From: Paulo Alcantara <pc@manguebit.org> mainline inclusion from mainline-v7.3-rc6 commit aa994489bd835547c191827acc460192e147032d category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/20578 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- The mode 0 / FALLOC_FL_KEEP_SIZE fallocate emulation for small interior ranges in smb3_simple_fallocate_range() issues FSCTL_QUERY_ALLOCATED_RANGES and zero-fills any sub-range the server reports as an unallocated hole, to force block allocation without changing file contents. This is unsafe against Windows servers. Per the Win32 documentation, FSCTL_QUERY_ALLOCATED_RANGES only reports ranges that *may* contain nonzero data and is explicitly not coherent with recently written data: "a call to FSCTL_QUERY_ALLOCATED_RANGES [after writing to a network file] would not necessarily return a correct list of allocated regions. To ensure coherency [...] flush the data to the file" fsx (generic/363) reproduces the resulting corruption against Windows Server 2022: a range is written, an uncached read returns the data, yet the next FSCTL_QUERY_ALLOCATED_RANGES on that range reports it as a whole hole, so the emulation overwrites live data with zeroes. A network trace confirmed the WRITE, the READ returning data and the query returning an empty range list within microseconds. Samba does not exhibit this; its query is coherent with the written data. Write back the dirty pages, drain any outstanding I/O and issue an SMB2 FLUSH to force the server to commit the data before querying the allocated ranges, so the query reflects the data actually present. With this, generic/363 passes against both Windows Server 2022 and Samba over 100000 fsx operations. Fixes: 966a3cb7c7db ("cifs: improve fallocate emulation") Reviewed-by: David Howells <dhowells@redhat.com> Reviewed-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Paulo Alcantara <pc@manguebit.org> Cc: Christian Brauner <brauner@kernel.org> Cc: Matthew Wilcox <willy@infradead.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 Conflicts: fs/smb/client/smb2ops.c [smb3_simple_fallocate_range() in this tree lacks the pre-EOF fast path and buffers are allocated after the ioctl; drop netfs_wait_for_outstanding_io() as this tree has no netfs io_count and cifs uses its own writeback path, and keep filemap_write_and_wait_range() plus SMB2_flush() before FSCTL_QUERY_ALLOCATED_RANGES.] Signed-off-by: Yifan Qiao <qiaoyifan4@huawei.com> --- fs/smb/client/smb2ops.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 781c471927e8..f5f92a9ed422 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3454,12 +3454,30 @@ static int smb3_simple_fallocate_range(unsigned int xid, loff_t off, loff_t len) { struct file_allocated_range_buffer in_data, *out_data = NULL, *tmp_data; + struct inode *inode = d_inode(cfile->dentry); u32 out_data_len; char *buf = NULL; u64 range_start, range_len, range_end; loff_t l; int rc; + filemap_invalidate_lock(inode->i_mapping); + + /* + * Flush and commit the data to the server, otherwise + * FSCTL_QUERY_ALLOCATED_RANGES might report recently written data as + * unallocated holes on Windows Servers, and the loop below would + * then zero-fill them and corrupt the file. + */ + rc = filemap_write_and_wait_range(inode->i_mapping, off, + off + len - 1); + if (rc) + goto out_unlock; + rc = SMB2_flush(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid); + if (rc) + goto out_unlock; + in_data.file_offset = cpu_to_le64(off); in_data.length = cpu_to_le64(len); rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, @@ -3469,12 +3487,12 @@ static int smb3_simple_fallocate_range(unsigned int xid, 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); if (rc) - goto out; + goto out_unlock; buf = kvzalloc(min_t(loff_t, len, SMB2_MAX_BUFFER_SIZE), GFP_KERNEL); if (buf == NULL) { rc = -ENOMEM; - goto out; + goto out_unlock; } tmp_data = out_data; @@ -3485,12 +3503,12 @@ static int smb3_simple_fallocate_range(unsigned int xid, if (out_data_len == 0) { rc = smb3_simple_fallocate_write_range(xid, tcon, cfile, off, len, buf); - goto out; + goto out_unlock; } if (out_data_len < sizeof(struct file_allocated_range_buffer)) { rc = -EINVAL; - goto out; + goto out_unlock; } range_start = le64_to_cpu(tmp_data->file_offset); @@ -3498,7 +3516,7 @@ static int smb3_simple_fallocate_range(unsigned int xid, if (check_add_overflow(range_start, range_len, &range_end) || range_end > S64_MAX) { rc = -EINVAL; - goto out; + goto out_unlock; } if (off < range_start) { @@ -3513,11 +3531,11 @@ static int smb3_simple_fallocate_range(unsigned int xid, rc = smb3_simple_fallocate_write_range(xid, tcon, cfile, off, l, buf); if (rc) - goto out; + goto out_unlock; off = off + l; len = len - l; if (len == 0) - goto out; + goto out_unlock; } /* * We are at a section of allocated data, just skip forward @@ -3536,7 +3554,8 @@ static int smb3_simple_fallocate_range(unsigned int xid, out_data_len -= sizeof(struct file_allocated_range_buffer); } - out: + out_unlock: + filemap_invalidate_unlock(inode->i_mapping); kfree(out_data); kvfree(buf); return rc; -- 2.52.0