From: Suzuki K Poulose <suzuki.poulose@arm.com> To: Anshuman Khandual <anshuman.khandual@arm.com>, coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, tamas.zsoldos@arm.com, al.grant@arm.com, leo.yan@linaro.org, mike.leach@linaro.org, mathieu.poirier@linaro.org, jinlmao@qti.qualcomm.com Subject: Re: [PATCH v2 04/10] coresight: trbe: Ensure the format flag is set on truncation Date: Fri, 30 Jul 2021 12:37:18 +0100 [thread overview] Message-ID: <a06e22d1-5f5c-87f1-d96c-fbda83fcd576@arm.com> (raw) In-Reply-To: <c7c09fa6-8010-ab7c-1c32-8598e519ac97@arm.com> On 30/07/2021 05:26, Anshuman Khandual wrote: > > > On 7/23/21 6:16 PM, Suzuki K Poulose wrote: >> When the TRBE is stopped on truncating an event, we may not >> set the FORMAT flag, even though the size of the record is 0. >> Let us be consistent and not confuse the user. Always set the >> format flag for TRBE generated records. >> >> Cc: Anshuman Khandual <anshuman.khandual@arm.com> >> Cc: Leo Yan <leo.yan@linaro.org> >> Cc: Mike Leach <mike.leach@linaro.org> >> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> >> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> >> --- >> drivers/hwtracing/coresight/coresight-trbe.c | 3 ++- >> 1 file changed, 2 insertions(+), 1 deletion(-) >> >> diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c >> index 176868496879..446f080f8320 100644 >> --- a/drivers/hwtracing/coresight/coresight-trbe.c >> +++ b/drivers/hwtracing/coresight/coresight-trbe.c >> @@ -132,7 +132,8 @@ static void trbe_stop_and_truncate_event(struct perf_output_handle *handle) >> * the update_buffer() to return a 0 size. >> */ >> trbe_drain_and_disable_local(); >> - perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); >> + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED | >> + PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW); >> *this_cpu_ptr(buf->cpudata->drvdata->handle) = NULL; >> } > > But why should not PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW also be set on > zero sized records as well ? Otherwise there are two instances during > TRBE buffer management, where PERF_AUX_FLAG_TRUNCATED is marked alone > without PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW. Those could be changed as > well. All records (irrespective of the size) generated by the TRBE must contain the "RAW" flag. Did I miss another instance where we don't do this ? Suzuki >
WARNING: multiple messages have this Message-ID (diff)
From: Suzuki K Poulose <suzuki.poulose@arm.com> To: Anshuman Khandual <anshuman.khandual@arm.com>, coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, tamas.zsoldos@arm.com, al.grant@arm.com, leo.yan@linaro.org, mike.leach@linaro.org, mathieu.poirier@linaro.org, jinlmao@qti.qualcomm.com Subject: Re: [PATCH v2 04/10] coresight: trbe: Ensure the format flag is set on truncation Date: Fri, 30 Jul 2021 12:37:18 +0100 [thread overview] Message-ID: <a06e22d1-5f5c-87f1-d96c-fbda83fcd576@arm.com> (raw) In-Reply-To: <c7c09fa6-8010-ab7c-1c32-8598e519ac97@arm.com> On 30/07/2021 05:26, Anshuman Khandual wrote: > > > On 7/23/21 6:16 PM, Suzuki K Poulose wrote: >> When the TRBE is stopped on truncating an event, we may not >> set the FORMAT flag, even though the size of the record is 0. >> Let us be consistent and not confuse the user. Always set the >> format flag for TRBE generated records. >> >> Cc: Anshuman Khandual <anshuman.khandual@arm.com> >> Cc: Leo Yan <leo.yan@linaro.org> >> Cc: Mike Leach <mike.leach@linaro.org> >> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> >> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> >> --- >> drivers/hwtracing/coresight/coresight-trbe.c | 3 ++- >> 1 file changed, 2 insertions(+), 1 deletion(-) >> >> diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c >> index 176868496879..446f080f8320 100644 >> --- a/drivers/hwtracing/coresight/coresight-trbe.c >> +++ b/drivers/hwtracing/coresight/coresight-trbe.c >> @@ -132,7 +132,8 @@ static void trbe_stop_and_truncate_event(struct perf_output_handle *handle) >> * the update_buffer() to return a 0 size. >> */ >> trbe_drain_and_disable_local(); >> - perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); >> + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED | >> + PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW); >> *this_cpu_ptr(buf->cpudata->drvdata->handle) = NULL; >> } > > But why should not PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW also be set on > zero sized records as well ? Otherwise there are two instances during > TRBE buffer management, where PERF_AUX_FLAG_TRUNCATED is marked alone > without PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW. Those could be changed as > well. All records (irrespective of the size) generated by the TRBE must contain the "RAW" flag. Did I miss another instance where we don't do this ? Suzuki > _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-07-30 11:37 UTC|newest] Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-07-23 12:46 [PATCH v2 00/10] coresight: TRBE and Self-Hosted trace fixes Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 01/10] coresight: etm4x: Save restore TRFCR_EL1 Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 3:05 ` Anshuman Khandual 2021-07-30 3:05 ` Anshuman Khandual 2021-07-23 12:46 ` [PATCH v2 02/10] coresight: etm4x: Use Trace Filtering controls dynamically Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 3:48 ` Anshuman Khandual 2021-07-30 3:48 ` Anshuman Khandual 2021-07-30 11:29 ` Suzuki K Poulose 2021-07-30 11:29 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 03/10] coresight: etm-pmu: Ensure the AUX handle is valid Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 4:14 ` Anshuman Khandual 2021-07-30 4:14 ` Anshuman Khandual 2021-07-23 12:46 ` [PATCH v2 04/10] coresight: trbe: Ensure the format flag is set on truncation Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 4:26 ` Anshuman Khandual 2021-07-30 4:26 ` Anshuman Khandual 2021-07-30 11:37 ` Suzuki K Poulose [this message] 2021-07-30 11:37 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 05/10] coresight: trbe: Drop duplicate TRUNCATE flags Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 4:47 ` Anshuman Khandual 2021-07-30 4:47 ` Anshuman Khandual 2021-07-30 12:58 ` Suzuki K Poulose 2021-07-30 12:58 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 06/10] coresight: trbe: Fix handling of spurious interrupts Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 5:15 ` Anshuman Khandual 2021-07-30 5:15 ` Anshuman Khandual 2021-07-30 12:57 ` Suzuki K Poulose 2021-07-30 12:57 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 07/10] coresight: trbe: Do not truncate buffer on IRQ Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-26 12:34 ` Mike Leach 2021-07-26 12:34 ` Mike Leach 2021-07-26 16:01 ` Suzuki K Poulose 2021-07-26 16:01 ` Suzuki K Poulose 2021-07-27 10:46 ` Mike Leach 2021-07-27 10:46 ` Mike Leach 2021-07-27 13:06 ` Suzuki K Poulose 2021-07-27 13:06 ` Suzuki K Poulose 2021-07-28 9:25 ` Suzuki K Poulose 2021-07-28 9:25 ` Suzuki K Poulose 2021-07-23 12:46 ` [PATCH v2 08/10] coresight: trbe: Unify the enabling sequence Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 5:40 ` Anshuman Khandual 2021-07-30 5:40 ` Anshuman Khandual 2021-07-23 12:46 ` [PATCH v2 09/10] coresight: trbe: End the AUX handle on truncation Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 5:54 ` Anshuman Khandual 2021-07-30 5:54 ` Anshuman Khandual 2021-07-23 12:46 ` [PATCH v2 10/10] coresight: trbe: Prohibit trace before disabling TRBE Suzuki K Poulose 2021-07-23 12:46 ` Suzuki K Poulose 2021-07-30 6:58 ` Anshuman Khandual 2021-07-30 6:58 ` Anshuman Khandual 2021-07-23 13:45 ` [PATCH v2 00/10] coresight: TRBE and Self-Hosted trace fixes Suzuki K Poulose 2021-07-23 13:45 ` Suzuki K Poulose
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=a06e22d1-5f5c-87f1-d96c-fbda83fcd576@arm.com \ --to=suzuki.poulose@arm.com \ --cc=al.grant@arm.com \ --cc=anshuman.khandual@arm.com \ --cc=coresight@lists.linaro.org \ --cc=jinlmao@qti.qualcomm.com \ --cc=leo.yan@linaro.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=mathieu.poirier@linaro.org \ --cc=mike.leach@linaro.org \ --cc=tamas.zsoldos@arm.com \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.