From 2e39465abc4b7856a0ea6fcf4f6b4668bb5db877 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Aug 2014 12:07:15 +0200 Subject: locking: Remove deprecated smp_mb__() barriers Its been a while and there are no in-tree users left, so remove the deprecated barriers. Signed-off-by: Peter Zijlstra Cc: Chen, Gong Cc: Jacob Pan Cc: Joe Perches Cc: John Sullivan Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Srinivas Pandruvada Cc: Theodore Ts'o Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1211575a2208..76c518c9b3a7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -90,22 +90,6 @@ #define CREATE_TRACE_POINTS #include -#ifdef smp_mb__before_atomic -void __smp_mb__before_atomic(void) -{ - smp_mb__before_atomic(); -} -EXPORT_SYMBOL(__smp_mb__before_atomic); -#endif - -#ifdef smp_mb__after_atomic -void __smp_mb__after_atomic(void) -{ - smp_mb__after_atomic(); -} -EXPORT_SYMBOL(__smp_mb__after_atomic); -#endif - void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) { unsigned long delta; -- cgit v1.2.3 From 242489cfe97d44290e7f88b12591fab6c0819045 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:50 -0700 Subject: locking/mutexes: Standardize arguments in lock/unlock slowpaths Just how the locking-end behaves, when unlocking, go ahead and obtain the proper data structure immediately after the previous (asm-end) call exits and there are (probably) pending waiters. This simplifies a bit some of the layering. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra Cc: jason.low2@hp.com Cc: aswin@hp.com Cc: mingo@kernel.org Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1406752916-3341-1-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index ae712b25e492..ad0e3335c481 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -679,9 +679,8 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); * Release the lock, slowpath: */ static inline void -__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) +__mutex_unlock_common_slowpath(struct mutex *lock, int nested) { - struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; /* @@ -716,7 +715,9 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) __visible void __mutex_unlock_slowpath(atomic_t *lock_count) { - __mutex_unlock_common_slowpath(lock_count, 1); + struct mutex *lock = container_of(lock_count, struct mutex, count); + + __mutex_unlock_common_slowpath(lock, 1); } #ifndef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 42fa566bd74aa7b95413fb00611ec983b488222d Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:51 -0700 Subject: locking/mutexes: Document quick lock release when unlocking When unlocking, we always want to reach the slowpath with the lock's counter indicating it is unlocked. -- as returned by the asm fastpath call or by explicitly setting it. While doing so, at least in theory, we can optimize and allow faster lock stealing. When unlocking, we always want to reach the slowpath with the lock's counter indicating it is unlocked. -- as returned by the asm fastpath call or by explicitly setting it. While doing so, at least in theory, we can optimize and allow faster lock stealing. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra Cc: jason.low2@hp.com Cc: aswin@hp.com Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1406752916-3341-2-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index ad0e3335c481..93bec48f09ed 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -684,9 +684,16 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested) unsigned long flags; /* - * some architectures leave the lock unlocked in the fastpath failure + * As a performance measurement, release the lock before doing other + * wakeup related duties to follow. This allows other tasks to acquire + * the lock sooner, while still handling cleanups in past unlock calls. + * This can be done as we do not enforce strict equivalence between the + * mutex counter and wait_list. + * + * + * Some architectures leave the lock unlocked in the fastpath failure * case, others need to leave it locked. In the later case we have to - * unlock it here + * unlock it here - as the lock counter is currently 0 or negative. */ if (__mutex_slowpath_needs_to_unlock()) atomic_set(&lock->count, 1); -- cgit v1.2.3 From aa9fc0c19bee0cbc152e0e06488095fb69229236 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:52 -0700 Subject: locking/mcs: Remove obsolete comment ... as we clearly inline mcs_spin_lock() now. Signed-off-by: Davidlohr Bueso Acked-by: Jason Low Signed-off-by: Peter Zijlstra Cc: aswin@hp.com Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1406752916-3341-3-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mcs_spinlock.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 23e89c5930e9..4d60986fcbee 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -56,9 +56,6 @@ do { \ * If the lock has already been acquired, then this will proceed to spin * on this node->locked until the previous lock holder sets the node->locked * in mcs_spin_unlock(). - * - * We don't inline mcs_spin_lock() so that perf can correctly account for the - * time spent in this lock function. */ static inline void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) -- cgit v1.2.3 From 76916515d9d84e6552ee5e218e0ed566ad75e600 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:53 -0700 Subject: locking/mutexes: Refactor optimistic spinning code When we fail to acquire the mutex in the fastpath, we end up calling __mutex_lock_common(). A *lot* goes on in this function. Move out the optimistic spinning code into mutex_optimistic_spin() and simplify the former a bit. Furthermore, this is similar to what we have in rwsems. No logical changes. Signed-off-by: Davidlohr Bueso Acked-by: Jason Low Signed-off-by: Peter Zijlstra Cc: aswin@hp.com Cc: mingo@kernel.org Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1406752916-3341-4-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 396 ++++++++++++++++++++++++++----------------------- 1 file changed, 214 insertions(+), 182 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 93bec48f09ed..0d8b6ed93874 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -106,6 +106,92 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +/* + * after acquiring lock with fastpath or when we lost out in contested + * slowpath, set ctx and wake up any waiters so they can recheck. + * + * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, + * as the fastpath and opportunistic spinning are disabled in that case. + */ +static __always_inline void +ww_mutex_set_context_fastpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + unsigned long flags; + struct mutex_waiter *cur; + + ww_mutex_lock_acquired(lock, ctx); + + lock->ctx = ctx; + + /* + * The lock->ctx update should be visible on all cores before + * the atomic read is done, otherwise contended waiters might be + * missed. The contended waiters will either see ww_ctx == NULL + * and keep spinning, or it will acquire wait_lock, add itself + * to waiter list and sleep. + */ + smp_mb(); /* ^^^ */ + + /* + * Check if lock is contended, if not there is nobody to wake up + */ + if (likely(atomic_read(&lock->base.count) == 0)) + return; + + /* + * Uh oh, we raced in fastpath, wake up everyone in this case, + * so they can see the new lock->ctx. + */ + spin_lock_mutex(&lock->base.wait_lock, flags); + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } + spin_unlock_mutex(&lock->base.wait_lock, flags); +} + + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * In order to avoid a stampede of mutex spinners from acquiring the mutex @@ -180,6 +266,129 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) */ return retval; } + +/* + * Atomically try to take the lock when it is available + */ +static inline bool mutex_try_to_acquire(struct mutex *lock) +{ + return !mutex_is_locked(lock) && + (atomic_cmpxchg(&lock->count, 1, 0) == 1); +} + +/* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that the lock owner + * is currently running on a (different) CPU and while we don't + * need to reschedule. The rationale is that if the lock owner is + * running, it is likely to release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + * + * The mutex spinners are queued up using MCS lock so that only one + * spinner can compete for the mutex. However, if mutex spinning isn't + * going to happen, there is no point in going through the lock/unlock + * overhead. + * + * Returns true when the lock was taken, otherwise false, indicating + * that we need to jump to the slowpath and sleep. + */ +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + struct task_struct *task = current; + + if (!mutex_can_spin_on_owner(lock)) + goto done; + + if (!osq_lock(&lock->osq)) + goto done; + + while (true) { + struct task_struct *owner; + + if (use_ww_ctx && ww_ctx->acquired > 0) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + /* + * If ww->ctx is set the contents are undefined, only + * by acquiring wait_lock there is a guarantee that + * they are not invalid when reading. + * + * As such, when deadlock detection needs to be + * performed the optimistic spinning cannot be done. + */ + if (ACCESS_ONCE(ww->ctx)) + break; + } + + /* + * If there's an owner, wait for it to either + * release the lock or go to sleep. + */ + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) + break; + + /* Try to acquire the mutex if it is unlocked. */ + if (mutex_try_to_acquire(lock)) { + lock_acquired(&lock->dep_map, ip); + + if (use_ww_ctx) { + struct ww_mutex *ww; + ww = container_of(lock, struct ww_mutex, base); + + ww_mutex_set_context_fastpath(ww, ww_ctx); + } + + mutex_set_owner(lock); + osq_unlock(&lock->osq); + return true; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax_lowlatency(); + } + + osq_unlock(&lock->osq); +done: + /* + * If we fell out of the spin path because of need_resched(), + * reschedule now, before we try-lock the mutex. This avoids getting + * scheduled out right after we obtained the mutex. + */ + if (need_resched()) + schedule_preempt_disabled(); + + return false; +} +#else +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + return false; +} #endif __visible __used noinline @@ -277,91 +486,6 @@ __mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) return 0; } -static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, - struct ww_acquire_ctx *ww_ctx) -{ -#ifdef CONFIG_DEBUG_MUTEXES - /* - * If this WARN_ON triggers, you used ww_mutex_lock to acquire, - * but released with a normal mutex_unlock in this call. - * - * This should never happen, always use ww_mutex_unlock. - */ - DEBUG_LOCKS_WARN_ON(ww->ctx); - - /* - * Not quite done after calling ww_acquire_done() ? - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); - - if (ww_ctx->contending_lock) { - /* - * After -EDEADLK you tried to - * acquire a different ww_mutex? Bad! - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); - - /* - * You called ww_mutex_lock after receiving -EDEADLK, - * but 'forgot' to unlock everything else first? - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); - ww_ctx->contending_lock = NULL; - } - - /* - * Naughty, using a different class will lead to undefined behavior! - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); -#endif - ww_ctx->acquired++; -} - -/* - * after acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. - * - * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, - * as the fastpath and opportunistic spinning are disabled in that case. - */ -static __always_inline void -ww_mutex_set_context_fastpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) -{ - unsigned long flags; - struct mutex_waiter *cur; - - ww_mutex_lock_acquired(lock, ctx); - - lock->ctx = ctx; - - /* - * The lock->ctx update should be visible on all cores before - * the atomic read is done, otherwise contended waiters might be - * missed. The contended waiters will either see ww_ctx == NULL - * and keep spinning, or it will acquire wait_lock, add itself - * to waiter list and sleep. - */ - smp_mb(); /* ^^^ */ - - /* - * Check if lock is contended, if not there is nobody to wake up - */ - if (likely(atomic_read(&lock->base.count) == 0)) - return; - - /* - * Uh oh, we raced in fastpath, wake up everyone in this case, - * so they can see the new lock->ctx. - */ - spin_lock_mutex(&lock->base.wait_lock, flags); - list_for_each_entry(cur, &lock->base.wait_list, list) { - debug_mutex_wake_waiter(&lock->base, cur); - wake_up_process(cur->task); - } - spin_unlock_mutex(&lock->base.wait_lock, flags); -} - /* * Lock a mutex (possibly interruptible), slowpath: */ @@ -378,104 +502,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - /* - * Optimistic spinning. - * - * We try to spin for acquisition when we find that the lock owner - * is currently running on a (different) CPU and while we don't - * need to reschedule. The rationale is that if the lock owner is - * running, it is likely to release the lock soon. - * - * Since this needs the lock owner, and this mutex implementation - * doesn't track the owner atomically in the lock field, we need to - * track it non-atomically. - * - * We can't do this for DEBUG_MUTEXES because that relies on wait_lock - * to serialize everything. - * - * The mutex spinners are queued up using MCS lock so that only one - * spinner can compete for the mutex. However, if mutex spinning isn't - * going to happen, there is no point in going through the lock/unlock - * overhead. - */ - if (!mutex_can_spin_on_owner(lock)) - goto slowpath; - - if (!osq_lock(&lock->osq)) - goto slowpath; - - for (;;) { - struct task_struct *owner; - - if (use_ww_ctx && ww_ctx->acquired > 0) { - struct ww_mutex *ww; - - ww = container_of(lock, struct ww_mutex, base); - /* - * If ww->ctx is set the contents are undefined, only - * by acquiring wait_lock there is a guarantee that - * they are not invalid when reading. - * - * As such, when deadlock detection needs to be - * performed the optimistic spinning cannot be done. - */ - if (ACCESS_ONCE(ww->ctx)) - break; - } - - /* - * If there's an owner, wait for it to either - * release the lock or go to sleep. - */ - owner = ACCESS_ONCE(lock->owner); - if (owner && !mutex_spin_on_owner(lock, owner)) - break; - - /* Try to acquire the mutex if it is unlocked. */ - if (!mutex_is_locked(lock) && - (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { - lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx) { - struct ww_mutex *ww; - ww = container_of(lock, struct ww_mutex, base); - - ww_mutex_set_context_fastpath(ww, ww_ctx); - } - - mutex_set_owner(lock); - osq_unlock(&lock->osq); - preempt_enable(); - return 0; - } - - /* - * When there's no owner, we might have preempted between the - * owner acquiring the lock and setting the owner field. If - * we're an RT task that will live-lock because we won't let - * the owner complete. - */ - if (!owner && (need_resched() || rt_task(task))) - break; - - /* - * The cpu_relax() call is a compiler barrier which forces - * everything in this loop to be re-loaded. We don't need - * memory barriers as we'll eventually observe the right - * values at the cost of a few extra spins. - */ - cpu_relax_lowlatency(); + if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + /* got the lock, yay! */ + preempt_enable(); + return 0; } - osq_unlock(&lock->osq); -slowpath: - /* - * If we fell out of the spin path because of need_resched(), - * reschedule now, before we try-lock the mutex. This avoids getting - * scheduled out right after we obtained the mutex. - */ - if (need_resched()) - schedule_preempt_disabled(); -#endif + spin_lock_mutex(&lock->wait_lock, flags); /* -- cgit v1.2.3 From 7608a43d8f2e02f8b532f8e11481d7ecf8b5d3f9 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:54 -0700 Subject: locking/mutexes: Use MUTEX_SPIN_ON_OWNER when appropriate 4badad35 ("locking/mutex: Disable optimistic spinning on some architectures") added a ARCH_SUPPORTS_ATOMIC_RMW flag to disable the mutex optimistic feature on specific archs. Because CONFIG_MUTEX_SPIN_ON_OWNER only depended on DEBUG and SMP, it was ok to have the ->owner field conditional a bit flexible. However by adding a new variable to the matter, we can waste space with the unused field, ie: CONFIG_SMP && (!CONFIG_MUTEX_SPIN_ON_OWNER && !CONFIG_DEBUG_MUTEX). Signed-off-by: Davidlohr Bueso Acked-by: Jason Low Signed-off-by: Peter Zijlstra Cc: aswin@hp.com Cc: Davidlohr Bueso Cc: Heiko Carstens Cc: Jason Low Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Tim Chen Link: http://lkml.kernel.org/r/1406752916-3341-5-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 4115fbf83b12..5cda397607f2 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -16,7 +16,7 @@ #define mutex_remove_waiter(lock, waiter, ti) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#ifdef CONFIG_SMP +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline void mutex_set_owner(struct mutex *lock) { lock->owner = current; -- cgit v1.2.3 From 214e0aed639ef40987bf6159fad303171a6de31e Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Jul 2014 13:41:55 -0700 Subject: locking/Documentation: Move locking related docs into Documentation/locking/ Specifically: Documentation/locking/lockdep-design.txt Documentation/locking/lockstat.txt Documentation/locking/mutex-design.txt Documentation/locking/rt-mutex-design.txt Documentation/locking/rt-mutex.txt Documentation/locking/spinlocks.txt Documentation/locking/ww-mutex-design.txt Signed-off-by: Davidlohr Bueso Acked-by: Randy Dunlap Signed-off-by: Peter Zijlstra Cc: jason.low2@hp.com Cc: aswin@hp.com Cc: Alexei Starovoitov Cc: Al Viro Cc: Andrew Morton Cc: Chris Mason Cc: Dan Streetman Cc: David Airlie Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Jason Low Cc: Josef Bacik Cc: Kees Cook Cc: Linus Torvalds Cc: Lubomir Rintel Cc: Masanari Iida Cc: Paul E. McKenney Cc: Randy Dunlap Cc: Tim Chen Cc: Vineet Gupta Cc: fengguang.wu@intel.com Link: http://lkml.kernel.org/r/1406752916-3341-6-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 2 +- kernel/locking/rtmutex.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0d8b6ed93874..dadbf88c22c4 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -15,7 +15,7 @@ * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale * and Sven Dietrich. * - * Also see Documentation/mutex-design.txt. + * Also see Documentation/locking/mutex-design.txt. */ #include #include diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index a0ea2a141b3b..7c98873a3077 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -8,7 +8,7 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * - * See Documentation/rt-mutex-design.txt for details. + * See Documentation/locking/rt-mutex-design.txt for details. */ #include #include -- cgit v1.2.3 From f0bab73cb539fb803c4d419951e8d28aa4964f8f Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 6 Aug 2014 13:22:01 -0400 Subject: locking/lockdep: Restrict the use of recursive read_lock() with qrwlock Unlike the original unfair rwlock implementation, queued rwlock will grant lock according to the chronological sequence of the lock requests except when the lock requester is in the interrupt context. Consequently, recursive read_lock calls will now hang the process if there is a write_lock call somewhere in between the read_lock calls. This patch updates the lockdep implementation to look for recursive read_lock calls. A new read state (3) is used to mark those read_lock call that cannot be recursively called except in the interrupt context. The new read state does exhaust the 2 bits available in held_lock:read bit field. The addition of any new read state in the future may require a redesign of how all those bits are squeezed together in the held_lock structure. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra Cc: Maarten Lankhorst Cc: Rik van Riel Cc: Scott J Norton Cc: Fengguang Wu Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1407345722-61615-2-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 88d0d4420ad2..420ba685c4e5 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3597,6 +3597,12 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, raw_local_irq_save(flags); check_flags(flags); + /* + * An interrupt recursive read in interrupt context can be considered + * to be the same as a recursive read from checking perspective. + */ + if ((read == 3) && in_interrupt()) + read = 2; current->lockdep_recursion = 1; trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, -- cgit v1.2.3 From 315427691c7a064718b5ad7d378d7f1c1898a626 Mon Sep 17 00:00:00 2001 From: Mark Rustad Date: Wed, 3 Sep 2014 03:17:24 -0700 Subject: locking/semaphore: Resolve some shadow warnings Resolve some shadow warnings resulting from using the name jiffies, which is a well-known global. This is not a problem of course, but it could be a trap for someone copying and pasting code, and it just makes W=2 a little cleaner. Signed-off-by: Mark Rustad Signed-off-by: Jeff Kirsher Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/1409739444-13635-1-git-send-email-jeffrey.t.kirsher@intel.com Signed-off-by: Ingo Molnar --- kernel/locking/semaphore.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index 6815171a4fff..b8120abe594b 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -36,7 +36,7 @@ static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); static noinline int __down_killable(struct semaphore *sem); -static noinline int __down_timeout(struct semaphore *sem, long jiffies); +static noinline int __down_timeout(struct semaphore *sem, long timeout); static noinline void __up(struct semaphore *sem); /** @@ -145,14 +145,14 @@ EXPORT_SYMBOL(down_trylock); /** * down_timeout - acquire the semaphore within a specified time * @sem: the semaphore to be acquired - * @jiffies: how long to wait before failing + * @timeout: how long to wait before failing * * Attempts to acquire the semaphore. If no more tasks are allowed to * acquire the semaphore, calling this function will put the task to sleep. * If the semaphore is not released within the specified number of jiffies, * this function returns -ETIME. It returns 0 if the semaphore was acquired. */ -int down_timeout(struct semaphore *sem, long jiffies) +int down_timeout(struct semaphore *sem, long timeout) { unsigned long flags; int result = 0; @@ -161,7 +161,7 @@ int down_timeout(struct semaphore *sem, long jiffies) if (likely(sem->count > 0)) sem->count--; else - result = __down_timeout(sem, jiffies); + result = __down_timeout(sem, timeout); raw_spin_unlock_irqrestore(&sem->lock, flags); return result; @@ -248,9 +248,9 @@ static noinline int __sched __down_killable(struct semaphore *sem) return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT); } -static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies) +static noinline int __sched __down_timeout(struct semaphore *sem, long timeout) { - return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies); + return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout); } static noinline void __sched __up(struct semaphore *sem) -- cgit v1.2.3 From db0e716a1512179e8374a74c1f3184e9ce15d138 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 11 Sep 2014 22:34:25 -0700 Subject: locking/rwsem: Move EXPORT_SYMBOL() lines to follow function definition rw-semaphore is the only type of lock doing this ugliness of exporting at the end of the file. Signed-off-by: Davidlohr Bueso Cc: dave@stgolabs.net Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/1410500066-5909-1-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/rwsem-xadd.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index d6203faf2eb1..12166ec9b7e7 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -246,6 +246,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_down_read_failed); static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) { @@ -465,6 +466,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_down_write_failed); /* * handle waking up a waiter on the semaphore @@ -485,6 +487,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_wake); /* * downgrade a write lock into a read lock @@ -506,8 +509,4 @@ struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) return sem; } - -EXPORT_SYMBOL(rwsem_down_read_failed); -EXPORT_SYMBOL(rwsem_down_write_failed); -EXPORT_SYMBOL(rwsem_wake); EXPORT_SYMBOL(rwsem_downgrade_wake); -- cgit v1.2.3 From debfab74e453f079cd8b12b0604387a8c510ef3a Mon Sep 17 00:00:00 2001 From: Jason Low Date: Tue, 16 Sep 2014 17:16:57 -0700 Subject: locking/rwsem: Avoid double checking before try acquiring write lock Commit 9b0fc9c09f1b ("rwsem: skip initial trylock in rwsem_down_write_failed") checks for if there are known active lockers in order to avoid write trylocking using expensive cmpxchg() when it likely wouldn't get the lock. However, a subsequent patch was added such that we directly check for sem->count == RWSEM_WAITING_BIAS right before trying that cmpxchg(). Thus, commit 9b0fc9c09f1b now just adds overhead. This patch modifies it so that we only do a check for if count == RWSEM_WAITING_BIAS. Also, add a comment on why we do an "extra check" of count before the cmpxchg(). Signed-off-by: Jason Low Acked-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Aswin Chandramouleeswaran Cc: Chegu Vinod Cc: Peter Hurley Cc: Tim Chen Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1410913017.2447.22.camel@j-VirtualBox Signed-off-by: Ingo Molnar --- kernel/locking/rwsem-xadd.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 12166ec9b7e7..7628c3fc37ca 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -250,16 +250,18 @@ EXPORT_SYMBOL(rwsem_down_read_failed); static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) { - if (!(count & RWSEM_ACTIVE_MASK)) { - /* try acquiring the write lock */ - if (sem->count == RWSEM_WAITING_BIAS && - cmpxchg(&sem->count, RWSEM_WAITING_BIAS, - RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { - if (!list_is_singular(&sem->wait_list)) - rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); - return true; - } + /* + * Try acquiring the write lock. Check count first in order + * to reduce unnecessary expensive cmpxchg() operations. + */ + if (count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { + if (!list_is_singular(&sem->wait_list)) + rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + return true; } + return false; } -- cgit v1.2.3 From 8acd91e8620836a56ff62028ed28ba629f2881a0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Sep 2014 15:26:00 +0200 Subject: locking/lockdep: Revert qrwlock recusive stuff Commit f0bab73cb539 ("locking/lockdep: Restrict the use of recursive read_lock() with qrwlock") changed lockdep to try and conform to the qrwlock semantics which differ from the traditional rwlock semantics. In particular qrwlock is fair outside of interrupt context, but in interrupt context readers will ignore all fairness. The problem modeling this is that read and write side have different lock state (interrupts) semantics but we only have a single representation of these. Therefore lockdep will get confused, thinking the lock can cause interrupt lock inversions. So revert it for now; the old rwlock semantics were already imperfectly modeled and the qrwlock extra won't fit either. If we want to properly fix this, I think we need to resurrect the work by Gautham did a few years ago that split the read and write state of locks: http://lwn.net/Articles/332801/ FWIW the locking selftest that would've failed (and was reported by Borislav earlier) is something like: RL(X1); /* IRQ-ON */ LOCK(A); UNLOCK(A); RU(X1); IRQ_ENTER(); RL(X1); /* IN-IRQ */ RU(X1); IRQ_EXIT(); At which point it would report that because A is an IRQ-unsafe lock we can suffer the following inversion: CPU0 CPU1 lock(A) lock(X1) lock(A) lock(X1) And this is 'wrong' because X1 can recurse (assuming the above lock are in fact read-lock) but lockdep doesn't know about this. Signed-off-by: Peter Zijlstra (Intel) Cc: Waiman Long Cc: ego@linux.vnet.ibm.com Cc: bp@alien8.de Cc: Linus Torvalds Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/20140930132600.GA7444@worktop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 420ba685c4e5..88d0d4420ad2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3597,12 +3597,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, raw_local_irq_save(flags); check_flags(flags); - /* - * An interrupt recursive read in interrupt context can be considered - * to be the same as a recursive read from checking perspective. - */ - if ((read == 3) && in_interrupt()) - read = 2; current->lockdep_recursion = 1; trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, -- cgit v1.2.3