A patch from Ed Tomlinson which improves the way in which the kernel
reclaims slab objects.

The theory is: a cached object's usefulness is measured in terms of the
number of disk seeks which it saves.  Furthermore, we assume that one
dentry or inode saves as many seeks as one pagecache page.

So we reap slab objects at the same rate as we reclaim pages.  For each
1% of reclaimed pagecache we reclaim 1% of slab.  (Actually, we _scan_
1% of slab for each 1% of scanned pages).

Furthermore we assume that one swapout costs twice as many seeks as one
pagecache page, and twice as many seeks as one slab object.  So we
double the pressure on slab when anonymous pages are being considered
for eviction.

The code works nicely, and smoothly.  Possibly it does not shrink slab
hard enough, but that is now very easy to tune up and down.  It is just:

	ratio *= 3;

in shrink_caches().

Slab caches no longer hold onto completely empty pages.  Instead, pages
are freed as soon as they have zero objects.  This is possibly a
performance hit for slabs which have constructors, but it's doubtful.
Most allocations after a batch of frees are satisfied from inside
internally-fragmented pages and by the time slab gets back onto using
the wholly-empty pages they'll be cache-cold.  slab would be better off
going and requesting a new, cache-warm page and reconstructing the
objects therein.  (Once we have the per-cpu hot-page allocator in
place.  It's happening).

As a consequence of the above, kmem_cache_shrink() is now unused.  No
great loss there - the serialising effect of kmem_cache_shrink and its
semaphore in front of page reclaim was measurably bad.

Still todo:

- batch up the shrinking so we don't call into prune_dcache and
  friends at high frequency asking for a tiny number of objects.

- Maybe expose the shrink ratio via a tunable.

- clean up slab.c

- highmem page reclaim in prune_icache: highmem pages can pin
  inodes.

This uses the new wakeup machinery in some hot parts of the VFS and
block layers.

wait_on_buffer(), wait_on_page(), lock_page(), blk_congestion_wait().
Also in get_request_wait(), although the benefit for exclusive wakeups
will be lower.

This is worth a whopping 2% on spwecweb on an 8-way.  Which is faintly
surprising because __wake_up and other wait/wakeup functions are not
apparent in the specweb profiles which I've seen.


The main objective of this is to reduce the CPU cost of the wait/wakeup
operation.  When a task is woken up, its waitqueue is removed from the
waitqueue_head by the waker (ie: immediately), rather than by the woken
process.

This means that a subsequent wakeup does not need to revisit the
just-woken task.  It also means that the just-woken task does not need
to take the waitqueue_head's lock, which may well reside in another
CPU's cache.

I have no decent measurements on the effect of this change - possibly a
20-30% drop in __wake_up cost in Badari's 40-dds-to-40-disks test (it
was the most expensive function), but it's inconclusive.  And no
quantitative testing of which I am aware has been performed by
networking people.

The API is very simple to use (Linus thought it up):

my_func(waitqueue_head_t *wqh)
{
	DEFINE_WAIT(wait);

	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
	if (!some_test)
		schedule();
	finish_wait(wqh, &wait);
}

or:

	DEFINE_WAIT(wait);

	while (!some_test_1) {
		prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
		if (!some_test_2)
			schedule();
		...
	}
	finish_wait(wqh, &wait);

You need to bear in mind that once prepare_to_wait has been performed,
your task could be removed from the waitqueue_head and placed into
TASK_RUNNING at any time.  You don't know whether or not you're still
on the waitqueue_head.

Running prepare_to_wait() when you're already on the waitqueue_head is
fine - it will do the right thing.

Running finish_wait() when you're actually not on the waitqueue_head is
fine.

Running finish_wait() when you've _never_ been on the waitqueue_head is
fine, as ling as the DEFINE_WAIT() macro was used to initialise the
waitqueue.

You don't need to fiddle with current->state.  prepare_to_wait() and
finish_wait() will do that.  finish_wait() will always return in state
TASK_RUNNING.

There are plenty of usage examples in vm-wakeups.patch and
tcp-wakeups.patch.

From David M-T.

When this function successfully merges the new range into an existing
VMA, it forgets to extend the new protection mode into the just-merged
pages.

Patch from Rohit Seth

It fixes the problem which Andrea noted in his initial review of the
hugetlb code:

"In short doing "addr = vma->vm_end" and then checking if vm_end + len
 is below vm_next->vm_start is broken, because there's no guarantee
 that "addr" will be a largepage aligned address.  the LPAGE_ALIGN in
 found_addr should be dropped becaue moving the addr ahead without
 checking that addr+len doesn't then fall into a vma, will generate
 do_munmaps and in turn userspace mem corruption."

 - Remove the const that someone incorrectly stuck in there, it type conflicts.
   Alan has a better plan for fixing this long term, but this fixes the compile
   warning for now.

 - Move the printk of the xquad_portio setup *after* we put something in the variable
   so it actually prints something useful, not 0 ;-)

 - To derive the size of the xquad_portio area, multiply the number of nodes by the
   size of each nodes, not the size of two nodes (and remove define). Doh!

and does the wrong thing for higher HZ values anyway.

This fixes a number of bugs in the thread-release code:

 - notify parents only if the group leader is a zombie,
   and if it's not a detached thread.

 - do not reparent children to zombie tasks.

 - introduce the TASK_DEAD state for tasks, to serialize the task-release
   path. (to some it might be confusing that tasks are zombies first, then
   dead :-)

 - simplify tasklist_lock usage in release_task().

the effect of the above bugs ranged from unkillable hung zombies to kernel
crashes. None of those happens with the patch applied.

Patch killing off elevator_linus for good. Sniffle.

This introduces the deadline-ioscheduler, making it the default.  2nd
patch coming that deletes elevator_linus in a minute.

This one has read_expire at 500ms, and writes_starved at 2.

Sanity checkthe ESCD size. From 2.4.

These two chipsets are most common on alpha.
- cy82c693: allow the generic IDE setup code to work correctly
  with broken PCI registers layout of this chip. This fixes
  quite a few problems with secondary channel, plus some hacks in
  arch code can go away.
- ALi M5229: enable DMA.

This removes the cmpxchg from the PID allocator and replaces it with a
spinlock.  This spinlock is hit only a couple of times per bootup, so
it's not a performance issue.

Ulrich found another small detail wrt. POSIX requirements for threads -
this time it's the recursion features (read-held lock being write-locked
means an upgrade if the same 'process' is the owner, means a deadlock if a
different 'process').

this requirement even makes some sense - the group of threads who own a
lock really own all rights to the lock as well.

These changes fix this, all testcases pass now.  (inter-process
testcases as well, which are not affected by this patch.)

(SIGURG and SIGIO semantics should also continue to work - there's some
more stuff we can optimize with the new pidhash in this area, but that's
for later.)

The loop device driver was broken in 2.5.38 when it was converted over
to use gendisk.  I discovered this while doing final regression testing
on the ext3 htree code.

The problem is that figure_loop_size() is setting the capacity of the
loop device in kilobytes (because that's what compute_loop_size()
returns), but set_capacity() expects the size in 512 byte sectors.

I've enclosed a patch which fixes the problem, as well as simplifying
the code by eliminating compute_loop_size(), since it is a static
function is only used once by figure_loop_size().

into kleikamp.austin.ibm.com:/home/shaggy/bk/jfs-2.5

As it is at the moment, sys_mprotect will dereference a null pointer
if you use it on a region that is contained within the first vma.  I
have a little program that demonstrates this (I'll post it if anyone
is interested).  What happens then is that the process hangs in
do_page_fault at the down_read on the mm->mmap_sem, since sys_mprotect
has done a down_write on mm->mmap_sem.

The problem is that mprotect_fixup isn't updating prev properly.  Thus
we can finish the main loop in sys_mprotect with prev == NULL.  This
has been the case since Christoph's cleanups went in.  Prior to that,
mprotect_fixup always set prev to something non-NULL.  I suspect that
not updating prev could also cause vmas to get dropped completely if
the region being mprotected spans more than one vma.

The patch below fixes the problem by making mprotect_fixup set prev to
a reasonable value in all circumstances.

This unsafe access to per-CPU data via reordering of instructions or use
of "get_cpu()".

Before anyone balks at the brlock.h fix, note this was in the
alternative version of the code which is not used by default.

Before the irqs_disabled() check in preempt_schedule(), we worked around
some locking issues in slab.c.  Now that we will never preempt with
interrupts disabled, we can remove those and clean things up.

This is courtesy of Manfred Spraul.

This converts the debugging check in do_exit from a check on
preempt_count() to in_atomic().

The main benefit to this is we will stop warning over the BKL and now
use the standard mechanism for such checks.

Looks like I dropped a hunk from my patchset, sorry.

We never set FL_SLEEP in the flock case, so if we should block, we'll
livelock instead.

This is needed for reasonable read latency with the new VM
behaviour. 

NOTE! This is way too unfair, Andrew and Jens are working on
alternatives.

 - Makefile cleanups and fixes
 - a bunch of syscalls added
 - removed crap from asm/ide.h (it's not needed anymore)
 - __down_read_trylock fix

IDE must use blk_queue_empty() and not do a list_empty() on the
(potentially only) dispatch queue.  This took quite a while to find
while debugging a new io scheduler...

This fixes the emacs bug reported by Andries.  It should probably also
fix other, terminal handling related weirdnesses introduced by the new
PID handling code in 2.5.38.

The bug was in the session_of_pgrp() function, if no proper session is
found in the process group then we must take the session ID from the
process that has pgrp PID (which does not necesserily have to be part of
the pgrp).  The fallback code is only triggered when no process in the
process group has a valid session - besides being faster, this also
matches the old implementation.

[ hey, who needs a POSIX conformance testsuite when we have emacs! ;) ]

The direct-IO code is currently generating 1 meg BIOs (and
subsequent BUGs) because it doesn't know about bio_add_page().

Could we please drop it to 16k until we get it sorted out?

into kroah.com:/home/greg/linux/BK/gregkh-2.5

-increased timeout value because some people reported problems
-(important!) Vender ID has changed from 0x1212 to 0x10D2 , my official
  assigned one.
-added usblcd driver to configure.help

Update to full working driver status. Latest firmware 4.06 too. Driver
now officially supported.

Based off of a patch from Stuart MacDonald <stuartm@connecttech.com>

This cleans up the error path in the open() call to make a bit more
sense.

This fixes a stupid error in the timeout value when downloading firmware
to a device.  The WhiteHEAT device now works properly with this patch.

Like the header says, this patch fixes up the various Transfer- and
Transport-level return codes.  There were a lot of places in the various
subdrivers that were not particularly careful about distinguishing the
two; it would help if the people currently maintaining those drivers could
take a look at my changes to make sure I haven't screwed anything up.

# Converted US_BULK_TRANSFER_xxx to USB_STOR_XFER_xxx, to make it more
# easily distinguishable from USB_STOR_TRANSPORT_xxx.  (Also, in the
# future these codes may apply to control transfers as well as to bulk
# transfers.)
#
# Changed USB_STOR_XFER_FAILED to USB_STOR_XFER_ERROR, since it implies
# a transport error rather than a transport failure.
#
# Added a USB_STOR_XFER_STALLED code, to indicate a transfer that was
# terminated by an endpoint stall.

This patch is in preparation for one in which usb_stor_transfer_partial()
and usb_stor_transfer() are replaced by usb_stor_bulk_transfer_buf() and
usb_stor_bulk_transfer_srb() respectively, with slightly different
argument lists.  Ultimately the subdrivers will be able to use these
routines in place of the slightly specialized versions they have now and
in place of the ones in raw_bulk.c.

compile fails with the following message:

	> In file included from ohci-hcd.c:136:
	> ohci-dbg.c:318: parse error
	> make[3]: *** [ohci-hcd.o] Error 1

due to a missing #include <linux/version.h>

Here is a trivial patch for this.

is it guarenteed that callers have zero'd out the device
before this is invoked?  Else the following is necessary to
prevent potential OOPS's derefencing interface->dev.driver in
the generic device layer.

Here's an EHCI update, I'll send separate patches to sync 2.4 with
this version.  Changes in this version include:

  - An earlier locking update would give trouble on SPARC, where
    irqsave "flags" aren't flags.  This resolves that issue by
    adding a module parameter to limit work done with irqs off.
    (Some net drivers do the same thing.)

  - Optionally (now #ifdef DEBUG) collects some statistics on IRQs
    and URBs.  There are more IAA interrupts than I want to see,
    during extended usb-storage loading.

  - Adds a commented-out workaround for a problem I've seen on one
    VT8235.  Seems likely an issue with this specific motherboard;
    another tester hasn't reported such issues.

  - Includes the jiffies time_after() patch from Tim Schmielau.

  - Minor tweaks to the hcd portability (get rid of another #if).

  - Minor doc/diagnostic/... updates

This USB patch updates the OHCI driver:

  - converts to relying on td_list shadowing the hardware's
    schedule; only collecting the donelist needs dma_to_td(),
    and td list handling works much like EHCI or UHCI.

  - leaves faulted endpoint queues (bulk/intr) disabled until
    the relevant drivers had a chance to clean up.

  - fixes minor bugs (unreported) in the affected code:
      * byteswap problem when unlinking urbs ... symptom would
        be data toggle confusion (since 2.4.2x) on big-endian cpus
      * latent bug if folk unlinked queue in LIFO order, not FIFO

  - removes unnecessary debug code; mostly de-BUG()ged

The interesting fix is the "leave queues halted" one.  As
discussed on email a while back, this HCD fault handling
policy (also followed by EHCI) is sufficient to let device
drivers implement the two key fault handling policies that
seem to be necessary:

    (a) Datagram style, where issues on one I/O won't affect
        the next unless the device halted the endpoint.  The
        device driver can ignore most errors other than -EPIPE.

    (b) Stream style, where for example it'd be wrong to ever
        let block N+1 overwrite block N on the disk.  Once
        the first URB fails, the rest would just be unlinked
        in the completion handler.

As a consequence of using the td_list, you can now see urb
queuing in action in the driverfs 'async' file.  At least, if
you look at the right time, or use drivers (networking, etc)
that queue (bulk) reads for a long time.