Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD fixes from Shaohua Li:

 - fix a parity calculation bug of raid5 cache by Song

 - fix a potential deadlock issue by me

 - fix two endian issues by Jason

 - fix a disk limitation issue by Neil

 - other small fixes and cleanup

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md/raid1: fix a trivial typo in comments
  md/r5cache: fix set_syndrome_sources() for data in cache
  md: fix incorrect use of lexx_to_cpu in does_sb_need_changing
  md: fix super_offset endianness in super_1_rdev_size_change
  md/raid1/10: fix potential deadlock
  md: don't impose the MD_SB_DISKS limit on arrays without metadata.
  md: move funcs from pers->resize to update_size
  md-cluster: remove useless memset from gather_all_resync_info
  md-cluster: free md_cluster_info if node leave cluster
  md: delete dead code
  md/raid10: submit bio directly to replacement disk

1 files changed, 34 insertions, 7 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0536658c9d40..e89a8d78a9ed 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1478,11 +1478,24 @@ retry_write:
 			mbio->bi_bdev = (void*)rdev;
 
 			atomic_inc(&r10_bio->remaining);
+
+			cb = blk_check_plugged(raid10_unplug, mddev,
+					       sizeof(*plug));
+			if (cb)
+				plug = container_of(cb, struct raid10_plug_cb,
+						    cb);
+			else
+				plug = NULL;
 			spin_lock_irqsave(&conf->device_lock, flags);
-			bio_list_add(&conf->pending_bio_list, mbio);
-			conf->pending_count++;
+			if (plug) {
+				bio_list_add(&plug->pending, mbio);
+				plug->pending_cnt++;
+			} else {
+				bio_list_add(&conf->pending_bio_list, mbio);
+				conf->pending_count++;
+			}
 			spin_unlock_irqrestore(&conf->device_lock, flags);
-			if (!mddev_check_plugged(mddev))
+			if (!plug)
 				md_wakeup_thread(mddev->thread);
 		}
 	}
@@ -1572,7 +1585,25 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
 		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
 	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
@@ -3944,10 +3975,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, size);
-	if (mddev->queue) {
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
-	}
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > oldsize) {
 		mddev->recovery_cp = oldsize;