Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 22 6月, 2017 1 次提交
  3. 26 5月, 2017 1 次提交
  5. 23 5月, 2017 1 次提交
    • K
      perf/x86: Add sysfs entry to freeze counters on SMI · 6089327f
      由 Kan Liang 提交于 
      Currently, the SMIs are visible to all performance counters, because
many users want to measure everything including SMIs. But in some
cases, the SMI cycles should not be counted - for example, to calculate
the cost of an SMI itself. So a knob is needed.

When setting FREEZE_WHILE_SMM bit in IA32_DEBUGCTL, all performance
counters will be effected. There is no way to do per-counter freeze
on SMI. So it should not use the per-event interface (e.g. ioctl or
event attribute) to set FREEZE_WHILE_SMM bit.

Adds sysfs entry /sys/device/cpu/freeze_on_smi to set FREEZE_WHILE_SMM
bit in IA32_DEBUGCTL. When set, freezes perfmon and trace messages
while in SMM.

Value has to be 0 or 1. It will be applied to all processors.

Also serialize the entire setting so we don't get multiple concurrent
threads trying to update to different values.
Signed-off-by: NKan Liang <Kan.liang@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: bp@alien8.de
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1494600673-244667-1-git-send-email-kan.liang@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      6089327f
  7. 14 4月, 2017 1 次提交
    • K
      perf/x86: Fix spurious NMI with PEBS Load Latency event · fd583ad1
      由 Kan Liang 提交于 
      Spurious NMIs will be observed with the following command:

  while :; do
    perf record -bae "cpu/umask=0x01,event=0xcd,ldlat=0x80/pp"
                  -e "cpu/umask=0x03,event=0x0/"
                  -e "cpu/umask=0x02,event=0x0/"
                  -e cycles,branches,cache-misses
                  -e cache-references -- sleep 10
  done

The bug was introduced by commit:

  8077eca0 ("perf/x86/pebs: Add workaround for broken OVFL status on HSW+")

That commit clears the status bits for the counters used for PEBS
events, by masking the whole 64 bits pebs_enabled. However, only the
low 32 bits of both status and pebs_enabled are reserved for PEBS-able
counters.

For status bits 32-34 are fixed counter overflow bits. For
pebs_enabled bits 32-34 are for PEBS Load Latency.

In the test case, the PEBS Load Latency event and fixed counter event
could overflow at the same time. The fixed counter overflow bit will
be cleared by mistake. Once it is cleared, the fixed counter overflow
never be processed, which finally trigger spurious NMI.

Correct the PEBS enabled mask by ignoring the non-PEBS bits.
Signed-off-by: NKan Liang <kan.liang@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: 8077eca0 ("perf/x86/pebs: Add workaround for broken OVFL status on HSW+")
Link: http://lkml.kernel.org/r/1491333246-3965-1-git-send-email-kan.liang@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      fd583ad1
  9. 16 3月, 2017 1 次提交
  11. 17 1月, 2017 1 次提交
    • Z
      perf/x86/intel: Handle exclusive threadid correctly on CPU hotplug · 4e71de79
      由 Zhou Chengming 提交于 
      The CPU hotplug function intel_pmu_cpu_starting() sets
cpu_hw_events.excl_thread_id unconditionally to 1 when the shared exclusive
counters data structure is already availabe for the sibling thread.

This works during the boot process because the first sibling gets threadid
0 assigned and the second sibling which shares the data structure gets 1.

But when the first thread of the core is offlined and onlined again it
shares the data structure with the second thread and gets exclusive thread
id 1 assigned as well.

Prevent this by checking the threadid of the already online thread.

[ tglx: Rewrote changelog ]
Signed-off-by: NZhou Chengming <zhouchengming1@huawei.com>
Cc: NuoHan Qiao <qiaonuohan@huawei.com>
Cc: ak@linux.intel.com
Cc: peterz@infradead.org
Cc: kan.liang@intel.com
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: qiaonuohan@huawei.com
Cc: davidcc@google.com
Cc: guohanjun@huawei.com
Link: http://lkml.kernel.org/r/1484536871-3131-1-git-send-email-zhouchengming1@huawei.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>
---					---
 arch/x86/events/intel/core.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
      4e71de79
  13. 11 1月, 2017 1 次提交
  15. 23 12月, 2016 1 次提交
    • S
      perf/x86/pebs: Fix handling of PEBS buffer overflows · daa864b8
      由 Stephane Eranian 提交于 
      This patch solves a race condition between PEBS and the PMU handler.

In case multiple PEBS events are sampled at the same time,
it is possible to have GLOBAL_STATUS bit 62 set indicating
PEBS buffer overflow and also seeing at most 3 PEBS counters
having their bits set in the status register. This is a sign
that there was at least one PEBS record pending at the time
of the PMU interrupt. PEBS counters must only be processed
via the drain_pebs() calls, and not via the regular sample
processing loop coming after that the function, otherwise
phony regular samples may be generated in the sampling buffer
not marked with the EXACT tag.

Another possibility is to have one PEBS event and at least
one non-PEBS event whic hoverflows while PEBS has armed. In this
case, bit 62 of GLOBAL_STATUS will not be set, yet the overflow
status bit for the PEBS counter will be on Skylake.

To avoid this problem, we systematically ignore the PEBS-enabled
counters from the GLOBAL_STATUS mask and we always process PEBS
events via drain_pebs().

The problem manifested itself by having non-exact samples when
sampling only PEBS events, i.e., the PERF_SAMPLE_RECORD would
not have the EXACT flag set.

Note that this problem is only present on Skylake processor.
This fix is harmless on older processors.
Reported-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1482395366-8992-1-git-send-email-eranian@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      daa864b8
  17. 06 12月, 2016 1 次提交
    • P
      perf/x86: Fix full width counter, counter overflow · 7f612a7f
      由 Peter Zijlstra (Intel) 提交于 
      Lukasz reported that perf stat counters overflow handling is broken on KNL/SLM.

Both these parts have full_width_write set, and that does indeed have
a problem. In order to deal with counter wrap, we must sample the
counter at at least half the counter period (see also the sampling
theorem) such that we can unambiguously reconstruct the count.

However commit:

  069e0c3c ("perf/x86/intel: Support full width counting")

sets the sampling interval to the full period, not half.

Fixing that exposes another issue, in that we must not sign extend the
delta value when we shift it right; the counter cannot have
decremented after all.

With both these issues fixed, counter overflow functions correctly
again.
Reported-by: NLukasz Odzioba <lukasz.odzioba@intel.com>
Tested-by: NLiang, Kan <kan.liang@intel.com>
Tested-by: NOdzioba, Lukasz <lukasz.odzioba@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: stable@vger.kernel.org
Fixes: 069e0c3c ("perf/x86/intel: Support full width counting")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      7f612a7f
  19. 28 10月, 2016 1 次提交
    • I
      perf/x86/intel: Honour the CPUID for number of fixed counters in hypervisors · f92b7604
      由 Imre Palik 提交于 
      perf doesn't seem to honour the number of fixed counters specified by CPUID
leaf 0xa. It always assumes that Intel CPUs have at least 3 fixed counters.

So if some of the fixed counters are masked out by the hypervisor, it still
tries to check/set them.

This patch makes perf behave nicer when the kernel is running under a
hypervisor that doesn't expose all the counters.

This patch contains some ideas from Matt Wilson.
Signed-off-by: NImre Palik <imrep@amazon.de>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NAndi Kleen <ak@linux.intel.com>
Cc: Alexander Kozyrev <alexander.kozyrev@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Artyom Kuanbekov <artyom.kuanbekov@intel.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Wilson <msw@amazon.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1477037939-15605-1-git-send-email-imrep.amz@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      f92b7604
  21. 17 10月, 2016 1 次提交
  23. 15 9月, 2016 1 次提交
  25. 10 8月, 2016 1 次提交
    • P
      perf/x86: Ensure perf_sched_cb_{inc,dec}() is only called from pmu::{add,del}() · 68f7082f
      由 Peter Zijlstra 提交于 
      Currently perf_sched_cb_{inc,dec}() are called from
pmu::{start,stop}(), which has the problem that this can happen from
NMI context, this is making it hard to optimize perf_pmu_sched_task().

Furthermore, we really only need this accounting on pmu::{add,del}(),
so doing it from pmu::{start,stop}() is doing more work than we really
need.

Introduce x86_pmu::{add,del}() and wire up the LBR and PEBS.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      68f7082f
  27. 14 7月, 2016 1 次提交
  29. 03 7月, 2016 1 次提交
    • S
      perf/x86/intel: Update event constraints when HT is off · 9010ae4a
      由 Stephane Eranian 提交于 
      This patch updates the event constraints for non-PEBS mode for
Intel Broadwell and Skylake processors. When HT is off, each
CPU gets 8 generic counters. However, not all events can be
programmed on any of the 8 counters.  This patch adds the
constraints for the MEM_* events which can only be measured on the
bottom 4 counters. The constraints are also valid when HT is off
because, then, there are only 4 generic counters and they are the
bottom counters.
Signed-off-by: NStephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: kan.liang@intel.com
Link: http://lkml.kernel.org/r/1467411742-13245-1-git-send-email-eranian@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      9010ae4a
  31. 27 6月, 2016 2 次提交
    • D
      perf/x86/intel: Fix MSR_LAST_BRANCH_FROM_x bug when no TSX · 19fc9ddd
      由 David Carrillo-Cisneros 提交于 
      Intel's SDM states that bits 61:62 in MSR_LAST_BRANCH_FROM_x are the
TSX flags for formats with LBR_TSX flags (i.e. LBR_FORMAT_EIP_EFLAGS2).

However, when the CPU has TSX support deactivated, bits 61:62 actually
behave as follows:

  - For wrmsr(), bits 61:62 are considered part of the sign extension.
  - When capturing branches, the LBR hw will always clear bits 61:62.
    regardless of the sign extension.

Therefore, if:

  1) LBR has TSX format.
  2) CPU has no TSX support enabled.

... then any value passed to wrmsr() must be sign extended to 63 bits
and any value from rdmsr() must be converted to have a sign extension
of 61 bits, ignoring the values at TSX flags.

This bug was masked by the work-around to the Intel's CPU bug:
BJ94. "LBR May Contain Incorrect Information When Using FREEZE_LBRS_ON_PMI"
in Document Number: 324643-037US.

The aforementioned work-around uses hw flags to filter out all kernel
branches, limiting LBR callstack to user level execution only.

Since user addresses are not sign extended, they do not trigger the wrmsr()
bug in MSR_LAST_BRANCH_FROM_x when saved/restored at context switch.

To verify the hw bug:

  $ perf record -b -e cycles sleep 1
  $ rdmsr -p 0 0x680
  0x1fffffffb0b9b0cc
  $ wrmsr -p 0 0x680 0x1fffffffb0b9b0cc
  write(): Input/output error

The quirk for LBR_FROM_ MSRs is required before calls to wrmsrl() and
after rdmsrl().

This patch introduces it for wrmsrl()'s done for testing LBR support.

Future patch in series adds the quirk for context switch, that would
be required if LBR callstack is to be enabled for ring 0.
Signed-off-by: NDavid Carrillo-Cisneros <davidcc@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NStephane Eranian <eranian@google.com>
Reviewed-by: NAndi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1466533874-52003-3-git-send-email-davidcc@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      19fc9ddd
    • D
      perf/x86/intel: Print LBR support statement after validation · f09509b9
      由 David Carrillo-Cisneros 提交于 
      The following commit:

  338b522c ("perf/x86/intel: Protect LBR and extra_regs against KVM lying")

added an additional test to LBR support detection that is performed after
printing the LBR support statement to dmesg.

Move the LBR support output after the very last test, to make sure we
print the true status of LBR support.
Signed-off-by: NDavid Carrillo-Cisneros <davidcc@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NStephane Eranian <eranian@google.com>
Reviewed-by: NAndi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1466533874-52003-2-git-send-email-davidcc@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      f09509b9
  33. 08 6月, 2016 1 次提交
    • D
      perf/x86/intel: Use Intel family macros for core perf events · ef5f9f47
      由 Dave Hansen 提交于 
      Use the new model number macros instead of spelling things out
in the comments.

Note that this is missing a Nehalem model that is mentioned in
intel_idle which is fixed up in a later patch.

The resulting binary (arch/x86/events/intel/core.o) is exactly
the same with and without this patch modulo some harmless changes
to restoring %esi in the return path of functions, even those
untouched by this patch.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: jacob.jun.pan@intel.com
Link: http://lkml.kernel.org/r/20160603001929.C5F1C079@viggo.jf.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      ef5f9f47
  35. 03 6月, 2016 5 次提交
    • A
      perf/x86/intel: Use new topology_max_smt_threads() in HT leak workaround · 030ba6cd
      由 Andi Kleen 提交于 
      Now that we have topology_max_smt_threads() use it
to detect the HT workarounds for older CPUs.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1463703002-19686-6-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      030ba6cd
    • A
      perf/x86/intel: Add topdown events to Intel Atom · eb12b8ec
      由 Andi Kleen 提交于 
      Add topdown event declarations to Silvermont / Airmont.
These cores do not support the full Top Down metrics, but an useful
subset (FrontendBound, Retiring, Backend Bound/Bad Speculation).

The perf stat tool automatically handles the missing events
and combines the available metrics.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1463703002-19686-5-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      eb12b8ec
    • A
      perf/x86/intel: Add topdown events to Intel Core · a39fcae7
      由 Andi Kleen 提交于 
      Add declarations for the events needed for topdown to the
Intel big core CPUs starting with Sandy Bridge. We need
to report different values if HyperThreading is on or off.

The only thing this patch does is to export some events
in sysfs.

topdown level 1 uses a set of abstracted metrics which
are generic to out of order CPU cores (although some
CPUs may not implement all of them):

topdown-total-slots	  Available slots in the pipeline
topdown-slots-issued	  Slots issued into the pipeline
topdown-slots-retired	  Slots successfully retired
topdown-fetch-bubbles	  Pipeline gaps in the frontend
topdown-recovery-bubbles  Pipeline gaps during recovery
			  from misspeculation

A slot is a single operation in the CPU pipe line.

These metrics then allow to compute four useful metrics:
FrontendBound, BackendBound, Retiring, BadSpeculation.

The formulas to compute the metrics are generic, they
only change based on the availability on the abstracted
input values.

The kernel declares the events supported by the current
CPU and their scaling factors (such as the pipeline width)
and perf stat then computes the formulas based on the
available metrics.  This is similar how existing
perf metrics, such as TSC metrics or IPC, are implemented.

This abstracts all CPU pipe line specific knowledge in the
kernel driver, but still avoids the need for larger scale perf
interface changes.

For HyperThreading the any bit is needed to get accurate
values when both threads are executing. This implies that
the events can only be collected as root or with
perf_event_paranoid=-1 for now.

The basic scheme is based on the following paper:
  Yasin, A Top Down Method for Performance analysis and Counter architecture ISPASS14 (pdf available via google)
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1463703002-19686-4-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      a39fcae7
    • L
      perf/x86/intel: Change offcore response masks for Knights Landing · 9c489fce
      由 Lukasz Odzioba 提交于 
      Due to change in register definition we need to update OCR mask:

MSR_OFFCORE_RESP0 reserved bits: 3,4,18,29,30,33,34, 8,11,14
MSR_OFFCORE_RESP1 reserved bits: 3,4,18,29,30,33,34, 38
Reported-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NLukasz Odzioba <lukasz.odzioba@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akpm@linux-foundation.org
Cc: hpa@zytor.com
Cc: kan.liang@intel.com
Cc: lukasz.anaczkowski@intel.com
Cc: zheng.z.yan@intel.com
Link: http://lkml.kernel.org/r/1463433419-16893-1-git-send-email-lukasz.odzioba@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      9c489fce
    • L
      perf/x86/intel: Add 'static' keyword to locally used arrays · 20f36278
      由 Lukasz Odzioba 提交于 
      Add the 'static' keyword to intel_bdw_event_constraints[], snb_events_attrs[],
nhm_events_attrs[] and intel_skl_event_constraints arrays[], because
they are only used locally.
Signed-off-by: NLukasz Odzioba <lukasz.odzioba@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akpm@linux-foundation.org
Cc: hpa@zytor.com
Cc: kan.liang@intel.com
Cc: lukasz.anaczkowski@intel.com
Cc: zheng.z.yan@intel.com
Link: http://lkml.kernel.org/r/1463433378-16816-1-git-send-email-lukasz.odzioba@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      20f36278
  37. 12 5月, 2016 1 次提交
  39. 05 5月, 2016 2 次提交
  41. 23 4月, 2016 3 次提交
  43. 08 3月, 2016 4 次提交
    • A
      perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere · e17dc653
      由 Andi Kleen 提交于 
      Jiri reported some time ago that some entries in the PEBS data source table
in perf do not agree with the SDM. We investigated and the bits
changed for Sandy Bridge, but the SDM was not updated.

perf already implements the bits correctly for Sandy Bridge
and later. This patch patches it up for Nehalem and Westmere.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1456871124-15985-1-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      e17dc653
    • S
      perf/x86/pebs: Add proper PEBS constraints for Broadwell · b3e62463
      由 Stephane Eranian 提交于 
      This patch adds a Broadwell specific PEBS event constraint table.

Broadwell has a fix for the HT corruption bug erratum HSD29 on
Haswell. Therefore, there is no need to mark events 0xd0, 0xd1, 0xd2,
0xd3 has requiring the exclusive mode across both sibling HT threads.
This holds true for regular counting and sampling (see core.c) and
PEBS (ds.c) which we fix in this patch.

In doing so, we relax evnt scheduling for these events, they can now
be programmed on any 4 counters without impacting what is measured on
the sibling thread.
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@redhat.com
Cc: adrian.hunter@intel.com
Cc: jolsa@redhat.com
Cc: kan.liang@intel.com
Cc: namhyung@kernel.org
Link: http://lkml.kernel.org/r/1457034642-21837-4-git-send-email-eranian@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      b3e62463
    • S
      perf/x86/pebs: Add workaround for broken OVFL status on HSW+ · 8077eca0
      由 Stephane Eranian 提交于 
      This patch fixes an issue with the GLOBAL_OVERFLOW_STATUS bits on
Haswell, Broadwell and Skylake processors when using PEBS.

The SDM stipulates that when the PEBS iterrupt threshold is crossed,
an interrupt is posted and the kernel is interrupted. The kernel will
find GLOBAL_OVF_SATUS bit 62 set indicating there are PEBS records to
drain. But the bits corresponding to the actual counters should NOT be
set. The kernel follows the SDM and assumes that all PEBS events are
processed in the drain_pebs() callback. The kernel then checks for
remaining overflows on any other (non-PEBS) events and processes these
in the for_each_bit_set(&status) loop.

As it turns out, under certain conditions on HSW and later processors,
on PEBS buffer interrupt, bit 62 is set but the counter bits may be
set as well. In that case, the kernel drains PEBS and generates
SAMPLES with the EXACT tag, then it processes the counter bits, and
generates normal (non-EXACT) SAMPLES.

I ran into this problem by trying to understand why on HSW sampling on
a PEBS event was sometimes returning SAMPLES without the EXACT tag.
This should not happen on user level code because HSW has the
eventing_ip which always point to the instruction that caused the
event.

The workaround in this patch simply ensures that the bits for the
counters used for PEBS events are cleared after the PEBS buffer has
been drained. With this fix 100% of the PEBS samples on my user code
report the EXACT tag.

Before:
  $ perf record -e cpu/event=0xd0,umask=0x81/upp ./multichase
  $ perf report -D | fgrep SAMPLES
  PERF_RECORD_SAMPLE(IP, 0x2): 11775/11775: 0x406de5 period: 73469 addr: 0 exact=Y
                           \--- EXACT tag is missing

After:
  $ perf record -e cpu/event=0xd0,umask=0x81/upp ./multichase
  $ perf report -D | fgrep SAMPLES
  PERF_RECORD_SAMPLE(IP, 0x4002): 11775/11775: 0x406de5 period: 73469 addr: 0 exact=Y
                           \--- EXACT tag is set

The problem tends to appear more often when multiple PEBS events are used.
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: adrian.hunter@intel.com
Cc: kan.liang@intel.com
Cc: namhyung@kernel.org
Link: http://lkml.kernel.org/r/1457034642-21837-3-git-send-email-eranian@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      8077eca0
    • K
      perf/x86/intel: Fix PEBS warning by only restoring active PMU in pmi · c3d266c8
      由 Kan Liang 提交于 
      This patch tries to fix a PEBS warning found in my stress test. The
following perf command can easily trigger the pebs warning or spurious
NMI error on Skylake/Broadwell/Haswell platforms:

  sudo perf record -e 'cpu/umask=0x04,event=0xc4/pp,cycles,branches,ref-cycles,cache-misses,cache-references' --call-graph fp -b -c1000 -a

Also the NMI watchdog must be enabled.

For this case, the events number is larger than counter number. So
perf has to do multiplexing.

In perf_mux_hrtimer_handler, it does perf_pmu_disable(), schedule out
old events, rotate_ctx, schedule in new events and finally
perf_pmu_enable().

If the old events include precise event, the MSR_IA32_PEBS_ENABLE
should be cleared when perf_pmu_disable().  The MSR_IA32_PEBS_ENABLE
should keep 0 until the perf_pmu_enable() is called and the new event is
precise event.

However, there is a corner case which could restore PEBS_ENABLE to
stale value during the above period. In perf_pmu_disable(), GLOBAL_CTRL
will be set to 0 to stop overflow and followed PMI. But there may be
pending PMI from an earlier overflow, which cannot be stopped. So even
GLOBAL_CTRL is cleared, the kernel still be possible to get PMI. At
the end of the PMI handler, __intel_pmu_enable_all() will be called,
which will restore the stale values if old events haven't scheduled
out.

Once the stale pebs value is set, it's impossible to be corrected if
the new events are non-precise. Because the pebs_enabled will be set
to 0. x86_pmu.enable_all() will ignore the MSR_IA32_PEBS_ENABLE
setting. As a result, the following NMI with stale PEBS_ENABLE
trigger pebs warning.

The pending PMI after enabled=0 will become harmless if the NMI handler
does not change the state. This patch checks cpuc->enabled in pmi and
only restore the state when PMU is active.

Here is the dump:

  Call Trace:
   <NMI>  [<ffffffff813c3a2e>] dump_stack+0x63/0x85
   [<ffffffff810a46f2>] warn_slowpath_common+0x82/0xc0
   [<ffffffff810a483a>] warn_slowpath_null+0x1a/0x20
   [<ffffffff8100fe2e>] intel_pmu_drain_pebs_nhm+0x2be/0x320
   [<ffffffff8100caa9>] intel_pmu_handle_irq+0x279/0x460
   [<ffffffff810639b6>] ? native_write_msr_safe+0x6/0x40
   [<ffffffff811f290d>] ? vunmap_page_range+0x20d/0x330
   [<ffffffff811f2f11>] ?  unmap_kernel_range_noflush+0x11/0x20
   [<ffffffff8148379f>] ? ghes_copy_tofrom_phys+0x10f/0x2a0
   [<ffffffff814839c8>] ? ghes_read_estatus+0x98/0x170
   [<ffffffff81005a7d>] perf_event_nmi_handler+0x2d/0x50
   [<ffffffff810310b9>] nmi_handle+0x69/0x120
   [<ffffffff810316f6>] default_do_nmi+0xe6/0x100
   [<ffffffff810317f2>] do_nmi+0xe2/0x130
   [<ffffffff817aea71>] end_repeat_nmi+0x1a/0x1e
   [<ffffffff810639b6>] ? native_write_msr_safe+0x6/0x40
   [<ffffffff810639b6>] ? native_write_msr_safe+0x6/0x40
   [<ffffffff810639b6>] ? native_write_msr_safe+0x6/0x40
   <<EOE>>  <IRQ>  [<ffffffff81006df8>] ?  x86_perf_event_set_period+0xd8/0x180
   [<ffffffff81006eec>] x86_pmu_start+0x4c/0x100
   [<ffffffff8100722d>] x86_pmu_enable+0x28d/0x300
   [<ffffffff811994d7>] perf_pmu_enable.part.81+0x7/0x10
   [<ffffffff8119cb70>] perf_mux_hrtimer_handler+0x200/0x280
   [<ffffffff8119c970>] ?  __perf_install_in_context+0xc0/0xc0
   [<ffffffff8110f92d>] __hrtimer_run_queues+0xfd/0x280
   [<ffffffff811100d8>] hrtimer_interrupt+0xa8/0x190
   [<ffffffff81199080>] ?  __perf_read_group_add.part.61+0x1a0/0x1a0
   [<ffffffff81051bd8>] local_apic_timer_interrupt+0x38/0x60
   [<ffffffff817af01d>] smp_apic_timer_interrupt+0x3d/0x50
   [<ffffffff817ad15c>] apic_timer_interrupt+0x8c/0xa0
   <EOI>  [<ffffffff81199080>] ?  __perf_read_group_add.part.61+0x1a0/0x1a0
   [<ffffffff81123de5>] ?  smp_call_function_single+0xd5/0x130
   [<ffffffff81123ddb>] ?  smp_call_function_single+0xcb/0x130
   [<ffffffff81199080>] ?  __perf_read_group_add.part.61+0x1a0/0x1a0
   [<ffffffff8119765a>] event_function_call+0x10a/0x120
   [<ffffffff8119c660>] ? ctx_resched+0x90/0x90
   [<ffffffff811971e0>] ? cpu_clock_event_read+0x30/0x30
   [<ffffffff811976d0>] ? _perf_event_disable+0x60/0x60
   [<ffffffff8119772b>] _perf_event_enable+0x5b/0x70
   [<ffffffff81197388>] perf_event_for_each_child+0x38/0xa0
   [<ffffffff811976d0>] ? _perf_event_disable+0x60/0x60
   [<ffffffff811a0ffd>] perf_ioctl+0x12d/0x3c0
   [<ffffffff8134d855>] ? selinux_file_ioctl+0x95/0x1e0
   [<ffffffff8124a3a1>] do_vfs_ioctl+0xa1/0x5a0
   [<ffffffff81036d29>] ? sched_clock+0x9/0x10
   [<ffffffff8124a919>] SyS_ioctl+0x79/0x90
   [<ffffffff817ac4b2>] entry_SYSCALL_64_fastpath+0x1a/0xa4
  ---[ end trace aef202839fe9a71d ]---
  Uhhuh. NMI received for unknown reason 2d on CPU 2.
  Do you have a strange power saving mode enabled?
Signed-off-by: NKan Liang <kan.liang@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1457046448-6184-1-git-send-email-kan.liang@intel.com
[ Fixed various typos and other small details. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      c3d266c8
  45. 17 2月, 2016 2 次提交
  47. 29 1月, 2016 2 次提交
    • P
      perf/x86: De-obfuscate code · 8f04b853
      由 Peter Zijlstra 提交于 
      Get rid of the 'onln' obfuscation.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      8f04b853
    • P
      perf/x86: Fix uninitialized value usage · e01d8718
      由 Peter Zijlstra 提交于 
      When calling intel_alt_er() with .idx != EXTRA_REG_RSP_* we will not
initialize alt_idx and then use this uninitialized value to index an
array.

When that is not fatal, it can result in an infinite loop in its
caller __intel_shared_reg_get_constraints(), with IRQs disabled.

Alternative error modes are random memory corruption due to the
cpuc->shared_regs->regs[] array overrun, which manifest in either
get_constraints or put_constraints doing weird stuff.

Only took 6 hours of painful debugging to find this. Neither GCC nor
Smatch warnings flagged this bug.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: ae3f011f ("perf/x86/intel: Fix SLM MSR_OFFCORE_RSP1 valid_mask")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      e01d8718
  49. 06 1月, 2016 3 次提交
    • H
      perf/x86/intel: Add perf core PMU support for Intel Knights Landing · 1e7b9390
      由 Harish Chegondi 提交于 
      Knights Landing core is based on Silvermont core with several differences.
Like Silvermont, Knights Landing has 8 pairs of LBR MSRs. However, the
LBR MSRs addresses match those of the Xeon cores' first 8 pairs of LBR MSRs
Unlike Silvermont, Knights Landing supports hyperthreading. Knights Landing
offcore response events config register mask is different from that of the
Silvermont.

This patch was developed based on a patch from Andi Kleen.

For more details, please refer to the public document:

  https://software.intel.com/sites/default/files/managed/15/8d/IntelXeonPhi%E2%84%A2x200ProcessorPerformanceMonitoringReferenceManual_Volume1_Registers_v0%206.pdfSigned-off-by: NHarish Chegondi <harish.chegondi@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Harish Chegondi <harish.chegondi@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukasz Anaczkowski <lukasz.anaczkowski@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/d14593c7311f78c93c9cf6b006be843777c5ad5c.1449517401.git.harish.chegondi@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      1e7b9390
    • S
      perf/x86: Enable cycles:pp for Intel Atom · 673d188b
      由 Stephane Eranian 提交于 
      This patch updates the PEBS support for Intel Atom to provide
an alias for the cycles:pp event used by perf record/top by default
nowadays.

On Atom, only INST_RETIRED:ANY supports PEBS, so we use this event
instead with a large cmask to count cycles. Given that Core2 has
the same issue, we use the intel_pebs_aliases_core2() function for Atom
as well.
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: kan.liang@intel.com
Link: http://lkml.kernel.org/r/1449172990-30183-3-git-send-email-eranian@google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      673d188b
    • A
      perf/x86: Use INST_RETIRED.PREC_DIST for cycles: ppp · 72469764
      由 Andi Kleen 提交于 
      Add a new 'three-p' precise level, that uses INST_RETIRED.PREC_DIST as
base. The basic mechanism of abusing the inverse cmask to get all
cycles works the same as before.

PREC_DIST is available on Sandy Bridge or later. It had some problems
on Sandy Bridge, so we only use it on IvyBridge and later. I tested it
on Broadwell and Skylake.

PREC_DIST has special support for avoiding shadow effects, which can
give better results compare to UOPS_RETIRED. The drawback is that
PREC_DIST can only schedule on counter 1, but that is ok for cycle
sampling, as there is normally no need to do multiple cycle sampling
runs in parallel. It is still possible to run perf top in parallel, as
that doesn't use precise mode. Also of course the multiplexing can
still allow parallel operation.

:pp stays with the previous event.

Example:

Sample a loop with 10 sqrt with old cycles:pp

	  0.14 │10:   sqrtps %xmm1,%xmm0     <--------------
	  9.13 │      sqrtps %xmm1,%xmm0
	 11.58 │      sqrtps %xmm1,%xmm0
	 11.51 │      sqrtps %xmm1,%xmm0
	  6.27 │      sqrtps %xmm1,%xmm0
	 10.38 │      sqrtps %xmm1,%xmm0
	 12.20 │      sqrtps %xmm1,%xmm0
	 12.74 │      sqrtps %xmm1,%xmm0
	  5.40 │      sqrtps %xmm1,%xmm0
	 10.14 │      sqrtps %xmm1,%xmm0
	 10.51 │    ↑ jmp    10

We expect all 10 sqrt to get roughly the sample number of samples.

But you can see that the instruction directly after the JMP is
systematically underestimated in the result, due to sampling shadow
effects.

With the new PREC_DIST based sampling this problem is gone and all
instructions show up roughly evenly:

	  9.51 │10:   sqrtps %xmm1,%xmm0
	 11.74 │      sqrtps %xmm1,%xmm0
	 11.84 │      sqrtps %xmm1,%xmm0
	  6.05 │      sqrtps %xmm1,%xmm0
	 10.46 │      sqrtps %xmm1,%xmm0
	 12.25 │      sqrtps %xmm1,%xmm0
	 12.18 │      sqrtps %xmm1,%xmm0
	  5.26 │      sqrtps %xmm1,%xmm0
	 10.13 │      sqrtps %xmm1,%xmm0
	 10.43 │      sqrtps %xmm1,%xmm0
	  0.16 │    ↑ jmp    10

Even with PREC_DIST there is still sampling skid and the result is not
completely even, but systematic shadow effects are significantly
reduced.

The improvements are mainly expected to make a difference in high IPC
code. With low IPC it should be similar.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: hpa@zytor.com
Link: http://lkml.kernel.org/r/1448929689-13771-2-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      72469764