linux.git/tools/perf/Documentation, branch v5.16

perf arm-spe: Update --switch-events docs in 'perf record'

2021-11-13T21:11:50+00:00

Update 'perf record' docs and ARM SPE recording options so that they are
consistent. This includes supporting the --no-switch-events flag in ARM
SPE as well.

Reviewed-by: Leo Yan 
Signed-off-by: German Gomez 
Acked-by: Namhyung Kim 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Will Deacon 
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211111133625.193568-3-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf inject: Add vmlinux and ignore-vmlinux arguments

2021-11-07T15:27:38+00:00

Other perf tools allow specifying the path to vmlinux. 'perf inject'
didn't have this argument which made some auxtrace workflows difficult.

Also add --ignore-vmlinux for consistency with other tools.

Suggested-by: Denis Nikitin 
Signed-off-by: James Clark 
Tested-by: Denis Nikitin 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Link: https://lore.kernel.org/r/20211018134844.2627174-4-james.clark@arm.com
[ Added the perf-inject man page entries for these options, as noted by Denis ]
Signed-off-by: Arnaldo Carvalho de Melo

perf bpf: Pull in bpf_program__get_prog_info_linear()

2021-11-01T21:16:40+00:00

To prepare for impending deprecation of libbpf's bpf_program__get_prog_info_linear(),
pull in the function and associated helpers into the perf codebase and migrate
existing uses to the perf copy.

Since libbpf's deprecated definitions will still be visible to perf, it is necessary
to rename perf's definitions.

Signed-off-by: Dave Marchevsky 
Acked-by: Andrii Nakryiko 
Acked-by: Song Liu 
Cc: Alexei Starovoitov 
Cc: Daniel Borkmann 
Cc: Ingo Molnar 
Cc: Peter Zijlstra 
Link: https://lore.kernel.org/r/20211011082031.4148337-4-davemarchevsky@fb.com
Signed-off-by: Arnaldo Carvalho de Melo

perf script: Support instruction latency

2021-10-28T12:28:03+00:00

The instruction latency information can be recorded on
some platforms, e.g., the Intel Sapphire Rapids server. With both memory
latency (weight) and the new instruction latency information, users can
easily locate the expensive load instructions, and also understand the time
spent in different stages. The users can optimize their applications in
different pipeline stages.

Add a new field "ins_lat" to filter the instruction latency information,
which is available with sample type PERF_SAMPLE_WEIGHT_STRUCT.

Signed-off-by: Kan Liang 
Cc: Andi Kleen 
Cc: Jiri Olsa 
Cc: Joe Mario 
Link: https://lore.kernel.org/r/1632929894-102778-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf intel-pt: Support itrace d+o option to direct debug log to stdout

2021-10-27T19:21:01+00:00

It can be useful to see debug output in between normal output.

Add support for AUXTRACE_LOG_FLG_USE_STDOUT to Intel PT.

Reviewed-by: Andi Kleen 
Signed-off-by: Adrian Hunter 
Cc: Jiri Olsa 
Link: https://lore.kernel.org/r/20211027080334.365596-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf auxtrace: Add itrace d+o option to direct debug log to stdout

2021-10-27T19:20:45+00:00

It can be useful to see debug output in between normal output.

Add 'o' to the flags of debug option 'd', so that '--itrace=d+o' can
specify output of the debug log to stdout.

Reviewed-by: Andi Kleen 
Signed-off-by: Adrian Hunter 
Cc: Jiri Olsa 
Link: https://lore.kernel.org/r/20211027080334.365596-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf dlfilter: Add dlfilter-show-cycles

2021-10-27T19:20:30+00:00

Add a new dlfilter to show cycles.

Cycle counts are accumulated per CPU (or per thread if CPU is not recorded)
from IPC information, and printed together with the change since the last
print, at the start of each line. Separate counts are kept for branches,
instructions or other events.

Note also, the itrace A option can be useful to provide higher granularity
cycle information.

Example:

  $ perf record -e intel_pt/cyc/u uname
  Linux
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.044 MB perf.data ]
  $ perf script --itrace=A --call-trace --dlfilter dlfilter-show-cycles.so --deltatime | head
         0                   perf-exec  8509 [001]     0.000000000:  psb offs: 0
         0                   perf-exec  8509 [001]     0.000000000:  cbr: 42 freq: 4219 MHz (156%)
       833        833            uname  8509 [001]     0.000047689: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )        _start
       833                       uname  8509 [001]     0.000003261: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )            _dl_start
      2015       1182            uname  8509 [001]     0.000000282: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )            _dl_start
      2676        661            uname  8509 [001]     0.000002629: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )            _dl_start
      3612        936            uname  8509 [001]     0.000001232: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )            _dl_start
      4579        967            uname  8509 [001]     0.000002519: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )            _dl_start
      6145       1566            uname  8509 [001]     0.000001050: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )                _dl_setup_hash
      6239         94            uname  8509 [001]     0.000000023: (/usr/lib/x86_64-linux-gnu/ld-2.31.so              )                _dl_sysdep_start

Reviewed-by: Andi Kleen 
Signed-off-by: Adrian Hunter 
Cc: Jiri Olsa 
Link: https://lore.kernel.org/r/20211027080334.365596-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf intel-pt: Support itrace A option to approximate IPC

2021-10-27T19:20:18+00:00

Normally, for cycle-acccurate mode, IPC values are an exact number of
instructions and cycles. Due to the granularity of timestamps, that happens
only when a CYC packet correlates to the event.

Support the itrace 'A' option, to use instead, the number of cycles
associated with the current timestamp. This provides IPC information for
every change of timestamp, but at the expense of accuracy. Due to the
granularity of timestamps, the actual number of cycles increases even
though the cycles reported does not. The number of instructions is known,
but if IPC is reported, cycles can be too low and so IPC is too high. Note
that inaccuracy decreases as the period of sampling increases i.e. if the
number of cycles is too low by a small amount, that becomes less
significant if the number of cycles is large.

Furthermore, it can be used in conjunction with dlfilter-show-cycles.so
to provide higher granularity cycle information.

Reviewed-by: Andi Kleen 
Signed-off-by: Adrian Hunter 
Cc: Jiri Olsa 
Link: https://lore.kernel.org/r/20211027080334.365596-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf auxtrace: Add itrace A option to approximate IPC

2021-10-27T19:20:08+00:00

Add an option to specify that synthesized IPC can be approximate, rather
than completely accurate.

Reviewed-by: Andi Kleen 
Signed-off-by: Adrian Hunter 
Cc: Jiri Olsa 
Link: https://lore.kernel.org/r/20211027080334.365596-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf list: Display hybrid PMU events with cpu type

2021-10-25T16:47:42+00:00

Add a new option '--cputype' to 'perf list' to display core-only PMU
events or atom-only PMU events.

Each hybrid PMU event has been assigned with a PMU name, this patch
compares the PMU name before listing the result.

For example:

  perf list --cputype atom
  ...
  cache:
    core_reject_l2q.any
         [Counts the number of request that were not accepted into the L2Q because the L2Q is FULL. Unit: cpu_atom]
  ...

The "Unit: cpu_atom" is displayed in the brief description section
to indicate this is an atom event.

Signed-off-by: Jin Yao 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Peter Zijlstra 
Link: http://lore.kernel.org/lkml/20210903025239.22754-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo