md/raid5: abort any pending parity operations when array fails.

commit 9a3f530f39f4490eaa18b02719fb74ce5f4d2d86 upstream.

When the number of failed devices exceeds the allowed number
we must abort any active parity operations (checks or updates) as they
are no longer meaningful, and can lead to a BUG_ON in
handle_parity_checks6.

This bug was introduce by commit 6c0069c0ae9659e3a91b68eaed06a5c6c37f45c8
in 2.6.29.

Reported-by: Manish Katiyar <mkatiyar@gmail.com>
Tested-by: Manish Katiyar <mkatiyar@gmail.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f40448874a653ebe2153330ea41d981bbe488e5d..06c82c1bc2ccc0dcfe56031732e5d7f5f970b886 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3165,10 +3165,14 @@ static void handle_stripe(struct stripe_head *sh)
        /* check if the array has lost more than max_degraded devices and,
         * if so, some requests might need to be failed.
         */
-       if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
-               handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
-       if (s.failed > conf->max_degraded && s.syncing)
-               handle_failed_sync(conf, sh, &s);
+       if (s.failed > conf->max_degraded) {
+               sh->check_state = 0;
+               sh->reconstruct_state = 0;
+               if (s.to_read+s.to_write+s.written)
+                       handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+               if (s.syncing)
+                       handle_failed_sync(conf, sh, &s);
+       }
 
        /*
         * might be able to return some write requests if the parity blocks