[GIT PULL] smb3 client fixes (updated)

From: Steve French
Date: Sat Jun 21 2025 - 12:10:54 EST


Please pull the following changes since commit
e04c78d86a9699d136910cfc0bdcf01087e3267e:

Linux 6.16-rc2 (2025-06-15 13:49:41 -0700)

are available in the Git repository at:

git://git.samba.org/sfrench/cifs-2.6.git tags/v6.16-rc2-smb3-client-fixes-v2

for you to fetch changes up to 27e9d5d021dbaa1211836d07a240078bf84b284e:

smb: minor fix to use SMB2_NTLMV2_SESSKEY_SIZE for auth_key size
(2025-06-21 11:03:25 -0500)

----------------------------------------------------------------
Nine smb3 client fixes (updated P/R removing one SMB1 changeset as requested)
- Multichannel channel allocation fix for Kerberos mounts
- Two reconnect fixes
- Fix netfs_writepages crash with smbdirect/RDMA
- Directory caching fix
- Three minor cleanup fixes
- Log error when close cached dirs fails
----------------------------------------------------------------
Bharath SM (4):
smb: fix secondary channel creation issue with kerberos by
populating hostname when adding channels
smb: Use loff_t for directory position in cached_dirents
smb: minor fix to use sizeof to initialize flags_string buffer
smb: minor fix to use SMB2_NTLMV2_SESSKEY_SIZE for auth_key size

David Howells (1):
cifs: Fix prepare_write to negotiate wsize if needed

Pali Rohár (1):
cifs: Remove duplicate fattr->cf_dtype assignment from
wsl_to_fattr() function

Paul Aurich (1):
smb: Log an error when close_all_cached_dirs fails

Stefan Metzmacher (1):
smb: client: fix max_sge overflow in smb_extract_folioq_to_rdma()

zhangjian (1):
smb: client: fix first command failure during re-negotiation

fs/smb/client/cached_dir.c | 14 ++++++++++++--
fs/smb/client/cached_dir.h | 2 +-
fs/smb/client/cifs_debug.c | 2 +-
fs/smb/client/cifs_ioctl.h | 2 +-
fs/smb/client/connect.c | 1 +
fs/smb/client/file.c | 8 ++++++--
fs/smb/client/ioctl.c | 2 +-
fs/smb/client/reparse.c | 1 -
fs/smb/client/sess.c | 3 +--
fs/smb/client/smbdirect.c | 5 +++--
10 files changed, 27 insertions(+), 13 deletions(-)

--
Thanks,

Steve