[PATCH v1 24/49] perf python: Port failed-syscalls-by-pid to perf module

[Ian Rogers]

Port failed-syscalls-by-pid.py to a standalone script in
tools/perf/python/ using the perf module:
- Resolve architecture-aware syscall names using
  perf.syscall_name(id, session.e_machine) instead of host python-audit
  tables, supporting cross-architecture perf.data files without external
  dependencies.
- Translate negative syscall return values into symbolic E* error names
  using errno.errorcode and architecture-specific session.e_machine
  overrides.
- Encapsulate aggregation in a SyscallAnalyzer class using
  collections.defaultdict and add argparse filtering by comm, PID, and
  -i/--input.

Add a shell test (test_failed_syscalls_by_pid_python.sh) to verify the
standalone script.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/python/failed-syscalls-by-pid.py   | 175 ++++++++++++++++++
 .../test_failed_syscalls_by_pid_python.sh     |  92 +++++++++
 2 files changed, 267 insertions(+)
 create mode 100755 tools/perf/python/failed-syscalls-by-pid.py
 create mode 100755 tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh

diff --git a/tools/perf/python/failed-syscalls-by-pid.py b/tools/perf/python/failed-syscalls-by-pid.py
new file mode 100755
index 000000000000..91a5309e3658
--- /dev/null
+++ b/tools/perf/python/failed-syscalls-by-pid.py
@@ -0,0 +1,175 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""
+Displays system-wide failed system call totals, broken down by pid.
+If a [comm] or [pid] arg is specified, only syscalls called by it are displayed.
+
+Ported from tools/perf/scripts/python/failed-syscalls-by-pid.py
+"""
+from __future__ import annotations
+
+import argparse
+from collections import defaultdict
+import errno
+import os
+import sys
+from typing import Optional
+import perf
+
+
+_GENERIC_ERRNO_OVERRIDES: dict[int, str] = {
+    11: "EAGAIN", 35: "EDEADLK", 36: "ENAMETOOLONG", 37: "ENOLCK",
+    38: "ENOSYS", 39: "ENOTEMPTY", 40: "ELOOP", 42: "ENOMSG",
+    45: "EOPNOTSUPP", 60: "ENOSTR", 61: "ENODATA", 78: "EREMCHG",
+    87: "EUSERS", 89: "EDESTADDRREQ", 90: "EMSGSIZE", 110: "ETIMEDOUT",
+    111: "ECONNREFUSED", 122: "EDQUOT",
+}
+
+_ARCH_ERRNO_TABLES: dict[int, dict[int, str]] = {
+    2: {35: "EAGAIN", 36: "EINPROGRESS", 37: "EALREADY", 78: "EDEADLK", 87: "ENOMSG"},
+    8: {35: "ENOMSG", 45: "EDEADLK", 89: "ENOSYS", 90: "ELOOP", 122: "EDQUOT"},
+    15: {35: "ENOMSG", 45: "EDEADLK", 246: "EAGAIN", 251: "ENOSYS"},
+    43: {35: "EAGAIN", 36: "EINPROGRESS", 37: "EALREADY", 78: "EDEADLK", 87: "ENOMSG"},
+    0x9026: {35: "EAGAIN", 11: "EDEADLK", 60: "ETIMEDOUT", 61: "ECONNREFUSED"},
+}
+
+
+def strerror(nr: int, e_machine: int = 0) -> str:
+    """Return error string for a given errno, accounting for target e_machine."""
+    err_num = abs(nr)
+    if e_machine in _ARCH_ERRNO_TABLES and err_num in _ARCH_ERRNO_TABLES[e_machine]:
+        return _ARCH_ERRNO_TABLES[e_machine][err_num]
+    if e_machine != 0 and err_num in _GENERIC_ERRNO_OVERRIDES:
+        return _GENERIC_ERRNO_OVERRIDES[err_num]
+    try:
+        return errno.errorcode[err_num]
+    except KeyError:
+        return f"Unknown {nr} errno"
+
+
+class SyscallAnalyzer:
+    """Analyzes failed syscalls and aggregates counts."""
+
+    def __init__(self, for_comm: Optional[str] = None, for_pid: Optional[int] = None):
+        self.for_comm = for_comm
+        self.for_pid = for_pid
+        self.session: Optional[perf.session] = None
+        self.syscalls: dict[tuple[str, int, int, int], int] = defaultdict(int)
+        machine = os.uname().machine
+        self.host_64_bit = ("64" in machine or machine in ("s390x", "alpha")
+                            or sys.maxsize > 0xffffffff)
+
+    def process_event(self, sample: perf.sample_event) -> None:
+        """Process raw_syscalls:sys_exit and syscalls:sys_exit events."""
+        event_name = str(sample.evsel)
+        if "raw_syscalls:sys_exit" not in event_name and "syscalls:sys_exit" not in event_name:
+            return
+
+        pid = sample.sample_tid
+        comm = "Unknown"
+        if hasattr(self, 'session') and self.session:
+            try:
+                thread = self.session.find_thread(sample.sample_pid, pid)
+                if thread:
+                    comm = thread.comm() or "Unknown"
+            except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError):
+                pass
+
+        if self.for_comm is not None and comm != self.for_comm:
+            return
+        if self.for_pid is not None and pid != self.for_pid:
+            return
+
+        ret = getattr(sample, "ret", 0)
+        is_64_bit = (getattr(self.session, "is_64_bit", self.host_64_bit)
+                     if self.session else self.host_64_bit)
+        if ret > 0:
+            if not is_64_bit and 0xfffff000 <= ret <= 0xffffffff:
+                ret -= 0x100000000
+            elif ret >= 0xfffffffffffff000:
+                ret -= 0x10000000000000000
+
+        if -4095 <= ret < 0:
+            syscall_id = getattr(sample, "__syscall_nr", -1)
+            if syscall_id < 0 or syscall_id > 0xffff:
+                syscall_id = getattr(sample, "nr", -1)
+            if syscall_id < 0 or syscall_id > 0xffff:
+                syscall_id = getattr(sample, "sys_id", -1)
+            if syscall_id < 0 or syscall_id > 0xffff:
+                syscall_id = getattr(sample, "id", -1)
+
+            if 0 <= syscall_id <= 0xffff:
+                self.syscalls[(comm, pid, syscall_id, ret)] += 1
+
+    def print_summary(self) -> None:
+        """Print aggregated statistics."""
+        if self.for_comm is not None:
+            print(f"\nsyscall errors for {self.for_comm}:\n")
+        elif self.for_pid is not None:
+            print(f"\nsyscall errors for PID {self.for_pid}:\n")
+        else:
+            print("\nsyscall errors:\n")
+
+        print(f"{'comm [pid]':<30}  {'count':>10}")
+        print(f"{'-' * 30:<30}  {'-' * 10:>10}")
+
+        sorted_keys = sorted(
+            self.syscalls.keys(),
+            key=lambda k: (k[0], k[1], k[2], -self.syscalls[k])
+        )
+        current_comm_pid = None
+        current_syscall = None
+        emach = getattr(self.session, "e_machine", 0) or 0
+        for comm, pid, syscall_id, ret in sorted_keys:
+            if current_comm_pid != (comm, pid):
+                print(f"\n{comm} [{pid}]")
+                current_comm_pid = (comm, pid)
+                current_syscall = None
+            if current_syscall != syscall_id:
+                try:
+                    if emach:
+                        name = perf.syscall_name(syscall_id, emach) or str(syscall_id)
+                    else:
+                        name = perf.syscall_name(syscall_id) or str(syscall_id)
+                except AttributeError:
+                    name = str(syscall_id)
+                print(f"  syscall: {name:<16}")
+                current_syscall = syscall_id
+            err_str = strerror(ret, emach)
+            count = self.syscalls[(comm, pid, syscall_id, ret)]
+            print(f"    err = {err_str:<20}  {count:10d}")
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser(
+        description="Displays system-wide failed system call totals, "
+                    "broken down by pid.")
+    ap.add_argument("-i", "--input", default="perf.data",
+                    help="Input file name")
+    ap.add_argument("filter", nargs="?", help="COMM or PID to filter by")
+    args = ap.parse_args()
+
+    F_COMM = None
+    F_PID = None
+
+    if args.filter:
+        try:
+            F_PID = int(args.filter)
+        except ValueError:
+            F_COMM = args.filter
+
+    analyzer = SyscallAnalyzer(F_COMM, F_PID)
+
+    try:
+        print("Press control+C to stop and show the summary")
+        session = perf.session(perf.data(args.input), sample=analyzer.process_event)
+        analyzer.session = session
+        session.process_events()
+        analyzer.print_summary()
+    except KeyboardInterrupt:
+        analyzer.print_summary()
+    except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e:
+        print(f"Error processing events: {e}")
+        sys.exit(1)
+    finally:
+        analyzer.session = None
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
new file mode 100755
index 000000000000..d5fab922b8a9
--- /dev/null
+++ b/tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
@@ -0,0 +1,92 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# failed-syscalls-by-pid python test
+
+set -e
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+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}/failed-syscalls-by-pid.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, failed-syscalls-by-pid.py not found at $script_path"
+	exit 2
+fi
+
+err=0
+temp_data=""
+temp_out=""
+
+cleanup() {
+	rm -f "${temp_data}" "${temp_out}"
+}
+
+trap 'cleanup' EXIT TERM INT
+
+temp_data=$(mktemp /tmp/perf.data.XXXXXX)
+temp_out=$(mktemp /tmp/perf.out.XXXXXX)
+
+test_file_mode() {
+	echo "Testing failed-syscalls-by-pid.py..."
+
+	# Check if syscalls:sys_exit is supported/readable
+	if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+		if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
+			echo "Skipping test, no syscalls:sys_exit or raw_syscalls:sys_exit event"
+			exit 2
+		else
+			EVENT="raw_syscalls:sys_exit"
+		fi
+	else
+		EVENT="syscalls:sys_exit"
+	fi
+
+	# Generate some events by running a command that should fail at least some syscall
+	# (e.g. failing stat on non-existent file).
+	# Using '|| true' because 'perf record' returns the exit code of 'ls',
+	# which fails with ENOENT
+	perf record -e "${EVENT}" -o "${temp_data}" -- ls /does_not_exist >/dev/null 2>&1 || true
+	if [ ! -s "${temp_data}" ]; then
+		echo "Skipping test, perf record failed to create data"
+		exit 2
+	fi
+
+	# Run the script and check output
+	if ! "$PYTHON" "$script_path" -i "${temp_data}" > "${temp_out}"; then
+		echo "failed-syscalls-by-pid test failed."
+		err=1
+	elif ! "$PYTHON" "$script_path" -i "${temp_data}" "ls" >/dev/null; then
+		echo "failed-syscalls-by-pid comm filter test failed."
+		err=1
+	elif ! "$PYTHON" "$script_path" -i "${temp_data}" "$$" >/dev/null; then
+		echo "failed-syscalls-by-pid PID filter test failed."
+		err=1
+	else
+		if ! grep -n -q "err = ENOENT" "${temp_out}"; then
+			echo "Failed to find expected failed syscalls"
+			cat "${temp_out}"
+			err=1
+		else
+			echo "failed-syscalls-by-pid test passed."
+		fi
+	fi
+	rm -f "${temp_out}"
+}
+
+test_file_mode
+
+exit $err
-- 
2.55.0.1082.g2b9226bbc0-goog