store 128 bytes, usually NFS servers don't use file handles that
   are more than 32 bytes in size.  This patch creates an efficient
   mechanism for comparing file handles that ignores the unused bytes
   in a file handle.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   direct I/O support for NFS files.  The 2.4 VFS O_DIRECT logic was
   block based, thus the NFS client had to provide a minimum
   allowable blocksize for O_DIRECT reads and writes on NFS files. 
   For various reasons we chose 512 bytes. In 2.6, there is no
   requirement for a minimum blocksize.  NFS O_DIRECT reads and
   writes can go to any byte at any offset in a file.  Thus we revert
   the blocksize setting for NFS file systems to the previous
   behavior, which was to advertise the "wsize" setting as the
   optimal I/O block size.  This improves the performance of
   applications like 'cp' which use this value as their transfer
   size.

This patch also exposes the server's reported disk block size in the
   f_frsize of the vfsstat structure.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   request. Get rid of nfs_put_super.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   a heavy read and write workload on one mount point from
   interfering with workloads on other mount points.

Note that there is still some serialization due to the big kernel
   lock.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: Andy Adamson <andros@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   why we shouldn't be slightly stricter here, so I'm just going to
   keep sending this until I'm told to stop.... Make sure that
   unmapped errors are approximately in the range of defined NFS4
   errors.
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   nfs_open_revalidate() avoids several atomicity problems.
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   for the full set of permissions.
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   Currently we are wasting considerable amounts of space in the page
   cache.

NFSv4: fix buffer overrun bugs that were being hidden by the above.
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   using a dynamically allocated rpc_task structure instead of
   allocating one on the stack.  This reduces stack utilization by
   over 200 bytes for all synchronous NFS operations.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

   immediately unlocked on the server side if blocking
   has occurred.
Signed-off-by: Trond Myklebust <trond.myklebust@fys.uio.no>

drivers/net/Kconfig:1749:warning: 'select' used by config symbol 'VIA_VELOCITY'

We renamed CONFIG_CRC16.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Signed-off-by: Andrey Panin <pazke@donpac.ru>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

cciss uses /proc to hook into the SCSI subsystem.  If you do not build
/proc support into your kernel then you should also disable tape support in
the driver. 
Signed-off-by: Adrian Bunk <bunk@fs.tum.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch updates the maintainers list for HP drivers.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch changes our read_ahead to 1024.  This has been shown to increase
performance.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch fixes our usage of pdev->intr.  We were truncating it to an unchar.
 We were also reading it before calling pci_enable_device.  This patch fixes
both of those.  Thanks to Bjorn Helgaas for the patch.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Somehow I managed to get the wrong PCI ID in pci_ids.h.  3210 is the
correct PCI ID, 3211 is the subsystem ID.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch fixes the vendor ID for our cciss based SATA controller due out
later this year and adds the new PCI ID to pci_ids.h.

Also changes DRIVER_NAME to HP CCISS.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch fixes our cylinder calculations.  Without his fix the number of
cylinders maxes out at 65535.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch fixes our output in /proc to display the logical volume sizes and
RAID levels correctly.  Without this patch RAID level will always be 0 and
size may be displayed as 0GB.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch addresses a problem with our utilities.  We must zero out the
buffer before copying their data into it to prevent bogus info when switching
between SCSI & SATA or SAS drives.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch fixes our usage of copy_to_user.  We were passing in the size of
the address rather than the size of the struct.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Fix another gcc 3.5 compile issue, this time the default_policy prototype
was not marked static whereas the definition was. There is no need for
the prototype, so remove it.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Since various gnupg users have indicated that gpg wants to mlock 32kB of
memory, I created the patch below that increases the default mlock ulimit
to 32kB.

This is no security problem because it's trivial for processes to lock way
more memory than this in page tables, network buffers, etc.  In fact, since
this patch allows gnupg to mlock to prevent passphrase data from being
swapped out, the security people will probably like it ;)

This gets the new per-user mlock limit a bit more testing, too.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Here is the last agreed-on patch that lets normal users mlock pages up to
their rlimit.  This patch addresses all the issues brought up by Chris and
Andrea.

From: Chris Wright <chrisw@osdl.org>

Couple more nits.

The default lockable amount is one page now (first patch is was 0).  Why
don't we keep it as 0, with the CAP_IPC_LOCK overrides in place?  That way
nothing is changed from user perspective, and the rest of the policy can be
done by userspace as it should.

This patch breaks in one scenario.  When ulimit == 0, process has
CAP_IPC_LOCK, and does SHM_LOCK.  The subsequent unlock or destroy will
corrupt the locked_shm count.

It's also inconsistent in handling user_can_mlock/CAP_IPC_LOCK interaction
betwen shm_lock and shm_hugetlb.

SHM_HUGETLB can now only be done by the shm_group or CAP_IPC_LOCK.
Not any can_do_mlock() user.

Double check of can_do_mlock isn't needed in SHM_LOCK path.

Interface names user_can_mlock and user_substract_mlock could be better.

Incremental update below.  Ran some simple sanity tests on this plus my
patch below and didn't find any problems.

* Make default RLIM_MEMLOCK limit 0.
* Move CAP_IPC_LOCK check into user_can_mlock to be consistent
  and fix but with ulimit == 0 && CAP_IPC_LOCK with SHM_LOCK.
* Allow can_do_mlock() user to try SHM_HUGETLB setup.
* Remove unecessary extra can_do_mlock() test in shmem_lock().
* Rename user_can_mlock to user_shm_lock and user_subtract_mlock
  to user_shm_unlock.
* Use user instead of current->user to fit in 80 cols on SHM_LOCK.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Here is a consolidated readahead patch that takes care of the performance
regression seen with multiple threaded writes to the same file descriptor. 


	The patch does the following:

	1. Instead of calculating the average count of sequential
		access in the read patterns, it calculates the
		average amount of hits in the current window.
	2. This average is used to guide the size of the next current
		window.
	3. Since the field serial_cnt in the ra structure does not
	 	make sense with the introduction of the new logic,
		I have renamed that field as currnt_wnd_hit.

This patch will help the read patterns that are not neccessarily sequential
but have sufficient locality.  However it may regress random workload.  

	Results:

	1. Berkley Shands has reported great performance with this
		patch.
	2. iozone showed negligible effect on various read patterns.
	3. DSS workload saw neglible change.
	4. Sysbench saw a small improvement.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Ok I have enclosed the results for the recent readahead fixes.  The summary
is: there is no significant improvement or decrease in performance of (DSS
workload, iozone, sysbench) The increase or decrease is in the margin of
errors.

I have enclosed a patch that partially backs off Miklos's fix.  Shane
Shrybman correctly pointed out that the real fix is to set ra->average
value to max/2 when we move from readahead-off mode to readahead-on mode.
The other part of Miklos's fix becomes irrelevent.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

LOOP_CHANGE_FD is an ULONG compatible ioctl, basically same calling
convention as LOOP_SET_FD; mark it as such in the compat ioctl list.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

'make buildcheck' indicates that these functions should not be in an __exit
section, so undo that.  Yes, they can be called from .text.
Signed-off-by: Randy Dunlap <rddunlap@osdl.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Here is a patch to fix a problem of might-sleep-in-atomic which David
Mosberger mentioned at
http://www.gelato.unsw.edu.au/linux-ia64/0407/10526.html

On IA64 platform, a might-sleep-in-atomic warning raise while dumping a
multi-thread process.  That is because elf_core_dump holds the tasklist_lock
before the kernel does a access_process_vm in elf_core_copy_task_regs,

This patch detached elf_core_copy_task_regs function from inside
tasklist_lock to remove the warning.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fix compiling oldconfig with gcc-3.5:
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

This patch renames fs/aio.c:'struct timeout' to 'struct aio_timeout'.  The
rationale behind this decision is this type is used only inside the
aforementioned aio.c file and being the type name very generic, it is
likely to cause namespace conflicts in the future.

I actually found it while working on an extended schedule_timeout()- like
API used by robust mutexes but usable by anyone.  There I declared a
'struct timeout' and aio.c complained about it.  I could have also renamed
the struct for the schedule_timeout() like API, but being the aio.c one
specific to the file, I thought it might make more sense to rename the
later.
Signed-off-by: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

If netpoll attempts to use a device without polling support, it will oops
when shutting down.  This adds a check that we've actually attached to a
device.
Signed-off-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Remove now-unneeded open-coded unlikelies around IS_ERR().
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>