1 files changed, 502 insertions, 375 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 286f8b16c7bd..10ea3af40991 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -46,9 +46,6 @@
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
-#define raid1_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
-
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
@@ -414,18 +411,18 @@ static void raid1_end_read_request(struct bio *bio)
 
 static void close_write(struct r1bio *r1_bio)
 {
+	struct mddev *mddev = r1_bio->mddev;
+
 	/* it really is the end of this request */
 	if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
 		bio_free_pages(r1_bio->behind_master_bio);
 		bio_put(r1_bio->behind_master_bio);
 		r1_bio->behind_master_bio = NULL;
 	}
-	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
-			   r1_bio->sectors,
-			   !test_bit(R1BIO_Degraded, &r1_bio->state),
-			   test_bit(R1BIO_BehindIO, &r1_bio->state));
-	md_write_end(r1_bio->mddev);
+
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->end_behind_write(mddev);
+	md_write_end(mddev);
 }
 
 static void r1_bio_write_done(struct r1bio *r1_bio)
@@ -481,8 +478,6 @@ static void raid1_end_write_request(struct bio *bio)
 		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
 		else {
-			/* Fail the request */
-			set_bit(R1BIO_Degraded, &r1_bio->state);
 			/* Finished with this branch */
 			r1_bio->bios[mirror] = NULL;
 			to_put = bio;
@@ -498,9 +493,6 @@ static void raid1_end_write_request(struct bio *bio)
 		 * to user-side. So if something waits for IO, then it
 		 * will wait for the 'master' bio.
 		 */
-		sector_t first_bad;
-		int bad_sectors;
-
 		r1_bio->bios[mirror] = NULL;
 		to_put = bio;
 		/*
@@ -516,8 +508,8 @@ static void raid1_end_write_request(struct bio *bio)
 			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		    !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -582,211 +574,319 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector,
 	return len;
 }
 
-/*
- * This routine returns the disk from which the requested read should
- * be done. There is a per-array 'next expected sequential IO' sector
- * number - if this matches on the next IO then we use the last disk.
- * There is also a per-disk 'last know head position' sector that is
- * maintained from IRQ contexts, both the normal and the resync IO
- * completion handlers update this position correctly. If there is no
- * perfect sequential match then we pick the disk whose head is closest.
- *
- * If there are 2 mirrors in the same 2 devices, performance degrades
- * because position is mirror, not device based.
- *
- * The rdev for the device selected will have nr_pending incremented.
- */
-static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
+static void update_read_sectors(struct r1conf *conf, int disk,
+				sector_t this_sector, int len)
 {
-	const sector_t this_sector = r1_bio->sector;
-	int sectors;
-	int best_good_sectors;
-	int best_disk, best_dist_disk, best_pending_disk;
-	int has_nonrot_disk;
+	struct raid1_info *info = &conf->mirrors[disk];
+
+	atomic_inc(&info->rdev->nr_pending);
+	if (info->next_seq_sect != this_sector)
+		info->seq_start = this_sector;
+	info->next_seq_sect = this_sector + len;
+}
+
+static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			     int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int len = r1_bio->sectors;
 	int disk;
-	sector_t best_dist;
-	unsigned int min_pending;
-	struct md_rdev *rdev;
-	int choose_first;
-	int choose_next_idle;
 
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on, or below the resync window.
-	 * We take the first readable disk when above the resync window.
-	 */
- retry:
-	sectors = r1_bio->sectors;
-	best_disk = -1;
-	best_dist_disk = -1;
-	best_dist = MaxSector;
-	best_pending_disk = -1;
-	min_pending = UINT_MAX;
-	best_good_sectors = 0;
-	has_nonrot_disk = 0;
-	choose_next_idle = 0;
-	clear_bit(R1BIO_FailFast, &r1_bio->state);
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int read_len;
 
-	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-		    this_sector + sectors)))
-		choose_first = 1;
-	else
-		choose_first = 0;
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags))
+			continue;
+
+		/* choose the first disk even if it has some bad blocks. */
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > 0) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			*max_sectors = read_len;
+			return disk;
+		}
+	}
+
+	return -1;
+}
+
+static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+	return !test_bit(In_sync, &rdev->flags) &&
+	       rdev->recovery_offset < r1_bio->sector + r1_bio->sectors;
+}
+
+static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			  int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int best_disk = -1;
+	int best_len = 0;
+	int disk;
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
-		sector_t dist;
-		sector_t first_bad;
-		int bad_sectors;
-		unsigned int pending;
-		bool nonrot;
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
 
 		rdev = conf->mirrors[disk].rdev;
-		if (r1_bio->bios[disk] == IO_BLOCKED
-		    || rdev == NULL
-		    || test_bit(Faulty, &rdev->flags))
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    rdev_in_recovery(rdev, r1_bio) ||
+		    test_bit(WriteMostly, &rdev->flags))
 			continue;
-		if (!test_bit(In_sync, &rdev->flags) &&
-		    rdev->recovery_offset < this_sector + sectors)
+
+		/* keep track of the disk with the most readable sectors. */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > best_len) {
+			best_disk = disk;
+			best_len = read_len;
+		}
+	}
+
+	if (best_disk != -1) {
+		*max_sectors = best_len;
+		update_read_sectors(conf, best_disk, this_sector, best_len);
+	}
+
+	return best_disk;
+}
+
+static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			    int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int bb_disk = -1;
+	int bb_read_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
 			continue;
-		if (test_bit(WriteMostly, &rdev->flags)) {
-			/* Don't balance among write-mostly, just
-			 * use the first as a last resort */
-			if (best_dist_disk < 0) {
-				if (is_badblock(rdev, this_sector, sectors,
-						&first_bad, &bad_sectors)) {
-					if (first_bad <= this_sector)
-						/* Cannot use this */
-						continue;
-					best_good_sectors = first_bad - this_sector;
-				} else
-					best_good_sectors = sectors;
-				best_dist_disk = disk;
-				best_pending_disk = disk;
-			}
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(WriteMostly, &rdev->flags) ||
+		    rdev_in_recovery(rdev, r1_bio))
 			continue;
+
+		/* there are no bad blocks, we can use this disk */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len == r1_bio->sectors) {
+			*max_sectors = read_len;
+			update_read_sectors(conf, disk, this_sector, read_len);
+			return disk;
 		}
-		/* This is a reasonable device to use.  It might
-		 * even be best.
+
+		/*
+		 * there are partial bad blocks, choose the rdev with largest
+		 * read length.
 		 */
-		if (is_badblock(rdev, this_sector, sectors,
-				&first_bad, &bad_sectors)) {
-			if (best_dist < MaxSector)
-				/* already have a better device */
-				continue;
-			if (first_bad <= this_sector) {
-				/* cannot read here. If this is the 'primary'
-				 * device, then we must not read beyond
-				 * bad_sectors from another device..
-				 */
-				bad_sectors -= (this_sector - first_bad);
-				if (choose_first && sectors > bad_sectors)
-					sectors = bad_sectors;
-				if (best_good_sectors > sectors)
-					best_good_sectors = sectors;
-
-			} else {
-				sector_t good_sectors = first_bad - this_sector;
-				if (good_sectors > best_good_sectors) {
-					best_good_sectors = good_sectors;
-					best_disk = disk;
-				}
-				if (choose_first)
-					break;
-			}
-			continue;
-		} else {
-			if ((sectors > best_good_sectors) && (best_disk >= 0))
-				best_disk = -1;
-			best_good_sectors = sectors;
+		if (read_len > bb_read_len) {
+			bb_disk = disk;
+			bb_read_len = read_len;
 		}
+	}
+
+	if (bb_disk != -1) {
+		*max_sectors = bb_read_len;
+		update_read_sectors(conf, bb_disk, this_sector, bb_read_len);
+	}
+
+	return bb_disk;
+}
+
+static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
+{
+	/* TODO: address issues with this check and concurrency. */
+	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	       conf->mirrors[disk].head_position == r1_bio->sector;
+}
+
+/*
+ * If buffered sequential IO size exceeds optimal iosize, check if there is idle
+ * disk. If yes, choose the idle disk.
+ */
+static bool should_choose_next(struct r1conf *conf, int disk)
+{
+	struct raid1_info *mirror = &conf->mirrors[disk];
+	int opt_iosize;
+
+	if (!test_bit(Nonrot, &mirror->rdev->flags))
+		return false;
+
+	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
+	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
+	       mirror->next_seq_sect > opt_iosize &&
+	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+}
+
+static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+	if (!rdev || test_bit(Faulty, &rdev->flags))
+		return false;
+
+	if (rdev_in_recovery(rdev, r1_bio))
+		return false;
+
+	/* don't read from slow disk unless have to */
+	if (test_bit(WriteMostly, &rdev->flags))
+		return false;
+
+	/* don't split IO for bad blocks unless have to */
+	if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors))
+		return false;
+
+	return true;
+}
+
+struct read_balance_ctl {
+	sector_t closest_dist;
+	int closest_dist_disk;
+	int min_pending;
+	int min_pending_disk;
+	int sequential_disk;
+	int readable_disks;
+};
+
+static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio)
+{
+	int disk;
+	struct read_balance_ctl ctl = {
+		.closest_dist_disk      = -1,
+		.closest_dist           = MaxSector,
+		.min_pending_disk       = -1,
+		.min_pending            = UINT_MAX,
+		.sequential_disk	= -1,
+	};
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		sector_t dist;
+		unsigned int pending;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
 
-		if (best_disk >= 0)
-			/* At least two disks to choose from so failfast is OK */
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev_readable(rdev, r1_bio))
+			continue;
+
+		/* At least two disks to choose from so failfast is OK */
+		if (ctl.readable_disks++ == 1)
 			set_bit(R1BIO_FailFast, &r1_bio->state);
 
-		nonrot = bdev_nonrot(rdev->bdev);
-		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
-		dist = abs(this_sector - conf->mirrors[disk].head_position);
-		if (choose_first) {
-			best_disk = disk;
-			break;
-		}
+		dist = abs(r1_bio->sector - conf->mirrors[disk].head_position);
+
 		/* Don't change to another disk for sequential reads */
-		if (conf->mirrors[disk].next_seq_sect == this_sector
-		    || dist == 0) {
-			int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
-			struct raid1_info *mirror = &conf->mirrors[disk];
+		if (is_sequential(conf, disk, r1_bio)) {
+			if (!should_choose_next(conf, disk))
+				return disk;
 
-			best_disk = disk;
 			/*
-			 * If buffered sequential IO size exceeds optimal
-			 * iosize, check if there is idle disk. If yes, choose
-			 * the idle disk. read_balance could already choose an
-			 * idle disk before noticing it's a sequential IO in
-			 * this disk. This doesn't matter because this disk
-			 * will idle, next time it will be utilized after the
-			 * first disk has IO size exceeds optimal iosize. In
-			 * this way, iosize of the first disk will be optimal
-			 * iosize at least. iosize of the second disk might be
-			 * small, but not a big deal since when the second disk
-			 * starts IO, the first disk is likely still busy.
+			 * Add 'pending' to avoid choosing this disk if
+			 * there is other idle disk.
 			 */
-			if (nonrot && opt_iosize > 0 &&
-			    mirror->seq_start != MaxSector &&
-			    mirror->next_seq_sect > opt_iosize &&
-			    mirror->next_seq_sect - opt_iosize >=
-			    mirror->seq_start) {
-				choose_next_idle = 1;
-				continue;
-			}
-			break;
+			pending++;
+			/*
+			 * If there is no other idle disk, this disk
+			 * will be chosen.
+			 */
+			ctl.sequential_disk = disk;
 		}
 
-		if (choose_next_idle)
-			continue;
-
-		if (min_pending > pending) {
-			min_pending = pending;
-			best_pending_disk = disk;
+		if (ctl.min_pending > pending) {
+			ctl.min_pending = pending;
+			ctl.min_pending_disk = disk;
 		}
 
-		if (dist < best_dist) {
-			best_dist = dist;
-			best_dist_disk = disk;
+		if (ctl.closest_dist > dist) {
+			ctl.closest_dist = dist;
+			ctl.closest_dist_disk = disk;
 		}
 	}
 
 	/*
+	 * sequential IO size exceeds optimal iosize, however, there is no other
+	 * idle disk, so choose the sequential disk.
+	 */
+	if (ctl.sequential_disk != -1 && ctl.min_pending != 0)
+		return ctl.sequential_disk;
+
+	/*
 	 * If all disks are rotational, choose the closest disk. If any disk is
 	 * non-rotational, choose the disk with less pending request even the
 	 * disk is rotational, which might/might not be optimal for raids with
 	 * mixed ratation/non-rotational disks depending on workload.
 	 */
-	if (best_disk == -1) {
-		if (has_nonrot_disk || min_pending == 0)
-			best_disk = best_pending_disk;
-		else
-			best_disk = best_dist_disk;
-	}
+	if (ctl.min_pending_disk != -1 &&
+	    (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0))
+		return ctl.min_pending_disk;
+	else
+		return ctl.closest_dist_disk;
+}
 
-	if (best_disk >= 0) {
-		rdev = conf->mirrors[best_disk].rdev;
-		if (!rdev)
-			goto retry;
-		atomic_inc(&rdev->nr_pending);
-		sectors = best_good_sectors;
+/*
+ * This routine returns the disk from which the requested read should be done.
+ *
+ * 1) If resync is in progress, find the first usable disk and use it even if it
+ * has some bad blocks.
+ *
+ * 2) Now that there is no resync, loop through all disks and skipping slow
+ * disks and disks with bad blocks for now. Only pay attention to key disk
+ * choice.
+ *
+ * 3) If we've made it this far, now look for disks with bad blocks and choose
+ * the one with most number of sectors.
+ *
+ * 4) If we are all the way at the end, we have no choice but to use a disk even
+ * if it is write mostly.
+ *
+ * The rdev for the device selected will have nr_pending incremented.
+ */
+static int read_balance(struct r1conf *conf, struct r1bio *r1_bio,
+			int *max_sectors)
+{
+	int disk;
+
+	clear_bit(R1BIO_FailFast, &r1_bio->state);
 
-		if (conf->mirrors[best_disk].next_seq_sect != this_sector)
-			conf->mirrors[best_disk].seq_start = this_sector;
+	if (raid1_should_read_first(conf->mddev, r1_bio->sector,
+				    r1_bio->sectors))
+		return choose_first_rdev(conf, r1_bio, max_sectors);
 
-		conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
+	disk = choose_best_rdev(conf, r1_bio);
+	if (disk >= 0) {
+		*max_sectors = r1_bio->sectors;
+		update_read_sectors(conf, disk, r1_bio->sector,
+				    r1_bio->sectors);
+		return disk;
 	}
-	*max_sectors = sectors;
 
-	return best_disk;
+	/*
+	 * If we are here it means we didn't find a perfectly good disk so
+	 * now spend a bit more time trying to find one with the most good
+	 * sectors.
+	 */
+	disk = choose_bb_rdev(conf, r1_bio, max_sectors);
+	if (disk >= 0)
+		return disk;
+
+	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
 static void wake_up_barrier(struct r1conf *conf)
@@ -798,7 +898,7 @@ static void wake_up_barrier(struct r1conf *conf)
 static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 {
 	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
-	raid1_prepare_flush_writes(conf->mddev->bitmap);
+	raid1_prepare_flush_writes(conf->mddev);
 	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
@@ -1098,7 +1198,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
-	raid1_log(conf->mddev, "wait freeze");
+	mddev_add_trace_msg(conf->mddev, "raid1 wait freeze");
 	wait_event_lock_irq_cmd(
 		conf->wait_barrier,
 		get_unqueued_pending(conf) == extra,
@@ -1215,13 +1315,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
 	struct bio *read_bio;
-	struct bitmap *bitmap = mddev->bitmap;
 	const enum req_op op = bio_op(bio);
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
-	int rdisk;
+	int rdisk, error;
 	bool r1bio_existed = !!r1_bio;
-	char b[BDEVNAME_SIZE];
 
 	/*
 	 * If r1_bio is set, we are blocking the raid1d thread
@@ -1230,16 +1328,6 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 */
 	gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
-	if (r1bio_existed) {
-		/* Need to get the block device name carefully */
-		struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
-
-		if (rdev)
-			snprintf(b, sizeof(b), "%pg", rdev->bdev);
-		else
-			strcpy(b, "???");
-	}
-
 	/*
 	 * Still need barrier for READ in case that whole
 	 * array is frozen.
@@ -1261,15 +1349,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 * used and no empty request is available.
 	 */
 	rdisk = read_balance(conf, r1_bio, &max_sectors);
-
 	if (rdisk < 0) {
 		/* couldn't find anywhere to read from */
-		if (r1bio_existed) {
-			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
+		if (r1bio_existed)
+			pr_crit_ratelimited("md/raid1:%s: %pg: unrecoverable I/O read error for block %llu\n",
 					    mdname(mddev),
-					    b,
-					    (unsigned long long)r1_bio->sector);
-		}
+					    conf->mirrors[r1_bio->read_disk].rdev->bdev,
+					    r1_bio->sector);
 		raid_end_bio_io(r1_bio);
 		return;
 	}
@@ -1281,20 +1367,23 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 				    (unsigned long long)r1_bio->sector,
 				    mirror->rdev->bdev);
 
-	if (test_bit(WriteMostly, &mirror->rdev->flags) &&
-	    bitmap) {
+	if (test_bit(WriteMostly, &mirror->rdev->flags)) {
 		/*
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
-		raid1_log(mddev, "wait behind writes");
-		wait_event(bitmap->behind_wait,
-			   atomic_read(&bitmap->behind_writes) == 0);
+		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
+		mddev->bitmap_ops->wait_behind_writes(mddev);
 	}
 
 	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);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1320,12 +1409,49 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r1_bio;
+	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
+	submit_bio_noacct(read_bio);
+	return;
 
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-				      r1_bio->sector);
+err_handle:
+	atomic_dec(&mirror->rdev->nr_pending);
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
+}
 
-	submit_bio_noacct(read_bio);
+static bool wait_blocked_rdev(struct mddev *mddev, struct bio *bio)
+{
+	struct r1conf *conf = mddev->private;
+	int disks = conf->raid_disks * 2;
+	int i;
+
+retry:
+	for (i = 0; i < disks; i++) {
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
+
+		if (!rdev)
+			continue;
+
+		/* don't write here until the bad block is acknowledged */
+		if (test_bit(WriteErrorSeen, &rdev->flags) &&
+		    rdev_has_badblock(rdev, bio->bi_iter.bi_sector,
+				      bio_sectors(bio)) < 0)
+			set_bit(BlockedBadBlocks, &rdev->flags);
+
+		if (rdev_blocked(rdev)) {
+			if (bio->bi_opf & REQ_NOWAIT)
+				return false;
+
+			mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked",
+					    rdev->raid_disk);
+			atomic_inc(&rdev->nr_pending);
+			md_wait_for_blocked_rdev(rdev, rdev->mddev);
+			goto retry;
+		}
+	}
+
+	return true;
 }
 
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
@@ -1333,10 +1459,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
-	int i, disks;
-	struct bitmap *bitmap = mddev->bitmap;
+	int i, disks, k, error;
 	unsigned long flags;
-	struct md_rdev *blocked_rdev;
 	int first_clone;
 	int max_sectors;
 	bool write_behind = false;
@@ -1374,7 +1498,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		return;
 	}
 
- retry_write:
+	if (!wait_blocked_rdev(mddev, bio)) {
+		bio_wouldblock_error(bio);
+		return;
+	}
+
 	r1_bio = alloc_r1bio(mddev, bio);
 	r1_bio->sectors = max_write_sectors;
 
@@ -1390,7 +1518,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 */
 
 	disks = conf->raid_disks * 2;
-	blocked_rdev = NULL;
 	max_sectors = r1_bio->sectors;
 	for (i = 0;  i < disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
@@ -1403,17 +1530,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags))
 			write_behind = true;
 
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
-			if (i < conf->raid_disks)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
-		}
 
 		atomic_inc(&rdev->nr_pending);
 		if (test_bit(WriteErrorSeen, &rdev->flags)) {
@@ -1423,13 +1542,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 			is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
 					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
-				/* mustn't write here until the bad block is
-				 * acknowledged*/
-				set_bit(BlockedBadBlocks, &rdev->flags);
-				blocked_rdev = rdev;
-				break;
-			}
 			if (is_bad && first_bad <= r1_bio->sector) {
 				/* Cannot write here at all */
 				bad_sectors -= (r1_bio->sector - first_bad);
@@ -1439,20 +1551,24 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 					 */
 					max_sectors = bad_sectors;
 				rdev_dec_pending(rdev, mddev);
-				/* We don't set R1BIO_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 - r1_bio->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 - r1_bio->sector;
 				if (good_sectors < max_sectors)
 					max_sectors = good_sectors;
 			}
@@ -1460,38 +1576,23 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		r1_bio->bios[i] = bio;
 	}
 
-	if (unlikely(blocked_rdev)) {
-		/* Wait for this device to become unblocked */
-		int j;
-
-		for (j = 0; j < i; j++)
-			if (r1_bio->bios[j])
-				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-		free_r1bio(r1_bio);
-		allow_barrier(conf, bio->bi_iter.bi_sector);
-
-		if (bio->bi_opf & REQ_NOWAIT) {
-			bio_wouldblock_error(bio);
-			return;
-		}
-		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
-		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf, bio->bi_iter.bi_sector, false);
-		goto retry_write;
-	}
-
 	/*
 	 * When using a bitmap, we may call alloc_behind_master_bio below.
 	 * alloc_behind_master_bio allocates a copy of the data payload a page
 	 * at a time and thus needs a new bio that can fit the whole payload
 	 * this bio in page sized chunks.
 	 */
-	if (write_behind && bitmap)
+	if (write_behind && mddev->bitmap)
 		max_sectors = min_t(int, max_sectors,
 				    BIO_MAX_VECS * (PAGE_SIZE >> 9));
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      GFP_NOIO, &conf->bio_split);
+
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1513,19 +1614,22 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			continue;
 
 		if (first_clone) {
+			unsigned long max_write_behind =
+				mddev->bitmap_info.max_write_behind;
+			struct md_bitmap_stats stats;
+			int err;
+
 			/* do behind I/O ?
 			 * Not if there are too many, or cannot
 			 * allocate memory, or a reader on WriteMostly
 			 * is waiting for behind writes to flush */
-			if (bitmap && write_behind &&
-			    (atomic_read(&bitmap->behind_writes)
-			     < mddev->bitmap_info.max_write_behind) &&
-			    !waitqueue_active(&bitmap->behind_wait)) {
+			err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats);
+			if (!err && write_behind && !stats.behind_wait &&
+			    stats.behind_writes < max_write_behind)
 				alloc_behind_master_bio(r1_bio, bio);
-			}
 
-			md_bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors,
-					     test_bit(R1BIO_BehindIO, &r1_bio->state));
+			if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+				mddev->bitmap_ops->start_behind_write(mddev);
 			first_clone = 0;
 		}
 
@@ -1549,7 +1653,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 		mbio->bi_iter.bi_sector	= (r1_bio->sector + rdev->data_offset);
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
+		mbio->bi_opf = bio_op(bio) |
+			(bio->bi_opf & (REQ_SYNC | REQ_FUA | REQ_ATOMIC));
 		if (test_bit(FailFast, &rdev->flags) &&
 		    !test_bit(WriteMostly, &rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)
@@ -1557,10 +1662,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
+		mddev_trace_remap(mddev, mbio, r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
 		if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
@@ -1575,6 +1677,18 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	/* In case raid1d snuck in to freeze_array */
 	wake_up_barrier(conf);
+	return;
+err_handle:
+	for (k = 0; k < i; k++) {
+		if (r1_bio->bios[k]) {
+			rdev_dec_pending(conf->mirrors[k].rdev, mddev);
+			r1_bio->bios[k] = NULL;
+		}
+	}
+
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
@@ -1598,8 +1712,7 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
-		if (!md_write_start(mddev,bio))
-			return false;
+		md_write_start(mddev,bio);
 		raid1_write_request(mddev, bio, sectors);
 	}
 	return true;
@@ -1760,6 +1873,52 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
+static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk,
+			   bool replacement)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+
+	if (replacement)
+		info += conf->raid_disks;
+
+	if (info->rdev)
+		return false;
+
+	if (bdev_nonrot(rdev->bdev)) {
+		set_bit(Nonrot, &rdev->flags);
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1);
+	}
+
+	rdev->raid_disk = disk;
+	info->head_position = 0;
+	info->seq_start = MaxSector;
+	WRITE_ONCE(info->rdev, rdev);
+
+	return true;
+}
+
+static bool raid1_remove_conf(struct r1conf *conf, int disk)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+	struct md_rdev *rdev = info->rdev;
+
+	if (!rdev || test_bit(In_sync, &rdev->flags) ||
+	    atomic_read(&rdev->nr_pending))
+		return false;
+
+	/* Only remove non-faulty devices if recovery is not possible. */
+	if (!test_bit(Faulty, &rdev->flags) &&
+	    rdev->mddev->recovery_disabled != conf->recovery_disabled &&
+	    rdev->mddev->degraded < conf->raid_disks)
+		return false;
+
+	if (test_and_clear_bit(Nonrot, &rdev->flags))
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1);
+
+	WRITE_ONCE(info->rdev, NULL);
+	return true;
+}
+
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1772,9 +1931,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -1791,19 +1947,16 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			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;
-			rdev->raid_disk = mirror;
-			err = 0;
+			raid1_add_conf(conf, rdev, mirror, false);
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
 			if (rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
-			WRITE_ONCE(p->rdev, rdev);
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
@@ -1813,13 +1966,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (err && repl_slot >= 0) {
 		/* Add this device as a replacement */
-		p = conf->mirrors + repl_slot;
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
-		rdev->raid_disk = repl_slot;
+		raid1_add_conf(conf, rdev, repl_slot, true);
 		err = 0;
 		conf->fullsync = 1;
-		WRITE_ONCE(p[conf->raid_disks].rdev, rdev);
 	}
 
 	print_conf(conf);
@@ -1836,27 +1987,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (unlikely(number >= conf->raid_disks))
 		goto abort;
 
-	if (rdev != p->rdev)
-		p = conf->mirrors + conf->raid_disks + number;
+	if (rdev != p->rdev) {
+		number += conf->raid_disks;
+		p = conf->mirrors + number;
+	}
 
 	print_conf(conf);
 	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
+		if (!raid1_remove_conf(conf, number)) {
 			err = -EBUSY;
 			goto abort;
 		}
-		/* Only remove non-faulty devices if recovery
-		 * is not possible.
-		 */
-		if (!test_bit(Faulty, &rdev->flags) &&
-		    mddev->recovery_disabled != conf->recovery_disabled &&
-		    mddev->degraded < conf->raid_disks) {
-			err = -EBUSY;
-			goto abort;
-		}
-		WRITE_ONCE(p->rdev, NULL);
-		if (conf->mirrors[conf->raid_disks + number].rdev) {
+
+		if (number < conf->raid_disks &&
+		    conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
 			 * doing this to avoid confusion.
@@ -1916,7 +2060,7 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
 
 	/* make sure these bits don't get cleared. */
 	do {
-		md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1);
+		mddev->bitmap_ops->end_sync(mddev, s, &sync_blocks);
 		s += sync_blocks;
 		sectors_to_go -= sync_blocks;
 	} while (sectors_to_go > 0);
@@ -1944,8 +2088,6 @@ static void end_sync_write(struct bio *bio)
 	struct r1bio *r1_bio = get_resync_r1bio(bio);
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
-	sector_t first_bad;
-	int bad_sectors;
 	struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
 
 	if (!uptodate) {
@@ -1955,14 +2097,11 @@ static void end_sync_write(struct bio *bio)
 			set_bit(MD_RECOVERY_NEEDED, &
 				mddev->recovery);
 		set_bit(R1BIO_WriteError, &r1_bio->state);
-	} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-			       &first_bad, &bad_sectors) &&
-		   !is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
-				r1_bio->sector,
-				r1_bio->sectors,
-				&first_bad, &bad_sectors)
-		)
+	} else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		   !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev,
+				      r1_bio->sector, r1_bio->sectors)) {
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
+	}
 
 	put_sync_write_buf(r1_bio, uptodate);
 }
@@ -2279,16 +2418,12 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
 			      rdev->recovery_offset >= sect + s)) &&
-			    is_badblock(rdev, sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev, sect, s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, false))
@@ -2461,12 +2596,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * errors.
 			 */
 			fail = true;
-			if (!narrow_write_error(r1_bio, m)) {
+			if (!narrow_write_error(r1_bio, m))
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
 				/* an I/O failed, we can't clear the bitmap */
-				set_bit(R1BIO_Degraded, &r1_bio->state);
-			}
 			rdev_dec_pending(conf->mirrors[m].rdev,
 					 conf->mddev);
 		}
@@ -2557,8 +2690,6 @@ static void raid1d(struct md_thread *thread)
 			list_del(&r1_bio->retry_list);
 			idx = sector_to_idx(r1_bio->sector);
 			atomic_dec(&conf->nr_queued[idx]);
-			if (mddev->degraded)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
 			if (test_bit(R1BIO_WriteError, &r1_bio->state))
 				close_write(r1_bio);
 			raid_end_bio_io(r1_bio);
@@ -2643,18 +2774,18 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
  */
 
 static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
-				   int *skipped)
+				   sector_t max_sector, int *skipped)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 	struct bio *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int disk = -1;
 	int i;
 	int wonly = -1;
 	int write_targets = 0, read_targets = 0;
 	sector_t sync_blocks;
-	int still_degraded = 0;
+	bool still_degraded = false;
 	int good_sectors = RESYNC_SECTORS;
 	int min_bad = 0; /* number of sectors that are bad in all devices */
 	int idx = sector_to_idx(sector_nr);
@@ -2664,7 +2795,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (init_resync(conf))
 			return 0;
 
-	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
@@ -2672,12 +2802,12 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		 * We can find the current addess in mddev->curr_resync
 		 */
 		if (mddev->curr_resync < max_sector) /* aborted */
-			md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
-					   &sync_blocks, 1);
+			mddev->bitmap_ops->end_sync(mddev, mddev->curr_resync,
+						    &sync_blocks);
 		else /* completed sync */
 			conf->fullsync = 0;
 
-		md_bitmap_close_sync(mddev->bitmap);
+		mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 
 		if (mddev_is_clustered(mddev)) {
@@ -2697,7 +2827,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	/* before building a request, check if we can skip these blocks..
 	 * This call the bitmap_start_sync doesn't actually record anything
 	 */
-	if (!md_bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	if (!mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, true) &&
 	    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
 		/* We can skip this block, and probably several more */
 		*skipped = 1;
@@ -2715,9 +2845,9 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	 * sector_nr + two times RESYNC_SECTORS
 	 */
 
-	md_bitmap_cond_end_sync(mddev->bitmap, sector_nr,
-		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
-
+	mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
+		mddev_is_clustered(mddev) &&
+		(sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 
 	if (raise_barrier(conf, sector_nr))
 		return 0;
@@ -2748,7 +2878,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
-				still_degraded = 1;
+				still_degraded = true;
 		} else if (!test_bit(In_sync, &rdev->flags)) {
 			bio->bi_opf = REQ_OP_WRITE;
 			bio->bi_end_io = end_sync_write;
@@ -2872,8 +3002,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (len == 0)
 			break;
 		if (sync_blocks == 0) {
-			if (!md_bitmap_start_sync(mddev->bitmap, sector_nr,
-						  &sync_blocks, still_degraded) &&
+			if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
+						&sync_blocks, still_degraded) &&
 			    !conf->fullsync &&
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
@@ -3006,23 +3136,17 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
+	conf->raid_disks = mddev->raid_disks;
 	rdev_for_each(rdev, mddev) {
 		int disk_idx = rdev->raid_disk;
-		if (disk_idx >= mddev->raid_disks
-		    || disk_idx < 0)
+
+		if (disk_idx >= conf->raid_disks || disk_idx < 0)
 			continue;
-		if (test_bit(Replacement, &rdev->flags))
-			disk = conf->mirrors + mddev->raid_disks + disk_idx;
-		else
-			disk = conf->mirrors + disk_idx;
 
-		if (disk->rdev)
+		if (!raid1_add_conf(conf, rdev, disk_idx,
+				    test_bit(Replacement, &rdev->flags)))
 			goto abort;
-		disk->rdev = rdev;
-		disk->head_position = 0;
-		disk->seq_start = MaxSector;
 	}
-	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
 	INIT_LIST_HEAD(&conf->bio_end_io_list);
@@ -3086,12 +3210,24 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid1_free(struct mddev *mddev, void *priv);
+static int raid1_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+	int err;
+
+	md_init_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	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 raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
 	int i;
-	struct md_rdev *rdev;
 	int ret;
 
 	if (mddev->level != 1) {
@@ -3118,14 +3254,10 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-	rdev_for_each(rdev, mddev) {
-		if (!mddev->gendisk)
-			continue;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid1_set_limits(mddev);
+		if (ret)
+			return ret;
 	}
 
 	mddev->degraded = 0;
@@ -3139,8 +3271,7 @@ static int raid1_run(struct mddev *mddev)
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
 		md_unregister_thread(mddev, &conf->thread);
-		ret = -EINVAL;
-		goto abort;
+		return -EINVAL;
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
@@ -3164,14 +3295,8 @@ static int raid1_run(struct mddev *mddev)
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	ret = md_integrity_register(mddev);
-	if (ret) {
+	if (ret)
 		md_unregister_thread(mddev, &mddev->thread);
-		goto abort;
-	}
-	return 0;
-
-abort:
-	raid1_free(mddev, conf);
 	return ret;
 }
 
@@ -3201,14 +3326,16 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
 	 * worth it.
 	 */
 	sector_t newsize = raid1_size(mddev, sectors, 0);
+	int ret;
+
 	if (mddev->external_size &&
 	    mddev->array_sectors > newsize)
 		return -EINVAL;
-	if (mddev->bitmap) {
-		int ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
-		if (ret)
-			return ret;
-	}
+
+	ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
+	if (ret)
+		return ret;
+
 	md_set_array_sectors(mddev, newsize);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {