Linus suggested that probably all the supported architectures can
allow a negative mutex count without incorrect behavior, so we can
then back out the architecture specific change and allow the
mutex count to go to any negative number. That should further
reduce contention for non-x86 architecture.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Chandramouleeswaran Aswin <aswin@hp.com>
Cc: Davidlohr Bueso <davidlohr.bueso@hp.com>
Cc: Norton Scott J <scott.norton@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1366226594-5506-5-git-send-email-Waiman.Long@hp.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

The current mutex spinning code (with MUTEX_SPIN_ON_OWNER option
turned on) allow multiple tasks to spin on a single mutex
concurrently. A potential problem with the current approach is
that when the mutex becomes available, all the spinning tasks
will try to acquire the mutex more or less simultaneously. As a
result, there will be a lot of cacheline bouncing especially on
systems with a large number of CPUs.

This patch tries to reduce this kind of contention by putting
the mutex spinners into a queue so that only the first one in
the queue will try to acquire the mutex. This will reduce
contention and allow all the tasks to move forward faster.

The queuing of mutex spinners is done using an MCS lock based
implementation which will further reduce contention on the mutex
cacheline than a similar ticket spinlock based implementation.
This patch will add a new field into the mutex data structure
for holding the MCS lock. This expands the mutex size by 8 bytes
for 64-bit system and 4 bytes for 32-bit system. This overhead
will be avoid if the MUTEX_SPIN_ON_OWNER option is turned off.

The following table shows the jobs per minute (JPM) scalability
data on an 8-node 80-core Westmere box with a 3.7.10 kernel. The
numactl command is used to restrict the running of the fserver
workloads to 1/2/4/8 nodes with hyperthreading off.

+-----------------+-----------+-----------+-------------+----------+
|  Configuration  | Mean JPM  | Mean JPM  |  Mean JPM   | % Change |
|                 | w/o patch | patch 1   | patches 1&2 |  1->1&2  |
+-----------------+------------------------------------------------+
|                 |              User Range 1100 - 2000            |
+-----------------+------------------------------------------------+
| 8 nodes, HT off |  227972   |  227237   |   305043    |  +34.2%  |
| 4 nodes, HT off |  393503   |  381558   |   394650    |   +3.4%  |
| 2 nodes, HT off |  334957   |  325240   |   338853    |   +4.2%  |
| 1 node , HT off |  198141   |  197972   |   198075    |   +0.1%  |
+-----------------+------------------------------------------------+
|                 |              User Range 200 - 1000             |
+-----------------+------------------------------------------------+
| 8 nodes, HT off |  282325   |  312870   |   332185    |   +6.2%  |
| 4 nodes, HT off |  390698   |  378279   |   393419    |   +4.0%  |
| 2 nodes, HT off |  336986   |  326543   |   340260    |   +4.2%  |
| 1 node , HT off |  197588   |  197622   |   197582    |    0.0%  |
+-----------------+-----------+-----------+-------------+----------+

At low user range 10-100, the JPM differences were within +/-1%.
So they are not that interesting.

The fserver workload uses mutex spinning extensively. With just
the mutex change in the first patch, there is no noticeable
change in performance.  Rather, there is a slight drop in
performance. This mutex spinning patch more than recovers the
lost performance and show a significant increase of +30% at high
user load with the full 8 nodes. Similar improvements were also
seen in a 3.8 kernel.

The table below shows the %time spent by different kernel
functions as reported by perf when running the fserver workload
at 1500 users with all 8 nodes.

+-----------------------+-----------+---------+-------------+
|        Function       |  % time   | % time  |   % time    |
|                       | w/o patch | patch 1 | patches 1&2 |
+-----------------------+-----------+---------+-------------+
| __read_lock_failed    |  34.96%   | 34.91%  |   29.14%    |
| __write_lock_failed   |  10.14%   | 10.68%  |    7.51%    |
| mutex_spin_on_owner   |   3.62%   |  3.42%  |    2.33%    |
| mspin_lock            |    N/A    |   N/A   |    9.90%    |
| __mutex_lock_slowpath |   1.46%   |  0.81%  |    0.14%    |
| _raw_spin_lock        |   2.25%   |  2.50%  |    1.10%    |
+-----------------------+-----------+---------+-------------+

The fserver workload for an 8-node system is dominated by the
contention in the read/write lock. Mutex contention also plays a
role. With the first patch only, mutex contention is down (as
shown by the __mutex_lock_slowpath figure) which help a little
bit. We saw only a few percents improvement with that.

By applying patch 2 as well, the single mutex_spin_on_owner
figure is now split out into an additional mspin_lock figure.
The time increases from 3.42% to 11.23%. It shows a great
reduction in contention among the spinners leading to a 30%
improvement. The time ratio 9.9/2.33=4.3 indicates that there
are on average 4+ spinners waiting in the spin_lock loop for
each spinner in the mutex_spin_on_owner loop. Contention in
other locking functions also go down by quite a lot.

The table below shows the performance change of both patches 1 &
2 over patch 1 alone in other AIM7 workloads (at 8 nodes,
hyperthreading off).

+--------------+---------------+----------------+-----------------+
|   Workload   | mean % change | mean % change  | mean % change   |
|              | 10-100 users  | 200-1000 users | 1100-2000 users |
+--------------+---------------+----------------+-----------------+
| alltests     |      0.0%     |     -0.8%      |     +0.6%       |
| five_sec     |     -0.3%     |     +0.8%      |     +0.8%       |
| high_systime |     +0.4%     |     +2.4%      |     +2.1%       |
| new_fserver  |     +0.1%     |    +14.1%      |    +34.2%       |
| shared       |     -0.5%     |     -0.3%      |     -0.4%       |
| short        |     -1.7%     |     -9.8%      |     -8.3%       |
+--------------+---------------+----------------+-----------------+

The short workload is the only one that shows a decline in
performance probably due to the spinner locking and queuing
overhead.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Reviewed-by: Davidlohr Bueso <davidlohr.bueso@hp.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Chandramouleeswaran Aswin <aswin@hp.com>
Cc: Norton Scott J <scott.norton@hp.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1366226594-5506-4-git-send-email-Waiman.Long@hp.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

In the __mutex_lock_common() function, an initial entry into
the lock slow path will cause two atomic_xchg instructions to be
issued. Together with the atomic decrement in the fast path, a
total of three atomic read-modify-write instructions will be
issued in rapid succession. This can cause a lot of cache
bouncing when many tasks are trying to acquire the mutex at the
same time.

This patch will reduce the number of atomic_xchg instructions
used by checking the counter value first before issuing the
instruction. The atomic_read() function is just a simple memory
read. The atomic_xchg() function, on the other hand, can be up
to 2 order of magnitude or even more in cost when compared with
atomic_read(). By using atomic_read() to check the value first
before calling atomic_xchg(), we can avoid a lot of unnecessary
cache coherency traffic. The only downside with this change is
that a task on the slow path will have a tiny bit less chance of
getting the mutex when competing with another task in the fast
path.

The same is true for the atomic_cmpxchg() function in the
mutex-spin-on-owner loop. So an atomic_read() is also performed
before calling atomic_cmpxchg().

The mutex locking and unlocking code for the x86 architecture
can allow any negative number to be used in the mutex count to
indicate that some tasks are waiting for the mutex. I am not so
sure if that is the case for the other architectures. So the
default is to avoid atomic_xchg() if the count has already been
set to -1. For x86, the check is modified to include all
negative numbers to cover a larger case.

The following table shows the jobs per minutes (JPM) scalability
data on an 8-node 80-core Westmere box with a 3.7.10 kernel. The
numactl command is used to restrict the running of the
high_systime workloads to 1/2/4/8 nodes with hyperthreading on
and off.

+-----------------+-----------+------------+----------+
|  Configuration  | Mean JPM  |  Mean JPM  | % Change |
|		  | w/o patch | with patch |	      |
+-----------------+-----------------------------------+
|		  |      User Range 1100 - 2000	      |
+-----------------+-----------------------------------+
| 8 nodes, HT on  |    36980   |   148590  | +301.8%  |
| 8 nodes, HT off |    42799   |   145011  | +238.8%  |
| 4 nodes, HT on  |    61318   |   118445  |  +51.1%  |
| 4 nodes, HT off |   158481   |   158592  |   +0.1%  |
| 2 nodes, HT on  |   180602   |   173967  |   -3.7%  |
| 2 nodes, HT off |   198409   |   198073  |   -0.2%  |
| 1 node , HT on  |   149042   |   147671  |   -0.9%  |
| 1 node , HT off |   126036   |   126533  |   +0.4%  |
+-----------------+-----------------------------------+
|		  |       User Range 200 - 1000	      |
+-----------------+-----------------------------------+
| 8 nodes, HT on  |   41525    |   122349  | +194.6%  |
| 8 nodes, HT off |   49866    |   124032  | +148.7%  |
| 4 nodes, HT on  |   66409    |   106984  |  +61.1%  |
| 4 nodes, HT off |  119880    |   130508  |   +8.9%  |
| 2 nodes, HT on  |  138003    |   133948  |   -2.9%  |
| 2 nodes, HT off |  132792    |   131997  |   -0.6%  |
| 1 node , HT on  |  116593    |   115859  |   -0.6%  |
| 1 node , HT off |  104499    |   104597  |   +0.1%  |
+-----------------+------------+-----------+----------+

At low user range 10-100, the JPM differences were within +/-1%.
So they are not that interesting.

AIM7 benchmark run has a pretty large run-to-run variance due to
random nature of the subtests executed. So a difference of less
than +-5% may not be really significant.

This patch improves high_systime workload performance at 4 nodes
and up by maintaining transaction rates without significant
drop-off at high node count.  The patch has practically no
impact on 1 and 2 nodes system.

The table below shows the percentage time (as reported by perf
record -a -s -g) spent on the __mutex_lock_slowpath() function
by the high_systime workload at 1500 users for 2/4/8-node
configurations with hyperthreading off.

+---------------+-----------------+------------------+---------+
| Configuration | %Time w/o patch | %Time with patch | %Change |
+---------------+-----------------+------------------+---------+
|    8 nodes    |      65.34%     |      0.69%       |  -99%   |
|    4 nodes    |       8.70%	  |      1.02%	     |  -88%   |
|    2 nodes    |       0.41%     |      0.32%       |  -22%   |
+---------------+-----------------+------------------+---------+

It is obvious that the dramatic performance improvement at 8
nodes was due to the drastic cut in the time spent within the
__mutex_lock_slowpath() function.

The table below show the improvements in other AIM7 workloads
(at 8 nodes, hyperthreading off).

+--------------+---------------+----------------+-----------------+
|   Workload   | mean % change | mean % change  | mean % change   |
|              | 10-100 users  | 200-1000 users | 1100-2000 users |
+--------------+---------------+----------------+-----------------+
| alltests     |     +0.6%     |   +104.2%      |   +185.9%       |
| five_sec     |     +1.9%     |     +0.9%      |     +0.9%       |
| fserver      |     +1.4%     |     -7.7%      |     +5.1%       |
| new_fserver  |     -0.5%     |     +3.2%      |     +3.1%       |
| shared       |    +13.1%     |   +146.1%      |   +181.5%       |
| short        |     +7.4%     |     +5.0%      |     +4.2%       |
+--------------+---------------+----------------+-----------------+
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Reviewed-by: Davidlohr Bueso <davidlohr.bueso@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Chandramouleeswaran Aswin <aswin@hp.com>
Cc: Norton: Scott J <scott.norton@hp.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1366226594-5506-3-git-send-email-Waiman.Long@hp.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

As mentioned by Ingo, the SCHED_FEAT_OWNER_SPIN scheduler
feature bit was really just an early hack to make with/without
mutex-spinning testable. So it is no longer necessary.

This patch removes the SCHED_FEAT_OWNER_SPIN feature bit and
move the mutex spinning code from kernel/sched/core.c back to
kernel/mutex.c which is where they should belong.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Chandramouleeswaran Aswin <aswin@hp.com>
Cc: Davidlohr Bueso <davidlohr.bueso@hp.com>
Cc: Norton Scott J <scott.norton@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1366226594-5506-2-git-send-email-Waiman.Long@hp.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

sysfs started complaining about cases where permissions don't
match what's in the sysfs ops structure (such as allowing read
without a "show" callback).
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: williams@redhat.com
Link: http://lkml.kernel.org/r/1363795105-5884-1-git-send-email-sasha.levin@oracle.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Hong Zhiguo <honkiko@gmail.com>
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/1365058881-4044-1-git-send-email-honkiko@gmail.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

Pull KVM fix from Gleb Natapov:
 "Bugfix for the regression introduced by commit c300aa64"

* git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Allow cross page reads and writes from cached translations.

Pull x86 fixes from Peter Anvin:
 "Two quite small fixes: one a build problem, and the other fixes
  seccomp filters on x32."

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Fix rebuild with EFI_STUB enabled
  x86: remove the x32 syscall bitmask from syscall_get_nr()

Interrupt handlers are always invoked with interrupts disabled, so
remove all uses of the deprecated IRQF_DISABLED flag.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Linux has expected that interrupt handlers are executed with local
interrupts disabled for a while now, so ensure that this is the case on
Alpha even for non-device interrupts such as IPIs.

Without this patch, secondary boot results in the following backtrace:

  warning: at kernel/softirq.c:139 __local_bh_enable+0xb8/0xd0()
  trace:
    __local_bh_enable+0xb8/0xd0
    irq_enter+0x74/0xa0
    scheduler_ipi+0x50/0x100
    handle_ipi+0x84/0x260
    do_entint+0x1ac/0x2e0
    irq_exit+0x60/0xa0
    handle_irq+0x98/0x100
    do_entint+0x2c8/0x2e0
    ret_from_sys_call+0x0/0x10
    load_balance+0x3e4/0x870
    cpu_idle+0x24/0x80
    rcu_eqs_enter_common.isra.38+0x0/0x120
    cpu_idle+0x40/0x80
    rest_init+0xc0/0xe0
    _stext+0x1c/0x20

A similar dump occurs if you try to reboot using magic-sysrq.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Due to all of the goodness being packed into today's kernels, the
resulting image isn't as slim as it once was.

In light of this, don't pass -msmall-data to gcc, which otherwise results
in link failures due to impossible relocations when compiling anything but
the most trivial configurations.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Tested-by: Thorsten Kranzkowski <dl8bcu@dl8bcu.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fixes a NULL pointer dereference at boot on UP1500.

Cc: stable@vger.kernel.org
Reviewed-and-Tested-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Jay Estabrook <jay.estabrook@gmail.com>
Signed-off-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This patch adds support for kvm_gfn_to_hva_cache_init functions for
reads and writes that will cross a page.  If the range falls within
the same memslot, then this will be a fast operation.  If the range
is split between two memslots, then the slower kvm_read_guest and
kvm_write_guest are used.

Tested: Test against kvm_clock unit tests.
Signed-off-by: Andrew Honig <ahonig@google.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

Pull device-mapper fixes from Alasdair Kergon:
 "A pair of patches to fix the writethrough mode of the device-mapper
  cache target when the device being cached is not itself wrapped with
  device-mapper."

* tag 'dm-3.9-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm:
  dm cache: reduce bio front_pad size in writeback mode
  dm cache: fix writes to cache device in writethrough mode

Pull PCI fixes from Bjorn Helgaas:
 "PCI updates for v3.9:

  ASPM
      Revert "PCI/ACPI: Request _OSC control before scanning PCI root bus"
  kexec
      PCI: Don't try to disable Bus Master on disconnected PCI devices
  Platform ROM images
      PCI: Add PCI ROM helper for platform-provided ROM images
      nouveau: Attempt to use platform-provided ROM image
      radeon: Attempt to use platform-provided ROM image
  Hotplug
      PCI/ACPI: Always resume devices on ACPI wakeup notifications
      PCI/PM: Disable runtime PM of PCIe ports
  EISA
      EISA/PCI: Fix bus res reference
      EISA/PCI: Init EISA early, before PNP"

* tag 'pci-v3.9-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
  PCI/PM: Disable runtime PM of PCIe ports
  PCI/ACPI: Always resume devices on ACPI wakeup notifications
  PCI: Don't try to disable Bus Master on disconnected PCI devices
  Revert "PCI/ACPI: Request _OSC control before scanning PCI root bus"
  radeon: Attempt to use platform-provided ROM image
  nouveau: Attempt to use platform-provided ROM image
  EISA/PCI: Init EISA early, before PNP
  EISA/PCI: Fix bus res reference
  PCI: Add PCI ROM helper for platform-provided ROM images

Pull networking fixes from David Miller:

 1) Fix erroneous sock_orphan() leading to crashes and double
    kfree_skb() in NFC protocol.  From Thierry Escande and Samuel Ortiz.

 2) Fix use after free in remain-on-channel mac80211 code, from Johannes
    Berg.

 3) nf_reset() needs to reset the NF tracing cookie, otherwise we can
    leak it from one namespace into another.  Fix from Gao Feng and
    Patrick McHardy.

 4) Fix overflow in channel scanning array of mwifiex driver, from Stone
    Piao.

 5) Fix loss of link after suspend/shutdown in r8169, from Hayes Wang.

 6) Synchronization of unicast address lists to the undelying device
    doesn't work because whether to sync is maintained as a boolean
    rather than a true count.  Fix from Vlad Yasevich.

 7) Fix corruption of TSO packets in atl1e by limiting the segmented
    packet length.  From Hannes Frederic Sowa.

 8) Revert bogus AF_UNIX credential passing change and fix the
    coalescing issue properly, from Eric W Biederman.

 9) Changes of ipv4 address lifetime settings needs to generate a
    notification, from Jiri Pirko.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (22 commits)
  netfilter: don't reset nf_trace in nf_reset()
  net: ipv4: notify when address lifetime changes
  ixgbe: fix registration order of driver and DCA nofitication
  af_unix: If we don't care about credentials coallesce all messages
  Revert "af_unix: dont send SCM_CREDENTIAL when dest socket is NULL"
  bonding: remove sysfs before removing devices
  atl1e: limit gso segment size to prevent generation of wrong ip length fields
  net: count hw_addr syncs so that unsync works properly.
  r8169: fix auto speed down issue
  netfilter: ip6t_NPT: Fix translation for non-multiple of 32 prefix lengths
  mwifiex: limit channel number not to overflow memory
  NFC: microread: Fix build failure due to a new MEI bus API
  iwlwifi: dvm: fix the passive-no-RX workaround
  netfilter: nf_conntrack: fix error return code
  NFC: llcp: Keep the connected socket parent pointer alive
  mac80211: fix idle handling sequence
  netfilter: nfnetlink_acct: return -EINVAL if object name is empty
  netfilter: nfnetlink_queue: fix error return code in nfnetlink_queue_init()
  netfilter: reset nf_trace in nf_reset
  mac80211: fix remain-on-channel cancel crash
  ...

eboot.o and efi_stub_$(BITS).o didn't get added to "targets", and hence
their .cmd files don't get included by the build machinery, leading to
the files always getting rebuilt.

Rather than adding the two files individually, take the opportunity and
add $(VMLINUX_OBJS) to "targets" instead, thus allowing the assignment
at the top of the file to be shrunk quite a bit.

At the same time, remove a pointless flags override line - the variable
assigned to was misspelled anyway, and the options added are
meaningless for assembly sources.

[ hpa: the patch is not minimal, but I am taking it for -urgent anyway
  since the excess impact of the patch seems to be small enough. ]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/515C5D2502000078000CA6AD@nat28.tlf.novell.com
Cc: Matthew Garrett <mjg@redhat.com>
Cc: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

Commit 130549fe ("netfilter: reset nf_trace in nf_reset") added code
to reset nf_trace in nf_reset(). This is wrong and unnecessary.

nf_reset() is used in the following cases:

- when passing packets up the the socket layer, at which point we want to
  release all netfilter references that might keep modules pinned while
  the packet is queued. nf_trace doesn't matter anymore at this point.

- when encapsulating or decapsulating IPsec packets. We want to continue
  tracing these packets after IPsec processing.

- when passing packets through virtual network devices. Only devices on
  that encapsulate in IPv4/v6 matter since otherwise nf_trace is not
  used anymore. Its not entirely clear whether those packets should
  be traced after that, however we've always done that.

- when passing packets through virtual network devices that make the
  packet cross network namespace boundaries. This is the only cases
  where we clearly want to reset nf_trace and is also what the
  original patch intended to fix.

Add a new function nf_reset_trace() and use it in dev_forward_skb() to
fix this properly.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull MIPS fixes from Ralf Baechle:
 "Fixes for a number of small glitches in various corners of the MIPS
  tree.  No particular areas is standing out.

  With this applied all MIPS defconfigs are building fine.  No merge
  conflicts are expected."

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
  MIPS: Delete definition of SA_RESTORER.
  MIPS: Fix ISA level which causes secondary cache init bypassing and more
  MIPS: Fix build error cavium-octeon without CONFIG_SMP
  MIPS: Kconfig: Rename SNIPROM too
  MIPS: Alchemy: Fix typo "CONFIG_DEBUG_PCI"
  MIPS: Unbreak function tracer for 64-bit kernel.

Pull GFS2 fixes from Steven Whitehouse:
 "There are two patches which fix up a couple of minor issues in the DLM
  interface code, a missing error path in gfs2_rs_alloc(), one patch
  which fixes a problem during "withdraw" and a fix for discards/FITRIM
  when using 4k sector sized devices."

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes:
  GFS2: Issue discards in 512b sectors
  GFS2: Fix unlock of fcntl locks during withdrawn state
  GFS2: return error if malloc failed in gfs2_rs_alloc()
  GFS2: use memchr_inv
  GFS2: use kmalloc for lvb bitmap

Commit e2eed58b ("IB/qib: change QLogic to Intel") moved a firmware
file potentially breaking the ABI.

This patch reverts that aspect of the fix as well as reverting the
firmware name as used in qib.
Reported-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull spi fixes from Mark Brown:
 "A bunch of small driver fixes plus a fix for error handling in the
  core - nothing too exciting overall."

* tag 'spi-fix-v3.9-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/misc:
  spi/mpc512x-psc: optionally keep PSC SS asserted across xfer segmensts
  spi: Unlock a spinlock before calling into the controller driver.
  spi/s3c64xx: modified error interrupt handling and init
  spi/bcm63xx: don't disable non enabled clocks in probe error path
  spi/bcm63xx: Remove unused variable
  spi: slink-tegra20: move runtime pm calls to transfer_one_message

This patch changes GFS2's discard issuing code so that it calls
function sb_issue_discard rather than blkdev_issue_discard. The
code was calling blkdev_issue_discard and specifying the correct
sector offset and sector size, but blkdev_issue_discard expects
these values to be in terms of 512 byte sectors, even if the native
sector size for the device is different. Calling sb_issue_discard
with the BLOCK size instead ensures the correct block-to-512b-sector
translation. I verified that "minlen" is specified in blocks, so
comparing it to a number of blocks is correct.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

This reverts commit 0ef1594c.

This patch introduced a few races which cannot be easily fixed with a
small follow-up patch. Furthermore, the SoC with the broken hardware
register, which this patch intended to add support for, can only be used
with device trees, which this driver currently does not support.

[ Here is the discussion that led to this "revert" patch:
  https://lkml.org/lkml/2013/4/3/176 ]

Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull fbdev fixes from Tomi Valkeinen:
 "Fix uvesafb crash bug and typoed flag name in fbmon's new videomode
  code"

* tag 'fbdev-fixes-3.9-rc6' of git://gitorious.org/linux-omap-dss2/linux:
  video:uvesafb: Fix dereference NULL pointer code path
  fbmon: use VESA_DMT_VSYNC_HIGH to fix typo

Pull sound fixes from Takashi Iwai:
 "This contains slightly more volumes than usual at this stage, mostly
  because of my vacation in the last week.  Nothing to scare, all small
  and/or trivial fixes:

   - Fix loop path handling in ASoC DAPM
   - Some memory handling fixes in ASoC core
   - Fix spear_pcm to adapt to the updated API
   - HD-audio HDMI ELD handling fixes
   - Fix for CM6331 USB-audio SRC change bugs
   - Revert power_save_controller option change due to user-space usage
   - A few other small ASoC and HD-audio fixes"

* tag 'sound-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ALSA: hda/generic - fix uninitialized variable
  Revert "ALSA: hda - Allow power_save_controller option override DCAPS"
  ALSA: hda - fix typo in proc output
  ALSA: hda - Enabling Realtek ALC 671 codec
  ALSA: usb: Work around CM6631 sample rate change bug
  ALSA: hda - bug fix on HDMI ELD debug message
  ALSA: hda - bug fix on return value when getting HDMI ELD info
  ASoC: dma-sh7760: Fix compile error
  ASoC: core: fix invalid free of devm_ allocated data
  ASoC: spear_pcm: Update to new pcm_new() API
  ASoC:: max98090: Remove executable bit
  ASoC: dapm: Fix pointer dereference in is_connected_output_ep()
  ASoC: pcm030 audio fabric: remove __init from probe
  ASoC: imx-ssi: Fix occasional AC97 reset failure
  ASoC: core: fix possible memory leak in snd_soc_bytes_put()
  ASoC: wm_adsp: fix possible memory leak in wm_adsp_load_coeff()
  ASoC: dapm: Fix handling of loops
  ASoC: si476x: Add missing break for SNDRV_PCM_FORMAT_S8 switch case

A recent patch to fix the dm cache target's writethrough mode extended
the bio's front_pad to include a 1056-byte struct dm_bio_details.
Writeback mode doesn't need this, so this patch reduces the
per_bio_data_size to 16 bytes in this case instead of 1096.

The dm_bio_details structure was added in "dm cache: fix writes to
cache device in writethrough mode" which fixed commit e2e74d61 ("dm
cache: fix race in writethrough implementation").  In writeback mode
we avoid allocating the writethrough-specific members of the
per_bio_data structure (the dm_bio_details structure included).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

The dm-cache writethrough strategy introduced by commit e2e74d61
("dm cache: fix race in writethrough implementation") issues a bio to
the origin device, remaps and then issues the bio to the cache device.
This more conservative in-series approach was selected to favor
correctness over performance (of the previous parallel writethrough).
However, this in-series implementation that reuses the same bio to write
both the origin and cache device didn't take into account that the block
layer's req_bio_endio() modifies a completing bio's bi_sector and
bi_size.  So the new writethrough strategy needs to preserve these bio
fields, and restore them before submission to the cache device,
otherwise nothing gets written to the cache (because bi_size is 0).

This patch adds a struct dm_bio_details field to struct per_bio_data,
and uses dm_bio_record() and dm_bio_restore() to ensure the bio is
restored before reissuing to the cache device.  Adding such a large
structure to the per_bio_data is not ideal but we can improve this
later, for now correctness is the important thing.

This problem initially went unnoticed because the dm-cache test-suite
uses a linear DM device for the dm-cache device's origin device.
Writethrough worked as expected because DM submits a *clone* of the
original bio, so the original bio which was reused for the cache was
never touched.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

SA_RESTORER used to be defined as 0x04000000 but only the O32 ABI ever
supported its use and no libc was using it, so the entire sa-restorer
functionality was removed with lmo commit 39bffc12c3580ab [Zap sa_restorer.]
for 2.5.48 retaining only the SA_RESTORER definition as a reminder to avoid
accidental reuse of the mask bit.

Upstream cdef9602 [signal: always clear
sa_restorer on execve] adds code that assumes sa_sigaction has an
sa_restorer field, if SA_RESTORER is defined which would break MIPS.
So remove the SA_RESTORER definition before the v3.8.4 merge.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
(cherry picked from commit 17da8d63add23830892ac4dc2cbb3b5d4ffb79a8)

The commit a96102be introduced set_isa() where compatible ISA info is
also set aside from the one gets passed in. It means, for example, 1004K
will have MIPS_CPU_ISA_M32R2/M32R1/II/I flags. This leads to things like
the following inappropriate:

if (c->isa_level == MIPS_CPU_ISA_M32R1 ||
    c->isa_level == MIPS_CPU_ISA_M32R2 ||
    c->isa_level == MIPS_CPU_ISA_M64R1 ||
    c->isa_level == MIPS_CPU_ISA_M64R2)

This patch fixes it.
Signed-off-by: Deng-Cheng Zhu <dengcheng.zhu@imgtec.com>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: linux-mips@linux-mips.org
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

Singed-off-by: EunBong Song <eunb.song@samsung.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

CONFIG_SNIPROM was renamed to CONFIG_FW_SNIPROM in v3.8. Let's rename
SNIPROM itself too.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Cc: linux-mips@linux-mips.org;
Cc: linux-kernel@vger.kernel.org
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

Commit 7517de34 ("MIPS: Alchemy: Redo
PCI as platform driver") added a reference to CONFIG_DEBUG_PCI. Change
it to CONFIG_PCI_DEBUG, as that is a valid Kconfig macro.

Also add a newline to a debugging printk that this fix enables.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

Commit 58b69401 [MIPS: Function tracer: Fix broken function tracing]
completely broke the function tracer for 64-bit kernels.  The symptom is
a system hang very early in the boot process.

The fix: Remove/fix $sp adjustments for 64-bit case.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: Al Cooper <alcooperx@gmail.com>
Cc: viric@viric.name
Cc: stable@vger.kernel.org # 3.8.x
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

changed is not initialized in path_power_down_sync, but it is expected
to be false in case no change happened in the loop. So set it to
false.
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

if userspace changes lifetime of address, send netlink notification and
call notifier.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>

ixgbe_notify_dca cannot be called before driver registration
because it expects driver's klist_devices to be allocated and
initialized. While on it make sure debugfs files are removed
when registration fails.

Cc: stable <stable@vger.kernel.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It was reported that the following LSB test case failed
https://lsbbugs.linuxfoundation.org/attachment.cgi?id=2144 because we
were not coallescing unix stream messages when the application was
expecting us to.

The problem was that the first send was before the socket was accepted
and thus sock->sk_socket was NULL in maybe_add_creds, and the second
send after the socket was accepted had a non-NULL value for sk->socket
and thus we could tell the credentials were not needed so we did not
bother.

The unnecessary credentials on the first message cause
unix_stream_recvmsg to start verifying that all messages had the same
credentials before coallescing and then the coallescing failed because
the second message had no credentials.

Ignoring credentials when we don't care in unix_stream_recvmsg fixes a
long standing pessimization which would fail to coallesce messages when
reading from a unix stream socket if the senders were different even if
we did not care about their credentials.

I have tested this and verified that the in the LSB test case mentioned
above that the messages do coallesce now, while the were failing to
coallesce without this change.
Reported-by: Karel Srot <ksrot@redhat.com>
Reported-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This reverts commit 14134f65.

The problem that the above patch was meant to address is that af_unix
messages are not being coallesced because we are sending unnecesarry
credentials.  Not sending credentials in maybe_add_creds totally
breaks unconnected unix domain sockets that wish to send credentails
to other sockets.

In practice this break some versions of udev because they receive a
message and the sending uid is bogus so they drop the message.
Reported-by: Sven Joachim <svenjoac@gmx.de>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>