diff --git a/util/aio-posix.c b/util/aio-posix.c
index cd6cf0a..c3613d2 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -559,6 +559,11 @@
     int64_t timeout;
     int64_t start = 0;
 
+    /*
+     * 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));
 
     /* aio_notify can avoid the expensive event_notifier_set if
@@ -569,7 +574,13 @@
      * 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);
@@ -590,7 +601,8 @@
     }
 
     if (blocking) {
-        atomic_sub(&ctx->notify_me, 2);
+        /* Finish the poll before clearing the flag.  */
+        atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2);
         aio_notify_accept(ctx);
     }
 
diff --git a/util/aio-win32.c b/util/aio-win32.c
index a23b9c3..729d533 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -321,6 +321,12 @@
     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 @@
      * 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 @@
         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);
         }
 
diff --git a/util/async.c b/util/async.c
index b94518b..3165a28 100644
--- a/util/async.c
+++ b/util/async.c
@@ -249,7 +249,14 @@
 {
     AioContext *ctx = (AioContext *) source;
 
-    atomic_or(&ctx->notify_me, 1);
+    atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) | 1);
+
+    /*
+     * Write ctx->notify_me before computing the timeout
+     * (reading bottom half flags, etc.).  Pairs with
+     * smp_mb in aio_notify().
+     */
+    smp_mb();
 
     /* We assume there is no timeout already supplied */
     *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
@@ -268,7 +275,8 @@
     QEMUBH *bh;
     BHListSlice *s;
 
-    atomic_and(&ctx->notify_me, ~1);
+    /* Finish computing the timeout before clearing the flag.  */
+    atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) & ~1);
     aio_notify_accept(ctx);
 
     QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) {
@@ -411,10 +419,10 @@
 void aio_notify(AioContext *ctx)
 {
     /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
-     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
+     * with smp_mb in aio_ctx_prepare or aio_poll.
      */
     smp_mb();
-    if (ctx->notify_me) {
+    if (atomic_read(&ctx->notify_me)) {
         event_notifier_set(&ctx->notifier);
         atomic_mb_set(&ctx->notified, true);
     }