btrfs: move repair_io_failure to bio.c

repair_io_failure ties directly into all the glory low-level details of
mapping a bio with a logic address to the actual physical location.
Move it right below btrfs_submit_bio to keep all the related logic
together.

Also move btrfs_repair_eb_io_failure to its caller in disk-io.c now that
repair_io_failure is available in a header.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 90 insertions, 0 deletions

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 9e881dc91bae..b8fb7ef6b520 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -276,6 +276,96 @@ void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror
 	}
 }
 
+/*
+ * Submit a repair write.
+ *
+ * This bypasses btrfs_submit_bio deliberately, as that writes all copies in a
+ * RAID setup.  Here we only want to write the one bad copy, so we do the
+ * mapping ourselves and submit the bio directly.
+ *
+ * The I/O is issued sychronously to block the repair read completion from
+ * freeing the bio.
+ */
+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 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));
+	BUG_ON(!mirror_num);
+
+	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;
+		BUG_ON(mirror_num != bioc->mirror_num);
+	}
+
+	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
+	dev = bioc->stripes[bioc->mirror_num - 1].dev;
+	btrfs_put_bioc(bioc);
+
+	if (!dev || !dev->bdev ||
+	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &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_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);
+		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);
+	ret = 0;
+
+out_bio_uninit:
+	bio_uninit(&bio);
+out_counter_dec:
+	btrfs_bio_counter_dec(fs_info);
+	return ret;
+}
+
 int __init btrfs_bioset_init(void)
 {
 	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,