Merge tag 'md-6.12-20240829' of...

Merge tag 'md-6.12-20240829' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.12/block

Pull MD updates from Song:

"Major changes in this set are:

 1. md-bitmap refactoring, by Yu Kuai;
 2. raid5 performance optimization, by Artur Paszkiewicz;
 3. Other small fixes, by Yu Kuai and Chen Ni."

* tag 'md-6.12-20240829' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: (49 commits)
  md/raid5: rename wait_for_overlap to wait_for_reshape
  md/raid5: only add to wq if reshape is in progress
  md/raid5: use wait_on_bit() for R5_Overlap
  md: Remove flush handling
  md/md-bitmap: make in memory structure internal
  md/md-bitmap: merge md_bitmap_enabled() into bitmap_operations
  md/md-bitmap: merge md_bitmap_wait_behind_writes() into bitmap_operations
  md/md-bitmap: merge md_bitmap_free() into bitmap_operations
  md/md-bitmap: merge md_bitmap_set_pages() into struct bitmap_operations
  md/md-bitmap: merge md_bitmap_copy_from_slot() into struct bitmap_operation.
  md/md-bitmap: merge get_bitmap_from_slot() into bitmap_operations
  md/md-bitmap: merge md_bitmap_resize() into bitmap_operations
  md/md-bitmap: pass in mddev directly for md_bitmap_resize()
  md/md-bitmap: merge md_bitmap_daemon_work() into bitmap_operations
  md/md-bitmap: merge bitmap_unplug() into bitmap_operations
  md/md-bitmap: merge md_bitmap_unplug_async() into md_bitmap_unplug()
  md/md-bitmap: merge md_bitmap_sync_with_cluster() into bitmap_operations
  md/md-bitmap: merge md_bitmap_cond_end_sync() into bitmap_operations
  md/md-bitmap: merge md_bitmap_close_sync() into bitmap_operations
  md/md-bitmap: merge md_bitmap_end_sync() into bitmap_operations
  ...

drivers/md/dm-raid.c

@@ -3949,7 +3949,9 @@ static int __load_dirty_region_bitmap(struct raid_set *rs)
 	/* Try loading the bitmap unless "raid0", which does not have one */
 	if (!rs_is_raid0(rs) &&
 	    !test_and_set_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags)) {
-		r = md_bitmap_load(&rs->md);
+		struct mddev *mddev = &rs->md;
+
+		r = mddev->bitmap_ops->load(mddev);
 		if (r)
 			DMERR("Failed to load bitmap");
 	}
@@ -4066,7 +4068,8 @@ static int raid_preresume(struct dm_target *ti)
 	       mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) {
 		int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize;
 
-		r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, chunksize, 0);
+		r = mddev->bitmap_ops->resize(mddev, mddev->dev_sectors,
+					      chunksize, false);
 		if (r)
 			DMERR("Failed to resize bitmap");
 	}

drivers/md/md-cluster.c

@@ -317,7 +317,7 @@ static void recover_bitmaps(struct md_thread *thread)
 					str, ret);
 			goto clear_bit;
 		}
-		ret = md_bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
+		ret = mddev->bitmap_ops->copy_from_slot(mddev, slot, &lo, &hi, true);
 		if (ret) {
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
@@ -497,8 +497,8 @@ static void process_suspend_info(struct mddev *mddev,
 	 * we don't want to trigger lots of WARN.
 	 */
 	if (sb && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE))
-		md_bitmap_sync_with_cluster(mddev, cinfo->sync_low,
-					    cinfo->sync_hi, lo, hi);
+		mddev->bitmap_ops->sync_with_cluster(mddev, cinfo->sync_low,
+						     cinfo->sync_hi, lo, hi);
 	cinfo->sync_low = lo;
 	cinfo->sync_hi = hi;
 
@@ -628,8 +628,9 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		break;
 	case BITMAP_RESIZE:
 		if (le64_to_cpu(msg->high) != mddev->pers->size(mddev, 0, 0))
-			ret = md_bitmap_resize(mddev->bitmap,
-					    le64_to_cpu(msg->high), 0, 0);
+			ret = mddev->bitmap_ops->resize(mddev,
+							le64_to_cpu(msg->high),
+							0, false);
 		break;
 	default:
 		ret = -1;
@@ -856,7 +857,7 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 		}
 
 		/* Read the disk bitmap sb and check if it needs recovery */
-		ret = md_bitmap_copy_from_slot(mddev, i, &lo, &hi, false);
+		ret = mddev->bitmap_ops->copy_from_slot(mddev, i, &lo, &hi, false);
 		if (ret) {
 			pr_warn("md-cluster: Could not gather bitmaps from slot %d", i);
 			lockres_free(bm_lockres);
@@ -1143,13 +1144,16 @@ static int update_bitmap_size(struct mddev *mddev, sector_t size)
 
 static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsize)
 {
-	struct bitmap_counts *counts;
-	char str[64];
-	struct dlm_lock_resource *bm_lockres;
-	struct bitmap *bitmap = mddev->bitmap;
-	unsigned long my_pages = bitmap->counts.pages;
+	void *bitmap = mddev->bitmap;
+	struct md_bitmap_stats stats;
+	unsigned long my_pages;
 	int i, rv;
 
+	rv = mddev->bitmap_ops->get_stats(bitmap, &stats);
+	if (rv)
+		return rv;
+
+	my_pages = stats.pages;
 	/*
 	 * We need to ensure all the nodes can grow to a larger
 	 * bitmap size before make the reshaping.
@@ -1159,17 +1163,22 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
 		return rv;
 
 	for (i = 0; i < mddev->bitmap_info.nodes; i++) {
+		struct dlm_lock_resource *bm_lockres;
+		char str[64];
+
 		if (i == md_cluster_ops->slot_number(mddev))
 			continue;
 
-		bitmap = get_bitmap_from_slot(mddev, i);
+		bitmap = mddev->bitmap_ops->get_from_slot(mddev, i);
 		if (IS_ERR(bitmap)) {
 			pr_err("can't get bitmap from slot %d\n", i);
 			bitmap = NULL;
 			goto out;
 		}
-		counts = &bitmap->counts;
 
+		rv = mddev->bitmap_ops->get_stats(bitmap, &stats);
+		if (rv)
+			goto out;
 		/*
 		 * If we can hold the bitmap lock of one node then
 		 * the slot is not occupied, update the pages.
@@ -1183,21 +1192,21 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
 		bm_lockres->flags |= DLM_LKF_NOQUEUE;
 		rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
 		if (!rv)
-			counts->pages = my_pages;
+			mddev->bitmap_ops->set_pages(bitmap, my_pages);
 		lockres_free(bm_lockres);
 
-		if (my_pages != counts->pages)
+		if (my_pages != stats.pages)
 			/*
 			 * Let's revert the bitmap size if one node
 			 * can't resize bitmap
 			 */
 			goto out;
-		md_bitmap_free(bitmap);
+		mddev->bitmap_ops->free(bitmap);
 	}
 
 	return 0;
 out:
-	md_bitmap_free(bitmap);
+	mddev->bitmap_ops->free(bitmap);
 	update_bitmap_size(mddev, oldsize);
 	return -1;
 }
@@ -1207,24 +1216,27 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
  */
 static int cluster_check_sync_size(struct mddev *mddev)
 {
-	int i, rv;
-	bitmap_super_t *sb;
-	unsigned long my_sync_size, sync_size = 0;
-	int node_num = mddev->bitmap_info.nodes;
 	int current_slot = md_cluster_ops->slot_number(mddev);
-	struct bitmap *bitmap = mddev->bitmap;
-	char str[64];
+	int node_num = mddev->bitmap_info.nodes;
 	struct dlm_lock_resource *bm_lockres;
+	struct md_bitmap_stats stats;
+	void *bitmap = mddev->bitmap;
+	unsigned long sync_size = 0;
+	unsigned long my_sync_size;
+	char str[64];
+	int i, rv;
 
-	sb = kmap_atomic(bitmap->storage.sb_page);
-	my_sync_size = sb->sync_size;
-	kunmap_atomic(sb);
+	rv = mddev->bitmap_ops->get_stats(bitmap, &stats);
+	if (rv)
+		return rv;
+
+	my_sync_size = stats.sync_size;
 
 	for (i = 0; i < node_num; i++) {
 		if (i == current_slot)
 			continue;
 
-		bitmap = get_bitmap_from_slot(mddev, i);
+		bitmap = mddev->bitmap_ops->get_from_slot(mddev, i);
 		if (IS_ERR(bitmap)) {
 			pr_err("can't get bitmap from slot %d\n", i);
 			return -1;
@@ -1238,25 +1250,28 @@ static int cluster_check_sync_size(struct mddev *mddev)
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
 			pr_err("md-cluster: Cannot initialize %s\n", str);
-			md_bitmap_free(bitmap);
+			mddev->bitmap_ops->free(bitmap);
 			return -1;
 		}
 		bm_lockres->flags |= DLM_LKF_NOQUEUE;
 		rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
 		if (!rv)
-			md_bitmap_update_sb(bitmap);
+			mddev->bitmap_ops->update_sb(bitmap);
 		lockres_free(bm_lockres);
 
-		sb = kmap_atomic(bitmap->storage.sb_page);
-		if (sync_size == 0)
-			sync_size = sb->sync_size;
-		else if (sync_size != sb->sync_size) {
-			kunmap_atomic(sb);
-			md_bitmap_free(bitmap);
+		rv = mddev->bitmap_ops->get_stats(bitmap, &stats);
+		if (rv) {
+			mddev->bitmap_ops->free(bitmap);
+			return rv;
+		}
+
+		if (sync_size == 0) {
+			sync_size = stats.sync_size;
+		} else if (sync_size != stats.sync_size) {
+			mddev->bitmap_ops->free(bitmap);
 			return -1;
 		}
-		kunmap_atomic(sb);
-		md_bitmap_free(bitmap);
+		mddev->bitmap_ops->free(bitmap);
 	}
 
 	return (my_sync_size == sync_size) ? 0 : -1;
@@ -1585,7 +1600,7 @@ static int gather_bitmaps(struct md_rdev *rdev)
 	for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) {
 		if (sn == (cinfo->slot_number - 1))
 			continue;
-		err = md_bitmap_copy_from_slot(mddev, sn, &lo, &hi, false);
+		err = mddev->bitmap_ops->copy_from_slot(mddev, sn, &lo, &hi, false);
 		if (err) {
 			pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn);
 			goto out;

drivers/md/md.h

@@ -535,7 +535,8 @@ struct mddev {
 	struct percpu_ref		writes_pending;
 	int				sync_checkers;	/* # of threads checking writes_pending */
 
-	struct bitmap			*bitmap; /* the bitmap for the device */
+	void				*bitmap; /* the bitmap for the device */
+	struct bitmap_operations	*bitmap_ops;
 	struct {
 		struct file		*file; /* the bitmap file */
 		loff_t			offset; /* offset from superblock of
@@ -571,16 +572,6 @@ struct mddev {
 						   */
 	struct bio_set			io_clone_set;
 
-	/* Generic flush handling.
-	 * The last to finish preflush schedules a worker to submit
-	 * the rest of the request (without the REQ_PREFLUSH flag).
-	 */
-	struct bio *flush_bio;
-	atomic_t flush_pending;
-	ktime_t start_flush, prev_flush_start; /* prev_flush_start is when the previous completed
-						* flush was started.
-						*/
-	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
 	mempool_t *serial_info_pool;
 	void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);

drivers/md/raid1-10.c

@@ -140,7 +140,7 @@ static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio,
 	 * If bitmap is not enabled, it's safe to submit the io directly, and
 	 * this can get optimal performance.
 	 */
-	if (!md_bitmap_enabled(mddev->bitmap)) {
+	if (!mddev->bitmap_ops->enabled(mddev)) {
 		raid1_submit_write(bio);
 		return true;
 	}
@@ -166,12 +166,9 @@ static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio,
  * while current io submission must wait for bitmap io to be done. In order to
  * avoid such deadlock, submit bitmap io asynchronously.
  */
-static inline void raid1_prepare_flush_writes(struct bitmap *bitmap)
+static inline void raid1_prepare_flush_writes(struct mddev *mddev)
 {
-	if (current->bio_list)
-		md_bitmap_unplug_async(bitmap);
-	else
-		md_bitmap_unplug(bitmap);
+	mddev->bitmap_ops->unplug(mddev, current->bio_list == NULL);
 }
 
 /*

drivers/md/raid1.c

@@ -411,18 +411,20 @@ static void raid1_end_read_request(struct bio *bio)
 
 static void close_write(struct r1bio *r1_bio)
 {
+	struct mddev *mddev = r1_bio->mddev;
+
 	/* it really is the end of this request */
 	if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
 		bio_free_pages(r1_bio->behind_master_bio);
 		bio_put(r1_bio->behind_master_bio);
 		r1_bio->behind_master_bio = NULL;
 	}
+
 	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
-			   r1_bio->sectors,
-			   !test_bit(R1BIO_Degraded, &r1_bio->state),
-			   test_bit(R1BIO_BehindIO, &r1_bio->state));
-	md_write_end(r1_bio->mddev);
+	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));
+	md_write_end(mddev);
 }
 
 static void r1_bio_write_done(struct r1bio *r1_bio)
@@ -894,7 +896,7 @@ static void wake_up_barrier(struct r1conf *conf)
 static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 {
 	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
-	raid1_prepare_flush_writes(conf->mddev->bitmap);
+	raid1_prepare_flush_writes(conf->mddev);
 	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
@@ -1311,13 +1313,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
 	struct bio *read_bio;
-	struct bitmap *bitmap = mddev->bitmap;
 	const enum req_op op = bio_op(bio);
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
 	int rdisk;
 	bool r1bio_existed = !!r1_bio;
-	char b[BDEVNAME_SIZE];
 
 	/*
 	 * If r1_bio is set, we are blocking the raid1d thread
@@ -1326,16 +1326,6 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 */
 	gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
-	if (r1bio_existed) {
-		/* Need to get the block device name carefully */
-		struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
-
-		if (rdev)
-			snprintf(b, sizeof(b), "%pg", rdev->bdev);
-		else
-			strcpy(b, "???");
-	}
-
 	/*
 	 * Still need barrier for READ in case that whole
 	 * array is frozen.
@@ -1357,15 +1347,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 * used and no empty request is available.
 	 */
 	rdisk = read_balance(conf, r1_bio, &max_sectors);
-
 	if (rdisk < 0) {
 		/* couldn't find anywhere to read from */
-		if (r1bio_existed) {
-			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
+		if (r1bio_existed)
+			pr_crit_ratelimited("md/raid1:%s: %pg: unrecoverable I/O read error for block %llu\n",
 					    mdname(mddev),
-					    b,
-					    (unsigned long long)r1_bio->sector);
-		}
+					    conf->mirrors[r1_bio->read_disk].rdev->bdev,
+					    r1_bio->sector);
 		raid_end_bio_io(r1_bio);
 		return;
 	}
@@ -1377,15 +1365,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 				    (unsigned long long)r1_bio->sector,
 				    mirror->rdev->bdev);
 
-	if (test_bit(WriteMostly, &mirror->rdev->flags) &&
-	    bitmap) {
+	if (test_bit(WriteMostly, &mirror->rdev->flags)) {
 		/*
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
 		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
-		wait_event(bitmap->behind_wait,
-			   atomic_read(&bitmap->behind_writes) == 0);
+		mddev->bitmap_ops->wait_behind_writes(mddev);
 	}
 
 	if (max_sectors < bio_sectors(bio)) {
@@ -1426,7 +1412,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 	int i, disks;
-	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	int first_clone;
@@ -1579,7 +1564,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 * at a time and thus needs a new bio that can fit the whole payload
 	 * this bio in page sized chunks.
 	 */
-	if (write_behind && bitmap)
+	if (write_behind && mddev->bitmap)
 		max_sectors = min_t(int, max_sectors,
 				    BIO_MAX_VECS * (PAGE_SIZE >> 9));
 	if (max_sectors < bio_sectors(bio)) {
@@ -1606,19 +1591,23 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			continue;
 
 		if (first_clone) {
+			unsigned long max_write_behind =
+				mddev->bitmap_info.max_write_behind;
+			struct md_bitmap_stats stats;
+			int err;
+
 			/* do behind I/O ?
 			 * Not if there are too many, or cannot
 			 * allocate memory, or a reader on WriteMostly
 			 * is waiting for behind writes to flush */
-			if (bitmap && write_behind &&
-			    (atomic_read(&bitmap->behind_writes)
-			     < mddev->bitmap_info.max_write_behind) &&
-			    !waitqueue_active(&bitmap->behind_wait)) {
+			err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats);
+			if (!err && write_behind && !stats.behind_wait &&
+			    stats.behind_writes < max_write_behind)
 				alloc_behind_master_bio(r1_bio, bio);
-			}
 
-			md_bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors,
-					     test_bit(R1BIO_BehindIO, &r1_bio->state));
+			mddev->bitmap_ops->startwrite(
+				mddev, r1_bio->sector, r1_bio->sectors,
+				test_bit(R1BIO_BehindIO, &r1_bio->state));
 			first_clone = 0;
 		}
 
@@ -2036,7 +2025,7 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
 
 	/* make sure these bits don't get cleared. */
 	do {
-		md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1);
+		mddev->bitmap_ops->end_sync(mddev, s, &sync_blocks);
 		s += sync_blocks;
 		sectors_to_go -= sync_blocks;
 	} while (sectors_to_go > 0);
@@ -2765,7 +2754,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	int wonly = -1;
 	int write_targets = 0, read_targets = 0;
 	sector_t sync_blocks;
-	int still_degraded = 0;
+	bool still_degraded = false;
 	int good_sectors = RESYNC_SECTORS;
 	int min_bad = 0; /* number of sectors that are bad in all devices */
 	int idx = sector_to_idx(sector_nr);
@@ -2782,12 +2771,12 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		 * We can find the current addess in mddev->curr_resync
 		 */
 		if (mddev->curr_resync < max_sector) /* aborted */
-			md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
-					   &sync_blocks, 1);
+			mddev->bitmap_ops->end_sync(mddev, mddev->curr_resync,
+						    &sync_blocks);
 		else /* completed sync */
 			conf->fullsync = 0;
 
-		md_bitmap_close_sync(mddev->bitmap);
+		mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 
 		if (mddev_is_clustered(mddev)) {
@@ -2807,7 +2796,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	/* before building a request, check if we can skip these blocks..
 	 * This call the bitmap_start_sync doesn't actually record anything
 	 */
-	if (!md_bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	if (!mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, true) &&
 	    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
 		/* We can skip this block, and probably several more */
 		*skipped = 1;
@@ -2825,9 +2814,9 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	 * sector_nr + two times RESYNC_SECTORS
 	 */
 
-	md_bitmap_cond_end_sync(mddev->bitmap, sector_nr,
-		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
-
+	mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
+		mddev_is_clustered(mddev) &&
+		(sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 
 	if (raise_barrier(conf, sector_nr))
 		return 0;
@@ -2858,7 +2847,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
-				still_degraded = 1;
+				still_degraded = true;
 		} else if (!test_bit(In_sync, &rdev->flags)) {
 			bio->bi_opf = REQ_OP_WRITE;
 			bio->bi_end_io = end_sync_write;
@@ -2982,8 +2971,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (len == 0)
 			break;
 		if (sync_blocks == 0) {
-			if (!md_bitmap_start_sync(mddev->bitmap, sector_nr,
-						  &sync_blocks, still_degraded) &&
+			if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
+						&sync_blocks, still_degraded) &&
 			    !conf->fullsync &&
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
@@ -3307,14 +3296,16 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
 	 * worth it.
 	 */
 	sector_t newsize = raid1_size(mddev, sectors, 0);
+	int ret;
+
 	if (mddev->external_size &&
 	    mddev->array_sectors > newsize)
 		return -EINVAL;
-	if (mddev->bitmap) {
-		int ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
-		if (ret)
-			return ret;
-	}
+
+	ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
+	if (ret)
+		return ret;
+
 	md_set_array_sectors(mddev, newsize);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {

drivers/md/raid10.c

@@ -426,12 +426,13 @@ static void raid10_end_read_request(struct bio *bio)
 
 static void close_write(struct r10bio *r10_bio)
 {
+	struct mddev *mddev = r10_bio->mddev;
+
 	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
-			   r10_bio->sectors,
-			   !test_bit(R10BIO_Degraded, &r10_bio->state),
-			   0);
-	md_write_end(r10_bio->mddev);
+	mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors,
+				    !test_bit(R10BIO_Degraded, &r10_bio->state),
+				    false);
+	md_write_end(mddev);
 }
 
 static void one_write_done(struct r10bio *r10_bio)
@@ -884,7 +885,7 @@ static void flush_pending_writes(struct r10conf *conf)
 		__set_current_state(TASK_RUNNING);
 
 		blk_start_plug(&plug);
-		raid1_prepare_flush_writes(conf->mddev->bitmap);
+		raid1_prepare_flush_writes(conf->mddev);
 		wake_up(&conf->wait_barrier);
 
 		while (bio) { /* submit pending writes */
@@ -1100,7 +1101,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	/* we aren't scheduling, so we can do the write-out directly. */
 	bio = bio_list_get(&plug->pending);
-	raid1_prepare_flush_writes(mddev->bitmap);
+	raid1_prepare_flush_writes(mddev);
 	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
@@ -1492,7 +1493,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
+	mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors,
+				      false);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)
@@ -2465,7 +2467,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 			s = PAGE_SIZE >> 9;
 
 		rdev = conf->mirrors[dr].rdev;
-		addr = r10_bio->devs[0].addr + sect,
+		addr = r10_bio->devs[0].addr + sect;
 		ok = sync_page_io(rdev,
 				  addr,
 				  s << 9,
@@ -3192,13 +3194,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (mddev->curr_resync < max_sector) { /* aborted */
 			if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-				md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
-						   &sync_blocks, 1);
+				mddev->bitmap_ops->end_sync(mddev,
+							    mddev->curr_resync,
+							    &sync_blocks);
 			else for (i = 0; i < conf->geo.raid_disks; i++) {
 				sector_t sect =
 					raid10_find_virt(conf, mddev->curr_resync, i);
-				md_bitmap_end_sync(mddev->bitmap, sect,
-						   &sync_blocks, 1);
+
+				mddev->bitmap_ops->end_sync(mddev, sect,
+							    &sync_blocks);
 			}
 		} else {
 			/* completed sync */
@@ -3218,7 +3222,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			}
 			conf->fullsync = 0;
 		}
-		md_bitmap_close_sync(mddev->bitmap);
+		mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 		*skipped = 1;
 		return sectors_skipped;
@@ -3287,10 +3291,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		r10_bio = NULL;
 
 		for (i = 0 ; i < conf->geo.raid_disks; i++) {
-			int still_degraded;
+			bool still_degraded;
 			struct r10bio *rb2;
 			sector_t sect;
-			int must_sync;
+			bool must_sync;
 			int any_working;
 			struct raid10_info *mirror = &conf->mirrors[i];
 			struct md_rdev *mrdev, *mreplace;
@@ -3307,7 +3311,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (!mrdev && !mreplace)
 				continue;
 
-			still_degraded = 0;
+			still_degraded = false;
 			/* want to reconstruct this device */
 			rb2 = r10_bio;
 			sect = raid10_find_virt(conf, sector_nr, i);
@@ -3320,8 +3324,9 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			 * we only need to recover the block if it is set in
 			 * the bitmap
 			 */
-			must_sync = md_bitmap_start_sync(mddev->bitmap, sect,
-							 &sync_blocks, 1);
+			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
+								  &sync_blocks,
+								  true);
 			if (sync_blocks < max_sync)
 				max_sync = sync_blocks;
 			if (!must_sync &&
@@ -3359,13 +3364,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				struct md_rdev *rdev = conf->mirrors[j].rdev;
 
 				if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
-					still_degraded = 1;
+					still_degraded = false;
 					break;
 				}
 			}
 
-			must_sync = md_bitmap_start_sync(mddev->bitmap, sect,
-							 &sync_blocks, still_degraded);
+			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
+						&sync_blocks, still_degraded);
 
 			any_working = 0;
 			for (j=0; j<conf->copies;j++) {
@@ -3538,12 +3543,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		 * safety reason, which ensures curr_resync_completed is
 		 * updated in bitmap_cond_end_sync.
 		 */
-		md_bitmap_cond_end_sync(mddev->bitmap, sector_nr,
+		mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
 					mddev_is_clustered(mddev) &&
 					(sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 
-		if (!md_bitmap_start_sync(mddev->bitmap, sector_nr,
-					  &sync_blocks, mddev->degraded) &&
+		if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
+						   &sync_blocks,
+						   mddev->degraded) &&
 		    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED,
 						 &mddev->recovery)) {
 			/* We can skip this block */
@@ -4190,6 +4196,7 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	 */
 	struct r10conf *conf = mddev->private;
 	sector_t oldsize, size;
+	int ret;
 
 	if (mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -4202,11 +4209,11 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	if (mddev->external_size &&
 	    mddev->array_sectors > size)
 		return -EINVAL;
-	if (mddev->bitmap) {
-		int ret = md_bitmap_resize(mddev->bitmap, size, 0, 0);
-		if (ret)
-			return ret;
-	}
+
+	ret = mddev->bitmap_ops->resize(mddev, size, 0, false);
+	if (ret)
+		return ret;
+
 	md_set_array_sectors(mddev, size);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > oldsize) {
@@ -4472,7 +4479,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 		newsize = raid10_size(mddev, 0, conf->geo.raid_disks);
 
 		if (!mddev_is_clustered(mddev)) {
-			ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
+			ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
 			if (ret)
 				goto abort;
 			else
@@ -4487,20 +4494,20 @@ static int raid10_start_reshape(struct mddev *mddev)
 
 		/*
 		 * some node is already performing reshape, and no need to
-		 * call md_bitmap_resize again since it should be called when
+		 * call bitmap_ops->resize again since it should be called when
 		 * receiving BITMAP_RESIZE msg
 		 */
 		if ((sb && (le32_to_cpu(sb->feature_map) &
 			    MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize))
 			goto out;
 
-		ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
+		ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
 		if (ret)
 			goto abort;
 
 		ret = md_cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
 		if (ret) {
-			md_bitmap_resize(mddev->bitmap, oldsize, 0, 0);
+			mddev->bitmap_ops->resize(mddev, oldsize, 0, false);
 			goto abort;
 		}
 	}

drivers/md/raid5-cache.c

@@ -313,10 +313,10 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
-			md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
-					   RAID5_STRIPE_SECTORS(conf),
-					   !test_bit(STRIPE_DEGRADED, &sh->state),
-					   0);
+			conf->mddev->bitmap_ops->endwrite(conf->mddev,
+					sh->sector, RAID5_STRIPE_SECTORS(conf),
+					!test_bit(STRIPE_DEGRADED, &sh->state),
+					false);
 		}
 	}
 }
@@ -2798,7 +2798,6 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 {
 	struct r5l_log *log = READ_ONCE(conf->log);
 	int i;
-	int do_wakeup = 0;
 	sector_t tree_index;
 	void __rcu **pslot;
 	uintptr_t refcount;
@@ -2815,7 +2814,7 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 	for (i = sh->disks; i--; ) {
 		clear_bit(R5_InJournal, &sh->dev[i].flags);
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
-			do_wakeup = 1;
+			wake_up_bit(&sh->dev[i].flags, R5_Overlap);
 	}
 
 	/*
@@ -2828,9 +2827,6 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 		if (atomic_dec_and_test(&conf->pending_full_writes))
 			md_wakeup_thread(conf->mddev->thread);
 
-	if (do_wakeup)
-		wake_up(&conf->wait_for_overlap);
-
 	spin_lock_irq(&log->stripe_in_journal_lock);
 	list_del_init(&sh->r5c);
 	spin_unlock_irq(&log->stripe_in_journal_lock);

drivers/md/raid5.h

@@ -668,7 +668,7 @@ struct r5conf {
 	struct llist_head	released_stripes;
 	wait_queue_head_t	wait_for_quiescent;
 	wait_queue_head_t	wait_for_stripe;
-	wait_queue_head_t	wait_for_overlap;
+	wait_queue_head_t	wait_for_reshape;
 	unsigned long		cache_state;
 	struct shrinker		*shrinker;
 	int			pool_size; /* number of disks in stripeheads in pool */