COW writes remove the amount overwritten either directly for delalloc
reservations, or in earlier deferred transactions than adding the new
amount back in the bmap map transaction. This means st_blocks on an
inode where all data is overwritten using the COW path can temporarily
show a 0 st_blocks. This can easily be reproduced with the pending
zoned device support where all writes use this path and trips the
check in generic/615, but could also happen on a reflink file without
that.
Fix this by temporarily add the pending blocks to be mapped to
i_delayed_blks while the item is queued.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
Changes since v2:
- even better comments!
Changes since v1:
- slightly more and slightly improved comments
fs/xfs/libxfs/xfs_bmap.c | 1 +
fs/xfs/xfs_bmap_item.c | 17 +++++++++++++++++
2 files changed, 18 insertions(+)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 88c62e1158ac73..685a3278878ada 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4895,6 +4895,7 @@ xfs_bmapi_remap(
}
ip->i_nblocks += len;
+ ip->i_delayed_blks -= len; /* see xfs_bmap_defer_add */
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (ifp->if_format == XFS_DINODE_FMT_BTREE)
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 9a7e97a922b6d3..43be8e04cf0ead 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -357,6 +357,17 @@ xfs_bmap_defer_add(
trace_xfs_bmap_defer(bi);
xfs_bmap_update_get_group(tp->t_mountp, bi);
+
+ /*
+ * Ensure the deferred mapping is pre-recorded in i_delayed_blks.
+ *
+ * Otherwise stat can report zero blocks for an inode that actually has
+ * data when the entire mapping is in the process of being overwritten
+ * using the out of place write path. This is undone in xfs_bmapi_remap
+ * after it has incremented di_nblocks for a successful operation.
+ */
+ if (bi->bi_type == XFS_BMAP_MAP)
+ bi->bi_owner->i_delayed_blks += bi->bi_bmap.br_blockcount;
xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
}
@@ -381,6 +392,9 @@ xfs_bmap_update_cancel_item(
{
struct xfs_bmap_intent *bi = bi_entry(item);
+ if (bi->bi_type == XFS_BMAP_MAP)
+ bi->bi_owner->i_delayed_blks -= bi->bi_bmap.br_blockcount;
+
xfs_bmap_update_put_group(bi);
kmem_cache_free(xfs_bmap_intent_cache, bi);
}
@@ -478,6 +492,9 @@ xfs_bui_recover_work(
bi->bi_owner = *ipp;
xfs_bmap_update_get_group(mp, bi);
+ /* see xfs_bmap_defer_add for details */
+ if (bi->bi_type == XFS_BMAP_MAP)
+ bi->bi_owner->i_delayed_blks += bi->bi_bmap.br_blockcount;
xfs_defer_add_item(dfp, &bi->bi_list);
return bi;
}
--
2.43.0
