Merge tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fs hole punching vs cache filling race fixes from Jan Kara:
 "Fix races leading to possible data corruption or stale data exposure
  in multiple filesystems when hole punching races with operations such
  as readahead.

  This is the series I was sending for the last merge window but with
  your objection fixed - now filemap_fault() has been modified to take
  invalidate_lock only when we need to create new page in the page cache
  and / or bring it uptodate"

* tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  filesystems/locking: fix Malformed table warning
  cifs: Fix race between hole punch and page fault
  ceph: Fix race between hole punch and page fault
  fuse: Convert to using invalidate_lock
  f2fs: Convert to using invalidate_lock
  zonefs: Convert to using invalidate_lock
  xfs: Convert double locking of MMAPLOCK to use VFS helpers
  xfs: Convert to use invalidate_lock
  xfs: Refactor xfs_isilocked()
  ext2: Convert to using invalidate_lock
  ext4: Convert to use mapping->invalidate_lock
  mm: Add functions to lock invalidate_lock for two mappings
  mm: Protect operations adding pages to page cache with invalidate_lock
  documentation: Sync file_operations members with reality
  mm: Fix comments mentioning i_mutex

1 files changed, 8 insertions, 5 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index cc3cfb12df53..3dfbdcdb0d1c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1302,7 +1302,7 @@ xfs_file_llseek(
  *
  * mmap_lock (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmaplock (XFS - truncate serialisation)
+ *     invalidate_lock (vfs/XFS_MMAPLOCK - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1323,24 +1323,27 @@ __xfs_filemap_fault(
 		file_update_time(vmf->vma->vm_file);
 	}
 
-	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
 		pfn_t pfn;
 
+		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
 				(write_fault && !vmf->cow_page) ?
 				 &xfs_direct_write_iomap_ops :
 				 &xfs_read_iomap_ops);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
+		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	} else {
-		if (write_fault)
+		if (write_fault) {
+			xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 			ret = iomap_page_mkwrite(vmf,
 					&xfs_buffered_write_iomap_ops);
-		else
+			xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+		} else {
 			ret = filemap_fault(vmf);
+		}
 	}
-	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (write_fault)
 		sb_end_pagefault(inode->i_sb);