All of lore.kernel.org
 help / color / mirror / Atom feed
From: Leo Yan <leo.yan@linaro.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mathieu Poirier <mathieu.poirier@linaro.org>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Mike Leach <mike.leach@linaro.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	John Garry <john.garry@huawei.com>, Will Deacon <will@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>, Jiri Olsa <jolsa@redhat.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Daniel Kiss <Daniel.Kiss@arm.com>,
	Denis Nikitin <denik@chromium.org>,
	coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org
Cc: Leo Yan <leo.yan@linaro.org>
Subject: [PATCH v1 4/7] perf cs-etm: Add PID format into metadata
Date: Sat,  9 Jan 2021 15:44:32 +0800	[thread overview]
Message-ID: <20210109074435.626855-5-leo.yan@linaro.org> (raw)
In-Reply-To: <20210109074435.626855-1-leo.yan@linaro.org>

It's possible for CoreSight to trace PID in either CONTEXTIDR_EL1 or
CONTEXTIDR_EL2, the PID format info is used to distinguish the PID
is traced in which register.

This patch saves PID format into the metadata when record.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/arch/arm/util/cs-etm.c | 21 +++++++++++++++++++++
 tools/perf/util/cs-etm.c          |  2 ++
 tools/perf/util/cs-etm.h          |  2 ++
 3 files changed, 25 insertions(+)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fad7b6e13ccc..ee78df3b1b07 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -613,6 +613,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	u64 pid_fmt;
 
 	/* first see what kind of tracer this cpu is affined to */
 	if (cs_etm_is_etmv4(itr, cpu)) {
@@ -641,6 +642,16 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 				      metadata_etmv4_ro
 				      [CS_ETMV4_TRCAUTHSTATUS]);
 
+		/*
+		 * The PID format will be used when decode the trace data;
+		 * based on it the decoder will make decision for setting
+		 * sample's PID as context_id or VMID.
+		 */
+		pid_fmt = perf_pmu__format_bits(&cs_etm_pmu->format, "pid");
+		if (!pid_fmt)
+			pid_fmt = 1ULL << ETM_OPT_CTXTID;
+		info->priv[*offset + CS_ETMV4_PID_FMT] = pid_fmt;
+
 		/* How much space was used */
 		increment = CS_ETMV4_PRIV_MAX;
 	} else {
@@ -658,6 +669,16 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 			cs_etm_get_ro(cs_etm_pmu, cpu,
 				      metadata_etmv3_ro[CS_ETM_ETMIDR]);
 
+		/*
+		 * The PID format will be used when decode the trace data;
+		 * based on it the decoder will make decision for setting
+		 * sample's PID as context_id or VMID.
+		 */
+		pid_fmt = perf_pmu__format_bits(&cs_etm_pmu->format, "pid");
+		if (!pid_fmt)
+			pid_fmt = 1ULL << ETM_OPT_CTXTID;
+		info->priv[*offset + CS_ETM_PID_FMT] = pid_fmt;
+
 		/* How much space was used */
 		increment = CS_ETM_PRIV_MAX;
 	}
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5e284725dceb..763085db29ae 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2447,6 +2447,7 @@ static const char * const cs_etm_priv_fmts[] = {
 	[CS_ETM_ETMTRACEIDR]	= "	ETMTRACEIDR		       %llx\n",
 	[CS_ETM_ETMCCER]	= "	ETMCCER			       %llx\n",
 	[CS_ETM_ETMIDR]		= "	ETMIDR			       %llx\n",
+	[CS_ETM_PID_FMT]	= "	PID Format		       %llx\n",
 };
 
 static const char * const cs_etmv4_priv_fmts[] = {
@@ -2459,6 +2460,7 @@ static const char * const cs_etmv4_priv_fmts[] = {
 	[CS_ETMV4_TRCIDR2]	= "	TRCIDR2			       %llx\n",
 	[CS_ETMV4_TRCIDR8]	= "	TRCIDR8			       %llx\n",
 	[CS_ETMV4_TRCAUTHSTATUS] = "	TRCAUTHSTATUS		       %llx\n",
+	[CS_ETMV4_PID_FMT]	= "	PID Format		       %llx\n",
 };
 
 static void cs_etm__print_auxtrace_info(__u64 *val, int num)
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 4ad925d6d799..8cbbea6100a1 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -38,6 +38,7 @@ enum {
 	/* RO, taken from sysFS */
 	CS_ETM_ETMCCER,
 	CS_ETM_ETMIDR,
+	CS_ETM_PID_FMT,
 	CS_ETM_PRIV_MAX,
 };
 
@@ -52,6 +53,7 @@ enum {
 	CS_ETMV4_TRCIDR2,
 	CS_ETMV4_TRCIDR8,
 	CS_ETMV4_TRCAUTHSTATUS,
+	CS_ETMV4_PID_FMT,
 	CS_ETMV4_PRIV_MAX,
 };
 
-- 
2.25.1


WARNING: multiple messages have this Message-ID (diff)
From: Leo Yan <leo.yan@linaro.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mathieu Poirier <mathieu.poirier@linaro.org>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Mike Leach <mike.leach@linaro.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	John Garry <john.garry@huawei.com>, Will Deacon <will@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>, Jiri Olsa <jolsa@redhat.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Daniel Kiss <Daniel.Kiss@arm.com>,
	Denis Nikitin <denik@chromium.org>,
	coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org
Cc: Leo Yan <leo.yan@linaro.org>
Subject: [PATCH v1 4/7] perf cs-etm: Add PID format into metadata
Date: Sat,  9 Jan 2021 15:44:32 +0800	[thread overview]
Message-ID: <20210109074435.626855-5-leo.yan@linaro.org> (raw)
In-Reply-To: <20210109074435.626855-1-leo.yan@linaro.org>

It's possible for CoreSight to trace PID in either CONTEXTIDR_EL1 or
CONTEXTIDR_EL2, the PID format info is used to distinguish the PID
is traced in which register.

This patch saves PID format into the metadata when record.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/arch/arm/util/cs-etm.c | 21 +++++++++++++++++++++
 tools/perf/util/cs-etm.c          |  2 ++
 tools/perf/util/cs-etm.h          |  2 ++
 3 files changed, 25 insertions(+)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fad7b6e13ccc..ee78df3b1b07 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -613,6 +613,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	u64 pid_fmt;
 
 	/* first see what kind of tracer this cpu is affined to */
 	if (cs_etm_is_etmv4(itr, cpu)) {
@@ -641,6 +642,16 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 				      metadata_etmv4_ro
 				      [CS_ETMV4_TRCAUTHSTATUS]);
 
+		/*
+		 * The PID format will be used when decode the trace data;
+		 * based on it the decoder will make decision for setting
+		 * sample's PID as context_id or VMID.
+		 */
+		pid_fmt = perf_pmu__format_bits(&cs_etm_pmu->format, "pid");
+		if (!pid_fmt)
+			pid_fmt = 1ULL << ETM_OPT_CTXTID;
+		info->priv[*offset + CS_ETMV4_PID_FMT] = pid_fmt;
+
 		/* How much space was used */
 		increment = CS_ETMV4_PRIV_MAX;
 	} else {
@@ -658,6 +669,16 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 			cs_etm_get_ro(cs_etm_pmu, cpu,
 				      metadata_etmv3_ro[CS_ETM_ETMIDR]);
 
+		/*
+		 * The PID format will be used when decode the trace data;
+		 * based on it the decoder will make decision for setting
+		 * sample's PID as context_id or VMID.
+		 */
+		pid_fmt = perf_pmu__format_bits(&cs_etm_pmu->format, "pid");
+		if (!pid_fmt)
+			pid_fmt = 1ULL << ETM_OPT_CTXTID;
+		info->priv[*offset + CS_ETM_PID_FMT] = pid_fmt;
+
 		/* How much space was used */
 		increment = CS_ETM_PRIV_MAX;
 	}
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5e284725dceb..763085db29ae 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2447,6 +2447,7 @@ static const char * const cs_etm_priv_fmts[] = {
 	[CS_ETM_ETMTRACEIDR]	= "	ETMTRACEIDR		       %llx\n",
 	[CS_ETM_ETMCCER]	= "	ETMCCER			       %llx\n",
 	[CS_ETM_ETMIDR]		= "	ETMIDR			       %llx\n",
+	[CS_ETM_PID_FMT]	= "	PID Format		       %llx\n",
 };
 
 static const char * const cs_etmv4_priv_fmts[] = {
@@ -2459,6 +2460,7 @@ static const char * const cs_etmv4_priv_fmts[] = {
 	[CS_ETMV4_TRCIDR2]	= "	TRCIDR2			       %llx\n",
 	[CS_ETMV4_TRCIDR8]	= "	TRCIDR8			       %llx\n",
 	[CS_ETMV4_TRCAUTHSTATUS] = "	TRCAUTHSTATUS		       %llx\n",
+	[CS_ETMV4_PID_FMT]	= "	PID Format		       %llx\n",
 };
 
 static void cs_etm__print_auxtrace_info(__u64 *val, int num)
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 4ad925d6d799..8cbbea6100a1 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -38,6 +38,7 @@ enum {
 	/* RO, taken from sysFS */
 	CS_ETM_ETMCCER,
 	CS_ETM_ETMIDR,
+	CS_ETM_PID_FMT,
 	CS_ETM_PRIV_MAX,
 };
 
@@ -52,6 +53,7 @@ enum {
 	CS_ETMV4_TRCIDR2,
 	CS_ETMV4_TRCIDR8,
 	CS_ETMV4_TRCAUTHSTATUS,
+	CS_ETMV4_PID_FMT,
 	CS_ETMV4_PRIV_MAX,
 };
 
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2021-01-09  7:45 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-09  7:44 [PATCH v1 0/7] coresight: etm-perf: Fix pid tracing with VHE Leo Yan
2021-01-09  7:44 ` Leo Yan
2021-01-09  7:44 ` [PATCH v1 1/7] coresight: etm-perf: Add support for PID tracing for kernel at EL2 Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-09 10:05   ` kernel test robot
2021-01-10  1:24     ` [PATCH] " Suzuki K Poulose
2021-01-10  1:41       ` Leo Yan
2021-01-10 22:34         ` Suzuki K Poulose
2021-01-11  0:05           ` Leo Yan
2021-01-09 11:24   ` [PATCH v1 1/7] " kernel test robot
2021-01-11 16:22   ` Mike Leach
2021-01-11 16:22     ` Mike Leach
2021-01-12  7:22     ` Leo Yan
2021-01-12  7:22       ` Leo Yan
2021-01-12  8:58     ` Leo Yan
2021-01-12  8:58       ` Leo Yan
2021-01-12 11:03       ` Suzuki K Poulose
2021-01-12 11:03         ` Suzuki K Poulose
2021-01-12 11:23       ` Mike Leach
2021-01-12 11:23         ` Mike Leach
2021-01-12 14:14         ` Leo Yan
2021-01-12 14:14           ` Leo Yan
2021-01-12 23:43           ` Mike Leach
2021-01-12 23:43             ` Mike Leach
2021-01-15 22:30   ` Mathieu Poirier
2021-01-15 22:30     ` Mathieu Poirier
2021-01-19  7:05     ` Suzuki K Poulose
2021-01-19  7:05       ` Suzuki K Poulose
2021-01-09  7:44 ` [PATCH v1 2/7] perf cs_etm: Use pid tracing explicitly instead of contextid Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-15 22:44   ` Mathieu Poirier
2021-01-15 22:44     ` Mathieu Poirier
2021-01-19  2:32     ` Leo Yan
2021-01-19  2:32       ` Leo Yan
2021-01-09  7:44 ` [PATCH v1 3/7] perf cs-etm: Calculate per CPU metadata array size Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-11  7:28   ` Suzuki K Poulose
2021-01-11  7:28     ` Suzuki K Poulose
2021-01-11 12:09     ` Mike Leach
2021-01-11 12:09       ` Mike Leach
2021-01-11 15:06       ` Leo Yan
2021-01-11 15:06         ` Leo Yan
2021-01-13  0:00         ` Mike Leach
2021-01-13  0:00           ` Mike Leach
2021-01-13  2:27           ` Leo Yan
2021-01-13  2:27             ` Leo Yan
2021-01-15 22:46       ` Mathieu Poirier
2021-01-15 22:46         ` Mathieu Poirier
2021-01-16  0:50         ` Leo Yan
2021-01-16  0:50           ` Leo Yan
2021-01-09  7:44 ` Leo Yan [this message]
2021-01-09  7:44   ` [PATCH v1 4/7] perf cs-etm: Add PID format into metadata Leo Yan
2021-01-11  9:45   ` Suzuki K Poulose
2021-01-11  9:45     ` Suzuki K Poulose
2021-01-11 13:12     ` Leo Yan
2021-01-11 13:12       ` Leo Yan
2021-01-09  7:44 ` [PATCH v1 5/7] perf cs-etm: Fixup PID_FMT when it is zero Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-11  9:47   ` Suzuki K Poulose
2021-01-11  9:47     ` Suzuki K Poulose
2021-01-09  7:44 ` [PATCH v1 6/7] perf cs-etm: Add helper cs_etm__get_pid_fmt() Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-11  9:55   ` Suzuki K Poulose
2021-01-11  9:55     ` Suzuki K Poulose
2021-01-09  7:44 ` [PATCH v1 7/7] perf cs-etm: Detect pid in VMID for kernel running at EL2 Leo Yan
2021-01-09  7:44   ` Leo Yan
2021-01-11 10:07   ` Suzuki K Poulose
2021-01-11 10:07     ` Suzuki K Poulose
2021-01-11 13:10     ` Leo Yan
2021-01-11 13:10       ` Leo Yan
2021-01-11 18:16 ` [PATCH v1 0/7] coresight: etm-perf: Fix pid tracing with VHE Mathieu Poirier
2021-01-11 18:16   ` Mathieu Poirier
2021-01-12  7:23   ` Leo Yan
2021-01-12  7:23     ` Leo Yan

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=20210109074435.626855-5-leo.yan@linaro.org \
    --to=leo.yan@linaro.org \
    --cc=Daniel.Kiss@arm.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=coresight@lists.linaro.org \
    --cc=denik@chromium.org \
    --cc=john.garry@huawei.com \
    --cc=jolsa@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mathieu.poirier@linaro.org \
    --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 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.