Btrfs: Fix the multi-bio code to save the original bio for completion

The multi-bio code is responsible for duplicating blocks in raid1 and
single spindle duplication.  It has counters to make sure all of
the locations for a given extent are properly written before io completion
is returned to the higher layers.

But, it didn't always complete the same bio it was given, sometimes a
clone was completed instead.  This lead to problems with the async
work queues because they saved a pointer to the bio in a struct off
bi_private.

The fix is to remember the original bio and only complete that one.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0de51e37e7896771cdf4615cc5ca499f3a1b3022..09311b3066dfd6c7ac1dce4641b1b7f82eae0a07 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2070,6 +2070,7 @@ static int end_bio_multi_stripe(struct bio *bio,
 #endif
 {
        struct btrfs_multi_bio *multi = bio->bi_private;
+       int is_orig_bio = 0;
 
 #if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,23)
        if (bio->bi_size)
@@ -2078,7 +2079,14 @@ static int end_bio_multi_stripe(struct bio *bio,
        if (err)
                atomic_inc(&multi->error);
 
+       if (bio == multi->orig_bio)
+               is_orig_bio = 1;
+
        if (atomic_dec_and_test(&multi->stripes_pending)) {
+               if (!is_orig_bio) {
+                       bio_put(bio);
+                       bio = multi->orig_bio;
+               }
                bio->bi_private = multi->private;
                bio->bi_end_io = multi->end_io;
                /* only send an error to the higher layers if it is
@@ -2101,7 +2109,7 @@ static int end_bio_multi_stripe(struct bio *bio,
 #else
                bio_endio(bio, err);
 #endif
-       } else {
+       } else if (!is_orig_bio) {
                bio_put(bio);
        }
 #if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,23)
@@ -2196,6 +2204,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
        }
        multi->end_io = first_bio->bi_end_io;
        multi->private = first_bio->bi_private;
+       multi->orig_bio = first_bio;
        atomic_set(&multi->stripes_pending, multi->num_stripes);
 
        while(dev_nr < total_devs) {

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 48a44f7a938562ac13157d2d1ce3f7a5cb763fc0..c50e50580b51124dec6b67c110f6edef2fa0557a 100644 (file)
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -95,6 +95,7 @@ struct btrfs_bio_stripe {
 struct btrfs_multi_bio {
        atomic_t stripes_pending;
        bio_end_io_t *end_io;
+       struct bio *orig_bio;
        void *private;
        atomic_t error;
        int max_errors;