[PATCH v1 22/49] perf python: Port syscall-counts to perf module

[Ian Rogers]

Port tools/perf/scripts/python/syscall-counts.py to a standalone script
in tools/perf/python/ using the perf module. Avoiding the embedded
interpreter and per-event dictionary allocation overhead improves
execution speed by ~4x:

```
$ perf record -e raw_syscalls:sys_enter -a sleep 1
...
$ time perf script tools/perf/scripts/python/syscall-counts.py perf
...
real    0m3.887s
user    0m3.578s
sys     0m0.308s
$ time python3 tools/perf/python/syscall-counts.py perf
...
real    0m0.953s
user    0m0.905s
sys     0m0.048s
```

Additional improvements compared to the legacy script:
- Resolve syscall names using perf.syscall_name(id, session.e_machine)
  instead of host python-audit / Util.py tables, enabling accurate
  cross-architecture perf.data analysis without external dependencies.
- Support both raw_syscalls:sys_enter (sample.id) and individual
  syscalls:sys_enter_* tracepoints (sample.__syscall_nr / sample.nr),
  filtering out invalid/corrupt (> 0xffff or negative) syscall numbers.
- Add argparse CLI options (-i/--input and optional comm filter).

Add a shell test (test_syscall_counts_python.sh) to verify the
standalone script. The legacy script and its bin wrapper are retained
temporarily during the transition to maintain bisectability and are
removed once all scripts are migrated.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/python/syscall-counts.py           | 79 +++++++++++++++++++
 .../tests/shell/test_syscall_counts_python.sh | 74 +++++++++++++++++
 2 files changed, 153 insertions(+)
 create mode 100755 tools/perf/python/syscall-counts.py
 create mode 100755 tools/perf/tests/shell/test_syscall_counts_python.sh

diff --git a/tools/perf/python/syscall-counts.py b/tools/perf/python/syscall-counts.py
new file mode 100755
index 000000000000..4b0733b1536d
--- /dev/null
+++ b/tools/perf/python/syscall-counts.py
@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""
+Displays system-wide system call totals, broken down by syscall.
+
+If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+"""
+from __future__ import annotations
+
+import argparse
+from collections import defaultdict
+from typing import DefaultDict
+import perf
+
+syscalls: DefaultDict[int, int] = defaultdict(int)
+for_comm = None
+session = None
+
+
+def print_syscall_totals():
+    """Print aggregated statistics."""
+    if for_comm is not None:
+        print(f"\nsyscall events for {for_comm}:\n")
+    else:
+        print("\nsyscall events:\n")
+
+    print(f"{'event':<40} {'count':>10}")
+    print("---------------------------------------- -----------")
+
+    for sc_id, val in sorted(syscalls.items(),
+                             key=lambda kv: (kv[1], kv[0]), reverse=True):
+        e_machine = getattr(session, "e_machine", 0) or 0
+        if e_machine:
+            name = perf.syscall_name(sc_id, e_machine) or str(sc_id)
+        else:
+            name = perf.syscall_name(sc_id) or str(sc_id)
+        print(f"{name:<40} {val:>10}")
+
+
+def process_event(sample):
+    """Process a single sample event."""
+    event_name = str(sample.evsel)
+    if event_name.startswith("evsel(raw_syscalls:sys_enter"):
+        sc_id = getattr(sample, "id", -1)
+    elif event_name.startswith("evsel(syscalls:sys_enter"):
+        sc_id = getattr(sample, "__syscall_nr", getattr(sample, "id", None))
+        if sc_id is not None and (sc_id < 0 or sc_id > 0xffff):
+            sc_id = None
+        if sc_id is None:
+            sc_id = getattr(sample, "nr", -1)
+    else:
+        return
+
+    if sc_id < 0 or sc_id > 0xffff:
+        return
+
+    comm = "unknown"
+    try:
+        if session:
+            proc = session.find_thread(sample.sample_tid)
+            if proc:
+                comm = proc.comm() or "unknown"
+    except (TypeError, AttributeError):
+        pass
+
+    if for_comm and comm != for_comm:
+        return
+    syscalls[sc_id] += 1
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser()
+    ap.add_argument("comm", nargs="?", help="Only report syscalls for comm")
+    ap.add_argument("-i", "--input", default="perf.data", help="Input file name")
+    args = ap.parse_args()
+    for_comm = args.comm
+    session = perf.session(perf.data(args.input), sample=process_event)
+    session.process_events()
+    print_syscall_totals()
diff --git a/tools/perf/tests/shell/test_syscall_counts_python.sh b/tools/perf/tests/shell/test_syscall_counts_python.sh
new file mode 100755
index 000000000000..e1c6e2820cce
--- /dev/null
+++ b/tools/perf/tests/shell/test_syscall_counts_python.sh
@@ -0,0 +1,74 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# syscall-counts python test
+
+set -e
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+# If we don't have the perf python module, we can't test
+if ! "$PYTHON" -c 'import perf' > /dev/null 2>&1; then
+	echo "Skipping test, perf python module not found"
+	exit 2
+fi
+
+script_dir="$(dirname "$0")/../../python"
+script_path="${script_dir}/syscall-counts.py"
+
+if ! perf check feature -q libtraceevent > /dev/null 2>&1; then
+	echo "Skipping test, libtraceevent is disabled"
+	exit 2
+fi
+
+
+if [ ! -f "$script_path" ]; then
+	echo "Skipping test, syscall-counts.py not found at $script_path"
+	exit 2
+fi
+
+err=0
+temp_data=""
+
+cleanup() {
+	rm -f "${temp_data}"
+}
+
+trap 'cleanup' EXIT TERM INT
+
+temp_data=$(mktemp /tmp/perf.data.XXXXXX)
+
+test_file_mode() {
+	echo "Testing syscall-counts.py..."
+	# Some systems might not have raw_syscalls:sys_enter (e.g. stripped kernels or permissions)
+	if ! perf list | grep -q raw_syscalls:sys_enter; then
+		echo "Skipping test, raw_syscalls:sys_enter not found"
+		exit 2
+	fi
+
+	# Generate some syscall events
+	if ! perf record -e raw_syscalls:sys_enter -o "${temp_data}" -- sleep 0.5 2>/dev/null; then
+		echo "perf record failed (permissions?), skipping file mode test."
+		exit 2
+	fi
+
+	if ! "$PYTHON" "$script_path" -i "${temp_data}" >/dev/null; then
+		echo "File mode test failed."
+		err=1
+	else
+		echo "File mode test passed."
+	fi
+
+	# Test with a comm argument
+	if ! "$PYTHON" "$script_path" -i "${temp_data}" "sleep" >/dev/null; then
+		echo "Comm filter test failed."
+		err=1
+	else
+		echo "Comm filter test passed."
+	fi
+}
+
+test_file_mode
+
+exit $err
-- 
2.55.0.1082.g2b9226bbc0-goog