@@ -3522,6 +3522,21 @@ static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
0, NULL, NULL);
}
+static long query_server_eof(const unsigned int xid,
+ struct cifs_tcon *tcon,
+ struct cifsFileInfo *cfile,
+ unsigned long long *eof)
+{
+ struct smb2_file_all_info file_inf = {};
+ long rc;
+
+ rc = SMB2_query_info(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, &file_inf);
+ if (!rc)
+ *eof = le64_to_cpu(file_inf.EndOfFile);
+ return rc;
+}
+
static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
unsigned long long offset, unsigned long long len,
bool keep_size)
@@ -3565,10 +3580,16 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
truncate_pagecache_range(inode, min(offset, i_size), offset + len - 1);
netfs_wait_for_outstanding_io(inode);
- /* if file not oplocked can't be sure whether asking to extend size */
- rc = -EOPNOTSUPP;
- if (keep_size == false && !CIFS_CACHE_READ(cifsi))
- goto zero_range_exit;
+ if (!keep_size && !CIFS_CACHE_READ(cifsi)) {
+ rc = query_server_eof(xid, tcon, cfile, &remote_i_size);
+ if (rc)
+ goto zero_range_exit;
+ i_size = max(i_size, remote_i_size);
+ if (i_size < new_size) {
+ rc = -EOPNOTSUPP;
+ goto zero_range_exit;
+ }
+ }
fscache_invalidate(cifs_inode_cookie(inode), NULL,
i_size_read(inode), 0);
@@ -3580,7 +3601,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
/*
* do we also need to change the size of the file?
*/
- if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) {
+ if (!keep_size && umax(i_size, i_size_read(inode)) < new_size) {
rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid, cfile->pid, new_size);
if (rc >= 0) {
smb3_zero_range() refuses any FALLOC_FL_ZERO_RANGE that clears FALLOC_FL_KEEP_SIZE with -EOPNOTSUPP whenever the inode is not read caching: /* if file not oplocked can't be sure whether asking to extend size */ rc = -EOPNOTSUPP; if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; The read lease is only needed to trust the cached i_size when deciding whether the range extends the file. When it is not held, the size can instead be fetched from the server, which is authoritative, rather than refusing the request outright: query the server's end of file and take the larger of it and the cached size for the interior-vs-extend decision. The larger of the two is used because the server's end of file reflects another client's growth while the cached size reflects this client's own writes that may not have reached the server yet; using the server size alone would wrongly shrink the file when the range flush above left an extending write unwritten. The query isn't lease-protected either, so its result is only trusted to confirm the range is interior, never to justify extending: if it still shows the range going past EOF, refuse with -EOPNOTSUPP instead of calling SMB2_set_eof(), which could otherwise shrink the file if another client extended it further between the query and the call. For the same reason, take the larger of the already-computed i_size and a fresh i_size_read(inode) right before that call, instead of relying on either alone: the local variable carries the query's result, which is never written back to the inode, while a concurrent write on this client can still extend the cached i_size during the flush, the query, or the zero-data round trip that happen in between. Rejecting interior ranges is observed as generic/363 randomly failing against Windows Server with do_zero_range: fallocate: Operation not supported fsx issues an interior, non-KEEP_SIZE zero range while the inode is transiently not read caching: the server had just downgraded the file's lease from RWH to RH after breaking the write caching, and the ensuing handle reopen/revalidation left CIFS_CACHE_READ momentarily clear. The range sat well within the server's end of file, so no extend was needed, yet the range was refused and fsx aborted. This keeps the emulation correct even when a genuine lease break from another client leaves the inode without read caching -- the case the -EOPNOTSUPP guard turned into a hard failure. The extra round trip only happens on the no-lease path; the common cached case is unchanged. Fixes: 30175628bf7f ("[SMB3] Enable fallocate -z support for SMB3 mounts") 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/smb2ops.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-)