diff options
Diffstat (limited to 'tools/perf/util/arm-spe.c')
-rw-r--r-- | tools/perf/util/arm-spe.c | 137 |
1 files changed, 109 insertions, 28 deletions
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 58b7069c5a5f..fccac06b573a 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -51,6 +51,7 @@ struct arm_spe { u8 timeless_decoding; u8 data_queued; + u64 sample_type; u8 sample_flc; u8 sample_llc; u8 sample_tlb; @@ -71,6 +72,7 @@ struct arm_spe { u64 kernel_start; unsigned long num_events; + u8 use_ctx_pkt_for_pid; }; struct arm_spe_queue { @@ -100,7 +102,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, const char *color = PERF_COLOR_BLUE; color_fprintf(stdout, color, - ". ... ARM SPE data: size %zu bytes\n", + ". ... ARM SPE data: size %#zx bytes\n", len); while (len) { @@ -226,6 +228,44 @@ static inline u8 arm_spe_cpumode(struct arm_spe *spe, u64 ip) PERF_RECORD_MISC_USER; } +static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, + struct auxtrace_queue *queue) +{ + struct arm_spe_queue *speq = queue->priv; + pid_t tid; + + tid = machine__get_current_tid(spe->machine, speq->cpu); + if (tid != -1) { + speq->tid = tid; + thread__zput(speq->thread); + } else + speq->tid = queue->tid; + + if ((!speq->thread) && (speq->tid != -1)) { + speq->thread = machine__find_thread(spe->machine, -1, + speq->tid); + } + + if (speq->thread) { + speq->pid = speq->thread->pid_; + if (queue->cpu == -1) + speq->cpu = speq->thread->cpu; + } +} + +static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) +{ + struct arm_spe *spe = speq->spe; + int err = machine__set_current_tid(spe->machine, speq->cpu, -1, tid); + + if (err) + return err; + + arm_spe_set_pid_tid_cpu(spe, &spe->queues.queue_array[speq->queue_nr]); + + return 0; +} + static void arm_spe_prep_sample(struct arm_spe *spe, struct arm_spe_queue *speq, union perf_event *event, @@ -248,6 +288,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe, event->sample.header.size = sizeof(struct perf_event_header); } +static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) +{ + event->header.size = perf_event__sample_event_size(sample, type, 0); + return perf_event__synthesize_sample(event, type, 0, sample); +} + static inline int arm_spe_deliver_synth_event(struct arm_spe *spe, struct arm_spe_queue *speq __maybe_unused, @@ -256,6 +302,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe, { int ret; + if (spe->synth_opts.inject) { + ret = arm_spe__inject_event(event, sample, spe->sample_type); + if (ret) + return ret; + } + ret = perf_session__deliver_synth_event(spe->session, event, sample); if (ret) pr_err("ARM SPE: failed to deliver event, error %d\n", ret); @@ -460,6 +512,19 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp) * can correlate samples between Arm SPE trace data and other * perf events with correct time ordering. */ + + /* + * Update pid/tid info. + */ + record = &speq->decoder->record; + if (!spe->timeless_decoding && record->context_id != (u64)-1) { + ret = arm_spe_set_tid(speq, record->context_id); + if (ret) + return ret; + + spe->use_ctx_pkt_for_pid = true; + } + ret = arm_spe_sample(speq); if (ret) return ret; @@ -586,31 +651,6 @@ static bool arm_spe__is_timeless_decoding(struct arm_spe *spe) return timeless_decoding; } -static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, - struct auxtrace_queue *queue) -{ - struct arm_spe_queue *speq = queue->priv; - pid_t tid; - - tid = machine__get_current_tid(spe->machine, speq->cpu); - if (tid != -1) { - speq->tid = tid; - thread__zput(speq->thread); - } else - speq->tid = queue->tid; - - if ((!speq->thread) && (speq->tid != -1)) { - speq->thread = machine__find_thread(spe->machine, -1, - speq->tid); - } - - if (speq->thread) { - speq->pid = speq->thread->pid_; - if (queue->cpu == -1) - speq->cpu = speq->thread->cpu; - } -} - static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) { unsigned int queue_nr; @@ -641,7 +681,12 @@ static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) ts = timestamp; } - arm_spe_set_pid_tid_cpu(spe, queue); + /* + * A previous context-switch event has set pid/tid in the machine's context, so + * here we need to update the pid/tid in the thread and SPE queue. + */ + if (!spe->use_ctx_pkt_for_pid) + arm_spe_set_pid_tid_cpu(spe, queue); ret = arm_spe_run_decoder(speq, &ts); if (ret < 0) { @@ -681,6 +726,25 @@ static int arm_spe_process_timeless_queues(struct arm_spe *spe, pid_t tid, return 0; } +static int arm_spe_context_switch(struct arm_spe *spe, union perf_event *event, + struct perf_sample *sample) +{ + pid_t pid, tid; + int cpu; + + if (!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT)) + return 0; + + pid = event->context_switch.next_prev_pid; + tid = event->context_switch.next_prev_tid; + cpu = sample->cpu; + + if (tid == -1) + pr_warning("context_switch event has no tid\n"); + + return machine__set_current_tid(spe->machine, cpu, pid, tid); +} + static int arm_spe_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -718,6 +782,13 @@ static int arm_spe_process_event(struct perf_session *session, } } else if (timestamp) { err = arm_spe_process_queues(spe, timestamp); + if (err) + return err; + + if (!spe->use_ctx_pkt_for_pid && + (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE || + event->header.type == PERF_RECORD_SWITCH)) + err = arm_spe_context_switch(spe, event, sample); } return err; @@ -783,7 +854,15 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused, return arm_spe_process_timeless_queues(spe, -1, MAX_TIMESTAMP - 1); - return arm_spe_process_queues(spe, MAX_TIMESTAMP); + ret = arm_spe_process_queues(spe, MAX_TIMESTAMP); + if (ret) + return ret; + + if (!spe->use_ctx_pkt_for_pid) + ui__warning("Arm SPE CONTEXT packets not found in the traces.\n" + "Matching of TIDs to SPE events could be inaccurate.\n"); + + return 0; } static void arm_spe_free_queue(void *priv) @@ -920,6 +999,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) else attr.sample_type |= PERF_SAMPLE_TIME; + spe->sample_type = attr.sample_type; + attr.exclude_user = evsel->core.attr.exclude_user; attr.exclude_kernel = evsel->core.attr.exclude_kernel; attr.exclude_hv = evsel->core.attr.exclude_hv; |