Skip to content

K
kernel_linux

OpenHarmony / kernel_linux
上一次同步 3 年多

通知 13
Star 8
Fork 2
K
kernel_linux
切换分支/标签
  1. 24 9月, 2008 3 次提交
    • S
      [CIFS] fix busy-file renames and refactor cifs_rename logic · ee2fd967
      由 Steve French 提交于 
      Break out the code that does the actual renaming into a separate
function and have cifs_rename call that. That function will attempt a
path based rename first and then do a filehandle based one if it looks
like the source is busy.

The existing logic tried a path based rename first, but if we needed to
remove the destination then it only attempted a filehandle based rename
afterward. Not all servers support renaming by filehandle, so we need to
always attempt path rename first and fall back to filehandle rename if
it doesn't work.

This also fixes renames of open files on windows servers (at least when
the source and destination directories are the same).

CC: Jeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      ee2fd967
    • J
      cifs: add function to set file disposition · 6d22f098
      由 Jeff Layton 提交于 
      cifs: add function to set file disposition

The proper way to set the delete on close bit on an already existing
file is to use SET_FILE_INFO with an infolevel of
SMB_FILE_DISPOSITION_INFO. Add a function to do that and have the
silly-rename code use it.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      6d22f098
    • J
      cifs: move rename and delete-on-close logic into helper function · a12a1ac7
      由 Jeff Layton 提交于 
      cifs: move rename and delete-on-close logic into helper function

When a file is still open on the server, we attempt to set the
DELETE_ON_CLOSE bit and rename it to a new filename. When the
last opener closes the file, the server should delete it.

This patch moves this mechanism into a helper function and has
the two places in cifs_unlink that do this procedure call it. It
also fixes the open flags to be correct.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      a12a1ac7
  3. 17 9月, 2008 2 次提交
  5. 19 8月, 2008 1 次提交
  7. 14 8月, 2008 1 次提交
    • S
      [CIFS] mount of IPC$ breaks with iget patch · ad661334
      由 Steve French 提交于 
      In looking at network named pipe support on cifs, I noticed that
Dave Howell's iget patch:

    iget: stop CIFS from using iget() and read_inode()

broke mounts to IPC$ (the interprocess communication share), and don't
handle the error case (when getting info on the root inode fails).

Thanks to Gunter who noted a typo in a debug line in the original
version of this patch.

CC: David Howells <dhowells@redhat.com>
CC: Gunter Kukkukk <linux@kukkukk.com>
CC: Stable Kernel <stable@kernel.org>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      ad661334
  9. 07 8月, 2008 3 次提交
  11. 06 8月, 2008 5 次提交
  13. 24 7月, 2008 1 次提交
  15. 13 7月, 2008 1 次提交
  17. 25 5月, 2008 1 次提交
    • J
      disable most mode changes on non-unix/non-cifsacl mounts · 5132861a
      由 Jeff Layton 提交于 
      CIFS currently allows you to change the mode of an inode on a share that
doesn't have unix extensions enabled, and isn't using cifsacl. The inode
in this case *only* has its mode changed in memory on the client. This
is problematic since it can change any time the inode is purged from the
cache.

This patch makes cifs_setattr silently ignore most mode changes when
unix extensions and cifsacl support are not enabled, and when the share
is not mounted with the "dynperm" option. The exceptions are:

When a mode change would remove all write access to an inode we turn on
the ATTR_READONLY bit on the server and remove all write bits from the
inode's mode in memory.

When a mode change would add a write bit to an inode that previously had
them all turned off, it turns off the ATTR_READONLY bit on the server,
and resets the mode back to what it would normally be (generally, the
file_mode or dir_mode of the share).
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      5132861a
  19. 24 5月, 2008 4 次提交
    • J
      silently ignore ownership changes unless unix extensions are enabled or we're faking uid changes · 4ca691a8
      由 Jeff Layton 提交于 
      CIFS currently allows you to change the ownership of a file, but unless
unix extensions are enabled this change is not passed off to the server.

Have CIFS silently ignore ownership changes that can't be persistently
stored on the server unless the "setuids" option is explicitly
specified.

We could return an error here (-EOPNOTSUPP or something), but this is
how most disk-based windows filesystems on behave on Linux (e.g.  VFAT,
NTFS, etc). With cifsacl support and proper Windows to Unix idmapping
support, we may be able to do this more properly in the future.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      4ca691a8
    • S
      [CIFS] remove trailing whitespace · 4e94a105
      由 Steve French 提交于 
      Signed-off-by: NSteve French <sfrench@us.ibm.com>
      4e94a105
    • J
      when creating new inodes, use file_mode/dir_mode exclusively on mount without unix extensions · b0fd30d3
      由 Jeff Layton 提交于 
      When CIFS creates a new inode on a mount without unix extensions, it
temporarily assigns the mode that was passed to it in the create/mkdir
call. Eventually, when the inode is revalidated, it changes to have the
file_mode or dir_mode for the mount. This is confusing to users who
expect that the mode shouldn't change this way. It's also problematic
since only the mode is treated this way, not the uid or gid. Suppose you
have a CIFS mount that's mounted with:

uid=0,gid=0,file_mode=0666,dir_mode=0777

...if an unprivileged user comes along and does this on the mount:

mkdir -m 0700 foo
touch foo/bar

...there is a period of time where the touch will fail, since the dir
will initially be owned by root and have mode 0700. If the user waits
long enough, then "foo" will be revalidated and will get the correct
dir_mode permissions.

This patch changes cifs_mkdir and cifs_create to not overwrite the
mode found by the initial cifs_get_inode_info call after the inode is
created on the server. Legacy behavior can be reenabled with the
new "dynperm" mount option.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      b0fd30d3
    • J
      on non-posix shares, clear write bits in mode when ATTR_READONLY is set · 4468eb3f
      由 Jeff Layton 提交于 
      When mounting a share with posix extensions disabled,
cifs_get_inode_info turns off all the write bits in the mode for regular
files if ATTR_READONLY is set. Directories and other inode types,
however, can also have ATTR_READONLY set, but the mode gives no
indication of this.

This patch makes this apply to other inode types besides regular files.
It also cleans up how modes are set in cifs_get_inode_info for both the
"normal" and "dynperm" cases.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      4468eb3f
  21. 22 5月, 2008 1 次提交
  23. 21 5月, 2008 3 次提交
  25. 15 5月, 2008 2 次提交
  27. 12 5月, 2008 2 次提交
  29. 03 5月, 2008 1 次提交
  31. 30 4月, 2008 1 次提交
  33. 29 4月, 2008 1 次提交
  35. 19 4月, 2008 1 次提交
    • S
      [CIFS] Fix UNC path prefix on QueryUnixPathInfo to have correct slash · 076d8423
      由 Steve French 提交于 
      When a share was in DFS and the server was Unix/Linux, we were sending paths of the form
    \\server\share/dir/file
rather than
    //server/share/dir/file

There was some discussion between me and jra over whether we should use
    /server/share/dir/file
as MS sometimes says - but the documentation for this claims it should be
doubleslash for this type of UNC-like path format and that works, so leaving
it as doubleslash but converting the \ to / in the the //server/share portion.

This gets Samba to now correctly return STATUS_PATH_NOT_COVERED when it is
supposed to (Windows already did since the direction of the slash was not an issue
for them).  Still need another minor change to fully enable DFS (need to finish
some chages to SMBGetDFSRefer
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      076d8423
  37. 23 3月, 2008 1 次提交
  39. 15 3月, 2008 2 次提交
    • S
      [CIFS] file create with acl support enabled is slow · 8b1327f6
      由 Steve French 提交于 
      Shirish Pargaonkar noted:
With cifsacl mount option, when a file is created on the Windows server,
exclusive oplock is broken right away because the get cifs acl code
again opens the file to obtain security descriptor.
The client does not have the newly created file handle or inode in any
of its lists yet so it does not respond to oplock break and server waits for
its duration and then responds to the second open. This slows down file
creation signficantly.  The fix is to pass the file descriptor to the get
cifsacl code wherever available so that get cifs acl code does not send
second open (NT Create ANDX) and oplock is not broken.

CC: Shirish Pargaonkar <shirishp@us.ibm.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      8b1327f6
    • S
      [CIFS] Fix mtime on cp -p when file data cached but written out too late · 50531444
      由 Steve French 提交于 
      Kukks noticed that cp -p can write out file data too late, after the timestamp
is already set.  This was introduced as an unintentional sideeffect of the change
in an earlier patch (see below) which fixed some delayed return code propagation.

cea21805
Author: Jeff Layton <jlayton@redhat.com>
Date:   Tue Nov 20 23:19:03 2007 +0000
Acked-by: NShirish Pargaonkar <shirishp@us.ibm.com>
Acked-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>
      50531444
  41. 12 3月, 2008 1 次提交
  43. 09 3月, 2008 1 次提交
  45. 26 2月, 2008 1 次提交