Fix possible VDEV stats array overflow

Fix a possible VDEV statistics array overflow when ZIOs with ZIO_PRIORITY_NOW complete. Signed-off-by: Tony Hutter <[email protected]> Signed-off-by: Chunwei Chen <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Issue openzfs#4883 Closes openzfs#4917
chenhaiq · Aug 2, 2016 · 4eb0db4 · 4eb0db4
1 parent e24e62a
commit 4eb0db4
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c
@@ -2982,7 +2982,8 @@ vdev_stat_update(zio_t *zio, uint64_t psize)
 		 * The bytes/ops/histograms are recorded at the leaf level and
 		 * aggregated into the higher level vdevs in vdev_get_stats().
 		 */
-		if (vd->vdev_ops->vdev_op_leaf) {
+		if (vd->vdev_ops->vdev_op_leaf &&
+		    (zio->io_priority < ZIO_PRIORITY_NUM_QUEUEABLE)) {
 
 			vs->vs_ops[type]++;
 			vs->vs_bytes[type] += psize;