Merge tag 'md-6.9-20240301' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.9/block

Pull MD updates from Song:

"The major changes are:

 1. Refactor raid1 read_balance, by Yu Kuai and Paul Luse.
 2. Clean up and fix for md_ioctl, by Li Nan.
 3. Other small fixes, by Gui-Dong Han and Heming Zhao."

* tag 'md-6.9-20240301' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: (22 commits)
  md/raid1: factor out helpers to choose the best rdev from read_balance()
  md/raid1: factor out the code to manage sequential IO
  md/raid1: factor out choose_bb_rdev() from read_balance()
  md/raid1: factor out choose_slow_rdev() from read_balance()
  md/raid1: factor out read_first_rdev() from read_balance()
  md/raid1-10: factor out a new helper raid1_should_read_first()
  md/raid1-10: add a helper raid1_check_read_range()
  md/raid1: fix choose next idle in read_balance()
  md/raid1: record nonrot rdevs while adding/removing rdevs to conf
  md/raid1: factor out helpers to add rdev to conf
  md: add a new helper rdev_has_badblock()
  md/raid5: fix atomicity violation in raid5_cache_count
  md/md-bitmap: fix incorrect usage for sb_index
  md: check mddev->pers before calling md_set_readonly()
  md: clean up openers check in do_md_stop() and md_set_readonly()
  md: sync blockdev before stopping raid or setting readonly
  md: factor out a helper to sync mddev
  md: Don't clear MD_CLOSING when the raid is about to stop
  md: return directly before setting did_set_md_closing
  md: clean up invalid BUG_ON in md_ioctl
  ...

8 files changed, 549 insertions, 381 deletions

diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 9672f75c3050..a4976ceae868 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -234,7 +234,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	sector_t doff;
 
 	bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
-	if (pg_index == store->file_pages - 1) {
+	/* we compare length (page numbers), not page offset. */
+	if ((pg_index - store->sb_index) == store->file_pages - 1) {
 		unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1);
 
 		if (last_page_size == 0)
@@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index,
 	struct page *page = store->filemap[pg_index];
 
 	if (mddev_is_clustered(bitmap->mddev)) {
-		pg_index += bitmap->cluster_slot *
-			DIV_ROUND_UP(store->bytes, PAGE_SIZE);
+		/* go to node bitmap area starting point */
+		pg_index += store->sb_index;
 	}
 
 	if (store->file)
@@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 75266c34b1f9..48ae2b1cb57a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -529,6 +529,24 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
+/* sync bdev before setting device to readonly or stopping raid*/
+static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num)
+{
+	mutex_lock(&mddev->open_mutex);
+	if (mddev->pers && atomic_read(&mddev->openers) > opener_num) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	mutex_unlock(&mddev->open_mutex);
+
+	sync_blockdev(mddev->gendisk->part0);
+	return 0;
+}
+
 /*
  * Generic flush handling for md
  */
@@ -4464,8 +4482,8 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
+static int do_md_stop(struct mddev *mddev, int ro);
+static int md_set_readonly(struct mddev *mddev);
 static int restart_array(struct mddev *mddev);
 
 static ssize_t
@@ -4482,6 +4500,17 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case broken:		/* cannot be set */
 	case bad_word:
 		return -EINVAL;
+	case clear:
+	case readonly:
+	case inactive:
+	case read_auto:
+		if (!mddev->pers || !md_is_rdwr(mddev))
+			break;
+		/* write sysfs will not open mddev and opener should be 0 */
+		err = mddev_set_closing_and_sync_blockdev(mddev, 0);
+		if (err)
+			return err;
+		break;
 	default:
 		break;
 	}
@@ -4515,14 +4544,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case inactive:
 		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
-			err = do_md_stop(mddev, 2, NULL);
+			err = do_md_stop(mddev, 2);
 		break;
 	case clear:
-		err = do_md_stop(mddev, 0, NULL);
+		err = do_md_stop(mddev, 0);
 		break;
 	case readonly:
 		if (mddev->pers)
-			err = md_set_readonly(mddev, NULL);
+			err = md_set_readonly(mddev);
 		else {
 			mddev->ro = MD_RDONLY;
 			set_disk_ro(mddev->gendisk, 1);
@@ -4532,7 +4561,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (md_is_rdwr(mddev))
-				err = md_set_readonly(mddev, NULL);
+				err = md_set_readonly(mddev);
 			else if (mddev->ro == MD_RDONLY)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -4581,6 +4610,11 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	mddev_unlock(mddev);
+
+	if (st == readonly || st == read_auto || st == inactive ||
+	    (err && st == clear))
+		clear_bit(MD_CLOSING, &mddev->flags);
+
 	return err ?: len;
 }
 static struct md_sysfs_entry md_array_state =
@@ -6265,7 +6299,15 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	mddev->flags = 0;
+	/*
+	 * Don't clear MD_CLOSING, or mddev can be opened again.
+	 * 'hold_active != 0' means mddev is still in the creation
+	 * process and will be used later.
+	 */
+	if (mddev->hold_active)
+		mddev->flags = 0;
+	else
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6378,7 +6420,8 @@ void md_stop(struct mddev *mddev)
 
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
+/* ensure 'mddev->pers' exist before calling md_set_readonly() */
+static int md_set_readonly(struct mddev *mddev)
 {
 	int err = 0;
 	int did_freeze = 0;
@@ -6396,34 +6439,29 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
 		err = -EBUSY;
 		goto out;
 	}
 
-	if (mddev->pers) {
-		__md_stop_writes(mddev);
-
-		if (mddev->ro == MD_RDONLY) {
-			err  = -ENXIO;
-			goto out;
-		}
+	__md_stop_writes(mddev);
 
-		mddev->ro = MD_RDONLY;
-		set_disk_ro(mddev->gendisk, 1);
+	if (mddev->ro == MD_RDONLY) {
+		err  = -ENXIO;
+		goto out;
 	}
 
+	mddev->ro = MD_RDONLY;
+	set_disk_ro(mddev->gendisk, 1);
+
 out:
-	if ((mddev->pers && !err) || did_freeze) {
+	if (!err || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 
-	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
 
@@ -6431,8 +6469,7 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev *mddev, int mode,
-		      struct block_device *bdev)
+static int do_md_stop(struct mddev *mddev, int mode)
 {
 	struct gendisk *disk = mddev->gendisk;
 	struct md_rdev *rdev;
@@ -6445,12 +6482,9 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 	stop_sync_thread(mddev, true, false);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sysfs_active ||
+	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -6472,13 +6506,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
 				sysfs_unlink_rdev(mddev, rdev);
 
 		set_capacity_and_notify(disk, 0);
-		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
 
 		if (!md_is_rdwr(mddev))
 			mddev->ro = MD_RDWR;
-	} else
-		mutex_unlock(&mddev->open_mutex);
+	}
 	/*
 	 * Free resources if final stop
 	 */
@@ -6524,7 +6556,7 @@ static void autorun_array(struct mddev *mddev)
 	err = do_md_run(mddev);
 	if (err) {
 		pr_warn("md: do_md_run() returned %d\n", err);
-		do_md_stop(mddev, 0, NULL);
+		do_md_stop(mddev, 0);
 	}
 }
 
@@ -7522,16 +7554,17 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static inline bool md_ioctl_valid(unsigned int cmd)
+static inline int md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
-	case ADD_NEW_DISK:
 	case GET_ARRAY_INFO:
-	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
+	case RAID_VERSION:
+		return 0;
+	case ADD_NEW_DISK:
+	case GET_BITMAP_FILE:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
 	case RUN_ARRAY:
 	case SET_ARRAY_INFO:
@@ -7540,9 +7573,11 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case STOP_ARRAY:
 	case STOP_ARRAY_RO:
 	case CLUSTERED_DISK_NACK:
-		return true;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		return 0;
 	default:
-		return false;
+		return -ENOTTY;
 	}
 }
 
@@ -7600,31 +7635,17 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	bool did_set_md_closing = false;
 
-	if (!md_ioctl_valid(cmd))
-		return -ENOTTY;
-
-	switch (cmd) {
-	case RAID_VERSION:
-	case GET_ARRAY_INFO:
-	case GET_DISK_INFO:
-		break;
-	default:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
-	}
+	err = md_ioctl_valid(cmd);
+	if (err)
+		return err;
 
 	/*
 	 * Commands dealing with the RAID driver but not any
 	 * particular array:
 	 */
-	switch (cmd) {
-	case RAID_VERSION:
-		err = get_version(argp);
-		goto out;
-	default:;
-	}
+	if (cmd == RAID_VERSION)
+		return get_version(argp);
 
 	/*
 	 * Commands creating/starting a new array:
@@ -7632,35 +7653,23 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	mddev = bdev->bd_disk->private_data;
 
-	if (!mddev) {
-		BUG();
-		goto out;
-	}
-
 	/* Some actions do not requires the mutex */
 	switch (cmd) {
 	case GET_ARRAY_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_array_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_array_info(mddev, argp);
 
 	case GET_DISK_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_disk_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_disk_info(mddev, argp);
 
 	case SET_DISK_FAULTY:
-		err = set_disk_faulty(mddev, new_decode_dev(arg));
-		goto out;
+		return set_disk_faulty(mddev, new_decode_dev(arg));
 
 	case GET_BITMAP_FILE:
-		err = get_bitmap_file(mddev, argp);
-		goto out;
-
+		return get_bitmap_file(mddev, argp);
 	}
 
 	if (cmd == HOT_REMOVE_DISK)
@@ -7673,20 +7682,9 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
 		 */
-		mutex_lock(&mddev->open_mutex);
-		if (mddev->pers && atomic_read(&mddev->openers) > 1) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		did_set_md_closing = true;
-		mutex_unlock(&mddev->open_mutex);
-		sync_blockdev(bdev);
+		err = mddev_set_closing_and_sync_blockdev(mddev, 1);
+		if (err)
+			return err;
 	}
 
 	if (!md_is_rdwr(mddev))
@@ -7727,11 +7725,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		goto unlock;
 
 	case STOP_ARRAY:
-		err = do_md_stop(mddev, 0, bdev);
+		err = do_md_stop(mddev, 0);
 		goto unlock;
 
 	case STOP_ARRAY_RO:
-		err = md_set_readonly(mddev, bdev);
+		if (mddev->pers)
+			err = md_set_readonly(mddev);
 		goto unlock;
 
 	case HOT_REMOVE_DISK:
@@ -7826,7 +7825,7 @@ unlock:
 				     mddev_unlock(mddev);
 
 out:
-	if(did_set_md_closing)
+	if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
 		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 8d881cc59799..b2076a165c10 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -207,6 +207,7 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
+	Nonrot,			/* non-rotational device (SSD) */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -222,6 +223,16 @@ static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 	}
 	return 0;
 }
+
+static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s,
+				    int sectors)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors);
+}
+
 extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 512746551f36..2ea1710a3b70 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -227,3 +227,72 @@ static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 
 	return false;
 }
+
+/**
+ * raid1_check_read_range() - check a given read range for bad blocks,
+ * available read length is returned;
+ * @rdev: the rdev to read;
+ * @this_sector: read position;
+ * @len: read length;
+ *
+ * helper function for read_balance()
+ *
+ * 1) If there are no bad blocks in the range, @len is returned;
+ * 2) If the range are all bad blocks, 0 is returned;
+ * 3) If there are partial bad blocks:
+ *  - If the bad block range starts after @this_sector, the length of first
+ *  good region is returned;
+ *  - If the bad block range starts before @this_sector, 0 is returned and
+ *  the @len is updated to the offset into the region before we get to the
+ *  good blocks;
+ */
+static inline int raid1_check_read_range(struct md_rdev *rdev,
+					 sector_t this_sector, int *len)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	/* no bad block overlap */
+	if (!is_badblock(rdev, this_sector, *len, &first_bad, &bad_sectors))
+		return *len;
+
+	/*
+	 * bad block range starts offset into our range so we can return the
+	 * number of sectors before the bad blocks start.
+	 */
+	if (first_bad > this_sector)
+		return first_bad - this_sector;
+
+	/* read range is fully consumed by bad blocks. */
+	if (this_sector + *len <= first_bad + bad_sectors)
+		return 0;
+
+	/*
+	 * final case, bad block range starts before or at the start of our
+	 * range but does not cover our entire range so we still return 0 but
+	 * update the length with the number of sectors before we get to the
+	 * good ones.
+	 */
+	*len = first_bad + bad_sectors - this_sector;
+	return 0;
+}
+
+/*
+ * Check if read should choose the first rdev.
+ *
+ * Balance on the whole device if no resync is going on (recovery is ok) or
+ * below the resync window. Otherwise, take the first readable disk.
+ */
+static inline bool raid1_should_read_first(struct mddev *mddev,
+					   sector_t this_sector, int len)
+{
+	if ((mddev->recovery_cp < this_sector + len))
+		return true;
+
+	if (mddev_is_clustered(mddev) &&
+	    md_cluster_ops->area_resyncing(mddev, READ, this_sector,
+					   this_sector + len))
+		return true;
+
+	return false;
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 286f8b16c7bd..afca975ec7f3 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -498,9 +498,6 @@ 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 +513,8 @@ 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 +579,312 @@ 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 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) ||
+		    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))
 			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) {
+			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;
+
+	/* still in recovery */
+	if (!test_bit(In_sync, &rdev->flags) &&
+	    rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
+		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;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev_readable(rdev, r1_bio))
+			continue;
 
-		if (best_disk >= 0)
-			/* At least two disks to choose from so failfast is OK */
+		/* 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)
@@ -1760,6 +1858,52 @@ 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;
@@ -1795,15 +1939,13 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 				disk_stack_limits(mddev->gendisk, rdev->bdev,
 						  rdev->data_offset << 9);
 
-			p->head_position = 0;
-			rdev->raid_disk = mirror;
+			raid1_add_conf(conf, rdev, mirror, false);
 			err = 0;
 			/* 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 +1955,11 @@ 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 +1976,20 @@ 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.
@@ -1944,8 +2077,6 @@ 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 +2086,11 @@ 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 +2407,12 @@ 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))
@@ -3006,23 +3130,17 @@ 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);
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 14d4211a123a..5300cbaa58a4 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -71,6 +71,7 @@ struct r1conf {
 						 * allow for replacements.
 						 */
 	int			raid_disks;
+	int			nonrot_disks;
 
 	spinlock_t		device_lock;
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7412066ea22c..8aecdb1ccc16 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -518,11 +518,7 @@ 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 +531,9 @@ 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 +748,8 @@ 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++) {
@@ -1330,10 +1316,7 @@ retry_wait:
 		}
 
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
-			int is_bad;
 
 			/*
 			 * Discard request doesn't care the write result
@@ -1342,9 +1325,8 @@ retry_wait:
 			if (!r10_bio->sectors)
 				continue;
 
-			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
-					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
+			if (rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0) {
 				/*
 				 * Mustn't write here until the bad block
 				 * is acknowledged
@@ -2290,8 +2272,6 @@ 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 +2292,10 @@ 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);
 
@@ -2597,11 +2576,8 @@ 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 +2634,14 @@ 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 +
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 14f2cf75abbd..48129de21aec 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1210,10 +1210,8 @@ again:
 		 */
 		while (op_is_write(op) && rdev &&
 		       test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
-			int bad_sectors;
-			int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					      &first_bad, &bad_sectors);
+			int bad = rdev_has_badblock(rdev, sh->sector,
+						    RAID5_STRIPE_SECTORS(conf));
 			if (!bad)
 				break;
 
@@ -2412,7 +2410,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	atomic_inc(&conf->active_stripes);
 
 	raid5_release_stripe(sh);
-	conf->max_nr_stripes++;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1);
 	return 1;
 }
 
@@ -2707,7 +2705,7 @@ static int drop_one_stripe(struct r5conf *conf)
 	shrink_buffers(sh);
 	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
-	conf->max_nr_stripes--;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1);
 	return 1;
 }
 
@@ -2855,8 +2853,6 @@ static void raid5_end_write_request(struct bio *bi)
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *rdev;
-	sector_t first_bad;
-	int bad_sectors;
 	int replacement = 0;
 
 	for (i = 0 ; i < disks; i++) {
@@ -2888,9 +2884,8 @@ static void raid5_end_write_request(struct bio *bi)
 	if (replacement) {
 		if (bi->bi_status)
 			md_error(conf->mddev, rdev);
-		else if (is_badblock(rdev, sh->sector,
-				     RAID5_STRIPE_SECTORS(conf),
-				     &first_bad, &bad_sectors))
+		else if (rdev_has_badblock(rdev, sh->sector,
+					   RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
@@ -2900,9 +2895,8 @@ static void raid5_end_write_request(struct bio *bi)
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
 				set_bit(MD_RECOVERY_NEEDED,
 					&rdev->mddev->recovery);
-		} else if (is_badblock(rdev, sh->sector,
-				       RAID5_STRIPE_SECTORS(conf),
-				       &first_bad, &bad_sectors)) {
+		} else if (rdev_has_badblock(rdev, sh->sector,
+					     RAID5_STRIPE_SECTORS(conf))) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
 			if (test_bit(R5_ReadError, &sh->dev[i].flags))
 				/* That was a successful write so make
@@ -4674,8 +4668,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	/* Now to look around and see what can be done */
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
-		sector_t first_bad;
-		int bad_sectors;
 		int is_bad = 0;
 
 		dev = &sh->dev[i];
@@ -4719,8 +4711,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		rdev = conf->disks[i].replacement;
 		if (rdev && !test_bit(Faulty, &rdev->flags) &&
 		    rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) &&
-		    !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-				 &first_bad, &bad_sectors))
+		    !rdev_has_badblock(rdev, sh->sector,
+				       RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
 			if (rdev && !test_bit(Faulty, &rdev->flags))
@@ -4733,8 +4725,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (rdev && test_bit(Faulty, &rdev->flags))
 			rdev = NULL;
 		if (rdev) {
-			is_bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					     &first_bad, &bad_sectors);
+			is_bad = rdev_has_badblock(rdev, sh->sector,
+						   RAID5_STRIPE_SECTORS(conf));
 			if (s->blocked_rdev == NULL
 			    && (test_bit(Blocked, &rdev->flags)
 				|| is_bad < 0)) {
@@ -5463,8 +5455,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct r5conf *conf = mddev->private;
 	struct bio *align_bio;
 	struct md_rdev *rdev;
-	sector_t sector, end_sector, first_bad;
-	int bad_sectors, dd_idx;
+	sector_t sector, end_sector;
+	int dd_idx;
 	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
@@ -5493,8 +5485,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 
 	atomic_inc(&rdev->nr_pending);
 
-	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
-			&bad_sectors)) {
+	if (rdev_has_badblock(rdev, sector, bio_sectors(raid_bio))) {
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
@@ -6820,7 +6811,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
 
-	conf->min_nr_stripes = size;
+	WRITE_ONCE(conf->min_nr_stripes, size);
 	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
@@ -6832,7 +6823,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL)) {
-			conf->min_nr_stripes = conf->max_nr_stripes;
+			WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes);
 			result = -ENOMEM;
 			break;
 		}
@@ -7388,11 +7379,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
 	struct r5conf *conf = shrink->private_data;
+	int max_stripes = READ_ONCE(conf->max_nr_stripes);
+	int min_stripes = READ_ONCE(conf->min_nr_stripes);
 
-	if (conf->max_nr_stripes < conf->min_nr_stripes)
+	if (max_stripes < min_stripes)
 		/* unlikely, but not impossible */
 		return 0;
-	return conf->max_nr_stripes - conf->min_nr_stripes;
+	return max_stripes - min_stripes;
 }
 
 static struct r5conf *setup_conf(struct mddev *mddev)