diff options
Diffstat (limited to 'kernel/locking/mutex.c')
| -rw-r--r-- | kernel/locking/mutex.c | 990 |
1 files changed, 627 insertions, 363 deletions
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index a70b90db3909..ad2d9e22697b 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -27,41 +27,180 @@ #include <linux/debug_locks.h> #include <linux/osq_lock.h> -/* - * In the DEBUG case we are using the "NULL fastpath" for mutexes, - * which forces all calls into the slowpath: - */ #ifdef CONFIG_DEBUG_MUTEXES # include "mutex-debug.h" -# include <asm-generic/mutex-null.h> -/* - * Must be 0 for the debug case so we do not do the unlock outside of the - * wait_lock region. debug_mutex_unlock() will do the actual unlock in this - * case. - */ -# undef __mutex_slowpath_needs_to_unlock -# define __mutex_slowpath_needs_to_unlock() 0 #else # include "mutex.h" -# include <asm/mutex.h> #endif void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { - atomic_set(&lock->count, 1); + atomic_long_set(&lock->owner, 0); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); - mutex_clear_owner(lock); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER osq_lock_init(&lock->osq); #endif debug_mutex_init(lock, name, key); } - EXPORT_SYMBOL(__mutex_init); +/* + * @owner: contains: 'struct task_struct *' to the current lock owner, + * NULL means not owned. Since task_struct pointers are aligned at + * at least L1_CACHE_BYTES, we have low bits to store extra state. + * + * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup. + * Bit1 indicates unlock needs to hand the lock to the top-waiter + * Bit2 indicates handoff has been done and we're waiting for pickup. + */ +#define MUTEX_FLAG_WAITERS 0x01 +#define MUTEX_FLAG_HANDOFF 0x02 +#define MUTEX_FLAG_PICKUP 0x04 + +#define MUTEX_FLAGS 0x07 + +static inline struct task_struct *__owner_task(unsigned long owner) +{ + return (struct task_struct *)(owner & ~MUTEX_FLAGS); +} + +static inline unsigned long __owner_flags(unsigned long owner) +{ + return owner & MUTEX_FLAGS; +} + +/* + * Trylock variant that retuns the owning task on failure. + */ +static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock) +{ + unsigned long owner, curr = (unsigned long)current; + + owner = atomic_long_read(&lock->owner); + for (;;) { /* must loop, can race against a flag */ + unsigned long old, flags = __owner_flags(owner); + unsigned long task = owner & ~MUTEX_FLAGS; + + if (task) { + if (likely(task != curr)) + break; + + if (likely(!(flags & MUTEX_FLAG_PICKUP))) + break; + + flags &= ~MUTEX_FLAG_PICKUP; + } else { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(flags & MUTEX_FLAG_PICKUP); +#endif + } + + /* + * We set the HANDOFF bit, we must make sure it doesn't live + * past the point where we acquire it. This would be possible + * if we (accidentally) set the bit on an unlocked mutex. + */ + flags &= ~MUTEX_FLAG_HANDOFF; + + old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags); + if (old == owner) + return NULL; + + owner = old; + } + + return __owner_task(owner); +} + +/* + * Actual trylock that will work on any unlocked state. + */ +static inline bool __mutex_trylock(struct mutex *lock) +{ + return !__mutex_trylock_or_owner(lock); +} + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +/* + * Lockdep annotations are contained to the slow paths for simplicity. + * There is nothing that would stop spreading the lockdep annotations outwards + * except more code. + */ + +/* + * Optimistic trylock that only works in the uncontended case. Make sure to + * follow with a __mutex_trylock() before failing. + */ +static __always_inline bool __mutex_trylock_fast(struct mutex *lock) +{ + unsigned long curr = (unsigned long)current; + + if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr)) + return true; + + return false; +} + +static __always_inline bool __mutex_unlock_fast(struct mutex *lock) +{ + unsigned long curr = (unsigned long)current; + + if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr) + return true; + + return false; +} +#endif + +static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_or(flag, &lock->owner); +} + +static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_andnot(flag, &lock->owner); +} + +static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter) +{ + return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; +} + +/* + * Give up ownership to a specific task, when @task = NULL, this is equivalent + * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves + * WAITERS. Provides RELEASE semantics like a regular unlock, the + * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff. + */ +static void __mutex_handoff(struct mutex *lock, struct task_struct *task) +{ + unsigned long owner = atomic_long_read(&lock->owner); + + for (;;) { + unsigned long old, new; + +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); + DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP); +#endif + + new = (owner & MUTEX_FLAG_WAITERS); + new |= (unsigned long)task; + if (task) + new |= MUTEX_FLAG_PICKUP; + + old = atomic_long_cmpxchg_release(&lock->owner, owner, new); + if (old == owner) + break; + + owner = old; + } +} + #ifndef CONFIG_DEBUG_LOCK_ALLOC /* * We split the mutex lock/unlock logic into separate fastpath and @@ -69,7 +208,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); +static void __sched __mutex_lock_slowpath(struct mutex *lock); /** * mutex_lock - acquire the mutex @@ -95,19 +234,15 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); void __sched mutex_lock(struct mutex *lock) { might_sleep(); - /* - * The locking fastpath is the 1->0 transition from - * 'unlocked' into 'locked' state. - */ - __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); - mutex_set_owner(lock); -} + if (!__mutex_trylock_fast(lock)) + __mutex_lock_slowpath(lock); +} EXPORT_SYMBOL(mutex_lock); #endif -static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, - struct ww_acquire_ctx *ww_ctx) +static __always_inline void +ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { #ifdef CONFIG_DEBUG_MUTEXES /* @@ -146,20 +281,50 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ww_ctx->acquired++; } +static inline bool __sched +__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) +{ + return a->stamp - b->stamp <= LONG_MAX && + (a->stamp != b->stamp || a > b); +} + /* - * After acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. + * Wake up any waiters that may have to back off when the lock is held by the + * given context. + * + * Due to the invariants on the wait list, this can only affect the first + * waiter with a context. * - * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, - * as the fastpath and opportunistic spinning are disabled in that case. + * The current task must not be on the wait list. */ -static __always_inline void -ww_mutex_set_context_fastpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) +static void __sched +__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { - unsigned long flags; struct mutex_waiter *cur; + lockdep_assert_held(&lock->wait_lock); + + list_for_each_entry(cur, &lock->wait_list, list) { + if (!cur->ww_ctx) + continue; + + if (cur->ww_ctx->acquired > 0 && + __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { + debug_mutex_wake_waiter(lock, cur); + wake_up_process(cur->task); + } + + break; + } +} + +/* + * After acquiring lock with fastpath or when we lost out in contested + * slowpath, set ctx and wake up any waiters so they can recheck. + */ +static __always_inline void +ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ ww_mutex_lock_acquired(lock, ctx); lock->ctx = ctx; @@ -176,58 +341,91 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, /* * Check if lock is contended, if not there is nobody to wake up */ - if (likely(atomic_read(&lock->base.count) == 0)) + if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) 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); + spin_lock(&lock->base.wait_lock); + __ww_mutex_wakeup_for_backoff(&lock->base, ctx); + spin_unlock(&lock->base.wait_lock); } /* - * After acquiring lock in the slowpath set ctx and wake up any - * waiters so they can recheck. + * After acquiring lock in the slowpath set ctx. + * + * Unlike for the fast path, the caller ensures that waiters are woken up where + * necessary. * * Callers must hold the mutex wait_lock. */ static __always_inline void -ww_mutex_set_context_slowpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) +ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - struct mutex_waiter *cur; - ww_mutex_lock_acquired(lock, ctx); lock->ctx = ctx; +} + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + +static inline +bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + struct mutex_waiter *waiter) +{ + 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. + * + * Check this in every inner iteration because we may + * be racing against another thread's ww_mutex_lock. + */ + if (ww_ctx->acquired > 0 && READ_ONCE(ww->ctx)) + return false; /* - * Give any possible sleeping processes the chance to wake up, - * so they can recheck if they have to back off. + * If we aren't on the wait list yet, cancel the spin + * if there are waiters. We want to avoid stealing the + * lock from a waiter with an earlier stamp, since the + * other thread may already own a lock that we also + * need. */ - list_for_each_entry(cur, &lock->base.wait_list, list) { - debug_mutex_wake_waiter(&lock->base, cur); - wake_up_process(cur->task); - } + if (!waiter && (atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS)) + return false; + + /* + * Similarly, stop spinning if we are no longer the + * first waiter. + */ + if (waiter && !__mutex_waiter_is_first(lock, waiter)) + return false; + + return true; } -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. + * Look out! "owner" is an entirely speculative pointer access and not + * reliable. + * + * "noinline" so that this function shows up on perf profiles. */ static noinline -bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, + struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { bool ret = true; rcu_read_lock(); - while (lock->owner == owner) { + while (__mutex_owner(lock) == owner) { /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking lock->owner still matches owner. If that fails, @@ -236,12 +434,21 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) */ barrier(); - if (!owner->on_cpu || need_resched()) { + /* + * Use vcpu_is_preempted to detect lock holder preemption issue. + */ + if (!owner->on_cpu || need_resched() || + vcpu_is_preempted(task_cpu(owner))) { + ret = false; + break; + } + + if (ww_ctx && !ww_mutex_spin_on_owner(lock, ww_ctx, waiter)) { ret = false; break; } - cpu_relax_lowlatency(); + cpu_relax(); } rcu_read_unlock(); @@ -260,27 +467,25 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) return 0; rcu_read_lock(); - owner = READ_ONCE(lock->owner); + owner = __mutex_owner(lock); + + /* + * As lock holder preemption issue, we both skip spinning if task is not + * on cpu or its cpu is preempted + */ if (owner) - retval = owner->on_cpu; + retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); rcu_read_unlock(); + /* - * if lock->owner is not set, the mutex owner may have just acquired - * it and not set the owner yet or the mutex has been released. + * If lock->owner is not set, the mutex has been released. Return true + * such that we'll trylock in the spin path, which is a faster option + * than the blocking slow path. */ 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_acquire(&lock->count, 1, 0) == 1); -} - -/* * Optimistic spinning. * * We try to spin for acquisition when we find that the lock owner @@ -288,13 +493,6 @@ static inline bool mutex_try_to_acquire(struct mutex *lock) * 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 @@ -302,74 +500,50 @@ static inline bool mutex_try_to_acquire(struct mutex *lock) * * Returns true when the lock was taken, otherwise false, indicating * that we need to jump to the slowpath and sleep. + * + * The waiter flag is set to true if the spinner is a waiter in the wait + * queue. The waiter-spinner will spin on the lock directly and concurrently + * with the spinner at the head of the OSQ, if present, until the owner is + * changed to itself. */ -static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +static __always_inline bool +mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, struct mutex_waiter *waiter) { - struct task_struct *task = current; - - if (!mutex_can_spin_on_owner(lock)) - goto done; - - /* - * In order to avoid a stampede of mutex spinners trying to - * acquire the mutex all at once, the spinners need to take a - * MCS (queued) lock first before spinning on the owner field. - */ - 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 (READ_ONCE(ww->ctx)) - break; - } - + if (!waiter) { /* - * If there's an owner, wait for it to either - * release the lock or go to sleep. + * The purpose of the mutex_can_spin_on_owner() function is + * to eliminate the overhead of osq_lock() and osq_unlock() + * in case spinning isn't possible. As a waiter-spinner + * is not going to take OSQ lock anyway, there is no need + * to call mutex_can_spin_on_owner(). */ - owner = READ_ONCE(lock->owner); - if (owner && !mutex_spin_on_owner(lock, owner)) - break; + if (!mutex_can_spin_on_owner(lock)) + goto fail; - /* 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); + /* + * In order to avoid a stampede of mutex spinners trying to + * acquire the mutex all at once, the spinners need to take a + * MCS (queued) lock first before spinning on the owner field. + */ + if (!osq_lock(&lock->osq)) + goto fail; + } - ww_mutex_set_context_fastpath(ww, ww_ctx); - } + for (;;) { + struct task_struct *owner; - mutex_set_owner(lock); - osq_unlock(&lock->osq); - return true; - } + /* Try to acquire the mutex... */ + owner = __mutex_trylock_or_owner(lock); + if (!owner) + break; /* - * 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. + * There's an owner, wait for it to either + * release the lock or go to sleep. */ - if (!owner && (need_resched() || rt_task(task))) - break; + if (!mutex_spin_on_owner(lock, owner, ww_ctx, waiter)) + goto fail_unlock; /* * The cpu_relax() call is a compiler barrier which forces @@ -377,11 +551,20 @@ static bool mutex_optimistic_spin(struct mutex *lock, * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - cpu_relax_lowlatency(); + cpu_relax(); } - osq_unlock(&lock->osq); -done: + if (!waiter) + osq_unlock(&lock->osq); + + return true; + + +fail_unlock: + if (!waiter) + osq_unlock(&lock->osq); + +fail: /* * If we fell out of the spin path because of need_resched(), * reschedule now, before we try-lock the mutex. This avoids getting @@ -399,15 +582,15 @@ done: return false; } #else -static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +static __always_inline bool +mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, struct mutex_waiter *waiter) { return false; } #endif -__visible __used noinline -void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip); /** * mutex_unlock - release the mutex @@ -422,21 +605,12 @@ void __sched __mutex_unlock_slowpath(atomic_t *lock_count); */ void __sched mutex_unlock(struct mutex *lock) { - /* - * The unlocking fastpath is the 0->1 transition from 'locked' - * into 'unlocked' state: - */ -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(lock); +#ifndef CONFIG_DEBUG_LOCK_ALLOC + if (__mutex_unlock_fast(lock)) + return; #endif - __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); + __mutex_unlock_slowpath(lock, _RET_IP_); } - EXPORT_SYMBOL(mutex_unlock); /** @@ -465,36 +639,93 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) lock->ctx = NULL; } -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(&lock->base); -#endif - __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); + mutex_unlock(&lock->base); } EXPORT_SYMBOL(ww_mutex_unlock); static inline int __sched -__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) +__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); + struct mutex_waiter *cur; + + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) + goto deadlock; + + /* + * If there is a waiter in front of us that has a context, then its + * stamp is earlier than ours and we must back off. + */ + cur = waiter; + list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) { + if (cur->ww_ctx) + goto deadlock; + } - if (!hold_ctx) + return 0; + +deadlock: +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; +} + +static inline int __sched +__ww_mutex_add_waiter(struct mutex_waiter *waiter, + struct mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct mutex_waiter *cur; + struct list_head *pos; + + if (!ww_ctx) { + list_add_tail(&waiter->list, &lock->wait_list); return 0; + } - if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && - (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { + /* + * Add the waiter before the first waiter with a higher stamp. + * Waiters without a context are skipped to avoid starving + * them. + */ + pos = &lock->wait_list; + list_for_each_entry_reverse(cur, &lock->wait_list, list) { + if (!cur->ww_ctx) + continue; + + if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { + /* Back off immediately if necessary. */ + if (ww_ctx->acquired > 0) { #ifdef CONFIG_DEBUG_MUTEXES - DEBUG_LOCKS_WARN_ON(ctx->contending_lock); - ctx->contending_lock = ww; + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); + ww_ctx->contending_lock = ww; #endif - return -EDEADLK; + return -EDEADLK; + } + + break; + } + + pos = &cur->list; + + /* + * Wake up the waiter so that it gets a chance to back + * off. + */ + if (cur->ww_ctx->acquired > 0) { + debug_mutex_wake_waiter(lock, cur); + wake_up_process(cur->task); + } } + list_add_tail(&waiter->list, pos); return 0; } @@ -506,13 +737,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip, struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) { - struct task_struct *task = current; struct mutex_waiter waiter; - unsigned long flags; + bool first = false; + struct ww_mutex *ww; int ret; - if (use_ww_ctx) { - struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + might_sleep(); + + ww = container_of(lock, struct ww_mutex, base); + if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; } @@ -520,106 +753,157 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); - if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + if (__mutex_trylock(lock) || + mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) { /* got the lock, yay! */ + lock_acquired(&lock->dep_map, ip); + if (use_ww_ctx && ww_ctx) + ww_mutex_set_context_fastpath(ww, ww_ctx); preempt_enable(); return 0; } - spin_lock_mutex(&lock->wait_lock, flags); - + spin_lock(&lock->wait_lock); /* - * Once more, try to acquire the lock. Only try-lock the mutex if - * it is unlocked to reduce unnecessary xchg() operations. + * After waiting to acquire the wait_lock, try again. */ - if (!mutex_is_locked(lock) && - (atomic_xchg_acquire(&lock->count, 0) == 1)) + if (__mutex_trylock(lock)) { + if (use_ww_ctx && ww_ctx) + __ww_mutex_wakeup_for_backoff(lock, ww_ctx); + goto skip_wait; + } debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, task); - - /* add waiting tasks to the end of the waitqueue (FIFO): */ - list_add_tail(&waiter.list, &lock->wait_list); - waiter.task = task; + debug_mutex_add_waiter(lock, &waiter, current); lock_contended(&lock->dep_map, ip); + if (!use_ww_ctx) { + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + +#ifdef CONFIG_DEBUG_MUTEXES + waiter.ww_ctx = MUTEX_POISON_WW_CTX; +#endif + } else { + /* Add in stamp order, waking up waiters that must back off. */ + ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); + if (ret) + goto err_early_backoff; + + waiter.ww_ctx = ww_ctx; + } + + waiter.task = current; + + if (__mutex_waiter_is_first(lock, &waiter)) + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); + + set_current_state(state); for (;;) { /* - * Lets try to take the lock again - this is needed even if - * we get here for the first time (shortly after failing to - * acquire the lock), to make sure that we get a wakeup once - * it's unlocked. Later on, if we sleep, this is the - * operation that gives us the lock. We xchg it to -1, so - * that when we release the lock, we properly wake up the - * other waiters. We only attempt the xchg if the count is - * non-negative in order to avoid unnecessary xchg operations: + * Once we hold wait_lock, we're serialized against + * mutex_unlock() handing the lock off to us, do a trylock + * before testing the error conditions to make sure we pick up + * the handoff. */ - if (atomic_read(&lock->count) >= 0 && - (atomic_xchg_acquire(&lock->count, -1) == 1)) - break; + if (__mutex_trylock(lock)) + goto acquired; /* - * got a signal? (This code gets eliminated in the - * TASK_UNINTERRUPTIBLE case.) + * Check for signals and wound conditions while holding + * wait_lock. This ensures the lock cancellation is ordered + * against mutex_unlock() and wake-ups do not go missing. */ - if (unlikely(signal_pending_state(state, task))) { + if (unlikely(signal_pending_state(state, current))) { ret = -EINTR; goto err; } - if (use_ww_ctx && ww_ctx->acquired > 0) { - ret = __ww_mutex_lock_check_stamp(lock, ww_ctx); + if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) { + ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx); if (ret) goto err; } - __set_task_state(task, state); - - /* didn't get the lock, go to sleep: */ - spin_unlock_mutex(&lock->wait_lock, flags); + spin_unlock(&lock->wait_lock); schedule_preempt_disabled(); - spin_lock_mutex(&lock->wait_lock, flags); + + /* + * ww_mutex needs to always recheck its position since its waiter + * list is not FIFO ordered. + */ + if ((use_ww_ctx && ww_ctx) || !first) { + first = __mutex_waiter_is_first(lock, &waiter); + if (first) + __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); + } + + set_current_state(state); + /* + * Here we order against unlock; we must either see it change + * state back to RUNNING and fall through the next schedule(), + * or we must see its unlock and acquire. + */ + if (__mutex_trylock(lock) || + (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter))) + break; + + spin_lock(&lock->wait_lock); } - __set_task_state(task, TASK_RUNNING); + spin_lock(&lock->wait_lock); +acquired: + __set_current_state(TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, task); - /* set it to 0 if there are no waiters left: */ + mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); + __mutex_clear_flag(lock, MUTEX_FLAGS); + debug_mutex_free_waiter(&waiter); skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); - mutex_set_owner(lock); - if (use_ww_ctx) { - struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + if (use_ww_ctx && ww_ctx) ww_mutex_set_context_slowpath(ww, ww_ctx); - } - spin_unlock_mutex(&lock->wait_lock, flags); + spin_unlock(&lock->wait_lock); preempt_enable(); return 0; err: - mutex_remove_waiter(lock, &waiter, task); - spin_unlock_mutex(&lock->wait_lock, flags); + __set_current_state(TASK_RUNNING); + mutex_remove_waiter(lock, &waiter, current); +err_early_backoff: + spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); preempt_enable(); return ret; } +static int __sched +__mutex_lock(struct mutex *lock, long state, unsigned int subclass, + struct lockdep_map *nest_lock, unsigned long ip) +{ + return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false); +} + +static int __sched +__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass, + struct lockdep_map *nest_lock, unsigned long ip, + struct ww_acquire_ctx *ww_ctx) +{ + return __mutex_lock_common(lock, state, subclass, nest_lock, ip, ww_ctx, true); +} + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL, 0); + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_nested); @@ -627,32 +911,38 @@ EXPORT_SYMBOL_GPL(mutex_lock_nested); void __sched _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) { - might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - 0, nest, _RET_IP_, NULL, 0); + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_); } - EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - return __mutex_lock_common(lock, TASK_KILLABLE, - subclass, NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_); } - EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); +void __sched +mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) +{ + int token; + + might_sleep(); + + token = io_schedule_prepare(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + subclass, NULL, _RET_IP_, NULL, 0); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io_nested); + static inline int ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { @@ -680,89 +970,102 @@ ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) } int __sched -__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; might_sleep(); - ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx, 1); - if (!ret && ctx->acquired > 1) + ret = __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, + 0, ctx ? &ctx->dep_map : NULL, _RET_IP_, + ctx); + if (!ret && ctx && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; } -EXPORT_SYMBOL_GPL(__ww_mutex_lock); +EXPORT_SYMBOL_GPL(ww_mutex_lock); int __sched -__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; might_sleep(); - ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx, 1); + ret = __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, + 0, ctx ? &ctx->dep_map : NULL, _RET_IP_, + ctx); - if (!ret && ctx->acquired > 1) + if (!ret && ctx && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; } -EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); +EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); #endif /* * Release the lock, slowpath: */ -static inline void -__mutex_unlock_common_slowpath(struct mutex *lock, int nested) +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip) { - unsigned long flags; - WAKE_Q(wake_q); + struct task_struct *next = NULL; + DEFINE_WAKE_Q(wake_q); + unsigned long owner; + + mutex_release(&lock->dep_map, 1, ip); /* - * 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. - * + * Release the lock before (potentially) taking the spinlock such that + * other contenders can get on with things ASAP. * - * 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 - as the lock counter is currently 0 or negative. + * Except when HANDOFF, in that case we must not clear the owner field, + * but instead set it to the top waiter. */ - if (__mutex_slowpath_needs_to_unlock()) - atomic_set(&lock->count, 1); + owner = atomic_long_read(&lock->owner); + for (;;) { + unsigned long old; - spin_lock_mutex(&lock->wait_lock, flags); - mutex_release(&lock->dep_map, nested, _RET_IP_); - debug_mutex_unlock(lock); +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); + DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP); +#endif + if (owner & MUTEX_FLAG_HANDOFF) + break; + + old = atomic_long_cmpxchg_release(&lock->owner, owner, + __owner_flags(owner)); + if (old == owner) { + if (owner & MUTEX_FLAG_WAITERS) + break; + + return; + } + + owner = old; + } + + spin_lock(&lock->wait_lock); + debug_mutex_unlock(lock); if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ struct mutex_waiter *waiter = - list_entry(lock->wait_list.next, - struct mutex_waiter, list); + list_first_entry(&lock->wait_list, + struct mutex_waiter, list); + + next = waiter->task; debug_mutex_wake_waiter(lock, waiter); - wake_q_add(&wake_q, waiter->task); + wake_q_add(&wake_q, next); } - spin_unlock_mutex(&lock->wait_lock, flags); - wake_up_q(&wake_q); -} + if (owner & MUTEX_FLAG_HANDOFF) + __mutex_handoff(lock, next); -/* - * Release the lock, slowpath: - */ -__visible void -__mutex_unlock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); + spin_unlock(&lock->wait_lock); - __mutex_unlock_common_slowpath(lock, 1); + wake_up_q(&wake_q); } #ifndef CONFIG_DEBUG_LOCK_ALLOC @@ -789,104 +1092,72 @@ __mutex_lock_interruptible_slowpath(struct mutex *lock); */ int __sched mutex_lock_interruptible(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_interruptible_slowpath(lock); + + return __mutex_lock_interruptible_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_killable_slowpath(lock); + + return __mutex_lock_killable_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_killable); -__visible void __sched -__mutex_lock_slowpath(atomic_t *lock_count) +void __sched mutex_lock_io(struct mutex *lock) { - struct mutex *lock = container_of(lock_count, struct mutex, count); + int token; - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL, 0); + token = io_schedule_prepare(); + mutex_lock(lock); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io); + +static noinline void __sched +__mutex_lock_slowpath(struct mutex *lock) +{ + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_killable_slowpath(struct mutex *lock) { - return __mutex_lock_common(lock, TASK_KILLABLE, 0, - NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_interruptible_slowpath(struct mutex *lock) { - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx, 1); + return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0, NULL, + _RET_IP_, ctx); } static noinline int __sched __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx, 1); + return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0, NULL, + _RET_IP_, ctx); } #endif -/* - * Spinlock based trylock, we take the spinlock and check whether we - * can get the lock: - */ -static inline int __mutex_trylock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); - unsigned long flags; - int prev; - - /* No need to trylock if the mutex is locked. */ - if (mutex_is_locked(lock)) - return 0; - - spin_lock_mutex(&lock->wait_lock, flags); - - prev = atomic_xchg_acquire(&lock->count, -1); - if (likely(prev == 1)) { - mutex_set_owner(lock); - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - } - - /* Set it back to 0 if there are no waiters: */ - if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); - - spin_unlock_mutex(&lock->wait_lock, flags); - - return prev == 1; -} - /** * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired @@ -903,52 +1174,45 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) */ int __sched mutex_trylock(struct mutex *lock) { - int ret; + bool locked = __mutex_trylock(lock); - ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); - if (ret) - mutex_set_owner(lock); + if (locked) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - return ret; + return locked; } EXPORT_SYMBOL(mutex_trylock); #ifndef CONFIG_DEBUG_LOCK_ALLOC int __sched -__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); + if (__mutex_trylock_fast(&lock->base)) { + if (ctx) + ww_mutex_set_context_fastpath(lock, ctx); + return 0; + } - if (likely(!ret)) { - ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_slowpath(lock, ctx); - return ret; + return __ww_mutex_lock_slowpath(lock, ctx); } -EXPORT_SYMBOL(__ww_mutex_lock); +EXPORT_SYMBOL(ww_mutex_lock); int __sched -__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); + if (__mutex_trylock_fast(&lock->base)) { + if (ctx) + ww_mutex_set_context_fastpath(lock, ctx); + return 0; + } - if (likely(!ret)) { - ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx); - return ret; + return __ww_mutex_lock_interruptible_slowpath(lock, ctx); } -EXPORT_SYMBOL(__ww_mutex_lock_interruptible); +EXPORT_SYMBOL(ww_mutex_lock_interruptible); #endif |