diff options
| author | NeilBrown <neil@brown.name> | 2025-07-24 08:23:38 +0900 | 
|---|---|---|
| committer | Steve French <stfrench@microsoft.com> | 2025-07-24 10:59:18 -0500 | 
| commit | 4e45cca31d4e70019a5e0fe15208de72f6a55a5e (patch) | |
| tree | ec3fdeddb4934057113f947a25b2f9d52d8a0317 /rust/helpers/mutex.c | |
| parent | d5fc1400a34b4ea5e8f2ce296ea12bf8c8421694 (diff) | |
smb/server: add ksmbd_vfs_kern_path()
The function ksmbd_vfs_kern_path_locked() seems to serve two functions
and as a result has an odd interface.
On success it returns with the parent directory locked and with write
access on that filesystem requested, but it may have crossed over a
mount point to return the path, which makes the lock and the write
access irrelevant.
This patches separates the functionality into two functions:
- ksmbd_vfs_kern_path() does not lock the parent, does not request
  write access, but does cross mount points
- ksmbd_vfs_kern_path_locked() does not cross mount points but
  does lock the parent and request write access.
The parent_path parameter is no longer needed.  For the _locked case
the final path is sufficient to drop write access and to unlock the
parent (using path->dentry->d_parent which is safe while the lock is
held).
There were 3 caller of ksmbd_vfs_kern_path_locked().
- smb2_create_link() needs to remove the target if it existed and
  needs the lock and the write-access, so it continues to use
  ksmbd_vfs_kern_path_locked().  It would not make sense to
  cross mount points in this case.
- smb2_open() is the only user that needs to cross mount points
  and it has no need for the lock or write access, so it now uses
  ksmbd_vfs_kern_path()
- smb2_creat() does not need to cross mountpoints as it is accessing
  a file that it has just created on *this* filesystem.  But also it
  does not need the lock or write access because by the time
  ksmbd_vfs_kern_path_locked() was called it has already created the
  file.  So it could use either interface.  It is simplest to use
  ksmbd_vfs_kern_path().
ksmbd_vfs_kern_path_unlock() is still needed after
ksmbd_vfs_kern_path_locked() but it doesn't require the parent_path any
more.  After a successful call to ksmbd_vfs_kern_path(), only path_put()
is needed to release the path.
Signed-off-by: NeilBrown <neil@brown.name>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
Diffstat (limited to 'rust/helpers/mutex.c')
0 files changed, 0 insertions, 0 deletions
