xfs: reserve quota for target dir expansion when renaming files

[ Upstream commit 41667260bc84db4dfe566e3f6ab6da5293d60d8d ]

XFS does not reserve quota for directory expansion when renaming
children into a directory.  This means that we don't reject the
expansion with EDQUOT when we're at or near a hard limit, which means
that unprivileged userspace can use rename() to exceed quota.

Rename operations don't always expand the target directory, and we allow
a rename to proceed with no space reservation if we don't need to add a
block to the target directory to handle the addition.  Moreover, the
unlink operation on the source directory generally does not expand the
directory (you'd have to free a block and then cause a btree split) and
it's probably of little consequence to leave the corner case that
renaming a file out of a directory can increase its size.

As with link and unlink, there is a further bug in that we do not
trigger the blockgc workers to try to clear space when we're out of
quota.

Because rename is its own special tricky animal, we'll patch xfs_rename
directly to reserve quota to the rename transaction.  We'll leave
cleaning up the rest of xfs_rename for the metadata directory tree
patchset.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Leah Rumancik <leah.rumancik@gmail.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f4dec7f6c6d0152cd4fe51065d4cbb06221b30dd..fb7a97cdf99f1a8782e4089e87ca1644a615f78f 100644 (file)
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3103,7 +3103,8 @@ xfs_rename(
        bool                    new_parent = (src_dp != target_dp);
        bool                    src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
        int                     spaceres;
-       int                     error;
+       bool                    retried = false;
+       int                     error, nospace_error = 0;
 
        trace_xfs_rename(src_dp, target_dp, src_name, target_name);
 
@@ -3127,9 +3128,12 @@ xfs_rename(
        xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip,
                                inodes, &num_inodes);
 
+retry:
+       nospace_error = 0;
        spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
        error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp);
        if (error == -ENOSPC) {
+               nospace_error = error;
                spaceres = 0;
                error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0,
                                &tp);
@@ -3183,6 +3187,31 @@ xfs_rename(
                                        target_dp, target_name, target_ip,
                                        spaceres);
 
+       /*
+        * Try to reserve quota to handle an expansion of the target directory.
+        * We'll allow the rename to continue in reservationless mode if we hit
+        * a space usage constraint.  If we trigger reservationless mode, save
+        * the errno if there isn't any free space in the target directory.
+        */
+       if (spaceres != 0) {
+               error = xfs_trans_reserve_quota_nblks(tp, target_dp, spaceres,
+                               0, false);
+               if (error == -EDQUOT || error == -ENOSPC) {
+                       if (!retried) {
+                               xfs_trans_cancel(tp);
+                               xfs_blockgc_free_quota(target_dp, 0);
+                               retried = true;
+                               goto retry;
+                       }
+
+                       nospace_error = error;
+                       spaceres = 0;
+                       error = 0;
+               }
+               if (error)
+                       goto out_trans_cancel;
+       }
+
        /*
         * Check for expected errors before we dirty the transaction
         * so we can return an error without a transaction abort.
@@ -3429,6 +3458,8 @@ out_trans_cancel:
 out_release_wip:
        if (wip)
                xfs_irele(wip);
+       if (error == -ENOSPC && nospace_error)
+               error = nospace_error;
        return error;
 }