xfs: reorder zeroing and flushing sequence in truncate

Currently zeroing out blocks and waiting for writeout is a bit of a mess in
truncate.  This patch gives it a clear order in preparation for the iomap
path:

 (1) we first wait for any direct I/O to complete to prevent any races
     for it
 (2) we then perform the actual zeroing, and only use the truncate_page
     helpers for truncating down.  The truncate up case already is
     handled by the separate call to xfs_zero_eof.
 (3) only then we write back dirty data, as zeroing block may cause
     dirty pages when using either xfs_zero_eof or the new iomap
     infrastructure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

1 files changed, 19 insertions, 14 deletions

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index c5d4eba6972e..1a5ca4b4a866 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -801,20 +801,35 @@ xfs_setattr_size(
                 return error;
 
         /*
+         * Wait for all direct I/O to complete.
+         */
+        inode_dio_wait(inode);
+
+        /*
          * File data changes must be complete before we start the transaction to
          * modify the inode.  This needs to be done before joining the inode to
          * the transaction because the inode cannot be unlocked once it is a
          * part of the transaction.
          *
-         * Start with zeroing any data block beyond EOF that we may expose on
-         * file extension.
+         * Start with zeroing any data beyond EOF that we may expose on file
+         * extension, or zeroing out the rest of the block on a downward
+         * truncate.
          */
         if (newsize > oldsize) {
                 error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
-                if (error)
-                        return error;
+        } else {
+                if (IS_DAX(inode)) {
+                        error = dax_truncate_page(inode, newsize,
+                                        xfs_get_blocks_direct);
+                } else {
+                        error = block_truncate_page(inode->i_mapping, newsize,
+                                        xfs_get_blocks);
+                }
         }
 
+        if (error)
+                return error;
+
         /*
          * We are going to log the inode size change in this transaction so
          * any previous writes that are beyond the on disk EOF and the new
@@ -831,9 +846,6 @@ xfs_setattr_size(
                         return error;
         }
 
-        /* Now wait for all direct I/O to complete. */
-        inode_dio_wait(inode);
-
         /*
          * We've already locked out new page faults, so now we can safely remove
          * pages from the page cache knowing they won't get refaulted until we
@@ -851,13 +863,6 @@ xfs_setattr_size(
          * to hope that the caller sees ENOMEM and retries the truncate
          * operation.
          */
-        if (IS_DAX(inode))
-                error = dax_truncate_page(inode, newsize, xfs_get_blocks_direct);
-        else
-                error = block_truncate_page(inode->i_mapping, newsize,
-                                            xfs_get_blocks);
-        if (error)
-                return error;
         truncate_setsize(inode, newsize);
 
         error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);