perf python: Port syscall-counts to perf module

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@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 95 insertions, 0 deletions

diff --git a/tools/perf/python/syscall-counts.py b/tools/perf/python/syscall-counts.py
new file mode 100755
index 000000000000..3ddb1bcc27e0
--- /dev/null
+++ b/tools/perf/python/syscall-counts.py
@@ -0,0 +1,95 @@
+#!/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])):
+        e_machine = getattr(session, "e_machine", 0) or 0
+        # Mask out the x86_64 x32 ABI bit (__X32_SYSCALL_BIT = 0x40000000) before
+        # resolving the syscall number in the architecture's syscall table.
+        raw_sc_id = sc_id & ~0x40000000
+        if e_machine:
+            name = perf.syscall_name(raw_sc_id, e_machine) or str(sc_id)
+        else:
+            name = perf.syscall_name(raw_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)
+    # Per-syscall syscalls:sys_enter_* tracepoints expose '__syscall_nr' (or 'nr')
+    # and may have an unrelated syscall argument named 'id' (e.g. sys_enter_clock_gettime),
+    # whereas raw_syscalls:sys_enter (and legacy pre-2.6.35 syscalls:sys_enter) expose 'id'.
+    if event_name.startswith("evsel(syscalls:sys_enter_"):
+        sc_id = getattr(sample, "__syscall_nr", None)
+        if sc_id is not None and not (0 <= (sc_id & ~0x40000000) <= 0xffff):
+            sc_id = None
+        if sc_id is None:
+            sc_id = getattr(sample, "nr", -1)
+    elif event_name.startswith(("evsel(raw_syscalls:sys_enter", "evsel(syscalls:sys_enter")):
+        sc_id = getattr(sample, "id", -1)
+        if not (0 <= (sc_id & ~0x40000000) <= 0xffff):
+            sc_id = getattr(sample, "__syscall_nr", -1)
+        if not (0 <= (sc_id & ~0x40000000) <= 0xffff):
+            sc_id = getattr(sample, "nr", -1)
+    else:
+        return
+
+    # Mask out __X32_SYSCALL_BIT (0x40000000) when validating the syscall ID range.
+    if not (0 <= (sc_id & ~0x40000000) <= 0xffff):
+        return
+
+    comm = "unknown"
+    try:
+        if session:
+            proc = session.find_thread(sample.sample_pid, 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
+    try:
+        session = perf.session(perf.data(args.input), sample=process_event)
+        session.process_events()
+        print_syscall_totals()
+    finally:
+        # Break the reference cycle between session and process_event (whose module
+        # globals reference session) since perf.session lacks cyclic GC (tp_traverse).
+        session = None