10 Aug, 2010
5 commits
-
Move the call to vmtruncate to get rid of accessive blocks to the callers
in prepearation of the new truncate calling sequence. This was only done
for DIO_LOCKING filesystems, so the __blockdev_direct_IO_newtrunc variant
was not needed anyway. Get rid of blockdev_direct_IO_no_locking and
its _newtrunc variant while at it as just opencoding the two additional
paramters is shorted than the name suffix.Signed-off-by: Christoph Hellwig
Signed-off-by: Al Viro -
if kmalloc fails, we still need to drop the inode, as we do
on other failure exits.Signed-off-by: Al Viro
-
a) count file openers correctly; i_count use was completely wrong
b) use new mutex for exclusion between final close/open/truncate,
to protect tailpacking logics. i_mutex use was wrong and resulted
in deadlocks.Signed-off-by: Al Viro
-
Signed-off-by: Al Viro
-
Signed-off-by: Al Viro
04 Aug, 2010
4 commits
-
* 'for-linus' of git://oss.sgi.com/xfs/xfs: (49 commits)
xfs simplify and speed up direct I/O completions
xfs: move aio completion after unwritten extent conversion
direct-io: move aio_complete into ->end_io
xfs: fix big endian build
xfs: clean up xfs_bmap_get_bp
xfs: simplify xfs_truncate_file
xfs: kill the b_strat callback in xfs_buf
xfs: remove obsolete osyncisosync mount option
xfs: clean up filestreams helpers
xfs: fix gcc 4.6 set but not read and unused statement warnings
xfs: Fix build when CONFIG_XFS_POSIX_ACL=n
xfs: fix unsigned underflow in xfs_free_eofblocks
xfs: use GFP_NOFS for page cache allocation
xfs: fix memory reclaim recursion deadlock on locked inode buffer
xfs: fix xfs_trans_add_item() lockdep warnings
xfs: simplify and remove xfs_ireclaim
xfs: don't block on buffer read errors
xfs: move inode shrinker unregister even earlier
xfs: remove a dmapi leftover
xfs: writepage always has buffers
... -
* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6: (29 commits)
cifs: fsc should not default to "on"
[CIFS] remove redundant path walking in dfs_do_refmount
cifs: ignore the "mand", "nomand" and "_netdev" mount options
cifs: map NT_STATUS_ERROR_WRITE_PROTECTED to -EROFS
cifs: don't allow cifs_iget to match inodes of the wrong type
[CIFS] relinquish fscache cookie before freeing CIFSTconInfo
cifs: add separate cred_uid field to sesInfo
fs: cifs: check kmalloc() result
[CIFS] Missing ifdef
[CIFS] Missing line from previous commit
[CIFS] Fix build break when CONFIG_CIFS_FSCACHE disabled
cifs: add mount option to enable local caching
cifs: read pages from FS-Cache
cifs: store pages into local cache
cifs: FS-Cache page management
cifs: define inode-level cache object and register them
cifs: define superblock-level cache index objects and register them
cifs: remove unused cifsUidInfo struct
cifs: clean up cifs_find_smb_ses (try #2)
cifs: match secType when searching for existing tcp session
... -
* 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (291 commits)
ARM: AMBA: Add pclk support to AMBA bus infrastructure
ARM: 6278/2: fix regression in RealView after the introduction of pclk
ARM: 6277/1: mach-shmobile: Allow users to select HZ, default to 128
ARM: 6276/1: mach-shmobile: remove duplicate NR_IRQS_LEGACY
ARM: 6246/1: mmci: support larger MMCIDATALENGTH register
ARM: 6245/1: mmci: enable hardware flow control on Ux500 variants
ARM: 6244/1: mmci: add variant data and default MCICLOCK support
ARM: 6243/1: mmci: pass power_mode to the translate_vdd callback
ARM: 6274/1: add global control registers definition header file for nuc900
mx2_camera: fix type of dma buffer virtual address pointer
mx2_camera: Add soc_camera support for i.MX25/i.MX27
arm/imx/gpio: add spinlock protection
ARM: Add support for the LPC32XX arch
ARM: LPC32XX: Arch config menu supoport and makefiles
ARM: LPC32XX: Phytec 3250 platform support
ARM: LPC32XX: Misc support functions
ARM: LPC32XX: Serial support code
ARM: LPC32XX: System suspend support
ARM: LPC32XX: GPIO, timer, and IRQ drivers
ARM: LPC32XX: Clock driver
... -
avoid potential stack overflow by correctly checking count parameter
Reported-by: Ilja
Signed-off-by: Helge Deller
Acked-by: Kyle McMartin
Cc: James E.J. Bottomley
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds
02 Aug, 2010
31 commits
-
I'm not sure why this was merged with this flag hardcoded on, but it
seems quite dangerous. Turn it off.Also, mount.cifs hands unrecognized options off to the kernel so there
should be no need for changes there in order to support this.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
Reviewed-by: Dave Howells
Signed-off-by: Igor Mammedov
Signed-off-by: Steve French -
These are all handled by the userspace mount programs, but older versions
of mount.cifs also handed them off to the kernel. Ignore them.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
Seems like a more sensible mapping than -EIO.
Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
If the type is different from what we think it should be, then don't
match the existing inode.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
Doh, fix a use after free bug.
Signed-off-by: Suresh Jayaraman
Reviewed-and-Tested-by: Jeff Layton
Signed-off-by: Steve French -
Right now, there's no clear separation between the uid that owns the
credentials used to do the mount and the overriding owner of the files
on that mount.Add a separate cred_uid field that is set to the real uid
of the mount user. Unlike the linux_uid, the uid= option does not
override this parameter. The parm is sent to cifs.upcall, which can then
preferentially use the creduid= parm instead of the uid= parm for
finding credentials.This is not the only way to solve this. We could try to do all of this
in kernel instead by having a module parameter that affects what gets
passed in the uid= field of the upcall. That said, we have a lot more
flexibility to change things in userspace so I think it probably makes
sense to do it this way.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
If kmalloc() fails exit with -ENOMEM.
Signed-off-by: Kulikov Vasiliy
Acked-by: Dave Kleikamp
Acked-by: Jeff Layton
Signed-off-by: Steve French -
Signed-off-by: Steve French
-
CC: Suresh Jayaraman
Signed-off-by: Steve French -
CC: Suresh Jayaraman
Signed-off-by: Steve French -
Add a mount option 'fsc' to enable local caching on CIFS.
I considered adding a separate debug bit for caching, but it appears that
debugging would be relatively easier with the normal CIFS_INFO level.As the cifs-utils (userspace) changes are not done yet, this patch enables
'fsc' by default to enable testing.Signed-off-by: Suresh Jayaraman
Acked-by: David Howells
Signed-off-by: Steve French -
Read pages from a FS-Cache data storage object into a CIFS inode.
Signed-off-by: Suresh Jayaraman
Acked-by: David Howells
Signed-off-by: Steve French -
Store pages from an CIFS inode into the data storage object associated with
that inode.Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Takes care of invalidation and release of FS-Cache marked pages and also
invalidation of the FsCache page flag when the inode is removed.Signed-off-by: Suresh Jayaraman
Acked-by: David Howells
Signed-off-by: Steve French -
Define inode-level data storage objects (managed by cifsInodeInfo structs).
Each inode-level object is created in a super-block level object and is itself
a data storage object in to which pages from the inode are stored.The inode object is keyed by UniqueId. The coherency data being used is
LastWriteTime, LastChangeTime and end of file reported by the server.Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Define superblock-level cache index objects (managed by cifsTconInfo structs).
Each superblock object is created in a server-level index object and in itself
an index into which inode-level objects are inserted.The superblock object is keyed by sharename. The UniqueId/IndexNumber is used to
validate that the exported share is the same since we accessed it last time.Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
This patch replaces the earlier patch by the same name. The only
difference is that MAX_PASSWORD_SIZE has been increased to attempt to
match the limits that windows enforces.Do a better job of matching sessions by authtype. Matching by username
for a Kerberos session is incorrect, and anonymous sessions need special
handling.Also, in the case where we do match by username, we also need to match
by password. That ensures that someone else doesn't "borrow" an existing
session without needing to know the password.Finally, passwords can be longer than 16 bytes. Bump MAX_PASSWORD_SIZE
to 512 to match the size that the userspace mount helper allows.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
The secType is a per-tcp session entity, but the current routine doesn't
verify that it is acceptible when attempting to match an existing TCP
session.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
Move the address comparator out of cifs_find_tcp_session and into a
separate function for cleanliness. Also change the argument to
that function to a "struct sockaddr" pointer. Passing pointers to
sockaddr_storage is a little odd since that struct is generally for
declaring static storage.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
This patch should replace the patch I sent a couple of weeks ago to
set the port in cifs_convert_address.Currently we set this in cifs_find_tcp_session, but that's more of a
side effect than anything. Add a new function called cifs_fill_sockaddr.
Have it call cifs_convert_address and then set the port.This also allows us to skip passing in the port as a separate parm to
cifs_find_tcp_session.Also, change cifs_convert_address take a struct sockaddr * rather than
void * to make it clearer how this function should be called.Signed-off-by: Jeff Layton
Signed-off-by: Steve French -
Define server-level cache index objects (as managed by TCP_ServerInfo structs)
and register then with FS-Cache. Each server object is created in the CIFS
top-level index object and is itself an index into which superblock-level
objects are inserted.The server objects are now keyed by {IPaddress,family,port} tuple.
Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Define CIFS for FS-Cache and register for caching. Upon registration the
top-level index object cookie will be stuck to the netfs definition by
FS-Cache.Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Signed-off-by: Joe Perches
Signed-off-by: Steve French -
Add a kernel config option to enable local caching for CIFS.
Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
The ip_address field is not used and seems redundant as there is union addr
already and I don't see any future use as well.Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
The recent commit 6ca9f3bae8b1854794dfa63cdd3b88b7dfe24c13 modified the code so
that filp is full instantiated whenever the file is created and passed back.
The below comment is no longer true, remove it.Cc: Jeff Layton
Signed-off-by: Suresh Jayaraman
Signed-off-by: Steve French -
Add conditional compile macros to guard the header file against multiple
inclusion.Signed-off-by: Suresh Jayaraman
Acked-by: Jeff Layton
Signed-off-by: Steve French
