diff options
Diffstat (limited to 'tools/perf/util/tool_pmu.c')
| -rw-r--r-- | tools/perf/util/tool_pmu.c | 158 |
1 files changed, 116 insertions, 42 deletions
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c index 4fb097578479..6a9df3dc0e07 100644 --- a/tools/perf/util/tool_pmu.c +++ b/tools/perf/util/tool_pmu.c @@ -6,6 +6,7 @@ #include "pmu.h" #include "print-events.h" #include "smt.h" +#include "stat.h" #include "time-utils.h" #include "tool_pmu.h" #include "tsc.h" @@ -30,6 +31,8 @@ static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = { "slots", "smt_on", "system_tsc_freq", + "core_wide", + "target_cpu", }; bool tool_pmu__skip_event(const char *name __maybe_unused) @@ -62,7 +65,8 @@ int tool_pmu__num_skip_events(void) const char *tool_pmu__event_to_str(enum tool_pmu_event ev) { - if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) + if ((ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) && + !tool_pmu__skip_event(tool_pmu__event_names[ev])) return tool_pmu__event_names[ev]; return NULL; @@ -238,9 +242,6 @@ int evsel__tool_pmu_open(struct evsel *evsel, nthreads = perf_thread_map__nr(threads); for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { for (thread = 0; thread < nthreads; thread++) { - if (thread >= nthreads) - break; - if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); @@ -331,7 +332,11 @@ static bool has_pmem(void) return has_pmem; } -bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) +bool tool_pmu__read_event(enum tool_pmu_event ev, + struct evsel *evsel, + bool system_wide, + const char *user_requested_cpu_list, + u64 *result) { const struct cpu_topology *topology; @@ -346,17 +351,60 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) return true; case TOOL_PMU__EVENT_NUM_CPUS: - *result = cpu__max_present_cpu().cpu; + if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) { + /* No evsel to be specific to. */ + *result = cpu__max_present_cpu().cpu; + } else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) { + /* Evsel just has specific CPUs. */ + *result = perf_cpu_map__nr(evsel->core.cpus); + } else { + /* + * "Any CPU" event that can be scheduled on any CPU in + * the PMU's cpumask. The PMU cpumask should be saved in + * pmu_cpus. If not present fall back to max. + */ + if (!perf_cpu_map__is_empty(evsel->core.pmu_cpus)) + *result = perf_cpu_map__nr(evsel->core.pmu_cpus); + else + *result = cpu__max_present_cpu().cpu; + } return true; case TOOL_PMU__EVENT_NUM_CPUS_ONLINE: { struct perf_cpu_map *online = cpu_map__online(); - if (online) { + if (!online) + return false; + + if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) { + /* No evsel to be specific to. */ *result = perf_cpu_map__nr(online); - return true; + } else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) { + /* Evsel just has specific CPUs. */ + struct perf_cpu_map *tmp = + perf_cpu_map__intersect(online, evsel->core.cpus); + + *result = perf_cpu_map__nr(tmp); + perf_cpu_map__put(tmp); + } else { + /* + * "Any CPU" event that can be scheduled on any CPU in + * the PMU's cpumask. The PMU cpumask should be saved in + * pmu_cpus, if not present then just the online cpu + * mask. + */ + if (!perf_cpu_map__is_empty(evsel->core.pmu_cpus)) { + struct perf_cpu_map *tmp = + perf_cpu_map__intersect(online, evsel->core.pmu_cpus); + + *result = perf_cpu_map__nr(tmp); + perf_cpu_map__put(tmp); + } else { + *result = perf_cpu_map__nr(online); + } } - return false; + perf_cpu_map__put(online); + return true; } case TOOL_PMU__EVENT_NUM_DIES: topology = online_topology(); @@ -380,6 +428,14 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) *result = arch_get_tsc_freq(); return true; + case TOOL_PMU__EVENT_CORE_WIDE: + *result = core_wide(system_wide, user_requested_cpu_list) ? 1 : 0; + return true; + + case TOOL_PMU__EVENT_TARGET_CPU: + *result = system_wide || (user_requested_cpu_list != NULL) ? 1 : 0; + return true; + case TOOL_PMU__EVENT_NONE: case TOOL_PMU__EVENT_DURATION_TIME: case TOOL_PMU__EVENT_USER_TIME: @@ -390,16 +446,39 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) } } +static void perf_counts__update(struct perf_counts_values *count, + const struct perf_counts_values *old_count, + bool raw, u64 val) +{ + /* + * The values of enabled and running must make a ratio of 100%. The + * exact values don't matter as long as they are non-zero to avoid + * issues with evsel__count_has_error. + */ + if (old_count) { + count->val = raw ? val : old_count->val + val; + count->run = old_count->run + 1; + count->ena = old_count->ena + 1; + count->lost = old_count->lost; + } else { + count->val = val; + count->run++; + count->ena++; + count->lost = 0; + } +} + int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) { __u64 *start_time, cur_time, delta_start; - u64 val; - int fd, err = 0; + int err = 0; struct perf_counts_values *count, *old_count = NULL; bool adjust = false; enum tool_pmu_event ev = evsel__tool_event(evsel); count = perf_counts(evsel->counts, cpu_map_idx, thread); + if (evsel->prev_raw_counts) + old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); switch (ev) { case TOOL_PMU__EVENT_HAS_PMEM: @@ -410,26 +489,23 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) case TOOL_PMU__EVENT_NUM_PACKAGES: case TOOL_PMU__EVENT_SLOTS: case TOOL_PMU__EVENT_SMT_ON: - case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ: - if (evsel->prev_raw_counts) - old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); - val = 0; + case TOOL_PMU__EVENT_CORE_WIDE: + case TOOL_PMU__EVENT_TARGET_CPU: + case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ: { + u64 val = 0; + if (cpu_map_idx == 0 && thread == 0) { - if (!tool_pmu__read_event(ev, &val)) { + if (!tool_pmu__read_event(ev, evsel, + stat_config.system_wide, + stat_config.user_requested_cpu_list, + &val)) { count->lost++; val = 0; } } - if (old_count) { - count->val = old_count->val + val; - count->run = old_count->run + 1; - count->ena = old_count->ena + 1; - } else { - count->val = val; - count->run++; - count->ena++; - } + perf_counts__update(count, old_count, /*raw=*/false, val); return 0; + } case TOOL_PMU__EVENT_DURATION_TIME: /* * Pretend duration_time is only on the first CPU and thread, or @@ -445,9 +521,9 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) case TOOL_PMU__EVENT_USER_TIME: case TOOL_PMU__EVENT_SYSTEM_TIME: { bool system = evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME; + int fd = FD(evsel, cpu_map_idx, thread); start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread); - fd = FD(evsel, cpu_map_idx, thread); lseek(fd, SEEK_SET, 0); if (evsel->pid_stat) { /* The event exists solely on 1 CPU. */ @@ -481,25 +557,23 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) if (adjust) { __u64 ticks_per_sec = sysconf(_SC_CLK_TCK); - delta_start *= 1000000000 / ticks_per_sec; + delta_start *= 1e9 / ticks_per_sec; } - count->val = delta_start; - count->ena = count->run = delta_start; - count->lost = 0; + perf_counts__update(count, old_count, /*raw=*/true, delta_start); return 0; } -struct perf_pmu *perf_pmus__tool_pmu(void) +struct perf_pmu *tool_pmu__new(void) { - static struct perf_pmu tool = { - .name = "tool", - .type = PERF_PMU_TYPE_TOOL, - .aliases = LIST_HEAD_INIT(tool.aliases), - .caps = LIST_HEAD_INIT(tool.caps), - .format = LIST_HEAD_INIT(tool.format), - }; - if (!tool.events_table) - tool.events_table = find_core_events_table("common", "common"); - - return &tool; + struct perf_pmu *tool = zalloc(sizeof(struct perf_pmu)); + + if (!tool) + return NULL; + + if (perf_pmu__init(tool, PERF_PMU_TYPE_TOOL, "tool") != 0) { + perf_pmu__delete(tool); + return NULL; + } + tool->events_table = find_core_events_table("common", "common"); + return tool; } |
