linux-toradex.git/tools/perf/util/stat-shadow.c, branch v6.3

perf stat: Avoid merging/aggregating metric counts twice

2023-02-09T21:28:08+00:00

The added perf_stat_merge_counters combines uncore counters. When
metrics are enabled, the counts are merged into a metric_leader via the
stat-shadow saved_value logic. As the leader now is passed an aggregated
count, it leads to all counters being added together twice and counts
appearing approximately doubled in metrics.

This change disables the saved_value merging of counts for evsels that
are merged. It is recommended that later changes remove the saved_value
entirely as the two layers of aggregation in the code is confusing.

Fixes: 942c5593393d9418 ("perf stat: Add perf_stat_merge_counters()")
Reported-by: Perry Taylor 
Signed-off-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexander Shishkin 
Cc: Eduard Zingerman 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20230209064447.83733-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Remove evsel metric_name/expr

2023-02-03T16:54:21+00:00

Metrics are their own unit and these variables held broken metrics
previously and now just hold the value NULL. Remove code that used
these variables.

Reviewed-by: John Garry 
Reviewed-by: Kajol Jain 
Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Caleb Biggers 
Cc: Florian Fischer 
Cc: Ian Rogers 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jing Zhang 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Kang Minchul 
Cc: Kim Phillips 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Rob Herring 
Cc: Sandipan Das 
Cc: Stephane Eranian 
Cc: Will Deacon 
Cc: Xing Zhengjun 
Cc: linux-arm-kernel@lists.infradead.org
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230126233645.200509-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

Merge remote-tracking branch 'torvalds/master' into perf/core

2022-12-16T12:53:53+00:00

To resolve a trivial merge conflict with c302378bc157f6a7 ("libbpf:
Hashmap interface update to allow both long and void* keys/values"),
where a function present upstream was removed in the perf tools
development tree.

Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Tidy hashmap dependency

2022-11-16T15:17:15+00:00

hashmap.h comes from libbpf but isn't installed with its
headers. Always use the header file of the code in util. Change the
hashmap.h dependency in expr.h to a forward declaration, add the
necessary header file includes in the C files.

Signed-off-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexander Shishkin 
Cc: Andrii Nakryiko 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Masahiro Yamada 
Cc: Nick Desaulniers 
Cc: Nicolas Schier 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: bpf@vger.kernel.org
Link: http://lore.kernel.org/lkml/20221109184914.1357295-12-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

libbpf: Hashmap interface update to allow both long and void* keys/values

2022-11-10T04:45:14+00:00

An update for libbpf's hashmap interface from void* -> void* to a
polymorphic one, allowing both long and void* keys and values.

This simplifies many use cases in libbpf as hashmaps there are mostly
integer to integer.

Perf copies hashmap implementation from libbpf and has to be
updated as well.

Changes to libbpf, selftests/bpf and perf are packed as a single
commit to avoid compilation issues with any future bisect.

Polymorphic interface is acheived by hiding hashmap interface
functions behind auxiliary macros that take care of necessary
type casts, for example:

    #define hashmap_cast_ptr(p)						\
	({								\
		_Static_assert((p) == NULL || sizeof(*(p)) == sizeof(long),\
			       #p " pointee should be a long-sized integer or a pointer"); \
		(long *)(p);						\
	})

    bool hashmap_find(const struct hashmap *map, long key, long *value);

    #define hashmap__find(map, key, value) \
		hashmap_find((map), (long)(key), hashmap_cast_ptr(value))

- hashmap__find macro casts key and value parameters to long
  and long* respectively
- hashmap_cast_ptr ensures that value pointer points to a memory
  of appropriate size.

This hack was suggested by Andrii Nakryiko in [1].
This is a follow up for [2].

[1] https://lore.kernel.org/bpf/CAEf4BzZ8KFneEJxFAaNCCFPGqp20hSpS2aCj76uRk3-qZUH5xg@mail.gmail.com/
[2] https://lore.kernel.org/bpf/af1facf9-7bc8-8a3d-0db4-7b3f333589a2@meta.com/T/#m65b28f1d6d969fcd318b556db6a3ad499a42607d

Signed-off-by: Eduard Zingerman 
Signed-off-by: Andrii Nakryiko 
Link: https://lore.kernel.org/bpf/20221109142611.879983-2-eddyz87@gmail.com

perf stat: Don't compare runtime stat for shadow stats

2022-10-06T11:03:53+00:00

Now it always uses the global rt_stat.  Let's get rid of the field from
the saved_value.  When the both evsels are NULL, it'd return 0 so remove
the block in the saved_value_cmp.

Reviewed-by: James Clark 
Signed-off-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Peter Zijlstra 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20220930202110.845199-7-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Use thread map index for shadow stat

2022-10-06T11:03:53+00:00

When AGGR_THREAD is active, it aggregates the values for each thread.
Previously it used cpu map index which is invalid for AGGR_THREAD so
it had to use separate runtime stats with index 0.

But it can just use the rt_stat with thread_map_index.  Rename the
first_shadow_map_idx() and make it return the thread index.

Reviewed-by: James Clark 
Signed-off-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Peter Zijlstra 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20220930202110.845199-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Rename saved_value->cpu_map_idx

2022-10-06T11:03:53+00:00

The cpu_map_idx fields is just to differentiate values from other
entries.  It doesn't need to be strictly cpu map index.  Actually we can
pass thread map index or aggr map index.  So rename the fields first.

No functional change intended.

Signed-off-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Andi Kleen 
Cc: Ian Rogers 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Peter Zijlstra 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20220930202110.845199-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf metrics: Don't scale counts going into metrics

2022-10-06T11:03:52+00:00

Counts are scaled prior to going into saved_value, reverse the scaling
so that metrics don't double scale values.

Signed-off-by: Ian Rogers 
Cc: Ahmad Yasin 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Caleb Biggers 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Kshipra Bopardikar 
Cc: Mark Rutland 
Cc: Miaoqian Lin 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Samantha Alt 
Cc: Stephane Eranian 
Cc: Thomas Richter 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20221004021612.325521-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf metrics: Wire up core_wide

2022-10-04T11:55:22+00:00

Pass state necessary for core_wide into the expression parser. Add
system_wide and user_requested_cpu_list to perf_stat_config to make it
available at display time. evlist isn't used as the
evlist__create_maps, that computes user_requested_cpus, needs the list
of events which is generated by the metric.

Signed-off-by: Ian Rogers 
Cc: Ahmad Yasin 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Caleb Biggers 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Kan Liang 
Cc: Kshipra Bopardikar 
Cc: Mark Rutland 
Cc: Miaoqian Lin 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Thomas Richter 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20220831174926.579643-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo