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>
[PG: use 2.6.32.49 backport since raid5.c @ 9a3f530f/v3.2 differs more]
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc3e4fcea655f88e0c9636c63281ea0473034649..2936c3bec8e614a673e409c5b9b99a2257c124fa 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3040,12 +3040,16 @@ static void handle_stripe5(struct stripe_head *sh)
        /* check if the array has lost two devices and, if so, some requests might
         * need to be failed
         */
-       if (s.failed > 1 && s.to_read+s.to_write+s.written)
-               handle_failed_stripe(conf, sh, &s, disks, &return_bi);
-       if (s.failed > 1 && s.syncing) {
-               md_done_sync(conf->mddev, STRIPE_SECTORS,0);
-               clear_bit(STRIPE_SYNCING, &sh->state);
-               s.syncing = 0;
+       if (s.failed > 1) {
+               sh->check_state = 0;
+               sh->reconstruct_state = 0;
+               if (s.to_read+s.to_write+s.written)
+                       handle_failed_stripe(conf, sh, &s, disks, &return_bi);
+               if (s.syncing) {
+                       md_done_sync(conf->mddev, STRIPE_SECTORS,0);
+                       clear_bit(STRIPE_SYNCING, &sh->state);
+                       s.syncing = 0;
+               }
        }
 
        /* might be able to return some write requests if the parity block
@@ -3323,12 +3327,16 @@ static void handle_stripe6(struct stripe_head *sh)
        /* check if the array has lost >2 devices and, if so, some requests
         * might need to be failed
         */
-       if (s.failed > 2 && s.to_read+s.to_write+s.written)
-               handle_failed_stripe(conf, sh, &s, disks, &return_bi);
-       if (s.failed > 2 && s.syncing) {
-               md_done_sync(conf->mddev, STRIPE_SECTORS,0);
-               clear_bit(STRIPE_SYNCING, &sh->state);
-               s.syncing = 0;
+       if (s.failed > 2) {
+               sh->check_state = 0;
+               sh->reconstruct_state = 0;
+               if (s.to_read+s.to_write+s.written)
+                       handle_failed_stripe(conf, sh, &s, disks, &return_bi);
+               if (s.syncing) {
+                       md_done_sync(conf->mddev, STRIPE_SECTORS,0);
+                       clear_bit(STRIPE_SYNCING, &sh->state);
+                       s.syncing = 0;
+               }
        }
 
        /*