diff options
Diffstat (limited to 'tools/lib/perf')
| -rw-r--r-- | tools/lib/perf/Documentation/libperf.txt | 1 | ||||
| -rw-r--r-- | tools/lib/perf/cpumap.c | 10 | ||||
| -rw-r--r-- | tools/lib/perf/evlist.c | 119 | ||||
| -rw-r--r-- | tools/lib/perf/evsel.c | 11 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/evsel.h | 3 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/cpumap.h | 2 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/event.h | 30 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/threadmap.h | 1 | ||||
| -rw-r--r-- | tools/lib/perf/threadmap.c | 17 |
9 files changed, 155 insertions, 39 deletions
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index 59aabdd3cabf..4072bc9b7670 100644 --- a/tools/lib/perf/Documentation/libperf.txt +++ b/tools/lib/perf/Documentation/libperf.txt @@ -210,6 +210,7 @@ SYNOPSIS struct perf_record_time_conv; struct perf_record_header_feature; struct perf_record_compressed; + struct perf_record_compressed2; -- DESCRIPTION diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 4454a5987570..b20a5280f2b3 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -242,6 +242,16 @@ out: return cpus; } +struct perf_cpu_map *perf_cpu_map__new_int(int cpu) +{ + struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); + + if (cpus) + RC_CHK_ACCESS(cpus)->map[0].cpu = cpu; + + return cpus; +} + static int __perf_cpu_map__nr(const struct perf_cpu_map *cpus) { return RC_CHK_ACCESS(cpus)->nr; diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index b1f4c8176b32..3ed023f4b190 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -36,49 +36,88 @@ void perf_evlist__init(struct perf_evlist *evlist) static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, struct perf_evsel *evsel) { - if (evsel->system_wide) { - /* System wide: set the cpu map of the evsel to all online CPUs. */ - perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__new_online_cpus(); - } else if (evlist->has_user_cpus && evsel->is_pmu_core) { - /* - * User requested CPUs on a core PMU, ensure the requested CPUs - * are valid by intersecting with those of the PMU. - */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + if (perf_cpu_map__is_empty(evsel->pmu_cpus)) { + /* + * Assume the unset PMU cpus were for a system-wide + * event, like a software or tracepoint. + */ + evsel->pmu_cpus = perf_cpu_map__new_online_cpus(); + } + if (evlist->has_user_cpus && !evsel->system_wide) { + /* + * Use the user CPUs unless the evsel is set to be + * system wide, such as the dummy event. + */ + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } else { + /* + * System wide and other modes, assume the cpu map + * should be set to all PMU CPUs. + */ + evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); + } + } + /* + * Avoid "any CPU"(-1) for uncore and PMUs that require a CPU, even if + * requested. + */ + if (evsel->requires_cpu && perf_cpu_map__has_any_cpu(evsel->cpus)) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); + evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); + } - /* - * Empty cpu lists would eventually get opened as "any" so remove - * genuinely empty ones before they're opened in the wrong place. - */ - if (perf_cpu_map__is_empty(evsel->cpus)) { - struct perf_evsel *next = perf_evlist__next(evlist, evsel); - - perf_evlist__remove(evlist, evsel); - /* Keep idx contiguous */ - if (next) - list_for_each_entry_from(next, &evlist->entries, node) - next->idx--; + /* + * Globally requested CPUs replace user requested unless the evsel is + * set to be system wide. + */ + if (evlist->has_user_cpus && !evsel->system_wide) { + assert(!perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)); + if (!perf_cpu_map__equal(evsel->cpus, evlist->user_requested_cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } - } else if (!evsel->own_cpus || evlist->has_user_cpus || - (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { - /* - * The PMU didn't specify a default cpu map, this isn't a core - * event and the user requested CPUs or the evlist user - * requested CPUs have the "any CPU" (aka dummy) CPU value. In - * which case use the user requested CPUs rather than the PMU - * ones. - */ + } + + /* Ensure cpus only references valid PMU CPUs. */ + if (!perf_cpu_map__has_any_cpu(evsel->cpus) && + !perf_cpu_map__is_subset(evsel->pmu_cpus, evsel->cpus)) { + struct perf_cpu_map *tmp = perf_cpu_map__intersect(evsel->pmu_cpus, evsel->cpus); + perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); - } else if (evsel->cpus != evsel->own_cpus) { - /* - * No user requested cpu map but the PMU cpu map doesn't match - * the evsel's. Reset it back to the PMU cpu map. - */ + evsel->cpus = tmp; + } + + /* + * Was event requested on all the PMU's CPUs but the user requested is + * any CPU (-1)? If so switch to using any CPU (-1) to reduce the number + * of events. + */ + if (!evsel->system_wide && + !evsel->requires_cpu && + perf_cpu_map__equal(evsel->cpus, evsel->pmu_cpus) && + perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evsel->own_cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } + + /* Sanity check assert before the evsel is potentially removed. */ + assert(!evsel->requires_cpu || !perf_cpu_map__has_any_cpu(evsel->cpus)); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + + return; } if (evsel->system_wide) { @@ -98,6 +137,10 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) evlist->needs_map_propagation = true; + /* Clear the all_cpus set which will be merged into during propagation. */ + perf_cpu_map__put(evlist->all_cpus); + evlist->all_cpus = NULL; + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index c475319e2e41..13a307fc75ae 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -40,8 +40,19 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) return evsel; } +void perf_evsel__exit(struct perf_evsel *evsel) +{ + assert(evsel->fd == NULL); /* If not fds were not closed. */ + assert(evsel->mmap == NULL); /* If not munmap wasn't called. */ + assert(evsel->sample_id == NULL); /* If not free_id wasn't called. */ + perf_cpu_map__put(evsel->cpus); + perf_cpu_map__put(evsel->pmu_cpus); + perf_thread_map__put(evsel->threads); +} + void perf_evsel__delete(struct perf_evsel *evsel) { + perf_evsel__exit(evsel); free(evsel); } diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index ea78defa77d0..fefe64ba5e26 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -99,7 +99,7 @@ struct perf_evsel { * cpu map for opening the event on, for example, the first CPU on a * socket for an uncore event. */ - struct perf_cpu_map *own_cpus; + struct perf_cpu_map *pmu_cpus; struct perf_thread_map *threads; struct xyarray *fd; struct xyarray *mmap; @@ -133,6 +133,7 @@ struct perf_evsel { void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx); +void perf_evsel__exit(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__close_fd(struct perf_evsel *evsel); void perf_evsel__free_fd(struct perf_evsel *evsel); diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 8c1ab0f9194e..58cc5c5fa47c 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -37,6 +37,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void); * perf_cpu_map__new_online_cpus is returned. */ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); +/** perf_cpu_map__new_int - create a map with the one given cpu. */ +LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_int(int cpu); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); LIBPERF_API int perf_cpu_map__merge(struct perf_cpu_map **orig, struct perf_cpu_map *other); diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 37bb7771d914..6608f1e3701b 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -457,6 +457,32 @@ struct perf_record_compressed { char data[]; }; +/* + * `header.size` includes the padding we are going to add while writing the record. + * `data_size` only includes the size of `data[]` itself. + */ +struct perf_record_compressed2 { + struct perf_event_header header; + __u64 data_size; + char data[]; +}; + +#define BPF_METADATA_KEY_LEN 64 +#define BPF_METADATA_VALUE_LEN 256 +#define BPF_PROG_NAME_LEN KSYM_NAME_LEN + +struct perf_record_bpf_metadata_entry { + char key[BPF_METADATA_KEY_LEN]; + char value[BPF_METADATA_VALUE_LEN]; +}; + +struct perf_record_bpf_metadata { + struct perf_event_header header; + char prog_name[BPF_PROG_NAME_LEN]; + __u64 nr_entries; + struct perf_record_bpf_metadata_entry entries[]; +}; + enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, @@ -478,6 +504,8 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_HEADER_FEATURE = 80, PERF_RECORD_COMPRESSED = 81, PERF_RECORD_FINISHED_INIT = 82, + PERF_RECORD_COMPRESSED2 = 83, + PERF_RECORD_BPF_METADATA = 84, PERF_RECORD_HEADER_MAX }; @@ -518,6 +546,8 @@ union perf_event { struct perf_record_time_conv time_conv; struct perf_record_header_feature feat; struct perf_record_compressed pack; + struct perf_record_compressed2 pack2; + struct perf_record_bpf_metadata bpf_metadata; }; #endif /* __LIBPERF_EVENT_H */ diff --git a/tools/lib/perf/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h index 8b40e7777cea..44deb815b817 100644 --- a/tools/lib/perf/include/perf/threadmap.h +++ b/tools/lib/perf/include/perf/threadmap.h @@ -14,6 +14,7 @@ LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int idx); LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads); LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx); +LIBPERF_API int perf_thread_map__idx(struct perf_thread_map *map, pid_t pid); LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map); diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c index 07968f3ea093..db431b036f57 100644 --- a/tools/lib/perf/threadmap.c +++ b/tools/lib/perf/threadmap.c @@ -97,5 +97,22 @@ int perf_thread_map__nr(struct perf_thread_map *threads) pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx) { + if (!map) { + assert(idx == 0); + return -1; + } + return map->map[idx].pid; } + +int perf_thread_map__idx(struct perf_thread_map *threads, pid_t pid) +{ + if (!threads) + return pid == -1 ? 0 : -1; + + for (int i = 0; i < threads->nr; ++i) { + if (threads->map[i].pid == pid) + return i; + } + return -1; +} |