ceph: fix improper use of smp_mb__before_atomic()

This barrier only applies to the read-modify-write operations; in
particular, it does not apply to the atomic64_set() primitive.

Replace the barrier with an smp_mb().

Fixes: fdd4e15838e59 ("ceph: rework dcache readdir")
Reported-by: "Paul E. McKenney" <paulmck@linux.ibm.com>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 7209548527ab018c2f315a99f4c861560c60bdbc..29ea4eba98fea8bebabbd3feecaf373005133990 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -545,7 +545,12 @@ static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
                                           long long release_count,
                                           long long ordered_count)
 {
-       smp_mb__before_atomic();
+       /*
+        * Makes sure operations that setup readdir cache (update page
+        * cache and i_size) are strongly ordered w.r.t. the following
+        * atomic64_set() operations.
+        */
+       smp_mb();
        atomic64_set(&ci->i_complete_seq[0], release_count);
        atomic64_set(&ci->i_complete_seq[1], ordered_count);
 }