perf: cs-etm: Create decoders based on the trace ID mappings

Now that each queue has a unique set of trace ID mappings, use this
list to create the decoders. In unformatted mode just add a single
mapping so only one decoder is made.

Previously each queue would have a decoder created for each traced CPU
on the system but this won't work anymore because CPUs can have
overlapping trace IDs.

This also means that the CORESIGHT_TRACE_ID_UNUSED_FLAG isn't needed
any more. If mappings aren't added then decoders aren't created, rather
than needing a flag to suppress creation.

Reviewed-by: Mike Leach <[e-mail]>
Signed-off-by: James Clark <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Alexandre Torgue <[e-mail]>
Cc: Anshuman Khandual <[e-mail]>
Cc: Ganapatrao Kulkarni <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: John Garry <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Leo Yan <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Maxime Coquelin <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Suzuki Poulouse <[e-mail]>
Cc: Will Deacon <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: James Clark <[e-mail]>
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/arch/arm/util/cs-etm.c

···
 	/* Get trace configuration register */
 	data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr);
 	/* traceID set to legacy version, in case new perf running on older system */
-	data[CS_ETMV4_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu) |
-				     CORESIGHT_TRACE_ID_UNUSED_FLAG;
+	data[CS_ETMV4_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu);
 
 	/* Get read-only information from sysFS */
 	cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0],
···
 	/* Get trace configuration register */
 	data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr);
 	/* traceID set to legacy version, in case new perf running on older system */
-	data[CS_ETE_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
+	data[CS_ETE_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu);
 
 	/* Get read-only information from sysFS */
 	cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCIDR0], &data[CS_ETE_TRCIDR0]);
···
 		/* Get configuration register */
 		info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
 		/* traceID set to legacy value in case new perf running on old system */
-		info->priv[*offset + CS_ETM_ETMTRACEIDR] = cs_etm_get_legacy_trace_id(cpu) |
-							   CORESIGHT_TRACE_ID_UNUSED_FLAG;
+		info->priv[*offset + CS_ETM_ETMTRACEIDR] = cs_etm_get_legacy_trace_id(cpu);
 		/* Get read-only information from sysFS */
 		cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv3_ro[CS_ETM_ETMCCER],
 			      &info->priv[*offset + CS_ETM_ETMCCER]);

tools/perf/util/cs-etm-decoder/cs-etm-decoder.c

···
 		return -1;
 	}
 
-	/* if the CPU has no trace ID associated, no decoder needed */
-	if (csid == CORESIGHT_TRACE_ID_UNUSED_VAL)
-		return 0;
-
 	if (d_params->operation == CS_ETM_OPERATION_DECODE) {
 		if (ocsd_dt_create_decoder(decoder->dcd_tree,
 					   decoder->decoder_name,

tools/perf/util/cs-etm.c

···
 
 /*
  * update metadata trace ID from the value found in the AUX_HW_INFO packet.
- * This will also clear the CORESIGHT_TRACE_ID_UNUSED_FLAG flag if present.
  */
 static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
 {
···
 }
 
 static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int t_idx,
-					  int m_idx, u32 etmidr)
+					  u64 *metadata, u32 etmidr)
 {
-	u64 **metadata = etm->metadata;
-
-	t_params[t_idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
-	t_params[t_idx].etmv3.reg_ctrl = metadata[m_idx][CS_ETM_ETMCR];
-	t_params[t_idx].etmv3.reg_trc_id = metadata[m_idx][CS_ETM_ETMTRACEIDR];
+	t_params->protocol = cs_etm__get_v7_protocol_version(etmidr);
+	t_params->etmv3.reg_ctrl = metadata[CS_ETM_ETMCR];
+	t_params->etmv3.reg_trc_id = metadata[CS_ETM_ETMTRACEIDR];
 }
 
 static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int t_idx,
-					  int m_idx)
+					  u64 *metadata)
 {
-	u64 **metadata = etm->metadata;
-
-	t_params[t_idx].protocol = CS_ETM_PROTO_ETMV4i;
-	t_params[t_idx].etmv4.reg_idr0 = metadata[m_idx][CS_ETMV4_TRCIDR0];
-	t_params[t_idx].etmv4.reg_idr1 = metadata[m_idx][CS_ETMV4_TRCIDR1];
-	t_params[t_idx].etmv4.reg_idr2 = metadata[m_idx][CS_ETMV4_TRCIDR2];
-	t_params[t_idx].etmv4.reg_idr8 = metadata[m_idx][CS_ETMV4_TRCIDR8];
-	t_params[t_idx].etmv4.reg_configr = metadata[m_idx][CS_ETMV4_TRCCONFIGR];
-	t_params[t_idx].etmv4.reg_traceidr = metadata[m_idx][CS_ETMV4_TRCTRACEIDR];
+	t_params->protocol = CS_ETM_PROTO_ETMV4i;
+	t_params->etmv4.reg_idr0 = metadata[CS_ETMV4_TRCIDR0];
+	t_params->etmv4.reg_idr1 = metadata[CS_ETMV4_TRCIDR1];
+	t_params->etmv4.reg_idr2 = metadata[CS_ETMV4_TRCIDR2];
+	t_params->etmv4.reg_idr8 = metadata[CS_ETMV4_TRCIDR8];
+	t_params->etmv4.reg_configr = metadata[CS_ETMV4_TRCCONFIGR];
+	t_params->etmv4.reg_traceidr = metadata[CS_ETMV4_TRCTRACEIDR];
 }
 
 static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int t_idx,
-					  int m_idx)
+					u64 *metadata)
 {
-	u64 **metadata = etm->metadata;
-
-	t_params[t_idx].protocol = CS_ETM_PROTO_ETE;
-	t_params[t_idx].ete.reg_idr0 = metadata[m_idx][CS_ETE_TRCIDR0];
-	t_params[t_idx].ete.reg_idr1 = metadata[m_idx][CS_ETE_TRCIDR1];
-	t_params[t_idx].ete.reg_idr2 = metadata[m_idx][CS_ETE_TRCIDR2];
-	t_params[t_idx].ete.reg_idr8 = metadata[m_idx][CS_ETE_TRCIDR8];
-	t_params[t_idx].ete.reg_configr = metadata[m_idx][CS_ETE_TRCCONFIGR];
-	t_params[t_idx].ete.reg_traceidr = metadata[m_idx][CS_ETE_TRCTRACEIDR];
-	t_params[t_idx].ete.reg_devarch = metadata[m_idx][CS_ETE_TRCDEVARCH];
+	t_params->protocol = CS_ETM_PROTO_ETE;
+	t_params->ete.reg_idr0 = metadata[CS_ETE_TRCIDR0];
+	t_params->ete.reg_idr1 = metadata[CS_ETE_TRCIDR1];
+	t_params->ete.reg_idr2 = metadata[CS_ETE_TRCIDR2];
+	t_params->ete.reg_idr8 = metadata[CS_ETE_TRCIDR8];
+	t_params->ete.reg_configr = metadata[CS_ETE_TRCCONFIGR];
+	t_params->ete.reg_traceidr = metadata[CS_ETE_TRCTRACEIDR];
+	t_params->ete.reg_devarch = metadata[CS_ETE_TRCDEVARCH];
 }
 
 static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
-				     struct cs_etm_auxtrace *etm,
-				     enum cs_etm_format format,
-				     int sample_cpu,
-				     int decoders)
+				     struct cs_etm_queue *etmq)
 {
-	int t_idx, m_idx;
-	u32 etmidr;
-	u64 architecture;
+	struct int_node *inode;
 
-	for (t_idx = 0; t_idx < decoders; t_idx++) {
-		if (format == FORMATTED)
-			m_idx = t_idx;
-		else {
-			m_idx = get_cpu_data_idx(etm, sample_cpu);
-			if (m_idx == -1) {
-				pr_warning("CS_ETM: unknown CPU, falling back to first metadata\n");
-				m_idx = 0;
-			}
-		}
-
-		architecture = etm->metadata[m_idx][CS_ETM_MAGIC];
+	intlist__for_each_entry(inode, etmq->traceid_list) {
+		u64 *metadata = inode->priv;
+		u64 architecture = metadata[CS_ETM_MAGIC];
+		u32 etmidr;
 
 		switch (architecture) {
 		case __perf_cs_etmv3_magic:
-			etmidr = etm->metadata[m_idx][CS_ETM_ETMIDR];
-			cs_etm__set_trace_param_etmv3(t_params, etm, t_idx, m_idx, etmidr);
+			etmidr = metadata[CS_ETM_ETMIDR];
+			cs_etm__set_trace_param_etmv3(t_params++, metadata, etmidr);
 			break;
 		case __perf_cs_etmv4_magic:
-			cs_etm__set_trace_param_etmv4(t_params, etm, t_idx, m_idx);
+			cs_etm__set_trace_param_etmv4(t_params++, metadata);
 			break;
 		case __perf_cs_ete_magic:
-			cs_etm__set_trace_param_ete(t_params, etm, t_idx, m_idx);
+			cs_etm__set_trace_param_ete(t_params++, metadata);
 			break;
 		default:
 			return -EINVAL;
···
 }
 
 /*
- * If we found AUX_HW_ID packets, then set any metadata marked as unused to the
- * unused value to reduce the number of unneeded decoders created.
- */
-static int cs_etm__clear_unused_trace_ids_metadata(int num_cpu, u64 **metadata)
-{
-	u64 cs_etm_magic;
-	int i;
-
-	for (i = 0; i < num_cpu; i++) {
-		cs_etm_magic = metadata[i][CS_ETM_MAGIC];
-		switch (cs_etm_magic) {
-		case __perf_cs_etmv3_magic:
-			if (metadata[i][CS_ETM_ETMTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG)
-				metadata[i][CS_ETM_ETMTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL;
-			break;
-		case __perf_cs_etmv4_magic:
-		case __perf_cs_ete_magic:
-			if (metadata[i][CS_ETMV4_TRCTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG)
-				metadata[i][CS_ETMV4_TRCTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL;
-			break;
-		default:
-			/* unknown magic number */
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
-/*
  * Use the data gathered by the peeks for HW_ID (trace ID mappings) and AUX
  * (formatted or not) packets to create the decoders.
  */
 static int cs_etm__create_queue_decoders(struct cs_etm_queue *etmq)
 {
 	struct cs_etm_decoder_params d_params;
+	struct cs_etm_trace_params  *t_params;
+	int decoders = intlist__nr_entries(etmq->traceid_list);
+
+	if (decoders == 0)
+		return 0;
 
 	/*
 	 * Each queue can only contain data from one CPU when unformatted, so only one decoder is
 	 * needed.
 	 */
-	int decoders = etmq->format == FORMATTED ? etmq->etm->num_cpu : 1;
+	if (etmq->format == UNFORMATTED)
+		assert(decoders == 1);
 
 	/* Use metadata to fill in trace parameters for trace decoder */
-	struct cs_etm_trace_params  *t_params = zalloc(sizeof(*t_params) * decoders);
+	t_params = zalloc(sizeof(*t_params) * decoders);
 
 	if (!t_params)
 		goto out_free;
 
-	if (cs_etm__init_trace_params(t_params, etmq->etm, etmq->format,
-				      etmq->queue_nr, decoders))
+	if (cs_etm__init_trace_params(t_params, etmq))
 		goto out_free;
 
 	/* Set decoder parameters to decode trace packets */
···
 	/*
 	 * Map Trace ID values to CPU metadata.
 	 *
-	 * Trace metadata will always contain Trace ID values from the legacy algorithm. If the
-	 * files has been recorded by a "new" perf updated to handle AUX_HW_ID then the metadata
-	 * ID value will also have the CORESIGHT_TRACE_ID_UNUSED_FLAG set.
+	 * Trace metadata will always contain Trace ID values from the legacy algorithm
+	 * in case it's read by a version of Perf that doesn't know about HW_ID packets
+	 * or the kernel doesn't emit them.
 	 *
 	 * The updated kernel drivers that use AUX_HW_ID to sent Trace IDs will attempt to use
 	 * the same IDs as the old algorithm as far as is possible, unless there are clashes
···
 	 *
 	 * For a perf able to interpret AUX_HW_ID packets we first check for the presence of
 	 * those packets. If they are there then the values will be mapped and plugged into
-	 * the metadata. We then set any remaining metadata values with the used flag to a
-	 * value CORESIGHT_TRACE_ID_UNUSED_VAL - which indicates no decoder is required.
+	 * the metadata and decoders are only created for each mapping received.
 	 *
 	 * If no AUX_HW_ID packets are present - which means a file recorded on an old kernel
-	 * then we map Trace ID values to CPU directly from the metadata - clearing any unused
-	 * flags if present.
+	 * then we map Trace ID values to CPU directly from the metadata and create decoders
+	 * for all mappings.
 	 */
 
 	/* Scan for AUX_OUTPUT_HW_ID records to map trace ID values to CPU metadata */
···
 	if (err)
 		goto err_free_queues;
 
-	/* if HW ID found then clear any unused metadata ID values */
-	if (aux_hw_id_found)
-		err = cs_etm__clear_unused_trace_ids_metadata(num_cpu, metadata);
-	/* otherwise, this is a file with metadata values only, map from metadata */
-	else
+	/* if no HW ID found this is a file with metadata values only, map from metadata */
+	if (!aux_hw_id_found) {
 		err = cs_etm__map_trace_ids_metadata(etm, num_cpu, metadata);
-
-	if (err)
-		goto err_free_queues;
+		if (err)
+			goto err_free_queues;
+	}
 
 	err = cs_etm__create_decoders(etm);
 	if (err)

tools/perf/util/cs-etm.h

···
 /* CoreSight trace ID is currently the bottom 7 bits of the value */
 #define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
 
-/*
- * perf record will set the legacy meta data values as unused initially.
- * This allows perf report to manage the decoders created when dynamic
- * allocation in operation.
- */
-#define CORESIGHT_TRACE_ID_UNUSED_FLAG	BIT(31)
-
-/* Value to set for unused trace ID values */
-#define CORESIGHT_TRACE_ID_UNUSED_VAL	0x7F
-
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
 void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr);