/Linux-v6.6/tools/testing/selftests/powerpc/dscr/ |
D | dscr_explicit_test.c | 55 sem_t semaphores[2]; in dscr_explicit_lockstep_test() local 56 sem_t *prev = &semaphores[1]; /* reversed prev/next than for the other thread */ in dscr_explicit_lockstep_test() 57 sem_t *next = &semaphores[0]; in dscr_explicit_lockstep_test() 68 FAIL_IF(pthread_create(&thread, NULL, dscr_explicit_lockstep_thread, (void *)semaphores)); in dscr_explicit_lockstep_test()
|
/Linux-v6.6/Documentation/locking/ |
D | percpu-rw-semaphore.rst | 2 Percpu rw semaphores 5 Percpu rw semaphores is a new read-write semaphore design that is 8 The problem with traditional read-write semaphores is that when multiple
|
D | locktypes.rst | 89 The aforementioned lock types except semaphores have strict owner 122 semaphores and PREEMPT_RT 126 semaphores have no concept of owners, thus preventing PREEMPT_RT from 127 providing priority inheritance for semaphores. After all, an unknown 128 owner cannot be boosted. As a consequence, blocking on semaphores can
|
D | mutex-design.rst | 16 behave similarly to binary semaphores, and were introduced in 2006[1] 73 number of workloads. Note that this technique is also used for rw-semaphores.
|
/Linux-v6.6/drivers/gpu/drm/radeon/ |
D | radeon_sync.c | 46 sync->semaphores[i] = NULL; in radeon_sync_create() 153 sync->semaphores[count++] = semaphore; in radeon_sync_rings() 203 radeon_semaphore_free(rdev, &sync->semaphores[i], fence); in radeon_sync_free()
|
D | radeon.h | 572 struct radeon_semaphore *semaphores[RADEON_NUM_SYNCS]; member
|
/Linux-v6.6/Documentation/translations/zh_CN/locking/ |
D | mutex-design.rst | 27 排斥”。互斥锁是一种睡眠锁,它的行为类似于二进制信号量(semaphores),在 72 改善一些工作负载的性能。注意,这种技术也被用于读写信号量(rw-semaphores)。
|
/Linux-v6.6/Documentation/translations/zh_CN/ |
D | glossary.rst | 34 * semaphores: 信号量。
|
/Linux-v6.6/Documentation/translations/zh_CN/infiniband/ |
D | core_locking.rst | 109 不能持有任何可能导致死锁的semaphores。
|
/Linux-v6.6/drivers/gpu/drm/i915/ |
D | i915_scheduler_types.h | 69 intel_engine_mask_t semaphores; member
|
D | i915_request.c | 658 if (request->sched.semaphores && in __i915_request_submit() 660 engine->saturated |= request->sched.semaphores; in __i915_request_submit() 737 if (request->sched.semaphores && __i915_request_has_started(request)) in __i915_request_unsubmit() 738 request->sched.semaphores = 0; in __i915_request_unsubmit() 1140 return rq->sched.semaphores | READ_ONCE(rq->engine->saturated); in already_busywaiting() 1240 to->sched.semaphores |= mask; in emit_semaphore_wait()
|
D | i915_scheduler.c | 308 node->semaphores = 0; in i915_sched_node_reinit()
|
D | Kconfig.profile | 132 interact with each other via userspace semaphores. Each context
|
/Linux-v6.6/drivers/media/pci/cx18/ |
D | cx18-scb.h | 231 u32 semaphores[8]; /* Semaphores */ member
|
/Linux-v6.6/Documentation/userspace-api/ |
D | futex2.rst | 10 performant synchronization mechanisms, such as mutexes, semaphores and
|
/Linux-v6.6/Documentation/scsi/ |
D | ChangeLog.ips | 26 4.80.14 - Take all semaphores off stack
|
/Linux-v6.6/Documentation/infiniband/ |
D | core_locking.rst | 108 semaphores that could cause deadlock if a consumer calls back into
|
/Linux-v6.6/Documentation/RCU/ |
D | rcuref.rst | 17 reader/writer spinlocks or semaphores are straightforward:
|
D | whatisRCU.rst | 486 - Use some solid design (such as locks or semaphores) to
|
/Linux-v6.6/Documentation/filesystems/ |
D | journalling.rst | 88 jbd2_journal_stop() as if they were semaphores and include them in
|
/Linux-v6.6/Documentation/scheduler/ |
D | completion.rst | 14 misuse of locks/semaphores and busy-loops. Any time you think of using
|
/Linux-v6.6/arch/arc/ |
D | Kconfig | 197 hardware semaphores, shared memory,....
|
/Linux-v6.6/Documentation/PCI/ |
D | pci-error-recovery.rst | 136 to complete; it can take semaphores, schedule, etc... everything but
|
/Linux-v6.6/Documentation/accel/qaic/ |
D | aic100.rst | 378 By using the semaphores in conjunction with the workload running on the NSPs,
|
/Linux-v6.6/Documentation/ |
D | memory-barriers.txt | 1994 (*) semaphores 1995 (*) R/W semaphores 2098 Locks and semaphores may not provide any guarantee of ordering on UP compiled
|