1 files changed, 172 insertions, 190 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9c20049d1fec..272901514b0c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -182,6 +182,13 @@ const char *btrfs_bg_type_to_raid_name(u64 flags)
 	return btrfs_raid_array[index].raid_name;
 }
 
+int btrfs_nr_parity_stripes(u64 type)
+{
+	enum btrfs_raid_types index = btrfs_bg_flags_to_raid_index(type);
+
+	return btrfs_raid_array[index].nparity;
+}
+
 /*
  * Fill @buf with textual description of @bg_flags, no more than @size_buf
  * bytes including terminating null byte.
@@ -238,7 +245,6 @@ out_overflow:;
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans);
 static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info);
-static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
 static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			     enum btrfs_map_op op,
@@ -1396,12 +1402,7 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start)
 {
 	switch (device->fs_devices->chunk_alloc_policy) {
 	case BTRFS_CHUNK_ALLOC_REGULAR:
-		/*
-		 * We don't want to overwrite the superblock on the drive nor
-		 * any area used by the boot loader (grub for example), so we
-		 * make sure to start at an offset of at least 1MB.
-		 */
-		return max_t(u64, start, SZ_1M);
+		return max_t(u64, start, BTRFS_DEVICE_RANGE_RESERVED);
 	case BTRFS_CHUNK_ALLOC_ZONED:
 		/*
 		 * We don't care about the starting region like regular
@@ -5071,26 +5072,16 @@ static void init_alloc_chunk_ctl_policy_regular(
 				struct btrfs_fs_devices *fs_devices,
 				struct alloc_chunk_ctl *ctl)
 {
-	u64 type = ctl->type;
+	struct btrfs_space_info *space_info;
 
-	if (type & BTRFS_BLOCK_GROUP_DATA) {
-		ctl->max_stripe_size = SZ_1G;
-		ctl->max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
-	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
-		/* For larger filesystems, use larger metadata chunks */
-		if (fs_devices->total_rw_bytes > 50ULL * SZ_1G)
-			ctl->max_stripe_size = SZ_1G;
-		else
-			ctl->max_stripe_size = SZ_256M;
-		ctl->max_chunk_size = ctl->max_stripe_size;
-	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
-		ctl->max_stripe_size = SZ_32M;
-		ctl->max_chunk_size = 2 * ctl->max_stripe_size;
-		ctl->devs_max = min_t(int, ctl->devs_max,
-				      BTRFS_MAX_DEVS_SYS_CHUNK);
-	} else {
-		BUG();
-	}
+	space_info = btrfs_find_space_info(fs_devices->fs_info, ctl->type);
+	ASSERT(space_info);
+
+	ctl->max_chunk_size = READ_ONCE(space_info->chunk_size);
+	ctl->max_stripe_size = ctl->max_chunk_size;
+
+	if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM)
+		ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
 
 	/* We don't want a chunk larger than 10% of writable space */
 	ctl->max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
@@ -5720,7 +5711,8 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	int ret;
+	enum btrfs_raid_types index;
+	int ret = 1;
 
 	em = btrfs_get_chunk_map(fs_info, logical, len);
 	if (IS_ERR(em))
@@ -5733,10 +5725,11 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		return 1;
 
 	map = em->map_lookup;
-	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1_MASK))
-		ret = map->num_stripes;
-	else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
-		ret = map->sub_stripes;
+	index = btrfs_bg_flags_to_raid_index(map->type);
+
+	/* Non-RAID56, use their ncopies from btrfs_raid_array. */
+	if (!(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK))
+		ret = btrfs_raid_array[index].ncopies;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
 		ret = 2;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
@@ -5748,8 +5741,6 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		 * stripe under reconstruction.
 		 */
 		ret = map->num_stripes;
-	else
-		ret = 1;
 	free_extent_map(em);
 
 	down_read(&fs_info->dev_replace.rwsem);
@@ -5768,6 +5759,9 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 	struct map_lookup *map;
 	unsigned long len = fs_info->sectorsize;
 
+	if (!btrfs_fs_incompat(fs_info, RAID56))
+		return len;
+
 	em = btrfs_get_chunk_map(fs_info, logical, len);
 
 	if (!WARN_ON(IS_ERR(em))) {
@@ -5785,6 +5779,9 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	struct map_lookup *map;
 	int ret = 0;
 
+	if (!btrfs_fs_incompat(fs_info, RAID56))
+		return 0;
+
 	em = btrfs_get_chunk_map(fs_info, logical, len);
 
 	if(!WARN_ON(IS_ERR(em))) {
@@ -5917,18 +5914,17 @@ void btrfs_put_bioc(struct btrfs_io_context *bioc)
 		kfree(bioc);
 }
 
-/* can REQ_OP_DISCARD be sent with other REQ like REQ_OP_WRITE? */
 /*
  * Please note that, discard won't be sent to target device of device
  * replace.
  */
-static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
-					 u64 logical, u64 *length_ret,
-					 struct btrfs_io_context **bioc_ret)
+struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
+					       u64 logical, u64 *length_ret,
+					       u32 *num_stripes)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct btrfs_io_context *bioc;
+	struct btrfs_discard_stripe *stripes;
 	u64 length = *length_ret;
 	u64 offset;
 	u64 stripe_nr;
@@ -5937,29 +5933,26 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 	u64 stripe_cnt;
 	u64 stripe_len;
 	u64 stripe_offset;
-	u64 num_stripes;
 	u32 stripe_index;
 	u32 factor = 0;
 	u32 sub_stripes = 0;
 	u64 stripes_per_dev = 0;
 	u32 remaining_stripes = 0;
 	u32 last_stripe = 0;
-	int ret = 0;
+	int ret;
 	int i;
 
-	/* Discard always returns a bioc. */
-	ASSERT(bioc_ret);
-
 	em = btrfs_get_chunk_map(fs_info, logical, length);
 	if (IS_ERR(em))
-		return PTR_ERR(em);
+		return ERR_CAST(em);
 
 	map = em->map_lookup;
+
 	/* we don't discard raid56 yet */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		ret = -EOPNOTSUPP;
-		goto out;
-	}
+		goto out_free_map;
+}
 
 	offset = logical - em->start;
 	length = min_t(u64, em->start + em->len - logical, length);
@@ -5985,7 +5978,7 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 	 * device we have to walk to find the data, and stripe_index is
 	 * the number of our device in the stripe array
 	 */
-	num_stripes = 1;
+	*num_stripes = 1;
 	stripe_index = 0;
 	if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 			 BTRFS_BLOCK_GROUP_RAID10)) {
@@ -5995,7 +5988,7 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 			sub_stripes = map->sub_stripes;
 
 		factor = map->num_stripes / sub_stripes;
-		num_stripes = min_t(u64, map->num_stripes,
+		*num_stripes = min_t(u64, map->num_stripes,
 				    sub_stripes * stripe_cnt);
 		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
 		stripe_index *= sub_stripes;
@@ -6005,31 +5998,30 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 		last_stripe *= sub_stripes;
 	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1_MASK |
 				BTRFS_BLOCK_GROUP_DUP)) {
-		num_stripes = map->num_stripes;
+		*num_stripes = map->num_stripes;
 	} else {
 		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
 					&stripe_index);
 	}
 
-	bioc = alloc_btrfs_io_context(fs_info, num_stripes, 0);
-	if (!bioc) {
+	stripes = kcalloc(*num_stripes, sizeof(*stripes), GFP_NOFS);
+	if (!stripes) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_free_map;
 	}
 
-	for (i = 0; i < num_stripes; i++) {
-		bioc->stripes[i].physical =
+	for (i = 0; i < *num_stripes; i++) {
+		stripes[i].physical =
 			map->stripes[stripe_index].physical +
 			stripe_offset + stripe_nr * map->stripe_len;
-		bioc->stripes[i].dev = map->stripes[stripe_index].dev;
+		stripes[i].dev = map->stripes[stripe_index].dev;
 
 		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 				 BTRFS_BLOCK_GROUP_RAID10)) {
-			bioc->stripes[i].length = stripes_per_dev *
-				map->stripe_len;
+			stripes[i].length = stripes_per_dev * map->stripe_len;
 
 			if (i / sub_stripes < remaining_stripes)
-				bioc->stripes[i].length += map->stripe_len;
+				stripes[i].length += map->stripe_len;
 
 			/*
 			 * Special for the first stripe and
@@ -6040,17 +6032,17 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 			 *    off     end_off
 			 */
 			if (i < sub_stripes)
-				bioc->stripes[i].length -= stripe_offset;
+				stripes[i].length -= stripe_offset;
 
 			if (stripe_index >= last_stripe &&
 			    stripe_index <= (last_stripe +
 					     sub_stripes - 1))
-				bioc->stripes[i].length -= stripe_end_offset;
+				stripes[i].length -= stripe_end_offset;
 
 			if (i == sub_stripes - 1)
 				stripe_offset = 0;
 		} else {
-			bioc->stripes[i].length = length;
+			stripes[i].length = length;
 		}
 
 		stripe_index++;
@@ -6060,12 +6052,11 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	*bioc_ret = bioc;
-	bioc->map_type = map->type;
-	bioc->num_stripes = num_stripes;
-out:
 	free_extent_map(em);
-	return ret;
+	return stripes;
+out_free_map:
+	free_extent_map(em);
+	return ERR_PTR(ret);
 }
 
 /*
@@ -6208,7 +6199,6 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 					bioc->stripes + i;
 
 				new->physical = old->physical;
-				new->length = old->length;
 				new->dev = dev_replace->tgtdev;
 				bioc->tgtdev_map[i] = index_where_to_add;
 				index_where_to_add++;
@@ -6249,8 +6239,6 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 				bioc->stripes + num_stripes;
 
 			tgtdev_stripe->physical = physical_of_found;
-			tgtdev_stripe->length =
-				bioc->stripes[index_srcdev].length;
 			tgtdev_stripe->dev = dev_replace->tgtdev;
 			bioc->tgtdev_map[index_srcdev] = num_stripes;
 
@@ -6472,6 +6460,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		ASSERT(map->stripe_len == BTRFS_STRIPE_LEN);
 		if (need_raid_map && (need_full_stripe(op) || mirror_num > 1)) {
 			/* push stripe_nr back to the start of the full stripe */
 			stripe_nr = div64_u64(raid56_full_stripe_start,
@@ -6479,9 +6468,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 			/* RAID[56] write or recovery. Return all stripes */
 			num_stripes = map->num_stripes;
-			max_errors = nr_parity_stripes(map);
+			max_errors = btrfs_chunk_max_errors(map);
 
-			*length = map->stripe_len;
+			/* Return the length to the full stripe end */
+			*length = min(logical + *length,
+				      raid56_full_stripe_start + em->start +
+				      data_stripes * stripe_len) - logical;
 			stripe_index = 0;
 			stripe_offset = 0;
 		} else {
@@ -6604,10 +6596,6 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		      u64 logical, u64 *length,
 		      struct btrfs_io_context **bioc_ret, int mirror_num)
 {
-	if (op == BTRFS_MAP_DISCARD)
-		return __btrfs_map_block_for_discard(fs_info, logical,
-						     length, bioc_ret);
-
 	return __btrfs_map_block(fs_info, op, logical, length, bioc_ret,
 				 mirror_num, 0);
 }
@@ -6620,77 +6608,106 @@ int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	return __btrfs_map_block(fs_info, op, logical, length, bioc_ret, 0, 1);
 }
 
-static inline void btrfs_end_bioc(struct btrfs_io_context *bioc, struct bio *bio)
+static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_io_context *bioc)
+{
+	if (bioc->orig_bio->bi_opf & REQ_META)
+		return bioc->fs_info->endio_meta_workers;
+	return bioc->fs_info->endio_workers;
+}
+
+static void btrfs_end_bio_work(struct work_struct *work)
+{
+	struct btrfs_bio *bbio =
+		container_of(work, struct btrfs_bio, end_io_work);
+
+	bio_endio(&bbio->bio);
+}
+
+static void btrfs_end_bioc(struct btrfs_io_context *bioc, bool async)
 {
-	bio->bi_private = bioc->private;
-	bio->bi_end_io = bioc->end_io;
-	bio_endio(bio);
+	struct bio *orig_bio = bioc->orig_bio;
+	struct btrfs_bio *bbio = btrfs_bio(orig_bio);
+
+	bbio->mirror_num = bioc->mirror_num;
+	orig_bio->bi_private = bioc->private;
+	orig_bio->bi_end_io = bioc->end_io;
+
+	/*
+	 * Only send an error to the higher layers if it is beyond the tolerance
+	 * threshold.
+	 */
+	if (atomic_read(&bioc->error) > bioc->max_errors)
+		orig_bio->bi_status = BLK_STS_IOERR;
+	else
+		orig_bio->bi_status = BLK_STS_OK;
+
+	if (btrfs_op(orig_bio) == BTRFS_MAP_READ && async) {
+		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
+		queue_work(btrfs_end_io_wq(bioc), &bbio->end_io_work);
+	} else {
+		bio_endio(orig_bio);
+	}
 
 	btrfs_put_bioc(bioc);
 }
 
 static void btrfs_end_bio(struct bio *bio)
 {
-	struct btrfs_io_context *bioc = bio->bi_private;
-	int is_orig_bio = 0;
+	struct btrfs_io_stripe *stripe = bio->bi_private;
+	struct btrfs_io_context *bioc = stripe->bioc;
 
 	if (bio->bi_status) {
 		atomic_inc(&bioc->error);
 		if (bio->bi_status == BLK_STS_IOERR ||
 		    bio->bi_status == BLK_STS_TARGET) {
-			struct btrfs_device *dev = btrfs_bio(bio)->device;
-
-			ASSERT(dev->bdev);
 			if (btrfs_op(bio) == BTRFS_MAP_WRITE)
-				btrfs_dev_stat_inc_and_print(dev,
+				btrfs_dev_stat_inc_and_print(stripe->dev,
 						BTRFS_DEV_STAT_WRITE_ERRS);
 			else if (!(bio->bi_opf & REQ_RAHEAD))
-				btrfs_dev_stat_inc_and_print(dev,
+				btrfs_dev_stat_inc_and_print(stripe->dev,
 						BTRFS_DEV_STAT_READ_ERRS);
 			if (bio->bi_opf & REQ_PREFLUSH)
-				btrfs_dev_stat_inc_and_print(dev,
+				btrfs_dev_stat_inc_and_print(stripe->dev,
 						BTRFS_DEV_STAT_FLUSH_ERRS);
 		}
 	}
 
-	if (bio == bioc->orig_bio)
-		is_orig_bio = 1;
+	if (bio != bioc->orig_bio)
+		bio_put(bio);
 
 	btrfs_bio_counter_dec(bioc->fs_info);
-
-	if (atomic_dec_and_test(&bioc->stripes_pending)) {
-		if (!is_orig_bio) {
-			bio_put(bio);
-			bio = bioc->orig_bio;
-		}
-
-		btrfs_bio(bio)->mirror_num = bioc->mirror_num;
-		/* only send an error to the higher layers if it is
-		 * beyond the tolerance of the btrfs bio
-		 */
-		if (atomic_read(&bioc->error) > bioc->max_errors) {
-			bio->bi_status = BLK_STS_IOERR;
-		} else {
-			/*
-			 * this bio is actually up to date, we didn't
-			 * go over the max number of errors
-			 */
-			bio->bi_status = BLK_STS_OK;
-		}
-
-		btrfs_end_bioc(bioc, bio);
-	} else if (!is_orig_bio) {
-		bio_put(bio);
-	}
+	if (atomic_dec_and_test(&bioc->stripes_pending))
+		btrfs_end_bioc(bioc, true);
 }
 
-static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
-			      u64 physical, struct btrfs_device *dev)
+static void submit_stripe_bio(struct btrfs_io_context *bioc,
+			      struct bio *orig_bio, int dev_nr, bool clone)
 {
 	struct btrfs_fs_info *fs_info = bioc->fs_info;
+	struct btrfs_device *dev = bioc->stripes[dev_nr].dev;
+	u64 physical = bioc->stripes[dev_nr].physical;
+	struct bio *bio;
+
+	if (!dev || !dev->bdev ||
+	    test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) ||
+	    (btrfs_op(orig_bio) == BTRFS_MAP_WRITE &&
+	     !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
+		atomic_inc(&bioc->error);
+		if (atomic_dec_and_test(&bioc->stripes_pending))
+			btrfs_end_bioc(bioc, false);
+		return;
+	}
+
+	if (clone) {
+		bio = bio_alloc_clone(dev->bdev, orig_bio, GFP_NOFS, &fs_bio_set);
+	} else {
+		bio = orig_bio;
+		bio_set_dev(bio, dev->bdev);
+		btrfs_bio(bio)->device = dev;
+	}
 
-	bio->bi_private = bioc;
-	btrfs_bio(bio)->device = dev;
+	bioc->stripes[dev_nr].bioc = bioc;
+	bio->bi_private = &bioc->stripes[dev_nr];
 	bio->bi_end_io = btrfs_end_bio;
 	bio->bi_iter.bi_sector = physical >> 9;
 	/*
@@ -6708,8 +6725,8 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 		}
 	}
 	btrfs_debug_in_rcu(fs_info,
-	"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-		bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
+	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
+		__func__, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
 		(unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
 		dev->devid, bio->bi_iter.bi_size);
 
@@ -6719,66 +6736,39 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 	submit_bio(bio);
 }
 
-static void bioc_error(struct btrfs_io_context *bioc, struct bio *bio, u64 logical)
-{
-	atomic_inc(&bioc->error);
-	if (atomic_dec_and_test(&bioc->stripes_pending)) {
-		/* Should be the original bio. */
-		WARN_ON(bio != bioc->orig_bio);
-
-		btrfs_bio(bio)->mirror_num = bioc->mirror_num;
-		bio->bi_iter.bi_sector = logical >> 9;
-		if (atomic_read(&bioc->error) > bioc->max_errors)
-			bio->bi_status = BLK_STS_IOERR;
-		else
-			bio->bi_status = BLK_STS_OK;
-		btrfs_end_bioc(bioc, bio);
-	}
-}
-
-blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			   int mirror_num)
+void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
 {
-	struct btrfs_device *dev;
-	struct bio *first_bio = bio;
 	u64 logical = bio->bi_iter.bi_sector << 9;
-	u64 length = 0;
-	u64 map_length;
+	u64 length = bio->bi_iter.bi_size;
+	u64 map_length = length;
 	int ret;
 	int dev_nr;
 	int total_devs;
 	struct btrfs_io_context *bioc = NULL;
 
-	length = bio->bi_iter.bi_size;
-	map_length = length;
-
 	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
 				&map_length, &bioc, mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
+		bio->bi_status = errno_to_blk_status(ret);
+		bio_endio(bio);
+		return;
 	}
 
 	total_devs = bioc->num_stripes;
-	bioc->orig_bio = first_bio;
-	bioc->private = first_bio->bi_private;
-	bioc->end_io = first_bio->bi_end_io;
-	atomic_set(&bioc->stripes_pending, bioc->num_stripes);
+	bioc->orig_bio = bio;
+	bioc->private = bio->bi_private;
+	bioc->end_io = bio->bi_end_io;
+	atomic_set(&bioc->stripes_pending, total_devs);
 
 	if ((bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
 	    ((btrfs_op(bio) == BTRFS_MAP_WRITE) || (mirror_num > 1))) {
-		/* In this case, map_length has been set to the length of
-		   a single stripe; not the whole write */
-		if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-			ret = raid56_parity_write(bio, bioc, map_length);
-		} else {
-			ret = raid56_parity_recover(bio, bioc, map_length,
-						    mirror_num, 1);
-		}
-
-		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
+		if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+			raid56_parity_write(bio, bioc);
+		else
+			raid56_parity_recover(bio, bioc, mirror_num, true);
+		return;
 	}
 
 	if (map_length < length) {
@@ -6789,26 +6779,11 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	}
 
 	for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
-		dev = bioc->stripes[dev_nr].dev;
-		if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING,
-						   &dev->dev_state) ||
-		    (btrfs_op(first_bio) == BTRFS_MAP_WRITE &&
-		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
-			bioc_error(bioc, first_bio, logical);
-			continue;
-		}
-
-		if (dev_nr < total_devs - 1) {
-			bio = btrfs_bio_clone(dev->bdev, first_bio);
-		} else {
-			bio = first_bio;
-			bio_set_dev(bio, dev->bdev);
-		}
+		const bool should_clone = (dev_nr < total_devs - 1);
 
-		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
+		submit_stripe_bio(bioc, bio, dev_nr, should_clone);
 	}
 	btrfs_bio_counter_dec(fs_info);
-	return BLK_STS_OK;
 }
 
 static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args,
@@ -6966,11 +6941,12 @@ static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info,
 			      devid, uuid);
 }
 
-static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
+u64 btrfs_calc_stripe_length(const struct extent_map *em)
 {
-	const int data_stripes = calc_data_stripes(type, num_stripes);
+	const struct map_lookup *map = em->map_lookup;
+	const int data_stripes = calc_data_stripes(map->type, map->num_stripes);
 
-	return div_u64(chunk_len, data_stripes);
+	return div_u64(em->len, data_stripes);
 }
 
 #if BITS_PER_LONG == 32
@@ -7109,8 +7085,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 	map->type = type;
 	map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
 	map->verified_stripes = 0;
-	em->orig_block_len = calc_stripe_length(type, em->len,
-						map->num_stripes);
+	em->orig_block_len = btrfs_calc_stripe_length(em);
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -7236,7 +7211,8 @@ static int read_one_dev(struct extent_buffer *leaf,
 	u8 fs_uuid[BTRFS_FSID_SIZE];
 	u8 dev_uuid[BTRFS_UUID_SIZE];
 
-	devid = args.devid = btrfs_device_id(leaf, dev_item);
+	devid = btrfs_device_id(leaf, dev_item);
+	args.devid = devid;
 	read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item),
 			   BTRFS_UUID_SIZE);
 	read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
@@ -7865,11 +7841,7 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans)
 void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index)
 {
 	btrfs_dev_stat_inc(dev, index);
-	btrfs_dev_stat_print_on_error(dev);
-}
 
-static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev)
-{
 	if (!dev->dev_stats_valid)
 		return;
 	btrfs_err_rl_in_rcu(dev->fs_info,
@@ -8011,7 +7983,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 	}
 
 	map = em->map_lookup;
-	stripe_len = calc_stripe_length(map->type, em->len, map->num_stripes);
+	stripe_len = btrfs_calc_stripe_length(em);
 	if (physical_len != stripe_len) {
 		btrfs_err(fs_info,
 "dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
@@ -8021,6 +7993,16 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
+	/*
+	 * Very old mkfs.btrfs (before v4.1) will not respect the reserved
+	 * space. Although kernel can handle it without problem, better to warn
+	 * the users.
+	 */
+	if (physical_offset < BTRFS_DEVICE_RANGE_RESERVED)
+		btrfs_warn(fs_info,
+		"devid %llu physical %llu len %llu inside the reserved space",
+			   devid, physical_offset, physical_len);
+
 	for (i = 0; i < map->num_stripes; i++) {
 		if (map->stripes[i].dev->devid == devid &&
 		    map->stripes[i].physical == physical_offset) {