linux.git/tools/perf/util/parse-events.c, branch v6.12

perf pmus: Fake PMU clean up

2024-09-11T14:27:42+00:00

Rather than passing a fake PMU around, just pass that the fake PMU
should be used - true when doing testing. Move the fake PMU into
pmus.[ch] and try to abstract the PMU's properties in pmu.c, ie so
there is less "if fake_pmu" in non-PMU code. Give the fake PMU a made
up type number.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Athira Rajeev 
Cc: Benjamin Gray 
Cc: Changbin Du 
Cc: Clément Le Goffic 
Cc: Colin Ian King 
Cc: Dominique Martinet 
Cc: Dr. David Alan Gilbert 
Cc: Howard Chu 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jing Zhang 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Junhao He 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Oliver Upton 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Sun Haiyong 
Cc: Tiezhu Yang 
Cc: Veronika Molnarova 
Cc: Weilin Wang 
Cc: Will Deacon 
Cc: Xu Yang 
Cc: Yang Jihong 
Cc: Yicong Yang 
Cc: Ze Gao 
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20240907050830.6752-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Vary default_breakpoint_len on i386 and arm64

2024-09-04T12:50:46+00:00

On arm64 the breakpoint length should be 4-bytes but 8-bytes is
tolerated as perf passes that as sizeof(long). Just pass the correct
value.

On i386 the sizeof(long) check in the kernel needs to match the
kernel's long size. Check using an environment (uname checks) whether
4 or 8 bytes needs to be passed. Cache the value in a static.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Athira Rajeev 
Cc: Chaitanya S Prakash 
Cc: Colin Ian King 
Cc: Dominique Martinet 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Junhao He 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Masami Hiramatsu 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Yang Jihong 
Link: https://lore.kernel.org/r/20240904050606.752788-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Add default_breakpoint_len helper

2024-09-04T12:49:09+00:00

The default breakpoint length is "sizeof(long)" however this is
incorrect on platforms like Aarch64 where sizeof(long) is 8 but the
breakpoint length is 4. Add a helper function that can be used to
determine the correct breakpoint length, in this change it just
returns the existing default sizeof(long) value.

Use the helper in the bp_account test so that, when modifying the
event from a watchpoint to a breakpoint, the breakpoint length is
appropriate for the architecture and not just sizeof(long).

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Athira Rajeev 
Cc: Chaitanya S Prakash 
Cc: Colin Ian King 
Cc: Dominique Martinet 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Junhao He 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Masami Hiramatsu 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Yang Jihong 
Link: https://lore.kernel.org/r/20240904050606.752788-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Pass cpu_list as a perf_cpu_map in __add_event()

2024-09-03T19:45:34+00:00

Previously the cpu_list is a string and typically no cpu_list is
passed to __add_event().

Wanting to make events have their cpus distinct from the PMU means that
in more occassions we want to pass a cpu_list.

If we're reading this from sysfs it is easier to read a perf_cpu_map
than allocate and pass around strings that will later be parsed.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ananth Narayan 
Cc: Bjorn Helgaas 
Cc: Dhananjay Ugwekar 
Cc: Dominique Martinet 
Cc: Gautham Shenoy 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Jonathan Corbet 
Cc: K Prateek Nayak 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Link: https://lore.kernel.org/r/20240718003025.1486232-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Add a retirement latency modifier

2024-08-12T21:15:27+00:00

Retirement latency is a separate sampled count used on newer Intel
CPUs.

Reviewed-by: Namhyung Kim 
Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Caleb Biggers 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Samantha Alt 
Link: https://lore.kernel.org/r/20240720062102.444578-2-weilin.wang@intel.com
Signed-off-by: Weilin Wang 
Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Refactor tool events

2024-06-10T23:45:10+00:00

Tool events unnecessarily open a dummy perf event which is useless
even with `perf record` which will still open a dummy event. Change
the behavior of tool events so:

 - duration_time - call `rdclock` on open and then report the count as
   a delta since the start in evsel__read_counter. This moves code out
   of builtin-stat making it more general purpose.

 - user_time/system_time - open the fd as either `/proc/pid/stat` or
   `/proc/stat` for cases like system wide. evsel__read_counter will
   read the appropriate field out of the procfs file. These values
   were previously supplied by wait4, if the procfs read fails then
   the wait4 values are used, assuming the process/thread terminated.
   By reading user_time and system_time this way, interval mode, per
   PID and per CPU can be supported although there are restrictions
   given what the files provide (e.g. per PID can't be combined with
   per CPU).

Opening any of the tool events for `perf record` is changed to return
invalid.

Signed-off-by: Ian Rogers 
Tested-by: Weilin Wang 
Cc: Ravi Bangoria 
Cc: James Clark 
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Ze Gao 
Cc: Song Liu 
Cc: Leo Yan 
Signed-off-by: Namhyung Kim 
Link: https://lore.kernel.org/r/20240503232849.17752-1-irogers@google.com

perf: parse-events: Fix compilation error while defining DEBUG_PARSER

2024-06-06T07:19:36+00:00

Compiling perf tool with 'DEBUG_PARSER=1' leads to errors:

$> make -C tools/perf PARSER_DEBUG=1 NO_LIBTRACEEVENT=1
...
  CC      util/expr-flex.o
  CC      util/expr.o
util/parse-events.c:33:12: error: redundant redeclaration of ‘parse_events_debug’ [-Werror=redundant-decls]
   33 | extern int parse_events_debug;
      |            ^~~~~~~~~~~~~~~~~~
In file included from util/parse-events.c:18:
util/parse-events-bison.h:43:12: note: previous declaration of ‘parse_events_debug’ with type ‘int’
   43 | extern int parse_events_debug;
      |            ^~~~~~~~~~~~~~~~~~
util/expr.c:27:12: error: redundant redeclaration of ‘expr_debug’ [-Werror=redundant-decls]
   27 | extern int expr_debug;
      |            ^~~~~~~~~~
In file included from util/expr.c:11:
util/expr-bison.h:43:12: note: previous declaration of ‘expr_debug’ with type ‘int’
   43 | extern int expr_debug;
      |            ^~~~~~~~~~
cc-1: all warnings being treated as errors

Remove extern declaration from the parse-envents.c file as there is a
conflict with the ones generated using bison and yacc tools from the file
parse-events.[ly].

Signed-off-by: Clément Le Goffic 
Reviewed-by: Ian Rogers 
Cc: James Clark 
Cc: John Garry 
Signed-off-by: Namhyung Kim 
Link: https://lore.kernel.org/r/20240605140453.614862-1-clement.legoffic@foss.st.com

Revert "perf parse-events: Prefer sysfs/JSON hardware events over legacy"

2024-05-26T11:41:34+00:00

This reverts commit 617824a7f0f73e4de325cf8add58e55b28c12493.

This made a simple 'perf record -e cycles:pp make -j199' stop working on
the Ampere ARM64 system Linus uses to test ARM64 kernels, as discussed
at length in the threads in the Link tags below.

The fix provided by Ian wasn't acceptable and work to fix this will take
time we don't have at this point, so lets revert this and work on it on
the next devel cycle.

Reported-by: Linus Torvalds 
Cc: Adrian Hunter 
Cc: Bhaskar Chowdhury 
Cc: Ethan Adams 
Cc: Ian Rogers 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Namhyung Kim 
Cc: Thomas Gleixner 
Cc: Thomas Richter 
Cc: Tycho Andersen 
Cc: Yang Jihong 
Link: https://lore.kernel.org/lkml/CAHk-=wi5Ri=yR2jBVk-4HzTzpoAWOgstr1LEvg_-OXtJvXXJOA@mail.gmail.com
Link: https://lore.kernel.org/lkml/CAHk-=wiWvtFyedDNpoV7a8Fq_FpbB+F5KmWK2xPY3QoYseOf_A@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Add new 'fake_tp' parameter for tests

2024-05-10T13:49:26+00:00

The next commit will allow tracepoints starting with digits, but most
systems do not have any available by default so tests should skip the
actual "check if it exists in /sys/kernel/debug/tracing" step.

In order to do that, add a new boolean flag specifying if we should
actually "format" the probe or not.

Originally-by: Jiri Olsa 
Reviewed-by: Ian Rogers 
Signed-off-by: Dominique Martinet 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Link: https://lore.kernel.org/r/20240510-perf_digit-v4-2-db1553f3233b@codewreck.org
Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: pass parse_state to add_tracepoint

2024-05-10T13:49:09+00:00

The next patch will add another flag to parse_state that we will want to
pass to evsel__newtp_idx(), so pass the whole parse_state all the way
down instead of giving only the index

Originally-by: Jiri Olsa 
Reviewed-by: Ian Rogers 
Signed-off-by: Dominique Martinet 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Link: https://lore.kernel.org/r/20240510-perf_digit-v4-1-db1553f3233b@codewreck.org
Signed-off-by: Arnaldo Carvalho de Melo