xfs: rework collapse range into an atomic operation

The collapse range operation uses a unique transaction and ilock
cycle for the hole punch and each extent shift iteration of the
overall operation. While the hole punch is safe as a separate
operation due to the iolock, cycling the ilock after each extent
shift is risky w.r.t. concurrent operations, similar to insert range.

To avoid this problem, make collapse range atomic with respect to
ilock. Hold the ilock across the entire operation, replace the
individual transactions with a single rolling transaction sequence
and finish dfops on each iteration to perform pending frees and roll
the transaction. Remove the unnecessary quota reservation as
collapse range can only ever merge extents (and thus remove extent
records and potentially free bmap blocks). The dfops call
automatically relogs the inode to keep it moving in the log. This
guarantees that nothing else can change the extent mapping of an
inode while a collapse range operation is in progress.

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

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index f6787e844a04e0130c5b2fa0c7ef6590c8c8d487..3df4d0af9f226d0573b635072e11d530d8ab3bb6 100644 (file)
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1062,7 +1062,6 @@ xfs_collapse_file_space(
        int                     error;
        xfs_fileoff_t           next_fsb = XFS_B_TO_FSB(mp, offset + len);
        xfs_fileoff_t           shift_fsb = XFS_B_TO_FSB(mp, len);
-       uint                    resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
        bool                    done = false;
 
        ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
@@ -1078,32 +1077,34 @@ xfs_collapse_file_space(
        if (error)
                return error;
 
-       while (!error && !done) {
-               error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
-                                       &tp);
-               if (error)
-                       break;
+       error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
+       if (error)
+               return error;
 
-               xfs_ilock(ip, XFS_ILOCK_EXCL);
-               error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
-                               ip->i_gdquot, ip->i_pdquot, resblks, 0,
-                               XFS_QMOPT_RES_REGBLKS);
-               if (error)
-                       goto out_trans_cancel;
-               xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+       xfs_ilock(ip, XFS_ILOCK_EXCL);
+       xfs_trans_ijoin(tp, ip, 0);
 
+       while (!done) {
                error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
                                &done);
                if (error)
                        goto out_trans_cancel;
+               if (done)
+                       break;
 
-               error = xfs_trans_commit(tp);
+               /* finish any deferred frees and roll the transaction */
+               error = xfs_defer_finish(&tp);
+               if (error)
+                       goto out_trans_cancel;
        }
 
+       error = xfs_trans_commit(tp);
+       xfs_iunlock(ip, XFS_ILOCK_EXCL);
        return error;
 
 out_trans_cancel:
        xfs_trans_cancel(tp);
+       xfs_iunlock(ip, XFS_ILOCK_EXCL);
        return error;
 }