md/raid5: fix handling of degraded stripes in batches.
There is no need for special handling of stripe-batches when the array
is degraded.
There may be if there is a failure in the batch, but STRIPE_DEGRADED
does not imply an error.
So don't set STRIPE_BATCH_ERR in ops_run_io just because the array is
degraded.
This actually causes a bug: the STRIPE_DEGRADED flag gets cleared in
check_break_stripe_batch_list() and so the bitmap bit gets cleared
when it shouldn't.
So in check_break_stripe_batch_list(), split the batch up completely -
again STRIPE_DEGRADED isn't meaningful.
Also don't set STRIPE_BATCH_ERR when there is a write error to a
replacement device. This simply removes the replacement device and
requires no extra handling.
Signed-off-by: NeilBrown <neilb@suse.de>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3873eaa..1ba97fd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1078,9 +1078,6 @@
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
- if (sh->batch_head)
- set_bit(STRIPE_BATCH_ERR,
- &sh->batch_head->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
@@ -2448,7 +2445,7 @@
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && !uptodate)
+ if (sh->batch_head && !uptodate && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
@@ -4214,15 +4211,9 @@
return;
head_sh = sh;
- do {
- sh = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
- BUG_ON(sh == head_sh);
- } while (!test_bit(STRIPE_DEGRADED, &sh->state));
- while (sh != head_sh) {
- next = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
+ list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
+
list_del_init(&sh->batch_list);
set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
@@ -4242,8 +4233,6 @@
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
-
- sh = next;
}
}