Btrfs: fix meta data raid-repair merge problem

Commit 4a54c8c16 introduced raid-repair, killing the individual
readpage_io_failed_hook entries from inode.c and disk-io.c. Commit
4bb31e92 introduced new readahead code, adding a readpage_io_failed_hook to
disk-io.c.

The raid-repair commit had logic to disable raid-repair, if
readpage_io_failed_hook is set. Thus, the readahead commit effectively
disabled raid-repair for meta data.

This commit changes the logic to always attempt raid-repair when needed and
call the readpage_io_failed_hook in case raid-repair fails. This is much
more straight forward and should have been like that from the beginning.

Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
Reported-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9472d3de5e52aab2142766767d863ca46f34147d..be1bf627a14b292655ad10a4478c015d2bff9a44 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2287,14 +2287,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                if (!uptodate) {
                        int failed_mirror;
                        failed_mirror = (int)(unsigned long)bio->bi_bdev;
-                       if (tree->ops && tree->ops->readpage_io_failed_hook)
-                               ret = tree->ops->readpage_io_failed_hook(
-                                               bio, page, start, end,
-                                               failed_mirror, state);
-                       else
-                               ret = bio_readpage_error(bio, page, start, end,
-                                                        failed_mirror, NULL);
+                       /*
+                        * The generic bio_readpage_error handles errors the
+                        * following way: If possible, new read requests are
+                        * created and submitted and will end up in
+                        * end_bio_extent_readpage as well (if we're lucky, not
+                        * in the !uptodate case). In that case it returns 0 and
+                        * we just go on with the next page in our bio. If it
+                        * can't handle the error it will return -EIO and we
+                        * remain responsible for that page.
+                        */
+                       ret = bio_readpage_error(bio, page, start, end,
+                                                       failed_mirror, NULL);
                        if (ret == 0) {
+error_handled:
                                uptodate =
                                        test_bit(BIO_UPTODATE, &bio->bi_flags);
                                if (err)
@@ -2302,6 +2308,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                                uncache_state(&cached);
                                continue;
                        }
+                       if (tree->ops && tree->ops->readpage_io_failed_hook) {
+                               ret = tree->ops->readpage_io_failed_hook(
+                                                       bio, page, start, end,
+                                                       failed_mirror, state);
+                               if (ret == 0)
+                                       goto error_handled;
+                       }
                }
 
                if (uptodate) {