From: James Clark <james.clark@arm.com>
To: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: acme@kernel.org, coresight@lists.linaro.org, leo.yan@linaro.org,
al.grant@arm.com, branislav.rankov@arm.com,
suzuki.poulose@arm.com, anshuman.khandual@arm.com,
Mike Leach <mike.leach@linaro.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
John Garry <john.garry@huawei.com>, Will Deacon <will@kernel.org>,
linux-arm-kernel@lists.infradead.org,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 6/6] perf cs-etm: Pass unformatted flag to decoder
Date: Wed, 21 Jul 2021 09:35:53 +0100 [thread overview]
Message-ID: <2af8d1ee-6dd0-42b5-6882-2396df8c07bc@arm.com> (raw)
In-Reply-To: <20210720154539.GC2296792@p14s>
On 20/07/2021 16:45, Mathieu Poirier wrote:
> On Tue, Jul 13, 2021 at 04:40:08PM +0100, James Clark wrote:
>> The TRBE (Trace Buffer Extension) feature allows a separate trace buffer
>> for each trace source, therefore the trace wouldn't need to be
>> formatted. The driver was introduced in commit 3fbf7f011f24
>> ("coresight: sink: Add TRBE driver").
>>
>> The formatted/unformatted mode is encoded in one of the flags of the
>> AUX record. The first AUX record encountered for each event is used to
>> determine the mode, and this will persist for the remaining trace that
>> is either decoded or dumped.
>>
>> Signed-off-by: James Clark <james.clark@arm.com>
>> ---
>> tools/perf/util/cs-etm.c | 42 +++++++++++++++++++++++++++-------------
>> 1 file changed, 29 insertions(+), 13 deletions(-)
>>
>> diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
>> index 760050ea936d..62769a84a53f 100644
>> --- a/tools/perf/util/cs-etm.c
>> +++ b/tools/perf/util/cs-etm.c
>> @@ -461,13 +461,14 @@ static void cs_etm__set_trace_param_etmv4(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)
>> + struct cs_etm_auxtrace *etm,
>> + int decoders_per_cpu)
>> {
>> int i;
>> u32 etmidr;
>> u64 architecture;
>>
>> - for (i = 0; i < etm->num_cpu; i++) {
>> + for (i = 0; i < decoders_per_cpu; i++) {
>> architecture = etm->metadata[i][CS_ETM_MAGIC];
>>
>> switch (architecture) {
>> @@ -488,7 +489,8 @@ static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
>>
>> static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params,
>> struct cs_etm_queue *etmq,
>> - enum cs_etm_decoder_operation mode)
>> + enum cs_etm_decoder_operation mode,
>> + bool formatted)
>> {
>> int ret = -EINVAL;
>>
>> @@ -498,7 +500,7 @@ 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 = true;
>> + d_params->formatted = formatted;
>> d_params->fsyncs = false;
>> d_params->hsyncs = false;
>> d_params->frame_aligned = true;
>> @@ -720,11 +722,13 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
>> return len;
>> }
>>
>> -static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
>> +static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
>> + bool formatted)
>> {
>> struct cs_etm_decoder_params d_params;
>> struct cs_etm_trace_params *t_params = NULL;
>> struct cs_etm_queue *etmq;
>> + int decoders_per_cpu = formatted ? etm->num_cpu : 1;
>
> I really tripped on the name "decoders_per_cpu", to a point where I had to
> review the current code before looking at this patch. I find the "_per_cpu"
> part especially puzzling. In the end the variable determines the amount of
> decoders to instantiate for a specific queue...
>
> Couldn't it be just "decoders"? Or maybe it just needs a little comment to
> disambiguate things?
>
Yeah I think just decoders will be good if I add a comment explaining why there is
a difference with formatted vs unformatted. I will re-submit with the change.
Thanks for the reviews.
James
> Thanks,
> Mathieu
>
>>
>> etmq = zalloc(sizeof(*etmq));
>> if (!etmq)
>> @@ -735,21 +739,23 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
>> goto out_free;
>>
>> /* Use metadata to fill in trace parameters for trace decoder */
>> - t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
>> + t_params = zalloc(sizeof(*t_params) * decoders_per_cpu);
>>
>> if (!t_params)
>> goto out_free;
>>
>> - if (cs_etm__init_trace_params(t_params, etm))
>> + if (cs_etm__init_trace_params(t_params, etm, decoders_per_cpu))
>> goto out_free;
>>
>> /* Set decoder parameters to decode trace packets */
>> if (cs_etm__init_decoder_params(&d_params, etmq,
>> dump_trace ? CS_ETM_OPERATION_PRINT :
>> - CS_ETM_OPERATION_DECODE))
>> + CS_ETM_OPERATION_DECODE,
>> + formatted))
>> goto out_free;
>>
>> - etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
>> + etmq->decoder = cs_etm_decoder__new(decoders_per_cpu, &d_params,
>> + t_params);
>>
>> if (!etmq->decoder)
>> goto out_free;
>> @@ -777,14 +783,15 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
>>
>> static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
>> struct auxtrace_queue *queue,
>> - unsigned int queue_nr)
>> + unsigned int queue_nr,
>> + bool formatted)
>> {
>> struct cs_etm_queue *etmq = queue->priv;
>>
>> if (list_empty(&queue->head) || etmq)
>> return 0;
>>
>> - etmq = cs_etm__alloc_queue(etm);
>> + etmq = cs_etm__alloc_queue(etm, formatted);
>>
>> if (!etmq)
>> return -ENOMEM;
>> @@ -2430,8 +2437,14 @@ 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);
>> + idx, true);
>> if (err)
>> return err;
>>
>> @@ -2678,6 +2691,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
>> union perf_event auxtrace_fragment;
>> __u64 aux_offset, aux_size;
>> __u32 idx;
>> + bool formatted;
>>
>> struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
>> struct cs_etm_auxtrace,
>> @@ -2745,7 +2759,9 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
>> return err;
>>
>> idx = auxtrace_event->idx;
>> - return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], idx);
>> + formatted = !(aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW);
>> + return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx],
>> + idx, formatted);
>> }
>>
>> /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
>> --
>> 2.28.0
>>
prev parent reply other threads:[~2021-07-21 9:00 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-13 15:40 [PATCH 0/6] perf cs-etm: Support TRBE (unformatted decoding) James Clark
2021-07-13 15:40 ` [PATCH 1/6] perf cs-etm: Refactor initialisation of kernel start address James Clark
2021-07-19 19:37 ` Mathieu Poirier
2021-07-13 15:40 ` [PATCH 2/6] perf cs-etm: Split setup and timestamp search functions James Clark
2021-07-19 19:38 ` Mathieu Poirier
2021-07-13 15:40 ` [PATCH 3/6] perf cs-etm: Only setup queues when they are modified James Clark
2021-07-19 19:38 ` Mathieu Poirier
2021-07-13 15:40 ` [PATCH 4/6] perf cs-etm: Suppress printing when resetting decoder James Clark
2021-07-19 19:39 ` Mathieu Poirier
2021-07-13 15:40 ` [PATCH 5/6] perf cs-etm: Use existing decoder instead of resetting it James Clark
2021-07-19 19:39 ` Mathieu Poirier
2021-07-13 15:40 ` [PATCH 6/6] perf cs-etm: Pass unformatted flag to decoder James Clark
2021-07-19 19:40 ` Mathieu Poirier
2021-07-20 15:45 ` Mathieu Poirier
2021-07-21 8:35 ` James Clark [this message]
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=2af8d1ee-6dd0-42b5-6882-2396df8c07bc@arm.com \
--to=james.clark@arm.com \
--cc=acme@kernel.org \
--cc=al.grant@arm.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=branislav.rankov@arm.com \
--cc=coresight@lists.linaro.org \
--cc=john.garry@huawei.com \
--cc=jolsa@redhat.com \
--cc=leo.yan@linaro.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mathieu.poirier@linaro.org \
--cc=mike.leach@linaro.org \
--cc=namhyung@kernel.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).