I blame Mikey for this. He elevated my slightly dubious testcase:

to benchmark status. And naturally we need to be number 1 at creating
zeros. So lets improve __clear_user some more.

As Paul suggests we can use dcbz for large lengths. This patch gets
the destination cacheline aligned then uses dcbz on whole cachelines.

Before:
10485760000 bytes (10 GB) copied, 0.414744 s, 25.3 GB/s

After:
10485760000 bytes (10 GB) copied, 0.268597 s, 39.0 GB/s

39 GB/s, a new record.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NOlof Johansson <olof@lixom.net>
Acked-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

At the moment all queues in a multiqueue adapter will serialise
against the IOMMU table lock. This is proving to be a big issue,
especially with 10Gbit ethernet.

This patch creates 4 pools and tries to spread the load across
them. If the table is under 1GB in size we revert back to the
original behaviour of 1 pool and 1 largealloc pool.

We create a hash to map CPUs to pools. Since we prefer interrupts to
be affinitised to primary CPUs, without some form of hashing we are
very likely to end up using the same pool. As an example, POWER7
has 4 way SMT and with 4 pools all primary threads will map to the
same pool.

The largealloc pool is reduced from 1/2 to 1/4 of the space to
partially offset the overhead of breaking the table up into pools.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 69% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

In preparation for IOMMU pools, push the spinlock into
iommu_range_alloc and __iommu_free.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch moves tce_free outside of the lock in iommu_free.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 25% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We currently hold the IOMMU spinlock around tce_build and tce_flush.
This causes our spinlock hold times to be much higher than required
and can impact multiqueue adapters.

This patch moves tce_build and tce_flush outside of the lock in
iommu_alloc, and tce_flush outside of the lock in iommu_free.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 32% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

tce_buildmulti_pSeriesLP uses a per cpu page to communicate with the
hypervisor. We currently rely on the IOMMU table spinlock but
subsequent patches will be removing that so disable interrupts
around all accesses of tce_page.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Implement a POWER7 optimised memcpy using VMX and enhanced prefetch
instructions.

This is a copy of the POWER7 optimised copy_to_user/copy_from_user
loop. Detailed implementation and performance details can be found in
commit a66086b8 (powerpc: POWER7 optimised
copy_to_user/copy_from_user using VMX).

I noticed memcpy issues when profiling a RAID6 workload:

	.memcpy
	.async_memcpy
	.async_copy_data
	.__raid_run_ops
	.handle_stripe
	.raid5d
	.md_thread

I created a simplified testcase by building a RAID6 array with 4 1GB
ramdisks (booting with brd.rd_size=1048576):

# mdadm -CR -e 1.2 /dev/md0 --level=6 -n4 /dev/ram[0-3]

I then timed how long it took to write to the entire array:

# dd if=/dev/zero of=/dev/md0 bs=1M

Before: 892 MB/s
After:  999 MB/s

A 12% improvement.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Version 2.06 of the POWER ISA introduced enhanced touch instructions,
allowing us to specify a number of attributes including the length of
a stream.

This patch adds a software stream for both loads and stores in the
POWER7 copy_tofrom_user loop. Since the setup is quite complicated
and we have to use an eieio to ensure correct ordering of the "GO"
command we only do this for copies above 4kB.

To quantify any performance improvements we need a working set
bigger than the caches so we operate on a 1GB file:

# dd if=/dev/zero of=/tmp/foo bs=1M count=1024

And we compare how fast we can read the file:

# dd if=/tmp/foo of=/dev/null bs=1M

before: 7.7 GB/s
after:  9.6 GB/s

A 25% improvement.

The worst case for this patch will be a completely L1 cache contained
copy of just over 4kB. We can test this with the copy_to_user
testcase we used to tune copy_tofrom_user originally:

http://ozlabs.org/~anton/junkcode/copy_to_user.c

# time ./copy_to_user2 -l 4224 -i 10000000

before: 6.807 s
after:  6.946 s

A 2% slowdown, which seems reasonable considering our data is unlikely
to be completely L1 contained.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

While creating the PCI root bus through function pci_create_root_bus()
of PCI core, it should have assigned the secondary bus number for the
newly created PCI root bus. Thus we needn't do the explicit assignment
for the secondary bus number again in pcibios_scan_phb().
Signed-off-by: NGavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The form affinity for NUMA is set to 1 if the firmware supports
OPAL. Otherwise, we have to retrieve that from OF node "/chosen".
For the latter case, OF node "/chosen" reference count was never
decreased.
Signed-off-by: NGavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Implement a POWER7 optimised copy_page using VMX and enhanced
prefetch instructions. We use enhanced prefetch hints to prefetch
both the load and store side. We copy a cacheline at a time and
fall back to regular loads and stores if we are unable to use VMX
(eg we are in an interrupt).

The following microbenchmark was used to assess the impact of
the patch:

http://ozlabs.org/~anton/junkcode/page_fault_file.c

We test MAP_PRIVATE page faults across a 1GB file, 100 times:

# time ./page_fault_file -p -l 1G -i 100

Before: 22.25s
After:  18.89s

17% faster
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Subsequent patches will add more VMX library functions and it makes
sense to keep all the c-code helper functions in the one file.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

mtmsrd is an expensive instruction, we save a few cycles by
doing it once instead of twice.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Version 2.06 of the POWER ISA introduced enhanced touch instructions,
allowing us to specify a number of attributes including the length of
a stream.

This patch adds a software stream for both loads and stores in the
POWER7 copy_tofrom_user loop. Since the setup is quite complicated
and we have to use an eieio to ensure correct ordering of the "GO"
command we only do this for copies above 4kB.

To quantify any performance improvements we need a working set
bigger than the caches so we operate on a 1GB file:

# dd if=/dev/zero of=/tmp/foo bs=1M count=1024

And we compare how fast we can read the file:

# dd if=/tmp/foo of=/dev/null bs=1M

before: 7.7 GB/s
after:  9.6 GB/s

A 25% improvement.

The worst case for this patch will be a completely L1 cache contained
copy of just over 4kB. We can test this with the copy_to_user
testcase we used to tune copy_tofrom_user originally:

http://ozlabs.org/~anton/junkcode/copy_to_user.c

# time ./copy_to_user2 -l 4224 -i 10000000

before: 6.807 s
after:  6.946 s

A 2% slowdown, which seems reasonable considering our data is unlikely
to be completely L1 contained.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

1) call_function.lock used in smp_call_function_many() is just to protect
   call_function.queue and &data->refs, cpu_online_mask is outside of the
   lock. And it's not necessary to protect cpu_online_mask,
   because data->cpumask is pre-calculate and even if a cpu is brougt up
   when calling arch_send_call_function_ipi_mask(), it's harmless because
   validation test in generic_smp_call_function_interrupt() will take care
   of it.

2) For cpu down issue, stop_machine() will guarantee that no concurrent
   smp_call_fuction() is processing.
Signed-off-by: NYong Zhang <yong.zhang0@gmail.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

I noticed __clear_user high up in a profile of one of my RAID stress
tests. The testcase was doing a dd from /dev/zero which ends up
calling __clear_user.

__clear_user is basically a loop with a single 4 byte store which
is horribly slow. We can do much better by aligning the desination
and doing 32 bytes of 8 byte stores in a loop.

The following testcase was used to verify the patch:

http://ozlabs.org/~anton/junkcode/stress_clear_user.c

To show the improvement in performance I ran a dd from /dev/zero
to /dev/null on a POWER7 box:

Before:

# dd if=/dev/zero of=/dev/null bs=1M count=10000
10485760000 bytes (10 GB) copied, 3.72379 s, 2.8 GB/s

After:

# time dd if=/dev/zero of=/dev/null bs=1M count=10000
10485760000 bytes (10 GB) copied, 0.728318 s, 14.4 GB/s

Over 5x faster.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

irq_entry, irq_exit, timer_interrupt_entry and timer_interrupt_exit
all do the same thing so use DECLARE_EVENT_CLASS to avoid duplicating
everything 4 times.

This saves quite a lot of space in both instruction text and data:

   text    data     bss     dec     hex filename
   9265   19622      16   28903    70e7 arch/powerpc/kernel/irq.o
   6817   19019      16   25852    64fc arch/powerpc/kernel/irq.o
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

When looking through some instruction traces I noticed our tracepoint
checks were inline. It turns out we don't have CONFIG_JUMP_LABEL
enabled.

By enabling CONFIG_JUMP_LABEL we replace a load/compare/branch with
a nop at every tracepoint call. For example in do_IRQ:

CONFIG_JUMP_LABEL disabled:
        stdx 3,11,9
        lwz 0,8(29)
        cmpwi 7,0,0
        bne- 7,.L124
        bl .irq_enter

CONFIG_JUMP_LABEL enabled:
        stdx 3,11,9
        nop
        bl .irq_enter
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The following patch is to remove the pseries_notify_add_cpu() call
and replace it by a hot plug notifier.

This would prevent cpuidle resources being released and allocated each
time cpu comes online on pseries.

The earlier design was causing a lockdep problem
in start_secondary as reported on this thread
	-https://lkml.org/lkml/2012/5/17/2

This applies on 3.4-rc7
Signed-off-by: NDeepthi Dharwar <deepthi@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

An upcoming release of firmware will add DDW extensions, in particular
an API to "reset" the DMA window to the original configuration (32-bit,
2GB in size). With that API available, we can safely remove the default
window, increasing the resources available to firmware for creation of
larger windows for the slot in question -- if we encounter an error, we
can use the new API to reset the state of the slot.

Further, this same release of firmware will make it a hard requirement
for OSes to release the existing window before any other windows will be
shown as available, to avoid conflicts in addressing between the two
windows.

In anticipation of these changes, always remove the default window
before we do any DDW manipulations.
Signed-off-by: NNishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The patch_instruction() interface is made to modify kernel text. It is
safer to use that then the probe_kernel_write() when modifying kernel
code.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

For ftrace to use the patch_instruction code, it needs to check for
faults on write. Ftrace updates code all over the kernel, and we need to
know if code is updated or not due to protections that are placed on
some portions of the kernel. If ftrace does not detect a fault, it will
error later on, and it will be much more difficult to find the problem.

By changing patch_instruction() to detect faults, then ftrace will be
able to make use of it too.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

PowerPC does not have the synchronization issues that x86 has with
modifying code on one CPU while another CPU is executing it.
The other CPU will either see the old or new code without any
issues, unlike x86 which may issue a GPF.

Instead of calling the heavy stop_machine, just update the code.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Currently we build all board files regardless of the final zImage
target.  This is sub-optimal (in terms on compilation) and leads to
problems in one platform needlessly causing failures for other
platforms.

Use the Kconfig variables to selectively construct this board files to
build.
Signed-off-by: NTony Breeds <tony@bakeyournoodle.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Pull two ARM fixes from Russell King:
 "It's been fairly quiet with the fixes.  Just two this time.  One fixes
  a long standing problem with KALLSYMS needing an additional pass, and
  the other sorts a problem with the vmalloc space interacting with
  static IO mappings."

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7438/1: fill possible PMD empty section gaps
  ARM: 7428/1: Prevent KALLSYM size mismatch on ARM.

On ARM with the 2-level page table format, a PMD entry is represented by
two consecutive section entries covering 2MB of virtual space.

However, static mappings always were allowed to use separate 1MB section
entries.  This means in practice that a static mapping may create half
populated PMDs via create_mapping().

Since commit 0536bdf3 (ARM: move iotable mappings within the vmalloc
region) those static mappings are located in the vmalloc area. We must
ensure no such half populated PMDs are accessible once vmalloc() or
ioremap() start looking at the vmalloc area for nearby free virtual
address ranges, or various things leading to a kernel crash will happen.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Reported-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: N"R, Sricharan" <r.sricharan@ti.com>
Reviewed-by: NCatalin Marinas <catalin.marinas@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Pull ARM SoC fixes from Olof Johansson:
 "Another week, another batch of fixes.

  All are small, contained, targeted fixes for explicit problems --
  mostly build and boot failures across i.MX, OMAP, Renesas/Shmobile and
  Samsung."

* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
  ARM: imx6q: fix suspend regression caused by common clk migration
  ARM: OMAP4470: Fix OMAP4470 boot failure
  ARM: EXYNOS: Fix EXYNOS_DEV_DMA Kconfig entry
  ARM: OMAP2+: nand: fix build error when CONFIG_MTD_ONENAND_OMAP2=n
  ARM: shmobile: r8a7779: Route all interrupts to ARM
  ARM: shmobile: kzm9d: use late init machine hook
  ARM: shmobile: kzm9g: use late init machine hook
  ARM: mach-shmobile: armadillo800eva: Use late init machine hook
  ARM: SAMSUNG: Fix for S3C2412 EBI memory mapping
  ARM: mach-shmobile: add missing GPIO IRQ configuration on mackerel
  ARM: mach-shmobile: Fix build when SMP is enabled and EMEV2 is not enabled
  ARM: shmobile: sh7372: bugfix: chclr_offset base
  ARM: shmobile: sh73a0: bugfix: SY-DMAC number
  ARM: SAMSUNG: Should check for IS_ERR(clk) instead of NULL

Fix kernel-doc warnings in printk.c: use correct parameter name.

  Warning(kernel/printk.c:2429): No description found for parameter 'buf'
  Warning(kernel/printk.c:2429): Excess function parameter 'line' description in 'kmsg_dump_get_buffer'
Signed-off-by: NRandy Dunlap <rdunlap@xenotime.net>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix kernel-doc warning.  This struct member was removed in commit
87568264 ("irq: Remove irq_chip->release()") so remove its
associated kernel-doc entry also.

  Warning(include/linux/irq.h:338): Excess struct/union/enum/typedef member 'release' description in 'irq_chip'
Signed-off-by: NRandy Dunlap <rdunlap@xenotime.net>
Cc: Richard Weinberger <richard@nod.at>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Merge branch 'v3.5-samsung-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung into fixes

* 'v3.5-samsung-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung:
  ARM: EXYNOS: Fix EXYNOS_DEV_DMA Kconfig entry
  ARM: SAMSUNG: Fix for S3C2412 EBI memory mapping
  ARM: SAMSUNG: Should check for IS_ERR(clk) instead of NULL

When moving to common clk framework, the imx6q clks rom and mmdc_ch1_axi
get different on/off states than old clk driver, which breaks suspend
function.  There might be a better way to manage these clocks, but let's
takes the old clk driver approach to fix the regression first.
Signed-off-by: NShawn Guo <shawn.guo@linaro.org>
Signed-off-by: NOlof Johansson <olof@lixom.net>

Merge tag 'omap-fixes-for-v3.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes

From Tony Lindgren:
"Here's one more regression fix that I missed earlier, and a
 trivial fix to get omap4470 booting."

* tag 'omap-fixes-for-v3.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
  ARM: OMAP4470: Fix OMAP4470 boot failure
  ARM: OMAP2+: nand: fix build error when CONFIG_MTD_ONENAND_OMAP2=n

Pull ACPI & Power Management patches from Len Brown.

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
  acpi_pad: fix power_saving thread deadlock
  ACPI video: Still use ACPI backlight control if _DOS doesn't exist
  ACPI, APEI, Avoid too much error reporting in runtime
  ACPI: Add a quirk for "AMILO PRO V2030" to ignore the timer overriding
  ACPI: Remove one board specific WARN when ignoring timer overriding
  ACPI: Make acpi_skip_timer_override cover all source_irq==0 cases
  ACPI, x86: fix Dell M6600 ACPI reboot regression via DMI
  ACPI sysfs.c strlen fix

Pull driver Core fixes from Greg Kroah-Hartman:
 "Here is a number of printk() fixes, specifically a few reported by the
  crazy blog program that ships in SUSE releases (that's "boot log" and
  not "web log", it predates the general "blog" terminology by many
  years), and the restoration of the continuation line functionality
  reported by Stephen and others.  Yes, the changes seem a bit big this
  late in the cycle, but I've been beating on them for a while now, and
  Stephen has even optimized it a bit, so all looks good to me.

  The other change in here is a Documentation update for the stable
  kernel rules describing how some distro patches should be backported,
  to hopefully drive a bit more response from the distros to the stable
  kernel releases.

  Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>"

* tag 'driver-core-3.5-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  printk: Optimize if statement logic where newline exists
  printk: flush continuation lines immediately to console
  syslog: fill buffer with more than a single message for SYSLOG_ACTION_READ
  Revert "printk: return -EINVAL if the message len is bigger than the buf size"
  printk: fix regression in SYSLOG_ACTION_CLEAR
  stable: Allow merging of backports for serious user-visible performance issues

Merge branches 'acpi_pad-bugzilla-42981', 'apei-bugzilla-43282', 'video-bugzilla-43168', 'bugzilla-40002' and 'bugfix-misc' into release

bug fixes

The acpi_pad driver can get stuck in destroy_power_saving_task()
waiting for kthread_stop() to stop a power_saving thread.  The problem
is that the isolated_cpus_lock mutex is owned when
destroy_power_saving_task() calls kthread_stop(), which waits for a
power_saving thread to end, and the power_saving thread tries to
acquire the isolated_cpus_lock when it calls round_robin_cpu().  This
patch fixes the issue by making round_robin_cpu() use its own mutex.

https://bugzilla.kernel.org/show_bug.cgi?id=42981

Cc: stable@vger.kernel.org
Signed-off-by: NStuart Hayes <Stuart_Hayes@Dell.com>
Signed-off-by: NLen Brown <len.brown@intel.com>

This fixes a regression in 3.4-rc1 caused by commit
ea9f8856
(ACPI video: Harden video bus adding.)

Some platforms don't have _DOS control method, but the ACPI
backlight still works.
We should not invoke _DOS for these platforms.

https://bugzilla.kernel.org/show_bug.cgi?id=43168

Cc: Igor Murzov <intergalactic.anonymous@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: NZhang Rui <rui.zhang@intel.com>
Signed-off-by: NLen Brown <len.brown@intel.com>

Pull power management fixes from Rafael J. Wysocki:

 * Fix for a bug in async suspend error code path causing parents to
   wait forever for their children in case of a suspend error from
   Mandeep Singh Baines (-stable metarial).

 * Fix for a suspend regression related to earlier changes in the ACPI
   cpuidle driver from Deepthi Dharwar.

* tag 'pm-for-3.5-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM / ACPI: Fix suspend/resume regression caused by cpuidle cleanup.
  PM / Sleep: Prevent waiting forever on asynchronous suspend after abort

In reviewing Kay's fix up patch: "printk: Have printk() never buffer its
data", I found two if statements that could be combined and optimized.

Put together the two 'cont.len && cont.owner == current' if statements
into a single one, and check if we need to call cont_add(). This also
removes the unneeded double cont_flush() calls.

Link: http://lkml.kernel.org/r/1340869133.876.10.camel@mopSigned-off-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>