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. 10 12月, 2020 1 次提交
  3. 10 11月, 2020 2 次提交
  5. 29 10月, 2020 2 次提交
  7. 03 10月, 2020 1 次提交
  9. 29 9月, 2020 2 次提交
  11. 24 8月, 2020 1 次提交
  13. 18 8月, 2020 5 次提交
    • K
      perf/x86/intel: Support per-thread RDPMC TopDown metrics · 2cb5383b
      由 Kan Liang 提交于 
      Starts from Ice Lake, the TopDown metrics are directly available as
fixed counters and do not require generic counters. Also, the TopDown
metrics can be collected per thread. Extend the RDPMC usage to support
per-thread TopDown metrics.

The RDPMC index of the PERF_METRICS will be output if RDPMC users ask
for the RDPMC index of the metrics events.

To support per thread RDPMC TopDown, the metrics and slots counters have
to be saved/restored during the context switching.

The last_period and period_left are not used in the counting mode. Use
the fields for saved_metric and saved_slots.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-12-kan.liang@linux.intel.com
      2cb5383b
    • K
      perf/x86/intel: Support TopDown metrics on Ice Lake · 59a854e2
      由 Kan Liang 提交于 
      Ice Lake supports the hardware TopDown metrics feature, which can free
up the scarce GP counters.

Update the event constraints for the metrics events. The metric counters
do not exist, which are mapped to a dummy offset. The sharing between
multiple users of the same metric without multiplexing is not allowed.

Implement set_topdown_event_period for Ice Lake. The values in
PERF_METRICS MSR are derived from the fixed counter 3. Both registers
should start from zero.

Implement update_topdown_event for Ice Lake. The metric is reported by
multiplying the metric (fraction) with slots. To maintain accurate
measurements, both registers are cleared for each update. The fixed
counter 3 should always be cleared before the PERF_METRICS.

Implement td_attr for the new metrics events and the new slots fixed
counter. Make them visible to the perf user tools.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-11-kan.liang@linux.intel.com
      59a854e2
    • K
      perf/x86/intel: Generic support for hardware TopDown metrics · 7b2c05a1
      由 Kan Liang 提交于 
      Intro
=====

The TopDown Microarchitecture Analysis (TMA) Method is a structured
analysis methodology to identify critical performance bottlenecks in
out-of-order processors. Current perf has supported the method.

The method works well, but there is one problem. To collect the TopDown
events, several GP counters have to be used. If a user wants to collect
other events at the same time, the multiplexing probably be triggered,
which impacts the accuracy.

To free up the scarce GP counters, the hardware TopDown metrics feature
is introduced from Ice Lake. The hardware implements an additional
"metrics" register and a new Fixed Counter 3 that measures pipeline
"slots". The TopDown events can be calculated from them instead.

Events
======

The level 1 TopDown has four metrics. There is no event-code assigned to
the TopDown metrics. Four metric events are exported as separate perf
events, which map to the internal "metrics" counter register. Those
events do not exist in hardware, but can be allocated by the scheduler.

For the event mapping, a special 0x00 event code is used, which is
reserved for fake events. The metric events start from umask 0x10.

When setting up the metric events, they point to the Fixed Counter 3.
They have to be specially handled.
- Add the update_topdown_event() callback to read the additional metrics
  MSR and generate the metrics.
- Add the set_topdown_event_period() callback to initialize metrics MSR
  and the fixed counter 3.
- Add a variable n_metric_event to track the number of the accepted
  metrics events. The sharing between multiple users of the same metric
  without multiplexing is not allowed.
- Only enable/disable the fixed counter 3 when there are no other active
  TopDown events, which avoid the unnecessary writing of the fixed
  control register.
- Disable the PMU when reading the metrics event. The metrics MSR and
  the fixed counter 3 are read separately. The values may be modified by
  an NMI.

All four metric events don't support sampling. Since they will be
handled specially for event update, a flag PERF_X86_EVENT_TOPDOWN is
introduced to indicate this case.

The slots event can support both sampling and counting.
For counting, the flag is also applied.
For sampling, it will be handled normally as other normal events.

Groups
======

The slots event is required in a Topdown group.
To avoid reading the METRICS register multiple times, the metrics and
slots value can only be updated by slots event in a group.
All active slots and metrics events will be updated one time.
Therefore, the slots event must be before any metric events in a Topdown
group.

NMI
======

The METRICS related register may be overflow. The bit 48 of the STATUS
register will be set. If so, PERF_METRICS and Fixed counter 3 are
required to be reset. The patch also update all active slots and
metrics events in the NMI handler.

The update_topdown_event() has to read two registers separately. The
values may be modified by an NMI. PMU has to be disabled before calling
the function.

RDPMC
======

RDPMC is temporarily disabled. A later patch will enable it.
Suggested-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-9-kan.liang@linux.intel.com
      7b2c05a1
    • K
      perf/x86/intel: Use switch in intel_pmu_disable/enable_event · 58da7dbe
      由 Kan Liang 提交于 
      Currently, the if-else is used in the intel_pmu_disable/enable_event to
check the type of an event. It works well, but with more and more types
added later, e.g., perf metrics, compared to the switch statement, the
if-else may impair the readability of the code.

There is no harm to use the switch statement to replace the if-else
here. Also, some optimizing compilers may compile a switch statement
into a jump-table which is more efficient than if-else for a large
number of cases. The performance gain may not be observed for now,
because the number of cases is only 5, but the benefits may be observed
with more and more types added in the future.

Use switch to replace the if-else in the intel_pmu_disable/enable_event.

If the idx is invalid, print a warning.

For the case INTEL_PMC_IDX_FIXED_BTS in intel_pmu_disable_event, don't
need to check the event->attr.precise_ip. Use return for the case.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-7-kan.liang@linux.intel.com
      58da7dbe
    • K
      perf/x86/intel: Name the global status bit in NMI handler · 60a2a271
      由 Kan Liang 提交于 
      Magic numbers are used in the current NMI handler for the global status
bit. Use a meaningful name to replace the magic numbers to improve the
readability of the code.

Remove a Tab for all GLOBAL_STATUS_* and INTEL_PMC_IDX_FIXED_BTS macros
to reduce the length of the line.
Suggested-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-3-kan.liang@linux.intel.com
      60a2a271
  15. 08 7月, 2020 4 次提交
    • K
      perf/x86/intel/lbr: Support Architectural LBR · 47125db2
      由 Kan Liang 提交于 
      Last Branch Records (LBR) enables recording of software path history by
logging taken branches and other control flows within architectural
registers now. Intel CPUs have had model-specific LBR for quite some
time, but this evolves them into an architectural feature now.

The main improvements of Architectural LBR implemented includes:
- Linux kernel can support the LBR features without knowing the model
  number of the current CPU.
- Architectural LBR capabilities can be enumerated by CPUID. The
  lbr_ctl_map is based on the CPUID Enumeration.
- The possible LBR depth can be retrieved from CPUID enumeration. The
  max value is written to the new MSR_ARCH_LBR_DEPTH as the number of
  LBR entries.
- A new IA32_LBR_CTL MSR is introduced to enable and configure LBRs,
  which replaces the IA32_DEBUGCTL[bit 0] and the LBR_SELECT MSR.
- Each LBR record or entry is still comprised of three MSRs,
  IA32_LBR_x_FROM_IP, IA32_LBR_x_TO_IP and IA32_LBR_x_TO_IP.
  But they become the architectural MSRs.
- Architectural LBR is stack-like now. Entry 0 is always the youngest
  branch, entry 1 the next youngest... The TOS MSR has been removed.

The way to enable/disable Architectural LBR is similar to the previous
model-specific LBR. __intel_pmu_lbr_enable/disable() can be reused, but
some modifications are required, which include:
- MSR_ARCH_LBR_CTL is used to enable and configure the Architectural
  LBR.
- When checking the value of the IA32_DEBUGCTL MSR, ignoring the
  DEBUGCTLMSR_LBR (bit 0) for Architectural LBR, which has no meaning
  and always return 0.
- The FREEZE_LBRS_ON_PMI has to be explicitly set/clear, because
  MSR_IA32_DEBUGCTLMSR is not touched in __intel_pmu_lbr_disable() for
  Architectural LBR.
- Only MSR_ARCH_LBR_CTL is cleared in __intel_pmu_lbr_disable() for
  Architectural LBR.

Some Architectural LBR dedicated functions are implemented to
reset/read/save/restore LBR.
- For reset, writing to the ARCH_LBR_DEPTH MSR clears all Arch LBR
  entries, which is a lot faster and can improve the context switch
  latency.
- For read, the branch type information can be retrieved from
  the MSR_ARCH_LBR_INFO_*. But it's not fully compatible due to
  OTHER_BRANCH type. The software decoding is still required for the
  OTHER_BRANCH case.
  LBR records are stored in the age order as well. Reuse
  intel_pmu_store_lbr(). Check the CPUID enumeration before accessing
  the corresponding bits in LBR_INFO.
- For save/restore, applying the fast reset (writing ARCH_LBR_DEPTH).
  Reading 'lbr_from' of entry 0 instead of the TOS MSR to check if the
  LBR registers are reset in the deep C-state. If 'the deep C-state
  reset' bit is not set in CPUID enumeration, ignoring the check.
  XSAVE support for Architectural LBR will be implemented later.

The number of LBR entries cannot be hardcoded anymore, which should be
retrieved from CPUID enumeration. A new structure
x86_perf_task_context_arch_lbr is introduced for Architectural LBR.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-15-git-send-email-kan.liang@linux.intel.com
      47125db2
    • K
      perf/x86/intel/lbr: Add the function pointers for LBR save and restore · 799571bf
      由 Kan Liang 提交于 
      The MSRs of Architectural LBR are different from previous model-specific
LBR. Perf has to implement different functions to save and restore them.

The function pointers for LBR save and restore are introduced. Perf
should initialize the corresponding functions at boot time.

The generic optimizations, e.g. avoiding restore LBR if no one else
touched them, still apply for Architectural LBRs. The related codes are
not moved to model-specific functions.

Current model-specific LBR functions are set as default.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-5-git-send-email-kan.liang@linux.intel.com
      799571bf
    • K
      perf/x86/intel/lbr: Add a function pointer for LBR read · c301b1d8
      由 Kan Liang 提交于 
      The method to read Architectural LBRs is different from previous
model-specific LBR. Perf has to implement a different function.

A function pointer for LBR read is introduced. Perf should initialize
the corresponding function at boot time, and avoid checking lbr_format
at run time.

The current 64-bit LBR read function is set as default.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-4-git-send-email-kan.liang@linux.intel.com
      c301b1d8
    • K
      perf/x86/intel/lbr: Add a function pointer for LBR reset · 9f354a72
      由 Kan Liang 提交于 
      The method to reset Architectural LBRs is different from previous
model-specific LBR. Perf has to implement a different function.

A function pointer is introduced for LBR reset. The enum of
LBR_FORMAT_* is also moved to perf_event.h. Perf should initialize the
corresponding functions at boot time, and avoid checking lbr_format at
run time.

The current 64-bit LBR reset function is set as default.
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-3-git-send-email-kan.liang@linux.intel.com
      9f354a72
  17. 02 7月, 2020 3 次提交
  19. 20 5月, 2020 1 次提交
  21. 11 2月, 2020 2 次提交
  23. 15 11月, 2019 1 次提交
    • A
      x86: retpolines: eliminate retpoline from msr event handlers · 74c504a6
      由 Andrea Arcangeli 提交于 
      It's enough to check the value and issue the direct call.

After this commit is applied, here the most common retpolines executed
under a high resolution timer workload in the guest on a VMX host:

[..]
@[
    trace_retpoline+1
    __trace_retpoline+30
    __x86_indirect_thunk_rax+33
    do_syscall_64+89
    entry_SYSCALL_64_after_hwframe+68
]: 267
@[]: 2256
@[
    trace_retpoline+1
    __trace_retpoline+30
    __x86_indirect_thunk_rax+33
    __kvm_wait_lapic_expire+284
    vmx_vcpu_run.part.97+1091
    vcpu_enter_guest+377
    kvm_arch_vcpu_ioctl_run+261
    kvm_vcpu_ioctl+559
    do_vfs_ioctl+164
    ksys_ioctl+96
    __x64_sys_ioctl+22
    do_syscall_64+89
    entry_SYSCALL_64_after_hwframe+68
]: 2390
@[]: 33410

@total: 315707

Note the highest hit above is __delay so probably not worth optimizing
even if it would be more frequent than 2k hits per sec.
Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
      74c504a6
  25. 28 10月, 2019 1 次提交
  27. 18 10月, 2019 1 次提交
    • J
      perf_event: Add support for LSM and SELinux checks · da97e184
      由 Joel Fernandes (Google) 提交于 
      In current mainline, the degree of access to perf_event_open(2) system
call depends on the perf_event_paranoid sysctl.  This has a number of
limitations:

1. The sysctl is only a single value. Many types of accesses are controlled
   based on the single value thus making the control very limited and
   coarse grained.
2. The sysctl is global, so if the sysctl is changed, then that means
   all processes get access to perf_event_open(2) opening the door to
   security issues.

This patch adds LSM and SELinux access checking which will be used in
Android to access perf_event_open(2) for the purposes of attaching BPF
programs to tracepoints, perf profiling and other operations from
userspace. These operations are intended for production systems.

5 new LSM hooks are added:
1. perf_event_open: This controls access during the perf_event_open(2)
   syscall itself. The hook is called from all the places that the
   perf_event_paranoid sysctl is checked to keep it consistent with the
   systctl. The hook gets passed a 'type' argument which controls CPU,
   kernel and tracepoint accesses (in this context, CPU, kernel and
   tracepoint have the same semantics as the perf_event_paranoid sysctl).
   Additionally, I added an 'open' type which is similar to
   perf_event_paranoid sysctl == 3 patch carried in Android and several other
   distros but was rejected in mainline [1] in 2016.

2. perf_event_alloc: This allocates a new security object for the event
   which stores the current SID within the event. It will be useful when
   the perf event's FD is passed through IPC to another process which may
   try to read the FD. Appropriate security checks will limit access.

3. perf_event_free: Called when the event is closed.

4. perf_event_read: Called from the read(2) and mmap(2) syscalls for the event.

5. perf_event_write: Called from the ioctl(2) syscalls for the event.

[1] https://lwn.net/Articles/696240/

Since Peter had suggest LSM hooks in 2016 [1], I am adding his
Suggested-by tag below.

To use this patch, we set the perf_event_paranoid sysctl to -1 and then
apply selinux checking as appropriate (default deny everything, and then
add policy rules to give access to domains that need it). In the future
we can remove the perf_event_paranoid sysctl altogether.
Suggested-by: NPeter Zijlstra <peterz@infradead.org>
Co-developed-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NJoel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NJames Morris <jmorris@namei.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: rostedt@goodmis.org
Cc: Yonghong Song <yhs@fb.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: jeffv@google.com
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: primiano@google.com
Cc: Song Liu <songliubraving@fb.com>
Cc: rsavitski@google.com
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Matthew Garrett <matthewgarrett@google.com>
Link: https://lkml.kernel.org/r/20191014170308.70668-1-joel@joelfernandes.org
      da97e184
  29. 12 10月, 2019 2 次提交
  31. 30 8月, 2019 1 次提交
    • J
      perf/x86/intel: Restrict period on Nehalem · 44d3bbb6
      由 Josh Hunt 提交于 
      We see our Nehalem machines reporting 'perfevents: irq loop stuck!' in
some cases when using perf:

perfevents: irq loop stuck!
WARNING: CPU: 0 PID: 3485 at arch/x86/events/intel/core.c:2282 intel_pmu_handle_irq+0x37b/0x530
...
RIP: 0010:intel_pmu_handle_irq+0x37b/0x530
...
Call Trace:
<NMI>
? perf_event_nmi_handler+0x2e/0x50
? intel_pmu_save_and_restart+0x50/0x50
perf_event_nmi_handler+0x2e/0x50
nmi_handle+0x6e/0x120
default_do_nmi+0x3e/0x100
do_nmi+0x102/0x160
end_repeat_nmi+0x16/0x50
...
? native_write_msr+0x6/0x20
? native_write_msr+0x6/0x20
</NMI>
intel_pmu_enable_event+0x1ce/0x1f0
x86_pmu_start+0x78/0xa0
x86_pmu_enable+0x252/0x310
__perf_event_task_sched_in+0x181/0x190
? __switch_to_asm+0x41/0x70
? __switch_to_asm+0x35/0x70
? __switch_to_asm+0x41/0x70
? __switch_to_asm+0x35/0x70
finish_task_switch+0x158/0x260
__schedule+0x2f6/0x840
? hrtimer_start_range_ns+0x153/0x210
schedule+0x32/0x80
schedule_hrtimeout_range_clock+0x8a/0x100
? hrtimer_init+0x120/0x120
ep_poll+0x2f7/0x3a0
? wake_up_q+0x60/0x60
do_epoll_wait+0xa9/0xc0
__x64_sys_epoll_wait+0x1a/0x20
do_syscall_64+0x4e/0x110
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fdeb1e96c03
...
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: acme@kernel.org
Cc: Josh Hunt <johunt@akamai.com>
Cc: bpuranda@akamai.com
Cc: mingo@redhat.com
Cc: jolsa@redhat.com
Cc: tglx@linutronix.de
Cc: namhyung@kernel.org
Cc: alexander.shishkin@linux.intel.com
Link: https://lkml.kernel.org/r/1566256411-18820-1-git-send-email-johunt@akamai.com
      44d3bbb6
  33. 28 8月, 2019 5 次提交
  35. 26 7月, 2019 1 次提交
    • G
      perf/x86/intel: Mark expected switch fall-throughs · 7b26b91d
      由 Gustavo A. R. Silva 提交于 
      In preparation to enabling -Wimplicit-fallthrough, mark switch
cases where we are expecting to fall through.

This patch fixes the following warnings:

arch/x86/events/intel/core.c: In function ‘intel_pmu_init’:
arch/x86/events/intel/core.c:4959:8: warning: this statement may fall through [-Wimplicit-fallthrough=]
   pmem = true;
   ~~~~~^~~~~~
arch/x86/events/intel/core.c:4960:2: note: here
  case INTEL_FAM6_SKYLAKE_MOBILE:
  ^~~~
arch/x86/events/intel/core.c:5008:8: warning: this statement may fall through [-Wimplicit-fallthrough=]
   pmem = true;
   ~~~~~^~~~~~
arch/x86/events/intel/core.c:5009:2: note: here
  case INTEL_FAM6_ICELAKE_MOBILE:
  ^~~~

Warning level 3 was used: -Wimplicit-fallthrough=3

This patch is part of the ongoing efforts to enable
-Wimplicit-fallthrough.
Signed-off-by: NGustavo A. R. Silva <gustavo@embeddedor.com>
      7b26b91d
  37. 25 7月, 2019 3 次提交
  39. 13 7月, 2019 1 次提交
    • K
      perf/x86/intel: Fix spurious NMI on fixed counter · e4557c1a
      由 Kan Liang 提交于 
      If a user first sample a PEBS event on a fixed counter, then sample a
non-PEBS event on the same fixed counter on Icelake, it will trigger
spurious NMI. For example:

  perf record -e 'cycles:p' -a
  perf record -e 'cycles' -a

The error message for spurious NMI:

  [June 21 15:38] Uhhuh. NMI received for unknown reason 30 on CPU 2.
  [    +0.000000] Do you have a strange power saving mode enabled?
  [    +0.000000] Dazed and confused, but trying to continue

The bug was introduced by the following commit:

  commit 6f55967a ("perf/x86/intel: Fix race in intel_pmu_disable_event()")

The commit moves the intel_pmu_pebs_disable() after intel_pmu_disable_fixed(),
which returns immediately.  The related bit of PEBS_ENABLE MSR will never be
cleared for the fixed counter. Then a non-PEBS event runs on the fixed counter,
but the bit on PEBS_ENABLE is still set, which triggers spurious NMIs.

Check and disable PEBS for fixed counters after intel_pmu_disable_fixed().
Reported-by: NYi, Ammy <ammy.yi@intel.com>
Signed-off-by: NKan Liang <kan.liang@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NJiri Olsa <jolsa@kernel.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>
Fixes: 6f55967a ("perf/x86/intel: Fix race in intel_pmu_disable_event()")
Link: https://lkml.kernel.org/r/20190625142135.22112-1-kan.liang@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      e4557c1a