Lines Matching defs:sem_lock
189 * a) global sem_lock() for read/write
195 * b) global or semaphore sem_lock() for read/write:
203 * * global sem_lock() for write
204 * * either local or global sem_lock() for read.
224 * Initialization is done while holding sem_lock(), so no further barrier is
227 * smp_store_release() (for case a) and while holding sem_lock()
229 * The ACQUIRE when reading the result code without holding sem_lock() is
232 * Reading the result code while holding sem_lock() needs no further barriers,
233 * the locks inside sem_lock() enforce ordering (case b above)
236 * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock().
239 * when holding sem_lock(), no further barriers are required.
389 static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
501 sem_lock(sma, NULL, -1);
1379 sem_lock(sma, NULL, -1);
1438 sem_lock(sma, NULL, -1);
1535 sem_lock(sma, NULL, -1);
1626 sem_lock(sma, NULL, -1);
1631 sem_lock(sma, NULL, -1);
2073 locknum = sem_lock(sma, sops, nsops);
2080 * entangled here and why it's RMID race safe on comments at sem_lock()
2157 /* memory ordering ensured by the lock in sem_lock() */
2161 /* memory ordering is ensured by the lock in sem_lock() */
2176 * slowpath (aka after taking sem_lock), such that we can detect
2189 locknum = sem_lock(sma, sops, nsops);
2195 * No necessity for any barrier: We are protect by sem_lock()
2387 sem_lock(sma, NULL, -1);
2457 * The proc interface isn't aware of sem_lock(), it calls
2460 * In order to stay compatible with sem_lock(), we must