[RFC PATCH v2 1/7] scripts: convert checkstack.pl to Python

[Breno Rodrigues Alves <breno3011alves@gmail.com>]

Faithful re-implementation of checkstack.pl in Python 3
(stdlib only). Same per-architecture regexes for x86/x86_64,
arm, arm64, m68k, mips, nios2, openrisc, parisc, powerpc,
s390, sparc, riscv and loongarch.

Verified byte-for-byte identical to the Perl version on a
synthetic objdump stream for x86_64.

Signed-off-by: Breno Rodrigues Alves <breno3011alves@gmail.com>
---
 scripts/checkstack.py | 143 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 143 insertions(+)
 create mode 100755 scripts/checkstack.py

diff --git a/scripts/checkstack.py b/scripts/checkstack.py
new file mode 100755
index 000000000..8be3861b3
--- /dev/null
+++ b/scripts/checkstack.py
@@ -0,0 +1,143 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check the stack usage of functions.
+# Usage: objdump -d vmlinux | checkstack.py [arch] [min_stack]
+
+import platform
+import re
+import sys
+
+X = '[0-9a-f]'
+RE_FUNC = re.compile(rf'^({X}*) <(.*)>:$')
+RE_FILE = re.compile(r'(.*):\s*file format')
+
+
+def arm_push_handler(line):
+    if re.search(r'.*push.*fp, ip, lr, pc}', line):
+        return (line.count(',') + 1) * 4
+    return 0
+
+
+def config_for(arch):
+    """Return (main_re, dynamic_re, sub_fn)."""
+    if re.match(r'^(?:aarch|arm)64$', arch):
+        return (
+            re.compile(rf'^.*stp.*sp, ?#-([0-9]{{1,8}})\]!'),
+            re.compile(rf'^.*sub.*sp, sp, #(0x{X}{{1,8}})'),
+            None)
+    if arch == 'arm':
+        return (re.compile(r'.*sub.*sp, sp, #([0-9]{1,4})'), None,
+                arm_push_handler)
+    if re.match(r'^x86(?:_64)?$', arch) or re.match(r'^i[3456]86$', arch):
+        return (
+            re.compile(rf'^.*[as][du][db]    \$(0x{X}{{1,8}}),%(?:e|r)sp$'),
+            re.compile(r'^.*[as][du][db]    (%.*),%(?:e|r)sp$'),
+            None)
+    if arch == 'm68k':
+        return (re.compile(r'.*(?:linkw %fp,|addaw )#-([0-9]{1,4})'
+                           r'(?:,%sp)?$'), None, None)
+    if arch == 'mips64':
+        return (re.compile(r'.*daddiu.*sp,sp,-([0-9]{1,8})'), None, None)
+    if arch == 'mips':
+        return (re.compile(r'.*addiu.*sp,sp,-([0-9]{1,8})'), None, None)
+    if arch == 'nios2':
+        return (re.compile(r'.*addi.*sp,sp,-([0-9]{1,8})'), None, None)
+    if arch == 'openrisc':
+        return (re.compile(r'.*l\.addi.*r1,r1,-([0-9]{1,8})'), None, None)
+    if arch in ('parisc', 'parisc64'):
+        return (re.compile(rf'.*ldo ({X}{{1,8}})\(sp\),sp'), None, None)
+    if arch == 'powerpc' or re.match(r'^ppc(?:64)?(?:le)?$', arch):
+        return (re.compile(rf'.*st[dw]u.*r1,-({X}{{1,8}})\(r1\)'),
+                None, None)
+    if re.match(r'^s390x?$', arch):
+        return (re.compile(r'.*(?:lay|ag?hi).*\%r15,-([0-9]+)'
+                           r'(?:\(\%r15\))?$'), None, None)
+    if arch in ('sparc', 'sparc64'):
+        return (re.compile(r'.*save.*%sp, -([0-9]{1,8}), %sp'), None, None)
+    if re.match(r'^riscv(?:64)?$', arch):
+        return (re.compile(r'.*addi.*sp,sp,-([0-9]{1,8})'), None, None)
+    if re.match(r'^loongarch(?:32|64)?$', arch):
+        return (re.compile(r'.*addi\..*sp, .*sp, -([0-9]{1,8}).*'),
+                None, None)
+    print(f'wrong or unknown architecture "{arch}"')
+    sys.exit(1)
+
+
+def parse_size(s):
+    return int(s, 16) if s.startswith('0x') else int(s)
+
+
+def main(argv):
+    arch = argv[0] if argv else platform.machine()
+    min_stack = int(argv[1]) if len(argv) > 1 and argv[1].isdigit() else 512
+
+    main_re, dyn_re, sub_fn = config_for(arch)
+
+    stack = []
+    func = None
+    file = ''
+    intro = ''
+    total = 0
+
+    for raw in sys.stdin:
+        line = raw.rstrip('\n')
+
+        m = RE_FUNC.match(line)
+        if m:
+            func = m.group(2)
+            if total > min_stack:
+                stack.append(f'{intro}{total}\n')
+            addr = m.group(1)
+            intro = f'0x{addr} {func} [{file}]:'
+            pad = 56 - len(intro)
+            while pad > 0:
+                intro += '\t'
+                pad -= 8
+            total = 0
+            continue
+
+        m = RE_FILE.match(line)
+        if m:
+            file = m.group(1).replace('.ko', '')
+            idx = file.rfind('/')
+            if idx != -1:
+                file = file[idx + 1:]
+            continue
+
+        m = main_re.search(line)
+        if m:
+            size = parse_size(m.group(1))
+            if size > 0xf0000000:
+                size = -size + 0x80000000 + 0x80000000
+            if size > 0x10000000:
+                continue
+            total += size
+            continue
+
+        if dyn_re is not None:
+            m = dyn_re.search(line)
+            if m:
+                total += parse_size(m.group(1))
+                continue
+
+        if sub_fn is not None:
+            total += sub_fn(line)
+
+    if total > min_stack:
+        stack.append(f'{intro}{total}\n')
+
+    def key(entry):
+        m = re.search(r':\t*(\d+)$', entry)
+        size = int(m.group(1)) if m else 0
+        m = re.search(r' (.*):', entry)
+        fname = m.group(1) if m else ''
+        return (-size, fname)
+
+    for entry in sorted(stack, key=key):
+        sys.stdout.write(entry)
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))
\ No newline at end of file
-- 
2.43.0