diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-03 12:15:00 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-03 12:15:00 -0700 |
commit | 00bcf5cdd6c0e2e92ce3dd852ca68a3b779fa4ec (patch) | |
tree | 387b2ed2ac0e35776714515665f25ddb5fee1de3 /include | |
parent | de956b8f45b3338cfb66a725e22b4050109daf2a (diff) | |
parent | 08645077b7f9f7824dbaf1959b0e014a894c8acc (diff) |
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar:
"The main changes in this cycle were:
- rwsem micro-optimizations (Davidlohr Bueso)
- Improve the implementation and optimize the performance of
percpu-rwsems. (Peter Zijlstra.)
- Convert all lglock users to better facilities such as percpu-rwsems
or percpu-spinlocks and remove lglocks. (Peter Zijlstra)
- Remove the ticket (spin)lock implementation. (Peter Zijlstra)
- Korean translation of memory-barriers.txt and related fixes to the
English document. (SeongJae Park)
- misc fixes and cleanups"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
x86/cmpxchg, locking/atomics: Remove superfluous definitions
x86, locking/spinlocks: Remove ticket (spin)lock implementation
locking/lglock: Remove lglock implementation
stop_machine: Remove stop_cpus_lock and lg_double_lock/unlock()
fs/locks: Use percpu_down_read_preempt_disable()
locking/percpu-rwsem: Add down_read_preempt_disable()
fs/locks: Replace lg_local with a per-cpu spinlock
fs/locks: Replace lg_global with a percpu-rwsem
locking/percpu-rwsem: Add DEFINE_STATIC_PERCPU_RWSEMand percpu_rwsem_assert_held()
locking/pv-qspinlock: Use cmpxchg_release() in __pv_queued_spin_unlock()
locking/rwsem, x86: Drop a bogus cc clobber
futex: Add some more function commentry
locking/hung_task: Show all locks
locking/rwsem: Scan the wait_list for readers only once
locking/rwsem: Remove a few useless comments
locking/rwsem: Return void in __rwsem_mark_wake()
locking, rcu, cgroup: Avoid synchronize_sched() in __cgroup_procs_write()
locking/Documentation: Add Korean translation
locking/Documentation: Fix a typo of example result
locking/Documentation: Fix wrong section reference
...
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/lglock.h | 81 | ||||
-rw-r--r-- | include/linux/percpu-rwsem.h | 108 | ||||
-rw-r--r-- | include/linux/rcu_sync.h | 1 |
3 files changed, 100 insertions, 90 deletions
diff --git a/include/linux/lglock.h b/include/linux/lglock.h deleted file mode 100644 index c92ebd100d9b..000000000000 --- a/include/linux/lglock.h +++ /dev/null @@ -1,81 +0,0 @@ -/* - * Specialised local-global spinlock. Can only be declared as global variables - * to avoid overhead and keep things simple (and we don't want to start using - * these inside dynamically allocated structures). - * - * "local/global locks" (lglocks) can be used to: - * - * - Provide fast exclusive access to per-CPU data, with exclusive access to - * another CPU's data allowed but possibly subject to contention, and to - * provide very slow exclusive access to all per-CPU data. - * - Or to provide very fast and scalable read serialisation, and to provide - * very slow exclusive serialisation of data (not necessarily per-CPU data). - * - * Brlocks are also implemented as a short-hand notation for the latter use - * case. - * - * Copyright 2009, 2010, Nick Piggin, Novell Inc. - */ -#ifndef __LINUX_LGLOCK_H -#define __LINUX_LGLOCK_H - -#include <linux/spinlock.h> -#include <linux/lockdep.h> -#include <linux/percpu.h> -#include <linux/cpu.h> -#include <linux/notifier.h> - -#ifdef CONFIG_SMP - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -#define LOCKDEP_INIT_MAP lockdep_init_map -#else -#define LOCKDEP_INIT_MAP(a, b, c, d) -#endif - -struct lglock { - arch_spinlock_t __percpu *lock; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lock_key; - struct lockdep_map lock_dep_map; -#endif -}; - -#define DEFINE_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ - struct lglock name = { .lock = &name ## _lock } - -#define DEFINE_STATIC_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ - static struct lglock name = { .lock = &name ## _lock } - -void lg_lock_init(struct lglock *lg, char *name); - -void lg_local_lock(struct lglock *lg); -void lg_local_unlock(struct lglock *lg); -void lg_local_lock_cpu(struct lglock *lg, int cpu); -void lg_local_unlock_cpu(struct lglock *lg, int cpu); - -void lg_double_lock(struct lglock *lg, int cpu1, int cpu2); -void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2); - -void lg_global_lock(struct lglock *lg); -void lg_global_unlock(struct lglock *lg); - -#else -/* When !CONFIG_SMP, map lglock to spinlock */ -#define lglock spinlock -#define DEFINE_LGLOCK(name) DEFINE_SPINLOCK(name) -#define DEFINE_STATIC_LGLOCK(name) static DEFINE_SPINLOCK(name) -#define lg_lock_init(lg, name) spin_lock_init(lg) -#define lg_local_lock spin_lock -#define lg_local_unlock spin_unlock -#define lg_local_lock_cpu(lg, cpu) spin_lock(lg) -#define lg_local_unlock_cpu(lg, cpu) spin_unlock(lg) -#define lg_global_lock spin_lock -#define lg_global_unlock spin_unlock -#endif - -#endif diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index c2fa3ecb0dce..5b2e6159b744 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -10,32 +10,122 @@ struct percpu_rw_semaphore { struct rcu_sync rss; - unsigned int __percpu *fast_read_ctr; + unsigned int __percpu *read_count; struct rw_semaphore rw_sem; - atomic_t slow_read_ctr; - wait_queue_head_t write_waitq; + wait_queue_head_t writer; + int readers_block; }; -extern void percpu_down_read(struct percpu_rw_semaphore *); -extern int percpu_down_read_trylock(struct percpu_rw_semaphore *); -extern void percpu_up_read(struct percpu_rw_semaphore *); +#define DEFINE_STATIC_PERCPU_RWSEM(name) \ +static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ +static struct percpu_rw_semaphore name = { \ + .rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC), \ + .read_count = &__percpu_rwsem_rc_##name, \ + .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \ + .writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer), \ +} + +extern int __percpu_down_read(struct percpu_rw_semaphore *, int); +extern void __percpu_up_read(struct percpu_rw_semaphore *); + +static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem) +{ + might_sleep(); + + rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_); + + preempt_disable(); + /* + * We are in an RCU-sched read-side critical section, so the writer + * cannot both change sem->state from readers_fast and start checking + * counters while we are here. So if we see !sem->state, we know that + * the writer won't be checking until we're past the preempt_enable() + * and that one the synchronize_sched() is done, the writer will see + * anything we did within this RCU-sched read-size critical section. + */ + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + __percpu_down_read(sem, false); /* Unconditional memory barrier */ + barrier(); + /* + * The barrier() prevents the compiler from + * bleeding the critical section out. + */ +} + +static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +{ + percpu_down_read_preempt_disable(sem); + preempt_enable(); +} + +static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) +{ + int ret = 1; + + preempt_disable(); + /* + * Same as in percpu_down_read(). + */ + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ + preempt_enable(); + /* + * The barrier() from preempt_enable() prevents the compiler from + * bleeding the critical section out. + */ + + if (ret) + rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_); + + return ret; +} + +static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem) +{ + /* + * The barrier() prevents the compiler from + * bleeding the critical section out. + */ + barrier(); + /* + * Same as in percpu_down_read(). + */ + if (likely(rcu_sync_is_idle(&sem->rss))) + __this_cpu_dec(*sem->read_count); + else + __percpu_up_read(sem); /* Unconditional memory barrier */ + preempt_enable(); + + rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); +} + +static inline void percpu_up_read(struct percpu_rw_semaphore *sem) +{ + preempt_disable(); + percpu_up_read_preempt_enable(sem); +} extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); + extern void percpu_free_rwsem(struct percpu_rw_semaphore *); -#define percpu_init_rwsem(brw) \ +#define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ - __percpu_init_rwsem(brw, #brw, &rwsem_key); \ + __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) - #define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem) +#define percpu_rwsem_assert_held(sem) \ + lockdep_assert_held(&(sem)->rw_sem) + static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h index a63a33e6196e..ece7ed9a4a70 100644 --- a/include/linux/rcu_sync.h +++ b/include/linux/rcu_sync.h @@ -59,6 +59,7 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) } extern void rcu_sync_init(struct rcu_sync *, enum rcu_sync_type); +extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); |