From 79269ee3fa1da52f392f8a4ebf3082152c1c8c58 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 19 Apr 2017 14:30:37 -0700 Subject: doc/atomic_ops: Clarify smp_mb__{before,after}_atomic() This commit explicitly states that surrounding a non-value-returning atomic read-modify atomic operations provides full ordering, just as is provided by value-returning atomic read-modify-write operations. Signed-off-by: Paul E. McKenney --- Documentation/core-api/atomic_ops.rst | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'Documentation/core-api/atomic_ops.rst') diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst index 55e43f1c80de..fce929144ccd 100644 --- a/Documentation/core-api/atomic_ops.rst +++ b/Documentation/core-api/atomic_ops.rst @@ -303,6 +303,11 @@ defined which accomplish this:: void smp_mb__before_atomic(void); void smp_mb__after_atomic(void); +Preceding a non-value-returning read-modify-write atomic operation with +smp_mb__before_atomic() and following it with smp_mb__after_atomic() +provides the same full ordering that is provided by value-returning +read-modify-write atomic operations. + For example, smp_mb__before_atomic() can be used like so:: obj->dead = 1; -- cgit v1.2.3