linux-toradex.git/tools/lib/perf, branch v5.19-rc4

libperf evsel: Open shouldn't leak fd on failure

2022-06-19T13:41:43+00:00

If perf_event_open() fails the fd is opened but it is only freed by
closing (not by delete).

Typically when an open fails you don't call close and so this results in
a memory leak. To avoid this, add a close when open fails.

Signed-off-by: Ian Rogers 
Reviewed-By: Kajol Jain 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Anshuman Khandual 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Rob Herring 
Cc: Stephane Eranian 
Link: https://lore.kernel.org/r/20220609052355.1300162-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Allow system-wide events to keep their own threads

2022-05-26T15:36:57+00:00

System-wide events do not have threads, so do not propagate threads to
them.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-16-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Allow system-wide events to keep their own CPUs

2022-05-26T15:36:57+00:00

Currently, user_requested_cpus supplants system-wide CPUs when the evlist
has_user_cpus. Change that so that system-wide events retain their own
CPUs and they are added to all_cpus.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-15-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

libperf evsel: Add comments for booleans

2022-05-26T15:36:57+00:00

Add comments for 'system_wide' and 'requires_cpu' booleans

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Ian Rogers 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-14-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Add requires_cpu flag for uncore

2022-05-26T15:36:57+00:00

Uncore events require a CPU i.e. it cannot be -1.

The evsel system_wide flag is intended for events that should be on every
CPU, which does not make sense for uncore events because uncore events do
not map one-to-one with CPUs.

These 2 requirements are not exactly the same, so introduce a new flag
'requires_cpu' for the uncore case.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-13-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

libperf evlist: Check nr_mmaps is correct

2022-05-26T15:36:57+00:00

Print an error message if the predetermined number of mmaps is
incorrect.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-12-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

libperf evlist: Allow mixing per-thread and per-cpu mmaps

2022-05-26T15:36:57+00:00

mmap_per_evsel() will skip events that do not match the CPU, so all CPUs
can be iterated in any case.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-11-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Allow all_cpus to be a superset of user_requested_cpus

2022-05-26T15:36:57+00:00

To support collection of system-wide events with user requested CPUs,
all_cpus must be a superset of user_requested_cpus.

In order to support all_cpus to be a superset of user_requested_cpus,
all_cpus must be used instead of user_requested_cpus when dealing with CPUs
of all events instead of CPUs of requested events.

Signed-off-by: Adrian Hunter 
Acked-by: Ian Rogers 
Acked-by: Namhyung Kim 
Cc: Alexey Bayduraev 
Cc: Jiri Olsa 
Cc: Leo Yan 
Link: https://lore.kernel.org/r/20220524075436.29144-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

libperf: Add preadn()

2022-05-23T13:11:12+00:00

Add preadn() to provide pread() and readn() semantics.

Signed-off-by: Adrian Hunter 
Acked-by: Jiri Olsa 
Cc: Namhyung Kim 
Link: https://lore.kernel.org/r/ab8918a4-7ac8-a37e-2e2c-28438c422d87@intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cpumap: Add perf_cpu_map__for_each_idx()

2022-05-23T12:52:38+00:00

A variant of perf_cpu_map__for_each_cpu() that just iterates index values
without the corresponding load of the CPU.

Signed-off-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Alexei Starovoitov 
Cc: Andrii Nakryiko 
Cc: Daniel Borkmann 
Cc: Dave Marchevsky 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Fastabend 
Cc: KP Singh 
Cc: Kan Liang 
Cc: Lv Ruyi 
Cc: Mark Rutland 
Cc: Martin KaFai Lau 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Quentin Monnet 
Cc: Song Liu 
Cc: Stephane Eranian 
Cc: Xing Zhengjun 
Cc: Yonghong Song 
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20220519032005.1273691-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo