Re: 答复: [RFC] locking/rwsem: Avoid issuing wakeup before setting the reader waiter to nil

On Fri, Nov 30, 2018 at 09:34:19AM +, Liu,Qi(ACU-T1) wrote: > Is there a semantic divergence between x86 instruction "LOCK cmpxchg" > and the macro cmpxchg defined in linux kernel? The former guarantee > full barrier in any case, and the latter only imply barrier in case of > success? > So, we

答复: [RFC] locking/rwsem: Avoid issuing wakeup before setting the reader waiter to nil

Is there a semantic divergence between x86 instruction "LOCK cmpxchg" and the macro cmpxchg defined in linux kernel? The former guarantee full barrier in any case, and the latter only imply barrier in case of success? So, we use smp_mb__before_atomic() cmpxchg_relaxed() // no b