Btrfs: implement repair function when direct read fails

This patch implement data repair function when direct read fails.

The detail of the implementation is:
- When we find the data is not right, we try to read the data from the other
  mirror.
- When the io on the mirror ends, we will insert the endio work into the
  dedicated btrfs workqueue, not common read endio workqueue, because the
  original endio work is still blocked in the btrfs endio workqueue, if we
  insert the endio work of the io on the mirror into that workqueue, deadlock
  would happen.
- After we get right data, we write it back to the corrupted mirror.
- And if the data on the new mirror is still corrupted, we will try next
  mirror until we read right data or all the mirrors are traversed.
- After the above work, we set the uptodate flag according to the result.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

1 files changed, 7 insertions, 5 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 05533c99f89d..9e2ef27672e5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1962,7 +1962,7 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
                 SetPageUptodate(page);
 }
 
-static int free_io_failure(struct inode *inode, struct io_failure_record *rec)
+int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 {
         int ret;
         int err = 0;
@@ -2081,8 +2081,8 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
  * each time an IO finishes, we do a fast check in the IO failure tree
  * to see if we need to process or clean up an io_failure_record
  */
-static int clean_io_failure(struct inode *inode, u64 start,
-                            struct page *page, unsigned int pg_offset)
+int clean_io_failure(struct inode *inode, u64 start, struct page *page,
+                     unsigned int pg_offset)
 {
         u64 private;
         u64 private_failure;
@@ -2291,7 +2291,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
                                     struct io_failure_record *failrec,
                                     struct page *page, int pg_offset, int icsum,
-                                    bio_end_io_t *endio_func)
+                                    bio_end_io_t *endio_func, void *data)
 {
         struct bio *bio;
         struct btrfs_io_bio *btrfs_failed_bio;
@@ -2305,6 +2305,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
         bio->bi_iter.bi_sector = failrec->logical >> 9;
         bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
         bio->bi_iter.bi_size = 0;
+        bio->bi_private = data;
 
         btrfs_failed_bio = btrfs_io_bio(failed_bio);
         if (btrfs_failed_bio->csum) {
@@ -2362,7 +2363,8 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
         phy_offset >>= inode->i_sb->s_blocksize_bits;
         bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
                                       start - page_offset(page),
-                                      (int)phy_offset, failed_bio->bi_end_io);
+                                      (int)phy_offset, failed_bio->bi_end_io,
+                                      NULL);
         if (!bio) {
                 free_io_failure(inode, failrec);
                 return -EIO;