return 0;
}
+static int cs_etm__metadata_get_trace_id(u8 *trace_chan_id, u64 *cpu_metadata)
+{
+ u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC];
+
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ *trace_chan_id = (u8)(cpu_metadata[CS_ETM_ETMTRACEIDR] &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ *trace_chan_id = (u8)(cpu_metadata[CS_ETMV4_TRCTRACEIDR] &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * 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)
+{
+ u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC];
+
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ cpu_metadata[CS_ETM_ETMTRACEIDR] = trace_chan_id;
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ cpu_metadata[CS_ETMV4_TRCTRACEIDR] = trace_chan_id;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * FIELD_GET (linux/bitfield.h) not available outside kernel code,
+ * and the header contains too many dependencies to just copy over,
+ * so roll our own based on the original
+ */
+#define __bf_shf(x) (__builtin_ffsll(x) - 1)
+#define FIELD_GET(_mask, _reg) \
+ ({ \
+ (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \
+ })
+
+/*
+ * Handle the PERF_RECORD_AUX_OUTPUT_HW_ID event.
+ *
+ * The payload associates the Trace ID and the CPU.
+ * The routine is tolerant of seeing multiple packets with the same association,
+ * but a CPU / Trace ID association changing during a session is an error.
+ */
+static int cs_etm__process_aux_output_hw_id(struct perf_session *session,
+ union perf_event *event)
+{
+ struct cs_etm_auxtrace *etm;
+ struct perf_sample sample;
+ struct int_node *inode;
+ struct evsel *evsel;
+ u64 *cpu_data;
+ u64 hw_id;
+ int cpu, version, err;
+ u8 trace_chan_id, curr_chan_id;
+
+ /* extract and parse the HW ID */
+ hw_id = event->aux_output_hw_id.hw_id;
+ version = FIELD_GET(CS_AUX_HW_ID_VERSION_MASK, hw_id);
+ trace_chan_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id);
+
+ /* check that we can handle this version */
+ if (version > CS_AUX_HW_ID_CURR_VERSION)
+ return -EINVAL;
+
+ /* get access to the etm metadata */
+ etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace);
+ if (!etm || !etm->metadata)
+ return -EINVAL;
+
+ /* parse the sample to get the CPU */
+ evsel = evlist__event2evsel(session->evlist, event);
+ if (!evsel)
+ return -EINVAL;
+ err = evsel__parse_sample(evsel, event, &sample);
+ if (err)
+ return err;
+ cpu = sample.cpu;
+ if (cpu == -1) {
+ /* no CPU in the sample - possibly recorded with an old version of perf */
+ pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record.");
+ return -EINVAL;
+ }
+
+ /* See if the ID is mapped to a CPU, and it matches the current CPU */
+ inode = intlist__find(traceid_list, trace_chan_id);
+ if (inode) {
+ cpu_data = inode->priv;
+ if ((int)cpu_data[CS_ETM_CPU] != cpu) {
+ pr_err("CS_ETM: map mismatch between HW_ID packet CPU and Trace ID\n");
+ return -EINVAL;
+ }
+
+ /* check that the mapped ID matches */
+ err = cs_etm__metadata_get_trace_id(&curr_chan_id, cpu_data);
+ if (err)
+ return err;
+ if (curr_chan_id != trace_chan_id) {
+ pr_err("CS_ETM: mismatch between CPU trace ID and HW_ID packet ID\n");
+ return -EINVAL;
+ }
+
+ /* mapped and matched - return OK */
+ return 0;
+ }
+
+ /* not one we've seen before - lets map it */
+ cpu_data = etm->metadata[cpu];
+ err = cs_etm__map_trace_id(trace_chan_id, cpu_data);
+ if (err)
+ return err;
+
+ /*
+ * if we are picking up the association from the packet, need to plug
+ * the correct trace ID into the metadata for setting up decoders later.
+ */
+ err = cs_etm__metadata_set_trace_id(trace_chan_id, cpu_data);
+ return err;
+}
+
void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
u8 trace_chan_id)
{
}
/*
- * 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.
+ * In per-thread mode, auxtrace CPU is set to -1, but TID will be set instead. See
+ * auxtrace_mmap_params__set_idx(). However, the sample AUX event will contain a
+ * CPU as we set this always for the AUX_OUTPUT_HW_ID event.
+ * So now compare only TIDs if auxtrace CPU is -1, and CPUs if auxtrace CPU is not -1.
+ * Return 'not found' if mismatch.
*/
- if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) ||
- auxtrace_event->cpu != sample->cpu)
+ if (auxtrace_event->cpu == (__u32) -1) {
+ if (auxtrace_event->tid != sample->tid)
+ return 1;
+ } else if (auxtrace_event->cpu != sample->cpu)
return 1;
if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) {
return 1;
}
+static int cs_etm__process_aux_hw_id_cb(struct perf_session *session, union perf_event *event,
+ u64 offset __maybe_unused, void *data __maybe_unused)
+{
+ /* look to handle PERF_RECORD_AUX_OUTPUT_HW_ID early to ensure decoders can be set up */
+ if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) {
+ (*(int *)data)++; /* increment found count */
+ return cs_etm__process_aux_output_hw_id(session, event);
+ }
+ return 0;
+}
+
static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event,
u64 offset __maybe_unused, void *data __maybe_unused)
{
cs_etm_magic = metadata[i][CS_ETM_MAGIC];
switch (cs_etm_magic) {
case __perf_cs_etmv3_magic:
- trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) &
- CORESIGHT_TRACE_ID_VAL_MASK);
+ metadata[i][CS_ETM_ETMTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK;
+ trace_chan_id = (u8)(metadata[i][CS_ETM_ETMTRACEIDR]);
break;
case __perf_cs_etmv4_magic:
case __perf_cs_ete_magic:
- trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) &
- CORESIGHT_TRACE_ID_VAL_MASK);
+ metadata[i][CS_ETMV4_TRCTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK;
+ trace_chan_id = (u8)(metadata[i][CS_ETMV4_TRCTRACEIDR]);
break;
default:
/* unknown magic number */
return 0;
}
+/*
+ * 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;
+}
+
int cs_etm__process_auxtrace_info_full(union perf_event *event,
struct perf_session *session)
{
int priv_size = 0;
int num_cpu;
int err = 0;
+ int aux_hw_id_found;
int i, j;
u64 *ptr = NULL;
u64 **metadata = NULL;
if (err)
goto err_delete_thread;
- /* before aux records are queued, need to map metadata to trace IDs */
- err = cs_etm__map_trace_ids_metadata(num_cpu, metadata);
+ /*
+ * 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.
+ *
+ * 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
+ * in which case a different value will be used. This means an older perf may still
+ * be able to record and read files generate on a newer system.
+ *
+ * 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.
+ *
+ * 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.
+ */
+
+ /* first scan for AUX_OUTPUT_HW_ID records to map trace ID values to CPU metadata */
+ aux_hw_id_found = 0;
+ err = perf_session__peek_events(session, session->header.data_offset,
+ session->header.data_size,
+ cs_etm__process_aux_hw_id_cb, &aux_hw_id_found);
+ if (err)
+ goto err_delete_thread;
+
+ /* 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
+ err = cs_etm__map_trace_ids_metadata(num_cpu, metadata);
+
if (err)
goto err_delete_thread;
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;
err_delete_thread:
projects / platform / kernel / linux-rpi.git / commitdiff