From 5710a3e09f9b85801e5ce70797a4a511e5fc9e2c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 7 Apr 2020 10:07:46 -0400 Subject: async: use explicit memory barriers When using C11 atomics, non-seqcst reads and writes do not participate in the total order of seqcst operations. In util/async.c and util/aio-posix.c, in particular, the pattern that we use write ctx->notify_me write bh->scheduled read bh->scheduled read ctx->notify_me if !bh->scheduled, sleep if ctx->notify_me, notify needs to use seqcst operations for both the write and the read. In general this is something that we do not want, because there can be many sources that are polled in addition to bottom halves. The alternative is to place a seqcst memory barrier between the write and the read. This also comes with a disadvantage, in that the memory barrier is implicit on strongly-ordered architectures and it wastes a few dozen clock cycles. Fortunately, ctx->notify_me is never written concurrently by two threads, so we can assert that and relax the writes to ctx->notify_me. The resulting solution works and performs well on both aarch64 and x86. Note that the atomic_set/atomic_read combination is not an atomic read-modify-write, and therefore it is even weaker than C11 ATOMIC_RELAXED; on x86, ATOMIC_RELAXED compiles to a locked operation. Analyzed-by: Ying Fang Signed-off-by: Paolo Bonzini Tested-by: Ying Fang Message-Id: <20200407140746.8041-6-pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi --- util/aio-win32.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'util/aio-win32.c') diff --git a/util/aio-win32.c b/util/aio-win32.c index a23b9c364d..729d533faf 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -321,6 +321,12 @@ bool aio_poll(AioContext *ctx, bool blocking) int count; int timeout; + /* + * There cannot be two concurrent aio_poll calls for the same AioContext (or + * an aio_poll concurrent with a GSource prepare/check/dispatch callback). + * We rely on this below to avoid slow locked accesses to ctx->notify_me. + */ + assert(in_aio_context_home_thread(ctx)); progress = false; /* aio_notify can avoid the expensive event_notifier_set if @@ -331,7 +337,13 @@ bool aio_poll(AioContext *ctx, bool blocking) * so disable the optimization now. */ if (blocking) { - atomic_add(&ctx->notify_me, 2); + atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) + 2); + /* + * Write ctx->notify_me before computing the timeout + * (reading bottom half flags, etc.). Pairs with + * smp_mb in aio_notify(). + */ + smp_mb(); } qemu_lockcnt_inc(&ctx->list_lock); @@ -364,8 +376,7 @@ bool aio_poll(AioContext *ctx, bool blocking) ret = WaitForMultipleObjects(count, events, FALSE, timeout); if (blocking) { assert(first); - assert(in_aio_context_home_thread(ctx)); - atomic_sub(&ctx->notify_me, 2); + atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2); aio_notify_accept(ctx); } -- cgit v1.2.3