在sem_post（sem_t * sem）和sem_wait（sem_t * sem）周围是否有完整的内存屏障？ [英] Is there a full memory barrier around sem_post(sem_t * sem) and sem_wait(sem_t * sem)?

问题描述

在linux代码中，
我记得在mutex_lock（）周围有一个完整的内存屏障。
我想确认它是否在sem_xxx周围。

In linux code, I remember hearing there is a full memory barrier around mutex_lock(). I want to make sure whether it is around sem_xxx also.

推荐答案

是的，它使用原子递增/递减在无争议的情况下，当然有一个膜。对于有争议的情况，有一个系统调用futex，它也有一个membar。

Yes, it uses an atomic increment/decrement in the uncontended case, which of course has a membar. For the contended case there is a system call to futex, which also has a membar.

这篇关于在sem_post（sem_t * sem）和sem_wait（sem_t * sem）周围是否有完整的内存屏障？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！