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

Pull md fixes from NeilBrown:
 "A mixed bag of little fixes.  No real new functionality here.  Several
  patches are tagged for -stable."

* tag 'md-3.10' of git://neil.brown.name/md:
  MD: ignore discard request for hard disks of hybid raid1/raid10 array
  md: bad block list should default to disabled.
  md: raid1/raid10 md devices leak memory when stopping
  DM RAID: Add message/status support for changing sync action
  MD: Export 'md_reap_sync_thread' function
  md: don't update metadata when stopping a read-only array.
  md: Allow devices to be re-added to a read-only array.
  md/raid10: Allow skipping recovery when clean arrays are assembled
  MD: Fix typos in MD documentation
  md/raid5: avoid an extra write when writing to a known-bad-block.
  md/raid5: Change or of some order to improve efficiency.
  md: use set_bit_le and clear_bit_le
  md: HOT_DISK_REMOVE shouldn't make a read-auto device active.
  md: use common code for all calls to ->hot_remove_disk()
  md: never update metadata when array is read-only.

7 files changed, 293 insertions, 106 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 4fd9d6aeff6..5a2c7549982 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -846,7 +846,7 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set_bit(bit, kaddr);
 	else
-		test_and_set_bit_le(bit, kaddr);
+		set_bit_le(bit, kaddr);
 	kunmap_atomic(kaddr);
 	pr_debug("set file bit %lu page %lu\n", bit, page->index);
 	/* record page number so it gets flushed to disk when unplug occurs */
@@ -868,7 +868,7 @@ static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		clear_bit(bit, paddr);
 	else
-		test_and_clear_bit_le(bit, paddr);
+		clear_bit_le(bit, paddr);
 	kunmap_atomic(paddr);
 	if (!test_page_attr(bitmap, page->index, BITMAP_PAGE_NEEDWRITE)) {
 		set_page_attr(bitmap, page->index, BITMAP_PAGE_PENDING);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 311e3d35b27..1d3fe1a40a9 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1279,6 +1279,31 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_SUBMITTED;
 }
 
+static const char *decipher_sync_action(struct mddev *mddev)
+{
+	if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		return "frozen";
+
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	    (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
+		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+			return "reshape";
+
+		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+			if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+				return "resync";
+			else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+				return "check";
+			return "repair";
+		}
+
+		if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
+			return "recover";
+	}
+
+	return "idle";
+}
+
 static void raid_status(struct dm_target *ti, status_type_t type,
 			unsigned status_flags, char *result, unsigned maxlen)
 {
@@ -1298,8 +1323,18 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 			sync = rs->md.recovery_cp;
 
 		if (sync >= rs->md.resync_max_sectors) {
+			/*
+			 * Sync complete.
+			 */
 			array_in_sync = 1;
 			sync = rs->md.resync_max_sectors;
+		} else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
+			/*
+			 * If "check" or "repair" is occurring, the array has
+			 * undergone and initial sync and the health characters
+			 * should not be 'a' anymore.
+			 */
+			array_in_sync = 1;
 		} else {
 			/*
 			 * The array may be doing an initial sync, or it may
@@ -1311,6 +1346,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 				if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
 					array_in_sync = 1;
 		}
+
 		/*
 		 * Status characters:
 		 *  'D' = Dead/Failed device
@@ -1339,6 +1375,21 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		       (unsigned long long) sync,
 		       (unsigned long long) rs->md.resync_max_sectors);
 
+		/*
+		 * Sync action:
+		 *   See Documentation/device-mapper/dm-raid.c for
+		 *   information on each of these states.
+		 */
+		DMEMIT(" %s", decipher_sync_action(&rs->md));
+
+		/*
+		 * resync_mismatches/mismatch_cnt
+		 *   This field shows the number of discrepancies found when
+		 *   performing a "check" of the array.
+		 */
+		DMEMIT(" %llu",
+		       (unsigned long long)
+		       atomic64_read(&rs->md.resync_mismatches));
 		break;
 	case STATUSTYPE_TABLE:
 		/* The string you would use to construct this array */
@@ -1425,7 +1476,62 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int raid_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
+static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	if (!strcasecmp(argv[0], "reshape")) {
+		DMERR("Reshape not supported.");
+		return -EINVAL;
+	}
+
+	if (!mddev->pers || !mddev->pers->sync_request)
+		return -EINVAL;
+
+	if (!strcasecmp(argv[0], "frozen"))
+		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	else
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
+		if (mddev->sync_thread) {
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+			md_reap_sync_thread(mddev);
+		}
+	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+		return -EBUSY;
+	else if (!strcasecmp(argv[0], "resync"))
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	else if (!strcasecmp(argv[0], "recover")) {
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	} else {
+		if (!strcasecmp(argv[0], "check"))
+			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+		else if (!!strcasecmp(argv[0], "repair"))
+			return -EINVAL;
+		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	}
+	if (mddev->ro == 2) {
+		/* A write to sync_action is enough to justify
+		 * canceling read-auto mode
+		 */
+		mddev->ro = 0;
+		if (!mddev->suspended)
+			md_wakeup_thread(mddev->sync_thread);
+	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	if (!mddev->suspended)
+		md_wakeup_thread(mddev->thread);
+
+	return 0;
+}
+
+static int raid_iterate_devices(struct dm_target *ti,
+				iterate_devices_callout_fn fn, void *data)
 {
 	struct raid_set *rs = ti->private;
 	unsigned i;
@@ -1482,12 +1588,13 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 4, 2},
+	.version = {1, 5, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
 	.map = raid_map,
 	.status = raid_status,
+	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
 	.presuspend = raid_presuspend,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index aeceedfc530..4c74424c78b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -72,6 +72,9 @@ static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
 static struct workqueue_struct *md_misc_wq;
 
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this);
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 /*
@@ -1564,8 +1567,8 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 					     sector, count, 1) == 0)
 				return -EINVAL;
 		}
-	} else if (sb->bblog_offset == 0)
-		rdev->badblocks.shift = -1;
+	} else if (sb->bblog_offset != 0)
+		rdev->badblocks.shift = 0;
 
 	if (!refdev) {
 		ret = 1;
@@ -2411,6 +2414,11 @@ static void md_update_sb(struct mddev * mddev, int force_change)
 	int nospares = 0;
 	int any_badblocks_changed = 0;
 
+	if (mddev->ro) {
+		if (force_change)
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		return;
+	}
 repeat:
 	/* First make sure individual recovery_offsets are correct */
 	rdev_for_each(rdev, mddev) {
@@ -2800,12 +2808,10 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		/* personality does all needed checks */
 		if (rdev->mddev->pers->hot_remove_disk == NULL)
 			return -EINVAL;
-		err = rdev->mddev->pers->
-			hot_remove_disk(rdev->mddev, rdev);
-		if (err)
-			return err;
-		sysfs_unlink_rdev(rdev->mddev, rdev);
-		rdev->raid_disk = -1;
+		clear_bit(Blocked, &rdev->flags);
+		remove_and_add_spares(rdev->mddev, rdev);
+		if (rdev->raid_disk >= 0)
+			return -EBUSY;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
@@ -3221,7 +3227,7 @@ int md_rdev_init(struct md_rdev *rdev)
 	 * be used - I wonder if that matters
 	 */
 	rdev->badblocks.count = 0;
-	rdev->badblocks.shift = 0;
+	rdev->badblocks.shift = -1; /* disabled until explicitly enabled */
 	rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	seqlock_init(&rdev->badblocks.lock);
 	if (rdev->badblocks.page == NULL)
@@ -3293,9 +3299,6 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 			goto abort_free;
 		}
 	}
-	if (super_format == -1)
-		/* hot-add for 0.90, or non-persistent: so no badblocks */
-		rdev->badblocks.shift = -1;
 
 	return rdev;
 
@@ -4225,8 +4228,6 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
-static void reap_sync_thread(struct mddev *mddev);
-
 static ssize_t
 action_store(struct mddev *mddev, const char *page, size_t len)
 {
@@ -4241,7 +4242,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev);
 		}
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
@@ -5279,7 +5280,7 @@ static void __md_stop_writes(struct mddev *mddev)
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		reap_sync_thread(mddev);
+		md_reap_sync_thread(mddev);
 	}
 
 	del_timer_sync(&mddev->safemode_timer);
@@ -5287,7 +5288,8 @@ static void __md_stop_writes(struct mddev *mddev)
 	bitmap_flush(mddev);
 	md_super_wait(mddev);
 
-	if (!mddev->in_sync || mddev->flags) {
+	if (mddev->ro == 0 &&
+	    (!mddev->in_sync || mddev->flags)) {
 		/* mark array as shutdown cleanly */
 		mddev->in_sync = 1;
 		md_update_sb(mddev, 1);
@@ -5810,7 +5812,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 		else
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 
-		md_update_sb(mddev, 1);
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		if (mddev->degraded)
 			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -5877,6 +5879,9 @@ static int hot_remove_disk(struct mddev * mddev, dev_t dev)
 	if (!rdev)
 		return -ENXIO;
 
+	clear_bit(Blocked, &rdev->flags);
+	remove_and_add_spares(mddev, rdev);
+
 	if (rdev->raid_disk >= 0)
 		goto busy;
 
@@ -6490,6 +6495,28 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		err = md_set_readonly(mddev, bdev);
 		goto done_unlock;
 
+	case HOT_REMOVE_DISK:
+		err = hot_remove_disk(mddev, new_decode_dev(arg));
+		goto done_unlock;
+
+	case ADD_NEW_DISK:
+		/* We can support ADD_NEW_DISK on read-only arrays
+		 * on if we are re-adding a preexisting device.
+		 * So require mddev->pers and MD_DISK_SYNC.
+		 */
+		if (mddev->pers) {
+			mdu_disk_info_t info;
+			if (copy_from_user(&info, argp, sizeof(info)))
+				err = -EFAULT;
+			else if (!(info.state & (1<<MD_DISK_SYNC)))
+				/* Need to clear read-only for this */
+				break;
+			else
+				err = add_new_disk(mddev, &info);
+			goto done_unlock;
+		}
+		break;
+
 	case BLKROSET:
 		if (get_user(ro, (int __user *)(arg))) {
 			err = -EFAULT;
@@ -6560,10 +6587,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		goto done_unlock;
 	}
 
-	case HOT_REMOVE_DISK:
-		err = hot_remove_disk(mddev, new_decode_dev(arg));
-		goto done_unlock;
-
 	case HOT_ADD_DISK:
 		err = hot_add_disk(mddev, new_decode_dev(arg));
 		goto done_unlock;
@@ -7644,14 +7667,16 @@ void md_do_sync(struct md_thread *thread)
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
-static int remove_and_add_spares(struct mddev *mddev)
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this)
 {
 	struct md_rdev *rdev;
 	int spares = 0;
 	int removed = 0;
 
 	rdev_for_each(rdev, mddev)
-		if (rdev->raid_disk >= 0 &&
+		if ((this == NULL || rdev == this) &&
+		    rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
 		     ! test_bit(In_sync, &rdev->flags)) &&
@@ -7666,74 +7691,52 @@ static int remove_and_add_spares(struct mddev *mddev)
 	if (removed && mddev->kobj.sd)
 		sysfs_notify(&mddev->kobj, NULL, "degraded");
 
+	if (this)
+		goto no_add;
+
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
 			spares++;
-		if (rdev->raid_disk < 0
-		    && !test_bit(Faulty, &rdev->flags)) {
-			rdev->recovery_offset = 0;
-			if (mddev->pers->
-			    hot_add_disk(mddev, rdev) == 0) {
-				if (sysfs_link_rdev(mddev, rdev))
-					/* failure here is OK */;
-				spares++;
-				md_new_event(mddev);
-				set_bit(MD_CHANGE_DEVS, &mddev->flags);
-			}
+		if (rdev->raid_disk >= 0)
+			continue;
+		if (test_bit(Faulty, &rdev->flags))
+			continue;
+		if (mddev->ro &&
+		    rdev->saved_raid_disk < 0)
+			continue;
+
+		rdev->recovery_offset = 0;
+		if (rdev->saved_raid_disk >= 0 && mddev->in_sync) {
+			spin_lock_irq(&mddev->write_lock);
+			if (mddev->in_sync)
+				/* OK, this device, which is in_sync,
+				 * will definitely be noticed before
+				 * the next write, so recovery isn't
+				 * needed.
+				 */
+				rdev->recovery_offset = mddev->recovery_cp;
+			spin_unlock_irq(&mddev->write_lock);
+		}
+		if (mddev->ro && rdev->recovery_offset != MaxSector)
+			/* not safe to add this disk now */
+			continue;
+		if (mddev->pers->
+		    hot_add_disk(mddev, rdev) == 0) {
+			if (sysfs_link_rdev(mddev, rdev))
+				/* failure here is OK */;
+			spares++;
+			md_new_event(mddev);
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		}
 	}
+no_add:
 	if (removed)
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	return spares;
 }
 
-static void reap_sync_thread(struct mddev *mddev)
-{
-	struct md_rdev *rdev;
-
-	/* resync has finished, collect result */
-	md_unregister_thread(&mddev->sync_thread);
-	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
-		/* success...*/
-		/* activate any spares */
-		if (mddev->pers->spare_active(mddev)) {
-			sysfs_notify(&mddev->kobj, NULL,
-				     "degraded");
-			set_bit(MD_CHANGE_DEVS, &mddev->flags);
-		}
-	}
-	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
-	    mddev->pers->finish_reshape)
-		mddev->pers->finish_reshape(mddev);
-
-	/* If array is no-longer degraded, then any saved_raid_disk
-	 * information must be scrapped.  Also if any device is now
-	 * In_sync we must scrape the saved_raid_disk for that device
-	 * do the superblock for an incrementally recovered device
-	 * written out.
-	 */
-	rdev_for_each(rdev, mddev)
-		if (!mddev->degraded ||
-		    test_bit(In_sync, &rdev->flags))
-			rdev->saved_raid_disk = -1;
-
-	md_update_sb(mddev, 1);
-	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-	/* flag recovery needed just to double check */
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	md_new_event(mddev);
-	if (mddev->event_work.func)
-		queue_work(md_misc_wq, &mddev->event_work);
-}
-
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -7789,22 +7792,16 @@ void md_check_recovery(struct mddev *mddev)
 		int spares = 0;
 
 		if (mddev->ro) {
-			/* Only thing we do on a ro array is remove
-			 * failed devices.
+			/* On a read-only array we can:
+			 * - remove failed devices
+			 * - add already-in_sync devices if the array itself
+			 *   is in-sync.
+			 * As we only add devices that are already in-sync,
+			 * we can activate the spares immediately.
 			 */
-			struct md_rdev *rdev;
-			rdev_for_each(rdev, mddev)
-				if (rdev->raid_disk >= 0 &&
-				    !test_bit(Blocked, &rdev->flags) &&
-				    test_bit(Faulty, &rdev->flags) &&
-				    atomic_read(&rdev->nr_pending)==0) {
-					if (mddev->pers->hot_remove_disk(
-						    mddev, rdev) == 0) {
-						sysfs_unlink_rdev(mddev, rdev);
-						rdev->raid_disk = -1;
-					}
-				}
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			remove_and_add_spares(mddev, NULL);
+			mddev->pers->spare_active(mddev);
 			goto unlock;
 		}
 
@@ -7836,7 +7833,7 @@ void md_check_recovery(struct mddev *mddev)
 			goto unlock;
 		}
 		if (mddev->sync_thread) {
-			reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev);
 			goto unlock;
 		}
 		/* Set RUNNING before clearing NEEDED to avoid
@@ -7867,7 +7864,7 @@ void md_check_recovery(struct mddev *mddev)
 				goto unlock;
 			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if ((spares = remove_and_add_spares(mddev))) {
+		} else if ((spares = remove_and_add_spares(mddev, NULL))) {
 			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 			clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
@@ -7917,6 +7914,51 @@ void md_check_recovery(struct mddev *mddev)
 	}
 }
 
+void md_reap_sync_thread(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+
+	/* resync has finished, collect result */
+	md_unregister_thread(&mddev->sync_thread);
+	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		/* success...*/
+		/* activate any spares */
+		if (mddev->pers->spare_active(mddev)) {
+			sysfs_notify(&mddev->kobj, NULL,
+				     "degraded");
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		}
+	}
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    mddev->pers->finish_reshape)
+		mddev->pers->finish_reshape(mddev);
+
+	/* If array is no-longer degraded, then any saved_raid_disk
+	 * information must be scrapped.  Also if any device is now
+	 * In_sync we must scrape the saved_raid_disk for that device
+	 * do the superblock for an incrementally recovered device
+	 * written out.
+	 */
+	rdev_for_each(rdev, mddev)
+		if (!mddev->degraded ||
+		    test_bit(In_sync, &rdev->flags))
+			rdev->saved_raid_disk = -1;
+
+	md_update_sb(mddev, 1);
+	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	/* flag recovery needed just to double check */
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+	md_new_event(mddev);
+	if (mddev->event_work.func)
+		queue_work(md_misc_wq, &mddev->event_work);
+}
+
 void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	sysfs_notify_dirent_safe(rdev->sysfs_state);
@@ -8642,6 +8684,7 @@ EXPORT_SYMBOL(md_register_thread);
 EXPORT_SYMBOL(md_unregister_thread);
 EXPORT_SYMBOL(md_wakeup_thread);
 EXPORT_SYMBOL(md_check_recovery);
+EXPORT_SYMBOL(md_reap_sync_thread);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
 MODULE_ALIAS("md");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index d90fb1a879e..653f992b687 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -567,6 +567,7 @@ extern struct md_thread *md_register_thread(
 extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
+extern void md_reap_sync_thread(struct mddev *mddev);
 extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fd86b372692..851023e2ba5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -981,7 +981,12 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+			/* Just ignore it */
+			bio_endio(bio, 0);
+		else
+			generic_make_request(bio);
 		bio = next;
 	}
 	kfree(plug);
@@ -2901,6 +2906,7 @@ static int stop(struct mddev *mddev)
 	if (conf->r1bio_pool)
 		mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
+	safe_put_page(conf->tmppage);
 	kfree(conf->poolinfo);
 	kfree(conf);
 	mddev->private = NULL;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 77b562d18a9..018741ba931 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1133,7 +1133,12 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+			/* Just ignore it */
+			bio_endio(bio, 0);
+		else
+			generic_make_request(bio);
 		bio = next;
 	}
 	kfree(plug);
@@ -2913,6 +2918,22 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (init_resync(conf))
 			return 0;
 
+	/*
+	 * Allow skipping a full rebuild for incremental assembly
+	 * of a clean array, like RAID1 does.
+	 */
+	if (mddev->bitmap == NULL &&
+	    mddev->recovery_cp == MaxSector &&
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    conf->fullsync == 0) {
+		*skipped = 1;
+		max_sector = mddev->dev_sectors;
+		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
+		    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+			max_sector = mddev->resync_max_sectors;
+		return max_sector - sector_nr;
+	}
+
  skipped:
 	max_sector = mddev->dev_sectors;
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -3810,6 +3831,7 @@ static int stop(struct mddev *mddev)
 
 	if (conf->r10bio_pool)
 		mempool_destroy(conf->r10bio_pool);
+	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
 	mddev->private = NULL;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f4e87bfc756..4a7be455d6d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1887,8 +1887,15 @@ static void raid5_end_write_request(struct bio *bi, int error)
 					&rdev->mddev->recovery);
 		} else if (is_badblock(rdev, sh->sector,
 				       STRIPE_SECTORS,
-				       &first_bad, &bad_sectors))
+				       &first_bad, &bad_sectors)) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
+			if (test_bit(R5_ReadError, &sh->dev[i].flags))
+				/* That was a successful write so make
+				 * sure it looks like we already did
+				 * a re-write.
+				 */
+				set_bit(R5_ReWrite, &sh->dev[i].flags);
+		}
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
@@ -4672,9 +4679,10 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
 		*skipped = 1;
 		return rv;
 	}
-	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
-	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
-	    !conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
+	if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    !conf->fullsync &&
+	    !bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	    sync_blocks >= STRIPE_SECTORS) {
 		/* we can skip this block, and probably more */
 		sync_blocks /= STRIPE_SECTORS;
 		*skipped = 1;