1 files changed, 185 insertions, 172 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a5f8419e2df1..15b9ae5bf84d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
 static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
-#define raid10_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-
 #include "raid1-10.c"
 
 #define NULL_CMD
@@ -429,12 +426,9 @@ 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)
@@ -503,7 +497,6 @@ 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;
@@ -518,11 +511,7 @@ static void raid10_end_write_request(struct bio *bio)
 		 * The 'master' represents the composite IO operation to
 		 * user-side. So if something waits for IO, then it will
 		 * wait for the 'master' bio.
-		 */
-		sector_t first_bad;
-		int bad_sectors;
-
-		/*
+		 *
 		 * 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
@@ -535,10 +524,9 @@ static void raid10_end_write_request(struct bio *bio)
 			set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev,
-				r10_bio->devs[slot].addr,
-				r10_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				      r10_bio->sectors) &&
+		    !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
@@ -753,17 +741,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	best_good_sectors = 0;
 	do_balance = 1;
 	clear_bit(R10BIO_FailFast, &r10_bio->state);
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on (recovery is ok), or below
-	 * the resync window. We take the first readable disk when
-	 * above the resync window.
-	 */
-	if ((conf->mddev->recovery_cp < MaxSector
-	     && (this_sector + sectors >= conf->next_resync)) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	     md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-					    this_sector + sectors)))
+
+	if (raid1_should_read_first(conf->mddev, this_sector, sectors))
 		do_balance = 0;
 
 	for (slot = 0; slot < conf->copies ; slot++) {
@@ -901,7 +880,7 @@ 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 */
@@ -1033,7 +1012,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
 			ret = false;
 		} else {
 			conf->nr_waiting++;
-			raid10_log(conf->mddev, "wait barrier");
+			mddev_add_trace_msg(conf->mddev, "raid10 wait barrier");
 			wait_event_barrier(conf, stop_waiting_barrier(conf));
 			conf->nr_waiting--;
 		}
@@ -1117,7 +1096,7 @@ 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 */
@@ -1152,7 +1131,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 			bio_wouldblock_error(bio);
 			return false;
 		}
-		raid10_log(conf->mddev, "wait reshape");
+		mddev_add_trace_msg(conf->mddev, "raid10 wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
@@ -1175,6 +1154,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	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) {
 		/*
@@ -1222,6 +1202,10 @@ 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);
@@ -1249,12 +1233,14 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r10_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-	                              r10_bio->sector);
+	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,
@@ -1264,6 +1250,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	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;
+	const blk_opf_t do_atomic = bio->bi_opf & REQ_ATOMIC;
 	unsigned long flags;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev;
@@ -1282,16 +1269,13 @@ 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;
+	mbio->bi_opf = op | do_sync | do_fua | do_atomic;
 	if (!replacement && test_bit(FailFast,
 				     &conf->mirrors[devnum].rdev->flags)
 			 && enough(conf, devnum))
 		mbio->bi_opf |= MD_FAILFAST;
 	mbio->bi_private = r10_bio;
-
-	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
-				      r10_bio->sector);
+	mddev_trace_remap(mddev, mbio, r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_bdev = (void *)rdev;
 
@@ -1307,9 +1291,9 @@ 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;
@@ -1317,51 +1301,44 @@ 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)) {
-			sector_t first_bad;
+		if (rdev) {
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
-			int is_bad;
 
 			/*
 			 * Discard request doesn't care the write result
 			 * so it doesn't need to wait blocked disk here.
 			 */
-			if (!r10_bio->sectors)
-				continue;
-
-			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
-					     &first_bad, &bad_sectors);
-			if (is_bad < 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)) {
 		/* Have to wait for this device to get unblocked, then retry */
 		allow_barrier(conf);
-		raid10_log(conf->mddev, "%s wait rdev %d blocked",
-				__func__, blocked_rdev->raid_disk);
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 %s wait rdev %d blocked",
+			__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, false);
 		goto retry_wait;
@@ -1372,9 +1349,10 @@ 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,
@@ -1416,7 +1394,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid10_log(conf->mddev, "wait reshape metadata");
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
@@ -1454,10 +1433,8 @@ 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;
@@ -1474,18 +1451,24 @@ 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;
 			}
@@ -1506,6 +1489,10 @@ 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);
@@ -1517,7 +1504,6 @@ 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)
@@ -1526,6 +1512,26 @@ 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)
@@ -1667,6 +1673,11 @@ 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 */
@@ -1677,6 +1688,11 @@ 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 */
@@ -1861,8 +1877,7 @@ 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))
@@ -2108,9 +2123,6 @@ 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;
 
@@ -2131,10 +2143,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
 		rdev->raid_disk = mirror;
@@ -2150,10 +2161,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
-		err = 0;
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		conf->fullsync = 1;
 		WRITE_ONCE(p->replacement, rdev);
 	}
@@ -2290,8 +2300,6 @@ static void end_sync_write(struct bio *bio)
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
-	sector_t first_bad;
-	int bad_sectors;
 	int slot;
 	int repl;
 	struct md_rdev *rdev = NULL;
@@ -2312,11 +2320,10 @@ static void end_sync_write(struct bio *bio)
 					&rdev->mddev->recovery);
 			set_bit(R10BIO_WriteError, &r10_bio->state);
 		}
-	} else if (is_badblock(rdev,
-			     r10_bio->devs[slot].addr,
-			     r10_bio->sectors,
-			     &first_bad, &bad_sectors))
+	} else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				     r10_bio->sectors)) {
 		set_bit(R10BIO_MadeGood, &r10_bio->state);
+	}
 
 	rdev_dec_pending(rdev, mddev);
 
@@ -2499,7 +2506,7 @@ 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,
@@ -2597,11 +2604,8 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
-	sector_t first_bad;
-	int bad_sectors;
-
-	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
-	    && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
+	if (rdev_has_badblock(rdev, sector, sectors) &&
+	    (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
 	if (sync_page_io(rdev, sector, sectors << 9, page, op, false))
 		/* success */
@@ -2658,16 +2662,14 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			d = r10_bio->devs[sl].devnum;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
-			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev,
+					      r10_bio->devs[sl].addr + sect,
+					      s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
@@ -2947,11 +2949,8 @@ 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;
@@ -3010,8 +3009,6 @@ 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))
@@ -3175,12 +3172,12 @@ 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;
@@ -3210,10 +3207,6 @@ 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;
@@ -3235,13 +3228,15 @@ 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 */
@@ -3261,7 +3256,7 @@ 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;
@@ -3330,10 +3325,10 @@ 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;
@@ -3350,7 +3345,7 @@ 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);
@@ -3363,8 +3358,9 @@ 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 &&
@@ -3402,13 +3398,13 @@ 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++) {
@@ -3581,12 +3577,13 @@ 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 */
@@ -4002,14 +3999,30 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid10_set_io_opt(struct r10conf *conf)
+static unsigned int raid10_nr_stripes(struct r10conf *conf)
 {
-	int raid_disks = conf->geo.raid_disks;
+	unsigned int raid_disks = conf->geo.raid_disks;
 
-	if (!(conf->geo.raid_disks % conf->geo.near_copies))
-		raid_disks /= conf->geo.near_copies;
-	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
-			 raid_disks);
+	if (conf->geo.raid_disks % conf->geo.near_copies)
+		return raid_disks;
+	return raid_disks / conf->geo.near_copies;
+}
+
+static int raid10_set_queue_limits(struct mddev *mddev)
+{
+	struct r10conf *conf = mddev->private;
+	struct queue_limits lim;
+	int err;
+
+	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);
+	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);
 }
 
 static int raid10_run(struct mddev *mddev)
@@ -4021,6 +4034,7 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -4047,12 +4061,6 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		raid10_set_io_opt(conf);
-	}
-
 	rdev_for_each(rdev, mddev) {
 		long long diff;
 
@@ -4081,14 +4089,19 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
 		disk->head_position = 0;
 		first = 0;
 	}
 
+	if (!mddev_is_dm(conf->mddev)) {
+		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 */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
@@ -4185,7 +4198,7 @@ out_free_conf:
 	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
-	return -EIO;
+	return ret;
 }
 
 static void raid10_free(struct mddev *mddev, void *priv)
@@ -4219,6 +4232,7 @@ 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;
@@ -4231,11 +4245,11 @@ 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) {
@@ -4501,7 +4515,7 @@ 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
@@ -4516,20 +4530,20 @@ 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);
 		if (ret) {
-			md_bitmap_resize(mddev->bitmap, oldsize, 0, 0);
+			mddev->bitmap_ops->resize(mddev, oldsize, 0, false);
 			goto abort;
 		}
 	}
@@ -4954,8 +4968,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (conf->mddev->queue)
-		raid10_set_io_opt(conf);
+	mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf));
 	conf->fullsync = 0;
 }