raid5: check faulty flag for array status during recovery.

When we have more than 1 drive failure, it's possible we start
rebuild one drive while leaving another faulty drive in array.
To determine whether array will be optimal after building, current
code only check whether a drive is missing, which could potentially
lead to data corruption. This patch is to add checking Faulty flag.

Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e75d48c0421a41788c9159ef7e74d22ad93d9695..cd2f96b2c57263628ef0816af3b114ad9437b740 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5121,12 +5121,17 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
                schedule_timeout_uninterruptible(1);
        }
        /* Need to check if array will still be degraded after recovery/resync
-        * We don't need to check the 'failed' flag as when that gets set,
-        * recovery aborts.
+        * Note in case of > 1 drive failures it's possible we're rebuilding
+        * one drive while leaving another faulty drive in array.
         */
-       for (i = 0; i < conf->raid_disks; i++)
-               if (conf->disks[i].rdev == NULL)
+       rcu_read_lock();
+       for (i = 0; i < conf->raid_disks; i++) {
+               struct md_rdev *rdev = ACCESS_ONCE(conf->disks[i].rdev);
+
+               if (rdev == NULL || test_bit(Faulty, &rdev->flags))
                        still_degraded = 1;
+       }
+       rcu_read_unlock();
 
        bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);