futex: Check value after qemu_futex_wait()

futex(2) - Linux manual page
https://man7.org/linux/man-pages/man2/futex.2.html
> Note that a wake-up can also be caused by common futex usage patterns
> in unrelated code that happened to have previously used the futex
> word's memory location (e.g., typical futex-based implementations of
> Pthreads mutexes can cause this under some conditions).  Therefore,
> callers should always conservatively assume that a return value of 0
> can mean a spurious wake-up, and use the futex word's value (i.e.,
> the user-space synchronization scheme) to decide whether to continue
> to block or not.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Link: https://lore.kernel.org/r/20250529-event-v5-1-53b285203794@daynix.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 24 insertions, 13 deletions

diff --git a/include/qemu/futex.h b/include/qemu/futex.h
index 91ae889..f577740 100644
--- a/include/qemu/futex.h
+++ b/include/qemu/futex.h
@@ -24,6 +24,15 @@ static inline void qemu_futex_wake(void *f, int n)
     qemu_futex(f, FUTEX_WAKE, n, NULL, NULL, 0);
 }
 
+/*
+ * Note that a wake-up can also be caused by common futex usage patterns in
+ * unrelated code that happened to have previously used the futex word's
+ * memory location (e.g., typical futex-based implementations of Pthreads
+ * mutexes can cause this under some conditions).  Therefore, callers should
+ * always conservatively assume that it is a spurious wake-up, and use the futex
+ * word's value (i.e., the user-space synchronization scheme) to decide whether
+ * to continue to block or not.
+ */
 static inline void qemu_futex_wait(void *f, unsigned val)
 {
     while (qemu_futex(f, FUTEX_WAIT, (int) val, NULL, NULL, 0)) {
diff --git a/tests/unit/test-aio-multithread.c b/tests/unit/test-aio-multithread.c
index 08d4570..8c2e415 100644
--- a/tests/unit/test-aio-multithread.c
+++ b/tests/unit/test-aio-multithread.c
@@ -305,7 +305,9 @@ static void mcs_mutex_lock(void)
     prev = qatomic_xchg(&mutex_head, id);
     if (prev != -1) {
         qatomic_set(&nodes[prev].next, id);
-        qemu_futex_wait(&nodes[id].locked, 1);
+        while (qatomic_read(&nodes[id].locked) == 1) {
+            qemu_futex_wait(&nodes[id].locked, 1);
+        }
     }
 }
 
diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c
index b2e26e2..f81fca5 100644
--- a/util/qemu-thread-posix.c
+++ b/util/qemu-thread-posix.c
@@ -428,17 +428,17 @@ void qemu_event_wait(QemuEvent *ev)
 
     assert(ev->initialized);
 
-    /*
-     * qemu_event_wait must synchronize with qemu_event_set even if it does
-     * not go down the slow path, so this load-acquire is needed that
-     * synchronizes with the first memory barrier in qemu_event_set().
-     *
-     * If we do go down the slow path, there is no requirement at all: we
-     * might miss a qemu_event_set() here but ultimately the memory barrier in
-     * qemu_futex_wait() will ensure the check is done correctly.
-     */
-    value = qatomic_load_acquire(&ev->value);
-    if (value != EV_SET) {
+    while (true) {
+        /*
+         * qemu_event_wait must synchronize with qemu_event_set even if it does
+         * not go down the slow path, so this load-acquire is needed that
+         * synchronizes with the first memory barrier in qemu_event_set().
+         */
+        value = qatomic_load_acquire(&ev->value);
+        if (value == EV_SET) {
+            break;
+        }
+
         if (value == EV_FREE) {
             /*
              * Leave the event reset and tell qemu_event_set that there are
@@ -452,7 +452,7 @@ void qemu_event_wait(QemuEvent *ev)
              * like the load above.
              */
             if (qatomic_cmpxchg(&ev->value, EV_FREE, EV_BUSY) == EV_SET) {
-                return;
+                break;
             }
         }