kernel/linux.git/tools/lib/perf/evlist.c, branch v6.19.11

perf parse-events: Support user CPUs mixed with threads/processes

2025-07-24T20:41:35+00:00

Counting events system-wide with a specified CPU prior to this change worked: ``` $ perf stat -e 'msr/tsc/,msr/tsc,cpu=cpu_core/,msr/tsc,cpu=cpu_atom/' -a sleep 1 Performance counter stats for 'system wide': 59,393,419,099 msr/tsc/ 33,927,965,927 msr/tsc,cpu=cpu_core/ 25,465,608,044 msr/tsc,cpu=cpu_atom/ ``` However, when counting with process the counts became system wide: ``` $ perf stat -e 'msr/tsc/,msr/tsc,cpu=cpu_core/,msr/tsc,cpu=cpu_atom/' perf test -F 10 10.1: Basic parsing test : Ok 10.2: Parsing without PMU name : Ok 10.3: Parsing with PMU name : Ok Performance counter stats for 'perf test -F 10': 59,233,549 msr/tsc/ 59,227,556 msr/tsc,cpu=cpu_core/ 59,224,053 msr/tsc,cpu=cpu_atom/ ``` Make the handling of CPU maps with event parsing clearer. When an event is parsed creating an evsel the cpus should be either the PMU's cpumask or user specified CPUs. Update perf_evlist__propagate_maps so that it doesn't clobber the user specified CPUs. Try to make the behavior clearer, firstly fix up missing cpumasks. Next, perform sanity checks and adjustments from the global evlist CPU requests and for the PMU including simplifying to the "any CPU"(-1) value. Finally remove the event if the cpumask is empty. So that events are opened with a CPU and a thread change stat's create_perf_stat_counter to give both. With the change things are fixed: ``` $ perf stat --no-scale -e 'msr/tsc/,msr/tsc,cpu=cpu_core/,msr/tsc,cpu=cpu_atom/' perf test -F 10 10.1: Basic parsing test : Ok 10.2: Parsing without PMU name : Ok 10.3: Parsing with PMU name : Ok Performance counter stats for 'perf test -F 10': 63,704,975 msr/tsc/ 47,060,704 msr/tsc,cpu=cpu_core/ (4.62%) 16,640,591 msr/tsc,cpu=cpu_atom/ (2.18%) ``` However, note the "--no-scale" option is used. This is necessary as the running time for the event on the counter isn't the same as the enabled time because the thread doesn't necessarily run on the CPUs specified for the counter. All counter values are scaled with: scaled_value = value * time_enabled / time_running and so without --no-scale the scaled_value becomes very large. This problem already exists on hybrid systems for the same reason. Here are 2 runs of the same code with an instructions event that counts the same on both types of core, there is no real multiplexing happening on the event: ``` $ perf stat -e instructions perf test -F 10 ... Performance counter stats for 'perf test -F 10': 87,896,447 cpu_atom/instructions/ (14.37%) 98,171,964 cpu_core/instructions/ (85.63%) ... $ perf stat --no-scale -e instructions perf test -F 10 ... Performance counter stats for 'perf test -F 10': 13,069,890 cpu_atom/instructions/ (19.32%) 83,460,274 cpu_core/instructions/ (80.68%) ... ``` The scaling has inflated per-PMU instruction counts and the overall count by 2x. To fix this the kernel needs changing when a task+CPU event (or just task event on hybrid) is scheduled out. A fix could be that the state isn't inactive but off for such events, so that time_enabled counts don't accumulate on them. Reviewed-by: Thomas Falcon Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250719030517.1990983-13-irogers@google.com Signed-off-by: Namhyung Kim

libperf evsel: Rename own_cpus to pmu_cpus

2025-07-24T20:41:35+00:00

own_cpus is generally the cpumask from the PMU. Rename to pmu_cpus to try to make this clearer. Variable rename with no other changes. Reviewed-by: Thomas Falcon Signed-off-by: Ian Rogers Tested-by: James Clark Link: https://lore.kernel.org/r/20250719030517.1990983-7-irogers@google.com Signed-off-by: Namhyung Kim

Merge remote-tracking branch 'torvalds/master' into perf-tools-next

2024-12-13T14:53:27+00:00

To get the fixes that went thru perf-tools for v6.13. Signed-off-by: Arnaldo Carvalho de Melo

libperf: evlist: Fix --cpu argument on hybrid platform

2024-12-11T17:19:44+00:00

Since the linked fixes: commit, specifying a CPU on hybrid platforms results in an error because Perf tries to open an extended type event on "any" CPU which isn't valid. Extended type events can only be opened on CPUs that match the type. Before (working): $ perf record --cpu 1 -- true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.385 MB perf.data (7 samples) ] After (not working): $ perf record -C 1 -- true WARNING: A requested CPU in '1' is not supported by PMU 'cpu_atom' (CPUs 16-27) for event 'cycles:P' Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cpu_atom/cycles:P/). /bin/dmesg | grep -i perf may provide additional information. (Ignore the warning message, that's expected and not particularly relevant to this issue). This is because perf_cpu_map__intersect() of the user specified CPU (1) and one of the PMU's CPUs (16-27) correctly results in an empty (NULL) CPU map. However for the purposes of opening an event, libperf converts empty CPU maps into an any CPU (-1) which the kernel rejects. Fix it by deleting evsels with empty CPU maps in the specific case where user requested CPU maps are evaluated. Fixes: 251aa040244a ("perf parse-events: Wildcard most "numeric" events") Reviewed-by: Ian Rogers Tested-by: Thomas Falcon Signed-off-by: James Clark Tested-by: Arnaldo Carvalho de Melo Link: https://lore.kernel.org/r/20241114160450.295844-2-james.clark@linaro.org Signed-off-by: Namhyung Kim

libperf cpumap: Refactor perf_cpu_map__merge()

2024-12-09T20:52:41+00:00

The perf_cpu_map__merge() function has two arguments, 'orig' and 'other'. The function definition might cause confusion as it could give the impression that the CPU maps in the two arguments are copied into a new allocated structure, which is then returned as the result. The purpose of the function is to merge the CPU map 'other' into the CPU map 'orig'. This commit changes the 'orig' argument to a pointer to pointer, so the new result will be updated into 'orig'. The return value is changed to an int type, as an error number or 0 for success. Update callers and tests for the new function definition. Reviewed-by: Adrian Hunter Signed-off-by: Leo Yan Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Ian Rogers Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/r/20241107125308.41226-2-leo.yan@arm.com Signed-off-by: Arnaldo Carvalho de Melo

libperf evlist: Avoid out-of-bounds access

2024-02-29T21:57:02+00:00

Parallel testing appears to show a race between allocating and setting evsel ids. As there is a bounds check on the xyarray it yields a segv like: ``` AddressSanitizer:DEADLYSIGNAL ================================================================= ==484408==ERROR: AddressSanitizer: SEGV on unknown address 0x000000000010 ==484408==The signal is caused by a WRITE memory access. ==484408==Hint: address points to the zero page. #0 0x55cef5d4eff4 in perf_evlist__id_hash tools/lib/perf/evlist.c:256 #1 0x55cef5d4f132 in perf_evlist__id_add tools/lib/perf/evlist.c:274 #2 0x55cef5d4f545 in perf_evlist__id_add_fd tools/lib/perf/evlist.c:315 #3 0x55cef5a1923f in store_evsel_ids util/evsel.c:3130 #4 0x55cef5a19400 in evsel__store_ids util/evsel.c:3147 #5 0x55cef5888204 in __run_perf_stat tools/perf/builtin-stat.c:832 #6 0x55cef5888c06 in run_perf_stat tools/perf/builtin-stat.c:960 #7 0x55cef58932db in cmd_stat tools/perf/builtin-stat.c:2878 ... ``` Avoid this crash by early exiting the perf_evlist__id_add_fd and perf_evlist__id_add is the access is out-of-bounds. Signed-off-by: Ian Rogers Cc: Yang Jihong Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240229070757.796244-1-irogers@google.com

libperf cpumap: Replace usage of perf_cpu_map__new(NULL) with perf_cpu_map__new_online_cpus()

2023-12-12T17:55:13+00:00

Passing NULL to perf_cpu_map__new() performs perf_cpu_map__new_online_cpus(), just directly call perf_cpu_map__new_online_cpus() to be more intention revealing. Reviewed-by: James Clark Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andrew Jones Cc: André Almeida Cc: Athira Jajeev Cc: Atish Patra Cc: Changbin Du Cc: Darren Hart Cc: Davidlohr Bueso Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: K Prateek Nayak Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Paolo Bonzini Cc: Paran Lee Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Suzuki Poulouse Cc: Thomas Gleixner Cc: Will Deacon Cc: Yang Jihong Cc: Yang Li Cc: Yanteng Si Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20231129060211.1890454-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

libperf cpumap: Rename perf_cpu_map__empty() to perf_cpu_map__has_any_cpu_or_is_empty()

2023-12-12T17:55:13+00:00

The name perf_cpu_map_empty is misleading as true is also returned when the map contains an "any" CPU (aka dummy) map. Rename to perf_cpu_map__has_any_cpu_or_is_empty(), later changes will (re)introduce perf_cpu_map__empty() and perf_cpu_map__has_any_cpu(). Reviewed-by: James Clark Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andrew Jones Cc: André Almeida Cc: Athira Jajeev Cc: Atish Patra Cc: Changbin Du Cc: Darren Hart Cc: Davidlohr Bueso Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: K Prateek Nayak Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Paolo Bonzini Cc: Paran Lee Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Suzuki Poulouse Cc: Thomas Gleixner Cc: Will Deacon Cc: Yang Jihong Cc: Yang Li Cc: Yanteng Si Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20231129060211.1890454-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Add perf_evlist__go_system_wide() helper

2023-09-12T20:31:22+00:00

For dummy events that keep tracking, we may need to modify its cpu_maps. For example, change the cpu_maps to record sideband events for all CPUS. Add perf_evlist__go_system_wide() helper to support this scenario. Signed-off-by: Yang Jihong Acked-by: Adrian Hunter Tested-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Andi Kleen Cc: Anshuman Khandual Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Link: https://lore.kernel.org/r/20230904023340.12707-2-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Propagate user CPU maps intersecting core PMU maps

2023-05-27T12:38:39+00:00

The CPU map for a non-core PMU gives a default CPU value for perf_event_open. For core PMUs the CPU map lists all CPUs the evsel may be opened on. If there are >1 core PMU, the CPU maps will list the CPUs for that core PMU, but the user_requested_cpus may contain CPUs that are invalid for the PMU and cause perf_event_open to fail. To avoid this, when propagating the CPU map for core PMUs intersect it with the CPU map of the PMU (the evsel's "own_cpus"). Add comments to __perf_evlist__propagate_maps to explain its somewhat complex behavior. Fix the related comments for system_wide in struct perf_evsel. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ali Saidi Cc: Athira Rajeev Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Mike Leach Cc: Ming Wang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sandipan Das Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo