From patchwork Fri Jan 8 02:47:20 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dmitry Kozlyuk X-Patchwork-Id: 86142 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (xvm-189-124.dc0.ghst.net [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 258EBA0524; Fri, 8 Jan 2021 03:47:43 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DCC58140DD0; Fri, 8 Jan 2021 03:47:36 +0100 (CET) Received: from mail-lf1-f51.google.com (mail-lf1-f51.google.com [209.85.167.51]) by mails.dpdk.org (Postfix) with ESMTP id B8310140DB4 for ; Fri, 8 Jan 2021 03:47:35 +0100 (CET) Received: by mail-lf1-f51.google.com with SMTP id 23so19487784lfg.10 for ; Thu, 07 Jan 2021 18:47:35 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=th0aCz+hOrNzE/+zodKztsegy9THJ+QqOEZKcblfXmc=; b=FywfHagyuyqpLr4GLJAWHz3BWRihjYRtKuJ99k392IbDPiCHRHPwV+r+KoCJHPxAKE HvL6PjNfM49Nw6mvB6w94Nw29DnA/6brop3rT4lW+VXybFSWiqtGSjO9Wp8sbwi2mmSH fRnmexMXHv15cIIiko2SNjDXZ8b0xBC8i54ObmM5j4Fjqu4tA/lsO+Y8btKO+bHBECXP m6xb2724wk0Odvz9xN1x9a3npPIFfLs0nJM3P4hOll0Exy1yAZ7DHapCWWNYpx976a/0 lMfpMzN3vIAyr7JROGJZiKkyW6PVAlLEvs89aAKkeFOrbDDtsS6dkgMDoS3TpjmZUIqV MrlQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=th0aCz+hOrNzE/+zodKztsegy9THJ+QqOEZKcblfXmc=; b=DfJD6YsdW3k/5w28UlNO9TTYyKyhHI4J/1gMfaqj40eJyBKD5Z01IbeXxMbJijj5cQ dg7uOAJ7iu96jasUpkFe5GDVJpDb+YtsV/pa5HE8SPO0GCWAM3Nejvvc3zrQ9LrdP8wz 93ZPrg4GaxWz5j2nGCAWB2h4Vuq0Wz43ZJuV2bGAe08mCj5HPEJpMHK8eyPLa+FQb6qi cDUyww46X47oHWLeagZBoVqc5oEUwR6Iem3F/Ubc4sgIP1yD3ypRSYhXBC4agVN0DTXO bxPjfUUkHhVN6stG/FrP2MZuTTkqegld7nK7ZowgU66hpWHR9xVtFk4G72MmJOmSteTM JD3w== X-Gm-Message-State: AOAM532XqXDInoeBUQV2yw56vM9hbVZeglPKVSix9z8L1OpfhF+3Yvmv WXQIQuoKG/jhJ9TV62+rq4dSvO3wzF+Xs/xi X-Google-Smtp-Source: ABdhPJx4JbYHWaXlOdE3JQHBnM5qcfMulkcxvs7U1tu6YkdZrT4Pt+W+jhARlii6ZSmWIkhTLt7PLA== X-Received: by 2002:a2e:b4d3:: with SMTP id r19mr543720ljm.419.1610074054961; Thu, 07 Jan 2021 18:47:34 -0800 (PST) Received: from localhost.localdomain (broadband-37-110-65-23.ip.moscow.rt.ru. [37.110.65.23]) by smtp.gmail.com with ESMTPSA id i19sm1733599ljj.26.2021.01.07.18.47.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 07 Jan 2021 18:47:34 -0800 (PST) From: Dmitry Kozlyuk To: dev@dpdk.org Cc: Narcisa Ana Maria Vasile , Pallavi Kadam , Dmitry Malloy , Bruce Richardson , Neil Horman , Dmitry Kozlyuk Date: Fri, 8 Jan 2021 05:47:20 +0300 Message-Id: <20210108024723.26210-2-dmitry.kozliuk@gmail.com> X-Mailer: git-send-email 2.29.2 In-Reply-To: <20210108024723.26210-1-dmitry.kozliuk@gmail.com> References: <20201212233447.23154-1-dmitry.kozliuk@gmail.com> <20210108024723.26210-1-dmitry.kozliuk@gmail.com> MIME-Version: 1.0 Subject: [dpdk-dev] [PATCH v2 1/4] pmdinfogen: support COFF X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Common Object File Format (COFF) is used on Windows in place of ELF. Add COFF parser to pmdinfogen. Also add an argument to specify input file format, which is selected at configure time based on the target. Signed-off-by: Dmitry Kozlyuk --- Depends-on: series-13153 ("pmdinfogen: rewrite in Python") buildtools/coff.py | 154 +++++++++++++++++++++++++++++++++++++++ buildtools/meson.build | 7 ++ buildtools/pmdinfogen.py | 117 +++++++++++++++++++++-------- 3 files changed, 248 insertions(+), 30 deletions(-) create mode 100644 buildtools/coff.py diff --git a/buildtools/coff.py b/buildtools/coff.py new file mode 100644 index 000000000..86fb0602b --- /dev/null +++ b/buildtools/coff.py @@ -0,0 +1,154 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright (c) 2020 Dmitry Kozlyuk + +import ctypes + +# x86_64 little-endian +COFF_MAGIC = 0x8664 + +# Names up to this length are stored immediately in symbol table entries. +COFF_NAMELEN = 8 + +# Special "section numbers" changing the meaning of symbol table entry. +COFF_SN_UNDEFINED = 0 +COFF_SN_ABSOLUTE = -1 +COFF_SN_DEBUG = -2 + + +class CoffFileHeader(ctypes.LittleEndianStructure): + _pack_ = True + _fields_ = [ + ("magic", ctypes.c_uint16), + ("section_count", ctypes.c_uint16), + ("timestamp", ctypes.c_uint32), + ("symbol_table_offset", ctypes.c_uint32), + ("symbol_count", ctypes.c_uint32), + ("optional_header_size", ctypes.c_uint16), + ("flags", ctypes.c_uint16), + ] + + +class CoffName(ctypes.Union): + class Reference(ctypes.LittleEndianStructure): + _pack_ = True + _fields_ = [ + ("zeroes", ctypes.c_uint32), + ("offset", ctypes.c_uint32), + ] + + Immediate = ctypes.c_char * 8 + + _pack_ = True + _fields_ = [ + ("immediate", Immediate), + ("reference", Reference), + ] + + +class CoffSection(ctypes.LittleEndianStructure): + _pack_ = True + _fields_ = [ + ("name", CoffName), + ("physical_address", ctypes.c_uint32), + ("physical_address", ctypes.c_uint32), + ("size", ctypes.c_uint32), + ("data_offset", ctypes.c_uint32), + ("relocations_offset", ctypes.c_uint32), + ("line_numbers_offset", ctypes.c_uint32), + ("relocation_count", ctypes.c_uint16), + ("line_number_count", ctypes.c_uint16), + ("flags", ctypes.c_uint32), + ] + + +class CoffSymbol(ctypes.LittleEndianStructure): + _pack_ = True + _fields_ = [ + ("name", CoffName), + ("value", ctypes.c_uint32), + ("section_number", ctypes.c_int16), + ("type", ctypes.c_uint16), + ("storage_class", ctypes.c_uint8), + ("auxiliary_count", ctypes.c_uint8), + ] + + +class Symbol: + def __init__(self, image, symbol: CoffSymbol): + self._image = image + self._coff = symbol + + @property + def name(self): + if self._coff.name.reference.zeroes: + return decode_asciiz(bytes(self._coff.name.immediate)) + + offset = self._coff.name.reference.offset + offset -= ctypes.sizeof(ctypes.c_uint32) + return self._image.get_string(offset) + + def get_value(self, offset): + section_number = self._coff.section_number + + if section_number == COFF_SN_UNDEFINED: + return None + + if section_number == COFF_SN_DEBUG: + return None + + if section_number == COFF_SN_ABSOLUTE: + return bytes(ctypes.c_uint32(self._coff.value)) + + section_data = self._image.get_section_data(section_number) + section_offset = self._coff.value + offset + return section_data[section_offset:] + + +class Image: + def __init__(self, data): + header = CoffFileHeader.from_buffer_copy(data) + header_size = ctypes.sizeof(header) + header.optional_header_size + + sections_desc = CoffSection * header.section_count + sections = sections_desc.from_buffer_copy(data, header_size) + + symbols_desc = CoffSymbol * header.symbol_count + symbols = symbols_desc.from_buffer_copy(data, header.symbol_table_offset) + + strings_offset = header.symbol_table_offset + ctypes.sizeof(symbols) + strings = Image._parse_strings(data[strings_offset:]) + + self._data = data + self._header = header + self._sections = sections + self._symbols = symbols + self._strings = strings + + @staticmethod + def _parse_strings(data): + full_size = ctypes.c_uint32.from_buffer_copy(data) + header_size = ctypes.sizeof(full_size) + return data[header_size : full_size.value] + + @property + def symbols(self): + i = 0 + while i < self._header.symbol_count: + symbol = self._symbols[i] + yield Symbol(self, symbol) + i += symbol.auxiliary_count + 1 + + def get_section_data(self, number): + # section numbers are 1-based + section = self._sections[number - 1] + base = section.data_offset + return self._data[base : base + section.size] + + def get_string(self, offset): + return decode_asciiz(self._strings[offset:]) + + +def decode_asciiz(data): + index = data.find(b'\x00') + end = index if index >= 0 else len(data) + return data[:end].decode() diff --git a/buildtools/meson.build b/buildtools/meson.build index dd4c0f640..23cefd4be 100644 --- a/buildtools/meson.build +++ b/buildtools/meson.build @@ -17,7 +17,14 @@ else endif map_to_win_cmd = py3 + files('map_to_win.py') sphinx_wrapper = py3 + files('call-sphinx-build.py') + +# select object file format pmdinfogen = py3 + files('pmdinfogen.py') +if host_machine.system() == 'windows' + pmdinfogen += 'coff' +else + pmdinfogen += 'elf' +endif # TODO: starting from Meson 0.51.0 use # python3 = import('python').find_installation('python', diff --git a/buildtools/pmdinfogen.py b/buildtools/pmdinfogen.py index 0cca47ff1..474168f21 100755 --- a/buildtools/pmdinfogen.py +++ b/buildtools/pmdinfogen.py @@ -9,8 +9,13 @@ import sys import tempfile -from elftools.elf.elffile import ELFFile -from elftools.elf.sections import SymbolTableSection +try: + from elftools.elf.elffile import ELFFile + from elftools.elf.sections import SymbolTableSection +except ImportError: + pass + +import coff class ELFSymbol: @@ -18,21 +23,18 @@ def __init__(self, image, symbol): self._image = image self._symbol = symbol - @property - def size(self): - return self._symbol["st_size"] - - @property - def value(self): - data = self._image.get_section_data(self._symbol["st_shndx"]) - base = self._symbol["st_value"] - return data[base:base + self.size] - @property def string_value(self): - value = self.value + size = self._symbol["st_size"] + value = self.get_value(0, size) return value[:-1].decode() if value else "" + def get_value(self, offset, size): + section = self._symbol["st_shndx"] + data = self._image.get_section(section).data() + base = self._symbol["st_value"] + offset + return data[base : base + size] + class ELFImage: def __init__(self, data): @@ -45,18 +47,50 @@ def __init__(self, data): def is_big_endian(self): return not self._image.little_endian - def get_section_data(self, name): - return self._image.get_section(name).data() - def find_by_name(self, name): symbol = self._symtab.get_symbol_by_name(name) - return ELFSymbol(self, symbol[0]) if symbol else None + return ELFSymbol(self._image, symbol[0]) if symbol else None def find_by_prefix(self, prefix): for i in range(self._symtab.num_symbols()): symbol = self._symtab.get_symbol(i) if symbol.name.startswith(prefix): - yield ELFSymbol(self, symbol) + yield ELFSymbol(self._image, symbol) + + +class COFFSymbol: + def __init__(self, image, symbol): + self._image = image + self._symbol = symbol + + def get_value(self, offset, size): + value = self._symbol.get_value(offset) + return value[:size] if value else value + + @property + def string_value(self): + value = self._symbol.get_value(0) + return coff.decode_asciiz(value) if value else '' + + +class COFFImage: + def __init__(self, data): + self._image = coff.Image(data) + + @property + def is_big_endian(self): + return False + + def find_by_prefix(self, prefix): + for symbol in self._image.symbols: + if symbol.name.startswith(prefix): + yield COFFSymbol(self._image, symbol) + + def find_by_name(self, name): + for symbol in self._image.symbols: + if symbol.name == name: + return COFFSymbol(self._image, symbol) + return None def define_rte_pci_id(is_big_endian): @@ -117,19 +151,24 @@ def _load_pci_ids(image, table_name_symbol): rte_pci_id = define_rte_pci_id(image.is_big_endian) - pci_id_size = ctypes.sizeof(rte_pci_id) - pci_ids_desc = rte_pci_id * (table_symbol.size // pci_id_size) - pci_ids = pci_ids_desc.from_buffer_copy(table_symbol.value) result = [] - for pci_id in pci_ids: + while True: + size = ctypes.sizeof(rte_pci_id) + offset = size * len(result) + data = table_symbol.get_value(offset, size) + if not data: + break + pci_id = rte_pci_id.from_buffer_copy(data) if not pci_id.device_id: break - result.append([ - pci_id.vendor_id, - pci_id.device_id, - pci_id.subsystem_vendor_id, - pci_id.subsystem_device_id, - ]) + result.append( + [ + pci_id.vendor_id, + pci_id.device_id, + pci_id.subsystem_vendor_id, + pci_id.subsystem_device_id, + ] + ) return result def dump(self, file): @@ -157,6 +196,7 @@ def dump_drivers(drivers, file): def parse_args(): parser = argparse.ArgumentParser() + parser.add_argument("format", help="object file format, 'elf' or 'coff'") parser.add_argument("input", help="input object file path or '-' for stdin") parser.add_argument("output", help="output C file path or '-' for stdout") return parser.parse_args() @@ -170,6 +210,21 @@ def open_input(path): return open(path, "rb") +def read_input(path): + if path == "-": + return sys.stdin.buffer.read() + with open(path, "rb") as file: + return file.read() + + +def load_image(fmt, path): + if fmt == "elf": + return ELFImage(open_input(path)) + if fmt == "coff": + return COFFImage(read_input(path)) + raise Exception("unsupported object file format") + + def open_output(path): if path == "-": return sys.stdout @@ -178,8 +233,10 @@ def open_output(path): def main(): args = parse_args() - infile = open_input(args.input) - image = ELFImage(infile) + if args.format == "elf" and "ELFFile" not in globals(): + raise Exception("elftools module not found") + + image = load_image(args.format, args.input) drivers = load_drivers(image) output = open_output(args.output) dump_drivers(drivers, output)