kernel/linux.git/tools/lib/perf/evlist.c, branch v5.18.2

perf tools: Fix segfault accessing sample_id xyarray

2022-04-14T01:23:02+00:00

perf_evsel::sample_id is an xyarray which can cause a segfault when accessed beyond its size. e.g. # perf record -e intel_pt// -C 1 sleep 1 Segmentation fault (core dumped) # That is happening because a dummy event is opened to capture text poke events accross all CPUs, however the mmap logic is allocating according to the number of user_requested_cpus. In general, perf sometimes uses the evsel cpus to open events, and sometimes the evlist user_requested_cpus. However, it is not necessary to determine which case is which because the opened event file descriptors are also in an xyarray, the size of whch can be used to correctly allocate the size of the sample_id xyarray, because there is one ID per file descriptor. Note, in the affected code path, perf_evsel fd array is subsequently used to get the file descriptor for the mmap, so it makes sense for the xyarrays to be the same size there. Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf") Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE") Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org # 5.5+ Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Rename cpus to user_requested_cpus

2022-04-01T19:19:35+00:00

evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps of all evsels. For non-task targets, cpus is set to be cpus requested from the command line, defaulting to all online cpus if no cpus are specified. For an uncore event, all_cpus may be just CPU 0 or every online CPU. This causes all_cpus to have fewer values than the cpus variable which is confusing given the 'all' in the name. To try to make the behavior clearer, rename cpus to user_requested_cpus and add comments on the two struct variables. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Antonov Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrii Nakryiko Cc: Daniel Borkmann Cc: German Gomez Cc: James Clark Cc: Jiri Olsa Cc: John Fastabend Cc: John Garry Cc: KP Singh Cc: Kajol Jain Cc: Leo Yan Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Song Liu Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yonghong Song Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf cpumap: Give CPUs their own type

2022-01-12T17:28:23+00:00

A common problem is confusing CPU map indices with the CPU, by wrapping the CPU with a struct then this is avoided. This approach is similar to atomic_t. Committer notes: To make it build with BUILD_BPF_SKEL=1 these files needed the conversions to 'struct perf_cpu' usage: tools/perf/util/bpf_counter.c tools/perf/util/bpf_counter_cgroup.c tools/perf/util/bpf_ftrace.c Also perf_env__get_cpu() was removed back in "perf cpumap: Switch cpu_map__build_map to cpu function". Additionally these needed to be fixed for the ARM builds to complete: tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/pmu.c Suggested-by: John Garry Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Vineet Singh Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220105061351.120843-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Allow setting arbitrary leader

2021-12-08T01:18:24+00:00

The leader of a group is the first, but allow it to be an arbitrary list member so that for Intel topdown events slots may always be the group leader. Reviewed-by: Kajol Jain Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Vineet Singh Link: http://lore.kernel.org/lkml/20211130174945.247604-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

libperf: Adopt evlist__set_leader() from tools/perf as perf_evlist__set_leader()

2021-07-09T17:04:32+00:00

Move the implementation of evlist__set_leader() to a new libperf perf_evlist__set_leader() function with the same functionality make it a libperf exported API. Signed-off-by: Jiri Olsa Requested-by: Shunsuke Nakamura Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210706151704.73662-6-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

libperf: Move 'idx' from tools/perf to perf_evsel::idx

2021-07-09T17:04:28+00:00

Move evsel::idx to perf_evsel::idx, so we can move the group interface to libperf. Committer notes: Fixup evsel->idx usage in tools/perf/util/bpf_counter_cgroup.c, that appeared in my tree in my local tree. Also fixed up these: $ find tools/perf/ -name "*.[ch]" | xargs grep 'evsel->idx' tools/perf/ui/gtk/annotate.c: evsel->idx + i); tools/perf/ui/gtk/annotate.c: evsel->idx); $ That running 'make -C tools/perf build-test' caught. Signed-off-by: Jiri Olsa Requested-by: Shunsuke Nakamura Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210706151704.73662-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

libperf: Add perf_evlist__reset_id_hash()

2021-03-06T19:54:31+00:00

Add the perf_evlist__reset_id_hash() function as an internal function so that it can be called by perf to reset the hash table. This is necessary for 'perf stat' to run the workload multiple times. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210225035148.778569-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Fix id index for heterogeneous systems

2021-01-21T20:25:33+00:00

perf_evlist__set_sid_idx() updates perf_sample_id with the evlist map index, CPU number and TID. It is passed indexes to the evsel's cpu and thread maps, but references the evlist's maps instead. That results in using incorrect CPU numbers on heterogeneous systems. Fix it by using evsel maps. The id index (PERF_RECORD_ID_INDEX) is used by AUX area tracing when in sampling mode. Having an incorrect CPU number causes the trace data to be attributed to the wrong CPU, and can result in decoder errors because the trace data is then associated with the wrong process. Committer notes: Keep the class prefix convention in the function name, switching from perf_evlist__set_sid_idx() to perf_evsel__set_sid_idx(). Fixes: 3c659eedada2fbf9 ("perf tools: Add id index") Signed-off-by: Adrian Hunter Cc: Jin Yao Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20210121125446.11287-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Fix out of bounds CPU map access when handling armv8_pmu events

2020-10-07T12:57:58+00:00

It was reported that 'perf stat' crashed when using with armv8_pmu (CPU) events with the task mode. As 'perf stat' uses an empty cpu map for task mode but armv8_pmu has its own cpu mask, it has confused which map it should use when accessing file descriptors and this causes segfaults: (gdb) bt #0 0x0000000000603fc8 in perf_evsel__close_fd_cpu (evsel=, cpu=) at evsel.c:122 #1 perf_evsel__close_cpu (evsel=evsel@entry=0x716e950, cpu=7) at evsel.c:156 #2 0x00000000004d4718 in evlist__close (evlist=0x70a7cb0) at util/evlist.c:1242 #3 0x0000000000453404 in __run_perf_stat (argc=3, argc@entry=1, argv=0x30, argv@entry=0xfffffaea2f90, run_idx=119, run_idx@entry=1701998435) at builtin-stat.c:929 #4 0x0000000000455058 in run_perf_stat (run_idx=1701998435, argv=0xfffffaea2f90, argc=1) at builtin-stat.c:947 #5 cmd_stat (argc=1, argv=0xfffffaea2f90) at builtin-stat.c:2357 #6 0x00000000004bb888 in run_builtin (p=p@entry=0x9764b8 , argc=argc@entry=4, argv=argv@entry=0xfffffaea2f90) at perf.c:312 #7 0x00000000004bbb54 in handle_internal_command (argc=argc@entry=4, argv=argv@entry=0xfffffaea2f90) at perf.c:364 #8 0x0000000000435378 in run_argv (argcp=, argv=) at perf.c:408 #9 main (argc=4, argv=0xfffffaea2f90) at perf.c:538 To fix this, I simply used the given cpu map unless the evsel actually is not a system-wide event (like uncore events). Fixes: 7736627b865d ("perf stat: Use affinity for closing file descriptors") Reported-by: Wei Li Signed-off-by: Namhyung Kim Tested-by: Barry Song Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20201007081311.1831003-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

libperf: Add flags to fdarray fds objects

2020-07-21T12:52:51+00:00

Store flags per struct pollfd *entries object in a bitmap of int size. Implement fdarray_flag__nonfilterable flag to skip object from counting by fdarray__filter(). Fixed fdarray test issue reported by kernel test robot. Reported-by: kernel test robot Signed-off-by: Alexey Budankov Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/6b7d43ff-0801-d5dd-4e90-fcd86b17c1c8@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo