linux.git/tools/perf/util/parse-events.c, branch v5.10

perf tools: Add support for exclusive groups/events

2020-10-14T15:24:28+00:00

Peter suggested that using the exclusive mode in perf could avoid some
problems with bad scheduling of groups. Exclusive is implemented in the
kernel, but wasn't exposed by the perf tool, so hard to use without
custom low level API users.

Add support for marking groups or events with :e for exclusive in the
perf tool.  The implementation is basically the same as the existing
pinned attribute.

Committer testing:

  # perf test "parse event"
   6: Parse event definition strings                                  : Ok
  # perf test -v "parse event" |& grep :u*e
  running test 56 'instructions:uep'
  running test 57 '{cycles,cache-misses,branch-misses}:e'
  #
  #
  # grep "model name" -m1 /proc/cpuinfo
  model name	: AMD Ryzen 9 3900X 12-Core Processor
  #
  # perf stat -a -e '{cycles,cache-misses,branch-misses}:e' sleep 1

   Performance counter stats for 'system wide':

             cycles                                                        (0.00%)
             cache-misses                                                  (0.00%)
             branch-misses                                                 (0.00%)

         1.001269893 seconds time elapsed

  Some events weren't counted. Try disabling the NMI watchdog:
  	echo 0 > /proc/sys/kernel/nmi_watchdog
  	perf stat ...
  	echo 1 > /proc/sys/kernel/nmi_watchdog
  # echo 0 > /proc/sys/kernel/nmi_watchdog
  # perf stat -a -e '{cycles,cache-misses,branch-misses}:e' sleep 1

   Performance counter stats for 'system wide':

       1,298,663,141      cycles
          30,962,215      cache-misses
           5,325,150      branch-misses

         1.001474934 seconds time elapsed

  #
  # The output for asking for precise events on AMD needs to improve, it
  # supposedly works only for system wide or per CPU
  #
  # perf stat -a -e '{cycles,cache-misses,branch-misses}:uep' sleep 1
  Error:
  The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
  /bin/dmesg | grep -i perf may provide additional information.

  # perf stat -a -e '{cycles,cache-misses,branch-misses}:ue' sleep 1

   Performance counter stats for 'system wide':

         746,363,126      cycles
          16,881,611      cache-misses
           2,871,259      branch-misses

         1.001636066 seconds time elapsed

  #

Signed-off-by: Andi Kleen 
Acked-by: Jiri Olsa 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Andi Kleen 
Cc: Peter Zijlstra 
Link: http://lore.kernel.org/lkml/20201014144255.22699-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo

Merge branch 'perf/urgent' into perf/core

2020-10-13T16:02:20+00:00

To pick fixes that missed v5.9.

Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Reduce casts around bp_addr

2020-09-28T12:22:39+00:00

perf_event_attr bp_addr is a u64. parse-events.y parses it as a u64, but
casts it to a void* and then parse-events.c casts it back to a u64.
Rather than all the casts, change the type of the address to be a u64.

This removes an issue noted in:

  https://lore.kernel.org/lkml/20200903184359.GC3495158@kernel.org/

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Jin Yao 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20200925003903.561568-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-event: Release cpu_map refcount if evsel alloc failed

2020-09-17T16:28:15+00:00

Signed-off-by: Namhyung Kim 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20200917060219.1287863-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-event: Fix cpu map refcounting

2020-09-17T16:25:35+00:00

Like evlist cpu map, evsel's cpu map should have a proper refcount.

As it's created with a refcount, we don't need to get an extra count.
Thanks to Arnaldo for the simpler suggestion.

This, together with the following patch, fixes the following ASAN
report:

  Direct leak of 840 byte(s) in 70 object(s) allocated from:
    #0 0x7fe36703f628 in malloc (/lib/x86_64-linux-gnu/libasan.so.5+0x107628)
    #1 0x559fbbf611ca in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x559fbbf6229c in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:237
    #3 0x559fbbcc6c6d in __add_event util/parse-events.c:357
    #4 0x559fbbcc6c6d in add_event_tool util/parse-events.c:408
    #5 0x559fbbcc6c6d in parse_events_add_tool util/parse-events.c:1414
    #6 0x559fbbd8474d in parse_events_parse util/parse-events.y:439
    #7 0x559fbbcc95da in parse_events__scanner util/parse-events.c:2096
    #8 0x559fbbcc95da in __parse_events util/parse-events.c:2141
    #9 0x559fbbc2788b in check_parse_id tests/pmu-events.c:406
    #10 0x559fbbc2788b in check_parse_id tests/pmu-events.c:393
    #11 0x559fbbc2788b in check_parse_fake tests/pmu-events.c:436
    #12 0x559fbbc2788b in metric_parse_fake tests/pmu-events.c:553
    #13 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:599
    #14 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:574
    #15 0x559fbbc0109b in run_test tests/builtin-test.c:410
    #16 0x559fbbc0109b in test_and_print tests/builtin-test.c:440
    #17 0x559fbbc03e69 in __cmd_test tests/builtin-test.c:695
    #18 0x559fbbc03e69 in cmd_test tests/builtin-test.c:807
    #19 0x559fbbc691f4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:312
    #20 0x559fbbb071a8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:364
    #21 0x559fbbb071a8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:408
    #22 0x559fbbb071a8 in main /home/namhyung/project/linux/tools/perf/perf.c:538
    #23 0x7fe366b68cc9 in __libc_start_main ../csu/libc-start.c:308

And I've failed which commit introduced this bug as the code was
heavily changed since then. ;-/

Signed-off-by: Namhyung Kim 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20200917060219.1287863-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-event: Fix memory leak in evsel->unit

2020-09-15T12:18:56+00:00

The evsel->unit borrows a pointer of pmu event or alias instead of
owns a string.  But tool event (duration_time) passes a result of
strdup() caused a leak.

It was found by ASAN during metric test:

  Direct leak of 210 byte(s) in 70 object(s) allocated from:
    #0 0x7fe366fca0b5 in strdup (/lib/x86_64-linux-gnu/libasan.so.5+0x920b5)
    #1 0x559fbbcc6ea3 in add_event_tool util/parse-events.c:414
    #2 0x559fbbcc6ea3 in parse_events_add_tool util/parse-events.c:1414
    #3 0x559fbbd8474d in parse_events_parse util/parse-events.y:439
    #4 0x559fbbcc95da in parse_events__scanner util/parse-events.c:2096
    #5 0x559fbbcc95da in __parse_events util/parse-events.c:2141
    #6 0x559fbbc28555 in check_parse_id tests/pmu-events.c:406
    #7 0x559fbbc28555 in check_parse_id tests/pmu-events.c:393
    #8 0x559fbbc28555 in check_parse_cpu tests/pmu-events.c:415
    #9 0x559fbbc28555 in test_parsing tests/pmu-events.c:498
    #10 0x559fbbc0109b in run_test tests/builtin-test.c:410
    #11 0x559fbbc0109b in test_and_print tests/builtin-test.c:440
    #12 0x559fbbc03e69 in __cmd_test tests/builtin-test.c:695
    #13 0x559fbbc03e69 in cmd_test tests/builtin-test.c:807
    #14 0x559fbbc691f4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:312
    #15 0x559fbbb071a8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:364
    #16 0x559fbbb071a8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:408
    #17 0x559fbbb071a8 in main /home/namhyung/project/linux/tools/perf/perf.c:538
    #18 0x7fe366b68cc9 in __libc_start_main ../csu/libc-start.c:308

Fixes: f0fbb114e3025 ("perf stat: Implement duration_time as a proper event")
Signed-off-by: Namhyung Kim 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20200915031819.386559-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Avoid an uninitialized read when using fake PMUs

2020-09-01T15:15:52+00:00

With a fake_pmu the pmu_info isn't populated by perf_pmu__check_alias.
In this case, don't try to copy the uninitialized values to the evsel.

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20200826042910.1902374-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Set exclude_guest=1 for user-space counting

2020-09-01T15:15:51+00:00

Currently if we run 'perf record -e cycles:u', exclude_guest=0.

But it doesn't make sense in most cases that we request for
user-space counting but we also get the guest report.

Of course, we also need to consider 'perf kvm' usage case that
authorized perf users on the host may only want to count guest user
space events. For example,

  # perf kvm --guest record -e cycles:u

When we have 'exclude_guest=1' for 'perf kvm' usage, we may get nothing
from guest events.

To keep perf semantics consistent and clear, this patch sets
exclude_guest=1 for user-space counting but except for 'perf kvm' usage.

Before:

  perf record -e cycles:u ./div
  perf evlist -v
  cycles:u: ..., exclude_kernel: 1, exclude_hv: 1, ...

After:
  perf record -e cycles:u ./div
  perf evlist -v
  cycles:u: ..., exclude_kernel: 1, exclude_hv: 1,  exclude_guest: 1, ...

Before:
  perf kvm --guest record -e cycles:u -vvv

perf_event_attr:

  size                             120
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|ID|CPU|PERIOD
  read_format                      ID
  disabled                         1
  inherit                          1
  exclude_kernel                   1
  exclude_hv                       1
  freq                             1
  sample_id_all                    1

After:

  perf kvm --guest record -e cycles:u -vvv

perf_event_attr:
  size                             120
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|ID|CPU|PERIOD
  read_format                      ID
  disabled                         1
  inherit                          1
  exclude_kernel                   1
  exclude_hv                       1
  freq                             1
  sample_id_all                    1

For Before/After, exclude_guest are both 0 for perf kvm usage.

perf test 6

 6: Parse event definition strings             : Ok

Signed-off-by: Jin Yao 
Tested-by: Like Xu 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Peter Zijlstra 
Link: http://lore.kernel.org/lkml/20200814012120.16647-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix term parsing for raw syntax

2020-07-30T10:01:48+00:00

Jin Yao reported issue with possible conflict between raw events and
term values in pmu event syntax.

Currently following syntax is resolved as raw event with 0xead value:

  uncore_imc_free_running/read/

instead of using 'read' term from uncore_imc_free_running pmu, because
'read' is correct raw event syntax with 0xead value.

To solve this issue we do following:

  - check existing terms during rXXXX syntax processing
    and make them priority in case of conflict

  - allow pmu/r0x1234/ syntax to be able to specify conflicting
    raw event (implemented in previous patch)

Also add automated tests for this and perf_pmu__parse_cleanup call to
parse_events_terms, so the test gets properly cleaned up.

Fixes: 3a6c51e4d66c ("perf parser: Add support to specify rXXX event with pmu")
Reported-by: Jin Yao 
Signed-off-by: Jiri Olsa 
Tested-by: Jin Yao 
Acked-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Thomas Richter 
Link: http://lore.kernel.org/lkml/20200726075244.1191481-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Report BPF errors

2020-07-10T12:33:42+00:00

Setting the parse_events_error directly doesn't increment num_errors
causing the error message not to be displayed. Use the
parse_events__handle_error function that sets num_errors and handle
multiple errors.

Committer notes:

Ian provided a before/after upon request:

Before:

  $ /tmp/perf/perf record -e /tmp/perf/util/parse-events.o
  Run 'perf list' for a list of valid events

  Usage: perf record [] []
     or: perf record [] --  []

     -e, --event    event selector. use 'perf list' to list available event

After:

  $ /tmp/perf/perf record -e /tmp/perf/util/parse-events.o
  event syntax error: '/tmp/perf/util/parse-events.o'
                      \___ Failed to load /tmp/perf/util/parse-events.o: BPF object format invalid

  (add -v to see detail)
  Run 'perf list' for a list of valid events

  Usage: perf record [] []
     or: perf record [] --  []

     -e, --event    event selector. use 'perf list' to list available events

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Alexei Starovoitov 
Cc: Andrii Nakryiko 
Cc: bpf@vger.kernel.org
Cc: Daniel Borkmann 
Cc: John Fastabend 
Cc: KP Singh 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Martin KaFai Lau 
Cc: Namhyung Kim 
Cc: netdev@vger.kernel.org
Cc: Peter Zijlstra 
Cc: Song Liu 
Cc: Stephane Eranian 
Cc: Yonghong Song 
Link: http://lore.kernel.org/lkml/20200707211449.3868944-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo