[PATCH] ntfs: take invalidate_lock in ntfs_filemap_page_mkwrite()

[Hongling Zeng]

ntfs_filemap_page_mkwrite() calls iomap_page_mkwrite() without holding
mapping->invalidate_lock, so a concurrent truncate or fallocate can be
in the middle of invalidating pagecache and rewriting the runlist while
the write fault maps blocks and dirties the folio.  This races with
ntfs_attr_fallocate(), which merges clusters into the in-memory
runlist, drops the runlist lock, and only afterwards zeroes the newly
allocated clusters on disk; and with the punch-hole/insert/collapse
paths that free clusters after truncating the cache.

Per Documentation/filesystems/locking.rst, ->page_mkwrite() must ensure
there are no truncate/invalidate races, "usually mapping->invalidate_lock
is suitable for proper serialization".  xfs takes its mmaplock (= the
invalidate_lock rwsem) shared in exactly this path.

Take invalidate_lock shared around iomap_page_mkwrite().  The read-only
fault path is already covered because filemap_fault() itself grabs
invalidate_lock shared on instantiation/read paths; only page_mkwrite
was bypassing it in this driver.

Fixes: 9c87959601e8 ("ntfs: update file operations")
Cc: stable@xxxxxxxxxxxxxxx
Co-developed-by: Namjae Jeon <linkinjeon@xxxxxxxxxx>
Reviewed-by: Hyunchul Lee <hyc.lee@xxxxxxxxx>
Reviewed-by: Baolin Liu <liubaolin@xxxxxxxxxx>
Signed-off-by: Hongling Zeng <zenghongling@xxxxxxxxxx>
---
Change in v1:
 -Move truncate_pagecache() and pagecache_isize_extended() inside the
 invalidate_lock hold range in ntfs_fallocate(), per review comment
---
 fs/ntfs/file.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 585ab2145797..8164326b7812 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -676,6 +676,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct address_space *mapping = inode->i_mapping;
 	vm_fault_t ret;
 
 	if (NInoWofCompressed(NTFS_I(inode)))
@@ -684,7 +685,14 @@ static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vmf->vma->vm_file);
 
+	/*
+	 * Serialize against truncate/fallocate which hold the lock
+	 * exclusively while invalidating pagecache and changing extents.
+	 */
+	filemap_invalidate_lock_shared(mapping);
 	ret = iomap_page_mkwrite(vmf, &ntfs_page_mkwrite_iomap_ops, NULL);
+	filemap_invalidate_unlock_shared(mapping);
+
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
@@ -1185,13 +1193,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le
 
 	err = file_modified(file);
 out:
+	if (!err && mode == 0 && NInoNonResident(ni) &&
+	    offset > old_size) {
+		truncate_pagecache(vi, old_size);
+		pagecache_isize_extended(vi, old_size, offset);
+	}
+
 	filemap_invalidate_unlock(vi->i_mapping);
+
 	if (!err) {
-		if (mode == 0 && NInoNonResident(ni) &&
-		    offset > old_size) {
-			truncate_pagecache(vi, old_size);
-			pagecache_isize_extended(vi, old_size, offset);
-		}
 		NInoSetFileNameDirty(ni);
 		inode_set_mtime_to_ts(vi, inode_set_ctime_current(vi));
 		mark_inode_dirty(vi);
-- 
2.25.1