Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md/raid5: don't include 'spare' drives when reshaping to fewer devices.
  md/raid5: add a missing 'continue' in a loop.
  md/raid5: Allow recovered part of partially recovered devices to be in-sync
  md/raid5: More careful check for "has array failed".
  md: Don't update ->recovery_offset when reshaping an array to fewer devices.
  md/raid5: avoid oops when number of devices is reduced then increased.
  md: enable raid4->raid0 takeover
  md: clear layout after ->raid0 takeover
  md: fix raid10 takeover: use new_layout for setup_conf
  md: fix handling of array level takeover that re-arranges devices.
  md: raid10: Fix null pointer dereference in fix_read_error()
  Restore partition detection of newly created md arrays.

1 files changed, 33 insertions, 5 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 46b3a044eadf..cb20d0b0555a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2087,6 +2087,7 @@ static void sync_sbs(mddev_t * mddev, int nospares)
 	/* First make sure individual recovery_offsets are correct */
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		if (rdev->raid_disk >= 0 &&
+		    mddev->delta_disks >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    mddev->curr_resync_completed > rdev->recovery_offset)
 				rdev->recovery_offset = mddev->curr_resync_completed;
@@ -3001,6 +3002,9 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 		return -EINVAL;
 	}
 
+	list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev->new_raid_disk = rdev->raid_disk;
+
 	/* ->takeover must set new_* and/or delta_disks
 	 * if it succeeds, and may set them when it fails.
 	 */
@@ -3051,13 +3055,35 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 		mddev->safemode = 0;
 	}
 
-	module_put(mddev->pers->owner);
-	/* Invalidate devices that are now superfluous */
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		if (rdev->raid_disk >= mddev->raid_disks) {
-			rdev->raid_disk = -1;
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		char nm[20];
+		if (rdev->raid_disk < 0)
+			continue;
+		if (rdev->new_raid_disk > mddev->raid_disks)
+			rdev->new_raid_disk = -1;
+		if (rdev->new_raid_disk == rdev->raid_disk)
+			continue;
+		sprintf(nm, "rd%d", rdev->raid_disk);
+		sysfs_remove_link(&mddev->kobj, nm);
+	}
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (rdev->raid_disk < 0)
+			continue;
+		if (rdev->new_raid_disk == rdev->raid_disk)
+			continue;
+		rdev->raid_disk = rdev->new_raid_disk;
+		if (rdev->raid_disk < 0)
 			clear_bit(In_sync, &rdev->flags);
+		else {
+			char nm[20];
+			sprintf(nm, "rd%d", rdev->raid_disk);
+			if(sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+				printk("md: cannot register %s for %s after level change\n",
+				       nm, mdname(mddev));
 		}
+	}
+
+	module_put(mddev->pers->owner);
 	mddev->pers = pers;
 	mddev->private = priv;
 	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
@@ -5895,6 +5921,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	atomic_inc(&mddev->openers);
 	mutex_unlock(&mddev->open_mutex);
 
+	check_disk_size_change(mddev->gendisk, bdev);
  out:
 	return err;
 }
@@ -6846,6 +6873,7 @@ void md_do_sync(mddev_t *mddev)
 			rcu_read_lock();
 			list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
 				if (rdev->raid_disk >= 0 &&
+				    mddev->delta_disks >= 0 &&
 				    !test_bit(Faulty, &rdev->flags) &&
 				    !test_bit(In_sync, &rdev->flags) &&
 				    rdev->recovery_offset < mddev->curr_resync)