@@ -1412,6 +1412,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
* server could even support copy of range where source = target
*/
lock_two_nondirectories(target_inode, src_inode);
+ filemap_invalidate_lock(target_inode->i_mapping);
if (len == 0) {
loff_t src_size = i_size_read(src_inode);
@@ -1475,6 +1476,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend);
truncate_inode_pages_range(&target_inode->i_data,
min(fstart, i_size), fend);
+ netfs_wait_for_outstanding_io(target_inode);
fscache_invalidate(cifs_inode_cookie(target_inode), NULL, i_size, 0);
@@ -1513,6 +1515,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
if (rc)
CIFS_I(target_inode)->time = 0;
unlock:
+ filemap_invalidate_unlock(target_inode->i_mapping);
/* although unlocking in the reverse order from locking is not
strictly necessary here it is a little cleaner to be consistent */
unlock_two_nondirectories(src_inode, target_inode);
@@ -1536,6 +1539,9 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
struct cifs_tcon *target_tcon;
ssize_t rc;
+ if (len == 0)
+ return 0;
+
cifs_dbg(FYI, "copychunk range\n");
if (!src_file->private_data || !dst_file->private_data) {
@@ -1565,6 +1571,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
* server could even support copy of range where source = target
*/
lock_two_nondirectories(target_inode, src_inode);
+ filemap_invalidate_lock(target_inode->i_mapping);
cifs_dbg(FYI, "about to flush pages\n");
@@ -1590,11 +1597,24 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
* Start at the old EOF when extending so the folio straddling it, which
* may hold data written past EOF through an mmap, is dropped too.
*/
- rc = filemap_invalidate_inode(target_inode, true,
- min(destoff, i_size_read(target_inode)),
- destoff + len - 1);
- if (rc)
- goto unlock;
+ if (target_inode->i_mapping->nrpages) {
+ loff_t fstart = min(destoff, i_size_read(target_inode));
+ loff_t fend = destoff + len - 1;
+
+ unmap_mapping_pages(target_inode->i_mapping,
+ fstart >> PAGE_SHIFT,
+ (fend >> PAGE_SHIFT) -
+ (fstart >> PAGE_SHIFT) + 1,
+ false);
+ rc = filemap_write_and_wait_range(target_inode->i_mapping,
+ fstart, fend);
+ if (rc)
+ goto unlock;
+ invalidate_inode_pages2_range(target_inode->i_mapping,
+ fstart >> PAGE_SHIFT,
+ fend >> PAGE_SHIFT);
+ }
+ netfs_wait_for_outstanding_io(target_inode);
fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
i_size_read(target_inode), 0);
@@ -1626,6 +1646,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
CIFS_I(target_inode)->time = 0;
unlock:
+ filemap_invalidate_unlock(target_inode->i_mapping);
/* although unlocking in the reverse order from locking is not
* strictly necessary here it is a little cleaner to be consistent
*/
cifs_file_copychunk_range() and the clone (FICLONE) path of cifs_remap_file_range() do not serialise the destination page cache against the server-side copy the way the other server-side range operations (smb3_zero_range(), smb3_punch_hole(), smb3_collapse_range() and smb3_insert_range()) do. cifs_file_copychunk_range() invalidates the destination range with filemap_invalidate_inode(), which takes and drops the mapping's invalidate_lock internally, so the lock is no longer held when the copychunk ioctl is issued. It also never drains in-flight netfs I/O on the target. The clone path never takes the invalidate_lock at all (only i_rwsem), uses a bare truncate_inode_pages_range() and likewise does not drain outstanding I/O. As a result an asynchronous destination writeback can complete after the server-side copy/clone has run and reinstate stale data over the region just written by the server, corrupting the file. This is the same class of corruption as commit d7d2adcd022b ("smb/client: flush dirty data before punching a hole") and has been seen randomly in generic/363 against Windows Server. Fix both paths to follow the established ordering: hold the target mapping's invalidate_lock across the flush and invalidation of the destination and the server ioctl, and call netfs_wait_for_outstanding_io() on the target to drain in-flight writes before the ioctl is issued. Only the target inode's invalidate_lock is required, as the source is merely flushed and not invalidated; i_rwsem (already held via lock_two_nondirectories()) is acquired before the invalidate_lock, matching the VFS lock ordering. Since filemap_invalidate_inode() takes that same lock internally, replace it with its own unmap/flush/invalidate steps instead of calling it, and return early on a zero-length copy to avoid a range underflow. Fixes: 8101d6e112e2 ("cifs: Fix copy offload to flush destination region") Fixes: c54fc3a4f375 ("cifs: Fix flushing, invalidation and file size with FICLONE") Signed-off-by: Paulo Alcantara <pc@manguebit.org> Cc: Christian Brauner <brauner@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com> Cc: Shyam Prasad N <sprasad@microsoft.com> Cc: Tom Talpey <tom@talpey.com> Cc: Bharath SM <bharathsm@microsoft.com> Cc: stable@vger.kernel.org --- fs/smb/client/cifsfs.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-)