xfs: force writes to delalloc regions to unwritten

When writing to a delalloc region in the data fork, commit the new
allocations (of the da reservation) as unwritten so that the mappings
are only marked written once writeback completes successfully.  This
fixes the problem of stale data exposure if the system goes down during
targeted writeback of a specific region of a file, as tested by
generic/042.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index edc63dba007f4a96fa55a7de2a968f17523ee5d2..667cdd0dfdf4a3e2317025bf6c6847fc9fd34c52 100644 (file)
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4145,17 +4145,7 @@ xfs_bmapi_allocate(
        bma->got.br_blockcount = bma->length;
        bma->got.br_state = XFS_EXT_NORM;
 
-       /*
-        * In the data fork, a wasdelay extent has been initialized, so
-        * shouldn't be flagged as unwritten.
-        *
-        * For the cow fork, however, we convert delalloc reservations
-        * (extents allocated for speculative preallocation) to
-        * allocated unwritten extents, and only convert the unwritten
-        * extents to real extents when we're about to write the data.
-        */
-       if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) &&
-           (bma->flags & XFS_BMAPI_PREALLOC))
+       if (bma->flags & XFS_BMAPI_PREALLOC)
                bma->got.br_state = XFS_EXT_UNWRITTEN;
 
        if (bma->wasdel)
@@ -4563,8 +4553,23 @@ xfs_bmapi_convert_delalloc(
        bma.offset = bma.got.br_startoff;
        bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount, MAXEXTLEN);
        bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
+
+       /*
+        * When we're converting the delalloc reservations backing dirty pages
+        * in the page cache, we must be careful about how we create the new
+        * extents:
+        *
+        * New CoW fork extents are created unwritten, turned into real extents
+        * when we're about to write the data to disk, and mapped into the data
+        * fork after the write finishes.  End of story.
+        *
+        * New data fork extents must be mapped in as unwritten and converted
+        * to real extents after the write succeeds to avoid exposing stale
+        * disk contents if we crash.
+        */
+       bma.flags = XFS_BMAPI_PREALLOC;
        if (whichfork == XFS_COW_FORK)
-               bma.flags = XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC;
+               bma.flags |= XFS_BMAPI_COWFORK;
 
        if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev))
                bma.prev.br_startoff = NULLFILEOFF;