X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=tools%2Fperf%2Futil%2Fcs-etm.c;h=f4b2bff533f3ce268db29d52cb6548c9db2e775e;hb=9182f04a85b2c2062bbf4f8e53bec9ce698d55f0;hp=32ad92d3e454d210ea56a5606ea8ceb726f7e883;hpb=e083bbd6040f4efa5c13633fb4e460b919d69dae;p=linux-2.6-microblaze.git diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 32ad92d3e454..f4b2bff533f3 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -62,7 +62,6 @@ struct cs_etm_auxtrace { u64 instructions_sample_period; u64 instructions_id; u64 **metadata; - u64 kernel_start; unsigned int pmu_type; }; @@ -97,7 +96,6 @@ struct cs_etm_queue { /* RB tree for quick conversion between traceID and metadata pointers */ static struct intlist *traceid_list; -static int cs_etm__update_queues(struct cs_etm_auxtrace *etm); static int cs_etm__process_queues(struct cs_etm_auxtrace *etm); static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, pid_t tid); @@ -463,13 +461,14 @@ static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params, } static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params, - struct cs_etm_auxtrace *etm) + struct cs_etm_auxtrace *etm, + int decoders) { int i; u32 etmidr; u64 architecture; - for (i = 0; i < etm->num_cpu; i++) { + for (i = 0; i < decoders; i++) { architecture = etm->metadata[i][CS_ETM_MAGIC]; switch (architecture) { @@ -490,7 +489,8 @@ static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params, static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params, struct cs_etm_queue *etmq, - enum cs_etm_decoder_operation mode) + enum cs_etm_decoder_operation mode, + bool formatted) { int ret = -EINVAL; @@ -500,7 +500,7 @@ static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params, d_params->packet_printer = cs_etm__packet_dump; d_params->operation = mode; d_params->data = etmq; - d_params->formatted = true; + d_params->formatted = formatted; d_params->fsyncs = false; d_params->hsyncs = false; d_params->frame_aligned = true; @@ -510,14 +510,11 @@ out: return ret; } -static void cs_etm__dump_event(struct cs_etm_auxtrace *etm, +static void cs_etm__dump_event(struct cs_etm_queue *etmq, struct auxtrace_buffer *buffer) { int ret; const char *color = PERF_COLOR_BLUE; - struct cs_etm_decoder_params d_params; - struct cs_etm_trace_params *t_params; - struct cs_etm_decoder *decoder; size_t buffer_used = 0; fprintf(stdout, "\n"); @@ -525,29 +522,11 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm, ". ... CoreSight ETM Trace data: size %zu bytes\n", buffer->size); - /* Use metadata to fill in trace parameters for trace decoder */ - t_params = zalloc(sizeof(*t_params) * etm->num_cpu); - - if (!t_params) - return; - - if (cs_etm__init_trace_params(t_params, etm)) - goto out_free; - - /* Set decoder parameters to simply print the trace packets */ - if (cs_etm__init_decoder_params(&d_params, NULL, - CS_ETM_OPERATION_PRINT)) - goto out_free; - - decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params); - - if (!decoder) - goto out_free; do { size_t consumed; ret = cs_etm_decoder__process_data_block( - decoder, buffer->offset, + etmq->decoder, buffer->offset, &((u8 *)buffer->data)[buffer_used], buffer->size - buffer_used, &consumed); if (ret) @@ -556,16 +535,12 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm, buffer_used += consumed; } while (buffer_used < buffer->size); - cs_etm_decoder__free(decoder); - -out_free: - zfree(&t_params); + cs_etm_decoder__reset(etmq->decoder); } static int cs_etm__flush_events(struct perf_session *session, struct perf_tool *tool) { - int ret; struct cs_etm_auxtrace *etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace); @@ -575,11 +550,6 @@ static int cs_etm__flush_events(struct perf_session *session, if (!tool->ordered_events) return -EINVAL; - ret = cs_etm__update_queues(etm); - - if (ret < 0) - return ret; - if (etm->timeless_decoding) return cs_etm__process_timeless_queues(etm, -1); @@ -691,7 +661,7 @@ static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) machine = etmq->etm->machine; - if (address >= etmq->etm->kernel_start) { + if (address >= machine__kernel_start(machine)) { if (machine__is_host(machine)) return PERF_RECORD_MISC_KERNEL; else @@ -752,11 +722,17 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, return len; } -static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm) +static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, + bool formatted) { struct cs_etm_decoder_params d_params; struct cs_etm_trace_params *t_params = NULL; struct cs_etm_queue *etmq; + /* + * Each queue can only contain data from one CPU when unformatted, so only one decoder is + * needed. + */ + int decoders = formatted ? etm->num_cpu : 1; etmq = zalloc(sizeof(*etmq)); if (!etmq) @@ -767,20 +743,23 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm) goto out_free; /* Use metadata to fill in trace parameters for trace decoder */ - t_params = zalloc(sizeof(*t_params) * etm->num_cpu); + t_params = zalloc(sizeof(*t_params) * decoders); if (!t_params) goto out_free; - if (cs_etm__init_trace_params(t_params, etm)) + if (cs_etm__init_trace_params(t_params, etm, decoders)) goto out_free; /* Set decoder parameters to decode trace packets */ if (cs_etm__init_decoder_params(&d_params, etmq, - CS_ETM_OPERATION_DECODE)) + dump_trace ? CS_ETM_OPERATION_PRINT : + CS_ETM_OPERATION_DECODE, + formatted)) goto out_free; - etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params); + etmq->decoder = cs_etm_decoder__new(decoders, &d_params, + t_params); if (!etmq->decoder) goto out_free; @@ -808,31 +787,35 @@ out_free: static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, struct auxtrace_queue *queue, - unsigned int queue_nr) + unsigned int queue_nr, + bool formatted) { - int ret = 0; - unsigned int cs_queue_nr; - u8 trace_chan_id; - u64 cs_timestamp; struct cs_etm_queue *etmq = queue->priv; if (list_empty(&queue->head) || etmq) - goto out; + return 0; - etmq = cs_etm__alloc_queue(etm); + etmq = cs_etm__alloc_queue(etm, formatted); - if (!etmq) { - ret = -ENOMEM; - goto out; - } + if (!etmq) + return -ENOMEM; queue->priv = etmq; etmq->etm = etm; etmq->queue_nr = queue_nr; etmq->offset = 0; - if (etm->timeless_decoding) - goto out; + return 0; +} + +static int cs_etm__queue_first_cs_timestamp(struct cs_etm_auxtrace *etm, + struct cs_etm_queue *etmq, + unsigned int queue_nr) +{ + int ret = 0; + unsigned int cs_queue_nr; + u8 trace_chan_id; + u64 cs_timestamp; /* * We are under a CPU-wide trace scenario. As such we need to know @@ -896,33 +879,6 @@ out: return ret; } -static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm) -{ - unsigned int i; - int ret; - - if (!etm->kernel_start) - etm->kernel_start = machine__kernel_start(etm->machine); - - for (i = 0; i < etm->queues.nr_queues; i++) { - ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i); - if (ret) - return ret; - } - - return 0; -} - -static int cs_etm__update_queues(struct cs_etm_auxtrace *etm) -{ - if (etm->queues.new_data) { - etm->queues.new_data = false; - return cs_etm__setup_queues(etm); - } - - return 0; -} - static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq) @@ -2222,13 +2178,27 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, static int cs_etm__process_queues(struct cs_etm_auxtrace *etm) { int ret = 0; - unsigned int cs_queue_nr, queue_nr; + unsigned int cs_queue_nr, queue_nr, i; u8 trace_chan_id; u64 cs_timestamp; struct auxtrace_queue *queue; struct cs_etm_queue *etmq; struct cs_etm_traceid_queue *tidq; + /* + * Pre-populate the heap with one entry from each queue so that we can + * start processing in time order across all queues. + */ + for (i = 0; i < etm->queues.nr_queues; i++) { + etmq = etm->queues.queue_array[i].priv; + if (!etmq) + continue; + + ret = cs_etm__queue_first_cs_timestamp(etm, etmq, i); + if (ret) + return ret; + } + while (1) { if (!etm->heap.heap_cnt) goto out; @@ -2382,7 +2352,6 @@ static int cs_etm__process_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool) { - int err = 0; u64 sample_kernel_timestamp; struct cs_etm_auxtrace *etm = container_of(session->auxtrace, struct cs_etm_auxtrace, @@ -2401,12 +2370,6 @@ static int cs_etm__process_event(struct perf_session *session, else sample_kernel_timestamp = 0; - if (sample_kernel_timestamp || etm->timeless_decoding) { - err = cs_etm__update_queues(etm); - if (err) - return err; - } - /* * Don't wait for cs_etm__flush_events() in per-thread/timeless mode to start the decode. We * need the tid of the PERF_RECORD_EXIT event to assign to the synthesised samples because @@ -2434,6 +2397,22 @@ static int cs_etm__process_event(struct perf_session *session, return 0; } +static void dump_queued_data(struct cs_etm_auxtrace *etm, + struct perf_record_auxtrace *event) +{ + struct auxtrace_buffer *buf; + unsigned int i; + /* + * Find all buffers with same reference in the queues and dump them. + * This is because the queues can contain multiple entries of the same + * buffer that were split on aux records. + */ + for (i = 0; i < etm->queues.nr_queues; ++i) + list_for_each_entry(buf, &etm->queues.queue_array[i].head, list) + if (buf->reference == event->reference) + cs_etm__dump_event(etm->queues.queue_array[i].priv, buf); +} + static int cs_etm__process_auxtrace_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool __maybe_unused) @@ -2447,6 +2426,7 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, int fd = perf_data__fd(session->data); bool is_pipe = perf_data__is_pipe(session->data); int err; + int idx = event->auxtrace.idx; if (is_pipe) data_offset = 0; @@ -2461,12 +2441,24 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, if (err) return err; + /* + * Knowing if the trace is formatted or not requires a lookup of + * the aux record so only works in non-piped mode where data is + * queued in cs_etm__queue_aux_records(). Always assume + * formatted in piped mode (true). + */ + err = cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], + idx, true); + if (err) + return err; + if (dump_trace) if (auxtrace_buffer__get_data(buffer, fd)) { - cs_etm__dump_event(etm, buffer); + cs_etm__dump_event(etm->queues.queue_array[idx].priv, buffer); auxtrace_buffer__put_data(buffer); } - } + } else if (dump_trace) + dump_queued_data(etm, &event->auxtrace); return 0; } @@ -2683,6 +2675,181 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset, return metadata; } +/** + * Puts a fragment of an auxtrace buffer into the auxtrace queues based + * on the bounds of aux_event, if it matches with the buffer that's at + * file_offset. + * + * Normally, whole auxtrace buffers would be added to the queue. But we + * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder + * is reset across each buffer, so splitting the buffers up in advance has + * the same effect. + */ +static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz, + struct perf_record_aux *aux_event, struct perf_sample *sample) +{ + int err; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *auxtrace_event_union; + struct perf_record_auxtrace *auxtrace_event; + union perf_event auxtrace_fragment; + __u64 aux_offset, aux_size; + __u32 idx; + bool formatted; + + struct cs_etm_auxtrace *etm = container_of(session->auxtrace, + struct cs_etm_auxtrace, + auxtrace); + + /* + * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got + * from looping through the auxtrace index. + */ + err = perf_session__peek_event(session, file_offset, buf, + PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL); + if (err) + return err; + auxtrace_event = &auxtrace_event_union->auxtrace; + if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE) + return -EINVAL; + + if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) || + auxtrace_event->header.size != sz) { + return -EINVAL; + } + + /* + * In per-thread mode, CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + */ + if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || + auxtrace_event->cpu != sample->cpu) + return 1; + + if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { + /* + * Clamp size in snapshot mode. The buffer size is clamped in + * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect + * the buffer size. + */ + aux_size = min(aux_event->aux_size, auxtrace_event->size); + + /* + * In this mode, the head also points to the end of the buffer so aux_offset + * needs to have the size subtracted so it points to the beginning as in normal mode + */ + aux_offset = aux_event->aux_offset - aux_size; + } else { + aux_size = aux_event->aux_size; + aux_offset = aux_event->aux_offset; + } + + if (aux_offset >= auxtrace_event->offset && + aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) { + /* + * If this AUX event was inside this buffer somewhere, create a new auxtrace event + * based on the sizes of the aux event, and queue that fragment. + */ + auxtrace_fragment.auxtrace = *auxtrace_event; + auxtrace_fragment.auxtrace.size = aux_size; + auxtrace_fragment.auxtrace.offset = aux_offset; + file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size; + + pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu); + err = auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment, + file_offset, NULL); + if (err) + return err; + + idx = auxtrace_event->idx; + formatted = !(aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW); + return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], + idx, formatted); + } + + /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */ + return 1; +} + +static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + struct perf_sample sample; + int ret; + struct auxtrace_index_entry *ent; + struct auxtrace_index *auxtrace_index; + struct evsel *evsel; + size_t i; + + /* Don't care about any other events, we're only queuing buffers for AUX events */ + if (event->header.type != PERF_RECORD_AUX) + return 0; + + if (event->header.size < sizeof(struct perf_record_aux)) + return -EINVAL; + + /* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */ + if (!event->aux.aux_size) + return 0; + + /* + * Parse the sample, we need the sample_id_all data that comes after the event so that the + * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID. + */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + ret = evsel__parse_sample(evsel, event, &sample); + if (ret) + return ret; + + /* + * Loop through the auxtrace index to find the buffer that matches up with this aux event. + */ + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { + for (i = 0; i < auxtrace_index->nr; i++) { + ent = &auxtrace_index->entries[i]; + ret = cs_etm__queue_aux_fragment(session, ent->file_offset, + ent->sz, &event->aux, &sample); + /* + * Stop search on error or successful values. Continue search on + * 1 ('not found') + */ + if (ret != 1) + return ret; + } + } + + /* + * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but + * don't exit with an error because it will still be possible to decode other aux records. + */ + pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); + return 0; +} + +static int cs_etm__queue_aux_records(struct perf_session *session) +{ + struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index, + struct auxtrace_index, list); + if (index && index->nr > 0) + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__queue_aux_records_cb, NULL); + + /* + * We would get here if there are no entries in the index (either no auxtrace + * buffers or no index at all). Fail silently as there is the possibility of + * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still + * false. + * + * In that scenario, buffers will not be split by AUX records. + */ + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2876,18 +3043,24 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); - return 0; } err = cs_etm__synth_events(etm, session); if (err) goto err_delete_thread; - err = auxtrace_queues__process_index(&etm->queues, session); + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; etm->data_queued = etm->queues.populated; + /* + * Print warning in pipe mode, see cs_etm__process_auxtrace_event() and + * cs_etm__queue_aux_fragment() for details relating to limitations. + */ + if (!etm->data_queued) + pr_warning("CS ETM warning: Coresight decode and TRBE support requires random file access.\n" + "Continuing with best effort decoding in piped mode.\n\n"); return 0;