summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2015-02-02 10:44:29 +1100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2015-02-11 15:00:53 +0800
commitd2d9e9edf939ea938921f0e6c7e3151a308d4411 (patch)
tree0967d193acb029c2ca0d3d017984cd801c373d43
parent0e8422433e621f9df297bbe07e12b851679d3dbe (diff)
md/raid5: fix another livelock caused by non-aligned writes.
commit b1b02fe97f75b12ab34b2303bfd4e3526d903a58 upstream. If a non-page-aligned write is destined for a device which is missing/faulty, we can deadlock. As the target device is missing, a read-modify-write cycle is not possible. As the write is not for a full-page, a recontruct-write cycle is not possible. This should be handled by logic in fetch_block() which notices there is a non-R5_OVERWRITE write to a missing device, and so loads all blocks. However since commit 67f455486d2ea2, that code requires STRIPE_PREREAD_ACTIVE before it will active, and those circumstances never set STRIPE_PREREAD_ACTIVE. So: in handle_stripe_dirtying, if neither rmw or rcw was possible, set STRIPE_DELAYED, which will cause STRIPE_PREREAD_ACTIVE be set after a suitable delay. Fixes: 67f455486d2ea20b2d94d6adf5b9b783d079e321 Reported-by: Mikulas Patocka <mpatocka@redhat.com> Tested-by: Heinz Mauelshagen <heinzm@redhat.com> Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--drivers/md/raid5.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c1b0d52bfcb0..b98765f6f77f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3195,6 +3195,11 @@ static void handle_stripe_dirtying(struct r5conf *conf,
(unsigned long long)sh->sector,
rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
}
+
+ if (rcw > disks && rmw > disks &&
+ !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ set_bit(STRIPE_DELAYED, &sh->state);
+
/* now if nothing is locked, and if we have enough data,
* we can start a write request
*/