Merge tag 'md-next-20230729' of...

Merge tag 'md-next-20230729' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.6/block

Pull MD updates from Song:

"1. Deprecate bitmap file support, by Christoph Hellwig;
 2. Fix deadlock with md sync thread, by Yu Kuai;
 3. Refactor md io accounting, by Yu Kuai;
 4. Various non-urgent fixes by Li Nan, Yu Kuai, and Jack Wang."

* tag 'md-next-20230729' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: (36 commits)
  md/md-bitmap: hold 'reconfig_mutex' in backlog_store()
  md/md-bitmap: remove unnecessary local variable in backlog_store()
  md/raid10: use dereference_rdev_and_rrdev() to get devices
  md/raid10: factor out dereference_rdev_and_rrdev()
  md/raid10: check replacement and rdev to prevent submit the same io twice
  md/raid1: Avoid lock contention from wake_up()
  md: restore 'noio_flag' for the last mddev_resume()
  md: don't quiesce in mddev_suspend()
  md: remove redundant check in fix_read_error()
  md/raid10: optimize fix_read_error
  md/raid1: prioritize adding disk to 'removed' mirror
  md/md-faulty: enable io accounting
  md/md-linear: enable io accounting
  md/md-multipath: enable io accounting
  md/raid10: switch to use md_account_bio() for io accounting
  md/raid1: switch to use md_account_bio() for io accounting
  raid5: fix missing io accounting in raid5_align_endio()
  md: also clone new io if io accounting is disabled
  md: move initialization and destruction of 'io_acct_set' to md.c
  md: deprecate bitmap file support
  ...

drivers/md/Kconfig

@@ -50,6 +50,16 @@ config MD_AUTODETECT
 
 	  If unsure, say Y.
 
+config MD_BITMAP_FILE
+	bool "MD bitmap file support (deprecated)"
+	default y
+	help
+	  If you say Y here, support for write intent bitmaps in files on an
+	  external file system is enabled.  This is an alternative to the internal
+	  bitmaps near the MD superblock, and very problematic code that abuses
+	  various kernel APIs and can only work with files on a file system not
+	  actually sitting on the MD device.
+
 config MD_LINEAR
 	tristate "Linear (append) mode (deprecated)"
 	depends on BLK_DEV_MD

drivers/md/dm-raid.c

@@ -3725,7 +3725,6 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_unregister_thread(&mddev->sync_thread);
 			md_reap_sync_thread(mddev);
 		}
 	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)

drivers/md/md-bitmap.h

@@ -201,6 +201,7 @@ struct bitmap {
 		struct file *file;		/* backing disk file */
 		struct page *sb_page;		/* cached copy of the bitmap
 						 * file superblock */
+		unsigned long sb_index;
 		struct page **filemap;		/* list of cache pages for
 						 * the file */
 		unsigned long *filemap_attr;	/* attributes associated

drivers/md/md-faulty.c

@@ -204,6 +204,8 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
 			failit = 1;
 		}
 	}
+
+	md_account_bio(mddev, &bio);
 	if (failit) {
 		struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO,
 						&mddev->bio_set);

drivers/md/md-linear.c

@@ -238,6 +238,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		bio = split;
 	}
 
+	md_account_bio(mddev, &bio);
 	bio_set_dev(bio, tmp_dev->rdev->bdev);
 	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
 		start_sector + data_offset;

drivers/md/md-multipath.c

@@ -107,6 +107,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	    && md_flush_request(mddev, bio))
 		return true;
 
+	md_account_bio(mddev, &bio);
 	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
 	mp_bh->master_bio = bio;

drivers/md/md.h

@@ -510,7 +510,7 @@ struct mddev {
 	struct bio_set			sync_set; /* for sync operations like
 						   * metadata and bitmap writes
 						   */
-	struct bio_set			io_acct_set; /* for raid0 and raid5 io accounting */
+	struct bio_set			io_clone_set;
 
 	/* Generic flush handling.
 	 * The last to finish preflush schedules a worker to submit
@@ -535,6 +535,11 @@ struct mddev {
 	 */
 	struct list_head		deleting;
 
+	/* Used to synchronize idle and frozen for action_store() */
+	struct mutex			sync_mutex;
+	/* The sequence number for sync thread */
+	atomic_t sync_seq;
+
 	bool	has_superblocks:1;
 	bool	fail_last_dev:1;
 	bool	serialize_policy:1;
@@ -731,7 +736,7 @@ struct md_thread {
 	void			*private;
 };
 
-struct md_io_acct {
+struct md_io_clone {
 	struct mddev	*mddev;
 	struct bio	*orig_bio;
 	unsigned long	start_time;
@@ -769,8 +774,6 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
-int acct_bioset_init(struct mddev *mddev);
-void acct_bioset_exit(struct mddev *mddev);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);

drivers/md/raid0.c

@@ -377,7 +377,6 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	struct r0conf *conf = priv;
 
 	free_conf(mddev, conf);
-	acct_bioset_exit(mddev);
 }
 
 static int raid0_run(struct mddev *mddev)
@@ -392,16 +391,11 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
-	if (acct_bioset_init(mddev)) {
-		pr_err("md/raid0:%s: alloc acct bioset failed.\n", mdname(mddev));
-		return -ENOMEM;
-	}
-
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
 		if (ret < 0)
-			goto exit_acct_set;
+			return ret;
 		mddev->private = conf;
 	}
 	conf = mddev->private;
@@ -432,14 +426,8 @@ static int raid0_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		goto free;
-
-	return ret;
-
-free:
 		free_conf(mddev, conf);
-exit_acct_set:
-	acct_bioset_exit(mddev);
+
 	return ret;
 }
 

drivers/md/raid1.c

@@ -304,8 +304,6 @@ static void call_bio_endio(struct r1bio *r1_bio)
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		bio_end_io_acct(bio, r1_bio->start_time);
 	bio_endio(bio);
 }
 
@@ -791,11 +789,17 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
+static void wake_up_barrier(struct r1conf *conf)
+{
+	if (wq_has_sleeper(&conf->wait_barrier))
+		wake_up(&conf->wait_barrier);
+}
+
 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);
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
@@ -972,7 +976,7 @@ static bool _wait_barrier(struct r1conf *conf, int idx, bool nowait)
 	 * In case freeze_array() is waiting for
 	 * get_unqueued_pending() == extra
 	 */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 	/* Wait for the barrier in same barrier unit bucket to drop. */
 
 	/* Return false when nowait flag is set */
@@ -1015,7 +1019,7 @@ static bool wait_read_barrier(struct r1conf *conf, sector_t sector_nr, bool nowa
 	 * In case freeze_array() is waiting for
 	 * get_unqueued_pending() == extra
 	 */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 	/* Wait for array to be unfrozen */
 
 	/* Return false when nowait flag is set */
@@ -1044,7 +1048,7 @@ static bool wait_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait)
 static void _allow_barrier(struct r1conf *conf, int idx)
 {
 	atomic_dec(&conf->nr_pending[idx]);
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 }
 
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr)
@@ -1173,7 +1177,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		spin_lock_irq(&conf->device_lock);
 		bio_list_merge(&conf->pending_bio_list, &plug->pending);
 		spin_unlock_irq(&conf->device_lock);
-		wake_up(&conf->wait_barrier);
+		wake_up_barrier(conf);
 		md_wakeup_thread(mddev->thread);
 		kfree(plug);
 		return;
@@ -1303,10 +1307,10 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	r1_bio->read_disk = rdisk;
-
-	if (!r1bio_existed && blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r1_bio->start_time = bio_start_io_acct(bio);
-
+	if (!r1bio_existed) {
+		md_account_bio(mddev, &bio);
+		r1_bio->master_bio = bio;
+	}
 	read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp,
 				   &mddev->bio_set);
 
@@ -1500,8 +1504,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		r1_bio->sectors = max_sectors;
 	}
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r1_bio->start_time = bio_start_io_acct(bio);
+	md_account_bio(mddev, &bio);
+	r1_bio->master_bio = bio;
 	atomic_set(&r1_bio->remaining, 1);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
@@ -1576,7 +1580,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	r1_bio_write_done(r1_bio);
 
 	/* In case raid1d snuck in to freeze_array */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
@@ -1766,7 +1770,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
 	int err = -EEXIST;
-	int mirror = 0;
+	int mirror = 0, repl_slot = -1;
 	struct raid1_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
@@ -1809,17 +1813,21 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
-		    p[conf->raid_disks].rdev == NULL) {
+		    p[conf->raid_disks].rdev == NULL && repl_slot < 0)
+			repl_slot = mirror;
+	}
+
+	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 = mirror;
+		rdev->raid_disk = repl_slot;
 		err = 0;
 		conf->fullsync = 1;
 		rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
-			break;
-		}
 	}
+
 	print_conf(conf);
 	return err;
 }
@@ -2299,7 +2307,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d++;
 			if (d == conf->raid_disks * 2)
 				d = 0;
-		} while (!success && d != read_disk);
+		} while (d != read_disk);
 
 		if (!success) {
 			/* Cannot read from anywhere - mark it bad */

drivers/md/raid1.h

@@ -157,7 +157,6 @@ struct r1bio {
 	sector_t		sector;
 	int			sectors;
 	unsigned long		state;
-	unsigned long		start_time;
 	struct mddev		*mddev;
 	/*
 	 * original bio going to /dev/mdx

drivers/md/raid10.c

@@ -325,8 +325,6 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
-	if (r10_bio->start_time)
-		bio_end_io_acct(bio, r10_bio->start_time);
 	bio_endio(bio);
 	/*
 	 * Wake up any possible resync thread that waits for the device
@@ -1172,7 +1170,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 }
 
 static void raid10_read_request(struct mddev *mddev, struct bio *bio,
-				struct r10bio *r10_bio)
+				struct r10bio *r10_bio, bool io_accounting)
 {
 	struct r10conf *conf = mddev->private;
 	struct bio *read_bio;
@@ -1243,9 +1241,10 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	slot = r10_bio->read_slot;
 
-	if (!r10_bio->start_time &&
-	    blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r10_bio->start_time = bio_start_io_acct(bio);
+	if (io_accounting) {
+		md_account_bio(mddev, &bio);
+		r10_bio->master_bio = bio;
+	}
 	read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set);
 
 	r10_bio->devs[slot].bio = read_bio;
@@ -1322,6 +1321,25 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	}
 }
 
+static struct md_rdev *dereference_rdev_and_rrdev(struct raid10_info *mirror,
+						  struct md_rdev **prrdev)
+{
+	struct md_rdev *rdev, *rrdev;
+
+	rrdev = rcu_dereference(mirror->replacement);
+	/*
+	 * Read replacement first to prevent reading both rdev and
+	 * replacement as NULL during replacement replace rdev.
+	 */
+	smp_mb();
+	rdev = rcu_dereference(mirror->rdev);
+	if (rdev == rrdev)
+		rrdev = NULL;
+
+	*prrdev = rrdev;
+	return rdev;
+}
+
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
 	int i;
@@ -1332,11 +1350,9 @@ static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 	blocked_rdev = NULL;
 	rcu_read_lock();
 	for (i = 0; i < conf->copies; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[i].replacement);
-		if (rdev == rrdev)
-			rrdev = NULL;
+		struct md_rdev *rdev, *rrdev;
+
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[i], &rrdev);
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			atomic_inc(&rdev->nr_pending);
 			blocked_rdev = rdev;
@@ -1465,15 +1481,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		int d = r10_bio->devs[i].devnum;
 		struct md_rdev *rdev, *rrdev;
 
-		rrdev = rcu_dereference(conf->mirrors[d].replacement);
-		/*
-		 * Read replacement first to prevent reading both rdev and
-		 * replacement as NULL during replacement replace rdev.
-		 */
-		smp_mb();
-		rdev = rcu_dereference(conf->mirrors[d].rdev);
-		if (rdev == rrdev)
-			rrdev = NULL;
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[d], &rrdev);
 		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
@@ -1543,8 +1551,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->master_bio = bio;
 	}
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r10_bio->start_time = bio_start_io_acct(bio);
+	md_account_bio(mddev, &bio);
+	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
 	md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
 
@@ -1571,12 +1579,11 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
 	r10_bio->read_slot = -1;
-	r10_bio->start_time = 0;
 	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) *
 			conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)
-		raid10_read_request(mddev, bio, r10_bio);
+		raid10_read_request(mddev, bio, r10_bio, true);
 	else
 		raid10_write_request(mddev, bio, r10_bio);
 }
@@ -1780,10 +1787,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	 */
 	rcu_read_lock();
 	for (disk = 0; disk < geo->raid_disks; disk++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[disk].replacement);
+		struct md_rdev *rdev, *rrdev;
 
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[disk], &rrdev);
 		r10_bio->devs[disk].bio = NULL;
 		r10_bio->devs[disk].repl_bio = NULL;
 
@@ -2720,10 +2726,10 @@ static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10bio *r10_bio)
 {
 	int sect = 0; /* Offset from r10_bio->sector */
-	int sectors = r10_bio->sectors;
+	int sectors = r10_bio->sectors, slot = r10_bio->read_slot;
 	struct md_rdev *rdev;
 	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
-	int d = r10_bio->devs[r10_bio->read_slot].devnum;
+	int d = r10_bio->devs[slot].devnum;
 
 	/* still own a reference to this rdev, so it cannot
 	 * have been cleared recently.
@@ -2744,13 +2750,13 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		pr_notice("md/raid10:%s: %pg: Failing raid device\n",
 			  mdname(mddev), rdev->bdev);
 		md_error(mddev, rdev);
-		r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED;
+		r10_bio->devs[slot].bio = IO_BLOCKED;
 		return;
 	}
 
 	while(sectors) {
 		int s = sectors;
-		int sl = r10_bio->read_slot;
+		int sl = slot;
 		int success = 0;
 		int start;
 
@@ -2785,7 +2791,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			sl++;
 			if (sl == conf->copies)
 				sl = 0;
-		} while (!success && sl != r10_bio->read_slot);
+		} while (sl != slot);
 		rcu_read_unlock();
 
 		if (!success) {
@@ -2793,16 +2799,16 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			 * as bad on the first device to discourage future
 			 * reads.
 			 */
-			int dn = r10_bio->devs[r10_bio->read_slot].devnum;
+			int dn = r10_bio->devs[slot].devnum;
 			rdev = conf->mirrors[dn].rdev;
 
 			if (!rdev_set_badblocks(
 				    rdev,
-				    r10_bio->devs[r10_bio->read_slot].addr
+				    r10_bio->devs[slot].addr
 				    + sect,
 				    s, 0)) {
 				md_error(mddev, rdev);
-				r10_bio->devs[r10_bio->read_slot].bio
+				r10_bio->devs[slot].bio
 					= IO_BLOCKED;
 			}
 			break;
@@ -2811,7 +2817,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		start = sl;
 		/* write it back and re-read */
 		rcu_read_lock();
-		while (sl != r10_bio->read_slot) {
+		while (sl != slot) {
 			if (sl==0)
 				sl = conf->copies;
 			sl--;
@@ -2845,7 +2851,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			rcu_read_lock();
 		}
 		sl = start;
-		while (sl != r10_bio->read_slot) {
+		while (sl != slot) {
 			if (sl==0)
 				sl = conf->copies;
 			sl--;
@@ -2985,7 +2991,7 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 
 	rdev_dec_pending(rdev, mddev);
 	r10_bio->state = 0;
-	raid10_read_request(mddev, r10_bio->master_bio, r10_bio);
+	raid10_read_request(mddev, r10_bio->master_bio, r10_bio, false);
 	/*
 	 * allow_barrier after re-submit to ensure no sync io
 	 * can be issued while regular io pending.

drivers/md/raid10.h

@@ -123,7 +123,6 @@ struct r10bio {
 	sector_t		sector;	/* virtual sector number */
 	int			sectors;
 	unsigned long		state;
-	unsigned long		start_time;
 	struct mddev		*mddev;
 	/*
 	 * original bio going to /dev/mdx

drivers/md/raid5.c

@@ -5468,26 +5468,17 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf,
  */
 static void raid5_align_endio(struct bio *bi)
 {
-	struct md_io_acct *md_io_acct = bi->bi_private;
-	struct bio *raid_bi = md_io_acct->orig_bio;
-	struct mddev *mddev;
-	struct r5conf *conf;
-	struct md_rdev *rdev;
+	struct bio *raid_bi = bi->bi_private;
+	struct md_rdev *rdev = (void *)raid_bi->bi_next;
+	struct mddev *mddev = rdev->mddev;
+	struct r5conf *conf = mddev->private;
 	blk_status_t error = bi->bi_status;
-	unsigned long start_time = md_io_acct->start_time;
 
 	bio_put(bi);
-
-	rdev = (void*)raid_bi->bi_next;
 	raid_bi->bi_next = NULL;
-	mddev = rdev->mddev;
-	conf = mddev->private;
-
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error) {
-		if (blk_queue_io_stat(raid_bi->bi_bdev->bd_disk->queue))
-			bio_end_io_acct(raid_bi, start_time);
 		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
@@ -5506,7 +5497,6 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct md_rdev *rdev;
 	sector_t sector, end_sector, first_bad;
 	int bad_sectors, dd_idx;
-	struct md_io_acct *md_io_acct;
 	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
@@ -5543,16 +5533,13 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		return 0;
 	}
 
-	align_bio = bio_alloc_clone(rdev->bdev, raid_bio, GFP_NOIO,
-				    &mddev->io_acct_set);
-	md_io_acct = container_of(align_bio, struct md_io_acct, bio_clone);
+	md_account_bio(mddev, &raid_bio);
 	raid_bio->bi_next = (void *)rdev;
-	if (blk_queue_io_stat(raid_bio->bi_bdev->bd_disk->queue))
-		md_io_acct->start_time = bio_start_io_acct(raid_bio);
-	md_io_acct->orig_bio = raid_bio;
 
+	align_bio = bio_alloc_clone(rdev->bdev, raid_bio, GFP_NOIO,
+				    &mddev->bio_set);
 	align_bio->bi_end_io = raid5_align_endio;
-	align_bio->bi_private = md_io_acct;
+	align_bio->bi_private = raid_bio;
 	align_bio->bi_iter.bi_sector = sector;
 
 	/* No reshape active, so we can trust rdev->data_offset */
@@ -7787,19 +7774,12 @@ static int raid5_run(struct mddev *mddev)
 	struct md_rdev *rdev;
 	struct md_rdev *journal_dev = NULL;
 	sector_t reshape_offset = 0;
-	int i, ret = 0;
+	int i;
 	long long min_offset_diff = 0;
 	int first = 1;
 
-	if (acct_bioset_init(mddev)) {
-		pr_err("md/raid456:%s: alloc acct bioset failed.\n", mdname(mddev));
+	if (mddev_init_writes_pending(mddev) < 0)
 		return -ENOMEM;
-	}
-
-	if (mddev_init_writes_pending(mddev) < 0) {
-		ret = -ENOMEM;
-		goto exit_acct_set;
-	}
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7830,8 +7810,7 @@ static int raid5_run(struct mddev *mddev)
 	    (mddev->bitmap_info.offset || mddev->bitmap_info.file)) {
 		pr_notice("md/raid:%s: array cannot have both journal and bitmap\n",
 			  mdname(mddev));
-		ret = -EINVAL;
-		goto exit_acct_set;
+		return -EINVAL;
 	}
 
 	if (mddev->reshape_position != MaxSector) {
@@ -7856,15 +7835,13 @@ static int raid5_run(struct mddev *mddev)
 		if (journal_dev) {
 			pr_warn("md/raid:%s: don't support reshape with journal - aborting.\n",
 				mdname(mddev));
-			ret = -EINVAL;
-			goto exit_acct_set;
+			return -EINVAL;
 		}
 
 		if (mddev->new_level != mddev->level) {
 			pr_warn("md/raid:%s: unsupported reshape required - aborting.\n",
 				mdname(mddev));
-			ret = -EINVAL;
-			goto exit_acct_set;
+			return -EINVAL;
 		}
 		old_disks = mddev->raid_disks - mddev->delta_disks;
 		/* reshape_position must be on a new-stripe boundary, and one
@@ -7880,8 +7857,7 @@ static int raid5_run(struct mddev *mddev)
 		if (sector_div(here_new, chunk_sectors * new_data_disks)) {
 			pr_warn("md/raid:%s: reshape_position not on a stripe boundary\n",
 				mdname(mddev));
-			ret = -EINVAL;
-			goto exit_acct_set;
+			return -EINVAL;
 		}
 		reshape_offset = here_new * chunk_sectors;
 		/* here_new is the stripe we will write to */
@@ -7903,8 +7879,7 @@ static int raid5_run(struct mddev *mddev)
 			else if (mddev->ro == 0) {
 				pr_warn("md/raid:%s: in-place reshape must be started in read-only mode - aborting\n",
 					mdname(mddev));
-				ret = -EINVAL;
-				goto exit_acct_set;
+				return -EINVAL;
 			}
 		} else if (mddev->reshape_backwards
 		    ? (here_new * chunk_sectors + min_offset_diff <=
@@ -7914,8 +7889,7 @@ static int raid5_run(struct mddev *mddev)
 			/* Reading from the same stripe as writing to - bad */
 			pr_warn("md/raid:%s: reshape_position too early for auto-recovery - aborting.\n",
 				mdname(mddev));
-			ret = -EINVAL;
-			goto exit_acct_set;
+			return -EINVAL;
 		}
 		pr_debug("md/raid:%s: reshape will continue\n", mdname(mddev));
 		/* OK, we should be able to continue; */
@@ -7939,10 +7913,8 @@ static int raid5_run(struct mddev *mddev)
 	else
 		conf = mddev->private;
 
-	if (IS_ERR(conf)) {
-		ret = PTR_ERR(conf);
-		goto exit_acct_set;
-	}
+	if (IS_ERR(conf))
+		return PTR_ERR(conf);
 
 	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
 		if (!journal_dev) {
@@ -8140,10 +8112,7 @@ static int raid5_run(struct mddev *mddev)
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	ret = -EIO;
-exit_acct_set:
-	acct_bioset_exit(mddev);
-	return ret;
+	return -EIO;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -8151,7 +8120,6 @@ static void raid5_free(struct mddev *mddev, void *priv)
 	struct r5conf *conf = priv;
 
 	free_conf(conf);
-	acct_bioset_exit(mddev);
 	mddev->to_remove = &raid5_attrs_group;
 }