linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: James Clark <james.clark@linaro.org>
To: Mike Leach <mike.leach@linaro.org>
Cc: coresight@lists.linaro.org, suzuki.poulose@arm.com,
	gankulkarni@os.amperecomputing.com, leo.yan@linux.dev,
	anshuman.khandual@arm.com, James Clark <james.clark@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Maxime Coquelin <mcoquelin.stm32@gmail.com>,
	Alexandre Torgue <alexandre.torgue@foss.st.com>,
	John Garry <john.g.garry@oracle.com>,
	Will Deacon <will@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>, Jiri Olsa <jolsa@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	"Liang, Kan" <kan.liang@linux.intel.com>,
	linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-stm32@st-md-mailman.stormreply.com,
	linux-perf-users@vger.kernel.org
Subject: Re: [PATCH v5 02/17] perf: cs-etm: Allocate queues for all CPUs
Date: Fri, 19 Jul 2024 10:36:10 +0100	[thread overview]
Message-ID: <e355cee6-92a7-4265-ac59-731e1adee970@linaro.org> (raw)
In-Reply-To: <CAJ9a7VgUXpOo7we8v8mCMDWNtCGsHmBi5tk8YA-MeNhHk59zLg@mail.gmail.com>



On 18/07/2024 2:24 pm, Mike Leach wrote:
> Hi James
> 
> On Fri, 12 Jul 2024 at 11:22, James Clark <james.clark@linaro.org> wrote:
>>
>> From: James Clark <james.clark@arm.com>
>>
>> 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@arm.com>
>> Signed-off-by: James Clark <james.clark@linaro.org>
>> ---
>>   tools/perf/util/cs-etm.c | 76 +++++++++++++++++++++-------------------
>>   1 file changed, 40 insertions(+), 36 deletions(-)
>>
>> diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
>> index f09004c4ba44..1a95c4bb898f 100644
>> --- a/tools/perf/util/cs-etm.c
>> +++ b/tools/perf/util/cs-etm.c
>> @@ -97,13 +97,19 @@ struct cs_etm_traceid_queue {
>>          struct cs_etm_packet_queue packet_queue;
>>   };
>>
>> +enum cs_etm_format {
>> +       UNSET,
>> +       FORMATTED,
>> +       UNFORMATTED
>> +};
>> +
> 
> Minor Nit: Could this...
> 
>>   struct cs_etm_queue {
>>          struct cs_etm_auxtrace *etm;
>>          struct cs_etm_decoder *decoder;
>>          struct auxtrace_buffer *buffer;
>>          unsigned int queue_nr;
>>          u8 pending_timestamp_chan_id;
>> -       bool formatted;
>> +       enum cs_etm_format format;
> 
> and this be introduced in the previous set? Avoid a bit of churn?
> 

Yep, I'll move it

>>          u64 offset;
>>          const unsigned char *buf;
>>          size_t buf_len, buf_used;
>> @@ -697,7 +703,7 @@ static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params,
>>
>>   static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
>>                                       struct cs_etm_auxtrace *etm,
>> -                                    bool formatted,
>> +                                    enum cs_etm_format format,
>>                                       int sample_cpu,
>>                                       int decoders)
>>   {
>> @@ -706,7 +712,7 @@ static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
>>          u64 architecture;
>>
>>          for (t_idx = 0; t_idx < decoders; t_idx++) {
>> -               if (formatted)
>> +               if (format == FORMATTED)
>>                          m_idx = t_idx;
>>                  else {
>>                          m_idx = get_cpu_data_idx(etm, sample_cpu);
>> @@ -749,7 +755,7 @@ static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params,
>>          d_params->packet_printer = cs_etm__packet_dump;
>>          d_params->operation = mode;
>>          d_params->data = etmq;
>> -       d_params->formatted = etmq->formatted;
>> +       d_params->formatted = etmq->format == FORMATTED;
>>          d_params->fsyncs = false;
>>          d_params->hsyncs = false;
>>          d_params->frame_aligned = true;
>> @@ -1056,16 +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, 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 +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->formatted = formatted;
>>
>>          return 0;
>>   }
>> @@ -2791,17 +2791,6 @@ 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);
>> @@ -2918,8 +2907,7 @@ 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;
>> +       enum cs_etm_format format;
>>
>>          struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
>>                                                     struct cs_etm_auxtrace,
>> @@ -2985,6 +2973,8 @@ 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 +2991,14 @@ 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);
>> +               format = (aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW) ?
>> +                               UNFORMATTED : FORMATTED;
>> +               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' */
>> @@ -3200,7 +3194,7 @@ static int cs_etm__create_queue_decoders(struct cs_etm_queue *etmq)
>>           * Each queue can only contain data from one CPU when unformatted, so only one decoder is
>>           * needed.
>>           */
>> -       int decoders = etmq->formatted ? etmq->etm->num_cpu : 1;
>> +       int decoders = etmq->format == FORMATTED ? etmq->etm->num_cpu : 1;
>>
>>          /* Use metadata to fill in trace parameters for trace decoder */
>>          struct cs_etm_trace_params  *t_params = zalloc(sizeof(*t_params) * decoders);
>> @@ -3208,7 +3202,7 @@ static int cs_etm__create_queue_decoders(struct cs_etm_queue *etmq)
>>          if (!t_params)
>>                  goto out_free;
>>
>> -       if (cs_etm__init_trace_params(t_params, etmq->etm, etmq->formatted,
>> +       if (cs_etm__init_trace_params(t_params, etmq->etm, etmq->format,
>>                                        etmq->queue_nr, decoders))
>>                  goto out_free;
>>
>> @@ -3256,6 +3250,7 @@ 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->format == UNSET));
>>                  if (empty)
>>                          continue;
>>
>> @@ -3275,10 +3270,10 @@ 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 +3304,7 @@ 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 +3328,9 @@ 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 +3360,16 @@ 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 +3491,7 @@ 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
>>
> 
> Reviewed-by: Mike Leach <mike.leach@linaro.org>
> 
> 
> --
> Mike Leach
> Principal Engineer, ARM Ltd.
> Manchester Design Centre. UK

  reply	other threads:[~2024-07-19  9:36 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-12 10:20 [PATCH v5 00/17] coresight: Use per-sink trace ID maps for Perf sessions James Clark
2024-07-12 10:20 ` [PATCH v5 01/17] perf: cs-etm: Create decoders after both AUX and HW_ID search passes James Clark
2024-07-18 13:23   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 02/17] perf: cs-etm: Allocate queues for all CPUs James Clark
2024-07-18 13:24   ` Mike Leach
2024-07-19  9:36     ` James Clark [this message]
2024-07-12 10:20 ` [PATCH v5 03/17] perf: cs-etm: Move traceid_list to each queue James Clark
2024-07-18 13:24   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 04/17] perf: cs-etm: Create decoders based on the trace ID mappings James Clark
2024-07-18 13:24   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 05/17] perf: cs-etm: Only save valid trace IDs into files James Clark
2024-07-18 13:24   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 06/17] perf: cs-etm: Support version 0.1 of HW_ID packets James Clark
2024-07-18 13:24   ` Mike Leach
2024-07-19 10:48     ` James Clark
2024-07-19 10:49       ` James Clark
2024-07-19 13:45         ` Mike Leach
2024-07-19 13:57           ` James Clark
2024-07-12 10:20 ` [PATCH v5 07/17] perf: cs-etm: Print queue number in raw trace dump James Clark
2024-07-18 13:25   ` Mike Leach
2024-07-18 14:30     ` James Clark
2024-07-12 10:20 ` [PATCH v5 08/17] perf: cs-etm: Add runtime version check for OpenCSD James Clark
2024-07-18 13:25   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 09/17] coresight: Remove unused ETM Perf stubs James Clark
2024-07-12 10:20 ` [PATCH v5 10/17] coresight: Clarify comments around the PID of the sink owner James Clark
2024-07-12 10:20 ` [PATCH v5 11/17] coresight: Move struct coresight_trace_id_map to common header James Clark
2024-07-12 10:20 ` [PATCH v5 12/17] coresight: Expose map arguments in trace ID API James Clark
2024-07-17 15:03   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 13/17] coresight: Make CPU id map a property of a trace ID map James Clark
2024-07-17 15:03   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 14/17] coresight: Use per-sink trace ID maps for Perf sessions James Clark
2024-07-17 15:03   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 15/17] coresight: Remove pending trace ID release mechanism James Clark
2024-07-17 15:03   ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 16/17] coresight: Emit sink ID in the HW_ID packets James Clark
2024-07-17 15:03   ` Mike Leach
2024-07-19  9:29     ` James Clark
2024-07-19  9:48       ` Mike Leach
2024-07-12 10:20 ` [PATCH v5 17/17] coresight: Make trace ID map spinlock local to the map James Clark
2024-07-17 15:03   ` Mike Leach

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e355cee6-92a7-4265-ac59-731e1adee970@linaro.org \
    --to=james.clark@linaro.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=alexandre.torgue@foss.st.com \
    --cc=anshuman.khandual@arm.com \
    --cc=coresight@lists.linaro.org \
    --cc=gankulkarni@os.amperecomputing.com \
    --cc=irogers@google.com \
    --cc=james.clark@arm.com \
    --cc=john.g.garry@oracle.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=leo.yan@linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux-stm32@st-md-mailman.stormreply.com \
    --cc=mark.rutland@arm.com \
    --cc=mcoquelin.stm32@gmail.com \
    --cc=mike.leach@linaro.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=suzuki.poulose@arm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).