rcu: make memory barriers more explicit

Prepare for introducing smp_mb_placeholder() and smp_mb_global().
The new smp_mb() in synchronize_rcu() is not strictly necessary, since
the first atomic_mb_set for rcu_gp_ctr provides the required ordering.
However, synchronize_rcu is not performance critical, and it *will* be
necessary to introduce a smp_mb_global before calling wait_for_readers().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

include/qemu/rcu.h

@@ -79,7 +79,10 @@ static inline void rcu_read_lock(void)
     }
 
     ctr = atomic_read(&rcu_gp_ctr);
-    atomic_xchg(&p_rcu_reader->ctr, ctr);
+    atomic_set(&p_rcu_reader->ctr, ctr);
+
+    /* Write p_rcu_reader->ctr before reading RCU-protected pointers.  */
+    smp_mb();
 }
 
 static inline void rcu_read_unlock(void)
@@ -91,7 +94,15 @@ static inline void rcu_read_unlock(void)
         return;
     }
 
-    atomic_xchg(&p_rcu_reader->ctr, 0);
+    /* Ensure that the critical section is seen to precede the
+     * store to p_rcu_reader->ctr.  Together with the following
+     * smp_mb(), this ensures writes to p_rcu_reader->ctr
+     * are sequentially consistent.
+     */
+    atomic_store_release(&p_rcu_reader->ctr, 0);
+
+    /* Write p_rcu_reader->ctr before reading p_rcu_reader->waiting.  */
+    smp_mb();
     if (unlikely(atomic_read(&p_rcu_reader->waiting))) {
         atomic_set(&p_rcu_reader->waiting, false);
         qemu_event_set(&rcu_gp_event);

util/rcu.c

@@ -92,8 +92,9 @@ static void wait_for_readers(void)
             atomic_set(&index->waiting, true);
         }
 
-        /* Here, order the stores to index->waiting before the
-         * loads of index->ctr.
+        /* Here, order the stores to index->waiting before the loads of
+         * index->ctr.  Pairs with smp_mb() in rcu_read_unlock(),
+         * ensuring that the loads of index->ctr are sequentially consistent.
          */
         smp_mb();
 
@@ -142,8 +143,13 @@ static void wait_for_readers(void)
 void synchronize_rcu(void)
 {
     qemu_mutex_lock(&rcu_sync_lock);
-    qemu_mutex_lock(&rcu_registry_lock);
 
+    /* Write RCU-protected pointers before reading p_rcu_reader->ctr.
+     * Pairs with smp_mb() in rcu_read_lock().
+     */
+    smp_mb();
+
+    qemu_mutex_lock(&rcu_registry_lock);
     if (!QLIST_EMPTY(&registry)) {
         /* In either case, the atomic_mb_set below blocks stores that free
          * old RCU-protected pointers.