btrfs: log csums for all modified extents

Amir reported a bug discovered by his cleaned up version of my
dm-log-writes xfstests where we were missing csums at certain replay
points.  This is because fsx was doing an msync(), which essentially
fsync()'s a specific range of a file.  We will log all modified extents,
but only search for the checksums in the range we are being asked to
sync.  We cannot simply log the extents in the range we're being asked
because we are logging the inode item as it is currently, which if it
has had a i_size update before the msync means we will miss extents when
replaying.  We could possibly get around this by marking the inode with
the transaction that extended the i_size to see if we have this case,
but this would be racy and we'd have to lock the whole range of the
inode to make sure we didn't have an ordered extent outside of our range
that was in the middle of completing.

Fix this simply by keeping track of the modified extents range and
logging the csums for the entire range of extents that we are logging.
This makes the xfstest pass.

Reported-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ad7f4bab640be36d9f43b8b2f3371a7bd871738f..c800d067fcbf0c8eec90c479eefe5df13e2dc945 100644 (file)
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
        struct extent_map *em, *n;
        struct list_head extents;
        struct extent_map_tree *tree = &inode->extent_tree;
+       u64 logged_start, logged_end;
        u64 test_gen;
        int ret = 0;
        int num = 0;
@@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
        down_write(&inode->dio_sem);
        write_lock(&tree->lock);
        test_gen = root->fs_info->last_trans_committed;
+       logged_start = start;
+       logged_end = end;
 
        list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
                list_del_init(&em->list);
-
                /*
                 * Just an arbitrary number, this can be really CPU intensive
                 * once we start getting a lot of extents, and really once we
@@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 
                if (em->generation <= test_gen)
                        continue;
+
+               if (em->start < logged_start)
+                       logged_start = em->start;
+               if ((em->start + em->len - 1) > logged_end)
+                       logged_end = em->start + em->len - 1;
+
                /* Need a ref to keep it from getting evicted from cache */
                refcount_inc(&em->refs);
                set_bit(EXTENT_FLAG_LOGGING, &em->flags);
@@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
        }
 
        list_sort(NULL, &extents, extent_cmp);
-       btrfs_get_logged_extents(inode, logged_list, start, end);
+       btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
        /*
         * Some ordered extents started by fsync might have completed
         * before we could collect them into the list logged_list, which