#!/usr/bin/env python3# SPDX-License-Identifier: GPL-2.0-only## Copyright (C) 2018-2019 Netronome Systems, Inc.# Copyright (C) 2021 Isovalent, Inc. # In case user attempts to run with Python 2.from __future__ import print_function import argparseimport reimport sys, osimport subprocess helpersDocStart = 'Start of BPF helper function descriptions:' class NoHelperFound(BaseException):    pass class NoSyscallCommandFound(BaseException):    pass class ParsingError(BaseException):    def __init__(self, line='<line not provided>', reader=None):        if reader:            BaseException.__init__(self,                                   'Error at file offset %d, parsing line: %s' %                                   (reader.tell(), line))        else:            BaseException.__init__(self, 'Error parsing line: %s' % line)  class APIElement(object):    """    An object representing the description of an aspect of the eBPF API.    @proto: prototype of the API symbol    @desc: textual description of the symbol    @ret: (optional) description of any associated return value    """    def __init__(self, proto='', desc='', ret='', attrs=[]):        self.proto = proto        self.desc = desc        self.ret = ret        self.attrs = attrs  class Helper(APIElement):    """    An object representing the description of an eBPF helper function.    @proto: function prototype of the helper function    @desc: textual description of the helper function    @ret: description of the return value of the helper function    """    def __init__(self, *args, **kwargs):        super().__init__(*args, **kwargs)        self.enum_val = None     def proto_break_down(self):        """        Break down helper function protocol into smaller chunks: return type,        name, distincts arguments.        """        arg_re = re.compile(r'((\w+ )*?(\w+|...))( (\**)(\w+))?$')        res = {}        proto_re = re.compile(r'(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$')         capture = proto_re.match(self.proto)        res['ret_type'] = capture.group(1)        res['ret_star'] = capture.group(2)        res['name']     = capture.group(3)        res['args'] = []         args    = capture.group(4).split(', ')        for a in args:            capture = arg_re.match(a)            res['args'].append({                'type' : capture.group(1),                'star' : capture.group(5),                'name' : capture.group(6)            })         return res  ATTRS = {    '__bpf_fastcall': 'bpf_fastcall'}  class HeaderParser(object):    """    An object used to parse a file in order to extract the documentation of a    list of eBPF helper functions. All the helpers that can be retrieved are    stored as Helper object, in the self.helpers() array.    @filename: name of file to parse, usually include/uapi/linux/bpf.h in the               kernel tree    """    def __init__(self, filename):        self.reader = open(filename, 'r')        self.line = ''        self.helpers = []        self.commands = []        self.desc_unique_helpers = set()        self.define_unique_helpers = []        self.helper_enum_vals = {}        self.helper_enum_pos = {}        self.desc_syscalls = []        self.enum_syscalls = []     def parse_element(self):        proto    = self.parse_symbol()        desc     = self.parse_desc(proto)        ret      = self.parse_ret(proto)        return APIElement(proto=proto, desc=desc, ret=ret)     def parse_helper(self):        proto    = self.parse_proto()        desc     = self.parse_desc(proto)        ret      = self.parse_ret(proto)        attrs    = self.parse_attrs(proto)        return Helper(proto=proto, desc=desc, ret=ret, attrs=attrs)     def parse_symbol(self):        p = re.compile(r' \* ?(BPF\w+)$')        capture = p.match(self.line)        if not capture:            raise NoSyscallCommandFound        end_re = re.compile(r' \* ?NOTES$')        end = end_re.match(self.line)        if end:            raise NoSyscallCommandFound        self.line = self.reader.readline()        return capture.group(1)     def parse_proto(self):        # Argument can be of shape:        #   - "void"        #   - "type  name"        #   - "type *name"        #   - Same as above, with "const" and/or "struct" in front of type        #   - "..." (undefined number of arguments, for bpf_trace_printk())        # There is at least one term ("void"), and at most five arguments.        p = re.compile(r' \* ?((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$')        capture = p.match(self.line)        if not capture:            raise NoHelperFound        self.line = self.reader.readline()        return capture.group(1)     def parse_desc(self, proto):        p = re.compile(r' \* ?(?:\t| {5,8})Description$')        capture = p.match(self.line)        if not capture:            raise Exception("No description section found for " + proto)        # Description can be several lines, some of them possibly empty, and it        # stops when another subsection title is met.        desc = ''        desc_present = False        while True:            self.line = self.reader.readline()            if self.line == ' *\n':                desc += '\n'            else:                p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')                capture = p.match(self.line)                if capture:                    desc_present = True                    desc += capture.group(1) + '\n'                else:                    break         if not desc_present:            raise Exception("No description found for " + proto)        return desc     def parse_ret(self, proto):        p = re.compile(r' \* ?(?:\t| {5,8})Return$')        capture = p.match(self.line)        if not capture:            raise Exception("No return section found for " + proto)        # Return value description can be several lines, some of them possibly        # empty, and it stops when another subsection title is met.        ret = ''        ret_present = False        while True:            self.line = self.reader.readline()            if self.line == ' *\n':                ret += '\n'            else:                p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')                capture = p.match(self.line)                if capture:                    ret_present = True                    ret += capture.group(1) + '\n'                else:                    break         if not ret_present:            raise Exception("No return found for " + proto)        return ret     def parse_attrs(self, proto):        p = re.compile(r' \* ?(?:\t| {5,8})Attributes$')        capture = p.match(self.line)        if not capture:            return []        # Expect a single line with mnemonics for attributes separated by spaces        self.line = self.reader.readline()        p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')        capture = p.match(self.line)        if not capture:            raise Exception("Incomplete 'Attributes' section for " + proto)        attrs = capture.group(1).split(' ')        for attr in attrs:            if attr not in ATTRS:                raise Exception("Unexpected attribute '" + attr + "' specified for " + proto)        self.line = self.reader.readline()        if self.line != ' *\n':            raise Exception("Expecting empty line after 'Attributes' section for " + proto)        # Prepare a line for next self.parse_* to consume        self.line = self.reader.readline()        return attrs     def seek_to(self, target, help_message, discard_lines = 1):        self.reader.seek(0)        offset = self.reader.read().find(target)        if offset == -1:            raise Exception(help_message)        self.reader.seek(offset)        self.reader.readline()        for _ in range(discard_lines):            self.reader.readline()        self.line = self.reader.readline()     def parse_desc_syscall(self):        self.seek_to('* DOC: eBPF Syscall Commands',                     'Could not find start of eBPF syscall descriptions list')        while True:            try:                command = self.parse_element()                self.commands.append(command)                self.desc_syscalls.append(command.proto)             except NoSyscallCommandFound:                break     def parse_enum_syscall(self):        self.seek_to('enum bpf_cmd {',                     'Could not find start of bpf_cmd enum', 0)        # Searches for either one or more BPF\w+ enums        bpf_p = re.compile(r'\s*(BPF\w+)+')        # Searches for an enum entry assigned to another entry,        # for e.g. BPF_PROG_RUN = BPF_PROG_TEST_RUN, which is        # not documented hence should be skipped in check to        # determine if the right number of syscalls are documented        assign_p = re.compile(r'\s*(BPF\w+)\s*=\s*(BPF\w+)')        bpf_cmd_str = ''        while True:            capture = assign_p.match(self.line)            if capture:                # Skip line if an enum entry is assigned to another entry                self.line = self.reader.readline()                continue            capture = bpf_p.match(self.line)            if capture:                bpf_cmd_str += self.line            else:                break            self.line = self.reader.readline()        # Find the number of occurences of BPF\w+        self.enum_syscalls = re.findall(r'(BPF\w+)+', bpf_cmd_str)     def parse_desc_helpers(self):        self.seek_to(helpersDocStart,                     'Could not find start of eBPF helper descriptions list')        while True:            try:                helper = self.parse_helper()                self.helpers.append(helper)                proto = helper.proto_break_down()                self.desc_unique_helpers.add(proto['name'])            except NoHelperFound:                break     def parse_define_helpers(self):        # Parse FN(...) in #define ___BPF_FUNC_MAPPER to compare later with the        # number of unique function names present in description and use the        # correct enumeration value.        # Note: seek_to(..) discards the first line below the target search text,        # resulting in FN(unspec, 0, ##ctx) being skipped and not added to        # self.define_unique_helpers.        self.seek_to('#define ___BPF_FUNC_MAPPER(FN, ctx...)',                     'Could not find start of eBPF helper definition list')        # Searches for one FN(\w+) define or a backslash for newline        p = re.compile(r'\s*FN\((\w+), (\d+), ##ctx\)|\\\\')        fn_defines_str = ''        i = 0        while True:            capture = p.match(self.line)            if capture:                fn_defines_str += self.line                helper_name = capture.expand(r'bpf_\1')                self.helper_enum_vals[helper_name] = int(capture.group(2))                self.helper_enum_pos[helper_name] = i                i += 1            else:                break            self.line = self.reader.readline()        # Find the number of occurences of FN(\w+)        self.define_unique_helpers = re.findall(r'FN\(\w+, \d+, ##ctx\)', fn_defines_str)     def validate_helpers(self):        last_helper = ''        seen_helpers = set()        seen_enum_vals = set()        i = 0        for helper in self.helpers:            proto = helper.proto_break_down()            name = proto['name']            try:                enum_val = self.helper_enum_vals[name]                enum_pos = self.helper_enum_pos[name]            except KeyError:                raise Exception("Helper %s is missing from enum bpf_func_id" % name)             if name in seen_helpers:                if last_helper != name:                    raise Exception("Helper %s has multiple descriptions which are not grouped together" % name)                continue             # Enforce current practice of having the descriptions ordered            # by enum value.            if enum_pos != i:                raise Exception("Helper %s (ID %d) comment order (#%d) must be aligned with its position (#%d) in enum bpf_func_id" % (name, enum_val, i + 1, enum_pos + 1))            if enum_val in seen_enum_vals:                raise Exception("Helper %s has duplicated value %d" % (name, enum_val))             seen_helpers.add(name)            last_helper = name            seen_enum_vals.add(enum_val)             helper.enum_val = enum_val            i += 1     def run(self):        self.parse_desc_syscall()        self.parse_enum_syscall()        self.parse_desc_helpers()        self.parse_define_helpers()        self.validate_helpers()        self.reader.close() ############################################################################### class Printer(object):    """    A generic class for printers. Printers should be created with an array of    Helper objects, and implement a way to print them in the desired fashion.    @parser: A HeaderParser with objects to print to standard output    """    def __init__(self, parser):        self.parser = parser        self.elements = []     def print_header(self):        pass     def print_footer(self):        pass     def print_one(self, helper):        pass     def print_all(self):        self.print_header()        for elem in self.elements:            self.print_one(elem)        self.print_footer()     def elem_number_check(self, desc_unique_elem, define_unique_elem, type, instance):        """        Checks the number of helpers/syscalls documented within the header file        description with those defined as part of enum/macro and raise an        Exception if they don't match.        """        nr_desc_unique_elem = len(desc_unique_elem)        nr_define_unique_elem = len(define_unique_elem)        if nr_desc_unique_elem != nr_define_unique_elem:            exception_msg = '''The number of unique %s in description (%d) doesn\'t match the number of unique %s defined in %s (%d)''' % (type, nr_desc_unique_elem, type, instance, nr_define_unique_elem)            if nr_desc_unique_elem < nr_define_unique_elem:                # Function description is parsed until no helper is found (which can be due to                # misformatting). Hence, only print the first missing/misformatted helper/enum.                exception_msg += '''The description for %s is not present or formatted correctly.''' % (define_unique_elem[nr_desc_unique_elem])            raise Exception(exception_msg) class PrinterRST(Printer):    """    A generic class for printers that print ReStructured Text. Printers should    be created with a HeaderParser object, and implement a way to print API    elements in the desired fashion.    @parser: A HeaderParser with objects to print to standard output    """    def __init__(self, parser):        self.parser = parser     def print_license(self):        license = '''\.. Copyright (C) All BPF authors and contributors from 2014 to present... See git log include/uapi/linux/bpf.h in kernel tree for details... .. SPDX-License-Identifier: Linux-man-pages-copyleft.. .. Please do not edit this file. It was generated from the documentation.. located in file include/uapi/linux/bpf.h of the Linux kernel sources.. (helpers description), and from scripts/bpf_doc.py in the same.. repository (header and footer).'''        print(license)     def print_elem(self, elem):        if (elem.desc):            print('\tDescription')            # Do not strip all newline characters: formatted code at the end of            # a section must be followed by a blank line.            for line in re.sub('\n$', '', elem.desc, count=1).split('\n'):                print('{}{}'.format('\t\t' if line else '', line))         if (elem.ret):            print('\tReturn')            for line in elem.ret.rstrip().split('\n'):                print('{}{}'.format('\t\t' if line else '', line))         print('')     def get_kernel_version(self):        try:            version = subprocess.run(['git', 'describe'], cwd=linuxRoot,                                     capture_output=True, check=True)            version = version.stdout.decode().rstrip()        except:            try:                version = subprocess.run(['make', '-s', '--no-print-directory', 'kernelversion'],                                         cwd=linuxRoot, capture_output=True, check=True)                version = version.stdout.decode().rstrip()            except:                return 'Linux'        return 'Linux {version}'.format(version=version)     def get_last_doc_update(self, delimiter):        try:            cmd = ['git', 'log', '-1', '--pretty=format:%cs', '--no-patch',                   '-L',                   '/{}/,/\\*\\//:include/uapi/linux/bpf.h'.format(delimiter)]            date = subprocess.run(cmd, cwd=linuxRoot,                                  capture_output=True, check=True)            return date.stdout.decode().rstrip()        except:            return '' class PrinterHelpersRST(PrinterRST):    """    A printer for dumping collected information about helpers as a ReStructured    Text page compatible with the rst2man program, which can be used to    generate a manual page for the helpers.    @parser: A HeaderParser with Helper objects to print to standard output    """    def __init__(self, parser):        self.elements = parser.helpers        self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '___BPF_FUNC_MAPPER')     def print_header(self):        header = '''\===========BPF-HELPERS===========-------------------------------------------------------------------------------list of eBPF helper functions------------------------------------------------------------------------------- :Manual section: 7:Version: {version}{date_field}{date} DESCRIPTION=========== The extended Berkeley Packet Filter (eBPF) subsystem consists in programswritten in a pseudo-assembly language, then attached to one of the severalkernel hooks and run in reaction of specific events. This framework differsfrom the older, "classic" BPF (or "cBPF") in several aspects, one of them beingthe ability to call special functions (or "helpers") from within a program.These functions are restricted to a white-list of helpers defined in thekernel. These helpers are used by eBPF programs to interact with the system, or withthe context in which they work. For instance, they can be used to print

Lines 1–500 of 940. Load more