diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index b39eefb38d..54840f8622 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -81,6 +81,8 @@ extern AioWait global_aio_wait;
     AioContext *ctx_ = (ctx);                                      \
     /* Increment wait_->num_waiters before evaluating cond. */     \
     qatomic_inc(&wait_->num_waiters);                              \
+    /* Paired with smp_mb in aio_wait_kick(). */                   \
+    smp_mb();                                                      \
     if (ctx_ && in_aio_context_home_thread(ctx_)) {                \
         while ((cond)) {                                           \
             aio_poll(ctx_, true);                                  \
diff --git a/util/aio-wait.c b/util/aio-wait.c
index bdb3d3af22..98c5accd29 100644
--- a/util/aio-wait.c
+++ b/util/aio-wait.c
@@ -35,7 +35,21 @@ static void dummy_bh_cb(void *opaque)
 
 void aio_wait_kick(void)
 {
-    /* The barrier (or an atomic op) is in the caller.  */
+    /*
+     * Paired with smp_mb in AIO_WAIT_WHILE. Here we have:
+     * write(condition);
+     * aio_wait_kick() {
+     *      smp_mb();
+     *      read(num_waiters);
+     * }
+     *
+     * And in AIO_WAIT_WHILE:
+     * write(num_waiters);
+     * smp_mb();
+     * read(condition);
+     */
+    smp_mb();
+
     if (qatomic_read(&global_aio_wait.num_waiters)) {
         aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
     }