Merge branch 'md-next' into md-linus

18 files changed, 3434 insertions, 1418 deletions

diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 3cbda1af87a0..4d48714ccc6b 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -18,7 +18,7 @@ dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
 dm-verity-y	+= dm-verity-target.o
 md-mod-y	+= md.o bitmap.o
-raid456-y	+= raid5.o raid5-cache.o
+raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 9fb2ccac958a..bf7419a56454 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -471,6 +471,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
 	kunmap_atomic(sb);
 	write_page(bitmap, bitmap->storage.sb_page, 1);
 }
+EXPORT_SYMBOL(bitmap_update_sb);
 
 /* print out the bitmap file superblock */
 void bitmap_print_sb(struct bitmap *bitmap)
@@ -696,7 +697,7 @@ re_read:
 
 out:
 	kunmap_atomic(sb);
-	/* Assiging chunksize is required for "re_read" */
+	/* Assigning chunksize is required for "re_read" */
 	bitmap->mddev->bitmap_info.chunksize = chunksize;
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		err = md_setup_cluster(bitmap->mddev, nodes);
@@ -1727,7 +1728,7 @@ void bitmap_flush(struct mddev *mddev)
 /*
  * free memory that was allocated
  */
-static void bitmap_free(struct bitmap *bitmap)
+void bitmap_free(struct bitmap *bitmap)
 {
 	unsigned long k, pages;
 	struct bitmap_page *bp;
@@ -1761,6 +1762,21 @@ static void bitmap_free(struct bitmap *bitmap)
 	kfree(bp);
 	kfree(bitmap);
 }
+EXPORT_SYMBOL(bitmap_free);
+
+void bitmap_wait_behind_writes(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	/* wait for behind writes to complete */
+	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		pr_debug("md:%s: behind writes in progress - waiting to stop.\n",
+			 mdname(mddev));
+		/* need to kick something here to make sure I/O goes? */
+		wait_event(bitmap->behind_wait,
+			   atomic_read(&bitmap->behind_writes) == 0);
+	}
+}
 
 void bitmap_destroy(struct mddev *mddev)
 {
@@ -1769,6 +1785,8 @@ void bitmap_destroy(struct mddev *mddev)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
+	bitmap_wait_behind_writes(mddev);
+
 	mutex_lock(&mddev->bitmap_info.mutex);
 	spin_lock(&mddev->lock);
 	mddev->bitmap = NULL; /* disconnect from the md device */
@@ -1920,6 +1938,27 @@ out:
 }
 EXPORT_SYMBOL_GPL(bitmap_load);
 
+struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot)
+{
+	int rv = 0;
+	struct bitmap *bitmap;
+
+	bitmap = bitmap_create(mddev, slot);
+	if (IS_ERR(bitmap)) {
+		rv = PTR_ERR(bitmap);
+		return ERR_PTR(rv);
+	}
+
+	rv = bitmap_init_from_disk(bitmap, 0);
+	if (rv) {
+		bitmap_free(bitmap);
+		return ERR_PTR(rv);
+	}
+
+	return bitmap;
+}
+EXPORT_SYMBOL(get_bitmap_from_slot);
+
 /* Loads the bitmap associated with slot and copies the resync information
  * to our bitmap
  */
@@ -1929,14 +1968,13 @@ int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	int rv = 0, i, j;
 	sector_t block, lo = 0, hi = 0;
 	struct bitmap_counts *counts;
-	struct bitmap *bitmap = bitmap_create(mddev, slot);
-
-	if (IS_ERR(bitmap))
-		return PTR_ERR(bitmap);
+	struct bitmap *bitmap;
 
-	rv = bitmap_init_from_disk(bitmap, 0);
-	if (rv)
-		goto err;
+	bitmap = get_bitmap_from_slot(mddev, slot);
+	if (IS_ERR(bitmap)) {
+		pr_err("%s can't get bitmap from slot %d\n", __func__, slot);
+		return -1;
+	}
 
 	counts = &bitmap->counts;
 	for (j = 0; j < counts->chunks; j++) {
@@ -1963,8 +2001,7 @@ int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	bitmap_unplug(mddev->bitmap);
 	*low = lo;
 	*high = hi;
-err:
-	bitmap_free(bitmap);
+
 	return rv;
 }
 EXPORT_SYMBOL_GPL(bitmap_copy_from_slot);
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index 5b6dd63dda91..d15721ac07a6 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -267,8 +267,11 @@ void bitmap_daemon_work(struct mddev *mddev);
 
 int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		  int chunksize, int init);
+struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot);
 int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 				sector_t *lo, sector_t *hi, bool clear_bits);
+void bitmap_free(struct bitmap *bitmap);
+void bitmap_wait_behind_writes(struct mddev *mddev);
 #endif
 
 #endif
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 377a8a3672e3..df6f2c98eca7 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -249,54 +249,49 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 {
 	char b[BDEVNAME_SIZE];
 	struct dev_info *tmp_dev;
-	struct bio *split;
 	sector_t start_sector, end_sector, data_offset;
+	sector_t bio_sector = bio->bi_iter.bi_sector;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	do {
-		sector_t bio_sector = bio->bi_iter.bi_sector;
-		tmp_dev = which_dev(mddev, bio_sector);
-		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
-		end_sector = tmp_dev->end_sector;
-		data_offset = tmp_dev->rdev->data_offset;
-		bio->bi_bdev = tmp_dev->rdev->bdev;
-
-		if (unlikely(bio_sector >= end_sector ||
-			     bio_sector < start_sector))
-			goto out_of_bounds;
-
-		if (unlikely(bio_end_sector(bio) > end_sector)) {
-			/* This bio crosses a device boundary, so we have to
-			 * split it.
-			 */
-			split = bio_split(bio, end_sector - bio_sector,
-					  GFP_NOIO, fs_bio_set);
-			bio_chain(split, bio);
-		} else {
-			split = bio;
-		}
+	tmp_dev = which_dev(mddev, bio_sector);
+	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+	end_sector = tmp_dev->end_sector;
+	data_offset = tmp_dev->rdev->data_offset;
+
+	if (unlikely(bio_sector >= end_sector ||
+		     bio_sector < start_sector))
+		goto out_of_bounds;
+
+	if (unlikely(bio_end_sector(bio) > end_sector)) {
+		/* This bio crosses a device boundary, so we have to split it */
+		struct bio *split = bio_split(bio, end_sector - bio_sector,
+					      GFP_NOIO, mddev->bio_set);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+	}
 
-		split->bi_iter.bi_sector = split->bi_iter.bi_sector -
-			start_sector + data_offset;
-
-		if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
-			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
-			/* Just ignore it */
-			bio_endio(split);
-		} else {
-			if (mddev->gendisk)
-				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
-						      split, disk_devt(mddev->gendisk),
-						      bio_sector);
-			mddev_check_writesame(mddev, split);
-			mddev_check_write_zeroes(mddev, split);
-			generic_make_request(split);
-		}
-	} while (split != bio);
+	bio->bi_bdev = tmp_dev->rdev->bdev;
+	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
+		start_sector + data_offset;
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
+		/* Just ignore it */
+		bio_endio(bio);
+	} else {
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+					      bio, disk_devt(mddev->gendisk),
+					      bio_sector);
+		mddev_check_writesame(mddev, bio);
+		mddev_check_write_zeroes(mddev, bio);
+		generic_make_request(bio);
+	}
 	return;
 
 out_of_bounds:
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 321ecac23027..7299ce2f08a8 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -67,9 +67,10 @@ struct resync_info {
  * set up all the related infos such as bitmap and personality */
 #define		MD_CLUSTER_ALREADY_IN_CLUSTER		6
 #define		MD_CLUSTER_PENDING_RECV_EVENT		7
-
+#define 	MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD		8
 
 struct md_cluster_info {
+	struct mddev *mddev; /* the md device which md_cluster_info belongs to */
 	/* dlm lock space and resources for clustered raid. */
 	dlm_lockspace_t *lockspace;
 	int slot_number;
@@ -103,6 +104,7 @@ enum msg_type {
 	REMOVE,
 	RE_ADD,
 	BITMAP_NEEDS_SYNC,
+	CHANGE_CAPACITY,
 };
 
 struct cluster_msg {
@@ -523,11 +525,17 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 
 static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
 {
+	int got_lock = 0;
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	mddev->good_device_nr = le32_to_cpu(msg->raid_slot);
-	set_bit(MD_RELOAD_SB, &mddev->flags);
+
 	dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
-	md_wakeup_thread(mddev->thread);
+	wait_event(mddev->thread->wqueue,
+		   (got_lock = mddev_trylock(mddev)) ||
+		    test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state));
+	md_reload_sb(mddev, mddev->good_device_nr);
+	if (got_lock)
+		mddev_unlock(mddev);
 }
 
 static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
@@ -572,6 +580,10 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 	case METADATA_UPDATED:
 		process_metadata_update(mddev, msg);
 		break;
+	case CHANGE_CAPACITY:
+		set_capacity(mddev->gendisk, mddev->array_sectors);
+		revalidate_disk(mddev->gendisk);
+		break;
 	case RESYNCING:
 		process_suspend_info(mddev, le32_to_cpu(msg->slot),
 				     le64_to_cpu(msg->low),
@@ -646,11 +658,29 @@ out:
  * Takes the lock on the TOKEN lock resource so no other
  * node can communicate while the operation is underway.
  */
-static int lock_token(struct md_cluster_info *cinfo)
+static int lock_token(struct md_cluster_info *cinfo, bool mddev_locked)
 {
-	int error;
+	int error, set_bit = 0;
+	struct mddev *mddev = cinfo->mddev;
 
+	/*
+	 * If resync thread run after raid1d thread, then process_metadata_update
+	 * could not continue if raid1d held reconfig_mutex (and raid1d is blocked
+	 * since another node already got EX on Token and waitting the EX of Ack),
+	 * so let resync wake up thread in case flag is set.
+	 */
+	if (mddev_locked && !test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
+				      &cinfo->state)) {
+		error = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
+					      &cinfo->state);
+		WARN_ON_ONCE(error);
+		md_wakeup_thread(mddev->thread);
+		set_bit = 1;
+	}
 	error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
+	if (set_bit)
+		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
+
 	if (error)
 		pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
 				__func__, __LINE__, error);
@@ -663,12 +693,12 @@ static int lock_token(struct md_cluster_info *cinfo)
 /* lock_comm()
  * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel.
  */
-static int lock_comm(struct md_cluster_info *cinfo)
+static int lock_comm(struct md_cluster_info *cinfo, bool mddev_locked)
 {
 	wait_event(cinfo->wait,
 		   !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state));
 
-	return lock_token(cinfo);
+	return lock_token(cinfo, mddev_locked);
 }
 
 static void unlock_comm(struct md_cluster_info *cinfo)
@@ -743,11 +773,12 @@ failed_message:
 	return error;
 }
 
-static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg,
+		   bool mddev_locked)
 {
 	int ret;
 
-	lock_comm(cinfo);
+	lock_comm(cinfo, mddev_locked);
 	ret = __sendmsg(cinfo, cmsg);
 	unlock_comm(cinfo);
 	return ret;
@@ -834,6 +865,7 @@ static int join(struct mddev *mddev, int nodes)
 	mutex_init(&cinfo->recv_mutex);
 
 	mddev->cluster_info = cinfo;
+	cinfo->mddev = mddev;
 
 	memset(str, 0, 64);
 	sprintf(str, "%pU", mddev->uuid);
@@ -908,6 +940,7 @@ static int join(struct mddev *mddev, int nodes)
 
 	return 0;
 err:
+	set_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
 	md_unregister_thread(&cinfo->recovery_thread);
 	md_unregister_thread(&cinfo->recv_thread);
 	lockres_free(cinfo->message_lockres);
@@ -943,7 +976,7 @@ static void resync_bitmap(struct mddev *mddev)
 	int err;
 
 	cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);
-	err = sendmsg(cinfo, &cmsg);
+	err = sendmsg(cinfo, &cmsg, 1);
 	if (err)
 		pr_err("%s:%d: failed to send BITMAP_NEEDS_SYNC message (%d)\n",
 			__func__, __LINE__, err);
@@ -963,6 +996,7 @@ static int leave(struct mddev *mddev)
 	if (cinfo->slot_number > 0 && mddev->recovery_cp != MaxSector)
 		resync_bitmap(mddev);
 
+	set_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
 	md_unregister_thread(&cinfo->recovery_thread);
 	md_unregister_thread(&cinfo->recv_thread);
 	lockres_free(cinfo->message_lockres);
@@ -997,16 +1031,30 @@ static int slot_number(struct mddev *mddev)
 static int metadata_update_start(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+	int ret;
+
+	/*
+	 * metadata_update_start is always called with the protection of
+	 * reconfig_mutex, so set WAITING_FOR_TOKEN here.
+	 */
+	ret = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
+				    &cinfo->state);
+	WARN_ON_ONCE(ret);
+	md_wakeup_thread(mddev->thread);
 
 	wait_event(cinfo->wait,
 		   !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state) ||
 		   test_and_clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state));
 
 	/* If token is already locked, return 0 */
-	if (cinfo->token_lockres->mode == DLM_LOCK_EX)
+	if (cinfo->token_lockres->mode == DLM_LOCK_EX) {
+		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
 		return 0;
+	}
 
-	return lock_token(cinfo);
+	ret = lock_token(cinfo, 1);
+	clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
+	return ret;
 }
 
 static int metadata_update_finish(struct mddev *mddev)
@@ -1043,6 +1091,141 @@ static void metadata_update_cancel(struct mddev *mddev)
 	unlock_comm(cinfo);
 }
 
+/*
+ * return 0 if all the bitmaps have the same sync_size
+ */
+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];
+	struct dlm_lock_resource *bm_lockres;
+
+	sb = kmap_atomic(bitmap->storage.sb_page);
+	my_sync_size = sb->sync_size;
+	kunmap_atomic(sb);
+
+	for (i = 0; i < node_num; i++) {
+		if (i == current_slot)
+			continue;
+
+		bitmap = get_bitmap_from_slot(mddev, i);
+		if (IS_ERR(bitmap)) {
+			pr_err("can't get bitmap from slot %d\n", i);
+			return -1;
+		}
+
+		/*
+		 * If we can hold the bitmap lock of one node then
+		 * the slot is not occupied, update the sb.
+		 */
+		snprintf(str, 64, "bitmap%04d", i);
+		bm_lockres = lockres_init(mddev, str, NULL, 1);
+		if (!bm_lockres) {
+			pr_err("md-cluster: Cannot initialize %s\n", str);
+			bitmap_free(bitmap);
+			return -1;
+		}
+		bm_lockres->flags |= DLM_LKF_NOQUEUE;
+		rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
+		if (!rv)
+			bitmap_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);
+			bitmap_free(bitmap);
+			return -1;
+		}
+		kunmap_atomic(sb);
+		bitmap_free(bitmap);
+	}
+
+	return (my_sync_size == sync_size) ? 0 : -1;
+}
+
+/*
+ * Update the size for cluster raid is a little more complex, we perform it
+ * by the steps:
+ * 1. hold token lock and update superblock in initiator node.
+ * 2. send METADATA_UPDATED msg to other nodes.
+ * 3. The initiator node continues to check each bitmap's sync_size, if all
+ *    bitmaps have the same value of sync_size, then we can set capacity and
+ *    let other nodes to perform it. If one node can't update sync_size
+ *    accordingly, we need to revert to previous value.
+ */
+static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
+{
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	struct cluster_msg cmsg;
+	struct md_rdev *rdev;
+	int ret = 0;
+	int raid_slot = -1;
+
+	md_update_sb(mddev, 1);
+	lock_comm(cinfo, 1);
+
+	memset(&cmsg, 0, sizeof(cmsg));
+	cmsg.type = cpu_to_le32(METADATA_UPDATED);
+	rdev_for_each(rdev, mddev)
+		if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) {
+			raid_slot = rdev->desc_nr;
+			break;
+		}
+	if (raid_slot >= 0) {
+		cmsg.raid_slot = cpu_to_le32(raid_slot);
+		/*
+		 * We can only change capiticy after all the nodes can do it,
+		 * so need to wait after other nodes already received the msg
+		 * and handled the change
+		 */
+		ret = __sendmsg(cinfo, &cmsg);
+		if (ret) {
+			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
+			       __func__, __LINE__);
+			unlock_comm(cinfo);
+			return;
+		}
+	} else {
+		pr_err("md-cluster: No good device id found to send\n");
+		unlock_comm(cinfo);
+		return;
+	}
+
+	/*
+	 * check the sync_size from other node's bitmap, if sync_size
+	 * have already updated in other nodes as expected, send an
+	 * empty metadata msg to permit the change of capacity
+	 */
+	if (cluster_check_sync_size(mddev) == 0) {
+		memset(&cmsg, 0, sizeof(cmsg));
+		cmsg.type = cpu_to_le32(CHANGE_CAPACITY);
+		ret = __sendmsg(cinfo, &cmsg);
+		if (ret)
+			pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n",
+			       __func__, __LINE__);
+		set_capacity(mddev->gendisk, mddev->array_sectors);
+		revalidate_disk(mddev->gendisk);
+	} else {
+		/* revert to previous sectors */
+		ret = mddev->pers->resize(mddev, old_dev_sectors);
+		if (!ret)
+			revalidate_disk(mddev->gendisk);
+		ret = __sendmsg(cinfo, &cmsg);
+		if (ret)
+			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
+			       __func__, __LINE__);
+	}
+	unlock_comm(cinfo);
+}
+
 static int resync_start(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
@@ -1069,7 +1252,14 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 	cmsg.low = cpu_to_le64(lo);
 	cmsg.high = cpu_to_le64(hi);
 
-	return sendmsg(cinfo, &cmsg);
+	/*
+	 * mddev_lock is held if resync_info_update is called from
+	 * resync_finish (md_reap_sync_thread -> resync_finish)
+	 */
+	if (lo == 0 && hi == 0)
+		return sendmsg(cinfo, &cmsg, 1);
+	else
+		return sendmsg(cinfo, &cmsg, 0);
 }
 
 static int resync_finish(struct mddev *mddev)
@@ -1119,7 +1309,7 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
 	cmsg.type = cpu_to_le32(NEWDISK);
 	memcpy(cmsg.uuid, uuid, 16);
 	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
-	lock_comm(cinfo);
+	lock_comm(cinfo, 1);
 	ret = __sendmsg(cinfo, &cmsg);
 	if (ret)
 		return ret;
@@ -1179,7 +1369,7 @@ static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	cmsg.type = cpu_to_le32(REMOVE);
 	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
-	return sendmsg(cinfo, &cmsg);
+	return sendmsg(cinfo, &cmsg, 1);
 }
 
 static int lock_all_bitmaps(struct mddev *mddev)
@@ -1243,7 +1433,7 @@ static int gather_bitmaps(struct md_rdev *rdev)
 
 	cmsg.type = cpu_to_le32(RE_ADD);
 	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
-	err = sendmsg(cinfo, &cmsg);
+	err = sendmsg(cinfo, &cmsg, 1);
 	if (err)
 		goto out;
 
@@ -1281,6 +1471,7 @@ static struct md_cluster_operations cluster_ops = {
 	.gather_bitmaps = gather_bitmaps,
 	.lock_all_bitmaps = lock_all_bitmaps,
 	.unlock_all_bitmaps = unlock_all_bitmaps,
+	.update_size = update_size,
 };
 
 static int __init cluster_init(void)
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index e765499ba591..274016177983 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -27,6 +27,7 @@ struct md_cluster_operations {
 	int (*gather_bitmaps)(struct md_rdev *rdev);
 	int (*lock_all_bitmaps)(struct mddev *mddev);
 	void (*unlock_all_bitmaps)(struct mddev *mddev);
+	void (*update_size)(struct mddev *mddev, sector_t old_dev_sectors);
 };
 
 #endif /* _MD_CLUSTER_H */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f6ae1d67bcd0..82f798be964f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -65,6 +65,8 @@
 #include <linux/raid/md_p.h>
 #include <linux/raid/md_u.h>
 #include <linux/slab.h>
+#include <linux/percpu-refcount.h>
+
 #include <trace/events/block.h>
 #include "md.h"
 #include "bitmap.h"
@@ -172,6 +174,16 @@ static const struct block_device_operations md_fops;
 
 static int start_readonly;
 
+/*
+ * The original mechanism for creating an md device is to create
+ * a device node in /dev and to open it.  This causes races with device-close.
+ * The preferred method is to write to the "new_array" module parameter.
+ * This can avoid races.
+ * Setting create_on_open to false disables the original mechanism
+ * so all the races disappear.
+ */
+static bool create_on_open = true;
+
 /* bio_clone_mddev
  * like bio_clone, but with a local bio set
  */
@@ -1507,6 +1519,12 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	} else if (sb->bblog_offset != 0)
 		rdev->badblocks.shift = 0;
 
+	if (le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) {
+		rdev->ppl.offset = (__s16)le16_to_cpu(sb->ppl.offset);
+		rdev->ppl.size = le16_to_cpu(sb->ppl.size);
+		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
+	}
+
 	if (!refdev) {
 		ret = 1;
 	} else {
@@ -1619,6 +1637,13 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
+
+		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) {
+			if (le32_to_cpu(sb->feature_map) &
+			    (MD_FEATURE_BITMAP_OFFSET | MD_FEATURE_JOURNAL))
+				return -EINVAL;
+			set_bit(MD_HAS_PPL, &mddev->flags);
+		}
 	} else if (mddev->pers == NULL) {
 		/* Insist of good event counter while assembling, except for
 		 * spares (which don't need an event count) */
@@ -1832,6 +1857,12 @@ retry:
 	if (test_bit(MD_HAS_JOURNAL, &mddev->flags))
 		sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL);
 
+	if (test_bit(MD_HAS_PPL, &mddev->flags)) {
+		sb->feature_map |= cpu_to_le32(MD_FEATURE_PPL);
+		sb->ppl.offset = cpu_to_le16(rdev->ppl.offset);
+		sb->ppl.size = cpu_to_le16(rdev->ppl.size);
+	}
+
 	rdev_for_each(rdev2, mddev) {
 		i = rdev2->desc_nr;
 		if (test_bit(Faulty, &rdev2->flags))
@@ -2072,6 +2103,10 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if (find_rdev(mddev, rdev->bdev->bd_dev))
 		return -EEXIST;
 
+	if ((bdev_read_only(rdev->bdev) || bdev_read_only(rdev->meta_bdev)) &&
+	    mddev->pers)
+		return -EROFS;
+
 	/* make sure rdev->sectors exceeds mddev->dev_sectors */
 	if (!test_bit(Journal, &rdev->flags) &&
 	    rdev->sectors &&
@@ -2233,6 +2268,33 @@ static void export_array(struct mddev *mddev)
 	mddev->major_version = 0;
 }
 
+static bool set_in_sync(struct mddev *mddev)
+{
+	WARN_ON_ONCE(!spin_is_locked(&mddev->lock));
+	if (!mddev->in_sync) {
+		mddev->sync_checkers++;
+		spin_unlock(&mddev->lock);
+		percpu_ref_switch_to_atomic_sync(&mddev->writes_pending);
+		spin_lock(&mddev->lock);
+		if (!mddev->in_sync &&
+		    percpu_ref_is_zero(&mddev->writes_pending)) {
+			mddev->in_sync = 1;
+			/*
+			 * Ensure ->in_sync is visible before we clear
+			 * ->sync_checkers.
+			 */
+			smp_mb();
+			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
+		}
+		if (--mddev->sync_checkers == 0)
+			percpu_ref_switch_to_percpu(&mddev->writes_pending);
+	}
+	if (mddev->safemode == 1)
+		mddev->safemode = 0;
+	return mddev->in_sync;
+}
+
 static void sync_sbs(struct mddev *mddev, int nospares)
 {
 	/* Update each superblock (in-memory image), but
@@ -3131,6 +3193,78 @@ static ssize_t ubb_store(struct md_rdev *rdev, const char *page, size_t len)
 static struct rdev_sysfs_entry rdev_unack_bad_blocks =
 __ATTR(unacknowledged_bad_blocks, S_IRUGO|S_IWUSR, ubb_show, ubb_store);
 
+static ssize_t
+ppl_sector_show(struct md_rdev *rdev, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)rdev->ppl.sector);
+}
+
+static ssize_t
+ppl_sector_store(struct md_rdev *rdev, const char *buf, size_t len)
+{
+	unsigned long long sector;
+
+	if (kstrtoull(buf, 10, &sector) < 0)
+		return -EINVAL;
+	if (sector != (sector_t)sector)
+		return -EINVAL;
+
+	if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) &&
+	    rdev->raid_disk >= 0)
+		return -EBUSY;
+
+	if (rdev->mddev->persistent) {
+		if (rdev->mddev->major_version == 0)
+			return -EINVAL;
+		if ((sector > rdev->sb_start &&
+		     sector - rdev->sb_start > S16_MAX) ||
+		    (sector < rdev->sb_start &&
+		     rdev->sb_start - sector > -S16_MIN))
+			return -EINVAL;
+		rdev->ppl.offset = sector - rdev->sb_start;
+	} else if (!rdev->mddev->external) {
+		return -EBUSY;
+	}
+	rdev->ppl.sector = sector;
+	return len;
+}
+
+static struct rdev_sysfs_entry rdev_ppl_sector =
+__ATTR(ppl_sector, S_IRUGO|S_IWUSR, ppl_sector_show, ppl_sector_store);
+
+static ssize_t
+ppl_size_show(struct md_rdev *rdev, char *page)
+{
+	return sprintf(page, "%u\n", rdev->ppl.size);
+}
+
+static ssize_t
+ppl_size_store(struct md_rdev *rdev, const char *buf, size_t len)
+{
+	unsigned int size;
+
+	if (kstrtouint(buf, 10, &size) < 0)
+		return -EINVAL;
+
+	if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) &&
+	    rdev->raid_disk >= 0)
+		return -EBUSY;
+
+	if (rdev->mddev->persistent) {
+		if (rdev->mddev->major_version == 0)
+			return -EINVAL;
+		if (size > U16_MAX)
+			return -EINVAL;
+	} else if (!rdev->mddev->external) {
+		return -EBUSY;
+	}
+	rdev->ppl.size = size;
+	return len;
+}
+
+static struct rdev_sysfs_entry rdev_ppl_size =
+__ATTR(ppl_size, S_IRUGO|S_IWUSR, ppl_size_show, ppl_size_store);
+
 static struct attribute *rdev_default_attrs[] = {
 	&rdev_state.attr,
 	&rdev_errors.attr,
@@ -3141,6 +3275,8 @@ static struct attribute *rdev_default_attrs[] = {
 	&rdev_recovery_start.attr,
 	&rdev_bad_blocks.attr,
 	&rdev_unack_bad_blocks.attr,
+	&rdev_ppl_sector.attr,
+	&rdev_ppl_size.attr,
 	NULL,
 };
 static ssize_t
@@ -3903,6 +4039,7 @@ array_state_show(struct mddev *mddev, char *page)
 			st = read_auto;
 			break;
 		case 0:
+			spin_lock(&mddev->lock);
 			if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
 				st = write_pending;
 			else if (mddev->in_sync)
@@ -3911,6 +4048,7 @@ array_state_show(struct mddev *mddev, char *page)
 				st = active_idle;
 			else
 				st = active;
+			spin_unlock(&mddev->lock);
 		}
 	else {
 		if (list_empty(&mddev->disks) &&
@@ -3931,7 +4069,7 @@ static int restart_array(struct mddev *mddev);
 static ssize_t
 array_state_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	int err;
+	int err = 0;
 	enum array_state st = match_word(buf, array_states);
 
 	if (mddev->pers && (st == active || st == clean) && mddev->ro != 1) {
@@ -3944,18 +4082,9 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
 			md_wakeup_thread(mddev->thread);
 			wake_up(&mddev->sb_wait);
-			err = 0;
 		} else /* st == clean */ {
 			restart_array(mddev);
-			if (atomic_read(&mddev->writes_pending) == 0) {
-				if (mddev->in_sync == 0) {
-					mddev->in_sync = 1;
-					if (mddev->safemode == 1)
-						mddev->safemode = 0;
-					set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
-				}
-				err = 0;
-			} else
+			if (!set_in_sync(mddev))
 				err = -EBUSY;
 		}
 		if (!err)
@@ -4013,15 +4142,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 			if (err)
 				break;
 			spin_lock(&mddev->lock);
-			if (atomic_read(&mddev->writes_pending) == 0) {
-				if (mddev->in_sync == 0) {
-					mddev->in_sync = 1;
-					if (mddev->safemode == 1)
-						mddev->safemode = 0;
-					set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
-				}
-				err = 0;
-			} else
+			if (!set_in_sync(mddev))
 				err = -EBUSY;
 			spin_unlock(&mddev->lock);
 		} else
@@ -4843,8 +4964,10 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 		return err;
 
 	/* cluster raid doesn't support change array_sectors */
-	if (mddev_is_clustered(mddev))
+	if (mddev_is_clustered(mddev)) {
+		mddev_unlock(mddev);
 		return -EINVAL;
+	}
 
 	if (strncmp(buf, "default", 7) == 0) {
 		if (mddev->pers)
@@ -4877,6 +5000,52 @@ static struct md_sysfs_entry md_array_size =
 __ATTR(array_size, S_IRUGO|S_IWUSR, array_size_show,
        array_size_store);
 
+static ssize_t
+consistency_policy_show(struct mddev *mddev, char *page)
+{
+	int ret;
+
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		ret = sprintf(page, "journal\n");
+	} else if (test_bit(MD_HAS_PPL, &mddev->flags)) {
+		ret = sprintf(page, "ppl\n");
+	} else if (mddev->bitmap) {
+		ret = sprintf(page, "bitmap\n");
+	} else if (mddev->pers) {
+		if (mddev->pers->sync_request)
+			ret = sprintf(page, "resync\n");
+		else
+			ret = sprintf(page, "none\n");
+	} else {
+		ret = sprintf(page, "unknown\n");
+	}
+
+	return ret;
+}
+
+static ssize_t
+consistency_policy_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	int err = 0;
+
+	if (mddev->pers) {
+		if (mddev->pers->change_consistency_policy)
+			err = mddev->pers->change_consistency_policy(mddev, buf);
+		else
+			err = -EBUSY;
+	} else if (mddev->external && strncmp(buf, "ppl", 3) == 0) {
+		set_bit(MD_HAS_PPL, &mddev->flags);
+	} else {
+		err = -EINVAL;
+	}
+
+	return err ? err : len;
+}
+
+static struct md_sysfs_entry md_consistency_policy =
+__ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
+       consistency_policy_store);
+
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_layout.attr,
@@ -4892,6 +5061,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_reshape_direction.attr,
 	&md_array_size.attr,
 	&max_corr_read_errors.attr,
+	&md_consistency_policy.attr,
 	NULL,
 };
 
@@ -4976,6 +5146,7 @@ static void md_free(struct kobject *ko)
 		del_gendisk(mddev->gendisk);
 		put_disk(mddev->gendisk);
 	}
+	percpu_ref_exit(&mddev->writes_pending);
 
 	kfree(mddev);
 }
@@ -5001,8 +5172,19 @@ static void mddev_delayed_delete(struct work_struct *ws)
 	kobject_put(&mddev->kobj);
 }
 
+static void no_op(struct percpu_ref *r) {}
+
 static int md_alloc(dev_t dev, char *name)
 {
+	/*
+	 * If dev is zero, name is the name of a device to allocate with
+	 * an arbitrary minor number.  It will be "md_???"
+	 * If dev is non-zero it must be a device number with a MAJOR of
+	 * MD_MAJOR or mdp_major.  In this case, if "name" is NULL, then
+	 * the device is being created by opening a node in /dev.
+	 * If "name" is not NULL, the device is being created by
+	 * writing to /sys/module/md_mod/parameters/new_array.
+	 */
 	static DEFINE_MUTEX(disks_mutex);
 	struct mddev *mddev = mddev_find(dev);
 	struct gendisk *disk;
@@ -5028,7 +5210,7 @@ static int md_alloc(dev_t dev, char *name)
 	if (mddev->gendisk)
 		goto abort;
 
-	if (name) {
+	if (name && !dev) {
 		/* Need to ensure that 'name' is not a duplicate.
 		 */
 		struct mddev *mddev2;
@@ -5042,6 +5224,11 @@ static int md_alloc(dev_t dev, char *name)
 			}
 		spin_unlock(&all_mddevs_lock);
 	}
+	if (name && dev)
+		/*
+		 * Creating /dev/mdNNN via "newarray", so adjust hold_active.
+		 */
+		mddev->hold_active = UNTIL_STOP;
 
 	error = -ENOMEM;
 	mddev->queue = blk_alloc_queue(GFP_KERNEL);
@@ -5052,6 +5239,10 @@ static int md_alloc(dev_t dev, char *name)
 	blk_queue_make_request(mddev->queue, md_make_request);
 	blk_set_stacking_limits(&mddev->queue->limits);
 
+	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
+		goto abort;
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
 	disk = alloc_disk(1 << shift);
 	if (!disk) {
 		blk_cleanup_queue(mddev->queue);
@@ -5108,38 +5299,48 @@ static int md_alloc(dev_t dev, char *name)
 
 static struct kobject *md_probe(dev_t dev, int *part, void *data)
 {
-	md_alloc(dev, NULL);
+	if (create_on_open)
+		md_alloc(dev, NULL);
 	return NULL;
 }
 
 static int add_named_array(const char *val, struct kernel_param *kp)
 {
-	/* val must be "md_*" where * is not all digits.
-	 * We allocate an array with a large free minor number, and
+	/*
+	 * val must be "md_*" or "mdNNN".
+	 * For "md_*" we allocate an array with a large free minor number, and
 	 * set the name to val.  val must not already be an active name.
+	 * For "mdNNN" we allocate an array with the minor number NNN
+	 * which must not already be in use.
 	 */
 	int len = strlen(val);
 	char buf[DISK_NAME_LEN];
+	unsigned long devnum;
 
 	while (len && val[len-1] == '\n')
 		len--;
 	if (len >= DISK_NAME_LEN)
 		return -E2BIG;
 	strlcpy(buf, val, len+1);
-	if (strncmp(buf, "md_", 3) != 0)
-		return -EINVAL;
-	return md_alloc(0, buf);
+	if (strncmp(buf, "md_", 3) == 0)
+		return md_alloc(0, buf);
+	if (strncmp(buf, "md", 2) == 0 &&
+	    isdigit(buf[2]) &&
+	    kstrtoul(buf+2, 10, &devnum) == 0 &&
+	    devnum <= MINORMASK)
+		return md_alloc(MKDEV(MD_MAJOR, devnum), NULL);
+
+	return -EINVAL;
 }
 
 static void md_safemode_timeout(unsigned long data)
 {
 	struct mddev *mddev = (struct mddev *) data;
 
-	if (!atomic_read(&mddev->writes_pending)) {
-		mddev->safemode = 1;
-		if (mddev->external)
-			sysfs_notify_dirent_safe(mddev->sysfs_state);
-	}
+	mddev->safemode = 1;
+	if (mddev->external)
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
+
 	md_wakeup_thread(mddev->thread);
 }
 
@@ -5185,6 +5386,13 @@ int md_run(struct mddev *mddev)
 			continue;
 		sync_blockdev(rdev->bdev);
 		invalidate_bdev(rdev->bdev);
+		if (mddev->ro != 1 &&
+		    (bdev_read_only(rdev->bdev) ||
+		     bdev_read_only(rdev->meta_bdev))) {
+			mddev->ro = 1;
+			if (mddev->gendisk)
+				set_disk_ro(mddev->gendisk, 1);
+		}
 
 		/* perform some consistency tests on the device.
 		 * We don't want the data to overlap the metadata,
@@ -5344,7 +5552,6 @@ int md_run(struct mddev *mddev)
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;
 
-	atomic_set(&mddev->writes_pending,0);
 	atomic_set(&mddev->max_corr_read_errors,
 		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
 	mddev->safemode = 0;
@@ -5410,6 +5617,9 @@ out:
 static int restart_array(struct mddev *mddev)
 {
 	struct gendisk *disk = mddev->gendisk;
+	struct md_rdev *rdev;
+	bool has_journal = false;
+	bool has_readonly = false;
 
 	/* Complain if it has no devices */
 	if (list_empty(&mddev->disks))
@@ -5418,24 +5628,21 @@ static int restart_array(struct mddev *mddev)
 		return -EINVAL;
 	if (!mddev->ro)
 		return -EBUSY;
-	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
-		struct md_rdev *rdev;
-		bool has_journal = false;
-
-		rcu_read_lock();
-		rdev_for_each_rcu(rdev, mddev) {
-			if (test_bit(Journal, &rdev->flags) &&
-			    !test_bit(Faulty, &rdev->flags)) {
-				has_journal = true;
-				break;
-			}
-		}
-		rcu_read_unlock();
 
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (test_bit(Journal, &rdev->flags) &&
+		    !test_bit(Faulty, &rdev->flags))
+			has_journal = true;
+		if (bdev_read_only(rdev->bdev))
+			has_readonly = true;
+	}
+	rcu_read_unlock();
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !has_journal)
 		/* Don't restart rw with journal missing/faulty */
-		if (!has_journal)
 			return -EINVAL;
-	}
+	if (has_readonly)
+		return -EROFS;
 
 	mddev->safemode = 0;
 	mddev->ro = 0;
@@ -5535,15 +5742,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 
 static void mddev_detach(struct mddev *mddev)
 {
-	struct bitmap *bitmap = mddev->bitmap;
-	/* wait for behind writes to complete */
-	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
-		pr_debug("md:%s: behind writes in progress - waiting to stop.\n",
-			 mdname(mddev));
-		/* need to kick something here to make sure I/O goes? */
-		wait_event(bitmap->behind_wait,
-			   atomic_read(&bitmap->behind_writes) == 0);
-	}
+	bitmap_wait_behind_writes(mddev);
 	if (mddev->pers && mddev->pers->quiesce) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
@@ -5556,6 +5755,7 @@ static void mddev_detach(struct mddev *mddev)
 static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
+	bitmap_destroy(mddev);
 	mddev_detach(mddev);
 	/* Ensure ->event_work is done */
 	flush_workqueue(md_misc_wq);
@@ -5576,7 +5776,6 @@ void md_stop(struct mddev *mddev)
 	 * This is called from dm-raid
 	 */
 	__md_stop(mddev);
-	bitmap_destroy(mddev);
 	if (mddev->bio_set)
 		bioset_free(mddev->bio_set);
 }
@@ -5714,7 +5913,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if (mode == 0) {
 		pr_info("md: %s stopped.\n", mdname(mddev));
 
-		bitmap_destroy(mddev);
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
 			spin_lock(&mddev->lock);
@@ -6493,10 +6691,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	struct md_rdev *rdev;
 	int rv;
 	int fit = (num_sectors == 0);
-
-	/* cluster raid doesn't support update size */
-	if (mddev_is_clustered(mddev))
-		return -EINVAL;
+	sector_t old_dev_sectors = mddev->dev_sectors;
 
 	if (mddev->pers->resize == NULL)
 		return -EINVAL;
@@ -6525,7 +6720,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	}
 	rv = mddev->pers->resize(mddev, num_sectors);
 	if (!rv) {
-		if (mddev->queue) {
+		if (mddev_is_clustered(mddev))
+			md_cluster_ops->update_size(mddev, old_dev_sectors);
+		else if (mddev->queue) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
 			revalidate_disk(mddev->gendisk);
 		}
@@ -6776,6 +6973,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
 	int ro;
+	bool did_set_md_closing = false;
 
 	if (!md_ioctl_valid(cmd))
 		return -ENOTTY;
@@ -6865,7 +7063,9 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EBUSY;
 			goto out;
 		}
+		WARN_ON_ONCE(test_bit(MD_CLOSING, &mddev->flags));
 		set_bit(MD_CLOSING, &mddev->flags);
+		did_set_md_closing = true;
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
@@ -7058,6 +7258,8 @@ unlock:
 		mddev->hold_active = 0;
 	mddev_unlock(mddev);
 out:
+	if(did_set_md_closing)
+		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
 #ifdef CONFIG_COMPAT
@@ -7208,8 +7410,8 @@ void md_wakeup_thread(struct md_thread *thread)
 {
 	if (thread) {
 		pr_debug("md: waking up MD thread %s.\n", thread->tsk->comm);
-		set_bit(THREAD_WAKEUP, &thread->flags);
-		wake_up(&thread->wqueue);
+		if (!test_and_set_bit(THREAD_WAKEUP, &thread->flags))
+			wake_up(&thread->wqueue);
 	}
 }
 EXPORT_SYMBOL(md_wakeup_thread);
@@ -7756,10 +7958,13 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 		md_wakeup_thread(mddev->sync_thread);
 		did_change = 1;
 	}
-	atomic_inc(&mddev->writes_pending);
+	rcu_read_lock();
+	percpu_ref_get(&mddev->writes_pending);
+	smp_mb(); /* Match smp_mb in set_in_sync() */
 	if (mddev->safemode == 1)
 		mddev->safemode = 0;
-	if (mddev->in_sync) {
+	/* sync_checkers is always 0 when writes_pending is in per-cpu mode */
+	if (mddev->in_sync || !mddev->sync_checkers) {
 		spin_lock(&mddev->lock);
 		if (mddev->in_sync) {
 			mddev->in_sync = 0;
@@ -7770,6 +7975,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 		}
 		spin_unlock(&mddev->lock);
 	}
+	rcu_read_unlock();
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
@@ -7777,15 +7983,38 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 }
 EXPORT_SYMBOL(md_write_start);
 
+/* md_write_inc can only be called when md_write_start() has
+ * already been called at least once of the current request.
+ * It increments the counter and is useful when a single request
+ * is split into several parts.  Each part causes an increment and
+ * so needs a matching md_write_end().
+ * Unlike md_write_start(), it is safe to call md_write_inc() inside
+ * a spinlocked region.
+ */
+void md_write_inc(struct mddev *mddev, struct bio *bi)
+{
+	if (bio_data_dir(bi) != WRITE)
+		return;
+	WARN_ON_ONCE(mddev->in_sync || mddev->ro);
+	percpu_ref_get(&mddev->writes_pending);
+}
+EXPORT_SYMBOL(md_write_inc);
+
 void md_write_end(struct mddev *mddev)
 {
-	if (atomic_dec_and_test(&mddev->writes_pending)) {
-		if (mddev->safemode == 2)
-			md_wakeup_thread(mddev->thread);
-		else if (mddev->safemode_delay)
-			mod_timer(&mddev->safemode_timer, jiffies + mddev->safemode_delay);
-	}
+	percpu_ref_put(&mddev->writes_pending);
+
+	if (mddev->safemode == 2)
+		md_wakeup_thread(mddev->thread);
+	else if (mddev->safemode_delay)
+		/* The roundup() ensures this only performs locking once
+		 * every ->safemode_delay jiffies
+		 */
+		mod_timer(&mddev->safemode_timer,
+			  roundup(jiffies, mddev->safemode_delay) +
+			  mddev->safemode_delay);
 }
+
 EXPORT_SYMBOL(md_write_end);
 
 /* md_allow_write(mddev)
@@ -8385,9 +8614,8 @@ void md_check_recovery(struct mddev *mddev)
 		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
 		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
 		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-		test_bit(MD_RELOAD_SB, &mddev->flags) ||
 		(mddev->external == 0 && mddev->safemode == 1) ||
-		(mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending)
+		(mddev->safemode == 2
 		 && !mddev->in_sync && mddev->recovery_cp == MaxSector)
 		))
 		return;
@@ -8434,27 +8662,12 @@ void md_check_recovery(struct mddev *mddev)
 						rdev->raid_disk < 0)
 					md_kick_rdev_from_array(rdev);
 			}
-
-			if (test_and_clear_bit(MD_RELOAD_SB, &mddev->flags))
-				md_reload_sb(mddev, mddev->good_device_nr);
 		}
 
-		if (!mddev->external) {
-			int did_change = 0;
+		if (!mddev->external && !mddev->in_sync) {
 			spin_lock(&mddev->lock);
-			if (mddev->safemode &&
-			    !atomic_read(&mddev->writes_pending) &&
-			    !mddev->in_sync &&
-			    mddev->recovery_cp == MaxSector) {
-				mddev->in_sync = 1;
-				did_change = 1;
-				set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
-			}
-			if (mddev->safemode == 1)
-				mddev->safemode = 0;
+			set_in_sync(mddev);
 			spin_unlock(&mddev->lock);
-			if (did_change)
-				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
 
 		if (mddev->sb_flags)
@@ -8747,6 +8960,18 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 	int role, ret;
 	char b[BDEVNAME_SIZE];
 
+	/*
+	 * If size is changed in another node then we need to
+	 * do resize as well.
+	 */
+	if (mddev->dev_sectors != le64_to_cpu(sb->size)) {
+		ret = mddev->pers->resize(mddev, le64_to_cpu(sb->size));
+		if (ret)
+			pr_info("md-cluster: resize failed\n");
+		else
+			bitmap_update_sb(mddev->bitmap);
+	}
+
 	/* Check for change of roles in the active devices */
 	rdev_for_each(rdev2, mddev) {
 		if (test_bit(Faulty, &rdev2->flags))
@@ -8997,6 +9222,7 @@ static int set_ro(const char *val, struct kernel_param *kp)
 module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
 module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
 module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR);
+module_param(create_on_open, bool, S_IRUSR|S_IWUSR);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1e76d64ce180..4e75d121bfcc 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -122,6 +122,13 @@ struct md_rdev {
 					   * sysfs entry */
 
 	struct badblocks badblocks;
+
+	struct {
+		short offset;	/* Offset from superblock to start of PPL.
+				 * Not used by external metadata. */
+		unsigned int size;	/* Size in sectors of the PPL space */
+		sector_t sector;	/* First sector of the PPL space */
+	} ppl;
 };
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
@@ -219,9 +226,6 @@ enum mddev_flags {
 				 * it then */
 	MD_JOURNAL_CLEAN,	/* A raid with journal is already clean */
 	MD_HAS_JOURNAL,		/* The raid array has journal feature set */
-	MD_RELOAD_SB,		/* Reload the superblock because another node
-				 * updated it.
-				 */
 	MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node
 				   * already took resync lock, need to
 				   * release the lock */
@@ -229,6 +233,7 @@ enum mddev_flags {
 				 * supported as calls to md_error() will
 				 * never cause the array to become failed.
 				 */
+	MD_HAS_PPL,		/* The raid array has PPL feature set */
 };
 
 enum mddev_sb_flags {
@@ -404,7 +409,8 @@ struct mddev {
 							 */
 	unsigned int			safemode_delay;
 	struct timer_list		safemode_timer;
-	atomic_t			writes_pending;
+	struct percpu_ref		writes_pending;
+	int				sync_checkers;	/* # of threads checking writes_pending */
 	struct request_queue		*queue;	/* for plugging ... */
 
 	struct bitmap			*bitmap; /* the bitmap for the device */
@@ -540,6 +546,8 @@ struct md_personality
 	/* congested implements bdi.congested_fn().
 	 * Will not be called while array is 'suspended' */
 	int (*congested)(struct mddev *mddev, int bits);
+	/* Changes the consistency policy of an active array. */
+	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
 };
 
 struct md_sysfs_entry {
@@ -641,6 +649,7 @@ extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
 extern void md_write_start(struct mddev *mddev, struct bio *bi);
+extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
@@ -716,4 +725,58 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 	    !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
+
+/* Maximum size of each resync request */
+#define RESYNC_BLOCK_SIZE (64*1024)
+#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
+
+/* for managing resync I/O pages */
+struct resync_pages {
+	unsigned	idx;	/* for get/put page from the pool */
+	void		*raid_bio;
+	struct page	*pages[RESYNC_PAGES];
+};
+
+static inline int resync_alloc_pages(struct resync_pages *rp,
+				     gfp_t gfp_flags)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++) {
+		rp->pages[i] = alloc_page(gfp_flags);
+		if (!rp->pages[i])
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	while (--i >= 0)
+		put_page(rp->pages[i]);
+	return -ENOMEM;
+}
+
+static inline void resync_free_pages(struct resync_pages *rp)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++)
+		put_page(rp->pages[i]);
+}
+
+static inline void resync_get_all_pages(struct resync_pages *rp)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++)
+		get_page(rp->pages[i]);
+}
+
+static inline struct page *resync_fetch_page(struct resync_pages *rp,
+					     unsigned idx)
+{
+	if (WARN_ON_ONCE(idx >= RESYNC_PAGES))
+		return NULL;
+	return rp->pages[idx];
+}
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ce7a6a56cf73..84e58596594d 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -29,7 +29,8 @@
 #define UNSUPPORTED_MDDEV_FLAGS		\
 	((1L << MD_HAS_JOURNAL) |	\
 	 (1L << MD_JOURNAL_CLEAN) |	\
-	 (1L << MD_FAILFAST_SUPPORTED))
+	 (1L << MD_FAILFAST_SUPPORTED) |\
+	 (1L << MD_HAS_PPL))
 
 static int raid0_congested(struct mddev *mddev, int bits)
 {
@@ -462,53 +463,54 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
-	struct bio *split;
+	sector_t bio_sector;
+	sector_t sector;
+	unsigned chunk_sects;
+	unsigned sectors;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	do {
-		sector_t bio_sector = bio->bi_iter.bi_sector;
-		sector_t sector = bio_sector;
-		unsigned chunk_sects = mddev->chunk_sectors;
+	bio_sector = bio->bi_iter.bi_sector;
+	sector = bio_sector;
+	chunk_sects = mddev->chunk_sectors;
 
-		unsigned sectors = chunk_sects -
-			(likely(is_power_of_2(chunk_sects))
-			 ? (sector & (chunk_sects-1))
-			 : sector_div(sector, chunk_sects));
+	sectors = chunk_sects -
+		(likely(is_power_of_2(chunk_sects))
+		 ? (sector & (chunk_sects-1))
+		 : sector_div(sector, chunk_sects));
 
-		/* Restore due to sector_div */
-		sector = bio_sector;
+	/* Restore due to sector_div */
+	sector = bio_sector;
 
-		if (sectors < bio_sectors(bio)) {
-			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
-			bio_chain(split, bio);
-		} else {
-			split = bio;
-		}
+	if (sectors < bio_sectors(bio)) {
+		struct bio *split = bio_split(bio, sectors, GFP_NOIO, mddev->bio_set);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+	}
 
-		zone = find_zone(mddev->private, &sector);
-		tmp_dev = map_sector(mddev, zone, sector, &sector);
-		split->bi_bdev = tmp_dev->bdev;
-		split->bi_iter.bi_sector = sector + zone->dev_start +
-			tmp_dev->data_offset;
-
-		if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
-			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
-			/* Just ignore it */
-			bio_endio(split);
-		} else {
-			if (mddev->gendisk)
-				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
-						      split, disk_devt(mddev->gendisk),
-						      bio_sector);
-			mddev_check_writesame(mddev, split);
-			mddev_check_write_zeroes(mddev, split);
-			generic_make_request(split);
-		}
-	} while (split != bio);
+	zone = find_zone(mddev->private, &sector);
+	tmp_dev = map_sector(mddev, zone, sector, &sector);
+	bio->bi_bdev = tmp_dev->bdev;
+	bio->bi_iter.bi_sector = sector + zone->dev_start +
+		tmp_dev->data_offset;
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
+		/* Just ignore it */
+		bio_endio(bio);
+	} else {
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+					      bio, disk_devt(mddev->gendisk),
+					      bio_sector);
+		mddev_check_writesame(mddev, bio);
+		mddev_check_write_zeroes(mddev, bio);
+		generic_make_request(bio);
+	}
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b59cc100320a..7ed59351fe97 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -47,7 +47,8 @@
 
 #define UNSUPPORTED_MDDEV_FLAGS		\
 	((1L << MD_HAS_JOURNAL) |	\
-	 (1L << MD_JOURNAL_CLEAN))
+	 (1L << MD_JOURNAL_CLEAN) |	\
+	 (1L << MD_HAS_PPL))
 
 /*
  * Number of guaranteed r1bios in case of extreme VM load:
@@ -80,6 +81,24 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 #define raid1_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
 
+/*
+ * 'strct resync_pages' stores actual pages used for doing the resync
+ *  IO, and it is per-bio, so make .bi_private points to it.
+ */
+static inline struct resync_pages *get_resync_pages(struct bio *bio)
+{
+	return bio->bi_private;
+}
+
+/*
+ * for resync bio, r1bio pointer can be retrieved from the per-bio
+ * 'struct resync_pages'.
+ */
+static inline struct r1bio *get_resync_r1bio(struct bio *bio)
+{
+	return get_resync_pages(bio)->raid_bio;
+}
+
 static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct pool_info *pi = data;
@@ -94,10 +113,8 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 	kfree(r1_bio);
 }
 
-#define RESYNC_BLOCK_SIZE (64*1024)
 #define RESYNC_DEPTH 32
 #define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
-#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 #define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
 #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
 #define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
@@ -109,12 +126,18 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	struct r1bio *r1_bio;
 	struct bio *bio;
 	int need_pages;
-	int i, j;
+	int j;
+	struct resync_pages *rps;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
 	if (!r1_bio)
 		return NULL;
 
+	rps = kmalloc(sizeof(struct resync_pages) * pi->raid_disks,
+		      gfp_flags);
+	if (!rps)
+		goto out_free_r1bio;
+
 	/*
 	 * Allocate bios : 1 for reading, n-1 for writing
 	 */
@@ -134,19 +157,22 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 		need_pages = pi->raid_disks;
 	else
 		need_pages = 1;
-	for (j = 0; j < need_pages; j++) {
+	for (j = 0; j < pi->raid_disks; j++) {
+		struct resync_pages *rp = &rps[j];
+
 		bio = r1_bio->bios[j];
-		bio->bi_vcnt = RESYNC_PAGES;
 
-		if (bio_alloc_pages(bio, gfp_flags))
-			goto out_free_pages;
-	}
-	/* If not user-requests, copy the page pointers to all bios */
-	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
-		for (i=0; i<RESYNC_PAGES ; i++)
-			for (j=1; j<pi->raid_disks; j++)
-				r1_bio->bios[j]->bi_io_vec[i].bv_page =
-					r1_bio->bios[0]->bi_io_vec[i].bv_page;
+		if (j < need_pages) {
+			if (resync_alloc_pages(rp, gfp_flags))
+				goto out_free_pages;
+		} else {
+			memcpy(rp, &rps[0], sizeof(*rp));
+			resync_get_all_pages(rp);
+		}
+
+		rp->idx = 0;
+		rp->raid_bio = r1_bio;
+		bio->bi_private = rp;
 	}
 
 	r1_bio->master_bio = NULL;
@@ -155,11 +181,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 out_free_pages:
 	while (--j >= 0)
-		bio_free_pages(r1_bio->bios[j]);
+		resync_free_pages(&rps[j]);
 
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
+	kfree(rps);
+
+out_free_r1bio:
 	r1bio_pool_free(r1_bio, data);
 	return NULL;
 }
@@ -167,18 +196,18 @@ out_free_bio:
 static void r1buf_pool_free(void *__r1_bio, void *data)
 {
 	struct pool_info *pi = data;
-	int i,j;
+	int i;
 	struct r1bio *r1bio = __r1_bio;
+	struct resync_pages *rp = NULL;
 
-	for (i = 0; i < RESYNC_PAGES; i++)
-		for (j = pi->raid_disks; j-- ;) {
-			if (j == 0 ||
-			    r1bio->bios[j]->bi_io_vec[i].bv_page !=
-			    r1bio->bios[0]->bi_io_vec[i].bv_page)
-				safe_put_page(r1bio->bios[j]->bi_io_vec[i].bv_page);
-		}
-	for (i=0 ; i < pi->raid_disks; i++)
+	for (i = pi->raid_disks; i--; ) {
+		rp = get_resync_pages(r1bio->bios[i]);
+		resync_free_pages(rp);
 		bio_put(r1bio->bios[i]);
+	}
+
+	/* resync pages array stored in the 1st bio's .bi_private */
+	kfree(rp);
 
 	r1bio_pool_free(r1bio, data);
 }
@@ -245,35 +274,17 @@ static void reschedule_retry(struct r1bio *r1_bio)
 static void call_bio_endio(struct r1bio *r1_bio)
 {
 	struct bio *bio = r1_bio->master_bio;
-	int done;
 	struct r1conf *conf = r1_bio->mddev->private;
-	sector_t bi_sector = bio->bi_iter.bi_sector;
-
-	if (bio->bi_phys_segments) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		bio->bi_phys_segments--;
-		done = (bio->bi_phys_segments == 0);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		/*
-		 * make_request() might be waiting for
-		 * bi_phys_segments to decrease
-		 */
-		wake_up(&conf->wait_barrier);
-	} else
-		done = 1;
 
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
 		bio->bi_error = -EIO;
 
-	if (done) {
-		bio_endio(bio);
-		/*
-		 * Wake up any possible resync thread that waits for the device
-		 * to go idle.
-		 */
-		allow_barrier(conf, bi_sector);
-	}
+	bio_endio(bio);
+	/*
+	 * Wake up any possible resync thread that waits for the device
+	 * to go idle.
+	 */
+	allow_barrier(conf, r1_bio->sector);
 }
 
 static void raid_end_bio_io(struct r1bio *r1_bio)
@@ -377,12 +388,9 @@ static void close_write(struct r1bio *r1_bio)
 {
 	/* it really is the end of this request */
 	if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-		/* free extra copy of the data pages */
-		int i = r1_bio->behind_page_count;
-		while (i--)
-			safe_put_page(r1_bio->behind_bvecs[i].bv_page);
-		kfree(r1_bio->behind_bvecs);
-		r1_bio->behind_bvecs = NULL;
+		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 */
 	bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
@@ -484,6 +492,10 @@ static void raid1_end_write_request(struct bio *bio)
 	}
 
 	if (behind) {
+		/* we release behind master bio when all write are done */
+		if (r1_bio->behind_master_bio == bio)
+			to_put = NULL;
+
 		if (test_bit(WriteMostly, &rdev->flags))
 			atomic_dec(&r1_bio->behind_remaining);
 
@@ -775,6 +787,30 @@ static int raid1_congested(struct mddev *mddev, int bits)
 	return ret;
 }
 
+static void flush_bio_list(struct r1conf *conf, struct bio *bio)
+{
+	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
+	bitmap_unplug(conf->mddev->bitmap);
+	wake_up(&conf->wait_barrier);
+
+	while (bio) { /* submit pending writes */
+		struct bio *next = bio->bi_next;
+		struct md_rdev *rdev = (void*)bio->bi_bdev;
+		bio->bi_next = NULL;
+		bio->bi_bdev = rdev->bdev;
+		if (test_bit(Faulty, &rdev->flags)) {
+			bio->bi_error = -EIO;
+			bio_endio(bio);
+		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+			/* Just ignore it */
+			bio_endio(bio);
+		else
+			generic_make_request(bio);
+		bio = next;
+	}
+}
+
 static void flush_pending_writes(struct r1conf *conf)
 {
 	/* Any writes that have been queued but are awaiting
@@ -787,27 +823,7 @@ static void flush_pending_writes(struct r1conf *conf)
 		bio = bio_list_get(&conf->pending_bio_list);
 		conf->pending_count = 0;
 		spin_unlock_irq(&conf->device_lock);
-		/* flush any pending bitmap writes to
-		 * disk before proceeding w/ I/O */
-		bitmap_unplug(conf->mddev->bitmap);
-		wake_up(&conf->wait_barrier);
-
-		while (bio) { /* submit pending writes */
-			struct bio *next = bio->bi_next;
-			struct md_rdev *rdev = (void*)bio->bi_bdev;
-			bio->bi_next = NULL;
-			bio->bi_bdev = rdev->bdev;
-			if (test_bit(Faulty, &rdev->flags)) {
-				bio->bi_error = -EIO;
-				bio_endio(bio);
-			} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-					    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
-				/* Just ignore it */
-				bio_endio(bio);
-			else
-				generic_make_request(bio);
-			bio = next;
-		}
+		flush_bio_list(conf, bio);
 	} else
 		spin_unlock_irq(&conf->device_lock);
 }
@@ -869,7 +885,7 @@ static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
 			     atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH,
 			    conf->resync_lock);
 
-	atomic_inc(&conf->nr_pending[idx]);
+	atomic_inc(&conf->nr_sync_pending);
 	spin_unlock_irq(&conf->resync_lock);
 }
 
@@ -880,7 +896,7 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
 	BUG_ON(atomic_read(&conf->barrier[idx]) <= 0);
 
 	atomic_dec(&conf->barrier[idx]);
-	atomic_dec(&conf->nr_pending[idx]);
+	atomic_dec(&conf->nr_sync_pending);
 	wake_up(&conf->wait_barrier);
 }
 
@@ -1017,7 +1033,8 @@ static int get_unqueued_pending(struct r1conf *conf)
 {
 	int idx, ret;
 
-	for (ret = 0, idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
+	ret = atomic_read(&conf->nr_sync_pending);
+	for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
 		ret += atomic_read(&conf->nr_pending[idx]) -
 			atomic_read(&conf->nr_queued[idx]);
 
@@ -1068,39 +1085,49 @@ static void unfreeze_array(struct r1conf *conf)
 	wake_up(&conf->wait_barrier);
 }
 
-/* duplicate the data pages for behind I/O
- */
-static void alloc_behind_pages(struct bio *bio, struct r1bio *r1_bio)
+static struct bio *alloc_behind_master_bio(struct r1bio *r1_bio,
+					   struct bio *bio)
 {
-	int i;
-	struct bio_vec *bvec;
-	struct bio_vec *bvecs = kzalloc(bio->bi_vcnt * sizeof(struct bio_vec),
-					GFP_NOIO);
-	if (unlikely(!bvecs))
-		return;
+	int size = bio->bi_iter.bi_size;
+	unsigned vcnt = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	int i = 0;
+	struct bio *behind_bio = NULL;
+
+	behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
+	if (!behind_bio)
+		goto fail;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		bvecs[i] = *bvec;
-		bvecs[i].bv_page = alloc_page(GFP_NOIO);
-		if (unlikely(!bvecs[i].bv_page))
-			goto do_sync_io;
-		memcpy(kmap(bvecs[i].bv_page) + bvec->bv_offset,
-		       kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
-		kunmap(bvecs[i].bv_page);
-		kunmap(bvec->bv_page);
-	}
-	r1_bio->behind_bvecs = bvecs;
-	r1_bio->behind_page_count = bio->bi_vcnt;
+	/* discard op, we don't support writezero/writesame yet */
+	if (!bio_has_data(bio))
+		goto skip_copy;
+
+	while (i < vcnt && size) {
+		struct page *page;
+		int len = min_t(int, PAGE_SIZE, size);
+
+		page = alloc_page(GFP_NOIO);
+		if (unlikely(!page))
+			goto free_pages;
+
+		bio_add_page(behind_bio, page, len, 0);
+
+		size -= len;
+		i++;
+	}
+
+	bio_copy_data(behind_bio, bio);
+skip_copy:
+	r1_bio->behind_master_bio = behind_bio;;
 	set_bit(R1BIO_BehindIO, &r1_bio->state);
-	return;
 
-do_sync_io:
-	for (i = 0; i < bio->bi_vcnt; i++)
-		if (bvecs[i].bv_page)
-			put_page(bvecs[i].bv_page);
-	kfree(bvecs);
+	return behind_bio;
+
+free_pages:
 	pr_debug("%dB behind alloc failed, doing sync I/O\n",
 		 bio->bi_iter.bi_size);
+	bio_free_pages(behind_bio);
+fail:
+	return behind_bio;
 }
 
 struct raid1_plug_cb {
@@ -1130,91 +1157,102 @@ static void raid1_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);
-	bitmap_unplug(mddev->bitmap);
-	wake_up(&conf->wait_barrier);
-
-	while (bio) { /* submit pending writes */
-		struct bio *next = bio->bi_next;
-		struct md_rdev *rdev = (void*)bio->bi_bdev;
-		bio->bi_next = NULL;
-		bio->bi_bdev = rdev->bdev;
-		if (test_bit(Faulty, &rdev->flags)) {
-			bio->bi_error = -EIO;
-			bio_endio(bio);
-		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
-			/* Just ignore it */
-			bio_endio(bio);
-		else
-			generic_make_request(bio);
-		bio = next;
-	}
+	flush_bio_list(conf, bio);
 	kfree(plug);
 }
 
+static void init_r1bio(struct r1bio *r1_bio, struct mddev *mddev, struct bio *bio)
+{
+	r1_bio->master_bio = bio;
+	r1_bio->sectors = bio_sectors(bio);
+	r1_bio->state = 0;
+	r1_bio->mddev = mddev;
+	r1_bio->sector = bio->bi_iter.bi_sector;
+}
+
 static inline struct r1bio *
-alloc_r1bio(struct mddev *mddev, struct bio *bio, sector_t sectors_handled)
+alloc_r1bio(struct mddev *mddev, struct bio *bio)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 
 	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
-	r1_bio->master_bio = bio;
-	r1_bio->sectors = bio_sectors(bio) - sectors_handled;
-	r1_bio->state = 0;
-	r1_bio->mddev = mddev;
-	r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
-
+	/* Ensure no bio records IO_BLOCKED */
+	memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
+	init_r1bio(r1_bio, mddev, bio);
 	return r1_bio;
 }
 
-static void raid1_read_request(struct mddev *mddev, struct bio *bio)
+static void raid1_read_request(struct mddev *mddev, struct bio *bio,
+			       int max_read_sectors, struct r1bio *r1_bio)
 {
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
-	struct r1bio *r1_bio;
 	struct bio *read_bio;
 	struct bitmap *bitmap = mddev->bitmap;
 	const int op = bio_op(bio);
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
-	int sectors_handled;
 	int max_sectors;
 	int rdisk;
+	bool print_msg = !!r1_bio;
+	char b[BDEVNAME_SIZE];
 
 	/*
-	 * Still need barrier for READ in case that whole
-	 * array is frozen.
+	 * If r1_bio is set, we are blocking the raid1d thread
+	 * so there is a tiny risk of deadlock.  So ask for
+	 * emergency memory if needed.
 	 */
-	wait_read_barrier(conf, bio->bi_iter.bi_sector);
+	gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
-	r1_bio = alloc_r1bio(mddev, bio, 0);
+	if (print_msg) {
+		/* Need to get the block device name carefully */
+		struct md_rdev *rdev;
+		rcu_read_lock();
+		rdev = rcu_dereference(conf->mirrors[r1_bio->read_disk].rdev);
+		if (rdev)
+			bdevname(rdev->bdev, b);
+		else
+			strcpy(b, "???");
+		rcu_read_unlock();
+	}
 
 	/*
-	 * We might need to issue multiple reads to different
-	 * devices if there are bad blocks around, so we keep
-	 * track of the number of reads in bio->bi_phys_segments.
-	 * If this is 0, there is only one r1_bio and no locking
-	 * will be needed when requests complete.  If it is
-	 * non-zero, then it is the number of not-completed requests.
+	 * Still need barrier for READ in case that whole
+	 * array is frozen.
 	 */
-	bio->bi_phys_segments = 0;
-	bio_clear_flag(bio, BIO_SEG_VALID);
+	wait_read_barrier(conf, bio->bi_iter.bi_sector);
+
+	if (!r1_bio)
+		r1_bio = alloc_r1bio(mddev, bio);
+	else
+		init_r1bio(r1_bio, mddev, bio);
+	r1_bio->sectors = max_read_sectors;
 
 	/*
 	 * make_request() can abort the operation when read-ahead is being
 	 * used and no empty request is available.
 	 */
-read_again:
 	rdisk = read_balance(conf, r1_bio, &max_sectors);
 
 	if (rdisk < 0) {
 		/* couldn't find anywhere to read from */
+		if (print_msg) {
+			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
+					    mdname(mddev),
+					    b,
+					    (unsigned long long)r1_bio->sector);
+		}
 		raid_end_bio_io(r1_bio);
 		return;
 	}
 	mirror = conf->mirrors + rdisk;
 
+	if (print_msg)
+		pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n",
+				    mdname(mddev),
+				    (unsigned long long)r1_bio->sector,
+				    bdevname(mirror->rdev->bdev, b));
+
 	if (test_bit(WriteMostly, &mirror->rdev->flags) &&
 	    bitmap) {
 		/*
@@ -1225,11 +1263,20 @@ read_again:
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
+
+	if (max_sectors < bio_sectors(bio)) {
+		struct bio *split = bio_split(bio, max_sectors,
+					      gfp, conf->bio_split);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		r1_bio->master_bio = bio;
+		r1_bio->sectors = max_sectors;
+	}
+
 	r1_bio->read_disk = rdisk;
 
-	read_bio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-	bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
-		 max_sectors);
+	read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
 
 	r1_bio->bios[rdisk] = read_bio;
 
@@ -1248,35 +1295,11 @@ read_again:
 	                              read_bio, disk_devt(mddev->gendisk),
 	                              r1_bio->sector);
 
-	if (max_sectors < r1_bio->sectors) {
-		/*
-		 * could not read all from this device, so we will need another
-		 * r1_bio.
-		 */
-		sectors_handled = (r1_bio->sector + max_sectors
-				   - bio->bi_iter.bi_sector);
-		r1_bio->sectors = max_sectors;
-		spin_lock_irq(&conf->device_lock);
-		if (bio->bi_phys_segments == 0)
-			bio->bi_phys_segments = 2;
-		else
-			bio->bi_phys_segments++;
-		spin_unlock_irq(&conf->device_lock);
-
-		/*
-		 * Cannot call generic_make_request directly as that will be
-		 * queued in __make_request and subsequent mempool_alloc might
-		 * block waiting for it.  So hand bio over to raid1d.
-		 */
-		reschedule_retry(r1_bio);
-
-		r1_bio = alloc_r1bio(mddev, bio, sectors_handled);
-		goto read_again;
-	} else
-		generic_make_request(read_bio);
+	generic_make_request(read_bio);
 }
 
-static void raid1_write_request(struct mddev *mddev, struct bio *bio)
+static void raid1_write_request(struct mddev *mddev, struct bio *bio,
+				int max_write_sectors)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
@@ -1287,7 +1310,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
 	int first_clone;
-	int sectors_handled;
 	int max_sectors;
 
 	/*
@@ -1326,17 +1348,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 	}
 	wait_barrier(conf, bio->bi_iter.bi_sector);
 
-	r1_bio = alloc_r1bio(mddev, bio, 0);
-
-	/* We might need to issue multiple writes to different
-	 * devices if there are bad blocks around, so we keep
-	 * track of the number of writes in bio->bi_phys_segments.
-	 * If this is 0, there is only one r1_bio and no locking
-	 * will be needed when requests complete.  If it is
-	 * non-zero, then it is the number of not-completed requests.
-	 */
-	bio->bi_phys_segments = 0;
-	bio_clear_flag(bio, BIO_SEG_VALID);
+	r1_bio = alloc_r1bio(mddev, bio);
+	r1_bio->sectors = max_write_sectors;
 
 	if (conf->pending_count >= max_queued_requests) {
 		md_wakeup_thread(mddev->thread);
@@ -1435,31 +1448,26 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 		goto retry_write;
 	}
 
-	if (max_sectors < r1_bio->sectors) {
-		/* We are splitting this write into multiple parts, so
-		 * we need to prepare for allocating another r1_bio.
-		 */
+	if (max_sectors < bio_sectors(bio)) {
+		struct bio *split = bio_split(bio, max_sectors,
+					      GFP_NOIO, conf->bio_split);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		r1_bio->master_bio = bio;
 		r1_bio->sectors = max_sectors;
-		spin_lock_irq(&conf->device_lock);
-		if (bio->bi_phys_segments == 0)
-			bio->bi_phys_segments = 2;
-		else
-			bio->bi_phys_segments++;
-		spin_unlock_irq(&conf->device_lock);
 	}
-	sectors_handled = r1_bio->sector + max_sectors - bio->bi_iter.bi_sector;
 
 	atomic_set(&r1_bio->remaining, 1);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
 	first_clone = 1;
+
 	for (i = 0; i < disks; i++) {
 		struct bio *mbio = NULL;
-		sector_t offset;
 		if (!r1_bio->bios[i])
 			continue;
 
-		offset = r1_bio->sector - bio->bi_iter.bi_sector;
 
 		if (first_clone) {
 			/* do behind I/O ?
@@ -1470,11 +1478,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 			    (atomic_read(&bitmap->behind_writes)
 			     < mddev->bitmap_info.max_write_behind) &&
 			    !waitqueue_active(&bitmap->behind_wait)) {
-				mbio = bio_clone_bioset_partial(bio, GFP_NOIO,
-								mddev->bio_set,
-								offset << 9,
-								max_sectors << 9);
-				alloc_behind_pages(mbio, r1_bio);
+				mbio = alloc_behind_master_bio(r1_bio, bio);
 			}
 
 			bitmap_startwrite(bitmap, r1_bio->sector,
@@ -1485,26 +1489,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 		}
 
 		if (!mbio) {
-			if (r1_bio->behind_bvecs)
-				mbio = bio_clone_bioset_partial(bio, GFP_NOIO,
-								mddev->bio_set,
-								offset << 9,
-								max_sectors << 9);
-			else {
+			if (r1_bio->behind_master_bio)
+				mbio = bio_clone_fast(r1_bio->behind_master_bio,
+						      GFP_NOIO,
+						      mddev->bio_set);
+			else
 				mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-				bio_trim(mbio, offset, max_sectors);
-			}
 		}
 
-		if (r1_bio->behind_bvecs) {
-			struct bio_vec *bvec;
-			int j;
-
-			/*
-			 * We trimmed the bio, so _all is legit
-			 */
-			bio_for_each_segment_all(bvec, mbio, j)
-				bvec->bv_page = r1_bio->behind_bvecs[j].bv_page;
+		if (r1_bio->behind_master_bio) {
 			if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
 				atomic_inc(&r1_bio->behind_remaining);
 		}
@@ -1548,17 +1541,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 		if (!plug)
 			md_wakeup_thread(mddev->thread);
 	}
-	/* Mustn't call r1_bio_write_done before this next test,
-	 * as it could result in the bio being freed.
-	 */
-	if (sectors_handled < bio_sectors(bio)) {
-		r1_bio_write_done(r1_bio);
-		/* We need another r1_bio.  It has already been counted
-		 * in bio->bi_phys_segments
-		 */
-		r1_bio = alloc_r1bio(mddev, bio, sectors_handled);
-		goto retry_write;
-	}
 
 	r1_bio_write_done(r1_bio);
 
@@ -1568,7 +1550,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 
 static void raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
-	struct bio *split;
 	sector_t sectors;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
@@ -1576,43 +1557,20 @@ static void raid1_make_request(struct mddev *mddev, struct bio *bio)
 		return;
 	}
 
-	/* if bio exceeds barrier unit boundary, split it */
-	do {
-		sectors = align_to_barrier_unit_end(
-				bio->bi_iter.bi_sector, bio_sectors(bio));
-		if (sectors < bio_sectors(bio)) {
-			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
-			bio_chain(split, bio);
-		} else {
-			split = bio;
-		}
-
-		if (bio_data_dir(split) == READ) {
-			raid1_read_request(mddev, split);
+	/*
+	 * There is a limit to the maximum size, but
+	 * the read/write handler might find a lower limit
+	 * due to bad blocks.  To avoid multiple splits,
+	 * we pass the maximum number of sectors down
+	 * and let the lower level perform the split.
+	 */
+	sectors = align_to_barrier_unit_end(
+		bio->bi_iter.bi_sector, bio_sectors(bio));
 
-			/*
-			 * If a bio is splitted, the first part of bio will
-			 * pass barrier but the bio is queued in
-			 * current->bio_list (see generic_make_request). If
-			 * there is a raise_barrier() called here, the second
-			 * part of bio can't pass barrier. But since the first
-			 * part bio isn't dispatched to underlaying disks yet,
-			 * the barrier is never released, hence raise_barrier
-			 * will alays wait. We have a deadlock.
-			 * Note, this only happens in read path. For write
-			 * path, the first part of bio is dispatched in a
-			 * schedule() call (because of blk plug) or offloaded
-			 * to raid10d.
-			 * Quitting from the function immediately can change
-			 * the bio order queued in bio_list and avoid the deadlock.
-			 */
-			if (split != bio) {
-				generic_make_request(bio);
-				break;
-			}
-		} else
-			raid1_write_request(mddev, split);
-	} while (split != bio);
+	if (bio_data_dir(bio) == READ)
+		raid1_read_request(mddev, bio, sectors, NULL);
+	else
+		raid1_write_request(mddev, bio, sectors);
 }
 
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
@@ -1874,9 +1832,9 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			p->rdev = repl;
 			conf->mirrors[conf->raid_disks + number].rdev = NULL;
 			unfreeze_array(conf);
-			clear_bit(WantReplacement, &rdev->flags);
-		} else
-			clear_bit(WantReplacement, &rdev->flags);
+		}
+
+		clear_bit(WantReplacement, &rdev->flags);
 		err = md_integrity_register(mddev);
 	}
 abort:
@@ -1887,7 +1845,7 @@ abort:
 
 static void end_sync_read(struct bio *bio)
 {
-	struct r1bio *r1_bio = bio->bi_private;
+	struct r1bio *r1_bio = get_resync_r1bio(bio);
 
 	update_head_pos(r1_bio->read_disk, r1_bio);
 
@@ -1906,7 +1864,7 @@ static void end_sync_read(struct bio *bio)
 static void end_sync_write(struct bio *bio)
 {
 	int uptodate = !bio->bi_error;
-	struct r1bio *r1_bio = bio->bi_private;
+	struct r1bio *r1_bio = get_resync_r1bio(bio);
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
 	sector_t first_bad;
@@ -1985,6 +1943,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
 	struct bio *bio = r1_bio->bios[r1_bio->read_disk];
+	struct page **pages = get_resync_pages(bio)->pages;
 	sector_t sect = r1_bio->sector;
 	int sectors = r1_bio->sectors;
 	int idx = 0;
@@ -2018,7 +1977,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				 */
 				rdev = conf->mirrors[d].rdev;
 				if (sync_page_io(rdev, sect, s<<9,
-						 bio->bi_io_vec[idx].bv_page,
+						 pages[idx],
 						 REQ_OP_READ, 0, false)) {
 					success = 1;
 					break;
@@ -2073,7 +2032,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				continue;
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
-					    bio->bi_io_vec[idx].bv_page,
+					    pages[idx],
 					    WRITE) == 0) {
 				r1_bio->bios[d]->bi_end_io = NULL;
 				rdev_dec_pending(rdev, mddev);
@@ -2088,7 +2047,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				continue;
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
-					    bio->bi_io_vec[idx].bv_page,
+					    pages[idx],
 					    READ) != 0)
 				atomic_add(s, &rdev->corrected_errors);
 		}
@@ -2122,7 +2081,9 @@ static void process_checks(struct r1bio *r1_bio)
 		int j;
 		int size;
 		int error;
+		struct bio_vec *bi;
 		struct bio *b = r1_bio->bios[i];
+		struct resync_pages *rp = get_resync_pages(b);
 		if (b->bi_end_io != end_sync_read)
 			continue;
 		/* fixup the bio for reuse, but preserve errno */
@@ -2135,12 +2096,11 @@ static void process_checks(struct r1bio *r1_bio)
 			conf->mirrors[i].rdev->data_offset;
 		b->bi_bdev = conf->mirrors[i].rdev->bdev;
 		b->bi_end_io = end_sync_read;
-		b->bi_private = r1_bio;
+		rp->raid_bio = r1_bio;
+		b->bi_private = rp;
 
 		size = b->bi_iter.bi_size;
-		for (j = 0; j < vcnt ; j++) {
-			struct bio_vec *bi;
-			bi = &b->bi_io_vec[j];
+		bio_for_each_segment_all(bi, b, j) {
 			bi->bv_offset = 0;
 			if (size > PAGE_SIZE)
 				bi->bv_len = PAGE_SIZE;
@@ -2162,20 +2122,24 @@ static void process_checks(struct r1bio *r1_bio)
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
 		int error = sbio->bi_error;
+		struct page **ppages = get_resync_pages(pbio)->pages;
+		struct page **spages = get_resync_pages(sbio)->pages;
+		struct bio_vec *bi;
+		int page_len[RESYNC_PAGES] = { 0 };
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
 		/* Now we can 'fixup' the error value */
 		sbio->bi_error = 0;
 
+		bio_for_each_segment_all(bi, sbio, j)
+			page_len[j] = bi->bv_len;
+
 		if (!error) {
 			for (j = vcnt; j-- ; ) {
-				struct page *p, *s;
-				p = pbio->bi_io_vec[j].bv_page;
-				s = sbio->bi_io_vec[j].bv_page;
-				if (memcmp(page_address(p),
-					   page_address(s),
-					   sbio->bi_io_vec[j].bv_len))
+				if (memcmp(page_address(ppages[j]),
+					   page_address(spages[j]),
+					   page_len[j]))
 					break;
 			}
 		} else
@@ -2222,6 +2186,8 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 		     (i == r1_bio->read_disk ||
 		      !test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
 			continue;
+		if (test_bit(Faulty, &conf->mirrors[i].rdev->flags))
+			continue;
 
 		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
 		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags))
@@ -2391,18 +2357,11 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		/* Write at 'sector' for 'sectors'*/
 
 		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-			unsigned vcnt = r1_bio->behind_page_count;
-			struct bio_vec *vec = r1_bio->behind_bvecs;
-
-			while (!vec->bv_page) {
-				vec++;
-				vcnt--;
-			}
-
-			wbio = bio_alloc_mddev(GFP_NOIO, vcnt, mddev);
-			memcpy(wbio->bi_io_vec, vec, vcnt * sizeof(struct bio_vec));
-
-			wbio->bi_vcnt = vcnt;
+			wbio = bio_clone_fast(r1_bio->behind_master_bio,
+					      GFP_NOIO,
+					      mddev->bio_set);
+			/* We really need a _all clone */
+			wbio->bi_iter = (struct bvec_iter){ 0 };
 		} else {
 			wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
 					      mddev->bio_set);
@@ -2501,11 +2460,8 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 
 static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 {
-	int disk;
-	int max_sectors;
 	struct mddev *mddev = conf->mddev;
 	struct bio *bio;
-	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev;
 	dev_t bio_dev;
 	sector_t bio_sector;
@@ -2521,7 +2477,6 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	 */
 
 	bio = r1_bio->bios[r1_bio->read_disk];
-	bdevname(bio->bi_bdev, b);
 	bio_dev = bio->bi_bdev->bd_dev;
 	bio_sector = conf->mirrors[r1_bio->read_disk].rdev->data_offset + r1_bio->sector;
 	bio_put(bio);
@@ -2539,62 +2494,12 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	}
 
 	rdev_dec_pending(rdev, conf->mddev);
+	allow_barrier(conf, r1_bio->sector);
+	bio = r1_bio->master_bio;
 
-read_more:
-	disk = read_balance(conf, r1_bio, &max_sectors);
-	if (disk == -1) {
-		pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
-				    mdname(mddev), b, (unsigned long long)r1_bio->sector);
-		raid_end_bio_io(r1_bio);
-	} else {
-		const unsigned long do_sync
-			= r1_bio->master_bio->bi_opf & REQ_SYNC;
-		r1_bio->read_disk = disk;
-		bio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
-				     mddev->bio_set);
-		bio_trim(bio, r1_bio->sector - bio->bi_iter.bi_sector,
-			 max_sectors);
-		r1_bio->bios[r1_bio->read_disk] = bio;
-		rdev = conf->mirrors[disk].rdev;
-		pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n",
-				    mdname(mddev),
-				    (unsigned long long)r1_bio->sector,
-				    bdevname(rdev->bdev, b));
-		bio->bi_iter.bi_sector = r1_bio->sector + rdev->data_offset;
-		bio->bi_bdev = rdev->bdev;
-		bio->bi_end_io = raid1_end_read_request;
-		bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
-		if (test_bit(FailFast, &rdev->flags) &&
-		    test_bit(R1BIO_FailFast, &r1_bio->state))
-			bio->bi_opf |= MD_FAILFAST;
-		bio->bi_private = r1_bio;
-		if (max_sectors < r1_bio->sectors) {
-			/* Drat - have to split this up more */
-			struct bio *mbio = r1_bio->master_bio;
-			int sectors_handled = (r1_bio->sector + max_sectors
-					       - mbio->bi_iter.bi_sector);
-			r1_bio->sectors = max_sectors;
-			spin_lock_irq(&conf->device_lock);
-			if (mbio->bi_phys_segments == 0)
-				mbio->bi_phys_segments = 2;
-			else
-				mbio->bi_phys_segments++;
-			spin_unlock_irq(&conf->device_lock);
-			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-					      bio, bio_dev, bio_sector);
-			generic_make_request(bio);
-			bio = NULL;
-
-			r1_bio = alloc_r1bio(mddev, mbio, sectors_handled);
-			set_bit(R1BIO_ReadError, &r1_bio->state);
-
-			goto read_more;
-		} else {
-			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-					      bio, bio_dev, bio_sector);
-			generic_make_request(bio);
-		}
-	}
+	/* Reuse the old r1_bio so that the IO_BLOCKED settings are preserved */
+	r1_bio->state = 0;
+	raid1_read_request(mddev, bio, r1_bio->sectors, r1_bio);
 }
 
 static void raid1d(struct md_thread *thread)
@@ -2660,10 +2565,7 @@ static void raid1d(struct md_thread *thread)
 		else if (test_bit(R1BIO_ReadError, &r1_bio->state))
 			handle_read_error(conf, r1_bio);
 		else
-			/* just a partial read to be scheduled from separate
-			 * context
-			 */
-			generic_make_request(r1_bio->bios[r1_bio->read_disk]);
+			WARN_ON_ONCE(1);
 
 		cond_resched();
 		if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
@@ -2793,7 +2695,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		struct md_rdev *rdev;
 		bio = r1_bio->bios[i];
-		bio_reset(bio);
 
 		rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev == NULL ||
@@ -2849,7 +2750,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			atomic_inc(&rdev->nr_pending);
 			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
 			bio->bi_bdev = rdev->bdev;
-			bio->bi_private = r1_bio;
 			if (test_bit(FailFast, &rdev->flags))
 				bio->bi_opf |= MD_FAILFAST;
 		}
@@ -2935,31 +2835,25 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 
 		for (i = 0 ; i < conf->raid_disks * 2; i++) {
+			struct resync_pages *rp;
+
 			bio = r1_bio->bios[i];
+			rp = get_resync_pages(bio);
 			if (bio->bi_end_io) {
-				page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
-				if (bio_add_page(bio, page, len, 0) == 0) {
-					/* stop here */
-					bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
-					while (i > 0) {
-						i--;
-						bio = r1_bio->bios[i];
-						if (bio->bi_end_io==NULL)
-							continue;
-						/* remove last page from this bio */
-						bio->bi_vcnt--;
-						bio->bi_iter.bi_size -= len;
-						bio_clear_flag(bio, BIO_SEG_VALID);
-					}
-					goto bio_full;
-				}
+				page = resync_fetch_page(rp, rp->idx++);
+
+				/*
+				 * won't fail because the vec table is big
+				 * enough to hold all these pages
+				 */
+				bio_add_page(bio, page, len, 0);
 			}
 		}
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
 		sync_blocks -= (len>>9);
-	} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
- bio_full:
+	} while (get_resync_pages(r1_bio->bios[disk]->bi_private)->idx < RESYNC_PAGES);
+
 	r1_bio->sectors = nr_sectors;
 
 	if (mddev_is_clustered(mddev) &&
@@ -3059,12 +2953,15 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	if (!conf->r1bio_pool)
 		goto abort;
 
+	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!conf->bio_split)
+		goto abort;
+
 	conf->poolinfo->mddev = mddev;
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
 	rdev_for_each(rdev, mddev) {
-		struct request_queue *q;
 		int disk_idx = rdev->raid_disk;
 		if (disk_idx >= mddev->raid_disks
 		    || disk_idx < 0)
@@ -3077,8 +2974,6 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 		if (disk->rdev)
 			goto abort;
 		disk->rdev = rdev;
-		q = bdev_get_queue(rdev->bdev);
-
 		disk->head_position = 0;
 		disk->seq_start = MaxSector;
 	}
@@ -3140,6 +3035,8 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 		kfree(conf->nr_waiting);
 		kfree(conf->nr_queued);
 		kfree(conf->barrier);
+		if (conf->bio_split)
+			bioset_free(conf->bio_split);
 		kfree(conf);
 	}
 	return ERR_PTR(err);
@@ -3247,6 +3144,8 @@ static void raid1_free(struct mddev *mddev, void *priv)
 	kfree(conf->nr_waiting);
 	kfree(conf->nr_queued);
 	kfree(conf->barrier);
+	if (conf->bio_split)
+		bioset_free(conf->bio_split);
 	kfree(conf);
 }
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index dd22a37d0d83..c8894ef1e9d2 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -84,6 +84,7 @@ struct r1conf {
 	 */
 	wait_queue_head_t	wait_barrier;
 	spinlock_t		resync_lock;
+	atomic_t		nr_sync_pending;
 	atomic_t		*nr_pending;
 	atomic_t		*nr_waiting;
 	atomic_t		*nr_queued;
@@ -107,6 +108,8 @@ struct r1conf {
 	mempool_t		*r1bio_pool;
 	mempool_t		*r1buf_pool;
 
+	struct bio_set		*bio_split;
+
 	/* temporary buffer to synchronous IO when attempting to repair
 	 * a read error.
 	 */
@@ -153,9 +156,13 @@ struct r1bio {
 	int			read_disk;
 
 	struct list_head	retry_list;
-	/* Next two are only valid when R1BIO_BehindIO is set */
-	struct bio_vec		*behind_bvecs;
-	int			behind_page_count;
+
+	/*
+	 * When R1BIO_BehindIO is set, we store pages for write behind
+	 * in behind_master_bio.
+	 */
+	struct bio		*behind_master_bio;
+
 	/*
 	 * if the IO is in WRITE direction, then multiple bios are used.
 	 * We choose the number when they are allocated.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 28ec3a93acee..6b86a0032cf8 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -110,6 +110,24 @@ static void end_reshape(struct r10conf *conf);
 #define raid10_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
 
+/*
+ * 'strct resync_pages' stores actual pages used for doing the resync
+ *  IO, and it is per-bio, so make .bi_private points to it.
+ */
+static inline struct resync_pages *get_resync_pages(struct bio *bio)
+{
+	return bio->bi_private;
+}
+
+/*
+ * for resync bio, r10bio pointer can be retrieved from the per-bio
+ * 'struct resync_pages'.
+ */
+static inline struct r10bio *get_resync_r10bio(struct bio *bio)
+{
+	return get_resync_pages(bio)->raid_bio;
+}
+
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct r10conf *conf = data;
@@ -125,9 +143,6 @@ static void r10bio_pool_free(void *r10_bio, void *data)
 	kfree(r10_bio);
 }
 
-/* Maximum size of each resync request */
-#define RESYNC_BLOCK_SIZE (64*1024)
-#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 /* amount of memory to reserve for resync requests */
 #define RESYNC_WINDOW (1024*1024)
 /* maximum number of concurrent requests, memory permitting */
@@ -143,11 +158,11 @@ static void r10bio_pool_free(void *r10_bio, void *data)
 static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct r10conf *conf = data;
-	struct page *page;
 	struct r10bio *r10_bio;
 	struct bio *bio;
-	int i, j;
-	int nalloc;
+	int j;
+	int nalloc, nalloc_rp;
+	struct resync_pages *rps;
 
 	r10_bio = r10bio_pool_alloc(gfp_flags, conf);
 	if (!r10_bio)
@@ -159,6 +174,15 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 	else
 		nalloc = 2; /* recovery */
 
+	/* allocate once for all bios */
+	if (!conf->have_replacement)
+		nalloc_rp = nalloc;
+	else
+		nalloc_rp = nalloc * 2;
+	rps = kmalloc(sizeof(struct resync_pages) * nalloc_rp, gfp_flags);
+	if (!rps)
+		goto out_free_r10bio;
+
 	/*
 	 * Allocate bios.
 	 */
@@ -178,36 +202,40 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * Allocate RESYNC_PAGES data pages and attach them
 	 * where needed.
 	 */
-	for (j = 0 ; j < nalloc; j++) {
+	for (j = 0; j < nalloc; j++) {
 		struct bio *rbio = r10_bio->devs[j].repl_bio;
+		struct resync_pages *rp, *rp_repl;
+
+		rp = &rps[j];
+		if (rbio)
+			rp_repl = &rps[nalloc + j];
+
 		bio = r10_bio->devs[j].bio;
-		for (i = 0; i < RESYNC_PAGES; i++) {
-			if (j > 0 && !test_bit(MD_RECOVERY_SYNC,
-					       &conf->mddev->recovery)) {
-				/* we can share bv_page's during recovery
-				 * and reshape */
-				struct bio *rbio = r10_bio->devs[0].bio;
-				page = rbio->bi_io_vec[i].bv_page;
-				get_page(page);
-			} else
-				page = alloc_page(gfp_flags);
-			if (unlikely(!page))
+
+		if (!j || test_bit(MD_RECOVERY_SYNC,
+				   &conf->mddev->recovery)) {
+			if (resync_alloc_pages(rp, gfp_flags))
 				goto out_free_pages;
+		} else {
+			memcpy(rp, &rps[0], sizeof(*rp));
+			resync_get_all_pages(rp);
+		}
 
-			bio->bi_io_vec[i].bv_page = page;
-			if (rbio)
-				rbio->bi_io_vec[i].bv_page = page;
+		rp->idx = 0;
+		rp->raid_bio = r10_bio;
+		bio->bi_private = rp;
+		if (rbio) {
+			memcpy(rp_repl, rp, sizeof(*rp));
+			rbio->bi_private = rp_repl;
 		}
 	}
 
 	return r10_bio;
 
 out_free_pages:
-	for ( ; i > 0 ; i--)
-		safe_put_page(bio->bi_io_vec[i-1].bv_page);
-	while (j--)
-		for (i = 0; i < RESYNC_PAGES ; i++)
-			safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page);
+	while (--j >= 0)
+		resync_free_pages(&rps[j * 2]);
+
 	j = 0;
 out_free_bio:
 	for ( ; j < nalloc; j++) {
@@ -216,30 +244,34 @@ out_free_bio:
 		if (r10_bio->devs[j].repl_bio)
 			bio_put(r10_bio->devs[j].repl_bio);
 	}
+	kfree(rps);
+out_free_r10bio:
 	r10bio_pool_free(r10_bio, conf);
 	return NULL;
 }
 
 static void r10buf_pool_free(void *__r10_bio, void *data)
 {
-	int i;
 	struct r10conf *conf = data;
 	struct r10bio *r10bio = __r10_bio;
 	int j;
+	struct resync_pages *rp = NULL;
 
-	for (j=0; j < conf->copies; j++) {
+	for (j = conf->copies; j--; ) {
 		struct bio *bio = r10bio->devs[j].bio;
-		if (bio) {
-			for (i = 0; i < RESYNC_PAGES; i++) {
-				safe_put_page(bio->bi_io_vec[i].bv_page);
-				bio->bi_io_vec[i].bv_page = NULL;
-			}
-			bio_put(bio);
-		}
+
+		rp = get_resync_pages(bio);
+		resync_free_pages(rp);
+		bio_put(bio);
+
 		bio = r10bio->devs[j].repl_bio;
 		if (bio)
 			bio_put(bio);
 	}
+
+	/* resync pages array stored in the 1st bio's .bi_private */
+	kfree(rp);
+
 	r10bio_pool_free(r10bio, conf);
 }
 
@@ -301,27 +333,18 @@ static void reschedule_retry(struct r10bio *r10_bio)
 static void raid_end_bio_io(struct r10bio *r10_bio)
 {
 	struct bio *bio = r10_bio->master_bio;
-	int done;
 	struct r10conf *conf = r10_bio->mddev->private;
 
-	if (bio->bi_phys_segments) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		bio->bi_phys_segments--;
-		done = (bio->bi_phys_segments == 0);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-	} else
-		done = 1;
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
 		bio->bi_error = -EIO;
-	if (done) {
-		bio_endio(bio);
-		/*
-		 * Wake up any possible resync thread that waits for the device
-		 * to go idle.
-		 */
-		allow_barrier(conf);
-	}
+
+	bio_endio(bio);
+	/*
+	 * Wake up any possible resync thread that waits for the device
+	 * to go idle.
+	 */
+	allow_barrier(conf);
+
 	free_r10bio(r10_bio);
 }
 
@@ -1095,12 +1118,41 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	struct bio *read_bio;
 	const int op = bio_op(bio);
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
-	int sectors_handled;
 	int max_sectors;
 	sector_t sectors;
 	struct md_rdev *rdev;
-	int slot;
+	char b[BDEVNAME_SIZE];
+	int slot = r10_bio->read_slot;
+	struct md_rdev *err_rdev = NULL;
+	gfp_t gfp = GFP_NOIO;
 
+	if (r10_bio->devs[slot].rdev) {
+		/*
+		 * This is an error retry, but we cannot
+		 * safely dereference the rdev in the r10_bio,
+		 * we must use the one in conf.
+		 * If it has already been disconnected (unlikely)
+		 * we lose the device name in error messages.
+		 */
+		int disk;
+		/*
+		 * As we are blocking raid10, it is a little safer to
+		 * use __GFP_HIGH.
+		 */
+		gfp = GFP_NOIO | __GFP_HIGH;
+
+		rcu_read_lock();
+		disk = r10_bio->devs[slot].devnum;
+		err_rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		if (err_rdev)
+			bdevname(err_rdev->bdev, b);
+		else {
+			strcpy(b, "???");
+			/* This never gets dereferenced */
+			err_rdev = r10_bio->devs[slot].rdev;
+		}
+		rcu_read_unlock();
+	}
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
@@ -1108,7 +1160,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	 */
 	wait_barrier(conf);
 
-	sectors = bio_sectors(bio);
+	sectors = r10_bio->sectors;
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
 	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
@@ -1125,17 +1177,33 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		wait_barrier(conf);
 	}
 
-read_again:
 	rdev = read_balance(conf, r10_bio, &max_sectors);
 	if (!rdev) {
+		if (err_rdev) {
+			pr_crit_ratelimited("md/raid10:%s: %s: unrecoverable I/O read error for block %llu\n",
+					    mdname(mddev), b,
+					    (unsigned long long)r10_bio->sector);
+		}
 		raid_end_bio_io(r10_bio);
 		return;
 	}
+	if (err_rdev)
+		pr_err_ratelimited("md/raid10:%s: %s: redirecting sector %llu to another mirror\n",
+				   mdname(mddev),
+				   bdevname(rdev->bdev, b),
+				   (unsigned long long)r10_bio->sector);
+	if (max_sectors < bio_sectors(bio)) {
+		struct bio *split = bio_split(bio, max_sectors,
+					      gfp, conf->bio_split);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		r10_bio->master_bio = bio;
+		r10_bio->sectors = max_sectors;
+	}
 	slot = r10_bio->read_slot;
 
-	read_bio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-	bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
-		 max_sectors);
+	read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
 
 	r10_bio->devs[slot].bio = read_bio;
 	r10_bio->devs[slot].rdev = rdev;
@@ -1154,55 +1222,86 @@ read_again:
 	        trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
 	                              read_bio, disk_devt(mddev->gendisk),
 	                              r10_bio->sector);
-	if (max_sectors < r10_bio->sectors) {
-		/*
-		 * Could not read all from this device, so we will need another
-		 * r10_bio.
-		 */
-		sectors_handled = (r10_bio->sector + max_sectors
-				   - bio->bi_iter.bi_sector);
-		r10_bio->sectors = max_sectors;
-		spin_lock_irq(&conf->device_lock);
-		if (bio->bi_phys_segments == 0)
-			bio->bi_phys_segments = 2;
-		else
-			bio->bi_phys_segments++;
-		spin_unlock_irq(&conf->device_lock);
-		/*
-		 * Cannot call generic_make_request directly as that will be
-		 * queued in __generic_make_request and subsequent
-		 * mempool_alloc might block waiting for it.  so hand bio over
-		 * to raid10d.
-		 */
-		reschedule_retry(r10_bio);
-
-		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
-		r10_bio->master_bio = bio;
-		r10_bio->sectors = bio_sectors(bio) - sectors_handled;
-		r10_bio->state = 0;
-		r10_bio->mddev = mddev;
-		r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
-		goto read_again;
-	} else
-		generic_make_request(read_bio);
+	generic_make_request(read_bio);
 	return;
 }
 
-static void raid10_write_request(struct mddev *mddev, struct bio *bio,
-				 struct r10bio *r10_bio)
+static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
+				  struct bio *bio, bool replacement,
+				  int n_copy)
 {
-	struct r10conf *conf = mddev->private;
-	int i;
 	const int op = bio_op(bio);
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
 	unsigned long flags;
-	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid10_plug_cb *plug = NULL;
+	struct r10conf *conf = mddev->private;
+	struct md_rdev *rdev;
+	int devnum = r10_bio->devs[n_copy].devnum;
+	struct bio *mbio;
+
+	if (replacement) {
+		rdev = conf->mirrors[devnum].replacement;
+		if (rdev == NULL) {
+			/* Replacement just got moved to main 'rdev' */
+			smp_mb();
+			rdev = conf->mirrors[devnum].rdev;
+		}
+	} else
+		rdev = conf->mirrors[devnum].rdev;
+
+	mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+	if (replacement)
+		r10_bio->devs[n_copy].repl_bio = mbio;
+	else
+		r10_bio->devs[n_copy].bio = mbio;
+
+	mbio->bi_iter.bi_sector	= (r10_bio->devs[n_copy].addr +
+				   choose_data_offset(r10_bio, rdev));
+	mbio->bi_bdev = rdev->bdev;
+	mbio->bi_end_io	= raid10_end_write_request;
+	bio_set_op_attrs(mbio, op, do_sync | do_fua);
+	if (!replacement && test_bit(FailFast,
+				     &conf->mirrors[devnum].rdev->flags)
+			 && enough(conf, devnum))
+		mbio->bi_opf |= MD_FAILFAST;
+	mbio->bi_private = r10_bio;
+
+	if (conf->mddev->gendisk)
+		trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
+				      mbio, disk_devt(conf->mddev->gendisk),
+				      r10_bio->sector);
+	/* flush_pending_writes() needs access to the rdev so...*/
+	mbio->bi_bdev = (void *)rdev;
+
+	atomic_inc(&r10_bio->remaining);
+
+	cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
+	if (cb)
+		plug = container_of(cb, struct raid10_plug_cb, cb);
+	else
+		plug = NULL;
+	spin_lock_irqsave(&conf->device_lock, flags);
+	if (plug) {
+		bio_list_add(&plug->pending, mbio);
+		plug->pending_cnt++;
+	} else {
+		bio_list_add(&conf->pending_bio_list, mbio);
+		conf->pending_count++;
+	}
+	spin_unlock_irqrestore(&conf->device_lock, flags);
+	if (!plug)
+		md_wakeup_thread(mddev->thread);
+}
+
+static void raid10_write_request(struct mddev *mddev, struct bio *bio,
+				 struct r10bio *r10_bio)
+{
+	struct r10conf *conf = mddev->private;
+	int i;
+	struct md_rdev *blocked_rdev;
 	sector_t sectors;
-	int sectors_handled;
 	int max_sectors;
 
 	md_write_start(mddev, bio);
@@ -1214,7 +1313,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	 */
 	wait_barrier(conf);
 
-	sectors = bio_sectors(bio);
+	sectors = r10_bio->sectors;
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
 	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
@@ -1262,9 +1361,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	 * on which we have seen a write error, we want to avoid
 	 * writing to those blocks.  This potentially requires several
 	 * writes to write around the bad blocks.  Each set of writes
-	 * gets its own r10_bio with a set of bios attached.  The number
-	 * of r10_bios is recored in bio->bi_phys_segments just as with
-	 * the read case.
+	 * gets its own r10_bio with a set of bios attached.
 	 */
 
 	r10_bio->read_slot = -1; /* make sure repl_bio gets freed */
@@ -1384,145 +1481,31 @@ retry_write:
 		goto retry_write;
 	}
 
-	if (max_sectors < r10_bio->sectors) {
-		/* We are splitting this into multiple parts, so
-		 * we need to prepare for allocating another r10_bio.
-		 */
+	if (max_sectors < r10_bio->sectors)
 		r10_bio->sectors = max_sectors;
-		spin_lock_irq(&conf->device_lock);
-		if (bio->bi_phys_segments == 0)
-			bio->bi_phys_segments = 2;
-		else
-			bio->bi_phys_segments++;
-		spin_unlock_irq(&conf->device_lock);
+
+	if (r10_bio->sectors < bio_sectors(bio)) {
+		struct bio *split = bio_split(bio, r10_bio->sectors,
+					      GFP_NOIO, conf->bio_split);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		r10_bio->master_bio = bio;
 	}
-	sectors_handled = r10_bio->sector + max_sectors -
-		bio->bi_iter.bi_sector;
 
 	atomic_set(&r10_bio->remaining, 1);
 	bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
 
 	for (i = 0; i < conf->copies; i++) {
-		struct bio *mbio;
-		int d = r10_bio->devs[i].devnum;
-		if (r10_bio->devs[i].bio) {
-			struct md_rdev *rdev = conf->mirrors[d].rdev;
-			mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-			bio_trim(mbio, r10_bio->sector - bio->bi_iter.bi_sector,
-				 max_sectors);
-			r10_bio->devs[i].bio = mbio;
-
-			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr+
-					   choose_data_offset(r10_bio, rdev));
-			mbio->bi_bdev = rdev->bdev;
-			mbio->bi_end_io	= raid10_end_write_request;
-			bio_set_op_attrs(mbio, op, do_sync | do_fua);
-			if (test_bit(FailFast, &conf->mirrors[d].rdev->flags) &&
-			    enough(conf, d))
-				mbio->bi_opf |= MD_FAILFAST;
-			mbio->bi_private = r10_bio;
-
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
-						      mbio, disk_devt(conf->mddev->gendisk),
-						      r10_bio->sector);
-			/* flush_pending_writes() needs access to the rdev so...*/
-			mbio->bi_bdev = (void*)rdev;
-
-			atomic_inc(&r10_bio->remaining);
-
-			cb = blk_check_plugged(raid10_unplug, mddev,
-					       sizeof(*plug));
-			if (cb)
-				plug = container_of(cb, struct raid10_plug_cb,
-						    cb);
-			else
-				plug = NULL;
-			spin_lock_irqsave(&conf->device_lock, flags);
-			if (plug) {
-				bio_list_add(&plug->pending, mbio);
-				plug->pending_cnt++;
-			} else {
-				bio_list_add(&conf->pending_bio_list, mbio);
-				conf->pending_count++;
-			}
-			spin_unlock_irqrestore(&conf->device_lock, flags);
-			if (!plug)
-				md_wakeup_thread(mddev->thread);
-		}
-
-		if (r10_bio->devs[i].repl_bio) {
-			struct md_rdev *rdev = conf->mirrors[d].replacement;
-			if (rdev == NULL) {
-				/* Replacement just got moved to main 'rdev' */
-				smp_mb();
-				rdev = conf->mirrors[d].rdev;
-			}
-			mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-			bio_trim(mbio, r10_bio->sector - bio->bi_iter.bi_sector,
-				 max_sectors);
-			r10_bio->devs[i].repl_bio = mbio;
-
-			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr +
-					   choose_data_offset(r10_bio, rdev));
-			mbio->bi_bdev = rdev->bdev;
-			mbio->bi_end_io	= raid10_end_write_request;
-			bio_set_op_attrs(mbio, op, do_sync | do_fua);
-			mbio->bi_private = r10_bio;
-
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
-						      mbio, disk_devt(conf->mddev->gendisk),
-						      r10_bio->sector);
-			/* flush_pending_writes() needs access to the rdev so...*/
-			mbio->bi_bdev = (void*)rdev;
-
-			atomic_inc(&r10_bio->remaining);
-
-			cb = blk_check_plugged(raid10_unplug, mddev,
-					       sizeof(*plug));
-			if (cb)
-				plug = container_of(cb, struct raid10_plug_cb,
-						    cb);
-			else
-				plug = NULL;
-			spin_lock_irqsave(&conf->device_lock, flags);
-			if (plug) {
-				bio_list_add(&plug->pending, mbio);
-				plug->pending_cnt++;
-			} else {
-				bio_list_add(&conf->pending_bio_list, mbio);
-				conf->pending_count++;
-			}
-			spin_unlock_irqrestore(&conf->device_lock, flags);
-			if (!plug)
-				md_wakeup_thread(mddev->thread);
-		}
-	}
-
-	/* Don't remove the bias on 'remaining' (one_write_done) until
-	 * after checking if we need to go around again.
-	 */
-
-	if (sectors_handled < bio_sectors(bio)) {
-		one_write_done(r10_bio);
-		/* We need another r10_bio.  It has already been counted
-		 * in bio->bi_phys_segments.
-		 */
-		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
-		r10_bio->master_bio = bio;
-		r10_bio->sectors = bio_sectors(bio) - sectors_handled;
-
-		r10_bio->mddev = mddev;
-		r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
-		r10_bio->state = 0;
-		goto retry_write;
+		if (r10_bio->devs[i].bio)
+			raid10_write_one_disk(mddev, r10_bio, bio, false, i);
+		if (r10_bio->devs[i].repl_bio)
+			raid10_write_one_disk(mddev, r10_bio, bio, true, i);
 	}
 	one_write_done(r10_bio);
 }
 
-static void __make_request(struct mddev *mddev, struct bio *bio)
+static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
@@ -1530,21 +1513,12 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 	r10_bio->master_bio = bio;
-	r10_bio->sectors = bio_sectors(bio);
+	r10_bio->sectors = sectors;
 
 	r10_bio->mddev = mddev;
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
-
-	/*
-	 * We might need to issue multiple reads to different devices if there
-	 * are bad blocks around, so we keep track of the number of reads in
-	 * bio->bi_phys_segments.  If this is 0, there is only one r10_bio and
-	 * no locking will be needed when the request completes.  If it is
-	 * non-zero, then it is the number of not-completed requests.
-	 */
-	bio->bi_phys_segments = 0;
-	bio_clear_flag(bio, BIO_SEG_VALID);
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);
 
 	if (bio_data_dir(bio) == READ)
 		raid10_read_request(mddev, bio, r10_bio);
@@ -1557,54 +1531,26 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 	struct r10conf *conf = mddev->private;
 	sector_t chunk_mask = (conf->geo.chunk_mask & conf->prev.chunk_mask);
 	int chunk_sects = chunk_mask + 1;
-
-	struct bio *split;
+	int sectors = bio_sectors(bio);
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	do {
-
-		/*
-		 * If this request crosses a chunk boundary, we need to split
-		 * it.
-		 */
-		if (unlikely((bio->bi_iter.bi_sector & chunk_mask) +
-			     bio_sectors(bio) > chunk_sects
-			     && (conf->geo.near_copies < conf->geo.raid_disks
-				 || conf->prev.near_copies <
-				 conf->prev.raid_disks))) {
-			split = bio_split(bio, chunk_sects -
-					  (bio->bi_iter.bi_sector &
-					   (chunk_sects - 1)),
-					  GFP_NOIO, fs_bio_set);
-			bio_chain(split, bio);
-		} else {
-			split = bio;
-		}
-
-		/*
-		 * If a bio is splitted, the first part of bio will pass
-		 * barrier but the bio is queued in current->bio_list (see
-		 * generic_make_request). If there is a raise_barrier() called
-		 * here, the second part of bio can't pass barrier. But since
-		 * the first part bio isn't dispatched to underlaying disks
-		 * yet, the barrier is never released, hence raise_barrier will
-		 * alays wait. We have a deadlock.
-		 * Note, this only happens in read path. For write path, the
-		 * first part of bio is dispatched in a schedule() call
-		 * (because of blk plug) or offloaded to raid10d.
-		 * Quitting from the function immediately can change the bio
-		 * order queued in bio_list and avoid the deadlock.
-		 */
-		__make_request(mddev, split);
-		if (split != bio && bio_data_dir(bio) == READ) {
-			generic_make_request(bio);
-			break;
-		}
-	} while (split != bio);
+	/*
+	 * If this request crosses a chunk boundary, we need to split
+	 * it.
+	 */
+	if (unlikely((bio->bi_iter.bi_sector & chunk_mask) +
+		     sectors > chunk_sects
+		     && (conf->geo.near_copies < conf->geo.raid_disks
+			 || conf->prev.near_copies <
+			 conf->prev.raid_disks)))
+		sectors = chunk_sects -
+			(bio->bi_iter.bi_sector &
+			 (chunk_sects - 1));
+	__make_request(mddev, bio, sectors);
 
 	/* In case raid10d snuck in to freeze_array */
 	wake_up(&conf->wait_barrier);
@@ -1928,13 +1874,9 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			   * but will never see neither -- if they are careful.
 			   */
 		p->replacement = NULL;
-		clear_bit(WantReplacement, &rdev->flags);
-	} else
-		/* We might have just remove the Replacement as faulty
-		 * Clear the flag just in case
-		 */
-		clear_bit(WantReplacement, &rdev->flags);
+	}
 
+	clear_bit(WantReplacement, &rdev->flags);
 	err = md_integrity_register(mddev);
 
 abort:
@@ -1943,17 +1885,9 @@ abort:
 	return err;
 }
 
-static void end_sync_read(struct bio *bio)
+static void __end_sync_read(struct r10bio *r10_bio, struct bio *bio, int d)
 {
-	struct r10bio *r10_bio = bio->bi_private;
 	struct r10conf *conf = r10_bio->mddev->private;
-	int d;
-
-	if (bio == r10_bio->master_bio) {
-		/* this is a reshape read */
-		d = r10_bio->read_slot; /* really the read dev */
-	} else
-		d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
 
 	if (!bio->bi_error)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
@@ -1977,6 +1911,23 @@ static void end_sync_read(struct bio *bio)
 	}
 }
 
+static void end_sync_read(struct bio *bio)
+{
+	struct r10bio *r10_bio = get_resync_r10bio(bio);
+	struct r10conf *conf = r10_bio->mddev->private;
+	int d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
+
+	__end_sync_read(r10_bio, bio, d);
+}
+
+static void end_reshape_read(struct bio *bio)
+{
+	/* reshape read bio isn't allocated from r10buf_pool */
+	struct r10bio *r10_bio = bio->bi_private;
+
+	__end_sync_read(r10_bio, bio, r10_bio->read_slot);
+}
+
 static void end_sync_request(struct r10bio *r10_bio)
 {
 	struct mddev *mddev = r10_bio->mddev;
@@ -2006,7 +1957,7 @@ static void end_sync_request(struct r10bio *r10_bio)
 
 static void end_sync_write(struct bio *bio)
 {
-	struct r10bio *r10_bio = bio->bi_private;
+	struct r10bio *r10_bio = get_resync_r10bio(bio);
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
@@ -2065,6 +2016,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	int i, first;
 	struct bio *tbio, *fbio;
 	int vcnt;
+	struct page **tpages, **fpages;
 
 	atomic_set(&r10_bio->remaining, 1);
 
@@ -2080,12 +2032,14 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	fbio = r10_bio->devs[i].bio;
 	fbio->bi_iter.bi_size = r10_bio->sectors << 9;
 	fbio->bi_iter.bi_idx = 0;
+	fpages = get_resync_pages(fbio)->pages;
 
 	vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
 	/* now find blocks with errors */
 	for (i=0 ; i < conf->copies ; i++) {
 		int  j, d;
 		struct md_rdev *rdev;
+		struct resync_pages *rp;
 
 		tbio = r10_bio->devs[i].bio;
 
@@ -2093,6 +2047,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			continue;
 		if (i == first)
 			continue;
+
+		tpages = get_resync_pages(tbio)->pages;
 		d = r10_bio->devs[i].devnum;
 		rdev = conf->mirrors[d].rdev;
 		if (!r10_bio->devs[i].bio->bi_error) {
@@ -2105,8 +2061,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 				int len = PAGE_SIZE;
 				if (sectors < (len / 512))
 					len = sectors * 512;
-				if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
-					   page_address(tbio->bi_io_vec[j].bv_page),
+				if (memcmp(page_address(fpages[j]),
+					   page_address(tpages[j]),
 					   len))
 					break;
 				sectors -= len/512;
@@ -2127,11 +2083,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		 * First we need to fixup bv_offset, bv_len and
 		 * bi_vecs, as the read request might have corrupted these
 		 */
+		rp = get_resync_pages(tbio);
 		bio_reset(tbio);
 
 		tbio->bi_vcnt = vcnt;
 		tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
-		tbio->bi_private = r10_bio;
+		rp->raid_bio = r10_bio;
+		tbio->bi_private = rp;
 		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
 		tbio->bi_end_io = end_sync_write;
 		bio_set_op_attrs(tbio, REQ_OP_WRITE, 0);
@@ -2202,6 +2160,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 	int idx = 0;
 	int dr = r10_bio->devs[0].devnum;
 	int dw = r10_bio->devs[1].devnum;
+	struct page **pages = get_resync_pages(bio)->pages;
 
 	while (sectors) {
 		int s = sectors;
@@ -2217,7 +2176,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 		ok = sync_page_io(rdev,
 				  addr,
 				  s << 9,
-				  bio->bi_io_vec[idx].bv_page,
+				  pages[idx],
 				  REQ_OP_READ, 0, false);
 		if (ok) {
 			rdev = conf->mirrors[dw].rdev;
@@ -2225,7 +2184,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 			ok = sync_page_io(rdev,
 					  addr,
 					  s << 9,
-					  bio->bi_io_vec[idx].bv_page,
+					  pages[idx],
 					  REQ_OP_WRITE, 0, false);
 			if (!ok) {
 				set_bit(WriteErrorSeen, &rdev->flags);
@@ -2625,9 +2584,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 	struct bio *bio;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev = r10_bio->devs[slot].rdev;
-	char b[BDEVNAME_SIZE];
-	unsigned long do_sync;
-	int max_sectors;
 	dev_t bio_dev;
 	sector_t bio_last_sector;
 
@@ -2640,7 +2596,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 	 * frozen.
 	 */
 	bio = r10_bio->devs[slot].bio;
-	bdevname(bio->bi_bdev, b);
 	bio_dev = bio->bi_bdev->bd_dev;
 	bio_last_sector = r10_bio->devs[slot].addr + rdev->data_offset + r10_bio->sectors;
 	bio_put(bio);
@@ -2656,69 +2611,9 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 		md_error(mddev, rdev);
 
 	rdev_dec_pending(rdev, mddev);
-
-read_more:
-	rdev = read_balance(conf, r10_bio, &max_sectors);
-	if (rdev == NULL) {
-		pr_crit_ratelimited("md/raid10:%s: %s: unrecoverable I/O read error for block %llu\n",
-				    mdname(mddev), b,
-				    (unsigned long long)r10_bio->sector);
-		raid_end_bio_io(r10_bio);
-		return;
-	}
-
-	do_sync = (r10_bio->master_bio->bi_opf & REQ_SYNC);
-	slot = r10_bio->read_slot;
-	pr_err_ratelimited("md/raid10:%s: %s: redirecting sector %llu to another mirror\n",
-			   mdname(mddev),
-			   bdevname(rdev->bdev, b),
-			   (unsigned long long)r10_bio->sector);
-	bio = bio_clone_fast(r10_bio->master_bio, GFP_NOIO, mddev->bio_set);
-	bio_trim(bio, r10_bio->sector - bio->bi_iter.bi_sector, max_sectors);
-	r10_bio->devs[slot].bio = bio;
-	r10_bio->devs[slot].rdev = rdev;
-	bio->bi_iter.bi_sector = r10_bio->devs[slot].addr
-		+ choose_data_offset(r10_bio, rdev);
-	bio->bi_bdev = rdev->bdev;
-	bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
-	if (test_bit(FailFast, &rdev->flags) &&
-	    test_bit(R10BIO_FailFast, &r10_bio->state))
-		bio->bi_opf |= MD_FAILFAST;
-	bio->bi_private = r10_bio;
-	bio->bi_end_io = raid10_end_read_request;
-	trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-			      bio, bio_dev,
-			      bio_last_sector - r10_bio->sectors);
-
-	if (max_sectors < r10_bio->sectors) {
-		/* Drat - have to split this up more */
-		struct bio *mbio = r10_bio->master_bio;
-		int sectors_handled =
-			r10_bio->sector + max_sectors
-			- mbio->bi_iter.bi_sector;
-		r10_bio->sectors = max_sectors;
-		spin_lock_irq(&conf->device_lock);
-		if (mbio->bi_phys_segments == 0)
-			mbio->bi_phys_segments = 2;
-		else
-			mbio->bi_phys_segments++;
-		spin_unlock_irq(&conf->device_lock);
-		generic_make_request(bio);
-
-		r10_bio = mempool_alloc(conf->r10bio_pool,
-					GFP_NOIO);
-		r10_bio->master_bio = mbio;
-		r10_bio->sectors = bio_sectors(mbio) - sectors_handled;
-		r10_bio->state = 0;
-		set_bit(R10BIO_ReadError,
-			&r10_bio->state);
-		r10_bio->mddev = mddev;
-		r10_bio->sector = mbio->bi_iter.bi_sector
-			+ sectors_handled;
-
-		goto read_more;
-	} else
-		generic_make_request(bio);
+	allow_barrier(conf);
+	r10_bio->state = 0;
+	raid10_read_request(mddev, r10_bio->master_bio, r10_bio);
 }
 
 static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
@@ -2805,6 +2700,11 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
 			conf->nr_queued++;
 			spin_unlock_irq(&conf->device_lock);
+			/*
+			 * In case freeze_array() is waiting for condition
+			 * nr_pending == nr_queued + extra to be true.
+			 */
+			wake_up(&conf->wait_barrier);
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
 			if (test_bit(R10BIO_WriteError,
@@ -2879,13 +2779,8 @@ static void raid10d(struct md_thread *thread)
 			recovery_request_write(mddev, r10_bio);
 		else if (test_bit(R10BIO_ReadError, &r10_bio->state))
 			handle_read_error(mddev, r10_bio);
-		else {
-			/* just a partial read to be scheduled from a
-			 * separate context
-			 */
-			int slot = r10_bio->read_slot;
-			generic_make_request(r10_bio->devs[slot].bio);
-		}
+		else
+			WARN_ON_ONCE(1);
 
 		cond_resched();
 		if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
@@ -3199,10 +3094,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					}
 				}
 				bio = r10_bio->devs[0].bio;
-				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
-				bio->bi_private = r10_bio;
 				bio->bi_end_io = end_sync_read;
 				bio_set_op_attrs(bio, REQ_OP_READ, 0);
 				if (test_bit(FailFast, &rdev->flags))
@@ -3226,10 +3119,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 				if (!test_bit(In_sync, &mrdev->flags)) {
 					bio = r10_bio->devs[1].bio;
-					bio_reset(bio);
 					bio->bi_next = biolist;
 					biolist = bio;
-					bio->bi_private = r10_bio;
 					bio->bi_end_io = end_sync_write;
 					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 					bio->bi_iter.bi_sector = to_addr
@@ -3254,10 +3145,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				if (mreplace == NULL || bio == NULL ||
 				    test_bit(Faulty, &mreplace->flags))
 					break;
-				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
-				bio->bi_private = r10_bio;
 				bio->bi_end_io = end_sync_write;
 				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 				bio->bi_iter.bi_sector = to_addr +
@@ -3379,7 +3268,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				r10_bio->devs[i].repl_bio->bi_end_io = NULL;
 
 			bio = r10_bio->devs[i].bio;
-			bio_reset(bio);
 			bio->bi_error = -EIO;
 			rcu_read_lock();
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
@@ -3404,7 +3292,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			atomic_inc(&r10_bio->remaining);
 			bio->bi_next = biolist;
 			biolist = bio;
-			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_read;
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 			if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
@@ -3423,13 +3310,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
-			bio_reset(bio);
 			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
 			bio->bi_next = biolist;
 			biolist = bio;
-			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_write;
 			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
@@ -3468,27 +3353,17 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (len == 0)
 			break;
 		for (bio= biolist ; bio ; bio=bio->bi_next) {
-			struct bio *bio2;
-			page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
-			if (bio_add_page(bio, page, len, 0))
-				continue;
-
-			/* stop here */
-			bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
-			for (bio2 = biolist;
-			     bio2 && bio2 != bio;
-			     bio2 = bio2->bi_next) {
-				/* remove last page from this bio */
-				bio2->bi_vcnt--;
-				bio2->bi_iter.bi_size -= len;
-				bio_clear_flag(bio2, BIO_SEG_VALID);
-			}
-			goto bio_full;
+			struct resync_pages *rp = get_resync_pages(bio);
+			page = resync_fetch_page(rp, rp->idx++);
+			/*
+			 * won't fail because the vec table is big enough
+			 * to hold all these pages
+			 */
+			bio_add_page(bio, page, len, 0);
 		}
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
-	} while (biolist->bi_vcnt < RESYNC_PAGES);
- bio_full:
+	} while (get_resync_pages(biolist)->idx < RESYNC_PAGES);
 	r10_bio->sectors = nr_sectors;
 
 	while (biolist) {
@@ -3496,7 +3371,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		biolist = biolist->bi_next;
 
 		bio->bi_next = NULL;
-		r10_bio = bio->bi_private;
+		r10_bio = get_resync_r10bio(bio);
 		r10_bio->sectors = nr_sectors;
 
 		if (bio->bi_end_io == end_sync_read) {
@@ -3678,6 +3553,10 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	if (!conf->r10bio_pool)
 		goto out;
 
+	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!conf->bio_split)
+		goto out;
+
 	calc_sectors(conf, mddev->dev_sectors);
 	if (mddev->reshape_position == MaxSector) {
 		conf->prev = conf->geo;
@@ -3715,6 +3594,8 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 		mempool_destroy(conf->r10bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
+		if (conf->bio_split)
+			bioset_free(conf->bio_split);
 		kfree(conf);
 	}
 	return ERR_PTR(err);
@@ -3760,7 +3641,6 @@ static int raid10_run(struct mddev *mddev)
 
 	rdev_for_each(rdev, mddev) {
 		long long diff;
-		struct request_queue *q;
 
 		disk_idx = rdev->raid_disk;
 		if (disk_idx < 0)
@@ -3779,7 +3659,6 @@ static int raid10_run(struct mddev *mddev)
 				goto out_free_conf;
 			disk->rdev = rdev;
 		}
-		q = bdev_get_queue(rdev->bdev);
 		diff = (rdev->new_data_offset - rdev->data_offset);
 		if (!mddev->reshape_backwards)
 			diff = -diff;
@@ -3796,6 +3675,7 @@ static int raid10_run(struct mddev *mddev)
 
 		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
 			discard_supported = true;
+		first = 0;
 	}
 
 	if (mddev->queue) {
@@ -3925,6 +3805,8 @@ static void raid10_free(struct mddev *mddev, void *priv)
 	kfree(conf->mirrors);
 	kfree(conf->mirrors_old);
 	kfree(conf->mirrors_new);
+	if (conf->bio_split)
+		bioset_free(conf->bio_split);
 	kfree(conf);
 }
 
@@ -4198,6 +4080,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 				diff = 0;
 			if (first || diff < min_offset_diff)
 				min_offset_diff = diff;
+			first = 0;
 		}
 	}
 
@@ -4388,6 +4271,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 	struct bio *blist;
 	struct bio *bio, *read_bio;
 	int sectors_done = 0;
+	struct page **pages;
 
 	if (sector_nr == 0) {
 		/* If restarting in the middle, skip the initial sectors */
@@ -4508,7 +4392,7 @@ read_more:
 	read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
 			       + rdev->data_offset);
 	read_bio->bi_private = r10_bio;
-	read_bio->bi_end_io = end_sync_read;
+	read_bio->bi_end_io = end_reshape_read;
 	bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
 	read_bio->bi_error = 0;
@@ -4538,11 +4422,9 @@ read_more:
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
 			continue;
 
-		bio_reset(b);
 		b->bi_bdev = rdev2->bdev;
 		b->bi_iter.bi_sector = r10_bio->devs[s/2].addr +
 			rdev2->new_data_offset;
-		b->bi_private = r10_bio;
 		b->bi_end_io = end_reshape_write;
 		bio_set_op_attrs(b, REQ_OP_WRITE, 0);
 		b->bi_next = blist;
@@ -4552,31 +4434,22 @@ read_more:
 	/* Now add as many pages as possible to all of these bios. */
 
 	nr_sectors = 0;
+	pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
 	for (s = 0 ; s < max_sectors; s += PAGE_SIZE >> 9) {
-		struct page *page = r10_bio->devs[0].bio->bi_io_vec[s/(PAGE_SIZE>>9)].bv_page;
+		struct page *page = pages[s / (PAGE_SIZE >> 9)];
 		int len = (max_sectors - s) << 9;
 		if (len > PAGE_SIZE)
 			len = PAGE_SIZE;
 		for (bio = blist; bio ; bio = bio->bi_next) {
-			struct bio *bio2;
-			if (bio_add_page(bio, page, len, 0))
-				continue;
-
-			/* Didn't fit, must stop */
-			for (bio2 = blist;
-			     bio2 && bio2 != bio;
-			     bio2 = bio2->bi_next) {
-				/* Remove last page from this bio */
-				bio2->bi_vcnt--;
-				bio2->bi_iter.bi_size -= len;
-				bio_clear_flag(bio2, BIO_SEG_VALID);
-			}
-			goto bio_full;
+			/*
+			 * won't fail because the vec table is big enough
+			 * to hold all these pages
+			 */
+			bio_add_page(bio, page, len, 0);
 		}
 		sector_nr += len >> 9;
 		nr_sectors += len >> 9;
 	}
-bio_full:
 	rcu_read_unlock();
 	r10_bio->sectors = nr_sectors;
 
@@ -4690,7 +4563,10 @@ static int handle_reshape_read_error(struct mddev *mddev,
 	struct r10bio *r10b = &on_stack.r10_bio;
 	int slot = 0;
 	int idx = 0;
-	struct bio_vec *bvec = r10_bio->master_bio->bi_io_vec;
+	struct page **pages;
+
+	/* reshape IOs share pages from .devs[0].bio */
+	pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
 
 	r10b->sector = r10_bio->sector;
 	__raid10_find_phys(&conf->prev, r10b);
@@ -4719,7 +4595,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
 			success = sync_page_io(rdev,
 					       addr,
 					       s << 9,
-					       bvec[idx].bv_page,
+					       pages[idx],
 					       REQ_OP_READ, 0, false);
 			rdev_dec_pending(rdev, mddev);
 			rcu_read_lock();
@@ -4747,7 +4623,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
 
 static void end_reshape_write(struct bio *bio)
 {
-	struct r10bio *r10_bio = bio->bi_private;
+	struct r10bio *r10_bio = get_resync_r10bio(bio);
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 3162615e57bd..735ce1a3d260 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -82,6 +82,7 @@ struct r10conf {
 	mempool_t		*r10bio_pool;
 	mempool_t		*r10buf_pool;
 	struct page		*tmppage;
+	struct bio_set		*bio_split;
 
 	/* When taking over an array from a different personality, we store
 	 * the new thread here until we fully activate the array.
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3f307be01b10..b6194e082e48 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -30,6 +30,7 @@
  * underneath hardware sector size. only works with PAGE_SIZE == 4096
  */
 #define BLOCK_SECTORS (8)
+#define BLOCK_SECTOR_SHIFT (3)
 
 /*
  * log->max_free_space is min(1/4 disk size, 10G reclaimable space).
@@ -43,7 +44,7 @@
 /* wake up reclaim thread periodically */
 #define R5C_RECLAIM_WAKEUP_INTERVAL (30 * HZ)
 /* start flush with these full stripes */
-#define R5C_FULL_STRIPE_FLUSH_BATCH 256
+#define R5C_FULL_STRIPE_FLUSH_BATCH(conf) (conf->max_nr_stripes / 4)
 /* reclaim stripes in groups */
 #define R5C_RECLAIM_STRIPE_GROUP (NR_STRIPE_HASH_LOCKS * 2)
 
@@ -307,8 +308,7 @@ static void __r5l_set_io_unit_state(struct r5l_io_unit *io,
 }
 
 static void
-r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev,
-			      struct bio_list *return_bi)
+r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev)
 {
 	struct bio *wbi, *wbi2;
 
@@ -317,24 +317,21 @@ r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev,
 	while (wbi && wbi->bi_iter.bi_sector <
 	       dev->sector + STRIPE_SECTORS) {
 		wbi2 = r5_next_bio(wbi, dev->sector);
-		if (!raid5_dec_bi_active_stripes(wbi)) {
-			md_write_end(conf->mddev);
-			bio_list_add(return_bi, wbi);
-		}
+		md_write_end(conf->mddev);
+		bio_endio(wbi);
 		wbi = wbi2;
 	}
 }
 
 void r5c_handle_cached_data_endio(struct r5conf *conf,
-	  struct stripe_head *sh, int disks, struct bio_list *return_bi)
+				  struct stripe_head *sh, int disks)
 {
 	int i;
 
 	for (i = sh->disks; i--; ) {
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
-			r5c_return_dev_pending_writes(conf, &sh->dev[i],
-						      return_bi);
+			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
 			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
 					STRIPE_SECTORS,
 					!test_bit(STRIPE_DEGRADED, &sh->state),
@@ -343,6 +340,8 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 	}
 }
 
+void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
+
 /* Check whether we should flush some stripes to free up stripe cache */
 void r5c_check_stripe_cache_usage(struct r5conf *conf)
 {
@@ -381,7 +380,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)
 	 * or a full stripe (chunk size / 4k stripes).
 	 */
 	if (atomic_read(&conf->r5c_cached_full_stripes) >=
-	    min(R5C_FULL_STRIPE_FLUSH_BATCH,
+	    min(R5C_FULL_STRIPE_FLUSH_BATCH(conf),
 		conf->chunk_sectors >> STRIPE_SHIFT))
 		r5l_wake_reclaim(conf->log, 0);
 }
@@ -590,7 +589,7 @@ static void r5l_log_endio(struct bio *bio)
 
 	spin_lock_irqsave(&log->io_list_lock, flags);
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
-	if (log->need_cache_flush)
+	if (log->need_cache_flush && !list_empty(&io->stripe_list))
 		r5l_move_to_end_ios(log);
 	else
 		r5l_log_run_stripes(log);
@@ -618,9 +617,11 @@ static void r5l_log_endio(struct bio *bio)
 			bio_endio(bi);
 			atomic_dec(&io->pending_stripe);
 		}
-		if (atomic_read(&io->pending_stripe) == 0)
-			__r5l_stripe_write_finished(io);
 	}
+
+	/* finish flush only io_unit and PAYLOAD_FLUSH only io_unit */
+	if (atomic_read(&io->pending_stripe) == 0)
+		__r5l_stripe_write_finished(io);
 }
 
 static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io)
@@ -842,6 +843,41 @@ static void r5l_append_payload_page(struct r5l_log *log, struct page *page)
 	r5_reserve_log_entry(log, io);
 }
 
+static void r5l_append_flush_payload(struct r5l_log *log, sector_t sect)
+{
+	struct mddev *mddev = log->rdev->mddev;
+	struct r5conf *conf = mddev->private;
+	struct r5l_io_unit *io;
+	struct r5l_payload_flush *payload;
+	int meta_size;
+
+	/*
+	 * payload_flush requires extra writes to the journal.
+	 * To avoid handling the extra IO in quiesce, just skip
+	 * flush_payload
+	 */
+	if (conf->quiesce)
+		return;
+
+	mutex_lock(&log->io_mutex);
+	meta_size = sizeof(struct r5l_payload_flush) + sizeof(__le64);
+
+	if (r5l_get_meta(log, meta_size)) {
+		mutex_unlock(&log->io_mutex);
+		return;
+	}
+
+	/* current implementation is one stripe per flush payload */
+	io = log->current_io;
+	payload = page_address(io->meta_page) + io->meta_offset;
+	payload->header.type = cpu_to_le16(R5LOG_PAYLOAD_FLUSH);
+	payload->header.flags = cpu_to_le16(0);
+	payload->size = cpu_to_le32(sizeof(__le64));
+	payload->flush_stripes[0] = cpu_to_le64(sect);
+	io->meta_offset += meta_size;
+	mutex_unlock(&log->io_mutex);
+}
+
 static int r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
 			   int data_pages, int parity_pages)
 {
@@ -1393,7 +1429,7 @@ static void r5c_do_reclaim(struct r5conf *conf)
 		stripes_to_flush = R5C_RECLAIM_STRIPE_GROUP;
 	else if (total_cached > conf->min_nr_stripes * 1 / 2 ||
 		 atomic_read(&conf->r5c_cached_full_stripes) - flushing_full >
-		 R5C_FULL_STRIPE_FLUSH_BATCH)
+		 R5C_FULL_STRIPE_FLUSH_BATCH(conf))
 		/*
 		 * if stripe cache pressure moderate, or if there is many full
 		 * stripes,flush all full stripes
@@ -1552,6 +1588,8 @@ bool r5l_log_disk_error(struct r5conf *conf)
 	return ret;
 }
 
+#define R5L_RECOVERY_PAGE_POOL_SIZE 256
+
 struct r5l_recovery_ctx {
 	struct page *meta_page;		/* current meta */
 	sector_t meta_total_blocks;	/* total size of current meta and data */
@@ -1560,18 +1598,131 @@ struct r5l_recovery_ctx {
 	int data_parity_stripes;	/* number of data_parity stripes */
 	int data_only_stripes;		/* number of data_only stripes */
 	struct list_head cached_list;
+
+	/*
+	 * read ahead page pool (ra_pool)
+	 * in recovery, log is read sequentially. It is not efficient to
+	 * read every page with sync_page_io(). The read ahead page pool
+	 * reads multiple pages with one IO, so further log read can
+	 * just copy data from the pool.
+	 */
+	struct page *ra_pool[R5L_RECOVERY_PAGE_POOL_SIZE];
+	sector_t pool_offset;	/* offset of first page in the pool */
+	int total_pages;	/* total allocated pages */
+	int valid_pages;	/* pages with valid data */
+	struct bio *ra_bio;	/* bio to do the read ahead */
 };
 
+static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
+					    struct r5l_recovery_ctx *ctx)
+{
+	struct page *page;
+
+	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, log->bs);
+	if (!ctx->ra_bio)
+		return -ENOMEM;
+
+	ctx->valid_pages = 0;
+	ctx->total_pages = 0;
+	while (ctx->total_pages < R5L_RECOVERY_PAGE_POOL_SIZE) {
+		page = alloc_page(GFP_KERNEL);
+
+		if (!page)
+			break;
+		ctx->ra_pool[ctx->total_pages] = page;
+		ctx->total_pages += 1;
+	}
+
+	if (ctx->total_pages == 0) {
+		bio_put(ctx->ra_bio);
+		return -ENOMEM;
+	}
+
+	ctx->pool_offset = 0;
+	return 0;
+}
+
+static void r5l_recovery_free_ra_pool(struct r5l_log *log,
+					struct r5l_recovery_ctx *ctx)
+{
+	int i;
+
+	for (i = 0; i < ctx->total_pages; ++i)
+		put_page(ctx->ra_pool[i]);
+	bio_put(ctx->ra_bio);
+}
+
+/*
+ * fetch ctx->valid_pages pages from offset
+ * In normal cases, ctx->valid_pages == ctx->total_pages after the call.
+ * However, if the offset is close to the end of the journal device,
+ * ctx->valid_pages could be smaller than ctx->total_pages
+ */
+static int r5l_recovery_fetch_ra_pool(struct r5l_log *log,
+				      struct r5l_recovery_ctx *ctx,
+				      sector_t offset)
+{
+	bio_reset(ctx->ra_bio);
+	ctx->ra_bio->bi_bdev = log->rdev->bdev;
+	bio_set_op_attrs(ctx->ra_bio, REQ_OP_READ, 0);
+	ctx->ra_bio->bi_iter.bi_sector = log->rdev->data_offset + offset;
+
+	ctx->valid_pages = 0;
+	ctx->pool_offset = offset;
+
+	while (ctx->valid_pages < ctx->total_pages) {
+		bio_add_page(ctx->ra_bio,
+			     ctx->ra_pool[ctx->valid_pages], PAGE_SIZE, 0);
+		ctx->valid_pages += 1;
+
+		offset = r5l_ring_add(log, offset, BLOCK_SECTORS);
+
+		if (offset == 0)  /* reached end of the device */
+			break;
+	}
+
+	return submit_bio_wait(ctx->ra_bio);
+}
+
+/*
+ * try read a page from the read ahead page pool, if the page is not in the
+ * pool, call r5l_recovery_fetch_ra_pool
+ */
+static int r5l_recovery_read_page(struct r5l_log *log,
+				  struct r5l_recovery_ctx *ctx,
+				  struct page *page,
+				  sector_t offset)
+{
+	int ret;
+
+	if (offset < ctx->pool_offset ||
+	    offset >= ctx->pool_offset + ctx->valid_pages * BLOCK_SECTORS) {
+		ret = r5l_recovery_fetch_ra_pool(log, ctx, offset);
+		if (ret)
+			return ret;
+	}
+
+	BUG_ON(offset < ctx->pool_offset ||
+	       offset >= ctx->pool_offset + ctx->valid_pages * BLOCK_SECTORS);
+
+	memcpy(page_address(page),
+	       page_address(ctx->ra_pool[(offset - ctx->pool_offset) >>
+					 BLOCK_SECTOR_SHIFT]),
+	       PAGE_SIZE);
+	return 0;
+}
+
 static int r5l_recovery_read_meta_block(struct r5l_log *log,
 					struct r5l_recovery_ctx *ctx)
 {
 	struct page *page = ctx->meta_page;
 	struct r5l_meta_block *mb;
 	u32 crc, stored_crc;
+	int ret;
 
-	if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, REQ_OP_READ, 0,
-			  false))
-		return -EIO;
+	ret = r5l_recovery_read_page(log, ctx, page, ctx->pos);
+	if (ret != 0)
+		return ret;
 
 	mb = page_address(page);
 	stored_crc = le32_to_cpu(mb->checksum);
@@ -1653,8 +1804,7 @@ static void r5l_recovery_load_data(struct r5l_log *log,
 	raid5_compute_sector(conf,
 			     le64_to_cpu(payload->location), 0,
 			     &dd_idx, sh);
-	sync_page_io(log->rdev, log_offset, PAGE_SIZE,
-		     sh->dev[dd_idx].page, REQ_OP_READ, 0, false);
+	r5l_recovery_read_page(log, ctx, sh->dev[dd_idx].page, log_offset);
 	sh->dev[dd_idx].log_checksum =
 		le32_to_cpu(payload->checksum[0]);
 	ctx->meta_total_blocks += BLOCK_SECTORS;
@@ -1673,17 +1823,15 @@ static void r5l_recovery_load_parity(struct r5l_log *log,
 	struct r5conf *conf = mddev->private;
 
 	ctx->meta_total_blocks += BLOCK_SECTORS * conf->max_degraded;
-	sync_page_io(log->rdev, log_offset, PAGE_SIZE,
-		     sh->dev[sh->pd_idx].page, REQ_OP_READ, 0, false);
+	r5l_recovery_read_page(log, ctx, sh->dev[sh->pd_idx].page, log_offset);
 	sh->dev[sh->pd_idx].log_checksum =
 		le32_to_cpu(payload->checksum[0]);
 	set_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags);
 
 	if (sh->qd_idx >= 0) {
-		sync_page_io(log->rdev,
-			     r5l_ring_add(log, log_offset, BLOCK_SECTORS),
-			     PAGE_SIZE, sh->dev[sh->qd_idx].page,
-			     REQ_OP_READ, 0, false);
+		r5l_recovery_read_page(
+			log, ctx, sh->dev[sh->qd_idx].page,
+			r5l_ring_add(log, log_offset, BLOCK_SECTORS));
 		sh->dev[sh->qd_idx].log_checksum =
 			le32_to_cpu(payload->checksum[1]);
 		set_bit(R5_Wantwrite, &sh->dev[sh->qd_idx].flags);
@@ -1814,14 +1962,15 @@ r5c_recovery_replay_stripes(struct list_head *cached_stripe_list,
 
 /* if matches return 0; otherwise return -EINVAL */
 static int
-r5l_recovery_verify_data_checksum(struct r5l_log *log, struct page *page,
+r5l_recovery_verify_data_checksum(struct r5l_log *log,
+				  struct r5l_recovery_ctx *ctx,
+				  struct page *page,
 				  sector_t log_offset, __le32 log_checksum)
 {
 	void *addr;
 	u32 checksum;
 
-	sync_page_io(log->rdev, log_offset, PAGE_SIZE,
-		     page, REQ_OP_READ, 0, false);
+	r5l_recovery_read_page(log, ctx, page, log_offset);
 	addr = kmap_atomic(page);
 	checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
 	kunmap_atomic(addr);
@@ -1843,6 +1992,7 @@ r5l_recovery_verify_data_checksum_for_mb(struct r5l_log *log,
 	sector_t log_offset = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
 	struct page *page;
 	struct r5l_payload_data_parity *payload;
+	struct r5l_payload_flush *payload_flush;
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page)
@@ -1850,33 +2000,42 @@ r5l_recovery_verify_data_checksum_for_mb(struct r5l_log *log,
 
 	while (mb_offset < le32_to_cpu(mb->meta_size)) {
 		payload = (void *)mb + mb_offset;
+		payload_flush = (void *)mb + mb_offset;
 
-		if (payload->header.type == R5LOG_PAYLOAD_DATA) {
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_DATA) {
 			if (r5l_recovery_verify_data_checksum(
-				    log, page, log_offset,
+				    log, ctx, page, log_offset,
 				    payload->checksum[0]) < 0)
 				goto mismatch;
-		} else if (payload->header.type == R5LOG_PAYLOAD_PARITY) {
+		} else if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_PARITY) {
 			if (r5l_recovery_verify_data_checksum(
-				    log, page, log_offset,
+				    log, ctx, page, log_offset,
 				    payload->checksum[0]) < 0)
 				goto mismatch;
 			if (conf->max_degraded == 2 && /* q for RAID 6 */
 			    r5l_recovery_verify_data_checksum(
-				    log, page,
+				    log, ctx, page,
 				    r5l_ring_add(log, log_offset,
 						 BLOCK_SECTORS),
 				    payload->checksum[1]) < 0)
 				goto mismatch;
-		} else /* not R5LOG_PAYLOAD_DATA or R5LOG_PAYLOAD_PARITY */
+		} else if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_FLUSH) {
+			/* nothing to do for R5LOG_PAYLOAD_FLUSH here */
+		} else /* not R5LOG_PAYLOAD_DATA/PARITY/FLUSH */
 			goto mismatch;
 
-		log_offset = r5l_ring_add(log, log_offset,
-					  le32_to_cpu(payload->size));
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_FLUSH) {
+			mb_offset += sizeof(struct r5l_payload_flush) +
+				le32_to_cpu(payload_flush->size);
+		} else {
+			/* DATA or PARITY payload */
+			log_offset = r5l_ring_add(log, log_offset,
+						  le32_to_cpu(payload->size));
+			mb_offset += sizeof(struct r5l_payload_data_parity) +
+				sizeof(__le32) *
+				(le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
+		}
 
-		mb_offset += sizeof(struct r5l_payload_data_parity) +
-			sizeof(__le32) *
-			(le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
 	}
 
 	put_page(page);
@@ -1904,6 +2063,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 	struct r5conf *conf = mddev->private;
 	struct r5l_meta_block *mb;
 	struct r5l_payload_data_parity *payload;
+	struct r5l_payload_flush *payload_flush;
 	int mb_offset;
 	sector_t log_offset;
 	sector_t stripe_sect;
@@ -1929,7 +2089,31 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 		int dd;
 
 		payload = (void *)mb + mb_offset;
-		stripe_sect = (payload->header.type == R5LOG_PAYLOAD_DATA) ?
+		payload_flush = (void *)mb + mb_offset;
+
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_FLUSH) {
+			int i, count;
+
+			count = le32_to_cpu(payload_flush->size) / sizeof(__le64);
+			for (i = 0; i < count; ++i) {
+				stripe_sect = le64_to_cpu(payload_flush->flush_stripes[i]);
+				sh = r5c_recovery_lookup_stripe(cached_stripe_list,
+								stripe_sect);
+				if (sh) {
+					WARN_ON(test_bit(STRIPE_R5C_CACHING, &sh->state));
+					r5l_recovery_reset_stripe(sh);
+					list_del_init(&sh->lru);
+					raid5_release_stripe(sh);
+				}
+			}
+
+			mb_offset += sizeof(struct r5l_payload_flush) +
+				le32_to_cpu(payload_flush->size);
+			continue;
+		}
+
+		/* DATA or PARITY payload */
+		stripe_sect = (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_DATA) ?
 			raid5_compute_sector(
 				conf, le64_to_cpu(payload->location), 0, &dd,
 				NULL)
@@ -1967,7 +2151,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 			list_add_tail(&sh->lru, cached_stripe_list);
 		}
 
-		if (payload->header.type == R5LOG_PAYLOAD_DATA) {
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_DATA) {
 			if (!test_bit(STRIPE_R5C_CACHING, &sh->state) &&
 			    test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags)) {
 				r5l_recovery_replay_one_stripe(conf, sh, ctx);
@@ -1975,7 +2159,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 			}
 			r5l_recovery_load_data(log, sh, ctx, payload,
 					       log_offset);
-		} else if (payload->header.type == R5LOG_PAYLOAD_PARITY)
+		} else if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_PARITY)
 			r5l_recovery_load_parity(log, sh, ctx, payload,
 						 log_offset);
 		else
@@ -2177,7 +2361,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 				payload = (void *)mb + offset;
 				payload->header.type = cpu_to_le16(
 					R5LOG_PAYLOAD_DATA);
-				payload->size = BLOCK_SECTORS;
+				payload->size = cpu_to_le32(BLOCK_SECTORS);
 				payload->location = cpu_to_le64(
 					raid5_compute_blocknr(sh, i, 0));
 				addr = kmap_atomic(dev->page);
@@ -2241,55 +2425,70 @@ static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
 static int r5l_recovery_log(struct r5l_log *log)
 {
 	struct mddev *mddev = log->rdev->mddev;
-	struct r5l_recovery_ctx ctx;
+	struct r5l_recovery_ctx *ctx;
 	int ret;
 	sector_t pos;
 
-	ctx.pos = log->last_checkpoint;
-	ctx.seq = log->last_cp_seq;
-	ctx.meta_page = alloc_page(GFP_KERNEL);
-	ctx.data_only_stripes = 0;
-	ctx.data_parity_stripes = 0;
-	INIT_LIST_HEAD(&ctx.cached_list);
-
-	if (!ctx.meta_page)
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
 		return -ENOMEM;
 
-	ret = r5c_recovery_flush_log(log, &ctx);
-	__free_page(ctx.meta_page);
+	ctx->pos = log->last_checkpoint;
+	ctx->seq = log->last_cp_seq;
+	INIT_LIST_HEAD(&ctx->cached_list);
+	ctx->meta_page = alloc_page(GFP_KERNEL);
 
-	if (ret)
-		return ret;
+	if (!ctx->meta_page) {
+		ret =  -ENOMEM;
+		goto meta_page;
+	}
 
-	pos = ctx.pos;
-	ctx.seq += 10000;
+	if (r5l_recovery_allocate_ra_pool(log, ctx) != 0) {
+		ret = -ENOMEM;
+		goto ra_pool;
+	}
 
+	ret = r5c_recovery_flush_log(log, ctx);
 
-	if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
+	if (ret)
+		goto error;
+
+	pos = ctx->pos;
+	ctx->seq += 10000;
+
+	if ((ctx->data_only_stripes == 0) && (ctx->data_parity_stripes == 0))
 		pr_debug("md/raid:%s: starting from clean shutdown\n",
 			 mdname(mddev));
 	else
 		pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n",
-			 mdname(mddev), ctx.data_only_stripes,
-			 ctx.data_parity_stripes);
-
-	if (ctx.data_only_stripes == 0) {
-		log->next_checkpoint = ctx.pos;
-		r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
-		ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
-	} else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+			 mdname(mddev), ctx->data_only_stripes,
+			 ctx->data_parity_stripes);
+
+	if (ctx->data_only_stripes == 0) {
+		log->next_checkpoint = ctx->pos;
+		r5l_log_write_empty_meta_block(log, ctx->pos, ctx->seq++);
+		ctx->pos = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
+	} else if (r5c_recovery_rewrite_data_only_stripes(log, ctx)) {
 		pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
 		       mdname(mddev));
-		return -EIO;
+		ret =  -EIO;
+		goto error;
 	}
 
-	log->log_start = ctx.pos;
-	log->seq = ctx.seq;
+	log->log_start = ctx->pos;
+	log->seq = ctx->seq;
 	log->last_checkpoint = pos;
 	r5l_write_super(log, pos);
 
-	r5c_recovery_flush_data_only_stripes(log, &ctx);
-	return 0;
+	r5c_recovery_flush_data_only_stripes(log, ctx);
+	ret = 0;
+error:
+	r5l_recovery_free_ra_pool(log, ctx);
+ra_pool:
+	__free_page(ctx->meta_page);
+meta_page:
+	kfree(ctx);
+	return ret;
 }
 
 static void r5l_write_super(struct r5l_log *log, sector_t cp)
@@ -2618,11 +2817,11 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 		atomic_dec(&conf->r5c_flushing_full_stripes);
 		atomic_dec(&conf->r5c_cached_full_stripes);
 	}
+
+	r5l_append_flush_payload(log, sh->sector);
 }
 
-int
-r5c_cache_data(struct r5l_log *log, struct stripe_head *sh,
-	       struct stripe_head_state *s)
+int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
 	int pages = 0;
@@ -2785,6 +2984,10 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 {
 	struct request_queue *q = bdev_get_queue(rdev->bdev);
 	struct r5l_log *log;
+	char b[BDEVNAME_SIZE];
+
+	pr_debug("md/raid:%s: using device %s as journal\n",
+		 mdname(conf->mddev), bdevname(rdev->bdev, b));
 
 	if (PAGE_SIZE != 4096)
 		return -EINVAL;
@@ -2887,8 +3090,13 @@ io_kc:
 	return -EINVAL;
 }
 
-void r5l_exit_log(struct r5l_log *log)
+void r5l_exit_log(struct r5conf *conf)
 {
+	struct r5l_log *log = conf->log;
+
+	conf->log = NULL;
+	synchronize_rcu();
+
 	flush_work(&log->disable_writeback_work);
 	md_unregister_thread(&log->reclaim_thread);
 	mempool_destroy(log->meta_pool);
diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h
new file mode 100644
index 000000000000..27097101ccca
--- /dev/null
+++ b/drivers/md/raid5-log.h
@@ -0,0 +1,115 @@
+#ifndef _RAID5_LOG_H
+#define _RAID5_LOG_H
+
+extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
+extern void r5l_exit_log(struct r5conf *conf);
+extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
+extern void r5l_write_stripe_run(struct r5l_log *log);
+extern void r5l_flush_stripe_to_raid(struct r5l_log *log);
+extern void r5l_stripe_write_finished(struct stripe_head *sh);
+extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio);
+extern void r5l_quiesce(struct r5l_log *log, int state);
+extern bool r5l_log_disk_error(struct r5conf *conf);
+extern bool r5c_is_writeback(struct r5l_log *log);
+extern int
+r5c_try_caching_write(struct r5conf *conf, struct stripe_head *sh,
+		      struct stripe_head_state *s, int disks);
+extern void
+r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh,
+			    struct stripe_head_state *s);
+extern void r5c_release_extra_page(struct stripe_head *sh);
+extern void r5c_use_extra_page(struct stripe_head *sh);
+extern void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
+extern void r5c_handle_cached_data_endio(struct r5conf *conf,
+	struct stripe_head *sh, int disks);
+extern int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh);
+extern void r5c_make_stripe_write_out(struct stripe_head *sh);
+extern void r5c_flush_cache(struct r5conf *conf, int num);
+extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
+extern void r5c_check_cached_full_stripe(struct r5conf *conf);
+extern struct md_sysfs_entry r5c_journal_mode;
+extern void r5c_update_on_rdev_error(struct mddev *mddev);
+extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
+
+extern struct dma_async_tx_descriptor *
+ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu,
+		       struct dma_async_tx_descriptor *tx);
+extern int ppl_init_log(struct r5conf *conf);
+extern void ppl_exit_log(struct r5conf *conf);
+extern int ppl_write_stripe(struct r5conf *conf, struct stripe_head *sh);
+extern void ppl_write_stripe_run(struct r5conf *conf);
+extern void ppl_stripe_write_finished(struct stripe_head *sh);
+extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add);
+
+static inline bool raid5_has_ppl(struct r5conf *conf)
+{
+	return test_bit(MD_HAS_PPL, &conf->mddev->flags);
+}
+
+static inline int log_stripe(struct stripe_head *sh, struct stripe_head_state *s)
+{
+	struct r5conf *conf = sh->raid_conf;
+
+	if (conf->log) {
+		if (!test_bit(STRIPE_R5C_CACHING, &sh->state)) {
+			/* writing out phase */
+			if (s->waiting_extra_page)
+				return 0;
+			return r5l_write_stripe(conf->log, sh);
+		} else if (test_bit(STRIPE_LOG_TRAPPED, &sh->state)) {
+			/* caching phase */
+			return r5c_cache_data(conf->log, sh);
+		}
+	} else if (raid5_has_ppl(conf)) {
+		return ppl_write_stripe(conf, sh);
+	}
+
+	return -EAGAIN;
+}
+
+static inline void log_stripe_write_finished(struct stripe_head *sh)
+{
+	struct r5conf *conf = sh->raid_conf;
+
+	if (conf->log)
+		r5l_stripe_write_finished(sh);
+	else if (raid5_has_ppl(conf))
+		ppl_stripe_write_finished(sh);
+}
+
+static inline void log_write_stripe_run(struct r5conf *conf)
+{
+	if (conf->log)
+		r5l_write_stripe_run(conf->log);
+	else if (raid5_has_ppl(conf))
+		ppl_write_stripe_run(conf);
+}
+
+static inline void log_exit(struct r5conf *conf)
+{
+	if (conf->log)
+		r5l_exit_log(conf);
+	else if (raid5_has_ppl(conf))
+		ppl_exit_log(conf);
+}
+
+static inline int log_init(struct r5conf *conf, struct md_rdev *journal_dev,
+			   bool ppl)
+{
+	if (journal_dev)
+		return r5l_init_log(conf, journal_dev);
+	else if (ppl)
+		return ppl_init_log(conf);
+
+	return 0;
+}
+
+static inline int log_modify(struct r5conf *conf, struct md_rdev *rdev, bool add)
+{
+	if (raid5_has_ppl(conf))
+		return ppl_modify_log(conf, rdev, add);
+
+	return 0;
+}
+
+#endif
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
new file mode 100644
index 000000000000..5d25bebf3328
--- /dev/null
+++ b/drivers/md/raid5-ppl.c
@@ -0,0 +1,1271 @@
+/*
+ * Partial Parity Log for closing the RAID5 write hole
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/crc32c.h>
+#include <linux/flex_array.h>
+#include <linux/async_tx.h>
+#include <linux/raid/md_p.h>
+#include "md.h"
+#include "raid5.h"
+
+/*
+ * PPL consists of a 4KB header (struct ppl_header) and at least 128KB for
+ * partial parity data. The header contains an array of entries
+ * (struct ppl_header_entry) which describe the logged write requests.
+ * Partial parity for the entries comes after the header, written in the same
+ * sequence as the entries:
+ *
+ * Header
+ *   entry0
+ *   ...
+ *   entryN
+ * PP data
+ *   PP for entry0
+ *   ...
+ *   PP for entryN
+ *
+ * An entry describes one or more consecutive stripe_heads, up to a full
+ * stripe. The modifed raid data chunks form an m-by-n matrix, where m is the
+ * number of stripe_heads in the entry and n is the number of modified data
+ * disks. Every stripe_head in the entry must write to the same data disks.
+ * An example of a valid case described by a single entry (writes to the first
+ * stripe of a 4 disk array, 16k chunk size):
+ *
+ * sh->sector   dd0   dd1   dd2    ppl
+ *            +-----+-----+-----+
+ * 0          | --- | --- | --- | +----+
+ * 8          | -W- | -W- | --- | | pp |   data_sector = 8
+ * 16         | -W- | -W- | --- | | pp |   data_size = 3 * 2 * 4k
+ * 24         | -W- | -W- | --- | | pp |   pp_size = 3 * 4k
+ *            +-----+-----+-----+ +----+
+ *
+ * data_sector is the first raid sector of the modified data, data_size is the
+ * total size of modified data and pp_size is the size of partial parity for
+ * this entry. Entries for full stripe writes contain no partial parity
+ * (pp_size = 0), they only mark the stripes for which parity should be
+ * recalculated after an unclean shutdown. Every entry holds a checksum of its
+ * partial parity, the header also has a checksum of the header itself.
+ *
+ * A write request is always logged to the PPL instance stored on the parity
+ * disk of the corresponding stripe. For each member disk there is one ppl_log
+ * used to handle logging for this disk, independently from others. They are
+ * grouped in child_logs array in struct ppl_conf, which is assigned to
+ * r5conf->log_private.
+ *
+ * ppl_io_unit represents a full PPL write, header_page contains the ppl_header.
+ * PPL entries for logged stripes are added in ppl_log_stripe(). A stripe_head
+ * can be appended to the last entry if it meets the conditions for a valid
+ * entry described above, otherwise a new entry is added. Checksums of entries
+ * are calculated incrementally as stripes containing partial parity are being
+ * added. ppl_submit_iounit() calculates the checksum of the header and submits
+ * a bio containing the header page and partial parity pages (sh->ppl_page) for
+ * all stripes of the io_unit. When the PPL write completes, the stripes
+ * associated with the io_unit are released and raid5d starts writing their data
+ * and parity. When all stripes are written, the io_unit is freed and the next
+ * can be submitted.
+ *
+ * An io_unit is used to gather stripes until it is submitted or becomes full
+ * (if the maximum number of entries or size of PPL is reached). Another io_unit
+ * can't be submitted until the previous has completed (PPL and stripe
+ * data+parity is written). The log->io_list tracks all io_units of a log
+ * (for a single member disk). New io_units are added to the end of the list
+ * and the first io_unit is submitted, if it is not submitted already.
+ * The current io_unit accepting new stripes is always at the end of the list.
+ */
+
+struct ppl_conf {
+	struct mddev *mddev;
+
+	/* array of child logs, one for each raid disk */
+	struct ppl_log *child_logs;
+	int count;
+
+	int block_size;		/* the logical block size used for data_sector
+				 * in ppl_header_entry */
+	u32 signature;		/* raid array identifier */
+	atomic64_t seq;		/* current log write sequence number */
+
+	struct kmem_cache *io_kc;
+	mempool_t *io_pool;
+	struct bio_set *bs;
+
+	/* used only for recovery */
+	int recovered_entries;
+	int mismatch_count;
+
+	/* stripes to retry if failed to allocate io_unit */
+	struct list_head no_mem_stripes;
+	spinlock_t no_mem_stripes_lock;
+};
+
+struct ppl_log {
+	struct ppl_conf *ppl_conf;	/* shared between all log instances */
+
+	struct md_rdev *rdev;		/* array member disk associated with
+					 * this log instance */
+	struct mutex io_mutex;
+	struct ppl_io_unit *current_io;	/* current io_unit accepting new data
+					 * always at the end of io_list */
+	spinlock_t io_list_lock;
+	struct list_head io_list;	/* all io_units of this log */
+};
+
+#define PPL_IO_INLINE_BVECS 32
+
+struct ppl_io_unit {
+	struct ppl_log *log;
+
+	struct page *header_page;	/* for ppl_header */
+
+	unsigned int entries_count;	/* number of entries in ppl_header */
+	unsigned int pp_size;		/* total size current of partial parity */
+
+	u64 seq;			/* sequence number of this log write */
+	struct list_head log_sibling;	/* log->io_list */
+
+	struct list_head stripe_list;	/* stripes added to the io_unit */
+	atomic_t pending_stripes;	/* how many stripes not written to raid */
+
+	bool submitted;			/* true if write to log started */
+
+	/* inline bio and its biovec for submitting the iounit */
+	struct bio bio;
+	struct bio_vec biovec[PPL_IO_INLINE_BVECS];
+};
+
+struct dma_async_tx_descriptor *
+ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu,
+		       struct dma_async_tx_descriptor *tx)
+{
+	int disks = sh->disks;
+	struct page **srcs = flex_array_get(percpu->scribble, 0);
+	int count = 0, pd_idx = sh->pd_idx, i;
+	struct async_submit_ctl submit;
+
+	pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
+
+	/*
+	 * Partial parity is the XOR of stripe data chunks that are not changed
+	 * during the write request. Depending on available data
+	 * (read-modify-write vs. reconstruct-write case) we calculate it
+	 * differently.
+	 */
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
+		/*
+		 * rmw: xor old data and parity from updated disks
+		 * This is calculated earlier by ops_run_prexor5() so just copy
+		 * the parity dev page.
+		 */
+		srcs[count++] = sh->dev[pd_idx].page;
+	} else if (sh->reconstruct_state == reconstruct_state_drain_run) {
+		/* rcw: xor data from all not updated disks */
+		for (i = disks; i--;) {
+			struct r5dev *dev = &sh->dev[i];
+			if (test_bit(R5_UPTODATE, &dev->flags))
+				srcs[count++] = dev->page;
+		}
+	} else {
+		return tx;
+	}
+
+	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, tx,
+			  NULL, sh, flex_array_get(percpu->scribble, 0)
+			  + sizeof(struct page *) * (sh->disks + 2));
+
+	if (count == 1)
+		tx = async_memcpy(sh->ppl_page, srcs[0], 0, 0, PAGE_SIZE,
+				  &submit);
+	else
+		tx = async_xor(sh->ppl_page, srcs, 0, count, PAGE_SIZE,
+			       &submit);
+
+	return tx;
+}
+
+static void *ppl_io_pool_alloc(gfp_t gfp_mask, void *pool_data)
+{
+	struct kmem_cache *kc = pool_data;
+	struct ppl_io_unit *io;
+
+	io = kmem_cache_alloc(kc, gfp_mask);
+	if (!io)
+		return NULL;
+
+	io->header_page = alloc_page(gfp_mask);
+	if (!io->header_page) {
+		kmem_cache_free(kc, io);
+		return NULL;
+	}
+
+	return io;
+}
+
+static void ppl_io_pool_free(void *element, void *pool_data)
+{
+	struct kmem_cache *kc = pool_data;
+	struct ppl_io_unit *io = element;
+
+	__free_page(io->header_page);
+	kmem_cache_free(kc, io);
+}
+
+static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
+					  struct stripe_head *sh)
+{
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct ppl_io_unit *io;
+	struct ppl_header *pplhdr;
+	struct page *header_page;
+
+	io = mempool_alloc(ppl_conf->io_pool, GFP_NOWAIT);
+	if (!io)
+		return NULL;
+
+	header_page = io->header_page;
+	memset(io, 0, sizeof(*io));
+	io->header_page = header_page;
+
+	io->log = log;
+	INIT_LIST_HEAD(&io->log_sibling);
+	INIT_LIST_HEAD(&io->stripe_list);
+	atomic_set(&io->pending_stripes, 0);
+	bio_init(&io->bio, io->biovec, PPL_IO_INLINE_BVECS);
+
+	pplhdr = page_address(io->header_page);
+	clear_page(pplhdr);
+	memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED);
+	pplhdr->signature = cpu_to_le32(ppl_conf->signature);
+
+	io->seq = atomic64_add_return(1, &ppl_conf->seq);
+	pplhdr->generation = cpu_to_le64(io->seq);
+
+	return io;
+}
+
+static int ppl_log_stripe(struct ppl_log *log, struct stripe_head *sh)
+{
+	struct ppl_io_unit *io = log->current_io;
+	struct ppl_header_entry *e = NULL;
+	struct ppl_header *pplhdr;
+	int i;
+	sector_t data_sector = 0;
+	int data_disks = 0;
+	unsigned int entry_space = (log->rdev->ppl.size << 9) - PPL_HEADER_SIZE;
+	struct r5conf *conf = sh->raid_conf;
+
+	pr_debug("%s: stripe: %llu\n", __func__, (unsigned long long)sh->sector);
+
+	/* check if current io_unit is full */
+	if (io && (io->pp_size == entry_space ||
+		   io->entries_count == PPL_HDR_MAX_ENTRIES)) {
+		pr_debug("%s: add io_unit blocked by seq: %llu\n",
+			 __func__, io->seq);
+		io = NULL;
+	}
+
+	/* add a new unit if there is none or the current is full */
+	if (!io) {
+		io = ppl_new_iounit(log, sh);
+		if (!io)
+			return -ENOMEM;
+		spin_lock_irq(&log->io_list_lock);
+		list_add_tail(&io->log_sibling, &log->io_list);
+		spin_unlock_irq(&log->io_list_lock);
+
+		log->current_io = io;
+	}
+
+	for (i = 0; i < sh->disks; i++) {
+		struct r5dev *dev = &sh->dev[i];
+
+		if (i != sh->pd_idx && test_bit(R5_Wantwrite, &dev->flags)) {
+			if (!data_disks || dev->sector < data_sector)
+				data_sector = dev->sector;
+			data_disks++;
+		}
+	}
+	BUG_ON(!data_disks);
+
+	pr_debug("%s: seq: %llu data_sector: %llu data_disks: %d\n", __func__,
+		 io->seq, (unsigned long long)data_sector, data_disks);
+
+	pplhdr = page_address(io->header_page);
+
+	if (io->entries_count > 0) {
+		struct ppl_header_entry *last =
+				&pplhdr->entries[io->entries_count - 1];
+		struct stripe_head *sh_last = list_last_entry(
+				&io->stripe_list, struct stripe_head, log_list);
+		u64 data_sector_last = le64_to_cpu(last->data_sector);
+		u32 data_size_last = le32_to_cpu(last->data_size);
+
+		/*
+		 * Check if we can append the stripe to the last entry. It must
+		 * be just after the last logged stripe and write to the same
+		 * disks. Use bit shift and logarithm to avoid 64-bit division.
+		 */
+		if ((sh->sector == sh_last->sector + STRIPE_SECTORS) &&
+		    (data_sector >> ilog2(conf->chunk_sectors) ==
+		     data_sector_last >> ilog2(conf->chunk_sectors)) &&
+		    ((data_sector - data_sector_last) * data_disks ==
+		     data_size_last >> 9))
+			e = last;
+	}
+
+	if (!e) {
+		e = &pplhdr->entries[io->entries_count++];
+		e->data_sector = cpu_to_le64(data_sector);
+		e->parity_disk = cpu_to_le32(sh->pd_idx);
+		e->checksum = cpu_to_le32(~0);
+	}
+
+	le32_add_cpu(&e->data_size, data_disks << PAGE_SHIFT);
+
+	/* don't write any PP if full stripe write */
+	if (!test_bit(STRIPE_FULL_WRITE, &sh->state)) {
+		le32_add_cpu(&e->pp_size, PAGE_SIZE);
+		io->pp_size += PAGE_SIZE;
+		e->checksum = cpu_to_le32(crc32c_le(le32_to_cpu(e->checksum),
+						    page_address(sh->ppl_page),
+						    PAGE_SIZE));
+	}
+
+	list_add_tail(&sh->log_list, &io->stripe_list);
+	atomic_inc(&io->pending_stripes);
+	sh->ppl_io = io;
+
+	return 0;
+}
+
+int ppl_write_stripe(struct r5conf *conf, struct stripe_head *sh)
+{
+	struct ppl_conf *ppl_conf = conf->log_private;
+	struct ppl_io_unit *io = sh->ppl_io;
+	struct ppl_log *log;
+
+	if (io || test_bit(STRIPE_SYNCING, &sh->state) || !sh->ppl_page ||
+	    !test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags) ||
+	    !test_bit(R5_Insync, &sh->dev[sh->pd_idx].flags)) {
+		clear_bit(STRIPE_LOG_TRAPPED, &sh->state);
+		return -EAGAIN;
+	}
+
+	log = &ppl_conf->child_logs[sh->pd_idx];
+
+	mutex_lock(&log->io_mutex);
+
+	if (!log->rdev || test_bit(Faulty, &log->rdev->flags)) {
+		mutex_unlock(&log->io_mutex);
+		return -EAGAIN;
+	}
+
+	set_bit(STRIPE_LOG_TRAPPED, &sh->state);
+	clear_bit(STRIPE_DELAYED, &sh->state);
+	atomic_inc(&sh->count);
+
+	if (ppl_log_stripe(log, sh)) {
+		spin_lock_irq(&ppl_conf->no_mem_stripes_lock);
+		list_add_tail(&sh->log_list, &ppl_conf->no_mem_stripes);
+		spin_unlock_irq(&ppl_conf->no_mem_stripes_lock);
+	}
+
+	mutex_unlock(&log->io_mutex);
+
+	return 0;
+}
+
+static void ppl_log_endio(struct bio *bio)
+{
+	struct ppl_io_unit *io = bio->bi_private;
+	struct ppl_log *log = io->log;
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct stripe_head *sh, *next;
+
+	pr_debug("%s: seq: %llu\n", __func__, io->seq);
+
+	if (bio->bi_error)
+		md_error(ppl_conf->mddev, log->rdev);
+
+	list_for_each_entry_safe(sh, next, &io->stripe_list, log_list) {
+		list_del_init(&sh->log_list);
+
+		set_bit(STRIPE_HANDLE, &sh->state);
+		raid5_release_stripe(sh);
+	}
+}
+
+static void ppl_submit_iounit_bio(struct ppl_io_unit *io, struct bio *bio)
+{
+	char b[BDEVNAME_SIZE];
+
+	pr_debug("%s: seq: %llu size: %u sector: %llu dev: %s\n",
+		 __func__, io->seq, bio->bi_iter.bi_size,
+		 (unsigned long long)bio->bi_iter.bi_sector,
+		 bdevname(bio->bi_bdev, b));
+
+	submit_bio(bio);
+}
+
+static void ppl_submit_iounit(struct ppl_io_unit *io)
+{
+	struct ppl_log *log = io->log;
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct ppl_header *pplhdr = page_address(io->header_page);
+	struct bio *bio = &io->bio;
+	struct stripe_head *sh;
+	int i;
+
+	bio->bi_private = io;
+
+	if (!log->rdev || test_bit(Faulty, &log->rdev->flags)) {
+		ppl_log_endio(bio);
+		return;
+	}
+
+	for (i = 0; i < io->entries_count; i++) {
+		struct ppl_header_entry *e = &pplhdr->entries[i];
+
+		pr_debug("%s: seq: %llu entry: %d data_sector: %llu pp_size: %u data_size: %u\n",
+			 __func__, io->seq, i, le64_to_cpu(e->data_sector),
+			 le32_to_cpu(e->pp_size), le32_to_cpu(e->data_size));
+
+		e->data_sector = cpu_to_le64(le64_to_cpu(e->data_sector) >>
+					     ilog2(ppl_conf->block_size >> 9));
+		e->checksum = cpu_to_le32(~le32_to_cpu(e->checksum));
+	}
+
+	pplhdr->entries_count = cpu_to_le32(io->entries_count);
+	pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PPL_HEADER_SIZE));
+
+	bio->bi_end_io = ppl_log_endio;
+	bio->bi_opf = REQ_OP_WRITE | REQ_FUA;
+	bio->bi_bdev = log->rdev->bdev;
+	bio->bi_iter.bi_sector = log->rdev->ppl.sector;
+	bio_add_page(bio, io->header_page, PAGE_SIZE, 0);
+
+	list_for_each_entry(sh, &io->stripe_list, log_list) {
+		/* entries for full stripe writes have no partial parity */
+		if (test_bit(STRIPE_FULL_WRITE, &sh->state))
+			continue;
+
+		if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
+			struct bio *prev = bio;
+
+			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
+					       ppl_conf->bs);
+			bio->bi_opf = prev->bi_opf;
+			bio->bi_bdev = prev->bi_bdev;
+			bio->bi_iter.bi_sector = bio_end_sector(prev);
+			bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0);
+
+			bio_chain(bio, prev);
+			ppl_submit_iounit_bio(io, prev);
+		}
+	}
+
+	ppl_submit_iounit_bio(io, bio);
+}
+
+static void ppl_submit_current_io(struct ppl_log *log)
+{
+	struct ppl_io_unit *io;
+
+	spin_lock_irq(&log->io_list_lock);
+
+	io = list_first_entry_or_null(&log->io_list, struct ppl_io_unit,
+				      log_sibling);
+	if (io && io->submitted)
+		io = NULL;
+
+	spin_unlock_irq(&log->io_list_lock);
+
+	if (io) {
+		io->submitted = true;
+
+		if (io == log->current_io)
+			log->current_io = NULL;
+
+		ppl_submit_iounit(io);
+	}
+}
+
+void ppl_write_stripe_run(struct r5conf *conf)
+{
+	struct ppl_conf *ppl_conf = conf->log_private;
+	struct ppl_log *log;
+	int i;
+
+	for (i = 0; i < ppl_conf->count; i++) {
+		log = &ppl_conf->child_logs[i];
+
+		mutex_lock(&log->io_mutex);
+		ppl_submit_current_io(log);
+		mutex_unlock(&log->io_mutex);
+	}
+}
+
+static void ppl_io_unit_finished(struct ppl_io_unit *io)
+{
+	struct ppl_log *log = io->log;
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	unsigned long flags;
+
+	pr_debug("%s: seq: %llu\n", __func__, io->seq);
+
+	local_irq_save(flags);
+
+	spin_lock(&log->io_list_lock);
+	list_del(&io->log_sibling);
+	spin_unlock(&log->io_list_lock);
+
+	mempool_free(io, ppl_conf->io_pool);
+
+	spin_lock(&ppl_conf->no_mem_stripes_lock);
+	if (!list_empty(&ppl_conf->no_mem_stripes)) {
+		struct stripe_head *sh;
+
+		sh = list_first_entry(&ppl_conf->no_mem_stripes,
+				      struct stripe_head, log_list);
+		list_del_init(&sh->log_list);
+		set_bit(STRIPE_HANDLE, &sh->state);
+		raid5_release_stripe(sh);
+	}
+	spin_unlock(&ppl_conf->no_mem_stripes_lock);
+
+	local_irq_restore(flags);
+}
+
+void ppl_stripe_write_finished(struct stripe_head *sh)
+{
+	struct ppl_io_unit *io;
+
+	io = sh->ppl_io;
+	sh->ppl_io = NULL;
+
+	if (io && atomic_dec_and_test(&io->pending_stripes))
+		ppl_io_unit_finished(io);
+}
+
+static void ppl_xor(int size, struct page *page1, struct page *page2)
+{
+	struct async_submit_ctl submit;
+	struct dma_async_tx_descriptor *tx;
+	struct page *xor_srcs[] = { page1, page2 };
+
+	init_async_submit(&submit, ASYNC_TX_ACK|ASYNC_TX_XOR_DROP_DST,
+			  NULL, NULL, NULL, NULL);
+	tx = async_xor(page1, xor_srcs, 0, 2, size, &submit);
+
+	async_tx_quiesce(&tx);
+}
+
+/*
+ * PPL recovery strategy: xor partial parity and data from all modified data
+ * disks within a stripe and write the result as the new stripe parity. If all
+ * stripe data disks are modified (full stripe write), no partial parity is
+ * available, so just xor the data disks.
+ *
+ * Recovery of a PPL entry shall occur only if all modified data disks are
+ * available and read from all of them succeeds.
+ *
+ * A PPL entry applies to a stripe, partial parity size for an entry is at most
+ * the size of the chunk. Examples of possible cases for a single entry:
+ *
+ * case 0: single data disk write:
+ *   data0    data1    data2     ppl        parity
+ * +--------+--------+--------+           +--------------------+
+ * | ------ | ------ | ------ | +----+    | (no change)        |
+ * | ------ | -data- | ------ | | pp | -> | data1 ^ pp         |
+ * | ------ | -data- | ------ | | pp | -> | data1 ^ pp         |
+ * | ------ | ------ | ------ | +----+    | (no change)        |
+ * +--------+--------+--------+           +--------------------+
+ * pp_size = data_size
+ *
+ * case 1: more than one data disk write:
+ *   data0    data1    data2     ppl        parity
+ * +--------+--------+--------+           +--------------------+
+ * | ------ | ------ | ------ | +----+    | (no change)        |
+ * | -data- | -data- | ------ | | pp | -> | data0 ^ data1 ^ pp |
+ * | -data- | -data- | ------ | | pp | -> | data0 ^ data1 ^ pp |
+ * | ------ | ------ | ------ | +----+    | (no change)        |
+ * +--------+--------+--------+           +--------------------+
+ * pp_size = data_size / modified_data_disks
+ *
+ * case 2: write to all data disks (also full stripe write):
+ *   data0    data1    data2                parity
+ * +--------+--------+--------+           +--------------------+
+ * | ------ | ------ | ------ |           | (no change)        |
+ * | -data- | -data- | -data- | --------> | xor all data       |
+ * | ------ | ------ | ------ | --------> | (no change)        |
+ * | ------ | ------ | ------ |           | (no change)        |
+ * +--------+--------+--------+           +--------------------+
+ * pp_size = 0
+ *
+ * The following cases are possible only in other implementations. The recovery
+ * code can handle them, but they are not generated at runtime because they can
+ * be reduced to cases 0, 1 and 2:
+ *
+ * case 3:
+ *   data0    data1    data2     ppl        parity
+ * +--------+--------+--------+ +----+    +--------------------+
+ * | ------ | -data- | -data- | | pp |    | data1 ^ data2 ^ pp |
+ * | ------ | -data- | -data- | | pp | -> | data1 ^ data2 ^ pp |
+ * | -data- | -data- | -data- | | -- | -> | xor all data       |
+ * | -data- | -data- | ------ | | pp |    | data0 ^ data1 ^ pp |
+ * +--------+--------+--------+ +----+    +--------------------+
+ * pp_size = chunk_size
+ *
+ * case 4:
+ *   data0    data1    data2     ppl        parity
+ * +--------+--------+--------+ +----+    +--------------------+
+ * | ------ | -data- | ------ | | pp |    | data1 ^ pp         |
+ * | ------ | ------ | ------ | | -- | -> | (no change)        |
+ * | ------ | ------ | ------ | | -- | -> | (no change)        |
+ * | -data- | ------ | ------ | | pp |    | data0 ^ pp         |
+ * +--------+--------+--------+ +----+    +--------------------+
+ * pp_size = chunk_size
+ */
+static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
+			     sector_t ppl_sector)
+{
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct mddev *mddev = ppl_conf->mddev;
+	struct r5conf *conf = mddev->private;
+	int block_size = ppl_conf->block_size;
+	struct page *page1;
+	struct page *page2;
+	sector_t r_sector_first;
+	sector_t r_sector_last;
+	int strip_sectors;
+	int data_disks;
+	int i;
+	int ret = 0;
+	char b[BDEVNAME_SIZE];
+	unsigned int pp_size = le32_to_cpu(e->pp_size);
+	unsigned int data_size = le32_to_cpu(e->data_size);
+
+	page1 = alloc_page(GFP_KERNEL);
+	page2 = alloc_page(GFP_KERNEL);
+
+	if (!page1 || !page2) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	r_sector_first = le64_to_cpu(e->data_sector) * (block_size >> 9);
+
+	if ((pp_size >> 9) < conf->chunk_sectors) {
+		if (pp_size > 0) {
+			data_disks = data_size / pp_size;
+			strip_sectors = pp_size >> 9;
+		} else {
+			data_disks = conf->raid_disks - conf->max_degraded;
+			strip_sectors = (data_size >> 9) / data_disks;
+		}
+		r_sector_last = r_sector_first +
+				(data_disks - 1) * conf->chunk_sectors +
+				strip_sectors;
+	} else {
+		data_disks = conf->raid_disks - conf->max_degraded;
+		strip_sectors = conf->chunk_sectors;
+		r_sector_last = r_sector_first + (data_size >> 9);
+	}
+
+	pr_debug("%s: array sector first: %llu last: %llu\n", __func__,
+		 (unsigned long long)r_sector_first,
+		 (unsigned long long)r_sector_last);
+
+	/* if start and end is 4k aligned, use a 4k block */
+	if (block_size == 512 &&
+	    (r_sector_first & (STRIPE_SECTORS - 1)) == 0 &&
+	    (r_sector_last & (STRIPE_SECTORS - 1)) == 0)
+		block_size = STRIPE_SIZE;
+
+	/* iterate through blocks in strip */
+	for (i = 0; i < strip_sectors; i += (block_size >> 9)) {
+		bool update_parity = false;
+		sector_t parity_sector;
+		struct md_rdev *parity_rdev;
+		struct stripe_head sh;
+		int disk;
+		int indent = 0;
+
+		pr_debug("%s:%*s iter %d start\n", __func__, indent, "", i);
+		indent += 2;
+
+		memset(page_address(page1), 0, PAGE_SIZE);
+
+		/* iterate through data member disks */
+		for (disk = 0; disk < data_disks; disk++) {
+			int dd_idx;
+			struct md_rdev *rdev;
+			sector_t sector;
+			sector_t r_sector = r_sector_first + i +
+					    (disk * conf->chunk_sectors);
+
+			pr_debug("%s:%*s data member disk %d start\n",
+				 __func__, indent, "", disk);
+			indent += 2;
+
+			if (r_sector >= r_sector_last) {
+				pr_debug("%s:%*s array sector %llu doesn't need parity update\n",
+					 __func__, indent, "",
+					 (unsigned long long)r_sector);
+				indent -= 2;
+				continue;
+			}
+
+			update_parity = true;
+
+			/* map raid sector to member disk */
+			sector = raid5_compute_sector(conf, r_sector, 0,
+						      &dd_idx, NULL);
+			pr_debug("%s:%*s processing array sector %llu => data member disk %d, sector %llu\n",
+				 __func__, indent, "",
+				 (unsigned long long)r_sector, dd_idx,
+				 (unsigned long long)sector);
+
+			rdev = conf->disks[dd_idx].rdev;
+			if (!rdev) {
+				pr_debug("%s:%*s data member disk %d missing\n",
+					 __func__, indent, "", dd_idx);
+				update_parity = false;
+				break;
+			}
+
+			pr_debug("%s:%*s reading data member disk %s sector %llu\n",
+				 __func__, indent, "", bdevname(rdev->bdev, b),
+				 (unsigned long long)sector);
+			if (!sync_page_io(rdev, sector, block_size, page2,
+					REQ_OP_READ, 0, false)) {
+				md_error(mddev, rdev);
+				pr_debug("%s:%*s read failed!\n", __func__,
+					 indent, "");
+				ret = -EIO;
+				goto out;
+			}
+
+			ppl_xor(block_size, page1, page2);
+
+			indent -= 2;
+		}
+
+		if (!update_parity)
+			continue;
+
+		if (pp_size > 0) {
+			pr_debug("%s:%*s reading pp disk sector %llu\n",
+				 __func__, indent, "",
+				 (unsigned long long)(ppl_sector + i));
+			if (!sync_page_io(log->rdev,
+					ppl_sector - log->rdev->data_offset + i,
+					block_size, page2, REQ_OP_READ, 0,
+					false)) {
+				pr_debug("%s:%*s read failed!\n", __func__,
+					 indent, "");
+				md_error(mddev, log->rdev);
+				ret = -EIO;
+				goto out;
+			}
+
+			ppl_xor(block_size, page1, page2);
+		}
+
+		/* map raid sector to parity disk */
+		parity_sector = raid5_compute_sector(conf, r_sector_first + i,
+				0, &disk, &sh);
+		BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
+		parity_rdev = conf->disks[sh.pd_idx].rdev;
+
+		BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
+		pr_debug("%s:%*s write parity at sector %llu, disk %s\n",
+			 __func__, indent, "",
+			 (unsigned long long)parity_sector,
+			 bdevname(parity_rdev->bdev, b));
+		if (!sync_page_io(parity_rdev, parity_sector, block_size,
+				page1, REQ_OP_WRITE, 0, false)) {
+			pr_debug("%s:%*s parity write error!\n", __func__,
+				 indent, "");
+			md_error(mddev, parity_rdev);
+			ret = -EIO;
+			goto out;
+		}
+	}
+out:
+	if (page1)
+		__free_page(page1);
+	if (page2)
+		__free_page(page2);
+	return ret;
+}
+
+static int ppl_recover(struct ppl_log *log, struct ppl_header *pplhdr)
+{
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct md_rdev *rdev = log->rdev;
+	struct mddev *mddev = rdev->mddev;
+	sector_t ppl_sector = rdev->ppl.sector + (PPL_HEADER_SIZE >> 9);
+	struct page *page;
+	int i;
+	int ret = 0;
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	/* iterate through all PPL entries saved */
+	for (i = 0; i < le32_to_cpu(pplhdr->entries_count); i++) {
+		struct ppl_header_entry *e = &pplhdr->entries[i];
+		u32 pp_size = le32_to_cpu(e->pp_size);
+		sector_t sector = ppl_sector;
+		int ppl_entry_sectors = pp_size >> 9;
+		u32 crc, crc_stored;
+
+		pr_debug("%s: disk: %d entry: %d ppl_sector: %llu pp_size: %u\n",
+			 __func__, rdev->raid_disk, i,
+			 (unsigned long long)ppl_sector, pp_size);
+
+		crc = ~0;
+		crc_stored = le32_to_cpu(e->checksum);
+
+		/* read parial parity for this entry and calculate its checksum */
+		while (pp_size) {
+			int s = pp_size > PAGE_SIZE ? PAGE_SIZE : pp_size;
+
+			if (!sync_page_io(rdev, sector - rdev->data_offset,
+					s, page, REQ_OP_READ, 0, false)) {
+				md_error(mddev, rdev);
+				ret = -EIO;
+				goto out;
+			}
+
+			crc = crc32c_le(crc, page_address(page), s);
+
+			pp_size -= s;
+			sector += s >> 9;
+		}
+
+		crc = ~crc;
+
+		if (crc != crc_stored) {
+			/*
+			 * Don't recover this entry if the checksum does not
+			 * match, but keep going and try to recover other
+			 * entries.
+			 */
+			pr_debug("%s: ppl entry crc does not match: stored: 0x%x calculated: 0x%x\n",
+				 __func__, crc_stored, crc);
+			ppl_conf->mismatch_count++;
+		} else {
+			ret = ppl_recover_entry(log, e, ppl_sector);
+			if (ret)
+				goto out;
+			ppl_conf->recovered_entries++;
+		}
+
+		ppl_sector += ppl_entry_sectors;
+	}
+
+	/* flush the disk cache after recovery if necessary */
+	ret = blkdev_issue_flush(rdev->bdev, GFP_KERNEL, NULL);
+out:
+	__free_page(page);
+	return ret;
+}
+
+static int ppl_write_empty_header(struct ppl_log *log)
+{
+	struct page *page;
+	struct ppl_header *pplhdr;
+	struct md_rdev *rdev = log->rdev;
+	int ret = 0;
+
+	pr_debug("%s: disk: %d ppl_sector: %llu\n", __func__,
+		 rdev->raid_disk, (unsigned long long)rdev->ppl.sector);
+
+	page = alloc_page(GFP_NOIO | __GFP_ZERO);
+	if (!page)
+		return -ENOMEM;
+
+	pplhdr = page_address(page);
+	memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED);
+	pplhdr->signature = cpu_to_le32(log->ppl_conf->signature);
+	pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PAGE_SIZE));
+
+	if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
+			  PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_FUA, 0,
+			  false)) {
+		md_error(rdev->mddev, rdev);
+		ret = -EIO;
+	}
+
+	__free_page(page);
+	return ret;
+}
+
+static int ppl_load_distributed(struct ppl_log *log)
+{
+	struct ppl_conf *ppl_conf = log->ppl_conf;
+	struct md_rdev *rdev = log->rdev;
+	struct mddev *mddev = rdev->mddev;
+	struct page *page;
+	struct ppl_header *pplhdr;
+	u32 crc, crc_stored;
+	u32 signature;
+	int ret = 0;
+
+	pr_debug("%s: disk: %d\n", __func__, rdev->raid_disk);
+
+	/* read PPL header */
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
+			  PAGE_SIZE, page, REQ_OP_READ, 0, false)) {
+		md_error(mddev, rdev);
+		ret = -EIO;
+		goto out;
+	}
+	pplhdr = page_address(page);
+
+	/* check header validity */
+	crc_stored = le32_to_cpu(pplhdr->checksum);
+	pplhdr->checksum = 0;
+	crc = ~crc32c_le(~0, pplhdr, PAGE_SIZE);
+
+	if (crc_stored != crc) {
+		pr_debug("%s: ppl header crc does not match: stored: 0x%x calculated: 0x%x\n",
+			 __func__, crc_stored, crc);
+		ppl_conf->mismatch_count++;
+		goto out;
+	}
+
+	signature = le32_to_cpu(pplhdr->signature);
+
+	if (mddev->external) {
+		/*
+		 * For external metadata the header signature is set and
+		 * validated in userspace.
+		 */
+		ppl_conf->signature = signature;
+	} else if (ppl_conf->signature != signature) {
+		pr_debug("%s: ppl header signature does not match: stored: 0x%x configured: 0x%x\n",
+			 __func__, signature, ppl_conf->signature);
+		ppl_conf->mismatch_count++;
+		goto out;
+	}
+
+	/* attempt to recover from log if we are starting a dirty array */
+	if (!mddev->pers && mddev->recovery_cp != MaxSector)
+		ret = ppl_recover(log, pplhdr);
+out:
+	/* write empty header if we are starting the array */
+	if (!ret && !mddev->pers)
+		ret = ppl_write_empty_header(log);
+
+	__free_page(page);
+
+	pr_debug("%s: return: %d mismatch_count: %d recovered_entries: %d\n",
+		 __func__, ret, ppl_conf->mismatch_count,
+		 ppl_conf->recovered_entries);
+	return ret;
+}
+
+static int ppl_load(struct ppl_conf *ppl_conf)
+{
+	int ret = 0;
+	u32 signature = 0;
+	bool signature_set = false;
+	int i;
+
+	for (i = 0; i < ppl_conf->count; i++) {
+		struct ppl_log *log = &ppl_conf->child_logs[i];
+
+		/* skip missing drive */
+		if (!log->rdev)
+			continue;
+
+		ret = ppl_load_distributed(log);
+		if (ret)
+			break;
+
+		/*
+		 * For external metadata we can't check if the signature is
+		 * correct on a single drive, but we can check if it is the same
+		 * on all drives.
+		 */
+		if (ppl_conf->mddev->external) {
+			if (!signature_set) {
+				signature = ppl_conf->signature;
+				signature_set = true;
+			} else if (signature != ppl_conf->signature) {
+				pr_warn("md/raid:%s: PPL header signature does not match on all member drives\n",
+					mdname(ppl_conf->mddev));
+				ret = -EINVAL;
+				break;
+			}
+		}
+	}
+
+	pr_debug("%s: return: %d mismatch_count: %d recovered_entries: %d\n",
+		 __func__, ret, ppl_conf->mismatch_count,
+		 ppl_conf->recovered_entries);
+	return ret;
+}
+
+static void __ppl_exit_log(struct ppl_conf *ppl_conf)
+{
+	clear_bit(MD_HAS_PPL, &ppl_conf->mddev->flags);
+
+	kfree(ppl_conf->child_logs);
+
+	if (ppl_conf->bs)
+		bioset_free(ppl_conf->bs);
+	mempool_destroy(ppl_conf->io_pool);
+	kmem_cache_destroy(ppl_conf->io_kc);
+
+	kfree(ppl_conf);
+}
+
+void ppl_exit_log(struct r5conf *conf)
+{
+	struct ppl_conf *ppl_conf = conf->log_private;
+
+	if (ppl_conf) {
+		__ppl_exit_log(ppl_conf);
+		conf->log_private = NULL;
+	}
+}
+
+static int ppl_validate_rdev(struct md_rdev *rdev)
+{
+	char b[BDEVNAME_SIZE];
+	int ppl_data_sectors;
+	int ppl_size_new;
+
+	/*
+	 * The configured PPL size must be enough to store
+	 * the header and (at the very least) partial parity
+	 * for one stripe. Round it down to ensure the data
+	 * space is cleanly divisible by stripe size.
+	 */
+	ppl_data_sectors = rdev->ppl.size - (PPL_HEADER_SIZE >> 9);
+
+	if (ppl_data_sectors > 0)
+		ppl_data_sectors = rounddown(ppl_data_sectors, STRIPE_SECTORS);
+
+	if (ppl_data_sectors <= 0) {
+		pr_warn("md/raid:%s: PPL space too small on %s\n",
+			mdname(rdev->mddev), bdevname(rdev->bdev, b));
+		return -ENOSPC;
+	}
+
+	ppl_size_new = ppl_data_sectors + (PPL_HEADER_SIZE >> 9);
+
+	if ((rdev->ppl.sector < rdev->data_offset &&
+	     rdev->ppl.sector + ppl_size_new > rdev->data_offset) ||
+	    (rdev->ppl.sector >= rdev->data_offset &&
+	     rdev->data_offset + rdev->sectors > rdev->ppl.sector)) {
+		pr_warn("md/raid:%s: PPL space overlaps with data on %s\n",
+			mdname(rdev->mddev), bdevname(rdev->bdev, b));
+		return -EINVAL;
+	}
+
+	if (!rdev->mddev->external &&
+	    ((rdev->ppl.offset > 0 && rdev->ppl.offset < (rdev->sb_size >> 9)) ||
+	     (rdev->ppl.offset <= 0 && rdev->ppl.offset + ppl_size_new > 0))) {
+		pr_warn("md/raid:%s: PPL space overlaps with superblock on %s\n",
+			mdname(rdev->mddev), bdevname(rdev->bdev, b));
+		return -EINVAL;
+	}
+
+	rdev->ppl.size = ppl_size_new;
+
+	return 0;
+}
+
+int ppl_init_log(struct r5conf *conf)
+{
+	struct ppl_conf *ppl_conf;
+	struct mddev *mddev = conf->mddev;
+	int ret = 0;
+	int i;
+	bool need_cache_flush = false;
+
+	pr_debug("md/raid:%s: enabling distributed Partial Parity Log\n",
+		 mdname(conf->mddev));
+
+	if (PAGE_SIZE != 4096)
+		return -EINVAL;
+
+	if (mddev->level != 5) {
+		pr_warn("md/raid:%s PPL is not compatible with raid level %d\n",
+			mdname(mddev), mddev->level);
+		return -EINVAL;
+	}
+
+	if (mddev->bitmap_info.file || mddev->bitmap_info.offset) {
+		pr_warn("md/raid:%s PPL is not compatible with bitmap\n",
+			mdname(mddev));
+		return -EINVAL;
+	}
+
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		pr_warn("md/raid:%s PPL is not compatible with journal\n",
+			mdname(mddev));
+		return -EINVAL;
+	}
+
+	ppl_conf = kzalloc(sizeof(struct ppl_conf), GFP_KERNEL);
+	if (!ppl_conf)
+		return -ENOMEM;
+
+	ppl_conf->mddev = mddev;
+
+	ppl_conf->io_kc = KMEM_CACHE(ppl_io_unit, 0);
+	if (!ppl_conf->io_kc) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ppl_conf->io_pool = mempool_create(conf->raid_disks, ppl_io_pool_alloc,
+					   ppl_io_pool_free, ppl_conf->io_kc);
+	if (!ppl_conf->io_pool) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ppl_conf->bs = bioset_create(conf->raid_disks, 0);
+	if (!ppl_conf->bs) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ppl_conf->count = conf->raid_disks;
+	ppl_conf->child_logs = kcalloc(ppl_conf->count, sizeof(struct ppl_log),
+				       GFP_KERNEL);
+	if (!ppl_conf->child_logs) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	atomic64_set(&ppl_conf->seq, 0);
+	INIT_LIST_HEAD(&ppl_conf->no_mem_stripes);
+	spin_lock_init(&ppl_conf->no_mem_stripes_lock);
+
+	if (!mddev->external) {
+		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
+		ppl_conf->block_size = 512;
+	} else {
+		ppl_conf->block_size = queue_logical_block_size(mddev->queue);
+	}
+
+	for (i = 0; i < ppl_conf->count; i++) {
+		struct ppl_log *log = &ppl_conf->child_logs[i];
+		struct md_rdev *rdev = conf->disks[i].rdev;
+
+		mutex_init(&log->io_mutex);
+		spin_lock_init(&log->io_list_lock);
+		INIT_LIST_HEAD(&log->io_list);
+
+		log->ppl_conf = ppl_conf;
+		log->rdev = rdev;
+
+		if (rdev) {
+			struct request_queue *q;
+
+			ret = ppl_validate_rdev(rdev);
+			if (ret)
+				goto err;
+
+			q = bdev_get_queue(rdev->bdev);
+			if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+				need_cache_flush = true;
+		}
+	}
+
+	if (need_cache_flush)
+		pr_warn("md/raid:%s: Volatile write-back cache should be disabled on all member drives when using PPL!\n",
+			mdname(mddev));
+
+	/* load and possibly recover the logs from the member disks */
+	ret = ppl_load(ppl_conf);
+
+	if (ret) {
+		goto err;
+	} else if (!mddev->pers &&
+		   mddev->recovery_cp == 0 && !mddev->degraded &&
+		   ppl_conf->recovered_entries > 0 &&
+		   ppl_conf->mismatch_count == 0) {
+		/*
+		 * If we are starting a dirty array and the recovery succeeds
+		 * without any issues, set the array as clean.
+		 */
+		mddev->recovery_cp = MaxSector;
+		set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
+	} else if (mddev->pers && ppl_conf->mismatch_count > 0) {
+		/* no mismatch allowed when enabling PPL for a running array */
+		ret = -EINVAL;
+		goto err;
+	}
+
+	conf->log_private = ppl_conf;
+	set_bit(MD_HAS_PPL, &ppl_conf->mddev->flags);
+
+	return 0;
+err:
+	__ppl_exit_log(ppl_conf);
+	return ret;
+}
+
+int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add)
+{
+	struct ppl_conf *ppl_conf = conf->log_private;
+	struct ppl_log *log;
+	int ret = 0;
+	char b[BDEVNAME_SIZE];
+
+	if (!rdev)
+		return -EINVAL;
+
+	pr_debug("%s: disk: %d operation: %s dev: %s\n",
+		 __func__, rdev->raid_disk, add ? "add" : "remove",
+		 bdevname(rdev->bdev, b));
+
+	if (rdev->raid_disk < 0)
+		return 0;
+
+	if (rdev->raid_disk >= ppl_conf->count)
+		return -ENODEV;
+
+	log = &ppl_conf->child_logs[rdev->raid_disk];
+
+	mutex_lock(&log->io_mutex);
+	if (add) {
+		ret = ppl_validate_rdev(rdev);
+		if (!ret) {
+			log->rdev = rdev;
+			ret = ppl_write_empty_header(log);
+		}
+	} else {
+		log->rdev = NULL;
+	}
+	mutex_unlock(&log->io_mutex);
+
+	return ret;
+}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2efdb0d67460..2e38cfac5b1d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -58,11 +58,13 @@
 #include <linux/sched/signal.h>
 
 #include <trace/events/block.h>
+#include <linux/list_sort.h>
 
 #include "md.h"
 #include "raid5.h"
 #include "raid0.h"
 #include "bitmap.h"
+#include "raid5-log.h"
 
 #define UNSUPPORTED_MDDEV_FLAGS	(1L << MD_FAILFAST_SUPPORTED)
 
@@ -156,17 +158,6 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 	return slot;
 }
 
-static void return_io(struct bio_list *return_bi)
-{
-	struct bio *bi;
-	while ((bi = bio_list_pop(return_bi)) != NULL) {
-		bi->bi_iter.bi_size = 0;
-		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
-					 bi, 0);
-		bio_endio(bi);
-	}
-}
-
 static void print_raid5_conf (struct r5conf *conf);
 
 static int stripe_operations_active(struct stripe_head *sh)
@@ -176,6 +167,13 @@ static int stripe_operations_active(struct stripe_head *sh)
 	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
 }
 
+static bool stripe_is_lowprio(struct stripe_head *sh)
+{
+	return (test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) ||
+		test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state)) &&
+	       !test_bit(STRIPE_R5C_CACHING, &sh->state);
+}
+
 static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
@@ -191,7 +189,10 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
 	if (list_empty(&sh->lru)) {
 		struct r5worker_group *group;
 		group = conf->worker_groups + cpu_to_group(cpu);
-		list_add_tail(&sh->lru, &group->handle_list);
+		if (stripe_is_lowprio(sh))
+			list_add_tail(&sh->lru, &group->loprio_list);
+		else
+			list_add_tail(&sh->lru, &group->handle_list);
 		group->stripes_cnt++;
 		sh->group = group;
 	}
@@ -254,7 +255,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			clear_bit(STRIPE_BIT_DELAY, &sh->state);
 			if (conf->worker_cnt_per_group == 0) {
-				list_add_tail(&sh->lru, &conf->handle_list);
+				if (stripe_is_lowprio(sh))
+					list_add_tail(&sh->lru,
+							&conf->loprio_list);
+				else
+					list_add_tail(&sh->lru,
+							&conf->handle_list);
 			} else {
 				raid5_wakeup_stripe_thread(sh);
 				return;
@@ -481,6 +487,7 @@ static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
 		sh->dev[i].page = page;
 		sh->dev[i].orig_page = page;
 	}
+
 	return 0;
 }
 
@@ -729,7 +736,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
 		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
@@ -863,41 +870,107 @@ static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
 	return 1;
 }
 
-static void flush_deferred_bios(struct r5conf *conf)
+static void dispatch_bio_list(struct bio_list *tmp)
 {
-	struct bio_list tmp;
 	struct bio *bio;
 
-	if (!conf->batch_bio_dispatch || !conf->group_cnt)
+	while ((bio = bio_list_pop(tmp)))
+		generic_make_request(bio);
+}
+
+static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b)
+{
+	const struct r5pending_data *da = list_entry(a,
+				struct r5pending_data, sibling);
+	const struct r5pending_data *db = list_entry(b,
+				struct r5pending_data, sibling);
+	if (da->sector > db->sector)
+		return 1;
+	if (da->sector < db->sector)
+		return -1;
+	return 0;
+}
+
+static void dispatch_defer_bios(struct r5conf *conf, int target,
+				struct bio_list *list)
+{
+	struct r5pending_data *data;
+	struct list_head *first, *next = NULL;
+	int cnt = 0;
+
+	if (conf->pending_data_cnt == 0)
+		return;
+
+	list_sort(NULL, &conf->pending_list, cmp_stripe);
+
+	first = conf->pending_list.next;
+
+	/* temporarily move the head */
+	if (conf->next_pending_data)
+		list_move_tail(&conf->pending_list,
+				&conf->next_pending_data->sibling);
+
+	while (!list_empty(&conf->pending_list)) {
+		data = list_first_entry(&conf->pending_list,
+			struct r5pending_data, sibling);
+		if (&data->sibling == first)
+			first = data->sibling.next;
+		next = data->sibling.next;
+
+		bio_list_merge(list, &data->bios);
+		list_move(&data->sibling, &conf->free_list);
+		cnt++;
+		if (cnt >= target)
+			break;
+	}
+	conf->pending_data_cnt -= cnt;
+	BUG_ON(conf->pending_data_cnt < 0 || cnt < target);
+
+	if (next != &conf->pending_list)
+		conf->next_pending_data = list_entry(next,
+				struct r5pending_data, sibling);
+	else
+		conf->next_pending_data = NULL;
+	/* list isn't empty */
+	if (first != &conf->pending_list)
+		list_move_tail(&conf->pending_list, first);
+}
+
+static void flush_deferred_bios(struct r5conf *conf)
+{
+	struct bio_list tmp = BIO_EMPTY_LIST;
+
+	if (conf->pending_data_cnt == 0)
 		return;
 
-	bio_list_init(&tmp);
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_merge(&tmp, &conf->pending_bios);
-	bio_list_init(&conf->pending_bios);
+	dispatch_defer_bios(conf, conf->pending_data_cnt, &tmp);
+	BUG_ON(conf->pending_data_cnt != 0);
 	spin_unlock(&conf->pending_bios_lock);
 
-	while ((bio = bio_list_pop(&tmp)))
-		generic_make_request(bio);
+	dispatch_bio_list(&tmp);
 }
 
-static void defer_bio_issue(struct r5conf *conf, struct bio *bio)
+static void defer_issue_bios(struct r5conf *conf, sector_t sector,
+				struct bio_list *bios)
 {
-	/*
-	 * change group_cnt will drain all bios, so this is safe
-	 *
-	 * A read generally means a read-modify-write, which usually means a
-	 * randwrite, so we don't delay it
-	 */
-	if (!conf->batch_bio_dispatch || !conf->group_cnt ||
-	    bio_op(bio) == REQ_OP_READ) {
-		generic_make_request(bio);
-		return;
-	}
+	struct bio_list tmp = BIO_EMPTY_LIST;
+	struct r5pending_data *ent;
+
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_add(&conf->pending_bios, bio);
+	ent = list_first_entry(&conf->free_list, struct r5pending_data,
+							sibling);
+	list_move_tail(&ent->sibling, &conf->pending_list);
+	ent->sector = sector;
+	bio_list_init(&ent->bios);
+	bio_list_merge(&ent->bios, bios);
+	conf->pending_data_cnt++;
+	if (conf->pending_data_cnt >= PENDING_IO_MAX)
+		dispatch_defer_bios(conf, PENDING_IO_ONE_FLUSH, &tmp);
+
 	spin_unlock(&conf->pending_bios_lock);
-	md_wakeup_thread(conf->mddev->thread);
+
+	dispatch_bio_list(&tmp);
 }
 
 static void
@@ -910,21 +983,15 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 	struct r5conf *conf = sh->raid_conf;
 	int i, disks = sh->disks;
 	struct stripe_head *head_sh = sh;
+	struct bio_list pending_bios = BIO_EMPTY_LIST;
+	bool should_defer;
 
 	might_sleep();
 
-	if (!test_bit(STRIPE_R5C_CACHING, &sh->state)) {
-		/* writing out phase */
-		if (s->waiting_extra_page)
-			return;
-		if (r5l_write_stripe(conf->log, sh) == 0)
-			return;
-	} else {  /* caching phase */
-		if (test_bit(STRIPE_LOG_TRAPPED, &sh->state)) {
-			r5c_cache_data(conf->log, sh, s);
-			return;
-		}
-	}
+	if (log_stripe(sh, s) == 0)
+		return;
+
+	should_defer = conf->batch_bio_dispatch && conf->group_cnt;
 
 	for (i = disks; i--; ) {
 		int op, op_flags = 0;
@@ -1080,7 +1147,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
 						      bi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, bi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, bi);
+			else
+				generic_make_request(bi);
 		}
 		if (rrdev) {
 			if (s->syncing || s->expanding || s->expanded
@@ -1125,7 +1195,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
 						      rbi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, rbi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, rbi);
+			else
+				generic_make_request(rbi);
 		}
 		if (!rdev && !rrdev) {
 			if (op_is_write(op))
@@ -1143,6 +1216,9 @@ again:
 		if (sh != head_sh)
 			goto again;
 	}
+
+	if (should_defer && !bio_list_empty(&pending_bios))
+		defer_issue_bios(conf, head_sh->sector, &pending_bios);
 }
 
 static struct dma_async_tx_descriptor *
@@ -1212,7 +1288,6 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
 static void ops_complete_biofill(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	struct bio_list return_bi = BIO_EMPTY_LIST;
 	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -1236,16 +1311,13 @@ static void ops_complete_biofill(void *stripe_head_ref)
 			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				if (!raid5_dec_bi_active_stripes(rbi))
-					bio_list_add(&return_bi, rbi);
+				bio_endio(rbi);
 				rbi = rbi2;
 			}
 		}
 	}
 	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
-	return_io(&return_bi);
-
 	set_bit(STRIPE_HANDLE, &sh->state);
 	raid5_release_stripe(sh);
 }
@@ -2014,6 +2086,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			tx = ops_run_prexor6(sh, percpu, tx);
 	}
 
+	if (test_bit(STRIPE_OP_PARTIAL_PARITY, &ops_request))
+		tx = ops_run_partial_parity(sh, percpu, tx);
+
 	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
 		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
@@ -2046,8 +2121,15 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
+static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
+{
+	if (sh->ppl_page)
+		__free_page(sh->ppl_page);
+	kmem_cache_free(sc, sh);
+}
+
 static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
-	int disks)
+	int disks, struct r5conf *conf)
 {
 	struct stripe_head *sh;
 	int i;
@@ -2061,6 +2143,7 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
 		INIT_LIST_HEAD(&sh->r5c);
 		INIT_LIST_HEAD(&sh->log_list);
 		atomic_set(&sh->count, 1);
+		sh->raid_conf = conf;
 		sh->log_start = MaxSector;
 		for (i = 0; i < disks; i++) {
 			struct r5dev *dev = &sh->dev[i];
@@ -2068,6 +2151,14 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
 			bio_init(&dev->req, &dev->vec, 1);
 			bio_init(&dev->rreq, &dev->rvec, 1);
 		}
+
+		if (raid5_has_ppl(conf)) {
+			sh->ppl_page = alloc_page(gfp);
+			if (!sh->ppl_page) {
+				free_stripe(sc, sh);
+				sh = NULL;
+			}
+		}
 	}
 	return sh;
 }
@@ -2075,15 +2166,13 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 {
 	struct stripe_head *sh;
 
-	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
+	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size, conf);
 	if (!sh)
 		return 0;
 
-	sh->raid_conf = conf;
-
 	if (grow_buffers(sh, gfp)) {
 		shrink_buffers(sh);
-		kmem_cache_free(conf->slab_cache, sh);
+		free_stripe(conf->slab_cache, sh);
 		return 0;
 	}
 	sh->hash_lock_index =
@@ -2210,7 +2299,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	 *    pages have been transferred over, and the old kmem_cache is
 	 *    freed when all stripes are done.
 	 * 3/ reallocate conf->disks to be suitable bigger.  If this fails,
-	 *    we simple return a failre status - no need to clean anything up.
+	 *    we simple return a failure status - no need to clean anything up.
 	 * 4/ allocate new pages for the new slots in the new stripe_heads.
 	 *    If this fails, we don't bother trying the shrink the
 	 *    stripe_heads down again, we just leave them as they are.
@@ -2228,9 +2317,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	int i;
 	int hash, cnt;
 
-	if (newsize <= conf->pool_size)
-		return 0; /* never bother to shrink */
-
 	err = md_allow_write(conf->mddev);
 	if (err)
 		return err;
@@ -2246,11 +2332,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	mutex_lock(&conf->cache_size_mutex);
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
+		nsh = alloc_stripe(sc, GFP_KERNEL, newsize, conf);
 		if (!nsh)
 			break;
 
-		nsh->raid_conf = conf;
 		list_add(&nsh->lru, &newstripes);
 	}
 	if (i) {
@@ -2258,7 +2343,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		while (!list_empty(&newstripes)) {
 			nsh = list_entry(newstripes.next, struct stripe_head, lru);
 			list_del(&nsh->lru);
-			kmem_cache_free(sc, nsh);
+			free_stripe(sc, nsh);
 		}
 		kmem_cache_destroy(sc);
 		mutex_unlock(&conf->cache_size_mutex);
@@ -2284,7 +2369,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 			nsh->dev[i].orig_page = osh->dev[i].page;
 		}
 		nsh->hash_lock_index = hash;
-		kmem_cache_free(conf->slab_cache, osh);
+		free_stripe(conf->slab_cache, osh);
 		cnt++;
 		if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS +
 		    !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) {
@@ -2323,6 +2408,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		err = -ENOMEM;
 
 	mutex_unlock(&conf->cache_size_mutex);
+
+	conf->slab_cache = sc;
+	conf->active_name = 1-conf->active_name;
+
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -2340,8 +2429,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	}
 	/* critical section pass, GFP_NOIO no longer needed */
 
-	conf->slab_cache = sc;
-	conf->active_name = 1-conf->active_name;
 	if (!err)
 		conf->pool_size = newsize;
 	return err;
@@ -2359,7 +2446,7 @@ static int drop_one_stripe(struct r5conf *conf)
 		return 0;
 	BUG_ON(atomic_read(&sh->count));
 	shrink_buffers(sh);
-	kmem_cache_free(conf->slab_cache, sh);
+	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
 	conf->max_nr_stripes--;
 	return 1;
@@ -3082,6 +3169,12 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 		s->locked++;
 	}
 
+	if (raid5_has_ppl(sh->raid_conf) && sh->ppl_page &&
+	    test_bit(STRIPE_OP_BIODRAIN, &s->ops_request) &&
+	    !test_bit(STRIPE_FULL_WRITE, &sh->state) &&
+	    test_bit(R5_Insync, &sh->dev[pd_idx].flags))
+		set_bit(STRIPE_OP_PARTIAL_PARITY, &s->ops_request);
+
 	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
 		s->locked, s->ops_request);
@@ -3103,14 +3196,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 		(unsigned long long)bi->bi_iter.bi_sector,
 		(unsigned long long)sh->sector);
 
-	/*
-	 * If several bio share a stripe. The bio bi_phys_segments acts as a
-	 * reference count to avoid race. The reference count should already be
-	 * increased before this function is called (for example, in
-	 * raid5_make_request()), so other bio sharing this stripe will not free the
-	 * stripe. If a stripe is owned by one stripe, the stripe lock will
-	 * protect it.
-	 */
 	spin_lock_irq(&sh->stripe_lock);
 	/* Don't allow new IO added to stripes in batch list */
 	if (sh->batch_head)
@@ -3129,6 +3214,36 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 	if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi))
 		goto overlap;
 
+	if (forwrite && raid5_has_ppl(conf)) {
+		/*
+		 * With PPL only writes to consecutive data chunks within a
+		 * stripe are allowed because for a single stripe_head we can
+		 * only have one PPL entry at a time, which describes one data
+		 * range. Not really an overlap, but wait_for_overlap can be
+		 * used to handle this.
+		 */
+		sector_t sector;
+		sector_t first = 0;
+		sector_t last = 0;
+		int count = 0;
+		int i;
+
+		for (i = 0; i < sh->disks; i++) {
+			if (i != sh->pd_idx &&
+			    (i == dd_idx || sh->dev[i].towrite)) {
+				sector = sh->dev[i].sector;
+				if (count == 0 || sector < first)
+					first = sector;
+				if (sector > last)
+					last = sector;
+				count++;
+			}
+		}
+
+		if (first + conf->chunk_sectors * (count - 1) != last)
+			goto overlap;
+	}
+
 	if (!forwrite || previous)
 		clear_bit(STRIPE_BATCH_READY, &sh->state);
 
@@ -3136,7 +3251,8 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 	if (*bip)
 		bi->bi_next = *bip;
 	*bip = bi;
-	raid5_inc_bi_active_stripes(bi);
+	bio_inc_remaining(bi);
+	md_write_inc(conf->mddev, bi);
 
 	if (forwrite) {
 		/* check if page is covered */
@@ -3213,8 +3329,7 @@ static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
 
 static void
 handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
-				struct stripe_head_state *s, int disks,
-				struct bio_list *return_bi)
+		     struct stripe_head_state *s, int disks)
 {
 	int i;
 	BUG_ON(sh->batch_head);
@@ -3250,7 +3365,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		if (bi)
 			bitmap_end = 1;
 
-		r5l_stripe_write_finished(sh);
+		log_stripe_write_finished(sh);
 
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);
@@ -3260,10 +3375,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 
 			bi->bi_error = -EIO;
-			if (!raid5_dec_bi_active_stripes(bi)) {
-				md_write_end(conf->mddev);
-				bio_list_add(return_bi, bi);
-			}
+			md_write_end(conf->mddev);
+			bio_endio(bi);
 			bi = nextbi;
 		}
 		if (bitmap_end)
@@ -3284,10 +3397,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 
 			bi->bi_error = -EIO;
-			if (!raid5_dec_bi_active_stripes(bi)) {
-				md_write_end(conf->mddev);
-				bio_list_add(return_bi, bi);
-			}
+			md_write_end(conf->mddev);
+			bio_endio(bi);
 			bi = bi2;
 		}
 
@@ -3312,8 +3423,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 					r5_next_bio(bi, sh->dev[i].sector);
 
 				bi->bi_error = -EIO;
-				if (!raid5_dec_bi_active_stripes(bi))
-					bio_list_add(return_bi, bi);
+				bio_endio(bi);
 				bi = nextbi;
 			}
 		}
@@ -3449,7 +3559,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 		/* Pre-reads at not permitted until after short delay
 		 * to gather multiple requests.  However if this
-		 * device is no Insync, the block could only be be computed
+		 * device is no Insync, the block could only be computed
 		 * and there is no need to delay that.
 		 */
 		return 0;
@@ -3468,7 +3578,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 
 	/* If we are forced to do a reconstruct-write, either because
 	 * the current RAID6 implementation only supports that, or
-	 * or because parity cannot be trusted and we are currently
+	 * because parity cannot be trusted and we are currently
 	 * recovering it, there is extra need to be careful.
 	 * If one of the devices that we would need to read, because
 	 * it is not being overwritten (and maybe not written at all)
@@ -3508,9 +3618,20 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
 		BUG_ON(test_bit(R5_Wantread, &dev->flags));
 		BUG_ON(sh->batch_head);
+
+		/*
+		 * In the raid6 case if the only non-uptodate disk is P
+		 * then we already trusted P to compute the other failed
+		 * drives. It is safe to compute rather than re-read P.
+		 * In other cases we only compute blocks from failed
+		 * devices, otherwise check/repair might fail to detect
+		 * a real inconsistency.
+		 */
+
 		if ((s->uptodate == disks - 1) &&
+		    ((sh->qd_idx >= 0 && sh->pd_idx == disk_idx) ||
 		    (s->failed && (disk_idx == s->failed_num[0] ||
-				   disk_idx == s->failed_num[1]))) {
+				   disk_idx == s->failed_num[1])))) {
 			/* have disk failed, and we're requested to fetch it;
 			 * do compute it
 			 */
@@ -3612,7 +3733,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
  * never LOCKED, so we don't need to test 'failed' directly.
  */
 static void handle_stripe_clean_event(struct r5conf *conf,
-	struct stripe_head *sh, int disks, struct bio_list *return_bi)
+	struct stripe_head *sh, int disks)
 {
 	int i;
 	struct r5dev *dev;
@@ -3644,10 +3765,8 @@ returnbi:
 				while (wbi && wbi->bi_iter.bi_sector <
 					dev->sector + STRIPE_SECTORS) {
 					wbi2 = r5_next_bio(wbi, dev->sector);
-					if (!raid5_dec_bi_active_stripes(wbi)) {
-						md_write_end(conf->mddev);
-						bio_list_add(return_bi, wbi);
-					}
+					md_write_end(conf->mddev);
+					bio_endio(wbi);
 					wbi = wbi2;
 				}
 				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
@@ -3669,7 +3788,7 @@ returnbi:
 				discard_pending = 1;
 		}
 
-	r5l_stripe_write_finished(sh);
+	log_stripe_write_finished(sh);
 
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -4556,7 +4675,8 @@ static void handle_stripe(struct stripe_head *sh)
 	if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
 		goto finish;
 
-	if (s.handle_bad_blocks) {
+	if (s.handle_bad_blocks ||
+	    test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
 		set_bit(STRIPE_HANDLE, &sh->state);
 		goto finish;
 	}
@@ -4589,7 +4709,7 @@ static void handle_stripe(struct stripe_head *sh)
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
 		if (s.to_read+s.to_write+s.written)
-			handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+			handle_failed_stripe(conf, sh, &s, disks);
 		if (s.syncing + s.replacing)
 			handle_failed_sync(conf, sh, &s);
 	}
@@ -4655,11 +4775,11 @@ static void handle_stripe(struct stripe_head *sh)
 			     && !test_bit(R5_LOCKED, &qdev->flags)
 			     && (test_bit(R5_UPTODATE, &qdev->flags) ||
 				 test_bit(R5_Discard, &qdev->flags))))))
-		handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
+		handle_stripe_clean_event(conf, sh, disks);
 
 	if (s.just_cached)
-		r5c_handle_cached_data_endio(conf, sh, disks, &s.return_bi);
-	r5l_stripe_write_finished(sh);
+		r5c_handle_cached_data_endio(conf, sh, disks);
+	log_stripe_write_finished(sh);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
@@ -4886,16 +5006,6 @@ finish:
 			md_wakeup_thread(conf->mddev->thread);
 	}
 
-	if (!bio_list_empty(&s.return_bi)) {
-		if (test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
-			spin_lock_irq(&conf->device_lock);
-			bio_list_merge(&conf->return_bi, &s.return_bi);
-			spin_unlock_irq(&conf->device_lock);
-			md_wakeup_thread(conf->mddev->thread);
-		} else
-			return_io(&s.return_bi);
-	}
-
 	clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
 }
 
@@ -4984,12 +5094,14 @@ static void add_bio_to_retry(struct bio *bi,struct r5conf *conf)
 	md_wakeup_thread(conf->mddev->thread);
 }
 
-static struct bio *remove_bio_from_retry(struct r5conf *conf)
+static struct bio *remove_bio_from_retry(struct r5conf *conf,
+					 unsigned int *offset)
 {
 	struct bio *bi;
 
 	bi = conf->retry_read_aligned;
 	if (bi) {
+		*offset = conf->retry_read_offset;
 		conf->retry_read_aligned = NULL;
 		return bi;
 	}
@@ -4997,11 +5109,7 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
 	if(bi) {
 		conf->retry_read_aligned_list = bi->bi_next;
 		bi->bi_next = NULL;
-		/*
-		 * this sets the active strip count to 1 and the processed
-		 * strip count to zero (upper 8 bits)
-		 */
-		raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */
+		*offset = 0;
 	}
 
 	return bi;
@@ -5136,24 +5244,20 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct bio *split;
+	sector_t sector = raid_bio->bi_iter.bi_sector;
+	unsigned chunk_sects = mddev->chunk_sectors;
+	unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
 
-	do {
-		sector_t sector = raid_bio->bi_iter.bi_sector;
-		unsigned chunk_sects = mddev->chunk_sectors;
-		unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
-
-		if (sectors < bio_sectors(raid_bio)) {
-			split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
-			bio_chain(split, raid_bio);
-		} else
-			split = raid_bio;
+	if (sectors < bio_sectors(raid_bio)) {
+		struct r5conf *conf = mddev->private;
+		split = bio_split(raid_bio, sectors, GFP_NOIO, conf->bio_split);
+		bio_chain(split, raid_bio);
+		generic_make_request(raid_bio);
+		raid_bio = split;
+	}
 
-		if (!raid5_read_one_chunk(mddev, split)) {
-			if (split != raid_bio)
-				generic_make_request(raid_bio);
-			return split;
-		}
-	} while (split != raid_bio);
+	if (!raid5_read_one_chunk(mddev, raid_bio))
+		return raid_bio;
 
 	return NULL;
 }
@@ -5170,19 +5274,27 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
  */
 static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 {
-	struct stripe_head *sh = NULL, *tmp;
+	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
-	struct r5worker_group *wg = NULL;
+	struct r5worker_group *wg;
+	bool second_try = !r5c_is_writeback(conf->log);
+	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
 
+again:
+	wg = NULL;
+	sh = NULL;
 	if (conf->worker_cnt_per_group == 0) {
-		handle_list = &conf->handle_list;
+		handle_list = try_loprio ? &conf->loprio_list :
+					&conf->handle_list;
 	} else if (group != ANY_GROUP) {
-		handle_list = &conf->worker_groups[group].handle_list;
+		handle_list = try_loprio ? &conf->worker_groups[group].loprio_list :
+				&conf->worker_groups[group].handle_list;
 		wg = &conf->worker_groups[group];
 	} else {
 		int i;
 		for (i = 0; i < conf->group_cnt; i++) {
-			handle_list = &conf->worker_groups[i].handle_list;
+			handle_list = try_loprio ? &conf->worker_groups[i].loprio_list :
+				&conf->worker_groups[i].handle_list;
 			wg = &conf->worker_groups[i];
 			if (!list_empty(handle_list))
 				break;
@@ -5233,8 +5345,13 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 		wg = NULL;
 	}
 
-	if (!sh)
-		return NULL;
+	if (!sh) {
+		if (second_try)
+			return NULL;
+		second_try = true;
+		try_loprio = !try_loprio;
+		goto again;
+	}
 
 	if (wg) {
 		wg->stripes_cnt--;
@@ -5323,7 +5440,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	struct r5conf *conf = mddev->private;
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
-	int remaining;
 	int stripe_sectors;
 
 	if (mddev->reshape_position != MaxSector)
@@ -5334,7 +5450,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
 
 	bi->bi_next = NULL;
-	bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
+	md_write_start(mddev, bi);
 
 	stripe_sectors = conf->chunk_sectors *
 		(conf->raid_disks - conf->max_degraded);
@@ -5380,7 +5496,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 				continue;
 			sh->dev[d].towrite = bi;
 			set_bit(R5_OVERWRITE, &sh->dev[d].flags);
-			raid5_inc_bi_active_stripes(bi);
+			bio_inc_remaining(bi);
+			md_write_inc(mddev, bi);
 			sh->overwrite_disks++;
 		}
 		spin_unlock_irq(&sh->stripe_lock);
@@ -5403,11 +5520,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		release_stripe_plug(mddev, sh);
 	}
 
-	remaining = raid5_dec_bi_active_stripes(bi);
-	if (remaining == 0) {
-		md_write_end(mddev);
-		bio_endio(bi);
-	}
+	md_write_end(mddev);
+	bio_endio(bi);
 }
 
 static void raid5_make_request(struct mddev *mddev, struct bio * bi)
@@ -5418,7 +5532,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 	const int rw = bio_data_dir(bi);
-	int remaining;
 	DEFINE_WAIT(w);
 	bool do_prepare;
 	bool do_flush = false;
@@ -5440,8 +5553,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 		do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
-	md_write_start(mddev, bi);
-
 	/*
 	 * If array is degraded, better not do chunk aligned read because
 	 * later we might have to read it again in order to reconstruct
@@ -5462,7 +5573,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
-	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
+	md_write_start(mddev, bi);
 
 	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
@@ -5597,16 +5708,9 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	}
 	finish_wait(&conf->wait_for_overlap, &w);
 
-	remaining = raid5_dec_bi_active_stripes(bi);
-	if (remaining == 0) {
-
-		if ( rw == WRITE )
-			md_write_end(mddev);
-
-		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
-					 bi, 0);
-		bio_endio(bi);
-	}
+	if (rw == WRITE)
+		md_write_end(mddev);
+	bio_endio(bi);
 }
 
 static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks);
@@ -5955,7 +6059,8 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 	return STRIPE_SECTORS;
 }
 
-static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
+static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
+			       unsigned int offset)
 {
 	/* We may not be able to submit a whole bio at once as there
 	 * may not be enough stripe_heads available.
@@ -5971,7 +6076,6 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	int dd_idx;
 	sector_t sector, logical_sector, last_sector;
 	int scnt = 0;
-	int remaining;
 	int handled = 0;
 
 	logical_sector = raid_bio->bi_iter.bi_sector &
@@ -5985,7 +6089,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		     sector += STRIPE_SECTORS,
 		     scnt++) {
 
-		if (scnt < raid5_bi_processed_stripes(raid_bio))
+		if (scnt < offset)
 			/* already done this stripe */
 			continue;
 
@@ -5993,15 +6097,15 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
-			raid5_set_bi_processed_stripes(raid_bio, scnt);
 			conf->retry_read_aligned = raid_bio;
+			conf->retry_read_offset = scnt;
 			return handled;
 		}
 
 		if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) {
 			raid5_release_stripe(sh);
-			raid5_set_bi_processed_stripes(raid_bio, scnt);
 			conf->retry_read_aligned = raid_bio;
+			conf->retry_read_offset = scnt;
 			return handled;
 		}
 
@@ -6010,12 +6114,9 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		raid5_release_stripe(sh);
 		handled++;
 	}
-	remaining = raid5_dec_bi_active_stripes(raid_bio);
-	if (remaining == 0) {
-		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
-					 raid_bio, 0);
-		bio_endio(raid_bio);
-	}
+
+	bio_endio(raid_bio);
+
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_quiescent);
 	return handled;
@@ -6058,7 +6159,7 @@ static int handle_active_stripes(struct r5conf *conf, int group,
 
 	for (i = 0; i < batch_size; i++)
 		handle_stripe(batch[i]);
-	r5l_write_stripe_run(conf->log);
+	log_write_stripe_run(conf);
 
 	cond_resched();
 
@@ -6075,6 +6176,7 @@ static void raid5_do_work(struct work_struct *work)
 	struct r5worker *worker = container_of(work, struct r5worker, work);
 	struct r5worker_group *group = worker->group;
 	struct r5conf *conf = group->conf;
+	struct mddev *mddev = conf->mddev;
 	int group_id = group - conf->worker_groups;
 	int handled;
 	struct blk_plug plug;
@@ -6095,6 +6197,9 @@ static void raid5_do_work(struct work_struct *work)
 		if (!batch_size && !released)
 			break;
 		handled += batch_size;
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -6122,24 +6227,13 @@ static void raid5d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
-	if (!bio_list_empty(&conf->return_bi) &&
-	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-		struct bio_list tmp = BIO_EMPTY_LIST;
-		spin_lock_irq(&conf->device_lock);
-		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-			bio_list_merge(&tmp, &conf->return_bi);
-			bio_list_init(&conf->return_bi);
-		}
-		spin_unlock_irq(&conf->device_lock);
-		return_io(&tmp);
-	}
-
 	blk_start_plug(&plug);
 	handled = 0;
 	spin_lock_irq(&conf->device_lock);
 	while (1) {
 		struct bio *bio;
 		int batch_size, released;
+		unsigned int offset;
 
 		released = release_stripe_list(conf, conf->temp_inactive_list);
 		if (released)
@@ -6157,10 +6251,10 @@ static void raid5d(struct md_thread *thread)
 		}
 		raid5_activate_delayed(conf);
 
-		while ((bio = remove_bio_from_retry(conf))) {
+		while ((bio = remove_bio_from_retry(conf, &offset))) {
 			int ok;
 			spin_unlock_irq(&conf->device_lock);
-			ok = retry_aligned_read(conf, bio);
+			ok = retry_aligned_read(conf, bio, offset);
 			spin_lock_irq(&conf->device_lock);
 			if (!ok)
 				break;
@@ -6544,6 +6638,7 @@ static int alloc_thread_groups(struct r5conf *conf, int cnt,
 
 		group = &(*worker_groups)[i];
 		INIT_LIST_HEAD(&group->handle_list);
+		INIT_LIST_HEAD(&group->loprio_list);
 		group->conf = conf;
 		group->workers = workers + i * cnt;
 
@@ -6634,8 +6729,8 @@ static void free_conf(struct r5conf *conf)
 {
 	int i;
 
-	if (conf->log)
-		r5l_exit_log(conf->log);
+	log_exit(conf);
+
 	if (conf->shrinker.nr_deferred)
 		unregister_shrinker(&conf->shrinker);
 
@@ -6646,7 +6741,10 @@ static void free_conf(struct r5conf *conf)
 		if (conf->disks[i].extra_page)
 			put_page(conf->disks[i].extra_page);
 	kfree(conf->disks);
+	if (conf->bio_split)
+		bioset_free(conf->bio_split);
 	kfree(conf->stripe_hashtbl);
+	kfree(conf->pending_data);
 	kfree(conf);
 }
 
@@ -6756,6 +6854,14 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL);
 	if (conf == NULL)
 		goto abort;
+	INIT_LIST_HEAD(&conf->free_list);
+	INIT_LIST_HEAD(&conf->pending_list);
+	conf->pending_data = kzalloc(sizeof(struct r5pending_data) *
+		PENDING_IO_MAX, GFP_KERNEL);
+	if (!conf->pending_data)
+		goto abort;
+	for (i = 0; i < PENDING_IO_MAX; i++)
+		list_add(&conf->pending_data[i].sibling, &conf->free_list);
 	/* Don't enable multi-threading by default*/
 	if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group,
 				 &new_group)) {
@@ -6771,15 +6877,14 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
+	INIT_LIST_HEAD(&conf->loprio_list);
 	INIT_LIST_HEAD(&conf->hold_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
 	INIT_LIST_HEAD(&conf->bitmap_list);
-	bio_list_init(&conf->return_bi);
 	init_llist_head(&conf->released_stripes);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
 	atomic_set(&conf->active_aligned_reads, 0);
-	bio_list_init(&conf->pending_bios);
 	spin_lock_init(&conf->pending_bios_lock);
 	conf->batch_bio_dispatch = true;
 	rdev_for_each(rdev, mddev) {
@@ -6813,6 +6918,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 			goto abort;
 	}
 
+	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!conf->bio_split)
+		goto abort;
 	conf->mddev = mddev;
 
 	if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
@@ -7097,6 +7205,13 @@ static int raid5_run(struct mddev *mddev)
 		BUG_ON(mddev->delta_disks != 0);
 	}
 
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) &&
+	    test_bit(MD_HAS_PPL, &mddev->flags)) {
+		pr_warn("md/raid:%s: using journal device and PPL not allowed - disabling PPL\n",
+			mdname(mddev));
+		clear_bit(MD_HAS_PPL, &mddev->flags);
+	}
+
 	if (mddev->private == NULL)
 		conf = setup_conf(mddev);
 	else
@@ -7188,7 +7303,10 @@ static int raid5_run(struct mddev *mddev)
 
 	if (mddev->degraded > dirty_parity_disks &&
 	    mddev->recovery_cp != MaxSector) {
-		if (mddev->ok_start_degraded)
+		if (test_bit(MD_HAS_PPL, &mddev->flags))
+			pr_crit("md/raid:%s: starting dirty degraded array with PPL.\n",
+				mdname(mddev));
+		else if (mddev->ok_start_degraded)
 			pr_crit("md/raid:%s: starting dirty degraded array - data corruption possible.\n",
 				mdname(mddev));
 		else {
@@ -7254,14 +7372,6 @@ static int raid5_run(struct mddev *mddev)
 		mddev->queue->limits.discard_alignment = stripe;
 		mddev->queue->limits.discard_granularity = stripe;
 
-		/*
-		 * We use 16-bit counter of active stripes in bi_phys_segments
-		 * (minus one for over-loaded initialization)
-		 */
-		blk_queue_max_hw_sectors(mddev->queue, 0xfffe * STRIPE_SECTORS);
-		blk_queue_max_discard_sectors(mddev->queue,
-					      0xfffe * STRIPE_SECTORS);
-
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 
@@ -7299,14 +7409,8 @@ static int raid5_run(struct mddev *mddev)
 		blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
 	}
 
-	if (journal_dev) {
-		char b[BDEVNAME_SIZE];
-
-		pr_debug("md/raid:%s: using device %s as journal\n",
-			 mdname(mddev), bdevname(journal_dev->bdev, b));
-		if (r5l_init_log(conf, journal_dev))
-			goto abort;
-	}
+	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
+		goto abort;
 
 	return 0;
 abort:
@@ -7420,17 +7524,16 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	print_raid5_conf(conf);
 	if (test_bit(Journal, &rdev->flags) && conf->log) {
-		struct r5l_log *log;
 		/*
 		 * we can't wait pending write here, as this is called in
 		 * raid5d, wait will deadlock.
+		 * neilb: there is no locking about new writes here,
+		 * so this cannot be safe.
 		 */
-		if (atomic_read(&mddev->writes_pending))
+		if (atomic_read(&conf->active_stripes)) {
 			return -EBUSY;
-		log = conf->log;
-		conf->log = NULL;
-		synchronize_rcu();
-		r5l_exit_log(log);
+		}
+		log_exit(conf);
 		return 0;
 	}
 	if (rdev == p->rdev)
@@ -7469,6 +7572,11 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			*rdevp = rdev;
 		}
 	}
+	if (!err) {
+		err = log_modify(conf, rdev, false);
+		if (err)
+			goto abort;
+	}
 	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
 		p->rdev = p->replacement;
@@ -7477,12 +7585,12 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			   * but will never see neither - if they are careful
 			   */
 		p->replacement = NULL;
-		clear_bit(WantReplacement, &rdev->flags);
-	} else
-		/* We might have just removed the Replacement as faulty-
-		 * clear the bit just in case
-		 */
-		clear_bit(WantReplacement, &rdev->flags);
+
+		if (!err)
+			err = log_modify(conf, p->rdev, true);
+	}
+
+	clear_bit(WantReplacement, &rdev->flags);
 abort:
 
 	print_raid5_conf(conf);
@@ -7499,7 +7607,6 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int last = conf->raid_disks - 1;
 
 	if (test_bit(Journal, &rdev->flags)) {
-		char b[BDEVNAME_SIZE];
 		if (conf->log)
 			return -EBUSY;
 
@@ -7508,9 +7615,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * The array is in readonly mode if journal is missing, so no
 		 * write requests running. We should be safe
 		 */
-		r5l_init_log(conf, rdev);
-		pr_debug("md/raid:%s: using device %s as journal\n",
-			 mdname(mddev), bdevname(rdev->bdev, b));
+		log_init(conf, rdev, false);
 		return 0;
 	}
 	if (mddev->recovery_disabled == conf->recovery_disabled)
@@ -7537,10 +7642,12 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		if (p->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;
-			err = 0;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
+
+			err = log_modify(conf, rdev, true);
+
 			goto out;
 		}
 	}
@@ -7574,7 +7681,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 	sector_t newsize;
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return -EINVAL;
 	sectors &= ~((sector_t)conf->chunk_sectors - 1);
 	newsize = raid5_size(mddev, sectors, mddev->raid_disks);
@@ -7625,7 +7732,7 @@ static int check_reshape(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return -EINVAL;
 	if (mddev->delta_disks == 0 &&
 	    mddev->new_layout == mddev->layout &&
@@ -7658,6 +7765,9 @@ static int check_reshape(struct mddev *mddev)
 				      mddev->chunk_sectors)
 			    ) < 0)
 			return -ENOMEM;
+
+	if (conf->previous_raid_disks + mddev->delta_disks <= conf->pool_size)
+		return 0; /* never bother to shrink */
 	return resize_stripes(conf, (conf->previous_raid_disks
 				     + mddev->delta_disks));
 }
@@ -8148,6 +8258,68 @@ static void *raid6_takeover(struct mddev *mddev)
 	return setup_conf(mddev);
 }
 
+static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
+{
+	struct r5conf *conf;
+	int err;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	conf = mddev->private;
+	if (!conf) {
+		mddev_unlock(mddev);
+		return -ENODEV;
+	}
+
+	if (strncmp(buf, "ppl", 3) == 0) {
+		/* ppl only works with RAID 5 */
+		if (!raid5_has_ppl(conf) && conf->level == 5) {
+			err = log_init(conf, NULL, true);
+			if (!err) {
+				err = resize_stripes(conf, conf->pool_size);
+				if (err)
+					log_exit(conf);
+			}
+		} else
+			err = -EINVAL;
+	} else if (strncmp(buf, "resync", 6) == 0) {
+		if (raid5_has_ppl(conf)) {
+			mddev_suspend(mddev);
+			log_exit(conf);
+			mddev_resume(mddev);
+			err = resize_stripes(conf, conf->pool_size);
+		} else if (test_bit(MD_HAS_JOURNAL, &conf->mddev->flags) &&
+			   r5l_log_disk_error(conf)) {
+			bool journal_dev_exists = false;
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (test_bit(Journal, &rdev->flags)) {
+					journal_dev_exists = true;
+					break;
+				}
+
+			if (!journal_dev_exists) {
+				mddev_suspend(mddev);
+				clear_bit(MD_HAS_JOURNAL, &mddev->flags);
+				mddev_resume(mddev);
+			} else  /* need remove journal device first */
+				err = -EBUSY;
+		} else
+			err = -EINVAL;
+	} else {
+		err = -EINVAL;
+	}
+
+	if (!err)
+		md_update_sb(mddev, 1);
+
+	mddev_unlock(mddev);
+
+	return err;
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8170,6 +8342,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 static struct md_personality raid5_personality =
 {
@@ -8193,6 +8366,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
 static struct md_personality raid4_personality =
@@ -8217,6 +8391,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 4bb27b97bf6b..625c7f16fd6b 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -224,10 +224,16 @@ struct stripe_head {
 	spinlock_t		batch_lock; /* only header's lock is useful */
 	struct list_head	batch_list; /* protected by head's batch lock*/
 
-	struct r5l_io_unit	*log_io;
+	union {
+		struct r5l_io_unit	*log_io;
+		struct ppl_io_unit	*ppl_io;
+	};
+
 	struct list_head	log_list;
 	sector_t		log_start; /* first meta block on the journal */
 	struct list_head	r5c; /* for r5c_cache->stripe_in_journal */
+
+	struct page		*ppl_page; /* partial parity of this stripe */
 	/**
 	 * struct stripe_operations
 	 * @target - STRIPE_OP_COMPUTE_BLK target
@@ -272,7 +278,6 @@ struct stripe_head_state {
 	int dec_preread_active;
 	unsigned long ops_request;
 
-	struct bio_list return_bi;
 	struct md_rdev *blocked_rdev;
 	int handle_bad_blocks;
 	int log_failed;
@@ -400,6 +405,7 @@ enum {
 	STRIPE_OP_BIODRAIN,
 	STRIPE_OP_RECONSTRUCT,
 	STRIPE_OP_CHECK,
+	STRIPE_OP_PARTIAL_PARITY,
 };
 
 /*
@@ -481,50 +487,6 @@ static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 		return NULL;
 }
 
-/*
- * We maintain a biased count of active stripes in the bottom 16 bits of
- * bi_phys_segments, and a count of processed stripes in the upper 16 bits
- */
-static inline int raid5_bi_processed_stripes(struct bio *bio)
-{
-	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
-	return (atomic_read(segments) >> 16) & 0xffff;
-}
-
-static inline int raid5_dec_bi_active_stripes(struct bio *bio)
-{
-	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
-	return atomic_sub_return(1, segments) & 0xffff;
-}
-
-static inline void raid5_inc_bi_active_stripes(struct bio *bio)
-{
-	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
-	atomic_inc(segments);
-}
-
-static inline void raid5_set_bi_processed_stripes(struct bio *bio,
-	unsigned int cnt)
-{
-	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-	int old, new;
-
-	do {
-		old = atomic_read(segments);
-		new = (old & 0xffff) | (cnt << 16);
-	} while (atomic_cmpxchg(segments, old, new) != old);
-}
-
-static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
-{
-	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
-	atomic_set(segments, cnt);
-}
-
 /* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
  * This is because we sometimes take all the spinlocks
  * and creating that much locking depth can cause
@@ -542,6 +504,7 @@ struct r5worker {
 
 struct r5worker_group {
 	struct list_head handle_list;
+	struct list_head loprio_list;
 	struct r5conf *conf;
 	struct r5worker *workers;
 	int stripes_cnt;
@@ -571,6 +534,14 @@ enum r5_cache_state {
 				 */
 };
 
+#define PENDING_IO_MAX 512
+#define PENDING_IO_ONE_FLUSH 128
+struct r5pending_data {
+	struct list_head sibling;
+	sector_t sector; /* stripe sector */
+	struct bio_list bios;
+};
+
 struct r5conf {
 	struct hlist_head	*stripe_hashtbl;
 	/* only protect corresponding hash list and inactive_list */
@@ -608,10 +579,12 @@ struct r5conf {
 						  */
 
 	struct list_head	handle_list; /* stripes needing handling */
+	struct list_head	loprio_list; /* low priority stripes */
 	struct list_head	hold_list; /* preread ready stripes */
 	struct list_head	delayed_list; /* stripes that have plugged requests */
 	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */
 	struct bio		*retry_read_aligned; /* currently retrying aligned bios   */
+	unsigned int		retry_read_offset; /* sector offset into retry_read_aligned */
 	struct bio		*retry_read_aligned_list; /* aligned bios retry list  */
 	atomic_t		preread_active_stripes; /* stripes with scheduled io */
 	atomic_t		active_aligned_reads;
@@ -621,9 +594,6 @@ struct r5conf {
 	int			skip_copy; /* Don't copy data from bio to stripe cache */
 	struct list_head	*last_hold; /* detect hold_list promotions */
 
-	/* bios to have bi_end_io called after metadata is synced */
-	struct bio_list		return_bi;
-
 	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
 	/* unfortunately we need two cache names as we temporarily have
 	 * two caches.
@@ -676,6 +646,7 @@ struct r5conf {
 	int			pool_size; /* number of disks in stripeheads in pool */
 	spinlock_t		device_lock;
 	struct disk_info	*disks;
+	struct bio_set		*bio_split;
 
 	/* When taking over an array from a different personality, we store
 	 * the new thread here until we fully activate the array.
@@ -686,10 +657,15 @@ struct r5conf {
 	int			group_cnt;
 	int			worker_cnt_per_group;
 	struct r5l_log		*log;
+	void			*log_private;
 
-	struct bio_list		pending_bios;
 	spinlock_t		pending_bios_lock;
 	bool			batch_bio_dispatch;
+	struct r5pending_data	*pending_data;
+	struct list_head	free_list;
+	struct list_head	pending_list;
+	int			pending_data_cnt;
+	struct r5pending_data	*next_pending_data;
 };
 
 
@@ -765,34 +741,4 @@ extern struct stripe_head *
 raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 			int previous, int noblock, int noquiesce);
 extern int raid5_calc_degraded(struct r5conf *conf);
-extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
-extern void r5l_exit_log(struct r5l_log *log);
-extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
-extern void r5l_write_stripe_run(struct r5l_log *log);
-extern void r5l_flush_stripe_to_raid(struct r5l_log *log);
-extern void r5l_stripe_write_finished(struct stripe_head *sh);
-extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio);
-extern void r5l_quiesce(struct r5l_log *log, int state);
-extern bool r5l_log_disk_error(struct r5conf *conf);
-extern bool r5c_is_writeback(struct r5l_log *log);
-extern int
-r5c_try_caching_write(struct r5conf *conf, struct stripe_head *sh,
-		      struct stripe_head_state *s, int disks);
-extern void
-r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh,
-			    struct stripe_head_state *s);
-extern void r5c_release_extra_page(struct stripe_head *sh);
-extern void r5c_use_extra_page(struct stripe_head *sh);
-extern void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
-extern void r5c_handle_cached_data_endio(struct r5conf *conf,
-	struct stripe_head *sh, int disks, struct bio_list *return_bi);
-extern int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh,
-			  struct stripe_head_state *s);
-extern void r5c_make_stripe_write_out(struct stripe_head *sh);
-extern void r5c_flush_cache(struct r5conf *conf, int num);
-extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
-extern void r5c_check_cached_full_stripe(struct r5conf *conf);
-extern struct md_sysfs_entry r5c_journal_mode;
-extern void r5c_update_on_rdev_error(struct mddev *mddev);
-extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
 #endif