- 论坛徽章:
- 8
|
本帖最后由 firocu 于 2016-05-31 11:27 编辑
我来贴段gcc里面的实现, 可以看出来是没有差别的(FIXME):- int
- pthread_spin_lock (pthread_spinlock_t *lock)
- {
- /* atomic_exchange usually takes less instructions than
- atomic_compare_and_exchange. On the other hand,
- atomic_compare_and_exchange potentially generates less bus traffic
- when the lock is locked.
- We assume that the first try mostly will be successful, and we use
- atomic_exchange. For the subsequent tries we use
- atomic_compare_and_exchange. */
- if (atomic_exchange_acq (lock, 1) == 0)
- return 0;
- do
- {
- /* The lock is contended and we need to wait. Going straight back
- to cmpxchg is not a good idea on many targets as that will force
- expensive memory synchronizations among processors and penalize other
- running threads.
- On the other hand, we do want to update memory state on the local core
- once in a while to avoid spinning indefinitely until some event that
- will happen to update local memory as a side-effect. */
- if (SPIN_LOCK_READS_BETWEEN_CMPXCHG >= 0)
- {
- int wait = SPIN_LOCK_READS_BETWEEN_CMPXCHG;
- while (*lock != 0 && wait > 0)
- --wait;
- }
- else
- {
- while (*lock != 0)
- ;
- }
- }
- while (atomic_compare_and_exchange_val_acq (lock, 1, 0) != 0);
- return 0;
- }
复制代码 |
|