kernel/smp.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/kernel/smp.c b/kernel/smp.c
index f38a1e692259..13a8e75e1379 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -19,7 +19,6 @@
 
 enum {
 	CSD_FLAG_LOCK		= 0x01,
-	CSD_FLAG_WAIT		= 0x02,
 };
 
 struct call_function_data {
@@ -114,26 +113,24 @@ static void csd_lock_wait(struct call_single_data *csd)
 static void csd_lock(struct call_single_data *csd)
 {
 	csd_lock_wait(csd);
-	csd->flags |= CSD_FLAG_LOCK;
+	csd->flags = CSD_FLAG_LOCK;
 
 	/*
 	 * prevent CPU from reordering the above assignment
 	 * to ->flags with any subsequent assignments to other
 	 * fields of the specified call_single_data structure:
 	 */
-	smp_mb();
+	smp_wmb();
 }
 
 static void csd_unlock(struct call_single_data *csd)
 {
-	WARN_ON((csd->flags & CSD_FLAG_WAIT) && !(csd->flags & CSD_FLAG_LOCK));
+	WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
 
 	/*
 	 * ensure we're all done before releasing data:
 	 */
-	smp_mb();
-
-	csd->flags &= ~CSD_FLAG_LOCK;
+	smp_store_release(&csd->flags, 0);
 }
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
@@ -173,9 +170,6 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	csd->func = func;
 	csd->info = info;
 
-	if (wait)
-		csd->flags |= CSD_FLAG_WAIT;
-
 	/*
 	 * The list addition should be visible before sending the IPI
 	 * handler locks the list to pull the entry off it because of