From: Nigel Croxon <ncroxon@xxxxxxxxxx>
commit b2176a1dfb518d870ee073445d27055fea64dfb8 upstream.
The problem is that any 'uptodate' vs 'disks' check is not precise
in this path. Put a "WARN_ON(!test_bit(R5_UPTODATE, &dev->flags)" on the
device that might try to kick off writes and then skip the action.
Better to prevent the raid driver from taking unexpected action *and* keep
the system alive vs killing the machine with BUG_ON.
Note: fixed warning reported by kbuild test robot <lkp@xxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Signed-off-by: Nigel Croxon <ncroxon@xxxxxxxxxx>
Signed-off-by: Song Liu <songliubraving@xxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/md/raid5.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4187,7 +4187,7 @@ static void handle_parity_checks6(struct
/* now write out any block on a failed drive,
* or P or Q if they were recomputed
*/
- BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
+ dev = NULL;
if (s->failed == 2) {
dev = &sh->dev[s->failed_num[1]];
s->locked++;
@@ -4212,6 +4212,14 @@ static void handle_parity_checks6(struct
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
+ if (WARN_ONCE(dev && !test_bit(R5_UPTODATE, &dev->flags),
+ "%s: disk%td not up to date\n",
+ mdname(conf->mddev),
+ dev - (struct r5dev *) &sh->dev)) {
+ clear_bit(R5_LOCKED, &dev->flags);
+ clear_bit(R5_Wantwrite, &dev->flags);
+ s->locked--;
+ }
clear_bit(STRIPE_DEGRADED, &sh->state);
set_bit(STRIPE_INSYNC, &sh->state);
