[PATCH 0/3] perf: Suppress redundant ITRACE start records for Arm SPE and CoreSight

[PATCH 0/3] perf: Suppress redundant ITRACE start records for Arm SPE and CoreSight

[Leo Yan]

Thanks to Tamas Petz for noticing that Arm CoreSight perf data can contain
many PERF_RECORD_ITRACE_START records.

PERF_RECORD_ITRACE_START provides the decoder with the initial thread
context when that information is absent from the trace stream. Once
tracing has started, Arm SPE and CoreSight decoders track subsequent
context changes using context packets or recorded sched_switch events.

Have both drivers call perf_event_itrace_started() after successfully
starting event. This prevents perf core from emitting redundant
PERF_RECORD_ITRACE_START records when an event is scheduled in again.

Since the Arm SPE and CoreSight drivers can be built as modules, export
perf_event_itrace_started() before using it in those drivers.

This series was verified with Arm CoreSight using the commands below.
The perf data contains 100 sched_switch events but only one
PERF_RECORD_ITRACE_START record:

  taskset -c 2 perf record -e cs_etm//u -e sched:sched_switch -- \
	  taskset -c 2 bash -c 'while true; do sleep 0.01; done'
  ^C

  perf script -D 2>&1 | grep -c sched_switch
  100

  perf script -D 2>&1 | grep -c PERF_RECORD_ITRACE_START
  1

Signed-off-by: Leo Yan <leo.yan@arm.com>
---
Leo Yan (3):
      perf/core: Export perf_event_itrace_started()
      perf: arm_spe: Suppress redundant ITRACE start records
      coresight: perf: Suppress ITRACE start records

 drivers/hwtracing/coresight/coresight-etm-perf.c | 2 ++
 drivers/perf/arm_spe_pmu.c                       | 2 ++
 kernel/events/core.c                             | 1 +
 3 files changed, 5 insertions(+)
---
base-commit: 786262be6048deab760f68c8acc2c85607165894
change-id: 20260901-perf_suppress_itrace_start_records-42faf45e9ce9

Best regards,
-- 
Leo Yan <leo.yan@arm.com>

[PATCH 1/3] perf/core: Export perf_event_itrace_started()

[Leo Yan]

Since Arm SPE and CoreSight drivers can be built as modules, export
perf_event_itrace_started() so that it can be used by these modules.

Signed-off-by: Leo Yan <leo.yan@arm.com>
---
 kernel/events/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6c8e38a311042afab6b65814a84c67b87ba929b..8afe89179a62127eebae0f38f29cde045ba56251 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10560,6 +10560,7 @@ void perf_event_itrace_started(struct perf_event *event)
 {
 	WRITE_ONCE(event->attach_state, event->attach_state | PERF_ATTACH_ITRACE);
 }
+EXPORT_SYMBOL_GPL(perf_event_itrace_started);
 
 static void perf_log_itrace_start(struct perf_event *event)
 {

-- 
2.34.1

Re: [PATCH 1/3] perf/core: Export perf_event_itrace_started()

[Leo Yan]

On Tue, Sep 01, 2026 at 05:36:15PM +0100, Leo Yan wrote:
> Since Arm SPE and CoreSight drivers can be built as modules, export
> perf_event_itrace_started() so that it can be used by these modules.
> 
> Signed-off-by: Leo Yan <leo.yan@arm.com>

Gentle ping!

> ---
>  kernel/events/core.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index a6c8e38a311042afab6b65814a84c67b87ba929b..8afe89179a62127eebae0f38f29cde045ba56251 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -10560,6 +10560,7 @@ void perf_event_itrace_started(struct perf_event *event)
>  {
>  	WRITE_ONCE(event->attach_state, event->attach_state | PERF_ATTACH_ITRACE);
>  }
> +EXPORT_SYMBOL_GPL(perf_event_itrace_started);
>  
>  static void perf_log_itrace_start(struct perf_event *event)
>  {
> 
> -- 
> 2.34.1
> 

Re: [PATCH 1/3] perf/core: Export perf_event_itrace_started()

[Peter Zijlstra]

On Tue, Sep 01, 2026 at 05:36:15PM +0100, Leo Yan wrote:
> Since Arm SPE and CoreSight drivers can be built as modules, export
> perf_event_itrace_started() so that it can be used by these modules.
> 
> Signed-off-by: Leo Yan <leo.yan@arm.com>

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>

> ---
>  kernel/events/core.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index a6c8e38a311042afab6b65814a84c67b87ba929b..8afe89179a62127eebae0f38f29cde045ba56251 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -10560,6 +10560,7 @@ void perf_event_itrace_started(struct perf_event *event)
>  {
>  	WRITE_ONCE(event->attach_state, event->attach_state | PERF_ATTACH_ITRACE);
>  }
> +EXPORT_SYMBOL_GPL(perf_event_itrace_started);
>  
>  static void perf_log_itrace_start(struct perf_event *event)
>  {
> 
> -- 
> 2.34.1
> 

[PATCH 2/3] perf: arm_spe: Suppress redundant ITRACE start records

[Leo Yan]

PERF_RECORD_ITRACE_START establishes the initial thread context at the
beginning of a trace. Afterwards, decoders track the thread context using
context packets or recorded sched_switch events.

Call perf_event_itrace_started() when event starts to prevent perf core
from emitting redundant PERF_RECORD_ITRACE_START records on later
schedule-ins.

Signed-off-by: Leo Yan <leo.yan@arm.com>
---
 drivers/perf/arm_spe_pmu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index b70f3fedf0282baba1395ce1116272ec5f961ea8..40314ef8b731e1272e02783a9e6dc7d92ec47139 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -890,6 +890,8 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags)
 		return;
 	}
 
+	perf_event_itrace_started(event);
+
 	reg = arm_spe_event_to_pmsfcr(event);
 	write_sysreg_s(reg, SYS_PMSFCR_EL1);
 

-- 
2.34.1

[PATCH 3/3] coresight: perf: Suppress ITRACE start records

[Leo Yan]

PERF_RECORD_ITRACE_START establishes the initial thread context at the
beginning of a trace. Afterwards, decoders track the thread context using
context packets.

Call perf_event_itrace_started() after successfully starting the event
to prevent perf core from emitting redundant PERF_RECORD_ITRACE_START
records when the event is scheduled in again.

When per-thread mode traces multiple child threads, tooling should
enable context ID tracing instead to identify each thread.

Signed-off-by: Leo Yan <leo.yan@arm.com>
---
 drivers/hwtracing/coresight/coresight-etm-perf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 09b21a711a8764ea429d712890265c84648e889e..80502e8b084074980000a039e73e1a164940011d 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -613,6 +613,8 @@ static void etm_event_start(struct perf_event *event, int flags)
 		perf_report_aux_output_id(event, hw_id);
 	}
 
+	perf_event_itrace_started(event);
+
 out:
 	/* Tell the perf core the event is alive */
 	event->hw.state = 0;

-- 
2.34.1

Re: [PATCH 0/3] perf: Suppress redundant ITRACE start records for Arm SPE and CoreSight

[James Clark]

On 01/09/2026 17:36, Leo Yan wrote:
> Thanks to Tamas Petz for noticing that Arm CoreSight perf data can contain
> many PERF_RECORD_ITRACE_START records.
> 
> PERF_RECORD_ITRACE_START provides the decoder with the initial thread
> context when that information is absent from the trace stream. Once
> tracing has started, Arm SPE and CoreSight decoders track subsequent
> context changes using context packets or recorded sched_switch events.
> 
> Have both drivers call perf_event_itrace_started() after successfully
> starting event. This prevents perf core from emitting redundant
> PERF_RECORD_ITRACE_START records when an event is scheduled in again.
> 
> Since the Arm SPE and CoreSight drivers can be built as modules, export
> perf_event_itrace_started() before using it in those drivers.
> 
> This series was verified with Arm CoreSight using the commands below.
> The perf data contains 100 sched_switch events but only one
> PERF_RECORD_ITRACE_START record:
> 
>    taskset -c 2 perf record -e cs_etm//u -e sched:sched_switch -- \
> 	  taskset -c 2 bash -c 'while true; do sleep 0.01; done'
>    ^C
> 
>    perf script -D 2>&1 | grep -c sched_switch
>    100
> 
>    perf script -D 2>&1 | grep -c PERF_RECORD_ITRACE_START
>    1
> 
> Signed-off-by: Leo Yan <leo.yan@arm.com>
> ---
> Leo Yan (3):
>        perf/core: Export perf_event_itrace_started()
>        perf: arm_spe: Suppress redundant ITRACE start records
>        coresight: perf: Suppress ITRACE start records
> 
>   drivers/hwtracing/coresight/coresight-etm-perf.c | 2 ++
>   drivers/perf/arm_spe_pmu.c                       | 2 ++
>   kernel/events/core.c                             | 1 +
>   3 files changed, 5 insertions(+)
> ---
> base-commit: 786262be6048deab760f68c8acc2c85607165894
> change-id: 20260901-perf_suppress_itrace_start_records-42faf45e9ce9
> 
> Best regards,

Reviewed-by: James Clark <james.clark@linaro.org>