Merge tag 'md-3.10-fixes' of git://neil.brown.name/md

Pull md bugfixes from Neil Brown:
 "A few bugfixes for md

  Some tagged for -stable"

* tag 'md-3.10-fixes' of git://neil.brown.name/md:
  md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place
  md/raid1,raid10: use freeze_array in place of raise_barrier in various places.
  md/raid1: consider WRITE as successful only if at least one non-Faulty and non-rebuilding drive completed it.
  md: md_stop_writes() should always freeze recovery.

1 files changed, 19 insertions, 10 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 59d4daa5f4c7..6ddae2501b9a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -490,7 +490,17 @@ static void raid10_end_write_request(struct bio *bio, int error)
                 sector_t first_bad;
                 int bad_sectors;
 
-                set_bit(R10BIO_Uptodate, &r10_bio->state);
+                /*
+                 * Do not set R10BIO_Uptodate if the current device is
+                 * rebuilding or Faulty. This is because we cannot use
+                 * such device for properly reading the data back (we could
+                 * potentially use it, if the current write would have felt
+                 * before rdev->recovery_offset, but for simplicity we don't
+                 * check this here.
+                 */
+                if (test_bit(In_sync, &rdev->flags) &&
+                    !test_bit(Faulty, &rdev->flags))
+                        set_bit(R10BIO_Uptodate, &r10_bio->state);
 
                 /* Maybe we can clear some bad blocks. */
                 if (is_badblock(rdev,
@@ -1055,17 +1065,17 @@ static void allow_barrier(struct r10conf *conf)
         wake_up(&conf->wait_barrier);
 }
 
-static void freeze_array(struct r10conf *conf)
+static void freeze_array(struct r10conf *conf, int extra)
 {
         /* stop syncio and normal IO and wait for everything to
          * go quiet.
          * We increment barrier and nr_waiting, and then
-         * wait until nr_pending match nr_queued+1
+         * wait until nr_pending match nr_queued+extra
          * This is called in the context of one normal IO request
          * that has failed. Thus any sync request that might be pending
          * will be blocked by nr_pending, and we need to wait for
          * pending IO requests to complete or be queued for re-try.
-         * Thus the number queued (nr_queued) plus this request (1)
+         * Thus the number queued (nr_queued) plus this request (extra)
          * must match the number of pending IOs (nr_pending) before
          * we continue.
          */
@@ -1073,7 +1083,7 @@ static void freeze_array(struct r10conf *conf)
         conf->barrier++;
         conf->nr_waiting++;
         wait_event_lock_irq_cmd(conf->wait_barrier,
-                                conf->nr_pending == conf->nr_queued+1,
+                                conf->nr_pending == conf->nr_queued+extra,
                                 conf->resync_lock,
                                 flush_pending_writes(conf));
 
@@ -1837,8 +1847,8 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
                  * we wait for all outstanding requests to complete.
                  */
                 synchronize_sched();
-                raise_barrier(conf, 0);
-                lower_barrier(conf);
+                freeze_array(conf, 0);
+                unfreeze_array(conf);
                 clear_bit(Unmerged, &rdev->flags);
         }
         md_integrity_add_rdev(rdev, mddev);
@@ -2612,7 +2622,7 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
         r10_bio->devs[slot].bio = NULL;
 
         if (mddev->ro == 0) {
-                freeze_array(conf);
+                freeze_array(conf, 1);
                 fix_read_error(conf, mddev, r10_bio);
                 unfreeze_array(conf);
         } else
@@ -3609,8 +3619,7 @@ static int run(struct mddev *mddev)
         if (mddev->queue) {
                 blk_queue_max_discard_sectors(mddev->queue,
                                               mddev->chunk_sectors);
-                blk_queue_max_write_same_sectors(mddev->queue,
-                                                 mddev->chunk_sectors);
+                blk_queue_max_write_same_sectors(mddev->queue, 0);
                 blk_queue_io_min(mddev->queue, chunk_size);
                 if (conf->geo.raid_disks % conf->geo.near_copies)
                         blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);