[SRU][N:gke][PATCH 064/106] perf: cs-etm: Allocate queues for all CPUs
Tim Whisonant
tim.whisonant at canonical.com
Mon Jul 21 16:21:47 UTC 2025
From: James Clark <james.clark at arm.com>
BugLink: https://bugs.launchpad.net/bugs/2117098
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.
Reviewed-by: Mike Leach <mike.leach at linaro.org>
Signed-off-by: James Clark <james.clark at arm.com>
Cc: Adrian Hunter <adrian.hunter at intel.com>
Cc: Alexander Shishkin <alexander.shishkin at linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue at foss.st.com>
Cc: Anshuman Khandual <anshuman.khandual at arm.com>
Cc: Ganapatrao Kulkarni <gankulkarni at os.amperecomputing.com>
Cc: Ian Rogers <irogers at google.com>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: Jiri Olsa <jolsa at kernel.org>
Cc: John Garry <john.g.garry at oracle.com>
Cc: Kan Liang <kan.liang at linux.intel.com>
Cc: Leo Yan <leo.yan at linux.dev>
Cc: Mark Rutland <mark.rutland at arm.com>
Cc: Maxime Coquelin <mcoquelin.stm32 at gmail.com>
Cc: Namhyung Kim <namhyung at kernel.org>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose at arm.com>
Cc: Will Deacon <will at kernel.org>
Link: https://lore.kernel.org/r/20240722101202.26915-3-james.clark@linaro.org
Signed-off-by: James Clark <james.clark at linaro.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme at redhat.com>
(cherry picked from commit 57880a7966be510cdaa08ab76b9d63e3df786bf0)
Signed-off-by: Tim Whisonant <tim.whisonant at canonical.com>
---
tools/perf/util/cs-etm.c | 53 +++++++++++++++++++---------------------
1 file changed, 25 insertions(+), 28 deletions(-)
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index fb2df9f69e7ed..94bcee1a92ece 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1062,16 +1062,11 @@ 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, enum cs_etm_format format)
+ unsigned int queue_nr)
{
struct cs_etm_queue *etmq = queue->priv;
- if (etmq && format != etmq->format) {
- 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();
@@ -1084,7 +1079,6 @@ 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->format = format;
return 0;
}
@@ -2808,17 +2802,6 @@ 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, FORMATTED);
- 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);
@@ -2935,7 +2918,6 @@ 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;
enum cs_etm_format format;
struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
@@ -3002,6 +2984,8 @@ 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.
@@ -3018,11 +3002,14 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
if (err)
return err;
- idx = auxtrace_event->idx;
format = (aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW) ?
UNFORMATTED : FORMATTED;
-
- return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], idx, format);
+ if (etmq->format != UNSET && format != etmq->format) {
+ pr_err("CS_ETM: mixed formatted and unformatted trace not supported\n");
+ return -EINVAL;
+ }
+ etmq->format = format;
+ return 0;
}
/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
@@ -3274,6 +3261,7 @@ static int cs_etm__create_decoders(struct cs_etm_auxtrace *etm)
* Don't create decoders for empty queues, mainly because
* etmq->format is unknown for empty queues.
*/
+ assert(empty == (etmq->format == UNSET));
if (empty)
continue;
@@ -3293,10 +3281,10 @@ 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;
@@ -3327,7 +3315,7 @@ 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,
@@ -3351,6 +3339,9 @@ 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];
}
/*
@@ -3380,10 +3371,16 @@ 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 {
@@ -3505,7 +3502,7 @@ 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:
--
2.43.0
More information about the kernel-team
mailing list