sched: correctly place paranioa memory barriers in synchronize_sched_expedited()

The memory barriers must be in the SMP case, not in the !SMP case.
Also add a barrier after the atomic_inc() in order to ensure that
other CPUs see post-synchronize_sched_expedited() actions as following
the expedited grace period.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/sched.c b/kernel/sched.c
index e9c6d798831a28c365b61c881b1dabdca488d7de..155a16d5214627cbb6c5ed45b041766284bdda77 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8931,6 +8931,15 @@ struct cgroup_subsys cpuacct_subsys = {
 #ifndef CONFIG_SMP
 
 void synchronize_sched_expedited(void)
+{
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
+
+static int synchronize_sched_expedited_cpu_stop(void *data)
 {
        /*
         * There must be a full memory barrier on each affected CPU
@@ -8943,16 +8952,7 @@ void synchronize_sched_expedited(void)
         * necessary.  Do smp_mb() anyway for documentation and
         * robustness against future implementation changes.
         */
-       smp_mb();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#else /* #ifndef CONFIG_SMP */
-
-static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
-
-static int synchronize_sched_expedited_cpu_stop(void *data)
-{
+       smp_mb(); /* See above comment block. */
        return 0;
 }
 
@@ -8990,6 +8990,7 @@ void synchronize_sched_expedited(void)
                get_online_cpus();
        }
        atomic_inc(&synchronize_sched_expedited_count);
+       smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
        put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);