On systems with many CPUs, recording extra context switch events can be
excessive and unnecessary. Add perf config intel-pt.all-switch-events=false
to control the behaviour.

Example:

 # perf config intel-pt.all-switch-events=false
 # perf record -eintel_pt//u uname
 Linux
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.082 MB perf.data ]
 # perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
       5 PERF_RECORD_SWITCH
 # perf config intel-pt.all-switch-events=true
 # perf record -eintel_pt//u uname
 Linux
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.102 MB perf.data ]
 # perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
     180 PERF_RECORD_SWITCH_CPU_WIDE

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Documentation/perf-config.txt |  4 ++++
 tools/perf/arch/x86/util/intel-pt.c      | 16 +++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 36ebebc875ea..c6f335659667 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -708,6 +708,10 @@ intel-pt.*::
 		the maximum is exceeded there will be a "Never-ending loop"
 		error. The default is 100000.
 
+	intel-pt.all-switch-events::
+		If the user has permission to do so, always record all context
+		switch events on all CPUs.
+
 auxtrace.*::
 
 	auxtrace.dumpdir::
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 8f235d8b67b6..add33cb5d1da 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -19,6 +19,7 @@
 #include "../../../util/evlist.h"
 #include "../../../util/evsel.h"
 #include "../../../util/evsel_config.h"
+#include "../../../util/config.h"
 #include "../../../util/cpumap.h"
 #include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
@@ -52,6 +53,7 @@ struct intel_pt_recording {
 	struct perf_pmu			*intel_pt_pmu;
 	int				have_sched_switch;
 	struct evlist		*evlist;
+	bool				all_switch_events;
 	bool				snapshot_mode;
 	bool				snapshot_init_done;
 	size_t				snapshot_size;
@@ -794,7 +796,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			bool cpu_wide = !target__none(&opts->target) &&
 					!target__has_task(&opts->target);
 
-			if (!cpu_wide && perf_can_record_cpu_wide()) {
+			if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) {
 				struct evsel *switch_evsel;
 
 				switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
@@ -1178,6 +1180,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt_recording *ptr = data;
+
+	if (!strcmp(var, "intel-pt.all-switch-events"))
+		ptr->all_switch_events = perf_config_bool(var, value);
+
+	return 0;
+}
+
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
@@ -1197,6 +1209,8 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 		return NULL;
 	}
 
+	perf_config(intel_pt_perf_config, ptr);
+
 	ptr->intel_pt_pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
-- 
2.45.2

On Mon, May 12, 2025 at 12:39:31PM +0300, Adrian Hunter wrote:
> On systems with many CPUs, recording extra context switch events can be
> excessive and unnecessary. Add perf config intel-pt.all-switch-events=false
> to control the behaviour.
> 
> Example:
> 
>  # perf config intel-pt.all-switch-events=false
>  # perf record -eintel_pt//u uname
>  Linux
>  [ perf record: Woken up 1 times to write data ]
>  [ perf record: Captured and wrote 0.082 MB perf.data ]
>  # perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
>        5 PERF_RECORD_SWITCH
>  # perf config intel-pt.all-switch-events=true
>  # perf record -eintel_pt//u uname
>  Linux
>  [ perf record: Woken up 1 times to write data ]
>  [ perf record: Captured and wrote 0.102 MB perf.data ]
>  # perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
>      180 PERF_RECORD_SWITCH_CPU_WIDE

Thanks, tested and applied the series.

BTW, I used 'perf report --stats' that shows the number of PERF_RECORD_
events:

Committer testing:

While doing a make -j28 allmodconfig:

  root@five:~# grep "model name" -m1 /proc/cpuinfo
  model name    : Intel(R) Core(TM) i7-14700K
  root@five:~#
  root@five:~# perf config intel-pt.all-switch-events=false
  root@five:~# perf record -e intel_pt//u uname
  Linux
  [ perf record: Woken up 2 times to write data ]
  [ perf record: Captured and wrote 0.019 MB perf.data ]
  root@five:~# perf report --stats | grep SWITCH_CPU_WIDE
  root@five:~# 
  root@five:~# perf config intel-pt.all-switch-events=true
  root@five:~# perf record -e intel_pt//u uname
  Linux
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.047 MB perf.data ]
  root@five:~# perf report --stats | grep SWITCH_CPU_WIDE
       SWITCH_CPU_WIDE events:        542  (96.4%)
  root@five:~#

- Arnaldo