On Fri, May 22, 2020 at 05:17:05PM +0200, Sebastian A. Siewior wrote: > On 2020-05-22 16:57:07 [+0200], Peter Zijlstra wrote: > > > @@ -725,21 +735,48 @@ void lru_add_drain_all(void) > > > if (WARN_ON(!mm_percpu_wq)) > > > return; > > > > > > > > + this_gen = READ_ONCE(lru_drain_gen); > > > + smp_rmb(); > > > > this_gen = smp_load_acquire(&lru_drain_gen); > > > > > > mutex_lock(&lock); > > > > > > /* > > > + * (C) Exit the draining operation if a newer generation, from another > > > + * lru_add_drain_all(), was already scheduled for draining. Check (A). > > > */ > > > + if (unlikely(this_gen != lru_drain_gen)) > > > goto done; > > > > > > > > + WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); > > > + smp_wmb(); > > > > You can leave this smp_wmb() out and rely on the smp_mb() implied by > > queue_work_on()'s test_and_set_bit(). > > This is to avoid smp_store_release() ? store_release would have the barrier on the other end. If you read the comments (I so helpfully cut out) you'll see it wants to order against later stores, not ealier.
