rcu: Avoid misordering in __call_rcu_nocb_enqueue()

The NOCB leader wakeup ordering depends on the store to the header
happening before the check for the leader already being awake.  However,
because atomic_long_add() does not return a value, it does not provide
ordering guarantees, the incorrect comment in wake_nocb_leader()
notwithstanding.  This commit therefore adds a smp_mb__after_atomic()
after the final atomic_long_add() to provide the needed ordering
guarantee.

Reported-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Paul Gortmaker <paul.gortmaker@windriver.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d5aec549558d..4ad63d861599 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2042,7 +2042,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
         if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
                 return;
         if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
-                /* Prior xchg orders against prior callback enqueue. */
+                /* Prior smp_mb__after_atomic() orders against prior enqueue. */
                 ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
                 wake_up(&rdp_leader->nocb_wq);
         }
@@ -2071,6 +2071,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
         ACCESS_ONCE(*old_rhpp) = rhp;
         atomic_long_add(rhcount, &rdp->nocb_q_count);
         atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
+        smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
 
         /* If we are not being polled and there is a kthread, awaken it ... */
         t = ACCESS_ONCE(rdp->nocb_kthread);