diff options
Diffstat (limited to 'kernel/locking')
| -rw-r--r-- | kernel/locking/lockdep.c | 191 | ||||
| -rw-r--r-- | kernel/locking/lockdep_proc.c | 2 | ||||
| -rw-r--r-- | kernel/locking/locktorture.c | 25 | ||||
| -rw-r--r-- | kernel/locking/mutex.c | 9 | ||||
| -rw-r--r-- | kernel/locking/percpu-rwsem.c | 1 | ||||
| -rw-r--r-- | kernel/locking/qspinlock.c | 60 | ||||
| -rw-r--r-- | kernel/locking/qspinlock_stat.h | 32 | ||||
| -rw-r--r-- | kernel/locking/rwsem-spinlock.c | 19 | ||||
| -rw-r--r-- | kernel/locking/rwsem-xadd.c | 38 | ||||
| -rw-r--r-- | kernel/locking/rwsem.c | 35 |
10 files changed, 364 insertions, 48 deletions
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 53ab2f85d77e..81f1a7107c0e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -45,6 +45,7 @@ #include <linux/bitops.h> #include <linux/gfp.h> #include <linux/kmemcheck.h> +#include <linux/random.h> #include <asm/sections.h> @@ -708,7 +709,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) * yet. Otherwise we look it up. We cache the result in the lock object * itself, so actual lookup of the hash should be once per lock object. */ -static inline struct lock_class * +static struct lock_class * register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) { struct lockdep_subclass_key *key; @@ -1999,6 +2000,79 @@ static inline int get_first_held_lock(struct task_struct *curr, return ++i; } +#ifdef CONFIG_DEBUG_LOCKDEP +/* + * Returns the next chain_key iteration + */ +static u64 print_chain_key_iteration(int class_idx, u64 chain_key) +{ + u64 new_chain_key = iterate_chain_key(chain_key, class_idx); + + printk(" class_idx:%d -> chain_key:%016Lx", + class_idx, + (unsigned long long)new_chain_key); + return new_chain_key; +} + +static void +print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_next) +{ + struct held_lock *hlock; + u64 chain_key = 0; + int depth = curr->lockdep_depth; + int i; + + printk("depth: %u\n", depth + 1); + for (i = get_first_held_lock(curr, hlock_next); i < depth; i++) { + hlock = curr->held_locks + i; + chain_key = print_chain_key_iteration(hlock->class_idx, chain_key); + + print_lock(hlock); + } + + print_chain_key_iteration(hlock_next->class_idx, chain_key); + print_lock(hlock_next); +} + +static void print_chain_keys_chain(struct lock_chain *chain) +{ + int i; + u64 chain_key = 0; + int class_id; + + printk("depth: %u\n", chain->depth); + for (i = 0; i < chain->depth; i++) { + class_id = chain_hlocks[chain->base + i]; + chain_key = print_chain_key_iteration(class_id + 1, chain_key); + + print_lock_name(lock_classes + class_id); + printk("\n"); + } +} + +static void print_collision(struct task_struct *curr, + struct held_lock *hlock_next, + struct lock_chain *chain) +{ + printk("\n"); + printk("======================\n"); + printk("[chain_key collision ]\n"); + print_kernel_ident(); + printk("----------------------\n"); + printk("%s/%d: ", current->comm, task_pid_nr(current)); + printk("Hash chain already cached but the contents don't match!\n"); + + printk("Held locks:"); + print_chain_keys_held_locks(curr, hlock_next); + + printk("Locks in cached chain:"); + print_chain_keys_chain(chain); + + printk("\nstack backtrace:\n"); + dump_stack(); +} +#endif + /* * Checks whether the chain and the current held locks are consistent * in depth and also in content. If they are not it most likely means @@ -2014,14 +2088,18 @@ static int check_no_collision(struct task_struct *curr, i = get_first_held_lock(curr, hlock); - if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) { + print_collision(curr, hlock, chain); return 0; + } for (j = 0; j < chain->depth - 1; j++, i++) { id = curr->held_locks[i].class_idx - 1; - if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) { + print_collision(curr, hlock, chain); return 0; + } } #endif return 1; @@ -2099,15 +2177,37 @@ cache_hit: chain->irq_context = hlock->irq_context; i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; + + BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks)); + BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks)); + BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes)); + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; - nr_chain_hlocks += chain->depth; for (j = 0; j < chain->depth - 1; j++, i++) { int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; } chain_hlocks[chain->base + j] = class - lock_classes; } + + if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS) + nr_chain_hlocks += chain->depth; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * Important for check_no_collision(). + */ + if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) { + if (debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); + dump_stack(); + return 0; + } +#endif + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); @@ -2855,6 +2955,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 2 * !!task->hardirq_context + !!task->softirq_context; +} + static int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -2863,8 +2968,6 @@ static int separate_irq_context(struct task_struct *curr, /* * Keep track of points where we cross into an interrupt context: */ - hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + - curr->softirq_context; if (depth) { struct held_lock *prev_hlock; @@ -2896,6 +2999,11 @@ static inline int mark_irqflags(struct task_struct *curr, return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 0; +} + static inline int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -3164,6 +3272,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->acquire_ip = ip; hlock->instance = lock; hlock->nest_lock = nest_lock; + hlock->irq_context = task_irq_context(curr); hlock->trylock = trylock; hlock->read = read; hlock->check = check; @@ -3477,7 +3586,35 @@ static int __lock_is_held(struct lockdep_map *lock) return 0; } -static void __lock_pin_lock(struct lockdep_map *lock) +static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock) +{ + struct pin_cookie cookie = NIL_COOKIE; + struct task_struct *curr = current; + int i; + + if (unlikely(!debug_locks)) + return cookie; + + for (i = 0; i < curr->lockdep_depth; i++) { + struct held_lock *hlock = curr->held_locks + i; + + if (match_held_lock(hlock, lock)) { + /* + * Grab 16bits of randomness; this is sufficient to not + * be guessable and still allows some pin nesting in + * our u32 pin_count. + */ + cookie.val = 1 + (prandom_u32() >> 16); + hlock->pin_count += cookie.val; + return cookie; + } + } + + WARN(1, "pinning an unheld lock\n"); + return cookie; +} + +static void __lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { struct task_struct *curr = current; int i; @@ -3489,7 +3626,7 @@ static void __lock_pin_lock(struct lockdep_map *lock) struct held_lock *hlock = curr->held_locks + i; if (match_held_lock(hlock, lock)) { - hlock->pin_count++; + hlock->pin_count += cookie.val; return; } } @@ -3497,7 +3634,7 @@ static void __lock_pin_lock(struct lockdep_map *lock) WARN(1, "pinning an unheld lock\n"); } -static void __lock_unpin_lock(struct lockdep_map *lock) +static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { struct task_struct *curr = current; int i; @@ -3512,7 +3649,11 @@ static void __lock_unpin_lock(struct lockdep_map *lock) if (WARN(!hlock->pin_count, "unpinning an unpinned lock\n")) return; - hlock->pin_count--; + hlock->pin_count -= cookie.val; + + if (WARN((int)hlock->pin_count < 0, "pin count corrupted\n")) + hlock->pin_count = 0; + return; } } @@ -3643,24 +3784,44 @@ int lock_is_held(struct lockdep_map *lock) } EXPORT_SYMBOL_GPL(lock_is_held); -void lock_pin_lock(struct lockdep_map *lock) +struct pin_cookie lock_pin_lock(struct lockdep_map *lock) { + struct pin_cookie cookie = NIL_COOKIE; unsigned long flags; if (unlikely(current->lockdep_recursion)) - return; + return cookie; raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; - __lock_pin_lock(lock); + cookie = __lock_pin_lock(lock); current->lockdep_recursion = 0; raw_local_irq_restore(flags); + + return cookie; } EXPORT_SYMBOL_GPL(lock_pin_lock); -void lock_unpin_lock(struct lockdep_map *lock) +void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + + current->lockdep_recursion = 1; + __lock_repin_lock(lock, cookie); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_repin_lock); + +void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { unsigned long flags; @@ -3671,7 +3832,7 @@ void lock_unpin_lock(struct lockdep_map *lock) check_flags(flags); current->lockdep_recursion = 1; - __lock_unpin_lock(lock); + __lock_unpin_lock(lock, cookie); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dbb61a302548..a0f61effad25 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v) int i; if (v == SEQ_START_TOKEN) { + if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS) + seq_printf(m, "(buggered) "); seq_printf(m, "all lock chains:\n"); return 0; } diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8ef1919d63b2..f8c5af52a131 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -75,12 +75,7 @@ struct lock_stress_stats { long n_lock_acquired; }; -#if defined(MODULE) -#define LOCKTORTURE_RUNNABLE_INIT 1 -#else -#define LOCKTORTURE_RUNNABLE_INIT 0 -#endif -int torture_runnable = LOCKTORTURE_RUNNABLE_INIT; +int torture_runnable = IS_ENABLED(MODULE); module_param(torture_runnable, int, 0444); MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init"); @@ -394,12 +389,12 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp) if (!rt_task(current)) { /* - * (1) Boost priority once every ~50k operations. When the + * Boost priority once every ~50k operations. When the * task tries to take the lock, the rtmutex it will account * for the new priority, and do any corresponding pi-dance. */ - if (!(torture_random(trsp) % - (cxt.nrealwriters_stress * factor))) { + if (trsp && !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor))) { policy = SCHED_FIFO; param.sched_priority = MAX_RT_PRIO - 1; } else /* common case, do nothing */ @@ -748,6 +743,15 @@ static void lock_torture_cleanup(void) if (torture_cleanup_begin()) return; + /* + * Indicates early cleanup, meaning that the test has not run, + * such as when passing bogus args when loading the module. As + * such, only perform the underlying torture-specific cleanups, + * and avoid anything related to locktorture. + */ + if (!cxt.lwsa) + goto end; + if (writer_tasks) { for (i = 0; i < cxt.nrealwriters_stress; i++) torture_stop_kthread(lock_torture_writer, @@ -776,6 +780,7 @@ static void lock_torture_cleanup(void) else lock_torture_print_module_parms(cxt.cur_ops, "End of test: SUCCESS"); +end: torture_cleanup_end(); } @@ -870,6 +875,7 @@ static int __init lock_torture_init(void) VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory"); firsterr = -ENOMEM; kfree(cxt.lwsa); + cxt.lwsa = NULL; goto unwind; } @@ -878,6 +884,7 @@ static int __init lock_torture_init(void) cxt.lrsa[i].n_lock_acquired = 0; } } + lock_torture_print_module_parms(cxt.cur_ops, "Start of test"); /* Prepare torture context. */ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index e364b424b019..79d2d765a75f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) if (!hold_ctx) return 0; - if (unlikely(ctx == hold_ctx)) - return -EALREADY; - if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { #ifdef CONFIG_DEBUG_MUTEXES @@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, unsigned long flags; int ret; + if (use_ww_ctx) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) + return -EALREADY; + } + preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index f231e0bb311c..bec0b647f9cc 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -37,6 +37,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw) free_percpu(brw->fast_read_ctr); brw->fast_read_ctr = NULL; /* catch use after free bugs */ } +EXPORT_SYMBOL_GPL(percpu_free_rwsem); /* * This is the fast-path for down_read/up_read. If it succeeds we rely diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index ce2f75e32ae1..5fc8c311b8fe 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -267,6 +267,66 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock, #define queued_spin_lock_slowpath native_queued_spin_lock_slowpath #endif +/* + * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before + * issuing an _unordered_ store to set _Q_LOCKED_VAL. + * + * This means that the store can be delayed, but no later than the + * store-release from the unlock. This means that simply observing + * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired. + * + * There are two paths that can issue the unordered store: + * + * (1) clear_pending_set_locked(): *,1,0 -> *,0,1 + * + * (2) set_locked(): t,0,0 -> t,0,1 ; t != 0 + * atomic_cmpxchg_relaxed(): t,0,0 -> 0,0,1 + * + * However, in both cases we have other !0 state we've set before to queue + * ourseves: + * + * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our + * load is constrained by that ACQUIRE to not pass before that, and thus must + * observe the store. + * + * For (2) we have a more intersting scenario. We enqueue ourselves using + * xchg_tail(), which ends up being a RELEASE. This in itself is not + * sufficient, however that is followed by an smp_cond_acquire() on the same + * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and + * guarantees we must observe that store. + * + * Therefore both cases have other !0 state that is observable before the + * unordered locked byte store comes through. This means we can use that to + * wait for the lock store, and then wait for an unlock. + */ +#ifndef queued_spin_unlock_wait +void queued_spin_unlock_wait(struct qspinlock *lock) +{ + u32 val; + + for (;;) { + val = atomic_read(&lock->val); + + if (!val) /* not locked, we're done */ + goto done; + + if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */ + break; + + /* not locked, but pending, wait until we observe the lock */ + cpu_relax(); + } + + /* any unlock is good */ + while (atomic_read(&lock->val) & _Q_LOCKED_MASK) + cpu_relax(); + +done: + smp_rmb(); /* CTRL + RMB -> ACQUIRE */ +} +EXPORT_SYMBOL(queued_spin_unlock_wait); +#endif + #endif /* _GEN_PV_LOCK_SLOWPATH */ /** diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index eb2a2c9bc3fc..22e025309845 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -136,10 +136,12 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, } if (counter == qstat_pv_hash_hops) { - u64 frac; + u64 frac = 0; - frac = 100ULL * do_div(stat, kicks); - frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); + if (kicks) { + frac = 100ULL * do_div(stat, kicks); + frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); + } /* * Return a X.XX decimal number @@ -189,8 +191,6 @@ static ssize_t qstat_write(struct file *file, const char __user *user_buf, for (i = 0 ; i < qstat_num; i++) WRITE_ONCE(ptr[i], 0); - for (i = 0 ; i < qstat_num; i++) - WRITE_ONCE(ptr[i], 0); } return count; } @@ -212,10 +212,8 @@ static int __init init_qspinlock_stat(void) struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL); int i; - if (!d_qstat) { - pr_warn("Could not create 'qlockstat' debugfs directory\n"); - return 0; - } + if (!d_qstat) + goto out; /* * Create the debugfs files @@ -225,12 +223,20 @@ static int __init init_qspinlock_stat(void) * performance. */ for (i = 0; i < qstat_num; i++) - debugfs_create_file(qstat_names[i], 0400, d_qstat, - (void *)(long)i, &fops_qstat); + if (!debugfs_create_file(qstat_names[i], 0400, d_qstat, + (void *)(long)i, &fops_qstat)) + goto fail_undo; + + if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, + (void *)(long)qstat_reset_cnts, &fops_qstat)) + goto fail_undo; - debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, - (void *)(long)qstat_reset_cnts, &fops_qstat); return 0; +fail_undo: + debugfs_remove_recursive(d_qstat); +out: + pr_warn("Could not create 'qlockstat' debugfs entries\n"); + return -ENOMEM; } fs_initcall(init_qspinlock_stat); diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 3a5048572065..1591f6b3539f 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -191,11 +191,12 @@ int __down_read_trylock(struct rw_semaphore *sem) /* * get a write lock on the semaphore */ -void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) +int __sched __down_write_common(struct rw_semaphore *sem, int state) { struct rwsem_waiter waiter; struct task_struct *tsk; unsigned long flags; + int ret = 0; raw_spin_lock_irqsave(&sem->wait_lock, flags); @@ -215,21 +216,33 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) */ if (sem->count == 0) break; - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (signal_pending_state(state, current)) { + ret = -EINTR; + goto out; + } + set_task_state(tsk, state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); raw_spin_lock_irqsave(&sem->wait_lock, flags); } /* got the lock */ sem->count = -1; +out: list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; } void __sched __down_write(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + __down_write_common(sem, TASK_UNINTERRUPTIBLE); +} + +int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return __down_write_common(sem, TASK_KILLABLE); } /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index a4d4de05b2d1..09e30c6225e5 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -433,12 +433,13 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem) /* * Wait until we successfully acquire the write lock */ -__visible -struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) +static inline struct rw_semaphore * +__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) { long count; bool waiting = true; /* any queued threads before us */ struct rwsem_waiter waiter; + struct rw_semaphore *ret = sem; /* undo write bias from down_write operation, stop active locking */ count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem); @@ -478,7 +479,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); /* wait until we successfully acquire the lock */ - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(state); while (true) { if (rwsem_try_write_lock(count, sem)) break; @@ -486,21 +487,48 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) /* Block until there are no active lockers. */ do { + if (signal_pending_state(state, current)) + goto out_nolock; + schedule(); - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(state); } while ((count = sem->count) & RWSEM_ACTIVE_MASK); raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); + list_del(&waiter.list); + raw_spin_unlock_irq(&sem->wait_lock); + return ret; + +out_nolock: + __set_current_state(TASK_RUNNING); + raw_spin_lock_irq(&sem->wait_lock); list_del(&waiter.list); + if (list_empty(&sem->wait_list)) + rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem); + else + __rwsem_do_wake(sem, RWSEM_WAKE_ANY); raw_spin_unlock_irq(&sem->wait_lock); - return sem; + return ERR_PTR(-EINTR); +} + +__visible struct rw_semaphore * __sched +rwsem_down_write_failed(struct rw_semaphore *sem) +{ + return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(rwsem_down_write_failed); +__visible struct rw_semaphore * __sched +rwsem_down_write_failed_killable(struct rw_semaphore *sem) +{ + return __rwsem_down_write_failed_common(sem, TASK_KILLABLE); +} +EXPORT_SYMBOL(rwsem_down_write_failed_killable); + /* * handle waking up a waiter on the semaphore * - up_read/up_write has decremented the active part of count if we come here diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 205be0ce34de..2e853ad93a3a 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -55,6 +55,25 @@ void __sched down_write(struct rw_semaphore *sem) EXPORT_SYMBOL(down_write); /* + * lock for writing + */ +int __sched down_write_killable(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + + if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) { + rwsem_release(&sem->dep_map, 1, _RET_IP_); + return -EINTR; + } + + rwsem_set_owner(sem); + return 0; +} + +EXPORT_SYMBOL(down_write_killable); + +/* * trylock for writing -- returns 1 if successful, 0 if contention */ int down_write_trylock(struct rw_semaphore *sem) @@ -154,6 +173,22 @@ void down_write_nested(struct rw_semaphore *sem, int subclass) EXPORT_SYMBOL(down_write_nested); +int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); + + if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) { + rwsem_release(&sem->dep_map, 1, _RET_IP_); + return -EINTR; + } + + rwsem_set_owner(sem); + return 0; +} + +EXPORT_SYMBOL(down_write_killable_nested); + void up_read_non_owner(struct rw_semaphore *sem) { __up_read(sem); |
