contrib/plugins/uftrace_symbols.py: generate debug files to map symbols to source

Enhance uftrace_symbols.py to generate .dbg files, containing
source location for every symbol present in .sym file.
It allows to use `uftrace {replay,dump} --srcline` and show origin of
functions, connecting trace to original source code.

It was first implemented with pyelftools DWARF parser, which was way
too slow (~minutes) to get locations for every symbol in the linux
kernel. Thus, we use `addr2line` instead, which runs in seconds.

As well, there were some bugs with latest pyelftools release,
requiring to run master version, which is not installable with pip.
Thus, since we now require binutils (addr2line), we can ditch pyelftools
based implementation and simply rely on `nm` to get symbols information,
which is faster and better.

Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20251016150357.876415-8-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

contrib/plugins/uftrace_symbols.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
-# Create symbols and mapping files for uftrace.
+# Create symbols, debug and mapping files for uftrace.
 #
 # Copyright 2025 Linaro Ltd
 # Author: Pierrick Bouvier <pierrick.bouvier@linaro.org>
@@ -9,44 +9,71 @@
 # SPDX-License-Identifier: GPL-2.0-or-later
 
 import argparse
-import elftools # pip install pyelftools
 import os
-
-from elftools.elf.elffile import ELFFile
-from elftools.elf.sections import SymbolTableSection
-
-def elf_func_symbols(elf):
-    symbol_tables = [(idx, s) for idx, s in enumerate(elf.iter_sections())
-                  if isinstance(s, SymbolTableSection)]
-    symbols = []
-    for _, section in symbol_tables:
-        for _, symbol in enumerate(section.iter_symbols()):
-            if symbol_size(symbol) == 0:
-                continue
-            type = symbol['st_info']['type']
-            if type == 'STT_FUNC' or type == 'STT_NOTYPE':
-                symbols.append(symbol)
-    symbols.sort(key = lambda x: symbol_addr(x))
+import subprocess
+
+class Symbol:
+    def __init__(self, name, addr, size):
+        self.name = name
+        # clamp addr to 48 bits, like uftrace entries
+        self.addr = addr & 0xffffffffffff
+        self.full_addr = addr
+        self.size = size
+
+    def set_loc(self, file, line):
+        self.file = file
+        self.line = line
+
+def get_symbols(elf_file):
+    symbols=[]
+    try:
+        out = subprocess.check_output(['nm', '--print-size', elf_file],
+                                      stderr=subprocess.STDOUT,
+                                      text=True)
+    except subprocess.CalledProcessError as e:
+        print(e.output)
+        raise
+    out = out.strip().split('\n')
+    for line in out:
+        info = line.split(' ')
+        if len(info) == 3:
+            # missing size information
+            continue
+        addr, size, type, name = info
+        # add only symbols from .text section
+        if type.lower() != 't':
+            continue
+        addr = int(addr, 16)
+        size = int(size, 16)
+        symbols.append(Symbol(name, addr, size))
+    symbols.sort(key = lambda x: x.addr)
     return symbols
 
-def symbol_size(symbol):
-    return symbol['st_size']
-
-def symbol_addr(symbol):
-    addr = symbol['st_value']
-    # clamp addr to 48 bits, like uftrace entries
-    return addr & 0xffffffffffff
-
-def symbol_name(symbol):
-    return symbol.name
+def find_symbols_locations(elf_file, symbols):
+    addresses = '\n'.join([hex(x.full_addr) for x in symbols])
+    try:
+        out = subprocess.check_output(['addr2line', '--exe', elf_file],
+                                      stderr=subprocess.STDOUT,
+                                      input=addresses, text=True)
+    except subprocess.CalledProcessError as e:
+        print(e.output)
+        raise
+    out = out.strip().split('\n')
+    assert len(out) == len(symbols)
+    for i in range(len(symbols)):
+        s = symbols[i]
+        file, line = out[i].split(':')
+        # addr2line may return 'line (discriminator [0-9]+)' sometimes,
+        # remove this to keep only line number.
+        line = line.split(' ')[0]
+        s.set_loc(file, line)
 
 class BinaryFile:
     def __init__(self, path, map_offset):
         self.fullpath = os.path.realpath(path)
         self.map_offset = map_offset
-        with open(path, 'rb') as f:
-            self.elf = ELFFile(f)
-            self.symbols = elf_func_symbols(self.elf)
+        self.symbols = get_symbols(self.fullpath)
+        find_symbols_locations(self.fullpath, self.symbols)
 
     def path(self):
         return self.fullpath
@@ -56,24 +83,31 @@ class BinaryFile:
 
     def addr_end(self):
         last_sym = self.symbols[-1]
-        return symbol_addr(last_sym) + symbol_size(last_sym) + self.map_offset
+        return last_sym.addr + last_sym.size + self.map_offset
 
     def generate_symbol_file(self, prefix_symbols):
         binary_name = os.path.basename(self.fullpath)
-        sym_file_path = f'./uftrace.data/{binary_name}.sym'
+        sym_file_path = os.path.join('uftrace.data', f'{binary_name}.sym')
         print(f'{sym_file_path} ({len(self.symbols)} symbols)')
         with open(sym_file_path, 'w') as sym_file:
             # print hexadecimal addresses on 48 bits
             addrx = "0>12x"
             for s in self.symbols:
-                addr = symbol_addr(s)
+                addr = s.addr
                 addr = f'{addr:{addrx}}'
-                size = f'{symbol_size(s):{addrx}}'
-                name = symbol_name(s)
+                size = f'{s.size:{addrx}}'
                 if prefix_symbols:
-                    name = f'{binary_name}:{name}'
+                    name = f'{binary_name}:{s.name}'
                 print(addr, size, 'T', name, file=sym_file)
 
+    def generate_debug_file(self):
+        binary_name = os.path.basename(self.fullpath)
+        dbg_file_path = os.path.join('uftrace.data', f'{binary_name}.dbg')
+        with open(dbg_file_path, 'w') as dbg_file:
+            for s in self.symbols:
+                print(f'F: {hex(s.addr)} {s.name}', file=dbg_file)
+                print(f'L: {s.line} {s.file}', file=dbg_file)
+
 def parse_parameter(p):
     s = p.split(":")
     path = s[0]
@@ -84,7 +118,7 @@ def parse_parameter(p):
     offset = s[1]
     if not offset.startswith('0x'):
         err = f'offset "{offset}" is not an hexadecimal constant. '
-        err += 'It should starts with "0x".'
+        err += 'It should start with "0x".'
         raise ValueError(err)
     offset = int(offset, 16)
     return path, offset
@@ -97,7 +131,7 @@ def is_from_user_mode(map_file_path):
     return False
 
 def generate_map(binaries):
-    map_file_path = './uftrace.data/sid-0.map'
+    map_file_path = os.path.join('uftrace.data', 'sid-0.map')
 
     if is_from_user_mode(map_file_path):
         print(f'do not overwrite {map_file_path} generated from qemu-user')
@@ -124,7 +158,8 @@ def generate_map(binaries):
 
 def main():
     parser = argparse.ArgumentParser(description=
-                                     'generate symbol files for uftrace')
+                                     'generate symbol files for uftrace. '
+                                     'Require binutils (nm and addr2line).')
     parser.add_argument('elf_file', nargs='+',
                         help='path to an ELF file. '
                         'Use /path/to/file:0xdeadbeef to add a mapping offset.')
@@ -133,8 +168,8 @@ def main():
                         action=argparse.BooleanOptionalAction)
     args = parser.parse_args()
 
-    if not os.path.exists('./uftrace.data'):
-        os.mkdir('./uftrace.data')
+    if not os.path.exists('uftrace.data'):
+        os.mkdir('uftrace.data')
 
     binaries = []
     for file in args.elf_file:
@@ -145,6 +180,7 @@ def main():
 
     for b in binaries:
         b.generate_symbol_file(args.prefix_symbols)
+        b.generate_debug_file()
 
     generate_map(binaries)