I have benchmarked this on an x86_64 NUMA system and see no significant
performance difference on kernbench.  Tested on both x86_64 and powerpc.

The way we do file struct accounting is not very suitable for batched
freeing.  For scalability reasons, file accounting was
constructor/destructor based.  This meant that nr_files was decremented
only when the object was removed from the slab cache.  This is susceptible
to slab fragmentation.  With RCU based file structure, consequent batched
freeing and a test program like Serge's, we just speed this up and end up
with a very fragmented slab -

llm22:~ # cat /proc/sys/fs/file-nr
587730  0       758844

At the same time, I see only a 2000+ objects in filp cache.  The following
patch I fixes this problem.

This patch changes the file counting by removing the filp_count_lock.
Instead we use a separate percpu counter, nr_files, for now and all
accesses to it are through get_nr_files() api.  In the sysctl handler for
nr_files, we populate files_stat.nr_files before returning to user.

Counting files as an when they are created and destroyed (as opposed to
inside slab) allows us to correctly count open files with RCU.
Signed-off-by: NDipankar Sarma <dipankar@in.ibm.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch adds new tunables for RCU queue and finished batches.  There are
two types of controls - number of completed RCU updates invoked in a batch
(blimit) and monitoring for high rate of incoming RCUs on a cpu (qhimark,
qlowmark).

By default, the per-cpu batch limit is set to a small value.  If the input
RCU rate exceeds the high watermark, we do two things - force quiescent
state on all cpus and set the batch limit of the CPU to INTMAX.  Setting
batch limit to INTMAX forces all finished RCUs to be processed in one shot.
 If we have more than INTMAX RCUs queued up, then we have bigger problems
anyway.  Once the incoming queued RCUs fall below the low watermark, the
batch limit is set to the default.
Signed-off-by: NDipankar Sarma <dipankar@in.ibm.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Implement percpu_counter_sum().  This is a more accurate but slower version of
percpu_counter_read_positive().

We need this for Alex's speedup-ext3_statfs patch and for the nr_file
accounting fix.  Otherwise these things would be too inaccurate on large CPU
counts.

Cc: Ravikiran G Thirumalai <kiran@scalex86.org>
Cc: Alex Tomas <alex@clusterfs.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix i386 nmi_watchdog that does not meet watchdog timeout condition.  It
does not hit die_nmi when it should be triggered, because the current
nmi_watchdog_tick in arch/i386/kernel/nmi.c never count up alert_counter
like this:

	void nmi_watchdog_tick (struct pt_regs * regs) {
	if (last_irq_sums[cpu] == sum) {
		alert_counter[cpu]++;		<- count up alert_counter, but
		if (alert_counter[cpu] == 5*nmi_hz)
			die_nmi(regs, "NMI Watchdog detected LOCKUP");
		alert_counter[cpu] = 0;		<- reset alert_counter

This patch changes it back to the previous and working version.

This was found and originally written by Kohta NAKASHIMA.

(akpm: also uninline write_watchdog_counter(), saving 184 byets)
Signed-off-by: NGOTO Masanori <gotom@sanori.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

If the 'ptr' is a const, this code cause "assignment of read-only variable"
error on gcc 4.x.

Use __u64 instead of __typeof__(*(ptr)) for temporary variable to get
rid of errors on gcc 4.x.
Signed-off-by: NAtsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Idle threads should have a sane ->timestamp value, to avoid init kernel
thread(s) from inheriting it and causing miscalculations in
try_to_wake_up().

Reported-by: Mike Galbraith <efault@gmx.de>.
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix a bug in udf where it would write uid/gid = 0 to the disk for files
owned by the id given with the uid=/gid= mount options.  It also adds 4 new
mount options: uid/gid=forget and uid/gid=ignore.  Without any options the
id in core and on disk always match.  Giving uid/gid=nnn specifies a
default ID to be used in core when the on disk ID is -1.  uid/gid=ignore
forces the in core ID to allways be used no matter what the on disk ID is.
uid/gid=forget forces the on disk ID to always be written out as -1.

The use of these options allows you to override ownerships on a disk or
disable ownwership information from being written, allowing the media to be
used portably between different computers and possibly different users
without permissions issues that would require root to correct.
Signed-off-by: NPhillip Susi <psusi@cfl.rr.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix the mm/mempolicy.c build for !CONFIG_HUGETLB_PAGE.

Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: Martin Bligh <mbligh@google.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

We're presently getting oopses because Bluetooth (and possibly other) drivers
are calling core functions after things have been shut down.

So rather than oopsing, let's drop a warning then take avoiding action, so the
machine survives.  Once all the sub-drivers are fixed up we can remove the
take-avoiding-action part.
Signed-off-by: NPavel Machek <pavel@suse.cz>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

We fixed this:

arch/powerpc/platforms/pseries/eeh.c: In function `eeh_add_device_tree_late':
arch/powerpc/platforms/pseries/eeh.c:901: warning: implicit declaration of function `eeh_add_device_late'
arch/powerpc/platforms/pseries/eeh.c: At top level:
arch/powerpc/platforms/pseries/eeh.c:918: error: conflicting types for 'eeh_add_device_late'
arch/powerpc/platforms/pseries/eeh.c:901: error: previous implicit declaration of 'eeh_add_device_late' was here
make[2]: *** [arch/powerpc/platforms/pseries/eeh.o] Error 1

But we forgot the !CONFIG_EEH stub.
Signed-off-by: NMark Fasheh <mark.fasheh@oracle.com>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

They aren't used (nor even really usable) outside of pipe.c anyway
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
  [IA64] mca recovery return value when no bus check
  [IA64] SGI SN drivers: don't report !sn2 hardware as an error
  [IA64] don't report !sn2 or !summit hardware as an error
  [IA64] gensparse_defconfig: turn on PNPACPI
  [IA64] Increase severity of MCA recovery messages

Instead of having a hard-to-read and confusing conditional in the
caller, just make the slab order calculation handle this special case,
since it's simple and obvious there.
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

* master.kernel.org:/home/rmk/linux-2.6-serial:
  [SERIAL] ip22zilog: Fix oops on runlevel change with serial console
  [SERIAL] Fix two bugs in parport_serial

* master.kernel.org:/home/rmk/linux-2.6-arm:
  [ARM] 3353/1: NAS100d: protect  nas100d_power_exit() with machine_is_nas100d()
  [ARM] 3352/1: DSB required for the completion of a TLB maintenance operation

When there is no bus check, the return code should be failure, not success.

Signed-off-by: Russ Anderson (rja@sgi.com)
Signed-off-by: NTony Luck <tony.luck@intel.com>

This stuff is all in the generic ia64 kernel, and the new initcall error
reporting complains about them.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

This stuff is all in the generic ia64 kernel, and the new initcall error
reporting complains about them.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Turn on CONFIG_PNPACPI.  I recently removed 8250_acpi.c.  All devices
previously claimed by 8250_acpi.c should now be claimed by 8250_pnp.c.
This depends on having CONFIG_PNPACPI so ACPI devices show up as PNP
devices.

All other ia64 defconfigs either have CONFIG_PNPACPI already, or
don't have 8250 support turned on at all.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

The MCA recovery messages are currently KERN_DEBUG,
so they don't show up in /var/log/messages (by default).
Increase the severity to KERN_ERR, for the initial
message (and also add the physical address to this
message). Leave the successful isolation message as
KERN_DEBUG, but increase the severity when isolation
fails to KERN_CRIT.

[Russ' patch made these all KERN_CRIT]

Signed-off-by: Russ Anderson (rja@sgi.com)
Signed-off-by: NTony Luck <tony.luck@intel.com>

The size of the skb carrying the netlink message is not
equivalent to the length of the actual netlink message
due to padding. ip_queue matches the length of the payload
against the original packet size to determine if packet
mangling is desired, due to the above wrong assumption
arbitary packets may not be mangled depening on their
original size.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Patch from Alessandro Zummo

nas100d_power_exit(void) gets some protection
to avoid freeing an irq when it is not appropriate to do so.
Signed-off-by: NRod Whitby <rod@whitby.id.au>
Signed-off-by: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Incorrect uart_write_wakeup() calls cause reference to a NULL tty
pointer.  This has been fixed in the sunsab and sunzilog serial drivers
in October 2005.  Update the ip22zilog, which is based on sunzilog,
accordingly.
Signed-off-by: NMartin Michlmayr <tbm@cyrius.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [TG3]: Add DMA address workaround

We don't do interruptible waits for the pipe mutex anywhere else any
more either, so don't do it in fifo_open() either.
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Patch from Catalin Marinas

Chapter B2.7.3 in the latest ARM ARM (with v6 information) states that
the completion of a TLB maintenance operation is only guaranteed by
the execution of a DSB (Data Syncronization Barrier, formerly Data
Write Barrier or Drain Write Buffer).

Note that a DSB is only needed in the flush_tlb_kernel_* functions
since the completion is guaranteed by a mode change (i.e. switching
back to user mode) for the flush_tlb_user_* functions.
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Add DMA workaround for chips that do not support full 64-bit DMA
addresses.

5714, 5715, and 5780 chips only support DMA addresses less than 40
bits. On 64-bit systems with IOMMU, set the dma_mask to 40-bit so
that pci_map_xxx() calls will map the DMA address below 40 bits if
necessary. On 64-bit systems without IOMMU, set the dma_mask to
64-bit and check for DMA addresses exceeding the limit in
tg3_start_xmit().

5788 only supports 32-bit DMA so need to set the mask appropriately
also.

Thanks to Chris Elmquist at SGI for reporting and helping to debug
the problem on 5714.

Thanks to David Miller for explaining the HIGHMEM and DMA stuff.
Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
  IB/srp: Don't send task management commands after target removal

Rather than checking for some known failures, check positively for the
success response code 0x0001 and return -EIO for unrecognized failure
response codes.
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Cc: Greg Smith <gsmith@nc.rr.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix matching of devmodel in modaliases.  It breaks automatic loading of any
dasd module.

Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The Windfarm PID module lacks a licence, it should be GPL, here it is
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The point of the smaps "shared" is to count the number of pages that are
mapped by more than one process, according to Mauricio Lin.  However, smaps
uses page_count for this, so it will return a false positive for every page
that is mapped by just that one process, which is also in pagecache or
swapcache.  There are false positive situations for anonymous pages not in
swapcache as well: - page reclaim, migration - get_user_pages (eg.
direct-io, ptrace)

Use page_mapcount instead, to count the number of mappings to the page.

Use vm_normal_page so that weird things like /dev/mem aren't counted either.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

smaps doesn't have a hugepage pagetable walker. Skip walking hugepage
vmas.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

ramfs neglects to update the directory mtime and ctime fields when creating
a new symbolic link.  Ramfs was modified in 2.6.15 to update these fields
when other types of entries are created.  The symlink support is separate
from that other support, so that change did not cover quite all of the
possibilities.

All of the directory content manipulation entry points now seem to be
covered with respect to these time field updates.
Signed-off-by: NPeter Staubach <staubach@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch makes the kernel bootable again on ia32 EFI systems.
Signed-off-by: NEdgar Hucek <hostmaster@ed-soft.at>
Cc: Matt Domsch <Matt_Domsch@dell.com>
Cc: Zachary Amsden <zach@vmware.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Change the format of numa_maps to be more compact and contain additional
information that is useful for managing and troubleshooting memory on a
NUMA system.  Numa_maps can now also support huge pages.

Fixes:

1. More compact format. Only display fields if they contain additional
	information.

2. Always display information for all vmas. The old numa_maps did not display
	vma with no mapped entries. This was a bit confusing because page
	migration removes ptes for file backed vmas. After page migration
	a part of the vmas vanished.

3. Rename maxref to maxmap. This is the maximum mapcount of all the pages
	in a vma and may be used as an indicator as to how many processes
	may be using a certain vma.

4. Include the ability to scan over huge page vmas.

New items shown:

dirty
	Number of pages in a vma that have either the dirty bit set in the
	page_struct or in the pte.

file=<filename>
	The file backing the pages if any

stack
	Stack area

heap
	Heap area

huge
	Huge page area. The number of pages shows is the number of huge
	pages not the regular sized pages.

swapcache
	Number of pages with swap references. Must be >0 in order to
	be shown.

active
	Number of active pages. Only displayed if different from the number
	of pages mapped.

writeback
	Number of pages under writeback. Only displayed if >0.

Sample ouput of a process using huge pages:

00000000 default
2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13
2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2
2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1
2000000000074000 default file=/lib/librt-2.3.90.so
2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1
2000000000084000 default
2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52
20000000002bc000 default file=/lib/libc-2.3.90.so
20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2
20000000002d4000 default anon=1 swapcache=1 N1=1
20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6
20000000002fc000 default file=/lib/libpthread-2.3.90.so
2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1
200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1
2000000000320000 default anon=1 dirty=1 N1=1
200000000071c000 default
2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1
2000000000f1c000 default
2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1
200000000171c000 default
2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1
2000000001b20000 default
2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2
2000000001b48000 default file=/lib/libgcc_s.so.1
2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1
2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2
2000000001b74000 default file=/lib/libunwind.so.7.0.0
2000000001b80000 default file=/lib/libunwind.so.7.0.0
2000000001b84000 default
4000000000000000 default file=/media/huge/test9 mapped=1 N1=1
6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1
6000000000004000 default heap
607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1
607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1
8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3
8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2
80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix bugs in error paths of snd_ctl_elem_add()
 - NULL reference
 - double free (already freed in snd_ctl_add())
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Cc: Jaroslav Kysela <perex@suse.cz>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Add a compiler barrier so that we don't read jiffies before updating
jiffies_64.
Signed-off-by: NAtsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Systems with extemely large numbers of nodes or cpus need to kmalloc
structures larger than is currently supported.  This patch increases the
maximum supported size for very large systems.

This patch should have no effect on current systems.

(akpm: why not just use alloc_pages() for sysfs_cpus?)
Signed-off-by: NJack Steiner <steiner@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

include/linux/memory_hotplug.h:53: warning: 'struct page' declared inside parameter list

(akpm: I tossed in a couple more possibly-needed-sometime struct decls too)
Signed-off-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>