cregit-Linux how code gets into the kernel

Release 4.7 kernel/locking/rwsem-xadd.c

Directory: kernel/locking
/* rwsem.c: R/W semaphores: contention handling functions
 *
 * Written by David Howells (dhowells@redhat.com).
 * Derived from arch/i386/kernel/semaphore.c
 *
 * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
 * and Michel Lespinasse <walken@google.com>
 *
 * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
 * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
 */
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/sched/rt.h>
#include <linux/osq_lock.h>

#include "rwsem.h"

/*
 * Guide to the rw_semaphore's count field for common values.
 * (32-bit case illustrated, similar for 64-bit)
 *
 * 0x0000000X   (1) X readers active or attempting lock, no writer waiting
 *                  X = #active_readers + #readers attempting to lock
 *                  (X*ACTIVE_BIAS)
 *
 * 0x00000000   rwsem is unlocked, and no one is waiting for the lock or
 *              attempting to read lock or write lock.
 *
 * 0xffff000X   (1) X readers active or attempting lock, with waiters for lock
 *                  X = #active readers + # readers attempting lock
 *                  (X*ACTIVE_BIAS + WAITING_BIAS)
 *              (2) 1 writer attempting lock, no waiters for lock
 *                  X-1 = #active readers + #readers attempting lock
 *                  ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
 *              (3) 1 writer active, no waiters for lock
 *                  X-1 = #active readers + #readers attempting lock
 *                  ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
 *
 * 0xffff0001   (1) 1 reader active or attempting lock, waiters for lock
 *                  (WAITING_BIAS + ACTIVE_BIAS)
 *              (2) 1 writer active or attempting lock, no waiters for lock
 *                  (ACTIVE_WRITE_BIAS)
 *
 * 0xffff0000   (1) There are writers or readers queued but none active
 *                  or in the process of attempting lock.
 *                  (WAITING_BIAS)
 *              Note: writer can attempt to steal lock for this count by adding
 *              ACTIVE_WRITE_BIAS in cmpxchg and checking the old count
 *
 * 0xfffe0001   (1) 1 writer active, or attempting lock. Waiters on queue.
 *                  (ACTIVE_WRITE_BIAS + WAITING_BIAS)
 *
 * Note: Readers attempt to lock by adding ACTIVE_BIAS in down_read and checking
 *       the count becomes more than 0 for successful lock acquisition,
 *       i.e. the case where there are only readers or nobody has lock.
 *       (1st and 2nd case above).
 *
 *       Writers attempt to lock by adding ACTIVE_WRITE_BIAS in down_write and
 *       checking the count becomes ACTIVE_WRITE_BIAS for successful lock
 *       acquisition (i.e. nobody else has lock or attempts lock).  If
 *       unsuccessful, in rwsem_down_write_failed, we'll check to see if there
 *       are only waiters but none active (5th case above), and attempt to
 *       steal the lock.
 *
 */

/*
 * Initialize an rwsem:
 */

void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key) { #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Make sure we are not reinitializing a held semaphore: */ debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif sem->count = RWSEM_UNLOCKED_VALUE; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER sem->owner = NULL; osq_lock_init(&sem->osq); #endif }

Contributors

PersonTokensPropCommitsCommitProp
ingo molnaringo molnar7477.08%114.29%
davidlohr buesodavidlohr bueso1515.62%228.57%
jason lowjason low44.17%228.57%
peter zijlstrapeter zijlstra22.08%114.29%
thomas gleixnerthomas gleixner11.04%114.29%
Total96100.00%7100.00%

EXPORT_SYMBOL(__init_rwsem); enum rwsem_waiter_type { RWSEM_WAITING_FOR_WRITE, RWSEM_WAITING_FOR_READ }; struct rwsem_waiter { struct list_head list; struct task_struct *task; enum rwsem_waiter_type type; }; enum rwsem_wake_type { RWSEM_WAKE_ANY, /* Wake whatever's at head of wait list */ RWSEM_WAKE_READERS, /* Wake readers only */ RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ }; /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then: * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) * - there must be someone on the queue * - the spinlock must be held by the caller * - woken process blocks are discarded from the list after having task zeroed * - writers are only woken if downgrading is false */
static struct rw_semaphore * __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) { struct rwsem_waiter *waiter; struct task_struct *tsk; struct list_head *next; long oldcount, woken, loop, adjustment; waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); if (waiter->type == RWSEM_WAITING_FOR_WRITE) { if (wake_type == RWSEM_WAKE_ANY) /* Wake writer at the front of the queue, but do not * grant it the lock yet as we want other writers * to be able to steal it. Readers, on the other hand, * will block as they will notice the queued writer. */ wake_up_process(waiter->task); goto out; } /* Writers might steal the lock before we grant it to the next reader. * We prefer to do the first reader grant before counting readers * so we can bail out early if a writer stole the lock. */ adjustment = 0; if (wake_type != RWSEM_WAKE_READ_OWNED) { adjustment = RWSEM_ACTIVE_READ_BIAS; try_reader_grant: oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { /* A writer stole the lock. Undo our reader grant. */ if (rwsem_atomic_update(-adjustment, sem) & RWSEM_ACTIVE_MASK) goto out; /* Last active locker left. Retry waking readers. */ goto try_reader_grant; } } /* Grant an infinite number of read locks to the readers at the front * of the queue. Note we increment the 'active part' of the count by * the number of readers before waking any processes up. */ woken = 0; do { woken++; if (waiter->list.next == &sem->wait_list) break; waiter = list_entry(waiter->list.next, struct rwsem_waiter, list); } while (waiter->type != RWSEM_WAITING_FOR_WRITE); adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; if (waiter->type != RWSEM_WAITING_FOR_WRITE) /* hit end of list above */ adjustment -= RWSEM_WAITING_BIAS; if (adjustment) rwsem_atomic_add(adjustment, sem); next = sem->wait_list.next; loop = woken; do { waiter = list_entry(next, struct rwsem_waiter, list); next = waiter->list.next; tsk = waiter->task; /* * Make sure we do not wakeup the next reader before * setting the nil condition to grant the next reader; * otherwise we could miss the wakeup on the other * side and end up sleeping again. See the pairing * in rwsem_down_read_failed(). */ smp_mb(); waiter->task = NULL; wake_up_process(tsk); put_task_struct(tsk); } while (--loop); sem->wait_list.next = next; next->prev = &sem->wait_list; out: return sem; }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds19662.03%426.67%
michel lespinassemichel lespinasse10934.49%746.67%
david howellsdavid howells72.22%16.67%
alex shialex shi20.63%16.67%
andrew mortonandrew morton10.32%16.67%
davidlohr buesodavidlohr bueso10.32%16.67%
Total316100.00%15100.00%

/* * Wait for the read lock to be granted */
__visible struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; struct rwsem_waiter waiter; struct task_struct *tsk = current; /* set up my own style of waitqueue */ waiter.task = tsk; waiter.type = RWSEM_WAITING_FOR_READ; get_task_struct(tsk); raw_spin_lock_irq(&sem->wait_lock); if (list_empty(&sem->wait_list)) adjustment += RWSEM_WAITING_BIAS; list_add_tail(&waiter.list, &sem->wait_list); /* we're now waiting on the lock, but no longer actively locking */ count = rwsem_atomic_update(adjustment, sem); /* If there are no active locks, wake the front queued process(es). * * If there are no writers and we are first in the queue, * wake our own waiter to join the existing active readers ! */ if (count == RWSEM_WAITING_BIAS || (count > RWSEM_WAITING_BIAS && adjustment != -RWSEM_ACTIVE_READ_BIAS)) sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); raw_spin_unlock_irq(&sem->wait_lock); /* wait to be given the lock */ while (true) { set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!waiter.task) break; schedule(); } __set_task_state(tsk, TASK_RUNNING); return sem; }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds8752.41%628.57%
michel lespinassemichel lespinasse6941.57%942.86%
davidlohr buesodavidlohr bueso63.61%29.52%
david howellsdavid howells10.60%14.76%
andi kleenandi kleen10.60%14.76%
thomas gleixnerthomas gleixner10.60%14.76%
livio soareslivio soares10.60%14.76%
Total166100.00%21100.00%

EXPORT_SYMBOL(rwsem_down_read_failed);
static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) { /* * Try acquiring the write lock. Check count first in order * to reduce unnecessary expensive cmpxchg() operations. */ if (count == RWSEM_WAITING_BIAS && cmpxchg_acquire(&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); rwsem_set_owner(sem); return true; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso4161.19%337.50%
michel lespinassemichel lespinasse1623.88%112.50%
linus torvaldslinus torvalds913.43%337.50%
jason lowjason low11.49%112.50%
Total67100.00%8100.00%

#ifdef CONFIG_RWSEM_SPIN_ON_OWNER /* * Try to acquire write lock before the writer has been put on wait queue. */
static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) { long old, count = READ_ONCE(sem->count); while (true) { if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; old = cmpxchg_acquire(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); if (old == count) { rwsem_set_owner(sem); return true; } count = old; } }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso5668.29%555.56%
michel lespinassemichel lespinasse2631.71%444.44%
Total82100.00%9100.00%


static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; bool ret = true; if (need_resched()) return false; rcu_read_lock(); owner = READ_ONCE(sem->owner); if (!owner) { long count = READ_ONCE(sem->count); /* * If sem->owner is not set, yet we have just recently entered the * slowpath with the lock being active, then there is a possibility * reader(s) may have the lock. To be safe, bail spinning in these * situations. */ if (count & RWSEM_ACTIVE_MASK) ret = false; goto done; } ret = owner->on_cpu; done: rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso8193.10%350.00%
michel lespinassemichel lespinasse44.60%116.67%
linus torvaldslinus torvalds11.15%116.67%
jason lowjason low11.15%116.67%
Total87100.00%6100.00%


static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) { long count; rcu_read_lock(); while (sem->owner == owner) { /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking sem->owner still matches owner, if that fails, * owner might point to free()d memory, if it still matches, * the rcu_read_lock() ensures the memory stays valid. */ barrier(); /* abort spinning when need_resched or owner is not running */ if (!owner->on_cpu || need_resched()) { rcu_read_unlock(); return false; } cpu_relax_lowlatency(); } rcu_read_unlock(); if (READ_ONCE(sem->owner)) return true; /* new owner, continue spinning */ /* * When the owner is not set, the lock could be free or * held by readers. Check the counter to verify the * state. */ count = READ_ONCE(sem->count); return (count == 0 || count == RWSEM_WAITING_BIAS); }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso8386.46%375.00%
jason lowjason low1313.54%125.00%
Total96100.00%4100.00%


static bool rwsem_optimistic_spin(struct rw_semaphore *sem) { struct task_struct *owner; bool taken = false; preempt_disable(); /* sem->wait_lock should not be held when doing optimistic spinning */ if (!rwsem_can_spin_on_owner(sem)) goto done; if (!osq_lock(&sem->osq)) goto done; while (true) { owner = READ_ONCE(sem->owner); if (owner && !rwsem_spin_on_owner(sem, owner)) break; /* wait_lock will be acquired if write_lock is obtained */ if (rwsem_try_write_lock_unqueued(sem)) { taken = true; 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. */ if (!owner && (need_resched() || rt_task(current))) 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(&sem->osq); done: preempt_enable(); return taken; }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso130100.00%3100.00%
Total130100.00%3100.00%

/* * Return true if the rwsem has active spinner */
static inline bool rwsem_has_spinner(struct rw_semaphore *sem) { return osq_is_locked(&sem->osq); }

Contributors

PersonTokensPropCommitsCommitProp
waiman longwaiman long21100.00%1100.00%
Total21100.00%1100.00%

#else
static bool rwsem_optimistic_spin(struct rw_semaphore *sem) { return false; }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso14100.00%1100.00%
Total14100.00%1100.00%


static inline bool rwsem_has_spinner(struct rw_semaphore *sem) { return false; }

Contributors

PersonTokensPropCommitsCommitProp
waiman longwaiman long15100.00%1100.00%
Total15100.00%1100.00%

#endif /* * Wait until we successfully acquire the write lock */
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); /* do optimistic spinning and steal lock if possible */ if (rwsem_optimistic_spin(sem)) return sem; /* * Optimistic spinning failed, proceed to the slowpath * and block until we can acquire the sem. */ waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; raw_spin_lock_irq(&sem->wait_lock); /* account for this before adding a new element to the list */ if (list_empty(&sem->wait_list)) waiting = false; list_add_tail(&waiter.list, &sem->wait_list); /* we're now waiting on the lock, but no longer actively locking */ if (waiting) { count = READ_ONCE(sem->count); /* * If there were already threads queued before us and there are * no active writers, the lock must be read owned; so we try to * wake any read locks that were queued ahead of us. */ if (count > RWSEM_WAITING_BIAS) sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); } else count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); /* wait until we successfully acquire the lock */ set_current_state(state); while (true) { if (rwsem_try_write_lock(count, sem)) break; raw_spin_unlock_irq(&sem->wait_lock); /* Block until there are no active lockers. */ do { if (signal_pending_state(state, current)) goto out_nolock; schedule(); 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 ERR_PTR(-EINTR); }

Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso17555.91%222.22%
peter zijlstrapeter zijlstra6520.77%111.11%
michel lespinassemichel lespinasse4313.74%444.44%
michal hockomichal hocko299.27%111.11%
andrew mortonandrew morton10.32%111.11%
Total313100.00%9100.00%


__visible struct rw_semaphore * __sched rwsem_down_write_failed(struct rw_semaphore *sem) { return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE); }

Contributors

PersonTokensPropCommitsCommitProp
michal hockomichal hocko1986.36%133.33%
linus torvaldslinus torvalds29.09%133.33%
michel lespinassemichel lespinasse14.55%133.33%
Total22100.00%3100.00%

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); }

Contributors

PersonTokensPropCommitsCommitProp
michal hockomichal hocko22100.00%1100.00%
Total22100.00%1100.00%

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 */
__visible struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the * unlock operation. * * spinning writer up_write/up_read caller * --------------- ----------------------- * [S] osq_unlock() [L] osq * MB RMB * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock) * * Here, it is important to make sure that there won't be a missed * wakeup while the rwsem is free and the only spinning writer goes * to sleep without taking the rwsem. Even when the spinning writer * is just going to break out of the waiting loop, it will still do * a trylock in rwsem_down_write_failed() before sleeping. IOW, if * rwsem_has_spinner() is true, it will guarantee at least one * trylock attempt on the rwsem later on. */ if (rwsem_has_spinner(sem)) { /* * The smp_rmb() here is to make sure that the spinner * state is consulted before reading the wait_lock. */ smp_rmb(); if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags)) return sem; goto locked; } raw_spin_lock_irqsave(&sem->wait_lock, flags); locked: /* do nothing if list empty */ if (!list_empty(&sem->wait_list)) sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return sem; }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds4850.00%333.33%
waiman longwaiman long3536.46%111.11%
david howellsdavid howells99.38%222.22%
thomas gleixnerthomas gleixner22.08%111.11%
andi kleenandi kleen11.04%111.11%
michel lespinassemichel lespinasse11.04%111.11%
Total96100.00%9100.00%

EXPORT_SYMBOL(rwsem_wake); /* * downgrade a write lock into a read lock * - caller incremented waiting part of count and discovered it still negative * - just wake up any readers at the front of the queue */
__visible struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) { unsigned long flags; raw_spin_lock_irqsave(&sem->wait_lock, flags); /* do nothing if list empty */ if (!list_empty(&sem->wait_list)) sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return sem; }

Contributors

PersonTokensPropCommitsCommitProp
david howellsdavid howells5793.44%240.00%
thomas gleixnerthomas gleixner23.28%120.00%
michel lespinassemichel lespinasse11.64%120.00%
andi kleenandi kleen11.64%120.00%
Total61100.00%5100.00%

EXPORT_SYMBOL(rwsem_downgrade_wake);

Overall Contributors

PersonTokensPropCommitsCommitProp
davidlohr buesodavidlohr bueso63737.23%1322.03%
linus torvaldslinus torvalds36621.39%610.17%
michel lespinassemichel lespinasse29517.24%1627.12%
ingo molnaringo molnar804.68%11.69%
david howellsdavid howells784.56%35.08%
michal hockomichal hocko754.38%11.69%
waiman longwaiman long724.21%11.69%
peter zijlstrapeter zijlstra673.92%23.39%
jason lowjason low191.11%58.47%
thomas gleixnerthomas gleixner60.35%11.69%
andrew mortonandrew morton50.29%35.08%
andi kleenandi kleen30.18%11.69%
alex shialex shi20.12%11.69%
nick pigginnick piggin20.12%11.69%
geert uytterhoevengeert uytterhoeven10.06%11.69%
tim chentim chen10.06%11.69%
livio soareslivio soares10.06%11.69%
paul gortmakerpaul gortmaker10.06%11.69%
Total1711100.00%59100.00%
Directory: kernel/locking
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
{% endraw %}