> On May 11, 2020, at 12:54 PM, Will Deacon <w...@kernel.org> wrote: > > Hmm, I don't see how it can remove the cmpxchg(). Do you have a link to that > discussion, please? lore.kernel.org/lkml/20200211124753.gp14...@hirez.programming.kicks-ass.net Correction — if compilers could prove ”prev->next != node” is always true, that cmpxchg() would not run. cpu_relax() should be sufficient to keep that “if statement” been optimized away in any case.
- Re: [PATCH -next v2] locking/osq_lock: annotate a data ra... Paul E. McKenney
- Re: [PATCH -next v2] locking/osq_lock: annotate a da... Will Deacon
- Re: [PATCH -next v2] locking/osq_lock: annotate ... Qian Cai
- Re: [PATCH -next v2] locking/osq_lock: annot... Will Deacon
- Re: [PATCH -next v2] locking/osq_lock: a... Qian Cai
- Re: [PATCH -next v2] locking/osq_lock: annotate ... Paul E. McKenney
- Re: [PATCH -next v2] locking/osq_lock: annot... Will Deacon
- Re: [PATCH -next v2] locking/osq_lock: a... Paul E. McKenney
- Re: [PATCH -next v2] locking/osq_lo... Will Deacon
- Re: [PATCH -next v2] locking/os... Paul E. McKenney