[PATCH 04/17] perf: cs-etm: Allocate queues for all CPUs

From: James Clark
Date: Mon Apr 29 2024 - 11:25:25 EST


Make cs_etm__setup_queue() setup a queue even if it's empty, and
pre-allocate queues based on the max CPU that was recorded. In per-CPU
mode aux queues are indexed based on CPU ID even if all CPUs aren't
recorded, sparse queue arrays aren't used.

This will allow HW_IDs to be saved even if no aux data was received in
that queue without having to call cs_etm__setup_queue() from two
different places.

Signed-off-by: James Clark <james.clark@xxxxxxx>
---
tools/perf/util/cs-etm.c | 55 ++++++++++++++++++++--------------------
1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index f09004c4ba44..e40dfd09d3ed 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -104,6 +104,7 @@ struct cs_etm_queue {
unsigned int queue_nr;
u8 pending_timestamp_chan_id;
bool formatted;
+ bool formatted_set;
u64 offset;
const unsigned char *buf;
size_t buf_len, buf_used;
@@ -1056,16 +1057,11 @@ static struct cs_etm_queue *cs_etm__alloc_queue(void)

static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
struct auxtrace_queue *queue,
- unsigned int queue_nr, bool formatted)
+ unsigned int queue_nr)
{
struct cs_etm_queue *etmq = queue->priv;

- if (etmq && formatted != etmq->formatted) {
- pr_err("CS_ETM: mixed formatted and unformatted trace not supported\n");
- return -EINVAL;
- }
-
- if (list_empty(&queue->head) || etmq)
+ if (etmq)
return 0;

etmq = cs_etm__alloc_queue();
@@ -1078,7 +1074,6 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
etmq->queue_nr = queue_nr;
queue->cpu = queue_nr; /* Placeholder, may be reset to -1 in per-thread mode */
etmq->offset = 0;
- etmq->formatted = formatted;

return 0;
}
@@ -2791,17 +2786,6 @@ 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->queues.queue_array[idx].priv, buffer);
@@ -2918,7 +2902,6 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
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,
@@ -2985,6 +2968,8 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o

if (aux_offset >= auxtrace_event->offset &&
aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) {
+ struct cs_etm_queue *etmq = etm->queues.queue_array[auxtrace_event->idx].priv;
+
/*
* 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.
@@ -3001,10 +2986,14 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
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);
+ if (etmq->formatted_set && formatted != etmq->formatted) {
+ pr_err("CS_ETM: mixed formatted and unformatted trace not supported\n");
+ return -EINVAL;
+ }
+ etmq->formatted = formatted;
+ etmq->formatted_set = true;
+ return 0;
}

/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
@@ -3256,6 +3245,7 @@ static int cs_etm__create_decoders(struct cs_etm_auxtrace *etm)
* Don't create decoders for empty queues, mainly because
* etmq->formatted is unknown for empty queues.
*/
+ assert(empty == !etmq->formatted_set);
if (empty)
continue;

@@ -3275,10 +3265,10 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
int event_header_size = sizeof(struct perf_event_header);
int total_size = auxtrace_info->header.size;
int priv_size = 0;
- int num_cpu;
+ int num_cpu, max_cpu = 0;
int err = 0;
int aux_hw_id_found;
- int i, j;
+ int i;
u64 *ptr = NULL;
u64 **metadata = NULL;

@@ -3309,7 +3299,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
* required by the trace decoder to properly decode the trace due
* to its highly compressed nature.
*/
- for (j = 0; j < num_cpu; j++) {
+ for (int j = 0; j < num_cpu; j++) {
if (ptr[i] == __perf_cs_etmv3_magic) {
metadata[j] =
cs_etm__create_meta_blk(ptr, &i,
@@ -3333,6 +3323,9 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
err = -ENOMEM;
goto err_free_metadata;
}
+
+ if ((int) metadata[j][CS_ETM_CPU] > max_cpu)
+ max_cpu = metadata[j][CS_ETM_CPU];
}

/*
@@ -3362,10 +3355,16 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
*/
etm->pid_fmt = cs_etm__init_pid_fmt(metadata[0]);

- err = auxtrace_queues__init(&etm->queues);
+ err = auxtrace_queues__init_nr(&etm->queues, max_cpu + 1);
if (err)
goto err_free_etm;

+ for (unsigned int j = 0; j < etm->queues.nr_queues; ++j) {
+ err = cs_etm__setup_queue(etm, &etm->queues.queue_array[j], j);
+ if (err)
+ goto err_free_queues;
+ }
+
if (session->itrace_synth_opts->set) {
etm->synth_opts = *session->itrace_synth_opts;
} else {
@@ -3487,7 +3486,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
zfree(&etm);
err_free_metadata:
/* No need to check @metadata[j], free(NULL) is supported */
- for (j = 0; j < num_cpu; j++)
+ for (int j = 0; j < num_cpu; j++)
zfree(&metadata[j]);
zfree(&metadata);
err_free_traceid_list:
--
2.34.1