[PATCH v1 0/9] perf python: Follow-up fixes and shell test deflaking

[PATCH v1 0/9] perf python: Follow-up fixes and shell test deflaking

[Ian Rogers]

This series contains follow-up fixes for the standalone Python scripts
and their shell tests, particularly when running 'perf test' as root
under heavy parallel load:

- Clamp sample_id size calculation for PERF_RECORD_KSYMBOL,
  PERF_RECORD_BPF_EVENT, and PERF_RECORD_TEXT_POKE records to work
  around kernels without "perf/core: Restore header fields in sideband
  output callbacks" [1].
- Fix offline interval printing in sctop.py and live signal races in
  stat-cpi.py.
- Deflake Intel PT, failed-syscalls, and other Python shell tests under
  parallel 'perf test' load by scoping tracepoint checks to
  'perf list tracepoint', passing '-B -N --no-bpf-event' to 'perf record',
  and avoiding unnecessary system-wide ('-a') recordings.
- Default event_analyzing_sample.py to an in-memory SQLite database
  (':memory:') when '--db' is not specified.
- Initialize perf debug output ('perf_debug_setup()') when loading the
  'perf' Python extension module.
- Fix races in 'perf list' ('perf_pmus__print_pmu_events()' and
  'tp_pmu.c') when concurrent tests dynamically create and remove
  kprobe/uprobes tracepoints.

[1] https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com

Ian Rogers (9):
  perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke
    events
  perf python sctop: Fix offline interval printing and test flakiness
  perf python stat-cpi: Fix live mode signal races and test flakiness
  perf test: Deflake Intel PT Python shell tests under load
  perf test: Deflake failed-syscalls Python shell tests under load
  perf test: Reduce overhead and contention in Python shell tests
  perf python event_analyzing_sample: Default to in-memory SQLite
    database
  perf python: Initialize debug output on module load
  perf pmu: Fix race with concurrent tracepoint creation and removal in
    perf list

 tools/perf/python/event_analyzing_sample.py   | 35 +++-------
 tools/perf/python/sctop.py                    |  9 ++-
 tools/perf/python/stat-cpi.py                 | 19 +++---
 .../shell/test_check_perf_trace_python.sh     |  8 ++-
 .../shell/test_compaction_times_python.sh     |  8 ++-
 .../test_event_analyzing_sample_python.sh     | 11 ++-
 .../shell/test_export_to_postgresql_python.sh | 49 +++++++------
 .../shell/test_export_to_sqlite_python.sh     | 50 ++++++++------
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 44 +++++++-----
 .../tests/shell/test_flamegraph_python.sh     |  5 +-
 .../shell/test_futex_contention_python.sh     |  7 +-
 tools/perf/tests/shell/test_gecko_python.sh   |  3 +-
 .../shell/test_intel_pt_events_python.sh      | 43 ++++++------
 .../tests/shell/test_mem_phys_addr_python.sh  |  8 ++-
 .../shell/test_net_dropmonitor_python.sh      |  9 +--
 .../tests/shell/test_netdev_times_python.sh   |  6 +-
 .../tests/shell/test_powerpc_hcalls_python.sh |  4 +-
 .../tests/shell/test_rw_by_file_python.sh     |  5 +-
 .../perf/tests/shell/test_rw_by_pid_python.sh |  4 +-
 tools/perf/tests/shell/test_rwtop_python.sh   |  4 +-
 .../shell/test_sched_migration_python.sh      |  4 +-
 tools/perf/tests/shell/test_sctop_python.sh   | 48 ++++++-------
 .../tests/shell/test_stackcollapse_python.sh  |  2 +-
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++-
 .../test_syscall_counts_by_pid_python.sh      |  6 +-
 .../tests/shell/test_syscall_counts_python.sh |  5 +-
 tools/perf/tests/shell/test_task_analyzer.sh  |  3 +-
 .../tests/shell/test_wakeup_latency_python.sh |  7 +-
 tools/perf/util/debug.c                       |  2 +-
 tools/perf/util/evlist.c                      |  6 +-
 tools/perf/util/evsel.c                       | 59 +++++++++++++++-
 tools/perf/util/evsel.h                       |  1 +
 tools/perf/util/pmus.c                        | 20 ++++--
 tools/perf/util/python.c                      |  1 +
 tools/perf/util/tp_pmu.c                      |  8 ++-
 36 files changed, 358 insertions(+), 225 deletions(-)

-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 1/9] perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke events

[Ian Rogers]

On kernels without the fix ("perf/core: Restore header fields in
sideband output callbacks") to restore event_id.header.size in
perf_event_ksymbol_output(), perf_event_bpf_output(), and
perf_event_text_poke_output(), concurrent perf sessions cause those
sideband records to be emitted with header.size inflated by multiple
id_header_size increments while the single id_sample is written
immediately after the event payload. Indexing backwards from
event->header.size reads uninitialized ring-buffer bytes at the end of
the record, causing evlist__event2evsel() to fail with -EFAULT.

Add evsel__event_size() to clamp the effective size used to locate the
trailing id_sample for PERF_RECORD_KSYMBOL, PERF_RECORD_BPF_EVENT, and
PERF_RECORD_TEXT_POKE to payload + id_hdr_size while leaving
event->header.size intact for advancing the ring-buffer/file stream.

Fixes: 9aa0bfa370b2 ("perf tools: Handle PERF_RECORD_KSYMBOL")
Fixes: 45178a928a4b ("perf tools: Handle PERF_RECORD_BPF_EVENT")
Fixes: 246eba8e9041 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Link: https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/evlist.c |  6 ++--
 tools/perf/util/evsel.c  | 59 +++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 9392d912d254..c2402e4791b6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -973,13 +973,15 @@ static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64
 	const __u64 *array = event->sample.array;
 	ssize_t n;
 
-	n = (event->header.size - sizeof(event->header)) >> 3;
-
 	if (event->header.type == PERF_RECORD_SAMPLE) {
+		n = (event->header.size - sizeof(event->header)) >> 3;
 		if (evlist__id_pos(evlist) >= n)
 			return -1;
 		*id = array[evlist__id_pos(evlist)];
 	} else {
+		u16 size = evsel__event_size(evlist__first(evlist), event);
+
+		n = (size - sizeof(event->header)) >> 3;
 		if (evlist__is_pos(evlist) > n)
 			return -1;
 		n -= evlist__is_pos(evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3367242c5764..70da6be798cc 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3216,7 +3216,7 @@ static int perf_evsel__parse_id_sample(const union perf_event *event,
 	const __u64 *array = event->sample.array;
 	bool swapped = evsel->needs_swap;
 	union u64_swap u;
-	int i = ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1;
+	int i = ((evsel__event_size(evsel, event) - sizeof(event->header)) / sizeof(u64)) - 1;
 
 	if (type & PERF_SAMPLE_IDENTIFIER) {
 		if (i < 0)
@@ -3966,6 +3966,63 @@ u16 evsel__id_hdr_size(const struct evsel *evsel)
 	return size;
 }
 
+/*
+ * Prior to kernel fix, perf_event_ksymbol_output(), perf_event_bpf_output(),
+ * and perf_event_text_poke_output() in kernel/events/core.c did not save and
+ * restore event_id.header.size across perf_iterate_sb() iterations. When
+ * multiple perf_events had attr.ksymbol, attr.bpf_event, or attr.text_poke
+ * enabled, header.size was incremented by id_header_size for each matching
+ * event while only a single id_sample was written immediately after the event
+ * payload. Clamp the effective size used to locate the trailing id_sample to
+ * payload + id_hdr_size so events recorded on unpatched kernels can be parsed
+ * without reading uninitialized ring-buffer bytes.
+ */
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event)
+{
+	u16 size = event->header.size;
+	u16 id_hdr_size;
+	size_t payload;
+
+	if (!evsel->core.attr.sample_id_all)
+		return size;
+
+	switch (event->header.type) {
+	case PERF_RECORD_KSYMBOL: {
+		const char *name = event->ksymbol.name;
+		size_t fixed = offsetof(struct perf_record_ksymbol, name);
+		size_t max_len, len;
+
+		if (size <= fixed)
+			return size;
+		max_len = size - fixed;
+		len = strnlen(name, max_len);
+		if (len == max_len)
+			return size;
+		payload = fixed + PERF_ALIGN(len + 1, sizeof(u64));
+		break;
+	}
+	case PERF_RECORD_BPF_EVENT:
+		payload = sizeof(struct perf_record_bpf_event);
+		break;
+	case PERF_RECORD_TEXT_POKE: {
+		size_t fixed = offsetof(struct perf_record_text_poke_event, bytes);
+
+		if (size < fixed)
+			return size;
+		payload = fixed + PERF_ALIGN((size_t)event->text_poke.old_len +
+					     event->text_poke.new_len, sizeof(u64));
+		break;
+	}
+	default:
+		return size;
+	}
+
+	id_hdr_size = evsel__id_hdr_size(evsel);
+	if (payload + id_hdr_size < size)
+		return payload + id_hdr_size;
+	return size;
+}
+
 #ifdef HAVE_LIBTRACEEVENT
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5c5799cee601..174f3414fd3c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -469,6 +469,7 @@ int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
 				  u64 *timestamp);
 
 u16 evsel__id_hdr_size(const struct evsel *evsel);
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event);
 
 static inline struct evsel *evsel__next(struct evsel *evsel)
 {
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 2/9] perf python sctop: Fix offline interval printing and test flakiness

[Ian Rogers]

In sctop.py, process_event() updated self.last_print_time on every
sample in offline mode even when skip was true for non-matching comm
events. When filtering by comm with a short interval (such as 'sleep 1'
in test_sctop_python.sh) on a system-wide recording spanning more than
1 second under heavy load, non-matching samples could trigger
print_current_totals() and clear self.syscalls, followed by finally:
printing a trailing empty table. In addition, analyzer.e_machine was
initialized after session.process_events() instead of before.

Fix sctop.py by initializing analyzer.e_machine before
session.process_events(), only advancing self.last_print_time when a
sample is not skipped, and only calling print_current_totals() in
finally: if no table has been printed yet or remaining syscalls are
pending.

In test_sctop_python.sh, use 'perf list tracepoint' instead of
unfiltered 'perf list', record the child workload directly without '-a'
and with '-B -N --no-bpf-event' to avoid system-wide ringbuffer overflow
and synthesis contention, and retry up to 5 times if needed.

Fixes: b83f0bacf5e4 ("perf python: Port sctop to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/sctop.py                  |  9 ++--
 tools/perf/tests/shell/test_sctop_python.sh | 48 +++++++++++----------
 2 files changed, 31 insertions(+), 26 deletions(-)

diff --git a/tools/perf/python/sctop.py b/tools/perf/python/sctop.py
index 42e95ecfffad..c524e08e6440 100755
--- a/tools/perf/python/sctop.py
+++ b/tools/perf/python/sctop.py
@@ -37,6 +37,7 @@ class SCTopAnalyzer:
         self.offline = offline
         self.own_pid = os.getpid()
         self.last_print_time: Optional[int] = None
+        self.printed = False
         self.session: Optional[perf.session] = None
         self.e_machine: Optional[int] = None
 
@@ -127,7 +128,7 @@ class SCTopAnalyzer:
             if not skip and is_enter and 0 <= (syscall_id & ~0x40000000) <= 0xffff:
                 self.syscalls[syscall_id] += 1
 
-        if self.offline and hasattr(sample, "sample_time"):
+        if not skip and self.offline and hasattr(sample, "sample_time"):
             interval_ns = self.interval * (10 ** 9)
             if self.last_print_time is None:
                 self.last_print_time = sample.sample_time
@@ -137,6 +138,7 @@ class SCTopAnalyzer:
 
     def print_current_totals(self):
         """Print current syscall totals."""
+        self.printed = True
         # Clear terminal
         if not self.offline:
             print("\x1b[2J\x1b[H", end="")
@@ -217,8 +219,8 @@ def main():
         if args.input:
             session = perf.session(perf.data(args.input), sample=analyzer.process_event)
             analyzer.session = session
-            session.process_events()
             analyzer.e_machine = getattr(session, "e_machine", None)
+            session.process_events()
         else:
             try:
                 live_session = LiveSession(
@@ -237,7 +239,8 @@ def main():
         sys.exit(1)
     finally:
         if args.input:
-            analyzer.print_current_totals()
+            if not analyzer.printed or analyzer.syscalls:
+                analyzer.print_current_totals()
             # Break the reference cycle between perf.session and analyzer.process_event
             # because perf.session lacks cyclic GC support (tp_traverse).
             analyzer.session = None
diff --git a/tools/perf/tests/shell/test_sctop_python.sh b/tools/perf/tests/shell/test_sctop_python.sh
index 007f2584cce6..230eeca96fb8 100755
--- a/tools/perf/tests/shell/test_sctop_python.sh
+++ b/tools/perf/tests/shell/test_sctop_python.sh
@@ -41,37 +41,39 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing sctop.py..."
 
 # Create a perf.data file.
-if perf list | grep -q "raw_syscalls:sys_enter"; then
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.1 >/dev/null 2>&1 || \
-		{ echo "Skipping test, perf record failed"; exit 2; }
-else
+if ! perf list tracepoint | grep -q "raw_syscalls:sys_enter"; then
 	echo "Skipping test, no raw_syscalls:sys_enter event"
 	exit 2
 fi
 
-if [ ! -s "${temp_data}" ]; then
-	echo "Skipping test, perf record failed to create data"
-	exit 2
-fi
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1; then
+		echo "Skipping test, perf record failed"
+		exit 2
+	fi
+
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script sctop -i "${temp_data}" > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}" && \
+	   perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
 
-# Check that the script executes
-if ! perf script sctop -i "${temp_data}" > "${temp_out}"; then
+if [ "$passed" -eq 0 ]; then
 	echo "sctop.py test failed"
 	err=1
-elif ! grep -E -q "[0-9]+$" "${temp_out}"; then
-	echo "Failed to find metric data rows in default run"
-	err=1
-elif ! perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}"; then
-	echo "sctop.py comm+interval test failed"
-	err=1
 else
-	if ! grep -E -q "[0-9]+$" "${temp_out}"; then
-		echo "Failed to find metric data rows"
-		err=1
-	else
-		echo "sctop test passed."
-	fi
+	echo "sctop test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 3/9] perf python stat-cpi: Fix live mode signal races and test flakiness

[Ian Rogers]

In test_stat_cpi_python.sh, 'perf test -w noploop &' defaults to a
1-second duration and can exit under heavy parallel load before
'perf stat -p' and 'perf script stat-cpi' finish starting up. In
addition, the fixed 'sleep 0.5' before sending SIGINT can fire before
Python finishes importing the perf module, opening the live evlist, and
flushing the first interval.

In stat-cpi.py, register SIGINT and SIGTERM handlers before calling
_open_live_evlist() and pass flush=True when printing live output so
redirected stdout is flushed immediately after each interval.

In test_stat_cpi_python.sh, run 'perf test -w noploop 60 &' so the
target workload stays alive until killed, and poll the output file for
'cpi' (up to 5 seconds) before sending SIGINT.

Fixes: 4425182d426b ("perf python: Port stat-cpi to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/stat-cpi.py                 | 19 ++++++++++---------
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++++++++---
 2 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/tools/perf/python/stat-cpi.py b/tools/perf/python/stat-cpi.py
index 0b7d76876a6c..da92cf560067 100755
--- a/tools/perf/python/stat-cpi.py
+++ b/tools/perf/python/stat-cpi.py
@@ -106,7 +106,8 @@ class StatCpiAnalyzer:
             if ins != 0:
                 cpi = cyc / float(ins)
             t_sec = timestamp / 1000000000.0
-            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})")
+            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})",
+                  flush=True)
 
     def read_counters(self, evlist: Any) -> None:
         """Read counters live."""
@@ -173,19 +174,19 @@ class StatCpiAnalyzer:
 
     def run_live(self) -> None:
         """Read counters live."""
-        try:
-            evlist = self._open_live_evlist()
-        except OSError as e:
-            print(f"Failed to open events: {e}", file=sys.stderr)
-            sys.exit(1)
-
         def handle_signal(_signum: int, _frame: Any) -> None:
             raise KeyboardInterrupt
 
         signal.signal(signal.SIGINT, signal.default_int_handler)
         signal.signal(signal.SIGTERM, handle_signal)
 
-        print("Live mode started. Press Ctrl+C to stop.")
+        try:
+            evlist = self._open_live_evlist()
+        except OSError as e:
+            print(f"Failed to open events: {e}", file=sys.stderr)
+            sys.exit(1)
+
+        print("Live mode started. Press Ctrl+C to stop.", flush=True)
         try:
             while True:
                 time.sleep(self.args.interval)
@@ -195,7 +196,7 @@ class StatCpiAnalyzer:
                 self.data.clear()
                 self.recorded_pairs.clear()
         except KeyboardInterrupt:
-            print("\nStopped.")
+            print("\nStopped.", flush=True)
         finally:
             evlist.close()
 
diff --git a/tools/perf/tests/shell/test_stat_cpi_python.sh b/tools/perf/tests/shell/test_stat_cpi_python.sh
index fe7562307634..6cb376c92e2f 100755
--- a/tools/perf/tests/shell/test_stat_cpi_python.sh
+++ b/tools/perf/tests/shell/test_stat_cpi_python.sh
@@ -50,7 +50,7 @@ test_live_mode() {
 		echo "perf stat failed (permissions?), skipping live mode test."
 		return 0
 	fi
-	perf test -w noploop &
+	perf test -w noploop 60 &
 	workload_pid=$!
 	if ! perf stat -e cycles,instructions -p "$workload_pid" -- sleep 0.05 2>/dev/null && \
 	   ! perf stat -e cycles:u,instructions:u -p "$workload_pid" -- sleep 0.05 2>/dev/null; then
@@ -61,10 +61,16 @@ test_live_mode() {
 	fi
 	ran=1
 
-	# Run live mode for 1 interval in the background, give it a tiny sleep, then interrupt
+	# Run live mode in the background, wait until at least one interval is
+	# printed, then interrupt.
 	perf script stat-cpi -I 0.1 -p "$workload_pid" > "${temp_out}" &
 	pid=$!
-	sleep 0.5
+	for _ in $(seq 1 50); do
+		if grep -q "cpi" "${temp_out}"; then
+			break
+		fi
+		sleep 0.1
+	done
 	kill -INT "$pid" 2>/dev/null || true
 	set +e
 	wait "$pid"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 4/9] perf test: Deflake Intel PT Python shell tests under load

[Ian Rogers]

In test_intel_pt_events_python.sh, test_export_to_sqlite_python.sh, and
test_export_to_postgresql_python.sh, 'sh -c "uname; true"' uses the
shell builtin 'true' and exits within microseconds of 'uname', sending
SIGCHLD to 'perf record' before the Intel PT AUX buffer is always
flushed under heavy parallel load (~5-10% drop rate).

Sleep 0.05s in the subshell after 'uname' ('sh -c "uname; sleep 0.05"')
so 'uname' completely exits and flushes its AUX trace before 'sh' exits,
and wrap the record and verification step in a bounded retry loop (up to
5 attempts). Also pass '-B -N --no-bpf-event' to 'perf record -g' in
test_export_to_sqlite_python.sh and test_export_to_postgresql_python.sh
to avoid build-id cache and BPF synthesis overhead.

Fixes: d4ce72e9e238 ("perf python: Port intel-pt-events and libxed to perf module")
Fixes: 62d350135e67 ("perf python: Port export-to-sqlite to perf module")
Fixes: b1f968c9656a ("perf python: Port export-to-postgresql to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../shell/test_export_to_postgresql_python.sh | 49 ++++++++++--------
 .../shell/test_export_to_sqlite_python.sh     | 50 +++++++++++--------
 .../shell/test_intel_pt_events_python.sh      | 43 +++++++++-------
 3 files changed, 79 insertions(+), 63 deletions(-)

diff --git a/tools/perf/tests/shell/test_export_to_postgresql_python.sh b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
index 350813466700..835f48f002e9 100755
--- a/tools/perf/tests/shell/test_export_to_postgresql_python.sh
+++ b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
@@ -61,9 +61,10 @@ test_file_mode() {
 	fi
 
 	# Generate events with callchains and context switches
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -92,29 +93,33 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-postgresql.py with intel_pt..."
 
-	psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
-	rm -f "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
+		rm -f "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-postgresql -i "${temp_data}" \
-		-o "${temp_db}" --itrace cr >/dev/null; then
-		echo "intel_pt file mode test failed."
-		err=1
-	else
-		# Check DB for calls
-		if ! psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-postgresql -i "${temp_data}" \
+			-o "${temp_db}" --itrace cr >/dev/null && \
+		   psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
 			grep -q '[1-9]'; then
-			echo "PostgreSQL intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
+			passed=1
+			break
 		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "PostgreSQL intel_pt validation failed (no calls found)."
+		err=1
+	else
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_export_to_sqlite_python.sh b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
index d3c5e22a0754..19ca7c539cf7 100755
--- a/tools/perf/tests/shell/test_export_to_sqlite_python.sh
+++ b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
@@ -47,9 +47,10 @@ test_file_mode() {
 	echo "Testing export-to-sqlite.py..."
 
 	# Generate events with callchains and context switches if supported
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -77,29 +78,34 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-sqlite.py with intel_pt..."
 
-	rm -f "${temp_db}" "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
+	query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
+	query="${query}exit(1 if r == 0 else 0)"
+
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_db}" "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr; then
-		echo "intel_pt file mode test failed."
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr && \
+		   "$PYTHON" -c "$query" >/dev/null 2>&1; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "SQLite intel_pt validation failed (no calls found)."
 		err=1
 	else
-		# Check DB for calls
-		query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
-		query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
-		query="${query}exit(1 if r == 0 else 0)"
-		if ! "$PYTHON" -c "$query" >/dev/null 2>&1; then
-			echo "SQLite intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
-		fi
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_intel_pt_events_python.sh b/tools/perf/tests/shell/test_intel_pt_events_python.sh
index b5c3173fa2db..9754b9125da1 100755
--- a/tools/perf/tests/shell/test_intel_pt_events_python.sh
+++ b/tools/perf/tests/shell/test_intel_pt_events_python.sh
@@ -30,7 +30,8 @@ cleanup() {
 	[ -n "${temp_dir}" ] && rm -rf "${temp_dir}"
 }
 
-trap 'cleanup' EXIT TERM INT
+trap 'cleanup' EXIT
+trap 'cleanup; exit 1' TERM INT
 
 temp_dir=$(mktemp -d /tmp/perf.ipt.XXXXXX)
 temp_data="${temp_dir}/perf.data"
@@ -39,27 +40,31 @@ temp_out="${temp_dir}/perf.out"
 test_intel_pt() {
 	echo "Testing intel-pt-events.py with intel_pt..."
 
-	rm -f "${temp_data}" "${temp_out}"
-	# Generate some intel_pt events; use a subshell that waits for uname so
-	# uname's AUX buffer is flushed before the parent workload exits.
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		exit 2
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			exit 2
+		fi
 
-	# Run the script and check output
-	if ! perf script intel-pt-events -i "${temp_data}" > "${temp_out}"; then
-		echo "intel-pt-events.py test failed."
+		# Run the script and check output
+		if perf script intel-pt-events -i "${temp_data}" > "${temp_out}" && \
+		   grep -q "Intel PT Branch Trace" "${temp_out}" && \
+		   grep -q "uname" "${temp_out}"; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "Failed to find expected output: $(cat "${temp_out}" 2>/dev/null)"
 		err=1
 	else
-		if ! grep -q "Intel PT Branch Trace" "${temp_out}" || \
-		   ! grep -q "uname" "${temp_out}"; then
-			echo "Failed to find expected output: $(cat "${temp_out}")"
-			err=1
-		else
-			echo "intel-pt-events test passed."
-		fi
+		echo "intel-pt-events test passed."
 	fi
 	rm -f "${temp_out}"
 }
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 5/9] perf test: Deflake failed-syscalls Python shell tests under load

[Ian Rogers]

When running 'perf test' in parallel under heavy system load, a one-shot
'perf record -e ... -- ls /does_not_exist' without '-B -N --no-bpf-event'
can exit in under 300 microseconds before 'ls's PERF_RECORD_COMM and
ENOENT sys_exit events are captured, while also contending on ~/.debug
build-id caching and BPF event synthesis.

Pass '-B -N --no-bpf-event' to 'perf record', sleep 0.05s in a subshell
after 'ls' so its events are flushed before the parent subshell exits,
and wrap the record and check steps in a bounded retry loop (up to 5
attempts).

Fixes: b76c43d09b06 ("perf python: Port failed-syscalls-by-pid to perf module")
Fixes: 4e3fe6987cba ("perf python: Port failed-syscalls from Perl to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 44 +++++++-----
 2 files changed, 67 insertions(+), 45 deletions(-)

diff --git a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
index 215372d4e1c5..070a7ef6b8ad 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
@@ -41,8 +41,10 @@ test_file_mode() {
 	echo "Testing failed-syscalls-by-pid.py..."
 
 	# Check if syscalls:sys_exit is supported/readable
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-		if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+			-o /dev/null -- true >/dev/null 2>&1; then
 			echo "Skipping test, no syscalls:sys_exit or raw_syscalls:sys_exit event"
 			exit 2
 		else
@@ -52,41 +54,49 @@ test_file_mode() {
 		EVENT="syscalls:sys_exit"
 	fi
 
-	# Generate some events by running a command that should fail at least some syscall
-	# (e.g. failing stat on non-existent file).
-	# Using '|| true' because 'perf record' returns the exit code of 'ls',
-	# which fails with ENOENT
-	perf record -e "${EVENT}" -o "${temp_data}" -- ls /does_not_exist >/dev/null 2>&1 || true
+	# Generate some events by running a command that fails a syscall
+	# (e.g. failing stat on non-existent file), sleeping briefly in the
+	# subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
+		perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+			-- sh -c "ls /does_not_exist 2>/dev/null; sleep 0.05 || true" \
+			>/dev/null 2>&1 || true
+		if [ ! -s "${temp_data}" ]; then
+			continue
+		fi
+
+		if perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}" && \
+		   grep -n -q "err = ENOENT" "${temp_out}" && \
+		   perf script failed-syscalls-by-pid -i "${temp_data}" \
+			"ls" > "${temp_out}.comm" && \
+		   grep -q "err = ENOENT" "${temp_out}.comm"; then
+			ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' \
+				"${temp_out}.comm" | head -n 1)
+			if [ -n "${ls_pid}" ] && \
+			   perf script failed-syscalls-by-pid -i "${temp_data}" \
+				"${ls_pid}" > "${temp_out}.pid" && \
+			   grep -q "err = ENOENT" "${temp_out}.pid"; then
+				passed=1
+				break
+			fi
+		fi
+	done
+
 	if [ ! -s "${temp_data}" ]; then
 		echo "Skipping test, perf record failed to create data"
 		exit 2
 	fi
 
-	# Run the script and check output
-	if ! perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}"; then
+	if [ "$passed" -eq 0 ]; then
 		echo "failed-syscalls-by-pid test failed."
-		err=1
-	elif ! grep -n -q "err = ENOENT" "${temp_out}"; then
-		echo "Failed to find expected failed syscalls"
-		cat "${temp_out}"
-		err=1
-	elif ! perf script failed-syscalls-by-pid -i "${temp_data}" "ls" > "${temp_out}.comm" || \
-	     ! grep -q "err = ENOENT" "${temp_out}.comm"; then
-		echo "failed-syscalls-by-pid comm filter test failed."
-		cat "${temp_out}.comm"
+		cat "${temp_out}" 2>/dev/null || true
+		cat "${temp_out}.comm" 2>/dev/null || true
+		cat "${temp_out}.pid" 2>/dev/null || true
 		err=1
 	else
-		ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' "${temp_out}.comm" | head -n 1)
-		if [ -z "${ls_pid}" ] || \
-		   ! perf script failed-syscalls-by-pid -i "${temp_data}" \
-			"${ls_pid}" > "${temp_out}.pid" || \
-		   ! grep -q "err = ENOENT" "${temp_out}.pid"; then
-			echo "failed-syscalls-by-pid PID filter test failed."
-			cat "${temp_out}.pid" 2>/dev/null || true
-			err=1
-		else
-			echo "failed-syscalls-by-pid test passed."
-		fi
+		echo "failed-syscalls-by-pid test passed."
 	fi
 	rm -f "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
 }
diff --git a/tools/perf/tests/shell/test_failed_syscalls_python.sh b/tools/perf/tests/shell/test_failed_syscalls_python.sh
index 861c2ba71c0a..88a42e3de4f3 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_python.sh
@@ -41,8 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing failed-syscalls.py..."
 
 # Check if sys_exit event can be recorded
-if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+	-o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
 		echo "Skipping test, no permission or support for sys_exit event"
 		exit 2
 	else
@@ -52,28 +54,38 @@ else
 	EVENT="raw_syscalls:sys_exit"
 fi
 
-# Run perf record with a command that fails a syscall (ls non-existent file).
-# ls exits with non-zero, so perf record returns non-zero exit code of the workload.
-perf record -e "${EVENT}" -o "${temp_data}" \
-	-- ls /nonexistent_file_for_test >/dev/null 2>&1 || true
+# Run perf record with a command that fails a syscall (ls non-existent file),
+# sleeping briefly in the subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+		-- sh -c "ls /nonexistent_file_for_test 2>/dev/null; sleep 0.05 || true" \
+		>/dev/null 2>&1 || true
+
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script failed-syscalls -i "${temp_data}" > "${temp_out}" && \
+	   grep -q "failed syscalls by comm" "${temp_out}" && \
+	   grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
 
 if [ ! -s "${temp_data}" ]; then
 	echo "Skipping test, perf record failed to create data"
 	exit 2
 fi
 
-# Check that the script executes
-if ! perf script failed-syscalls -i "${temp_data}" > "${temp_out}"; then
-	echo "failed-syscalls.py test failed"
+if [ "$passed" -eq 0 ]; then
+	echo "Failed to find the metrics table header or expected error"
 	err=1
 else
-	if ! grep -q "failed syscalls by comm" "${temp_out}" || \
-		! grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
-		echo "Failed to find the metrics table header or expected error"
-		err=1
-	else
-		echo "failed-syscalls test passed."
-	fi
+	echo "failed-syscalls test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 6/9] perf test: Reduce overhead and contention in Python shell tests

[Ian Rogers]

When all Python shell tests run concurrently during 'perf test' under
heavy load:
1. Unfiltered 'perf list' initializes all hardware PMUs and metrics in
   each test process; use 'perf list tracepoint' when checking for
   tracepoint events.
2. Running 'perf record' without '-B -N --no-bpf-event' synthesizes BPF
   events across the system and caches build-ids into ~/.debug; add
   '-B -N --no-bpf-event' to all Python shell test recordings.
3. Drop '-a' in test_check_perf_trace_python.sh,
   test_rw_by_file_python.sh, test_rw_by_pid_python.sh,
   test_rwtop_python.sh, and test_syscall_counts_by_pid_python.sh where
   only a single child workload ('dd' or 'sleep') is tested, avoiding
   system-wide /proc synthesis and ringbuffer contention.
4. Add '-W 1' to 'ping -c 1' in test_net_dropmonitor_python.sh and
   test_netdev_times_python.sh, and narrow 'compaction:*' to
   'compaction:mm_compaction_begin,compaction:mm_compaction_end' in
   test_compaction_times_python.sh.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/test_check_perf_trace_python.sh   | 8 +++++---
 tools/perf/tests/shell/test_compaction_times_python.sh   | 8 +++++---
 .../tests/shell/test_event_analyzing_sample_python.sh    | 3 ++-
 tools/perf/tests/shell/test_flamegraph_python.sh         | 5 +++--
 tools/perf/tests/shell/test_futex_contention_python.sh   | 7 ++++---
 tools/perf/tests/shell/test_gecko_python.sh              | 3 ++-
 tools/perf/tests/shell/test_mem_phys_addr_python.sh      | 8 +++++---
 tools/perf/tests/shell/test_net_dropmonitor_python.sh    | 9 +++++----
 tools/perf/tests/shell/test_netdev_times_python.sh       | 6 +++---
 tools/perf/tests/shell/test_powerpc_hcalls_python.sh     | 4 ++--
 tools/perf/tests/shell/test_rw_by_file_python.sh         | 5 +++--
 tools/perf/tests/shell/test_rw_by_pid_python.sh          | 4 ++--
 tools/perf/tests/shell/test_rwtop_python.sh              | 4 ++--
 tools/perf/tests/shell/test_sched_migration_python.sh    | 4 ++--
 tools/perf/tests/shell/test_stackcollapse_python.sh      | 2 +-
 .../tests/shell/test_syscall_counts_by_pid_python.sh     | 6 +++---
 tools/perf/tests/shell/test_syscall_counts_python.sh     | 5 +++--
 tools/perf/tests/shell/test_task_analyzer.sh             | 3 ++-
 tools/perf/tests/shell/test_wakeup_latency_python.sh     | 7 ++++---
 19 files changed, 58 insertions(+), 43 deletions(-)

diff --git a/tools/perf/tests/shell/test_check_perf_trace_python.sh b/tools/perf/tests/shell/test_check_perf_trace_python.sh
index 92cc7b1f0033..baf55945d429 100755
--- a/tools/perf/tests/shell/test_check_perf_trace_python.sh
+++ b/tools/perf/tests/shell/test_check_perf_trace_python.sh
@@ -45,10 +45,11 @@ test_file_mode() {
 	echo "Testing check-perf-trace.py..."
 
 	events=""
-	if perf list | grep -q "irq:softirq_entry"; then
+	tp_list=$(perf list tracepoint)
+	if echo "$tp_list" | grep -q "irq:softirq_entry"; then
 		events="irq:softirq_entry"
 	fi
-	if perf list | grep -q "kmem:kmalloc"; then
+	if echo "$tp_list" | grep -q "kmem:kmalloc"; then
 		if [ -n "$events" ]; then
 			events="$events,kmem:kmalloc,kmem:kfree"
 		else
@@ -62,7 +63,8 @@ test_file_mode() {
 	fi
 
 	# Generate events
-	if ! perf record -e "$events" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e "$events" -o "${temp_data}" \
+		-- sh -c "sleep 0.1" >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_compaction_times_python.sh b/tools/perf/tests/shell/test_compaction_times_python.sh
index 50397afaafed..3f5a71e52388 100755
--- a/tools/perf/tests/shell/test_compaction_times_python.sh
+++ b/tools/perf/tests/shell/test_compaction_times_python.sh
@@ -44,15 +44,17 @@ test_file_mode() {
 	echo "Testing compaction-times.py..."
 
 	# Check for any compaction events to see if kernel supports it
-	if ! perf list | grep -q "compaction:mm_compaction_begin"; then
+	if ! perf list tracepoint | grep -q "compaction:mm_compaction_begin"; then
 		echo "Skipping test, compaction tracepoints not found"
 		exit 2
 	fi
 
 	# Generate some events
-	# We might not naturally trigger compaction in 0.5s sleep, but the script
+	# We might not naturally trigger compaction in 0.1s sleep, but the script
 	# should parse the empty or sparse file correctly without crashing.
-	if ! perf record -e "compaction:*" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event \
+		-e "compaction:mm_compaction_begin,compaction:mm_compaction_end" \
+		-a -o "${temp_data}" -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index a7a8ded003db..5f0a41080acf 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing event_analyzing_sample.py..."
 
 	# Generate some events
-	if ! perf record -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_flamegraph_python.sh b/tools/perf/tests/shell/test_flamegraph_python.sh
index 86313c72f53e..787d6bbdf04a 100755
--- a/tools/perf/tests/shell/test_flamegraph_python.sh
+++ b/tools/perf/tests/shell/test_flamegraph_python.sh
@@ -60,7 +60,8 @@ test_file_mode() {
 	echo "Testing flamegraph.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
@@ -75,7 +76,7 @@ test_file_mode() {
 
 	# Run the script in pipe ('-') mode and validate JSON output
 	rm -f "${temp_json}"
-	if ! perf record -g -o - -- perf test -w noploop 2>/dev/null | \
+	if ! perf record -B -N --no-bpf-event -g -o - -- perf test -w noploop 2>/dev/null | \
 		perf script flamegraph -i - -f json -o "${temp_json}" >/dev/null; then
 		echo "Pipe stdin JSON mode test failed."
 		err=1
diff --git a/tools/perf/tests/shell/test_futex_contention_python.sh b/tools/perf/tests/shell/test_futex_contention_python.sh
index a8846ed68ac2..41ce8470a75f 100755
--- a/tools/perf/tests/shell/test_futex_contention_python.sh
+++ b/tools/perf/tests/shell/test_futex_contention_python.sh
@@ -89,14 +89,15 @@ EOF
 test_file_mode() {
 	echo "Testing futex-contention.py..."
 	# Some systems might not have syscalls:sys_enter_futex
-	if ! perf list | grep -q syscalls:sys_enter_futex; then
+	if ! perf list tracepoint | grep -q syscalls:sys_enter_futex; then
 		echo "Skipping file mode test, syscalls:sys_enter_futex not found"
 		return
 	fi
 
 	# Generate some futex events
-	if ! perf record -e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
-		-- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event \
+		-e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
+		-- sleep 0.1 2>/dev/null; then
 		echo "Skipping file mode test (record failed)"
 		return
 	fi
diff --git a/tools/perf/tests/shell/test_gecko_python.sh b/tools/perf/tests/shell/test_gecko_python.sh
index de1d7fcf88b7..18e9f5cd2ab0 100755
--- a/tools/perf/tests/shell/test_gecko_python.sh
+++ b/tools/perf/tests/shell/test_gecko_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing gecko.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_mem_phys_addr_python.sh b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
index 451692d5e089..cbb9f572be9d 100755
--- a/tools/perf/tests/shell/test_mem_phys_addr_python.sh
+++ b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
@@ -78,10 +78,12 @@ test_file_mode() {
 	echo "Testing mem-phys-addr.py file mode..."
 
 	# Generate memory access events (try unprivileged user-space first, then system-wide)
-	if ! perf record --phys-data -d -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event --phys-data -d -o "${temp_data}" \
 	     -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -o "${temp_data}" -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -a -o "${temp_data}" -- sleep 0.2 >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -d -o "${temp_data}" \
+	     -- perf test -w datasym >/dev/null 2>&1 && \
+	   ! perf record -B -N --no-bpf-event -d -a -o "${temp_data}" \
+	     -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping file mode record test, perf record -d not supported"
 		return 0
 	fi
diff --git a/tools/perf/tests/shell/test_net_dropmonitor_python.sh b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
index 05056a897bc9..2e37994418fc 100755
--- a/tools/perf/tests/shell/test_net_dropmonitor_python.sh
+++ b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
@@ -42,11 +42,12 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing net_dropmonitor.py..."
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -o "${temp_data}" -a \
-	-- ping -c 1 255.255.255.255 >/dev/null 2>&1; then
-	if ! perf record -e skb:kfree_skb -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" -a \
+	-- ping -c 1 -W 1 255.255.255.255 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1; then
-		if ! perf record -o "${temp_data}" -- uname >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+			-- uname >/dev/null 2>&1; then
 			echo "Skipping test, cannot record perf events"
 			exit 2
 		fi
diff --git a/tools/perf/tests/shell/test_netdev_times_python.sh b/tools/perf/tests/shell/test_netdev_times_python.sh
index 393bf446efb2..0d8d10a42cab 100755
--- a/tools/perf/tests/shell/test_netdev_times_python.sh
+++ b/tools/perf/tests/shell/test_netdev_times_python.sh
@@ -85,9 +85,9 @@ then
 fi
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -a -o "${temp_data}" \
-	-- ping -c 1 127.0.0.1 >/dev/null 2>&1; then
-	perf record -e cycles -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -a -o "${temp_data}" \
+	-- ping -c 1 -W 1 127.0.0.1 >/dev/null 2>&1; then
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
index 19569c6d3613..b140ccf00ffa 100755
--- a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
+++ b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
@@ -67,8 +67,8 @@ if ! grep -q "H_REMOVE.*1.*1500.*1500.*1500" "${temp_out}"; then
 fi
 
 # Create a perf.data file if powerpc hcall tracepoints are available on this host.
-if ! perf record -e powerpc:hcall_entry,powerpc:hcall_exit -a -o "${temp_data}" \
-	-- perf test -w noploop >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e powerpc:hcall_entry,powerpc:hcall_exit \
+	-a -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
 	echo "Skipping live record test, powerpc hcall tracepoints not available"
 	exit 0
 fi
diff --git a/tools/perf/tests/shell/test_rw_by_file_python.sh b/tools/perf/tests/shell/test_rw_by_file_python.sh
index f121597f418f..e3c538c3ace3 100755
--- a/tools/perf/tests/shell/test_rw_by_file_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_file_python.sh
@@ -37,8 +37,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-file.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
-	perf record -e syscalls:sys_enter_read,syscalls:sys_enter_write -a -o "${temp_data}" \
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
+	perf record -B -N --no-bpf-event -e syscalls:sys_enter_read,syscalls:sys_enter_write \
+		-o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rw_by_pid_python.sh b/tools/perf/tests/shell/test_rw_by_pid_python.sh
index 41eaa29097a2..cd93c1d9714c 100755
--- a/tools/perf/tests/shell/test_rw_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_pid_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-pid.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rwtop_python.sh b/tools/perf/tests/shell/test_rwtop_python.sh
index 05897e384702..d33807923c92 100755
--- a/tools/perf/tests/shell/test_rwtop_python.sh
+++ b/tools/perf/tests/shell/test_rwtop_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rwtop.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_sched_migration_python.sh b/tools/perf/tests/shell/test_sched_migration_python.sh
index 75465bcd3791..714275b0e492 100755
--- a/tools/perf/tests/shell/test_sched_migration_python.sh
+++ b/tools/perf/tests/shell/test_sched_migration_python.sh
@@ -44,10 +44,10 @@ echo "Testing sched-migration.py..."
 ev="sched:sched_switch,sched:sched_migrate_task"
 ev="${ev},sched:sched_wakeup_new,sched:sched_wakeup"
 has_sched=1
-if ! perf record -e "$ev" -a -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 	-- sleep 0.1 >/dev/null 2>&1; then
 	has_sched=0
-	perf record -e cycles -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_stackcollapse_python.sh b/tools/perf/tests/shell/test_stackcollapse_python.sh
index ce0f80407eec..2048734c5e0d 100755
--- a/tools/perf/tests/shell/test_stackcollapse_python.sh
+++ b/tools/perf/tests/shell/test_stackcollapse_python.sh
@@ -37,7 +37,7 @@ echo "Testing stackcollapse.py..."
 
 # Create a perf.data file with callchains. Use a busy workload rather than
 # sleep, as an idle system may not generate any samples at all.
-perf record -g -o "${temp_data}" \
+perf record -B -N --no-bpf-event -g -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
index 45bbdc554c8f..300289fe33b4 100755
--- a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
@@ -43,14 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts-by-pid.py..."
 	# Some systems might not have raw_syscalls:sys_enter
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.5 >/dev/null 2>&1 || \
+	perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
 	if ! perf script syscall-counts-by-pid -i "${temp_data}" > "${temp_out}"; then
diff --git a/tools/perf/tests/shell/test_syscall_counts_python.sh b/tools/perf/tests/shell/test_syscall_counts_python.sh
index 310e05d399f9..86463f14391b 100755
--- a/tools/perf/tests/shell/test_syscall_counts_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_python.sh
@@ -43,13 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts.py..."
 	# Some systems might not have raw_syscalls:sys_enter (e.g. stripped kernels or permissions)
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	if ! perf record -e raw_syscalls:sys_enter -o "${temp_data}" -- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" 2>/dev/null; then
 		echo "perf record failed (permissions?), skipping file mode test."
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh
index f99a637a6099..f53fa4a27c79 100755
--- a/tools/perf/tests/shell/test_task_analyzer.sh
+++ b/tools/perf/tests/shell/test_task_analyzer.sh
@@ -60,7 +60,8 @@ skip_no_probe_record_support() {
 
 prepare_perf_data() {
 	# 1s should be sufficient to catch at least some switches
-	perf record -e sched:sched_switch -a -o "${perfdata}" -- sleep 1 > /dev/null 2>&1
+	perf record -B -N --no-bpf-event -e sched:sched_switch -a -o "${perfdata}" \
+		-- sleep 1 > /dev/null 2>&1
 	# check if perf data file got created in above step.
 	if [ ! -e "${perfdata}" ]; then
 		printf "FAIL: perf record failed to create \"${perfdata}\" \n"
diff --git a/tools/perf/tests/shell/test_wakeup_latency_python.sh b/tools/perf/tests/shell/test_wakeup_latency_python.sh
index cb2571449168..b43a86996be2 100755
--- a/tools/perf/tests/shell/test_wakeup_latency_python.sh
+++ b/tools/perf/tests/shell/test_wakeup_latency_python.sh
@@ -41,9 +41,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing wakeup-latency.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "sched:sched_wakeup"; then
+if perf list tracepoint | grep -q "sched:sched_wakeup"; then
 	ev="sched:sched_wakeup,sched:sched_wakeup_new,sched:sched_switch"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
@@ -70,7 +70,8 @@ else
 fi
 
 # Also test zero-wakeups / unhandled events path to verify division-by-zero protection
-if perf record -e cycles -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+if perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
+	-- perf test -w noploop >/dev/null 2>&1; then
 	if ! perf script wakeup-latency -i "${temp_data}" > "${temp_out}" || \
 	   ! grep -q "avg_wakeup_latency (ns): N/A" "${temp_out}"; then
 		echo "wakeup-latency zero-wakeups guard test failed"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 7/9] perf python event_analyzing_sample: Default to in-memory SQLite database

[Ian Rogers]

When -d/--db is not specified, event_analyzing_sample.py created a
temporary file in /tmp via tempfile.mkstemp() and deleted it in
trace_end(). As noted during review, creating the database in a shared
/tmp directory does not reserve SQLite's auxiliary sidecar filenames
(-journal or -wal), and a temporary on-disk file is unnecessary when the
caller did not ask to persist the database.

Default to sqlite3.connect(":memory:") when db_path is not provided,
removing the temporary file creation and cleanup logic, and test both
the default in-memory mode and explicit -d file mode in
test_event_analyzing_sample_python.sh.

Fixes: eeb70645a809 ("perf python: Port event_analyzing_sample to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/event_analyzing_sample.py   | 35 ++++++-------------
 .../test_event_analyzing_sample_python.sh     |  8 ++++-
 2 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/tools/perf/python/event_analyzing_sample.py b/tools/perf/python/event_analyzing_sample.py
index 15b47cff9fa3..b4efee88d94b 100755
--- a/tools/perf/python/event_analyzing_sample.py
+++ b/tools/perf/python/event_analyzing_sample.py
@@ -17,10 +17,8 @@ from __future__ import annotations
 
 import argparse
 import math
-import os
 import sqlite3
 import struct
-import tempfile
 from typing import Any
 import perf
 
@@ -117,16 +115,11 @@ session: Any = None
 
 class _DB:
     con: sqlite3.Connection | None = None
-    temp_path: str | None = None
 
 def trace_begin(db_path: str | None = None) -> None:
     """Initialize database tables."""
     print("In trace_begin:\n")
-    if not db_path:
-        fd, db_path = tempfile.mkstemp(prefix="perf_events_", suffix=".db")
-        os.close(fd)
-        _DB.temp_path = db_path
-    con = sqlite3.connect(db_path)
+    con = sqlite3.connect(db_path or ":memory:")
     try:
         # Drop any pre-existing tables so repeated runs do not accumulate duplicate events.
         con.execute("drop table if exists gen_events;")
@@ -297,28 +290,20 @@ def show_pebs_ll() -> None:
 def trace_end() -> None:
     """Called at the end of trace processing."""
     print("In trace_end:\n")
-    try:
-        if _DB.con:
-            try:
-                _DB.con.commit()
-                show_general_events()
-                show_pebs_ll()
-            finally:
-                _DB.con.close()
-                _DB.con = None
-    finally:
-        if _DB.temp_path and os.path.exists(_DB.temp_path):
-            try:
-                os.remove(_DB.temp_path)
-            except OSError:
-                pass
-            _DB.temp_path = None
+    if _DB.con:
+        try:
+            _DB.con.commit()
+            show_general_events()
+            show_pebs_ll()
+        finally:
+            _DB.con.close()
+            _DB.con = None
 
 if __name__ == "__main__":
     ap = argparse.ArgumentParser(description="Analyze events with SQLite")
     ap.add_argument("-i", "--input", default="perf.data", help="Input file name")
     ap.add_argument("-d", "--db", "--database", dest="database", default=None,
-                    help="Database file name (defaults to a temporary file cleaned up on exit)")
+                    help="Database file name (defaults to an in-memory database)")
     args = ap.parse_args()
 
     try:
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index 5f0a41080acf..cddb12b67698 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -45,8 +45,14 @@ test_file_mode() {
 		exit 2
 	fi
 
-	# Run the script
+	# Run the script with default (:memory:) database and with explicit -d path
 	if ! perf script event_analyzing_sample -i "${temp_data}" \
+		> "${temp_dir}/perf.mem.out" 2>&1 || \
+	   ! grep -q "Statistics about the general events" "${temp_dir}/perf.mem.out" || \
+	   grep -q "Error creating/inserting event" "${temp_dir}/perf.mem.out"; then
+		echo "Default in-memory database mode test failed."
+		err=1
+	elif ! perf script event_analyzing_sample -i "${temp_data}" \
 		-d "${temp_db}" > "${temp_dir}/perf.out" 2>&1; then
 		echo "File mode test failed."
 		err=1
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 8/9] perf python: Initialize debug output on module load

[Ian Rogers]

Unlike the perf binary's main(), PyInit_perf() does not call
perf_debug_setup(). As a result, the first warning or error printed from
the perf Python C extension hits debug_file() with _debug_file == NULL
and emits 'debug_file not set' without a trailing newline before the
actual diagnostic message.

Call perf_debug_setup() in PyInit_perf() and add the missing trailing
newline to the fallback warning in debug_file().

Fixes: ec49230cf6dd ("perf debug: Expose debug file")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/debug.c  | 2 +-
 tools/perf/util/python.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 6b5ffe81f141..b7095519419e 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -55,7 +55,7 @@ FILE *debug_file(void)
 {
 	if (!_debug_file) {
 		debug_set_file(stderr);
-		pr_warning_once("debug_file not set");
+		pr_warning_once("%s not set\n", __func__);
 	}
 	return _debug_file;
 }
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 690a94fb4f62..95140dfaef9c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -5157,6 +5157,7 @@ PyMODINIT_FUNC PyInit_perf(void)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	perf_debug_setup();
 
 	Py_INCREF(&pyrf_evlist__type);
 	PyModule_AddObject(module, "evlist", (PyObject *)&pyrf_evlist__type);
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v1 9/9] perf pmu: Fix race with concurrent tracepoint creation and removal in perf list

[Ian Rogers]

perf_pmus__print_pmu_events() first counts events via
perf_pmu__num_events() to allocate the aliases array, then populates it
via perf_pmu__for_each_event(). When dynamic tracepoints (such as
kprobes or uprobes during 'perf test' runs) are concurrently created or
removed between the two passes:
- If an event is removed, state.index is smaller than the allocated len,
  leaving trailing zeroed entries in aliases[] with name == NULL and
  pmu == NULL, which causes qsort(cmp_sevent) or the print loop to crash
  with SIGSEGV.
- If a dynamic tracepoint subsystem directory is removed while scanning
  /sys/kernel/tracing/events, tp_pmu__for_each_tp_event() returns
  -ENOENT and aborts enumeration of all remaining tracepoint subsystems.
- If an event is added, perf_pmus__print_pmu_events__callback() aborts
  enumeration when state->index reaches state->aliases_len.

Grow state->aliases dynamically via realloc() when needed, use
state.index as the actual populated length for sorting and printing, and
ignore -ENOENT when a tracepoint subsystem directory disappears during
enumeration.

Fixes: c3245d2093c1 ("perf pmu: Abstract alias/event struct")
Fixes: 45b6e281cb06 ("perf tp_pmu: Add event APIs")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/pmus.c   | 20 ++++++++++++++++----
 tools/perf/util/tp_pmu.c |  8 ++++++--
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index e0a4cb2428ca..137abad37c33 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -571,7 +571,7 @@ static int cmp_sevent(const void *a, const void *b)
 	}
 
 	/* Order by event name. */
-	return strcmp(as->name, bs->name);
+	return strcmp(as->name ?: "", bs->name ?: "");
 }
 
 static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
@@ -581,7 +581,7 @@ static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
 		return false;
 
 	/* Don't remove duplicates for different PMUs */
-	return strcmp(a->pmu_name, b->pmu_name) == 0;
+	return strcmp(a->pmu_name ?: "", b->pmu_name ?: "") == 0;
 }
 
 struct events_callback_state {
@@ -597,8 +597,18 @@ static int perf_pmus__print_pmu_events__callback(void *vstate,
 	struct sevent *s;
 
 	if (state->index >= state->aliases_len) {
-		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
-		return 1;
+		size_t new_len = max_t(size_t, 16, state->aliases_len * 2);
+		struct sevent *new_aliases;
+
+		new_aliases = realloc(state->aliases, new_len * sizeof(struct sevent));
+		if (!new_aliases) {
+			pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
+			return 1;
+		}
+		memset(&new_aliases[state->aliases_len], 0,
+		       (new_len - state->aliases_len) * sizeof(struct sevent));
+		state->aliases = new_aliases;
+		state->aliases_len = new_len;
 	}
 	assert(info->pmu != NULL || info->name != NULL);
 	s = &state->aliases[state->index];
@@ -654,6 +664,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 		perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state,
 					 perf_pmus__print_pmu_events__callback);
 	}
+	aliases = state.aliases;
+	len = state.index;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
diff --git a/tools/perf/util/tp_pmu.c b/tools/perf/util/tp_pmu.c
index c2be8c9f9084..5ac732e06841 100644
--- a/tools/perf/util/tp_pmu.c
+++ b/tools/perf/util/tp_pmu.c
@@ -151,7 +151,9 @@ static int for_each_event_cb(void *state, const char *sys_name, const char *evt_
 
 static int for_each_event_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 int tp_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
@@ -176,7 +178,9 @@ static int num_events_cb(void *state, const char *sys_name __maybe_unused,
 
 static int num_events_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 size_t tp_pmu__num_events(struct perf_pmu *pmu __maybe_unused)
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 0/9] perf python: Follow-up fixes and shell test deflaking

[Ian Rogers]

This series contains follow-up fixes for the standalone Python scripts
and their shell tests, particularly when running 'perf test' as root
under heavy parallel load:

- Clamp sample_id size calculation for PERF_RECORD_KSYMBOL,
  PERF_RECORD_BPF_EVENT, and PERF_RECORD_TEXT_POKE records to work
  around kernels without "perf/core: Restore header fields in sideband
  output callbacks" [1].
- Fix offline interval printing in sctop.py and live signal races in
  stat-cpi.py.
- Deflake Intel PT, failed-syscalls, and other Python shell tests under
  parallel 'perf test' load by scoping tracepoint checks to
  'perf list tracepoint', passing '-B -N --no-bpf-event' to 'perf record',
  and avoiding unnecessary system-wide ('-a') recordings.
- Default event_analyzing_sample.py to an in-memory SQLite database
  (':memory:') when '--db' is not specified.
- Initialize perf debug output ('perf_debug_setup()') when loading the
  'perf' Python extension module.
- Fix races in 'perf list' ('perf_pmus__print_pmu_events()' and
  'tp_pmu.c') when concurrent tests dynamically create and remove
  kprobe/uprobes tracepoints.

v2:
- Fix 8-byte alignment calculation for PERF_RECORD_TEXT_POKE payload in
  evsel__event_size() by aligning fixed + old_len + new_len.
- Keep offline interval clock advancing on all samples in sctop.py while
  flushing any remaining syscalls at EOF.
- Use 'mktemp -d' private directories in test_sctop_python.sh and
  test_failed_syscalls_python.sh so temporary files are not unlinked and
  recreated directly in /tmp.
- Explicitly include <stdlib.h> in tools/perf/util/pmus.c.

[1] https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com

Ian Rogers (9):
  perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke
    events
  perf python sctop: Fix offline interval printing and test flakiness
  perf python stat-cpi: Fix live mode signal races and test flakiness
  perf test: Deflake Intel PT Python shell tests under load
  perf test: Deflake failed-syscalls Python shell tests under load
  perf test: Reduce overhead and contention in Python shell tests
  perf python event_analyzing_sample: Default to in-memory SQLite
    database
  perf python: Initialize debug output on module load
  perf pmu: Fix race with concurrent tracepoint creation and removal in
    perf list

 tools/perf/python/event_analyzing_sample.py   | 35 +++-------
 tools/perf/python/sctop.py                    |  7 +-
 tools/perf/python/stat-cpi.py                 | 19 +++---
 .../shell/test_check_perf_trace_python.sh     |  8 ++-
 .../shell/test_compaction_times_python.sh     |  8 ++-
 .../test_event_analyzing_sample_python.sh     | 11 ++-
 .../shell/test_export_to_postgresql_python.sh | 49 +++++++------
 .../shell/test_export_to_sqlite_python.sh     | 50 ++++++++------
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 54 +++++++++------
 .../tests/shell/test_flamegraph_python.sh     |  5 +-
 .../shell/test_futex_contention_python.sh     |  7 +-
 tools/perf/tests/shell/test_gecko_python.sh   |  3 +-
 .../shell/test_intel_pt_events_python.sh      | 43 ++++++------
 .../tests/shell/test_mem_phys_addr_python.sh  |  8 ++-
 .../shell/test_net_dropmonitor_python.sh      |  9 +--
 .../tests/shell/test_netdev_times_python.sh   |  6 +-
 .../tests/shell/test_powerpc_hcalls_python.sh |  4 +-
 .../tests/shell/test_rw_by_file_python.sh     |  5 +-
 .../perf/tests/shell/test_rw_by_pid_python.sh |  4 +-
 tools/perf/tests/shell/test_rwtop_python.sh   |  4 +-
 .../shell/test_sched_migration_python.sh      |  4 +-
 tools/perf/tests/shell/test_sctop_python.sh   | 58 ++++++++--------
 .../tests/shell/test_stackcollapse_python.sh  |  2 +-
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++-
 .../test_syscall_counts_by_pid_python.sh      |  6 +-
 .../tests/shell/test_syscall_counts_python.sh |  5 +-
 tools/perf/tests/shell/test_task_analyzer.sh  |  3 +-
 .../tests/shell/test_wakeup_latency_python.sh |  7 +-
 tools/perf/util/debug.c                       |  2 +-
 tools/perf/util/evlist.c                      |  6 +-
 tools/perf/util/evsel.c                       | 59 +++++++++++++++-
 tools/perf/util/evsel.h                       |  1 +
 tools/perf/util/pmus.c                        | 21 ++++--
 tools/perf/util/python.c                      |  1 +
 tools/perf/util/tp_pmu.c                      |  8 ++-
 36 files changed, 366 insertions(+), 236 deletions(-)

-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 1/9] perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke events

[Ian Rogers]

On kernels without the fix ("perf/core: Restore header fields in
sideband output callbacks") to restore event_id.header.size in
perf_event_ksymbol_output(), perf_event_bpf_output(), and
perf_event_text_poke_output(), concurrent perf sessions cause those
sideband records to be emitted with header.size inflated by multiple
id_header_size increments while the single id_sample is written
immediately after the event payload. Indexing backwards from
event->header.size reads uninitialized ring-buffer bytes at the end of
the record, causing evlist__event2evsel() to fail with -EFAULT.

Add evsel__event_size() to clamp the effective size used to locate the
trailing id_sample for PERF_RECORD_KSYMBOL, PERF_RECORD_BPF_EVENT, and
PERF_RECORD_TEXT_POKE to payload + id_hdr_size while leaving
event->header.size intact for advancing the ring-buffer/file stream.

Fixes: 9aa0bfa370b2 ("perf tools: Handle PERF_RECORD_KSYMBOL")
Fixes: 45178a928a4b ("perf tools: Handle PERF_RECORD_BPF_EVENT")
Fixes: 246eba8e9041 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Link: https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/evlist.c |  6 ++--
 tools/perf/util/evsel.c  | 59 +++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 9392d912d254..c2402e4791b6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -973,13 +973,15 @@ static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64
 	const __u64 *array = event->sample.array;
 	ssize_t n;
 
-	n = (event->header.size - sizeof(event->header)) >> 3;
-
 	if (event->header.type == PERF_RECORD_SAMPLE) {
+		n = (event->header.size - sizeof(event->header)) >> 3;
 		if (evlist__id_pos(evlist) >= n)
 			return -1;
 		*id = array[evlist__id_pos(evlist)];
 	} else {
+		u16 size = evsel__event_size(evlist__first(evlist), event);
+
+		n = (size - sizeof(event->header)) >> 3;
 		if (evlist__is_pos(evlist) > n)
 			return -1;
 		n -= evlist__is_pos(evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3367242c5764..9c5e7510f0c0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3216,7 +3216,7 @@ static int perf_evsel__parse_id_sample(const union perf_event *event,
 	const __u64 *array = event->sample.array;
 	bool swapped = evsel->needs_swap;
 	union u64_swap u;
-	int i = ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1;
+	int i = ((evsel__event_size(evsel, event) - sizeof(event->header)) / sizeof(u64)) - 1;
 
 	if (type & PERF_SAMPLE_IDENTIFIER) {
 		if (i < 0)
@@ -3966,6 +3966,63 @@ u16 evsel__id_hdr_size(const struct evsel *evsel)
 	return size;
 }
 
+/*
+ * Prior to kernel fix, perf_event_ksymbol_output(), perf_event_bpf_output(),
+ * and perf_event_text_poke_output() in kernel/events/core.c did not save and
+ * restore event_id.header.size across perf_iterate_sb() iterations. When
+ * multiple perf_events had attr.ksymbol, attr.bpf_event, or attr.text_poke
+ * enabled, header.size was incremented by id_header_size for each matching
+ * event while only a single id_sample was written immediately after the event
+ * payload. Clamp the effective size used to locate the trailing id_sample to
+ * payload + id_hdr_size so events recorded on unpatched kernels can be parsed
+ * without reading uninitialized ring-buffer bytes.
+ */
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event)
+{
+	u16 size = event->header.size;
+	u16 id_hdr_size;
+	size_t payload;
+
+	if (!evsel->core.attr.sample_id_all)
+		return size;
+
+	switch (event->header.type) {
+	case PERF_RECORD_KSYMBOL: {
+		const char *name = event->ksymbol.name;
+		size_t fixed = offsetof(struct perf_record_ksymbol, name);
+		size_t max_len, len;
+
+		if (size <= fixed)
+			return size;
+		max_len = size - fixed;
+		len = strnlen(name, max_len);
+		if (len == max_len)
+			return size;
+		payload = fixed + PERF_ALIGN(len + 1, sizeof(u64));
+		break;
+	}
+	case PERF_RECORD_BPF_EVENT:
+		payload = sizeof(struct perf_record_bpf_event);
+		break;
+	case PERF_RECORD_TEXT_POKE: {
+		size_t fixed = offsetof(struct perf_record_text_poke_event, bytes);
+
+		if (size < fixed)
+			return size;
+		payload = PERF_ALIGN(fixed + (size_t)event->text_poke.old_len +
+				     event->text_poke.new_len, sizeof(u64));
+		break;
+	}
+	default:
+		return size;
+	}
+
+	id_hdr_size = evsel__id_hdr_size(evsel);
+	if (payload + id_hdr_size < size)
+		return payload + id_hdr_size;
+	return size;
+}
+
 #ifdef HAVE_LIBTRACEEVENT
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5c5799cee601..174f3414fd3c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -469,6 +469,7 @@ int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
 				  u64 *timestamp);
 
 u16 evsel__id_hdr_size(const struct evsel *evsel);
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event);
 
 static inline struct evsel *evsel__next(struct evsel *evsel)
 {
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 2/9] perf python sctop: Fix offline interval printing and test flakiness

[Ian Rogers]

In sctop.py:
- If an earlier interval elapsed and printed an empty table before the
  target comm ('sleep') executed any syscalls, analyzer.printed became
  True and the final partial interval containing the target comm's
  syscalls was never flushed at EOF. Flush print_current_totals() in
  finally when analyzer.syscalls is non-empty as well as when nothing
  has been printed yet.
- Initialize analyzer.e_machine after creating perf.session rather than
  when session is still None.

In test_sctop_python.sh:
- Use a private temporary directory via 'mktemp -d'.
- Drop '-a' and pass '-B -N --no-bpf-event' to 'perf record', and sleep
  briefly in the subshell ('sh -c "sleep 0.1; sleep 0.05"') with a
  bounded retry loop so 'sleep's PERF_RECORD_COMM and sys_enter events
  are reliably captured under heavy load.

Fixes: b83f0bacf5e4 ("perf python: Port sctop to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/sctop.py                  |  7 ++-
 tools/perf/tests/shell/test_sctop_python.sh | 58 ++++++++++-----------
 2 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/tools/perf/python/sctop.py b/tools/perf/python/sctop.py
index 42e95ecfffad..48320af8b755 100755
--- a/tools/perf/python/sctop.py
+++ b/tools/perf/python/sctop.py
@@ -37,6 +37,7 @@ class SCTopAnalyzer:
         self.offline = offline
         self.own_pid = os.getpid()
         self.last_print_time: Optional[int] = None
+        self.printed = False
         self.session: Optional[perf.session] = None
         self.e_machine: Optional[int] = None
 
@@ -137,6 +138,7 @@ class SCTopAnalyzer:
 
     def print_current_totals(self):
         """Print current syscall totals."""
+        self.printed = True
         # Clear terminal
         if not self.offline:
             print("\x1b[2J\x1b[H", end="")
@@ -217,8 +219,8 @@ def main():
         if args.input:
             session = perf.session(perf.data(args.input), sample=analyzer.process_event)
             analyzer.session = session
-            session.process_events()
             analyzer.e_machine = getattr(session, "e_machine", None)
+            session.process_events()
         else:
             try:
                 live_session = LiveSession(
@@ -237,7 +239,8 @@ def main():
         sys.exit(1)
     finally:
         if args.input:
-            analyzer.print_current_totals()
+            if not analyzer.printed or analyzer.syscalls:
+                analyzer.print_current_totals()
             # Break the reference cycle between perf.session and analyzer.process_event
             # because perf.session lacks cyclic GC support (tp_traverse).
             analyzer.session = None
diff --git a/tools/perf/tests/shell/test_sctop_python.sh b/tools/perf/tests/shell/test_sctop_python.sh
index 007f2584cce6..b042fc3eefe5 100755
--- a/tools/perf/tests/shell/test_sctop_python.sh
+++ b/tools/perf/tests/shell/test_sctop_python.sh
@@ -27,51 +27,51 @@ if [ ! -f "$script_path" ]; then
 fi
 
 err=0
-temp_data=""
-temp_out=""
+temp_dir=$(mktemp -d /tmp/perf-sctop-XXXXXX)
+temp_data="${temp_dir}/perf.data"
+temp_out="${temp_dir}/perf.out"
 
 cleanup() {
-	rm -f "${temp_data}" "${temp_out}"
+	rm -rf "${temp_dir}"
 }
 trap 'cleanup' EXIT TERM INT
 
-temp_data=$(mktemp /tmp/perf.data.XXXXXX)
-temp_out=$(mktemp /tmp/perf.out.XXXXXX)
-
 echo "Testing sctop.py..."
 
 # Create a perf.data file.
-if perf list | grep -q "raw_syscalls:sys_enter"; then
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.1 >/dev/null 2>&1 || \
-		{ echo "Skipping test, perf record failed"; exit 2; }
-else
+if ! perf list tracepoint | grep -q "raw_syscalls:sys_enter"; then
 	echo "Skipping test, no raw_syscalls:sys_enter event"
 	exit 2
 fi
 
-if [ ! -s "${temp_data}" ]; then
-	echo "Skipping test, perf record failed to create data"
-	exit 2
-fi
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1; then
+		echo "Skipping test, perf record failed"
+		exit 2
+	fi
 
-# Check that the script executes
-if ! perf script sctop -i "${temp_data}" > "${temp_out}"; then
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script sctop -i "${temp_data}" > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}" && \
+	   perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
+
+if [ "$passed" -eq 0 ]; then
 	echo "sctop.py test failed"
 	err=1
-elif ! grep -E -q "[0-9]+$" "${temp_out}"; then
-	echo "Failed to find metric data rows in default run"
-	err=1
-elif ! perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}"; then
-	echo "sctop.py comm+interval test failed"
-	err=1
 else
-	if ! grep -E -q "[0-9]+$" "${temp_out}"; then
-		echo "Failed to find metric data rows"
-		err=1
-	else
-		echo "sctop test passed."
-	fi
+	echo "sctop test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 3/9] perf python stat-cpi: Fix live mode signal races and test flakiness

[Ian Rogers]

In test_stat_cpi_python.sh, 'perf test -w noploop &' defaults to a
1-second duration and can exit under heavy parallel load before
'perf stat -p' and 'perf script stat-cpi' finish starting up. In
addition, the fixed 'sleep 0.5' before sending SIGINT can fire before
Python finishes importing the perf module, opening the live evlist, and
flushing the first interval.

In stat-cpi.py, register SIGINT and SIGTERM handlers before calling
_open_live_evlist() and pass flush=True when printing live output so
redirected stdout is flushed immediately after each interval.

In test_stat_cpi_python.sh, run 'perf test -w noploop 60 &' so the
target workload stays alive until killed, and poll the output file for
'cpi' (up to 5 seconds) before sending SIGINT.

Fixes: 4425182d426b ("perf python: Port stat-cpi to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/stat-cpi.py                 | 19 ++++++++++---------
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++++++++---
 2 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/tools/perf/python/stat-cpi.py b/tools/perf/python/stat-cpi.py
index 0b7d76876a6c..da92cf560067 100755
--- a/tools/perf/python/stat-cpi.py
+++ b/tools/perf/python/stat-cpi.py
@@ -106,7 +106,8 @@ class StatCpiAnalyzer:
             if ins != 0:
                 cpi = cyc / float(ins)
             t_sec = timestamp / 1000000000.0
-            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})")
+            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})",
+                  flush=True)
 
     def read_counters(self, evlist: Any) -> None:
         """Read counters live."""
@@ -173,19 +174,19 @@ class StatCpiAnalyzer:
 
     def run_live(self) -> None:
         """Read counters live."""
-        try:
-            evlist = self._open_live_evlist()
-        except OSError as e:
-            print(f"Failed to open events: {e}", file=sys.stderr)
-            sys.exit(1)
-
         def handle_signal(_signum: int, _frame: Any) -> None:
             raise KeyboardInterrupt
 
         signal.signal(signal.SIGINT, signal.default_int_handler)
         signal.signal(signal.SIGTERM, handle_signal)
 
-        print("Live mode started. Press Ctrl+C to stop.")
+        try:
+            evlist = self._open_live_evlist()
+        except OSError as e:
+            print(f"Failed to open events: {e}", file=sys.stderr)
+            sys.exit(1)
+
+        print("Live mode started. Press Ctrl+C to stop.", flush=True)
         try:
             while True:
                 time.sleep(self.args.interval)
@@ -195,7 +196,7 @@ class StatCpiAnalyzer:
                 self.data.clear()
                 self.recorded_pairs.clear()
         except KeyboardInterrupt:
-            print("\nStopped.")
+            print("\nStopped.", flush=True)
         finally:
             evlist.close()
 
diff --git a/tools/perf/tests/shell/test_stat_cpi_python.sh b/tools/perf/tests/shell/test_stat_cpi_python.sh
index fe7562307634..6cb376c92e2f 100755
--- a/tools/perf/tests/shell/test_stat_cpi_python.sh
+++ b/tools/perf/tests/shell/test_stat_cpi_python.sh
@@ -50,7 +50,7 @@ test_live_mode() {
 		echo "perf stat failed (permissions?), skipping live mode test."
 		return 0
 	fi
-	perf test -w noploop &
+	perf test -w noploop 60 &
 	workload_pid=$!
 	if ! perf stat -e cycles,instructions -p "$workload_pid" -- sleep 0.05 2>/dev/null && \
 	   ! perf stat -e cycles:u,instructions:u -p "$workload_pid" -- sleep 0.05 2>/dev/null; then
@@ -61,10 +61,16 @@ test_live_mode() {
 	fi
 	ran=1
 
-	# Run live mode for 1 interval in the background, give it a tiny sleep, then interrupt
+	# Run live mode in the background, wait until at least one interval is
+	# printed, then interrupt.
 	perf script stat-cpi -I 0.1 -p "$workload_pid" > "${temp_out}" &
 	pid=$!
-	sleep 0.5
+	for _ in $(seq 1 50); do
+		if grep -q "cpi" "${temp_out}"; then
+			break
+		fi
+		sleep 0.1
+	done
 	kill -INT "$pid" 2>/dev/null || true
 	set +e
 	wait "$pid"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 4/9] perf test: Deflake Intel PT Python shell tests under load

[Ian Rogers]

In test_intel_pt_events_python.sh, test_export_to_sqlite_python.sh, and
test_export_to_postgresql_python.sh, 'sh -c "uname; true"' uses the
shell builtin 'true' and exits within microseconds of 'uname', sending
SIGCHLD to 'perf record' before the Intel PT AUX buffer is always
flushed under heavy parallel load (~5-10% drop rate).

Sleep 0.05s in the subshell after 'uname' ('sh -c "uname; sleep 0.05"')
so 'uname' completely exits and flushes its AUX trace before 'sh' exits,
and wrap the record and verification step in a bounded retry loop (up to
5 attempts). Also pass '-B -N --no-bpf-event' to 'perf record -g' in
test_export_to_sqlite_python.sh and test_export_to_postgresql_python.sh
to avoid build-id cache and BPF synthesis overhead.

Fixes: d4ce72e9e238 ("perf python: Port intel-pt-events and libxed to perf module")
Fixes: 62d350135e67 ("perf python: Port export-to-sqlite to perf module")
Fixes: b1f968c9656a ("perf python: Port export-to-postgresql to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../shell/test_export_to_postgresql_python.sh | 49 ++++++++++--------
 .../shell/test_export_to_sqlite_python.sh     | 50 +++++++++++--------
 .../shell/test_intel_pt_events_python.sh      | 43 +++++++++-------
 3 files changed, 79 insertions(+), 63 deletions(-)

diff --git a/tools/perf/tests/shell/test_export_to_postgresql_python.sh b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
index 350813466700..835f48f002e9 100755
--- a/tools/perf/tests/shell/test_export_to_postgresql_python.sh
+++ b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
@@ -61,9 +61,10 @@ test_file_mode() {
 	fi
 
 	# Generate events with callchains and context switches
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -92,29 +93,33 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-postgresql.py with intel_pt..."
 
-	psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
-	rm -f "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
+		rm -f "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-postgresql -i "${temp_data}" \
-		-o "${temp_db}" --itrace cr >/dev/null; then
-		echo "intel_pt file mode test failed."
-		err=1
-	else
-		# Check DB for calls
-		if ! psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-postgresql -i "${temp_data}" \
+			-o "${temp_db}" --itrace cr >/dev/null && \
+		   psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
 			grep -q '[1-9]'; then
-			echo "PostgreSQL intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
+			passed=1
+			break
 		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "PostgreSQL intel_pt validation failed (no calls found)."
+		err=1
+	else
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_export_to_sqlite_python.sh b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
index d3c5e22a0754..19ca7c539cf7 100755
--- a/tools/perf/tests/shell/test_export_to_sqlite_python.sh
+++ b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
@@ -47,9 +47,10 @@ test_file_mode() {
 	echo "Testing export-to-sqlite.py..."
 
 	# Generate events with callchains and context switches if supported
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -77,29 +78,34 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-sqlite.py with intel_pt..."
 
-	rm -f "${temp_db}" "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
+	query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
+	query="${query}exit(1 if r == 0 else 0)"
+
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_db}" "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr; then
-		echo "intel_pt file mode test failed."
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr && \
+		   "$PYTHON" -c "$query" >/dev/null 2>&1; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "SQLite intel_pt validation failed (no calls found)."
 		err=1
 	else
-		# Check DB for calls
-		query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
-		query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
-		query="${query}exit(1 if r == 0 else 0)"
-		if ! "$PYTHON" -c "$query" >/dev/null 2>&1; then
-			echo "SQLite intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
-		fi
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_intel_pt_events_python.sh b/tools/perf/tests/shell/test_intel_pt_events_python.sh
index b5c3173fa2db..9754b9125da1 100755
--- a/tools/perf/tests/shell/test_intel_pt_events_python.sh
+++ b/tools/perf/tests/shell/test_intel_pt_events_python.sh
@@ -30,7 +30,8 @@ cleanup() {
 	[ -n "${temp_dir}" ] && rm -rf "${temp_dir}"
 }
 
-trap 'cleanup' EXIT TERM INT
+trap 'cleanup' EXIT
+trap 'cleanup; exit 1' TERM INT
 
 temp_dir=$(mktemp -d /tmp/perf.ipt.XXXXXX)
 temp_data="${temp_dir}/perf.data"
@@ -39,27 +40,31 @@ temp_out="${temp_dir}/perf.out"
 test_intel_pt() {
 	echo "Testing intel-pt-events.py with intel_pt..."
 
-	rm -f "${temp_data}" "${temp_out}"
-	# Generate some intel_pt events; use a subshell that waits for uname so
-	# uname's AUX buffer is flushed before the parent workload exits.
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		exit 2
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			exit 2
+		fi
 
-	# Run the script and check output
-	if ! perf script intel-pt-events -i "${temp_data}" > "${temp_out}"; then
-		echo "intel-pt-events.py test failed."
+		# Run the script and check output
+		if perf script intel-pt-events -i "${temp_data}" > "${temp_out}" && \
+		   grep -q "Intel PT Branch Trace" "${temp_out}" && \
+		   grep -q "uname" "${temp_out}"; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "Failed to find expected output: $(cat "${temp_out}" 2>/dev/null)"
 		err=1
 	else
-		if ! grep -q "Intel PT Branch Trace" "${temp_out}" || \
-		   ! grep -q "uname" "${temp_out}"; then
-			echo "Failed to find expected output: $(cat "${temp_out}")"
-			err=1
-		else
-			echo "intel-pt-events test passed."
-		fi
+		echo "intel-pt-events test passed."
 	fi
 	rm -f "${temp_out}"
 }
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 5/9] perf test: Deflake failed-syscalls Python shell tests under load

[Ian Rogers]

When running 'perf test' in parallel under heavy system load, a one-shot
'perf record -e ... -- ls /does_not_exist' without '-B -N --no-bpf-event'
can exit in under 300 microseconds before 'ls's PERF_RECORD_COMM and
ENOENT sys_exit events are captured, while also contending on ~/.debug
build-id caching and BPF event synthesis.

Pass '-B -N --no-bpf-event' to 'perf record', sleep 0.05s in a subshell
after 'ls' so its events are flushed before the parent subshell exits,
and wrap the record and check steps in a bounded retry loop (up to 5
attempts).

Fixes: b76c43d09b06 ("perf python: Port failed-syscalls-by-pid to perf module")
Fixes: 4e3fe6987cba ("perf python: Port failed-syscalls from Perl to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 54 +++++++++------
 2 files changed, 71 insertions(+), 51 deletions(-)

diff --git a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
index 215372d4e1c5..070a7ef6b8ad 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
@@ -41,8 +41,10 @@ test_file_mode() {
 	echo "Testing failed-syscalls-by-pid.py..."
 
 	# Check if syscalls:sys_exit is supported/readable
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-		if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+			-o /dev/null -- true >/dev/null 2>&1; then
 			echo "Skipping test, no syscalls:sys_exit or raw_syscalls:sys_exit event"
 			exit 2
 		else
@@ -52,41 +54,49 @@ test_file_mode() {
 		EVENT="syscalls:sys_exit"
 	fi
 
-	# Generate some events by running a command that should fail at least some syscall
-	# (e.g. failing stat on non-existent file).
-	# Using '|| true' because 'perf record' returns the exit code of 'ls',
-	# which fails with ENOENT
-	perf record -e "${EVENT}" -o "${temp_data}" -- ls /does_not_exist >/dev/null 2>&1 || true
+	# Generate some events by running a command that fails a syscall
+	# (e.g. failing stat on non-existent file), sleeping briefly in the
+	# subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
+		perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+			-- sh -c "ls /does_not_exist 2>/dev/null; sleep 0.05 || true" \
+			>/dev/null 2>&1 || true
+		if [ ! -s "${temp_data}" ]; then
+			continue
+		fi
+
+		if perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}" && \
+		   grep -n -q "err = ENOENT" "${temp_out}" && \
+		   perf script failed-syscalls-by-pid -i "${temp_data}" \
+			"ls" > "${temp_out}.comm" && \
+		   grep -q "err = ENOENT" "${temp_out}.comm"; then
+			ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' \
+				"${temp_out}.comm" | head -n 1)
+			if [ -n "${ls_pid}" ] && \
+			   perf script failed-syscalls-by-pid -i "${temp_data}" \
+				"${ls_pid}" > "${temp_out}.pid" && \
+			   grep -q "err = ENOENT" "${temp_out}.pid"; then
+				passed=1
+				break
+			fi
+		fi
+	done
+
 	if [ ! -s "${temp_data}" ]; then
 		echo "Skipping test, perf record failed to create data"
 		exit 2
 	fi
 
-	# Run the script and check output
-	if ! perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}"; then
+	if [ "$passed" -eq 0 ]; then
 		echo "failed-syscalls-by-pid test failed."
-		err=1
-	elif ! grep -n -q "err = ENOENT" "${temp_out}"; then
-		echo "Failed to find expected failed syscalls"
-		cat "${temp_out}"
-		err=1
-	elif ! perf script failed-syscalls-by-pid -i "${temp_data}" "ls" > "${temp_out}.comm" || \
-	     ! grep -q "err = ENOENT" "${temp_out}.comm"; then
-		echo "failed-syscalls-by-pid comm filter test failed."
-		cat "${temp_out}.comm"
+		cat "${temp_out}" 2>/dev/null || true
+		cat "${temp_out}.comm" 2>/dev/null || true
+		cat "${temp_out}.pid" 2>/dev/null || true
 		err=1
 	else
-		ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' "${temp_out}.comm" | head -n 1)
-		if [ -z "${ls_pid}" ] || \
-		   ! perf script failed-syscalls-by-pid -i "${temp_data}" \
-			"${ls_pid}" > "${temp_out}.pid" || \
-		   ! grep -q "err = ENOENT" "${temp_out}.pid"; then
-			echo "failed-syscalls-by-pid PID filter test failed."
-			cat "${temp_out}.pid" 2>/dev/null || true
-			err=1
-		else
-			echo "failed-syscalls-by-pid test passed."
-		fi
+		echo "failed-syscalls-by-pid test passed."
 	fi
 	rm -f "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
 }
diff --git a/tools/perf/tests/shell/test_failed_syscalls_python.sh b/tools/perf/tests/shell/test_failed_syscalls_python.sh
index 861c2ba71c0a..9aaf05883c50 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_python.sh
@@ -27,22 +27,22 @@ if [ ! -f "$script_path" ]; then
 fi
 
 err=0
-temp_data=""
-temp_out=""
+temp_dir=$(mktemp -d /tmp/perf-failed-syscalls-XXXXXX)
+temp_data="${temp_dir}/perf.data"
+temp_out="${temp_dir}/perf.out"
 
 cleanup() {
-	rm -f "${temp_data}" "${temp_out}"
+	rm -rf "${temp_dir}"
 }
 trap 'cleanup' EXIT TERM INT
 
-temp_data=$(mktemp /tmp/perf.data.XXXXXX)
-temp_out=$(mktemp /tmp/perf.out.XXXXXX)
-
 echo "Testing failed-syscalls.py..."
 
 # Check if sys_exit event can be recorded
-if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+	-o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
 		echo "Skipping test, no permission or support for sys_exit event"
 		exit 2
 	else
@@ -52,28 +52,38 @@ else
 	EVENT="raw_syscalls:sys_exit"
 fi
 
-# Run perf record with a command that fails a syscall (ls non-existent file).
-# ls exits with non-zero, so perf record returns non-zero exit code of the workload.
-perf record -e "${EVENT}" -o "${temp_data}" \
-	-- ls /nonexistent_file_for_test >/dev/null 2>&1 || true
+# Run perf record with a command that fails a syscall (ls non-existent file),
+# sleeping briefly in the subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+		-- sh -c "ls /nonexistent_file_for_test 2>/dev/null; sleep 0.05 || true" \
+		>/dev/null 2>&1 || true
+
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script failed-syscalls -i "${temp_data}" > "${temp_out}" && \
+	   grep -q "failed syscalls by comm" "${temp_out}" && \
+	   grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
 
 if [ ! -s "${temp_data}" ]; then
 	echo "Skipping test, perf record failed to create data"
 	exit 2
 fi
 
-# Check that the script executes
-if ! perf script failed-syscalls -i "${temp_data}" > "${temp_out}"; then
-	echo "failed-syscalls.py test failed"
+if [ "$passed" -eq 0 ]; then
+	echo "Failed to find the metrics table header or expected error"
 	err=1
 else
-	if ! grep -q "failed syscalls by comm" "${temp_out}" || \
-		! grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
-		echo "Failed to find the metrics table header or expected error"
-		err=1
-	else
-		echo "failed-syscalls test passed."
-	fi
+	echo "failed-syscalls test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 6/9] perf test: Reduce overhead and contention in Python shell tests

[Ian Rogers]

When all Python shell tests run concurrently during 'perf test' under
heavy load:
1. Unfiltered 'perf list' initializes all hardware PMUs and metrics in
   each test process; use 'perf list tracepoint' when checking for
   tracepoint events.
2. Running 'perf record' without '-B -N --no-bpf-event' synthesizes BPF
   events across the system and caches build-ids into ~/.debug; add
   '-B -N --no-bpf-event' to all Python shell test recordings.
3. Drop '-a' in test_check_perf_trace_python.sh,
   test_rw_by_file_python.sh, test_rw_by_pid_python.sh,
   test_rwtop_python.sh, and test_syscall_counts_by_pid_python.sh where
   only a single child workload ('dd' or 'sleep') is tested, avoiding
   system-wide /proc synthesis and ringbuffer contention.
4. Add '-W 1' to 'ping -c 1' in test_net_dropmonitor_python.sh and
   test_netdev_times_python.sh, and narrow 'compaction:*' to
   'compaction:mm_compaction_begin,compaction:mm_compaction_end' in
   test_compaction_times_python.sh.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/test_check_perf_trace_python.sh   | 8 +++++---
 tools/perf/tests/shell/test_compaction_times_python.sh   | 8 +++++---
 .../tests/shell/test_event_analyzing_sample_python.sh    | 3 ++-
 tools/perf/tests/shell/test_flamegraph_python.sh         | 5 +++--
 tools/perf/tests/shell/test_futex_contention_python.sh   | 7 ++++---
 tools/perf/tests/shell/test_gecko_python.sh              | 3 ++-
 tools/perf/tests/shell/test_mem_phys_addr_python.sh      | 8 +++++---
 tools/perf/tests/shell/test_net_dropmonitor_python.sh    | 9 +++++----
 tools/perf/tests/shell/test_netdev_times_python.sh       | 6 +++---
 tools/perf/tests/shell/test_powerpc_hcalls_python.sh     | 4 ++--
 tools/perf/tests/shell/test_rw_by_file_python.sh         | 5 +++--
 tools/perf/tests/shell/test_rw_by_pid_python.sh          | 4 ++--
 tools/perf/tests/shell/test_rwtop_python.sh              | 4 ++--
 tools/perf/tests/shell/test_sched_migration_python.sh    | 4 ++--
 tools/perf/tests/shell/test_stackcollapse_python.sh      | 2 +-
 .../tests/shell/test_syscall_counts_by_pid_python.sh     | 6 +++---
 tools/perf/tests/shell/test_syscall_counts_python.sh     | 5 +++--
 tools/perf/tests/shell/test_task_analyzer.sh             | 3 ++-
 tools/perf/tests/shell/test_wakeup_latency_python.sh     | 7 ++++---
 19 files changed, 58 insertions(+), 43 deletions(-)

diff --git a/tools/perf/tests/shell/test_check_perf_trace_python.sh b/tools/perf/tests/shell/test_check_perf_trace_python.sh
index 92cc7b1f0033..baf55945d429 100755
--- a/tools/perf/tests/shell/test_check_perf_trace_python.sh
+++ b/tools/perf/tests/shell/test_check_perf_trace_python.sh
@@ -45,10 +45,11 @@ test_file_mode() {
 	echo "Testing check-perf-trace.py..."
 
 	events=""
-	if perf list | grep -q "irq:softirq_entry"; then
+	tp_list=$(perf list tracepoint)
+	if echo "$tp_list" | grep -q "irq:softirq_entry"; then
 		events="irq:softirq_entry"
 	fi
-	if perf list | grep -q "kmem:kmalloc"; then
+	if echo "$tp_list" | grep -q "kmem:kmalloc"; then
 		if [ -n "$events" ]; then
 			events="$events,kmem:kmalloc,kmem:kfree"
 		else
@@ -62,7 +63,8 @@ test_file_mode() {
 	fi
 
 	# Generate events
-	if ! perf record -e "$events" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e "$events" -o "${temp_data}" \
+		-- sh -c "sleep 0.1" >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_compaction_times_python.sh b/tools/perf/tests/shell/test_compaction_times_python.sh
index 50397afaafed..3f5a71e52388 100755
--- a/tools/perf/tests/shell/test_compaction_times_python.sh
+++ b/tools/perf/tests/shell/test_compaction_times_python.sh
@@ -44,15 +44,17 @@ test_file_mode() {
 	echo "Testing compaction-times.py..."
 
 	# Check for any compaction events to see if kernel supports it
-	if ! perf list | grep -q "compaction:mm_compaction_begin"; then
+	if ! perf list tracepoint | grep -q "compaction:mm_compaction_begin"; then
 		echo "Skipping test, compaction tracepoints not found"
 		exit 2
 	fi
 
 	# Generate some events
-	# We might not naturally trigger compaction in 0.5s sleep, but the script
+	# We might not naturally trigger compaction in 0.1s sleep, but the script
 	# should parse the empty or sparse file correctly without crashing.
-	if ! perf record -e "compaction:*" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event \
+		-e "compaction:mm_compaction_begin,compaction:mm_compaction_end" \
+		-a -o "${temp_data}" -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index a7a8ded003db..5f0a41080acf 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing event_analyzing_sample.py..."
 
 	# Generate some events
-	if ! perf record -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_flamegraph_python.sh b/tools/perf/tests/shell/test_flamegraph_python.sh
index 86313c72f53e..787d6bbdf04a 100755
--- a/tools/perf/tests/shell/test_flamegraph_python.sh
+++ b/tools/perf/tests/shell/test_flamegraph_python.sh
@@ -60,7 +60,8 @@ test_file_mode() {
 	echo "Testing flamegraph.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
@@ -75,7 +76,7 @@ test_file_mode() {
 
 	# Run the script in pipe ('-') mode and validate JSON output
 	rm -f "${temp_json}"
-	if ! perf record -g -o - -- perf test -w noploop 2>/dev/null | \
+	if ! perf record -B -N --no-bpf-event -g -o - -- perf test -w noploop 2>/dev/null | \
 		perf script flamegraph -i - -f json -o "${temp_json}" >/dev/null; then
 		echo "Pipe stdin JSON mode test failed."
 		err=1
diff --git a/tools/perf/tests/shell/test_futex_contention_python.sh b/tools/perf/tests/shell/test_futex_contention_python.sh
index a8846ed68ac2..41ce8470a75f 100755
--- a/tools/perf/tests/shell/test_futex_contention_python.sh
+++ b/tools/perf/tests/shell/test_futex_contention_python.sh
@@ -89,14 +89,15 @@ EOF
 test_file_mode() {
 	echo "Testing futex-contention.py..."
 	# Some systems might not have syscalls:sys_enter_futex
-	if ! perf list | grep -q syscalls:sys_enter_futex; then
+	if ! perf list tracepoint | grep -q syscalls:sys_enter_futex; then
 		echo "Skipping file mode test, syscalls:sys_enter_futex not found"
 		return
 	fi
 
 	# Generate some futex events
-	if ! perf record -e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
-		-- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event \
+		-e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
+		-- sleep 0.1 2>/dev/null; then
 		echo "Skipping file mode test (record failed)"
 		return
 	fi
diff --git a/tools/perf/tests/shell/test_gecko_python.sh b/tools/perf/tests/shell/test_gecko_python.sh
index de1d7fcf88b7..18e9f5cd2ab0 100755
--- a/tools/perf/tests/shell/test_gecko_python.sh
+++ b/tools/perf/tests/shell/test_gecko_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing gecko.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_mem_phys_addr_python.sh b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
index 451692d5e089..cbb9f572be9d 100755
--- a/tools/perf/tests/shell/test_mem_phys_addr_python.sh
+++ b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
@@ -78,10 +78,12 @@ test_file_mode() {
 	echo "Testing mem-phys-addr.py file mode..."
 
 	# Generate memory access events (try unprivileged user-space first, then system-wide)
-	if ! perf record --phys-data -d -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event --phys-data -d -o "${temp_data}" \
 	     -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -o "${temp_data}" -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -a -o "${temp_data}" -- sleep 0.2 >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -d -o "${temp_data}" \
+	     -- perf test -w datasym >/dev/null 2>&1 && \
+	   ! perf record -B -N --no-bpf-event -d -a -o "${temp_data}" \
+	     -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping file mode record test, perf record -d not supported"
 		return 0
 	fi
diff --git a/tools/perf/tests/shell/test_net_dropmonitor_python.sh b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
index 05056a897bc9..2e37994418fc 100755
--- a/tools/perf/tests/shell/test_net_dropmonitor_python.sh
+++ b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
@@ -42,11 +42,12 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing net_dropmonitor.py..."
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -o "${temp_data}" -a \
-	-- ping -c 1 255.255.255.255 >/dev/null 2>&1; then
-	if ! perf record -e skb:kfree_skb -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" -a \
+	-- ping -c 1 -W 1 255.255.255.255 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1; then
-		if ! perf record -o "${temp_data}" -- uname >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+			-- uname >/dev/null 2>&1; then
 			echo "Skipping test, cannot record perf events"
 			exit 2
 		fi
diff --git a/tools/perf/tests/shell/test_netdev_times_python.sh b/tools/perf/tests/shell/test_netdev_times_python.sh
index 393bf446efb2..0d8d10a42cab 100755
--- a/tools/perf/tests/shell/test_netdev_times_python.sh
+++ b/tools/perf/tests/shell/test_netdev_times_python.sh
@@ -85,9 +85,9 @@ then
 fi
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -a -o "${temp_data}" \
-	-- ping -c 1 127.0.0.1 >/dev/null 2>&1; then
-	perf record -e cycles -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -a -o "${temp_data}" \
+	-- ping -c 1 -W 1 127.0.0.1 >/dev/null 2>&1; then
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
index 19569c6d3613..b140ccf00ffa 100755
--- a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
+++ b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
@@ -67,8 +67,8 @@ if ! grep -q "H_REMOVE.*1.*1500.*1500.*1500" "${temp_out}"; then
 fi
 
 # Create a perf.data file if powerpc hcall tracepoints are available on this host.
-if ! perf record -e powerpc:hcall_entry,powerpc:hcall_exit -a -o "${temp_data}" \
-	-- perf test -w noploop >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e powerpc:hcall_entry,powerpc:hcall_exit \
+	-a -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
 	echo "Skipping live record test, powerpc hcall tracepoints not available"
 	exit 0
 fi
diff --git a/tools/perf/tests/shell/test_rw_by_file_python.sh b/tools/perf/tests/shell/test_rw_by_file_python.sh
index f121597f418f..e3c538c3ace3 100755
--- a/tools/perf/tests/shell/test_rw_by_file_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_file_python.sh
@@ -37,8 +37,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-file.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
-	perf record -e syscalls:sys_enter_read,syscalls:sys_enter_write -a -o "${temp_data}" \
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
+	perf record -B -N --no-bpf-event -e syscalls:sys_enter_read,syscalls:sys_enter_write \
+		-o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rw_by_pid_python.sh b/tools/perf/tests/shell/test_rw_by_pid_python.sh
index 41eaa29097a2..cd93c1d9714c 100755
--- a/tools/perf/tests/shell/test_rw_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_pid_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-pid.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rwtop_python.sh b/tools/perf/tests/shell/test_rwtop_python.sh
index 05897e384702..d33807923c92 100755
--- a/tools/perf/tests/shell/test_rwtop_python.sh
+++ b/tools/perf/tests/shell/test_rwtop_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rwtop.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_sched_migration_python.sh b/tools/perf/tests/shell/test_sched_migration_python.sh
index 75465bcd3791..714275b0e492 100755
--- a/tools/perf/tests/shell/test_sched_migration_python.sh
+++ b/tools/perf/tests/shell/test_sched_migration_python.sh
@@ -44,10 +44,10 @@ echo "Testing sched-migration.py..."
 ev="sched:sched_switch,sched:sched_migrate_task"
 ev="${ev},sched:sched_wakeup_new,sched:sched_wakeup"
 has_sched=1
-if ! perf record -e "$ev" -a -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 	-- sleep 0.1 >/dev/null 2>&1; then
 	has_sched=0
-	perf record -e cycles -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_stackcollapse_python.sh b/tools/perf/tests/shell/test_stackcollapse_python.sh
index ce0f80407eec..2048734c5e0d 100755
--- a/tools/perf/tests/shell/test_stackcollapse_python.sh
+++ b/tools/perf/tests/shell/test_stackcollapse_python.sh
@@ -37,7 +37,7 @@ echo "Testing stackcollapse.py..."
 
 # Create a perf.data file with callchains. Use a busy workload rather than
 # sleep, as an idle system may not generate any samples at all.
-perf record -g -o "${temp_data}" \
+perf record -B -N --no-bpf-event -g -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
index 45bbdc554c8f..300289fe33b4 100755
--- a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
@@ -43,14 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts-by-pid.py..."
 	# Some systems might not have raw_syscalls:sys_enter
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.5 >/dev/null 2>&1 || \
+	perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
 	if ! perf script syscall-counts-by-pid -i "${temp_data}" > "${temp_out}"; then
diff --git a/tools/perf/tests/shell/test_syscall_counts_python.sh b/tools/perf/tests/shell/test_syscall_counts_python.sh
index 310e05d399f9..86463f14391b 100755
--- a/tools/perf/tests/shell/test_syscall_counts_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_python.sh
@@ -43,13 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts.py..."
 	# Some systems might not have raw_syscalls:sys_enter (e.g. stripped kernels or permissions)
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	if ! perf record -e raw_syscalls:sys_enter -o "${temp_data}" -- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" 2>/dev/null; then
 		echo "perf record failed (permissions?), skipping file mode test."
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh
index f99a637a6099..f53fa4a27c79 100755
--- a/tools/perf/tests/shell/test_task_analyzer.sh
+++ b/tools/perf/tests/shell/test_task_analyzer.sh
@@ -60,7 +60,8 @@ skip_no_probe_record_support() {
 
 prepare_perf_data() {
 	# 1s should be sufficient to catch at least some switches
-	perf record -e sched:sched_switch -a -o "${perfdata}" -- sleep 1 > /dev/null 2>&1
+	perf record -B -N --no-bpf-event -e sched:sched_switch -a -o "${perfdata}" \
+		-- sleep 1 > /dev/null 2>&1
 	# check if perf data file got created in above step.
 	if [ ! -e "${perfdata}" ]; then
 		printf "FAIL: perf record failed to create \"${perfdata}\" \n"
diff --git a/tools/perf/tests/shell/test_wakeup_latency_python.sh b/tools/perf/tests/shell/test_wakeup_latency_python.sh
index cb2571449168..b43a86996be2 100755
--- a/tools/perf/tests/shell/test_wakeup_latency_python.sh
+++ b/tools/perf/tests/shell/test_wakeup_latency_python.sh
@@ -41,9 +41,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing wakeup-latency.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "sched:sched_wakeup"; then
+if perf list tracepoint | grep -q "sched:sched_wakeup"; then
 	ev="sched:sched_wakeup,sched:sched_wakeup_new,sched:sched_switch"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
@@ -70,7 +70,8 @@ else
 fi
 
 # Also test zero-wakeups / unhandled events path to verify division-by-zero protection
-if perf record -e cycles -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+if perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
+	-- perf test -w noploop >/dev/null 2>&1; then
 	if ! perf script wakeup-latency -i "${temp_data}" > "${temp_out}" || \
 	   ! grep -q "avg_wakeup_latency (ns): N/A" "${temp_out}"; then
 		echo "wakeup-latency zero-wakeups guard test failed"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 7/9] perf python event_analyzing_sample: Default to in-memory SQLite database

[Ian Rogers]

When -d/--db is not specified, event_analyzing_sample.py created a
temporary file in /tmp via tempfile.mkstemp() and deleted it in
trace_end(). As noted during review, creating the database in a shared
/tmp directory does not reserve SQLite's auxiliary sidecar filenames
(-journal or -wal), and a temporary on-disk file is unnecessary when the
caller did not ask to persist the database.

Default to sqlite3.connect(":memory:") when db_path is not provided,
removing the temporary file creation and cleanup logic, and test both
the default in-memory mode and explicit -d file mode in
test_event_analyzing_sample_python.sh.

Fixes: eeb70645a809 ("perf python: Port event_analyzing_sample to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/event_analyzing_sample.py   | 35 ++++++-------------
 .../test_event_analyzing_sample_python.sh     |  8 ++++-
 2 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/tools/perf/python/event_analyzing_sample.py b/tools/perf/python/event_analyzing_sample.py
index 15b47cff9fa3..b4efee88d94b 100755
--- a/tools/perf/python/event_analyzing_sample.py
+++ b/tools/perf/python/event_analyzing_sample.py
@@ -17,10 +17,8 @@ from __future__ import annotations
 
 import argparse
 import math
-import os
 import sqlite3
 import struct
-import tempfile
 from typing import Any
 import perf
 
@@ -117,16 +115,11 @@ session: Any = None
 
 class _DB:
     con: sqlite3.Connection | None = None
-    temp_path: str | None = None
 
 def trace_begin(db_path: str | None = None) -> None:
     """Initialize database tables."""
     print("In trace_begin:\n")
-    if not db_path:
-        fd, db_path = tempfile.mkstemp(prefix="perf_events_", suffix=".db")
-        os.close(fd)
-        _DB.temp_path = db_path
-    con = sqlite3.connect(db_path)
+    con = sqlite3.connect(db_path or ":memory:")
     try:
         # Drop any pre-existing tables so repeated runs do not accumulate duplicate events.
         con.execute("drop table if exists gen_events;")
@@ -297,28 +290,20 @@ def show_pebs_ll() -> None:
 def trace_end() -> None:
     """Called at the end of trace processing."""
     print("In trace_end:\n")
-    try:
-        if _DB.con:
-            try:
-                _DB.con.commit()
-                show_general_events()
-                show_pebs_ll()
-            finally:
-                _DB.con.close()
-                _DB.con = None
-    finally:
-        if _DB.temp_path and os.path.exists(_DB.temp_path):
-            try:
-                os.remove(_DB.temp_path)
-            except OSError:
-                pass
-            _DB.temp_path = None
+    if _DB.con:
+        try:
+            _DB.con.commit()
+            show_general_events()
+            show_pebs_ll()
+        finally:
+            _DB.con.close()
+            _DB.con = None
 
 if __name__ == "__main__":
     ap = argparse.ArgumentParser(description="Analyze events with SQLite")
     ap.add_argument("-i", "--input", default="perf.data", help="Input file name")
     ap.add_argument("-d", "--db", "--database", dest="database", default=None,
-                    help="Database file name (defaults to a temporary file cleaned up on exit)")
+                    help="Database file name (defaults to an in-memory database)")
     args = ap.parse_args()
 
     try:
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index 5f0a41080acf..cddb12b67698 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -45,8 +45,14 @@ test_file_mode() {
 		exit 2
 	fi
 
-	# Run the script
+	# Run the script with default (:memory:) database and with explicit -d path
 	if ! perf script event_analyzing_sample -i "${temp_data}" \
+		> "${temp_dir}/perf.mem.out" 2>&1 || \
+	   ! grep -q "Statistics about the general events" "${temp_dir}/perf.mem.out" || \
+	   grep -q "Error creating/inserting event" "${temp_dir}/perf.mem.out"; then
+		echo "Default in-memory database mode test failed."
+		err=1
+	elif ! perf script event_analyzing_sample -i "${temp_data}" \
 		-d "${temp_db}" > "${temp_dir}/perf.out" 2>&1; then
 		echo "File mode test failed."
 		err=1
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 8/9] perf python: Initialize debug output on module load

[Ian Rogers]

Unlike the perf binary's main(), PyInit_perf() does not call
perf_debug_setup(). As a result, the first warning or error printed from
the perf Python C extension hits debug_file() with _debug_file == NULL
and emits 'debug_file not set' without a trailing newline before the
actual diagnostic message.

Call perf_debug_setup() in PyInit_perf() and add the missing trailing
newline to the fallback warning in debug_file().

Fixes: ec49230cf6dd ("perf debug: Expose debug file")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/debug.c  | 2 +-
 tools/perf/util/python.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 6b5ffe81f141..b7095519419e 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -55,7 +55,7 @@ FILE *debug_file(void)
 {
 	if (!_debug_file) {
 		debug_set_file(stderr);
-		pr_warning_once("debug_file not set");
+		pr_warning_once("%s not set\n", __func__);
 	}
 	return _debug_file;
 }
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 690a94fb4f62..95140dfaef9c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -5157,6 +5157,7 @@ PyMODINIT_FUNC PyInit_perf(void)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	perf_debug_setup();
 
 	Py_INCREF(&pyrf_evlist__type);
 	PyModule_AddObject(module, "evlist", (PyObject *)&pyrf_evlist__type);
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v2 9/9] perf pmu: Fix race with concurrent tracepoint creation and removal in perf list

[Ian Rogers]

perf_pmus__print_pmu_events() first counts events via
perf_pmu__num_events() to allocate the aliases array, then populates it
via perf_pmu__for_each_event(). When dynamic tracepoints (such as
kprobes or uprobes during 'perf test' runs) are concurrently created or
removed between the two passes:
- If an event is removed, state.index is smaller than the allocated len,
  leaving trailing zeroed entries in aliases[] with name == NULL and
  pmu == NULL, which causes qsort(cmp_sevent) or the print loop to crash
  with SIGSEGV.
- If a dynamic tracepoint subsystem directory is removed while scanning
  /sys/kernel/tracing/events, tp_pmu__for_each_tp_event() returns
  -ENOENT and aborts enumeration of all remaining tracepoint subsystems.
- If an event is added, perf_pmus__print_pmu_events__callback() aborts
  enumeration when state->index reaches state->aliases_len.

Grow state->aliases dynamically via realloc() when needed, use
state.index as the actual populated length for sorting and printing, and
ignore -ENOENT when a tracepoint subsystem directory disappears during
enumeration.

Fixes: c3245d2093c1 ("perf pmu: Abstract alias/event struct")
Fixes: 45b6e281cb06 ("perf tp_pmu: Add event APIs")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/pmus.c   | 21 +++++++++++++++++----
 tools/perf/util/tp_pmu.c |  8 ++++++--
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index e0a4cb2428ca..1355b317f3ed 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -8,6 +8,7 @@
 #include <sys/types.h>
 #include <ctype.h>
 #include <pthread.h>
+#include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include "cpumap.h"
@@ -571,7 +572,7 @@ static int cmp_sevent(const void *a, const void *b)
 	}
 
 	/* Order by event name. */
-	return strcmp(as->name, bs->name);
+	return strcmp(as->name ?: "", bs->name ?: "");
 }
 
 static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
@@ -581,7 +582,7 @@ static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
 		return false;
 
 	/* Don't remove duplicates for different PMUs */
-	return strcmp(a->pmu_name, b->pmu_name) == 0;
+	return strcmp(a->pmu_name ?: "", b->pmu_name ?: "") == 0;
 }
 
 struct events_callback_state {
@@ -597,8 +598,18 @@ static int perf_pmus__print_pmu_events__callback(void *vstate,
 	struct sevent *s;
 
 	if (state->index >= state->aliases_len) {
-		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
-		return 1;
+		size_t new_len = max_t(size_t, 16, state->aliases_len * 2);
+		struct sevent *new_aliases;
+
+		new_aliases = realloc(state->aliases, new_len * sizeof(struct sevent));
+		if (!new_aliases) {
+			pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
+			return 1;
+		}
+		memset(&new_aliases[state->aliases_len], 0,
+		       (new_len - state->aliases_len) * sizeof(struct sevent));
+		state->aliases = new_aliases;
+		state->aliases_len = new_len;
 	}
 	assert(info->pmu != NULL || info->name != NULL);
 	s = &state->aliases[state->index];
@@ -654,6 +665,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 		perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state,
 					 perf_pmus__print_pmu_events__callback);
 	}
+	aliases = state.aliases;
+	len = state.index;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
diff --git a/tools/perf/util/tp_pmu.c b/tools/perf/util/tp_pmu.c
index c2be8c9f9084..5ac732e06841 100644
--- a/tools/perf/util/tp_pmu.c
+++ b/tools/perf/util/tp_pmu.c
@@ -151,7 +151,9 @@ static int for_each_event_cb(void *state, const char *sys_name, const char *evt_
 
 static int for_each_event_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 int tp_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
@@ -176,7 +178,9 @@ static int num_events_cb(void *state, const char *sys_name __maybe_unused,
 
 static int num_events_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 size_t tp_pmu__num_events(struct perf_pmu *pmu __maybe_unused)
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 0/9] perf python: Follow-up fixes and shell test deflaking

[Ian Rogers]

This series contains follow-up fixes for the standalone Python scripts
and their shell tests, particularly when running 'perf test' as root
under heavy parallel load:

- Clamp sample_id size calculation for PERF_RECORD_KSYMBOL,
  PERF_RECORD_BPF_EVENT, and PERF_RECORD_TEXT_POKE records to work
  around kernels without "perf/core: Restore header fields in sideband
  output callbacks" [1].
- Fix offline interval printing in sctop.py and live signal races in
  stat-cpi.py.
- Deflake Intel PT, failed-syscalls, and other Python shell tests under
  parallel 'perf test' load by scoping tracepoint checks to
  'perf list tracepoint', passing '-B -N --no-bpf-event' to 'perf record',
  and avoiding unnecessary system-wide ('-a') recordings.
- Default event_analyzing_sample.py to an in-memory SQLite database
  (':memory:') when '--db' is not specified.
- Initialize perf debug output ('perf_debug_setup()') when loading the
  'perf' Python extension module.
- Fix races in 'perf list' ('perf_pmus__print_pmu_events()' and
  'tp_pmu.c') when concurrent tests dynamically create and remove
  kprobe/uprobes tracepoints.

v3:
- Wrap _open_live_evlist() inside the try/except KeyboardInterrupt block
  in stat-cpi.py so signals arriving during event initialization are
  caught and cleaned up gracefully.

v2:
- Fix 8-byte alignment calculation for PERF_RECORD_TEXT_POKE payload in
  evsel__event_size() by aligning fixed + old_len + new_len.
- Keep offline interval clock advancing on all samples in sctop.py while
  flushing any remaining syscalls at EOF.
- Use 'mktemp -d' private directories in test_sctop_python.sh and
  test_failed_syscalls_python.sh so temporary files are not unlinked and
  recreated directly in /tmp.
- Explicitly include <stdlib.h> in tools/perf/util/pmus.c.

[1] https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com

Ian Rogers (9):
  perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke
    events
  perf python sctop: Fix offline interval printing and test flakiness
  perf python stat-cpi: Fix live mode signal races and test flakiness
  perf test: Deflake Intel PT Python shell tests under load
  perf test: Deflake failed-syscalls Python shell tests under load
  perf test: Reduce overhead and contention in Python shell tests
  perf python event_analyzing_sample: Default to in-memory SQLite
    database
  perf python: Initialize debug output on module load
  perf pmu: Fix race with concurrent tracepoint creation and removal in
    perf list

 tools/perf/python/event_analyzing_sample.py   | 35 +++-------
 tools/perf/python/sctop.py                    |  7 +-
 tools/perf/python/stat-cpi.py                 | 32 ++++++---
 .../shell/test_check_perf_trace_python.sh     |  8 ++-
 .../shell/test_compaction_times_python.sh     |  8 ++-
 .../test_event_analyzing_sample_python.sh     | 11 ++-
 .../shell/test_export_to_postgresql_python.sh | 49 +++++++------
 .../shell/test_export_to_sqlite_python.sh     | 50 ++++++++------
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 54 +++++++++------
 .../tests/shell/test_flamegraph_python.sh     |  5 +-
 .../shell/test_futex_contention_python.sh     |  7 +-
 tools/perf/tests/shell/test_gecko_python.sh   |  3 +-
 .../shell/test_intel_pt_events_python.sh      | 43 ++++++------
 .../tests/shell/test_mem_phys_addr_python.sh  |  8 ++-
 .../shell/test_net_dropmonitor_python.sh      |  9 +--
 .../tests/shell/test_netdev_times_python.sh   |  6 +-
 .../tests/shell/test_powerpc_hcalls_python.sh |  4 +-
 .../tests/shell/test_rw_by_file_python.sh     |  5 +-
 .../perf/tests/shell/test_rw_by_pid_python.sh |  4 +-
 tools/perf/tests/shell/test_rwtop_python.sh   |  4 +-
 .../shell/test_sched_migration_python.sh      |  4 +-
 tools/perf/tests/shell/test_sctop_python.sh   | 58 ++++++++--------
 .../tests/shell/test_stackcollapse_python.sh  |  2 +-
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++-
 .../test_syscall_counts_by_pid_python.sh      |  6 +-
 .../tests/shell/test_syscall_counts_python.sh |  5 +-
 tools/perf/tests/shell/test_task_analyzer.sh  |  3 +-
 .../tests/shell/test_wakeup_latency_python.sh |  7 +-
 tools/perf/util/debug.c                       |  2 +-
 tools/perf/util/evlist.c                      |  6 +-
 tools/perf/util/evsel.c                       | 59 +++++++++++++++-
 tools/perf/util/evsel.h                       |  1 +
 tools/perf/util/pmus.c                        | 21 ++++--
 tools/perf/util/python.c                      |  1 +
 tools/perf/util/tp_pmu.c                      |  8 ++-
 36 files changed, 378 insertions(+), 237 deletions(-)

-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 1/9] perf evsel: Clamp sample_id size for ksymbol, bpf, and text_poke events

[Ian Rogers]

On kernels without the fix ("perf/core: Restore header fields in
sideband output callbacks") to restore event_id.header.size in
perf_event_ksymbol_output(), perf_event_bpf_output(), and
perf_event_text_poke_output(), concurrent perf sessions cause those
sideband records to be emitted with header.size inflated by multiple
id_header_size increments while the single id_sample is written
immediately after the event payload. Indexing backwards from
event->header.size reads uninitialized ring-buffer bytes at the end of
the record, causing evlist__event2evsel() to fail with -EFAULT.

Add evsel__event_size() to clamp the effective size used to locate the
trailing id_sample for PERF_RECORD_KSYMBOL, PERF_RECORD_BPF_EVENT, and
PERF_RECORD_TEXT_POKE to payload + id_hdr_size while leaving
event->header.size intact for advancing the ring-buffer/file stream.

Fixes: 9aa0bfa370b2 ("perf tools: Handle PERF_RECORD_KSYMBOL")
Fixes: 45178a928a4b ("perf tools: Handle PERF_RECORD_BPF_EVENT")
Fixes: 246eba8e9041 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Link: https://lore.kernel.org/r/20260929014206.4175245-1-irogers@google.com
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/evlist.c |  6 ++--
 tools/perf/util/evsel.c  | 59 +++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 9392d912d254..c2402e4791b6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -973,13 +973,15 @@ static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64
 	const __u64 *array = event->sample.array;
 	ssize_t n;
 
-	n = (event->header.size - sizeof(event->header)) >> 3;
-
 	if (event->header.type == PERF_RECORD_SAMPLE) {
+		n = (event->header.size - sizeof(event->header)) >> 3;
 		if (evlist__id_pos(evlist) >= n)
 			return -1;
 		*id = array[evlist__id_pos(evlist)];
 	} else {
+		u16 size = evsel__event_size(evlist__first(evlist), event);
+
+		n = (size - sizeof(event->header)) >> 3;
 		if (evlist__is_pos(evlist) > n)
 			return -1;
 		n -= evlist__is_pos(evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3367242c5764..9c5e7510f0c0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3216,7 +3216,7 @@ static int perf_evsel__parse_id_sample(const union perf_event *event,
 	const __u64 *array = event->sample.array;
 	bool swapped = evsel->needs_swap;
 	union u64_swap u;
-	int i = ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1;
+	int i = ((evsel__event_size(evsel, event) - sizeof(event->header)) / sizeof(u64)) - 1;
 
 	if (type & PERF_SAMPLE_IDENTIFIER) {
 		if (i < 0)
@@ -3966,6 +3966,63 @@ u16 evsel__id_hdr_size(const struct evsel *evsel)
 	return size;
 }
 
+/*
+ * Prior to kernel fix, perf_event_ksymbol_output(), perf_event_bpf_output(),
+ * and perf_event_text_poke_output() in kernel/events/core.c did not save and
+ * restore event_id.header.size across perf_iterate_sb() iterations. When
+ * multiple perf_events had attr.ksymbol, attr.bpf_event, or attr.text_poke
+ * enabled, header.size was incremented by id_header_size for each matching
+ * event while only a single id_sample was written immediately after the event
+ * payload. Clamp the effective size used to locate the trailing id_sample to
+ * payload + id_hdr_size so events recorded on unpatched kernels can be parsed
+ * without reading uninitialized ring-buffer bytes.
+ */
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event)
+{
+	u16 size = event->header.size;
+	u16 id_hdr_size;
+	size_t payload;
+
+	if (!evsel->core.attr.sample_id_all)
+		return size;
+
+	switch (event->header.type) {
+	case PERF_RECORD_KSYMBOL: {
+		const char *name = event->ksymbol.name;
+		size_t fixed = offsetof(struct perf_record_ksymbol, name);
+		size_t max_len, len;
+
+		if (size <= fixed)
+			return size;
+		max_len = size - fixed;
+		len = strnlen(name, max_len);
+		if (len == max_len)
+			return size;
+		payload = fixed + PERF_ALIGN(len + 1, sizeof(u64));
+		break;
+	}
+	case PERF_RECORD_BPF_EVENT:
+		payload = sizeof(struct perf_record_bpf_event);
+		break;
+	case PERF_RECORD_TEXT_POKE: {
+		size_t fixed = offsetof(struct perf_record_text_poke_event, bytes);
+
+		if (size < fixed)
+			return size;
+		payload = PERF_ALIGN(fixed + (size_t)event->text_poke.old_len +
+				     event->text_poke.new_len, sizeof(u64));
+		break;
+	}
+	default:
+		return size;
+	}
+
+	id_hdr_size = evsel__id_hdr_size(evsel);
+	if (payload + id_hdr_size < size)
+		return payload + id_hdr_size;
+	return size;
+}
+
 #ifdef HAVE_LIBTRACEEVENT
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5c5799cee601..174f3414fd3c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -469,6 +469,7 @@ int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
 				  u64 *timestamp);
 
 u16 evsel__id_hdr_size(const struct evsel *evsel);
+u16 evsel__event_size(const struct evsel *evsel, const union perf_event *event);
 
 static inline struct evsel *evsel__next(struct evsel *evsel)
 {
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 2/9] perf python sctop: Fix offline interval printing and test flakiness

[Ian Rogers]

In sctop.py:
- If an earlier interval elapsed and printed an empty table before the
  target comm ('sleep') executed any syscalls, analyzer.printed became
  True and the final partial interval containing the target comm's
  syscalls was never flushed at EOF. Flush print_current_totals() in
  finally when analyzer.syscalls is non-empty as well as when nothing
  has been printed yet.
- Initialize analyzer.e_machine after creating perf.session rather than
  when session is still None.

In test_sctop_python.sh:
- Use a private temporary directory via 'mktemp -d'.
- Drop '-a' and pass '-B -N --no-bpf-event' to 'perf record', and sleep
  briefly in the subshell ('sh -c "sleep 0.1; sleep 0.05"') with a
  bounded retry loop so 'sleep's PERF_RECORD_COMM and sys_enter events
  are reliably captured under heavy load.

Fixes: b83f0bacf5e4 ("perf python: Port sctop to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/sctop.py                  |  7 ++-
 tools/perf/tests/shell/test_sctop_python.sh | 58 ++++++++++-----------
 2 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/tools/perf/python/sctop.py b/tools/perf/python/sctop.py
index 42e95ecfffad..48320af8b755 100755
--- a/tools/perf/python/sctop.py
+++ b/tools/perf/python/sctop.py
@@ -37,6 +37,7 @@ class SCTopAnalyzer:
         self.offline = offline
         self.own_pid = os.getpid()
         self.last_print_time: Optional[int] = None
+        self.printed = False
         self.session: Optional[perf.session] = None
         self.e_machine: Optional[int] = None
 
@@ -137,6 +138,7 @@ class SCTopAnalyzer:
 
     def print_current_totals(self):
         """Print current syscall totals."""
+        self.printed = True
         # Clear terminal
         if not self.offline:
             print("\x1b[2J\x1b[H", end="")
@@ -217,8 +219,8 @@ def main():
         if args.input:
             session = perf.session(perf.data(args.input), sample=analyzer.process_event)
             analyzer.session = session
-            session.process_events()
             analyzer.e_machine = getattr(session, "e_machine", None)
+            session.process_events()
         else:
             try:
                 live_session = LiveSession(
@@ -237,7 +239,8 @@ def main():
         sys.exit(1)
     finally:
         if args.input:
-            analyzer.print_current_totals()
+            if not analyzer.printed or analyzer.syscalls:
+                analyzer.print_current_totals()
             # Break the reference cycle between perf.session and analyzer.process_event
             # because perf.session lacks cyclic GC support (tp_traverse).
             analyzer.session = None
diff --git a/tools/perf/tests/shell/test_sctop_python.sh b/tools/perf/tests/shell/test_sctop_python.sh
index 007f2584cce6..b042fc3eefe5 100755
--- a/tools/perf/tests/shell/test_sctop_python.sh
+++ b/tools/perf/tests/shell/test_sctop_python.sh
@@ -27,51 +27,51 @@ if [ ! -f "$script_path" ]; then
 fi
 
 err=0
-temp_data=""
-temp_out=""
+temp_dir=$(mktemp -d /tmp/perf-sctop-XXXXXX)
+temp_data="${temp_dir}/perf.data"
+temp_out="${temp_dir}/perf.out"
 
 cleanup() {
-	rm -f "${temp_data}" "${temp_out}"
+	rm -rf "${temp_dir}"
 }
 trap 'cleanup' EXIT TERM INT
 
-temp_data=$(mktemp /tmp/perf.data.XXXXXX)
-temp_out=$(mktemp /tmp/perf.out.XXXXXX)
-
 echo "Testing sctop.py..."
 
 # Create a perf.data file.
-if perf list | grep -q "raw_syscalls:sys_enter"; then
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.1 >/dev/null 2>&1 || \
-		{ echo "Skipping test, perf record failed"; exit 2; }
-else
+if ! perf list tracepoint | grep -q "raw_syscalls:sys_enter"; then
 	echo "Skipping test, no raw_syscalls:sys_enter event"
 	exit 2
 fi
 
-if [ ! -s "${temp_data}" ]; then
-	echo "Skipping test, perf record failed to create data"
-	exit 2
-fi
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1; then
+		echo "Skipping test, perf record failed"
+		exit 2
+	fi
 
-# Check that the script executes
-if ! perf script sctop -i "${temp_data}" > "${temp_out}"; then
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script sctop -i "${temp_data}" > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}" && \
+	   perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
+
+if [ "$passed" -eq 0 ]; then
 	echo "sctop.py test failed"
 	err=1
-elif ! grep -E -q "[0-9]+$" "${temp_out}"; then
-	echo "Failed to find metric data rows in default run"
-	err=1
-elif ! perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}"; then
-	echo "sctop.py comm+interval test failed"
-	err=1
 else
-	if ! grep -E -q "[0-9]+$" "${temp_out}"; then
-		echo "Failed to find metric data rows"
-		err=1
-	else
-		echo "sctop test passed."
-	fi
+	echo "sctop test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 3/9] perf python stat-cpi: Fix live mode signal races and test flakiness

[Ian Rogers]

In test_stat_cpi_python.sh, 'perf test -w noploop &' defaults to a
1-second duration and can exit under heavy parallel load before
'perf stat -p' and 'perf script stat-cpi' finish starting up. In
addition, the fixed 'sleep 0.5' before sending SIGINT can fire before
Python finishes importing the perf module, opening the live evlist, and
flushing the first interval.

In stat-cpi.py, register SIGINT and SIGTERM handlers before calling
_open_live_evlist() and pass flush=True when printing live output so
redirected stdout is flushed immediately after each interval.

In test_stat_cpi_python.sh, run 'perf test -w noploop 60 &' so the
target workload stays alive until killed, and poll the output file for
'cpi' (up to 5 seconds) before sending SIGINT.

Fixes: 4425182d426b ("perf python: Port stat-cpi to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/stat-cpi.py                 | 32 +++++++++++++------
 .../perf/tests/shell/test_stat_cpi_python.sh  | 12 +++++--
 2 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/tools/perf/python/stat-cpi.py b/tools/perf/python/stat-cpi.py
index 0b7d76876a6c..b4ec87b07938 100755
--- a/tools/perf/python/stat-cpi.py
+++ b/tools/perf/python/stat-cpi.py
@@ -106,7 +106,8 @@ class StatCpiAnalyzer:
             if ins != 0:
                 cpi = cyc / float(ins)
             t_sec = timestamp / 1000000000.0
-            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})")
+            print(f"{t_sec:15f}: cpu {cpu}, thread {thread} -> cpi {cpi:f} ({cyc:.0f}/{ins:.0f})",
+                  flush=True)
 
     def read_counters(self, evlist: Any) -> None:
         """Read counters live."""
@@ -151,6 +152,7 @@ class StatCpiAnalyzer:
 
         last_err: Optional[OSError] = None
         for events, tmap in candidates:
+            evlist = None
             try:
                 evlist = perf.parse_events(events, None, tmap)
                 for evsel in evlist:
@@ -161,32 +163,41 @@ class StatCpiAnalyzer:
                 evlist.enable()
                 return evlist
             except PermissionError as e:
+                if evlist is not None:
+                    evlist.close()
                 last_err = e
             except OSError as e:
+                if evlist is not None:
+                    evlist.close()
                 if e.errno == 13:
                     last_err = e
                 else:
                     raise
+            except BaseException:
+                if evlist is not None:
+                    evlist.close()
+                raise
         if last_err is not None:
             raise last_err
         raise RuntimeError("Failed to open events")
 
     def run_live(self) -> None:
         """Read counters live."""
-        try:
-            evlist = self._open_live_evlist()
-        except OSError as e:
-            print(f"Failed to open events: {e}", file=sys.stderr)
-            sys.exit(1)
-
         def handle_signal(_signum: int, _frame: Any) -> None:
             raise KeyboardInterrupt
 
         signal.signal(signal.SIGINT, signal.default_int_handler)
         signal.signal(signal.SIGTERM, handle_signal)
 
-        print("Live mode started. Press Ctrl+C to stop.")
+        evlist = None
         try:
+            try:
+                evlist = self._open_live_evlist()
+            except OSError as e:
+                print(f"Failed to open events: {e}", file=sys.stderr)
+                sys.exit(1)
+
+            print("Live mode started. Press Ctrl+C to stop.", flush=True)
             while True:
                 time.sleep(self.args.interval)
                 timestamp = time.time_ns()
@@ -195,9 +206,10 @@ class StatCpiAnalyzer:
                 self.data.clear()
                 self.recorded_pairs.clear()
         except KeyboardInterrupt:
-            print("\nStopped.")
+            print("\nStopped.", flush=True)
         finally:
-            evlist.close()
+            if evlist is not None:
+                evlist.close()
 
 def main() -> None:
     """Main function."""
diff --git a/tools/perf/tests/shell/test_stat_cpi_python.sh b/tools/perf/tests/shell/test_stat_cpi_python.sh
index fe7562307634..6cb376c92e2f 100755
--- a/tools/perf/tests/shell/test_stat_cpi_python.sh
+++ b/tools/perf/tests/shell/test_stat_cpi_python.sh
@@ -50,7 +50,7 @@ test_live_mode() {
 		echo "perf stat failed (permissions?), skipping live mode test."
 		return 0
 	fi
-	perf test -w noploop &
+	perf test -w noploop 60 &
 	workload_pid=$!
 	if ! perf stat -e cycles,instructions -p "$workload_pid" -- sleep 0.05 2>/dev/null && \
 	   ! perf stat -e cycles:u,instructions:u -p "$workload_pid" -- sleep 0.05 2>/dev/null; then
@@ -61,10 +61,16 @@ test_live_mode() {
 	fi
 	ran=1
 
-	# Run live mode for 1 interval in the background, give it a tiny sleep, then interrupt
+	# Run live mode in the background, wait until at least one interval is
+	# printed, then interrupt.
 	perf script stat-cpi -I 0.1 -p "$workload_pid" > "${temp_out}" &
 	pid=$!
-	sleep 0.5
+	for _ in $(seq 1 50); do
+		if grep -q "cpi" "${temp_out}"; then
+			break
+		fi
+		sleep 0.1
+	done
 	kill -INT "$pid" 2>/dev/null || true
 	set +e
 	wait "$pid"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 4/9] perf test: Deflake Intel PT Python shell tests under load

[Ian Rogers]

In test_intel_pt_events_python.sh, test_export_to_sqlite_python.sh, and
test_export_to_postgresql_python.sh, 'sh -c "uname; true"' uses the
shell builtin 'true' and exits within microseconds of 'uname', sending
SIGCHLD to 'perf record' before the Intel PT AUX buffer is always
flushed under heavy parallel load (~5-10% drop rate).

Sleep 0.05s in the subshell after 'uname' ('sh -c "uname; sleep 0.05"')
so 'uname' completely exits and flushes its AUX trace before 'sh' exits,
and wrap the record and verification step in a bounded retry loop (up to
5 attempts). Also pass '-B -N --no-bpf-event' to 'perf record -g' in
test_export_to_sqlite_python.sh and test_export_to_postgresql_python.sh
to avoid build-id cache and BPF synthesis overhead.

Fixes: d4ce72e9e238 ("perf python: Port intel-pt-events and libxed to perf module")
Fixes: 62d350135e67 ("perf python: Port export-to-sqlite to perf module")
Fixes: b1f968c9656a ("perf python: Port export-to-postgresql to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../shell/test_export_to_postgresql_python.sh | 49 ++++++++++--------
 .../shell/test_export_to_sqlite_python.sh     | 50 +++++++++++--------
 .../shell/test_intel_pt_events_python.sh      | 43 +++++++++-------
 3 files changed, 79 insertions(+), 63 deletions(-)

diff --git a/tools/perf/tests/shell/test_export_to_postgresql_python.sh b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
index 350813466700..835f48f002e9 100755
--- a/tools/perf/tests/shell/test_export_to_postgresql_python.sh
+++ b/tools/perf/tests/shell/test_export_to_postgresql_python.sh
@@ -61,9 +61,10 @@ test_file_mode() {
 	fi
 
 	# Generate events with callchains and context switches
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -92,29 +93,33 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-postgresql.py with intel_pt..."
 
-	psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
-	rm -f "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		psql -c "DROP DATABASE IF EXISTS ${temp_db}" postgres >/dev/null 2>&1 || true
+		rm -f "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-postgresql -i "${temp_data}" \
-		-o "${temp_db}" --itrace cr >/dev/null; then
-		echo "intel_pt file mode test failed."
-		err=1
-	else
-		# Check DB for calls
-		if ! psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-postgresql -i "${temp_data}" \
+			-o "${temp_db}" --itrace cr >/dev/null && \
+		   psql -d "${temp_db}" -t -c 'SELECT COUNT(*) FROM calls WHERE id > 0;' | \
 			grep -q '[1-9]'; then
-			echo "PostgreSQL intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
+			passed=1
+			break
 		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "PostgreSQL intel_pt validation failed (no calls found)."
+		err=1
+	else
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_export_to_sqlite_python.sh b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
index d3c5e22a0754..19ca7c539cf7 100755
--- a/tools/perf/tests/shell/test_export_to_sqlite_python.sh
+++ b/tools/perf/tests/shell/test_export_to_sqlite_python.sh
@@ -47,9 +47,10 @@ test_file_mode() {
 	echo "Testing export-to-sqlite.py..."
 
 	# Generate events with callchains and context switches if supported
-	if ! perf record -g --switch-events -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event -g --switch-events -o "${temp_data}" \
 	     -- perf test -w noploop >/dev/null 2>&1 && \
-	   ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+	     -- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
@@ -77,29 +78,34 @@ test_file_mode() {
 test_intel_pt() {
 	echo "Testing export-to-sqlite.py with intel_pt..."
 
-	rm -f "${temp_db}" "${temp_data}"
-	# Generate some intel_pt events; use a subshell that waits for uname
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		return 0
-	fi
+	query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
+	query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
+	query="${query}exit(1 if r == 0 else 0)"
+
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_db}" "${temp_data}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			return 0
+		fi
 
-	# Run the script with --itrace cr to synthesize call_returns
-	if ! perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr; then
-		echo "intel_pt file mode test failed."
+		# Run the script with --itrace cr to synthesize call_returns
+		if perf script export-to-sqlite -i "${temp_data}" -o "${temp_db}" --itrace cr && \
+		   "$PYTHON" -c "$query" >/dev/null 2>&1; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "SQLite intel_pt validation failed (no calls found)."
 		err=1
 	else
-		# Check DB for calls
-		query="import sqlite3; c = sqlite3.connect('${temp_db}'); "
-		query="${query}r = c.execute('SELECT COUNT(*) FROM calls').fetchone()[0]; "
-		query="${query}exit(1 if r == 0 else 0)"
-		if ! "$PYTHON" -c "$query" >/dev/null 2>&1; then
-			echo "SQLite intel_pt validation failed (no calls found)."
-			err=1
-		else
-			echo "intel_pt test passed (cr validated)."
-		fi
+		echo "intel_pt test passed (cr validated)."
 	fi
 }
 
diff --git a/tools/perf/tests/shell/test_intel_pt_events_python.sh b/tools/perf/tests/shell/test_intel_pt_events_python.sh
index b5c3173fa2db..9754b9125da1 100755
--- a/tools/perf/tests/shell/test_intel_pt_events_python.sh
+++ b/tools/perf/tests/shell/test_intel_pt_events_python.sh
@@ -30,7 +30,8 @@ cleanup() {
 	[ -n "${temp_dir}" ] && rm -rf "${temp_dir}"
 }
 
-trap 'cleanup' EXIT TERM INT
+trap 'cleanup' EXIT
+trap 'cleanup; exit 1' TERM INT
 
 temp_dir=$(mktemp -d /tmp/perf.ipt.XXXXXX)
 temp_data="${temp_dir}/perf.data"
@@ -39,27 +40,31 @@ temp_out="${temp_dir}/perf.out"
 test_intel_pt() {
 	echo "Testing intel-pt-events.py with intel_pt..."
 
-	rm -f "${temp_data}" "${temp_out}"
-	# Generate some intel_pt events; use a subshell that waits for uname so
-	# uname's AUX buffer is flushed before the parent workload exits.
-	if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
-		-- sh -c "uname; true" >/dev/null 2>&1; then
-		echo "Skipping intel_pt test, intel_pt not available."
-		exit 2
-	fi
+	# Generate some intel_pt events; sleep briefly after uname in the subshell
+	# so uname's AUX buffer is flushed before SIGCHLD stops perf record.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}"
+		if ! perf record -B -N --no-bpf-event -e intel_pt//u -o "${temp_data}" \
+			-- sh -c "uname; sleep 0.05" >/dev/null 2>&1; then
+			echo "Skipping intel_pt test, intel_pt not available."
+			exit 2
+		fi
 
-	# Run the script and check output
-	if ! perf script intel-pt-events -i "${temp_data}" > "${temp_out}"; then
-		echo "intel-pt-events.py test failed."
+		# Run the script and check output
+		if perf script intel-pt-events -i "${temp_data}" > "${temp_out}" && \
+		   grep -q "Intel PT Branch Trace" "${temp_out}" && \
+		   grep -q "uname" "${temp_out}"; then
+			passed=1
+			break
+		fi
+	done
+
+	if [ "$passed" -eq 0 ]; then
+		echo "Failed to find expected output: $(cat "${temp_out}" 2>/dev/null)"
 		err=1
 	else
-		if ! grep -q "Intel PT Branch Trace" "${temp_out}" || \
-		   ! grep -q "uname" "${temp_out}"; then
-			echo "Failed to find expected output: $(cat "${temp_out}")"
-			err=1
-		else
-			echo "intel-pt-events test passed."
-		fi
+		echo "intel-pt-events test passed."
 	fi
 	rm -f "${temp_out}"
 }
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 5/9] perf test: Deflake failed-syscalls Python shell tests under load

[Ian Rogers]

When running 'perf test' in parallel under heavy system load, a one-shot
'perf record -e ... -- ls /does_not_exist' without '-B -N --no-bpf-event'
can exit in under 300 microseconds before 'ls's PERF_RECORD_COMM and
ENOENT sys_exit events are captured, while also contending on ~/.debug
build-id caching and BPF event synthesis.

Pass '-B -N --no-bpf-event' to 'perf record', sleep 0.05s in a subshell
after 'ls' so its events are flushed before the parent subshell exits,
and wrap the record and check steps in a bounded retry loop (up to 5
attempts).

Fixes: b76c43d09b06 ("perf python: Port failed-syscalls-by-pid to perf module")
Fixes: 4e3fe6987cba ("perf python: Port failed-syscalls from Perl to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../test_failed_syscalls_by_pid_python.sh     | 68 +++++++++++--------
 .../shell/test_failed_syscalls_python.sh      | 54 +++++++++------
 2 files changed, 71 insertions(+), 51 deletions(-)

diff --git a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
index 215372d4e1c5..070a7ef6b8ad 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
@@ -41,8 +41,10 @@ test_file_mode() {
 	echo "Testing failed-syscalls-by-pid.py..."
 
 	# Check if syscalls:sys_exit is supported/readable
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-		if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+			-o /dev/null -- true >/dev/null 2>&1; then
 			echo "Skipping test, no syscalls:sys_exit or raw_syscalls:sys_exit event"
 			exit 2
 		else
@@ -52,41 +54,49 @@ test_file_mode() {
 		EVENT="syscalls:sys_exit"
 	fi
 
-	# Generate some events by running a command that should fail at least some syscall
-	# (e.g. failing stat on non-existent file).
-	# Using '|| true' because 'perf record' returns the exit code of 'ls',
-	# which fails with ENOENT
-	perf record -e "${EVENT}" -o "${temp_data}" -- ls /does_not_exist >/dev/null 2>&1 || true
+	# Generate some events by running a command that fails a syscall
+	# (e.g. failing stat on non-existent file), sleeping briefly in the
+	# subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+	passed=0
+	for _ in 1 2 3 4 5; do
+		rm -f "${temp_data}" "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
+		perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+			-- sh -c "ls /does_not_exist 2>/dev/null; sleep 0.05 || true" \
+			>/dev/null 2>&1 || true
+		if [ ! -s "${temp_data}" ]; then
+			continue
+		fi
+
+		if perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}" && \
+		   grep -n -q "err = ENOENT" "${temp_out}" && \
+		   perf script failed-syscalls-by-pid -i "${temp_data}" \
+			"ls" > "${temp_out}.comm" && \
+		   grep -q "err = ENOENT" "${temp_out}.comm"; then
+			ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' \
+				"${temp_out}.comm" | head -n 1)
+			if [ -n "${ls_pid}" ] && \
+			   perf script failed-syscalls-by-pid -i "${temp_data}" \
+				"${ls_pid}" > "${temp_out}.pid" && \
+			   grep -q "err = ENOENT" "${temp_out}.pid"; then
+				passed=1
+				break
+			fi
+		fi
+	done
+
 	if [ ! -s "${temp_data}" ]; then
 		echo "Skipping test, perf record failed to create data"
 		exit 2
 	fi
 
-	# Run the script and check output
-	if ! perf script failed-syscalls-by-pid -i "${temp_data}" > "${temp_out}"; then
+	if [ "$passed" -eq 0 ]; then
 		echo "failed-syscalls-by-pid test failed."
-		err=1
-	elif ! grep -n -q "err = ENOENT" "${temp_out}"; then
-		echo "Failed to find expected failed syscalls"
-		cat "${temp_out}"
-		err=1
-	elif ! perf script failed-syscalls-by-pid -i "${temp_data}" "ls" > "${temp_out}.comm" || \
-	     ! grep -q "err = ENOENT" "${temp_out}.comm"; then
-		echo "failed-syscalls-by-pid comm filter test failed."
-		cat "${temp_out}.comm"
+		cat "${temp_out}" 2>/dev/null || true
+		cat "${temp_out}.comm" 2>/dev/null || true
+		cat "${temp_out}.pid" 2>/dev/null || true
 		err=1
 	else
-		ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' "${temp_out}.comm" | head -n 1)
-		if [ -z "${ls_pid}" ] || \
-		   ! perf script failed-syscalls-by-pid -i "${temp_data}" \
-			"${ls_pid}" > "${temp_out}.pid" || \
-		   ! grep -q "err = ENOENT" "${temp_out}.pid"; then
-			echo "failed-syscalls-by-pid PID filter test failed."
-			cat "${temp_out}.pid" 2>/dev/null || true
-			err=1
-		else
-			echo "failed-syscalls-by-pid test passed."
-		fi
+		echo "failed-syscalls-by-pid test passed."
 	fi
 	rm -f "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
 }
diff --git a/tools/perf/tests/shell/test_failed_syscalls_python.sh b/tools/perf/tests/shell/test_failed_syscalls_python.sh
index 861c2ba71c0a..9aaf05883c50 100755
--- a/tools/perf/tests/shell/test_failed_syscalls_python.sh
+++ b/tools/perf/tests/shell/test_failed_syscalls_python.sh
@@ -27,22 +27,22 @@ if [ ! -f "$script_path" ]; then
 fi
 
 err=0
-temp_data=""
-temp_out=""
+temp_dir=$(mktemp -d /tmp/perf-failed-syscalls-XXXXXX)
+temp_data="${temp_dir}/perf.data"
+temp_out="${temp_dir}/perf.out"
 
 cleanup() {
-	rm -f "${temp_data}" "${temp_out}"
+	rm -rf "${temp_dir}"
 }
 trap 'cleanup' EXIT TERM INT
 
-temp_data=$(mktemp /tmp/perf.data.XXXXXX)
-temp_out=$(mktemp /tmp/perf.out.XXXXXX)
-
 echo "Testing failed-syscalls.py..."
 
 # Check if sys_exit event can be recorded
-if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
-	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_exit \
+	-o /dev/null -- true >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e syscalls:sys_exit \
+		-o /dev/null -- true >/dev/null 2>&1; then
 		echo "Skipping test, no permission or support for sys_exit event"
 		exit 2
 	else
@@ -52,28 +52,38 @@ else
 	EVENT="raw_syscalls:sys_exit"
 fi
 
-# Run perf record with a command that fails a syscall (ls non-existent file).
-# ls exits with non-zero, so perf record returns non-zero exit code of the workload.
-perf record -e "${EVENT}" -o "${temp_data}" \
-	-- ls /nonexistent_file_for_test >/dev/null 2>&1 || true
+# Run perf record with a command that fails a syscall (ls non-existent file),
+# sleeping briefly in the subshell so ls's PERF_RECORD_COMM and sys_exit events are flushed.
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	perf record -B -N --no-bpf-event -e "${EVENT}" -o "${temp_data}" \
+		-- sh -c "ls /nonexistent_file_for_test 2>/dev/null; sleep 0.05 || true" \
+		>/dev/null 2>&1 || true
+
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script failed-syscalls -i "${temp_data}" > "${temp_out}" && \
+	   grep -q "failed syscalls by comm" "${temp_out}" && \
+	   grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
 
 if [ ! -s "${temp_data}" ]; then
 	echo "Skipping test, perf record failed to create data"
 	exit 2
 fi
 
-# Check that the script executes
-if ! perf script failed-syscalls -i "${temp_data}" > "${temp_out}"; then
-	echo "failed-syscalls.py test failed"
+if [ "$passed" -eq 0 ]; then
+	echo "Failed to find the metrics table header or expected error"
 	err=1
 else
-	if ! grep -q "failed syscalls by comm" "${temp_out}" || \
-		! grep -Eq '^ls[[:space:]]+[0-9]+' "${temp_out}"; then
-		echo "Failed to find the metrics table header or expected error"
-		err=1
-	else
-		echo "failed-syscalls test passed."
-	fi
+	echo "failed-syscalls test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 6/9] perf test: Reduce overhead and contention in Python shell tests

[Ian Rogers]

When all Python shell tests run concurrently during 'perf test' under
heavy load:
1. Unfiltered 'perf list' initializes all hardware PMUs and metrics in
   each test process; use 'perf list tracepoint' when checking for
   tracepoint events.
2. Running 'perf record' without '-B -N --no-bpf-event' synthesizes BPF
   events across the system and caches build-ids into ~/.debug; add
   '-B -N --no-bpf-event' to all Python shell test recordings.
3. Drop '-a' in test_check_perf_trace_python.sh,
   test_rw_by_file_python.sh, test_rw_by_pid_python.sh,
   test_rwtop_python.sh, and test_syscall_counts_by_pid_python.sh where
   only a single child workload ('dd' or 'sleep') is tested, avoiding
   system-wide /proc synthesis and ringbuffer contention.
4. Add '-W 1' to 'ping -c 1' in test_net_dropmonitor_python.sh and
   test_netdev_times_python.sh, and narrow 'compaction:*' to
   'compaction:mm_compaction_begin,compaction:mm_compaction_end' in
   test_compaction_times_python.sh.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/test_check_perf_trace_python.sh   | 8 +++++---
 tools/perf/tests/shell/test_compaction_times_python.sh   | 8 +++++---
 .../tests/shell/test_event_analyzing_sample_python.sh    | 3 ++-
 tools/perf/tests/shell/test_flamegraph_python.sh         | 5 +++--
 tools/perf/tests/shell/test_futex_contention_python.sh   | 7 ++++---
 tools/perf/tests/shell/test_gecko_python.sh              | 3 ++-
 tools/perf/tests/shell/test_mem_phys_addr_python.sh      | 8 +++++---
 tools/perf/tests/shell/test_net_dropmonitor_python.sh    | 9 +++++----
 tools/perf/tests/shell/test_netdev_times_python.sh       | 6 +++---
 tools/perf/tests/shell/test_powerpc_hcalls_python.sh     | 4 ++--
 tools/perf/tests/shell/test_rw_by_file_python.sh         | 5 +++--
 tools/perf/tests/shell/test_rw_by_pid_python.sh          | 4 ++--
 tools/perf/tests/shell/test_rwtop_python.sh              | 4 ++--
 tools/perf/tests/shell/test_sched_migration_python.sh    | 4 ++--
 tools/perf/tests/shell/test_stackcollapse_python.sh      | 2 +-
 .../tests/shell/test_syscall_counts_by_pid_python.sh     | 6 +++---
 tools/perf/tests/shell/test_syscall_counts_python.sh     | 5 +++--
 tools/perf/tests/shell/test_task_analyzer.sh             | 3 ++-
 tools/perf/tests/shell/test_wakeup_latency_python.sh     | 7 ++++---
 19 files changed, 58 insertions(+), 43 deletions(-)

diff --git a/tools/perf/tests/shell/test_check_perf_trace_python.sh b/tools/perf/tests/shell/test_check_perf_trace_python.sh
index 92cc7b1f0033..baf55945d429 100755
--- a/tools/perf/tests/shell/test_check_perf_trace_python.sh
+++ b/tools/perf/tests/shell/test_check_perf_trace_python.sh
@@ -45,10 +45,11 @@ test_file_mode() {
 	echo "Testing check-perf-trace.py..."
 
 	events=""
-	if perf list | grep -q "irq:softirq_entry"; then
+	tp_list=$(perf list tracepoint)
+	if echo "$tp_list" | grep -q "irq:softirq_entry"; then
 		events="irq:softirq_entry"
 	fi
-	if perf list | grep -q "kmem:kmalloc"; then
+	if echo "$tp_list" | grep -q "kmem:kmalloc"; then
 		if [ -n "$events" ]; then
 			events="$events,kmem:kmalloc,kmem:kfree"
 		else
@@ -62,7 +63,8 @@ test_file_mode() {
 	fi
 
 	# Generate events
-	if ! perf record -e "$events" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e "$events" -o "${temp_data}" \
+		-- sh -c "sleep 0.1" >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_compaction_times_python.sh b/tools/perf/tests/shell/test_compaction_times_python.sh
index 50397afaafed..3f5a71e52388 100755
--- a/tools/perf/tests/shell/test_compaction_times_python.sh
+++ b/tools/perf/tests/shell/test_compaction_times_python.sh
@@ -44,15 +44,17 @@ test_file_mode() {
 	echo "Testing compaction-times.py..."
 
 	# Check for any compaction events to see if kernel supports it
-	if ! perf list | grep -q "compaction:mm_compaction_begin"; then
+	if ! perf list tracepoint | grep -q "compaction:mm_compaction_begin"; then
 		echo "Skipping test, compaction tracepoints not found"
 		exit 2
 	fi
 
 	# Generate some events
-	# We might not naturally trigger compaction in 0.5s sleep, but the script
+	# We might not naturally trigger compaction in 0.1s sleep, but the script
 	# should parse the empty or sparse file correctly without crashing.
-	if ! perf record -e "compaction:*" -a -o "${temp_data}" -- sleep 0.5 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event \
+		-e "compaction:mm_compaction_begin,compaction:mm_compaction_end" \
+		-a -o "${temp_data}" -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index a7a8ded003db..5f0a41080acf 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing event_analyzing_sample.py..."
 
 	# Generate some events
-	if ! perf record -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record failed"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_flamegraph_python.sh b/tools/perf/tests/shell/test_flamegraph_python.sh
index 86313c72f53e..787d6bbdf04a 100755
--- a/tools/perf/tests/shell/test_flamegraph_python.sh
+++ b/tools/perf/tests/shell/test_flamegraph_python.sh
@@ -60,7 +60,8 @@ test_file_mode() {
 	echo "Testing flamegraph.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
@@ -75,7 +76,7 @@ test_file_mode() {
 
 	# Run the script in pipe ('-') mode and validate JSON output
 	rm -f "${temp_json}"
-	if ! perf record -g -o - -- perf test -w noploop 2>/dev/null | \
+	if ! perf record -B -N --no-bpf-event -g -o - -- perf test -w noploop 2>/dev/null | \
 		perf script flamegraph -i - -f json -o "${temp_json}" >/dev/null; then
 		echo "Pipe stdin JSON mode test failed."
 		err=1
diff --git a/tools/perf/tests/shell/test_futex_contention_python.sh b/tools/perf/tests/shell/test_futex_contention_python.sh
index a8846ed68ac2..41ce8470a75f 100755
--- a/tools/perf/tests/shell/test_futex_contention_python.sh
+++ b/tools/perf/tests/shell/test_futex_contention_python.sh
@@ -89,14 +89,15 @@ EOF
 test_file_mode() {
 	echo "Testing futex-contention.py..."
 	# Some systems might not have syscalls:sys_enter_futex
-	if ! perf list | grep -q syscalls:sys_enter_futex; then
+	if ! perf list tracepoint | grep -q syscalls:sys_enter_futex; then
 		echo "Skipping file mode test, syscalls:sys_enter_futex not found"
 		return
 	fi
 
 	# Generate some futex events
-	if ! perf record -e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
-		-- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event \
+		-e syscalls:sys_enter_futex,syscalls:sys_exit_futex -a -o "${temp_data}" \
+		-- sleep 0.1 2>/dev/null; then
 		echo "Skipping file mode test (record failed)"
 		return
 	fi
diff --git a/tools/perf/tests/shell/test_gecko_python.sh b/tools/perf/tests/shell/test_gecko_python.sh
index de1d7fcf88b7..18e9f5cd2ab0 100755
--- a/tools/perf/tests/shell/test_gecko_python.sh
+++ b/tools/perf/tests/shell/test_gecko_python.sh
@@ -39,7 +39,8 @@ test_file_mode() {
 	echo "Testing gecko.py..."
 
 	# Generate some events with callchains
-	if ! perf record -g -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -g -o "${temp_data}" \
+		-- perf test -w noploop >/dev/null 2>&1; then
 		echo "Skipping test, perf record -g failed (permissions or lack of support)"
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_mem_phys_addr_python.sh b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
index 451692d5e089..cbb9f572be9d 100755
--- a/tools/perf/tests/shell/test_mem_phys_addr_python.sh
+++ b/tools/perf/tests/shell/test_mem_phys_addr_python.sh
@@ -78,10 +78,12 @@ test_file_mode() {
 	echo "Testing mem-phys-addr.py file mode..."
 
 	# Generate memory access events (try unprivileged user-space first, then system-wide)
-	if ! perf record --phys-data -d -o "${temp_data}" \
+	if ! perf record -B -N --no-bpf-event --phys-data -d -o "${temp_data}" \
 	     -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -o "${temp_data}" -- perf test -w datasym >/dev/null 2>&1 && \
-	   ! perf record -d -a -o "${temp_data}" -- sleep 0.2 >/dev/null 2>&1; then
+	   ! perf record -B -N --no-bpf-event -d -o "${temp_data}" \
+	     -- perf test -w datasym >/dev/null 2>&1 && \
+	   ! perf record -B -N --no-bpf-event -d -a -o "${temp_data}" \
+	     -- sleep 0.1 >/dev/null 2>&1; then
 		echo "Skipping file mode record test, perf record -d not supported"
 		return 0
 	fi
diff --git a/tools/perf/tests/shell/test_net_dropmonitor_python.sh b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
index 05056a897bc9..2e37994418fc 100755
--- a/tools/perf/tests/shell/test_net_dropmonitor_python.sh
+++ b/tools/perf/tests/shell/test_net_dropmonitor_python.sh
@@ -42,11 +42,12 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing net_dropmonitor.py..."
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -o "${temp_data}" -a \
-	-- ping -c 1 255.255.255.255 >/dev/null 2>&1; then
-	if ! perf record -e skb:kfree_skb -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" -a \
+	-- ping -c 1 -W 1 255.255.255.255 >/dev/null 2>&1; then
+	if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1; then
-		if ! perf record -o "${temp_data}" -- uname >/dev/null 2>&1; then
+		if ! perf record -B -N --no-bpf-event -o "${temp_data}" \
+			-- uname >/dev/null 2>&1; then
 			echo "Skipping test, cannot record perf events"
 			exit 2
 		fi
diff --git a/tools/perf/tests/shell/test_netdev_times_python.sh b/tools/perf/tests/shell/test_netdev_times_python.sh
index 393bf446efb2..0d8d10a42cab 100755
--- a/tools/perf/tests/shell/test_netdev_times_python.sh
+++ b/tools/perf/tests/shell/test_netdev_times_python.sh
@@ -85,9 +85,9 @@ then
 fi
 
 # Create a perf.data file. Force dropping a packet if tracepoint is available!
-if ! perf record -e skb:kfree_skb -a -o "${temp_data}" \
-	-- ping -c 1 127.0.0.1 >/dev/null 2>&1; then
-	perf record -e cycles -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e skb:kfree_skb -a -o "${temp_data}" \
+	-- ping -c 1 -W 1 127.0.0.1 >/dev/null 2>&1; then
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
index 19569c6d3613..b140ccf00ffa 100755
--- a/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
+++ b/tools/perf/tests/shell/test_powerpc_hcalls_python.sh
@@ -67,8 +67,8 @@ if ! grep -q "H_REMOVE.*1.*1500.*1500.*1500" "${temp_out}"; then
 fi
 
 # Create a perf.data file if powerpc hcall tracepoints are available on this host.
-if ! perf record -e powerpc:hcall_entry,powerpc:hcall_exit -a -o "${temp_data}" \
-	-- perf test -w noploop >/dev/null 2>&1; then
+if ! perf record -B -N --no-bpf-event -e powerpc:hcall_entry,powerpc:hcall_exit \
+	-a -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
 	echo "Skipping live record test, powerpc hcall tracepoints not available"
 	exit 0
 fi
diff --git a/tools/perf/tests/shell/test_rw_by_file_python.sh b/tools/perf/tests/shell/test_rw_by_file_python.sh
index f121597f418f..e3c538c3ace3 100755
--- a/tools/perf/tests/shell/test_rw_by_file_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_file_python.sh
@@ -37,8 +37,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-file.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
-	perf record -e syscalls:sys_enter_read,syscalls:sys_enter_write -a -o "${temp_data}" \
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
+	perf record -B -N --no-bpf-event -e syscalls:sys_enter_read,syscalls:sys_enter_write \
+		-o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rw_by_pid_python.sh b/tools/perf/tests/shell/test_rw_by_pid_python.sh
index 41eaa29097a2..cd93c1d9714c 100755
--- a/tools/perf/tests/shell/test_rw_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_rw_by_pid_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rw-by-pid.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_rwtop_python.sh b/tools/perf/tests/shell/test_rwtop_python.sh
index 05897e384702..d33807923c92 100755
--- a/tools/perf/tests/shell/test_rwtop_python.sh
+++ b/tools/perf/tests/shell/test_rwtop_python.sh
@@ -41,10 +41,10 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing rwtop.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "syscalls:sys_enter_read"; then
+if perf list tracepoint | grep -q "syscalls:sys_enter_read"; then
 	ev="syscalls:sys_enter_read,syscalls:sys_exit_read"
 	ev="${ev},syscalls:sys_enter_write,syscalls:sys_exit_write"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -o "${temp_data}" \
 		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
diff --git a/tools/perf/tests/shell/test_sched_migration_python.sh b/tools/perf/tests/shell/test_sched_migration_python.sh
index 75465bcd3791..714275b0e492 100755
--- a/tools/perf/tests/shell/test_sched_migration_python.sh
+++ b/tools/perf/tests/shell/test_sched_migration_python.sh
@@ -44,10 +44,10 @@ echo "Testing sched-migration.py..."
 ev="sched:sched_switch,sched:sched_migrate_task"
 ev="${ev},sched:sched_wakeup_new,sched:sched_wakeup"
 has_sched=1
-if ! perf record -e "$ev" -a -o "${temp_data}" \
+if ! perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 	-- sleep 0.1 >/dev/null 2>&1; then
 	has_sched=0
-	perf record -e cycles -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 fi
diff --git a/tools/perf/tests/shell/test_stackcollapse_python.sh b/tools/perf/tests/shell/test_stackcollapse_python.sh
index ce0f80407eec..2048734c5e0d 100755
--- a/tools/perf/tests/shell/test_stackcollapse_python.sh
+++ b/tools/perf/tests/shell/test_stackcollapse_python.sh
@@ -37,7 +37,7 @@ echo "Testing stackcollapse.py..."
 
 # Create a perf.data file with callchains. Use a busy workload rather than
 # sleep, as an idle system may not generate any samples at all.
-perf record -g -o "${temp_data}" \
+perf record -B -N --no-bpf-event -g -o "${temp_data}" \
 		-- perf test -w noploop >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
index 45bbdc554c8f..300289fe33b4 100755
--- a/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_by_pid_python.sh
@@ -43,14 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts-by-pid.py..."
 	# Some systems might not have raw_syscalls:sys_enter
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.5 >/dev/null 2>&1 || \
+	perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 
 	if ! perf script syscall-counts-by-pid -i "${temp_data}" > "${temp_out}"; then
diff --git a/tools/perf/tests/shell/test_syscall_counts_python.sh b/tools/perf/tests/shell/test_syscall_counts_python.sh
index 310e05d399f9..86463f14391b 100755
--- a/tools/perf/tests/shell/test_syscall_counts_python.sh
+++ b/tools/perf/tests/shell/test_syscall_counts_python.sh
@@ -43,13 +43,14 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 test_file_mode() {
 	echo "Testing syscall-counts.py..."
 	# Some systems might not have raw_syscalls:sys_enter (e.g. stripped kernels or permissions)
-	if ! perf list | grep -q raw_syscalls:sys_enter; then
+	if ! perf list tracepoint | grep -q raw_syscalls:sys_enter; then
 		echo "Skipping test, raw_syscalls:sys_enter not found"
 		exit 2
 	fi
 
 	# Generate some syscall events
-	if ! perf record -e raw_syscalls:sys_enter -o "${temp_data}" -- sleep 0.5 2>/dev/null; then
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" 2>/dev/null; then
 		echo "perf record failed (permissions?), skipping file mode test."
 		exit 2
 	fi
diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh
index f99a637a6099..f53fa4a27c79 100755
--- a/tools/perf/tests/shell/test_task_analyzer.sh
+++ b/tools/perf/tests/shell/test_task_analyzer.sh
@@ -60,7 +60,8 @@ skip_no_probe_record_support() {
 
 prepare_perf_data() {
 	# 1s should be sufficient to catch at least some switches
-	perf record -e sched:sched_switch -a -o "${perfdata}" -- sleep 1 > /dev/null 2>&1
+	perf record -B -N --no-bpf-event -e sched:sched_switch -a -o "${perfdata}" \
+		-- sleep 1 > /dev/null 2>&1
 	# check if perf data file got created in above step.
 	if [ ! -e "${perfdata}" ]; then
 		printf "FAIL: perf record failed to create \"${perfdata}\" \n"
diff --git a/tools/perf/tests/shell/test_wakeup_latency_python.sh b/tools/perf/tests/shell/test_wakeup_latency_python.sh
index cb2571449168..b43a86996be2 100755
--- a/tools/perf/tests/shell/test_wakeup_latency_python.sh
+++ b/tools/perf/tests/shell/test_wakeup_latency_python.sh
@@ -41,9 +41,9 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing wakeup-latency.py..."
 
 # Create a perf.data file. Try to get tracepoint data.
-if perf list | grep -q "sched:sched_wakeup"; then
+if perf list tracepoint | grep -q "sched:sched_wakeup"; then
 	ev="sched:sched_wakeup,sched:sched_wakeup_new,sched:sched_switch"
-	perf record -e "$ev" -a -o "${temp_data}" \
+	perf record -B -N --no-bpf-event -e "$ev" -a -o "${temp_data}" \
 		-- sleep 0.1 >/dev/null 2>&1 || \
 		{ echo "Skipping test, perf record failed"; exit 2; }
 else
@@ -70,7 +70,8 @@ else
 fi
 
 # Also test zero-wakeups / unhandled events path to verify division-by-zero protection
-if perf record -e cycles -o "${temp_data}" -- perf test -w noploop >/dev/null 2>&1; then
+if perf record -B -N --no-bpf-event -e cycles -o "${temp_data}" \
+	-- perf test -w noploop >/dev/null 2>&1; then
 	if ! perf script wakeup-latency -i "${temp_data}" > "${temp_out}" || \
 	   ! grep -q "avg_wakeup_latency (ns): N/A" "${temp_out}"; then
 		echo "wakeup-latency zero-wakeups guard test failed"
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 7/9] perf python event_analyzing_sample: Default to in-memory SQLite database

[Ian Rogers]

When -d/--db is not specified, event_analyzing_sample.py created a
temporary file in /tmp via tempfile.mkstemp() and deleted it in
trace_end(). As noted during review, creating the database in a shared
/tmp directory does not reserve SQLite's auxiliary sidecar filenames
(-journal or -wal), and a temporary on-disk file is unnecessary when the
caller did not ask to persist the database.

Default to sqlite3.connect(":memory:") when db_path is not provided,
removing the temporary file creation and cleanup logic, and test both
the default in-memory mode and explicit -d file mode in
test_event_analyzing_sample_python.sh.

Fixes: eeb70645a809 ("perf python: Port event_analyzing_sample to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/python/event_analyzing_sample.py   | 35 ++++++-------------
 .../test_event_analyzing_sample_python.sh     |  8 ++++-
 2 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/tools/perf/python/event_analyzing_sample.py b/tools/perf/python/event_analyzing_sample.py
index 15b47cff9fa3..b4efee88d94b 100755
--- a/tools/perf/python/event_analyzing_sample.py
+++ b/tools/perf/python/event_analyzing_sample.py
@@ -17,10 +17,8 @@ from __future__ import annotations
 
 import argparse
 import math
-import os
 import sqlite3
 import struct
-import tempfile
 from typing import Any
 import perf
 
@@ -117,16 +115,11 @@ session: Any = None
 
 class _DB:
     con: sqlite3.Connection | None = None
-    temp_path: str | None = None
 
 def trace_begin(db_path: str | None = None) -> None:
     """Initialize database tables."""
     print("In trace_begin:\n")
-    if not db_path:
-        fd, db_path = tempfile.mkstemp(prefix="perf_events_", suffix=".db")
-        os.close(fd)
-        _DB.temp_path = db_path
-    con = sqlite3.connect(db_path)
+    con = sqlite3.connect(db_path or ":memory:")
     try:
         # Drop any pre-existing tables so repeated runs do not accumulate duplicate events.
         con.execute("drop table if exists gen_events;")
@@ -297,28 +290,20 @@ def show_pebs_ll() -> None:
 def trace_end() -> None:
     """Called at the end of trace processing."""
     print("In trace_end:\n")
-    try:
-        if _DB.con:
-            try:
-                _DB.con.commit()
-                show_general_events()
-                show_pebs_ll()
-            finally:
-                _DB.con.close()
-                _DB.con = None
-    finally:
-        if _DB.temp_path and os.path.exists(_DB.temp_path):
-            try:
-                os.remove(_DB.temp_path)
-            except OSError:
-                pass
-            _DB.temp_path = None
+    if _DB.con:
+        try:
+            _DB.con.commit()
+            show_general_events()
+            show_pebs_ll()
+        finally:
+            _DB.con.close()
+            _DB.con = None
 
 if __name__ == "__main__":
     ap = argparse.ArgumentParser(description="Analyze events with SQLite")
     ap.add_argument("-i", "--input", default="perf.data", help="Input file name")
     ap.add_argument("-d", "--db", "--database", dest="database", default=None,
-                    help="Database file name (defaults to a temporary file cleaned up on exit)")
+                    help="Database file name (defaults to an in-memory database)")
     args = ap.parse_args()
 
     try:
diff --git a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
index 5f0a41080acf..cddb12b67698 100755
--- a/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
+++ b/tools/perf/tests/shell/test_event_analyzing_sample_python.sh
@@ -45,8 +45,14 @@ test_file_mode() {
 		exit 2
 	fi
 
-	# Run the script
+	# Run the script with default (:memory:) database and with explicit -d path
 	if ! perf script event_analyzing_sample -i "${temp_data}" \
+		> "${temp_dir}/perf.mem.out" 2>&1 || \
+	   ! grep -q "Statistics about the general events" "${temp_dir}/perf.mem.out" || \
+	   grep -q "Error creating/inserting event" "${temp_dir}/perf.mem.out"; then
+		echo "Default in-memory database mode test failed."
+		err=1
+	elif ! perf script event_analyzing_sample -i "${temp_data}" \
 		-d "${temp_db}" > "${temp_dir}/perf.out" 2>&1; then
 		echo "File mode test failed."
 		err=1
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 8/9] perf python: Initialize debug output on module load

[Ian Rogers]

Unlike the perf binary's main(), PyInit_perf() does not call
perf_debug_setup(). As a result, the first warning or error printed from
the perf Python C extension hits debug_file() with _debug_file == NULL
and emits 'debug_file not set' without a trailing newline before the
actual diagnostic message.

Call perf_debug_setup() in PyInit_perf() and add the missing trailing
newline to the fallback warning in debug_file().

Fixes: ec49230cf6dd ("perf debug: Expose debug file")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/debug.c  | 2 +-
 tools/perf/util/python.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 6b5ffe81f141..b7095519419e 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -55,7 +55,7 @@ FILE *debug_file(void)
 {
 	if (!_debug_file) {
 		debug_set_file(stderr);
-		pr_warning_once("debug_file not set");
+		pr_warning_once("%s not set\n", __func__);
 	}
 	return _debug_file;
 }
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 690a94fb4f62..95140dfaef9c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -5157,6 +5157,7 @@ PyMODINIT_FUNC PyInit_perf(void)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	perf_debug_setup();
 
 	Py_INCREF(&pyrf_evlist__type);
 	PyModule_AddObject(module, "evlist", (PyObject *)&pyrf_evlist__type);
-- 
2.56.0.rc1.315.gc6ed9934b7-goog

[PATCH v3 9/9] perf pmu: Fix race with concurrent tracepoint creation and removal in perf list

[Ian Rogers]

perf_pmus__print_pmu_events() first counts events via
perf_pmu__num_events() to allocate the aliases array, then populates it
via perf_pmu__for_each_event(). When dynamic tracepoints (such as
kprobes or uprobes during 'perf test' runs) are concurrently created or
removed between the two passes:
- If an event is removed, state.index is smaller than the allocated len,
  leaving trailing zeroed entries in aliases[] with name == NULL and
  pmu == NULL, which causes qsort(cmp_sevent) or the print loop to crash
  with SIGSEGV.
- If a dynamic tracepoint subsystem directory is removed while scanning
  /sys/kernel/tracing/events, tp_pmu__for_each_tp_event() returns
  -ENOENT and aborts enumeration of all remaining tracepoint subsystems.
- If an event is added, perf_pmus__print_pmu_events__callback() aborts
  enumeration when state->index reaches state->aliases_len.

Grow state->aliases dynamically via realloc() when needed, use
state.index as the actual populated length for sorting and printing, and
ignore -ENOENT when a tracepoint subsystem directory disappears during
enumeration.

Fixes: c3245d2093c1 ("perf pmu: Abstract alias/event struct")
Fixes: 45b6e281cb06 ("perf tp_pmu: Add event APIs")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/pmus.c   | 21 +++++++++++++++++----
 tools/perf/util/tp_pmu.c |  8 ++++++--
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index e0a4cb2428ca..1355b317f3ed 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -8,6 +8,7 @@
 #include <sys/types.h>
 #include <ctype.h>
 #include <pthread.h>
+#include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include "cpumap.h"
@@ -571,7 +572,7 @@ static int cmp_sevent(const void *a, const void *b)
 	}
 
 	/* Order by event name. */
-	return strcmp(as->name, bs->name);
+	return strcmp(as->name ?: "", bs->name ?: "");
 }
 
 static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
@@ -581,7 +582,7 @@ static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
 		return false;
 
 	/* Don't remove duplicates for different PMUs */
-	return strcmp(a->pmu_name, b->pmu_name) == 0;
+	return strcmp(a->pmu_name ?: "", b->pmu_name ?: "") == 0;
 }
 
 struct events_callback_state {
@@ -597,8 +598,18 @@ static int perf_pmus__print_pmu_events__callback(void *vstate,
 	struct sevent *s;
 
 	if (state->index >= state->aliases_len) {
-		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
-		return 1;
+		size_t new_len = max_t(size_t, 16, state->aliases_len * 2);
+		struct sevent *new_aliases;
+
+		new_aliases = realloc(state->aliases, new_len * sizeof(struct sevent));
+		if (!new_aliases) {
+			pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
+			return 1;
+		}
+		memset(&new_aliases[state->aliases_len], 0,
+		       (new_len - state->aliases_len) * sizeof(struct sevent));
+		state->aliases = new_aliases;
+		state->aliases_len = new_len;
 	}
 	assert(info->pmu != NULL || info->name != NULL);
 	s = &state->aliases[state->index];
@@ -654,6 +665,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 		perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state,
 					 perf_pmus__print_pmu_events__callback);
 	}
+	aliases = state.aliases;
+	len = state.index;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
diff --git a/tools/perf/util/tp_pmu.c b/tools/perf/util/tp_pmu.c
index c2be8c9f9084..5ac732e06841 100644
--- a/tools/perf/util/tp_pmu.c
+++ b/tools/perf/util/tp_pmu.c
@@ -151,7 +151,9 @@ static int for_each_event_cb(void *state, const char *sys_name, const char *evt_
 
 static int for_each_event_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 int tp_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
@@ -176,7 +178,9 @@ static int num_events_cb(void *state, const char *sys_name __maybe_unused,
 
 static int num_events_sys_cb(void *state, const char *sys_name)
 {
-	return tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+	int ret = tp_pmu__for_each_tp_event(sys_name, state, num_events_cb);
+
+	return ret == -ENOENT ? 0 : ret;
 }
 
 size_t tp_pmu__num_events(struct perf_pmu *pmu __maybe_unused)
-- 
2.56.0.rc1.315.gc6ed9934b7-goog