wasm-micro-runtime/test-tools/addr2line/addr2line.py

#!/usr/bin/env python3
#
# Copyright (C) 2019 Intel Corporation.  All rights reserved.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
import argparse
import os
from pathlib import Path
import re
import shlex
import subprocess
import sys

"""
it is a tool to transfer the address, which is from a call-stack dump generated by iwasm, to line info for a wasm file.

> in order to generate the call-stack dump, you can use the following command: `$ cmake -DWAMR_BUILD_DUMP_CALL_STACK=1 ...`

When a wasm file is compiled with debug info, it is possible to transfer the address to line info.

For example, there is a call-stack dump:

```
#00: 0x0a04 - $f18
#01: 0x08e4 - $f11
#02: 0x096f - $f12
#03: 0x01aa - _start
```

- store the call-stack dump into a file, e.g. call_stack.txt
- run the following command to transfer the address to line info:
  ```
  $ cd test-tools/addr2line
  $ python3 addr2line.py --wasi-sdk <wasi-sdk installation> --wasm-file <wasm file path> call_stack.txt
  ```
- the script will use *llvm-dwarfdump* to lookup the line info for each address in the call-stack dump.
- the output will be:
  ```
  #00: 0x0a04 - $f18
  #01: 0x08e4 - $f11 (FILE:quicksort.c LINE:  176 COLUMN: 11 FUNC:Quick)
  #02: 0x096f - $f12 (FILE:quicksort.c LINE:  182 COLUMN:  3 FUNC:main)
  #03: 0x01aa - _start
  ```

"""


def get_line_info(dwarf_dump: Path, wasm_file: Path, offset: int) -> str:
    """
    Find the location info of a given offset in a wasm file.
    """
    cmd = f"{dwarf_dump} --lookup={offset} {wasm_file}"
    p = subprocess.run(
        shlex.split(cmd),
        check=False,
        capture_output=True,
        text=True,
        universal_newlines=True,
    )
    outputs = p.stdout.split(os.linesep)

    capture_name = False
    for line in outputs:
        line = line.strip()

        if "DW_TAG_subprogram" in line:
            capture_name = True
            continue

        if "DW_AT_name" in line and capture_name:
            PATTERN = r"DW_AT_name\s+\(\"(\S+)\"\)"
            m = re.match(PATTERN, line)
            assert m is not None

            function_name = m.groups()[0]

        if line.startswith("Line info"):
            location = line
            return (function_name, location)

    return ()


def parse_line_info(line_info: str) -> ():
    """
    line_info -> [file, line, column]
    """
    PATTERN = r"Line info: file \'(.+)\', line ([0-9]+), column ([0-9]+)"
    m = re.search(PATTERN, line_info)
    assert m is not None

    file, line, column = m.groups()
    return (file, int(line), int(column))


def parse_call_stack_line(line: str) -> ():
    """
    #00: 0x0a04 - $f18   => (00, 0x0a04, $f18)
    """
    PATTERN = r"#([0-9]+): 0x([0-9a-f]+) - (\S+)"
    m = re.match(PATTERN, line)
    return m.groups() if m else None


def main():
    parser = argparse.ArgumentParser(description="addr2line for wasm")
    parser.add_argument("--wasi-sdk", type=Path, help="path to wasi-sdk")
    parser.add_argument("--wasm-file", type=Path, help="path to wasm file")
    parser.add_argument("call_stack_file", type=Path, help="path to a call stack file")
    args = parser.parse_args()

    llvm_dwarf_dump = args.wasi_sdk.joinpath("bin/llvm-dwarfdump")
    assert llvm_dwarf_dump.exists()

    assert args.call_stack_file.exists()
    with open(args.call_stack_file, "rt", encoding="ascii") as f:
        for line in f:
            line = line.strip()

            if not line:
                continue

            splitted = parse_call_stack_line(line)
            if splitted is None:
                print(line)
                continue

            _, offset, _ = splitted

            offset = int(offset, 16)
            line_info = get_line_info(llvm_dwarf_dump, args.wasm_file, offset)
            if not line_info:
                print(line)
                continue

            function_name, line_info = line_info
            src_file, src_line, src_column = parse_line_info(line_info)
            print(
                f"{line} (FILE:{src_file} LINE:{src_line:5} COLUMN:{src_column:3} FUNC:{function_name})"
            )

    return 0


if __name__ == "__main__":
    sys.exit(main())