diff options
Diffstat (limited to 'tools/perf/builtin-record.c')
| -rw-r--r-- | tools/perf/builtin-record.c | 64 |
1 files changed, 40 insertions, 24 deletions
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a5cf6a99d67f..9a71f0330137 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -49,6 +49,7 @@ #include "util/clockid.h" #include "util/pmu-hybrid.h" #include "util/evlist-hybrid.h" +#include "util/off_cpu.h" #include "asm/bug.h" #include "perf.h" #include "cputopo.h" @@ -162,6 +163,7 @@ struct record { bool buildid_mmap; bool timestamp_filename; bool timestamp_boundary; + bool off_cpu; struct switch_output switch_output; unsigned long long samples; unsigned long output_max_size; /* = 0: unlimited */ @@ -869,7 +871,6 @@ static int record__auxtrace_init(struct record *rec __maybe_unused) static int record__config_text_poke(struct evlist *evlist) { struct evsel *evsel; - int err; /* Nothing to do if text poke is already configured */ evlist__for_each_entry(evlist, evsel) { @@ -877,32 +878,23 @@ static int record__config_text_poke(struct evlist *evlist) return 0; } - err = parse_events(evlist, "dummy:u", NULL); - if (err) - return err; - - evsel = evlist__last(evlist); + evsel = evlist__add_dummy_on_all_cpus(evlist); + if (!evsel) + return -ENOMEM; - evsel->core.attr.freq = 0; - evsel->core.attr.sample_period = 1; evsel->core.attr.text_poke = 1; evsel->core.attr.ksymbol = 1; - - evsel->core.system_wide = true; - evsel->no_aux_samples = true; evsel->immediate = true; - - /* Text poke must be collected on all CPUs */ - perf_cpu_map__put(evsel->core.own_cpus); - evsel->core.own_cpus = perf_cpu_map__new(NULL); - perf_cpu_map__put(evsel->core.cpus); - evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus); - evsel__set_sample_bit(evsel, TIME); return 0; } +static int record__config_off_cpu(struct record *rec) +{ + return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts); +} + static bool record__kcore_readable(struct machine *machine) { char kcore[PATH_MAX]; @@ -982,14 +974,20 @@ static void record__thread_data_close_pipes(struct record_thread *thread_data) } } +static bool evlist__per_thread(struct evlist *evlist) +{ + return cpu_map__is_dummy(evlist->core.user_requested_cpus); +} + static int record__thread_data_init_maps(struct record_thread *thread_data, struct evlist *evlist) { int m, tm, nr_mmaps = evlist->core.nr_mmaps; struct mmap *mmap = evlist->mmap; struct mmap *overwrite_mmap = evlist->overwrite_mmap; - struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; + struct perf_cpu_map *cpus = evlist->core.all_cpus; + bool per_thread = evlist__per_thread(evlist); - if (cpu_map__is_dummy(cpus)) + if (per_thread) thread_data->nr_mmaps = nr_mmaps; else thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, @@ -1010,7 +1008,7 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (cpu_map__is_dummy(cpus) || + if (per_thread || test_bit(perf_cpu_map__cpu(cpus, m).cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; @@ -1885,7 +1883,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus, + err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.all_cpus, process_synthesized_event, NULL); if (err < 0) { pr_err("Couldn't synthesize cpu map.\n"); @@ -2600,6 +2598,9 @@ out_free_threads: } else status = err; + if (rec->off_cpu) + rec->bytes_written += off_cpu_write(rec->session); + record__synthesize(rec, true); /* this will be recalculated during process_buildids() */ rec->samples = 0; @@ -3324,6 +3325,7 @@ static struct option __record_options[] = { OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec", "write collected trace data into several data files using parallel threads", record__parse_threads), + OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"), OPT_END() }; @@ -3683,12 +3685,12 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu static int record__init_thread_masks(struct record *rec) { int ret = 0; - struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus; + struct perf_cpu_map *cpus = rec->evlist->core.all_cpus; if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); - if (cpu_map__is_dummy(cpus)) { + if (evlist__per_thread(rec->evlist)) { pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); return -EINVAL; } @@ -3745,6 +3747,12 @@ int cmd_record(int argc, const char **argv) # undef REASON #endif +#ifndef HAVE_BPF_SKEL +# define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c) + set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true); +# undef set_nobuild +#endif + rec->opts.affinity = PERF_AFFINITY_SYS; rec->evlist = evlist__new(); @@ -3981,6 +3989,14 @@ int cmd_record(int argc, const char **argv) } } + if (rec->off_cpu) { + err = record__config_off_cpu(rec); + if (err) { + pr_err("record__config_off_cpu failed, error %d\n", err); + goto out; + } + } + if (record_opts__config(&rec->opts)) { err = -EINVAL; goto out; |