1 files changed, 176 insertions, 191 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a5adf08ee174..57d50465eed1 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -36,6 +36,7 @@
 #include "md.h"
 #include "raid1.h"
 #include "md-bitmap.h"
+#include "md-cluster.h"
 
 #define UNSUPPORTED_MDDEV_FLAGS		\
 	((1L << MD_HAS_JOURNAL) |	\
@@ -45,6 +46,7 @@
 
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
+static void raid1_free(struct mddev *mddev, void *priv);
 
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
@@ -125,10 +127,9 @@ static inline struct r1bio *get_resync_r1bio(struct bio *bio)
 	return get_resync_pages(bio)->raid_bio;
 }
 
-static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
+static void *r1bio_pool_alloc(gfp_t gfp_flags, struct r1conf *conf)
 {
-	struct pool_info *pi = data;
-	int size = offsetof(struct r1bio, bios[pi->raid_disks]);
+	int size = offsetof(struct r1bio, bios[conf->raid_disks * 2]);
 
 	/* allocate a r1bio with room for raid_disks entries in the bios array */
 	return kzalloc(size, gfp_flags);
@@ -143,18 +144,18 @@ static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
-	struct pool_info *pi = data;
+	struct r1conf *conf = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
 	int need_pages;
 	int j;
 	struct resync_pages *rps;
 
-	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
+	r1_bio = r1bio_pool_alloc(gfp_flags, conf);
 	if (!r1_bio)
 		return NULL;
 
-	rps = kmalloc_array(pi->raid_disks, sizeof(struct resync_pages),
+	rps = kmalloc_array(conf->raid_disks * 2, sizeof(struct resync_pages),
 			    gfp_flags);
 	if (!rps)
 		goto out_free_r1bio;
@@ -162,11 +163,11 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	/*
 	 * Allocate bios : 1 for reading, n-1 for writing
 	 */
-	for (j = pi->raid_disks ; j-- ; ) {
+	for (j = conf->raid_disks * 2; j-- ; ) {
 		bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
 		if (!bio)
 			goto out_free_bio;
-		bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
+		bio_init_inline(bio, NULL, RESYNC_PAGES, 0);
 		r1_bio->bios[j] = bio;
 	}
 	/*
@@ -175,11 +176,11 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * If this is a user-requested check/repair, allocate
 	 * RESYNC_PAGES for each bio.
 	 */
-	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		need_pages = pi->raid_disks;
+	if (test_bit(MD_RECOVERY_REQUESTED, &conf->mddev->recovery))
+		need_pages = conf->raid_disks * 2;
 	else
 		need_pages = 1;
-	for (j = 0; j < pi->raid_disks; j++) {
+	for (j = 0; j < conf->raid_disks * 2; j++) {
 		struct resync_pages *rp = &rps[j];
 
 		bio = r1_bio->bios[j];
@@ -205,7 +206,7 @@ out_free_pages:
 		resync_free_pages(&rps[j]);
 
 out_free_bio:
-	while (++j < pi->raid_disks) {
+	while (++j < conf->raid_disks * 2) {
 		bio_uninit(r1_bio->bios[j]);
 		kfree(r1_bio->bios[j]);
 	}
@@ -218,12 +219,12 @@ out_free_r1bio:
 
 static void r1buf_pool_free(void *__r1_bio, void *data)
 {
-	struct pool_info *pi = data;
+	struct r1conf *conf = data;
 	int i;
 	struct r1bio *r1bio = __r1_bio;
 	struct resync_pages *rp = NULL;
 
-	for (i = pi->raid_disks; i--; ) {
+	for (i = conf->raid_disks * 2; i--; ) {
 		rp = get_resync_pages(r1bio->bios[i]);
 		resync_free_pages(rp);
 		bio_uninit(r1bio->bios[i]);
@@ -253,7 +254,7 @@ static void free_r1bio(struct r1bio *r1_bio)
 	struct r1conf *conf = r1_bio->mddev->private;
 
 	put_all_bios(conf, r1_bio);
-	mempool_free(r1_bio, &conf->r1bio_pool);
+	mempool_free(r1_bio, conf->r1bio_pool);
 }
 
 static void put_buf(struct r1bio *r1_bio)
@@ -371,14 +372,16 @@ static void raid1_end_read_request(struct bio *bio)
 	 */
 	update_head_pos(r1_bio->read_disk, r1_bio);
 
-	if (uptodate)
+	if (uptodate) {
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
-	else if (test_bit(FailFast, &rdev->flags) &&
-		 test_bit(R1BIO_FailFast, &r1_bio->state))
+	} else if (test_bit(FailFast, &rdev->flags) &&
+		 test_bit(R1BIO_FailFast, &r1_bio->state)) {
 		/* This was a fail-fast read so we definitely
 		 * want to retry */
 		;
-	else {
+	} else if (!raid1_should_handle_error(bio)) {
+		uptodate = 1;
+	} else {
 		/* If all other devices have failed, we want to return
 		 * the error upwards rather than fail the last device.
 		 * Here we redefine "uptodate" to mean "Don't want to retry"
@@ -420,10 +423,8 @@ static void close_write(struct r1bio *r1_bio)
 		r1_bio->behind_master_bio = NULL;
 	}
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors,
-				    !test_bit(R1BIO_Degraded, &r1_bio->state),
-				    test_bit(R1BIO_BehindIO, &r1_bio->state));
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->end_behind_write(mddev);
 	md_write_end(mddev);
 }
 
@@ -451,16 +452,15 @@ static void raid1_end_write_request(struct bio *bio)
 	struct bio *to_put = NULL;
 	int mirror = find_bio_disk(r1_bio, bio);
 	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
-	bool discard_error;
 	sector_t lo = r1_bio->sector;
 	sector_t hi = r1_bio->sector + r1_bio->sectors;
-
-	discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+	bool ignore_error = !raid1_should_handle_error(bio) ||
+		(bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_status && !discard_error) {
+	if (bio->bi_status && !ignore_error) {
 		set_bit(WriteErrorSeen,	&rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
@@ -480,8 +480,6 @@ 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;
@@ -513,7 +511,7 @@ static void raid1_end_write_request(struct bio *bio)
 
 		/* Maybe we can clear some bad blocks. */
 		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
-		    !discard_error) {
+		    !ignore_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -1227,7 +1225,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 	int i = 0;
 	struct bio *behind_bio = NULL;
 
-	behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO,
+	behind_bio = bio_alloc_bioset(NULL, vcnt, bio->bi_opf, GFP_NOIO,
 				      &r1_bio->mddev->bio_set);
 
 	/* discard op, we don't support writezero/writesame yet */
@@ -1306,9 +1304,8 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 
-	r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
-	/* Ensure no bio records IO_BLOCKED */
-	memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
+	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+	memset(r1_bio, 0, offsetof(struct r1bio, bios[conf->raid_disks * 2]));
 	init_r1bio(r1_bio, mddev, bio);
 	return r1_bio;
 }
@@ -1319,10 +1316,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
 	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;
-	int rdisk, error;
+	int rdisk;
 	bool r1bio_existed = !!r1_bio;
 
 	/*
@@ -1371,7 +1366,8 @@ 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)) {
+	if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+	    md_bitmap_enabled(mddev, false)) {
 		/*
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
@@ -1381,16 +1377,13 @@ static void raid1_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);
+		bio = bio_submit_split_bioset(bio, max_sectors,
+					      &conf->bio_split);
+		if (!bio) {
+			set_bit(R1BIO_Returned, &r1_bio->state);
 			goto err_handle;
 		}
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
+
 		r1_bio->master_bio = bio;
 		r1_bio->sectors = max_sectors;
 	}
@@ -1402,13 +1395,12 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp,
 				   &mddev->bio_set);
-
+	read_bio->bi_opf &= ~REQ_NOWAIT;
 	r1_bio->bios[rdisk] = read_bio;
 
 	read_bio->bi_iter.bi_sector = r1_bio->sector +
 		mirror->rdev->data_offset;
 	read_bio->bi_end_io = raid1_end_read_request;
-	read_bio->bi_opf = op | do_sync;
 	if (test_bit(FailFast, &mirror->rdev->flags) &&
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
@@ -1419,8 +1411,6 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 
 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);
 }
 
@@ -1458,12 +1448,36 @@ retry:
 	return true;
 }
 
+static void raid1_start_write_behind(struct mddev *mddev, struct r1bio *r1_bio,
+				     struct bio *bio)
+{
+	unsigned long max_write_behind = mddev->bitmap_info.max_write_behind;
+	struct md_bitmap_stats stats;
+	int err;
+
+	/* behind write rely on bitmap, see bitmap_operations */
+	if (!md_bitmap_enabled(mddev, false))
+		return;
+
+	err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats);
+	if (err)
+		return;
+
+	/* Don't do behind IO if reader is waiting, or there are too many. */
+	if (!stats.behind_wait && stats.behind_writes < max_write_behind)
+		alloc_behind_master_bio(r1_bio, bio);
+
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->start_behind_write(mddev);
+
+}
+
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				int max_write_sectors)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
-	int i, disks, k, error;
+	int i, disks, k;
 	unsigned long flags;
 	int first_clone;
 	int max_sectors;
@@ -1471,7 +1485,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	bool is_discard = (bio_op(bio) == REQ_OP_DISCARD);
 
 	if (mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, WRITE,
+	    mddev->cluster_ops->area_resyncing(mddev, WRITE,
 		     bio->bi_iter.bi_sector, bio_end_sector(bio))) {
 
 		DEFINE_WAIT(w);
@@ -1482,7 +1496,7 @@ static void raid1_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;
@@ -1535,16 +1549,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			write_behind = true;
 
 		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)) {
 			sector_t first_bad;
-			int bad_sectors;
+			sector_t bad_sectors;
 			int is_bad;
 
 			is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
@@ -1558,20 +1569,22 @@ 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)
+					goto err_handle;
+
+				good_sectors = first_bad - r1_bio->sector;
 				if (good_sectors < max_sectors)
 					max_sectors = good_sectors;
 			}
@@ -1589,16 +1602,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		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);
+		bio = bio_submit_split_bioset(bio, max_sectors,
+					      &conf->bio_split);
+		if (!bio) {
+			set_bit(R1BIO_Returned, &r1_bio->state);
 			goto err_handle;
 		}
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
+
 		r1_bio->master_bio = bio;
 		r1_bio->sectors = max_sectors;
 	}
@@ -1617,23 +1627,8 @@ 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 */
-			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);
-
-			mddev->bitmap_ops->startwrite(
-				mddev, r1_bio->sector, r1_bio->sectors,
-				test_bit(R1BIO_BehindIO, &r1_bio->state));
+			if (write_behind)
+				raid1_start_write_behind(mddev, r1_bio, bio);
 			first_clone = 0;
 		}
 
@@ -1653,11 +1648,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				wait_for_serialization(rdev, r1_bio);
 		}
 
+		mbio->bi_opf &= ~REQ_NOWAIT;
 		r1_bio->bios[i] = mbio;
 
 		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));
 		if (test_bit(FailFast, &rdev->flags) &&
 		    !test_bit(WriteMostly, &rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)
@@ -1689,8 +1684,6 @@ err_handle:
 		}
 	}
 
-	bio->bi_status = errno_to_blk_status(error);
-	set_bit(R1BIO_Uptodate, &r1_bio->state);
 	raid_end_bio_io(r1_bio);
 }
 
@@ -2063,7 +2056,7 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
 
 	/* make sure these bits don't get cleared. */
 	do {
-		mddev->bitmap_ops->end_sync(mddev, s, &sync_blocks);
+		md_bitmap_end_sync(mddev, s, &sync_blocks);
 		s += sync_blocks;
 		sectors_to_go -= sync_blocks;
 	} while (sectors_to_go > 0);
@@ -2206,14 +2199,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				if (!rdev_set_badblocks(rdev, sect, s, 0))
 					abort = 1;
 			}
-			if (abort) {
-				conf->recovery_disabled =
-					mddev->recovery_disabled;
-				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_done_sync(mddev, r1_bio->sectors, 0);
-				put_buf(r1_bio);
+			if (abort)
 				return 0;
-			}
+
 			/* Try next page */
 			sectors -= s;
 			sect += s;
@@ -2352,10 +2340,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 	int disks = conf->raid_disks * 2;
 	struct bio *wbio;
 
-	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		/* ouch - failed to read all of that. */
-		if (!fix_sync_read_error(r1_bio))
+	if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+		/*
+		 * ouch - failed to read all of that.
+		 * No need to fix read error for check/repair
+		 * because all member disks are read.
+		 */
+		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) ||
+		    !fix_sync_read_error(r1_bio)) {
+			conf->recovery_disabled = mddev->recovery_disabled;
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+			md_done_sync(mddev, r1_bio->sectors, 0);
+			put_buf(r1_bio);
 			return;
+		}
+	}
 
 	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		process_checks(r1_bio);
@@ -2382,7 +2381,6 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 
 		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
-		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
 
 		submit_bio_noacct(wbio);
 	}
@@ -2489,7 +2487,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	}
 }
 
-static int narrow_write_error(struct r1bio *r1_bio, int i)
+static bool narrow_write_error(struct r1bio *r1_bio, int i)
 {
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
@@ -2510,10 +2508,10 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 	sector_t sector;
 	int sectors;
 	int sect_to_write = r1_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);
@@ -2599,12 +2597,10 @@ 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);
 		}
@@ -2695,8 +2691,6 @@ 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);
@@ -2750,7 +2744,7 @@ static int init_resync(struct r1conf *conf)
 	BUG_ON(mempool_initialized(&conf->r1buf_pool));
 
 	return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
-			    r1buf_pool_free, conf->poolinfo);
+			    r1buf_pool_free, conf);
 }
 
 static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
@@ -2760,7 +2754,7 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
 	struct bio *bio;
 	int i;
 
-	for (i = conf->poolinfo->raid_disks; i--; ) {
+	for (i = conf->raid_disks * 2; i--; ) {
 		bio = r1bio->bios[i];
 		rps = bio->bi_private;
 		bio_reset(bio, NULL, 0);
@@ -2809,12 +2803,13 @@ 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 */
-			mddev->bitmap_ops->end_sync(mddev, mddev->curr_resync,
-						    &sync_blocks);
+			md_bitmap_end_sync(mddev, mddev->curr_resync,
+					   &sync_blocks);
 		else /* completed sync */
 			conf->fullsync = 0;
 
-		mddev->bitmap_ops->close_sync(mddev);
+		if (md_bitmap_enabled(mddev, false))
+			mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 
 		if (mddev_is_clustered(mddev)) {
@@ -2825,7 +2820,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	}
 
 	if (mddev->bitmap == NULL &&
-	    mddev->recovery_cp == MaxSector &&
+	    mddev->resync_offset == MaxSector &&
 	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
 	    conf->fullsync == 0) {
 		*skipped = 1;
@@ -2834,7 +2829,7 @@ 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 (!mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, true) &&
+	if (!md_bitmap_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;
@@ -2851,10 +2846,11 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	/* we are incrementing sector_nr below. To be safe, we check against
 	 * sector_nr + two times RESYNC_SECTORS
 	 */
-
-	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_enabled(mddev, false))
+		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;
@@ -2893,7 +2889,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		} else {
 			/* may need to read from here */
 			sector_t first_bad = MaxSector;
-			int bad_sectors;
+			sector_t bad_sectors;
 
 			if (is_badblock(rdev, sector_nr, good_sectors,
 					&first_bad, &bad_sectors)) {
@@ -3009,8 +3005,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (len == 0)
 			break;
 		if (sync_blocks == 0) {
-			if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
-						&sync_blocks, still_degraded) &&
+			if (!md_bitmap_start_sync(mddev, sector_nr,
+						  &sync_blocks, still_degraded) &&
 			    !conf->fullsync &&
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
@@ -3045,9 +3041,9 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		conf->cluster_sync_low = mddev->curr_resync_completed;
 		conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS;
 		/* Send resync message */
-		md_cluster_ops->resync_info_update(mddev,
-				conf->cluster_sync_low,
-				conf->cluster_sync_high);
+		mddev->cluster_ops->resync_info_update(mddev,
+						       conf->cluster_sync_low,
+						       conf->cluster_sync_high);
 	}
 
 	/* For a user-requested sync, we read all readable devices and do a
@@ -3059,7 +3055,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio = r1_bio->bios[i];
 			if (bio->bi_end_io == end_sync_read) {
 				read_targets--;
-				md_sync_acct_bio(bio, nr_sectors);
 				if (read_targets == 1)
 					bio->bi_opf &= ~MD_FAILFAST;
 				submit_bio_noacct(bio);
@@ -3068,7 +3063,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	} else {
 		atomic_set(&r1_bio->remaining, 1);
 		bio = r1_bio->bios[r1_bio->read_disk];
-		md_sync_acct_bio(bio, nr_sectors);
 		if (read_targets == 1)
 			bio->bi_opf &= ~MD_FAILFAST;
 		submit_bio_noacct(bio);
@@ -3090,6 +3084,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	int i;
 	struct raid1_info *disk;
 	struct md_rdev *rdev;
+	size_t r1bio_size;
 	int err = -ENOMEM;
 
 	conf = kzalloc(sizeof(struct r1conf), GFP_KERNEL);
@@ -3126,21 +3121,15 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	if (!conf->tmppage)
 		goto abort;
 
-	conf->poolinfo = kzalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
-	if (!conf->poolinfo)
-		goto abort;
-	conf->poolinfo->raid_disks = mddev->raid_disks * 2;
-	err = mempool_init(&conf->r1bio_pool, NR_RAID_BIOS, r1bio_pool_alloc,
-			   rbio_pool_free, conf->poolinfo);
-	if (err)
+	r1bio_size = offsetof(struct r1bio, bios[mddev->raid_disks * 2]);
+	conf->r1bio_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS, r1bio_size);
+	if (!conf->r1bio_pool)
 		goto abort;
 
 	err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
 	if (err)
 		goto abort;
 
-	conf->poolinfo->mddev = mddev;
-
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
 	conf->raid_disks = mddev->raid_disks;
@@ -3203,10 +3192,9 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
  abort:
 	if (conf) {
-		mempool_exit(&conf->r1bio_pool);
+		mempool_destroy(conf->r1bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
-		kfree(conf->poolinfo);
 		kfree(conf->nr_pending);
 		kfree(conf->nr_waiting);
 		kfree(conf->nr_queued);
@@ -3224,11 +3212,12 @@ static int raid1_set_limits(struct mddev *mddev)
 
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
+	lim.max_hw_wzeroes_unmap_sectors = 0;
+	lim.logical_block_size = mddev->logical_block_size;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
@@ -3264,8 +3253,11 @@ static int raid1_run(struct mddev *mddev)
 
 	if (!mddev_is_dm(mddev)) {
 		ret = raid1_set_limits(mddev);
-		if (ret)
+		if (ret) {
+			if (!mddev->private)
+				raid1_free(mddev, conf);
 			return ret;
+		}
 	}
 
 	mddev->degraded = 0;
@@ -3279,13 +3271,15 @@ static int raid1_run(struct mddev *mddev)
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
 		md_unregister_thread(mddev, &conf->thread);
+		if (!mddev->private)
+			raid1_free(mddev, conf);
 		return -EINVAL;
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
-		mddev->recovery_cp = MaxSector;
+		mddev->resync_offset = MaxSector;
 
-	if (mddev->recovery_cp != MaxSector)
+	if (mddev->resync_offset != MaxSector)
 		pr_info("md/raid1:%s: not clean -- starting background reconstruction\n",
 			mdname(mddev));
 	pr_info("md/raid1:%s: active with %d out of %d mirrors\n",
@@ -3312,10 +3306,9 @@ static void raid1_free(struct mddev *mddev, void *priv)
 {
 	struct r1conf *conf = priv;
 
-	mempool_exit(&conf->r1bio_pool);
+	mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
-	kfree(conf->poolinfo);
 	kfree(conf->nr_pending);
 	kfree(conf->nr_waiting);
 	kfree(conf->nr_queued);
@@ -3334,20 +3327,22 @@ 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;
 
-	ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
-	if (ret)
-		return ret;
+	if (md_bitmap_enabled(mddev, false)) {
+		int ret = mddev->bitmap_ops->resize(mddev, newsize, 0);
+
+		if (ret)
+			return ret;
+	}
 
 	md_set_array_sectors(mddev, newsize);
 	if (sectors > mddev->dev_sectors &&
-	    mddev->recovery_cp > mddev->dev_sectors) {
-		mddev->recovery_cp = mddev->dev_sectors;
+	    mddev->resync_offset > mddev->dev_sectors) {
+		mddev->resync_offset = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 	mddev->dev_sectors = sectors;
@@ -3368,17 +3363,13 @@ static int raid1_reshape(struct mddev *mddev)
 	 * At the same time, we "pack" the devices so that all the missing
 	 * devices have the higher raid_disk numbers.
 	 */
-	mempool_t newpool, oldpool;
-	struct pool_info *newpoolinfo;
+	mempool_t *newpool, *oldpool;
+	size_t new_r1bio_size;
 	struct raid1_info *newmirrors;
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
 	int d, d2;
-	int ret;
-
-	memset(&newpool, 0, sizeof(newpool));
-	memset(&oldpool, 0, sizeof(oldpool));
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3404,24 +3395,16 @@ static int raid1_reshape(struct mddev *mddev)
 			return -EBUSY;
 	}
 
-	newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
-	if (!newpoolinfo)
+	new_r1bio_size = offsetof(struct r1bio, bios[raid_disks * 2]);
+	newpool = mempool_create_kmalloc_pool(NR_RAID_BIOS, new_r1bio_size);
+	if (!newpool) {
 		return -ENOMEM;
-	newpoolinfo->mddev = mddev;
-	newpoolinfo->raid_disks = raid_disks * 2;
-
-	ret = mempool_init(&newpool, NR_RAID_BIOS, r1bio_pool_alloc,
-			   rbio_pool_free, newpoolinfo);
-	if (ret) {
-		kfree(newpoolinfo);
-		return ret;
 	}
 	newmirrors = kzalloc(array3_size(sizeof(struct raid1_info),
 					 raid_disks, 2),
 			     GFP_KERNEL);
 	if (!newmirrors) {
-		kfree(newpoolinfo);
-		mempool_exit(&newpool);
+		mempool_destroy(newpool);
 		return -ENOMEM;
 	}
 
@@ -3446,8 +3429,6 @@ static int raid1_reshape(struct mddev *mddev)
 	}
 	kfree(conf->mirrors);
 	conf->mirrors = newmirrors;
-	kfree(conf->poolinfo);
-	conf->poolinfo = newpoolinfo;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded += (raid_disks - conf->raid_disks);
@@ -3461,7 +3442,7 @@ static int raid1_reshape(struct mddev *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 
-	mempool_exit(&oldpool);
+	mempool_destroy(oldpool);
 	return 0;
 }
 
@@ -3499,9 +3480,13 @@ static void *raid1_takeover(struct mddev *mddev)
 
 static struct md_personality raid1_personality =
 {
-	.name		= "raid1",
-	.level		= 1,
-	.owner		= THIS_MODULE,
+	.head = {
+		.type	= MD_PERSONALITY,
+		.id	= ID_RAID1,
+		.name	= "raid1",
+		.owner	= THIS_MODULE,
+	},
+
 	.make_request	= raid1_make_request,
 	.run		= raid1_run,
 	.free		= raid1_free,
@@ -3518,18 +3503,18 @@ static struct md_personality raid1_personality =
 	.takeover	= raid1_takeover,
 };
 
-static int __init raid_init(void)
+static int __init raid1_init(void)
 {
-	return register_md_personality(&raid1_personality);
+	return register_md_submodule(&raid1_personality.head);
 }
 
-static void raid_exit(void)
+static void __exit raid1_exit(void)
 {
-	unregister_md_personality(&raid1_personality);
+	unregister_md_submodule(&raid1_personality.head);
 }
 
-module_init(raid_init);
-module_exit(raid_exit);
+module_init(raid1_init);
+module_exit(raid1_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD");
 MODULE_ALIAS("md-personality-3"); /* RAID1 */