perf/core improvements and changes

334 lines not on this page · raw message

96 lines not on this page · raw message

127 lines not on this page · raw message

index 6a4c86b1431f..57b020b0b36f 100644
@@ -200,6 +200,121 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	}
 }
 
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
+			      const ocsd_generic_trace_elem *elem,
+			      const u8 trace_chan_id,
+			      enum cs_etm_sample_type sample_type)
+{
+	u32 et = 0;
+	struct int_node *inode = NULL;
+
+	if (decoder->packet_count >= MAX_BUFFER - 1)
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	/* Search the RB tree for the cpu associated with this traceID */
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	et = decoder->tail;
+	decoder->packet_buffer[et].sample_type = sample_type;
+	decoder->packet_buffer[et].start_addr = elem->st_addr;
+	decoder->packet_buffer[et].end_addr = elem->en_addr;
+	decoder->packet_buffer[et].exc = false;
+	decoder->packet_buffer[et].exc_ret = false;
+	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
+
+	/* Wrap around if need be */
+	et = (et + 1) & (MAX_BUFFER - 1);
+
+	decoder->tail = et;
+	decoder->packet_count++;
+
+	if (decoder->packet_count == MAX_BUFFER - 1)
+		return OCSD_RESP_WAIT;
+
+	return OCSD_RESP_CONT;
+}
+
+static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
+				const void *context,
+				const ocsd_trc_index_t indx __maybe_unused,
+				const u8 trace_chan_id __maybe_unused,
+				const ocsd_generic_trace_elem *elem)
+{
+	ocsd_datapath_resp_t resp = OCSD_RESP_CONT;
+	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+	switch (elem->elem_type) {
+	case OCSD_GEN_TRC_ELEM_UNKNOWN:
+		break;
+	case OCSD_GEN_TRC_ELEM_NO_SYNC:
+		decoder->trace_on = false;
+		break;
+	case OCSD_GEN_TRC_ELEM_TRACE_ON:
+		decoder->trace_on = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
+		resp = cs_etm_decoder__buffer_packet(decoder, elem,
+						     trace_chan_id,
+						     CS_ETM_RANGE);
+		break;
+	case OCSD_GEN_TRC_ELEM_EXCEPTION:
+		decoder->packet_buffer[decoder->tail].exc = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
+		decoder->packet_buffer[decoder->tail].exc_ret = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
+	case OCSD_GEN_TRC_ELEM_EO_TRACE:
+	case OCSD_GEN_TRC_ELEM_ADDR_NACC:
+	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+	case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
+	case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
+	case OCSD_GEN_TRC_ELEM_EVENT:
+	case OCSD_GEN_TRC_ELEM_SWTRACE:
+	case OCSD_GEN_TRC_ELEM_CUSTOM:
+	default:
+		break;
+	}
+
+	return resp;
+}
+
+static int cs_etm_decoder__create_etm_packet_decoder(
+					struct cs_etm_trace_params *t_params,
+					struct cs_etm_decoder *decoder)
+{
+	const char *decoder_name;
+	ocsd_etmv4_cfg trace_config_etmv4;
+	void *trace_config;
+	u8 csid;
+
+	switch (t_params->protocol) {
+	case CS_ETM_PROTO_ETMV4i:
+		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
+		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+		trace_config = &trace_config_etmv4;
+		break;
+	default:
+		return -1;
+	}
+
+	if (ocsd_dt_create_decoder(decoder->dcd_tree,
+				     decoder_name,
+				     OCSD_CREATE_FLG_FULL_DECODER,
+				     trace_config, &csid))
+		return -1;
+
+	if (ocsd_dt_set_gen_elem_outfn(decoder->dcd_tree,
+				       cs_etm_decoder__gen_trace_elem_printer,
+				       decoder))
+		return -1;
+
+	return 0;
+}
+
 static int
 cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
 				   struct cs_etm_trace_params *t_params,

@@ -208,6 +323,10 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
 	if (d_params->operation == CS_ETM_OPERATION_PRINT)
 		return cs_etm_decoder__create_etm_packet_printer(t_params,
 								 decoder);
+	else if (d_params->operation == CS_ETM_OPERATION_DECODE)
+		return cs_etm_decoder__create_etm_packet_decoder(t_params,
+								 decoder);
+
 	return -1;
 }
 

index 57b020b0b36f..1fb01849f1c7 100644
@@ -45,6 +45,66 @@ struct cs_etm_decoder {
 	struct cs_etm_packet packet_buffer[MAX_BUFFER];
 };
 
+static u32
+cs_etm_decoder__mem_access(const void *context,
+			   const ocsd_vaddr_t address,
+			   const ocsd_mem_space_acc_t mem_space __maybe_unused,
+			   const u32 req_size,
+			   u8 *buffer)
+{
+	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+	return decoder->mem_access(decoder->data,
+				   address,
+				   req_size,
+				   buffer);
+}
+
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+				      u64 start, u64 end,
+				      cs_etm_mem_cb_type cb_func)
+{
+	decoder->mem_access = cb_func;
+
+	if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end,
+					 OCSD_MEM_SPACE_ANY,
+					 cs_etm_decoder__mem_access, decoder))
+		return -1;
+
+	return 0;
+}
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
+{
+	ocsd_datapath_resp_t dp_ret;
+
+	dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
+				      0, 0, NULL, NULL);
+	if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
+		return -1;
+
+	return 0;
+}
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+			       struct cs_etm_packet *packet)
+{
+	if (!decoder || !packet)
+		return -EINVAL;
+
+	/* Nothing to do, might as well just return */
+	if (decoder->packet_count == 0)
+		return 0;
+
+	*packet = decoder->packet_buffer[decoder->head];
+
+	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
+
+	decoder->packet_count--;
+
+	return 1;
+}
+
 static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
 					     ocsd_etmv4_cfg *config)
 {

index a1e9b0ac5965..3d2e6205d186 100644
@@ -93,4 +93,13 @@ cs_etm_decoder__new(int num_cpu,
 
 void cs_etm_decoder__free(struct cs_etm_decoder *decoder);
 
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+				      u64 start, u64 end,
+				      cs_etm_mem_cb_type cb_func);
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+			       struct cs_etm_packet *packet);
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder);
+
 #endif /* INCLUDE__CS_ETM_DECODER_H__ */

index cad429ce3c00..83eb676274b5 100644
@@ -196,15 +196,215 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
+			      size_t size, u8 *buffer)
+{
+	u8  cpumode;
+	u64 offset;
+	int len;
+	struct	 thread *thread;
+	struct	 machine *machine;
+	struct	 addr_location al;
+
+	if (!etmq)
+		return -1;
+
+	machine = etmq->etm->machine;
+	if (address >= etmq->etm->kernel_start)
+		cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		cpumode = PERF_RECORD_MISC_USER;
+
+	thread = etmq->thread;
+	if (!thread) {
+		if (cpumode != PERF_RECORD_MISC_KERNEL)
+			return -EINVAL;
+		thread = etmq->etm->unknown_thread;
+	}
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
+
+	if (!al.map || !al.map->dso)
+		return 0;
+
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
+	    dso__data_status_seen(al.map->dso, DSO_DATA_STATUS_SEEN_ITRACE))
+		return 0;
+
+	offset = al.map->map_ip(al.map, address);
+
+	map__load(al.map);
+
+	len = dso__data_read_offset(al.map->dso, machine, offset, buffer, size);
+
+	if (len <= 0)
+		return 0;
+
+	return len;
+}
+
+static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
+						unsigned int queue_nr)
+{
+	int i;
+	struct cs_etm_decoder_params d_params;
+	struct cs_etm_trace_params  *t_params;
+	struct cs_etm_queue *etmq;
+
+	etmq = zalloc(sizeof(*etmq));
+	if (!etmq)
+		return NULL;
+
+	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+	if (!etmq->event_buf)
+		goto out_free;
+
+	etmq->etm = etm;
+	etmq->queue_nr = queue_nr;
+	etmq->pid = -1;
+	etmq->tid = -1;
+	etmq->cpu = -1;
+
+	/* Use metadata to fill in trace parameters for trace decoder */
+	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
+
+	if (!t_params)
+		goto out_free;
+
+	for (i = 0; i < etm->num_cpu; i++) {
+		t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
+		t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
+		t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
+		t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
+		t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
+		t_params[i].etmv4.reg_configr =
+					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
+		t_params[i].etmv4.reg_traceidr =
+					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
+	}
+
+	/* Set decoder parameters to simply print the trace packets */
+	d_params.packet_printer = cs_etm__packet_dump;
+	d_params.operation = CS_ETM_OPERATION_DECODE;
+	d_params.formatted = true;
+	d_params.fsyncs = false;
+	d_params.hsyncs = false;
+	d_params.frame_aligned = true;
+	d_params.data = etmq;
+
+	etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
+
+	zfree(&t_params);
+
+	if (!etmq->decoder)
+		goto out_free;
+
+	/*
+	 * Register a function to handle all memory accesses required by
+	 * the trace decoder library.
+	 */
+	if (cs_etm_decoder__add_mem_access_cb(etmq->decoder,
+					      0x0L, ((u64) -1L),
+					      cs_etm__mem_access))
+		goto out_free_decoder;
+
+	etmq->offset = 0;
+
+	return etmq;
+
+out_free_decoder:
+	cs_etm_decoder__free(etmq->decoder);
+out_free:
+	zfree(&etmq->event_buf);
+	free(etmq);
+
+	return NULL;
+}
+
+static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
+			       struct auxtrace_queue *queue,
+			       unsigned int queue_nr)
+{
+	struct cs_etm_queue *etmq = queue->priv;
+
+	if (list_empty(&queue->head) || etmq)
+		return 0;
+
+	etmq = cs_etm__alloc_queue(etm, queue_nr);
+
+	if (!etmq)
+		return -ENOMEM;
+
+	queue->priv = etmq;
+
+	if (queue->cpu != -1)
+		etmq->cpu = queue->cpu;
+
+	etmq->tid = queue->tid;
+
+	return 0;
+}
+
+static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
+{
+	unsigned int i;
+	int ret;
+
+	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 int cs_etm__process_event(struct perf_session *session,
 				 union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_tool *tool)
 {
-	(void) session;
-	(void) event;
-	(void) sample;
-	(void) tool;
+	int err = 0;
+	u64 timestamp;
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+
+	/* Keep compiler happy */
+	(void)event;
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events) {
+		pr_err("CoreSight ETM Trace requires ordered events\n");
+		return -EINVAL;
+	}
+
+	if (!etm->timeless_decoding)
+		return -EINVAL;
+
+	if (sample->time && (sample->time != (u64) -1))
+		timestamp = sample->time;
+	else
+		timestamp = 0;
+
+	if (timestamp || etm->timeless_decoding) {
+		err = cs_etm__update_queues(etm);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 

index 83eb676274b5..407095af1456 100644
@@ -70,6 +70,10 @@ struct cs_etm_queue {
 	u64 offset;
 };
 
+static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+					   pid_t tid, u64 time_);
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;

@@ -145,9 +149,25 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 static int cs_etm__flush_events(struct perf_session *session,
 				struct perf_tool *tool)
 {
-	(void) session;
-	(void) tool;
-	return 0;
+	int ret;
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events)
+		return -EINVAL;
+
+	if (!etm->timeless_decoding)
+		return -EINVAL;
+
+	ret = cs_etm__update_queues(etm);
+
+	if (ret < 0)
+		return ret;
+
+	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
 }
 
 static void cs_etm__free_queue(void *priv)

@@ -369,6 +389,138 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
 	return 0;
 }
 
+static int
+cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
+{
+	struct auxtrace_buffer *aux_buffer = etmq->buffer;
+	struct auxtrace_buffer *old_buffer = aux_buffer;
+	struct auxtrace_queue *queue;
+
+	queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
+
+	aux_buffer = auxtrace_buffer__next(queue, aux_buffer);
+
+	/* If no more data, drop the previous auxtrace_buffer and return */
+	if (!aux_buffer) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		buff->len = 0;
+		return 0;
+	}
+
+	etmq->buffer = aux_buffer;
+
+	/* If the aux_buffer doesn't have data associated, try to load it */
+	if (!aux_buffer->data) {
+		/* get the file desc associated with the perf data file */
+		int fd = perf_data__fd(etmq->etm->session->data);
+
+		aux_buffer->data = auxtrace_buffer__get_data(aux_buffer, fd);
+		if (!aux_buffer->data)
+			return -ENOMEM;
+	}
+
+	/* If valid, drop the previous buffer */
+	if (old_buffer)
+		auxtrace_buffer__drop_data(old_buffer);
+
+	buff->offset = aux_buffer->offset;
+	buff->len = aux_buffer->size;
+	buff->buf = aux_buffer->data;
+
+	buff->ref_timestamp = aux_buffer->reference;
+
+	return buff->len;
+}
+
+static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+				     struct auxtrace_queue *queue)
+{
+	struct cs_etm_queue *etmq = queue->priv;
+
+	/* CPU-wide tracing isn't supported yet */
+	if (queue->tid == -1)
+		return;
+
+	if ((!etmq->thread) && (etmq->tid != -1))
+		etmq->thread = machine__find_thread(etm->machine, -1,
+						    etmq->tid);
+
+	if (etmq->thread) {
+		etmq->pid = etmq->thread->pid_;
+		if (queue->cpu == -1)
+			etmq->cpu = etmq->thread->cpu;
+	}
+}
+
+static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
+{
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_buffer buffer;
+	size_t buffer_used, processed;
+	int err = 0;
+
+	if (!etm->kernel_start)
+		etm->kernel_start = machine__kernel_start(etm->machine);
+
+	/* Go through each buffer in the queue and decode them one by one */
+more:
+	buffer_used = 0;
+	memset(&buffer, 0, sizeof(buffer));
+	err = cs_etm__get_trace(&buffer, etmq);
+	if (err <= 0)
+		return err;
+	/*
+	 * We cannot assume consecutive blocks in the data file are contiguous,
+	 * reset the decoder to force re-sync.
+	 */
+	err = cs_etm_decoder__reset(etmq->decoder);
+	if (err != 0)
+		return err;
+
+	/* Run trace decoder until buffer consumed or end of trace */
+	do {
+		processed = 0;
+
+		err = cs_etm_decoder__process_data_block(
+						etmq->decoder,
+						etmq->offset,
+						&buffer.buf[buffer_used],
+						buffer.len - buffer_used,
+						&processed);
+
+		if (err)
+			return err;
+
+		etmq->offset += processed;
+		buffer_used += processed;
+	} while (buffer.len > buffer_used);
+
+goto more;
+
+	return err;
+}
+
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+					   pid_t tid, u64 time_)
+{
+	unsigned int i;
+	struct auxtrace_queues *queues = &etm->queues;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct auxtrace_queue *queue = &etm->queues.queue_array[i];
+		struct cs_etm_queue *etmq = queue->priv;
+
+		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
+			etmq->time = time_;
+			cs_etm__set_pid_tid_cpu(etm, queue);
+			cs_etm__run_decoder(etmq);
+		}
+	}
+
+	return 0;
+}
+
 static int cs_etm__process_event(struct perf_session *session,
 				 union perf_event *event,
 				 struct perf_sample *sample,

@@ -380,9 +532,6 @@ static int cs_etm__process_event(struct perf_session *session,
 						   struct cs_etm_auxtrace,
 						   auxtrace);
 
-	/* Keep compiler happy */
-	(void)event;
-
 	if (dump_trace)
 		return 0;
 

@@ -405,6 +554,11 @@ static int cs_etm__process_event(struct perf_session *session,
 			return err;
 	}
 
+	if (event->header.type == PERF_RECORD_EXIT)
+		return cs_etm__process_timeless_queues(etm,
+						       event->fork.tid,
+						       sample->time);
+
 	return 0;
 }
 

index 407095af1456..b9f0a53dfa65 100644
@@ -453,6 +453,157 @@ static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
 	}
 }
 
+/*
+ * The cs etm packet encodes an instruction range between a branch target
+ * and the next taken branch. Generate sample accordingly.
+ */
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
+				       struct cs_etm_packet *packet)
+{
+	int ret = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct perf_sample sample = {.ip = 0,};
+	union perf_event *event = etmq->event_buf;
+	u64 start_addr = packet->start_addr;
+	u64 end_addr = packet->end_addr;
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	sample.ip = start_addr;
+	sample.pid = etmq->pid;
+	sample.tid = etmq->tid;
+	sample.addr = end_addr;
+	sample.id = etmq->etm->branches_id;
+	sample.stream_id = etmq->etm->branches_id;
+	sample.period = 1;
+	sample.cpu = packet->cpu;
+	sample.flags = 0;
+	sample.cpumode = PERF_RECORD_MISC_USER;
+
+	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+	if (ret)
+		pr_err(
+		"CS ETM Trace: failed to deliver instruction event, error %d\n",
+		ret);
+
+	return ret;
+}
+
+struct cs_etm_synth {
+	struct perf_tool dummy_tool;
+	struct perf_session *session;
+};
+
+static int cs_etm__event_synth(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine __maybe_unused)
+{
+	struct cs_etm_synth *cs_etm_synth =
+		      container_of(tool, struct cs_etm_synth, dummy_tool);
+
+	return perf_session__deliver_synth_event(cs_etm_synth->session,
+						 event, NULL);
+}
+
+static int cs_etm__synth_event(struct perf_session *session,
+			       struct perf_event_attr *attr, u64 id)
+{
+	struct cs_etm_synth cs_etm_synth;
+
+	memset(&cs_etm_synth, 0, sizeof(struct cs_etm_synth));
+	cs_etm_synth.session = session;
+
+	return perf_event__synthesize_attr(&cs_etm_synth.dummy_tool, attr, 1,
+					   &id, cs_etm__event_synth);
+}
+
+static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
+				struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	bool found = false;
+	u64 id;
+	int err;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == etm->pmu_type) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_debug("No selected events with CoreSight Trace data\n");
+		return 0;
+	}
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.size = sizeof(struct perf_event_attr);
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+			    PERF_SAMPLE_PERIOD;
+	if (etm->timeless_decoding)
+		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+	else
+		attr.sample_type |= PERF_SAMPLE_TIME;
+
+	attr.exclude_user = evsel->attr.exclude_user;
+	attr.exclude_kernel = evsel->attr.exclude_kernel;
+	attr.exclude_hv = evsel->attr.exclude_hv;
+	attr.exclude_host = evsel->attr.exclude_host;
+	attr.exclude_guest = evsel->attr.exclude_guest;
+	attr.sample_id_all = evsel->attr.sample_id_all;
+	attr.read_format = evsel->attr.read_format;
+
+	/* create new id val to be a fixed offset from evsel id */
+	id = evsel->id[0] + 1000000000;
+
+	if (!id)
+		id = 1;
+
+	if (etm->synth_opts.branches) {
+		attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+		attr.sample_period = 1;
+		attr.sample_type |= PERF_SAMPLE_ADDR;
+		err = cs_etm__synth_event(session, &attr, id);
+		if (err)
+			return err;
+		etm->sample_branches = true;
+		etm->branches_sample_type = attr.sample_type;
+		etm->branches_id = id;
+	}
+
+	return 0;
+}
+
+static int cs_etm__sample(struct cs_etm_queue *etmq)
+{
+	int ret;
+	struct cs_etm_packet packet;
+
+	while (1) {
+		ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
+		if (ret <= 0)
+			return ret;
+
+		/*
+		 * If the packet contains an instruction range, generate an
+		 * instruction sequence event.
+		 */
+		if (packet.sample_type & CS_ETM_RANGE)
+			cs_etm__synth_branch_sample(etmq, &packet);
+	}
+
+	return 0;
+}
+
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;

@@ -494,6 +645,12 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 
 		etmq->offset += processed;
 		buffer_used += processed;
+
+		/*
+		 * Nothing to do with an error condition, let's hope the next
+		 * chunk will be better.
+		 */
+		err = cs_etm__sample(etmq);
 	} while (buffer.len > buffer_used);
 
 goto more;

@@ -828,6 +985,17 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 		return 0;
 	}
 
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+		etm->synth_opts = *session->itrace_synth_opts;
+	} else {
+		itrace_synth_opts__set_default(&etm->synth_opts);
+		etm->synth_opts.callchain = false;
+	}
+
+	err = cs_etm__synth_events(etm, session);
+	if (err)
+		goto err_free_queues;
+
 	err = auxtrace_queues__process_index(&etm->queues, session);
 	if (err)
 		goto err_free_queues;

index ab2598af91eb..af7ad814b2c3 100644
@@ -1533,7 +1533,7 @@ int bpf__apply_obj_config(void)
 			(strcmp("__bpf_stdout__", 	\
 				bpf_map__name(pos)) == 0))
 
-int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
 	struct bpf_object *obj, *tmp;

index 7dece5e0cdbb..322c2b15e407 100644
@@ -110,6 +110,7 @@ struct trace {
 	bool			summary;
 	bool			summary_only;
 	bool			show_comm;
+	bool			print_sample;
 	bool			show_tool_stats;
 	bool			trace_syscalls;
 	bool			kernel_syscallchains;

@@ -1578,6 +1579,23 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
 	return printed;
 }
 
+static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
+				 struct perf_sample *sample, struct thread *thread)
+{
+	int printed = 0;
+
+	if (trace->print_sample) {
+		double ts = (double)sample->time / NSEC_PER_MSEC;
+
+		printed += fprintf(trace->output, "%22s %10.3f %s %d/%d [%d]\n",
+				   perf_evsel__name(evsel), ts,
+				   thread__comm_str(thread),
+				   sample->pid, sample->tid, sample->cpu);
+	}
+
+	return printed;
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)

@@ -1598,6 +1616,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace == NULL)
 		goto out_put;
 
+	trace__fprintf_sample(trace, evsel, sample, thread);
+
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 
 	if (ttrace->entry_str == NULL) {

@@ -1688,6 +1708,8 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace == NULL)
 		goto out_put;
 
+	trace__fprintf_sample(trace, evsel, sample, thread);
+
 	if (trace->summary)
 		thread__update_stats(ttrace, id, sample);
 

@@ -3034,6 +3056,8 @@ int cmd_trace(int argc, const char **argv)
 		     "Set the maximum stack depth when parsing the callchain, "
 		     "anything beyond the specified depth will be ignored. "
 		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
+	OPT_BOOLEAN(0, "print-sample", &trace.print_sample,
+			"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,

index 322c2b15e407..ab00096328e4 100644
@@ -821,7 +821,7 @@ static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
 	size_t printed = fprintf(fp, "(");
 
 	if (!calculated)
-		printed += fprintf(fp, "     ?   ");
+		printed += fprintf(fp, "         ");
 	else if (duration >= 1.0)
 		printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
 	else if (duration >= 0.01)

@@ -1556,10 +1556,9 @@ static void thread__update_stats(struct thread_trace *ttrace,
 	update_stats(stats, duration);
 }
 
-static int trace__printf_interrupted_entry(struct trace *trace, struct perf_sample *sample)
+static int trace__printf_interrupted_entry(struct trace *trace)
 {
 	struct thread_trace *ttrace;
-	u64 duration;
 	size_t printed;
 
 	if (trace->current == NULL)

@@ -1570,9 +1569,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
 	if (!ttrace->entry_pending)
 		return 0;
 
-	duration = sample->time - ttrace->entry_time;
-
-	printed  = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
+	printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 

@@ -1627,7 +1624,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	}
 
 	if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
-		trace__printf_interrupted_entry(trace, sample);
+		trace__printf_interrupted_entry(trace);
 
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;

@@ -1941,7 +1938,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
-	trace__printf_interrupted_entry(trace, sample);
+	trace__printf_interrupted_entry(trace);
 	trace__fprintf_tstamp(trace, sample->time, trace->output);
 
 	if (trace->trace_syscalls)

index ab00096328e4..46d3ff09440c 100644
@@ -549,6 +549,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 #include "trace/beauty/eventfd.c"
 #include "trace/beauty/flock.c"
 #include "trace/beauty/futex_op.c"
+#include "trace/beauty/futex_val3.c"
 #include "trace/beauty/mmap.c"
 #include "trace/beauty/mode_t.c"
 #include "trace/beauty/msg_flags.c"

@@ -611,7 +612,8 @@ static struct syscall_fmt {
 	{ .name	    = "fstat", .alias = "newfstat", },
 	{ .name	    = "fstatat", .alias = "newfstatat", },
 	{ .name	    = "futex",
-	  .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ }, }, },
+	  .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ },
+		   [5] = { .scnprintf = SCA_FUTEX_VAL3, /* val3 */ }, }, },
 	{ .name	    = "futimesat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
 	{ .name	    = "getitimer",

new file mode 100644
index 000000000000..26f6b3253511
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/futex.h>
+
+#ifndef FUTEX_BITSET_MATCH_ANY
+#define FUTEX_BITSET_MATCH_ANY 0xffffffff
+#endif
+
+static size_t syscall_arg__scnprintf_futex_val3(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned int bitset = arg->val;
+
+	if (bitset == FUTEX_BITSET_MATCH_ANY)
+		return scnprintf(bf, size, "MATCH_ANY");
+
+	return scnprintf(bf, size, "%#xd", bitset);
+}
+
+#define SCA_FUTEX_VAL3  syscall_arg__scnprintf_futex_val3

index 98853162eae9..55d919dc5bc6 100644
@@ -26,6 +26,9 @@
 #include <sys/timerfd.h>
 #endif
 #include <sys/time.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 #include <linux/kernel.h>
 #include <linux/time64.h>

index 3499d68e1d70..ab19a6ee4093 100644
@@ -42,6 +42,7 @@
 #include <sys/param.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <unistd.h>
 
 #include "sane_ctype.h"

index 46d3ff09440c..868306ccd8b8 100644
@@ -56,6 +56,7 @@
 #include <linux/random.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <fcntl.h>
 
 #include "sane_ctype.h"
 

index 8e709c9d512c..e8399beca62b 100644
@@ -3,6 +3,7 @@
 #include <sys/epoll.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>

index 97c9407d02a0..43519267b93b 100644
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include "perf.h"
 #include "evlist.h"
 #include "evsel.h"

index d9ffc1e6eb39..984f69144f87 100644
@@ -6,6 +6,9 @@
 #include "cgroup.h"
 #include "evlist.h"
 #include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 int nr_cgroups;
 

index 120efd85f2c8..ac35cd214feb 100644
@@ -25,6 +25,7 @@
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
 
+#include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 

index e7fbca69cbac..75f8e0ad5d76 100644
@@ -7,7 +7,6 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
-#include <fcntl.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"

index 170316795a18..34589c427e52 100644
@@ -4,6 +4,9 @@
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
 #include "../perf.h"

index 868306ccd8b8..17d11deeb88d 100644
@@ -548,7 +548,6 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 #include "trace/beauty/arch_errno_names.c"
 #include "trace/beauty/eventfd.c"
-#include "trace/beauty/flock.c"
 #include "trace/beauty/futex_op.c"
 #include "trace/beauty/futex_val3.c"
 #include "trace/beauty/mmap.c"

index d8f6b2ec7fc5..984a504d335c 100644
@@ -79,6 +79,9 @@ size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_FCNTL_ARG syscall_arg__scnprintf_fcntl_arg
 
+size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FLOCK syscall_arg__scnprintf_flock
+
 size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
 

index f9707f57566c..c4ff6ad30b06 100644
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <fcntl.h>
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/fcntl.h>
 
 #ifndef LOCK_MAND
 #define LOCK_MAND	 32

@@ -17,8 +20,7 @@
 #define LOCK_RW		192
 #endif
 
-static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
-					   struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg)
 {
 	int printed = 0, op = arg->val;
 

@@ -45,5 +47,3 @@ static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
 
 	return printed;
 }
-
-#define SCA_FLOCK syscall_arg__scnprintf_flock