Merge tag 'xfs-5.17-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:
 "I was auditing operations in XFS that clear file privileges, and
  realized that XFS' fallocate implementation drops suid/sgid but
  doesn't clear file capabilities the same way that file writes and
  reflink do.

  There are VFS helpers that do it correctly, so refactor XFS to use
  them. I also noticed that we weren't flushing the log at the correct
  point in the fallocate operation, so that's fixed too.

  Summary:

   - Fix fallocate so that it drops all file privileges when files are
     modified instead of open-coding that incompletely.

   - Fix fallocate to flush the log if the caller wanted synchronous
     file updates"

* tag 'xfs-5.17-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: ensure log flush at the end of a synchronous fallocate call
  xfs: move xfs_update_prealloc_flags() to xfs_pnfs.c
  xfs: set prealloc flag in xfs_alloc_file_space()
  xfs: fallocate() should call file_modified()
  xfs: remove XFS_PREALLOC_SYNC
  xfs: reject crazy array sizes being fed to XFS_IOC_GETBMAP*

1 files changed, 39 insertions, 3 deletions

diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index d6334abbc0b3..4abe17312c2b 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -71,6 +71,40 @@ xfs_fs_get_uuid(
 }
 
 /*
+ * We cannot use file based VFS helpers such as file_modified() to update
+ * inode state as we modify the data/metadata in the inode here. Hence we have
+ * to open code the timestamp updates and SUID/SGID stripping. We also need
+ * to set the inode prealloc flag to ensure that the extents we allocate are not
+ * removed if the inode is reclaimed from memory before xfs_fs_block_commit()
+ * is from the client to indicate that data has been written and the file size
+ * can be extended.
+ */
+static int
+xfs_fs_map_update_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
+			0, 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	VFS_I(ip)->i_mode &= ~S_ISUID;
+	if (VFS_I(ip)->i_mode & S_IXGRP)
+		VFS_I(ip)->i_mode &= ~S_ISGID;
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	ip->i_diflags |= XFS_DIFLAG_PREALLOC;
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return xfs_trans_commit(tp);
+}
+
+/*
  * Get a layout for the pNFS client.
  */
 int
@@ -164,10 +198,12 @@ xfs_fs_map_blocks(
 		 * that the blocks allocated and handed out to the client are
 		 * guaranteed to be present even after a server crash.
 		 */
-		error = xfs_update_prealloc_flags(ip,
-				XFS_PREALLOC_SET | XFS_PREALLOC_SYNC);
+		error = xfs_fs_map_update_inode(ip);
+		if (!error)
+			error = xfs_log_force_inode(ip);
 		if (error)
 			goto out_unlock;
+
 	} else {
 		xfs_iunlock(ip, lock_flags);
 	}
@@ -255,7 +291,7 @@ xfs_fs_commit_blocks(
 		length = end - start;
 		if (!length)
 			continue;
-	
+
 		/*
 		 * Make sure reads through the pagecache see the new data.
 		 */