btrfs: introduce a new helper to submit write bio for repair

Both scrub and read-repair are utilizing a special repair writes that:

- Only writes back to a single device
  Even for read-repair on RAID56, we only update the corrupted data
  stripe itself, not triggering the full RMW path.

- Requires a valid @mirror_num
  For RAID56 case, only @mirror_num == 1 is valid.
  For non-RAID56 cases, we need @mirror_num to locate our stripe.

- No data csum generation needed

These two call sites still have some differences though:

- Read-repair goes plain bio
  It doesn't need a full btrfs_bio, and goes submit_bio_wait().

- New scrub repair would go btrfs_bio
  To simplify both read and write path.

So here this patch would:

- Introduce a common helper, btrfs_map_repair_block()
  Due to the single device nature, we can use an on-stack
  btrfs_io_stripe to pass device and its physical bytenr.

- Introduce a new interface, btrfs_submit_repair_bio(), for later scrub
  code
  This is for the incoming scrub code.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/bio.c

@@ -735,12 +735,9 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 			    u64 length, u64 logical, struct page *page,
 			    unsigned int pg_offset, int mirror_num)
 {
-	struct btrfs_device *dev;
+	struct btrfs_io_stripe smap = { 0 };
 	struct bio_vec bvec;
 	struct bio bio;
-	u64 map_length = 0;
-	u64 sector;
-	struct btrfs_io_context *bioc = NULL;
 	int ret = 0;
 
 	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
@@ -749,68 +746,38 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	if (btrfs_repair_one_zone(fs_info, logical))
 		return 0;
 
-	map_length = length;
-
 	/*
 	 * Avoid races with device replace and make sure our bioc has devices
 	 * associated to its stripes that don't go away while we are doing the
 	 * read repair operation.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
-	if (btrfs_is_parity_mirror(fs_info, logical, length)) {
-		/*
-		 * Note that we don't use BTRFS_MAP_WRITE because it's supposed
-		 * to update all raid stripes, but here we just want to correct
-		 * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
-		 * stripe's dev and sector.
-		 */
-		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
-				      &map_length, &bioc, 0);
-		if (ret)
-			goto out_counter_dec;
-		ASSERT(bioc->mirror_num == 1);
-	} else {
-		ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
-				      &map_length, &bioc, mirror_num);
-		if (ret)
-			goto out_counter_dec;
-		/*
-		 * This happens when dev-replace is also running, and the
-		 * mirror_num indicates the dev-replace target.
-		 *
-		 * In this case, we don't need to do anything, as the read
-		 * error just means the replace progress hasn't reached our
-		 * read range, and later replace routine would handle it well.
-		 */
-		if (mirror_num != bioc->mirror_num)
-			goto out_counter_dec;
-	}
-
-	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
-	dev = bioc->stripes[bioc->mirror_num - 1].dev;
-	btrfs_put_bioc(bioc);
+	ret = btrfs_map_repair_block(fs_info, &smap, logical, length, mirror_num);
+	if (ret < 0)
+		goto out_counter_dec;
 
-	if (!dev || !dev->bdev ||
-	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
+	if (!smap.dev->bdev ||
+	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &smap.dev->dev_state)) {
 		ret = -EIO;
 		goto out_counter_dec;
 	}
 
-	bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
-	bio.bi_iter.bi_sector = sector;
+	bio_init(&bio, smap.dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
+	bio.bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
 	__bio_add_page(&bio, page, length, pg_offset);
 
 	btrfsic_check_bio(&bio);
 	ret = submit_bio_wait(&bio);
 	if (ret) {
 		/* try to remap that extent elsewhere? */
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
+		btrfs_dev_stat_inc_and_print(smap.dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		goto out_bio_uninit;
 	}
 
 	btrfs_info_rl_in_rcu(fs_info,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
-			     ino, start, btrfs_dev_name(dev), sector);
+			     ino, start, btrfs_dev_name(smap.dev),
+			     smap.physical >> SECTOR_SHIFT);
 	ret = 0;
 
 out_bio_uninit:
@@ -820,6 +787,45 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	return ret;
 }
 
+/*
+ * Submit a btrfs_bio based repair write.
+ *
+ * If @dev_replace is true, the write would be submitted to dev-replace target.
+ */
+void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace)
+{
+	struct btrfs_fs_info *fs_info = bbio->fs_info;
+	u64 logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 length = bbio->bio.bi_iter.bi_size;
+	struct btrfs_io_stripe smap = { 0 };
+	int ret;
+
+	ASSERT(fs_info);
+	ASSERT(mirror_num > 0);
+	ASSERT(btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE);
+	ASSERT(!bbio->inode);
+
+	btrfs_bio_counter_inc_blocked(fs_info);
+	ret = btrfs_map_repair_block(fs_info, &smap, logical, length, mirror_num);
+	if (ret < 0)
+		goto fail;
+
+	if (dev_replace) {
+		if (btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE && btrfs_is_zoned(fs_info)) {
+			bbio->bio.bi_opf &= ~REQ_OP_WRITE;
+			bbio->bio.bi_opf |= REQ_OP_ZONE_APPEND;
+		}
+		ASSERT(smap.dev == fs_info->dev_replace.srcdev);
+		smap.dev = fs_info->dev_replace.tgtdev;
+	}
+	__btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num);
+	return;
+
+fail:
+	btrfs_bio_counter_dec(fs_info);
+	btrfs_bio_end_io(bbio, errno_to_blk_status(ret));
+}
+
 int __init btrfs_bioset_init(void)
 {
 	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,

fs/btrfs/bio.h

@@ -98,6 +98,7 @@ static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 #define REQ_BTRFS_CGROUP_PUNT			REQ_FS_PRIVATE
 
 void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num);
+void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
 int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 			    u64 length, u64 logical, struct page *page,
 			    unsigned int pg_offset, int mirror_num);

fs/btrfs/raid56.h

@@ -170,6 +170,11 @@ static inline int nr_data_stripes(const struct map_lookup *map)
 	return map->num_stripes - btrfs_nr_parity_stripes(map->type);
 }
 
+static inline int nr_bioc_data_stripes(const struct btrfs_io_context *bioc)
+{
+	return bioc->num_stripes - btrfs_nr_parity_stripes(bioc->map_type);
+}
+
 #define RAID5_P_STRIPE ((u64)-2)
 #define RAID6_Q_STRIPE ((u64)-1)
 

fs/btrfs/volumes.c

@@ -8019,3 +8019,76 @@ bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical)
 
 	return true;
 }
+
+static void map_raid56_repair_block(struct btrfs_io_context *bioc,
+				    struct btrfs_io_stripe *smap,
+				    u64 logical)
+{
+	int data_stripes = nr_bioc_data_stripes(bioc);
+	int i;
+
+	for (i = 0; i < data_stripes; i++) {
+		u64 stripe_start = bioc->full_stripe_logical +
+				   (i << BTRFS_STRIPE_LEN_SHIFT);
+
+		if (logical >= stripe_start &&
+		    logical < stripe_start + BTRFS_STRIPE_LEN)
+			break;
+	}
+	ASSERT(i < data_stripes);
+	smap->dev = bioc->stripes[i].dev;
+	smap->physical = bioc->stripes[i].physical +
+			((logical - bioc->full_stripe_logical) &
+			 BTRFS_STRIPE_LEN_MASK);
+}
+
+/*
+ * Map a repair write into a single device.
+ *
+ * A repair write is triggered by read time repair or scrub, which would only
+ * update the contents of a single device.
+ * Not update any other mirrors nor go through RMW path.
+ *
+ * Callers should ensure:
+ *
+ * - Call btrfs_bio_counter_inc_blocked() first
+ * - The range does not cross stripe boundary
+ * - Has a valid @mirror_num passed in.
+ */
+int btrfs_map_repair_block(struct btrfs_fs_info *fs_info,
+			   struct btrfs_io_stripe *smap, u64 logical,
+			   u32 length, int mirror_num)
+{
+	struct btrfs_io_context *bioc = NULL;
+	u64 map_length = length;
+	int mirror_ret = mirror_num;
+	int ret;
+
+	ASSERT(mirror_num > 0);
+
+	ret = __btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length,
+				&bioc, smap, &mirror_ret, true);
+	if (ret < 0)
+		return ret;
+
+	/* The map range should not cross stripe boundary. */
+	ASSERT(map_length >= length);
+
+	/* Already mapped to single stripe. */
+	if (!bioc)
+		goto out;
+
+	/* Map the RAID56 multi-stripe writes to a single one. */
+	if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		map_raid56_repair_block(bioc, smap, logical);
+		goto out;
+	}
+
+	ASSERT(mirror_num <= bioc->num_stripes);
+	smap->dev = bioc->stripes[mirror_num - 1].dev;
+	smap->physical = bioc->stripes[mirror_num - 1].physical;
+out:
+	btrfs_put_bioc(bioc);
+	ASSERT(smap->dev);
+	return 0;
+}

fs/btrfs/volumes.h

@@ -587,6 +587,9 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		      struct btrfs_io_context **bioc_ret,
 		      struct btrfs_io_stripe *smap, int *mirror_num_ret,
 		      int need_raid_map);
+int btrfs_map_repair_block(struct btrfs_fs_info *fs_info,
+			   struct btrfs_io_stripe *smap, u64 logical,
+			   u32 length, int mirror_num);
 struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes);