_extn; void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *, u32 offset, struct device_node *); void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); +void gic_cpu_if_down(void); static inline void gic_init(unsigned int nr, int start, void __iomem *dist , void __iomem *cpu) -- cgit v1.2.3 From 7e0bdf15cee7d2c809558b8169dc5b08792d0c82 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 18 Aug 2013 13:01:30 +0200 Subject: of: Make of_get_phy_mode() return int i.s.o. const int include/linux/of_net.h:16: warning: type qualifiers ignored on function return type Signed-off-by: Geert Uytterhoeven Signed-off-by: Grant Likely --- include/linux/of_net.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 61bf53b02779..34597c8c1a4c 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -9,10 +9,10 @@ #ifdef CONFIG_OF_NET #include -extern const int of_get_phy_mode(struct device_node *np); +extern int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); #else -static inline const int of_get_phy_mode(struct device_node *np) +static inline int of_get_phy_mode(struct device_node *np) { return -ENODEV; } -- cgit v1.2.3 From 0d69704ae348c03bc216b01e32a0e9a2372be419 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 10 Sep 2012 12:28:36 +1000 Subject: gpu/vga_switcheroo: add driver control power feature. (v3) For optimus and powerxpress muxless we really want the GPU driver deciding when to power up/down the GPU, not userspace. This adds the ability for a driver to dynamically power up/down the GPU and remove the switcheroo from controlling it, the switcheroo reports the dynamic state to userspace also. It also adds 2 power domains, one for machine where the power switch is controlled outside the GPU D3 state, so the powerdown ordering is done correctly, and the second for the hdmi audio device to make sure it can resume for PCI config space accesses. v1.1: fix build with switcheroo off v2: add power domain support for radeon and v1 nvidia dsms v2.1: fix typo in off case v3: add audio power domain for hdmi audio + misc audio fixes v4: use PCI_SLOT macro, drop power reference on hdmi audio resume failure also. Signed-off-by: Dave Airlie --- include/linux/vga_switcheroo.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index ddb419cf4530..502073a53dd3 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -45,7 +45,8 @@ struct vga_switcheroo_client_ops { #if defined(CONFIG_VGA_SWITCHEROO) void vga_switcheroo_unregister_client(struct pci_dev *dev); int vga_switcheroo_register_client(struct pci_dev *dev, - const struct vga_switcheroo_client_ops *ops); + const struct vga_switcheroo_client_ops *ops, + bool driver_power_control); int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, int id, bool active); @@ -60,11 +61,15 @@ int vga_switcheroo_process_delayed_switch(void); int vga_switcheroo_get_client_state(struct pci_dev *dev); +void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); + +int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); +int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {} static inline int vga_switcheroo_register_client(struct pci_dev *dev, - const struct vga_switcheroo_client_ops *ops) { return 0; } + const struct vga_switcheroo_client_ops *ops, bool driver_power_control) { return 0; } static inline void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info) {} static inline int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler) { return 0; } static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, @@ -74,6 +79,10 @@ static inline void vga_switcheroo_unregister_handler(void) {} static inline int vga_switcheroo_process_delayed_switch(void) { return 0; } static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } +static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} + +static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } +static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif #endif /* _LINUX_VGA_SWITCHEROO_H_ */ -- cgit v1.2.3 From 7dc5dbc879bd0779924b5132a48b731a0bc04a1e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 25 Mar 2013 20:07:01 -0700 Subject: sysfs: Restrict mounting sysfs Don't allow mounting sysfs unless the caller has CAP_SYS_ADMIN rights over the net namespace. The principle here is if you create or have capabilities over it you can mount it, otherwise you get to live with what other people have mounted. Instead of testing this with a straight forward ns_capable call, perform this check the long and torturous way with kobject helpers, this keeps direct knowledge of namespaces out of sysfs, and preserves the existing sysfs abstractions. Acked-by: Greg Kroah-Hartman Signed-off-by: "Eric W. Biederman" --- include/linux/kobject_ns.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index f66b065a8b5f..df32d2508290 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -39,6 +39,7 @@ enum kobj_ns_type { */ struct kobj_ns_type_operations { enum kobj_ns_type type; + bool (*current_may_mount)(void); void *(*grab_current_ns)(void); const void *(*netlink_ns)(struct sock *sk); const void *(*initial_ns)(void); @@ -50,6 +51,7 @@ int kobj_ns_type_registered(enum kobj_ns_type type); const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); +bool kobj_ns_current_may_mount(enum kobj_ns_type type); void *kobj_ns_grab_current(enum kobj_ns_type type); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); const void *kobj_ns_initial(enum kobj_ns_type type); -- cgit v1.2.3 From 43622021d2e2b82ea03d883926605bdd0525e1d1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 28 Aug 2013 22:29:55 +0200 Subject: HID: validate HID report id size The "Report ID" field of a HID report is used to build indexes of reports. The kernel's index of these is limited to 256 entries, so any malicious device that sets a Report ID greater than 255 will trigger memory corruption on the host: [ 1347.156239] BUG: unable to handle kernel paging request at ffff88094958a878 [ 1347.156261] IP: [] hid_register_report+0x2a/0x8b CVE-2013-2888 Signed-off-by: Kees Cook Cc: stable@kernel.org Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0c48991b0402..ff545cc33c3a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -393,10 +393,12 @@ struct hid_report { struct hid_device *device; /* associated device */ }; +#define HID_MAX_IDS 256 + struct hid_report_enum { unsigned numbered; struct list_head report_list; - struct hid_report *report_id_hash[256]; + struct hid_report *report_id_hash[HID_MAX_IDS]; }; #define HID_REPORT_TYPES 3 -- cgit v1.2.3 From 9efdd27678ef5e22c27c230a08a211b702768f3a Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Sun, 25 Aug 2013 17:54:13 +0200 Subject: regulator: Add devm_regulator_get_exclusive() Add a resource managed regulator_get_exclusive() Signed-off-by: Matthias Kaehlcke Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index e2bac6db4abc..91aca11198d8 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,8 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check devm_regulator_get_exclusive(struct device *dev, + const char *id); struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id); struct regulator *__must_check devm_regulator_get_optional(struct device *dev, -- cgit v1.2.3 From b800c3b966bcf004bd8592293a49ed5cb7ea67a9 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Tue, 27 Aug 2013 01:36:51 +0200 Subject: ipv6: drop fragmented ndisc packets by default (RFC 6980) This patch implements RFC6980: Drop fragmented ndisc packets by default. If a fragmented ndisc packet is received the user is informed that it is possible to disable the check. Cc: Fernando Gont Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9ac5047062c8..28ea38439313 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -50,6 +50,7 @@ struct ipv6_devconf { __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; + __s32 suppress_frag_ndisc; void *sysctl; }; -- cgit v1.2.3 From 5877457a96e5f89567d2eea092ec28db5d55fc06 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 29 Aug 2013 15:24:14 -0400 Subject: gpio: (gpio-pca953x) move header to linux/platform_data/ This patch moves the pca953x.h header from include/linux/i2c to include/linux/platform_data and updates existing support accordingly. Acked-by: Linus Walleij Acked-by: H Hartley Sweeten Signed-off-by: Vivien Didelot Signed-off-by: Olof Johansson --- include/linux/i2c/pca953x.h | 30 ------------------------------ include/linux/platform_data/pca953x.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 30 deletions(-) delete mode 100644 include/linux/i2c/pca953x.h create mode 100644 include/linux/platform_data/pca953x.h (limited to 'include/linux') diff --git a/include/linux/i2c/pca953x.h b/include/linux/i2c/pca953x.h deleted file mode 100644 index 3c98dd4f901f..000000000000 --- a/include/linux/i2c/pca953x.h +++ /dev/null @@ -1,30 +0,0 @@ -#ifndef _LINUX_PCA953X_H -#define _LINUX_PCA953X_H - -#include -#include - -/* platform data for the PCA9539 16-bit I/O expander driver */ - -struct pca953x_platform_data { - /* number of the first GPIO */ - unsigned gpio_base; - - /* initial polarity inversion setting */ - u32 invert; - - /* interrupt base */ - int irq_base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - const char *const *names; -}; - -#endif /* _LINUX_PCA953X_H */ diff --git a/include/linux/platform_data/pca953x.h b/include/linux/platform_data/pca953x.h new file mode 100644 index 000000000000..3c98dd4f901f --- /dev/null +++ b/include/linux/platform_data/pca953x.h @@ -0,0 +1,30 @@ +#ifndef _LINUX_PCA953X_H +#define _LINUX_PCA953X_H + +#include +#include + +/* platform data for the PCA9539 16-bit I/O expander driver */ + +struct pca953x_platform_data { + /* number of the first GPIO */ + unsigned gpio_base; + + /* initial polarity inversion setting */ + u32 invert; + + /* interrupt base */ + int irq_base; + + void *context; /* param to setup/teardown */ + + int (*setup)(struct i2c_client *client, + unsigned gpio, unsigned ngpio, + void *context); + int (*teardown)(struct i2c_client *client, + unsigned gpio, unsigned ngpio, + void *context); + const char *const *names; +}; + +#endif /* _LINUX_PCA953X_H */ -- cgit v1.2.3 From 5e33bc4165f3edd558d9633002465a95230effc1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 28 Aug 2013 21:41:01 +0200 Subject: driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu Reported-and-tested-by: Gu Zheng Suggested-by: Tejun Heo Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Toshi Kani --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..545a04285120 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -895,6 +895,7 @@ static inline bool device_supports_offline(struct device *dev) extern void lock_device_hotplug(void); extern void unlock_device_hotplug(void); +extern int lock_device_hotplug_sysfs(void); extern int device_offline(struct device *dev); extern int device_online(struct device *dev); /* -- cgit v1.2.3 From 5d261913ca3daf6c2d21d38924235667b3d07c40 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 28 Aug 2013 23:25:05 +0200 Subject: net: add lower_dev_list to net_device and make a full mesh This patch adds lower_dev_list list_head to net_device, which is the same as upper_dev_list, only for lower devices, and begins to use it in the same way as the upper list. It also changes the way the whole adjacent device lists work - now they contain *all* of upper/lower devices, not only the first level. The first level devices are distinguished by the bool neighbour field in netdev_adjacent, also added by this patch. There are cases when a device can be added several times to the adjacent list, the simplest would be: /---- eth0.10 ---\ eth0- --- bond0 \---- eth0.20 ---/ where both bond0 and eth0 'see' each other in the adjacent lists two times. To avoid duplication of netdev_adjacent structures ref_nr is being kept as the number of times the device was added to the list. The 'full view' is achieved by adding, on link creation, all of the upper_dev's upper_dev_list devices as upper devices to all of the lower_dev's lower_dev_list devices (and to the lower_dev itself), and vice versa. On unlink they are removed using the same logic. I've tested it with thousands vlans/bonds/bridges, everything works ok and no observable lags even on a huge number of interfaces. Memory footprint for 128 devices interconnected with each other via both upper and lower (which is impossible, but for the comparison) lists would be: 128*128*2*sizeof(netdev_adjacent) = 1.5MB but in the real world we usualy have at most several devices with slaves and a lot of vlans, so the footprint will be much lower. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Alexander Duyck CC: Cong Wang Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 077363dcd860..5ccf5b73c378 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1125,6 +1125,7 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; struct list_head upper_dev_list; /* List of upper devices */ + struct list_head lower_dev_list; /* currently active device features */ -- cgit v1.2.3 From 8b5be8561b804edf6b58fc27edbccf1d45863e08 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 28 Aug 2013 23:25:08 +0200 Subject: net: add netdev_for_each_upper_dev_rcu() The new macro netdev_for_each_upper_dev_rcu(dev, upper, iter) iterates through the dev->upper_dev_list starting from the first element, using the netdev_upper_get_next_dev_rcu(dev, &iter). Must be called under RCU read lock. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Alexander Duyck CC: Cong Wang Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ccf5b73c378..3ad49b833eab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2768,6 +2768,16 @@ extern int bpf_jit_enable; extern bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); extern bool netdev_has_any_upper_dev(struct net_device *dev); +extern struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); + +/* iterate through upper list, must be called under RCU read lock */ +#define netdev_for_each_upper_dev_rcu(dev, upper, iter) \ + for (iter = &(dev)->upper_dev_list, \ + upper = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ + upper; \ + upper = netdev_upper_get_next_dev_rcu(dev, &(iter))) + extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev); extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); extern int netdev_upper_dev_link(struct net_device *dev, -- cgit v1.2.3 From 035fd9482274bf43858b00e0ff95179af66df8e8 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 14 Aug 2013 15:27:10 -0600 Subject: of: introduce of_parse_phandle_with_fixed_args This is identical to of_parse_phandle_with_args(), except that the number of argument cells is fixed, rather than being parsed out of the node referenced by each phandle. Signed-off-by: Stephen Warren Acked-by: Mark Rutland Signed-off-by: Grant Likely --- include/linux/of.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 90a8811e9e48..87d08306fef4 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -280,6 +280,9 @@ extern struct device_node *of_parse_phandle(const struct device_node *np, extern int of_parse_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name, int index, struct of_phandle_args *out_args); +extern int of_parse_phandle_with_fixed_args(const struct device_node *np, + const char *list_name, int cells_count, int index, + struct of_phandle_args *out_args); extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); @@ -477,6 +480,13 @@ static inline int of_parse_phandle_with_args(struct device_node *np, return -ENOSYS; } +static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, + const char *list_name, int cells_count, int index, + struct of_phandle_args *out_args) +{ + return -ENOSYS; +} + static inline int of_count_phandle_with_args(struct device_node *np, const char *list_name, const char *cells_name) -- cgit v1.2.3 From 9120c0bea999cc26c3493486828d34138a7ac901 Mon Sep 17 00:00:00 2001 From: Josh Wu Date: Tue, 27 Aug 2013 12:28:00 +0100 Subject: iio: at91: Use different prescal, startup mask in MR for different IP For at91 boards, there are different IPs for adc. Different IPs has different STARTUP & PRESCAL mask in ADC_MR. Signed-off-by: Josh Wu Acked-by: Maxime Ripard Signed-off-by: Jonathan Cameron --- include/linux/platform_data/at91_adc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/at91_adc.h b/include/linux/platform_data/at91_adc.h index e15745b4f3a5..b3ca1e94e0c8 100644 --- a/include/linux/platform_data/at91_adc.h +++ b/include/linux/platform_data/at91_adc.h @@ -14,12 +14,16 @@ (Interruptions registers mostly) * @status_register: Offset of the Interrupt Status Register * @trigger_register: Offset of the Trigger setup register + * @mr_prescal_mask: Mask of the PRESCAL field in the adc MR register + * @mr_startup_mask: Mask of the STARTUP field in the adc MR register */ struct at91_adc_reg_desc { u8 channel_base; u32 drdy_mask; u8 status_register; u8 trigger_register; + u32 mr_prescal_mask; + u32 mr_startup_mask; }; /** -- cgit v1.2.3 From f97c43bbdf8a1ea42477b1a804a48e7e368cb13c Mon Sep 17 00:00:00 2001 From: Kyle McMartin Date: Tue, 27 Aug 2013 12:52:34 -0600 Subject: tegra-cpuidle: provide stub when !CONFIG_CPU_IDLE While poking at something using the for-3.12/* trees, I hit the following compile error: drivers/built-in.o: In function `tegra_pcie_map_irq': /builddir/build/BUILD/kernel-3.10.fc20/linux-3.11.0-0.rc6.git4.1.fc20.armv7hl/drivers/pci/host/pci-tegra.c:640: undefined reference to `tegra_cpuidle_pcie_irqs_in_use' drivers/built-in.o: In function `tegra_msi_map': /builddir/build/BUILD/kernel-3.10.fc20/linux-3.11.0-0.rc6.git4.1.fc20.armv7hl/drivers/pci/host/pci-tegra.c:1227: undefined reference to `tegra_cpuidle_pcie_irqs_in_use' make: *** [vmlinux] Error 1 Since our .config had CONFIG_CPU_IDLE off. We should probably provide an empty function to handle this to avoid cluttering up pci-tegra.c with conditionals. Signed-off-by: Kyle McMartin Reviewed-by: Thierry Reding [swarren, removed unnecessary return statement] Signed-off-by: Stephen Warren Signed-off-by: Olof Johansson --- include/linux/tegra-cpuidle.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tegra-cpuidle.h b/include/linux/tegra-cpuidle.h index dda3647242a4..9c6286bbf662 100644 --- a/include/linux/tegra-cpuidle.h +++ b/include/linux/tegra-cpuidle.h @@ -14,6 +14,12 @@ #ifndef __LINUX_TEGRA_CPUIDLE_H__ #define __LINUX_TEGRA_CPUIDLE_H__ +#ifdef CONFIG_CPU_IDLE void tegra_cpuidle_pcie_irqs_in_use(void); +#else +static inline void tegra_cpuidle_pcie_irqs_in_use(void) +{ +} +#endif #endif -- cgit v1.2.3 From a5ad3dcf358475dfc5ccf11e28d3822fc3c8e5fe Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:58:56 +0100 Subject: video/hdmi: Don't let the user of this API create invalid infoframes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To set the active aspect ratio value in the AVI infoframe today, you not only have to set the active_aspect field, but also the active_info_valid bit. Out of the 1 user of this API, we had 100% misuse, forgetting the _valid bit. This was fixed in: Author: Damien Lespiau Date: Tue Aug 6 20:32:17 2013 +0100 drm: Don't generate invalid AVI infoframes for CEA modes We can do better and derive the _valid bit from the user wanting to set the active aspect ratio. v2: Fix multi-lines comment style (Thierry Reding) Signed-off-by: Damien Lespiau Reviewed-by: Ville Syrjälä Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index bc6743e76e37..931474c60b71 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -109,7 +109,6 @@ struct hdmi_avi_infoframe { unsigned char version; unsigned char length; enum hdmi_colorspace colorspace; - bool active_info_valid; bool horizontal_bar_valid; bool vertical_bar_valid; enum hdmi_scan_mode scan_mode; -- cgit v1.2.3 From 974e0701c5251de879624d166890fbd0ee9fc429 Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:58:57 +0100 Subject: video/hdmi: Derive the bar data valid bit from the bar data fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just like: Author: Damien Lespiau Date: Mon Aug 12 11:53:24 2013 +0100 video/hdmi: Don't let the user of this API create invalid infoframes But this time for the horizontal/vertical bar data present bits. Signed-off-by: Damien Lespiau Reviewed-by: Ville Syrjälä Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 931474c60b71..b98340b82e05 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -109,8 +109,6 @@ struct hdmi_avi_infoframe { unsigned char version; unsigned char length; enum hdmi_colorspace colorspace; - bool horizontal_bar_valid; - bool vertical_bar_valid; enum hdmi_scan_mode scan_mode; enum hdmi_colorimetry colorimetry; enum hdmi_picture_aspect picture_aspect; -- cgit v1.2.3 From 7d27becb3532d881378846e72864031977be511a Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:58:58 +0100 Subject: video/hdmi: Introduce helpers for the HDMI vendor specific infoframe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide the same programming model than the other infoframe types. The generic _pack() function can't handle those yet as we need to move the vendor OUI in the generic hdmi_vendor_infoframe structure to know which kind of vendor infoframe we are dealing with. v2: Fix the value of Side-by-side (half), hmdi typo, pack 3D_Ext_Data (Ville Syrjälä) v3: Future proof the sending of 3D_Ext_Data (Ville Syrjälä), Fix multi-lines comment style (Thierry Reding) Signed-off-by: Damien Lespiau Reviewed-by: Ville Syrjälä Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index b98340b82e05..e733252c2b5d 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -234,11 +234,37 @@ struct hdmi_vendor_infoframe { ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, void *buffer, size_t size); +enum hdmi_3d_structure { + HDMI_3D_STRUCTURE_INVALID = -1, + HDMI_3D_STRUCTURE_FRAME_PACKING = 0, + HDMI_3D_STRUCTURE_FIELD_ALTERNATIVE, + HDMI_3D_STRUCTURE_LINE_ALTERNATIVE, + HDMI_3D_STRUCTURE_SIDE_BY_SIDE_FULL, + HDMI_3D_STRUCTURE_L_DEPTH, + HDMI_3D_STRUCTURE_L_DEPTH_GFX_GFX_DEPTH, + HDMI_3D_STRUCTURE_TOP_AND_BOTTOM, + HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF = 8, +}; + +struct hdmi_hdmi_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + u8 vic; + enum hdmi_3d_structure s3d_struct; + unsigned int s3d_ext_data; +}; + +int hdmi_hdmi_infoframe_init(struct hdmi_hdmi_infoframe *frame); +ssize_t hdmi_hdmi_infoframe_pack(struct hdmi_hdmi_infoframe *frame, + void *buffer, size_t size); + union hdmi_infoframe { struct hdmi_any_infoframe any; struct hdmi_avi_infoframe avi; struct hdmi_spd_infoframe spd; struct hdmi_vendor_infoframe vendor; + struct hdmi_hdmi_infoframe hdmi; struct hdmi_audio_infoframe audio; }; -- cgit v1.2.3 From c782d2e73d1e69c863d03945907bc7fbc879a778 Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:59:00 +0100 Subject: drm/edid: Move HDMI_IDENTIFIER to hdmi.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We'll need the HDMI OUI for the HDMI vendor infoframe data, so let's move the DRM one to hdmi.h, might as well use the hdmi header to store some hdmi defines. (Note that, in fact, infoframes are part of the CEA-861 standard, and only the HDMI vendor specific infoframe is special to HDMI, but details..) Signed-off-by: Damien Lespiau Reviewed-by: Ville Syrjälä Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index e733252c2b5d..37e0cd755284 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -18,6 +18,7 @@ enum hdmi_infoframe_type { HDMI_INFOFRAME_TYPE_AUDIO = 0x84, }; +#define HDMI_IDENTIFIER 0x000c03 #define HDMI_INFOFRAME_HEADER_SIZE 4 #define HDMI_AVI_INFOFRAME_SIZE 13 #define HDMI_SPD_INFOFRAME_SIZE 25 -- cgit v1.2.3 From af3e95b40720cdf301eb85387c0a3dc4067cc551 Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:59:01 +0100 Subject: video/hdmi: Hook the HDMI vendor infoframe with the generic _pack() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With this last bit, hdmi_infoframe_pack() is now able to pack any infoframe we support. At the same time, because it's impractical to make two commits out of this, we get rid of the version that encourages the open coding of the vendor infoframe packing. We can do so because the only user of this API has been ported in: Author: Damien Lespiau Date: Mon Aug 12 18:08:37 2013 +0100 gpu: host1x: Port the HDMI vendor infoframe code the common helpers v2: Change oui to be an unsigned int (Ville Syrjälä) Signed-off-by: Damien Lespiau Reviewed-by: Ville Syrjälä Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 37e0cd755284..e24d850a8ee6 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -225,16 +225,6 @@ int hdmi_audio_infoframe_init(struct hdmi_audio_infoframe *frame); ssize_t hdmi_audio_infoframe_pack(struct hdmi_audio_infoframe *frame, void *buffer, size_t size); -struct hdmi_vendor_infoframe { - enum hdmi_infoframe_type type; - unsigned char version; - unsigned char length; - u8 data[27]; -}; - -ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, - void *buffer, size_t size); - enum hdmi_3d_structure { HDMI_3D_STRUCTURE_INVALID = -1, HDMI_3D_STRUCTURE_FRAME_PACKING = 0, @@ -251,6 +241,7 @@ struct hdmi_hdmi_infoframe { enum hdmi_infoframe_type type; unsigned char version; unsigned char length; + unsigned int oui; u8 vic; enum hdmi_3d_structure s3d_struct; unsigned int s3d_ext_data; @@ -260,12 +251,21 @@ int hdmi_hdmi_infoframe_init(struct hdmi_hdmi_infoframe *frame); ssize_t hdmi_hdmi_infoframe_pack(struct hdmi_hdmi_infoframe *frame, void *buffer, size_t size); +union hdmi_vendor_infoframe { + struct { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + unsigned int oui; + } any; + struct hdmi_hdmi_infoframe hdmi; +}; + union hdmi_infoframe { struct hdmi_any_infoframe any; struct hdmi_avi_infoframe avi; struct hdmi_spd_infoframe spd; - struct hdmi_vendor_infoframe vendor; - struct hdmi_hdmi_infoframe hdmi; + union hdmi_vendor_infoframe vendor; struct hdmi_audio_infoframe audio; }; -- cgit v1.2.3 From ae84b900b009589a7017a1f8f060edd7de501642 Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:59:02 +0100 Subject: video/hdmi: Use hdmi_vendor_infoframe for the HDMI specific infoframe We just got rid of the version of hdmi_vendor_infoframe that had a byte array for anyone to poke at. It's now time to shuffle around the naming of hdmi_hdmi_infoframe to make hdmi_vendor_infoframe become the HDMI vendor specific structure. Cc: Thierry Reding Signed-off-by: Damien Lespiau Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index e24d850a8ee6..d4ae12c7931b 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -237,7 +237,8 @@ enum hdmi_3d_structure { HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF = 8, }; -struct hdmi_hdmi_infoframe { + +struct hdmi_vendor_infoframe { enum hdmi_infoframe_type type; unsigned char version; unsigned char length; @@ -247,25 +248,25 @@ struct hdmi_hdmi_infoframe { unsigned int s3d_ext_data; }; -int hdmi_hdmi_infoframe_init(struct hdmi_hdmi_infoframe *frame); -ssize_t hdmi_hdmi_infoframe_pack(struct hdmi_hdmi_infoframe *frame, - void *buffer, size_t size); +int hdmi_vendor_infoframe_init(struct hdmi_vendor_infoframe *frame); +ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, + void *buffer, size_t size); -union hdmi_vendor_infoframe { +union hdmi_vendor_any_infoframe { struct { enum hdmi_infoframe_type type; unsigned char version; unsigned char length; unsigned int oui; } any; - struct hdmi_hdmi_infoframe hdmi; + struct hdmi_vendor_infoframe hdmi; }; union hdmi_infoframe { struct hdmi_any_infoframe any; struct hdmi_avi_infoframe avi; struct hdmi_spd_infoframe spd; - union hdmi_vendor_infoframe vendor; + union hdmi_vendor_any_infoframe vendor; struct hdmi_audio_infoframe audio; }; -- cgit v1.2.3 From 6cb3b7f1c013fd4bea41e16ee557bcb2f1561787 Mon Sep 17 00:00:00 2001 From: "Lespiau, Damien" Date: Mon, 19 Aug 2013 16:59:05 +0100 Subject: video/hdmi: Rename HDMI_IDENTIFIER to HDMI_IEEE_OUI HDMI_IDENTIFIER was felt too generic, rename it to what it is, the IEEE OUI corresponding to HDMI Licensing, LLC. http://standards.ieee.org/develop/regauth/oui/oui.txt Cc: Thierry Reding Signed-off-by: Damien Lespiau Reviewed-by: Thierry Reding Signed-off-by: Dave Airlie --- include/linux/hdmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index d4ae12c7931b..9231be9e90a2 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -18,7 +18,7 @@ enum hdmi_infoframe_type { HDMI_INFOFRAME_TYPE_AUDIO = 0x84, }; -#define HDMI_IDENTIFIER 0x000c03 +#define HDMI_IEEE_OUI 0x000c03 #define HDMI_INFOFRAME_HEADER_SIZE 4 #define HDMI_AVI_INFOFRAME_SIZE 13 #define HDMI_SPD_INFOFRAME_SIZE 25 -- cgit v1.2.3 From ede23fa8161c1a04aa1b3bf5447812ca14b3fef1 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 26 Aug 2013 22:45:23 -0700 Subject: drivers:net: Convert dma_alloc_coherent(...__GFP_ZERO) to dma_zalloc_coherent __GFP_ZERO is an uncommon flag and perhaps is better not used. static inline dma_zalloc_coherent exists so convert the uses of dma_alloc_coherent with __GFP_ZERO to the more common kernel style with zalloc. Remove memset from the static inline dma_zalloc_coherent and add just one use of __GFP_ZERO instead. Trivially reduces the size of the existing uses of dma_zalloc_coherent. Realign arguments as appropriate. Signed-off-by: Joe Perches Acked-by: Neil Horman Acked-by: Jesse Brandeburg Acked-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/dma-mapping.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 94af41858513..3a8d0a2af607 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -132,9 +132,8 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) static inline void *dma_zalloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { - void *ret = dma_alloc_coherent(dev, size, dma_handle, flag); - if (ret) - memset(ret, 0, size); + void *ret = dma_alloc_coherent(dev, size, dma_handle, + flag | __GFP_ZERO); return ret; } -- cgit v1.2.3 From 84d72f9cc21d6e41c620dd34b8248734cd02d995 Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Wed, 21 Aug 2013 09:46:25 +0800 Subject: mfd: mmc: rtsx: Change default tx phase The default phase can meet most cards' requirement, but it is not the optimal one. In some extreme situation, the rx phase point produced by the following tuning process will drift quite a distance. Before tuning UHS card, this patch will set a more proper initial tx phase point, which is calculated from statistic data, and can achieve a much better tx signal quality. Signed-off-by: Wei WANG Acked-by: Lee Jones Acked-by: Chris Ball Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index daefca1bafb3..d1382dfbeff0 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -847,6 +847,9 @@ struct rtsx_pcr { #define PCR_REVERSE_SOCKET (1 << 1) u32 flags; + u32 tx_initial_phase; + u32 rx_initial_phase; + const u32 *sd_pull_ctl_enable_tbl; const u32 *sd_pull_ctl_disable_tbl; const u32 *ms_pull_ctl_enable_tbl; @@ -863,6 +866,18 @@ struct rtsx_pcr { #define PCI_VID(pcr) ((pcr)->pci->vendor) #define PCI_PID(pcr) ((pcr)->pci->device) +#define SDR104_PHASE(val) ((val) & 0xFF) +#define SDR50_PHASE(val) (((val) >> 8) & 0xFF) +#define DDR50_PHASE(val) (((val) >> 16) & 0xFF) +#define SDR104_TX_PHASE(pcr) SDR104_PHASE((pcr)->tx_initial_phase) +#define SDR50_TX_PHASE(pcr) SDR50_PHASE((pcr)->tx_initial_phase) +#define DDR50_TX_PHASE(pcr) DDR50_PHASE((pcr)->tx_initial_phase) +#define SDR104_RX_PHASE(pcr) SDR104_PHASE((pcr)->rx_initial_phase) +#define SDR50_RX_PHASE(pcr) SDR50_PHASE((pcr)->rx_initial_phase) +#define DDR50_RX_PHASE(pcr) DDR50_PHASE((pcr)->rx_initial_phase) +#define SET_CLOCK_PHASE(sdr104, sdr50, ddr50) \ + (((ddr50) << 16) | ((sdr50) << 8) | (sdr104)) + void rtsx_pci_start_run(struct rtsx_pcr *pcr); int rtsx_pci_write_register(struct rtsx_pcr *pcr, u16 addr, u8 mask, u8 data); int rtsx_pci_read_register(struct rtsx_pcr *pcr, u16 addr, u8 *data); -- cgit v1.2.3 From 1dada8e1f94e863a94f6622f0ddb5d1b01420150 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Aug 2013 19:58:45 -0400 Subject: SUNRPC: Remove unused struct rpc_clnt field cl_protname Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index bfe11be81f6f..481f9c07631e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -41,7 +41,6 @@ struct rpc_clnt { cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ - const char * cl_protname; /* protocol name */ struct rpc_auth * cl_auth; /* authenticator */ struct rpc_stat * cl_stats; /* per-program statistics */ struct rpc_iostats * cl_metrics; /* per-client statistics */ -- cgit v1.2.3 From c2190661039b3817b4cc1cbfea620b3f7dbe5cd8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Aug 2013 19:23:04 -0400 Subject: SUNRPC: Replace clnt->cl_principal The clnt->cl_principal is being used exclusively to store the service target name for RPCSEC_GSS/krb5 callbacks. Replace it with something that is stored only in the RPCSEC_GSS-specific code. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 10 ++++++++-- include/linux/sunrpc/clnt.h | 1 - 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 0dd00f4f6810..a9ab577b0c4a 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -87,6 +87,11 @@ struct rpc_auth { /* per-flavor data */ }; +struct rpc_auth_create_args { + rpc_authflavor_t pseudoflavor; + const char *target_name; +}; + /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ @@ -97,7 +102,7 @@ struct rpc_authops { struct module *owner; rpc_authflavor_t au_flavor; /* flavor (RPC_AUTH_*) */ char * au_name; - struct rpc_auth * (*create)(struct rpc_clnt *, rpc_authflavor_t); + struct rpc_auth * (*create)(struct rpc_auth_create_args *, struct rpc_clnt *); void (*destroy)(struct rpc_auth *); struct rpc_cred * (*lookup_cred)(struct rpc_auth *, struct auth_cred *, int); @@ -140,7 +145,8 @@ struct rpc_cred * rpc_lookup_cred(void); struct rpc_cred * rpc_lookup_machine_cred(const char *service_name); int rpcauth_register(const struct rpc_authops *); int rpcauth_unregister(const struct rpc_authops *); -struct rpc_auth * rpcauth_create(rpc_authflavor_t, struct rpc_clnt *); +struct rpc_auth * rpcauth_create(struct rpc_auth_create_args *, + struct rpc_clnt *); void rpcauth_release(struct rpc_auth *); rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t, struct rpcsec_gss_info *); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 481f9c07631e..b93b4aa49ffd 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -60,7 +60,6 @@ struct rpc_clnt { struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; const struct rpc_program *cl_program; - char *cl_principal; /* target to authenticate to */ }; /* -- cgit v1.2.3 From 6739ffb754b47e6c0fa9d9e268bde828f6856528 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Aug 2013 15:38:11 -0400 Subject: SUNRPC: Add a framework to clean up management of rpc_pipefs directories The current system requires everyone to set up notifiers, manage directory locking, etc. What we really want to do is have the rpc_client create its directory, and then create all the entries. This patch will allow the RPCSEC_GSS and NFS code to register all the objects that they want to have appear in the directory, and then have the sunrpc code call them back to actually create/destroy their pipefs dentries when the rpc_client creates/destroys the parent. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ include/linux/sunrpc/rpc_pipe_fs.h | 33 ++++++++++++++++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b93b4aa49ffd..0dccd01ae2de 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -55,6 +56,7 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; + struct rpc_pipe_dir_head cl_pipedir_objects; struct dentry * cl_dentry; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index aa5b582cc471..188e7fca67e1 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -5,6 +5,26 @@ #include +struct rpc_pipe_dir_head { + struct list_head pdh_entries; + struct dentry *pdh_dentry; +}; + +struct rpc_pipe_dir_object_ops; +struct rpc_pipe_dir_object { + struct list_head pdo_head; + const struct rpc_pipe_dir_object_ops *pdo_ops; + + void *pdo_data; +}; + +struct rpc_pipe_dir_object_ops { + int (*create)(struct dentry *dir, + struct rpc_pipe_dir_object *pdo); + void (*destroy)(struct dentry *dir, + struct rpc_pipe_dir_object *pdo); +}; + struct rpc_pipe_msg { struct list_head list; void *data; @@ -74,7 +94,18 @@ extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *); struct rpc_clnt; extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); -extern int rpc_remove_client_dir(struct dentry *); +extern int rpc_remove_client_dir(struct dentry *, struct rpc_clnt *); + +extern void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh); +extern void rpc_init_pipe_dir_object(struct rpc_pipe_dir_object *pdo, + const struct rpc_pipe_dir_object_ops *pdo_ops, + void *pdo_data); +extern int rpc_add_pipe_dir_object(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo); +extern void rpc_remove_pipe_dir_object(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo); struct cache_detail; extern struct dentry *rpc_create_cache_dir(struct dentry *, -- cgit v1.2.3 From 6290d60656e9f4f5a0071bafa798370ab35978a0 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Fri, 30 Aug 2013 18:06:06 +0800 Subject: regulator: tps65217: Convert to use linear ranges Below is the equation in original code: tps65217_uv1_ranges: 0 ... 24: uV = vsel * 25000 + 900000; 25 ... 52: uV = (vsel - 24) * 50000 + 1500000; = (vsel - 25) * 50000 + 1550000; 53 ... 55: uV = (vsel - 52) * 100000 + 2900000; = (vsel - 53) * 100000 + 3000000; 56 ... 62: uV = 3300000; tps65217_uv2_ranges: 0 ... 8: uV = vsel * 50000 + 1500000; 9 ... 13: uV = (vsel - 8) * 100000 + 1900000; = (vsel - 9) * 100000 + 2000000; 14 ... 31: uV = (vsel - 13) * 50000 + 2400000; = (vsel - 14) * 50000 + 2450000; The voltage tables are composed of linear ranges. This patch converts this driver to use multiple linear ranges APIs. In original code, voltage range for DCDC1 is 900000 ~ 1800000 and voltage range for DCDC3 is 900000 ~ 1500000. This patch separates the range 25~52 in tps65217_uv1_ranges table to two linear ranges: 25~30 and 31~52. This change makes it possible to reuse the same linear_ranges table for DCDCx. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/mfd/tps65217.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 29eab2bd3dfa..a5a7f0130e96 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -243,24 +243,6 @@ struct tps65217_board { struct tps65217_bl_pdata *bl_pdata; }; -/** - * struct tps_info - packages regulator constraints - * @name: Voltage regulator name - * @min_uV: minimum micro volts - * @max_uV: minimum micro volts - * @vsel_to_uv: Function pointer to get voltage from selector - * @uv_to_vsel: Function pointer to get selector from voltage - * - * This data is used to check the regualtor voltage limits while setting. - */ -struct tps_info { - const char *name; - int min_uV; - int max_uV; - int (*vsel_to_uv)(unsigned int vsel); - int (*uv_to_vsel)(int uV, unsigned int *vsel); -}; - /** * struct tps65217 - tps65217 sub-driver chip access routines * @@ -273,7 +255,6 @@ struct tps65217 { unsigned int id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regulator_dev *rdev[TPS65217_NUM_REGULATOR]; - struct tps_info *info[TPS65217_NUM_REGULATOR]; struct regmap *regmap; }; -- cgit v1.2.3 From b32843b772db6024336e36c39359d8edc3b416ab Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 30 Jul 2013 17:52:59 -0700 Subject: mtd: nand: hide in-memory BBT implementation details nand_base.c shouldn't have to know the implementation details of nand_bbt's in-memory BBT. Specifically, nand_base shouldn't perform the bit masking and shifting to isolate a BBT entry. Instead, just move some of the BBT code into a new nand_markbad_bbt() interface. This interface allows external users (i.e., nand_base) to mark a single block as bad in the BBT. Then nand_bbt will take care of modifying the in-memory BBT and updating the flash-based BBT (if applicable). Signed-off-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0745a42f1acd..9f7b248c70fe 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -628,8 +628,8 @@ extern struct nand_flash_dev nand_flash_ids[]; extern struct nand_manufacturers nand_manuf_ids[]; extern int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd); -extern int nand_update_bbt(struct mtd_info *mtd, loff_t offs); extern int nand_default_bbt(struct mtd_info *mtd); +extern int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); extern int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); extern int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, int allowbbt); -- cgit v1.2.3 From dad2256269cb2ee3a72baefc5eb6e02ae1de2cfe Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 30 Jul 2013 17:53:00 -0700 Subject: mtd: nand: remove NAND_BBT_SCANEMPTY NAND_BBT_SCANEMPTY is a strange, badly-supported option with omap as its single remaining user. NAND_BBT_SCANEMPTY was likely used by accident in omap2[1]. And anyway, omap2 doesn't scan the chip for bad blocks (courtesy of NAND_SKIP_BBTSCAN), and so its use of this option is irrelevant. This patch drops the NAND_BBT_SCANEMPTY option. [1] http://lists.infradead.org/pipermail/linux-mtd/2012-July/042902.html Signed-off-by: Brian Norris Cc: Ivan Djelic Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/bbm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 211ff67e8b0d..95fc482cef36 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -93,8 +93,6 @@ struct nand_bbt_descr { #define NAND_BBT_CREATE_EMPTY 0x00000400 /* Search good / bad pattern through all pages of a block */ #define NAND_BBT_SCANALLPAGES 0x00000800 -/* Scan block empty during good / bad block scan */ -#define NAND_BBT_SCANEMPTY 0x00001000 /* Write bbt if neccecary */ #define NAND_BBT_WRITE 0x00002000 /* Read and write back block contents when writing bbt */ -- cgit v1.2.3 From 9d8924297cd9c256c23c02abae40202563452453 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 30 Aug 2013 10:46:00 -0400 Subject: USB: fix build error when CONFIG_PM_SLEEP isn't enabled This patch fixes a build error that occurs when CONFIG_PM is enabled and CONFIG_PM_SLEEP isn't: >> drivers/usb/host/ohci-pci.c:294:10: error: 'usb_hcd_pci_pm_ops' undeclared here (not in a function) .pm = &usb_hcd_pci_pm_ops Since the usb_hcd_pci_pm_ops structure is defined and used when CONFIG_PM is enabled, its declaration should not be protected by CONFIG_PM_SLEEP. Signed-off-by: Alan Stern Reported-by: kbuild test robot CC: Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a9c7d44bd2ed..75efc45eaa2f 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -428,7 +428,7 @@ extern int usb_hcd_pci_probe(struct pci_dev *dev, extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif #endif /* CONFIG_PCI */ -- cgit v1.2.3 From 4cfeca2d58de8292f45351f84e84f657222a4611 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 17 May 2013 11:17:25 +0800 Subject: mtd: add datasheet's ECC information to nand_chip{} 1.) Why add the ECC information to the nand_chip{} ? Each nand chip has its requirement for the ECC correctability, such as "4bit ECC for each 512Byte" or "40bit ECC for each 1024Byte". This ECC info is very important to the nand controller, such as gpmi. Take the Micron MT29F64G08CBABA for example, its geometry is 8KiB page size, 744 bytes oob size and it requires 40bit ECC per 1KiB. If we do not provide the ECC info to the gpmi nand driver, it has to calculate the ECC correctability itself. The gpmi driver will gets the 56bit ECC for per 1KiB which is beyond its BCH's 40bit ecc capibility. The gpmi will quits in this case. But in actually, the gpmi can supports this nand chip if it can get the right ECC info. 2.) about the new fields. The @ecc_strength_ds stands for the ecc bits needed within the @ecc_step_ds. The two fields should be set from the nand chip's datasheets. For example: "4bit ECC for each 512Byte" could be: @ecc_strength_ds = 4, @ecc_step_ds = 512. "40bit ECC for each 1024Byte" could be: @ecc_strength_ds = 40, @ecc_step_ds = 1024. 3.) Why do not re-use the @strength and @size in the nand_ecc_ctrl{}? The @strength and @size in nand_ecc_ctrl{} is used by the nand controller driver, while the @ecc_strength_ds and @ecc_step_ds are get from the datasheet. Signed-off-by: Huang Shijie Reviewed-and-tested-by: Brian Norris Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9f7b248c70fe..fbf3bba37272 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -437,6 +437,12 @@ struct nand_buffers { * bad block marker position; i.e., BBM == 11110111b is * not bad when badblockbits == 7 * @cellinfo: [INTERN] MLC/multichip data from chip ident + * @ecc_strength_ds: [INTERN] ECC correctability from the datasheet. + * Minimum amount of bit errors per @ecc_step_ds guaranteed + * to be correctable. If unknown, set to zero. + * @ecc_step_ds: [INTERN] ECC step required by the @ecc_strength_ds, + * also from the datasheet. It is the recommended ECC step + * size, if known; if unknown, set to zero. * @numchips: [INTERN] number of physical chips * @chipsize: [INTERN] the size of one chip for multichip arrays * @pagemask: [INTERN] page number mask = number of (pages / chip) - 1 @@ -513,6 +519,8 @@ struct nand_chip { unsigned int pagebuf_bitflips; int subpagesize; uint8_t cellinfo; + uint16_t ecc_strength_ds; + uint16_t ecc_step_ds; int badblockpos; int badblockbits; -- cgit v1.2.3 From 5138a98f6f47ce62a86cce4b9c381aaf4ad3a643 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 17 May 2013 11:17:27 +0800 Subject: mtd: add data structures for Extended Parameter Page Since the ONFI 2.1, the onfi spec adds the Extended Parameter Page to store the ECC info. The onfi spec tells us that if the nand chip's recommended ECC codeword size is not 512 bytes, then the @ecc_bits is 0xff. The host _SHOULD_ then read the Extended ECC information that is part of the extended parameter page to retrieve the ECC requirements for this device. This patch adds [1] the neccessary fields for nand_onfi_params{}, [2] and adds the onfi_ext_ecc_info{} for Extended ECC information, [3] adds onfi_ext_section{} for extended sections, [4] and adds onfi_ext_param_page{} for the Extended Parameter Page. Acked-by: Pekon Gupta Signed-off-by: Huang Shijie Reviewed-and-tested-by: Brian Norris [Brian: amended for checkpatch.pl] Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index fbf3bba37272..01a7f3c71bd0 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -227,7 +227,10 @@ struct nand_onfi_params { __le16 revision; __le16 features; __le16 opt_cmd; - u8 reserved[22]; + u8 reserved0[2]; + __le16 ext_param_page_length; /* since ONFI 2.1 */ + u8 num_of_param_pages; /* since ONFI 2.1 */ + u8 reserved1[17]; /* manufacturer information block */ char manufacturer[12]; @@ -284,6 +287,40 @@ struct nand_onfi_params { #define ONFI_CRC_BASE 0x4F4E +/* Extended ECC information Block Definition (since ONFI 2.1) */ +struct onfi_ext_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ +#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ +#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ +struct onfi_ext_section { + u8 type; + u8 length; +} __packed; + +#define ONFI_EXT_SECTION_MAX 8 + +/* Extended Parameter Page Definition (since ONFI 2.1) */ +struct onfi_ext_param_page { + __le16 crc; + u8 sig[4]; /* 'E' 'P' 'P' 'S' */ + u8 reserved0[10]; + struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; + + /* + * The actual size of the Extended Parameter Page is in + * @ext_param_page_length of nand_onfi_params{}. + * The following are the variable length sections. + * So we do not add any fields below. Please see the ONFI spec. + */ +} __packed; + /** * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices * @lock: protection lock -- cgit v1.2.3 From 5b40db68cb1bd14b3d5b159754c9c1bc3bdeb080 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 17 May 2013 11:17:28 +0800 Subject: mtd: add a helper to get the supported features for ONFI nand add a helper to get the supported features for ONFI nand. Also add the neccessary macros. Signed-off-by: Huang Shijie Reviewed-and-tested-by: Brian Norris Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 01a7f3c71bd0..bf4c566f0647 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -202,6 +202,10 @@ typedef enum { /* Keep gcc happy */ struct nand_chip; +/* ONFI features */ +#define ONFI_FEATURE_16_BIT_BUS (1 << 0) +#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) + /* ONFI timing mode, used in both asynchronous and synchronous mode */ #define ONFI_TIMING_MODE_0 (1 << 0) #define ONFI_TIMING_MODE_1 (1 << 1) @@ -756,6 +760,12 @@ struct platform_nand_chip *get_platform_nandchip(struct mtd_info *mtd) return chip->priv; } +/* return the supported features. */ +static inline int onfi_feature(struct nand_chip *chip) +{ + return chip->onfi_version ? le16_to_cpu(chip->onfi_params.features) : 0; +} + /* return the supported asynchronous timing mode. */ static inline int onfi_get_async_timing_mode(struct nand_chip *chip) { -- cgit v1.2.3 From 2dc0bdd91bb63f7d5755137177315c49637f6a96 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 17 May 2013 11:17:31 +0800 Subject: mtd: add ECC info for nand_flash_dev{} Add an instance of an anonymous struct to store the ECC info for full id nand chips. @ecc.strength_ds: ECC correctability from the datasheet. @ecc.step_ds: ECC size required by the @ecc.strength_ds, These two fields are all from the datasheet. Also add the necessary macros to make the code simple and clean. Signed-off-by: Huang Shijie Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index bf4c566f0647..ac8e89d5a792 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -628,6 +628,11 @@ struct nand_chip { { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ .options = (opts) } +#define NAND_ECC_INFO(_strength, _step) \ + { .strength_ds = (_strength), .step_ds = (_step) } +#define NAND_ECC_STRENGTH(type) ((type)->ecc.strength_ds) +#define NAND_ECC_STEP(type) ((type)->ecc.step_ds) + /** * struct nand_flash_dev - NAND Flash Device ID Structure * @name: a human-readable name of the NAND chip @@ -645,6 +650,12 @@ struct nand_chip { * @options: stores various chip bit options * @id_len: The valid length of the @id. * @oobsize: OOB size + * @ecc.strength_ds: The ECC correctability from the datasheet, same as the + * @ecc_strength_ds in nand_chip{}. + * @ecc.step_ds: The ECC step required by the @ecc.strength_ds, same as the + * @ecc_step_ds in nand_chip{}, also from the datasheet. + * For example, the "4bit ECC for each 512Byte" can be set with + * NAND_ECC_INFO(4, 512). */ struct nand_flash_dev { char *name; @@ -661,6 +672,10 @@ struct nand_flash_dev { unsigned int options; uint16_t id_len; uint16_t oobsize; + struct { + uint16_t strength_ds; + uint16_t step_ds; + } ecc; }; /** -- cgit v1.2.3 From ec82135a011cf657ef02cfa2038331b381e39960 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 12 Aug 2013 14:14:54 -0300 Subject: mtd: nand: pxa3xx: Remove unneeded internal cmdset Use the defined macros for NAND command instead of using a constant internal structure. This commit is only a cleanup, there's no functionality modification. Signed-off-by: Ezequiel Garcia Tested-by: Daniel Mack Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/platform_data/mtd-nand-pxa3xx.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-pxa3xx.h b/include/linux/platform_data/mtd-nand-pxa3xx.h index c42f39f20195..ffb801998e5d 100644 --- a/include/linux/platform_data/mtd-nand-pxa3xx.h +++ b/include/linux/platform_data/mtd-nand-pxa3xx.h @@ -16,19 +16,6 @@ struct pxa3xx_nand_timing { unsigned int tAR; /* ND_ALE low to ND_nRE low delay */ }; -struct pxa3xx_nand_cmdset { - uint16_t read1; - uint16_t read2; - uint16_t program; - uint16_t read_status; - uint16_t read_id; - uint16_t erase; - uint16_t reset; - uint16_t lock; - uint16_t unlock; - uint16_t lock_status; -}; - struct pxa3xx_nand_flash { char *name; uint32_t chip_id; -- cgit v1.2.3 From c41a0582d59e3bc41978ac4a23e457d86ac7365f Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 16 Aug 2013 10:10:04 +0800 Subject: mtd: add a new ecc_step_size field to mtd_info{} In order to implement the NAND boot for some Freescale's chips, such as imx23/imx28/imx50/imx6, we use a tool (called kobs-ng) to burn the uboot and some metadata to nand chip. And the ROM code will use the metadata to configrate the BCH, and to find the uboot. The ECC information(ecc step size, ecc strength) which is used to configrure the BCH is part of the metadata. The kobs-ng can get the ecc strength from the sys node /sys/*/ecc_strength now. But it can not get the ecc step size. This patch adds a new field to store the ecc step size in mtd_info{}, and it makes preparation for the next patches. Signed-off-by: Huang Shijie Signed-off-by: Artem Bityutskiy Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index a5cf4e8d6818..f9bfe526d310 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -173,6 +173,9 @@ struct mtd_info { /* ECC layout structure pointer - read only! */ struct nand_ecclayout *ecclayout; + /* the ecc step size. */ + unsigned int ecc_step_size; + /* max number of correctible bit errors per ecc step */ unsigned int ecc_strength; -- cgit v1.2.3 From e2a240c7d3bcebf90936cc7c22c2729b3a4cec1f Mon Sep 17 00:00:00 2001 From: Sonic Zhang Date: Wed, 28 Aug 2013 18:55:39 +0800 Subject: driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set. Some synopsys ip implementation doesn't support DMA store and forward mode, such as BF60x. So, set force_thresh_dma_mode to use DMA thresholds only. Update document and devicetree as well. Signed-off-by: Sonic Zhang Acked-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 9e495d31516e..bb5deb0feb6b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -108,6 +108,7 @@ struct plat_stmmacenet_data { int bugged_jumbo; int pmt; int force_sf_dma_mode; + int force_thresh_dma_mode; int riwt_off; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); -- cgit v1.2.3 From 11d2a1618e377236facdd404113992bde1083914 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 30 Aug 2013 16:50:06 -0400 Subject: svcrpc: remove unused rq_resused I forgot to remove this in afc59400d6c65bad66d4ad0b2daf879cbff8e23e "nfsd4: cleanup: replace rq_resused count by rq_next_page pointer". Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 1f0216b9a6c9..6eecfc2e4f98 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -243,7 +243,6 @@ struct svc_rqst { struct xdr_buf rq_res; struct page * rq_pages[RPCSVC_MAXPAGES]; struct page * *rq_respages; /* points into rq_pages */ - int rq_resused; /* number of pages used for result */ struct page * *rq_next_page; /* next reply page to use */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ -- cgit v1.2.3 From da0a00ebc239e852a504abfce2ad98957434ae58 Mon Sep 17 00:00:00 2001 From: Marek Belisko Date: Thu, 29 Aug 2013 11:41:52 +0200 Subject: power: Add twl4030_madc battery driver. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver is used and tested on gta04 phone. It's using twl4030_madc (similar to rx51 existing driver). Driver also implement charging and discharging calibration data so user can define ranges and level. Signed-off-by: Marek Belisko Signed-off-by: Lukas Märdian Signed-off-by: Anton Vorontsov --- include/linux/power/twl4030_madc_battery.h | 39 ++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/power/twl4030_madc_battery.h (limited to 'include/linux') diff --git a/include/linux/power/twl4030_madc_battery.h b/include/linux/power/twl4030_madc_battery.h new file mode 100644 index 000000000000..23110dc77726 --- /dev/null +++ b/include/linux/power/twl4030_madc_battery.h @@ -0,0 +1,39 @@ +/* + * Dumb driver for LiIon batteries using TWL4030 madc. + * + * Copyright 2013 Golden Delicious Computers + * Nikolaus Schaller + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __TWL4030_MADC_BATTERY_H +#define __TWL4030_MADC_BATTERY_H + +/* + * Usually we can assume 100% @ 4.15V and 0% @ 3.3V but curves differ for + * charging and discharging! + */ + +struct twl4030_madc_bat_calibration { + short voltage; /* in mV - specify -1 for end of list */ + short level; /* in percent (0 .. 100%) */ +}; + +struct twl4030_madc_bat_platform_data { + unsigned int capacity; /* total capacity in uAh */ + struct twl4030_madc_bat_calibration *charging; + int charging_size; + struct twl4030_madc_bat_calibration *discharging; + int discharging_size; +}; + +#endif -- cgit v1.2.3 From c7b96acf1456ef127fef461fcfedb54b81fecfbb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 20 Mar 2013 12:49:49 -0700 Subject: userns: Kill nsown_capable it makes the wrong thing easy nsown_capable is a special case of ns_capable essentially for just CAP_SETUID and CAP_SETGID. For the existing users it doesn't noticably simplify things and from the suggested patches I have seen it encourages people to do the wrong thing. So remove nsown_capable. Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- include/linux/capability.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index d9a4f7f40f32..a6ee1f9a5018 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -210,7 +210,6 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); -extern bool nsown_capable(int cap); extern bool inode_capable(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); -- cgit v1.2.3 From 0edd1b1784cbdad55aca2c1293be018f53c0ab1d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jun 2013 16:37:22 -0700 Subject: nohz_full: Add full-system-idle state machine This commit adds the state machine that takes the per-CPU idle data as input and produces a full-system-idle indication as output. This state machine is driven out of RCU's quiescent-state-forcing mechanism, which invokes rcu_sysidle_check_cpu() to collect per-CPU idle state and then rcu_sysidle_report() to drive the state machine. The full-system-idle state is sampled using rcu_sys_is_idle(), which also drives the state machine if RCU is idle (and does so by forcing RCU to become non-idle). This function returns true if all but the timekeeping CPU (tick_do_timer_cpu) are idle and have been idle long enough to avoid memory contention on the full_sysidle_state state variable. The rcu_sysidle_force_exit() may be called externally to reset the state machine back into non-idle state. For large systems the state machine is driven out of RCU's force-quiescent-state logic, which provides good scalability at the price of millisecond-scale latencies on the transition to full-system-idle state. This is not so good for battery-powered systems, which are usually small enough that they don't need to care about scalability, but which do care deeply about energy efficiency. Small systems therefore drive the state machine directly out of the idle-entry code. The number of CPUs in a "small" system is defined by a new NO_HZ_FULL_SYSIDLE_SMALL Kconfig parameter, which defaults to 8. Note that this is a build-time definition. Signed-off-by: Paul E. McKenney Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Lai Jiangshan [ paulmck: Use true and false for boolean constants per Lai Jiangshan. ] Reviewed-by: Josh Triplett [ paulmck: Simplify logic and provide better comments for memory barriers, based on review comments and questions by Lai Jiangshan. ] --- include/linux/rcupdate.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 30bea9c25735..f1f1bc39346b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1011,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +/* Only for use by adaptive-ticks code. */ +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE +extern bool rcu_sys_is_idle(void); +extern void rcu_sysidle_force_exit(void); +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +static inline bool rcu_sys_is_idle(void) +{ + return false; +} + +static inline void rcu_sysidle_force_exit(void) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 5f42b016d7341871948a2b8cc8fb654691522d1a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Aug 2013 16:47:20 -0400 Subject: SUNRPC: Remove the obsolete auth-only interface for pipefs dentry management Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a9ab577b0c4a..6de26f2491e5 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -107,8 +107,6 @@ struct rpc_authops { struct rpc_cred * (*lookup_cred)(struct rpc_auth *, struct auth_cred *, int); struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int); - int (*pipes_create)(struct rpc_auth *); - void (*pipes_destroy)(struct rpc_auth *); int (*list_pseudoflavors)(rpc_authflavor_t *, int); rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *); int (*flavor2info)(rpc_authflavor_t, -- cgit v1.2.3 From c36dcfe1f7712b7c12df2d80359e638b9d246ce6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Aug 2013 17:44:26 -0400 Subject: SUNRPC: Remove the rpc_client->cl_dentry It is now redundant. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - include/linux/sunrpc/rpc_pipe_fs.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 0dccd01ae2de..76c0bf6ecd17 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -57,7 +57,6 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; struct rpc_pipe_dir_head cl_pipedir_objects; - struct dentry * cl_dentry; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 188e7fca67e1..b0cf1812be72 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -94,7 +94,7 @@ extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *); struct rpc_clnt; extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); -extern int rpc_remove_client_dir(struct dentry *, struct rpc_clnt *); +extern int rpc_remove_client_dir(struct rpc_clnt *); extern void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh); extern void rpc_init_pipe_dir_object(struct rpc_pipe_dir_object *pdo, -- cgit v1.2.3 From 298fc3558b9c1f5324c5ec6d5c587ca9ae6cc826 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 27 Aug 2013 16:27:04 -0400 Subject: SUNRPC: Add a helper to allow sharing of rpc_pipefs directory objects Add support for looking up existing objects and creating new ones if there is no match. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index b0cf1812be72..a353e0300b54 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -106,6 +106,12 @@ extern int rpc_add_pipe_dir_object(struct net *net, extern void rpc_remove_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo); +extern struct rpc_pipe_dir_object *rpc_find_or_alloc_pipe_dir_object( + struct net *net, + struct rpc_pipe_dir_head *pdh, + int (*match)(struct rpc_pipe_dir_object *, void *), + struct rpc_pipe_dir_object *(*alloc)(void *), + void *data); struct cache_detail; extern struct dentry *rpc_create_cache_dir(struct dentry *, -- cgit v1.2.3 From bd1c149aa9915b9abb6d83d0f01dfd2ace0680b5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 1 Sep 2013 20:35:01 +0100 Subject: Introduce [compat_]save_altstack_ex() to unbreak x86 SMAP For performance reasons, when SMAP is in use, SMAP is left open for an entire put_user_try { ... } put_user_catch(); block, however, calling __put_user() in the middle of that block will close SMAP as the STAC..CLAC constructs intentionally do not nest. Furthermore, using __put_user() rather than put_user_ex() here is bad for performance. Thus, introduce new [compat_]save_altstack_ex() helpers that replace __[compat_]save_altstack() for x86, being currently the only architecture which supports put_user_try { ... } put_user_catch(). Reported-by: H. Peter Anvin Signed-off-by: Al Viro Signed-off-by: H. Peter Anvin Cc: # v3.8+ Link: http://lkml.kernel.org/n/tip-es5p6y64if71k8p5u08agv9n@git.kernel.org --- include/linux/compat.h | 7 +++++++ include/linux/signal.h | 8 ++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 7f0c1dd09079..ec1aee4aec9c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -669,6 +669,13 @@ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); +#define compat_save_altstack_ex(uss, sp) do { \ + compat_stack_t __user *__uss = uss; \ + struct task_struct *t = current; \ + put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \ + put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \ + put_user_ex(t->sas_ss_size, &__uss->ss_size); \ +} while (0); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval); diff --git a/include/linux/signal.h b/include/linux/signal.h index d897484730c0..2ac423bdb676 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -434,6 +434,14 @@ void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); +#define save_altstack_ex(uss, sp) do { \ + stack_t __user *__uss = uss; \ + struct task_struct *t = current; \ + put_user_ex((void __user *)t->sas_ss_sp, &__uss->ss_sp); \ + put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \ + put_user_ex(t->sas_ss_size, &__uss->ss_size); \ +} while (0); + #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); -- cgit v1.2.3 From da1b6c05b8b5bd9af060acb319360604a0890c2e Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Sun, 11 Aug 2013 19:59:17 +0200 Subject: dmaengine: PL08x: Add support for PL080S variant PL080S is a modified version of PL080 that can be found on Samsung SoCs, such as S3C6400 and S3C6410. It has different offset of CONFIG register, separate CONTROL1 register that holds transfer size and larger maximum transfer size. Signed-off-by: Tomasz Figa Acked-by: Linus Walleij Signed-off-by: Vinod Koul --- include/linux/amba/pl080.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/amba/pl080.h b/include/linux/amba/pl080.h index 3e7b62fbefbd..91b84a7f0539 100644 --- a/include/linux/amba/pl080.h +++ b/include/linux/amba/pl080.h @@ -87,6 +87,7 @@ #define PL080_CONTROL_SB_SIZE_MASK (0x7 << 12) #define PL080_CONTROL_SB_SIZE_SHIFT (12) #define PL080_CONTROL_TRANSFER_SIZE_MASK (0xfff << 0) +#define PL080S_CONTROL_TRANSFER_SIZE_MASK (0x1ffffff << 0) #define PL080_CONTROL_TRANSFER_SIZE_SHIFT (0) #define PL080_BSIZE_1 (0x0) -- cgit v1.2.3 From 274481de6cb69abdb49403ff32abb63c23743413 Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Fri, 23 Aug 2013 15:51:03 -0400 Subject: perf: Export struct perf_branch_entry to userspace If PERF_SAMPLE_BRANCH_STACK is enabled then samples are returned with the format { u64 from, to, flags } but the flags layout is not specified. This field has the type struct perf_branch_entry; move this definition into include/uapi/linux/perf_event.h so users can access these fields. This is similar to the existing inclusion of perf_mem_data_src in the include/uapi/linux/perf_event.h file. Signed-off-by: Vince Weaver Acked-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308231544420.1889@vincent-weaver-1.um.maine.edu Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c43f6eabad5b..4019d82c3d03 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -63,30 +63,6 @@ struct perf_raw_record { void *data; }; -/* - * single taken branch record layout: - * - * from: source instruction (may not always be a branch insn) - * to: branch target - * mispred: branch target was mispredicted - * predicted: branch target was predicted - * - * support for mispred, predicted is optional. In case it - * is not supported mispred = predicted = 0. - * - * in_tx: running in a hardware transaction - * abort: aborting a hardware transaction - */ -struct perf_branch_entry { - __u64 from; - __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - reserved:60; -}; - /* * branch stack layout: * nr: number of taken branches stored in entries[] -- cgit v1.2.3 From 921a2c870faa0a88c34e5c8c2afbd898fe8d325d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 31 Aug 2013 14:08:56 +0100 Subject: mfd: davinci_voicecodec: Provide a regmap for register I/O This will be used to support refactoring of the ASoC CODEC driver to use a regmap. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/davinci_voicecodec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h index 13a1ee95a233..5166935ce66d 100644 --- a/include/linux/mfd/davinci_voicecodec.h +++ b/include/linux/mfd/davinci_voicecodec.h @@ -30,6 +30,8 @@ #include +struct regmap; + /* * Register values. */ @@ -113,6 +115,7 @@ struct davinci_vc { /* Memory resources */ void __iomem *base; + struct regmap *regmap; /* MFD cells */ struct mfd_cell cells[DAVINCI_VC_CELLS]; -- cgit v1.2.3 From c6f39257c952bc7da974bf93255936ff2ece2c34 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 31 Aug 2013 17:48:19 +0100 Subject: mfd: twl6040: Use regmap for register cache Rather then open coding a cache of the vibra control registers use the regmap cache code. Also cache the interrupt mask register, providing a small performance improvement for the interrupt code. Signed-off-by: Mark Brown Acked-by: Peter Ujfalusi Signed-off-by: Samuel Ortiz --- include/linux/mfd/twl6040.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index 7e7fbce7a308..2b7d26573431 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -229,7 +229,6 @@ struct twl6040 { int audpwron; int power_count; int rev; - u8 vibra_ctrl_cache[2]; /* PLL configuration */ int pll; -- cgit v1.2.3 From c4f6c41ba790bbbfcebb4c47a709ac8ff1fe1af9 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sun, 25 Aug 2013 00:33:24 +0400 Subject: dma: add driver for R-Car HPB-DMAC Add support for HPB-DMAC found in Renesas R-Car SoCs, using 'shdma-base' DMA driver framework. Based on the original patch by Phil Edworthy . Signed-off-by: Max Filippov [Sergei: removed useless #include, sorted #include's, fixed HPB_DMA_TCR_MAX, fixed formats and removed line breaks in the dev_dbg() calls, rephrased and added IRQ # to the shdma_request_irq() failure message, added MODULE_AUTHOR(), removed '__init'/'__exit' annotations from the probe()/remove() methods, removed '__initdata' annotation from 'hpb_dmae_driver', fixed guard macro name in the header file, fixed #define ASYNCRSTR_ASRST20, added #define ASYNCRSTR_ASRST24, added the necessary runtime PM calls to the probe() and remove() methods, handled errors returned by dma_async_device_register(), beautified comments and #define's.] Signed-off-by: Sergei Shtylyov Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-rcar-hpbdma.h | 103 ++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/linux/platform_data/dma-rcar-hpbdma.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-rcar-hpbdma.h b/include/linux/platform_data/dma-rcar-hpbdma.h new file mode 100644 index 000000000000..648b8ea61a22 --- /dev/null +++ b/include/linux/platform_data/dma-rcar-hpbdma.h @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2011-2013 Renesas Electronics Corporation + * Copyright (C) 2013 Cogent Embedded, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __DMA_RCAR_HPBDMA_H +#define __DMA_RCAR_HPBDMA_H + +#include +#include + +/* Transmit sizes and respective register values */ +enum { + XMIT_SZ_8BIT = 0, + XMIT_SZ_16BIT = 1, + XMIT_SZ_32BIT = 2, + XMIT_SZ_MAX +}; + +/* DMA control register (DCR) bits */ +#define HPB_DMAE_DCR_DTAMD (1u << 26) +#define HPB_DMAE_DCR_DTAC (1u << 25) +#define HPB_DMAE_DCR_DTAU (1u << 24) +#define HPB_DMAE_DCR_DTAU1 (1u << 23) +#define HPB_DMAE_DCR_SWMD (1u << 22) +#define HPB_DMAE_DCR_BTMD (1u << 21) +#define HPB_DMAE_DCR_PKMD (1u << 20) +#define HPB_DMAE_DCR_CT (1u << 18) +#define HPB_DMAE_DCR_ACMD (1u << 17) +#define HPB_DMAE_DCR_DIP (1u << 16) +#define HPB_DMAE_DCR_SMDL (1u << 13) +#define HPB_DMAE_DCR_SPDAM (1u << 12) +#define HPB_DMAE_DCR_SDRMD_MASK (3u << 10) +#define HPB_DMAE_DCR_SDRMD_MOD (0u << 10) +#define HPB_DMAE_DCR_SDRMD_AUTO (1u << 10) +#define HPB_DMAE_DCR_SDRMD_TIMER (2u << 10) +#define HPB_DMAE_DCR_SPDS_MASK (3u << 8) +#define HPB_DMAE_DCR_SPDS_8BIT (0u << 8) +#define HPB_DMAE_DCR_SPDS_16BIT (1u << 8) +#define HPB_DMAE_DCR_SPDS_32BIT (2u << 8) +#define HPB_DMAE_DCR_DMDL (1u << 5) +#define HPB_DMAE_DCR_DPDAM (1u << 4) +#define HPB_DMAE_DCR_DDRMD_MASK (3u << 2) +#define HPB_DMAE_DCR_DDRMD_MOD (0u << 2) +#define HPB_DMAE_DCR_DDRMD_AUTO (1u << 2) +#define HPB_DMAE_DCR_DDRMD_TIMER (2u << 2) +#define HPB_DMAE_DCR_DPDS_MASK (3u << 0) +#define HPB_DMAE_DCR_DPDS_8BIT (0u << 0) +#define HPB_DMAE_DCR_DPDS_16BIT (1u << 0) +#define HPB_DMAE_DCR_DPDS_32BIT (2u << 0) + +/* Asynchronous reset register (ASYNCRSTR) bits */ +#define HPB_DMAE_ASYNCRSTR_ASRST41 BIT(10) +#define HPB_DMAE_ASYNCRSTR_ASRST40 BIT(9) +#define HPB_DMAE_ASYNCRSTR_ASRST39 BIT(8) +#define HPB_DMAE_ASYNCRSTR_ASRST27 BIT(7) +#define HPB_DMAE_ASYNCRSTR_ASRST26 BIT(6) +#define HPB_DMAE_ASYNCRSTR_ASRST25 BIT(5) +#define HPB_DMAE_ASYNCRSTR_ASRST24 BIT(4) +#define HPB_DMAE_ASYNCRSTR_ASRST23 BIT(3) +#define HPB_DMAE_ASYNCRSTR_ASRST22 BIT(2) +#define HPB_DMAE_ASYNCRSTR_ASRST21 BIT(1) +#define HPB_DMAE_ASYNCRSTR_ASRST20 BIT(0) + +struct hpb_dmae_slave_config { + unsigned int id; + dma_addr_t addr; + u32 dcr; + u32 port; + u32 rstr; + u32 mdr; + u32 mdm; + u32 flags; +#define HPB_DMAE_SET_ASYNC_RESET BIT(0) +#define HPB_DMAE_SET_ASYNC_MODE BIT(1) + u32 dma_ch; +}; + +#define HPB_DMAE_CHANNEL(_irq, _s_id) \ +{ \ + .ch_irq = _irq, \ + .s_id = _s_id, \ +} + +struct hpb_dmae_channel { + unsigned int ch_irq; + unsigned int s_id; +}; + +struct hpb_dmae_pdata { + const struct hpb_dmae_slave_config *slaves; + int num_slaves; + const struct hpb_dmae_channel *channels; + int num_channels; + const unsigned int ts_shift[XMIT_SZ_MAX]; + int num_hw_channels; +}; + +#endif -- cgit v1.2.3 From 14f00c74f787a263e443b6901083187ffae641de Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 2 Sep 2013 17:47:33 +0530 Subject: dmaengine: dma_slave_caps: remove sg entries As pointed by Russell in [1], the sg properties are already availble in struct device, so no need to duplicate here. [1]: http://marc.info/?l=linux-omap&m=137416733628831 Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 5692bc3afd39..4310b8972867 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -380,11 +380,6 @@ struct dma_slave_config { * should be checked by controller as well * @cmd_pause: true, if pause and thereby resume is supported * @cmd_terminate: true, if terminate cmd is supported - * - * @max_sg_nr: maximum number of SG segments supported - * 0 for no maximum - * @max_sg_len: maximum length of a SG segment supported - * 0 for no maximum */ struct dma_slave_caps { u32 src_addr_widths; @@ -392,9 +387,6 @@ struct dma_slave_caps { u32 directions; bool cmd_pause; bool cmd_terminate; - - u32 max_sg_nr; - u32 max_sg_len; }; static inline const char *dma_chan_name(struct dma_chan *chan) -- cgit v1.2.3 From b3abd80250c13414bc258b53e57242feb159af91 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:14:19 -0700 Subject: lockref: add 'lockref_get_or_lock() helper This behaves like "lockref_get_not_zero()", but instead of doing nothing if the count was zero, it returns with the lock held. This allows callers to revalidate the lockref-protected data structure if required even if the count was zero to begin with, and possibly increment the count if it passes muster. In particular, the dentry code wants this when it wants to turn an RCU-protected dentry into a stable refcounted one: if the dentry count it zero, but the sequence number still validates the dentry, we can take a reference to it. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 01233e01627a..0ea026092d1d 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -53,6 +53,22 @@ static inline int lockref_get_not_zero(struct lockref *lockref) return retval; } +/** + * lockref_get_or_lock - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count was zero + * and we got the lock instead. + */ +static inline int lockref_get_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (!lockref->count) + return 0; + lockref->count++; + spin_unlock(&lockref->lock); + return 1; +} + /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockcnt: pointer to lockref structure -- cgit v1.2.3 From 15570086b590a69d59183b08a7770e316cca20a7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:38:06 -0700 Subject: vfs: reimplement d_rcu_to_refcount() using lockref_get_or_lock() This moves __d_rcu_to_refcount() from into fs/namei.c and re-implements it using the lockref infrastructure instead. It also adds a lot of comments about what is actually going on, because turning a dentry that was looked up using RCU into a long-lived reference counted entry is one of the more subtle parts of the rcu walk. We also used to be _particularly_ subtle in unlazy_walk() where we re-validate both the dentry and its parent using the same sequence count. We used to do it by nesting the locks and then verifying the sequence count just once. That was silly, because nested locking is expensive, but the sequence count check is not. So this just re-validates the dentry and the parent separately, avoiding the nested locking, and making the lockref lookup possible. Acked-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index efdc94434c30..9169b91ea2d2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -304,28 +304,6 @@ extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); -/** - * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok - * @dentry: dentry to take a ref on - * @seq: seqcount to verify against - * Returns: 0 on failure, else 1. - * - * __d_rcu_to_refcount operates on a dentry,seq pair that was returned - * by __d_lookup_rcu, to get a reference on an rcu-walk dentry. - */ -static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) -{ - int ret = 0; - - assert_spin_locked(&dentry->d_lock); - if (!read_seqcount_retry(&dentry->d_seq, seq)) { - ret = 1; - dentry->d_lockref.count++; - } - - return ret; -} - static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; -- cgit v1.2.3 From 2f4f12e571c4e2f50f3818a3c2544929145f75dd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:58:20 -0700 Subject: lockref: uninline lockref helper functions They aren't very good to inline, since they already call external functions (the spinlock code), and we're going to create rather more complicated versions of them that can do the reference count updates locklessly. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 66 +++---------------------------------------------- 1 file changed, 4 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 0ea026092d1d..4c0af31c8d47 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -21,67 +21,9 @@ struct lockref { unsigned int count; }; -/** - * lockref_get - Increments reference count unconditionally - * @lockcnt: pointer to lockref structure - * - * This operation is only valid if you already hold a reference - * to the object, so you know the count cannot be zero. - */ -static inline void lockref_get(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - lockref->count++; - spin_unlock(&lockref->lock); -} - -/** - * lockref_get_not_zero - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count is 0 - */ -static inline int lockref_get_not_zero(struct lockref *lockref) -{ - int retval = 0; - - spin_lock(&lockref->lock); - if (lockref->count) { - lockref->count++; - retval = 1; - } - spin_unlock(&lockref->lock); - return retval; -} - -/** - * lockref_get_or_lock - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count was zero - * and we got the lock instead. - */ -static inline int lockref_get_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (!lockref->count) - return 0; - lockref->count++; - spin_unlock(&lockref->lock); - return 1; -} - -/** - * lockref_put_or_lock - decrements count unless count <= 1 before decrement - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken - */ -static inline int lockref_put_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (lockref->count <= 1) - return 0; - lockref->count--; - spin_unlock(&lockref->lock); - return 1; -} +extern void lockref_get(struct lockref *); +extern int lockref_get_not_zero(struct lockref *); +extern int lockref_get_or_lock(struct lockref *); +extern int lockref_put_or_lock(struct lockref *); #endif /* __LINUX_LOCKREF_H */ -- cgit v1.2.3 From bc08b449ee14ace4d869adaa1bb35a44ce68d775 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 12:12:15 -0700 Subject: lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 4c0af31c8d47..ca07b5028b01 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -17,8 +17,15 @@ #include struct lockref { - spinlock_t lock; - unsigned int count; + union { +#ifdef CONFIG_CMPXCHG_LOCKREF + aligned_u64 lock_count; +#endif + struct { + spinlock_t lock; + unsigned int count; + }; + }; }; extern void lockref_get(struct lockref *); -- cgit v1.2.3 From 573145f08c2b92c45498468afbbba909f6ce6135 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 13 Aug 2013 11:43:12 -0300 Subject: clocksource: armada-370-xp: Use CLOCKSOURCE_OF_DECLARE This is almost cosmetic: we achieve a bit of consistency with other clocksource drivers by using the CLOCKSOURCE_OF_DECLARE macro for the boilerplate code. Signed-off-by: Ezequiel Garcia Signed-off-by: Daniel Lezcano Reviewed-by: Andrew Lunn --- include/linux/time-armada-370-xp.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/time-armada-370-xp.h (limited to 'include/linux') diff --git a/include/linux/time-armada-370-xp.h b/include/linux/time-armada-370-xp.h deleted file mode 100644 index dfdfdc03115b..000000000000 --- a/include/linux/time-armada-370-xp.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Marvell Armada 370/XP SoC timer handling. - * - * Copyright (C) 2012 Marvell - * - * Lior Amsalem - * Gregory CLEMENT - * Thomas Petazzoni - * - */ -#ifndef __TIME_ARMADA_370_XPPRCMU_H -#define __TIME_ARMADA_370_XPPRCMU_H - -#include - -void __init armada_370_xp_timer_init(void); - -#endif -- cgit v1.2.3 From 942e443127e928a5631c3d5102aca8c8b3c2dd98 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Tue, 3 Sep 2013 16:33:57 +0930 Subject: module: Fix mod->mkobj.kobj potentially freed too early DEBUG_KOBJECT_RELEASE helps to find the issue attached below. After some investigation, it seems the reason is: The mod->mkobj.kobj(ffffffffa01600d0 below) is freed together with mod itself in free_module(). However, its children still hold references to it, as the delay caused by DEBUG_KOBJECT_RELEASE. So when the child(holders below) tries to decrease the reference count to its parent in kobject_del(), BUG happens as it tries to access already freed memory. This patch tries to fix it by waiting for the mod->mkobj.kobj to be really released in the module removing process (and some error code paths). [ 1844.175287] kobject: 'holders' (ffff88007c1f1600): kobject_release, parent ffffffffa01600d0 (delayed) [ 1844.178991] kobject: 'notes' (ffff8800370b2a00): kobject_release, parent ffffffffa01600d0 (delayed) [ 1845.180118] kobject: 'holders' (ffff88007c1f1600): kobject_cleanup, parent ffffffffa01600d0 [ 1845.182130] kobject: 'holders' (ffff88007c1f1600): auto cleanup kobject_del [ 1845.184120] BUG: unable to handle kernel paging request at ffffffffa01601d0 [ 1845.185026] IP: [] kobject_put+0x11/0x60 [ 1845.185026] PGD 1a13067 PUD 1a14063 PMD 7bd30067 PTE 0 [ 1845.185026] Oops: 0000 [#1] PREEMPT [ 1845.185026] Modules linked in: xfs libcrc32c [last unloaded: kprobe_example] [ 1845.185026] CPU: 0 PID: 18 Comm: kworker/0:1 Tainted: G O 3.11.0-rc6-next-20130819+ #1 [ 1845.185026] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007 [ 1845.185026] Workqueue: events kobject_delayed_cleanup [ 1845.185026] task: ffff88007ca51f00 ti: ffff88007ca5c000 task.ti: ffff88007ca5c000 [ 1845.185026] RIP: 0010:[] [] kobject_put+0x11/0x60 [ 1845.185026] RSP: 0018:ffff88007ca5dd08 EFLAGS: 00010282 [ 1845.185026] RAX: 0000000000002000 RBX: ffffffffa01600d0 RCX: ffffffff8177d638 [ 1845.185026] RDX: ffff88007ca5dc18 RSI: 0000000000000000 RDI: ffffffffa01600d0 [ 1845.185026] RBP: ffff88007ca5dd18 R08: ffffffff824e9810 R09: ffffffffffffffff [ 1845.185026] R10: ffff8800ffffffff R11: dead4ead00000001 R12: ffffffff81a95040 [ 1845.185026] R13: ffff88007b27a960 R14: ffff88007c1f1600 R15: 0000000000000000 [ 1845.185026] FS: 0000000000000000(0000) GS:ffffffff81a23000(0000) knlGS:0000000000000000 [ 1845.185026] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 1845.185026] CR2: ffffffffa01601d0 CR3: 0000000037207000 CR4: 00000000000006b0 [ 1845.185026] Stack: [ 1845.185026] ffff88007c1f1600 ffff88007c1f1600 ffff88007ca5dd38 ffffffff812cdb7e [ 1845.185026] 0000000000000000 ffff88007c1f1640 ffff88007ca5dd68 ffffffff812cdbfe [ 1845.185026] ffff88007c974800 ffff88007c1f1640 ffff88007ff61a00 0000000000000000 [ 1845.185026] Call Trace: [ 1845.185026] [] kobject_del+0x2e/0x40 [ 1845.185026] [] kobject_delayed_cleanup+0x6e/0x1d0 [ 1845.185026] [] process_one_work+0x1e5/0x670 [ 1845.185026] [] ? process_one_work+0x183/0x670 [ 1845.185026] [] worker_thread+0x113/0x370 [ 1845.185026] [] ? rescuer_thread+0x290/0x290 [ 1845.185026] [] kthread+0xda/0xe0 [ 1845.185026] [] ? _raw_spin_unlock_irq+0x30/0x60 [ 1845.185026] [] ? kthread_create_on_node+0x130/0x130 [ 1845.185026] [] ret_from_fork+0x7a/0xb0 [ 1845.185026] [] ? kthread_create_on_node+0x130/0x130 [ 1845.185026] Code: 81 48 c7 c7 28 95 ad 81 31 c0 e8 9b da 01 00 e9 4f ff ff ff 66 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb 48 83 ec 08 48 85 ff 74 1d 87 00 01 00 00 01 74 1e 48 8d 7b 38 83 6b 38 01 0f 94 c0 84 [ 1845.185026] RIP [] kobject_put+0x11/0x60 [ 1845.185026] RSP [ 1845.185026] CR2: ffffffffa01601d0 [ 1845.185026] ---[ end trace 49a70afd109f5653 ]--- Signed-off-by: Li Zhong Acked-by: Greg Kroah-Hartman Signed-off-by: Rusty Russell --- include/linux/module.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 504035f3ece1..05f2447f8c15 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -42,6 +42,7 @@ struct module_kobject { struct module *mod; struct kobject *drivers_dir; struct module_param_attrs *mp; + struct completion *kobj_completion; }; struct module_attribute { -- cgit v1.2.3 From ccba4ffd9eff6120a20cc7656458ac554aec4b0c Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Thu, 15 Aug 2013 11:34:17 -0400 Subject: drivers: thermal: make usage of CONFIG_THERMAL_HWMON optional When registering a new thermal_device, the thermal framework will always add a hwmon sysfs interface. This patch adds a flag to make this behavior optional. Now when registering a new thermal device, the caller can optionally inform if hwmon interface is desirable. This can be done by means of passing a thermal_zone_params.no_hwmon == true. In order to keep same behavior as of today, all current calls will by default create the hwmon interface. Cc: David Woodhouse Cc: linux-acpi@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: Zhang Rui Suggested-by: Wei Ni Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index a386a1cbb6e1..b4a975f25be0 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -214,6 +214,14 @@ struct thermal_bind_params { /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { char governor_name[THERMAL_NAME_LENGTH]; + + /* + * a boolean to indicate if the thermal to hwmon sysfs interface + * is required. when no_hwmon == false, a hwmon sysfs interface + * will be created. when no_hwmon == true, nothing will be done + */ + bool no_hwmon; + int num_tbps; /* Number of tbp entries */ struct thermal_bind_params *tbp; }; -- cgit v1.2.3 From a8892d83894bcbd2717846cfa85955152b73453f Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Tue, 16 Jul 2013 15:26:28 -0400 Subject: thermal: thermal_core: allow binding with limits on bind_params When registering a thermal zone device using platform information via bind_params, the thermal framework will always perform the cdev binding using the lowest and highest limits (THERMAL_NO_LIMIT). This patch changes the data structures so that it is possible to inform what are the desired limits for each trip point inside a bind_param. The way the binding is performed is also changed so that it uses the new data structure. Cc: Zhang Rui Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index b4a975f25be0..b268d3cf7ae3 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -207,6 +207,16 @@ struct thermal_bind_params { * See Documentation/thermal/sysfs-api.txt for more information. */ int trip_mask; + + /* + * This is an array of cooling state limits. Must have exactly + * 2 * thermal_zone.number_of_trip_points. It is an array consisting + * of tuples of state limits. Each trip + * will be associated with one state limit tuple when binding. + * A NULL pointer means + * on all trips. + */ + unsigned long *binding_limits; int (*match) (struct thermal_zone_device *tz, struct thermal_cooling_device *cdev); }; -- cgit v1.2.3 From 81b5c7bc8de3e6f63419139c2fc91bf81dea8a7d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 28 Aug 2013 09:39:08 -0600 Subject: i915: Update VGA arbiter support for newer devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is intended to add VGA arbiter support for Intel HD graphics on Core processors. The old GMCH registers no longer exist, so even though it appears that i915 participates in VGA arbitration, it doesn't work. On Intel HD graphics we already attempt to disable VGA regions of the device. This makes registering as a VGA client unnecessary since we don't intend to operate differently depending on how many VGA devices are present. We can disable VGA memory regions by clearing the memory enable bit in the VGA MSR. That only leaves VGA IO, which we update the VGA arbiter to know that we don't participate in VGA memory arbitration. We also add a hook on unload to re-enable memory and reinstate VGA memory arbitration. v3: Use explicit LEGACY_IO | LEGACY_MEM when restoring rather than LEGACY_MASK, per Ville's comments. v2: I915_READ/WRITE accessors don't work in i915_disable_vga, use inb/outb directly. Also, on the driver unbind VGA enable path, acquire legacy IO to re-enable VGA memory. Correct comment. Signed-off-by: Alex Williamson Reviewed-by: Ville Syrjälä [danvet: Add patch changelog. Also squash in a fixup to have a dummy static inline for vga_set_legacy_decoding for CONFIG_VGA_ARB=n as reported by the 0-day kernel build bot.] Signed-off-by: Daniel Vetter fixup 2 --- include/linux/vgaarb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 2c02f3a8d2ba..80cf8173a65b 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -65,8 +65,15 @@ struct pci_dev; * out of the arbitration process (and can be safe to take * interrupts at any time. */ +#if defined(CONFIG_VGA_ARB) extern void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes); +#else +static inline void vga_set_legacy_decoding(struct pci_dev *pdev, + unsigned int decodes) +{ +} +#endif /** * vga_get - acquire & locks VGA resources -- cgit v1.2.3 From 4de6caa270afaa381dd3373e9e6d148b1090e0ec Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 14 Aug 2013 11:59:15 -0400 Subject: SUNRPC new rpc_credops to test credential expiry This patch provides the RPC layer helper functions to allow NFS to manage data in the face of expired credentials - such as avoiding buffered WRITEs and COMMITs when the gss context will expire before the WRITEs are flushed and COMMITs are sent. These helper functions enable checking the expiration of an underlying credential key for a generic rpc credential, e.g. the gss_cred gss context gc_expiry which for Kerberos is set to the remaining TGT lifetime. A new rpc_authops key_timeout is only defined for the generic auth. A new rpc_credops crkey_to_expire is only defined for the generic cred. A new rpc_credops crkey_timeout is only defined for the gss cred. Set a credential key expiry watermark, RPC_KEY_EXPIRE_TIMEO set to 240 seconds as a default and can be set via a module parameter as we need to ensure there is time for any dirty data to be flushed. If key_timeout is called on a credential with an underlying credential key that will expire within watermark seconds, we set the RPC_CRED_KEY_EXPIRE_SOON flag in the generic_cred acred so that the NFS layer can clean up prior to key expiration. Checking a generic credential's underlying credential involves a cred lookup. To avoid this lookup in the normal case when the underlying credential has a key that is valid (before the watermark), a notify flag is set in the generic credential the first time the key_timeout is called. The generic credential then stops checking the underlying credential key expiry, and the underlying credential (gss_cred) match routine then checks the key expiration upon each normal use and sets a flag in the associated generic credential only when the key expiration is within the watermark. This in turn signals the generic credential key_timeout to perform the extra credential lookup thereafter. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 6de26f2491e5..790be1472792 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -24,12 +24,21 @@ struct rpcsec_gss_info; +/* auth_cred ac_flags bits */ +enum { + RPC_CRED_NO_CRKEY_TIMEOUT = 0, /* underlying cred has no key timeout */ + RPC_CRED_KEY_EXPIRE_SOON = 1, /* underlying cred key will expire soon */ + RPC_CRED_NOTIFY_TIMEOUT = 2, /* nofity generic cred when underlying + key will expire soon */ +}; + /* Work around the lack of a VFS credential */ struct auth_cred { kuid_t uid; kgid_t gid; struct group_info *group_info; const char *principal; + unsigned long ac_flags; unsigned char machine_cred : 1; }; @@ -111,6 +120,8 @@ struct rpc_authops { rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *); int (*flavor2info)(rpc_authflavor_t, struct rpcsec_gss_info *); + int (*key_timeout)(struct rpc_auth *, + struct rpc_cred *); }; struct rpc_credops { @@ -127,6 +138,8 @@ struct rpc_credops { void *, __be32 *, void *); int (*crunwrap_resp)(struct rpc_task *, kxdrdproc_t, void *, __be32 *, void *); + int (*crkey_timeout)(struct rpc_cred *); + bool (*crkey_to_expire)(struct rpc_cred *); }; extern const struct rpc_authops authunix_ops; @@ -166,6 +179,9 @@ int rpcauth_uptodatecred(struct rpc_task *); int rpcauth_init_credcache(struct rpc_auth *); void rpcauth_destroy_credcache(struct rpc_auth *); void rpcauth_clear_credcache(struct rpc_cred_cache *); +int rpcauth_key_timeout_notify(struct rpc_auth *, + struct rpc_cred *); +bool rpcauth_cred_key_to_expire(struct rpc_cred *); static inline struct rpc_cred * get_rpccred(struct rpc_cred *cred) -- cgit v1.2.3 From ba6c05928dcafc7e0a0c8e4ee6a293ba47190fd4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Aug 2013 12:24:25 -0400 Subject: NFS: Ensure that rmdir() waits for sillyrenames to complete If an NFS client does mkdir("dir"); fd = open("dir/file"); unlink("dir/file"); close(fd); rmdir("dir"); then the asynchronous nature of the sillyrename operation means that we can end up getting EBUSY for the rmdir() in the above test. Fix that by ensuring that we wait for any in-progress sillyrenames before sending the rmdir() to the server. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7125cef74164..3ea4cde8701c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -524,6 +524,7 @@ static inline void nfs4_label_free(void *label) {} * linux/fs/nfs/unlink.c */ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); +extern void nfs_wait_on_sillyrename(struct dentry *dentry); extern void nfs_block_sillyrename(struct dentry *dentry); extern void nfs_unblock_sillyrename(struct dentry *dentry); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); -- cgit v1.2.3 From abf79bb341bf52f75f295b850abdf5f78f584311 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 9 Aug 2013 12:49:11 -0400 Subject: NFS: Add a slot table to struct nfs_client for NFSv4.0 transport blocking Anchor an nfs4_slot_table in the nfs_client for use with NFSv4.0 transport blocking. It is initialized only for NFSv4.0 nfs_client's. Introduce appropriate minor version ops to handle nfs_client initialization and shutdown requirements that differ for each minor version. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d2212432c456..fc83d3d384d0 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -78,6 +78,9 @@ struct nfs_client { u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; + /* NFSv4.0 transport blocking */ + struct nfs4_slot_table *cl_slot_tbl; + /* The sequence id to use for the next CREATE_SESSION */ u32 cl_seqid; /* The flags used for obtaining the clientid during EXCHANGE_ID */ -- cgit v1.2.3 From 42c7768316905dc64ad22256d6cbff273e3fbf55 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 25 Jun 2013 15:14:56 -0400 Subject: NVMe: Split header file into user-visible and kernel-visible pieces To build user programs that call the NVMe ioctls, we need to have a user header file. Catch up to the new way of doing that by splitting the header file into kernel and uapi portions. Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 461 +-------------------------------------------------- 1 file changed, 5 insertions(+), 456 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5d7c07946fbe..8d0041513e1a 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1,6 +1,6 @@ /* * Definitions for the NVM Express interface - * Copyright (c) 2011, Intel Corporation. + * Copyright (c) 2011-2013, Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -19,7 +19,10 @@ #ifndef _LINUX_NVME_H #define _LINUX_NVME_H -#include +#include +#include +#include +#include struct nvme_bar { __u64 cap; /* Controller Capabilities */ @@ -59,460 +62,8 @@ enum { NVME_CSTS_SHST_CMPLT = 2 << 2, }; -struct nvme_id_power_state { - __le16 max_power; /* centiwatts */ - __u16 rsvd2; - __le32 entry_lat; /* microseconds */ - __le32 exit_lat; /* microseconds */ - __u8 read_tput; - __u8 read_lat; - __u8 write_tput; - __u8 write_lat; - __u8 rsvd16[16]; -}; - #define NVME_VS(major, minor) (major << 16 | minor) -struct nvme_id_ctrl { - __le16 vid; - __le16 ssvid; - char sn[20]; - char mn[40]; - char fr[8]; - __u8 rab; - __u8 ieee[3]; - __u8 mic; - __u8 mdts; - __u8 rsvd78[178]; - __le16 oacs; - __u8 acl; - __u8 aerl; - __u8 frmw; - __u8 lpa; - __u8 elpe; - __u8 npss; - __u8 rsvd264[248]; - __u8 sqes; - __u8 cqes; - __u8 rsvd514[2]; - __le32 nn; - __le16 oncs; - __le16 fuses; - __u8 fna; - __u8 vwc; - __le16 awun; - __le16 awupf; - __u8 rsvd530[1518]; - struct nvme_id_power_state psd[32]; - __u8 vs[1024]; -}; - -enum { - NVME_CTRL_ONCS_COMPARE = 1 << 0, - NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, - NVME_CTRL_ONCS_DSM = 1 << 2, -}; - -struct nvme_lbaf { - __le16 ms; - __u8 ds; - __u8 rp; -}; - -struct nvme_id_ns { - __le64 nsze; - __le64 ncap; - __le64 nuse; - __u8 nsfeat; - __u8 nlbaf; - __u8 flbas; - __u8 mc; - __u8 dpc; - __u8 dps; - __u8 rsvd30[98]; - struct nvme_lbaf lbaf[16]; - __u8 rsvd192[192]; - __u8 vs[3712]; -}; - -enum { - NVME_NS_FEAT_THIN = 1 << 0, - NVME_LBAF_RP_BEST = 0, - NVME_LBAF_RP_BETTER = 1, - NVME_LBAF_RP_GOOD = 2, - NVME_LBAF_RP_DEGRADED = 3, -}; - -struct nvme_smart_log { - __u8 critical_warning; - __u8 temperature[2]; - __u8 avail_spare; - __u8 spare_thresh; - __u8 percent_used; - __u8 rsvd6[26]; - __u8 data_units_read[16]; - __u8 data_units_written[16]; - __u8 host_reads[16]; - __u8 host_writes[16]; - __u8 ctrl_busy_time[16]; - __u8 power_cycles[16]; - __u8 power_on_hours[16]; - __u8 unsafe_shutdowns[16]; - __u8 media_errors[16]; - __u8 num_err_log_entries[16]; - __u8 rsvd192[320]; -}; - -enum { - NVME_SMART_CRIT_SPARE = 1 << 0, - NVME_SMART_CRIT_TEMPERATURE = 1 << 1, - NVME_SMART_CRIT_RELIABILITY = 1 << 2, - NVME_SMART_CRIT_MEDIA = 1 << 3, - NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, -}; - -struct nvme_lba_range_type { - __u8 type; - __u8 attributes; - __u8 rsvd2[14]; - __u64 slba; - __u64 nlb; - __u8 guid[16]; - __u8 rsvd48[16]; -}; - -enum { - NVME_LBART_TYPE_FS = 0x01, - NVME_LBART_TYPE_RAID = 0x02, - NVME_LBART_TYPE_CACHE = 0x03, - NVME_LBART_TYPE_SWAP = 0x04, - - NVME_LBART_ATTRIB_TEMP = 1 << 0, - NVME_LBART_ATTRIB_HIDE = 1 << 1, -}; - -/* I/O commands */ - -enum nvme_opcode { - nvme_cmd_flush = 0x00, - nvme_cmd_write = 0x01, - nvme_cmd_read = 0x02, - nvme_cmd_write_uncor = 0x04, - nvme_cmd_compare = 0x05, - nvme_cmd_dsm = 0x09, -}; - -struct nvme_common_command { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __le32 cdw2[2]; - __le64 metadata; - __le64 prp1; - __le64 prp2; - __le32 cdw10[6]; -}; - -struct nvme_rw_command { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2; - __le64 metadata; - __le64 prp1; - __le64 prp2; - __le64 slba; - __le16 length; - __le16 control; - __le32 dsmgmt; - __le32 reftag; - __le16 apptag; - __le16 appmask; -}; - -enum { - NVME_RW_LR = 1 << 15, - NVME_RW_FUA = 1 << 14, - NVME_RW_DSM_FREQ_UNSPEC = 0, - NVME_RW_DSM_FREQ_TYPICAL = 1, - NVME_RW_DSM_FREQ_RARE = 2, - NVME_RW_DSM_FREQ_READS = 3, - NVME_RW_DSM_FREQ_WRITES = 4, - NVME_RW_DSM_FREQ_RW = 5, - NVME_RW_DSM_FREQ_ONCE = 6, - NVME_RW_DSM_FREQ_PREFETCH = 7, - NVME_RW_DSM_FREQ_TEMP = 8, - NVME_RW_DSM_LATENCY_NONE = 0 << 4, - NVME_RW_DSM_LATENCY_IDLE = 1 << 4, - NVME_RW_DSM_LATENCY_NORM = 2 << 4, - NVME_RW_DSM_LATENCY_LOW = 3 << 4, - NVME_RW_DSM_SEQ_REQ = 1 << 6, - NVME_RW_DSM_COMPRESSED = 1 << 7, -}; - -struct nvme_dsm_cmd { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 nr; - __le32 attributes; - __u32 rsvd12[4]; -}; - -enum { - NVME_DSMGMT_IDR = 1 << 0, - NVME_DSMGMT_IDW = 1 << 1, - NVME_DSMGMT_AD = 1 << 2, -}; - -struct nvme_dsm_range { - __le32 cattr; - __le32 nlb; - __le64 slba; -}; - -/* Admin commands */ - -enum nvme_admin_opcode { - nvme_admin_delete_sq = 0x00, - nvme_admin_create_sq = 0x01, - nvme_admin_get_log_page = 0x02, - nvme_admin_delete_cq = 0x04, - nvme_admin_create_cq = 0x05, - nvme_admin_identify = 0x06, - nvme_admin_abort_cmd = 0x08, - nvme_admin_set_features = 0x09, - nvme_admin_get_features = 0x0a, - nvme_admin_async_event = 0x0c, - nvme_admin_activate_fw = 0x10, - nvme_admin_download_fw = 0x11, - nvme_admin_format_nvm = 0x80, - nvme_admin_security_send = 0x81, - nvme_admin_security_recv = 0x82, -}; - -enum { - NVME_QUEUE_PHYS_CONTIG = (1 << 0), - NVME_CQ_IRQ_ENABLED = (1 << 1), - NVME_SQ_PRIO_URGENT = (0 << 1), - NVME_SQ_PRIO_HIGH = (1 << 1), - NVME_SQ_PRIO_MEDIUM = (2 << 1), - NVME_SQ_PRIO_LOW = (3 << 1), - NVME_FEAT_ARBITRATION = 0x01, - NVME_FEAT_POWER_MGMT = 0x02, - NVME_FEAT_LBA_RANGE = 0x03, - NVME_FEAT_TEMP_THRESH = 0x04, - NVME_FEAT_ERR_RECOVERY = 0x05, - NVME_FEAT_VOLATILE_WC = 0x06, - NVME_FEAT_NUM_QUEUES = 0x07, - NVME_FEAT_IRQ_COALESCE = 0x08, - NVME_FEAT_IRQ_CONFIG = 0x09, - NVME_FEAT_WRITE_ATOMIC = 0x0a, - NVME_FEAT_ASYNC_EVENT = 0x0b, - NVME_FEAT_SW_PROGRESS = 0x0c, - NVME_FWACT_REPL = (0 << 3), - NVME_FWACT_REPL_ACTV = (1 << 3), - NVME_FWACT_ACTV = (2 << 3), -}; - -struct nvme_identify { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 cns; - __u32 rsvd11[5]; -}; - -struct nvme_features { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 fid; - __le32 dword11; - __u32 rsvd12[4]; -}; - -struct nvme_create_cq { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __u64 rsvd8; - __le16 cqid; - __le16 qsize; - __le16 cq_flags; - __le16 irq_vector; - __u32 rsvd12[4]; -}; - -struct nvme_create_sq { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __u64 rsvd8; - __le16 sqid; - __le16 qsize; - __le16 sq_flags; - __le16 cqid; - __u32 rsvd12[4]; -}; - -struct nvme_delete_queue { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[9]; - __le16 qid; - __u16 rsvd10; - __u32 rsvd11[5]; -}; - -struct nvme_download_firmware { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __le64 prp2; - __le32 numd; - __le32 offset; - __u32 rsvd12[4]; -}; - -struct nvme_format_cmd { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[4]; - __le32 cdw10; - __u32 rsvd11[5]; -}; - -struct nvme_command { - union { - struct nvme_common_command common; - struct nvme_rw_command rw; - struct nvme_identify identify; - struct nvme_features features; - struct nvme_create_cq create_cq; - struct nvme_create_sq create_sq; - struct nvme_delete_queue delete_queue; - struct nvme_download_firmware dlfw; - struct nvme_format_cmd format; - struct nvme_dsm_cmd dsm; - }; -}; - -enum { - NVME_SC_SUCCESS = 0x0, - NVME_SC_INVALID_OPCODE = 0x1, - NVME_SC_INVALID_FIELD = 0x2, - NVME_SC_CMDID_CONFLICT = 0x3, - NVME_SC_DATA_XFER_ERROR = 0x4, - NVME_SC_POWER_LOSS = 0x5, - NVME_SC_INTERNAL = 0x6, - NVME_SC_ABORT_REQ = 0x7, - NVME_SC_ABORT_QUEUE = 0x8, - NVME_SC_FUSED_FAIL = 0x9, - NVME_SC_FUSED_MISSING = 0xa, - NVME_SC_INVALID_NS = 0xb, - NVME_SC_CMD_SEQ_ERROR = 0xc, - NVME_SC_LBA_RANGE = 0x80, - NVME_SC_CAP_EXCEEDED = 0x81, - NVME_SC_NS_NOT_READY = 0x82, - NVME_SC_CQ_INVALID = 0x100, - NVME_SC_QID_INVALID = 0x101, - NVME_SC_QUEUE_SIZE = 0x102, - NVME_SC_ABORT_LIMIT = 0x103, - NVME_SC_ABORT_MISSING = 0x104, - NVME_SC_ASYNC_LIMIT = 0x105, - NVME_SC_FIRMWARE_SLOT = 0x106, - NVME_SC_FIRMWARE_IMAGE = 0x107, - NVME_SC_INVALID_VECTOR = 0x108, - NVME_SC_INVALID_LOG_PAGE = 0x109, - NVME_SC_INVALID_FORMAT = 0x10a, - NVME_SC_BAD_ATTRIBUTES = 0x180, - NVME_SC_WRITE_FAULT = 0x280, - NVME_SC_READ_ERROR = 0x281, - NVME_SC_GUARD_CHECK = 0x282, - NVME_SC_APPTAG_CHECK = 0x283, - NVME_SC_REFTAG_CHECK = 0x284, - NVME_SC_COMPARE_FAILED = 0x285, - NVME_SC_ACCESS_DENIED = 0x286, -}; - -struct nvme_completion { - __le32 result; /* Used by admin commands to return data */ - __u32 rsvd; - __le16 sq_head; /* how much of this queue may be reclaimed */ - __le16 sq_id; /* submission queue that generated this entry */ - __u16 command_id; /* of the command which completed */ - __le16 status; /* did the command fail, and if so, why? */ -}; - -struct nvme_user_io { - __u8 opcode; - __u8 flags; - __u16 control; - __u16 nblocks; - __u16 rsvd; - __u64 metadata; - __u64 addr; - __u64 slba; - __u32 dsmgmt; - __u32 reftag; - __u16 apptag; - __u16 appmask; -}; - -struct nvme_admin_cmd { - __u8 opcode; - __u8 flags; - __u16 rsvd1; - __u32 nsid; - __u32 cdw2; - __u32 cdw3; - __u64 metadata; - __u64 addr; - __u32 metadata_len; - __u32 data_len; - __u32 cdw10; - __u32 cdw11; - __u32 cdw12; - __u32 cdw13; - __u32 cdw14; - __u32 cdw15; - __u32 timeout_ms; - __u32 result; -}; - -#define NVME_IOCTL_ID _IO('N', 0x40) -#define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) -#define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) - -#ifdef __KERNEL__ -#include -#include -#include - #define NVME_IO_TIMEOUT (5 * HZ) /* @@ -614,6 +165,4 @@ struct sg_io_hdr; int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); int nvme_sg_get_version_num(int __user *ip); -#endif - #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From c3bfe7176c035a0a2c70bc79180fb13a6c57142a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 8 Jul 2013 17:26:25 -0400 Subject: NVMe: Namespace IDs are unsigned The 'Number of Namespaces' read from the device was being treated as signed, which would cause us to not scan any namespaces for a device with more than 2 billion namespaces. That led to noticing that the namespace ID was also being treated as signed, which could lead to the result from NVME_IOCTL_ID being treated as an error code. Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 8d0041513e1a..3403c8f06fa0 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -104,7 +104,7 @@ struct nvme_ns { struct request_queue *queue; struct gendisk *disk; - int ns_id; + unsigned ns_id; int lba_shift; int ms; u64 mode_select_num_blocks; -- cgit v1.2.3 From 1894d8f16afe5ad54b732f0fa6c4e80bd4d40b91 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 15 Jul 2013 15:02:22 -0600 Subject: NVMe: Use normal shutdown The NVMe spec recommends using the shutdown normal sequence when safely taking the controller offline instead of hitting CC.EN on the next start-up to reset the controller. The spec recommends a minimum of 1 second for the shutdown complete. This patch waits 2 seconds to be on the safe side. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 3403c8f06fa0..26ebcf41c213 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -53,6 +53,7 @@ enum { NVME_CC_SHN_NONE = 0 << 14, NVME_CC_SHN_NORMAL = 1 << 14, NVME_CC_SHN_ABRUPT = 2 << 14, + NVME_CC_SHN_MASK = 3 << 14, NVME_CC_IOSQES = 6 << 16, NVME_CC_IOCQES = 4 << 20, NVME_CSTS_RDY = 1 << 0, @@ -60,6 +61,7 @@ enum { NVME_CSTS_SHST_NORMAL = 0 << 2, NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, + NVME_CSTS_SHST_MASK = 3 << 2, }; #define NVME_VS(major, minor) (major << 16 | minor) -- cgit v1.2.3 From 83a093b486ecfd25e7b04b82f6a388f24bd274b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 30 Aug 2013 18:08:44 +0200 Subject: net: etherdevice: add address inherit helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some etherdevices inherit their address from a parent or master device. The addr_assign_type should be updated along with the address in these cases. Adding a helper function to simplify this. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index c623861964e4..d8b512496e50 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -198,6 +198,21 @@ static inline void eth_hw_addr_random(struct net_device *dev) eth_random_addr(dev->dev_addr); } +/** + * eth_hw_addr_inherit - Copy dev_addr from another net_device + * @dst: pointer to net_device to copy dev_addr to + * @src: pointer to net_device to copy dev_addr from + * + * Copy the Ethernet address from one net_device to another along with + * the address attributes (addr_assign_type). + */ +static inline void eth_hw_addr_inherit(struct net_device *dst, + struct net_device *src) +{ + dst->addr_assign_type = src->addr_assign_type; + memcpy(dst->dev_addr, src->dev_addr, ETH_ALEN); +} + /** * compare_ether_addr - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address -- cgit v1.2.3 From bc6fc9fa0e1686d8a06aaa14005d3dbf7978d81f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 30 Aug 2013 15:36:14 +0100 Subject: net: fix comment typo for __skb_alloc_pages() The name of the function in the comment is __skb_alloc_page() while we are actually commenting __skb_alloc_pages(). Fix this typo and make it a valid kernel doc comment. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5ac96f31d546..6f1330af1ebb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1905,8 +1905,8 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } -/* - * __skb_alloc_page - allocate pages for ps-rx on a skb and preserve pfmemalloc data +/** + * __skb_alloc_pages - allocate pages for ps-rx on a skb and preserve pfmemalloc data * @gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX * @skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used * @order: size of the allocation -- cgit v1.2.3 From 8033426e6bdb2690d302872ac1e1fadaec1a5581 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 26 Jul 2013 06:23:25 -0400 Subject: vfs: allow umount to handle mountpoints without revalidating them Christopher reported a regression where he was unable to unmount a NFS filesystem where the root had gone stale. The problem is that d_revalidate handles the root of the filesystem differently from other dentries, but d_weak_revalidate does not. We could simply fix this by making d_weak_revalidate return success on IS_ROOT dentries, but there are cases where we do want to revalidate the root of the fs. A umount is really a special case. We generally aren't interested in anything but the dentry and vfsmount that's attached at that point. If the inode turns out to be stale we just don't care since the intent is to stop using it anyway. Try to handle this situation better by treating umount as a special case in the lookup code. Have it resolve the parent using normal means, and then do a lookup of the final dentry without revalidating it. In most cases, the final lookup will come out of the dcache, but the case where there's a trailing symlink or !LAST_NORM entry on the end complicates things a bit. Cc: Neil Brown Reported-by: Christopher T Vogan Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 5a5ff57ceed4..cd09751c71a0 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -58,6 +58,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); +extern int user_path_umountat(int, const char __user *, unsigned int, struct path *); #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) #define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path) -- cgit v1.2.3 From badcf2b7b816130a60152d9f5a06705176596925 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 16 Jul 2013 18:15:46 +0400 Subject: constify touch_atime() Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 981874773e85..65c9929cd340 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1804,7 +1804,7 @@ enum file_time_flags { S_VERSION = 8, }; -extern void touch_atime(struct path *); +extern void touch_atime(const struct path *); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) -- cgit v1.2.3 From ef7bca1456e7f65e66b9466c3b149601fe32eec0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Jul 2013 15:52:42 +0400 Subject: oprofile: don't bother with passing superblock to ->create_files() Signed-off-by: Al Viro --- include/linux/oprofile.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index a4c562453f6b..8a906b4034a7 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -51,7 +51,7 @@ struct pt_regs; struct oprofile_operations { /* create any necessary configuration files in the oprofile fs. * Optional. */ - int (*create_files)(struct super_block * sb, struct dentry * root); + int (*create_files)(struct dentry * root); /* Do any necessary interrupt setup. Optional. */ int (*setup)(void); /* Do any necessary interrupt shutdown. Optional. */ -- cgit v1.2.3 From ecde28237e10de3750a97579f42bc2ec65b8a0e1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Jul 2013 15:58:27 +0400 Subject: oprofilefs_mkdir() doesn't need superblock argument it's always equal to ->d_sb of the second argument (parent dentry), due to either being literally that, or ->d_sb of parent's parent. Signed-off-by: Al Viro --- include/linux/oprofile.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 8a906b4034a7..957877e7a408 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -144,8 +144,7 @@ int oprofilefs_create_ro_atomic(struct super_block * sb, struct dentry * root, char const * name, atomic_t * val); /** create a directory */ -struct dentry * oprofilefs_mkdir(struct super_block * sb, struct dentry * root, - char const * name); +struct dentry *oprofilefs_mkdir(struct dentry *parent, char const *name); /** * Write the given asciz string to the given user buffer @buf, updating *offset -- cgit v1.2.3 From 6af4ea0ba708172be8caf1ba5047b2b8a9d2fea3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Jul 2013 16:10:36 +0400 Subject: oprofilefs_create_...() do not need superblock argument same story as with oprofilefs_mkdir() Signed-off-by: Al Viro --- include/linux/oprofile.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 957877e7a408..166ef4fb4b5c 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -125,22 +125,22 @@ void oprofile_add_trace(unsigned long eip); * Create a file of the given name as a child of the given root, with * the specified file operations. */ -int oprofilefs_create_file(struct super_block * sb, struct dentry * root, +int oprofilefs_create_file(struct dentry * root, char const * name, const struct file_operations * fops); -int oprofilefs_create_file_perm(struct super_block * sb, struct dentry * root, +int oprofilefs_create_file_perm(struct dentry * root, char const * name, const struct file_operations * fops, int perm); /** Create a file for read/write access to an unsigned long. */ -int oprofilefs_create_ulong(struct super_block * sb, struct dentry * root, +int oprofilefs_create_ulong(struct dentry * root, char const * name, ulong * val); /** Create a file for read-only access to an unsigned long. */ -int oprofilefs_create_ro_ulong(struct super_block * sb, struct dentry * root, +int oprofilefs_create_ro_ulong(struct dentry * root, char const * name, ulong * val); /** Create a file for read-only access to an atomic_t. */ -int oprofilefs_create_ro_atomic(struct super_block * sb, struct dentry * root, +int oprofilefs_create_ro_atomic(struct dentry * root, char const * name, atomic_t * val); /** create a directory */ -- cgit v1.2.3 From 2b2fee80a7058959a6a9ba8706b3af5589b286d3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Jul 2013 16:13:30 +0400 Subject: oprofile: get rid of pointless forward declarations of struct super_block Signed-off-by: Al Viro --- include/linux/oprofile.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 166ef4fb4b5c..b2a0f15f11fe 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -42,7 +42,6 @@ #define IBS_FETCH_CODE 13 #define IBS_OP_CODE 14 -struct super_block; struct dentry; struct file_operations; struct pt_regs; -- cgit v1.2.3 From 8b27f27797cac5ed9b2f3e63dac89a7ae70e70a7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 2 Sep 2013 15:34:56 +0200 Subject: skb: allow skb_scrub_packet() to be used by tunnels This function was only used when a packet was sent to another netns. Now, it can also be used after tunnel encapsulation or decapsulation. Only skb_orphan() should not be done when a packet is not crossing netns. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f1330af1ebb..2ddb48d9312c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2392,7 +2392,7 @@ extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); -extern void skb_scrub_packet(struct sk_buff *skb); +extern void skb_scrub_packet(struct sk_buff *skb, bool xnet); extern struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); -- cgit v1.2.3 From 61e00655e9cb82e034eb72b95a51072e718d14a7 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Mon, 26 Aug 2013 19:14:46 +0200 Subject: Input: introduce BTN/ABS bits for drums and guitars There are a bunch of guitar and drums devices out there that all report similar data. To avoid reporting this as BTN_MISC or ABS_MISC, we allocate some proper namespace for them. Note that most of these devices are toys and we cannot report any sophisticated physics via this API. I did some google-images research and tried to provide definitions that work with all common devices. That's why I went with 4 toms, 4 cymbals, one bass, one hi-hat. I haven't seen other drums and I doubt that we need any additions to that. Anyway, the naming-scheme is intentionally done in an extensible way. For guitars, we support 5 frets (normally aligned vertically, compared to the real horizontal layouts), a single strum-bar with up/down directions, an optional fret-board and a whammy-bar. Most of the devices provide pressure values so I went with ABS_* bits. If we ever support devices which only provide digital input, we have to decide whether to emulate pressure data or add additional BTN_* bits. If someone is not familiar with these devices, here are two pictures which provide almost all introduced interfaces (or try the given keywords with a google-image search): Guitar: ("guitar hero world tour guitar") http://images1.wikia.nocookie.net/__cb20120911023442/applezone/es/images/f/f9/Wii_Guitar.jpg Drums: ("guitar hero drums") http://oyster.ignimgs.com/franchises/images/03/55/35526_band-hero-drum-set-hands-on-20090929040735768.jpg Signed-off-by: David Herrmann Acked-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index b62d4af6c667..65f8a8c4ebbc 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -277,7 +277,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_KEY_MIN_INTERESTING 0x71 #define INPUT_DEVICE_ID_KEY_MAX 0x2ff #define INPUT_DEVICE_ID_REL_MAX 0x0f -#define INPUT_DEVICE_ID_ABS_MAX 0x3f +#define INPUT_DEVICE_ID_ABS_MAX 0x4f #define INPUT_DEVICE_ID_MSC_MAX 0x07 #define INPUT_DEVICE_ID_LED_MAX 0x0f #define INPUT_DEVICE_ID_SND_MAX 0x07 -- cgit v1.2.3 From 39054a5afbb05f83aaa26f6cf55027e269744ba3 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Mon, 2 Sep 2013 14:00:05 +0200 Subject: HID: move HID_REPORT_TYPES closer to the report-definitions HID_REPORT_TYPES defines the number of available report-types. Move it closer to the actualy definition of the report-types so we can see the relation more clearly (and hopefully will never forget to update it). Signed-off-by: David Herrmann Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index d50137691a78..729bf27aac8f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -252,6 +252,8 @@ struct hid_item { #define HID_OUTPUT_REPORT 1 #define HID_FEATURE_REPORT 2 +#define HID_REPORT_TYPES 3 + /* * HID connect requests */ @@ -401,8 +403,6 @@ struct hid_report_enum { struct hid_report *report_id_hash[HID_MAX_IDS]; }; -#define HID_REPORT_TYPES 3 - #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ #define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ -- cgit v1.2.3 From 96874b9a241c543e2f32d7bd7100af4416522cfb Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 29 Aug 2013 18:05:42 -0500 Subject: ARM: edma: Add function to manually trigger an EDMA channel Manual trigger for events missed as a result of splitting a scatter gather list and DMA'ing it in batches. Add a helper function to trigger a channel incase any such events are missed. Signed-off-by: Joel Fernandes Acked-by: Sekhar Nori Signed-off-by: Vinod Koul --- include/linux/platform_data/edma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index 57300fd7cc03..179fb91bb5f2 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -180,4 +180,6 @@ struct edma_soc_info { const s16 (*xbar_chans)[2]; }; +int edma_trigger_channel(unsigned); + #endif -- cgit v1.2.3 From 7b7a8665edd8db733980389b098530f9e4f630b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Sep 2013 15:04:39 +0200 Subject: direct-io: Implement generic deferred AIO completions Add support to the core direct-io code to defer AIO completions to user context using a workqueue. This replaces opencoded and less efficient code in XFS and ext4 (we save a memory allocation for each direct IO) and will be needed to properly support O_(D)SYNC for AIO. The communication between the filesystem and the direct I/O code requires a new buffer head flag, which is a bit ugly but not avoidable until the direct I/O code stops abusing the buffer_head structure for communicating with the filesystems. Currently this creates a per-superblock unbound workqueue for these completions, which is taken from an earlier patch by Jan Kara. I'm not really convinced about this use and would prefer a "normal" global workqueue with a high concurrency limit, but this needs further discussion. JK: Fixed ext4 part, dynamic allocation of the workqueue. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Al Viro --- include/linux/buffer_head.h | 2 ++ include/linux/fs.h | 7 +++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 91fa9a94ae92..d77797a52b7b 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -36,6 +36,7 @@ enum bh_state_bits { BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ + BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities @@ -128,6 +129,7 @@ BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) +BUFFER_FNS(Defer_Completion, defer_completion) #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) diff --git a/include/linux/fs.h b/include/linux/fs.h index 65c9929cd340..c9013876eb29 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -46,6 +46,7 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; +struct workqueue_struct; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -63,8 +64,7 @@ struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, - ssize_t bytes, void *private, int ret, - bool is_async); + ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 @@ -1328,6 +1328,9 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; + + /* AIO completions deferred from interrupt context */ + struct workqueue_struct *s_dio_done_wq; }; /* superblock cache pruning functions */ -- cgit v1.2.3 From ef1820f9be27b6ad158f433ab38002ab8131db4d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 4 Sep 2013 17:04:49 +1000 Subject: NFSv4: Don't try to recover NFSv4 locks when they are lost. When an NFSv4 client loses contact with the server it can lose any locks that it holds. Currently when it reconnects to the server it simply tries to reclaim those locks. This might succeed even though some other client has held and released a lock in the mean time. So the first client might think the file is unchanged, but it isn't. This isn't good. If, when recovery happens, the locks cannot be claimed because some other client still holds the lock, then we get a message in the kernel logs, but the client can still write. So two clients can both think they have a lock and can both write at the same time. This is equally not good. There was a patch a while ago http://comments.gmane.org/gmane.linux.nfs/41917 which tried to address some of this, but it didn't seem to go anywhere. That patch would also send a signal to the process. That might be useful but for now this patch just causes writes to fail. For NFSv4 (unlike v2/v3) there is a strong link between the lock and the write request so we can fairly easily fail any IO of the lock is gone. While some applications might not expect this, it is still safer than allowing the write to succeed. Because this is a fairly big change in behaviour a module parameter, "recover_locks", is introduced which defaults to true (the current behaviour) but can be set to "false" to tell the client not to try to recover things that were lost. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index ddc3e32178c3..7c3956d65b3e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1419,12 +1419,12 @@ struct nfs_rpc_ops { void (*read_setup) (struct nfs_read_data *, struct rpc_message *); void (*read_pageio_init)(struct nfs_pageio_descriptor *, struct inode *, const struct nfs_pgio_completion_ops *); - void (*read_rpc_prepare)(struct rpc_task *, struct nfs_read_data *); + int (*read_rpc_prepare)(struct rpc_task *, struct nfs_read_data *); int (*read_done) (struct rpc_task *, struct nfs_read_data *); void (*write_setup) (struct nfs_write_data *, struct rpc_message *); void (*write_pageio_init)(struct nfs_pageio_descriptor *, struct inode *, int, const struct nfs_pgio_completion_ops *); - void (*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *); + int (*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *); int (*write_done) (struct rpc_task *, struct nfs_write_data *); void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *); void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *); -- cgit v1.2.3 From f1b6eb6e6be149b40ebb013f5bfe2ac86b6f1c1b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 4 Sep 2013 16:35:34 +0000 Subject: mm/sl[aou]b: Move kmallocXXX functions to common code The kmalloc* functions of all slab allcoators are similar now so lets move them into slab.h. This requires some function naming changes in slob. As a results of this patch there is a common set of functions for all allocators. Also means that kmalloc_large() is now available in general to perform large order allocations that go directly via the page allocator. kmalloc_large() can be substituted if kmalloc() throws warnings because of too large allocations. kmalloc_large() has exactly the same semantics as kmalloc but can only used for allocations > PAGE_SIZE. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 156 +++++++++++++++++++++++++++++++++++++---------- include/linux/slab_def.h | 106 -------------------------------- include/linux/slob_def.h | 31 ---------- include/linux/slub_def.h | 97 ----------------------------- 4 files changed, 124 insertions(+), 266 deletions(-) delete mode 100644 include/linux/slob_def.h (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 6c5cc0ea8713..386af639dcaa 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -4,6 +4,8 @@ * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. + * (C) Linux Foundation 2008-2013 + * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H @@ -94,6 +96,7 @@ #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) +#include struct mem_cgroup; /* @@ -289,6 +292,57 @@ static __always_inline int kmalloc_index(size_t size) } #endif /* !CONFIG_SLOB */ +void *__kmalloc(size_t size, gfp_t flags); +void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); + +#ifdef CONFIG_NUMA +void *__kmalloc_node(size_t size, gfp_t flags, int node); +void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +#else +static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __kmalloc(size, flags); +} + +static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) +{ + return kmem_cache_alloc(s, flags); +} +#endif + +#ifdef CONFIG_TRACING +extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); + +#ifdef CONFIG_NUMA +extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, + int node, size_t size); +#else +static __always_inline void * +kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, + int node, size_t size) +{ + return kmem_cache_alloc_trace(s, gfpflags, size); +} +#endif /* CONFIG_NUMA */ + +#else /* CONFIG_TRACING */ +static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, + gfp_t flags, size_t size) +{ + return kmem_cache_alloc(s, flags); +} + +static __always_inline void * +kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, + int node, size_t size) +{ + return kmem_cache_alloc_node(s, gfpflags, node); +} +#endif /* CONFIG_TRACING */ + #ifdef CONFIG_SLAB #include #endif @@ -297,9 +351,60 @@ static __always_inline int kmalloc_index(size_t size) #include #endif -#ifdef CONFIG_SLOB -#include +static __always_inline void * +kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret; + + flags |= (__GFP_COMP | __GFP_KMEMCG); + ret = (void *) __get_free_pages(flags, order); + kmemleak_alloc(ret, size, 1, flags); + return ret; +} + +#ifdef CONFIG_TRACING +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); +#else +static __always_inline void * +kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + return kmalloc_order(size, flags, order); +} +#endif + +static __always_inline void *kmalloc_large(size_t size, gfp_t flags) +{ + unsigned int order = get_order(size); + return kmalloc_order_trace(size, flags, order); +} + +/** + * kmalloc - allocate memory + * @size: how many bytes of memory are required. + * @flags: the type of memory to allocate (see kcalloc). + * + * kmalloc is the normal method of allocating memory + * for objects smaller than page size in the kernel. + */ +static __always_inline void *kmalloc(size_t size, gfp_t flags) +{ + if (__builtin_constant_p(size)) { + if (size > KMALLOC_MAX_CACHE_SIZE) + return kmalloc_large(size, flags); +#ifndef CONFIG_SLOB + if (!(flags & GFP_DMA)) { + int index = kmalloc_index(size); + + if (!index) + return ZERO_SIZE_PTR; + + return kmem_cache_alloc_trace(kmalloc_caches[index], + flags, size); + } #endif + } + return __kmalloc(size, flags); +} /* * Determine size used for the nth kmalloc cache. @@ -321,6 +426,23 @@ static __always_inline int kmalloc_size(int n) return 0; } +static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) +{ +#ifndef CONFIG_SLOB + if (__builtin_constant_p(size) && + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLAB_CACHE_DMA)) { + int i = kmalloc_index(size); + + if (!i) + return ZERO_SIZE_PTR; + + return kmem_cache_alloc_node_trace(kmalloc_caches[i], + flags, node, size); + } +#endif + return __kmalloc_node(size, flags, node); +} + /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer @@ -451,36 +573,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) return kmalloc_array(n, size, flags | __GFP_ZERO); } -#if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB) -/** - * kmalloc_node - allocate memory from a specific node - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kmalloc). - * @node: node to allocate from. - * - * kmalloc() for non-local nodes, used to allocate from a specific node - * if available. Equivalent to kmalloc() in the non-NUMA single-node - * case. - */ -static inline void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - return kmalloc(size, flags); -} - -static inline void *__kmalloc_node(size_t size, gfp_t flags, int node) -{ - return __kmalloc(size, flags); -} - -void *kmem_cache_alloc(struct kmem_cache *, gfp_t); - -static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep, - gfp_t flags, int node) -{ - return kmem_cache_alloc(cachep, flags); -} -#endif /* !CONFIG_NUMA && !CONFIG_SLOB */ - /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index cd401580bdd3..e9346b4f1ef4 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -3,20 +3,6 @@ /* * Definitions unique to the original Linux SLAB allocator. - * - * What we provide here is a way to optimize the frequent kmalloc - * calls in the kernel by selecting the appropriate general cache - * if kmalloc was called with a size that can be established at - * compile time. - */ - -#include -#include - -/* - * struct kmem_cache - * - * manages a cache. */ struct kmem_cache { @@ -102,96 +88,4 @@ struct kmem_cache { */ }; -void *kmem_cache_alloc(struct kmem_cache *, gfp_t); -void *__kmalloc(size_t size, gfp_t flags); - -#ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); -#else -static __always_inline void * -kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) -{ - return kmem_cache_alloc(cachep, flags); -} -#endif - -static __always_inline void *kmalloc(size_t size, gfp_t flags) -{ - struct kmem_cache *cachep; - void *ret; - - if (__builtin_constant_p(size)) { - int i; - - if (!size) - return ZERO_SIZE_PTR; - - if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) - return NULL; - - i = kmalloc_index(size); - -#ifdef CONFIG_ZONE_DMA - if (flags & GFP_DMA) - cachep = kmalloc_dma_caches[i]; - else -#endif - cachep = kmalloc_caches[i]; - - ret = kmem_cache_alloc_trace(cachep, flags, size); - - return ret; - } - return __kmalloc(size, flags); -} - -#ifdef CONFIG_NUMA -extern void *__kmalloc_node(size_t size, gfp_t flags, int node); -extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); - -#ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid, - size_t size); -#else -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid, - size_t size) -{ - return kmem_cache_alloc_node(cachep, flags, nodeid); -} -#endif - -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - struct kmem_cache *cachep; - - if (__builtin_constant_p(size)) { - int i; - - if (!size) - return ZERO_SIZE_PTR; - - if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) - return NULL; - - i = kmalloc_index(size); - -#ifdef CONFIG_ZONE_DMA - if (flags & GFP_DMA) - cachep = kmalloc_dma_caches[i]; - else -#endif - cachep = kmalloc_caches[i]; - - return kmem_cache_alloc_node_trace(cachep, flags, node, size); - } - return __kmalloc_node(size, flags, node); -} - -#endif /* CONFIG_NUMA */ - #endif /* _LINUX_SLAB_DEF_H */ diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h deleted file mode 100644 index 095a5a4a8516..000000000000 --- a/include/linux/slob_def.h +++ /dev/null @@ -1,31 +0,0 @@ -#ifndef __LINUX_SLOB_DEF_H -#define __LINUX_SLOB_DEF_H - -#include - -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); - -static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, - gfp_t flags) -{ - return kmem_cache_alloc_node(cachep, flags, NUMA_NO_NODE); -} - -void *__kmalloc_node(size_t size, gfp_t flags, int node); - -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - return __kmalloc_node(size, flags, node); -} - -static __always_inline void *kmalloc(size_t size, gfp_t flags) -{ - return __kmalloc_node(size, flags, NUMA_NO_NODE); -} - -static __always_inline void *__kmalloc(size_t size, gfp_t flags) -{ - return kmalloc(size, flags); -} - -#endif /* __LINUX_SLOB_DEF_H */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 027276fa8713..901fb6eb7467 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -6,14 +6,8 @@ * * (C) 2007 SGI, Christoph Lameter */ -#include -#include -#include -#include #include -#include - enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */ @@ -104,20 +98,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -void *kmem_cache_alloc(struct kmem_cache *, gfp_t); -void *__kmalloc(size_t size, gfp_t flags); - -static __always_inline void * -kmalloc_order(size_t size, gfp_t flags, unsigned int order) -{ - void *ret; - - flags |= (__GFP_COMP | __GFP_KMEMCG); - ret = (void *) __get_free_pages(flags, order); - kmemleak_alloc(ret, size, 1, flags); - return ret; -} - /** * Calling this on allocated memory will check that the memory * is expected to be in use, and print warnings if not. @@ -131,81 +111,4 @@ static inline bool verify_mem_not_deleted(const void *x) } #endif -#ifdef CONFIG_TRACING -extern void * -kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size); -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); -#else -static __always_inline void * -kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) -{ - return kmem_cache_alloc(s, gfpflags); -} - -static __always_inline void * -kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) -{ - return kmalloc_order(size, flags, order); -} -#endif - -static __always_inline void *kmalloc_large(size_t size, gfp_t flags) -{ - unsigned int order = get_order(size); - return kmalloc_order_trace(size, flags, order); -} - -static __always_inline void *kmalloc(size_t size, gfp_t flags) -{ - if (__builtin_constant_p(size)) { - if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); - - if (!(flags & GFP_DMA)) { - int index = kmalloc_index(size); - - if (!index) - return ZERO_SIZE_PTR; - - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } - } - return __kmalloc(size, flags); -} - -#ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node); -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); - -#ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size); -#else -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) -{ - return kmem_cache_alloc_node(s, gfpflags, node); -} -#endif - -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { - int index = kmalloc_index(size); - - if (!index) - return ZERO_SIZE_PTR; - - return kmem_cache_alloc_node_trace(kmalloc_caches[index], - flags, node, size); - } - return __kmalloc_node(size, flags, node); -} -#endif - #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 76b6f3d255a327383c89cb8c8384872dd4a0a054 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 4 Sep 2013 16:35:35 +0000 Subject: slub: remove verify_mem_not_deleted() I do not see any user for this code in the tree. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 901fb6eb7467..cc0b67eada42 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -98,17 +98,4 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -/** - * Calling this on allocated memory will check that the memory - * is expected to be in use, and print warnings if not. - */ -#ifdef CONFIG_SLUB_DEBUG -extern bool verify_mem_not_deleted(const void *x); -#else -static inline bool verify_mem_not_deleted(const void *x) -{ - return true; -} -#endif - #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 8d1018c7745e5ab861cd6cfd3dc4fa425b90575d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 4 Sep 2013 14:45:13 -0400 Subject: SUNRPC: Ensure rpc_task->tk_pid is available for tracepoints Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 6d870353674a..8ebb7c043f05 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -79,7 +79,7 @@ struct rpc_task { unsigned short tk_flags; /* misc flags */ unsigned short tk_timeouts; /* maj timeouts */ -#ifdef RPC_DEBUG +#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) unsigned short tk_pid; /* debugging aid */ #endif unsigned char tk_priority : 2,/* Task priority */ -- cgit v1.2.3 From 23774a2f6fee0848503bfb8004eeeb5adef94f5c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 4 Sep 2013 19:58:08 +0000 Subject: slab: Use correct GFP_DMA constant On Thu, 5 Sep 2013, kbuild test robot wrote: > >> include/linux/slab.h:433:53: sparse: restricted gfp_t degrades to integer > 429 static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) > 430 { > 431 #ifndef CONFIG_SLOB > 432 if (__builtin_constant_p(size) && > > 433 size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLAB_CACHE_DMA)) { > 434 int i = kmalloc_index(size); > 435 flags is of type gfp_t and not a slab internal flag. Therefore use GFP_DMA. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 386af639dcaa..74f105847d13 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -430,7 +430,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLAB_CACHE_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { int i = kmalloc_index(size); if (!i) -- cgit v1.2.3 From 2f048db4680ae19da13df15d352ac02748781ecb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 4 Sep 2013 21:51:44 -0400 Subject: SUNRPC: Add an identifier for struct rpc_clnt Add an identifier in order to aid debugging. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 76c0bf6ecd17..6740801aa71a 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -33,6 +33,7 @@ struct rpc_inode; */ struct rpc_clnt { atomic_t cl_count; /* Number of references */ + unsigned int cl_clid; /* client id */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ -- cgit v1.2.3 From 2031cd1af143f47dacacbb35efbef22f2fd079e6 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 13 Aug 2013 16:37:32 -0400 Subject: nfs4.1: Minimal SP4_MACH_CRED implementation This is a minimal client side implementation of SP4_MACH_CRED. It will attempt to negotiate SP4_MACH_CRED iff the EXCHANGE_ID is using krb5i or krb5p auth. SP4_MACH_CRED will be used if the server supports the minimal operations: BIND_CONN_TO_SESSION EXCHANGE_ID CREATE_SESSION DESTROY_SESSION DESTROY_CLIENTID This patch only includes the EXCHANGE_ID negotiation code because the client will already use the machine cred for these operations. If the server doesn't support SP4_MACH_CRED or doesn't support the minimal operations, the exchange id will be resent with SP4_NONE. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 4 ++++ include/linux/nfs_xdr.h | 19 +++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index fc83d3d384d0..9f7b9192cf5e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -90,6 +90,10 @@ struct nfs_client { struct nfs41_server_owner *cl_serverowner; struct nfs41_server_scope *cl_serverscope; struct nfs41_impl_id *cl_implid; + /* nfs 4.1+ state protection modes: */ + unsigned long cl_sp4_flags; +#define NFS_SP4_MACH_CRED_MINIMAL 1 /* Minimal sp4_mach_cred - state ops + * must use machine cred */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7c3956d65b3e..01fd84b566f7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1107,6 +1107,23 @@ struct pnfs_ds_commit_info { struct pnfs_commit_bucket *buckets; }; +#define NFS4_OP_MAP_NUM_LONGS \ + DIV_ROUND_UP(LAST_NFS4_OP, 8 * sizeof(unsigned long)) +#define NFS4_OP_MAP_NUM_WORDS \ + (NFS4_OP_MAP_NUM_LONGS * sizeof(unsigned long) / sizeof(u32)) +struct nfs4_op_map { + union { + unsigned long longs[NFS4_OP_MAP_NUM_LONGS]; + u32 words[NFS4_OP_MAP_NUM_WORDS]; + } u; +}; + +struct nfs41_state_protection { + u32 how; + struct nfs4_op_map enforce; + struct nfs4_op_map allow; +}; + #define NFS4_EXCHANGE_ID_LEN (48) struct nfs41_exchange_id_args { struct nfs_client *client; @@ -1114,6 +1131,7 @@ struct nfs41_exchange_id_args { unsigned int id_len; char id[NFS4_EXCHANGE_ID_LEN]; u32 flags; + struct nfs41_state_protection state_protect; }; struct nfs41_server_owner { @@ -1146,6 +1164,7 @@ struct nfs41_exchange_id_res { struct nfs41_server_owner *server_owner; struct nfs41_server_scope *server_scope; struct nfs41_impl_id *impl_id; + struct nfs41_state_protection state_protect; }; struct nfs41_create_session_args { -- cgit v1.2.3 From fa940720ceff2d7b24b4898c51a440ab59f39a4d Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 13 Aug 2013 16:37:34 -0400 Subject: nfs4.1: Add SP4_MACH_CRED cleanup support CLOSE and LOCKU can use the machine credential. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 9f7b9192cf5e..c0ba33874a85 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -94,6 +94,7 @@ struct nfs_client { unsigned long cl_sp4_flags; #define NFS_SP4_MACH_CRED_MINIMAL 1 /* Minimal sp4_mach_cred - state ops * must use machine cred */ +#define NFS_SP4_MACH_CRED_CLEANUP 2 /* CLOSE and LOCKU */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 8b5bee2e1b60a611b15b1862f55e60cc9f668324 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 13 Aug 2013 16:37:35 -0400 Subject: nfs4.1: Add SP4_MACH_CRED secinfo support SECINFO and SECINFO_NONAME can use the machine credential. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index c0ba33874a85..800da116950b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -95,6 +95,7 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_MINIMAL 1 /* Minimal sp4_mach_cred - state ops * must use machine cred */ #define NFS_SP4_MACH_CRED_CLEANUP 2 /* CLOSE and LOCKU */ +#define NFS_SP4_MACH_CRED_SECINFO 3 /* SECINFO and SECINFO_NO_NAME */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 3787d5063c52b0c38003e6293f24839508604070 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 13 Aug 2013 16:37:36 -0400 Subject: nfs4.1: Add SP4_MACH_CRED stateid support TEST_STATEID and FREE_STATEID can use the machine credential. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 800da116950b..179586555bbe 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -96,6 +96,7 @@ struct nfs_client { * must use machine cred */ #define NFS_SP4_MACH_CRED_CLEANUP 2 /* CLOSE and LOCKU */ #define NFS_SP4_MACH_CRED_SECINFO 3 /* SECINFO and SECINFO_NO_NAME */ +#define NFS_SP4_MACH_CRED_STATEID 4 /* TEST_STATEID and FREE_STATEID */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 8c21c62c4452f4e66c3dac9b3f6b74474fad3e08 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 13 Aug 2013 16:37:37 -0400 Subject: nfs4.1: Add SP4_MACH_CRED write and commit support WRITE and COMMIT can use the machine credential. If WRITE is supported and COMMIT is not, make all (mach cred) writes FILE_SYNC4. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 179586555bbe..e8ff178c3d33 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -97,6 +97,8 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_CLEANUP 2 /* CLOSE and LOCKU */ #define NFS_SP4_MACH_CRED_SECINFO 3 /* SECINFO and SECINFO_NO_NAME */ #define NFS_SP4_MACH_CRED_STATEID 4 /* TEST_STATEID and FREE_STATEID */ +#define NFS_SP4_MACH_CRED_WRITE 5 /* WRITE */ +#define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 53cf527513eed6e7170e9dceacd198f9267171b0 Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Wed, 4 Sep 2013 02:13:38 -0700 Subject: vxlan: Notify drivers for listening UDP port changes This patch adds two more ndo ops: ndo_add_rx_vxlan_port() and ndo_del_rx_vxlan_port(). Drivers can get notifications through the above functions about changes of the UDP listening port of VXLAN. Also, when physical ports come up, now they can call vxlan_get_rx_port() in order to obtain the port number(s) of the existing VXLAN interface in case they already up before them. This information about the listening UDP port would be used for VXLAN related offloads. A big thank you to John Fastabend (john.r.fastabend@intel.com) for his input and his suggestions on this patch set. CC: John Fastabend CC: Stephen Hemminger Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ad49b833eab..8ed4ae943053 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -948,6 +948,19 @@ struct netdev_phys_port_id { * Called to get ID of physical port of this device. If driver does * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. + * + * void (*ndo_add_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __u16 port); + * Called by vxlan to notiy a driver about the UDP port and socket + * address family that vxlan is listnening to. It is called only when + * a new port starts listening. The operation is protected by the + * vxlan_net->sock_lock. + * + * void (*ndo_del_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __u16 port); + * Called by vxlan to notify the driver about a UDP port and socket + * address family that vxlan is not listening to anymore. The operation + * is protected by the vxlan_net->sock_lock. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1078,6 +1091,12 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_port_id *ppid); + void (*ndo_add_vxlan_port)(struct net_device *dev, + sa_family_t sa_family, + __u16 port); + void (*ndo_del_vxlan_port)(struct net_device *dev, + sa_family_t sa_family, + __u16 port); }; /* -- cgit v1.2.3 From 848ac114e847af3f1f9141c90a39ebe79bdb13b3 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 5 Sep 2013 11:44:36 +0200 Subject: vfs: check submounts and drop atomically We check submounts before doing d_drop() on a non-empty directory dentry in NFS (have_submounts()), but we do not exclude a racing mount. Process A: have_submounts() -> returns false Process B: mount() -> success Process A: d_drop() This patch prepares the ground for the fix by doing the following operations all under the same rename lock: have_submounts() shrink_dcache_parent() d_drop() This is actually an optimization since have_submounts() and shrink_dcache_parent() both traverse the same dentry tree separately. Signed-off-by: Miklos Szeredi CC: David Howells CC: Steven Whitehouse CC: Trond Myklebust CC: Greg Kroah-Hartman Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9169b91ea2d2..c6d3fe50ff96 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -253,6 +253,7 @@ extern void d_prune_aliases(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int have_submounts(struct dentry *); +extern int check_submounts_and_drop(struct dentry *); /* * This adds the entry to the hash queues. -- cgit v1.2.3 From f0d3b3ded999daae1cf451d051018038c0a05bae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 5 Sep 2013 12:11:29 -0400 Subject: constify dcache.c inlined helpers where possible Signed-off-by: Al Viro --- include/linux/dcache.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c6d3fe50ff96..fe50f3db3af9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -212,7 +212,7 @@ struct dentry_operations { extern seqlock_t rename_lock; -static inline int dname_external(struct dentry *dentry) +static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } @@ -358,17 +358,17 @@ extern struct dentry *dget_parent(struct dentry *dentry); * Returns true if the dentry passed is not currently hashed. */ -static inline int d_unhashed(struct dentry *dentry) +static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } -static inline int d_unlinked(struct dentry *dentry) +static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } -static inline int cant_mount(struct dentry *dentry) +static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } @@ -382,12 +382,12 @@ static inline void dont_mount(struct dentry *dentry) extern void dput(struct dentry *); -static inline bool d_managed(struct dentry *dentry) +static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } -static inline bool d_mountpoint(struct dentry *dentry) +static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } -- cgit v1.2.3 From fd2ed4d252701d3bbed4cd3e3d267ad469bb832a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 16 Aug 2013 10:54:23 -0400 Subject: dm: add statistics support Support the collection of I/O statistics on user-defined regions of a DM device. If no regions are defined no statistics are collected so there isn't any performance impact. Only bio-based DM devices are currently supported. Each user-defined region specifies a starting sector, length and step. Individual statistics will be collected for each step-sized area within the range specified. The I/O statistics counters for each step-sized area of a region are in the same format as /sys/block/*/stat or /proc/diskstats but extra counters (12 and 13) are provided: total time spent reading and writing in milliseconds. All these counters may be accessed by sending the @stats_print message to the appropriate DM device via dmsetup. The creation of DM statistics will allocate memory via kmalloc or fallback to using vmalloc space. At most, 1/4 of the overall system memory may be allocated by DM statistics. The admin can see how much memory is used by reading /sys/module/dm_mod/parameters/stats_current_allocated_bytes See Documentation/device-mapper/statistics.txt for more details. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e151d4c9298d..653073de09e3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -10,6 +10,7 @@ #include #include +#include #include struct dm_dev; @@ -550,6 +551,14 @@ extern struct ratelimit_state dm_ratelimit_state; #define DM_MAPIO_REMAPPED 1 #define DM_MAPIO_REQUEUE DM_ENDIO_REQUEUE +#define dm_sector_div64(x, y)( \ +{ \ + u64 _res; \ + (x) = div64_u64_rem(x, y, &_res); \ + _res; \ +} \ +) + /* * Ceiling(n / sz) */ -- cgit v1.2.3 From da9803bc8812f5bd3b26baaa90e515b843c65ff7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 21 Aug 2013 17:29:38 -0400 Subject: FS-Cache: Add interface to check consistency of a cached object Extend the fscache netfs API so that the netfs can ask as to whether a cache object is up to date with respect to its corresponding netfs object: int fscache_check_consistency(struct fscache_cookie *cookie) This will call back to the netfs to check whether the auxiliary data associated with a cookie is correct. It returns 0 if it is and -ESTALE if it isn't; it may also return -ENOMEM and -ERESTARTSYS. The backends now have to implement a mandatory operation pointer: int (*check_consistency)(struct fscache_object *object) that corresponds to the above API call. FS-Cache takes care of pinning the object and the cookie in memory and managing this call with respect to the object state. Original-author: Hongyi Jia Signed-off-by: David Howells cc: Hongyi Jia cc: Milosz Tanski --- include/linux/fscache-cache.h | 4 ++++ include/linux/fscache.h | 20 ++++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index a9ff9a36b86d..7823e9ef995e 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -251,6 +251,10 @@ struct fscache_cache_ops { /* unpin an object in the cache */ void (*unpin_object)(struct fscache_object *object); + /* check the consistency between the backing cache and the FS-Cache + * cookie */ + bool (*check_consistency)(struct fscache_operation *op); + /* store the updated auxiliary data on an object */ void (*update_object)(struct fscache_object *object); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7a086235da4b..d984aff32a11 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -183,6 +183,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie( const struct fscache_cookie_def *, void *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, int); +extern int __fscache_check_consistency(struct fscache_cookie *); extern void __fscache_update_cookie(struct fscache_cookie *); extern int __fscache_attr_changed(struct fscache_cookie *); extern void __fscache_invalidate(struct fscache_cookie *); @@ -325,6 +326,25 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) __fscache_relinquish_cookie(cookie, retire); } +/** + * fscache_check_consistency - Request that if the cache is updated + * @cookie: The cookie representing the cache object + * + * Request an consistency check from fscache, which passes the request + * to the backing cache. + * + * Returns 0 if consistent and -ESTALE if inconsistent. May also + * return -ENOMEM and -ERESTARTSYS. + */ +static inline +int fscache_check_consistency(struct fscache_cookie *cookie) +{ + if (fscache_cookie_valid(cookie)) + return __fscache_check_consistency(cookie); + else + return 0; +} + /** * fscache_update_cookie - Request that a cache object be updated * @cookie: The cookie representing the cache object -- cgit v1.2.3 From 5a6f282a2052bb13171b53f03b34501cf72c33f1 Mon Sep 17 00:00:00 2001 From: Milosz Tanski Date: Wed, 21 Aug 2013 17:30:11 -0400 Subject: fscache: Netfs function for cleanup post readpages Currently the fscache code expect the netfs to call fscache_readpages_or_alloc inside the aops readpages callback. It marks all the pages in the list provided by readahead with PG_private_2. In the cases that the netfs fails to read all the pages (which is legal) it ends up returning to the readahead and triggering a BUG. This happens because the page list still contains marked pages. This patch implements a simple fscache_readpages_cancel function that the netfs should call before returning from readpages. It will revoke the pages from the underlying cache backend and unmark them. The problem was originally worked out in the Ceph devel tree, but it also occurs in CIFS. It appears that NFS, AFS and 9P are okay as read_cache_pages() will clean up the unprocessed pages in the case of an error. This can be used to address the following oops: [12410647.597278] BUG: Bad page state in process petabucket pfn:3d504e [12410647.597292] page:ffffea000f541380 count:0 mapcount:0 mapping: (null) index:0x0 [12410647.597298] page flags: 0x200000000001000(private_2) ... [12410647.597334] Call Trace: [12410647.597345] [] dump_stack+0x19/0x1b [12410647.597356] [] bad_page+0xc7/0x120 [12410647.597359] [] free_pages_prepare+0x10e/0x120 [12410647.597361] [] free_hot_cold_page+0x40/0x170 [12410647.597363] [] __put_single_page+0x27/0x30 [12410647.597365] [] put_page+0x25/0x40 [12410647.597376] [] ceph_readpages+0x2e9/0x6e0 [ceph] [12410647.597379] [] __do_page_cache_readahead+0x1af/0x260 [12410647.597382] [] ra_submit+0x21/0x30 [12410647.597384] [] filemap_fault+0x254/0x490 [12410647.597387] [] __do_fault+0x6f/0x4e0 [12410647.597391] [] ? __switch_to+0x16d/0x4a0 [12410647.597395] [] ? finish_task_switch+0x5a/0xc0 [12410647.597398] [] handle_pte_fault+0xf6/0x930 [12410647.597401] [] ? pte_mfn_to_pfn+0x93/0x110 [12410647.597403] [] ? xen_pmd_val+0xe/0x10 [12410647.597405] [] ? __raw_callee_save_xen_pmd_val+0x11/0x1e [12410647.597407] [] handle_mm_fault+0x251/0x370 [12410647.597411] [] ? call_rwsem_down_read_failed+0x14/0x30 [12410647.597414] [] __do_page_fault+0x1aa/0x550 [12410647.597418] [] ? up_write+0x1d/0x20 [12410647.597422] [] ? vm_mmap_pgoff+0xbc/0xe0 [12410647.597425] [] ? SyS_mmap_pgoff+0xd8/0x240 [12410647.597427] [] do_page_fault+0xe/0x10 [12410647.597431] [] page_fault+0x28/0x30 Signed-off-by: Milosz Tanski Signed-off-by: David Howells --- include/linux/fscache.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index d984aff32a11..19b46458e4e8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -209,6 +209,8 @@ extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, gfp_t); extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, struct inode *); +extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, + struct list_head *pages); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -589,6 +591,26 @@ int fscache_alloc_page(struct fscache_cookie *cookie, return -ENOBUFS; } +/** + * fscache_readpages_cancel - Cancel read/alloc on pages + * @cookie: The cookie representing the inode's cache object. + * @pages: The netfs pages that we canceled write on in readpages() + * + * Uncache/unreserve the pages reserved earlier in readpages() via + * fscache_readpages_or_alloc() and similar. In most successful caches in + * readpages() this doesn't do anything. In cases when the underlying netfs's + * readahead failed we need to clean up the pagelist (unmark and uncache). + * + * This function may sleep as it may have to clean up disk state. + */ +static inline +void fscache_readpages_cancel(struct fscache_cookie *cookie, + struct list_head *pages) +{ + if (fscache_cookie_valid(cookie)) + __fscache_readpages_cancel(cookie, pages); +} + /** * fscache_write_page - Request storage of a page in the cache * @cookie: The cookie representing the cache object -- cgit v1.2.3 From 9d731e7539713acc0ec7b67a5a91357c455d2334 Mon Sep 17 00:00:00 2001 From: Chris Ball Date: Fri, 6 Sep 2013 07:29:05 -0400 Subject: Revert "mmc: tmio-mmc: Remove .set_pwr() callback from platform data" This reverts commit 3af9d15c719017feb63fa99f89ac6009a5a3d467, which causes a build failure: drivers/mfd/asic3.c:724:2: error: unknown field 'set_pwr' specified in initializer --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index baa23464a1e6..b22883d60500 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -106,6 +106,7 @@ struct tmio_mmc_data { struct tmio_mmc_dma *dma; struct device *dev; unsigned int cd_gpio; + void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); int (*write16_hook)(struct tmio_mmc_host *host, int addr); /* clock management callbacks */ -- cgit v1.2.3 From 0042d0c840c616186a5b09207a0e77fab7581db3 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 6 Sep 2013 16:58:00 +0100 Subject: net: add documentation for BQL helpers Provide a kernel-doc comment documentation for the BQL helpers: - netdev_sent_queue - netdev_completed_queue - netdev_reset_queue Similarly to how it is done for the other functions, the documentation only covers the function operating on struct net_device and not struct netdev_queue. Signed-off-by: Florian Fainelli Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8ed4ae943053..041b42a305f6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2101,6 +2101,15 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/** + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes + */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); @@ -2130,6 +2139,16 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, #endif } +/** + * netdev_completed_queue - report bytes and packets completed by device + * @dev: network device + * @pkts: actual number of packets sent over the medium + * @bytes: actual number of bytes sent over the medium + * + * Report the number of bytes and packets transmitted by the network device + * hardware queue over the physical medium, @bytes must exactly match the + * @bytes amount passed to netdev_sent_queue() + */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { @@ -2144,6 +2163,13 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) #endif } +/** + * netdev_reset_queue - reset the packets and bytes count of a network device + * @dev_queue: network device + * + * Reset the bytes and packet count of a network device and clear the + * software flow control OFF bit for this network device + */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); -- cgit v1.2.3 From 0e20162ed1e9a639fc61d62c71327169fb1a1970 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 6 Sep 2013 14:14:00 -0400 Subject: NFSv4.1 Use MDS auth flavor for data server connection Commit 4edaa308 "NFS: Use "krb5i" to establish NFSv4 state whenever possible" uses the nfs_client cl_rpcclient for all state management operations, and will use krb5i or auth_sys with no regard to the mount command authflavor choice. The MDS, as any NFSv4.1 mount point, uses the nfs_server rpc client for all non-state management operations with a different nfs_server for each fsid encountered traversing the mount point, each with a potentially different auth flavor. pNFS data servers are not mounted in the normal sense as there is no associated nfs_server structure. Data servers can also export multiple fsids, each with a potentially different auth flavor. Data servers need to use the same authflavor as the MDS server rpc client for non-state management operations. Populate a list of rpc clients with the MDS server rpc client auth flavor for the DS to use. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e8ff178c3d33..b8cedced50c9 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -56,6 +56,7 @@ struct nfs_client { struct rpc_cred *cl_machine_cred; #if IS_ENABLED(CONFIG_NFS_V4) + struct list_head cl_ds_clients; /* auth flavor data servers */ u64 cl_clientid; /* constant */ nfs4_verifier cl_confirm; /* Clientid verifier */ unsigned long cl_state; -- cgit v1.2.3 From 68411521cc6055edc6274e03ab3210a5893533ba Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 7 Sep 2013 12:56:26 +1000 Subject: Reinstate "crypto: crct10dif - Wrap crc_t10dif function all to use crypto transform framework" This patch reinstates commits 67822649d7305caf3dd50ed46c27b99c94eff996 39761214eefc6b070f29402aa1165f24d789b3f7 0b95a7f85718adcbba36407ef88bba0a7379ed03 31d939625a9a20b1badd2d4e6bf6fd39fa523405 2d31e518a42828df7877bca23a958627d60408bc Now that module softdeps are in the kernel we can use that to resolve the boot issue which cause the revert. Signed-off-by: Herbert Xu --- include/linux/crc-t10dif.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index a9c96d865ee7..b3cb71f0d3b0 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -3,6 +3,10 @@ #include +#define CRC_T10DIF_DIGEST_SIZE 2 +#define CRC_T10DIF_BLOCK_SIZE 1 + +__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); __u16 crc_t10dif(unsigned char const *, size_t); #endif -- cgit v1.2.3 From b04c99e3b845892d754ee8052d6324c39c4040de Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 7 Sep 2013 09:48:41 -0700 Subject: Revert "Input: introduce BTN/ABS bits for drums and guitars" This reverts commits 61e00655e9cb, 73f8645db191 and 8e22ecb603c8: "Input: introduce BTN/ABS bits for drums and guitars" "HID: wiimote: add support for Guitar-Hero drums" "HID: wiimote: add support for Guitar-Hero guitars" The extra new ABS_xx values resulted in ABS_MAX no longer being a power-of-two, which broke the comparison logic. It also caused the ioctl numbers to overflow into the next byte, causing problems for that. We'll try again for 3.13. Reported-by: Markus Trippelsdorf Reported-by: Linus Torvalds Acked-by: David Herrmann Acked-by: Dmitry Torokhov Cc: Benjamin Tissoires Signed-off-by: Linus Torvalds --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 329aa307cb77..45e921401b06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -277,7 +277,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_KEY_MIN_INTERESTING 0x71 #define INPUT_DEVICE_ID_KEY_MAX 0x2ff #define INPUT_DEVICE_ID_REL_MAX 0x0f -#define INPUT_DEVICE_ID_ABS_MAX 0x4f +#define INPUT_DEVICE_ID_ABS_MAX 0x3f #define INPUT_DEVICE_ID_MSC_MAX 0x07 #define INPUT_DEVICE_ID_LED_MAX 0x0f #define INPUT_DEVICE_ID_SND_MAX 0x07 -- cgit v1.2.3 From e7d33bb5ea82922e6ddcfc6b28a630b1a4ced071 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 7 Sep 2013 15:49:18 -0700 Subject: lockref: add ability to mark lockrefs "dead" The only actual current lockref user (dcache) uses zero reference counts even for perfectly live dentries, because it's a cache: there may not be any users, but that doesn't mean that we want to throw away the dentry. At the same time, the dentry cache does have a notion of a truly "dead" dentry that we must not even increment the reference count of, because we have pruned it and it is not valid. Currently that distinction is not visible in the lockref itself, and the dentry cache validation uses "lockref_get_or_lock()" to either get a new reference to a dentry that already had existing references (and thus cannot be dead), or get the dentry lock so that we can then verify the dentry and increment the reference count under the lock if that verification was successful. That's all somewhat complicated. This adds the concept of being "dead" to the lockref itself, by simply using a count that is negative. This allows a usage scenario where we can increment the refcount of a dentry without having to validate it, and pushing the special "we killed it" case into the lockref code. The dentry code itself doesn't actually use this yet, and it's probably too late in the merge window to do that code (the dentry_kill() code with its "should I decrement the count" logic really is pretty complex code), but let's introduce the concept at the lockref level now. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index ca07b5028b01..f279ed9a9163 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -33,4 +33,7 @@ extern int lockref_get_not_zero(struct lockref *); extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); +extern void lockref_mark_dead(struct lockref *); +extern int lockref_get_not_dead(struct lockref *); + #endif /* __LINUX_LOCKREF_H */ -- cgit v1.2.3 From 4e10f3c98888ee88ea2543aa636db6410fa47477 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 30 Aug 2013 12:29:49 -0400 Subject: Kill indirect include of file.h from eventfd.h, use fdget() in cgroup.c kernel/cgroup.c is the only place in the tree that relies on eventfd.h pulling file.h; move that include there. Switch from eventfd_fget()/fput() to fdget()/fdput(), while we are at it - eventfd_ctx_fileget() will fail on non-eventfd descriptors just fine, no need to do that check twice... Signed-off-by: Al Viro --- include/linux/eventfd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index cf5d2af61b81..ff0b981f078e 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -9,7 +9,6 @@ #define _LINUX_EVENTFD_H #include -#include #include /* @@ -26,6 +25,8 @@ #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) +struct file; + #ifdef CONFIG_EVENTFD struct file *eventfd_file_create(unsigned int count, int flags); -- cgit v1.2.3 From 8aab6a27332bbf2abfcb35224738394e784d940b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 Sep 2013 13:26:18 -0700 Subject: vfs: reorganize dput() memory accesses This is me being a bit OCD after all the dentry optimization work this merge window: profiles end up showing 'dput()' as a rather expensive operation, and there were two unrelated bad reasons for that. The first reason was reading d_lockref.count for debugging purposes, which touches the lockref cacheline (for reads) before really need to. More importantly, the debugging test in question is _wrong_, and has hidden bugs. It's true that we can only sleep when the count goes down to zero, but the test as-is hides the much more subtle bug that happens if we race with somebody else deleting the file. Anyway we _will_ touch that cacheline, but let's do it for a write and in the right routine (ie in "lockref_put_or_lock()") which annotates the costs better. So remove the misleading debug code. The other was an unnecessary access to the cacheline that contains the d_lru list, just to check whether we already were on the LRU list or not. This is exactly what we have d_flags for, so that we can avoid touching extra cache lines for the common case. So just add another bit for "is this dentry on the LRU". Finally, mark the tests properly likely/unlikely, so that the common fast-paths are dense in the instruction stream. This makes the profiles look much saner. Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index fe50f3db3af9..feaa8d88eef7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -208,6 +208,7 @@ struct dentry_operations { #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) +#define DCACHE_LRU_LIST 0x80000 #define DCACHE_DENTRY_KILLED 0x100000 extern seqlock_t rename_lock; -- cgit v1.2.3 From 197df04c749a07616621b762e699b1fff4102fac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 8 Sep 2013 14:03:27 -0400 Subject: rename user_path_umountat() to user_path_mountpoint_at() ... and move the extern from linux/namei.h to fs/internal.h, along with that of vfs_path_lookup(). Signed-off-by: Al Viro --- include/linux/namei.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index cd09751c71a0..53c18f00d9fb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -58,7 +58,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -extern int user_path_umountat(int, const char __user *, unsigned int, struct path *); #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) #define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path) @@ -71,8 +70,6 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); -extern int vfs_path_lookup(struct dentry *, struct vfsmount *, - const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -- cgit v1.2.3 From 2d8646510120bb1eb251ae3381e950805a877763 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 8 Sep 2013 20:18:44 -0400 Subject: introduce kern_path_mountpoint() Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 53c18f00d9fb..8e47bc7a1665 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -70,6 +70,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -- cgit v1.2.3 From dd935f44a40f8fb02aff2cc0df2269c92422df1c Mon Sep 17 00:00:00 2001 From: Josh Durgin Date: Wed, 28 Aug 2013 21:43:09 -0700 Subject: libceph: add function to ensure notifies are complete Without a way to flush the osd client's notify workqueue, a watch event that is unregistered could continue receiving callbacks indefinitely. Unregistering the event simply means no new notifies are added to the queue, but there may still be events in the queue that will call the watch callback for the event. If the queue is flushed after the event is unregistered, the caller can be sure no more watch callbacks will occur for the canceled watch. Signed-off-by: Josh Durgin Reviewed-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ce6df39f60ff..8f47625a0661 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -335,6 +335,8 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); extern void ceph_osdc_sync(struct ceph_osd_client *osdc); +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc); + extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_vino vino, struct ceph_file_layout *layout, -- cgit v1.2.3 From 798ab48eecdf659df9ae0064ca5c62626c651827 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 16 Aug 2013 22:04:37 +0000 Subject: idr: Percpu ida Percpu frontend for allocating ids. With percpu allocation (that works), it's impossible to guarantee it will always be possible to allocate all nr_tags - typically, some will be stuck on a remote percpu freelist where the current job can't get to them. We do guarantee that it will always be possible to allocate at least (nr_tags / 2) tags - this is done by keeping track of which and how many cpus have tags on their percpu freelists. On allocation failure if enough cpus have tags that there could potentially be (nr_tags / 2) tags stuck on remote percpu freelists, we then pick a remote cpu at random to steal from. Note that there's no cpu hotplug notifier - we don't care, because steal_tags() will eventually get the down cpu's tags. We _could_ satisfy more allocations if we had a notifier - but we'll still meet our guarantees and it's absolutely not a correctness issue, so I don't think it's worth the extra code. From akpm: "It looks OK to me (that's as close as I get to an ack :)) v6 changes: - Add #include to include/linux/percpu_ida.h to make alpha/arc builds happy (Fengguang) - Move second (cpu >= nr_cpu_ids) check inside of first check scope in steal_tags() (akpm + nab) v5 changes: - Change percpu_ida->cpus_have_tags to cpumask_t (kmo + akpm) - Add comment for percpu_ida_cpu->lock + ->nr_free (kmo + akpm) - Convert steal_tags() to use cpumask_weight() + cpumask_next() + cpumask_first() + cpumask_clear_cpu() (kmo + akpm) - Add comment for alloc_global_tags() (kmo + akpm) - Convert percpu_ida_alloc() to use cpumask_set_cpu() (kmo + akpm) - Convert percpu_ida_free() to use cpumask_set_cpu() (kmo + akpm) - Drop percpu_ida->cpus_have_tags allocation in percpu_ida_init() (kmo + akpm) - Drop percpu_ida->cpus_have_tags kfree in percpu_ida_destroy() (kmo + akpm) - Add comment for percpu_ida_alloc @ gfp (kmo + akpm) - Move to percpu_ida.c + percpu_ida.h (kmo + akpm + nab) v4 changes: - Fix tags.c reference in percpu_ida_init (akpm) Signed-off-by: Kent Overstreet Cc: Tejun Heo Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Ingo Molnar Cc: Andi Kleen Cc: Jens Axboe Cc: "Nicholas A. Bellinger" Signed-off-by: Nicholas Bellinger --- include/linux/percpu_ida.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) create mode 100644 include/linux/percpu_ida.h (limited to 'include/linux') diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h new file mode 100644 index 000000000000..0b23edbee309 --- /dev/null +++ b/include/linux/percpu_ida.h @@ -0,0 +1,60 @@ +#ifndef __PERCPU_IDA_H__ +#define __PERCPU_IDA_H__ + +#include +#include +#include +#include +#include +#include + +struct percpu_ida_cpu; + +struct percpu_ida { + /* + * number of tags available to be allocated, as passed to + * percpu_ida_init() + */ + unsigned nr_tags; + + struct percpu_ida_cpu __percpu *tag_cpu; + + /* + * Bitmap of cpus that (may) have tags on their percpu freelists: + * steal_tags() uses this to decide when to steal tags, and which cpus + * to try stealing from. + * + * It's ok for a freelist to be empty when its bit is set - steal_tags() + * will just keep looking - but the bitmap _must_ be set whenever a + * percpu freelist does have tags. + */ + cpumask_t cpus_have_tags; + + struct { + spinlock_t lock; + /* + * When we go to steal tags from another cpu (see steal_tags()), + * we want to pick a cpu at random. Cycling through them every + * time we steal is a bit easier and more or less equivalent: + */ + unsigned cpu_last_stolen; + + /* For sleeping on allocation failure */ + wait_queue_head_t wait; + + /* + * Global freelist - it's a stack where nr_free points to the + * top + */ + unsigned nr_free; + unsigned *freelist; + } ____cacheline_aligned_in_smp; +}; + +int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp); +void percpu_ida_free(struct percpu_ida *pool, unsigned tag); + +void percpu_ida_destroy(struct percpu_ida *pool); +int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags); + +#endif /* __PERCPU_IDA_H__ */ -- cgit v1.2.3 From 4a43f394a08214eaf92cdd8ce3eae75e555323d8 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Mon, 9 Sep 2013 16:51:59 -0700 Subject: dmaengine: dma_sync_wait and dma_find_channel undefined dma_sync_wait and dma_find_channel are declared regardless of whether CONFIG_DMA_ENGINE is enabled, but calling the function without CONFIG_DMA_ENGINE enabled results "undefined reference" errors. To get around this, declare dma_sync_wait and dma_find_channel as inline functions if CONFIG_DMA_ENGINE is undefined. Signed-off-by: Jon Mason Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index b3ba7e410943..0c72b89a172c 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -961,8 +961,9 @@ dma_set_tx_state(struct dma_tx_state *st, dma_cookie_t last, dma_cookie_t used, } } -enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE +struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); +enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, @@ -970,6 +971,14 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); void dma_release_channel(struct dma_chan *chan); #else +static inline struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) +{ + return NULL; +} +static inline enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie) +{ + return DMA_SUCCESS; +} static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { return DMA_SUCCESS; @@ -997,7 +1006,6 @@ static inline void dma_release_channel(struct dma_chan *chan) int dma_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); -struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); struct dma_chan *net_dma_find_channel(void); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) #define dma_request_slave_channel_compat(mask, x, y, dev, name) \ -- cgit v1.2.3 From 19c763031acb831a5ab9c1a701b7fedda073eb3f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Sat, 31 Aug 2013 17:48:23 +0530 Subject: cpufreq: serialize calls to __cpufreq_governor() We can't take a big lock around __cpufreq_governor() as this causes recursive locking for some cases. But calls to this routine must be serialized for every policy. Otherwise we can see some unpredictable events. For example, consider following scenario: __cpufreq_remove_dev() __cpufreq_governor(policy, CPUFREQ_GOV_STOP); policy->governor->governor(policy, CPUFREQ_GOV_STOP); cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: mutex_destroy(&cpu_cdbs->timer_mutex) cpu_cdbs->cur_policy = NULL; store() __cpufreq_set_policy() __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); policy->governor->governor(policy, CPUFREQ_GOV_LIMITS); case CPUFREQ_GOV_LIMITS: mutex_lock(&cpu_cdbs->timer_mutex); <-- Warning (destroyed mutex) if (policy->max < cpu_cdbs->cur_policy->cur) <- cur_policy == NULL And so store() will eventually result in a crash if cur_policy is NULL at this point. Introduce an additional variable which would guarantee serialization here. Reported-by: Stephen Boyd Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d568f3975eeb..cca885dac1d3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -76,6 +76,7 @@ struct cpufreq_policy { struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ + bool governor_busy; struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ -- cgit v1.2.3 From 56d07db274b7b15ca38b60ea4a762d40de093000 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Sat, 7 Sep 2013 01:23:55 +0530 Subject: cpufreq: Remove temporary fix for race between CPU hotplug and sysfs-writes Commit "cpufreq: serialize calls to __cpufreq_governor()" had been a temporary and partial solution to the race condition between writing to a cpufreq sysfs file and taking a CPU offline. Now that we have a proper and complete solution to that problem, remove the temporary fix. Signed-off-by: Srivatsa S. Bhat Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index cca885dac1d3..d568f3975eeb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -76,7 +76,6 @@ struct cpufreq_policy { struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ - bool governor_busy; struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ -- cgit v1.2.3 From 798282a8718347b04a2f0a4bae7d775c48c6bcb9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 10 Sep 2013 02:54:50 +0200 Subject: Revert "cpufreq: make sure frequency transitions are serialized" Commit 7c30ed5 (cpufreq: make sure frequency transitions are serialized) attempted to serialize frequency transitions by adding checks to the CPUFREQ_PRECHANGE and CPUFREQ_POSTCHANGE notifications. However, it assumed that the notifications will always originate from the driver's .target() callback, but they also can be triggered by cpufreq_out_of_sync() and that leads to warnings like this on some systems: WARNING: CPU: 0 PID: 14543 at drivers/cpufreq/cpufreq.c:317 __cpufreq_notify_transition+0x238/0x260() In middle of another frequency transition accompanied by a call trace similar to this one: [] dump_stack+0x46/0x58 [] warn_slowpath_common+0x8c/0xc0 [] ? acpi_cpufreq_target+0x320/0x320 [] warn_slowpath_fmt+0x46/0x50 [] __cpufreq_notify_transition+0x238/0x260 [] cpufreq_notify_transition+0x3e/0x70 [] cpufreq_out_of_sync+0x6d/0xb0 [] cpufreq_update_policy+0x10c/0x160 [] ? cpufreq_update_policy+0x160/0x160 [] cpufreq_set_cur_state+0x8c/0xb5 [] processor_set_cur_state+0xa3/0xcf [] thermal_cdev_update+0x9c/0xb0 [] step_wise_throttle+0x5a/0x90 [] handle_thermal_trip+0x4f/0x140 [] thermal_zone_device_update+0x57/0xa0 [] acpi_thermal_check+0x2e/0x30 [] acpi_thermal_notify+0x40/0xdc [] acpi_device_notify+0x19/0x1b [] acpi_ev_notify_dispatch+0x41/0x5c [] acpi_os_execute_deferred+0x25/0x32 [] process_one_work+0x170/0x4a0 [] worker_thread+0x121/0x390 [] ? manage_workers.isra.20+0x170/0x170 [] kthread+0xc0/0xd0 [] ? flush_kthread_worker+0xb0/0xb0 [] ret_from_fork+0x7c/0xb0 [] ? flush_kthread_worker+0xb0/0xb0 For this reason, revert commit 7c30ed5 along with the fix 266c13d (cpufreq: Fix serialization of frequency transitions) on top of it and we will revisit the serialization problem later. Reported-by: Alessandro Bono Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d568f3975eeb..fcabc42d66ab 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -85,7 +85,6 @@ struct cpufreq_policy { struct list_head policy_list; struct kobject kobj; struct completion kobj_unregister; - int transition_ongoing; /* Tracks transition status */ }; /* Only for ACPI */ -- cgit v1.2.3 From 97b9f53d7deb3b8c0acdeb52a5801f9f5080ce0f Mon Sep 17 00:00:00 2001 From: Mike Miller Date: Wed, 4 Sep 2013 15:05:55 -0500 Subject: [SCSI] hpsa: add HP Smart Array Gen9 PCI ID's This patch adds the PCI ID's for HP Smart Array Gen9 controllers. Please consider this patch for inclusion. Signed-off-by: Mike Miller Signed-off-by: James Bottomley --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bed2e89611b..2ce39261fc91 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -756,6 +756,7 @@ #define PCI_DEVICE_ID_HP_CISSE 0x323a #define PCI_DEVICE_ID_HP_CISSF 0x323b #define PCI_DEVICE_ID_HP_CISSH 0x323c +#define PCI_DEVICE_ID_HP_CISSI 0x3239 #define PCI_DEVICE_ID_HP_ZX2_IOC 0x4031 #define PCI_VENDOR_ID_PCTECH 0x1042 -- cgit v1.2.3 From aac34df11791d25417f7d756dc277b6f95996b47 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Sep 2013 07:16:41 -0700 Subject: fs: remove vfs_follow_link For a long time no filesystem has been using vfs_follow_link, and as seen by recent filesystem submissions any new use is accidental as well. Remove vfs_follow_link, document the replacement in Documentation/filesystems/porting and also rename __vfs_follow_link to match its only caller better. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 529d8711baba..49e71b0f0e9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2494,7 +2494,6 @@ extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int vfs_readlink(struct dentry *, char __user *, int, const char *); -extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern void *page_follow_link_light(struct dentry *, struct nameidata *); extern void page_put_link(struct dentry *, struct nameidata *, void *); -- cgit v1.2.3 From 3942c07ccf98e66b8893f396dca98f5b076f905f Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:17:53 +1000 Subject: fs: bump inode and dentry counters to long MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: Dave Chinner Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 10 +++++----- include/linux/fs.h | 4 ++-- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index feaa8d88eef7..844a1ef387e4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,11 +55,11 @@ struct qstr { #define hashlen_len(hashlen) ((u32)((hashlen) >> 32)) struct dentry_stat_t { - int nr_dentry; - int nr_unused; - int age_limit; /* age in seconds */ - int want_pages; /* pages requested by system */ - int dummy[2]; + long nr_dentry; + long nr_unused; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long dummy[2]; }; extern struct dentry_stat_t dentry_stat; diff --git a/include/linux/fs.h b/include/linux/fs.h index 49e71b0f0e9f..3b3edac75df2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1271,12 +1271,12 @@ struct super_block { struct list_head s_mounts; /* list of mounts; _not_ for fs use */ /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ - int s_nr_dentry_unused; /* # of dentry on lru */ + long s_nr_dentry_unused; /* # of dentry on lru */ /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; struct list_head s_inode_lru; /* unused inode lru */ - int s_nr_inodes_unused; /* # of inodes on lru */ + long s_nr_inodes_unused; /* # of inodes on lru */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; -- cgit v1.2.3 From 55f841ce9395a72c6285fbcc4c403c0c786e1c74 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:17:53 +1000 Subject: super: fix calculation of shrinkable objects for small numbers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sysctl knob sysctl_vfs_cache_pressure is used to determine which percentage of the shrinkable objects in our cache we should actively try to shrink. It works great in situations in which we have many objects (at least more than 100), because the aproximation errors will be negligible. But if this is not the case, specially when total_objects < 100, we may end up concluding that we have no objects at all (total / 100 = 0, if total < 100). This is certainly not the biggest killer in the world, but may matter in very low kernel memory situations. Signed-off-by: Glauber Costa Reviewed-by: Carlos Maiolino Acked-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Cc: Dave Chinner Cc: Al Viro Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 844a1ef387e4..59066e0b4ff1 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -395,4 +395,8 @@ static inline bool d_mountpoint(const struct dentry *dentry) extern int sysctl_vfs_cache_pressure; +static inline unsigned long vfs_pressure_ratio(unsigned long val) +{ + return mult_frac(val, sysctl_vfs_cache_pressure, 100); +} #endif /* __LINUX_DCACHE_H */ -- cgit v1.2.3 From 19156840e33a23eeb1a749c0f991dab6588b077d Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:55 +1000 Subject: dentry: move to per-sb LRU locks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the dentry LRUs being per-sb structures, there is no real need for a global dentry_lru_lock. The locking can be made more fine-grained by moving to a per-sb LRU lock, isolating the LRU operations of different filesytsems completely from each other. The need for this is independent of any performance consideration that may arise: in the interest of abstracting the lru operations away, it is mandatory that each lru works around its own lock instead of a global lock for all of them. [glommer@openvz.org: updated changelog ] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Reviewed-by: Christoph Hellwig Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3b3edac75df2..14a90f6886fa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1269,7 +1269,9 @@ struct super_block { struct list_head s_files; #endif struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ + + /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */ + spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp; struct list_head s_dentry_lru; /* unused dentry lru */ long s_nr_dentry_unused; /* # of dentry on lru */ -- cgit v1.2.3 From 24f7c6b981fb70084757382da464ea85d72af300 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:56 +1000 Subject: mm: new shrinker API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current shrinker callout API uses an a single shrinker call for multiple functions. To determine the function, a special magical value is passed in a parameter to change the behaviour. This complicates the implementation and return value specification for the different behaviours. Separate the two different behaviours into separate operations, one to return a count of freeable objects in the cache, and another to scan a certain number of objects in the cache for freeing. In defining these new operations, ensure the return values and resultant behaviours are clearly defined and documented. Modify shrink_slab() to use the new API and implement the callouts for all the existing shrinkers. Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/shrinker.h | 38 +++++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index ac6b8ee07825..884e76222e1b 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -4,6 +4,12 @@ /* * This struct is used to pass information from page reclaim to the shrinkers. * We consolidate the values for easier extention later. + * + * The 'gfpmask' refers to the allocation we are currently trying to + * fulfil. + * + * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is + * querying the cache size, so a fastpath for that case is appropriate. */ struct shrink_control { gfp_t gfp_mask; @@ -12,23 +18,37 @@ struct shrink_control { unsigned long nr_to_scan; }; +#define SHRINK_STOP (~0UL) /* * A callback you can register to apply pressure to ageable caches. * - * 'sc' is passed shrink_control which includes a count 'nr_to_scan' - * and a 'gfpmask'. It should look through the least-recently-used - * 'nr_to_scan' entries and attempt to free them up. It should return - * the number of objects which remain in the cache. If it returns -1, it means - * it cannot do any scanning at this time (eg. there is a risk of deadlock). + * @shrink() should look through the least-recently-used 'nr_to_scan' entries + * and attempt to free them up. It should return the number of objects which + * remain in the cache. If it returns -1, it means it cannot do any scanning at + * this time (eg. there is a risk of deadlock). * - * The 'gfpmask' refers to the allocation we are currently trying to - * fulfil. + * @count_objects should return the number of freeable items in the cache. If + * there are no objects to free or the number of freeable items cannot be + * determined, it should return 0. No deadlock checks should be done during the + * count callback - the shrinker relies on aggregating scan counts that couldn't + * be executed due to potential deadlocks to be run at a later call when the + * deadlock condition is no longer pending. * - * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is - * querying the cache size, so a fastpath for that case is appropriate. + * @scan_objects will only be called if @count_objects returned a non-zero + * value for the number of freeable objects. The callout should scan the cache + * and attempt to free items from the cache. It should then return the number + * of objects freed during the scan, or SHRINK_STOP if progress cannot be made + * due to potential deadlocks. If SHRINK_STOP is returned, then no further + * attempts to call the @scan_objects will be made from the current reclaim + * context. */ struct shrinker { int (*shrink)(struct shrinker *, struct shrink_control *sc); + unsigned long (*count_objects)(struct shrinker *, + struct shrink_control *sc); + unsigned long (*scan_objects)(struct shrinker *, + struct shrink_control *sc); + int seeks; /* seeks to recreate an obj */ long batch; /* reclaim batch size, 0 = default */ -- cgit v1.2.3 From 0a234c6dcb79a270803f5c9773ed650b78730962 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:57 +1000 Subject: shrinker: convert superblock shrinkers to new API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 14a90f6886fa..0ae0bc3c1fde 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1335,10 +1335,6 @@ struct super_block { struct workqueue_struct *s_dio_done_wq; }; -/* superblock cache pruning functions */ -extern void prune_icache_sb(struct super_block *sb, int nr_to_scan); -extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan); - extern struct timespec current_fs_time(struct super_block *sb); /* @@ -1631,8 +1627,8 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - int (*nr_cached_objects)(struct super_block *); - void (*free_cached_objects)(struct super_block *, int); + long (*nr_cached_objects)(struct super_block *); + long (*free_cached_objects)(struct super_block *, long); }; /* -- cgit v1.2.3 From a38e40824844a5ec85f3ea95632be953477d2afa Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:58 +1000 Subject: list: add a new LRU list type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Several subsystems use the same construct for LRU lists - a list head, a spin lock and and item count. They also use exactly the same code for adding and removing items from the LRU. Create a generic type for these LRU lists. This is the beginning of generic, node aware LRUs for shrinkers to work with. [glommer@openvz.org: enum defined constants for lru. Suggested by gthelen, don't relock over retry] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Reviewed-by: Greg Thelen Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/list_lru.h | 115 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 115 insertions(+) create mode 100644 include/linux/list_lru.h (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h new file mode 100644 index 000000000000..1a548b0b7578 --- /dev/null +++ b/include/linux/list_lru.h @@ -0,0 +1,115 @@ +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#ifndef _LRU_LIST_H +#define _LRU_LIST_H + +#include + +/* list_lru_walk_cb has to always return one of those */ +enum lru_status { + LRU_REMOVED, /* item removed from list */ + LRU_ROTATE, /* item referenced, give another pass */ + LRU_SKIP, /* item cannot be locked, skip */ + LRU_RETRY, /* item not freeable. May drop the lock + internally, but has to return locked. */ +}; + +struct list_lru { + spinlock_t lock; + struct list_head list; + /* kept as signed so we can catch imbalance bugs */ + long nr_items; +}; + +int list_lru_init(struct list_lru *lru); + +/** + * list_lru_add: add an element to the lru list's tail + * @list_lru: the lru pointer + * @item: the item to be added. + * + * If the element is already part of a list, this function returns doing + * nothing. Therefore the caller does not need to keep state about whether or + * not the element already belongs in the list and is allowed to lazy update + * it. Note however that this is valid for *a* list, not *this* list. If + * the caller organize itself in a way that elements can be in more than + * one type of list, it is up to the caller to fully remove the item from + * the previous list (with list_lru_del() for instance) before moving it + * to @list_lru + * + * Return value: true if the list was updated, false otherwise + */ +bool list_lru_add(struct list_lru *lru, struct list_head *item); + +/** + * list_lru_del: delete an element to the lru list + * @list_lru: the lru pointer + * @item: the item to be deleted. + * + * This function works analogously as list_lru_add in terms of list + * manipulation. The comments about an element already pertaining to + * a list are also valid for list_lru_del. + * + * Return value: true if the list was updated, false otherwise + */ +bool list_lru_del(struct list_lru *lru, struct list_head *item); + +/** + * list_lru_count: return the number of objects currently held by @lru + * @lru: the lru pointer. + * + * Always return a non-negative number, 0 for empty lists. There is no + * guarantee that the list is not updated while the count is being computed. + * Callers that want such a guarantee need to provide an outer lock. + */ +static inline unsigned long list_lru_count(struct list_lru *lru) +{ + return lru->nr_items; +} + +typedef enum lru_status +(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); +/** + * list_lru_walk: walk a list_lru, isolating and disposing freeable items. + * @lru: the lru pointer. + * @isolate: callback function that is resposible for deciding what to do with + * the item currently being scanned + * @cb_arg: opaque type that will be passed to @isolate + * @nr_to_walk: how many items to scan. + * + * This function will scan all elements in a particular list_lru, calling the + * @isolate callback for each of those items, along with the current list + * spinlock and a caller-provided opaque. The @isolate callback can choose to + * drop the lock internally, but *must* return with the lock held. The callback + * will return an enum lru_status telling the list_lru infrastructure what to + * do with the object being scanned. + * + * Please note that nr_to_walk does not mean how many objects will be freed, + * just how many objects will be scanned. + * + * Return value: the number of objects effectively removed from the LRU. + */ +unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, + void *cb_arg, unsigned long nr_to_walk); + +typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list); +/** + * list_lru_dispose_all: forceably flush all elements in an @lru + * @lru: the lru pointer + * @dispose: callback function to be called for each lru list. + * + * This function will forceably isolate all elements into the dispose list, and + * call the @dispose callback to flush the list. Please note that the callback + * should expect items in any state, clean or dirty, and be able to flush all of + * them. + * + * Return value: how many objects were freed. It should be equal to all objects + * in the list_lru. + */ +unsigned long +list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose); +#endif /* _LRU_LIST_H */ -- cgit v1.2.3 From bc3b14cb2d505dda969dbe3a31038dbb24aca945 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:58 +1000 Subject: inode: convert inode lru list to generic lru list code. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [glommer@openvz.org: adapted for new LRU return codes] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0ae0bc3c1fde..e04786569c28 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -1275,10 +1276,7 @@ struct super_block { struct list_head s_dentry_lru; /* unused dentry lru */ long s_nr_dentry_unused; /* # of dentry on lru */ - /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ - spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; - struct list_head s_inode_lru; /* unused inode lru */ - long s_nr_inodes_unused; /* # of inodes on lru */ + struct list_lru s_inode_lru ____cacheline_aligned_in_smp; struct block_device *s_bdev; struct backing_dev_info *s_bdi; -- cgit v1.2.3 From f604156751db77e08afe47ce29fe8f3d51ad9b04 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:00 +1000 Subject: dcache: convert to use new lru list infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [glommer@openvz.org: don't reintroduce double decrement of nr_unused_dentries, adapted for new LRU return codes] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e04786569c28..36e45df87f6e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1270,14 +1270,6 @@ struct super_block { struct list_head s_files; #endif struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - - /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */ - spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp; - struct list_head s_dentry_lru; /* unused dentry lru */ - long s_nr_dentry_unused; /* # of dentry on lru */ - - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; - struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; @@ -1331,6 +1323,13 @@ struct super_block { /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; + + /* + * Keep the lru lists last in the structure so they always sit on their + * own individual cachelines. + */ + struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; + struct list_lru s_inode_lru ____cacheline_aligned_in_smp; }; extern struct timespec current_fs_time(struct super_block *sb); -- cgit v1.2.3 From 3b1d58a4c96799eb4c92039e1b851b86f853548a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:00 +1000 Subject: list_lru: per-node list infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that we have an LRU list API, we can start to enhance the implementation. This splits the single LRU list into per-node lists and locks to enhance scalability. Items are placed on lists according to the node the memory belongs to. To make scanning the lists efficient, also track whether the per-node lists have entries in them in a active nodemask. Note: We use a fixed-size array for the node LRU, this struct can be very big if MAX_NUMNODES is big. If this becomes a problem this is fixable by turning this into a pointer and dynamically allocating this to nr_node_ids. This quantity is firwmare-provided, and still would provide room for all nodes at the cost of a pointer lookup and an extra allocation. Because that allocation will most likely come from a may very well fail. [glommer@openvz.org: fix warnings, added note about node lru] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Reviewed-by: Greg Thelen Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/list_lru.h | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 1a548b0b7578..f4d4cb608c02 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -8,6 +8,7 @@ #define _LRU_LIST_H #include +#include /* list_lru_walk_cb has to always return one of those */ enum lru_status { @@ -18,11 +19,26 @@ enum lru_status { internally, but has to return locked. */ }; -struct list_lru { +struct list_lru_node { spinlock_t lock; struct list_head list; /* kept as signed so we can catch imbalance bugs */ long nr_items; +} ____cacheline_aligned_in_smp; + +struct list_lru { + /* + * Because we use a fixed-size array, this struct can be very big if + * MAX_NUMNODES is big. If this becomes a problem this is fixable by + * turning this into a pointer and dynamically allocating this to + * nr_node_ids. This quantity is firwmare-provided, and still would + * provide room for all nodes at the cost of a pointer lookup and an + * extra allocation. Because that allocation will most likely come from + * a different slab cache than the main structure holding this + * structure, we may very well fail. + */ + struct list_lru_node node[MAX_NUMNODES]; + nodemask_t active_nodes; }; int list_lru_init(struct list_lru *lru); @@ -66,10 +82,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item); * guarantee that the list is not updated while the count is being computed. * Callers that want such a guarantee need to provide an outer lock. */ -static inline unsigned long list_lru_count(struct list_lru *lru) -{ - return lru->nr_items; -} +unsigned long list_lru_count(struct list_lru *lru); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); -- cgit v1.2.3 From 6a4f496fd2fc74fa036732ae52c184952d6e3e37 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:18:02 +1000 Subject: list_lru: per-node API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adapts the list_lru API to accept an optional node argument, to be used by NUMA aware shrinking functions. Code that does not care about the NUMA placement of objects can still call into the very same functions as before. They will simply iterate over all nodes. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/list_lru.h | 39 ++++++++++++++++++++++++++++++++++----- 1 file changed, 34 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index f4d4cb608c02..2fe13e1a809a 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -75,20 +75,32 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item); bool list_lru_del(struct list_lru *lru, struct list_head *item); /** - * list_lru_count: return the number of objects currently held by @lru + * list_lru_count_node: return the number of objects currently held by @lru * @lru: the lru pointer. + * @nid: the node id to count from. * * Always return a non-negative number, 0 for empty lists. There is no * guarantee that the list is not updated while the count is being computed. * Callers that want such a guarantee need to provide an outer lock. */ -unsigned long list_lru_count(struct list_lru *lru); +unsigned long list_lru_count_node(struct list_lru *lru, int nid); +static inline unsigned long list_lru_count(struct list_lru *lru) +{ + long count = 0; + int nid; + + for_each_node_mask(nid, lru->active_nodes) + count += list_lru_count_node(lru, nid); + + return count; +} typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); /** - * list_lru_walk: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items. * @lru: the lru pointer. + * @nid: the node id to scan from. * @isolate: callback function that is resposible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate @@ -106,8 +118,25 @@ typedef enum lru_status * * Return value: the number of objects effectively removed from the LRU. */ -unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, - void *cb_arg, unsigned long nr_to_walk); +unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); + +static inline unsigned long +list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, + void *cb_arg, unsigned long nr_to_walk) +{ + long isolated = 0; + int nid; + + for_each_node_mask(nid, lru->active_nodes) { + isolated += list_lru_walk_node(lru, nid, isolate, + cb_arg, &nr_to_walk); + if (nr_to_walk <= 0) + break; + } + return isolated; +} typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list); /** -- cgit v1.2.3 From 4e717f5c1083995c334ced639cc77a75e9972567 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:18:03 +1000 Subject: list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa Cc: Michal Hocko Acked-by: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/list_lru.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 2fe13e1a809a..4d02ad3badab 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -137,21 +137,4 @@ list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, } return isolated; } - -typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list); -/** - * list_lru_dispose_all: forceably flush all elements in an @lru - * @lru: the lru pointer - * @dispose: callback function to be called for each lru list. - * - * This function will forceably isolate all elements into the dispose list, and - * call the @dispose callback to flush the list. Please note that the callback - * should expect items in any state, clean or dirty, and be able to flush all of - * them. - * - * Return value: how many objects were freed. It should be equal to all objects - * in the list_lru. - */ -unsigned long -list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose); #endif /* _LRU_LIST_H */ -- cgit v1.2.3 From 0ce3d74450815500e31f16a0b65f6bab687985c3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:03 +1000 Subject: shrinker: add node awareness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pass the node of the current zone being reclaimed to shrink_slab(), allowing the shrinker control nodemask to be set appropriately for node aware shrinkers. Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/shrinker.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 884e76222e1b..76f520c4c394 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -16,6 +16,9 @@ struct shrink_control { /* How many slab objects shrinker() should scan and try to reclaim */ unsigned long nr_to_scan; + + /* shrink from these nodes */ + nodemask_t nodes_to_scan; }; #define SHRINK_STOP (~0UL) -- cgit v1.2.3 From 1d3d4437eae1bb2963faab427f65f90663c64aa1 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:18:04 +1000 Subject: vmscan: per-node deferred work MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The list_lru infrastructure already keeps per-node LRU lists in its node-specific list_lru_node arrays and provide us with a per-node API, and the shrinkers are properly equiped with node information. This means that we can now focus our shrinking effort in a single node, but the work that is deferred from one run to another is kept global at nr_in_batch. Work can be deferred, for instance, during direct reclaim under a GFP_NOFS allocation, where situation, all the filesystem shrinkers will be prevented from running and accumulate in nr_in_batch the amount of work they should have done, but could not. This creates an impedance problem, where upon node pressure, work deferred will accumulate and end up being flushed in other nodes. The problem we describe is particularly harmful in big machines, where many nodes can accumulate at the same time, all adding to the global counter nr_in_batch. As we accumulate more and more, we start to ask for the caches to flush even bigger numbers. The result is that the caches are depleted and do not stabilize. To achieve stable steady state behavior, we need to tackle it differently. In this patch we keep the deferred count per-node, in the new array nr_deferred[] (the name is also a bit more descriptive) and will never accumulate that to other nodes. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/shrinker.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 76f520c4c394..8f80f243fed9 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -19,6 +19,8 @@ struct shrink_control { /* shrink from these nodes */ nodemask_t nodes_to_scan; + /* current node being shrunk (for NUMA aware shrinkers) */ + int nid; }; #define SHRINK_STOP (~0UL) @@ -44,6 +46,8 @@ struct shrink_control { * due to potential deadlocks. If SHRINK_STOP is returned, then no further * attempts to call the @scan_objects will be made from the current reclaim * context. + * + * @flags determine the shrinker abilities, like numa awareness */ struct shrinker { int (*shrink)(struct shrinker *, struct shrink_control *sc); @@ -54,12 +58,18 @@ struct shrinker { int seeks; /* seeks to recreate an obj */ long batch; /* reclaim batch size, 0 = default */ + unsigned long flags; /* These are for internal use */ struct list_head list; - atomic_long_t nr_in_batch; /* objs pending delete */ + /* objs pending delete, per node */ + atomic_long_t *nr_deferred; }; #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ -extern void register_shrinker(struct shrinker *); + +/* Flags */ +#define SHRINKER_NUMA_AWARE (1 << 0) + +extern int register_shrinker(struct shrinker *); extern void unregister_shrinker(struct shrinker *); #endif -- cgit v1.2.3 From 9b17c62382dd2e7507984b9890bf44e070cdd8bb Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:05 +1000 Subject: fs: convert inode and dentry shrinking to be node aware MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the shrinker is passing a node in the scan control structure, we can pass this to the the generic LRU list code to isolate reclaim to the lists on matching nodes. Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 36e45df87f6e..a4acd3c61190 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1624,8 +1624,8 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - long (*nr_cached_objects)(struct super_block *); - long (*free_cached_objects)(struct super_block *, long); + long (*nr_cached_objects)(struct super_block *, int); + long (*free_cached_objects)(struct super_block *, long, int); }; /* -- cgit v1.2.3 From a0b02131c5fcd8545b867db72224b3659e813f10 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:16 +1000 Subject: shrinker: Kill old ->shrink API. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no more users of this API, so kill it dead, dead, dead and quietly bury the corpse in a shallow, unmarked grave in a dark forest deep in the hills... [glommer@openvz.org: added flowers to the grave] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Reviewed-by: Greg Thelen Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/shrinker.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 8f80f243fed9..68c097077ef0 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -7,14 +7,15 @@ * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. - * - * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is - * querying the cache size, so a fastpath for that case is appropriate. */ struct shrink_control { gfp_t gfp_mask; - /* How many slab objects shrinker() should scan and try to reclaim */ + /* + * How many objects scan_objects should scan and try to reclaim. + * This is reset before every call, so it is safe for callees + * to modify. + */ unsigned long nr_to_scan; /* shrink from these nodes */ @@ -27,11 +28,6 @@ struct shrink_control { /* * A callback you can register to apply pressure to ageable caches. * - * @shrink() should look through the least-recently-used 'nr_to_scan' entries - * and attempt to free them up. It should return the number of objects which - * remain in the cache. If it returns -1, it means it cannot do any scanning at - * this time (eg. there is a risk of deadlock). - * * @count_objects should return the number of freeable items in the cache. If * there are no objects to free or the number of freeable items cannot be * determined, it should return 0. No deadlock checks should be done during the @@ -50,7 +46,6 @@ struct shrink_control { * @flags determine the shrinker abilities, like numa awareness */ struct shrinker { - int (*shrink)(struct shrinker *, struct shrink_control *sc); unsigned long (*count_objects)(struct shrinker *, struct shrink_control *sc); unsigned long (*scan_objects)(struct shrinker *, -- cgit v1.2.3 From 5ca302c8e502ca53b7d75f12127ec0289904003a Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:18:18 +1000 Subject: list_lru: dynamically adjust node arrays MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We currently use a compile-time constant to size the node array for the list_lru structure. Due to this, we don't need to allocate any memory at initialization time. But as a consequence, the structures that contain embedded list_lru lists can become way too big (the superblock for instance contains two of them). This patch aims at ameliorating this situation by dynamically allocating the node arrays with the firmware provided nr_node_ids. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/list_lru.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 4d02ad3badab..3ce541753c88 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -27,20 +27,11 @@ struct list_lru_node { } ____cacheline_aligned_in_smp; struct list_lru { - /* - * Because we use a fixed-size array, this struct can be very big if - * MAX_NUMNODES is big. If this becomes a problem this is fixable by - * turning this into a pointer and dynamically allocating this to - * nr_node_ids. This quantity is firwmare-provided, and still would - * provide room for all nodes at the cost of a pointer lookup and an - * extra allocation. Because that allocation will most likely come from - * a different slab cache than the main structure holding this - * structure, we may very well fail. - */ - struct list_lru_node node[MAX_NUMNODES]; + struct list_lru_node *node; nodemask_t active_nodes; }; +void list_lru_destroy(struct list_lru *lru); int list_lru_init(struct list_lru *lru); /** -- cgit v1.2.3 From 3b8967d713d7426e9dd107d065208b84adface91 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 11 Sep 2013 14:19:37 -0700 Subject: include/linux/smp.h:on_each_cpu(): switch back to a C function Revert commit c846ef7deba2 ("include/linux/smp.h:on_each_cpu(): switch back to a macro"). It turns out that the problematic linux/irqflags.h include was fixed within ia64 and mn10300. Cc: Geert Uytterhoeven Cc: David Daney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index c181399f2c20..c8488763277f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -11,6 +11,7 @@ #include #include #include +#include extern void cpu_idle(void); @@ -139,14 +140,17 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info) } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) -#define on_each_cpu(func, info, wait) \ - ({ \ - unsigned long __flags; \ - local_irq_save(__flags); \ - func(info); \ - local_irq_restore(__flags); \ - 0; \ - }) + +static inline int on_each_cpu(smp_call_func_t func, void *info, int wait) +{ + unsigned long flags; + + local_irq_save(flags); + func(info); + local_irq_restore(flags); + return 0; +} + /* * Note we still need to test the mask even for UP * because we actually can get an empty mask from -- cgit v1.2.3 From e1403b8edf669ff49bbdf602cc97fefa2760cb15 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 11 Sep 2013 14:20:06 -0700 Subject: include/linux/sched.h: don't use task->pid/tgid in same_thread_group/has_group_leader_pid task_struct->pid/tgid should go away. 1. Change same_thread_group() to use task->signal for comparison. 2. Change has_group_leader_pid(task) to compare task_pid(task) with signal->leader_pid. Signed-off-by: Oleg Nesterov Cc: Michal Hocko Cc: Sergey Dyasly Reviewed-by: "Eric W. Biederman" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ce1e1c0aaa33..45f254dddafc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2169,15 +2169,15 @@ static inline bool thread_group_leader(struct task_struct *p) * all we care about is that we have a task with the appropriate * pid, we don't actually care if we have the right task. */ -static inline int has_group_leader_pid(struct task_struct *p) +static inline bool has_group_leader_pid(struct task_struct *p) { - return p->pid == p->tgid; + return task_pid(p) == p->signal->leader_pid; } static inline -int same_thread_group(struct task_struct *p1, struct task_struct *p2) +bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { - return p1->tgid == p2->tgid; + return p1->signal == p2->signal; } static inline struct task_struct *next_thread(const struct task_struct *p) -- cgit v1.2.3 From bab55417b10c95e6bff8cea315c315adfa009487 Mon Sep 17 00:00:00 2001 From: Cai Zhiyong Date: Wed, 11 Sep 2013 14:20:09 -0700 Subject: block: support embedded device command line partition Read block device partition table from command line. The partition used for fixed block device (eMMC) embedded device. It is no MBR, save storage space. Bootloader can be easily accessed by absolute address of data on the block device. Users can easily change the partition. This code reference MTD partition, source "drivers/mtd/cmdlinepart.c" About the partition verbose reference "Documentation/block/cmdline-partition.txt" [akpm@linux-foundation.org: fix printk text] [yongjun_wei@trendmicro.com.cn: fix error return code in parse_parts()] Signed-off-by: Cai Zhiyong Cc: Karel Zak Cc: "Wanglin (Albert)" Cc: Marius Groeger Cc: David Woodhouse Cc: Jens Axboe Cc: Brian Norris Cc: Artem Bityutskiy Signed-off-by: Wei Yongjun Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cmdline-parser.h | 43 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 include/linux/cmdline-parser.h (limited to 'include/linux') diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h new file mode 100644 index 000000000000..98e892ef6d5a --- /dev/null +++ b/include/linux/cmdline-parser.h @@ -0,0 +1,43 @@ +/* + * Parsing command line, get the partitions information. + * + * Written by Cai Zhiyong + * + */ +#ifndef CMDLINEPARSEH +#define CMDLINEPARSEH + +#include + +/* partition flags */ +#define PF_RDONLY 0x01 /* Device is read only */ +#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */ + +struct cmdline_subpart { + char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */ + sector_t from; + sector_t size; + int flags; + struct cmdline_subpart *next_subpart; +}; + +struct cmdline_parts { + char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */ + unsigned int nr_subparts; + struct cmdline_subpart *subpart; + struct cmdline_parts *next_parts; +}; + +void cmdline_parts_free(struct cmdline_parts **parts); + +int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline); + +struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, + const char *bdev); + +void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, + int slot, + int (*add_part)(int, struct cmdline_subpart *, void *), + void *param); + +#endif /* CMDLINEPARSEH */ -- cgit v1.2.3 From ef0855d334e1e4af7c3e0c42146a8479ea14a5ab Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 11 Sep 2013 14:20:14 -0700 Subject: mm: mempolicy: turn vma_set_policy() into vma_dup_policy() Simple cleanup. Every user of vma_set_policy() does the same work, this looks a bit annoying imho. And the new trivial helper which does mpol_dup() + vma_set_policy() to simplify the callers. Signed-off-by: Oleg Nesterov Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0d7df39a5885..b2f897789838 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -91,7 +91,6 @@ static inline struct mempolicy *mpol_dup(struct mempolicy *pol) } #define vma_policy(vma) ((vma)->vm_policy) -#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol)) static inline void mpol_get(struct mempolicy *pol) { @@ -126,6 +125,7 @@ struct shared_policy { spinlock_t lock; }; +int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, @@ -240,7 +240,12 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) } #define vma_policy(vma) NULL -#define vma_set_policy(vma, pol) do {} while(0) + +static inline int +vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + return 0; +} static inline void numa_policy_init(void) { -- cgit v1.2.3 From 9824cf9753ecbe8f5b47aa9b2f218207defea211 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 11 Sep 2013 14:20:23 -0700 Subject: mm: vmstats: tlb flush counters I was investigating some TLB flush scaling issues and realized that we do not have any good methods for figuring out how many TLB flushes we are doing. It would be nice to be able to do these in generic code, but the arch-independent calls don't explicitly specify whether we actually need to do remote flushes or not. In the end, we really need to know if we actually _did_ global vs. local invalidations, so that leaves us with few options other than to muck with the counters from arch-specific code. Signed-off-by: Dave Hansen Cc: Peter Zijlstra Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index bd6cf61142be..dc2cdf07ac14 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -70,6 +70,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif + NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ + NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ + NR_TLB_LOCAL_FLUSH_ALL, + NR_TLB_LOCAL_FLUSH_ONE, + NR_TLB_LOCAL_FLUSH_ONE_KERNEL, NR_VM_EVENT_ITEMS }; -- cgit v1.2.3 From 6df46865ff8715932e7d42e52cac17e8461758cb Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 11 Sep 2013 14:20:24 -0700 Subject: mm: vmstats: track TLB flush stats on UP too The previous patch doing vmstats for TLB flushes ("mm: vmstats: tlb flush counters") effectively missed UP since arch/x86/mm/tlb.c is only compiled for SMP. UP systems do not do remote TLB flushes, so compile those counters out on UP. arch/x86/kernel/cpu/mtrr/generic.c calls __flush_tlb() directly. This is probably an optimization since both the mtrr code and __flush_tlb() write cr4. It would probably be safe to make that a flush_tlb_all() (and then get these statistics), but the mtrr code is ancient and I'm hesitant to touch it other than to just stick in the counters. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Dave Hansen Cc: Peter Zijlstra Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index dc2cdf07ac14..1855f0a22add 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -70,11 +70,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ +#endif NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, - NR_TLB_LOCAL_FLUSH_ONE_KERNEL, NR_VM_EVENT_ITEMS }; -- cgit v1.2.3 From 2a8f9449343260373398d59228a62a4332ea513a Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:28 -0700 Subject: swap: change block allocation algorithm for SSD I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to 20~30% CPU time (when cluster is hard to find, the CPU time can be up to 80%), which becomes a bottleneck. scan_swap_map() scans a byte array to search a 256 page cluster, which is very slow. Here I introduced a simple algorithm to search cluster. Since we only care about 256 pages cluster, we can just use a counter to track if a cluster is free. Every 256 pages use one int to store the counter. If the counter of a cluster is 0, the cluster is free. All free clusters will be added to a list, so searching cluster is very efficient. With this, scap_swap_map() overhead disappears. This might help low end SD card swap too. Because if the cluster is aligned, SD firmware can do flash erase more efficiently. We only enable the algorithm for SSD. Hard disk swap isn't fast enough and has downside with the algorithm which might introduce regression (see below). The patch slightly changes which cluster is choosen. It always adds free cluster to list tail. This can help wear leveling for low end SSD too. And if no cluster found, the scan_swap_map() will do search from the end of last cluster. So if no cluster found, the scan_swap_map() will do search from the end of last free cluster, which is random. For SSD, this isn't a problem at all. Another downside is the cluster must be aligned to 256 pages, which will reduce the chance to find a cluster. I would expect this isn't a big problem for SSD because of the non-seek penality. (And this is the reason I only enable the algorithm for SSD). Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d95cde5e257d..cb5baebf31d6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -181,6 +181,23 @@ enum { #define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */ +/* + * We use this to track usage of a cluster. A cluster is a block of swap disk + * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All + * free clusters are organized into a list. We fetch an entry from the list to + * get a free cluster. + * + * The data field stores next cluster if the cluster is free or cluster usage + * counter otherwise. The flags field determines if a cluster is free. This is + * protected by swap_info_struct.lock. + */ +struct swap_cluster_info { + unsigned int data:24; + unsigned int flags:8; +}; +#define CLUSTER_FLAG_FREE 1 /* This cluster is free */ +#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ + /* * The in-memory structure used to track swap areas. */ @@ -191,6 +208,9 @@ struct swap_info_struct { signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ + struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ + struct swap_cluster_info free_cluster_head; /* free cluster list head */ + struct swap_cluster_info free_cluster_tail; /* free cluster list tail */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ -- cgit v1.2.3 From 815c2c543d3aeb914a361f981440ece552778724 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:30 -0700 Subject: swap: make swap discard async swap can do cluster discard for SSD, which is good, but there are some problems here: 1. swap do the discard just before page reclaim gets a swap entry and writes the disk sectors. This is useless for high end SSD, because an overwrite to a sector implies a discard to original sector too. A discard + overwrite == overwrite. 2. the purpose of doing discard is to improve SSD firmware garbage collection. Idealy we should send discard as early as possible, so firmware can do something smart. Sending discard just after swap entry is freed is considered early compared to sending discard before write. Of course, if workload is already bound to gc speed, sending discard earlier or later doesn't make 3. block discard is a sync API, which will delay scan_swap_map() significantly. 4. Write and discard command can be executed parallel in PCIe SSD. Making swap discard async can make execution more efficiently. This patch makes swap discard async and moves discard to where swap entry is freed. Discard and write have no dependence now, so above issues can be avoided. Idealy we should do discard for any freed sectors, but some SSD discard is very slow. This patch still does discard for a whole cluster. My test does a several round of 'mmap, write, unmap', which will trigger a lot of swap discard. In a fusionio card, with this patch, the test runtime is reduced to 18% of the time without it, so around 5.5x faster. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index cb5baebf31d6..8a3c4a1caa14 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -217,8 +217,6 @@ struct swap_info_struct { unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ - unsigned int lowest_alloc; /* while preparing discard cluster */ - unsigned int highest_alloc; /* while preparing discard cluster */ struct swap_extent *curr_swap_extent; struct swap_extent first_swap_extent; struct block_device *bdev; /* swap device or bdev of swap file */ @@ -232,14 +230,18 @@ struct swap_info_struct { * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, - * cluster_nr, lowest_alloc and - * highest_alloc. other fields are only - * changed at swapon/swapoff, so are - * protected by swap_lock. changing - * flags need hold this lock and - * swap_lock. If both locks need hold, - * hold swap_lock first. + * cluster_nr, lowest_alloc, + * highest_alloc, free/discard cluster + * list. other fields are only changed + * at swapon/swapoff, so are protected + * by swap_lock. changing flags need + * hold this lock and swap_lock. If + * both locks need hold, hold swap_lock + * first. */ + struct work_struct discard_work; /* discard worker */ + struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */ + struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; struct swap_list_t { -- cgit v1.2.3 From ebc2a1a69111eadfeda8487e577f1a5d42ef0dae Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:32 -0700 Subject: swap: make cluster allocation per-cpu swap cluster allocation is to get better request merge to improve performance. But the cluster is shared globally, if multiple tasks are doing swap, this will cause interleave disk access. While multiple tasks swap is quite common, for example, each numa node has a kswapd thread doing swap and multiple threads/processes doing direct page reclaim. ioscheduler can't help too much here, because tasks don't send swapout IO down to block layer in the meantime. Block layer does merge some IOs, but a lot not, depending on how many tasks are doing swapout concurrently. In practice, I've seen a lot of small size IO in swapout workloads. We makes the cluster allocation per-cpu here. The interleave disk access issue goes away. All tasks swapout to their own cluster, so swapout will become sequential, which can be easily merged to big size IO. If one CPU can't get its per-cpu cluster (for example, there is no free cluster anymore in the swap), it will fallback to scan swap_map. The CPU can still continue swap. We don't need recycle free swap entries of other CPUs. In my test (swap to a 2-disk raid0 partition), this improves around 10% swapout throughput, and request size is increased significantly. How does this impact swap readahead is uncertain though. On one side, page reclaim always isolates and swaps several adjancent pages, this will make page reclaim write the pages sequentially and benefit readahead. On the other side, several CPU write pages interleave means the pages don't live _sequentially_ but relatively _near_. In the per-cpu allocation case, if adjancent pages are written by different cpus, they will live relatively _far_. So how this impacts swap readahead depends on how many pages page reclaim isolates and swaps one time. If the number is big, this patch will benefit swap readahead. Of course, this is about sequential access pattern. The patch has no impact for random access pattern, because the new cluster allocation algorithm is just for SSD. Alternative solution is organizing swap layout to be per-mm instead of this per-cpu approach. In the per-mm layout, we allocate a disk range for each mm, so pages of one mm live in swap disk adjacently. per-mm layout has potential issues of lock contention if multiple reclaimers are swap pages from one mm. For a sequential workload, per-mm layout is better to implement swap readahead, because pages from the mm are adjacent in disk. But per-cpu layout isn't very bad in this workload, as page reclaim always isolates and swaps several pages one time, such pages will still live in disk sequentially and readahead can utilize this. For a random workload, per-mm layout isn't beneficial of request merge, because it's quite possible pages from different mm are swapout in the meantime and IO can't be merged in per-mm layout. while with per-cpu layout we can merge requests from any mm. Considering random workload is more popular in workloads with swap (and per-cpu approach isn't too bad for sequential workload too), I'm choosing per-cpu layout. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8a3c4a1caa14..24db9142e93b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -198,6 +198,16 @@ struct swap_cluster_info { #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +/* + * We assign a cluster to each CPU, so each CPU can allocate swap entry from + * its own cluster and swapout sequentially. The purpose is to optimize swapout + * throughput. + */ +struct percpu_cluster { + struct swap_cluster_info index; /* Current cluster index */ + unsigned int next; /* Likely next allocation offset */ +}; + /* * The in-memory structure used to track swap areas. */ @@ -217,6 +227,7 @@ struct swap_info_struct { unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ + struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct swap_extent *curr_swap_extent; struct swap_extent first_swap_extent; struct block_device *bdev; /* swap device or bdev of swap file */ -- cgit v1.2.3 From 81c0a2bb515fd4daae8cab64352877480792b515 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Sep 2013 14:20:47 -0700 Subject: mm: page_alloc: fair zone allocator policy Each zone that holds userspace pages of one workload must be aged at a speed proportional to the zone size. Otherwise, the time an individual page gets to stay in memory depends on the zone it happened to be allocated in. Asymmetry in the zone aging creates rather unpredictable aging behavior and results in the wrong pages being reclaimed, activated etc. But exactly this happens right now because of the way the page allocator and kswapd interact. The page allocator uses per-node lists of all zones in the system, ordered by preference, when allocating a new page. When the first iteration does not yield any results, kswapd is woken up and the allocator retries. Due to the way kswapd reclaims zones below the high watermark while a zone can be allocated from when it is above the low watermark, the allocator may keep kswapd running while kswapd reclaim ensures that the page allocator can keep allocating from the first zone in the zonelist for extended periods of time. Meanwhile the other zones rarely see new allocations and thus get aged much slower in comparison. The result is that the occasional page placed in lower zones gets relatively more time in memory, even gets promoted to the active list after its peers have long been evicted. Meanwhile, the bulk of the working set may be thrashing on the preferred zone even though there may be significant amounts of memory available in the lower zones. Even the most basic test -- repeatedly reading a file slightly bigger than memory -- shows how broken the zone aging is. In this scenario, no single page should be able stay in memory long enough to get referenced twice and activated, but activation happens in spades: $ grep active_file /proc/zoneinfo nr_inactive_file 0 nr_active_file 0 nr_inactive_file 0 nr_active_file 8 nr_inactive_file 1582 nr_active_file 11994 $ cat data data data data >/dev/null $ grep active_file /proc/zoneinfo nr_inactive_file 0 nr_active_file 70 nr_inactive_file 258753 nr_active_file 443214 nr_inactive_file 149793 nr_active_file 12021 Fix this with a very simple round robin allocator. Each zone is allowed a batch of allocations that is proportional to the zone's size, after which it is treated as full. The batch counters are reset when all zones have been tried and the allocator enters the slowpath and kicks off kswapd reclaim. Allocation and reclaim is now fairly spread out to all available/allowable zones: $ grep active_file /proc/zoneinfo nr_inactive_file 0 nr_active_file 0 nr_inactive_file 174 nr_active_file 4865 nr_inactive_file 53 nr_active_file 860 $ cat data data data data >/dev/null $ grep active_file /proc/zoneinfo nr_inactive_file 0 nr_active_file 0 nr_inactive_file 666622 nr_active_file 4988 nr_inactive_file 190969 nr_active_file 937 When zone_reclaim_mode is enabled, allocations will now spread out to all zones on the local node, not just the first preferred zone (which on a 4G node might be a tiny Normal zone). Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Paul Bolle Cc: Zlatko Calusic Tested-by: Kevin Hilman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index af4a3b77a8de..ac1ea796ec0f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -105,6 +105,7 @@ struct zone_padding { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, + NR_ALLOC_BATCH, NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ -- cgit v1.2.3 From d2cf5ad6312ca9913464fac40fb47ba47ad945c4 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:29 -0700 Subject: swap: clean-up #ifdef in page_mapping() PageSwapCache() is always false when !CONFIG_SWAP, so compiler properly discard related code. Therefore, we don't need #ifdef explicitly. Signed-off-by: Joonsoo Kim Acked-by: Johannes Weiner Cc: Minchan Kim Cc: Mel Gorman Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 24db9142e93b..c03c139219c9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -447,6 +447,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #else /* CONFIG_SWAP */ +#define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL -- cgit v1.2.3 From 2bb921e526656556e68f99f5f15a4a1bf2691844 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 11 Sep 2013 14:21:30 -0700 Subject: vmstat: create separate function to fold per cpu diffs into local counters The main idea behind this patchset is to reduce the vmstat update overhead by avoiding interrupt enable/disable and the use of per cpu atomics. This patch (of 3): It is better to have a separate folding function because refresh_cpu_vm_stats() also does other things like expire pages in the page allocator caches. If we have a separate function then refresh_cpu_vm_stats() is only called from the local cpu which allows additional optimizations. The folding function is only called when a cpu is being downed and therefore no other processor will be accessing the counters. Also simplifies synchronization. [akpm@linux-foundation.org: fix UP build] Signed-off-by: Christoph Lameter Cc: KOSAKI Motohiro CC: Tejun Heo Cc: Joonsoo Kim Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index c586679b6fef..502767f4e4d4 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -198,7 +198,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); -void refresh_cpu_vm_stats(int); +void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); @@ -255,6 +255,7 @@ static inline void __dec_zone_page_state(struct page *page, static inline void refresh_cpu_vm_stats(int cpu) { } static inline void refresh_zone_stat_thresholds(void) { } +static inline void cpu_vm_stats_fold(int cpu) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } -- cgit v1.2.3 From 674470d97958a0ec72f72caf7f6451da40159cc7 Mon Sep 17 00:00:00 2001 From: Joonyoung Shim Date: Wed, 11 Sep 2013 14:21:43 -0700 Subject: lib/genalloc.c: fix overflow of ending address of memory chunk In struct gen_pool_chunk, end_addr means the end address of memory chunk (inclusive), but in the implementation it is treated as address + size of memory chunk (exclusive), so it points to the address plus one instead of correct ending address. The ending address of memory chunk plus one will cause overflow on the memory chunk including the last address of memory map, e.g. when starting address is 0xFFF00000 and size is 0x100000 on 32bit machine, ending address will be 0x100000000. Use correct ending address like starting address + size - 1. [akpm@linux-foundation.org: add comment to struct gen_pool_chunk:end_addr] Signed-off-by: Joonyoung Shim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 661d374aeb2d..f8d41cb1cbe0 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -66,8 +66,8 @@ struct gen_pool_chunk { struct list_head next_chunk; /* next chunk in pool */ atomic_t avail; phys_addr_t phys_addr; /* physical starting address of memory chunk */ - unsigned long start_addr; /* starting address of memory chunk */ - unsigned long end_addr; /* ending address of memory chunk */ + unsigned long start_addr; /* start address of memory chunk */ + unsigned long end_addr; /* end address of memory chunk (inclusive) */ unsigned long bits[0]; /* bitmap for allocating memory chunk */ }; -- cgit v1.2.3 From 31caf665e666b51fe36efd1e54031ed29e86c0b4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:21:59 -0700 Subject: mm: migrate: make core migration code aware of hugepage Currently hugepage migration is available only for soft offlining, but it's also useful for some other users of page migration (clearly because users of hugepage can enjoy the benefit of mempolicy and memory hotplug.) So this patchset tries to extend such users to support hugepage migration. The target of this patchset is to enable hugepage migration for NUMA related system calls (migrate_pages(2), move_pages(2), and mbind(2)), and memory hotplug. This patchset does not add hugepage migration for memory compaction, because users of memory compaction mainly expect to construct thp by arranging raw pages, and there's little or no need to compact hugepages. CMA, another user of page migration, can have benefit from hugepage migration, but is not enabled to support it for now (just because of lack of testing and expertise in CMA.) Hugepage migration of non pmd-based hugepage (for example 1GB hugepage in x86_64, or hugepages in architectures like ia64) is not enabled for now (again, because of lack of testing.) As for how these are achived, I extended the API (migrate_pages()) to handle hugepage (with patch 1 and 2) and adjusted code of each caller to check and collect movable hugepages (with patch 3-7). Remaining 2 patches are kind of miscellaneous ones to avoid unexpected behavior. Patch 8 is about making sure that we only migrate pmd-based hugepages. And patch 9 is about choosing appropriate zone for hugepage allocation. My test is mainly functional one, simply kicking hugepage migration via each entry point and confirm that migration is done correctly. Test code is available here: git://github.com/Naoya-Horiguchi/test_hugepage_migration_extension.git And I always run libhugetlbfs test when changing hugetlbfs's code. With this patchset, no regression was found in the test. This patch (of 9): Before enabling each user of page migration to support hugepage, this patch enables the list of pages for migration to link not only LRU pages, but also hugepages. As a result, putback_movable_pages() and migrate_pages() can handle both of LRU pages and hugepages. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c2b1801a160b..bc8d8370cd0d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -66,6 +66,8 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); int dequeue_hwpoisoned_huge_page(struct page *page); +bool isolate_huge_page(struct page *page, struct list_head *list); +void putback_active_hugepage(struct page *page); void copy_huge_page(struct page *dst, struct page *src); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -134,6 +136,8 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) return 0; } +#define isolate_huge_page(p, l) false +#define putback_active_hugepage(p) do {} while (0) static inline void copy_huge_page(struct page *dst, struct page *src) { } -- cgit v1.2.3 From b8ec1cee5a4375c1244b85709138a2eac2d89cb6 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:01 -0700 Subject: mm: soft-offline: use migrate_pages() instead of migrate_huge_page() Currently migrate_huge_page() takes a pointer to a hugepage to be migrated as an argument, instead of taking a pointer to the list of hugepages to be migrated. This behavior was introduced in commit 189ebff28 ("hugetlb: simplify migrate_huge_page()"), and was OK because until now hugepage migration is enabled only for soft-offlining which migrates only one hugepage in a single call. But the situation will change in the later patches in this series which enable other users of page migration to support hugepage migration. They can kick migration for both of normal pages and hugepages in a single call, so we need to go back to original implementation which uses linked lists to collect the hugepages to be migrated. With this patch, soft_offline_huge_page() switches to use migrate_pages(), and migrate_huge_page() is not used any more. So let's remove it. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index a405d3dc0f61..6fe521420631 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -41,8 +41,6 @@ extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, enum migrate_mode mode, int reason); -extern int migrate_huge_page(struct page *, new_page_t x, - unsigned long private, enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -62,9 +60,6 @@ static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, enum migrate_mode mode, int reason) { return -ENOSYS; } -static inline int migrate_huge_page(struct page *page, new_page_t x, - unsigned long private, enum migrate_mode mode) - { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } -- cgit v1.2.3 From 74060e4d78795c7c43805133cb717d82533d4e0d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:06 -0700 Subject: mm: mbind: add hugepage migration code to mbind() Extend do_mbind() to handle vma with VM_HUGETLB set. We will be able to migrate hugepage with mbind(2) after applying the enablement patch which comes later in this series. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bc8d8370cd0d..d1db00790a84 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -265,6 +265,8 @@ struct huge_bootmem_page { }; struct page *alloc_huge_page_node(struct hstate *h, int nid); +struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve); /* arch callback */ int __init alloc_bootmem_huge_page(struct hstate *h); @@ -378,6 +380,7 @@ static inline pgoff_t basepage_index(struct page *page) #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL #define hstate_sizelog(s) NULL -- cgit v1.2.3 From 71ea2efb1e936a127690a0a540b3a6162f95e48a Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:08 -0700 Subject: mm: migrate: remove VM_HUGETLB from vma flag check in vma_migratable() Enable hugepage migration from migrate_pages(2), move_pages(2), and mbind(2). Signed-off-by: Naoya Horiguchi Acked-by: Hillf Danton Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index b2f897789838..da6716b9e3fe 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -173,7 +173,7 @@ extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ static inline int vma_migratable(struct vm_area_struct *vma) { - if (vma->vm_flags & (VM_IO | VM_HUGETLB | VM_PFNMAP)) + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return 0; /* * Migration allocates pages in the highest zone. If we cannot -- cgit v1.2.3 From c8721bbbdd36382de51cd6b7a56322e0acca2414 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:09 -0700 Subject: mm: memory-hotplug: enable memory hotplug to handle hugepage Until now we can't offline memory blocks which contain hugepages because a hugepage is considered as an unmovable page. But now with this patch series, a hugepage has become movable, so by using hugepage migration we can offline such memory blocks. What's different from other users of hugepage migration is that we need to decompose all the hugepages inside the target memory block into free buddy pages after hugepage migration, because otherwise free hugepages remaining in the memory block intervene the memory offlining. For this reason we introduce new functions dissolve_free_huge_page() and dissolve_free_huge_pages(). Other than that, what this patch does is straightforwardly to add hugepage migration code, that is, adding hugepage code to the functions which scan over pfn and collect hugepages to be migrated, and adding a hugepage allocation function to alloc_migrate_target(). As for larger hugepages (1GB for x86_64), it's not easy to do hotremove over them because it's larger than memory block. So we now simply leave it to fail as it is. [yongjun_wei@trendmicro.com.cn: remove duplicated include] Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Cc: Hillf Danton Cc: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Wei Yongjun Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d1db00790a84..2e02c4ed1035 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -68,6 +68,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); +bool is_hugepage_active(struct page *page); void copy_huge_page(struct page *dst, struct page *src); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -138,6 +139,7 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) #define isolate_huge_page(p, l) false #define putback_active_hugepage(p) do {} while (0) +#define is_hugepage_active(x) false static inline void copy_huge_page(struct page *dst, struct page *src) { } @@ -377,6 +379,9 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern void dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn); + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL @@ -403,6 +408,7 @@ static inline pgoff_t basepage_index(struct page *page) { return page->index; } +#define dissolve_free_huge_pages(s, e) do {} while (0) #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From 83467efbdb7948146581a56cbd683a22a0684bbb Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:11 -0700 Subject: mm: migrate: check movability of hugepage in unmap_and_move_huge_page() Currently hugepage migration works well only for pmd-based hugepages (mainly due to lack of testing,) so we had better not enable migration of other levels of hugepages until we are ready for it. Some users of hugepage migration (mbind, move_pages, and migrate_pages) do page table walk and check pud/pmd_huge() there, so they are safe. But the other users (softoffline and memory hotremove) don't do this, so without this patch they can try to migrate unexpected types of hugepages. To prevent this, we introduce hugepage_migration_support() as an architecture dependent check of whether hugepage are implemented on a pmd basis or not. And on some architecture multiple sizes of hugepages are available, so hugepage_migration_support() also checks hugepage size. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Hillf Danton Cc: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2e02c4ed1035..0393270466c3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -381,6 +381,16 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); +int pmd_huge_support(void); +/* + * Currently hugepage migration is enabled only for pmd-based hugepage. + * This function will be updated when hugepage migration is more widely + * supported. + */ +static inline int hugepage_migration_support(struct hstate *h) +{ + return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +} #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -409,6 +419,8 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) +#define pmd_huge_support() 0 +#define hugepage_migration_support(h) 0 #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From e76b63f80d938a1319eb5fb0ae7ea69bddfbae38 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 11 Sep 2013 14:22:17 -0700 Subject: memblock, numa: binary search node id Current early_pfn_to_nid() on arch that support memblock go over memblock.memory one by one, so will take too many try near the end. We can use existing memblock_search to find the node id for given pfn, that could save some time on bigger system that have many entries memblock.memory array. Here are the timing differences for several machines. In each case with the patch less time was spent in __early_pfn_to_nid(). 3.11-rc5 with patch difference (%) -------- ---------- -------------- UV1: 256 nodes 9TB: 411.66 402.47 -9.19 (2.23%) UV2: 255 nodes 16TB: 1141.02 1138.12 -2.90 (0.25%) UV2: 64 nodes 2TB: 128.15 126.53 -1.62 (1.26%) UV2: 32 nodes 2TB: 121.87 121.07 -0.80 (0.66%) Time in seconds. Signed-off-by: Yinghai Lu Cc: Tejun Heo Acked-by: Russ Anderson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f388203db7e8..31e95acddb4d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -60,6 +60,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, + unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -- cgit v1.2.3 From d9104d1ca9662498339c0de975b4666c30485f4e Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 11 Sep 2013 14:22:24 -0700 Subject: mm: track vma changes with VM_SOFTDIRTY bit Pavel reported that in case if vma area get unmapped and then mapped (or expanded) in-place, the soft dirty tracker won't be able to recognize this situation since it works on pte level and ptes are get zapped on unmap, loosing soft dirty bit of course. So to resolve this situation we need to track actions on vma level, there VM_SOFTDIRTY flag comes in. When new vma area created (or old expanded) we set this bit, and keep it here until application calls for clearing soft dirty bit. Thus when user space application track memory changes now it can detect if vma area is renewed. Reported-by: Pavel Emelyanov Signed-off-by: Cyrill Gorcunov Cc: Andy Lutomirski Cc: Matt Mackall Cc: Xiao Guangrong Cc: Marcelo Tosatti Cc: KOSAKI Motohiro Cc: Stephen Rothwell Cc: Peter Zijlstra Cc: "Aneesh Kumar K.V" Cc: Rob Landley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d2d59b4149d0..dce24569f8fc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -115,6 +115,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ +#ifdef CONFIG_MEM_SOFT_DIRTY +# define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ +#else +# define VM_SOFTDIRTY 0 +#endif + #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ -- cgit v1.2.3 From 7a8010cd36273ff5f6fea5201ef9232f30cebbd9 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Sep 2013 14:22:35 -0700 Subject: mm: munlock: manual pte walk in fast path instead of follow_page_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently munlock_vma_pages_range() calls follow_page_mask() to obtain each individual struct page. This entails repeated full page table translations and page table lock taken for each page separately. This patch avoids the costly follow_page_mask() where possible, by iterating over ptes within single pmd under single page table lock. The first pte is obtained by get_locked_pte() for non-THP page acquired by the initial follow_page_mask(). The rest of the on-stack pagevec for munlock is filled up using pte_walk as long as pte_present() and vm_normal_page() are sufficient to obtain the struct page. After this patch, a 14% speedup was measured for munlocking a 56GB large memory area with THP disabled. Signed-off-by: Vlastimil Babka Cc: Jörn Engel Cc: Mel Gorman Cc: Michel Lespinasse Cc: Hugh Dickins Cc: Rik van Riel Cc: Johannes Weiner Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dce24569f8fc..03f84b8d7359 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -643,12 +643,12 @@ static inline enum zone_type page_zonenum(const struct page *page) #endif /* - * The identification function is only used by the buddy allocator for - * determining if two pages could be buddies. We are not really - * identifying a zone since we could be using a the section number - * id if we have not node id available in page flags. - * We guarantee only that it will return the same value for two - * combinable pages in a zone. + * The identification function is mainly used by the buddy allocator for + * determining if two pages could be buddies. We are not really identifying + * the zone since we could be using the section number id if we do not have + * node id available in page flags. + * We only guarantee that it will return the same value for two combinable + * pages in a zone. */ static inline int page_zone_id(struct page *page) { -- cgit v1.2.3 From 6e543d5780e36ff5ee56c44d7e2e30db3457a7ed Mon Sep 17 00:00:00 2001 From: Lisa Du Date: Wed, 11 Sep 2013 14:22:36 -0700 Subject: mm: vmscan: fix do_try_to_free_pages() livelock This patch is based on KOSAKI's work and I add a little more description, please refer https://lkml.org/lkml/2012/6/14/74. Currently, I found system can enter a state that there are lots of free pages in a zone but only order-0 and order-1 pages which means the zone is heavily fragmented, then high order allocation could make direct reclaim path's long stall(ex, 60 seconds) especially in no swap and no compaciton enviroment. This problem happened on v3.4, but it seems issue still lives in current tree, the reason is do_try_to_free_pages enter live lock: kswapd will go to sleep if the zones have been fully scanned and are still not balanced. As kswapd thinks there's little point trying all over again to avoid infinite loop. Instead it changes order from high-order to 0-order because kswapd think order-0 is the most important. Look at 73ce02e9 in detail. If watermarks are ok, kswapd will go back to sleep and may leave zone->all_unreclaimable =3D 0. It assume high-order users can still perform direct reclaim if they wish. Direct reclaim continue to reclaim for a high order which is not a COSTLY_ORDER without oom-killer until kswapd turn on zone->all_unreclaimble= . This is because to avoid too early oom-kill. So it means direct_reclaim depends on kswapd to break this loop. In worst case, direct-reclaim may continue to page reclaim forever when kswapd sleeps forever until someone like watchdog detect and finally kill the process. As described in: http://thread.gmane.org/gmane.linux.kernel.mm/103737 We can't turn on zone->all_unreclaimable from direct reclaim path because direct reclaim path don't take any lock and this way is racy. Thus this patch removes zone->all_unreclaimable field completely and recalculates zone reclaimable state every time. Note: we can't take the idea that direct-reclaim see zone->pages_scanned directly and kswapd continue to use zone->all_unreclaimable. Because, it is racy. commit 929bea7c71 (vmscan: all_unreclaimable() use zone->all_unreclaimable as a name) describes the detail. [akpm@linux-foundation.org: uninline zone_reclaimable_pages() and zone_reclaimable()] Cc: Aaditya Kumar Cc: Ying Han Cc: Nick Piggin Acked-by: Rik van Riel Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: Christoph Lameter Cc: Bob Liu Cc: Neil Zhang Cc: Russell King - ARM Linux Reviewed-by: Michal Hocko Acked-by: Minchan Kim Acked-by: Johannes Weiner Signed-off-by: KOSAKI Motohiro Signed-off-by: Lisa Du Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 1 + include/linux/mmzone.h | 1 - include/linux/vmstat.h | 1 - 3 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 1397ccf81e91..cf55945c83fb 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,6 +2,7 @@ #define LINUX_MM_INLINE_H #include +#include /** * page_is_file_cache - should the page be on a file LRU or anon LRU? diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ac1ea796ec0f..bd791e452ad7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -353,7 +353,6 @@ struct zone { * free areas of different sizes */ spinlock_t lock; - int all_unreclaimable; /* All pages pinned */ #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 502767f4e4d4..e4b948080d20 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -143,7 +143,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } extern unsigned long global_reclaimable_pages(void); -extern unsigned long zone_reclaimable_pages(struct zone *zone); #ifdef CONFIG_NUMA /* -- cgit v1.2.3 From 7d9f073b8da45a894bb7148433bd84d21eed6757 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 11 Sep 2013 14:22:40 -0700 Subject: mm/writeback: make writeback_inodes_wb static It's not used globally and could be static. Signed-off-by: Wanpeng Li Cc: Dave Hansen Cc: Rik van Riel Cc: Fengguang Wu Cc: Joonsoo Kim Cc: Johannes Weiner Cc: Tejun Heo Cc: Yasuaki Ishimatsu Cc: David Rientjes Cc: KOSAKI Motohiro Cc: Jiri Kosina Cc: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 4e198ca1f685..021b8a319b9e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -98,8 +98,6 @@ int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); void sync_inodes_sb(struct super_block *); -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, - enum wb_reason reason); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); -- cgit v1.2.3 From 5a53748568f79641eaf40e41081a2f4987f005c2 Mon Sep 17 00:00:00 2001 From: Maxim Patlasov Date: Wed, 11 Sep 2013 14:22:46 -0700 Subject: mm/page-writeback.c: add strictlimit feature The feature prevents mistrusted filesystems (ie: FUSE mounts created by unprivileged users) to grow a large number of dirty pages before throttling. For such filesystems balance_dirty_pages always check bdi counters against bdi limits. I.e. even if global "nr_dirty" is under "freerun", it's not allowed to skip bdi checks. The only use case for now is fuse: it sets bdi max_ratio to 1% by default and system administrators are supposed to expect that this limit won't be exceeded. The feature is on if a BDI is marked by BDI_CAP_STRICTLIMIT flag. A filesystem may set the flag when it initializes its BDI. The problematic scenario comes from the fact that nobody pays attention to the NR_WRITEBACK_TEMP counter (i.e. number of pages under fuse writeback). The implementation of fuse writeback releases original page (by calling end_page_writeback) almost immediately. A fuse request queued for real processing bears a copy of original page. Hence, if userspace fuse daemon doesn't finalize write requests in timely manner, an aggressive mmap writer can pollute virtually all memory by those temporary fuse page copies. They are carefully accounted in NR_WRITEBACK_TEMP, but nobody cares. To make further explanations shorter, let me use "NR_WRITEBACK_TEMP problem" as a shortcut for "a possibility of uncontrolled grow of amount of RAM consumed by temporary pages allocated by kernel fuse to process writeback". The problem was very easy to reproduce. There is a trivial example filesystem implementation in fuse userspace distribution: fusexmp_fh.c. I added "sleep(1);" to the write methods, then recompiled and mounted it. Then created a huge file on the mount point and run a simple program which mmap-ed the file to a memory region, then wrote a data to the region. An hour later I observed almost all RAM consumed by fuse writeback. Since then some unrelated changes in kernel fuse made it more difficult to reproduce, but it is still possible now. Putting this theoretical happens-in-the-lab thing aside, there is another thing that really hurts real world (FUSE) users. This is write-through page cache policy FUSE currently uses. I.e. handling write(2), kernel fuse populates page cache and flushes user data to the server synchronously. This is excessively suboptimal. Pavel Emelyanov's patches ("writeback cache policy") solve the problem, but they also make resolving NR_WRITEBACK_TEMP problem absolutely necessary. Otherwise, simply copying a huge file to a fuse mount would result in memory starvation. Miklos, the maintainer of FUSE, believes strictlimit feature the way to go. And eventually putting FUSE topics aside, there is one more use-case for strictlimit feature. Using a slow USB stick (mass storage) in a machine with huge amount of RAM installed is a well-known pain. Let's make simple computations. Assuming 64GB of RAM installed, existing implementation of balance_dirty_pages will start throttling only after 9.6GB of RAM becomes dirty (freerun == 15% of total RAM). So, the command "cp 9GB_file /media/my-usb-storage/" may return in a few seconds, but subsequent "umount /media/my-usb-storage/" will take more than two hours if effective throughput of the storage is, to say, 1MB/sec. After inclusion of strictlimit feature, it will be trivial to add a knob (e.g. /sys/devices/virtual/bdi/x:y/strictlimit) to enable it on demand. Manually or via udev rule. May be I'm wrong, but it seems to be quite a natural desire to limit the amount of dirty memory for some devices we are not fully trust (in the sense of sustainable throughput). [akpm@linux-foundation.org: fix warning in page-writeback.c] Signed-off-by: Maxim Patlasov Cc: Jan Kara Cc: Miklos Szeredi Cc: Wu Fengguang Cc: Pavel Emelyanov Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c3881553f7d1..5f66d519a726 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -243,6 +243,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_EXEC_MAP: Can be mapped for execution * * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed. + * + * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 @@ -254,6 +256,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_WB 0x00000080 #define BDI_CAP_SWAP_BACKED 0x00000100 #define BDI_CAP_STABLE_WRITES 0x00000200 +#define BDI_CAP_STRICTLIMIT 0x00000400 #define BDI_CAP_VMFLAGS \ (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) -- cgit v1.2.3 From f9121153fdfbfaa930bf65077a5597e20d3ac608 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 11 Sep 2013 14:22:52 -0700 Subject: mm/hwpoison: don't need to hold compound lock for hugetlbfs page compound lock is introduced by commit e9da73d67("thp: compound_lock."), it is used to serialize put_page against __split_huge_page_refcount(). In addition, transparent hugepages will be splitted in hwpoison handler and just one subpage will be poisoned. There is unnecessary to hold compound lock for hugetlbfs page. This patch replace compound_trans_order by compond_order in the place where the page is hugetlbfs page. Signed-off-by: Wanpeng Li Reviewed-by: Naoya Horiguchi Cc: Andi Kleen Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 03f84b8d7359..caf543c7eaa7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -495,20 +495,6 @@ static inline int compound_order(struct page *page) return (unsigned long)page[1].lru.prev; } -static inline int compound_trans_order(struct page *page) -{ - int order; - unsigned long flags; - - if (!PageHead(page)) - return 0; - - flags = compound_lock_irqsave(page); - order = compound_order(page); - compound_unlock_irqrestore(page, flags); - return order; -} - static inline void set_compound_order(struct page *page, unsigned long order) { page[1].lru.prev = (void *)order; -- cgit v1.2.3 From fa688207c9db48b64ab6538abc3fcdf26110b9ec Mon Sep 17 00:00:00 2001 From: David Daney Date: Wed, 11 Sep 2013 14:23:24 -0700 Subject: smp: quit unconditionally enabling irq in on_each_cpu_mask and on_each_cpu_cond As in commit f21afc25f9ed ("smp.h: Use local_irq_{save,restore}() in !SMP version of on_each_cpu()"), we don't want to enable irqs if they are not already enabled. There are currently no known problematical callers of these functions, but since it is a known failure pattern, we preemptively fix them. Since they are not trivial functions, make them non-inline by moving them to up.c. This also makes it so we don't have to fix #include dependancies for preempt_{disable,enable}. Signed-off-by: David Daney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 62 ++++++++++++++--------------------------------------- 1 file changed, 16 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index c8488763277f..3724a9070907 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -29,6 +29,22 @@ extern unsigned int total_cpus; int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, int wait); +/* + * Call a function on processors specified by mask, which might include + * the local one. + */ +void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, + void *info, bool wait); + +/* + * Call a function on each processor for which the supplied function + * cond_func returns a positive value. This may include the local + * processor. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags); + #ifdef CONFIG_SMP #include @@ -100,22 +116,6 @@ static inline void call_function_init(void) { } */ int on_each_cpu(smp_call_func_t func, void *info, int wait); -/* - * Call a function on processors specified by mask, which might include - * the local one. - */ -void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, - void *info, bool wait); - -/* - * Call a function on each processor for which the supplied function - * cond_func returns a positive value. This may include the local - * processor. - */ -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags); - /* * Mark the boot cpu "online" so that it can call console drivers in * printk() and can access its per-cpu storage. @@ -151,36 +151,6 @@ static inline int on_each_cpu(smp_call_func_t func, void *info, int wait) return 0; } -/* - * Note we still need to test the mask even for UP - * because we actually can get an empty mask from - * code that on SMP might call us without the local - * CPU in the mask. - */ -#define on_each_cpu_mask(mask, func, info, wait) \ - do { \ - if (cpumask_test_cpu(0, (mask))) { \ - local_irq_disable(); \ - (func)(info); \ - local_irq_enable(); \ - } \ - } while (0) -/* - * Preemption is disabled here to make sure the cond_func is called under the - * same condtions in UP and SMP. - */ -#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\ - do { \ - void *__info = (info); \ - preempt_disable(); \ - if ((cond_func)(0, __info)) { \ - local_irq_disable(); \ - (func)(__info); \ - local_irq_enable(); \ - } \ - preempt_enable(); \ - } while (0) - static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ -- cgit v1.2.3 From bff2dc42bcafdd75c0296987747f782965d691a0 Mon Sep 17 00:00:00 2001 From: David Daney Date: Wed, 11 Sep 2013 14:23:26 -0700 Subject: smp.h: move !SMP version of on_each_cpu() out-of-line All of the other non-trivial !SMP versions of functions in smp.h are out-of-line in up.c. Move on_each_cpu() there as well. This allows us to get rid of the #include . The drawback is that this makes both the x86_64 and i386 defconfig !SMP kernels about 200 bytes larger each. Signed-off-by: David Daney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 3724a9070907..cfb7ca094b38 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -11,7 +11,6 @@ #include #include #include -#include extern void cpu_idle(void); @@ -29,6 +28,11 @@ extern unsigned int total_cpus; int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, int wait); +/* + * Call a function on all processors + */ +int on_each_cpu(smp_call_func_t func, void *info, int wait); + /* * Call a function on processors specified by mask, which might include * the local one. @@ -111,11 +115,6 @@ void generic_smp_call_function_single_interrupt(void); static inline void call_function_init(void) { } #endif -/* - * Call a function on all processors - */ -int on_each_cpu(smp_call_func_t func, void *info, int wait); - /* * Mark the boot cpu "online" so that it can call console drivers in * printk() and can access its per-cpu storage. @@ -141,16 +140,6 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info) #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) -static inline int on_each_cpu(smp_call_func_t func, void *info, int wait) -{ - unsigned long flags; - - local_irq_save(flags); - func(info); - local_irq_restore(flags); - return 0; -} - static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ -- cgit v1.2.3 From f9597f24c089dcbddbd2d9e99fbf00df57fb70c6 Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Wed, 11 Sep 2013 14:23:28 -0700 Subject: syscalls.h: add forward declarations for inplace syscall wrappers Unclutter -Wmissing-prototypes warning types (enabled at make W=1) linux/include/linux/syscalls.h:190:18: warning: no previous prototype for 'SyS_semctl' [-Wmissing-prototypes] asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ ^ linux/include/linux/syscalls.h:183:2: note: in expansion of macro '__SYSCALL_DEFINEx' __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) ^ by adding forward declarations right before definitions. Signed-off-by: Sergei Trofimovich Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 1 + include/linux/syscalls.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ec1aee4aec9c..345da00a86e0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -43,6 +43,7 @@ #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ { \ return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 84662ecc7b51..7fac04e7ff6e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -186,6 +186,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ -- cgit v1.2.3 From c802d64a356b5cf349121ac4c5e005f037ce548d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 11 Sep 2013 14:24:11 -0700 Subject: kprobes: unify insn caches The current kpropes insn caches allocate memory areas for insn slots with module_alloc(). The assumption is that the kernel image and module area are both within the same +/- 2GB memory area. This however is not true for s390 where the kernel image resides within the first 2GB (DMA memory area), but the module area is far away in the vmalloc area, usually somewhere close below the 4TB area. For new pc relative instructions s390 needs insn slots that are within +/- 2GB of each area. That way we can patch displacements of pc-relative instructions within the insn slots just like x86 and powerpc. The module area works already with the normal insn slot allocator, however there is currently no way to get insn slots that are within the first 2GB on s390 (aka DMA area). Therefore this patch set modifies the kprobes insn slot cache code in order to allow to specify a custom allocator for the insn slot cache pages. In addition architecure can now have private insn slot caches withhout the need to modify common code. Patch 1 unifies and simplifies the current insn and optinsn caches implementation. This is a preparation which allows to add more insn caches in a simple way. Patch 2 adds the possibility to specify a custom allocator. Patch 3 makes s390 use the new insn slot mechanisms and adds support for pc-relative instructions with long displacements. This patch (of 3): The two insn caches (insn, and optinsn) each have an own mutex and alloc/free functions (get_[opt]insn_slot() / free_[opt]insn_slot()). Since there is the need for yet another insn cache which satifies dma allocations on s390, unify and simplify the current implementation: - Move the per insn cache mutex into struct kprobe_insn_cache. - Move the alloc/free functions to kprobe.h so they are simply wrappers for the generic __get_insn_slot/__free_insn_slot functions. The implementation is done with a DEFINE_INSN_CACHE_OPS() macro which provides the alloc/free functions for each cache if needed. - move the struct kprobe_insn_cache to kprobe.h which allows to generate architecture specific insn slot caches outside of the core kprobes code. Signed-off-by: Heiko Carstens Cc: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Ingo Molnar Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index ca1d27a0d6a6..077f65321b5e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -264,10 +264,34 @@ extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); extern void show_registers(struct pt_regs *regs); -extern kprobe_opcode_t *get_insn_slot(void); -extern void free_insn_slot(kprobe_opcode_t *slot, int dirty); extern void kprobes_inc_nmissed_count(struct kprobe *p); +struct kprobe_insn_cache { + struct mutex mutex; + struct list_head pages; /* list of kprobe_insn_page */ + size_t insn_size; /* size of instruction slot */ + int nr_garbage; +}; + +extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c); +extern void __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty); + +#define DEFINE_INSN_CACHE_OPS(__name) \ +extern struct kprobe_insn_cache kprobe_##__name##_slots; \ + \ +static inline kprobe_opcode_t *get_##__name##_slot(void) \ +{ \ + return __get_insn_slot(&kprobe_##__name##_slots); \ +} \ + \ +static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\ +{ \ + __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \ +} \ + +DEFINE_INSN_CACHE_OPS(insn); + #ifdef CONFIG_OPTPROBES /* * Internal structure for direct jump optimized probe @@ -287,13 +311,13 @@ extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); -extern kprobe_opcode_t *get_optinsn_slot(void); -extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr); extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); +DEFINE_INSN_CACHE_OPS(optinsn); + #ifdef CONFIG_SYSCTL extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, -- cgit v1.2.3 From af96397de8600232effbff43dc8b4ca20ddc02b1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 11 Sep 2013 14:24:13 -0700 Subject: kprobes: allow to specify custom allocator for insn caches The current two insn slot caches both use module_alloc/module_free to allocate and free insn slot cache pages. For s390 this is not sufficient since there is the need to allocate insn slots that are either within the vmalloc module area or within dma memory. Therefore add a mechanism which allows to specify an own allocator for an own insn slot cache. Signed-off-by: Heiko Carstens Acked-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Ingo Molnar Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 077f65321b5e..925eaf28fca9 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -268,6 +268,8 @@ extern void kprobes_inc_nmissed_count(struct kprobe *p); struct kprobe_insn_cache { struct mutex mutex; + void *(*alloc)(void); /* allocate insn page */ + void (*free)(void *); /* free insn page */ struct list_head pages; /* list of kprobe_insn_page */ size_t insn_size; /* size of instruction slot */ int nr_garbage; -- cgit v1.2.3 From 131b2f9f1214f338f0bf7c0d9760019f2b1d0c20 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 11 Sep 2013 14:24:39 -0700 Subject: exec: kill "int depth" in search_binary_handler() Nobody except search_binary_handler() should touch ->recursion_depth, "int depth" buys nothing but complicates the code, kill it. Probably we should also kill "fn" and the !NULL check, ->load_binary should be always defined. And it can not go away after read_unlock() or this code is buggy anyway. Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Evgeniy Polyakov Cc: Zach Levis Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 70cf138690e9..e8112ae50531 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -31,7 +31,7 @@ struct linux_binprm { #ifdef __alpha__ unsigned int taso:1; #endif - unsigned int recursion_depth; + unsigned int recursion_depth; /* only for search_binary_handler() */ struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ -- cgit v1.2.3 From be8a8d069e508d4408125e2b1471f549e7813d25 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Wed, 11 Sep 2013 14:24:49 -0700 Subject: vmcore: introduce ELF header in new memory feature For s390 we want to use /proc/vmcore for our SCSI stand-alone dump (zfcpdump). We have support where the first HSA_SIZE bytes are saved into a hypervisor owned memory area (HSA) before the kdump kernel is booted. When the kdump kernel starts, it is restricted to use only HSA_SIZE bytes. The advantages of this mechanism are: * No crashkernel memory has to be defined in the old kernel. * Early boot problems (before kexec_load has been done) can be dumped * Non-Linux systems can be dumped. We modify the s390 copy_oldmem_page() function to read from the HSA memory if memory below HSA_SIZE bytes is requested. Since we cannot use the kexec tool to load the kernel in this scenario, we have to build the ELF header in the 2nd (kdump/new) kernel. So with the following patch set we would like to introduce the new function that the ELF header for /proc/vmcore can be created in the 2nd kernel memory. The following steps are done during zfcpdump execution: 1. Production system crashes 2. User boots a SCSI disk that has been prepared with the zfcpdump tool 3. Hypervisor saves CPU state of boot CPU and HSA_SIZE bytes of memory into HSA 4. Boot loader loads kernel into low memory area 5. Kernel boots and uses only HSA_SIZE bytes of memory 6. Kernel saves registers of non-boot CPUs 7. Kernel does memory detection for dump memory map 8. Kernel creates ELF header for /proc/vmcore 9. /proc/vmcore uses this header for initialization 10. The zfcpdump user space reads /proc/vmcore to write dump to SCSI disk - copy_oldmem_page() copies from HSA for memory below HSA_SIZE - copy_oldmem_page() copies from real memory for memory above HSA_SIZE Currently for s390 we create the ELF core header in the 2nd kernel with a small trick. We relocate the addresses in the ELF header in a way that for the /proc/vmcore code it seems to be in the 1st kernel (old) memory and the read_from_oldmem() returns the correct data. This allows the /proc/vmcore code to use the ELF header in the 2nd kernel. This patch: Exchange the old mechanism with the new and much cleaner function call override feature that now offcially allows to create the ELF core header in the 2nd kernel. To use the new feature the following function have to be defined by the architecture backend code to read from new memory: * elfcorehdr_alloc: Allocate ELF header * elfcorehdr_free: Free the memory of the ELF header * elfcorehdr_read: Read from ELF header * elfcorehdr_read_notes: Read from ELF notes Signed-off-by: Michael Holzheu Acked-by: Vivek Goyal Cc: HATAYAMA Daisuke Cc: Jan Willeke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 37e4f8da7cdf..6571f828e313 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -12,6 +12,12 @@ extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; +extern int __weak elfcorehdr_alloc(unsigned long long *addr, + unsigned long long *size); +extern void __weak elfcorehdr_free(unsigned long long addr); +extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); +extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); + extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); -- cgit v1.2.3 From 9cb218131de1c59dca9063b2efe876f053f316af Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Wed, 11 Sep 2013 14:24:51 -0700 Subject: vmcore: introduce remap_oldmem_pfn_range() For zfcpdump we can't map the HSA storage because it is only available via a read interface. Therefore, for the new vmcore mmap feature we have introduce a new mechanism to create mappings on demand. This patch introduces a new architecture function remap_oldmem_pfn_range() that should be used to create mappings with remap_pfn_range() for oldmem areas that can be directly mapped. For zfcpdump this is everything besides of the HSA memory. For the areas that are not mapped by remap_oldmem_pfn_range() a generic vmcore a new generic vmcore fault handler mmap_vmcore_fault() is called. This handler works as follows: * Get already available or new page from page cache (find_or_create_page) * Check if /proc/vmcore page is filled with data (PageUptodate) * If yes: Return that page * If no: Fill page using __vmcore_read(), set PageUptodate, and return page Signed-off-by: Michael Holzheu Acked-by: Vivek Goyal Cc: HATAYAMA Daisuke Cc: Jan Willeke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 6571f828e313..fe68a5a98583 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -17,6 +17,9 @@ extern int __weak elfcorehdr_alloc(unsigned long long *addr, extern void __weak elfcorehdr_free(unsigned long long addr); extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); -- cgit v1.2.3 From 9dee5c51516d2c3fff22633c1272c5652e68075a Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Wed, 11 Sep 2013 14:25:10 -0700 Subject: rbtree: add postorder iteration functions Postorder iteration yields all of a node's children prior to yielding the node itself, and this particular implementation also avoids examining the leaf links in a node after that node has been yielded. In what I expect will be its most common usage, postorder iteration allows the deletion of every node in an rbtree without modifying the rbtree nodes (no _requirement_ that they be nulled) while avoiding referencing child nodes after they have been "deleted" (most commonly, freed). I have only updated zswap to use this functionality at this point, but numerous bits of code (most notably in the filesystem drivers) use a hand rolled postorder iteration that NULLs child links as it traverses the tree. Each of those instances could be replaced with this common implementation. 1 & 2 add rbtree postorder iteration functions. 3 adds testing of the iteration to the rbtree runtime tests 4 allows building the rbtree runtime tests as builtins 5 updates zswap. This patch: Add postorder iteration functions for rbtree. These are useful for safely freeing an entire rbtree without modifying the tree at all. Signed-off-by: Cody P Schafer Reviewed-by: Seth Jennings Cc: David Woodhouse Cc: Rik van Riel Cc: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 0022c1bb1e26..c467151e9950 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -68,6 +68,10 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); +/* Postorder iteration - always visit the parent after its children */ +extern struct rb_node *rb_first_postorder(const struct rb_root *); +extern struct rb_node *rb_next_postorder(const struct rb_node *); + /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -- cgit v1.2.3 From 2b529089257705499207ce7da9d0e3ae26a844ba Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Wed, 11 Sep 2013 14:25:11 -0700 Subject: rbtree: add rbtree_postorder_for_each_entry_safe() helper Because deletion (of the entire tree) is a relatively common use of the rbtree_postorder iteration, and because doing it safely means fiddling with temporary storage, provide a helper to simplify postorder rbtree iteration. Signed-off-by: Cody P Schafer Reviewed-by: Seth Jennings Cc: David Woodhouse Cc: Rik van Riel Cc: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index c467151e9950..aa870a4ddf54 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -85,4 +85,22 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, *rb_link = node; } +/** + * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of + * given type safe against removal of rb_node entry + * + * @pos: the 'type *' to use as a loop cursor. + * @n: another 'type *' to use as temporary storage + * @root: 'rb_root *' of the rbtree. + * @field: the name of the rb_node field within 'type'. + */ +#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ + for (pos = rb_entry(rb_first_postorder(root), typeof(*pos), field),\ + n = rb_entry(rb_next_postorder(&pos->field), \ + typeof(*pos), field); \ + &pos->field; \ + pos = n, \ + n = rb_entry(rb_next_postorder(&pos->field), \ + typeof(*pos), field)) + #endif /* _LINUX_RBTREE_H */ -- cgit v1.2.3 From 5e4c0d974139a98741b829b27cf38dc8f9284490 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 11 Sep 2013 14:26:05 -0700 Subject: lib/radix-tree.c: make radix_tree_node_alloc() work correctly within interrupt With users of radix_tree_preload() run from interrupt (block/blk-ioc.c is one such possible user), the following race can happen: radix_tree_preload() ... radix_tree_insert() radix_tree_node_alloc() if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; ... radix_tree_preload() ... radix_tree_insert() radix_tree_node_alloc() if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; And we give out one radix tree node twice. That clearly results in radix tree corruption with different results (usually OOPS) depending on which two users of radix tree race. We fix the problem by making radix_tree_node_alloc() always allocate fresh radix tree nodes when in interrupt. Using preloading when in interrupt doesn't make sense since all the allocations have to be atomic anyway and we cannot steal nodes from process-context users because some users rely on radix_tree_insert() succeeding after radix_tree_preload(). in_interrupt() check is somewhat ugly but we cannot simply key off passed gfp_mask as that is acquired from root_gfp_mask() and thus the same for all preload users. Another part of the fix is to avoid node preallocation in radix_tree_preload() when passed gfp_mask doesn't allow waiting. Again, preallocation in such case doesn't make sense and when preallocation would happen in interrupt we could possibly leak some allocated nodes. However, some users of radix_tree_preload() require following radix_tree_insert() to succeed. To avoid unexpected effects for these users, radix_tree_preload() only warns if passed gfp mask doesn't allow waiting and we provide a new function radix_tree_maybe_preload() for those users which get different gfp mask from different call sites and which are prepared to handle radix_tree_insert() failure. Signed-off-by: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index ffc444c38b0a..403940787be1 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,6 +231,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long radix_tree_prev_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); +int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag); -- cgit v1.2.3 From 57f150a58c40cda598c31af8bceb8598f43c3e5f Mon Sep 17 00:00:00 2001 From: Rob Landley Date: Wed, 11 Sep 2013 14:26:10 -0700 Subject: initmpfs: move rootfs code from fs/ramfs/ to init/ When the rootfs code was a wrapper around ramfs, having them in the same file made sense. Now that it can wrap another filesystem type, move it in with the init code instead. This also allows a subsequent patch to access rootfstype= command line arg. Signed-off-by: Rob Landley Cc: Jeff Layton Cc: Jens Axboe Cc: Stephen Warren Cc: Rusty Russell Cc: Jim Cromie Cc: Sam Ravnborg Cc: Greg Kroah-Hartman Cc: "Eric W. Biederman" Cc: Alexander Viro Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 1 + include/linux/ramfs.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index e73f2b708525..f1c27a71d03c 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -153,6 +153,7 @@ extern unsigned int reset_devices; void setup_arch(char **); void prepare_namespace(void); void __init load_default_modules(void); +int __init init_rootfs(void); extern void (*late_time_init)(void); diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 69e37c2d1ea5..753207c8ce20 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -25,7 +25,7 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); extern const struct file_operations ramfs_file_operations; extern const struct vm_operations_struct generic_file_vm_ops; -extern int __init init_rootfs(void); +extern int __init init_ramfs_fs(void); int ramfs_fill_super(struct super_block *sb, void *data, int silent); -- cgit v1.2.3 From d9a605e40b1376eb02b067d7690580255a0df68f Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 11 Sep 2013 14:26:24 -0700 Subject: ipc: rename ids->rw_mutex Since in some situations the lock can be shared for readers, we shouldn't be calling it a mutex, rename it to rwsem. Signed-off-by: Davidlohr Bueso Tested-by: Sedat Dilek Cc: Rik van Riel Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index c4d870b0d5e6..19c19a5eee29 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -22,7 +22,7 @@ struct ipc_ids { int in_use; unsigned short seq; unsigned short seq_max; - struct rw_semaphore rw_mutex; + struct rw_semaphore rwsem; struct idr ipcs_idr; int next_id; }; -- cgit v1.2.3 From b34081f1cd59585451efaa69e1dff1b9507e6c89 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 11 Sep 2013 14:26:32 -0700 Subject: lz4: fix compression/decompression signedness mismatch LZ4 compression and decompression functions require different in signedness input/output parameters: unsigned char for compression and signed char for decompression. Change decompression API to require "(const) unsigned char *". Signed-off-by: Sergey Senozhatsky Cc: Kyungsik Lee Cc: Geert Uytterhoeven Cc: Yann Collet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lz4.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lz4.h b/include/linux/lz4.h index d21c13f10a64..4356686b0a39 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -67,8 +67,8 @@ int lz4hc_compress(const unsigned char *src, size_t src_len, * note : Destination buffer must be already allocated. * slightly faster than lz4_decompress_unknownoutputsize() */ -int lz4_decompress(const char *src, size_t *src_len, char *dest, - size_t actual_dest_len); +int lz4_decompress(const unsigned char *src, size_t *src_len, + unsigned char *dest, size_t actual_dest_len); /* * lz4_decompress_unknownoutputsize() @@ -82,6 +82,6 @@ int lz4_decompress(const char *src, size_t *src_len, char *dest, * Error if return (< 0) * note : Destination buffer must be already allocated. */ -int lz4_decompress_unknownoutputsize(const char *src, size_t src_len, - char *dest, size_t *dest_len); +int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, + unsigned char *dest, size_t *dest_len); #endif -- cgit v1.2.3 From 7bd36014460f793c19e7d6c94dab67b0afcfcb7f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Sep 2013 16:50:56 -0700 Subject: timekeeping: Fix HRTICK related deadlock from ntp lock changes Gerlando Falauto reported that when HRTICK is enabled, it is possible to trigger system deadlocks. These were hard to reproduce, as HRTICK has been broken in the past, but seemed to be connected to the timekeeping_seq lock. Since seqlock/seqcount's aren't supported w/ lockdep, I added some extra spinlock based locking and triggered the following lockdep output: [ 15.849182] ntpd/4062 is trying to acquire lock: [ 15.849765] (&(&pool->lock)->rlock){..-...}, at: [] __queue_work+0x145/0x480 [ 15.850051] [ 15.850051] but task is already holding lock: [ 15.850051] (timekeeper_lock){-.-.-.}, at: [] do_adjtimex+0x7f/0x100 [ 15.850051] Chain exists of: &(&pool->lock)->rlock --> &p->pi_lock --> timekeeper_lock [ 15.850051] Possible unsafe locking scenario: [ 15.850051] [ 15.850051] CPU0 CPU1 [ 15.850051] ---- ---- [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&p->pi_lock); [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&(&pool->lock)->rlock); [ 15.850051] [ 15.850051] *** DEADLOCK *** The deadlock was introduced by 06c017fdd4dc48451a ("timekeeping: Hold timekeepering locks in do_adjtimex and hardpps") in 3.10 This patch avoids this deadlock, by moving the call to schedule_delayed_work() outside of the timekeeper lock critical section. Reported-by: Gerlando Falauto Tested-by: Lin Ming Signed-off-by: John Stultz Cc: Mathieu Desnoyers Cc: stable #3.11, 3.10 Link: http://lkml.kernel.org/r/1378943457-27314-1-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- include/linux/timex.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b3726e61368e..dd3edd7dfc94 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -141,6 +141,7 @@ extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); int read_current_timer(unsigned long *timer_val); +void ntp_notify_cmos_timer(void); /* The clock frequency of the i8253/i8254 PIT */ #define PIT_TICK_RATE 1193182ul -- cgit v1.2.3 From 1370e97bb2eb1ef2df7355204e5a4ba13e12b861 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 12 Sep 2013 10:55:34 -0400 Subject: seqlock: Add a new locking reader type The sequence lock (seqlock) was originally designed for the cases where the readers do not need to block the writers by making the readers retry the read operation when the data change. Since then, the use cases have been expanded to include situations where a thread does not need to change the data (effectively a reader) at all but have to take the writer lock because it can't tolerate changes to the protected structure. Some examples are the d_path() function and the getcwd() syscall in fs/dcache.c where the functions take the writer lock on rename_lock even though they don't need to change anything in the protected data structure at all. This is inefficient as a reader is now blocking other sequence number reading readers from moving forward by pretending to be a writer. This patch tries to eliminate this inefficiency by introducing a new type of locking reader to the seqlock locking mechanism. This new locking reader will try to take an exclusive lock preventing other writers and locking readers from going forward. However, it won't affect the progress of the other sequence number reading readers as the sequence number won't be changed. Signed-off-by: Waiman Long Cc: Alexander Viro Signed-off-by: Linus Torvalds --- include/linux/seqlock.h | 68 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 63 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 18299057402f..21a209336e79 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -3,15 +3,21 @@ /* * Reader/writer consistent mechanism without starving writers. This type of * lock for data where the reader wants a consistent set of information - * and is willing to retry if the information changes. Readers never - * block but they may have to retry if a writer is in - * progress. Writers do not wait for readers. + * and is willing to retry if the information changes. There are two types + * of readers: + * 1. Sequence readers which never block a writer but they may have to retry + * if a writer is in progress by detecting change in sequence number. + * Writers do not wait for a sequence reader. + * 2. Locking readers which will wait if a writer or another locking reader + * is in progress. A locking reader in progress will also block a writer + * from going forward. Unlike the regular rwlock, the read lock here is + * exclusive so that only one locking reader can get it. * - * This is not as cache friendly as brlock. Also, this will not work + * This is not as cache friendly as brlock. Also, this may not work well * for data that contains pointers, because any writer could * invalidate a pointer that a reader was following. * - * Expected reader usage: + * Expected non-blocking reader usage: * do { * seq = read_seqbegin(&foo); * ... @@ -268,4 +274,56 @@ write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) spin_unlock_irqrestore(&sl->lock, flags); } +/* + * A locking reader exclusively locks out other writers and locking readers, + * but doesn't update the sequence number. Acts like a normal spin_lock/unlock. + * Don't need preempt_disable() because that is in the spin_lock already. + */ +static inline void read_seqlock_excl(seqlock_t *sl) +{ + spin_lock(&sl->lock); +} + +static inline void read_sequnlock_excl(seqlock_t *sl) +{ + spin_unlock(&sl->lock); +} + +static inline void read_seqlock_excl_bh(seqlock_t *sl) +{ + spin_lock_bh(&sl->lock); +} + +static inline void read_sequnlock_excl_bh(seqlock_t *sl) +{ + spin_unlock_bh(&sl->lock); +} + +static inline void read_seqlock_excl_irq(seqlock_t *sl) +{ + spin_lock_irq(&sl->lock); +} + +static inline void read_sequnlock_excl_irq(seqlock_t *sl) +{ + spin_unlock_irq(&sl->lock); +} + +static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) +{ + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); + return flags; +} + +#define read_seqlock_excl_irqsave(lock, flags) \ + do { flags = __read_seqlock_excl_irqsave(lock); } while (0) + +static inline void +read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) +{ + spin_unlock_irqrestore(&sl->lock, flags); +} + #endif /* __LINUX_SEQLOCK_H */ -- cgit v1.2.3 From 5762482f5496cb1dd86acd2aace3ea25d1404e1f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 12 Sep 2013 10:12:47 -0700 Subject: vfs: move get_fs_root_and_pwd() to single caller Let's not pollute the include files with inline functions that are only used in a single place. Especially not if we decide we might want to change the semantics of said function to make it more efficient.. Signed-off-by: Linus Torvalds --- include/linux/fs_struct.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 2b93a9a5a1e6..0efc3e62843a 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -39,17 +39,6 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) spin_unlock(&fs->lock); } -static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, - struct path *pwd) -{ - spin_lock(&fs->lock); - *root = fs->root; - path_get(root); - *pwd = fs->pwd; - path_get(pwd); - spin_unlock(&fs->lock); -} - extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From 3b38722efd9f66da63bbbd41520c2e6fa9db3d68 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 12 Sep 2013 15:13:21 -0700 Subject: memcg, vmscan: integrate soft reclaim tighter with zone shrinking code This patchset is sitting out of tree for quite some time without any objections. I would be really happy if it made it into 3.12. I do not want to push it too hard but I think this work is basically ready and waiting more doesn't help. The basic idea is quite simple. Pull soft reclaim into shrink_zone in the first step and get rid of the previous soft reclaim infrastructure. shrink_zone is done in two passes now. First it tries to do the soft limit reclaim and it falls back to reclaim-all mode if no group is over the limit or no pages have been scanned. The second pass happens at the same priority so the only time we waste is the memcg tree walk which has been updated in the third step to have only negligible overhead. As a bonus we will get rid of a _lot_ of code by this and soft reclaim will not stand out like before when it wasn't integrated into the zone shrinking code and it reclaimed at priority 0 (the testing results show that some workloads suffers from such an aggressive reclaim). The clean up is in a separate patch because I felt it would be easier to review that way. The second step is soft limit reclaim integration into targeted reclaim. It should be rather straight forward. Soft limit has been used only for the global reclaim so far but it makes sense for any kind of pressure coming from up-the-hierarchy, including targeted reclaim. The third step (patches 4-8) addresses the tree walk overhead by enhancing memcg iterators to enable skipping whole subtrees and tracking number of over soft limit children at each level of the hierarchy. This information is updated same way the old soft limit tree was updated (from memcg_check_events) so we shouldn't see an additional overhead. In fact mem_cgroup_update_soft_limit is much simpler than tree manipulation done previously. __shrink_zone uses mem_cgroup_soft_reclaim_eligible as a predicate for mem_cgroup_iter so the decision whether a particular group should be visited is done at the iterator level which allows us to decide to skip the whole subtree as well (if there is no child in excess). This reduces the tree walk overhead considerably. * TEST 1 ======== My primary test case was a parallel kernel build with 2 groups (make is running with -j8 with a distribution .config in a separate cgroup without any hard limit) on a 32 CPU machine booted with 1GB memory and both builds run taskset to Node 0 cpus. I was mostly interested in 2 setups. Default - no soft limit set and - and 0 soft limit set to both groups. The first one should tell us whether the rework regresses the default behavior while the second one should show us improvements in an extreme case where both workloads are always over the soft limit. /usr/bin/time -v has been used to collect the statistics and each configuration had 3 runs after fresh boot without any other load on the system. base is mmotm-2013-07-18-16-40 rework all 8 patches applied on top of base * No-limit User no-limit/base: min: 651.92 max: 672.65 avg: 664.33 std: 8.01 runs: 6 no-limit/rework: min: 657.34 [100.8%] max: 668.39 [99.4%] avg: 663.13 [99.8%] std: 3.61 runs: 6 System no-limit/base: min: 69.33 max: 71.39 avg: 70.32 std: 0.79 runs: 6 no-limit/rework: min: 69.12 [99.7%] max: 71.05 [99.5%] avg: 70.04 [99.6%] std: 0.59 runs: 6 Elapsed no-limit/base: min: 398.27 max: 422.36 avg: 408.85 std: 7.74 runs: 6 no-limit/rework: min: 386.36 [97.0%] max: 438.40 [103.8%] avg: 416.34 [101.8%] std: 18.85 runs: 6 The results are within noise. Elapsed time has a bigger variance but the average looks good. * 0-limit User 0-limit/base: min: 573.76 max: 605.63 avg: 585.73 std: 12.21 runs: 6 0-limit/rework: min: 645.77 [112.6%] max: 666.25 [110.0%] avg: 656.97 [112.2%] std: 7.77 runs: 6 System 0-limit/base: min: 69.57 max: 71.13 avg: 70.29 std: 0.54 runs: 6 0-limit/rework: min: 68.68 [98.7%] max: 71.40 [100.4%] avg: 69.91 [99.5%] std: 0.87 runs: 6 Elapsed 0-limit/base: min: 1306.14 max: 1550.17 avg: 1430.35 std: 90.86 runs: 6 0-limit/rework: min: 404.06 [30.9%] max: 465.94 [30.1%] avg: 434.81 [30.4%] std: 22.68 runs: 6 The improvement is really huge here (even bigger than with my previous testing and I suspect that this highly depends on the storage). Page fault statistics tell us at least part of the story: Minor 0-limit/base: min: 37180461.00 max: 37319986.00 avg: 37247470.00 std: 54772.71 runs: 6 0-limit/rework: min: 36751685.00 [98.8%] max: 36805379.00 [98.6%] avg: 36774506.33 [98.7%] std: 17109.03 runs: 6 Major 0-limit/base: min: 170604.00 max: 221141.00 avg: 196081.83 std: 18217.01 runs: 6 0-limit/rework: min: 2864.00 [1.7%] max: 10029.00 [4.5%] avg: 5627.33 [2.9%] std: 2252.71 runs: 6 Same as with my previous testing Minor faults are more or less within noise but Major fault count is way bellow the base kernel. While this looks as a nice win it is fair to say that 0-limit configuration is quite artificial. So I was playing with 0-no-limit loads as well. * TEST 2 ======== The following results are from 2 groups configuration on a 16GB machine (single NUMA node). - A running stream IO (dd if=/dev/zero of=local.file bs=1024) with 2*TotalMem with 0 soft limit. - B running a mem_eater which consumes TotalMem-1G without any limit. The mem_eater consumes the memory in 100 chunks with 1s nap after each mmap+poppulate so that both loads have chance to fight for the memory. The expected result is that B shouldn't be reclaimed and A shouldn't see a big dropdown in elapsed time. User base: min: 2.68 max: 2.89 avg: 2.76 std: 0.09 runs: 3 rework: min: 3.27 [122.0%] max: 3.74 [129.4%] avg: 3.44 [124.6%] std: 0.21 runs: 3 System base: min: 86.26 max: 88.29 avg: 87.28 std: 0.83 runs: 3 rework: min: 81.05 [94.0%] max: 84.96 [96.2%] avg: 83.14 [95.3%] std: 1.61 runs: 3 Elapsed base: min: 317.28 max: 332.39 avg: 325.84 std: 6.33 runs: 3 rework: min: 281.53 [88.7%] max: 298.16 [89.7%] avg: 290.99 [89.3%] std: 6.98 runs: 3 System time improved slightly as well as Elapsed. My previous testing has shown worse numbers but this again seem to depend on the storage speed. My theory is that the writeback doesn't catch up and prio-0 soft reclaim falls into wait on writeback page too often in the base kernel. The patched kernel doesn't do that because the soft reclaim is done from the kswapd/direct reclaim context. This can be seen on the following graph nicely. The A's group usage_in_bytes regurarly drops really low very often. All 3 runs http://labs.suse.cz/mhocko/soft_limit_rework/stream_io-vs-mem_eater/stream.png resp. a detail of the single run http://labs.suse.cz/mhocko/soft_limit_rework/stream_io-vs-mem_eater/stream-one-run.png mem_eater seems to be doing better as well. It gets to the full allocation size faster as can be seen on the following graph: http://labs.suse.cz/mhocko/soft_limit_rework/stream_io-vs-mem_eater/mem_eater-one-run.png /proc/meminfo collected during the test also shows that rework kernel hasn't swapped that much (well almost not at all): base: max: 123900 K avg: 56388.29 K rework: max: 300 K avg: 128.68 K kswapd and direct reclaim statistics are of no use unfortunatelly because soft reclaim is not accounted properly as the counters are hidden by global_reclaim() checks in the base kernel. * TEST 3 ======== Another test was the same configuration as TEST2 except the stream IO was replaced by a single kbuild (16 parallel jobs bound to Node0 cpus same as in TEST1) and mem_eater allocated TotalMem-200M so kbuild had only 200MB left. Kbuild did better with the rework kernel here as well: User base: min: 860.28 max: 872.86 avg: 868.03 std: 5.54 runs: 3 rework: min: 880.81 [102.4%] max: 887.45 [101.7%] avg: 883.56 [101.8%] std: 2.83 runs: 3 System base: min: 84.35 max: 85.06 avg: 84.79 std: 0.31 runs: 3 rework: min: 85.62 [101.5%] max: 86.09 [101.2%] avg: 85.79 [101.2%] std: 0.21 runs: 3 Elapsed base: min: 135.36 max: 243.30 avg: 182.47 std: 45.12 runs: 3 rework: min: 110.46 [81.6%] max: 116.20 [47.8%] avg: 114.15 [62.6%] std: 2.61 runs: 3 Minor base: min: 36635476.00 max: 36673365.00 avg: 36654812.00 std: 15478.03 runs: 3 rework: min: 36639301.00 [100.0%] max: 36695541.00 [100.1%] avg: 36665511.00 [100.0%] std: 23118.23 runs: 3 Major base: min: 14708.00 max: 53328.00 avg: 31379.00 std: 16202.24 runs: 3 rework: min: 302.00 [2.1%] max: 414.00 [0.8%] avg: 366.33 [1.2%] std: 47.22 runs: 3 Again we can see a significant improvement in Elapsed (it also seems to be more stable), there is a huge dropdown for the Major page faults and much more swapping: base: max: 583736 K avg: 112547.43 K rework: max: 4012 K avg: 124.36 K Graphs from all three runs show the variability of the kbuild quite nicely. It even seems that it took longer after every run with the base kernel which would be quite surprising as the source tree for the build is removed and caches are dropped after each run so the build operates on a freshly extracted sources everytime. http://labs.suse.cz/mhocko/soft_limit_rework/stream_io-vs-mem_eater/kbuild-mem_eater.png My other testing shows that this is just a matter of timing and other runs behave differently the std for Elapsed time is similar ~50. Example of other three runs: http://labs.suse.cz/mhocko/soft_limit_rework/stream_io-vs-mem_eater/kbuild-mem_eater2.png So to wrap this up. The series is still doing good and improves the soft limit. The testing results for bunch of cgroups with both stream IO and kbuild loads can be found in "memcg: track children in soft limit excess to improve soft limit". This patch: Memcg soft reclaim has been traditionally triggered from the global reclaim paths before calling shrink_zone. mem_cgroup_soft_limit_reclaim then picked up a group which exceeds the soft limit the most and reclaimed it with 0 priority to reclaim at least SWAP_CLUSTER_MAX pages. The infrastructure requires per-node-zone trees which hold over-limit groups and keep them up-to-date (via memcg_check_events) which is not cost free. Although this overhead hasn't turned out to be a bottle neck the implementation is suboptimal because mem_cgroup_update_tree has no idea which zones consumed memory over the limit so we could easily end up having a group on a node-zone tree having only few pages from that node-zone. This patch doesn't try to fix node-zone trees management because it seems that integrating soft reclaim into zone shrinking sounds much easier and more appropriate for several reasons. First of all 0 priority reclaim was a crude hack which might lead to big stalls if the group's LRUs are big and hard to reclaim (e.g. a lot of dirty/writeback pages). Soft reclaim should be applicable also to the targeted reclaim which is awkward right now without additional hacks. Last but not least the whole infrastructure eats quite some code. After this patch shrink_zone is done in 2 passes. First it tries to do the soft reclaim if appropriate (only for global reclaim for now to keep compatible with the original state) and fall back to ignoring soft limit if no group is eligible to soft reclaim or nothing has been scanned during the first pass. Only groups which are over their soft limit or any of their parents up the hierarchy is over the limit are considered eligible during the first pass. Soft limit tree which is not necessary anymore will be removed in the follow up patch to make this patch smaller and easier to review. Signed-off-by: Michal Hocko Reviewed-by: Glauber Costa Reviewed-by: Tejun Heo Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Ying Han Cc: Hugh Dickins Cc: Michel Lespinasse Cc: Greg Thelen Cc: KOSAKI Motohiro Cc: Balbir Singh Cc: Glauber Costa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c416092e324..4b78661c68d0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,9 +180,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -359,11 +357,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) { - return 0; + return false; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From a5b7c87f92076352dbff2fe0423ec255e1c9a71b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 12 Sep 2013 15:13:25 -0700 Subject: vmscan, memcg: do softlimit reclaim also for targeted reclaim Soft reclaim has been done only for the global reclaim (both background and direct). Since "memcg: integrate soft reclaim tighter with zone shrinking code" there is no reason for this limitation anymore as the soft limit reclaim doesn't use any special code paths and it is a part of the zone shrinking code which is used by both global and targeted reclaims. From the semantic point of view it is natural to consider soft limit before touching all groups in the hierarchy tree which is touching the hard limit because soft limit tells us where to push back when there is a memory pressure. It is not important whether the pressure comes from the limit or imbalanced zones. This patch simply enables soft reclaim unconditionally in mem_cgroup_should_soft_reclaim so it is enabled for both global and targeted reclaim paths. mem_cgroup_soft_reclaim_eligible needs to learn about the root of the reclaim to know where to stop checking soft limit state of parents up the hierarchy. Say we have A (over soft limit) \ B (below s.l., hit the hard limit) / \ C D (below s.l.) B is the source of the outside memory pressure now for D but we shouldn't soft reclaim it because it is behaving well under B subtree and we can still reclaim from C (pressumably it is over the limit). mem_cgroup_soft_reclaim_eligible should therefore stop climbing up the hierarchy at B (root of the memory pressure). Signed-off-by: Michal Hocko Reviewed-by: Glauber Costa Reviewed-by: Tejun Heo Cc: Balbir Singh Cc: Greg Thelen Cc: Hugh Dickins Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Michel Lespinasse Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4b78661c68d0..d8dd6560621b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,7 +180,8 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, + struct mem_cgroup *root); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -357,7 +358,8 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, + struct mem_cgroup *root) { return false; } -- cgit v1.2.3 From de57780dc659f95b17ccb649f003278dde0b5b86 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 12 Sep 2013 15:13:26 -0700 Subject: memcg: enhance memcg iterator to support predicates The caller of the iterator might know that some nodes or even subtrees should be skipped but there is no way to tell iterators about that so the only choice left is to let iterators to visit each node and do the selection outside of the iterating code. This, however, doesn't scale well with hierarchies with many groups where only few groups are interesting. This patch adds mem_cgroup_iter_cond variant of the iterator with a callback which gets called for every visited node. There are three possible ways how the callback can influence the walk. Either the node is visited, it is skipped but the tree walk continues down the tree or the whole subtree of the current group is skipped. [hughd@google.com: fix memcg-less page reclaim] Signed-off-by: Michal Hocko Cc: Balbir Singh Cc: Glauber Costa Cc: Greg Thelen Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Michel Lespinasse Cc: Tejun Heo Cc: Ying Han Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 49 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 43 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d8dd6560621b..d4d1f9b0dbba 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -41,6 +41,23 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; +enum mem_cgroup_filter_t { + VISIT, /* visit current node */ + SKIP, /* skip the current node and continue traversal */ + SKIP_TREE, /* skip the whole subtree and continue traversal */ +}; + +/* + * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to + * iterate through the hierarchy tree. Each tree element is checked by the + * predicate before it is returned by the iterator. If a filter returns + * SKIP or SKIP_TREE then the iterator code continues traversal (with the + * next node down the hierarchy or the next node that doesn't belong under the + * memcg's subtree). + */ +typedef enum mem_cgroup_filter_t +(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); + #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -108,9 +125,18 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); +struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim, + mem_cgroup_iter_filter cond); + +static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim) +{ + return mem_cgroup_iter_cond(root, prev, reclaim, NULL); +} + void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -180,7 +206,8 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +enum mem_cgroup_filter_t +mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); @@ -295,6 +322,15 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } +static inline struct mem_cgroup * +mem_cgroup_iter_cond(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim, + mem_cgroup_iter_filter cond) +{ + /* first call must return non-NULL, second return NULL */ + return (struct mem_cgroup *)(unsigned long)!prev; +} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -358,10 +394,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +enum mem_cgroup_filter_t +mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root) { - return false; + return VISIT; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From 759496ba6407c6994d6a5ce3a5e74937d7816208 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 12 Sep 2013 15:13:39 -0700 Subject: arch: mm: pass userspace fault flag to generic fault handler Unlike global OOM handling, memory cgroup code will invoke the OOM killer in any OOM situation because it has no way of telling faults occuring in kernel context - which could be handled more gracefully - from user-triggered faults. Pass a flag that identifies faults originating in user space from the architecture-specific fault handlers to generic code so that memcg OOM handling can be improved. Signed-off-by: Johannes Weiner Reviewed-by: Michal Hocko Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: azurIt Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index caf543c7eaa7..3d9b503bcd00 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -176,6 +176,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ #define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ #define FAULT_FLAG_TRIED 0x40 /* second try */ +#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's -- cgit v1.2.3 From 519e52473ebe9db5cdef44670d5a97f1fd53d721 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 12 Sep 2013 15:13:42 -0700 Subject: mm: memcg: enable memcg OOM killer only for user faults System calls and kernel faults (uaccess, gup) can handle an out of memory situation gracefully and just return -ENOMEM. Enable the memcg OOM killer only for user faults, where it's really the only option available. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: azurIt Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 3 +++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d4d1f9b0dbba..34ac6497d01a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -151,6 +151,37 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); +/** + * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task + * @new: true to enable, false to disable + * + * Toggle whether a failed memcg charge should invoke the OOM killer + * or just return -ENOMEM. Returns the previous toggle state. + */ +static inline bool mem_cgroup_toggle_oom(bool new) +{ + bool old; + + old = current->memcg_oom.may_oom; + current->memcg_oom.may_oom = new; + + return old; +} + +static inline void mem_cgroup_enable_oom(void) +{ + bool old = mem_cgroup_toggle_oom(true); + + WARN_ON(old == true); +} + +static inline void mem_cgroup_disable_oom(void) +{ + bool old = mem_cgroup_toggle_oom(false); + + WARN_ON(old == false); +} + #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif @@ -383,6 +414,19 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, { } +static inline bool mem_cgroup_toggle_oom(bool new) +{ + return false; +} + +static inline void mem_cgroup_enable_oom(void) +{ +} + +static inline void mem_cgroup_disable_oom(void) +{ +} + static inline void mem_cgroup_inc_page_stat(struct page *page, enum mem_cgroup_page_stat_item idx) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 45f254dddafc..9ce1fa53031f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1393,6 +1393,9 @@ struct task_struct { unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; unsigned int memcg_kmem_skip_account; + struct memcg_oom_info { + unsigned int may_oom:1; + } memcg_oom; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; -- cgit v1.2.3 From 3812c8c8f3953921ef18544110dafc3505c1ac62 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 12 Sep 2013 15:13:44 -0700 Subject: mm: memcg: do not trap chargers with full callstack on OOM The memcg OOM handling is incredibly fragile and can deadlock. When a task fails to charge memory, it invokes the OOM killer and loops right there in the charge code until it succeeds. Comparably, any other task that enters the charge path at this point will go to a waitqueue right then and there and sleep until the OOM situation is resolved. The problem is that these tasks may hold filesystem locks and the mmap_sem; locks that the selected OOM victim may need to exit. For example, in one reported case, the task invoking the OOM killer was about to charge a page cache page during a write(), which holds the i_mutex. The OOM killer selected a task that was just entering truncate() and trying to acquire the i_mutex: OOM invoking task: mem_cgroup_handle_oom+0x241/0x3b0 mem_cgroup_cache_charge+0xbe/0xe0 add_to_page_cache_locked+0x4c/0x140 add_to_page_cache_lru+0x22/0x50 grab_cache_page_write_begin+0x8b/0xe0 ext3_write_begin+0x88/0x270 generic_file_buffered_write+0x116/0x290 __generic_file_aio_write+0x27c/0x480 generic_file_aio_write+0x76/0xf0 # takes ->i_mutex do_sync_write+0xea/0x130 vfs_write+0xf3/0x1f0 sys_write+0x51/0x90 system_call_fastpath+0x18/0x1d OOM kill victim: do_truncate+0x58/0xa0 # takes i_mutex do_last+0x250/0xa30 path_openat+0xd7/0x440 do_filp_open+0x49/0xa0 do_sys_open+0x106/0x240 sys_open+0x20/0x30 system_call_fastpath+0x18/0x1d The OOM handling task will retry the charge indefinitely while the OOM killed task is not releasing any resources. A similar scenario can happen when the kernel OOM killer for a memcg is disabled and a userspace task is in charge of resolving OOM situations. In this case, ALL tasks that enter the OOM path will be made to sleep on the OOM waitqueue and wait for userspace to free resources or increase the group's limit. But a userspace OOM handler is prone to deadlock itself on the locks held by the waiting tasks. For example one of the sleeping tasks may be stuck in a brk() call with the mmap_sem held for writing but the userspace handler, in order to pick an optimal victim, may need to read files from /proc/, which tries to acquire the same mmap_sem for reading and deadlocks. This patch changes the way tasks behave after detecting a memcg OOM and makes sure nobody loops or sleeps with locks held: 1. When OOMing in a user fault, invoke the OOM killer and restart the fault instead of looping on the charge attempt. This way, the OOM victim can not get stuck on locks the looping task may hold. 2. When OOMing in a user fault but somebody else is handling it (either the kernel OOM killer or a userspace handler), don't go to sleep in the charge context. Instead, remember the OOMing memcg in the task struct and then fully unwind the page fault stack with -ENOMEM. pagefault_out_of_memory() will then call back into the memcg code to check if the -ENOMEM came from the memcg, and then either put the task to sleep on the memcg's OOM waitqueue or just restart the fault. The OOM victim can no longer get stuck on any lock a sleeping task may hold. Debugged by Michal Hocko. Signed-off-by: Johannes Weiner Reported-by: azurIt Acked-by: Michal Hocko Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 21 +++++++++++++++++++++ include/linux/sched.h | 4 ++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 34ac6497d01a..89d576cfcc4c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -157,6 +157,10 @@ extern void mem_cgroup_replace_page_cache(struct page *oldpage, * * Toggle whether a failed memcg charge should invoke the OOM killer * or just return -ENOMEM. Returns the previous toggle state. + * + * NOTE: Any path that enables the OOM killer before charging must + * call mem_cgroup_oom_synchronize() afterward to finalize the + * OOM handling and clean up. */ static inline bool mem_cgroup_toggle_oom(bool new) { @@ -182,6 +186,13 @@ static inline void mem_cgroup_disable_oom(void) WARN_ON(old == false); } +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return p->memcg_oom.in_memcg_oom; +} + +bool mem_cgroup_oom_synchronize(void); + #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif @@ -427,6 +438,16 @@ static inline void mem_cgroup_disable_oom(void) { } +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return false; +} + +static inline bool mem_cgroup_oom_synchronize(void) +{ + return false; +} + static inline void mem_cgroup_inc_page_stat(struct page *page, enum mem_cgroup_page_stat_item idx) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 9ce1fa53031f..6682da36b293 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1395,6 +1395,10 @@ struct task_struct { unsigned int memcg_kmem_skip_account; struct memcg_oom_info { unsigned int may_oom:1; + unsigned int in_memcg_oom:1; + unsigned int oom_locked:1; + int wakeups; + struct mem_cgroup *wait_on_memcg; } memcg_oom; #endif #ifdef CONFIG_UPROBES -- cgit v1.2.3 From 34ff8dc08956098563989d8599840b130be81252 Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Thu, 12 Sep 2013 15:13:46 -0700 Subject: memcg: correct RESOURCE_MAX to ULLONG_MAX Current RESOURCE_MAX is ULONG_MAX, but the value we used to set resource limit is unsigned long long, so we can set bigger value than that which is strange. The XXX_MAX should be reasonable max value, bigger than that should be overflow. Notice that this change will affect user output of default *.limit_in_bytes: before change: $ cat /cgroup/memory/memory.limit_in_bytes 9223372036854775807 after change: $ cat /cgroup/memory/memory.limit_in_bytes 18446744073709551615 But it doesn't alter the API in term of input - we can still use "echo -1 > *.limit_in_bytes" to reset the numbers to "unlimited". Signed-off-by: Sha Zhengju Signed-off-by: Qiang Huang Acked-by: Michal Hocko Cc: Daisuke Nishimura Cc: Jeff Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 96a509b6be04..586bc7cb1dcf 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -54,7 +54,7 @@ struct res_counter { struct res_counter *parent; }; -#define RESOURCE_MAX (unsigned long long)LLONG_MAX +#define RESOURCE_MAX ULLONG_MAX /** * Helpers to interact with userspace -- cgit v1.2.3 From 6de5a8bfcae6e3b427d642eff078d8305b324b52 Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Thu, 12 Sep 2013 15:13:47 -0700 Subject: memcg: rename RESOURCE_MAX to RES_COUNTER_MAX RESOURCE_MAX is far too general name, change it to RES_COUNTER_MAX. Signed-off-by: Sha Zhengju Signed-off-by: Qiang Huang Acked-by: Michal Hocko Cc: Daisuke Nishimura Cc: Jeff Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 586bc7cb1dcf..201a69749659 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -54,7 +54,7 @@ struct res_counter { struct res_counter *parent; }; -#define RESOURCE_MAX ULLONG_MAX +#define RES_COUNTER_MAX ULLONG_MAX /** * Helpers to interact with userspace -- cgit v1.2.3 From 68b4876d996e8749142b2895bc2e251448996363 Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Thu, 12 Sep 2013 15:13:50 -0700 Subject: memcg: remove MEMCG_NR_FILE_MAPPED While accounting memcg page stat, it's not worth to use MEMCG_NR_FILE_MAPPED as an extra layer of indirection because of the complexity and presumed performance overhead. We can use MEM_CGROUP_STAT_FILE_MAPPED directly. Signed-off-by: Sha Zhengju Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Acked-by: Fengguang Wu Reviewed-by: Greg Thelen Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 89d576cfcc4c..f952a07ce7a9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -30,9 +30,20 @@ struct page; struct mm_struct; struct kmem_cache; -/* Stats that can be updated by kernel. */ -enum mem_cgroup_page_stat_item { - MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */ +/* + * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c, + * These two lists should keep in accord with each other. + */ +enum mem_cgroup_stat_index { + /* + * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. + */ + MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ + MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ + MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ + MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ + MEM_CGROUP_STAT_NSTATS, }; struct mem_cgroup_reclaim_cookie { @@ -233,17 +244,17 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, } void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx, + enum mem_cgroup_stat_index idx, int val); static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { mem_cgroup_update_page_stat(page, idx, 1); } static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { mem_cgroup_update_page_stat(page, idx, -1); } @@ -449,12 +460,12 @@ static inline bool mem_cgroup_oom_synchronize(void) } static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { } static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { } -- cgit v1.2.3 From 3ea67d06e4679a16f69f66f43a8d6ee4778985fc Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Thu, 12 Sep 2013 15:13:53 -0700 Subject: memcg: add per cgroup writeback pages accounting Add memcg routines to count writeback pages, later dirty pages will also be accounted. After Kame's commit 89c06bd52fb9 ("memcg: use new logic for page stat accounting"), we can use 'struct page' flag to test page state instead of per page_cgroup flag. But memcg has a feature to move a page from a cgroup to another one and may have race between "move" and "page stat accounting". So in order to avoid the race we have designed a new lock: mem_cgroup_begin_update_page_stat() modify page information -->(a) mem_cgroup_update_page_stat() -->(b) mem_cgroup_end_update_page_stat() It requires both (a) and (b)(writeback pages accounting) to be pretected in mem_cgroup_{begin/end}_update_page_stat(). It's full no-op for !CONFIG_MEMCG, almost no-op if memcg is disabled (but compiled in), rcu read lock in the most cases (no task is moving), and spin_lock_irqsave on top in the slow path. There're two writeback interfaces to modify: test_{clear/set}_page_writeback(). And the lock order is: --> memcg->move_lock --> mapping->tree_lock Signed-off-by: Sha Zhengju Acked-by: Michal Hocko Reviewed-by: Greg Thelen Cc: Fengguang Wu Cc: KAMEZAWA Hiroyuki Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f952a07ce7a9..60e95872da29 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -42,6 +42,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; -- cgit v1.2.3 From 5fbc461636c32efdb9d5216d491d37a40d54535b Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 12 Sep 2013 15:13:55 -0700 Subject: mm: make lru_add_drain_all() selective make lru_add_drain_all() only selectively interrupt the cpus that have per-cpu free pages that can be drained. This is important in nohz mode where calling mlockall(), for example, otherwise will interrupt every core unnecessarily. This is important on workloads where nohz cores are handling 10 Gb traffic in userspace. Those CPUs do not enter the kernel and place pages into LRU pagevecs and they really, really don't want to be interrupted, or they drop packets on the floor. Signed-off-by: Chris Metcalf Reviewed-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index c03c139219c9..46ba0c6c219f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -280,7 +280,7 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); -extern int lru_add_drain_all(void); +extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_page(struct page *page); extern void swap_setup(void); -- cgit v1.2.3 From 7caef26767c1727d7abfbbbfbe8b2bb473430d48 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 12 Sep 2013 15:13:56 -0700 Subject: truncate: drop 'oldsize' truncate_pagecache() parameter truncate_pagecache() doesn't care about old size since commit cedabed49b39 ("vfs: Fix vmtruncate() regression"). Let's drop it. Signed-off-by: Kirill A. Shutemov Cc: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3d9b503bcd00..928df792c005 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -985,7 +985,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } -extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); +extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); -- cgit v1.2.3 From c02925540ca7019465a43c00f8a3c0186ddace2b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 12 Sep 2013 15:14:05 -0700 Subject: thp: consolidate code between handle_mm_fault() and do_huge_pmd_anonymous_page() do_huge_pmd_anonymous_page() has copy-pasted piece of handle_mm_fault() to handle fallback path. Let's consolidate code back by introducing VM_FAULT_FALLBACK return code. Signed-off-by: Kirill A. Shutemov Acked-by: Hillf Danton Cc: Andrea Arcangeli Cc: Al Viro Cc: Hugh Dickins Cc: Wu Fengguang Cc: Jan Kara Cc: Mel Gorman Cc: Andi Kleen Cc: Matthew Wilcox Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 3 --- include/linux/mm.h | 3 ++- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b60de92e2edc..3935428c57cf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,9 +96,6 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end); -extern int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, unsigned int flags); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 928df792c005..8b6e55ee8855 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -877,11 +877,12 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ +#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_HWPOISON_LARGE) + VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) -- cgit v1.2.3 From 0244ad004a54e39308d495fee0a2e637f8b5c317 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 30 Aug 2013 09:39:53 +0200 Subject: Remove GENERIC_HARDIRQ config option After the last architecture switched to generic hard irqs the config options HAVE_GENERIC_HARDIRQS & GENERIC_HARDIRQS and the related code for !CONFIG_GENERIC_HARDIRQS can be removed. Signed-off-by: Martin Schwidefsky --- include/linux/cpu_rmap.h | 3 -- include/linux/hardirq.h | 4 --- include/linux/interrupt.h | 75 ++------------------------------------------- include/linux/irq.h | 9 ------ include/linux/irqdesc.h | 3 -- include/linux/irqnr.h | 19 ------------ include/linux/kernel_stat.h | 34 -------------------- 7 files changed, 3 insertions(+), 144 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 1739510d8994..bdd18caa6c94 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -52,8 +52,6 @@ static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu) return rmap->obj[rmap->near[cpu].index]; } -#ifdef CONFIG_GENERIC_HARDIRQS - /** * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs * @size: Number of objects to be mapped @@ -68,5 +66,4 @@ extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); -#endif #endif /* __LINUX_CPU_RMAP_H */ diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index ccfe17c5c8da..1e041063b226 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -7,11 +7,7 @@ #include -#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); -#else -# define synchronize_irq(irq) barrier() -#endif #if defined(CONFIG_TINY_RCU) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5fa5afeeb759..5e865b554940 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -120,7 +120,6 @@ struct irqaction { extern irqreturn_t no_action(int cpl, void *dev_id); -#ifdef CONFIG_GENERIC_HARDIRQS extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, @@ -140,40 +139,6 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, extern int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id); -#else - -extern int __must_check -request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, - const char *name, void *dev); - -/* - * Special function to avoid ifdeffery in kernel/irq/devres.c which - * gets magically built by GENERIC_HARDIRQS=n architectures (sparc, - * m68k). I really love these $@%#!* obvious Makefile references: - * ../../../kernel/irq/devres.o - */ -static inline int __must_check -request_threaded_irq(unsigned int irq, irq_handler_t handler, - irq_handler_t thread_fn, - unsigned long flags, const char *name, void *dev) -{ - return request_irq(irq, handler, flags, name, dev); -} - -static inline int __must_check -request_any_context_irq(unsigned int irq, irq_handler_t handler, - unsigned long flags, const char *name, void *dev_id) -{ - return request_irq(irq, handler, flags, name, dev_id); -} - -static inline int __must_check -request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *percpu_dev_id) -{ - return request_irq(irq, handler, 0, devname, percpu_dev_id); -} -#endif extern void free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); @@ -221,7 +186,6 @@ extern void enable_irq(unsigned int irq); extern void enable_percpu_irq(unsigned int irq, unsigned int type); /* The following three functions are for the core kernel use only. */ -#ifdef CONFIG_GENERIC_HARDIRQS extern void suspend_device_irqs(void); extern void resume_device_irqs(void); #ifdef CONFIG_PM_SLEEP @@ -229,13 +193,8 @@ extern int check_wakeup_irqs(void); #else static inline int check_wakeup_irqs(void) { return 0; } #endif -#else -static inline void suspend_device_irqs(void) { }; -static inline void resume_device_irqs(void) { }; -static inline int check_wakeup_irqs(void) { return 0; } -#endif -#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) +#if defined(CONFIG_SMP) extern cpumask_var_t irq_default_affinity; @@ -287,9 +246,8 @@ static inline int irq_set_affinity_hint(unsigned int irq, { return -EINVAL; } -#endif /* CONFIG_SMP && CONFIG_GENERIC_HARDIRQS */ +#endif /* CONFIG_SMP */ -#ifdef CONFIG_GENERIC_HARDIRQS /* * Special lockdep variants of irq disabling/enabling. * These should be used for locking constructs that @@ -354,33 +312,6 @@ static inline int disable_irq_wake(unsigned int irq) return irq_set_irq_wake(irq, 0); } -#else /* !CONFIG_GENERIC_HARDIRQS */ -/* - * NOTE: non-genirq architectures, if they want to support the lock - * validator need to define the methods below in their asm/irq.h - * files, under an #ifdef CONFIG_LOCKDEP section. - */ -#ifndef CONFIG_LOCKDEP -# define disable_irq_nosync_lockdep(irq) disable_irq_nosync(irq) -# define disable_irq_nosync_lockdep_irqsave(irq, flags) \ - disable_irq_nosync(irq) -# define disable_irq_lockdep(irq) disable_irq(irq) -# define enable_irq_lockdep(irq) enable_irq(irq) -# define enable_irq_lockdep_irqrestore(irq, flags) \ - enable_irq(irq) -# endif - -static inline int enable_irq_wake(unsigned int irq) -{ - return 0; -} - -static inline int disable_irq_wake(unsigned int irq) -{ - return 0; -} -#endif /* CONFIG_GENERIC_HARDIRQS */ - #ifdef CONFIG_IRQ_FORCED_THREADING extern bool force_irqthreads; @@ -655,7 +586,7 @@ void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) * if more than one irq occurred. */ -#if defined(CONFIG_GENERIC_HARDIRQS) && !defined(CONFIG_GENERIC_IRQ_PROBE) +#if !defined(CONFIG_GENERIC_IRQ_PROBE) static inline unsigned long probe_irq_on(void) { return 0; diff --git a/include/linux/irq.h b/include/linux/irq.h index f04d3ba335cb..56bb0dc8b7d4 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -382,8 +382,6 @@ extern void irq_cpu_online(void); extern void irq_cpu_offline(void); extern int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask); -#ifdef CONFIG_GENERIC_HARDIRQS - #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); void irq_move_masked_irq(struct irq_data *data); @@ -802,11 +800,4 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { } static inline void irq_gc_unlock(struct irq_chip_generic *gc) { } #endif -#else /* !CONFIG_GENERIC_HARDIRQS */ - -extern struct msi_desc *irq_get_msi_desc(unsigned int irq); -extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry); - -#endif /* CONFIG_GENERIC_HARDIRQS */ - #endif /* _LINUX_IRQ_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 623325e2ff97..56fb646909dc 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -76,8 +76,6 @@ struct irq_desc { extern struct irq_desc irq_desc[NR_IRQS]; #endif -#ifdef CONFIG_GENERIC_HARDIRQS - static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc) { return &desc->irq_data; @@ -173,6 +171,5 @@ __irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler) desc->preflow_handler = handler; } #endif -#endif #endif diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index 0a2dc46cdaf6..fdd5cc16c9c4 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -4,23 +4,6 @@ #include -#ifndef CONFIG_GENERIC_HARDIRQS -#include - -/* - * Wrappers for non-genirq architectures: - */ -#define nr_irqs NR_IRQS -#define irq_to_desc(irq) (&irq_desc[irq]) - -# define for_each_irq_desc(irq, desc) \ - for (irq = 0; irq < nr_irqs; irq++) - -# define for_each_irq_desc_reverse(irq, desc) \ - for (irq = nr_irqs - 1; irq >= 0; irq--) - -#else /* CONFIG_GENERIC_HARDIRQS */ - extern int nr_irqs; extern struct irq_desc *irq_to_desc(unsigned int irq); unsigned int irq_get_next_irq(unsigned int offset); @@ -50,8 +33,6 @@ unsigned int irq_get_next_irq(unsigned int offset); for (irq = irq_get_next_irq(0); irq < nr_irqs; \ irq = irq_get_next_irq(irq + 1)) -#endif /* CONFIG_GENERIC_HARDIRQS */ - #define for_each_irq_nr(irq) \ for (irq = 0; irq < nr_irqs; irq++) diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index ed5f6ed6eb77..51c72be4a7c3 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -36,9 +36,6 @@ struct kernel_cpustat { }; struct kernel_stat { -#ifndef CONFIG_GENERIC_HARDIRQS - unsigned int irqs[NR_IRQS]; -#endif unsigned long irqs_sum; unsigned int softirqs[NR_SOFTIRQS]; }; @@ -54,22 +51,6 @@ DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat); extern unsigned long long nr_context_switches(void); -#ifndef CONFIG_GENERIC_HARDIRQS - -struct irq_desc; - -static inline void kstat_incr_irqs_this_cpu(unsigned int irq, - struct irq_desc *desc) -{ - __this_cpu_inc(kstat.irqs[irq]); - __this_cpu_inc(kstat.irqs_sum); -} - -static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) -{ - return kstat_cpu(cpu).irqs[irq]; -} -#else #include extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu); @@ -79,8 +60,6 @@ do { \ __this_cpu_inc(kstat.irqs_sum); \ } while (0) -#endif - static inline void kstat_incr_softirqs_this_cpu(unsigned int irq) { __this_cpu_inc(kstat.softirqs[irq]); @@ -94,20 +73,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) /* * Number of interrupts per specific IRQ source, since bootup */ -#ifndef CONFIG_GENERIC_HARDIRQS -static inline unsigned int kstat_irqs(unsigned int irq) -{ - unsigned int sum = 0; - int cpu; - - for_each_possible_cpu(cpu) - sum += kstat_irqs_cpu(irq, cpu); - - return sum; -} -#else extern unsigned int kstat_irqs(unsigned int irq); -#endif /* * Number of interrupts per cpu, since bootup -- cgit v1.2.3 From 331415ff16a12147d57d5c953f3a961b7ede348b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 11 Sep 2013 21:56:50 +0200 Subject: HID: provide a helper for validating hid reports Many drivers need to validate the characteristics of their HID report during initialization to avoid misusing the reports. This adds a common helper to perform validation of the report exisitng, the field existing, and the expected number of values within the field. Signed-off-by: Kees Cook Cc: stable@vger.kernel.org Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ee1ffc5e19c9..31b9d299ef6c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -756,6 +756,10 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +struct hid_report *hid_validate_values(struct hid_device *hid, + unsigned int type, unsigned int id, + unsigned int field_index, + unsigned int report_counts); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); -- cgit v1.2.3 From 35e4237973665c8a1ad4e3f7a7cb87573deaa24a Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 13 Sep 2013 07:34:13 -0700 Subject: vxlan: Fix sparse warnings This patch fixes sparse warnings when incorrectly handling the port number and using int instead of unsigned int iterating through &vn->sock_list[]. Keeping the port as __be16 also makes things clearer wrt endianess. Also, it was pointed out that vxlan_get_rx_port() had unnecessary checks which got removed. Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 041b42a305f6..3de49aca4519 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -950,14 +950,14 @@ struct netdev_phys_port_id { * multiple net devices on single physical port. * * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notiy a driver about the UDP port and socket * address family that vxlan is listnening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. @@ -1093,10 +1093,10 @@ struct net_device_ops { struct netdev_phys_port_id *ppid); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); }; /* -- cgit v1.2.3 From 0f1799ba1a5db4c48b72ac2da2dc70d8c190a73d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:04:53 +0200 Subject: netfilter: ipset: Consistent userspace testing with nomatch flag The "nomatch" commandline flag should invert the matching at testing, similarly to the --return-nomatch flag of the "set" match of iptables. Until now it worked with the elements with "nomatch" flag only. From now on it works with elements without the flag too, i.e: # ipset n test hash:net # ipset a test 10.0.0.0/24 nomatch # ipset t test 10.0.0.1 10.0.0.1 is NOT in set test. # ipset t test 10.0.0.1 nomatch 10.0.0.1 is in set test. # ipset a test 192.168.0.0/24 # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is NOT in set test. Before the patch the results were ... # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is in set test. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index d80e2753847c..9ac9fbde7b61 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -296,10 +296,12 @@ ip_set_eexist(int ret, u32 flags) /* Match elements marked with nomatch */ static inline bool -ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && - ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); + (set->type->features & IPSET_TYPE_NOMATCH) && + ((flags >> 16) & IPSET_FLAG_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ -- cgit v1.2.3 From ba6a3541545542721ce821d1e7e5ce35752e6fdf Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Sep 2013 13:52:33 +0200 Subject: KVM: mmu: allow page tables to be in read-only slots Page tables in a read-only memory slot will currently cause a triple fault because the page walker uses gfn_to_hva and it fails on such a slot. OVMF uses such a page table; however, real hardware seems to be fine with that as long as the accessed/dirty bits are set. Save whether the slot is readonly, and later check it when updating the accessed and dirty bits. Reviewed-by: Xiao Guangrong Reviewed-by: Gleb Natapov Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ca645a01d37a..0fbbc7aa02cb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -533,6 +533,7 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -- cgit v1.2.3 From 7c2330f1afe13b3a934140857bc8060d00103a89 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Sep 2013 18:08:02 -0700 Subject: regulator: fix fatal kernel-doc error Fix fatal kernel-doc error in : Error(include/linux/regulator/driver.h:52): cannot understand prototype: 'struct regulator_linear_range ' Signed-off-by: Randy Dunlap [Rewrote first line -- broonie] Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 67e13aa5a478..9bdad43ad228 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -40,6 +40,8 @@ enum regulator_status { }; /** + * struct regulator_linear_range - specify linear voltage ranges + * * Specify a range of voltages for regulator_map_linar_range() and * regulator_list_linear_range(). * -- cgit v1.2.3 From f84cb8a46a771f36a04a02c61ea635c968ed5f6a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 19 Sep 2013 12:13:58 -0400 Subject: dm mpath: disable WRITE SAME if it fails Workaround the SCSI layer's problematic WRITE SAME heuristics by disabling WRITE SAME in the DM multipath device's queue_limits if an underlying device disabled it. The WRITE SAME heuristics, with both the original commit 5db44863b6eb ("[SCSI] sd: Implement support for WRITE SAME") and the updated commit 66c28f971 ("[SCSI] sd: Update WRITE SAME heuristics"), default to enabling WRITE SAME(10) even without successfully determining it is supported. After the first failed WRITE SAME the SCSI layer will disable WRITE SAME for the device (by setting sdkp->device->no_write_same which results in 'max_write_same_sectors' in device's queue_limits to be set to 0). When a device is stacked ontop of such a SCSI device any changes to that SCSI device's queue_limits do not automatically propagate up the stack. As such, a DM multipath device will not have its WRITE SAME support disabled. This causes the block layer to continue to issue WRITE SAME requests to the mpath device which causes paths to fail and (if mpath IO isn't configured to queue when no paths are available) it will result in actual IO errors to the upper layers. This fix doesn't help configurations that have additional devices stacked ontop of the mpath device (e.g. LVM created linear DM devices ontop). A proper fix that restacks all the queue_limits from the bottom of the device stack up will need to be explored if SCSI will continue to use this model of optimistically allowing op codes and then disabling them after they fail for the first time. Before this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: failing WRITE SAME IO with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. device-mapper: multipath: Failing path 8:112. end_request: I/O error, dev dm-6, sector 4616 dm-6: WRITE SAME failed. Manually zeroing. end_request: I/O error, dev dm-6, sector 4616 end_request: I/O error, dev dm-6, sector 5640 end_request: I/O error, dev dm-6, sector 6664 end_request: I/O error, dev dm-6, sector 7688 end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. end_request: I/O error, dev dm-6, sector 524296 Aborting journal on device dm-6-8. end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 33553920 After this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: WRITE SAME I/O failed with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 0 It should be noted that WRITE SAME support wasn't enabled in DM multipath until v3.10. Signed-off-by: Mike Snitzer Cc: Martin K. Petersen Cc: Hannes Reinecke Cc: stable@vger.kernel.org # 3.10+ --- include/linux/device-mapper.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 653073de09e3..ed419c62dde1 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -406,13 +406,14 @@ int dm_noflush_suspending(struct dm_target *ti); union map_info *dm_get_mapinfo(struct bio *bio); union map_info *dm_get_rq_mapinfo(struct request *rq); +struct queue_limits *dm_get_queue_limits(struct mapped_device *md); + /* * Geometry functions. */ int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo); int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); - /*----------------------------------------------------------------- * Functions for manipulating device-mapper tables. *---------------------------------------------------------------*/ -- cgit v1.2.3 From c26d436cbf7a9549ec1073480a2e3f0d3f64e02d Mon Sep 17 00:00:00 2001 From: Andre Naujoks Date: Fri, 13 Sep 2013 19:37:12 +0200 Subject: lib: introduce upper case hex ascii helpers To be able to use the hex ascii functions in case sensitive environments the array hex_asc_upper[] and the needed functions for hex_byte_pack_upper() are introduced. Signed-off-by: Andre Naujoks Signed-off-by: David S. Miller --- include/linux/kernel.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 482ad2d84a32..672ddc4de4af 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -439,6 +439,17 @@ static inline char *hex_byte_pack(char *buf, u8 byte) return buf; } +extern const char hex_asc_upper[]; +#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] +#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack_upper(char *buf, u8 byte) +{ + *buf++ = hex_asc_upper_hi(byte); + *buf++ = hex_asc_upper_lo(byte); + return buf; +} + static inline char * __deprecated pack_hex_byte(char *buf, u8 byte) { return hex_byte_pack(buf, byte); -- cgit v1.2.3 From 75afb352991ff1cd3cf5955bfe611de6d83a0c87 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Sat, 21 Sep 2013 13:57:47 -0600 Subject: block: Add nr_bios to block_rq_remap tracepoint Adding the number of bios in a remapped request to 'block_rq_remap' tracepoint. Request remapper clones bios in a request to track the completion status of each bio. So the number of bios can be useful information for investigation. Related discussions: http://www.redhat.com/archives/dm-devel/2013-August/msg00084.html http://www.redhat.com/archives/dm-devel/2013-September/msg00024.html Signed-off-by: Jun'ichi Nomura Acked-by: Mike Snitzer Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2fdb4a451b49..0e6f765aa1f5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -862,6 +862,17 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) return blk_queue_get_max_sectors(q, rq->cmd_flags); } +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + /* * Request issue related functions. */ -- cgit v1.2.3 From 47d06e532e95b71c0db3839ebdef3fe8812fca2c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 10 Sep 2013 10:52:35 -0400 Subject: random: run random_int_secret_init() run after all late_initcalls The some platforms (e.g., ARM) initializes their clocks as late_initcalls for some unknown reason. So make sure random_int_secret_init() is run after all of the late_initcalls are run. Cc: stable@vger.kernel.org Signed-off-by: "Theodore Ts'o" --- include/linux/random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 3b9377d6b7a5..6312dd9ba449 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -17,6 +17,7 @@ extern void add_interrupt_randomness(int irq, int irq_flags); extern void get_random_bytes(void *buf, int nbytes); extern void get_random_bytes_arch(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); +extern int random_int_secret_init(void); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From 82aeef0bf03684b377678c00c05e613f30dca39c Mon Sep 17 00:00:00 2001 From: "Li, Zhen-Hua" Date: Fri, 13 Sep 2013 14:27:32 +0800 Subject: x86/iommu: correct ICS register offset According to Intel Vt-D specs, the offset of Invalidation complete status register should be 0x9C, not 0x98. See Intel's VT-d spec, Revision 1.3, Chapter 10.4, Page 98; Signed-off-by: Li, Zhen-Hua Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 78e2ada50cd5..d380c5e68008 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -55,7 +55,7 @@ #define DMAR_IQT_REG 0x88 /* Invalidation queue tail register */ #define DMAR_IQ_SHIFT 4 /* Invalidation queue head/tail shift */ #define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */ -#define DMAR_ICS_REG 0x98 /* Invalidation complete status register */ +#define DMAR_ICS_REG 0x9c /* Invalidation complete status register */ #define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */ #define OFFSET_STRIDE (9) -- cgit v1.2.3 From 9809b18fcf6b8d8ec4d3643677345907e6b50eca Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 24 Sep 2013 15:27:30 -0700 Subject: watchdog: update watchdog_thresh properly watchdog_tresh controls how often nmi perf event counter checks per-cpu hrtimer_interrupts counter and blows up if the counter hasn't changed since the last check. The counter is updated by per-cpu watchdog_hrtimer hrtimer which is scheduled with 2/5 watchdog_thresh period which guarantees that hrtimer is scheduled 2 times per the main period. Both hrtimer and perf event are started together when the watchdog is enabled. So far so good. But... But what happens when watchdog_thresh is updated from sysctl handler? proc_dowatchdog will set a new sampling period and hrtimer callback (watchdog_timer_fn) will use the new value in the next round. The problem, however, is that nobody tells the perf event that the sampling period has changed so it is ticking with the period configured when it has been set up. This might result in an ear ripping dissonance between perf and hrtimer parts if the watchdog_thresh is increased. And even worse it might lead to KABOOM if the watchdog is configured to panic on such a spurious lockup. This patch fixes the issue by updating both nmi perf even counter and hrtimers if the threshold value has changed. The nmi one is disabled and then reinitialized from scratch. This has an unpleasant side effect that the allocation of the new event might fail theoretically so the hard lockup detector would be disabled for such cpus. On the other hand such a memory allocation failure is very unlikely because the original event is deallocated right before. It would be much nicer if we just changed perf event period but there doesn't seem to be any API to do that right now. It is also unfortunate that perf_event_alloc uses GFP_KERNEL allocation unconditionally so we cannot use on_each_cpu() and do the same thing from the per-cpu context. The update from the current CPU should be safe because perf_event_disable removes the event atomically before it clears the per-cpu watchdog_ev so it cannot change anything under running handler feet. The hrtimer is simply restarted (thanks to Don Zickus who has pointed this out) if it is queued because we cannot rely it will fire&adopt to the new sampling period before a new nmi event triggers (when the treshold is decreased). [akpm@linux-foundation.org: the UP version of __smp_call_function_single ended up in the wrong place] Signed-off-by: Michal Hocko Acked-by: Don Zickus Cc: Frederic Weisbecker Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Fabio Estevam Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index cfb7ca094b38..731f5237d5f4 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } +static inline void __smp_call_function_single(int cpuid, + struct call_single_data *data, int wait) +{ + on_each_cpu(data->func, data->info, wait); +} + #endif /* !SMP */ /* -- cgit v1.2.3 From 694fbc0fe78518d06efa63910bf4ecee660e7852 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:37 -0700 Subject: revert "memcg: enhance memcg iterator to support predicates" Revert commit de57780dc659 ("memcg: enhance memcg iterator to support predicates") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 49 ++++++---------------------------------------- 1 file changed, 6 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 60e95872da29..ef2b9bd7fafa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -enum mem_cgroup_filter_t { - VISIT, /* visit current node */ - SKIP, /* skip the current node and continue traversal */ - SKIP_TREE, /* skip the whole subtree and continue traversal */ -}; - -/* - * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to - * iterate through the hierarchy tree. Each tree element is checked by the - * predicate before it is returned by the iterator. If a filter returns - * SKIP or SKIP_TREE then the iterator code continues traversal (with the - * next node down the hierarchy or the next node that doesn't belong under the - * memcg's subtree). - */ -typedef enum mem_cgroup_filter_t -(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); - #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond); - -static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim) -{ - return mem_cgroup_iter_cond(root, prev, reclaim, NULL); -} - +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -260,8 +234,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); @@ -376,15 +349,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } -static inline struct mem_cgroup * -mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) -{ - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; -} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -471,11 +435,10 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root) { - return VISIT; + return false; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From b1aff7fcf86c88472b0a70f15d89d7a4adba07bb Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:38 -0700 Subject: revert "vmscan, memcg: do softlimit reclaim also for targeted reclaim" Revert commit a5b7c87f9207 ("vmscan, memcg: do softlimit reclaim also for targeted reclaim") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ef2b9bd7fafa..6054c9f3a5e8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -234,8 +234,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root); +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -435,8 +434,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) { return false; } -- cgit v1.2.3 From 0608f43da64a1f1c42507304b5f25bc8b1227aa4 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:41 -0700 Subject: revert "memcg, vmscan: integrate soft reclaim tighter with zone shrinking code" Revert commit 3b38722efd9f ("memcg, vmscan: integrate soft reclaim tighter with zone shrinking code") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6054c9f3a5e8..ecc82b37c4cc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -234,7 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -434,9 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { - return false; + return 0; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From b0b8c960ffcc5bfc82d1a09ad931673e3a36c15a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 4 Sep 2013 10:52:57 -0500 Subject: of: clean-up ifdefs in of_irq.h Much of of_irq.h is needlessly ifdef'ed. Clean this up and minimize the amount ifdef'ed code. This fixes some build warnings when CONFIG_OF is not enabled (seen on i386 and x86_64): include/linux/of_irq.h:82:7: warning: 'struct device_node' declared inside parameter list [enabled by default] include/linux/of_irq.h:82:7: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] include/linux/of_irq.h:87:47: warning: 'struct device_node' declared inside parameter list [enabled by default] Compile tested on i386, sparc and arm. Reported-by: Randy Dunlap Cc: Grant Likely Signed-off-by: Rob Herring --- include/linux/of_irq.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 535cecf1e02f..fcd63baee5f2 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -1,8 +1,6 @@ #ifndef __OF_IRQ_H #define __OF_IRQ_H -#if defined(CONFIG_OF) -struct of_irq; #include #include #include @@ -10,14 +8,6 @@ struct of_irq; #include #include -/* - * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC - * implements it differently. However, the prototype is the same for all, - * so declare it here regardless of the CONFIG_OF_IRQ setting. - */ -extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); - -#if defined(CONFIG_OF_IRQ) /** * of_irq - container for device_node/irq_specifier pair for an irq controller * @controller: pointer to interrupt controller device tree node @@ -71,11 +61,17 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern int of_irq_count(struct device_node *dev); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); -extern struct device_node *of_irq_find_parent(struct device_node *child); extern void of_irq_init(const struct of_device_id *matches); -#endif /* CONFIG_OF_IRQ */ +#if defined(CONFIG_OF) +/* + * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC + * implements it differently. However, the prototype is the same for all, + * so declare it here regardless of the CONFIG_OF_IRQ setting. + */ +extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); +extern struct device_node *of_irq_find_parent(struct device_node *child); #else /* !CONFIG_OF */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, -- cgit v1.2.3 From 19872d20c890073c5207d9e02bb8f14d451a11eb Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Mon, 9 Sep 2013 18:33:54 +0200 Subject: HID: uhid: allocate static minor udev has this nice feature of creating "dead" /dev/ device-nodes if it finds a devnode: modalias. Once the node is accessed, the kernel automatically loads the module that provides the node. However, this requires udev to know the major:minor code to use for the node. This feature was introduced by: commit 578454ff7eab61d13a26b568f99a89a2c9edc881 Author: Kay Sievers Date: Thu May 20 18:07:20 2010 +0200 driver core: add devname module aliases to allow module on-demand auto-loading However, uhid uses dynamic minor numbers so this doesn't actually work. We need to load uhid to know which minor it's going to use. Hence, allocate a static minor (just like uinput does) and we're good to go. Reported-by: Tom Gundersen Signed-off-by: David Herrmann Signed-off-by: Jiri Kosina --- include/linux/miscdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 09c2300ddb37..cb358355ef43 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -45,6 +45,7 @@ #define MAPPER_CTRL_MINOR 236 #define LOOP_CTRL_MINOR 237 #define VHOST_NET_MINOR 238 +#define UHID_MINOR 239 #define MISC_DYNAMIC_MINOR 255 struct device; -- cgit v1.2.3 From 5bc2afc2b53fc73f154e6344cd898585628e6d27 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 23 Sep 2013 18:01:28 -0400 Subject: NFSv4: Honour the 'opened' parameter in the atomic_open() filesystem method Determine if we've created a new file by examining the directory change attribute and/or the O_EXCL flag. This fixes a regression when doing a non-exclusive create of a new file. If the FILE_CREATED flag is not set, the atomic_open() command will perform full file access permissions checks instead of just checking for MAY_OPEN. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 01fd84b566f7..49f52c8f4422 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1455,7 +1455,8 @@ struct nfs_rpc_ops { struct inode * (*open_context) (struct inode *dir, struct nfs_open_context *ctx, int open_flags, - struct iattr *iattr); + struct iattr *iattr, + int *); int (*have_delegation)(struct inode *, fmode_t); int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); -- cgit v1.2.3 From 2bedea8f26c92e2610f2f67889144990749461e0 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Wed, 25 Sep 2013 12:11:02 +0200 Subject: bcma: make bcma_core_pci_{up,down}() callable from atomic context This patch removes the bcma_core_pci_power_save() call from the bcma_core_pci_{up,down}() functions as it tries to schedule thus requiring to call them from non-atomic context. The function bcma_core_pci_power_save() is now exported so the calling module can explicitly use it in non-atomic context. This fixes the 'scheduling while atomic' issue reported by Tod Jackson and Joe Perches. [ 13.210710] BUG: scheduling while atomic: dhcpcd/1800/0x00000202 [ 13.210718] Modules linked in: brcmsmac nouveau coretemp kvm_intel kvm cordic brcmutil bcma dell_wmi atl1c ttm mxm_wmi wmi [ 13.210756] CPU: 2 PID: 1800 Comm: dhcpcd Not tainted 3.11.0-wl #1 [ 13.210762] Hardware name: Alienware M11x R2/M11x R2, BIOS A04 11/23/2010 [ 13.210767] ffff880177c92c40 ffff880170fd1948 ffffffff8169af5b 0000000000000007 [ 13.210777] ffff880170fd1ab0 ffff880170fd1958 ffffffff81697ee2 ffff880170fd19d8 [ 13.210785] ffffffff816a19f5 00000000000f4240 000000000000d080 ffff880170fd1fd8 [ 13.210794] Call Trace: [ 13.210813] [] dump_stack+0x4f/0x84 [ 13.210826] [] __schedule_bug+0x43/0x51 [ 13.210837] [] __schedule+0x6e5/0x810 [ 13.210845] [] schedule+0x24/0x70 [ 13.210855] [] schedule_hrtimeout_range_clock+0x10c/0x150 [ 13.210867] [] ? update_rmtp+0x60/0x60 [ 13.210877] [] ? hrtimer_start_range_ns+0xf/0x20 [ 13.210887] [] schedule_hrtimeout_range+0xe/0x10 [ 13.210897] [] usleep_range+0x3b/0x40 [ 13.210910] [] bcma_pcie_mdio_set_phy.isra.3+0x4f/0x80 [bcma] [ 13.210921] [] bcma_pcie_mdio_write.isra.4+0xbf/0xd0 [bcma] [ 13.210932] [] bcma_pcie_mdio_writeread.isra.6.constprop.13+0x18/0x30 [bcma] [ 13.210942] [] bcma_core_pci_power_save+0x3e/0x80 [bcma] [ 13.210953] [] bcma_core_pci_up+0x2d/0x60 [bcma] [ 13.210975] [] brcms_c_up+0xfc/0x430 [brcmsmac] [ 13.210989] [] brcms_up+0x1d/0x20 [brcmsmac] [ 13.211003] [] brcms_ops_start+0x298/0x340 [brcmsmac] [ 13.211020] [] ? cfg80211_netdev_notifier_call+0xd2/0x5f0 [ 13.211030] [] ? packet_notifier+0xad/0x1d0 [ 13.211064] [] ieee80211_do_open+0x325/0xf80 [ 13.211076] [] ? __raw_notifier_call_chain+0x9/0x10 [ 13.211086] [] ieee80211_open+0x71/0x80 [ 13.211101] [] __dev_open+0x87/0xe0 [ 13.211109] [] __dev_change_flags+0x9c/0x180 [ 13.211117] [] dev_change_flags+0x23/0x70 [ 13.211127] [] devinet_ioctl+0x5b8/0x6a0 [ 13.211136] [] inet_ioctl+0x75/0x90 [ 13.211147] [] sock_do_ioctl+0x2b/0x70 [ 13.211155] [] sock_ioctl+0x71/0x2a0 [ 13.211169] [] do_vfs_ioctl+0x87/0x520 [ 13.211180] [] ? ____fput+0x9/0x10 [ 13.211198] [] ? task_work_run+0x9c/0xd0 [ 13.211202] [] SyS_ioctl+0x91/0xb0 [ 13.211208] [] system_call_fastpath+0x16/0x1b [ 13.211217] NOHZ: local_softirq_pending 202 The issue was introduced in v3.11 kernel by following commit: commit aa51e598d04c6acf5477934cd6383f5a17ce9029 Author: Hauke Mehrtens Date: Sat Aug 24 00:32:31 2013 +0200 brcmsmac: use bcma PCIe up and down functions replace the calls to bcma_core_pci_extend_L1timer() by calls to the newly introduced bcma_core_pci_ip() and bcma_core_pci_down() Signed-off-by: Hauke Mehrtens Cc: Arend van Spriel Signed-off-by: John W. Linville This fix has been discussed with Hauke Mehrtens [1] selection option 3) and is intended for v3.12. Ref: [1] http://mid.gmane.org/5239B12D.3040206@hauke-m.de Cc: # 3.11.x Cc: Tod Jackson Cc: Joe Perches Cc: Rafal Milecki Cc: Hauke Mehrtens Reviewed-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index d66033f418c9..0333e605ea0d 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -242,6 +242,7 @@ extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable); extern void bcma_core_pci_up(struct bcma_bus *bus); extern void bcma_core_pci_down(struct bcma_bus *bus); +extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); extern int bcma_core_pci_plat_dev_init(struct pci_dev *dev); -- cgit v1.2.3 From 3a4916050ba2e0f1d114ef540abdf02b2b173e61 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 6 Sep 2013 11:49:56 -0700 Subject: Drivers: hv: util: Correctly support ws2008R2 and earlier The current code does not correctly negotiate the version numbers for the util driver when hosted on earlier hosts. The version numbers presented by this driver were not compatible with the version numbers supported by Windows Server 2008. Fix this problem. I would like to thank Olaf Hering (ohering@suse.com) for identifying the problem. Reported-by: Olaf Hering Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a3b8b2e2d244..d98503bde7e9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -30,10 +30,13 @@ /* * Framework version for util services. */ +#define UTIL_FW_MINOR 0 + +#define UTIL_WS2K8_FW_MAJOR 1 +#define UTIL_WS2K8_FW_VERSION (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR) #define UTIL_FW_MAJOR 3 -#define UTIL_FW_MINOR 0 -#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) +#define UTIL_FW_VERSION (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) /* -- cgit v1.2.3 From 083986e8248d978b6c961d3da6beb0c921c68220 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 28 Sep 2013 11:23:59 +0200 Subject: mutex: replace CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX with simple ifdef Linus suggested to replace #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX #define arch_mutex_cpu_relax() cpu_relax() #endif with just a simple #ifndef arch_mutex_cpu_relax # define arch_mutex_cpu_relax() cpu_relax() #endif to get rid of CONFIG_HAVE_CPU_RELAX_SIMPLE. So architectures can simply define arch_mutex_cpu_relax if they want an architecture specific function instead of having to add a select statement in their Kconfig in addition. Suggested-by: Linus Torvalds Signed-off-by: Heiko Carstens --- include/linux/mutex.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index ccd4260834c5..bab49da8a0f0 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -15,8 +15,8 @@ #include #include #include - #include +#include /* * Simple, straightforward mutexes with strict semantics: @@ -175,8 +175,8 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); -#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX -#define arch_mutex_cpu_relax() cpu_relax() +#ifndef arch_mutex_cpu_relax +# define arch_mutex_cpu_relax() cpu_relax() #endif #endif -- cgit v1.2.3 From 60e453a940ac678565b6641d65f8c18541bb9f28 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 23 Sep 2013 20:59:35 +0800 Subject: USBNET: fix handling padding packet Commit 638c5115a7949(USBNET: support DMA SG) introduces DMA SG if the usb host controller is capable of building packet from discontinuous buffers, but missed handling padding packet when building DMA SG. This patch attachs the pre-allocated padding packet at the end of the sg list, so padding packet can be sent to device if drivers require that. Reported-by: David Laight Acked-by: Oliver Neukum Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 9cb2fe8ca944..e303eef94dd5 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -42,6 +42,7 @@ struct usbnet { struct usb_host_endpoint *status; unsigned maxpacket; struct timer_list delay; + const char *padding_pkt; /* protocol/interface state */ struct net_device *net; -- cgit v1.2.3 From 117aad1e9e4d97448d1df3f84b08bd65811e6d6a Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Mon, 30 Sep 2013 13:45:16 -0700 Subject: mm: avoid reinserting isolated balloon pages into LRU lists Isolated balloon pages can wrongly end up in LRU lists when migrate_pages() finishes its round without draining all the isolated page list. The same issue can happen when reclaim_clean_pages_from_list() tries to reclaim pages from an isolated page list, before migration, in the CMA path. Such balloon page leak opens a race window against LRU lists shrinkers that leads us to the following kernel panic: BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 IP: [] shrink_page_list+0x24e/0x897 PGD 3cda2067 PUD 3d713067 PMD 0 Oops: 0000 [#1] SMP CPU: 0 PID: 340 Comm: kswapd0 Not tainted 3.12.0-rc1-22626-g4367597 #87 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: shrink_page_list+0x24e/0x897 RSP: 0000:ffff88003da499b8 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff88003e82bd60 RCX: 00000000000657d5 RDX: 0000000000000000 RSI: 000000000000031f RDI: ffff88003e82bd40 RBP: ffff88003da49ab0 R08: 0000000000000001 R09: 0000000081121a45 R10: ffffffff81121a45 R11: ffff88003c4a9a28 R12: ffff88003e82bd40 R13: ffff88003da0e800 R14: 0000000000000001 R15: ffff88003da49d58 FS: 0000000000000000(0000) GS:ffff88003fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000067d9000 CR3: 000000003ace5000 CR4: 00000000000407b0 Call Trace: shrink_inactive_list+0x240/0x3de shrink_lruvec+0x3e0/0x566 __shrink_zone+0x94/0x178 shrink_zone+0x3a/0x82 balance_pgdat+0x32a/0x4c2 kswapd+0x2f0/0x372 kthread+0xa2/0xaa ret_from_fork+0x7c/0xb0 Code: 80 7d 8f 01 48 83 95 68 ff ff ff 00 4c 89 e7 e8 5a 7b 00 00 48 85 c0 49 89 c5 75 08 80 7d 8f 00 74 3e eb 31 48 8b 80 18 01 00 00 <48> 8b 74 0d 48 8b 78 30 be 02 00 00 00 ff d2 eb RIP [] shrink_page_list+0x24e/0x897 RSP CR2: 0000000000000028 ---[ end trace 703d2451af6ffbfd ]--- Kernel panic - not syncing: Fatal exception This patch fixes the issue, by assuring the proper tests are made at putback_movable_pages() & reclaim_clean_pages_from_list() to avoid isolated balloon pages being wrongly reinserted in LRU lists. [akpm@linux-foundation.org: clarify awkward comment text] Signed-off-by: Rafael Aquini Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Cc: Mel Gorman Cc: Rik van Riel Cc: Hugh Dickins Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/balloon_compaction.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index f7f1d7169b11..089743ade734 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -158,6 +158,26 @@ static inline bool balloon_page_movable(struct page *page) return false; } +/* + * isolated_balloon_page - identify an isolated balloon page on private + * compaction/migration page lists. + * + * After a compaction thread isolates a balloon page for migration, it raises + * the page refcount to prevent concurrent compaction threads from re-isolating + * the same page. For that reason putback_movable_pages(), or other routines + * that need to identify isolated balloon pages on private pagelists, cannot + * rely on balloon_page_movable() to accomplish the task. + */ +static inline bool isolated_balloon_page(struct page *page) +{ + /* Already isolated balloon pages, by default, have a raised refcount */ + if (page_flags_cleared(page) && !page_mapped(page) && + page_count(page) >= 2) + return __is_movable_balloon_page(page); + + return false; +} + /* * balloon_page_insert - insert a page into the balloon's page list and make * the page->mapping assignment accordingly. @@ -243,6 +263,11 @@ static inline bool balloon_page_movable(struct page *page) return false; } +static inline bool isolated_balloon_page(struct page *page) +{ + return false; +} + static inline bool balloon_page_isolate(struct page *page) { return false; -- cgit v1.2.3 From 45906723578f768d029ba7774cd97b435f2c5125 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 30 Sep 2013 14:16:41 +0200 Subject: skbuff: size of hole is wrong in a comment Since commit c93bdd0e03e8 ("netvm: allow skb allocation to use PFMEMALLOC reserves"), hole size is one bit less than what is written in the comment. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2ddb48d9312c..c2d89335f637 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -498,7 +498,7 @@ struct sk_buff { * headers if needed */ __u8 encapsulation:1; - /* 7/9 bit hole (depending on ndisc_nodetype presence) */ + /* 6/8 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL -- cgit v1.2.3 From 5bc3db5c9ca8407f52918b6504d3b27230defedc Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 30 Sep 2013 21:30:22 -0700 Subject: tc: export tc_defact.h to userspace Jamal sent patch to add tc user simple actions to iproute2 but required header was not being exported. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/tc_act/tc_defact.h | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 include/linux/tc_act/tc_defact.h (limited to 'include/linux') diff --git a/include/linux/tc_act/tc_defact.h b/include/linux/tc_act/tc_defact.h deleted file mode 100644 index 6f65d07c7ce2..000000000000 --- a/include/linux/tc_act/tc_defact.h +++ /dev/null @@ -1,19 +0,0 @@ -#ifndef __LINUX_TC_DEF_H -#define __LINUX_TC_DEF_H - -#include - -struct tc_defact { - tc_gen; -}; - -enum { - TCA_DEF_UNSPEC, - TCA_DEF_TM, - TCA_DEF_PARMS, - TCA_DEF_DATA, - __TCA_DEF_MAX -}; -#define TCA_DEF_MAX (__TCA_DEF_MAX - 1) - -#endif -- cgit v1.2.3 From 9886167d20c0720dcfb01e62cdff4d906b226f43 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 3 Oct 2013 16:02:23 +0200 Subject: perf: Fix perf_pmu_migrate_context While auditing the list_entry usage due to a trinity bug I found that perf_pmu_migrate_context violates the rules for perf_event::event_entry. The problem is that perf_event::event_entry is a RCU list element, and hence we must wait for a full RCU grace period before re-using the element after deletion. Therefore the usage in perf_pmu_migrate_context() which re-uses the entry immediately is broken. For now introduce another list_head into perf_event for this specific usage. This doesn't actually fix the trinity report because that never goes through this code. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-mkj72lxagw1z8fvjm648iznw@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 866e85c5eb94..c8ba627c1d60 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -294,9 +294,31 @@ struct ring_buffer; */ struct perf_event { #ifdef CONFIG_PERF_EVENTS - struct list_head group_entry; + /* + * entry onto perf_event_context::event_list; + * modifications require ctx->lock + * RCU safe iterations. + */ struct list_head event_entry; + + /* + * XXX: group_entry and sibling_list should be mutually exclusive; + * either you're a sibling on a group, or you're the group leader. + * Rework the code to always use the same list element. + * + * Locked for modification by both ctx->mutex and ctx->lock; holding + * either sufficies for read. + */ + struct list_head group_entry; struct list_head sibling_list; + + /* + * We need storage to track the entries in perf_pmu_migrate_context; we + * cannot use the event_entry because of RCU and we want to keep the + * group in tact which avoids us using the other two entries. + */ + struct list_head migrate_entry; + struct hlist_node hlist_entry; int nr_siblings; int group_flags; -- cgit v1.2.3 From 3573540cafa4296dd60f8be02f2aecaa31047525 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 2 Oct 2013 09:14:06 +0300 Subject: netif_set_xps_queue: make cpu mask const virtio wants to pass in cpumask_of(cpu), make parameter const to avoid build warnings. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3de49aca4519..25f5d2d11e7c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2264,11 +2264,12 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) } #ifdef CONFIG_XPS -extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, +extern int netif_set_xps_queue(struct net_device *dev, + const struct cpumask *mask, u16 index); #else static inline int netif_set_xps_queue(struct net_device *dev, - struct cpumask *mask, + const struct cpumask *mask, u16 index) { return 0; -- cgit v1.2.3 From d45ed4a4e33ae103053c0a53d280014e7101bb5c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 4 Oct 2013 00:14:06 -0700 Subject: net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [] dump_stack+0x55/0x76 [ 56.936067] [] print_usage_bug+0x1f7/0x208 [ 56.942445] [] ? save_stack_trace+0x2f/0x50 [ 56.948932] [] ? check_usage_backwards+0x150/0x150 [ 56.955470] [] mark_lock+0x282/0x2c0 [ 56.961945] [] __lock_acquire+0x45d/0x1d50 [ 56.968474] [] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [] ? cpumask_next_and+0x55/0x90 [ 56.981942] [] lock_acquire+0x92/0x1d0 [ 56.988745] [] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [] _raw_spin_lock+0x41/0x50 [ 57.002493] [] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [] ? free_object_rcu+0x93/0xa0 [ 57.051720] [] set_memory_rw+0x2f/0x40 [ 57.058727] [] bpf_jit_free+0x2c/0x40 [ 57.065577] [] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [] __do_softirq+0xf7/0x3f0 [ 57.085373] [] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/filter.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index a6ac84871d6d..ff4e40cd45b1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -6,6 +6,7 @@ #include #include +#include #include #ifdef CONFIG_COMPAT @@ -25,15 +26,19 @@ struct sk_filter { atomic_t refcnt; unsigned int len; /* Number of filter blocks */ + struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct sock_filter *filter); - struct rcu_head rcu; - struct sock_filter insns[0]; + union { + struct sock_filter insns[0]; + struct work_struct work; + }; }; -static inline unsigned int sk_filter_len(const struct sk_filter *fp) +static inline unsigned int sk_filter_size(unsigned int proglen) { - return fp->len * sizeof(struct sock_filter) + sizeof(*fp); + return max(sizeof(struct sk_filter), + offsetof(struct sk_filter, insns[proglen])); } extern int sk_filter(struct sock *sk, struct sk_buff *skb); @@ -67,11 +72,13 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, } #define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else +#include static inline void bpf_jit_compile(struct sk_filter *fp) { } static inline void bpf_jit_free(struct sk_filter *fp) { + kfree(fp); } #define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns) #endif -- cgit v1.2.3 From c1868b822515313c72445e70b7d9e47d8815bc52 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 11 Sep 2013 16:35:25 +0300 Subject: mlx5: Remove checksum on command interface commands Checksum calculations consume CPU resources and can be significant to the rate of resource creation/destruction. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- include/linux/mlx5/device.h | 2 +- include/linux/mlx5/driver.h | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 68029b30c3dc..770e3b448b3b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -181,7 +181,7 @@ enum { MLX5_DEV_CAP_FLAG_TLP_HINTS = 1LL << 39, MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, MLX5_DEV_CAP_FLAG_DCT = 1LL << 41, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 1LL << 46, + MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8888381fc150..2cfc4309d45f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -747,8 +747,7 @@ static inline u32 mlx5_idx_to_mkey(u32 mkey_idx) enum { MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_CMDIF_CSUM = (u64)1 << 1, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 2, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, }; enum { @@ -758,7 +757,6 @@ enum { struct mlx5_profile { u64 mask; u32 log_max_qp; - int cmdif_csum; struct { int size; int limit; -- cgit v1.2.3 From 2f6daec14d02deb84e7896a93196d78fbe9956a2 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 11 Sep 2013 16:35:29 +0300 Subject: mlx5: Fix layout of struct mlx5_init_seg The layout of struct health_buffer was not according to firmware specification. Fix it to comply. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- include/linux/mlx5/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 770e3b448b3b..5eb4e31af22b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -417,7 +417,7 @@ struct mlx5_init_seg { struct health_buffer health; __be32 rsvd2[884]; __be32 health_counter; - __be32 rsvd3[1023]; + __be32 rsvd3[1019]; __be64 ieee1588_clk; __be32 ieee1588_clk_type; __be32 clr_intx; -- cgit v1.2.3 From ada9f5d007971a71d619e2abf66ebd3a9a399413 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 11 Sep 2013 16:35:34 +0300 Subject: IB/mlx5: Fix eq names to display nicely in /proc/interrupts It's helpful for a driver to put the pci slot name in its interrupt names, so /proc/interrupts will show the pci slot of the device. Signed-off-by: Sagi Grimberg Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2cfc4309d45f..6b8c496572c8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -82,7 +82,7 @@ enum { }; enum { - MLX5_MAX_EQ_NAME = 20 + MLX5_MAX_EQ_NAME = 32 }; enum { -- cgit v1.2.3 From 61875f30daf60305712e25b209ef41ced2635bad Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 21 Sep 2013 13:58:22 -0400 Subject: random: allow architectures to optionally define random_get_entropy() Allow architectures which have a disabled get_cycles() function to provide a random_get_entropy() function which provides a fine-grained, rapidly changing counter that can be used by the /dev/random driver. For example, an architecture might have a rapidly changing register used to control random TLB cache eviction, or DRAM refresh that doesn't meet the requirements of get_cycles(), but which is good enough for the needs of the random driver. Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- include/linux/timex.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b3726e61368e..da4c32dbb2aa 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -64,6 +64,20 @@ #include +#ifndef random_get_entropy +/* + * The random_get_entropy() function is used by the /dev/random driver + * in order to extract entropy via the relative unpredictability of + * when an interrupt takes places versus a high speed, fine-grained + * timing source or cycle counter. Since it will be occurred on every + * single interrupt, it must have a very low cost/overhead. + * + * By default we use get_cycles() for this purpose, but individual + * architectures may override this in their asm/timex.h header file. + */ +#define random_get_entropy() get_cycles() +#endif + /* * SHIFT_PLL is used as a dampening factor to define how much we * adjust the frequency correction for a given offset in PLL mode. -- cgit v1.2.3 From ebff5fa9d545574324095d9c6a3cb80c9157abc5 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 11 Oct 2013 15:12:04 +1000 Subject: Revert "i915: Update VGA arbiter support for newer devices" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 81b5c7bc8de3e6f63419139c2fc91bf81dea8a7d. Adding drm/i915 into the vga arbiter chain means that X (in a piece of well-meant paranoia) will do a get/put on the vga decoding around _every_ accel call down into the ddx. Which results in some nice performance disasters [1]. This really breaks userspace, by disabling DRI for everyone, and stops OpenGL from working, this isn't limited to just the i915 but both the integrated and discrete GPUs on multi-gpu systems, in other words this causes untold worlds of pain, Ville tried to come up with a Great Hack to fiddle the required VGA I/O ops behind everyone's back using stop_machine, but that didn't really work out [2]. Given that we're fairly late in the -rc stage for such games let's just revert this all. One thing we might want to keep is to delay the disabling of the vga decoding until the fbdev emulation and the fbcon screen is set up. If we kill vga mem decoding beforehand fbcon can end up with a white square in the top-left corner it tried to save from the vga memory for a seamless transition. And we have bug reports on older platforms which seem to match these symptoms. But again that's something to play around with in -next. References: [1] http://lists.x.org/archives/xorg-devel/2013-September/037763.html References: [2] http://www.spinics.net/lists/intel-gfx/msg34062.html Cc: Alex Williamson Cc: Ville Syrjälä Cc: Chris Wilson Signed-off-by: Daniel Vetter Signed-off-by: Dave Airlie --- include/linux/vgaarb.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 80cf8173a65b..2c02f3a8d2ba 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -65,15 +65,8 @@ struct pci_dev; * out of the arbitration process (and can be safe to take * interrupts at any time. */ -#if defined(CONFIG_VGA_ARB) extern void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes); -#else -static inline void vga_set_legacy_decoding(struct pci_dev *pdev, - unsigned int decodes) -{ -} -#endif /** * vga_get - acquire & locks VGA resources -- cgit v1.2.3 From 3f0116c3238a96bc18ad4b4acefe4e7be32fa861 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 10 Oct 2013 10:16:30 +0200 Subject: compiler/gcc4: Add quirk for 'asm goto' miscompilation bug Fengguang Wu, Oleg Nesterov and Peter Zijlstra tracked down a kernel crash to a GCC bug: GCC miscompiles certain 'asm goto' constructs, as outlined here: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 Implement a workaround suggested by Jakub Jelinek. Reported-and-tested-by: Fengguang Wu Reported-by: Oleg Nesterov Reported-by: Peter Zijlstra Suggested-by: Jakub Jelinek Reviewed-by: Richard Henderson Cc: Linus Torvalds Cc: Andrew Morton Cc: Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc4.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 842de225055f..ded429966c1f 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -65,6 +65,21 @@ #define __visible __attribute__((externally_visible)) #endif +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * Fixed in GCC 4.8.2 and later versions. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#if GCC_VERSION <= 40801 +# define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) +#else +# define asm_volatile_goto(x...) do { asm goto(x); } while (0) +#endif #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP #if GCC_VERSION >= 40400 -- cgit v1.2.3 From 1931ee143b0ab72924944bc06e363d837ba05063 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 11 Oct 2013 09:27:28 +0200 Subject: Revert "drivers: of: add initialization code for dma reserved memory" This reverts commit 9d8eab7af79cb4ce2de5de39f82c455b1f796963. There is still no consensus on the bindings for the reserved memory and various drawbacks of the proposed solution has been shown, so the best now is to revert it completely and start again from scratch later. Signed-off-by: Marek Szyprowski Signed-off-by: Grant Likely --- include/linux/of_reserved_mem.h | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100644 include/linux/of_reserved_mem.h (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h deleted file mode 100644 index c84128255814..000000000000 --- a/include/linux/of_reserved_mem.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __OF_RESERVED_MEM_H -#define __OF_RESERVED_MEM_H - -#ifdef CONFIG_OF_RESERVED_MEM -void of_reserved_mem_device_init(struct device *dev); -void of_reserved_mem_device_release(struct device *dev); -void early_init_dt_scan_reserved_mem(void); -#else -static inline void of_reserved_mem_device_init(struct device *dev) { } -static inline void of_reserved_mem_device_release(struct device *dev) { } -static inline void early_init_dt_scan_reserved_mem(void) { } -#endif - -#endif /* __OF_RESERVED_MEM_H */ -- cgit v1.2.3 From 32c37fc30c52508711ea6a108cfd5855b8a07176 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Mon, 14 Oct 2013 15:24:55 +0200 Subject: usb-storage: add quirk for mandatory READ_CAPACITY_16 Some USB drive enclosures do not correctly report an overflow condition if they hold a drive with a capacity over 2TB and are confronted with a READ_CAPACITY_10. They answer with their capacity modulo 2TB. The generic layer cannot cope with that. It must be told to use READ_CAPACITY_16 from the beginning. Signed-off-by: Oliver Neukum Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_usual.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index bf99cd01be20..630356866030 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -66,7 +66,9 @@ US_FLAG(INITIAL_READ10, 0x00100000) \ /* Initial READ(10) (and others) must be retried */ \ US_FLAG(WRITE_CACHE, 0x00200000) \ - /* Write Cache status is not available */ + /* Write Cache status is not available */ \ + US_FLAG(NEEDS_CAP16, 0x00400000) + /* cannot handle READ_CAPACITY_10 */ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; -- cgit v1.2.3 From 4942642080ea82d99ab5b653abb9a12b7ba31f4a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 16 Oct 2013 13:46:59 -0700 Subject: mm: memcg: handle non-error OOM situations more gracefully Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full callstack on OOM") assumed that only a few places that can trigger a memcg OOM situation do not return VM_FAULT_OOM, like optional page cache readahead. But there are many more and it's impractical to annotate them all. First of all, we don't want to invoke the OOM killer when the failed allocation is gracefully handled, so defer the actual kill to the end of the fault handling as well. This simplifies the code quite a bit for added bonus. Second, since a failed allocation might not be the abrupt end of the fault, the memcg OOM handler needs to be re-entrant until the fault finishes for subsequent allocation attempts. If an allocation is attempted after the task already OOMed, allow it to bypass the limit so that it can quickly finish the fault and invoke the OOM killer. Reported-by: azurIt Signed-off-by: Johannes Weiner Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 50 ++++++++++------------------------------------ include/linux/sched.h | 7 +++---- 2 files changed, 14 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ecc82b37c4cc..b3e7a667e03c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -137,47 +137,24 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); -/** - * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task - * @new: true to enable, false to disable - * - * Toggle whether a failed memcg charge should invoke the OOM killer - * or just return -ENOMEM. Returns the previous toggle state. - * - * NOTE: Any path that enables the OOM killer before charging must - * call mem_cgroup_oom_synchronize() afterward to finalize the - * OOM handling and clean up. - */ -static inline bool mem_cgroup_toggle_oom(bool new) +static inline void mem_cgroup_oom_enable(void) { - bool old; - - old = current->memcg_oom.may_oom; - current->memcg_oom.may_oom = new; - - return old; + WARN_ON(current->memcg_oom.may_oom); + current->memcg_oom.may_oom = 1; } -static inline void mem_cgroup_enable_oom(void) +static inline void mem_cgroup_oom_disable(void) { - bool old = mem_cgroup_toggle_oom(true); - - WARN_ON(old == true); -} - -static inline void mem_cgroup_disable_oom(void) -{ - bool old = mem_cgroup_toggle_oom(false); - - WARN_ON(old == false); + WARN_ON(!current->memcg_oom.may_oom); + current->memcg_oom.may_oom = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { - return p->memcg_oom.in_memcg_oom; + return p->memcg_oom.memcg; } -bool mem_cgroup_oom_synchronize(void); +bool mem_cgroup_oom_synchronize(bool wait); #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; @@ -402,16 +379,11 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, { } -static inline bool mem_cgroup_toggle_oom(bool new) -{ - return false; -} - -static inline void mem_cgroup_enable_oom(void) +static inline void mem_cgroup_oom_enable(void) { } -static inline void mem_cgroup_disable_oom(void) +static inline void mem_cgroup_oom_disable(void) { } @@ -420,7 +392,7 @@ static inline bool task_in_memcg_oom(struct task_struct *p) return false; } -static inline bool mem_cgroup_oom_synchronize(void) +static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 6682da36b293..e27baeeda3f4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1394,11 +1394,10 @@ struct task_struct { } memcg_batch; unsigned int memcg_kmem_skip_account; struct memcg_oom_info { + struct mem_cgroup *memcg; + gfp_t gfp_mask; + int order; unsigned int may_oom:1; - unsigned int in_memcg_oom:1; - unsigned int oom_locked:1; - int wakeups; - struct mem_cgroup *wait_on_memcg; } memcg_oom; #endif #ifdef CONFIG_UPROBES -- cgit v1.2.3 From 94468783cd960aa14b22503dd59afd14efb785aa Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 16 Oct 2013 19:18:41 -0700 Subject: usb: usb_phy_gen: refine conditional declaration of usb_nop_xceiv_register Commit 3fa4d734 (usb: phy: rename nop_usb_xceiv => usb_phy_gen_xceiv) changed the conditional around the declaration of usb_nop_xceiv_register from #if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) to #if IS_ENABLED(CONFIG_NOP_USB_XCEIV) While that looks the same, it is semantically different. The first expression is true if CONFIG_NOP_USB_XCEIV is built as module and if the including code is built as module. The second expression is true if code depending on CONFIG_NOP_USB_XCEIV if built as module or into the kernel. As a result, the arm:allmodconfig build fails with arch/arm/mach-omap2/built-in.o: In function `omap3_evm_init': arch/arm/mach-omap2/board-omap3evm.c:703: undefined reference to `usb_nop_xceiv_register' Fix the problem by reverting to the old conditional. Cc: Josh Boyer Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/usb_phy_gen_xceiv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h index f9a7e7bc925b..11d85b9c1b08 100644 --- a/include/linux/usb/usb_phy_gen_xceiv.h +++ b/include/linux/usb/usb_phy_gen_xceiv.h @@ -12,7 +12,7 @@ struct usb_phy_gen_xceiv_platform_data { unsigned int needs_reset:1; }; -#if IS_ENABLED(CONFIG_NOP_USB_XCEIV) +#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) /* sometimes transceivers are accessed only through e.g. ULPI */ extern void usb_nop_xceiv_register(void); extern void usb_nop_xceiv_unregister(void); -- cgit v1.2.3 From 9e5f1721907fcfbd4b575bcafa0314188f7330a5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 14 Oct 2013 15:28:38 +0300 Subject: yam: integer underflow in yam_ioctl() We cap bitrate at YAM_MAXBITRATE in yam_ioctl(), but it could also be negative. I don't know the impact of using a negative bitrate but let's prevent it. Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- include/linux/yam.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/yam.h b/include/linux/yam.h index 7fe28228b274..512cdc2fb80f 100644 --- a/include/linux/yam.h +++ b/include/linux/yam.h @@ -77,6 +77,6 @@ struct yamdrv_ioctl_cfg { struct yamdrv_ioctl_mcs { int cmd; - int bitrate; + unsigned int bitrate; unsigned char bits[YAM_FPGA_SIZE]; }; -- cgit v1.2.3 From bd09d9a35111b6ffc0c7585d3853d0ec7f9f1eb4 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Wed, 30 Oct 2013 13:56:20 -0700 Subject: percpu: fix this_cpu_sub() subtrahend casting for unsigneds this_cpu_sub() is implemented as negation and addition. This patch casts the adjustment to the counter type before negation to sign extend the adjustment. This helps in cases where the counter type is wider than an unsigned adjustment. An alternative to this patch is to declare such operations unsupported, but it seemed useful to avoid surprises. This patch specifically helps the following example: unsigned int delta = 1 preempt_disable() this_cpu_write(long_counter, 0) this_cpu_sub(long_counter, delta) preempt_enable() Before this change long_counter on a 64 bit machine ends with value 0xffffffff, rather than 0xffffffffffffffff. This is because this_cpu_sub(pcp, delta) boils down to this_cpu_add(pcp, -delta), which is basically: long_counter = 0 + 0xffffffff Also apply the same cast to: __this_cpu_sub() __this_cpu_sub_return() this_cpu_sub_return() All percpu_test.ko passes, especially the following cases which previously failed: l -= ui_one; __this_cpu_sub(long_counter, ui_one); CHECK(l, long_counter, -1); l -= ui_one; this_cpu_sub(long_counter, ui_one); CHECK(l, long_counter, -1); CHECK(l, long_counter, 0xffffffffffffffff); ul -= ui_one; __this_cpu_sub(ulong_counter, ui_one); CHECK(ul, ulong_counter, -1); CHECK(ul, ulong_counter, 0xffffffffffffffff); ul = this_cpu_sub_return(ulong_counter, ui_one); CHECK(ul, ulong_counter, 2); ul = __this_cpu_sub_return(ulong_counter, ui_one); CHECK(ul, ulong_counter, 1); Signed-off-by: Greg Thelen Acked-by: Tejun Heo Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index cc88172c7d9a..c74088ab103b 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -332,7 +332,7 @@ do { \ #endif #ifndef this_cpu_sub -# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(val)) +# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(typeof(pcp))(val)) #endif #ifndef this_cpu_inc @@ -418,7 +418,7 @@ do { \ # define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) #endif -#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(typeof(pcp))(val)) #define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) #define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) @@ -586,7 +586,7 @@ do { \ #endif #ifndef __this_cpu_sub -# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(val)) +# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(typeof(pcp))(val)) #endif #ifndef __this_cpu_inc @@ -668,7 +668,7 @@ do { \ __pcpu_size_call_return2(__this_cpu_add_return_, pcp, val) #endif -#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(val)) +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) #define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) #define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) -- cgit v1.2.3 From 9bf76ca325d5e9208eb343f7bd4cc666f703ed30 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Sun, 3 Nov 2013 12:36:28 +0100 Subject: ipc, msg: forbid negative values for "msg{max,mnb,mni}" Negative message lengths make no sense -- so don't do negative queue lenghts or identifier counts. Prevent them from getting negative. Also change the underlying data types to be unsigned to avoid hairy surprises with sign extensions in cases where those variables get evaluated in unsigned expressions with bigger data types, e.g size_t. In case a user still wants to have "unlimited" sizes she could just use INT_MAX instead. Signed-off-by: Mathias Krause Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 19c19a5eee29..f6c82de12541 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -34,9 +34,9 @@ struct ipc_namespace { int sem_ctls[4]; int used_sems; - int msg_ctlmax; - int msg_ctlmnb; - int msg_ctlmni; + unsigned int msg_ctlmax; + unsigned int msg_ctlmnb; + unsigned int msg_ctlmni; atomic_t msg_bytes; atomic_t msg_hdrs; int auto_msgmni; -- cgit v1.2.3