Impact: improve wakeup affinity on NUMA systems, tweak SMP systems

Given the fixes+tweaks to the wakeup-buddy code, re-tweak the domain
balancing defaults on NUMA and SMP systems.

Turn on SD_WAKE_AFFINE which was off on x86 NUMA - there's no reason
why we would not want to have wakeup affinity across nodes as well.
(we already do this in the standard NUMA template.)

lat_ctx on a NUMA box is particularly happy about this change:

before:

 |   phoenix:~/l> ./lat_ctx -s 0 2
 |   "size=0k ovr=2.60
 |   2 5.70

after:

 |   phoenix:~/l> ./lat_ctx -s 0 2
 |   "size=0k ovr=2.65
 |   2 2.07

a 2.75x speedup.

pipe-test is similarly happy about it too:

 |  phoenix:~/sched-tests> ./pipe-test
 |   18.26 usecs/loop.
 |   14.70 usecs/loop.
 |   14.38 usecs/loop.
 |   10.55 usecs/loop.              # +WAKE_AFFINE on domain0+domain1
 |   8.63 usecs/loop.
 |   8.59 usecs/loop.
 |   9.03 usecs/loop.
 |   8.94 usecs/loop.
 |   8.96 usecs/loop.
 |   8.63 usecs/loop.

Also:

 - disable SD_BALANCE_NEWIDLE on NUMA and SMP domains (keep it for siblings)
 - enable SD_WAKE_BALANCE on SMP domains

Sysbench+postgresql improves all around the board, quite significantly:

           .28-rc3-11474e2c  .28-rc3-11474e2c-tune
-------------------------------------------------
    1:             571              688    +17.08%
    2:            1236             1206    -2.55%
    4:            2381             2642    +9.89%
    8:            4958             5164    +3.99%
   16:            9580             9574    -0.07%
   32:            7128             8118    +12.20%
   64:            7342             8266    +11.18%
  128:            7342             8064    +8.95%
  256:            7519             7884    +4.62%
  512:            7350             7731    +4.93%
-------------------------------------------------
  SUM:           55412            59341    +6.62%

So it's a win both for the runup portion, the peak area and the tail.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: scheduling order fix for group scheduling

For each level in the hierarchy, set the buddy to point to the right entity.
Therefore, when we do the hierarchical schedule, we have a fair chance of
ending up where we meant to.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: improve/change/fix wakeup-buddy scheduling

Currently we only have a forward looking buddy, that is, we prefer to
schedule to the task we last woke up, under the presumption that its
going to consume the data we just produced, and therefore will have
cache hot benefits.

This allows co-waking producer/consumer task pairs to run ahead of the
pack for a little while, keeping their cache warm. Without this, we
would interleave all pairs, utterly trashing the cache.

This patch introduces a backward looking buddy, that is, suppose that
in the above scenario, the consumer preempts the producer before it
can go to sleep, we will therefore miss the wakeup from consumer to
producer (its already running, after all), breaking the cycle and
reverting to the cache-trashing interleaved schedule pattern.

The backward buddy will try to schedule back to the task that woke us
up in case the forward buddy is not available, under the assumption
that the last task will be the one with the most cache hot task around
barring current.

This will basically allow a task to continue after it got preempted.

In order to avoid starvation, we allow either buddy to get wakeup_gran
ahead of the pack.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix cross-class preemption

Inter-class wakeup preemptions should go on class order.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

Clean up task selection
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
  xfrm: Fix xfrm_policy_gc_lock handling.
  niu: Use pci_ioremap_bar().
  bnx2x: Version Update
  bnx2x: Calling netif_carrier_off at the end of the probe
  bnx2x: PCI configuration bug on big-endian
  bnx2x: Removing the PMF indication when unloading
  mv643xx_eth: fix SMI bus access timeouts
  net: kconfig cleanup
  fs_enet: fix polling
  XFRM: copy_to_user_kmaddress() reports local address twice
  SMC91x: Fix compilation on some platforms.
  udp: Fix the SNMP counter of UDP_MIB_INERRORS
  udp: Fix the SNMP counter of UDP_MIB_INDATAGRAMS
  drivers/net/smc911x.c: Fix lockdep warning on xmit.

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev:
  libata: mask off DET when restoring SControl for detach
  libata: implement ATA_HORKAGE_ATAPI_MOD16_DMA and apply it
  libata: Fix a potential race condition in ata_scsi_park_show()
  sata_nv: fix generic, nf2/3 detection regression
  sata_via: restore vt*_prepare_host error handling
  sata_promise: add ATA engine reset to reset ops

Signed-off-by: NJianjun Kong <jianjun@zeuux.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

libata restores SControl on detach; however, trying to restore
non-zero DET can cause undeterministic behavior including PMP device
going offline till power cycling.  Mask off DET when restoring
SControl.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

libata always uses PIO for ATAPI commands when the number of bytes to
transfer isn't multiple of 16 but quantum DAT72 chokes on odd bytes
PIO transfers.  Implement a horkage to skip the mod16 check and apply
it to the quantum device.

This is reported by John Clark in the following thread.

  http://thread.gmane.org/gmane.linux.ide/34748Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: John Clark <clarkjc@runbox.com>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

Peter Moulder has pointed out that there is a slight chance that a
negative value might be passed to jiffies_to_msecs() in
ata_scsi_park_show(). This is fixed by saving the value of jiffies in a
local variable, thus also reducing code since the volatile variable
jiffies is accessed only once.
Signed-off-by: NElias Oltmanns <eo@nebensachen.de>
Signed-off-by: Tejun Heo <tj.kernel.org>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

All three flavors of sata_nv's are different in how their hardreset
behaves.

* generic: Hardreset is not reliable.  Link often doesn't come online
  after hardreset.

* nf2/3: A little bit better - link comes online with longer debounce
  timing.  However, nf2/3 can't reliable wait for the first D2H
  Register FIS, so it can't wait for device readiness or classify the
  device after hardreset.  Follow-up SRST required.

* ck804: Hardreset finally works.

The core layer change to prefer hardreset and follow up changes
exposed the above issues and caused various detection regressions for
all three flavors.  This patch, hopefully, fixes all the known issues
and should make sata_nv error handling more reliable.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

commit b9d5b89b (sata_via: fix support
for 5287) accidently (?) removed vt*_prepare_host error handling - restore it

catched by gcc:
drivers/ata/sata_via.c: In function 'svia_init_one':
drivers/ata/sata_via.c:567: warning: 'host' may be used uninitialized in this function
Signed-off-by: NMarcin Slusarz <marcin.slusarz@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joseph Chan <JosephChan@via.com.tw>
Cc: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

Promise ATA engines need to be reset when errors occur.
That's currently done for errors detected by sata_promise itself,
but it's not done for errors like timeouts detected outside of
the low-level driver.

The effect of this omission is that a timeout tends to result
in a sequence of failed COMRESETs after which libata EH gives
up and disables the port. At that point the port's ATA engine
hangs and even reloading the driver will not resume it.

To fix this, make sata_promise override ->hardreset on SATA
ports with code which calls pdc_reset_port() on the port in
question before calling libata's hardreset. PATA ports don't
use ->hardreset, so for those we override ->softreset instead.
Signed-off-by: NMikael Pettersson <mikpe@it.uu.se>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

From: Alexey Dobriyan <adobriyan@gmail.com>

Based upon a lockdep trace by Simon Arlott.

xfrm_policy_kill() can be called from both BH and
non-BH contexts, so we have to grab xfrm_policy_gc_lock
with BH disabling.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Updating the version
Signed-off-by: NEilon Greenstein <eilong@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

netif_carrier_off was called too early at the probe. In case of failure
or simply bad timing, this can cause a fatal error since linkwatch_event
might run too soon.
Signed-off-by: NEilon Greenstein <eilong@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current code read nothing but zeros on big-endian (wrong part of the
32bits). This caused poor performance on big-endian machines. Though this
issue did not cause the system to crash, the performance is significantly
better with the fix so I view it as critical bug fix.
Signed-off-by: NEilon Greenstein <eilong@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the PMF flag is set, the driver can access the HW freely. When the
driver is unloaded, it should not access the HW. The problem caused fatal
errors when "ethtool -i" was called after the calling instance was unloaded
and another instance was already loaded
Signed-off-by: NEilon Greenstein <eilong@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The mv643xx_eth mii bus implementation uses wait_event_timeout() to
wait for SMI completion interrupts.

If wait_event_timeout() would return zero, mv643xx_eth would conclude
that the SMI access timed out, but this is not necessarily true --
wait_event_timeout() can also return zero in the case where the SMI
completion interrupt did happen in time but where it took longer than
the requested timeout for the process performing the SMI access to be
scheduled again.  This would lead to occasional SMI access timeouts
when the system would be under heavy load.

The fix is to ignore the return value of wait_event_timeout(), and
to re-check the SMI done bit after wait_event_timeout() returns to
determine whether or not the SMI access timed out.
Signed-off-by: NLennert Buytenhek <buytenh@marvell.com>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

The bool kconfig option added to ixgbe and myri10ge for DCA is ambigous,
so this patch adds a description to the kconfig option.
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

1. compile fix for irqreturn_t type change
2. restore ->poll_controller after CONFIG_PPC_CPM_NEW_BINDING transition
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>

* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6:
  cifs: fix renaming one hardlink on top of another
  [CIFS] fix error in smb_send2
  [CIFS] Reduce number of socket retries in large write path

cifs: fix renaming one hardlink on top of another

POSIX says that renaming one hardlink on top of another to the same
inode is a no-op. We had the logic mostly right, but forgot to clear
the return code.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NSteve French <sfrench@us.ibm.com>

Merge branch 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  tracing, ring-buffer: add paranoid checks for loops
  ftrace: use kretprobe trampoline name to test in output
  tracing, alpha: undefined reference to `save_stack_trace'

Merge branch 'io-mappings-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'io-mappings-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  io mapping: clean up #ifdefs
  io mapping: improve documentation
  i915: use io-mapping interfaces instead of a variety of mapping kludges
  resources: add io-mapping functions to dynamically map large device apertures
  x86: add iomap_atomic*()/iounmap_atomic() on 32-bit using fixmaps

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:
  ALSA: hda: make a STAC_DELL_EQ option
  ALSA: emu10k1 - Add more invert_shared_spdif flag to Audigy models
  ALSA: hda - Add a quirk for another Acer Aspire (1025:0090)
  ALSA: remove direct access of dev->bus_id in sound/isa/*
  sound: struct device - replace bus_id with dev_name(), dev_set_name()
  ALSA: Fix PIT lockup on some chipsets when using the PC-Speaker
  ALSA: rawmidi - Add open check in rawmidi callbacks
  ALSA: hda - Add digital-mic for ALC269 auto-probe mode
  ALSA: hda - Disable broken mic auto-muting in Realtek codes

* 'proc-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/adobriyan/proc:
  proc: revert /proc/uptime to ->read_proc hook

* 'drm-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  i915: Add GEM ioctl to get available aperture size.
  drm/radeon: fixup further bus mastering confusion.
  build fix: CONFIG_DRM_I915=y && CONFIG_ACPI=n

Impact: cleanup

clean up ifdefs: change #ifdef CONFIG_X86_32/64 to
CONFIG_HAVE_ATOMIC_IOMAP.

flip around the #ifdef sections to clean up the structure.
Signed-off-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add documentation
Signed-off-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Add support for explicitly enabling the EQ distortion hack for
systems without software biquad support.
Signed-off-by: NMatthew Ranostay <mranostay@embeddedalley.com>
Cc: stable@kernel.org
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

While writing a new tracer, I had a bug where I caused the ring-buffer
to recurse in a bad way. The bug was with the tracer I was writing
and not the ring-buffer itself. But it took a long time to find the
problem.

This patch adds paranoid checks into the ring-buffer infrastructure
that will catch bugs of this nature.

Note: I put the bug back in the tracer and this patch showed the error
      nicely and prevented the lockup.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: ia64+tracing build fix

When a function is kprobed, the return address is set to the
kprobe_trampoline, or something similar. This caused the output
of the trace to look confusing when the parent seemed to be this
"kprobe_trampoline" function.

To fix this, Abhishek Sagar added a test of the instruction pointer
of the parent to see if it matched the kprobe_trampoline. If it
did, the output would print a "[unknown/kretprobe'd]" instead.

Unfortunately, not all archs do this the same way, and the trampoline
function may not be exported, which causes failures in builds.

This patch will compare the name instead of the pointer to see
if it matches. This prevents us from depending on a function from
being exported, and should work on all archs. The worst that can
happen is that an arch might use a different name and then we
go back to the confusing output. At least the arch will still build.
Reported-by: NAbhishek Sagar <sagar.abhishek@gmail.com>
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Tested-by: NAbhishek Sagar <sagar.abhishek@gmail.com>
Acked-by: NAbhishek Sagar <sagar.abhishek@gmail.com>

While adding support for MIGRATE/KMADDRESS in strongSwan (as specified
in draft-ebalard-mext-pfkey-enhanced-migrate-00), Andreas Steffen
noticed that XFRMA_KMADDRESS attribute passed to userland contains the
local address twice (remote provides local address instead of remote
one).

This bug in copy_to_user_kmaddress() affects only key managers that use
native XFRM interface (key managers that use PF_KEY are not affected).

For the record, the bug was in the initial changeset I posted which
added support for KMADDRESS (13c1d189
'xfrm: MIGRATE enhancements (draft-ebalard-mext-pfkey-enhanced-migrate)').
Signed-off-by: NArnaud Ebalard <arno@natisbad.org>
Reported-by: NAndreas Steffen <andreas.steffen@strongswan.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reported in Novell bnc#440862:
    https://bugzilla.novell.com/show_bug.cgi?id=440862Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Impact: build fix on !stacktrace architectures

only select STACKTRACE on architectures that have STACKTRACE_SUPPORT

... since we also need to ifdef out the guts of ftrace_trace_stack().
We also want to disallow setting TRACE_ITER_STACKTRACE in trace_flags
on such configs, but that can wait.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Acked-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Added a quirk for another Acer Aspier laptop (1025:0090) with ALC883
codec.  Reported in Novell bnc#426935:
    https://bugzilla.novell.com/show_bug.cgi?id=426935Signed-off-by: NTakashi Iwai <tiwai@suse.de>