1 files changed, 163 insertions, 135 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a4556d2e46bf..dce06bf65016 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -24,6 +24,7 @@
 #include "raid10.h"
 #include "raid0.h"
 #include "md-bitmap.h"
+#include "md-cluster.h"
 
 /*
  * RAID10 provides a combination of RAID0 and RAID1 functionality.
@@ -426,12 +427,9 @@ static void raid10_end_read_request(struct bio *bio)
 
 static void close_write(struct r10bio *r10_bio)
 {
-	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
-			   r10_bio->sectors,
-			   !test_bit(R10BIO_Degraded, &r10_bio->state),
-			   0);
-	md_write_end(r10_bio->mddev);
+	struct mddev *mddev = r10_bio->mddev;
+
+	md_write_end(mddev);
 }
 
 static void one_write_done(struct r10bio *r10_bio)
@@ -500,7 +498,6 @@ static void raid10_end_write_request(struct bio *bio)
 				set_bit(R10BIO_WriteError, &r10_bio->state);
 			else {
 				/* Fail the request */
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 				r10_bio->devs[slot].bio = NULL;
 				to_put = bio;
 				dec_rdev = 1;
@@ -751,7 +748,7 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 
 	for (slot = 0; slot < conf->copies ; slot++) {
 		sector_t first_bad;
-		int bad_sectors;
+		sector_t bad_sectors;
 		sector_t dev_sector;
 		unsigned int pending;
 		bool nonrot;
@@ -884,7 +881,7 @@ static void flush_pending_writes(struct r10conf *conf)
 		__set_current_state(TASK_RUNNING);
 
 		blk_start_plug(&plug);
-		raid1_prepare_flush_writes(conf->mddev->bitmap);
+		raid1_prepare_flush_writes(conf->mddev);
 		wake_up(&conf->wait_barrier);
 
 		while (bio) { /* submit pending writes */
@@ -1100,7 +1097,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	/* we aren't scheduling, so we can do the write-out directly. */
 	bio = bio_list_get(&plug->pending);
-	raid1_prepare_flush_writes(mddev->bitmap);
+	raid1_prepare_flush_writes(mddev);
 	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
@@ -1150,14 +1147,13 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 {
 	struct r10conf *conf = mddev->private;
 	struct bio *read_bio;
-	const enum req_op op = bio_op(bio);
-	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
 	struct md_rdev *rdev;
 	char b[BDEVNAME_SIZE];
 	int slot = r10_bio->read_slot;
 	struct md_rdev *err_rdev = NULL;
 	gfp_t gfp = GFP_NOIO;
+	int error;
 
 	if (slot >= 0 && r10_bio->devs[slot].rdev) {
 		/*
@@ -1205,6 +1201,10 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
@@ -1227,7 +1227,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
 		choose_data_offset(r10_bio, rdev);
 	read_bio->bi_end_io = raid10_end_read_request;
-	read_bio->bi_opf = op | do_sync;
 	if (test_bit(FailFast, &rdev->flags) &&
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
@@ -1235,15 +1234,17 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
+err_handle:
+	atomic_dec(&rdev->nr_pending);
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R10BIO_Uptodate, &r10_bio->state);
+	raid_end_bio_io(r10_bio);
 }
 
 static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 				  struct bio *bio, bool replacement,
 				  int n_copy)
 {
-	const enum req_op op = bio_op(bio);
-	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
-	const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
 	unsigned long flags;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev;
@@ -1262,7 +1263,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	mbio->bi_iter.bi_sector	= (r10_bio->devs[n_copy].addr +
 				   choose_data_offset(r10_bio, rdev));
 	mbio->bi_end_io	= raid10_end_write_request;
-	mbio->bi_opf = op | do_sync | do_fua;
 	if (!replacement && test_bit(FailFast,
 				     &conf->mirrors[devnum].rdev->flags)
 			 && enough(conf, devnum))
@@ -1284,9 +1284,9 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
-	int i;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *blocked_rdev;
+	int i;
 
 retry_wait:
 	blocked_rdev = NULL;
@@ -1294,40 +1294,36 @@ retry_wait:
 		struct md_rdev *rdev, *rrdev;
 
 		rdev = conf->mirrors[i].rdev;
-		rrdev = conf->mirrors[i].replacement;
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
-		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
-			atomic_inc(&rrdev->nr_pending);
-			blocked_rdev = rrdev;
-			break;
-		}
-
-		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+		if (rdev) {
 			sector_t dev_sector = r10_bio->devs[i].addr;
 
 			/*
 			 * Discard request doesn't care the write result
 			 * so it doesn't need to wait blocked disk here.
 			 */
-			if (!r10_bio->sectors)
-				continue;
-
-			if (rdev_has_badblock(rdev, dev_sector,
-					      r10_bio->sectors) < 0) {
+			if (test_bit(WriteErrorSeen, &rdev->flags) &&
+			    r10_bio->sectors &&
+			    rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0)
 				/*
-				 * Mustn't write here until the bad block
-				 * is acknowledged
+				 * Mustn't write here until the bad
+				 * block is acknowledged
 				 */
-				atomic_inc(&rdev->nr_pending);
 				set_bit(BlockedBadBlocks, &rdev->flags);
+
+			if (rdev_blocked(rdev)) {
 				blocked_rdev = rdev;
+				atomic_inc(&rdev->nr_pending);
 				break;
 			}
 		}
+
+		rrdev = conf->mirrors[i].replacement;
+		if (rrdev && rdev_blocked(rrdev)) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
 	}
 
 	if (unlikely(blocked_rdev)) {
@@ -1346,14 +1342,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 				 struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
-	int i;
+	int i, k;
 	sector_t sectors;
 	int max_sectors;
+	int error;
 
 	if ((mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, WRITE,
-					    bio->bi_iter.bi_sector,
-					    bio_end_sector(bio)))) {
+	     mddev->cluster_ops->area_resyncing(mddev, WRITE,
+						bio->bi_iter.bi_sector,
+						bio_end_sector(bio)))) {
 		DEFINE_WAIT(w);
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
@@ -1363,7 +1360,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		for (;;) {
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_IDLE);
-			if (!md_cluster_ops->area_resyncing(mddev, WRITE,
+			if (!mddev->cluster_ops->area_resyncing(mddev, WRITE,
 				 bio->bi_iter.bi_sector, bio_end_sector(bio)))
 				break;
 			schedule();
@@ -1429,14 +1426,12 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
 
-		if (!rdev && !rrdev) {
-			set_bit(R10BIO_Degraded, &r10_bio->state);
+		if (!rdev && !rrdev)
 			continue;
-		}
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
+			sector_t bad_sectors;
 			int is_bad;
 
 			is_bad = is_badblock(rdev, dev_sector, max_sectors,
@@ -1449,18 +1444,24 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 					 * to other devices yet
 					 */
 					max_sectors = bad_sectors;
-				/* We don't set R10BIO_Degraded as that
-				 * only applies if the disk is missing,
-				 * so it might be re-added, and we want to
-				 * know to recover this chunk.
-				 * In this case the device is here, and the
-				 * fact that this chunk is not in-sync is
-				 * recorded in the bad block log.
-				 */
 				continue;
 			}
 			if (is_bad) {
-				int good_sectors = first_bad - dev_sector;
+				int good_sectors;
+
+				/*
+				 * We cannot atomically write this, so just
+				 * error in that case. It could be possible to
+				 * atomically write other mirrors, but the
+				 * complexity of supporting that is not worth
+				 * the benefit.
+				 */
+				if (bio->bi_opf & REQ_ATOMIC) {
+					error = -EIO;
+					goto err_handle;
+				}
+
+				good_sectors = first_bad - dev_sector;
 				if (good_sectors < max_sectors)
 					max_sectors = good_sectors;
 			}
@@ -1481,6 +1482,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	if (r10_bio->sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, r10_bio->sectors,
 					      GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
@@ -1492,7 +1497,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)
@@ -1501,6 +1505,26 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			raid10_write_one_disk(mddev, r10_bio, bio, true, i);
 	}
 	one_write_done(r10_bio);
+	return;
+err_handle:
+	for (k = 0;  k < i; k++) {
+		int d = r10_bio->devs[k].devnum;
+		struct md_rdev *rdev = conf->mirrors[d].rdev;
+		struct md_rdev *rrdev = conf->mirrors[d].replacement;
+
+		if (r10_bio->devs[k].bio) {
+			rdev_dec_pending(rdev, mddev);
+			r10_bio->devs[k].bio = NULL;
+		}
+		if (r10_bio->devs[k].repl_bio) {
+			rdev_dec_pending(rrdev, mddev);
+			r10_bio->devs[k].repl_bio = NULL;
+		}
+	}
+
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R10BIO_Uptodate, &r10_bio->state);
+	raid_end_bio_io(r10_bio);
 }
 
 static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
@@ -1600,11 +1624,10 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		return -EAGAIN;
 
-	if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) {
+	if (!wait_barrier(conf, bio->bi_opf & REQ_NOWAIT)) {
 		bio_wouldblock_error(bio);
 		return 0;
 	}
-	wait_barrier(conf, false);
 
 	/*
 	 * Check reshape again to avoid reshape happens after checking
@@ -1642,6 +1665,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (remainder) {
 		split_size = stripe_size - remainder;
 		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return 0;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		/* Resend the fist split part */
@@ -1652,6 +1680,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (remainder) {
 		split_size = bio_sectors(bio) - remainder;
 		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return 0;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		/* Resend the second split part */
@@ -1702,6 +1735,7 @@ retry_discard:
 	 * The discard bio returns only first r10bio finishes
 	 */
 	if (first_copy) {
+		md_account_bio(mddev, &bio);
 		r10_bio->master_bio = bio;
 		set_bit(R10BIO_Discard, &r10_bio->state);
 		first_copy = false;
@@ -1836,8 +1870,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	    && md_flush_request(mddev, bio))
 		return true;
 
-	if (!md_write_start(mddev, bio))
-		return false;
+	md_write_start(mddev, bio);
 
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
 		if (!raid10_handle_discard(mddev, bio))
@@ -2083,9 +2116,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
 		return -EINVAL;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -2396,7 +2426,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		atomic_inc(&r10_bio->remaining);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));
 
 		if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
 			tbio->bi_opf |= MD_FAILFAST;
@@ -2418,8 +2447,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			bio_copy_data(tbio, fbio);
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
-		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     bio_sectors(tbio));
 		submit_bio_noacct(tbio);
 	}
 
@@ -2469,7 +2496,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 			s = PAGE_SIZE >> 9;
 
 		rdev = conf->mirrors[dr].rdev;
-		addr = r10_bio->devs[0].addr + sect,
+		addr = r10_bio->devs[0].addr + sect;
 		ok = sync_page_io(rdev,
 				  addr,
 				  s << 9,
@@ -2553,13 +2580,10 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	d = r10_bio->devs[1].devnum;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
 		submit_bio_noacct(wbio);
 	}
 	if (wbio2) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
-		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     bio_sectors(wbio2));
 		submit_bio_noacct(wbio2);
 	}
 }
@@ -2749,7 +2773,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	}
 }
 
-static int narrow_write_error(struct r10bio *r10_bio, int i)
+static bool narrow_write_error(struct r10bio *r10_bio, int i)
 {
 	struct bio *bio = r10_bio->master_bio;
 	struct mddev *mddev = r10_bio->mddev;
@@ -2770,10 +2794,10 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 	sector_t sector;
 	int sectors;
 	int sect_to_write = r10_bio->sectors;
-	int ok = 1;
+	bool ok = true;
 
 	if (rdev->badblocks.shift < 0)
-		return 0;
+		return false;
 
 	block_sectors = roundup(1 << rdev->badblocks.shift,
 				bdev_logical_block_size(rdev->bdev) >> 9);
@@ -2912,11 +2936,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 				rdev_dec_pending(rdev, conf->mddev);
 			} else if (bio != NULL && bio->bi_status) {
 				fail = true;
-				if (!narrow_write_error(r10_bio, m)) {
+				if (!narrow_write_error(r10_bio, m))
 					md_error(conf->mddev, rdev);
-					set_bit(R10BIO_Degraded,
-						&r10_bio->state);
-				}
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			bio = r10_bio->devs[m].repl_bio;
@@ -2975,8 +2996,6 @@ static void raid10d(struct md_thread *thread)
 			r10_bio = list_first_entry(&tmp, struct r10bio,
 						   retry_list);
 			list_del(&r10_bio->retry_list);
-			if (mddev->degraded)
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 
 			if (test_bit(R10BIO_WriteError,
 				     &r10_bio->state))
@@ -3140,12 +3159,12 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf)
  */
 
 static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
-			     int *skipped)
+				    sector_t max_sector, int *skipped)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 	struct bio *biolist = NULL, *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int i;
 	int max_sync;
 	sector_t sync_blocks;
@@ -3175,10 +3194,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			return 0;
 
  skipped:
-	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;
 	if (sector_nr >= max_sector) {
 		conf->cluster_sync_low = 0;
 		conf->cluster_sync_high = 0;
@@ -3200,13 +3215,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (mddev->curr_resync < max_sector) { /* aborted */
 			if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-				md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
-						   &sync_blocks, 1);
+				mddev->bitmap_ops->end_sync(mddev,
+							    mddev->curr_resync,
+							    &sync_blocks);
 			else for (i = 0; i < conf->geo.raid_disks; i++) {
 				sector_t sect =
 					raid10_find_virt(conf, mddev->curr_resync, i);
-				md_bitmap_end_sync(mddev->bitmap, sect,
-						   &sync_blocks, 1);
+
+				mddev->bitmap_ops->end_sync(mddev, sect,
+							    &sync_blocks);
 			}
 		} else {
 			/* completed sync */
@@ -3226,7 +3243,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			}
 			conf->fullsync = 0;
 		}
-		md_bitmap_close_sync(mddev->bitmap);
+		mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 		*skipped = 1;
 		return sectors_skipped;
@@ -3295,10 +3312,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		r10_bio = NULL;
 
 		for (i = 0 ; i < conf->geo.raid_disks; i++) {
-			int still_degraded;
+			bool still_degraded;
 			struct r10bio *rb2;
 			sector_t sect;
-			int must_sync;
+			bool must_sync;
 			int any_working;
 			struct raid10_info *mirror = &conf->mirrors[i];
 			struct md_rdev *mrdev, *mreplace;
@@ -3315,7 +3332,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (!mrdev && !mreplace)
 				continue;
 
-			still_degraded = 0;
+			still_degraded = false;
 			/* want to reconstruct this device */
 			rb2 = r10_bio;
 			sect = raid10_find_virt(conf, sector_nr, i);
@@ -3328,8 +3345,9 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			 * we only need to recover the block if it is set in
 			 * the bitmap
 			 */
-			must_sync = md_bitmap_start_sync(mddev->bitmap, sect,
-							 &sync_blocks, 1);
+			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
+								  &sync_blocks,
+								  true);
 			if (sync_blocks < max_sync)
 				max_sync = sync_blocks;
 			if (!must_sync &&
@@ -3367,13 +3385,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				struct md_rdev *rdev = conf->mirrors[j].rdev;
 
 				if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
-					still_degraded = 1;
+					still_degraded = false;
 					break;
 				}
 			}
 
-			must_sync = md_bitmap_start_sync(mddev->bitmap, sect,
-							 &sync_blocks, still_degraded);
+			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
+						&sync_blocks, still_degraded);
 
 			any_working = 0;
 			for (j=0; j<conf->copies;j++) {
@@ -3382,7 +3400,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				sector_t from_addr, to_addr;
 				struct md_rdev *rdev = conf->mirrors[d].rdev;
 				sector_t sector, first_bad;
-				int bad_sectors;
+				sector_t bad_sectors;
 				if (!rdev ||
 				    !test_bit(In_sync, &rdev->flags))
 					continue;
@@ -3546,12 +3564,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		 * safety reason, which ensures curr_resync_completed is
 		 * updated in bitmap_cond_end_sync.
 		 */
-		md_bitmap_cond_end_sync(mddev->bitmap, sector_nr,
+		mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
 					mddev_is_clustered(mddev) &&
 					(sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 
-		if (!md_bitmap_start_sync(mddev->bitmap, sector_nr,
-					  &sync_blocks, mddev->degraded) &&
+		if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
+						   &sync_blocks,
+						   mddev->degraded) &&
 		    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED,
 						 &mddev->recovery)) {
 			/* We can skip this block */
@@ -3577,7 +3596,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		for (i = 0; i < conf->copies; i++) {
 			int d = r10_bio->devs[i].devnum;
 			sector_t first_bad, sector;
-			int bad_sectors;
+			sector_t bad_sectors;
 			struct md_rdev *rdev;
 
 			if (r10_bio->devs[i].repl_bio)
@@ -3684,7 +3703,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			conf->cluster_sync_low = mddev->curr_resync_completed;
 			raid10_set_cluster_sync_high(conf);
 			/* Send resync message */
-			md_cluster_ops->resync_info_update(mddev,
+			mddev->cluster_ops->resync_info_update(mddev,
 						conf->cluster_sync_low,
 						conf->cluster_sync_high);
 		}
@@ -3717,7 +3736,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 		if (broadcast_msg) {
 			raid10_set_cluster_sync_high(conf);
-			md_cluster_ops->resync_info_update(mddev,
+			mddev->cluster_ops->resync_info_update(mddev,
 						conf->cluster_sync_low,
 						conf->cluster_sync_high);
 		}
@@ -3732,7 +3751,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		r10_bio->sectors = nr_sectors;
 
 		if (bio->bi_end_io == end_sync_read) {
-			md_sync_acct_bio(bio, nr_sectors);
 			bio->bi_status = 0;
 			submit_bio_noacct(bio);
 		}
@@ -3980,12 +3998,16 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 {
 	struct r10conf *conf = mddev->private;
 	struct queue_limits lim;
+	int err;
 
-	blk_set_stacking_limits(&lim);
+	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
-	mddev_stack_rdev_limits(mddev, &lim);
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err)
+		return err;
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
@@ -4058,9 +4080,12 @@ static int raid10_run(struct mddev *mddev)
 	}
 
 	if (!mddev_is_dm(conf->mddev)) {
-		ret = raid10_set_queue_limits(mddev);
-		if (ret)
+		int err = raid10_set_queue_limits(mddev);
+
+		if (err) {
+			ret = err;
 			goto out_free_conf;
+		}
 	}
 
 	/* need to check that every block has at least one working mirror */
@@ -4193,6 +4218,7 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	 */
 	struct r10conf *conf = mddev->private;
 	sector_t oldsize, size;
+	int ret;
 
 	if (mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -4205,11 +4231,11 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	if (mddev->external_size &&
 	    mddev->array_sectors > size)
 		return -EINVAL;
-	if (mddev->bitmap) {
-		int ret = md_bitmap_resize(mddev->bitmap, size, 0, 0);
-		if (ret)
-			return ret;
-	}
+
+	ret = mddev->bitmap_ops->resize(mddev, size, 0, false);
+	if (ret)
+		return ret;
+
 	md_set_array_sectors(mddev, size);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > oldsize) {
@@ -4475,7 +4501,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 		newsize = raid10_size(mddev, 0, conf->geo.raid_disks);
 
 		if (!mddev_is_clustered(mddev)) {
-			ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
+			ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
 			if (ret)
 				goto abort;
 			else
@@ -4490,20 +4516,20 @@ static int raid10_start_reshape(struct mddev *mddev)
 
 		/*
 		 * some node is already performing reshape, and no need to
-		 * call md_bitmap_resize again since it should be called when
+		 * call bitmap_ops->resize again since it should be called when
 		 * receiving BITMAP_RESIZE msg
 		 */
 		if ((sb && (le32_to_cpu(sb->feature_map) &
 			    MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize))
 			goto out;
 
-		ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
+		ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
 		if (ret)
 			goto abort;
 
-		ret = md_cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
+		ret = mddev->cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
 		if (ret) {
-			md_bitmap_resize(mddev->bitmap, oldsize, 0, 0);
+			mddev->bitmap_ops->resize(mddev, oldsize, 0, false);
 			goto abort;
 		}
 	}
@@ -4792,7 +4818,7 @@ read_more:
 				conf->cluster_sync_low = sb_reshape_pos;
 		}
 
-		md_cluster_ops->resync_info_update(mddev, conf->cluster_sync_low,
+		mddev->cluster_ops->resync_info_update(mddev, conf->cluster_sync_low,
 							  conf->cluster_sync_high);
 	}
 
@@ -4847,7 +4873,6 @@ read_more:
 	r10_bio->sectors = nr_sectors;
 
 	/* Now submit the read */
-	md_sync_acct_bio(read_bio, r10_bio->sectors);
 	atomic_inc(&r10_bio->remaining);
 	read_bio->bi_next = NULL;
 	submit_bio_noacct(read_bio);
@@ -4907,7 +4932,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			continue;
 
 		atomic_inc(&rdev->nr_pending);
-		md_sync_acct_bio(b, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
 		submit_bio_noacct(b);
@@ -4937,7 +4961,7 @@ static void raid10_update_reshape_pos(struct mddev *mddev)
 	struct r10conf *conf = mddev->private;
 	sector_t lo, hi;
 
-	md_cluster_ops->resync_info_get(mddev, &lo, &hi);
+	mddev->cluster_ops->resync_info_get(mddev, &lo, &hi);
 	if (((mddev->reshape_position <= hi) && (mddev->reshape_position >= lo))
 	    || mddev->reshape_position == MaxSector)
 		conf->reshape_progress = mddev->reshape_position;
@@ -5083,9 +5107,13 @@ static void raid10_finish_reshape(struct mddev *mddev)
 
 static struct md_personality raid10_personality =
 {
-	.name		= "raid10",
-	.level		= 10,
-	.owner		= THIS_MODULE,
+	.head = {
+		.type	= MD_PERSONALITY,
+		.id	= ID_RAID10,
+		.name	= "raid10",
+		.owner	= THIS_MODULE,
+	},
+
 	.make_request	= raid10_make_request,
 	.run		= raid10_run,
 	.free		= raid10_free,
@@ -5105,18 +5133,18 @@ static struct md_personality raid10_personality =
 	.update_reshape_pos = raid10_update_reshape_pos,
 };
 
-static int __init raid_init(void)
+static int __init raid10_init(void)
 {
-	return register_md_personality(&raid10_personality);
+	return register_md_submodule(&raid10_personality.head);
 }
 
-static void raid_exit(void)
+static void __exit raid10_exit(void)
 {
-	unregister_md_personality(&raid10_personality);
+	unregister_md_submodule(&raid10_personality.head);
 }
 
-module_init(raid_init);
-module_exit(raid_exit);
+module_init(raid10_init);
+module_exit(raid10_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD");
 MODULE_ALIAS("md-personality-9"); /* RAID10 */