The .rst documentation contains a brief description of the user interface and includes kernel-doc generated from uapi header.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- Documentation/networking/index.rst | 1 + Documentation/networking/tcp_authopt.rst | 44 ++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 Documentation/networking/tcp_authopt.rst

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 58bc8cd367c6..f5c324a060d8 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -100,10 +100,11 @@ Contents: strparser switchdev sysfs-tagging tc-actions-env-rules tcp-thin + tcp_authopt team timestamping tipc tproxy tuntap diff --git a/Documentation/networking/tcp_authopt.rst b/Documentation/networking/tcp_authopt.rst new file mode 100644 index 000000000000..484f66f41ad5 --- /dev/null +++ b/Documentation/networking/tcp_authopt.rst @@ -0,0 +1,44 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= +TCP Authentication Option +========================= + +The TCP Authentication option specified by RFC5925 replaces the TCP MD5 +Signature option. It similar in goals but not compatible in either wire formats +or ABI. + +Interface +========= + +Individual keys can be added to or removed from a TCP socket by using +TCP_AUTHOPT_KEY setsockopt and a ``struct tcp_authopt_key``. There is no +support for reading back keys and updates always replace the old key. These +structures represent "Master Key Tuples (MKTs)" as described by the RFC. + +Per-socket options can set or read using the TCP_AUTHOPT sockopt and a ``struct +tcp_authopt``. This is optional: doing setsockopt TCP_AUTHOPT_KEY is +sufficient to enable the feature. + +Configuration associated with TCP Authentication is indepedently attached to +each TCP socket. After listen and accept the newly returned socket gets an +independent copy of relevant settings from the listen socket. + +Key binding +----------- + +Keys can be bound to remote addresses in a way that is similar to TCP_MD5. + + * The full address must match (/32 or /128) + * Ports are ignored + * Address binding is optional, by default keys match all addresses + +RFC5925 requires that key ids do not overlap when tcp identifiers (addr/port) +overlap. This is not enforced by linux, configuring ambiguous keys will result +in packet drops and lost connections. + +ABI Reference +============= + +.. kernel-doc:: include/uapi/linux/tcp.h + :identifiers: tcp_authopt tcp_authopt_flag tcp_authopt_key tcp_authopt_key_flag tcp_authopt_alg

Add a python translation of the linux ABI for tcpao and test the behavior of TCP_AUTHOPT and TCP_AUTHOPT_KEY sockopts.

This includes several corner cases not normally covered by traffic tests.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- .../tcp_authopt/tcp_authopt_test/conftest.py | 71 +++++ .../tcp_authopt_test/linux_tcp_authopt.py | 266 ++++++++++++++++++ .../tcp_authopt/tcp_authopt_test/sockaddr.py | 122 ++++++++ .../tcp_authopt_test/test_sockopt.py | 203 +++++++++++++ 4 files changed, 662 insertions(+) create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/conftest.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_authopt.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/sockaddr.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sockopt.py

diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/conftest.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/conftest.py new file mode 100644 index 000000000000..a06ba848669d --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/conftest.py @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: GPL-2.0 +import logging +import os +from contextlib import ExitStack, nullcontext +from typing import ContextManager + +import pytest + +from .linux_tcp_authopt import enable_sysctl_tcp_authopt, has_tcp_authopt + +logger = logging.getLogger(__name__) + +skipif_missing_tcp_authopt = pytest.mark.skipif( + not has_tcp_authopt(), reason="Need CONFIG_TCP_AUTHOPT" +) + + +def get_effective_capabilities(): + for line in open("/proc/self/status", "r"): + if line.startswith("CapEff:"): + return int(line.split(":")[1], 16) + + +def has_effective_capability(bit) -> bool: + return get_effective_capabilities() & (1 << bit) != 0 + + +def can_capture() -> bool: + return has_effective_capability(13) + + +def raise_skip_no_netns(): + if not has_effective_capability(12): + pytest.skip("Need CAP_NET_ADMIN for network namespaces") + + +skipif_cant_capture = pytest.mark.skipif( + not can_capture(), reason="run as root to capture packets" +) + + +@pytest.fixture +def exit_stack(): + """Return a contextlib.ExitStack as a pytest fixture + + This reduces indentation making code more readable + """ + with ExitStack() as exit_stack: + yield exit_stack + + +def pytest_configure(): + # Silence messages regarding netns enter/exit: + logging.getLogger("nsenter").setLevel(logging.INFO) + if has_tcp_authopt(): + enable_sysctl_tcp_authopt() + + +def parametrize_product(**kw): + """Parametrize each key to each item in the value list""" + import itertools + + return pytest.mark.parametrize(",".join(kw.keys()), itertools.product(*kw.values())) + + +def raises_optional_exception(expected_exception, **kw) -> ContextManager: + """Like pytest.raises except accept expected_exception=None""" + if expected_exception is None: + return nullcontext() + else: + return pytest.raises(expected_exception, **kw) diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_authopt.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_authopt.py new file mode 100644 index 000000000000..b9dc9decda07 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_authopt.py @@ -0,0 +1,266 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Python wrapper around linux TCP_AUTHOPT ABI""" + +import errno +import logging +import socket +import struct +import typing +from dataclasses import dataclass +from enum import IntEnum, IntFlag + +from .sockaddr import ( + SockaddrConvertType, + sockaddr_base, + sockaddr_convert, + sockaddr_storage, + sockaddr_unpack, +) + +logger = logging.getLogger(__name__) + + +def BIT(x): + return 1 << x + + +TCP_AUTHOPT = 38 +TCP_AUTHOPT_KEY = 39 + +TCP_AUTHOPT_MAXKEYLEN = 80 + + +class TCP_AUTHOPT_FLAG(IntFlag): + REJECT_UNEXPECTED = BIT(2) + + +class TCP_AUTHOPT_KEY_FLAG(IntFlag): + DEL = BIT(0) + EXCLUDE_OPTS = BIT(1) + BIND_ADDR = BIT(2) + + +class TCP_AUTHOPT_ALG(IntEnum): + HMAC_SHA_1_96 = 1 + AES_128_CMAC_96 = 2 + + +@dataclass +class tcp_authopt: + """Like linux struct tcp_authopt""" + + flags: int = 0 + sizeof = 4 + + def pack(self) -> bytes: + return struct.pack( + "I", + self.flags, + ) + + def __bytes__(self): + return self.pack() + + @classmethod + def unpack(cls, b: bytes): + tup = struct.unpack("I", b) + return cls(*tup) + + +def set_tcp_authopt(sock, opt: tcp_authopt): + return sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT, bytes(opt)) + + +def get_tcp_authopt(sock: socket.socket) -> tcp_authopt: + b = sock.getsockopt(socket.SOL_TCP, TCP_AUTHOPT, tcp_authopt.sizeof) + return tcp_authopt.unpack(b) + + +class tcp_authopt_key: + """Like linux struct tcp_authopt_key + + :ivar auto_flags: If true(default) then set "binding" flags based on non-null values attributes. + """ + + KeyArgType = typing.Union[str, bytes] + AddrArgType = typing.Union[None, str, bytes, SockaddrConvertType] + + def __init__( + self, + flags: TCP_AUTHOPT_KEY_FLAG = TCP_AUTHOPT_KEY_FLAG(0), + send_id: int = 0, + recv_id: int = 0, + alg=TCP_AUTHOPT_ALG.HMAC_SHA_1_96, + key: KeyArgType = b"", + addr: AddrArgType = None, + auto_flags: bool = True, + include_options=None, + ): + self.flags = flags + self.send_id = send_id + self.recv_id = recv_id + self.alg = alg + self.key = key + self.addr = addr + self.auto_flags = auto_flags + if include_options is not None: + self.include_options = include_options + + def get_real_flags(self) -> TCP_AUTHOPT_KEY_FLAG: + result = self.flags + if self.auto_flags: + if self.addr is not None: + result |= TCP_AUTHOPT_KEY_FLAG.BIND_ADDR + else: + result &= ~TCP_AUTHOPT_KEY_FLAG.BIND_ADDR + return result + + def pack(self): + if len(self.key) > TCP_AUTHOPT_MAXKEYLEN: + raise ValueError(f"Max key length is {TCP_AUTHOPT_MAXKEYLEN}") + data = struct.pack( + "IBBBB80s", + self.get_real_flags(), + self.send_id, + self.recv_id, + self.alg, + len(self.key), + self.key, + ) + data += bytes(self.addrbuf.ljust(sockaddr_storage.sizeof, b"\x00")) + return data + + def __bytes__(self): + return self.pack() + + @property + def key(self) -> KeyArgType: + return self._key + + @key.setter + def key(self, val: KeyArgType) -> bytes: + if isinstance(val, str): + val = val.encode("utf-8") + if len(val) > TCP_AUTHOPT_MAXKEYLEN: + raise ValueError(f"Max key length is {TCP_AUTHOPT_MAXKEYLEN}") + self._key = val + return val + + @property + def addr(self): + if not self.addrbuf: + return None + else: + return sockaddr_unpack(bytes(self.addrbuf)) + + @addr.setter + def addr(self, val: AddrArgType): + if isinstance(val, bytes): + if len(val) > sockaddr_storage.sizeof: + raise ValueError(f"Must be up to {sockaddr_storage.sizeof}") + self.addrbuf = val + elif val is None: + self.addrbuf = b"" + elif isinstance(val, sockaddr_base): + self.addr = bytes(val) + else: + self.addr = sockaddr_convert(val) + return self.addr + + @property + def include_options(self) -> bool: + return not self.flags & TCP_AUTHOPT_KEY_FLAG.EXCLUDE_OPTS + + @include_options.setter + def include_options(self, value) -> bool: + if value: + self.flags &= ~TCP_AUTHOPT_KEY_FLAG.EXCLUDE_OPTS + else: + self.flags |= TCP_AUTHOPT_KEY_FLAG.EXCLUDE_OPTS + return value + + @property + def delete_flag(self) -> bool: + return bool(self.flags & TCP_AUTHOPT_KEY_FLAG.DEL) + + @delete_flag.setter + def delete_flag(self, value) -> bool: + if value: + self.flags |= TCP_AUTHOPT_KEY_FLAG.DEL + else: + self.flags &= ~TCP_AUTHOPT_KEY_FLAG.DEL + return value + + +def set_tcp_authopt_key(sock, keyopt: tcp_authopt_key): + return sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT_KEY, bytes(keyopt)) + + +def set_tcp_authopt_key_kwargs(sock, keyopt: tcp_authopt_key = None, **kw): + if keyopt is None: + keyopt = tcp_authopt_key() + for k, v in kw.items(): + setattr(keyopt, k, v) + return set_tcp_authopt_key(sock, keyopt) + + +def del_tcp_authopt_key(sock, key: tcp_authopt_key) -> bool: + """Try to delete an authopt key + + :return: True if a key was deleted, False if it was not present + """ + import copy + + key = copy.copy(key) + key.delete_flag = True + try: + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT_KEY, bytes(key)) + return True + except OSError as e: + if e.errno == errno.ENOENT: + return False + raise + + +def get_sysctl_tcp_authopt() -> typing.Optional[bool]: + from pathlib import Path + + path = Path("/proc/sys/net/ipv4/tcp_authopt") + if path.exists(): + return path.read_text().strip() != "0" + else: + return None + + +def enable_sysctl_tcp_authopt(): + from pathlib import Path + + path = Path("/proc/sys/net/ipv4/tcp_authopt") + # Do nothing if absent + if not path.exists(): + return + try: + if path.read_text().strip() == "0": + path.write_text("1") + except: + raise Exception("Failed to enable /proc/sys/net/ipv4/tcp_authopt") + + +def has_tcp_authopt() -> bool: + """Check is TCP_AUTHOPT is implemented by the OS + + Returns True if implemented but disabled by sysctl + Returns False if disabled at compile time + """ + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + try: + optbuf = bytes(4) + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT, optbuf) + return True + except OSError as e: + if e.errno == errno.ENOPROTOOPT: + return False + elif e.errno == errno.EPERM and get_sysctl_tcp_authopt() is False: + return True + else: + raise diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sockaddr.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sockaddr.py new file mode 100644 index 000000000000..3ad22c0b4015 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sockaddr.py @@ -0,0 +1,122 @@ +# SPDX-License-Identifier: GPL-2.0 +"""pack/unpack wrappers for sockaddr""" +import socket +import struct +import typing +from dataclasses import dataclass +from ipaddress import IPv4Address, IPv6Address, ip_address + + +class sockaddr_base: + def pack(self) -> bytes: + raise NotImplementedError() + + def __bytes__(self): + return self.pack() + + +class sockaddr_in(sockaddr_base): + port: int + addr: IPv4Address + sizeof = 8 + + def __init__(self, port=0, addr=None): + self.port = port + if addr is None: + addr = IPv4Address(0) + self.addr = IPv4Address(addr) + + def pack(self): + return struct.pack("HH4s", socket.AF_INET, self.port, self.addr.packed) + + @classmethod + def unpack(cls, buffer): + family, port, addr_packed = struct.unpack("HH4s", buffer[:8]) + if family != socket.AF_INET: + raise ValueError(f"Must be AF_INET not {family}") + return cls(port, addr_packed) + + +@dataclass +class sockaddr_in6(sockaddr_base): + """Like sockaddr_in6 but for python. Always contains scope_id""" + + port: int + addr: IPv6Address + flowinfo: int + scope_id: int + sizeof = 28 + + def __init__(self, port=0, addr=None, flowinfo=0, scope_id=0): + self.port = port + if addr is None: + addr = IPv6Address(0) + self.addr = IPv6Address(addr) + self.flowinfo = flowinfo + self.scope_id = scope_id + + def pack(self): + return struct.pack( + "HHI16sI", + socket.AF_INET6, + self.port, + self.flowinfo, + self.addr.packed, + self.scope_id, + ) + + @classmethod + def unpack(cls, buffer): + family, port, flowinfo, addr_packed, scope_id = struct.unpack( + "HHI16sI", buffer[:28] + ) + if family != socket.AF_INET6: + raise ValueError(f"Must be AF_INET6 not {family}") + return cls(port, addr_packed, flowinfo=flowinfo, scope_id=scope_id) + + +@dataclass +class sockaddr_storage(sockaddr_base): + family: int + data: bytes + sizeof = 128 + + def pack(self): + return struct.pack("H126s", self.family, self.data) + + @classmethod + def unpack(cls, buffer): + return cls(*struct.unpack("H126s", buffer)) + + +def sockaddr_unpack(buffer: bytes): + """Unpack based on family""" + family = struct.unpack("H", buffer[:2])[0] + if family == socket.AF_INET: + return sockaddr_in.unpack(buffer) + elif family == socket.AF_INET6: + return sockaddr_in6.unpack(buffer) + else: + return sockaddr_storage.unpack(buffer) + + +SockaddrConvertType = typing.Union[ + sockaddr_in, sockaddr_in6, sockaddr_storage, IPv4Address, IPv6Address, str +] + + +def sockaddr_convert(val: SockaddrConvertType) -> sockaddr_base: + """Try to convert address into some sort of sockaddr""" + if ( + isinstance(val, sockaddr_in) + or isinstance(val, sockaddr_in6) + or isinstance(val, sockaddr_storage) + ): + return val + if isinstance(val, IPv4Address): + return sockaddr_in(addr=val) + if isinstance(val, IPv6Address): + return sockaddr_in6(addr=val) + if isinstance(val, str): + return sockaddr_convert(ip_address(val)) + raise TypeError(f"Don't know how to convert {val!r} to sockaddr") diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sockopt.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sockopt.py new file mode 100644 index 000000000000..41ebde8b1b7c --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sockopt.py @@ -0,0 +1,203 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Test TCP_AUTHOPT sockopt API""" +import errno +import socket +import struct +from ipaddress import IPv4Address, IPv6Address + +import pytest + +from .conftest import skipif_missing_tcp_authopt +from .linux_tcp_authopt import ( + TCP_AUTHOPT, + TCP_AUTHOPT_ALG, + TCP_AUTHOPT_FLAG, + TCP_AUTHOPT_KEY, + TCP_AUTHOPT_KEY_FLAG, + del_tcp_authopt_key, + get_tcp_authopt, + set_tcp_authopt, + set_tcp_authopt_key, + tcp_authopt, + tcp_authopt_key, +) +from .sockaddr import sockaddr_in, sockaddr_in6, sockaddr_unpack + +pytestmark = skipif_missing_tcp_authopt + + +def test_authopt_key_pack_noaddr(): + b = bytes(tcp_authopt_key(key=b"a\x00b")) + assert b[7] == 3 + assert b[8:13] == b"a\x00b\x00\x00" + + +def test_authopt_key_pack_addr(): + b = bytes(tcp_authopt_key(key=b"a\x00b", addr="10.0.0.1")) + assert struct.unpack("H", b[88:90])[0] == socket.AF_INET + assert sockaddr_unpack(b[88:]).addr == IPv4Address("10.0.0.1") + + +def test_authopt_key_pack_addr6(): + b = bytes(tcp_authopt_key(key=b"abc", addr="fd00::1")) + assert struct.unpack("H", b[88:90])[0] == socket.AF_INET6 + assert sockaddr_unpack(b[88:]).addr == IPv6Address("fd00::1") + + +def test_tcp_authopt_key_del_without_active(exit_stack): + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + exit_stack.push(sock) + + # nothing happens: + key = tcp_authopt_key() + assert key.delete_flag is False + key.delete_flag = True + assert key.delete_flag is True + with pytest.raises(OSError) as e: + set_tcp_authopt_key(sock, key) + assert e.value.errno in [errno.EINVAL, errno.ENOENT] + + +def test_tcp_authopt_key_setdel(exit_stack): + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + exit_stack.push(sock) + set_tcp_authopt(sock, tcp_authopt()) + + # delete returns ENOENT + key = tcp_authopt_key() + key.delete_flag = True + with pytest.raises(OSError) as e: + set_tcp_authopt_key(sock, key) + assert e.value.errno == errno.ENOENT + + key = tcp_authopt_key(send_id=1, recv_id=2) + set_tcp_authopt_key(sock, key) + # First delete works fine: + key.delete_flag = True + set_tcp_authopt_key(sock, key) + # Duplicate delete returns ENOENT + with pytest.raises(OSError) as e: + set_tcp_authopt_key(sock, key) + assert e.value.errno == errno.ENOENT + + +def test_get_tcp_authopt(): + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + with pytest.raises(OSError) as e: + sock.getsockopt(socket.SOL_TCP, TCP_AUTHOPT, 4) + assert e.value.errno == errno.ENOENT + + +def test_set_get_tcp_authopt_flags(): + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + # No flags by default + set_tcp_authopt(sock, tcp_authopt()) + opt = get_tcp_authopt(sock) + assert opt.flags == 0 + + # simple flags are echoed + goodflag = TCP_AUTHOPT_FLAG.REJECT_UNEXPECTED + set_tcp_authopt(sock, tcp_authopt(flags=goodflag)) + opt = get_tcp_authopt(sock) + assert opt.flags == goodflag + + # attempting to set a badflag returns an error and has no effect + badflag = 1 << 27 + with pytest.raises(OSError) as e: + set_tcp_authopt(sock, tcp_authopt(flags=badflag)) + opt = get_tcp_authopt(sock) + assert opt.flags == goodflag + + +def test_set_ipv6_key_on_ipv4(): + """Binding a key to an ipv6 address on an ipv4 socket makes no sense""" + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + key = tcp_authopt_key("abc") + key.flags = TCP_AUTHOPT_KEY_FLAG.BIND_ADDR + key.addr = IPv6Address("::1234") + with pytest.raises(OSError): + set_tcp_authopt_key(sock, key) + + +def test_set_ipv4_key_on_ipv6(): + """This could be implemented for ipv6-mapped-ipv4 but it is not + + TCP_MD5SIG has a similar limitation + """ + with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as sock: + key = tcp_authopt_key("abc") + key.flags = TCP_AUTHOPT_KEY_FLAG.BIND_ADDR + key.addr = IPv4Address("1.2.3.4") + with pytest.raises(OSError): + set_tcp_authopt_key(sock, key) + + +def test_authopt_key_badflags(): + """Don't pretend to handle unknown flags""" + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + with pytest.raises(OSError): + set_tcp_authopt_key(sock, tcp_authopt_key(flags=0xABCDEF)) + + +def test_authopt_key_longer_bad(): + """Test that pass a longer sockopt with unknown data fails + + Old kernels won't pretend to handle features they don't know about + """ + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + key = tcp_authopt_key(alg=TCP_AUTHOPT_ALG.HMAC_SHA_1_96, key="aaa") + optbuf = bytes(key) + optbuf = optbuf.ljust(len(optbuf) + 256, b"\x5a") + with pytest.raises(OSError): + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT_KEY, optbuf) + + +def test_authopt_key_longer_zeros(): + """Test that passing a longer sockopt padded with zeros works + + This ensures applications using a larger struct tcp_authopt_key won't have + to pass a shorter optlen on old kernels. + """ + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + key = tcp_authopt_key(alg=TCP_AUTHOPT_ALG.HMAC_SHA_1_96, key="aaa") + optbuf = bytes(key) + optbuf = optbuf.ljust(len(optbuf) + 256, b"\x00") + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT_KEY, optbuf) + # the key was added and can be deleted normally + assert del_tcp_authopt_key(sock, key) == True + assert del_tcp_authopt_key(sock, key) == False + + +def test_authopt_longer_baddata(): + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + opt = tcp_authopt() + optbuf = bytes(opt) + optbuf = optbuf.ljust(len(optbuf) + 256, b"\x5a") + with pytest.raises(OSError): + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT, optbuf) + + +def test_authopt_longer_zeros(): + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + opt = tcp_authopt() + optbuf = bytes(opt) + optbuf = optbuf.ljust(len(optbuf) + 256, b"\x00") + sock.setsockopt(socket.SOL_TCP, TCP_AUTHOPT, optbuf) + + +def test_authopt_setdel_addrbind(): + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + key = tcp_authopt_key(addr="1.1.1.1", recv_id=1, send_id=1) + key2 = tcp_authopt_key(addr="1.1.1.2", recv_id=1, send_id=1) + set_tcp_authopt_key(sock, key) + assert del_tcp_authopt_key(sock, key2) == False + assert del_tcp_authopt_key(sock, key) == True + assert del_tcp_authopt_key(sock, key) == False + + +def test_authopt_include_options(): + key = tcp_authopt_key() + assert key.include_options + key.include_options = False + assert key.flags & TCP_AUTHOPT_KEY_FLAG.EXCLUDE_OPTS + assert not key.include_options

Computing tcp authopt packet signatures is a two step process:

* traffic key is computed based on tcp 4-tuple, initial sequence numbers and the secret key. * packet mac is computed based on traffic key and content of individual packets.

The traffic key could be cached for established sockets but it is not.

A single code path exists for ipv4/ipv6 and input/output. This keeps the code short but slightly slower due to lots of conditionals.

On output we read remote IP address from socket members on output, we can't use skb network header because it's computed after TCP options.

On input we read remote IP address from skb network headers, we can't use socket binding members because those are not available for SYN.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- net/ipv4/tcp_authopt.c | 510 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 510 insertions(+)

diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index 5455a9ecfe6b..1fd98d67ec10 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -425,5 +425,515 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen) memcpy(&key_info->addr, &opt.addr, sizeof(key_info->addr)); hlist_add_head_rcu(&key_info->node, &info->head);

return 0; } + +static int tcp_authopt_get_isn(struct sock *sk, + struct sk_buff *skb, + int input, + __be32 *sisn, + __be32 *disn) +{ + struct tcp_authopt_info *authopt_info; + struct tcphdr *th = tcp_hdr(skb); + + /* special cases for SYN and SYN/ACK */ + if (th->syn && !th->ack) { + *sisn = th->seq; + *disn = 0; + return 0; + } + if (th->syn && th->ack) { + *sisn = th->seq; + *disn = htonl(ntohl(th->ack_seq) - 1); + return 0; + } + + /* Fetching authopt_info like this should be safe because authopt_info + * is never released intil the socket is being closed + * + * tcp_timewait_sock is handled but not tcp_request_sock. + * for the synack case sk should be the listen socket. + */ + rcu_read_lock(); + if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV)) { + /* should never happen, sk should be the listen socket */ + authopt_info = NULL; + WARN_ONCE(1, "TCP-AO can't sign with request sock\n"); + return -EINVAL; + } else if (sk->sk_state == TCP_LISTEN) { + /* Signature computation for non-syn packet on a listen + * socket is not possible because we lack the initial + * sequence numbers. + * + * Input segments that are not matched by any request, + * established or timewait socket will get here. These + * are not normally sent by peers. + * + * Their signature might be valid but we don't have + * enough state to determine that. TCP-MD5 can attempt + * to validate and reply with a signed RST because it + * doesn't care about ISNs. + * + * Reporting an error from signature code causes the + * packet to be discarded which is good. + */ + if (input) { + /* Assume this is an ACK to a SYN/ACK + * This will incorrectly report "failed + * signature" for segments without a connection. + */ + *sisn = htonl(ntohl(th->seq) - 1); + *disn = htonl(ntohl(th->ack_seq) - 1); + rcu_read_unlock(); + return 0; + } + /* This would be an internal bug. */ + authopt_info = NULL; + WARN_ONCE(1, "TCP-AO can't sign non-syn from TCP_LISTEN sock\n"); + return -EINVAL; + } else if (sk->sk_state == TCP_TIME_WAIT) { + authopt_info = tcp_twsk(sk)->tw_authopt_info; + } else { + authopt_info = rcu_dereference(tcp_sk(sk)->authopt_info); + } + if (!authopt_info) { + rcu_read_unlock(); + return -EINVAL; + } + /* Initial sequence numbers for ESTABLISHED connections from info */ + if (input) { + *sisn = htonl(authopt_info->dst_isn); + *disn = htonl(authopt_info->src_isn); + } else { + *sisn = htonl(authopt_info->src_isn); + *disn = htonl(authopt_info->dst_isn); + } + rcu_read_unlock(); + return 0; +} + +/* feed traffic key into shash */ +static int tcp_authopt_shash_traffic_key(struct shash_desc *desc, + struct sock *sk, + struct sk_buff *skb, + bool input, + bool ipv6) +{ + struct tcphdr *th = tcp_hdr(skb); + int err; + __be32 sisn, disn; + __be16 digestbits = htons(crypto_shash_digestsize(desc->tfm) * 8); + + // RFC5926 section 3.1.1.1 + err = crypto_shash_update(desc, "\x01TCP-AO", 7); + if (err) + return err; + + /* Addresses from packet on input and from sk_common on output + * This is because on output MAC is computed before prepending IP header + */ + if (input) { + if (ipv6) + err = crypto_shash_update(desc, (u8 *)&ipv6_hdr(skb)->saddr, 32); + else + err = crypto_shash_update(desc, (u8 *)&ip_hdr(skb)->saddr, 8); + if (err) + return err; + } else { + if (ipv6) { + err = crypto_shash_update(desc, (u8 *)&sk->sk_v6_rcv_saddr, 16); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)&sk->sk_v6_daddr, 16); + if (err) + return err; + } else { + err = crypto_shash_update(desc, (u8 *)&sk->sk_rcv_saddr, 4); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)&sk->sk_daddr, 4); + if (err) + return err; + } + } + + /* TCP ports from header */ + err = crypto_shash_update(desc, (u8 *)&th->source, 4); + if (err) + return err; + err = tcp_authopt_get_isn(sk, skb, input, &sisn, &disn); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)&sisn, 4); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)&disn, 4); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)&digestbits, 2); + if (err) + return err; + + return 0; +} + +/* Convert a variable-length key to a 16-byte fixed-length key for AES-CMAC + * This is described in RFC5926 section 3.1.1.2 + */ +static int aes_setkey_derived(struct crypto_shash *tfm, u8 *key, size_t keylen) +{ + static const u8 zeros[16] = {0}; + u8 derived_key[16]; + int err; + + if (WARN_ON_ONCE(crypto_shash_digestsize(tfm) != 16)) + return -EINVAL; + err = crypto_shash_setkey(tfm, zeros, sizeof(zeros)); + if (err) + return err; + err = crypto_shash_tfm_digest(tfm, key, keylen, derived_key); + if (err) + return err; + return crypto_shash_setkey(tfm, derived_key, sizeof(derived_key)); +} + +static int tcp_authopt_setkey(struct crypto_shash *tfm, struct tcp_authopt_key_info *key) +{ + if (key->alg_id == TCP_AUTHOPT_ALG_AES_128_CMAC_96 && key->keylen != 16) + return aes_setkey_derived(tfm, key->key, key->keylen); + else + return crypto_shash_setkey(tfm, key->key, key->keylen); +} + +static int tcp_authopt_get_traffic_key(struct sock *sk, + struct sk_buff *skb, + struct tcp_authopt_key_info *key, + bool input, + bool ipv6, + u8 *traffic_key) +{ + SHASH_DESC_ON_STACK(desc, kdf_tfm); + struct crypto_shash *kdf_tfm; + int err; + + kdf_tfm = tcp_authopt_get_kdf_shash(key); + if (IS_ERR(kdf_tfm)) + return PTR_ERR(kdf_tfm); + + err = tcp_authopt_setkey(kdf_tfm, key); + if (err) + goto out; + + desc->tfm = kdf_tfm; + err = crypto_shash_init(desc); + if (err) + goto out; + + err = tcp_authopt_shash_traffic_key(desc, sk, skb, input, ipv6); + if (err) + goto out; + + err = crypto_shash_final(desc, traffic_key); + if (err) + goto out; + +out: + tcp_authopt_put_kdf_shash(key, kdf_tfm); + return err; +} + +static int crypto_shash_update_zero(struct shash_desc *desc, int len) +{ + u8 zero = 0; + int i, err; + + for (i = 0; i < len; ++i) { + err = crypto_shash_update(desc, &zero, 1); + if (err) + return err; + } + + return 0; +} + +static int tcp_authopt_hash_tcp4_pseudoheader(struct shash_desc *desc, + __be32 saddr, + __be32 daddr, + int nbytes) +{ + struct tcp4_pseudohdr phdr = { + .saddr = saddr, + .daddr = daddr, + .pad = 0, + .protocol = IPPROTO_TCP, + .len = htons(nbytes) + }; + return crypto_shash_update(desc, (u8 *)&phdr, sizeof(phdr)); +} + +static int tcp_authopt_hash_tcp6_pseudoheader(struct shash_desc *desc, + struct in6_addr *saddr, + struct in6_addr *daddr, + u32 plen) +{ + int err; + __be32 buf[2]; + + buf[0] = htonl(plen); + buf[1] = htonl(IPPROTO_TCP); + + err = crypto_shash_update(desc, (u8 *)saddr, sizeof(*saddr)); + if (err) + return err; + err = crypto_shash_update(desc, (u8 *)daddr, sizeof(*daddr)); + if (err) + return err; + return crypto_shash_update(desc, (u8 *)&buf, sizeof(buf)); +} + +/* TCP authopt as found in header */ +struct tcphdr_authopt { + u8 num; + u8 len; + u8 keyid; + u8 rnextkeyid; + u8 mac[0]; +}; + +/* Find TCP_AUTHOPT in header. + * + * Returns pointer to TCP_AUTHOPT or NULL if not found. + */ +static u8 *tcp_authopt_find_option(struct tcphdr *th) +{ + int length = (th->doff << 2) - sizeof(*th); + u8 *ptr = (u8 *)(th + 1); + + while (length >= 2) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return NULL; + case TCPOPT_NOP: + length--; + continue; + default: + if (length < 2) + return NULL; + opsize = *ptr++; + if (opsize < 2) + return NULL; + if (opsize > length) + return NULL; + if (opcode == TCPOPT_AUTHOPT) + return ptr - 2; + } + ptr += opsize - 2; + length -= opsize; + } + return NULL; +} + +/** Hash tcphdr options. + * If include_options is false then only the TCPOPT_AUTHOPT option itself is hashed + * Maybe we could skip option parsing by assuming the AUTHOPT header is at hash_location-4? + */ +static int tcp_authopt_hash_opts(struct shash_desc *desc, + struct tcphdr *th, + bool include_options) +{ + int err; + /* start of options */ + u8 *tcp_opts = (u8 *)(th + 1); + /* end of options */ + u8 *tcp_data = ((u8 *)th) + th->doff * 4; + /* pointer to TCPOPT_AUTHOPT */ + u8 *authopt_ptr = tcp_authopt_find_option(th); + u8 authopt_len; + + if (!authopt_ptr) + return -EINVAL; + authopt_len = *(authopt_ptr + 1); + + if (include_options) { + err = crypto_shash_update(desc, tcp_opts, authopt_ptr - tcp_opts + 4); + if (err) + return err; + err = crypto_shash_update_zero(desc, authopt_len - 4); + if (err) + return err; + err = crypto_shash_update(desc, + authopt_ptr + authopt_len, + tcp_data - (authopt_ptr + authopt_len)); + if (err) + return err; + } else { + err = crypto_shash_update(desc, authopt_ptr, 4); + if (err) + return err; + err = crypto_shash_update_zero(desc, authopt_len - 4); + if (err) + return err; + } + + return 0; +} + +static int skb_shash_frags(struct shash_desc *desc, + struct sk_buff *skb) +{ + struct sk_buff *frag_iter; + int err, i; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + u32 p_off, p_len, copied; + struct page *p; + u8 *vaddr; + + skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), + p, p_off, p_len, copied) { + vaddr = kmap_atomic(p); + err = crypto_shash_update(desc, vaddr + p_off, p_len); + kunmap_atomic(vaddr); + if (err) + return err; + } + } + + skb_walk_frags(skb, frag_iter) { + err = skb_shash_frags(desc, frag_iter); + if (err) + return err; + } + + return 0; +} + +static int tcp_authopt_hash_packet(struct crypto_shash *tfm, + struct sock *sk, + struct sk_buff *skb, + bool input, + bool ipv6, + bool include_options, + u8 *macbuf) +{ + struct tcphdr *th = tcp_hdr(skb); + SHASH_DESC_ON_STACK(desc, tfm); + int err; + + /* NOTE: SNE unimplemented */ + __be32 sne = 0; + + desc->tfm = tfm; + err = crypto_shash_init(desc); + if (err) + return err; + + err = crypto_shash_update(desc, (u8 *)&sne, 4); + if (err) + return err; + + if (ipv6) { + struct in6_addr *saddr; + struct in6_addr *daddr; + + if (input) { + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + } else { + saddr = &sk->sk_v6_rcv_saddr; + daddr = &sk->sk_v6_daddr; + } + err = tcp_authopt_hash_tcp6_pseudoheader(desc, saddr, daddr, skb->len); + if (err) + return err; + } else { + __be32 saddr; + __be32 daddr; + + if (input) { + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + } else { + saddr = sk->sk_rcv_saddr; + daddr = sk->sk_daddr; + } + err = tcp_authopt_hash_tcp4_pseudoheader(desc, saddr, daddr, skb->len); + if (err) + return err; + } + + // TCP header with checksum set to zero + { + struct tcphdr hashed_th = *th; + + hashed_th.check = 0; + err = crypto_shash_update(desc, (u8 *)&hashed_th, sizeof(hashed_th)); + if (err) + return err; + } + + // TCP options + err = tcp_authopt_hash_opts(desc, th, include_options); + if (err) + return err; + + // Rest of SKB->data + err = crypto_shash_update(desc, (u8 *)th + th->doff * 4, skb_headlen(skb) - th->doff * 4); + if (err) + return err; + + err = skb_shash_frags(desc, skb); + if (err) + return err; + + return crypto_shash_final(desc, macbuf); +} + +/* __tcp_authopt_calc_mac - Compute packet MAC using key + * + * The macbuf output buffer must be large enough to fit the digestsize of the + * underlying transform before truncation. + * This means TCP_AUTHOPT_MAXMACBUF, not TCP_AUTHOPT_MACLEN + */ +static int __tcp_authopt_calc_mac(struct sock *sk, + struct sk_buff *skb, + struct tcp_authopt_key_info *key, + bool input, + char *macbuf) +{ + struct crypto_shash *mac_tfm; + u8 traffic_key[TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN]; + int err; + bool ipv6 = (sk->sk_family != AF_INET); + + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) + return -EINVAL; + + err = tcp_authopt_get_traffic_key(sk, skb, key, input, ipv6, traffic_key); + if (err) + return err; + + mac_tfm = tcp_authopt_get_mac_shash(key); + if (IS_ERR(mac_tfm)) + return PTR_ERR(mac_tfm); + err = crypto_shash_setkey(mac_tfm, traffic_key, key->alg->traffic_key_len); + if (err) + goto out; + + err = tcp_authopt_hash_packet(mac_tfm, + sk, + skb, + input, + ipv6, + !(key->flags & TCP_AUTHOPT_KEY_EXCLUDE_OPTS), + macbuf); + +out: + tcp_authopt_put_mac_shash(key, mac_tfm); + return err; +}

The tcp_authopt features exposes a minimal interface to the rest of the TCP stack. Only a few functions are exposed and if the feature is disabled they return neutral values, avoiding ifdefs in the rest of the code.

Add calls into tcp authopt from send, receive and accept code.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- include/net/tcp_authopt.h | 99 +++++++++++++ include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_authopt.c | 288 ++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 17 +++ net/ipv4/tcp_ipv4.c | 20 ++- net/ipv4/tcp_minisocks.c | 12 ++ net/ipv4/tcp_output.c | 85 ++++++++++- net/ipv6/tcp_ipv6.c | 21 ++- 9 files changed, 538 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h index 5217b6c7c900..8bb76128ed11 100644 --- a/include/net/tcp_authopt.h +++ b/include/net/tcp_authopt.h @@ -65,28 +65,127 @@ struct tcp_authopt_info { /** @dst_isn: Remote Initial Sequence Number */ u32 dst_isn; };

#ifdef CONFIG_TCP_AUTHOPT +DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed); + +void tcp_authopt_free(struct sock *sk, struct tcp_authopt_info *info); void tcp_authopt_clear(struct sock *sk); int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen); int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key); int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen); +struct tcp_authopt_key_info *__tcp_authopt_select_key( + const struct sock *sk, + struct tcp_authopt_info *info, + const struct sock *addr_sk, + u8 *rnextkeyid); +static inline struct tcp_authopt_key_info *tcp_authopt_select_key( + const struct sock *sk, + const struct sock *addr_sk, + struct tcp_authopt_info **info, + u8 *rnextkeyid) +{ + if (static_branch_unlikely(&tcp_authopt_needed)) { + *info = rcu_dereference(tcp_sk(sk)->authopt_info); + + if (*info) + return __tcp_authopt_select_key(sk, *info, addr_sk, rnextkeyid); + } + return NULL; +} +int tcp_authopt_hash( + char *hash_location, + struct tcp_authopt_key_info *key, + struct tcp_authopt_info *info, + struct sock *sk, struct sk_buff *skb); +int __tcp_authopt_openreq(struct sock *newsk, const struct sock *oldsk, struct request_sock *req); +static inline int tcp_authopt_openreq( + struct sock *newsk, + const struct sock *oldsk, + struct request_sock *req) +{ + if (!rcu_dereference(tcp_sk(oldsk)->authopt_info)) + return 0; + else + return __tcp_authopt_openreq(newsk, oldsk, req); +} +static inline void tcp_authopt_time_wait( + struct tcp_timewait_sock *tcptw, + struct tcp_sock *tp) +{ + if (static_branch_unlikely(&tcp_authopt_needed)) { + /* Transfer ownership of authopt_info to the twsk + * This requires no other users of the origin sock. + */ + sock_owned_by_me((struct sock *)tp); + tcptw->tw_authopt_info = tp->authopt_info; + tp->authopt_info = NULL; + } else { + tcptw->tw_authopt_info = NULL; + } +} +int __tcp_authopt_inbound_check( + struct sock *sk, + struct sk_buff *skb, + struct tcp_authopt_info *info); +/** tcp_authopt_inbound_check - check for valid TCP-AO signature. + * + * Return negative ERRNO on error, 0 if not present and 1 if present and valid + * If both TCP-AO and MD5 signatures are found this is reported as an error. + */ +static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb) +{ + if (static_branch_unlikely(&tcp_authopt_needed)) { + struct tcp_authopt_info *info = rcu_dereference(tcp_sk(sk)->authopt_info); + + if (info) + return __tcp_authopt_inbound_check(sk, skb, info); + } + + return 0; +} #else static inline int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } static inline int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key) { return -ENOPROTOOPT; } +static inline void tcp_authopt_free(struct sock *sk, struct tcp_authopt_info *info) +{ +} static inline void tcp_authopt_clear(struct sock *sk) { } static inline int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } +static inline int tcp_authopt_hash( + char *hash_location, + struct tcp_authopt_key_info *key, + struct tcp_authopt_key *info, + struct sock *sk, struct sk_buff *skb) +{ + return -EINVAL; +} +static inline int tcp_authopt_openreq(struct sock *newsk, + const struct sock *oldsk, + struct request_sock *req) +{ + return 0; +} +static inline void tcp_authopt_time_wait( + struct tcp_timewait_sock *tcptw, + struct tcp_sock *tp) +{ +} +static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} #endif

#endif /* _LINUX_TCP_AUTHOPT_H */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 904909d020e2..1d96030889a1 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -290,10 +290,11 @@ enum LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ + LINUX_MIB_TCPAUTHOPTFAILURE, /* TCPAuthOptFailure */ __LINUX_MIB_MAX };

/* linux Xfrm mib definitions */ enum diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f30273afb539..70f7a8a47045 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -295,10 +295,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS), SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPAuthOptFailure", LINUX_MIB_TCPAUTHOPTFAILURE), SNMP_MIB_SENTINEL };

static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals, unsigned short *type, int count) diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index 1fd98d67ec10..5e80e5e5e36e 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -3,10 +3,14 @@ #include <linux/kernel.h> #include <net/tcp.h> #include <net/tcp_authopt.h> #include <crypto/hash.h>

+/* This is enabled when first struct tcp_authopt_info is allocated and never released */ +DEFINE_STATIC_KEY_FALSE(tcp_authopt_needed); +EXPORT_SYMBOL(tcp_authopt_needed); + /* All current algorithms have a mac length of 12 but crypto API digestsize can be larger */ #define TCP_AUTHOPT_MAXMACBUF 20 #define TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN 20 #define TCP_AUTHOPT_MACLEN 12

@@ -190,10 +194,55 @@ static bool tcp_authopt_key_match_exact(struct tcp_authopt_key_info *info, return false;

return true; }

+static bool tcp_authopt_key_match_skb_addr(struct tcp_authopt_key_info *key, + struct sk_buff *skb) +{ + u16 keyaf = key->addr.ss_family; + struct iphdr *iph = (struct iphdr *)skb_network_header(skb); + + if (keyaf == AF_INET && iph->version == 4) { + struct sockaddr_in *key_addr = (struct sockaddr_in *)&key->addr; + + return iph->saddr == key_addr->sin_addr.s_addr; + } else if (keyaf == AF_INET6 && iph->version == 6) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb); + struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr; + + return ipv6_addr_equal(&ip6h->saddr, &key_addr->sin6_addr); + } + + /* This actually happens with ipv6-mapped-ipv4-addresses + * IPv6 listen sockets will be asked to validate ipv4 packets. + */ + return false; +} + +static bool tcp_authopt_key_match_sk_addr(struct tcp_authopt_key_info *key, + const struct sock *addr_sk) +{ + u16 keyaf = key->addr.ss_family; + + /* This probably can't happen even with ipv4-mapped-ipv6 */ + if (keyaf != addr_sk->sk_family) + return false; + + if (keyaf == AF_INET) { + struct sockaddr_in *key_addr = (struct sockaddr_in *)&key->addr; + + return addr_sk->sk_daddr == key_addr->sin_addr.s_addr; + } else if (keyaf == AF_INET6) { + struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr; + + return ipv6_addr_equal(&addr_sk->sk_v6_daddr, &key_addr->sin6_addr); + } + + return false; +} + static struct tcp_authopt_key_info *tcp_authopt_key_lookup_exact(const struct sock *sk, struct tcp_authopt_info *info, struct tcp_authopt_key *ukey) { struct tcp_authopt_key_info *key_info; @@ -203,10 +252,50 @@ static struct tcp_authopt_key_info *tcp_authopt_key_lookup_exact(const struct so return key_info;

return NULL; }

+static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct tcp_authopt_info *info, + const struct sock *addr_sk, + int send_id) +{ + struct tcp_authopt_key_info *result = NULL; + struct tcp_authopt_key_info *key; + + hlist_for_each_entry_rcu(key, &info->head, node, 0) { + if (send_id >= 0 && key->send_id != send_id) + continue; + if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND) + if (!tcp_authopt_key_match_sk_addr(key, addr_sk)) + continue; + if (result && net_ratelimit()) + pr_warn("ambiguous tcp authentication keys configured for send\n"); + result = key; + } + + return result; +} + +/** + * __tcp_authopt_select_key - select key for sending + * + * @sk: socket + * @info: socket's tcp_authopt_info + * @addr_sk: socket used for address lookup. Same as sk except for synack case + * @rnextkeyid: value of rnextkeyid caller should write in packet + * + * Result is protected by RCU and can't be stored, it may only be passed to + * tcp_authopt_hash and only under a single rcu_read_lock. + */ +struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk, + struct tcp_authopt_info *info, + const struct sock *addr_sk, + u8 *rnextkeyid) +{ + return tcp_authopt_lookup_send(info, addr_sk, -1); +} + static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_authopt_info *info;

@@ -216,10 +305,12 @@ static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk

info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM);

+ /* Never released: */ + static_branch_inc(&tcp_authopt_needed); sk_nocaps_add(sk, NETIF_F_GSO_MASK); INIT_HLIST_HEAD(&info->head); rcu_assign_pointer(tp->authopt_info, info);

return info; @@ -508,10 +599,65 @@ static int tcp_authopt_get_isn(struct sock *sk, } else { *sisn = htonl(authopt_info->src_isn); *disn = htonl(authopt_info->dst_isn); } rcu_read_unlock(); + + return 0; +} + +static int tcp_authopt_clone_keys(struct sock *newsk, + const struct sock *oldsk, + struct tcp_authopt_info *new_info, + struct tcp_authopt_info *old_info) +{ + struct tcp_authopt_key_info *old_key; + struct tcp_authopt_key_info *new_key; + + hlist_for_each_entry_rcu(old_key, &old_info->head, node, lockdep_sock_is_held(oldsk)) { + new_key = sock_kmalloc(newsk, sizeof(*new_key), GFP_ATOMIC); + if (!new_key) + return -ENOMEM; + memcpy(new_key, old_key, sizeof(*new_key)); + hlist_add_head_rcu(&new_key->node, &new_info->head); + } + + return 0; +} + +/** Called to create accepted sockets. + * + * Need to copy authopt info from listen socket. + */ +int __tcp_authopt_openreq(struct sock *newsk, const struct sock *oldsk, struct request_sock *req) +{ + struct tcp_authopt_info *old_info; + struct tcp_authopt_info *new_info; + int err; + + old_info = rcu_dereference(tcp_sk(oldsk)->authopt_info); + if (!old_info) + return 0; + + /* Clear value copies from oldsk: */ + rcu_assign_pointer(tcp_sk(newsk)->authopt_info, NULL); + + new_info = kzalloc(sizeof(*new_info), GFP_ATOMIC); + if (!new_info) + return -ENOMEM; + + new_info->src_isn = tcp_rsk(req)->snt_isn; + new_info->dst_isn = tcp_rsk(req)->rcv_isn; + INIT_HLIST_HEAD(&new_info->head); + err = tcp_authopt_clone_keys(newsk, oldsk, new_info, old_info); + if (err) { + tcp_authopt_free(newsk, new_info); + return err; + } + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); + rcu_assign_pointer(tcp_sk(newsk)->authopt_info, new_info); + return 0; }

/* feed traffic key into shash */ static int tcp_authopt_shash_traffic_key(struct shash_desc *desc, @@ -814,10 +960,11 @@ static int skb_shash_frags(struct shash_desc *desc, }

static int tcp_authopt_hash_packet(struct crypto_shash *tfm, struct sock *sk, struct sk_buff *skb, + struct tcp_authopt_info *info, bool input, bool ipv6, bool include_options, u8 *macbuf) { @@ -901,10 +1048,11 @@ static int tcp_authopt_hash_packet(struct crypto_shash *tfm, * This means TCP_AUTHOPT_MAXMACBUF, not TCP_AUTHOPT_MACLEN */ static int __tcp_authopt_calc_mac(struct sock *sk, struct sk_buff *skb, struct tcp_authopt_key_info *key, + struct tcp_authopt_info *info, bool input, char *macbuf) { struct crypto_shash *mac_tfm; u8 traffic_key[TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN]; @@ -926,14 +1074,154 @@ static int __tcp_authopt_calc_mac(struct sock *sk, goto out;

err = tcp_authopt_hash_packet(mac_tfm, sk, skb, + info, input, ipv6, !(key->flags & TCP_AUTHOPT_KEY_EXCLUDE_OPTS), macbuf);

out: tcp_authopt_put_mac_shash(key, mac_tfm); return err; } + +/* tcp_authopt_hash - fill in the mac + * + * The key must come from tcp_authopt_select_key. + */ +int tcp_authopt_hash(char *hash_location, + struct tcp_authopt_key_info *key, + struct tcp_authopt_info *info, + struct sock *sk, + struct sk_buff *skb) +{ + /* MAC inside option is truncated to 12 bytes but crypto API needs output + * buffer to be large enough so we use a buffer on the stack. + */ + u8 macbuf[TCP_AUTHOPT_MAXMACBUF]; + int err; + + err = __tcp_authopt_calc_mac(sk, skb, key, info, false, macbuf); + if (err) + goto fail; + memcpy(hash_location, macbuf, TCP_AUTHOPT_MACLEN); + + return 0; + +fail: + /* If mac calculation fails and caller doesn't handle the error + * try to make it obvious inside the packet. + */ + memset(hash_location, 0, TCP_AUTHOPT_MACLEN); + return err; +} + +static struct tcp_authopt_key_info *tcp_authopt_lookup_recv(struct sock *sk, + struct sk_buff *skb, + struct tcp_authopt_info *info, + int recv_id) +{ + struct tcp_authopt_key_info *result = NULL; + struct tcp_authopt_key_info *key; + + /* multiple matches will cause occasional failures */ + hlist_for_each_entry_rcu(key, &info->head, node, 0) { + if (recv_id >= 0 && key->recv_id != recv_id) + continue; + if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND && + !tcp_authopt_key_match_skb_addr(key, skb)) + continue; + if (result && net_ratelimit()) + pr_warn("ambiguous tcp authentication keys configured for receive\n"); + result = key; + } + + return result; +} + +/* Show a rate-limited message for authentication fail */ +static void print_tcpao_notice(const char *msg, struct sk_buff *skb) +{ + struct iphdr *iph = (struct iphdr *)skb_network_header(skb); + struct tcphdr *th = (struct tcphdr *)skb_transport_header(skb); + + if (iph->version == 4) { + net_info_ratelimited("%s (%pI4, %d)->(%pI4, %d)\n", msg, + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest)); + } else if (iph->version == 6) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb); + + net_info_ratelimited("%s (%pI6, %d)->(%pI6, %d)\n", msg, + &ip6h->saddr, ntohs(th->source), + &ip6h->daddr, ntohs(th->dest)); + } else { + WARN_ONCE(1, "%s unknown IP version\n", msg); + } +} + +int __tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb, struct tcp_authopt_info *info) +{ + struct tcphdr *th = (struct tcphdr *)skb_transport_header(skb); + struct tcphdr_authopt *opt; + struct tcp_authopt_key_info *key; + u8 macbuf[TCP_AUTHOPT_MAXMACBUF]; + int err; + + opt = (struct tcphdr_authopt *)tcp_authopt_find_option(th); +#ifdef CONFIG_TCP_MD5SIG + /* RFC5925 2.2: An endpoint MUST NOT use TCP-AO for the same connection + * in which TCP MD5 is used. When both options appear, TCP MUST silently + * discard the segment. + */ + if (opt && tcp_parse_md5sig_option(th)) { + print_tcpao_notice("TCP AO and MD5 both present on same packet: discarded", skb); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); + return -EINVAL; + } +#endif + key = tcp_authopt_lookup_recv(sk, skb, info, opt ? opt->keyid : -1); + + /* nothing found or expected */ + if (!opt && !key) + return 0; + if (!opt && key) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); + print_tcpao_notice("TCP Authentication Missing", skb); + return -EINVAL; + } + if (opt && !key) { + /* RFC5925 Section 7.3: + * A TCP-AO implementation MUST allow for configuration of the behavior + * of segments with TCP-AO but that do not match an MKT. The initial + * default of this configuration SHOULD be to silently accept such + * connections. + */ + if (info->flags & TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); + print_tcpao_notice("TCP Authentication Unexpected: Rejected", skb); + return -EINVAL; + } + print_tcpao_notice("TCP Authentication Unexpected: Accepted", skb); + return 0; + } + + /* bad inbound key len */ + if (opt->len != TCPOLEN_AUTHOPT_OUTPUT) + return -EINVAL; + + err = __tcp_authopt_calc_mac(sk, skb, key, info, true, macbuf); + if (err) + return err; + + if (memcmp(macbuf, opt->mac, TCP_AUTHOPT_MACLEN)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); + print_tcpao_notice("TCP Authentication Failed", skb); + return -EINVAL; + } + + return 1; +} +EXPORT_SYMBOL(__tcp_authopt_inbound_check); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 246ab7b5e857..5dcde6e74bfc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -70,10 +70,11 @@ #include <linux/sysctl.h> #include <linux/kernel.h> #include <linux/prefetch.h> #include <net/dst.h> #include <net/tcp.h> +#include <net/tcp_authopt.h> #include <net/inet_common.h> #include <linux/ipsec.h> #include <asm/unaligned.h> #include <linux/errqueue.h> #include <trace/events/tcp.h> @@ -5984,18 +5985,34 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); }

+static void tcp_authopt_finish_connect(struct sock *sk, struct sk_buff *skb) +{ +#ifdef CONFIG_TCP_AUTHOPT + struct tcp_authopt_info *info; + + info = rcu_dereference_protected(tcp_sk(sk)->authopt_info, lockdep_sock_is_held(sk)); + if (!info) + return; + + info->src_isn = ntohl(tcp_hdr(skb)->ack_seq) - 1; + info->dst_isn = ntohl(tcp_hdr(skb)->seq); +#endif +} + void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk);

tcp_set_state(sk, TCP_ESTABLISHED); icsk->icsk_ack.lrcvtime = tcp_jiffies32;

+ tcp_authopt_finish_connect(sk, skb); + if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); sk_mark_napi_id(sk, skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c9f050fa0e8..da43567c3753 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1955,10 +1955,26 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; }

+static int tcp_v4_auth_inbound_check(struct sock *sk, + struct sk_buff *skb, + int dif, + int sdif) +{ + int aoret; + + aoret = tcp_authopt_inbound_check(sk, skb); + if (aoret < 0) + return aoret; + if (aoret > 0) + return 0; + + return tcp_v4_inbound_md5_hash(sk, skb, dif, sdif); +} + /* * From tcp_input.c */

int tcp_v4_rcv(struct sk_buff *skb) @@ -2012,11 +2028,11 @@ int tcp_v4_rcv(struct sk_buff *skb) struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk;

sk = req->rsk_listener; - if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { + if (unlikely(tcp_v4_auth_inbound_check(sk, skb, dif, sdif))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { @@ -2082,11 +2098,11 @@ int tcp_v4_rcv(struct sk_buff *skb) }

if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse;

- if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) + if (tcp_v4_auth_inbound_check(sk, skb, dif, sdif)) goto discard_and_relse;

nf_reset_ct(skb);

if (tcp_filter(sk, skb)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index cf913a66df17..d4828cf3d6d1 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -18,10 +18,11 @@ * Arnt Gulbrandsen, agulbra@nvg.unit.no * Jorge Cwik, jorge@laser.satlink.net */

#include <net/tcp.h> +#include <net/tcp_authopt.h> #include <net/xfrm.h> #include <net/busy_poll.h>

static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { @@ -300,10 +301,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); } } } while (0); #endif + tcp_authopt_time_wait(tcptw, tcp_sk(sk));

/* Get the TIME_WAIT timeout firing. */ if (timeo < rto) timeo = rto;

@@ -342,10 +344,19 @@ void tcp_twsk_destructor(struct sock *sk)

if (twsk->tw_md5_key) kfree_rcu(twsk->tw_md5_key, rcu); } #endif +#ifdef CONFIG_TCP_AUTHOPT + if (static_branch_unlikely(&tcp_authopt_needed)) { + struct tcp_timewait_sock *twsk = tcp_twsk(sk); + + /* twsk only contains sock_common so pass NULL as sk. */ + if (twsk->tw_authopt_info) + tcp_authopt_free(NULL, twsk->tw_authopt_info); + } +#endif } EXPORT_SYMBOL_GPL(tcp_twsk_destructor);

/* Warning : This function is called without sk_listener being locked. * Be sure to read socket fields once, as their value could change under us. @@ -532,10 +543,11 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ if (newtp->af_specific->md5_lookup(sk, newsk)) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif + tcp_authopt_openreq(newsk, sk, req); if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 96f16386f50e..1e5acc5a38cf 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -37,10 +37,11 @@

#define pr_fmt(fmt) "TCP: " fmt

#include <net/tcp.h> #include <net/mptcp.h> +#include <net/tcp_authopt.h>

#include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> @@ -410,10 +411,11 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)

#define OPTION_SACK_ADVERTISE BIT(0) #define OPTION_TS BIT(1) #define OPTION_MD5 BIT(2) #define OPTION_WSCALE BIT(3) +#define OPTION_AUTHOPT BIT(4) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10)

static void smc_options_write(__be32 *ptr, u16 *options) @@ -434,16 +436,22 @@ static void smc_options_write(__be32 *ptr, u16 *options) struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ - u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ +#ifdef CONFIG_TCP_AUTHOPT + u8 authopt_rnextkeyid; /* rnextkey */ +#endif __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ struct mptcp_out_options mptcp; +#ifdef CONFIG_TCP_AUTHOPT + struct tcp_authopt_info *authopt_info; + struct tcp_authopt_key_info *authopt_key; +#endif };

static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp, struct tcp_out_options *opts) { @@ -616,10 +624,25 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; }

+#ifdef CONFIG_TCP_AUTHOPT + if (unlikely(OPTION_AUTHOPT & options)) { + struct tcp_authopt_key_info *key = opts->authopt_key; + + WARN_ON(!key); + *ptr = htonl((TCPOPT_AUTHOPT << 24) | + (TCPOLEN_AUTHOPT_OUTPUT << 16) | + (key->send_id << 8) | + opts->authopt_rnextkeyid); + /* overload cookie hash location */ + opts->hash_location = (__u8 *)(ptr + 1); + ptr += TCPOLEN_AUTHOPT_OUTPUT / 4; + } +#endif + if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } @@ -751,10 +774,28 @@ static void mptcp_set_option_cond(const struct request_sock *req, } } } }

+static int tcp_authopt_init_options(const struct sock *sk, + const struct sock *addr_sk, + struct tcp_out_options *opts) +{ +#ifdef CONFIG_TCP_AUTHOPT + struct tcp_authopt_key_info *key; + + key = tcp_authopt_select_key(sk, addr_sk, &opts->authopt_info, &opts->authopt_rnextkeyid); + if (key) { + opts->options |= OPTION_AUTHOPT; + opts->authopt_key = key; + return TCPOLEN_AUTHOPT_OUTPUT; + } +#endif + + return 0; +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, @@ -763,12 +804,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req;

*md5 = NULL; + + remaining -= tcp_authopt_init_options(sk, sk, opts); #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && + !(opts->options & OPTION_AUTHOPT) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; @@ -847,12 +891,13 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE;

+ remaining -= tcp_authopt_init_options(sk, req_to_sk(req), opts); #ifdef CONFIG_TCP_MD5SIG - if (md5) { + if (md5 && !(opts->options & OPTION_AUTHOPT)) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED;

/* We can't fit any SACK blocks in a packet with MD5 + TS * options. There was discussion about disabling SACK @@ -918,13 +963,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb unsigned int size = 0; unsigned int eff_sacks;

opts->options = 0;

+ size += tcp_authopt_init_options(sk, sk, opts); *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && + !(opts->options & OPTION_AUTHOPT) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; @@ -1274,10 +1321,14 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,

inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts));

+#ifdef CONFIG_TCP_AUTHOPT + /* for tcp_authopt_init_options inside tcp_syn_options or tcp_established_options */ + rcu_read_lock(); +#endif if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); } else { tcp_options_size = tcp_established_options(sk, skb, &opts, &md5); @@ -1362,10 +1413,17 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, skb); } #endif +#ifdef CONFIG_TCP_AUTHOPT + if (opts.authopt_key) { + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + tcp_authopt_hash(opts.hash_location, opts.authopt_key, opts.authopt_info, sk, skb); + } + rcu_read_unlock(); +#endif

/* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);

INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, @@ -1830,12 +1888,21 @@ unsigned int tcp_current_mss(struct sock *sk) u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); }

+#ifdef CONFIG_TCP_AUTHOPT + /* Even if the result is not used rcu_read_lock is required when scanning for + * tcp authentication keys. Otherwise lockdep will complain. + */ + rcu_read_lock(); +#endif header_len = tcp_established_options(sk, NULL, &opts, &md5) + sizeof(struct tcphdr); +#ifdef CONFIG_TCP_AUTHOPT + rcu_read_unlock(); +#endif /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK * blocks etc) then our calculated header_len will be different, and * we have to adjust mss_now correspondingly */ if (header_len != tp->tcp_header_len) { @@ -3548,10 +3615,14 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, }

#ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); +#endif +#ifdef CONFIG_TCP_AUTHOPT + /* for tcp_authopt_init_options inside tcp_synack_options */ + rcu_read_lock(); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -3585,10 +3656,20 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, req_to_sk(req), skb); rcu_read_unlock(); #endif +#ifdef CONFIG_TCP_AUTHOPT + /* If signature fails we do nothing */ + if (opts.authopt_key) + tcp_authopt_hash(opts.hash_location, + opts.authopt_key, + opts.authopt_info, + req_to_sk(req), + skb); + rcu_read_unlock(); +#endif

bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts);

skb->skb_mstamp_ns = now; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2cc9b0e53ad1..96a29caf56c7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -40,10 +40,11 @@ #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h>

#include <net/tcp.h> +#include <net/tcp_authopt.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> @@ -1619,10 +1620,26 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; }

+static int tcp_v6_auth_inbound_check(struct sock *sk, + struct sk_buff *skb, + int dif, + int sdif) +{ + int aoret; + + aoret = tcp_authopt_inbound_check(sk, skb); + if (aoret < 0) + return aoret; + if (aoret > 0) + return 0; + + return tcp_v6_inbound_md5_hash(sk, skb, dif, sdif); +} + INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; @@ -1671,11 +1688,11 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk;

sk = req->rsk_listener; - if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) { + if (tcp_v6_auth_inbound_check(sk, skb, dif, sdif)) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { @@ -1738,11 +1755,11 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) }

if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse;

- if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) + if (tcp_v6_auth_inbound_check(sk, skb, dif, sdif)) goto discard_and_relse;

if (tcp_filter(sk, skb)) goto discard_and_relse; th = (const struct tcphdr *)skb->data;

Add a compute_sne function which finds the value of SNE for a certain SEQ given an already known "recent" SNE/SEQ. This is implemented using the standard tcp before/after macro and will work for SEQ values that are without 2^31 of the SEQ for which we know the SNE.

For updating we advance the value for rcv_sne at the same time as rcv_nxt and for snd_sne at the same time as snd_nxt. We could track other values (for example snd_una) but this is good enough and works very easily for timewait socket.

This implementation is different from RFC suggestions and doesn't require additional flags. It does pass tests from this draft: https://datatracker.ietf.org/doc/draft-touch-sne/

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- include/net/tcp_authopt.h | 36 ++++++++++++++++++ net/ipv4/tcp_authopt.c | 80 ++++++++++++++++++++++++++++++++++++++- net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_output.c | 1 + 4 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h index a505db1dd67b..7360bda20f97 100644 --- a/include/net/tcp_authopt.h +++ b/include/net/tcp_authopt.h @@ -62,10 +62,14 @@ struct tcp_authopt_info { u32 flags; /** @src_isn: Local Initial Sequence Number */ u32 src_isn; /** @dst_isn: Remote Initial Sequence Number */ u32 dst_isn; + /** @rcv_sne: Recv-side Sequence Number Extension tracking tcp_sock.rcv_nxt */ + u32 rcv_sne; + /** @snd_sne: Send-side Sequence Number Extension tracking tcp_sock.snd_nxt */ + u32 snd_sne; };

#ifdef CONFIG_TCP_AUTHOPT extern int sysctl_tcp_authopt; DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed); @@ -143,10 +147,36 @@ static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb return __tcp_authopt_inbound_check(sk, skb, info); }

return 0; } +void __tcp_authopt_update_rcv_sne(struct tcp_sock *tp, struct tcp_authopt_info *info, u32 seq); +static inline void tcp_authopt_update_rcv_sne(struct tcp_sock *tp, u32 seq) +{ + struct tcp_authopt_info *info; + + if (static_branch_unlikely(&tcp_authopt_needed)) { + rcu_read_lock(); + info = rcu_dereference(tp->authopt_info); + if (info) + __tcp_authopt_update_rcv_sne(tp, info, seq); + rcu_read_unlock(); + } +} +void __tcp_authopt_update_snd_sne(struct tcp_sock *tp, struct tcp_authopt_info *info, u32 seq); +static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq) +{ + struct tcp_authopt_info *info; + + if (static_branch_unlikely(&tcp_authopt_needed)) { + rcu_read_lock(); + info = rcu_dereference(tp->authopt_info); + if (info) + __tcp_authopt_update_snd_sne(tp, info, seq); + rcu_read_unlock(); + } +} #else static inline int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } @@ -185,8 +215,14 @@ static inline void tcp_authopt_time_wait( } static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb) { return 0; } +static inline void tcp_authopt_update_rcv_sne(struct tcp_sock *tp, u32 seq) +{ +} +static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq) +{ +} #endif

#endif /* _LINUX_TCP_AUTHOPT_H */ diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index 7c49dcce7d24..a48b741c83e4 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -968,10 +968,84 @@ static int skb_shash_frags(struct shash_desc *desc, }

return 0; }

+/* compute_sne - Calculate Sequence Number Extension + * + * Give old upper/lower 32bit values and a new lower 32bit value determine the + * new value of the upper 32 bit. The new sequence number can be 2^31 before or + * after prev_seq but TCP window scaling should limit this further. + * + * For correct accounting the stored SNE value should be only updated together + * with the SEQ. + */ +static u32 compute_sne(u32 sne, u32 prev_seq, u32 seq) +{ + if (before(seq, prev_seq)) { + if (seq > prev_seq) + --sne; + } else { + if (seq < prev_seq) + ++sne; + } + + return sne; +} + +/* Update rcv_sne, must be called immediately before rcv_nxt update */ +void __tcp_authopt_update_rcv_sne(struct tcp_sock *tp, + struct tcp_authopt_info *info, u32 seq) +{ + info->rcv_sne = compute_sne(info->rcv_sne, tp->rcv_nxt, seq); +} + +/* Update snd_sne, must be called immediately before snd_nxt update */ +void __tcp_authopt_update_snd_sne(struct tcp_sock *tp, + struct tcp_authopt_info *info, u32 seq) +{ + info->snd_sne = compute_sne(info->snd_sne, tp->snd_nxt, seq); +} + +/* Compute SNE for a specific packet (by seq). */ +static int compute_packet_sne(struct sock *sk, struct tcp_authopt_info *info, + u32 seq, bool input, __be32 *sne) +{ + u32 rcv_nxt, snd_nxt; + + // We can't use normal SNE computation before reaching TCP_ESTABLISHED + // For TCP_SYN_SENT the dst_isn field is initialized only after we + // validate the remote SYN/ACK + // For TCP_NEW_SYN_RECV there is no tcp_authopt_info at all + if (sk->sk_state == TCP_SYN_SENT || + sk->sk_state == TCP_NEW_SYN_RECV || + sk->sk_state == TCP_LISTEN) + return 0; + + if (sk->sk_state == TCP_TIME_WAIT) { + rcv_nxt = tcp_twsk(sk)->tw_rcv_nxt; + snd_nxt = tcp_twsk(sk)->tw_snd_nxt; + } else { + if (WARN_ONCE(!sk_fullsock(sk), + "unexpected minisock sk=%p state=%d", sk, + sk->sk_state)) + return -EINVAL; + rcv_nxt = tcp_sk(sk)->rcv_nxt; + snd_nxt = tcp_sk(sk)->snd_nxt; + } + + if (WARN_ONCE(!info, "unexpected missing info for sk=%p sk_state=%d", sk, sk->sk_state)) + return -EINVAL; + + if (input) + *sne = htonl(compute_sne(info->rcv_sne, rcv_nxt, seq)); + else + *sne = htonl(compute_sne(info->snd_sne, snd_nxt, seq)); + + return 0; +} + static int tcp_authopt_hash_packet(struct crypto_shash *tfm, struct sock *sk, struct sk_buff *skb, struct tcp_authopt_info *info, bool input, @@ -979,14 +1053,16 @@ static int tcp_authopt_hash_packet(struct crypto_shash *tfm, bool include_options, u8 *macbuf) { struct tcphdr *th = tcp_hdr(skb); SHASH_DESC_ON_STACK(desc, tfm); + __be32 sne = 0; int err;

- /* NOTE: SNE unimplemented */ - __be32 sne = 0; + err = compute_packet_sne(sk, info, ntohl(th->seq), input, &sne); + if (err) + return err;

desc->tfm = tfm; err = crypto_shash_init(desc); if (err) return err; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5dcde6e74bfc..0ac74e621b4e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3517,10 +3517,11 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt;

sock_owned_by_me((struct sock *)tp); + tcp_authopt_update_rcv_sne(tp, seq); tp->bytes_received += delta; WRITE_ONCE(tp->rcv_nxt, seq); }

/* Update our send window. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1e5acc5a38cf..ea53c24747b9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -67,10 +67,11 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out;

+ tcp_authopt_update_snd_sne(tp, TCP_SKB_CB(skb)->end_seq); WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);

__skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);

This is required because tcp ipv4 sometimes sends replies without allocating a full skb that can be signed by tcp authopt.

Handle this with additional code in tcp authopt.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- include/net/tcp_authopt.h | 7 ++ net/ipv4/tcp_authopt.c | 147 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 154 insertions(+)

diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h index 7360bda20f97..ae7d6a1eab8d 100644 --- a/include/net/tcp_authopt.h +++ b/include/net/tcp_authopt.h @@ -101,10 +101,17 @@ static inline struct tcp_authopt_key_info *tcp_authopt_select_key( int tcp_authopt_hash( char *hash_location, struct tcp_authopt_key_info *key, struct tcp_authopt_info *info, struct sock *sk, struct sk_buff *skb); +int tcp_v4_authopt_hash_reply( + char *hash_location, + struct tcp_authopt_info *info, + struct tcp_authopt_key_info *key, + __be32 saddr, + __be32 daddr, + struct tcphdr *th); int __tcp_authopt_openreq(struct sock *newsk, const struct sock *oldsk, struct request_sock *req); static inline int tcp_authopt_openreq( struct sock *newsk, const struct sock *oldsk, struct request_sock *req) diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index c9d201d8f7a7..aef63e35b56f 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -799,10 +799,74 @@ static int tcp_authopt_get_traffic_key(struct sock *sk, out: tcp_authopt_put_kdf_shash(key, kdf_tfm); return err; }

+struct tcp_v4_authopt_context_data { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + __be32 sisn; + __be32 disn; + __be16 digestbits; +} __packed; + +static int tcp_v4_authopt_get_traffic_key_noskb(struct tcp_authopt_key_info *key, + __be32 saddr, + __be32 daddr, + __be16 sport, + __be16 dport, + __be32 sisn, + __be32 disn, + u8 *traffic_key) +{ + int err; + struct crypto_shash *kdf_tfm; + SHASH_DESC_ON_STACK(desc, kdf_tfm); + struct tcp_v4_authopt_context_data data; + + BUILD_BUG_ON(sizeof(data) != 22); + + kdf_tfm = tcp_authopt_get_kdf_shash(key); + if (IS_ERR(kdf_tfm)) + return PTR_ERR(kdf_tfm); + + err = tcp_authopt_setkey(kdf_tfm, key); + if (err) + goto out; + + desc->tfm = kdf_tfm; + err = crypto_shash_init(desc); + if (err) + goto out; + + // RFC5926 section 3.1.1.1 + // Separate to keep alignment semi-sane + err = crypto_shash_update(desc, "\x01TCP-AO", 7); + if (err) + return err; + data.saddr = saddr; + data.daddr = daddr; + data.sport = sport; + data.dport = dport; + data.sisn = sisn; + data.disn = disn; + data.digestbits = htons(crypto_shash_digestsize(desc->tfm) * 8); + + err = crypto_shash_update(desc, (u8 *)&data, sizeof(data)); + if (err) + goto out; + err = crypto_shash_final(desc, traffic_key); + if (err) + goto out; + +out: + tcp_authopt_put_kdf_shash(key, kdf_tfm); + return err; +} + static int crypto_shash_update_zero(struct shash_desc *desc, int len) { u8 zero = 0; int i, err;

@@ -1205,10 +1269,93 @@ int tcp_authopt_hash(char *hash_location, memset(hash_location, 0, TCP_AUTHOPT_MACLEN); return err; } EXPORT_SYMBOL(tcp_authopt_hash);

+/** + * tcp_v4_authopt_hash_reply - Hash tcp+ipv4 header without SKB + * + * @hash_location: output buffer + * @info: sending socket's tcp_authopt_info + * @key: signing key, from tcp_authopt_select_key. + * @saddr: source address + * @daddr: destination address + * @th: Pointer to TCP header and options + */ +int tcp_v4_authopt_hash_reply(char *hash_location, + struct tcp_authopt_info *info, + struct tcp_authopt_key_info *key, + __be32 saddr, + __be32 daddr, + struct tcphdr *th) +{ + struct crypto_shash *mac_tfm; + u8 macbuf[TCP_AUTHOPT_MAXMACBUF]; + u8 traffic_key[TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN]; + SHASH_DESC_ON_STACK(desc, tfm); + __be32 sne = 0; + int err; + + /* Call special code path for computing traffic key without skb + * This can be called from tcp_v4_reqsk_send_ack so caching would be + * difficult here. + */ + err = tcp_v4_authopt_get_traffic_key_noskb(key, saddr, daddr, + th->source, th->dest, + htonl(info->src_isn), htonl(info->dst_isn), + traffic_key); + if (err) + goto out_err_traffic_key; + + /* Init mac shash */ + mac_tfm = tcp_authopt_get_mac_shash(key); + if (IS_ERR(mac_tfm)) + return PTR_ERR(mac_tfm); + err = crypto_shash_setkey(mac_tfm, traffic_key, key->alg->traffic_key_len); + if (err) + goto out_err; + + desc->tfm = mac_tfm; + err = crypto_shash_init(desc); + if (err) + return err; + + err = crypto_shash_update(desc, (u8 *)&sne, 4); + if (err) + return err; + + err = tcp_authopt_hash_tcp4_pseudoheader(desc, saddr, daddr, th->doff * 4); + if (err) + return err; + + // TCP header with checksum set to zero. Caller ensures this. + if (WARN_ON_ONCE(th->check != 0)) + goto out_err; + err = crypto_shash_update(desc, (u8 *)th, sizeof(*th)); + if (err) + goto out_err; + + // TCP options + err = tcp_authopt_hash_opts(desc, th, !(key->flags & TCP_AUTHOPT_KEY_EXCLUDE_OPTS)); + if (err) + goto out_err; + + err = crypto_shash_final(desc, macbuf); + if (err) + goto out_err; + memcpy(hash_location, macbuf, TCP_AUTHOPT_MACLEN); + + tcp_authopt_put_mac_shash(key, mac_tfm); + return 0; + +out_err: + tcp_authopt_put_mac_shash(key, mac_tfm); +out_err_traffic_key: + memset(hash_location, 0, TCP_AUTHOPT_MACLEN); + return err; +} + static struct tcp_authopt_key_info *tcp_authopt_lookup_recv(struct sock *sk, struct sk_buff *skb, struct tcp_authopt_info *info, int recv_id) {

Add implementation and tests for Sequence Number Extension.

One implementation is based on an IETF draft: https://datatracker.ietf.org/doc/draft-touch-sne/

The linux implementation is simpler and doesn't require additional flags, it just relies on standard before/after macros.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- .../tcp_authopt/tcp_authopt_test/sne_alg.py | 111 ++++++++++++++++++ .../tcp_authopt_test/test_sne_alg.py | 96 +++++++++++++++ 2 files changed, 207 insertions(+) create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/sne_alg.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sne_alg.py

diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sne_alg.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sne_alg.py new file mode 100644 index 000000000000..252356dc87a4 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/sne_alg.py @@ -0,0 +1,111 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Python implementation of SNE algorithms""" + + +def distance(x, y): + if x < y: + return y - x + else: + return x - y + + +class SequenceNumberExtender: + """Based on https://datatracker.ietf.org/doc/draft-touch-sne/""" + + sne: int = 0 + sne_flag: int = 1 + prev_seq: int = 0 + + def calc(self, seq): + """Update internal state and return SNE for certain SEQ""" + # use current SNE to start + result = self.sne + + # both in same SNE range? + if distance(seq, self.prev_seq) < 0x80000000: + # jumps fwd over N/2? + if seq >= 0x80000000 and self.prev_seq < 0x80000000: + self.sne_flag = 0 + # move prev forward if needed + self.prev_seq = max(seq, self.prev_seq) + # both in diff SNE ranges? + else: + # jumps forward over zero? + if seq < 0x80000000: + # update prev + self.prev_seq = seq + # first jump over zero? (wrap) + if self.sne_flag == 0: + # set flag so we increment once + self.sne_flag = 1 + # increment window + self.sne = self.sne + 1 + # use updated SNE value + result = self.sne + # jump backward over zero? + else: + # use pre-rollover SNE value + result = self.sne - 1 + + return result + + +class SequenceNumberExtenderRFC: + """Based on sample code in original RFC5925 document""" + + sne: int = 0 + sne_flag: int = 1 + prev_seq: int = 0 + + def calc(self, seq): + """Update internal state and return SNE for certain SEQ""" + # set the flag when the SEG.SEQ first rolls over + if self.sne_flag == 0 and self.prev_seq > 0x7FFFFFFF and seq < 0x7FFFFFFF: + self.sne = self.sne + 1 + self.sne_flag = 1 + # decide which SNE to use after incremented + if self.sne_flag and seq > 0x7FFFFFFF: + # use the pre-increment value + sne = self.sne - 1 + else: + # use the current value + sne = self.sne + # reset the flag in the *middle* of the window + if self.prev_seq < 0x7FFFFFFF and seq > 0x7FFFFFFF: + self.sne_flag = 0 + # save the current SEQ for the next time through the code + self.prev_seq = seq + + return sne + + +def tcp_seq_before(a, b) -> bool: + return ((a - b) & 0xFFFFFFFF) > 0x80000000 + + +def tcp_seq_after(a, b) -> bool: + return tcp_seq_before(a, b) + + +class SequenceNumberExtenderLinux: + """Based on linux implementation and with no extra flags""" + + sne: int = 0 + prev_seq: int = 0 + + def reset(self, seq, sne=0): + self.prev_seq = seq + self.sne = sne + + def calc(self, seq, update=True): + sne = self.sne + if tcp_seq_before(seq, self.prev_seq): + if seq > self.prev_seq: + sne -= 1 + else: + if seq < self.prev_seq: + sne += 1 + if update and tcp_seq_before(self.prev_seq, seq): + self.prev_seq = seq + self.sne = sne + return sne diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sne_alg.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sne_alg.py new file mode 100644 index 000000000000..9b74873cff4a --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_sne_alg.py @@ -0,0 +1,96 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Test SNE algorithm implementations""" + +import logging + +import pytest + +from .sne_alg import ( + SequenceNumberExtender, + SequenceNumberExtenderLinux, + SequenceNumberExtenderRFC, +) + +logger = logging.getLogger(__name__) + + +# Data from https://datatracker.ietf.org/doc/draft-touch-sne/ +_SNE_TEST_DATA = [ + (0x00000000, 0x00000000), + (0x00000000, 0x30000000), + (0x00000000, 0x90000000), + (0x00000000, 0x70000000), + (0x00000000, 0xA0000000), + (0x00000001, 0x00000001), + (0x00000000, 0xE0000000), + (0x00000001, 0x00000000), + (0x00000001, 0x7FFFFFFF), + (0x00000001, 0x00000000), + (0x00000001, 0x50000000), + (0x00000001, 0x80000000), + (0x00000001, 0x00000001), + (0x00000001, 0x40000000), + (0x00000001, 0x90000000), + (0x00000001, 0xB0000000), + (0x00000002, 0x0FFFFFFF), + (0x00000002, 0x20000000), + (0x00000002, 0x90000000), + (0x00000002, 0x70000000), + (0x00000002, 0xA0000000), + (0x00000003, 0x00004000), + (0x00000002, 0xD0000000), + (0x00000003, 0x20000000), + (0x00000003, 0x90000000), + (0x00000003, 0x70000000), + (0x00000003, 0xA0000000), + (0x00000004, 0x00004000), + (0x00000003, 0xD0000000), +] + + +# Easier test data with small jumps <= 0x30000000 +SNE_DATA_EASY = [ + (0x00000000, 0x00000000), + (0x00000000, 0x30000000), + (0x00000000, 0x60000000), + (0x00000000, 0x80000000), + (0x00000000, 0x90000000), + (0x00000000, 0xC0000000), + (0x00000000, 0xF0000000), + (0x00000001, 0x10000000), + (0x00000000, 0xF0030000), + (0x00000001, 0x00030000), + (0x00000001, 0x10030000), +] + + +def check_sne_alg(alg, data): + for sne, seq in data: + observed_sne = alg.calc(seq) + logger.info( + "seq %08x expected sne %08x observed sne %08x", seq, sne, observed_sne + ) + assert observed_sne == sne + + +def test_sne_alg(): + check_sne_alg(SequenceNumberExtender(), _SNE_TEST_DATA) + + +def test_sne_alg_easy(): + check_sne_alg(SequenceNumberExtender(), SNE_DATA_EASY) + + +@pytest.mark.xfail +def test_sne_alg_rfc(): + check_sne_alg(SequenceNumberExtenderRFC(), _SNE_TEST_DATA) + + +@pytest.mark.xfail +def test_sne_alg_rfc_easy(): + check_sne_alg(SequenceNumberExtenderRFC(), SNE_DATA_EASY) + + +def test_sne_alg_linux(): + check_sne_alg(SequenceNumberExtenderLinux(), _SNE_TEST_DATA) + check_sne_alg(SequenceNumberExtenderLinux(), SNE_DATA_EASY)

This patch validates that the TCP-AO signatures inserted by linux are correct in all algorithm permutations, using scapy.

It also tests that TCP-AO behaves correctly in a number of corner cases such as:

* reset handling * timewait * syn-recv * ipv4-mapped ipv6 * interaction with tcp-md5

This reverts commit 297a301a4f1c3abe41d554a9f6df192257a017b8.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- .../full_tcp_sniff_session.py | 91 +++ .../tcp_authopt_test/linux_tcp_md5sig.py | 110 ++++ .../tcp_authopt_test/scapy_conntrack.py | 173 ++++++ .../tcp_connection_fixture.py | 276 +++++++++ .../tcp_authopt_test/test_verify_capture.py | 559 ++++++++++++++++++ 5 files changed, 1209 insertions(+) create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/full_tcp_sniff_session.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_md5sig.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/scapy_conntrack.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/tcp_connection_fixture.py create mode 100644 tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_verify_capture.py

diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/full_tcp_sniff_session.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/full_tcp_sniff_session.py new file mode 100644 index 000000000000..d37f7d947bcd --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/full_tcp_sniff_session.py @@ -0,0 +1,91 @@ +# SPDX-License-Identifier: GPL-2.0 +import logging +import threading +import typing + +import scapy.sessions +from scapy.packet import Packet + +from .scapy_conntrack import TCPConnectionInfo, TCPConnectionTracker + +logger = logging.getLogger(__name__) + + +class FullTCPSniffSession(scapy.sessions.DefaultSession): + """Implementation of a scapy sniff session that can wait for a full TCP capture + + Allows another thread to wait for a complete FIN handshake without polling or sleep. + """ + + #: Server port used to identify client and server + server_port: int + #: Connection tracker + tracker: TCPConnectionTracker + + def __init__(self, server_port, **kw): + super().__init__(**kw) + self.server_port = server_port + self.tracker = TCPConnectionTracker() + self._close_event = threading.Event() + self._init_isn_event = threading.Event() + self._client_info = None + self._server_info = None + + @property + def client_info(self) -> TCPConnectionInfo: + if not self._client_info: + self._client_info = self.tracker.match_one(dport=self.server_port) + return self._client_info + + @property + def server_info(self) -> TCPConnectionInfo: + if not self._server_info: + self._server_info = self.tracker.match_one(sport=self.server_port) + return self._server_info + + @property + def client_isn(self): + return self.client_info.sisn + + @property + def server_isn(self): + return self.server_info.sisn + + def on_packet_received(self, p: Packet): + super().on_packet_received(p) + self.tracker.handle_packet(p) + + # check events: + if self.client_info.sisn is not None and self.client_info.disn is not None: + assert ( + self.client_info.sisn == self.server_info.disn + and self.server_info.sisn == self.client_info.disn + ) + self._init_isn_event.set() + if self.client_info.found_recv_finack and self.server_info.found_recv_finack: + self._close_event.set() + + def reset(self): + """Reset known information about client/server""" + self.tracker.reset() + self._server_info = None + self._client_info = None + self._close_event.clear() + self._init_isn_event.clear() + + def wait_close(self, timeout=10): + """Wait for a graceful close with FINs acked by both side""" + self._close_event.wait(timeout=timeout) + if not self._close_event.is_set(): + raise TimeoutError("Timed out waiting for graceful close") + + def wait_init_isn(self, timeout=10): + """Wait for both client_isn and server_isn to be determined""" + self._init_isn_event.wait(timeout=timeout) + if not self._init_isn_event.is_set(): + raise TimeoutError("Timed out waiting for Initial Sequence Numbers") + + def get_client_server_isn(self, timeout=10) -> typing.Tuple[int, int]: + """Return client/server ISN, blocking until they are captured""" + self.wait_init_isn(timeout=timeout) + return self.client_isn, self.server_isn diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_md5sig.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_md5sig.py new file mode 100644 index 000000000000..5cfd0428672a --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/linux_tcp_md5sig.py @@ -0,0 +1,110 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Python wrapper around linux TCP_MD5SIG ABI""" + +import socket +import struct +import typing +from dataclasses import dataclass +from enum import IntFlag + +from .sockaddr import sockaddr_convert, sockaddr_unpack + +TCP_MD5SIG = 14 +TCP_MD5SIG_EXT = 32 +TCP_MD5SIG_MAXKEYLEN = 80 + + +class TCP_MD5SIG_FLAG(IntFlag): + PREFIX = 0x1 + IFINDEX = 0x2 + + +@dataclass +class tcp_md5sig: + """Like linux struct tcp_md5sig""" + + addr: typing.Any + flags: typing.Optional[int] + prefixlen: typing.Optional[int] + keylen: typing.Optional[int] + ifindex: typing.Optional[int] + key: bytes + + sizeof = 128 + 88 + + def __init__( + self, addr=None, flags=None, prefixlen=None, keylen=None, ifindex=0, key=bytes() + ): + self.addr = addr + self.flags = flags + self.prefixlen = prefixlen + self.ifindex = ifindex + self.key = key + self.keylen = keylen + + def get_auto_flags(self): + return (TCP_MD5SIG_FLAG.PREFIX if self.prefixlen is not None else 0) | ( + TCP_MD5SIG_FLAG.IFINDEX if self.ifindex else 0 + ) + + def get_real_flags(self): + if self.flags is None: + return self.get_auto_flags() + else: + return self.flags + + def get_addr_bytes(self) -> bytes: + if self.addr is None: + return b"\0" * 128 + if self.addr is bytes: + assert len(self.addr) == 128 + return self.addr + return sockaddr_convert(self.addr).pack() + + def pack(self) -> bytes: + return struct.pack( + "128sBBHi80s", + self.get_addr_bytes(), + self.get_real_flags(), + self.prefixlen if self.prefixlen is not None else 0, + self.keylen if self.keylen is not None else len(self.key), + self.ifindex if self.ifindex is not None else 0, + self.key, + ) + + def __bytes__(self): + return self.pack() + + @classmethod + def unpack(cls, buffer: bytes) -> "tcp_md5sig": + tup = struct.unpack("128sBBHi80s", buffer) + addr = sockaddr_unpack(tup[0]) + return cls(addr, *tup[1:]) + + def set_ipv4_addr_all(self): + from .sockaddr import sockaddr_in + + self.addr = sockaddr_in() + self.prefixlen = 0 + + def set_ipv6_addr_all(self): + from .sockaddr import sockaddr_in6 + + self.addr = sockaddr_in6() + self.prefixlen = 0 + + +def setsockopt_md5sig(sock, opt: tcp_md5sig): + if opt.flags != 0: + optname = TCP_MD5SIG_EXT + else: + optname = TCP_MD5SIG + return sock.setsockopt(socket.SOL_TCP, optname, bytes(opt)) + + +def setsockopt_md5sig_kwargs(sock, opt: tcp_md5sig = None, **kw): + if opt is None: + opt = tcp_md5sig() + for k, v in kw.items(): + setattr(opt, k, v) + return setsockopt_md5sig(sock, opt) diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/scapy_conntrack.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/scapy_conntrack.py new file mode 100644 index 000000000000..0f7cba70a917 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/scapy_conntrack.py @@ -0,0 +1,173 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Identify TCP connections inside a capture and collect per-connection information""" +import typing +from dataclasses import dataclass + +from scapy.layers.inet import TCP +from scapy.packet import Packet + +from .scapy_utils import IPvXAddress, get_packet_ipvx_dst, get_packet_ipvx_src +from .sne_alg import SequenceNumberExtenderLinux + + +@dataclass(frozen=True) +class TCPConnectionKey: + """TCP connection identification key: standard 4-tuple""" + + saddr: typing.Optional[IPvXAddress] = None + daddr: typing.Optional[IPvXAddress] = None + sport: int = 0 + dport: int = 0 + + def rev(self) -> "TCPConnectionKey": + return TCPConnectionKey(self.daddr, self.saddr, self.dport, self.sport) + + +def get_packet_tcp_connection_key(p: Packet) -> TCPConnectionKey: + th = p[TCP] + return TCPConnectionKey( + get_packet_ipvx_src(p), get_packet_ipvx_dst(p), th.sport, th.dport + ) + + +class TCPConnectionInfo: + saddr: typing.Optional[IPvXAddress] = None + daddr: typing.Optional[IPvXAddress] = None + sport: int = 0 + dport: int = 0 + sisn: typing.Optional[int] = None + disn: typing.Optional[int] = None + rcv_sne: SequenceNumberExtenderLinux + snd_sne: SequenceNumberExtenderLinux + + found_syn = False + found_synack = False + + found_send_fin = False + found_send_finack = False + found_recv_fin = False + found_recv_finack = False + + def __init__(self): + self.rcv_sne = SequenceNumberExtenderLinux() + self.snd_sne = SequenceNumberExtenderLinux() + + def get_key(self): + return TCPConnectionKey(self.saddr, self.daddr, self.sport, self.dport) + + @classmethod + def from_key(cls, key: TCPConnectionKey) -> "TCPConnectionInfo": + obj = cls() + obj.saddr = key.saddr + obj.daddr = key.daddr + obj.sport = key.sport + obj.dport = key.dport + return obj + + def handle_send(self, p: Packet): + th = p[TCP] + if self.get_key() != get_packet_tcp_connection_key(p): + raise ValueError("Packet not for this connection") + + if th.flags.S and not th.flags.A: + assert th.ack == 0 + self.found_syn = True + self.sisn = th.seq + self.snd_sne.reset(th.seq) + elif th.flags.S and th.flags.A: + self.found_synack = True + self.sisn = th.seq + self.snd_sne.reset(th.seq) + assert self.disn == th.ack - 1 + + # Should track seq numbers instead + if th.flags.F: + self.found_send_fin = True + if th.flags.A and self.found_recv_fin: + self.found_send_finack = True + + # Should only take valid packets into account + self.snd_sne.calc(th.seq) + + def handle_recv(self, p: Packet): + th = p[TCP] + if self.get_key().rev() != get_packet_tcp_connection_key(p): + raise ValueError("Packet not for this connection") + + if th.flags.S and not th.flags.A: + assert th.ack == 0 + self.found_syn = True + self.disn = th.seq + self.rcv_sne.reset(th.seq) + elif th.flags.S and th.flags.A: + self.found_synack = True + self.disn = th.seq + self.rcv_sne.reset(th.seq) + assert self.sisn == th.ack - 1 + + # Should track seq numbers instead + if th.flags.F: + self.found_recv_fin = True + if th.flags.A and self.found_send_fin: + self.found_recv_finack = True + + # Should only take valid packets into account + self.rcv_sne.calc(th.seq) + + +class TCPConnectionTracker: + table: typing.Dict[TCPConnectionKey, TCPConnectionInfo] + + def __init__(self): + self.table = {} + + def reset(self): + """Forget known connections""" + self.table = {} + + def get_or_create(self, key: TCPConnectionKey) -> TCPConnectionInfo: + info = self.table.get(key, None) + if info is None: + info = TCPConnectionInfo.from_key(key) + self.table[key] = info + return info + + def get(self, key: TCPConnectionKey) -> typing.Optional[TCPConnectionInfo]: + return self.table.get(key, None) + + def handle_packet(self, p: Packet): + if not p or not TCP in p: + return + key = get_packet_tcp_connection_key(p) + info = self.get_or_create(key) + info.handle_send(p) + rkey = key.rev() + rinfo = self.get_or_create(rkey) + rinfo.handle_recv(p) + + def iter_match(self, saddr=None, daddr=None, sport=None, dport=None): + def attr_optional_match(obj, name, val) -> bool: + if val is None: + return True + else: + return getattr(obj, name) == val + + for key, info in self.table.items(): + if ( + attr_optional_match(key, "saddr", saddr) + and attr_optional_match(key, "daddr", daddr) + and attr_optional_match(key, "sport", sport) + and attr_optional_match(key, "dport", dport) + ): + yield info + + def match_one( + self, saddr=None, daddr=None, sport=None, dport=None + ) -> typing.Optional[TCPConnectionInfo]: + res = list(self.iter_match(saddr, daddr, sport, dport)) + if len(res) == 1: + return res[0] + elif len(res) == 0: + return None + else: + raise ValueError("Multiple connection matches") diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/tcp_connection_fixture.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/tcp_connection_fixture.py new file mode 100644 index 000000000000..0d14f343c282 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/tcp_connection_fixture.py @@ -0,0 +1,276 @@ +# SPDX-License-Identifier: GPL-2.0 +import logging +import socket +import subprocess +from contextlib import ExitStack + +import pytest +from scapy.data import ETH_P_IP, ETH_P_IPV6 +from scapy.layers.inet import IP, TCP +from scapy.layers.inet6 import IPv6 +from scapy.layers.l2 import Ether +from scapy.packet import Packet + +from . import linux_tcp_authopt +from .full_tcp_sniff_session import FullTCPSniffSession +from .linux_tcp_authopt import set_tcp_authopt_key, tcp_authopt_key +from .netns_fixture import NamespaceFixture +from .scapy_utils import ( + AsyncSnifferContext, + create_capture_socket, + create_l2socket, + scapy_tcp_get_authopt_val, + scapy_tcp_get_md5_sig, +) +from .server import SimpleServerThread +from .utils import ( + DEFAULT_TCP_SERVER_PORT, + create_client_socket, + create_listen_socket, + netns_context, + nstat_json, +) + +logger = logging.getLogger(__name__) + + +class TCPConnectionFixture: + """Test fixture with an instrumented TCP connection + + Includes: + * pair of network namespaces + * one listen socket + * server thread with echo protocol + * one client socket + * one async sniffer on the server interface + * A `FullTCPSniffSession` examining TCP packets + * l2socket allowing packet injection from client + + :ivar tcp_md5_key: Secret key for md5 (addr is implicit) + """ + + sniffer_session: FullTCPSniffSession + + def __init__( + self, + address_family=socket.AF_INET, + sniffer_kwargs=None, + tcp_authopt_key: tcp_authopt_key = None, + server_thread_kwargs=None, + tcp_md5_key=None, + ): + self.address_family = address_family + self.server_port = DEFAULT_TCP_SERVER_PORT + self.client_port = 27972 + self.sniffer_session = FullTCPSniffSession(DEFAULT_TCP_SERVER_PORT) + if sniffer_kwargs is None: + sniffer_kwargs = {} + self.sniffer_kwargs = sniffer_kwargs + self.tcp_authopt_key = tcp_authopt_key + self.server_thread = SimpleServerThread( + mode="echo", **(server_thread_kwargs or {}) + ) + self.tcp_md5_key = tcp_md5_key + + def _set_tcp_md5(self): + from . import linux_tcp_md5sig + from .sockaddr import sockaddr_convert + + linux_tcp_md5sig.setsockopt_md5sig( + self.listen_socket, + linux_tcp_md5sig.tcp_md5sig( + key=self.tcp_md5_key, addr=sockaddr_convert(self.client_addr) + ), + ) + linux_tcp_md5sig.setsockopt_md5sig( + self.client_socket, + linux_tcp_md5sig.tcp_md5sig( + key=self.tcp_md5_key, addr=sockaddr_convert(self.server_addr) + ), + ) + + def create_client_socket(self, bind_port=0): + return create_client_socket( + ns=self.nsfixture.client_netns_name, + family=self.address_family, + bind_addr=self.client_addr, + bind_port=bind_port, + ) + + def __enter__(self): + if self.tcp_authopt_key and not linux_tcp_authopt.has_tcp_authopt(): + pytest.skip("Need TCP_AUTHOPT") + + self.exit_stack = ExitStack() + self.exit_stack.__enter__() + + self.nsfixture = self.exit_stack.enter_context(NamespaceFixture()) + self.server_addr = self.nsfixture.get_addr(self.address_family, 1) + self.client_addr = self.nsfixture.get_addr(self.address_family, 2) + + self.listen_socket = create_listen_socket( + ns=self.nsfixture.server_netns_name, + family=self.address_family, + bind_addr=self.server_addr, + bind_port=self.server_port, + ) + self.exit_stack.enter_context(self.listen_socket) + self.client_socket = self.create_client_socket(bind_port=self.client_port) + self.exit_stack.enter_context(self.client_socket) + self.server_thread.add_listen_socket(self.listen_socket) + self.exit_stack.enter_context(self.server_thread) + + if self.tcp_authopt_key: + set_tcp_authopt_key(self.listen_socket, self.tcp_authopt_key) + set_tcp_authopt_key(self.client_socket, self.tcp_authopt_key) + + if self.tcp_md5_key: + self._set_tcp_md5() + + capture_filter = f"tcp port {self.server_port}" + self.capture_socket = create_capture_socket( + ns=self.nsfixture.server_netns_name, iface="veth0", filter=capture_filter + ) + self.exit_stack.enter_context(self.capture_socket) + + self.sniffer = AsyncSnifferContext( + opened_socket=self.capture_socket, + session=self.sniffer_session, + prn=log_tcp_authopt_packet, + **self.sniffer_kwargs, + ) + self.exit_stack.enter_context(self.sniffer) + + self.client_l2socket = create_l2socket( + ns=self.nsfixture.client_netns_name, iface="veth0" + ) + self.exit_stack.enter_context(self.client_l2socket) + self.server_l2socket = create_l2socket( + ns=self.nsfixture.server_netns_name, iface="veth0" + ) + self.exit_stack.enter_context(self.server_l2socket) + + def __exit__(self, *args): + self.exit_stack.__exit__(*args) + + @property + def ethertype(self): + if self.address_family == socket.AF_INET: + return ETH_P_IP + elif self.address_family == socket.AF_INET6: + return ETH_P_IPV6 + else: + raise ValueError("bad address_family={self.address_family}") + + def scapy_iplayer(self): + if self.address_family == socket.AF_INET: + return IP + elif self.address_family == socket.AF_INET6: + return IPv6 + else: + raise ValueError("bad address_family={self.address_family}") + + def create_client2server_packet(self) -> Packet: + return ( + Ether( + type=self.ethertype, + src=self.nsfixture.client_mac_addr, + dst=self.nsfixture.server_mac_addr, + ) + / self.scapy_iplayer()(src=str(self.client_addr), dst=str(self.server_addr)) + / TCP(sport=self.client_port, dport=self.server_port) + ) + + def create_server2client_packet(self) -> Packet: + return ( + Ether( + type=self.ethertype, + src=self.nsfixture.server_mac_addr, + dst=self.nsfixture.client_mac_addr, + ) + / self.scapy_iplayer()(src=str(self.server_addr), dst=str(self.client_addr)) + / TCP(sport=self.server_port, dport=self.client_port) + ) + + @property + def server_addr_port(self): + return (str(self.server_addr), self.server_port) + + @property + def server_netns_name(self): + return self.nsfixture.server_netns_name + + @property + def client_netns_name(self): + return self.nsfixture.client_netns_name + + def client_nstat_json(self): + with netns_context(self.client_netns_name): + return nstat_json() + + def server_nstat_json(self): + with netns_context(self.server_netns_name): + return nstat_json() + + def assert_no_snmp_output_failures(self): + client_nstat_dict = self.client_nstat_json() + assert client_nstat_dict["TcpExtTCPAuthOptFailure"] == 0 + server_nstat_dict = self.server_nstat_json() + assert server_nstat_dict["TcpExtTCPAuthOptFailure"] == 0 + + def _get_state_via_ss(self, command_prefix: str): + # Every namespace should have at most one socket + # the "state connected" filter includes TIME-WAIT but not LISTEN + cmd = command_prefix + "ss --numeric --no-header --tcp state connected" + out = subprocess.check_output(cmd, text=True, shell=True) + lines = out.splitlines() + # No socket found usually means "CLOSED". It is distinct from "TIME-WAIT" + if len(lines) == 0: + return None + if len(lines) > 1: + raise ValueError("At most one line expected") + return lines[0].split()[0] + + def get_client_tcp_state(self): + return self._get_state_via_ss(f"ip netns exec {self.client_netns_name} ") + + def get_server_tcp_state(self): + return self._get_state_via_ss(f"ip netns exec {self.server_netns_name} ") + + +def format_tcp_authopt_packet( + p: Packet, include_ethernet=False, include_seq=False, include_md5=True +) -> str: + """Format a TCP packet in a way that is useful for TCP-AO testing""" + if not TCP in p: + return p.summary() + th = p[TCP] + if isinstance(th.underlayer, IP): + result = p.sprintf(r"%IP.src%:%TCP.sport% > %IP.dst%:%TCP.dport%") + elif isinstance(th.underlayer, IPv6): + result = p.sprintf(r"%IPv6.src%:%TCP.sport% > %IPv6.dst%:%TCP.dport%") + else: + raise ValueError(f"Unknown TCP underlayer {th.underlayer}") + result += p.sprintf(r" Flags %-2s,TCP.flags%") + if include_ethernet: + result = p.sprintf(r"ethertype %Ether.type% ") + result + result = p.sprintf(r"%Ether.src% > %Ether.dst% ") + result + if include_seq: + result += p.sprintf(r" seq %TCP.seq% ack %TCP.ack%") + result += f" len {len(p[TCP].payload)}" + authopt = scapy_tcp_get_authopt_val(p[TCP]) + if authopt: + result += f" AO keyid={authopt.keyid} rnextkeyid={authopt.rnextkeyid} mac={authopt.mac.hex()}" + else: + result += " no AO" + if include_md5: + md5sig = scapy_tcp_get_md5_sig(p[TCP]) + if md5sig: + result += f" MD5 {md5sig.hex()}" + else: + result += " no MD5" + return result + + +def log_tcp_authopt_packet(p): + logger.info("sniff %s", format_tcp_authopt_packet(p, include_seq=True)) diff --git a/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_verify_capture.py b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_verify_capture.py new file mode 100644 index 000000000000..68d002139974 --- /dev/null +++ b/tools/testing/selftests/tcp_authopt/tcp_authopt_test/test_verify_capture.py @@ -0,0 +1,559 @@ +# SPDX-License-Identifier: GPL-2.0 +"""Capture packets with TCP-AO and verify signatures""" + +import logging +import os +import socket +import subprocess +from contextlib import ExitStack, nullcontext + +import pytest +import waiting +from scapy.layers.inet import TCP + +from .conftest import ( + raises_optional_exception, + skipif_cant_capture, + skipif_missing_tcp_authopt, +) +from .full_tcp_sniff_session import FullTCPSniffSession +from .linux_tcp_authopt import ( + TCP_AUTHOPT_ALG, + TCP_AUTHOPT_KEY_FLAG, + set_tcp_authopt_key, + tcp_authopt_key, +) +from .netns_fixture import NamespaceFixture +from .scapy_tcp_authopt import ( + TcpAuthOptAlg_HMAC_SHA1, + add_tcp_authopt_signature, + break_tcp_authopt_signature, +) +from .scapy_utils import ( + AsyncSnifferContext, + scapy_sniffer_stop, + scapy_tcp_get_authopt_val, + scapy_tcp_get_md5_sig, + tcp_seq_wrap, +) +from .server import SimpleServerThread +from .tcp_connection_fixture import TCPConnectionFixture +from .utils import ( + DEFAULT_TCP_SERVER_PORT, + check_socket_echo, + create_client_socket, + create_listen_socket, + nstat_json, + socket_set_linger, +) +from .validator import TcpAuthValidator, TcpAuthValidatorKey + +logger = logging.getLogger(__name__) +pytestmark = [skipif_missing_tcp_authopt, skipif_cant_capture] +DEFAULT_TCP_AUTHOPT_KEY = tcp_authopt_key( + alg=TCP_AUTHOPT_ALG.HMAC_SHA_1_96, + key=b"hello", +) + + +def get_alg_id(alg_name) -> int: + if alg_name == "HMAC-SHA-1-96": + return TCP_AUTHOPT_ALG.HMAC_SHA_1_96 + elif alg_name == "AES-128-CMAC-96": + return TCP_AUTHOPT_ALG.AES_128_CMAC_96 + else: + raise ValueError() + + +@pytest.mark.parametrize( + "address_family,alg_name,include_options,transfer_data", + [ + (socket.AF_INET, "HMAC-SHA-1-96", True, True), + (socket.AF_INET, "AES-128-CMAC-96", True, True), + (socket.AF_INET, "AES-128-CMAC-96", False, True), + (socket.AF_INET6, "HMAC-SHA-1-96", True, True), + (socket.AF_INET6, "HMAC-SHA-1-96", False, True), + (socket.AF_INET6, "AES-128-CMAC-96", True, True), + (socket.AF_INET, "HMAC-SHA-1-96", True, False), + (socket.AF_INET6, "AES-128-CMAC-96", False, False), + ], +) +def test_verify_capture( + exit_stack, address_family, alg_name, include_options, transfer_data +): + master_key = b"testvector" + alg_id = get_alg_id(alg_name) + + session = FullTCPSniffSession(server_port=DEFAULT_TCP_SERVER_PORT) + sniffer = exit_stack.enter_context( + AsyncSnifferContext( + filter=f"inbound and tcp port {DEFAULT_TCP_SERVER_PORT}", + iface="lo", + session=session, + ) + ) + + listen_socket = create_listen_socket(family=address_family) + listen_socket = exit_stack.enter_context(listen_socket) + exit_stack.enter_context(SimpleServerThread(listen_socket, mode="echo")) + + client_socket = socket.socket(address_family, socket.SOCK_STREAM) + client_socket = exit_stack.push(client_socket) + + key = tcp_authopt_key(alg=alg_id, key=master_key, include_options=include_options) + set_tcp_authopt_key(listen_socket, key) + set_tcp_authopt_key(client_socket, key) + + # even if one signature is incorrect keep processing the capture + old_nstat = nstat_json() + valkey = TcpAuthValidatorKey( + key=master_key, alg_name=alg_name, include_options=include_options + ) + validator = TcpAuthValidator(keys=[valkey]) + + try: + client_socket.settimeout(1.0) + client_socket.connect(("localhost", DEFAULT_TCP_SERVER_PORT)) + if transfer_data: + for _ in range(5): + check_socket_echo(client_socket) + client_socket.close() + session.wait_close() + except socket.timeout: + # If invalid packets are sent let the validator run + logger.warning("socket timeout", exc_info=True) + pass + + sniffer.stop() + + logger.info("capture: %r", sniffer.results) + for p in sniffer.results: + validator.handle_packet(p) + validator.raise_errors() + + new_nstat = nstat_json() + assert old_nstat["TcpExtTCPAuthOptFailure"] == new_nstat["TcpExtTCPAuthOptFailure"] + + +@pytest.mark.parametrize( + "address_family,use_tcp_authopt,use_tcp_md5sig", + [ + (socket.AF_INET, 0, 0), + (socket.AF_INET, 1, 0), + (socket.AF_INET, 0, 1), + (socket.AF_INET6, 0, 0), + (socket.AF_INET6, 1, 0), + (socket.AF_INET6, 0, 1), + (socket.AF_INET, 1, 1), + (socket.AF_INET6, 1, 1), + ], +) +def test_both_authopt_md5(exit_stack, address_family, use_tcp_authopt, use_tcp_md5sig): + """Basic test for interaction between TCP_AUTHOPT and TCP_MD5SIG + + Configuring both on same socket is allowed but RFC5925 doesn't allow both on the + same packet or same connection. + + The naive handling of inserting or validation both options is incorrect. + """ + con = TCPConnectionFixture(address_family=address_family) + if use_tcp_authopt: + con.tcp_authopt_key = DEFAULT_TCP_AUTHOPT_KEY + if use_tcp_md5sig: + con.tcp_md5_key = b"hello" + exit_stack.enter_context(con) + + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + check_socket_echo(con.client_socket) + check_socket_echo(con.client_socket) + con.client_socket.close() + + scapy_sniffer_stop(con.sniffer) + fail = False + for p in con.sniffer.results: + has_tcp_authopt = scapy_tcp_get_authopt_val(p[TCP]) is not None + has_tcp_md5sig = scapy_tcp_get_md5_sig(p[TCP]) is not None + + if has_tcp_authopt and has_tcp_md5sig: + logger.error("Packet has both AO and MD5: %r", p) + fail = False + + if use_tcp_authopt: + if not has_tcp_authopt: + logger.error("missing AO: %r", p) + fail = True + elif use_tcp_md5sig: + if not has_tcp_md5sig: + logger.error("missing MD5: %r", p) + fail = True + else: + if has_tcp_md5sig or has_tcp_authopt: + logger.error("unexpected MD5 or AO: %r", p) + fail = True + + assert not fail + + +@pytest.mark.parametrize("mode", ["none", "ao", "ao-addrbind", "md5"]) +def test_v4mapv6(exit_stack, mode: str): + """Test ipv4 client and ipv6 server with and without TCP-AO + + By default any IPv6 server will also receive packets from IPv4 clients. This + is not currently supported by TCP_AUTHOPT but it should fail in an orderly + manner. + """ + nsfixture = NamespaceFixture() + exit_stack.enter_context(nsfixture) + server_ipv4_addr = nsfixture.get_addr(socket.AF_INET, 1) + + listen_socket = create_listen_socket( + ns=nsfixture.server_netns_name, family=socket.AF_INET6 + ) + listen_socket = exit_stack.enter_context(listen_socket) + + server_thread = SimpleServerThread(listen_socket, mode="echo") + exit_stack.enter_context(server_thread) + + client_socket = create_client_socket( + ns=nsfixture.client_netns_name, + family=socket.AF_INET, + ) + client_socket = exit_stack.push(client_socket) + + if mode == "ao": + alg = TCP_AUTHOPT_ALG.HMAC_SHA_1_96 + key = tcp_authopt_key(alg=alg, key="hello") + set_tcp_authopt_key(listen_socket, key) + set_tcp_authopt_key(client_socket, key) + + if mode == "ao-addrbind": + alg = TCP_AUTHOPT_ALG.HMAC_SHA_1_96 + client_ipv6_addr = nsfixture.get_addr(socket.AF_INET6, 2) + server_key = tcp_authopt_key(alg=alg, key="hello", addr=client_ipv6_addr) + server_key.flags = TCP_AUTHOPT_KEY_FLAG.BIND_ADDR + set_tcp_authopt_key(listen_socket, server_key) + + client_key = tcp_authopt_key(alg=alg, key="hello") + set_tcp_authopt_key(client_socket, client_key) + + if mode == "md5": + from . import linux_tcp_md5sig + + server_md5key = linux_tcp_md5sig.tcp_md5sig(key=b"hello") + server_md5key.set_ipv6_addr_all() + linux_tcp_md5sig.setsockopt_md5sig(listen_socket, server_md5key) + client_md5key = linux_tcp_md5sig.tcp_md5sig(key=b"hellx") + client_md5key.set_ipv4_addr_all() + linux_tcp_md5sig.setsockopt_md5sig(client_socket, client_md5key) + + with raises_optional_exception(socket.timeout if mode != "none" else None): + client_socket.connect((str(server_ipv4_addr), DEFAULT_TCP_SERVER_PORT)) + check_socket_echo(client_socket) + client_socket.close() + + +@pytest.mark.parametrize( + "address_family,signed", + [ + (socket.AF_INET, True), + (socket.AF_INET, False), + (socket.AF_INET6, True), + (socket.AF_INET6, False), + ], +) +def test_rst(exit_stack: ExitStack, address_family, signed: bool): + """Check that an unsigned RST breaks a normal connection but not one protected by TCP-AO""" + + con = TCPConnectionFixture(address_family=address_family) + if signed: + con.tcp_authopt_key = DEFAULT_TCP_AUTHOPT_KEY + exit_stack.enter_context(con) + + # connect + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + + client_isn, server_isn = con.sniffer_session.get_client_server_isn() + p = con.create_client2server_packet() + p[TCP].flags = "R" + p[TCP].seq = tcp_seq_wrap(client_isn + 1001) + p[TCP].ack = tcp_seq_wrap(server_isn + 1001) + con.client_l2socket.send(p) + + if signed: + # When protected by TCP-AO unsigned RSTs are ignored. + check_socket_echo(con.client_socket) + else: + # By default an RST that guesses seq can kill the connection. + with pytest.raises(ConnectionResetError): + check_socket_echo(con.client_socket) + + +@pytest.mark.parametrize("address_family", [socket.AF_INET, socket.AF_INET6]) +def test_rst_signed_manually(exit_stack: ExitStack, address_family): + """Check that an manually signed RST breaks a connection protected by TCP-AO""" + + con = TCPConnectionFixture(address_family=address_family) + con.tcp_authopt_key = key = DEFAULT_TCP_AUTHOPT_KEY + exit_stack.enter_context(con) + + # connect + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + + client_isn, server_isn = con.sniffer_session.get_client_server_isn() + p = con.create_client2server_packet() + p[TCP].flags = "R" + p[TCP].seq = tcp_seq_wrap(client_isn + 1001) + p[TCP].ack = tcp_seq_wrap(server_isn + 1001) + + add_tcp_authopt_signature( + p, TcpAuthOptAlg_HMAC_SHA1(), key.key, client_isn, server_isn + ) + con.client_l2socket.send(p) + + # The server socket will close in response to RST without a TIME-WAIT + # Attempting to send additional packets will result in a timeout because + # the signature can't be validated. + with pytest.raises(socket.timeout): + check_socket_echo(con.client_socket) + + +@pytest.mark.parametrize("address_family", [socket.AF_INET, socket.AF_INET6]) +def test_tw_ack(exit_stack: ExitStack, address_family): + """Manually sent a duplicate ACK after FIN and check TWSK signs replies correctly + + Kernel has a custom code path for this + """ + + con = TCPConnectionFixture(address_family=address_family) + con.tcp_authopt_key = key = DEFAULT_TCP_AUTHOPT_KEY + exit_stack.enter_context(con) + + # connect and close nicely + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + assert con.get_client_tcp_state() == "ESTAB" + assert con.get_server_tcp_state() == "ESTAB" + con.client_socket.close() + con.sniffer_session.wait_close() + + assert con.get_client_tcp_state() == "TIME-WAIT" + assert con.get_server_tcp_state() is None + + # Sent a duplicate FIN/ACK + client_isn, server_isn = con.sniffer_session.get_client_server_isn() + p = con.create_server2client_packet() + p[TCP].flags = "FA" + p[TCP].seq = tcp_seq_wrap(server_isn + 1001) + p[TCP].ack = tcp_seq_wrap(client_isn + 1002) + add_tcp_authopt_signature( + p, TcpAuthOptAlg_HMAC_SHA1(), key.key, server_isn, client_isn + ) + pr = con.server_l2socket.sr1(p) + assert pr[TCP].ack == tcp_seq_wrap(server_isn + 1001) + assert pr[TCP].seq == tcp_seq_wrap(client_isn + 1001) + assert pr[TCP].flags == "A" + + scapy_sniffer_stop(con.sniffer) + + val = TcpAuthValidator() + val.keys.append(TcpAuthValidatorKey(key=b"hello", alg_name="HMAC-SHA-1-96")) + for p in con.sniffer.results: + val.handle_packet(p) + val.raise_errors() + + # The server does not have enough state to validate the ACK from TIME-WAIT + # so it reports a failure. + assert con.server_nstat_json()["TcpExtTCPAuthOptFailure"] == 1 + assert con.client_nstat_json()["TcpExtTCPAuthOptFailure"] == 0 + + +@pytest.mark.parametrize("address_family", [socket.AF_INET, socket.AF_INET6]) +def test_tw_rst(exit_stack: ExitStack, address_family): + """Manually sent a signed invalid packet after FIN and check TWSK signs RST correctly + + Kernel has a custom code path for this + """ + key = DEFAULT_TCP_AUTHOPT_KEY + con = TCPConnectionFixture( + address_family=address_family, + tcp_authopt_key=key, + ) + con.server_thread.keep_half_open = True + exit_stack.enter_context(con) + + # connect, transfer data and close client nicely + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + con.client_socket.close() + + # since server keeps connection open client goes to FIN-WAIT-2 + def check_socket_states(): + client_tcp_state_name = con.get_client_tcp_state() + server_tcp_state_name = con.get_server_tcp_state() + logger.info("%s %s", client_tcp_state_name, server_tcp_state_name) + return ( + client_tcp_state_name == "FIN-WAIT-2" + and server_tcp_state_name == "CLOSE-WAIT" + ) + + waiting.wait(check_socket_states) + + # sending a FIN-ACK with incorrect seq makes + # tcp_timewait_state_process return a TCP_TW_RST + client_isn, server_isn = con.sniffer_session.get_client_server_isn() + p = con.create_server2client_packet() + p[TCP].flags = "FA" + p[TCP].seq = tcp_seq_wrap(server_isn + 1001 + 1) + p[TCP].ack = tcp_seq_wrap(client_isn + 1002) + add_tcp_authopt_signature( + p, TcpAuthOptAlg_HMAC_SHA1(), key.key, server_isn, client_isn + ) + con.server_l2socket.send(p) + + # remove delay by scapy trick? + import time + + time.sleep(1) + scapy_sniffer_stop(con.sniffer) + + # Check client socket moved from FIN-WAIT-2 to CLOSED + assert con.get_client_tcp_state() is None + + # Check some RST was seen + def is_tcp_rst(p): + return TCP in p and p[TCP].flags.R + + assert any(is_tcp_rst(p) for p in con.sniffer.results) + + # Check everything was valid + val = TcpAuthValidator() + val.keys.append(TcpAuthValidatorKey(key=b"hello", alg_name="HMAC-SHA-1-96")) + for p in con.sniffer.results: + val.handle_packet(p) + val.raise_errors() + + # Check no snmp failures + con.assert_no_snmp_output_failures() + + +def test_rst_linger(exit_stack: ExitStack): + """Test RST sent deliberately via SO_LINGER is valid""" + con = TCPConnectionFixture( + sniffer_kwargs=dict(count=8), tcp_authopt_key=DEFAULT_TCP_AUTHOPT_KEY + ) + exit_stack.enter_context(con) + + con.client_socket.connect(con.server_addr_port) + check_socket_echo(con.client_socket) + socket_set_linger(con.client_socket, 1, 0) + con.client_socket.close() + + con.sniffer.join(timeout=3) + + val = TcpAuthValidator() + val.keys.append(TcpAuthValidatorKey(key=b"hello", alg_name="HMAC-SHA-1-96")) + for p in con.sniffer.results: + val.handle_packet(p) + val.raise_errors() + + def is_tcp_rst(p): + return TCP in p and p[TCP].flags.R + + assert any(is_tcp_rst(p) for p in con.sniffer.results) + + +@pytest.mark.parametrize( + "address_family,mode", + [ + (socket.AF_INET, "goodsign"), + (socket.AF_INET, "fakesign"), + (socket.AF_INET, "unsigned"), + (socket.AF_INET6, "goodsign"), + (socket.AF_INET6, "fakesign"), + (socket.AF_INET6, "unsigned"), + ], +) +def test_badack_to_synack(exit_stack, address_family, mode: str): + """Test bad ack in response to server to syn/ack. + + This is handled by a minisocket in the TCP_SYN_RECV state on a separate code path + """ + con = TCPConnectionFixture(address_family=address_family) + if mode != "unsigned": + con.tcp_authopt_key = tcp_authopt_key( + alg=TCP_AUTHOPT_ALG.HMAC_SHA_1_96, + key=b"hello", + ) + exit_stack.enter_context(con) + + client_l2socket = con.client_l2socket + client_isn = 1000 + server_isn = 0 + + def sign(packet): + if mode == "unsigned": + return + add_tcp_authopt_signature( + packet, + TcpAuthOptAlg_HMAC_SHA1(), + con.tcp_authopt_key.key, + client_isn, + server_isn, + ) + + # Prevent TCP in client namespace from sending RST + # Do this by removing the client address and insert a static ARP on server side + client_prefix_length = con.nsfixture.get_prefix_length(address_family) + subprocess.run( + f"""\ +set -e +ip netns exec {con.nsfixture.client_netns_name} ip addr del {con.client_addr}/{client_prefix_length} dev veth0 +ip netns exec {con.nsfixture.server_netns_name} ip neigh add {con.client_addr} lladdr {con.nsfixture.client_mac_addr} dev veth0 +""", + shell=True, + check=True, + ) + + p1 = con.create_client2server_packet() + p1[TCP].flags = "S" + p1[TCP].seq = client_isn + p1[TCP].ack = 0 + sign(p1) + + p2 = client_l2socket.sr1(p1, timeout=1) + server_isn = p2[TCP].seq + assert p2[TCP].ack == client_isn + 1 + assert p2[TCP].flags == "SA" + + p3 = con.create_client2server_packet() + p3[TCP].flags = "A" + p3[TCP].seq = client_isn + 1 + p3[TCP].ack = server_isn + 1 + sign(p3) + if mode == "fakesign": + break_tcp_authopt_signature(p3) + + assert con.server_nstat_json()["TcpExtTCPAuthOptFailure"] == 0 + client_l2socket.send(p3) + + def confirm_good(): + return len(con.server_thread.server_socket) > 0 + + def confirm_fail(): + return con.server_nstat_json()["TcpExtTCPAuthOptFailure"] == 1 + + def wait_good(): + assert not confirm_fail() + return confirm_good() + + def wait_fail(): + assert not confirm_good() + return confirm_fail() + + if mode == "fakesign": + waiting.wait(wait_fail, timeout_seconds=5, sleep_seconds=0.1) + else: + waiting.wait(wait_good, timeout_seconds=5, sleep_seconds=0.1)

The RFC requires that TCP can report the keyid and rnextkeyid values being sent or received, implement this via getsockopt values.

The RFC also requires that user can select the sending key and that the sending key is automatically switched based on rnextkeyid. These requirements can conflict so we implement both and add a flag which specifies if user or peer request takes priority.

Also add an option to control rnextkeyid explicitly from userspace.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- Documentation/networking/tcp_authopt.rst | 25 ++++++ include/net/tcp_authopt.h | 38 ++++++++- include/uapi/linux/tcp.h | 31 ++++++++ net/ipv4/tcp_authopt.c | 98 +++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 3 +- 6 files changed, 190 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/tcp_authopt.rst b/Documentation/networking/tcp_authopt.rst index 484f66f41ad5..cded87a70d05 100644 --- a/Documentation/networking/tcp_authopt.rst +++ b/Documentation/networking/tcp_authopt.rst @@ -35,10 +35,35 @@ Keys can be bound to remote addresses in a way that is similar to TCP_MD5.

RFC5925 requires that key ids do not overlap when tcp identifiers (addr/port) overlap. This is not enforced by linux, configuring ambiguous keys will result in packet drops and lost connections.

+Key selection +------------- + +On getsockopt(TCP_AUTHOPT) information is provided about keyid/rnextkeyid in +the last send packet and about the keyid/rnextkeyd in the last valid received +packet. + +By default the sending keyid is selected to match the "rnextkeyid" value sent +by the remote side. If that keyid is not available (or for new connections) a +random matching key is selected. + +If the `TCP_AUTHOPT_LOCK_KEYID` is set then the sending key is selected by the +`tcp_authopt.send_local_id` field and rnextkeyid is ignored. If no key with +local_id == send_local_id is configured then a random matching key is +selected. + +The current sending key is cached in the socket and will not change unless +requested by remote rnextkeyid or by setsockopt. + +The rnextkeyid value sent on the wire is usually the recv_id of the current +key used for sending. If the TCP_AUTHOPT_LOCK_RNEXTKEY flag is set in +`tcp_authopt.flags` the value of `tcp_authopt.send_rnextkeyid` is send +instead. This can be used to implement smooth rollover: the peer will switch +its keyid to the received rnextkeyid when it is available. + ABI Reference =============

.. kernel-doc:: include/uapi/linux/tcp.h :identifiers: tcp_authopt tcp_authopt_flag tcp_authopt_key tcp_authopt_key_flag tcp_authopt_alg diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h index ae7d6a1eab8d..9341e10ef542 100644 --- a/include/net/tcp_authopt.h +++ b/include/net/tcp_authopt.h @@ -66,10 +66,43 @@ struct tcp_authopt_info { u32 dst_isn; /** @rcv_sne: Recv-side Sequence Number Extension tracking tcp_sock.rcv_nxt */ u32 rcv_sne; /** @snd_sne: Send-side Sequence Number Extension tracking tcp_sock.snd_nxt */ u32 snd_sne; + + /** + * @send_keyid: keyid currently being sent + * + * This is controlled by userspace by userspace if + * TCP_AUTHOPT_FLAG_LOCK_KEYID, otherwise we try to match recv_rnextkeyid + */ + u8 send_keyid; + /** + * @send_rnextkeyid: rnextkeyid currently being sent + * + * This is controlled by userspace if TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID is set + */ + u8 send_rnextkeyid; + /** + * @recv_keyid: last keyid received from remote + * + * This is reported to userspace but has no other special behavior attached. + */ + u8 recv_keyid; + /** + * @recv_rnextkeyid: last rnextkeyid received from remote + * + * Linux tries to honor this unless TCP_AUTHOPT_FLAG_LOCK_KEYID is set + */ + u8 recv_rnextkeyid; + + /** + * @send_key: Current key used for sending, cached. + * + * Once a key is found it only changes by user or remote request. + */ + struct tcp_authopt_key_info *send_key; };

#ifdef CONFIG_TCP_AUTHOPT extern int sysctl_tcp_authopt; DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed); @@ -81,22 +114,23 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key); int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen); struct tcp_authopt_key_info *__tcp_authopt_select_key( const struct sock *sk, struct tcp_authopt_info *info, const struct sock *addr_sk, - u8 *rnextkeyid); + u8 *rnextkeyid, + bool locked); static inline struct tcp_authopt_key_info *tcp_authopt_select_key( const struct sock *sk, const struct sock *addr_sk, struct tcp_authopt_info **info, u8 *rnextkeyid) { if (static_branch_unlikely(&tcp_authopt_needed)) { *info = rcu_dereference(tcp_sk(sk)->authopt_info);

if (*info) - return __tcp_authopt_select_key(sk, *info, addr_sk, rnextkeyid); + return __tcp_authopt_select_key(sk, *info, addr_sk, rnextkeyid, true); } return NULL; } int tcp_authopt_hash( char *hash_location, diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 76d7be6b27f4..e02176390519 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -346,10 +346,24 @@ struct tcp_diag_md5sig {

/** * enum tcp_authopt_flag - flags for `tcp_authopt.flags` */ enum tcp_authopt_flag { + /** + * @TCP_AUTHOPT_FLAG_LOCK_KEYID: keyid controlled by sockopt + * + * If this is set `tcp_authopt.send_keyid` is used to determined sending + * key. Otherwise a key with send_id == recv_rnextkeyid is preferred. + */ + TCP_AUTHOPT_FLAG_LOCK_KEYID = (1 << 0), + /** + * @TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID: Override rnextkeyid from userspace + * + * If this is set then `tcp_authopt.send_rnextkeyid` is sent on outbound + * packets. Other the recv_id of the current sending key is sent. + */ + TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID = (1 << 1), /** * @TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED: * Configure behavior of segments with TCP-AO coming from hosts for which no * key is configured. The default recommended by RFC is to silently accept * such connections. @@ -361,10 +375,27 @@ enum tcp_authopt_flag { * struct tcp_authopt - Per-socket options related to TCP Authentication Option */ struct tcp_authopt { /** @flags: Combination of &enum tcp_authopt_flag */ __u32 flags; + /** + * @send_keyid: `tcp_authopt_key.send_id` of preferred send key + * + * This is only used if `TCP_AUTHOPT_FLAG_LOCK_KEYID` is set. + */ + __u8 send_keyid; + /** + * @send_rnextkeyid: The rnextkeyid to send in packets + * + * This is controlled by the user iff TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID is + * set. Otherwise rnextkeyid is the recv_id of the current key. + */ + __u8 send_rnextkeyid; + /** @recv_keyid: A recently-received keyid value. Only for getsockopt. */ + __u8 recv_keyid; + /** @recv_rnextkeyid: A recently-received rnextkeyid value. Only for getsockopt. */ + __u8 recv_rnextkeyid; };

/** * enum tcp_authopt_key_flag - flags for `tcp_authopt.flags` * diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index aef63e35b56f..a02fe0d14b63 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -285,20 +285,76 @@ static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct tcp_authopt_i * * @sk: socket * @info: socket's tcp_authopt_info * @addr_sk: socket used for address lookup. Same as sk except for synack case * @rnextkeyid: value of rnextkeyid caller should write in packet + * @locked: If we're holding the socket lock. This is false for some timewait and reset cases * * Result is protected by RCU and can't be stored, it may only be passed to * tcp_authopt_hash and only under a single rcu_read_lock. */ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk, struct tcp_authopt_info *info, const struct sock *addr_sk, - u8 *rnextkeyid) + u8 *rnextkeyid, + bool locked) { - return tcp_authopt_lookup_send(info, addr_sk, -1); + struct tcp_authopt_key_info *key, *new_key = NULL; + + /* Listen sockets don't refer to any specific connection so we don't try + * to keep using the same key and ignore any received keyids. + */ + if (sk->sk_state == TCP_LISTEN) { + int send_keyid = -1; + + if (info->flags & TCP_AUTHOPT_FLAG_LOCK_KEYID) + send_keyid = info->send_keyid; + key = tcp_authopt_lookup_send(info, addr_sk, send_keyid); + if (key) + *rnextkeyid = key->recv_id; + + return key; + } + + if (locked) + key = rcu_dereference_protected(info->send_key, lockdep_sock_is_held(sk)); + else + key = rcu_dereference(info->send_key); + + /* Try to keep the same sending key unless user or peer requires a different key + * User request (via TCP_AUTHOPT_FLAG_LOCK_KEYID) always overrides peer request. + */ + if (info->flags & TCP_AUTHOPT_FLAG_LOCK_KEYID) { + int send_keyid = info->send_keyid; + + if (!key || key->send_id != send_keyid) + new_key = tcp_authopt_lookup_send(info, addr_sk, send_keyid); + } else { + if (!key || key->send_id != info->recv_rnextkeyid) + new_key = tcp_authopt_lookup_send(info, addr_sk, info->recv_rnextkeyid); + } + /* If no key found with specific send_id try anything else. */ + if (!key && !new_key) + new_key = tcp_authopt_lookup_send(info, addr_sk, -1); + + /* Update current key only if we hold the socket lock, otherwise we might + * store a pointer that goes stale + */ + if (new_key && key != new_key) { + key = new_key; + if (locked) + rcu_assign_pointer(info->send_key, key); + } + + if (key) { + if (info->flags & TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID) + *rnextkeyid = info->send_rnextkeyid; + else + *rnextkeyid = info->send_rnextkeyid = key->recv_id; + } + + return key; } EXPORT_SYMBOL(__tcp_authopt_select_key);

static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk) { @@ -321,10 +377,12 @@ static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk

return info; }

#define TCP_AUTHOPT_KNOWN_FLAGS ( \ + TCP_AUTHOPT_FLAG_LOCK_KEYID | \ + TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID | \ TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED)

/* Like copy_from_sockopt except tolerate different optlen for compatibility reasons * * If the src is shorter then it's from an old userspace and the rest of dst is @@ -381,18 +439,23 @@ int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen) info = __tcp_authopt_info_get_or_create(sk); if (IS_ERR(info)) return PTR_ERR(info);

info->flags = opt.flags & TCP_AUTHOPT_KNOWN_FLAGS; + if (opt.flags & TCP_AUTHOPT_FLAG_LOCK_KEYID) + info->send_keyid = opt.send_keyid; + if (opt.flags & TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID) + info->send_rnextkeyid = opt.send_rnextkeyid;

return 0; }

int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_authopt_info *info; + struct tcp_authopt_key_info *send_key;

memset(opt, 0, sizeof(*opt)); sock_owned_by_me(sk); if (!sysctl_tcp_authopt) return -EPERM; @@ -400,10 +463,22 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt) info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk)); if (!info) return -ENOENT;

opt->flags = info->flags & TCP_AUTHOPT_KNOWN_FLAGS; + /* These keyids might be undefined, for example before connect. + * Reporting zero is not strictly correct because there are no reserved + * values. + */ + send_key = rcu_dereference_check(info->send_key, lockdep_sock_is_held(sk)); + if (send_key) + opt->send_keyid = send_key->send_id; + else + opt->send_keyid = 0; + opt->send_rnextkeyid = info->send_rnextkeyid; + opt->recv_keyid = info->recv_keyid; + opt->recv_rnextkeyid = info->recv_rnextkeyid;

return 0; }

/* Free key nicely, for living sockets */ @@ -411,10 +486,12 @@ static void tcp_authopt_key_del(struct sock *sk, struct tcp_authopt_info *info, struct tcp_authopt_key_info *key) { sock_owned_by_me(sk); hlist_del_rcu(&key->node); + if (rcu_dereference_protected(info->send_key, lockdep_sock_is_held(sk)) == key) + rcu_assign_pointer(info->send_key, NULL); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); }

/* Free info and keys. @@ -1439,11 +1516,11 @@ int __tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb, struct tcp NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); print_tcpao_notice("TCP Authentication Unexpected: Rejected", skb); return -EINVAL; } print_tcpao_notice("TCP Authentication Unexpected: Accepted", skb); - return 0; + goto accept; }

/* bad inbound key len */ if (opt->len != TCPOLEN_AUTHOPT_OUTPUT) return -EINVAL; @@ -1456,8 +1533,23 @@ int __tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb, struct tcp NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTHOPTFAILURE); print_tcpao_notice("TCP Authentication Failed", skb); return -EINVAL; }

+accept: + /* Doing this for all valid packets will results in keyids temporarily + * flipping back and forth if packets are reordered or retransmitted + * but keys should eventually stabilize. + * + * This is connection-specific so don't store for listen sockets. + * + * We could store rnextkeyid from SYN in a request sock and use it for + * the SYNACK but we don't. + */ + if (sk->sk_state != TCP_LISTEN) { + info->recv_keyid = opt->keyid; + info->recv_rnextkeyid = opt->rnextkeyid; + } + return 1; } EXPORT_SYMBOL(__tcp_authopt_inbound_check); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 21971f5fa40e..2165b95ff7ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -664,11 +664,11 @@ static int tcp_v4_authopt_handle_reply(const struct sock *sk, info = tcp_twsk(sk)->tw_authopt_info; else info = tcp_sk(sk)->authopt_info; if (!info) return 0; - key_info = __tcp_authopt_select_key(sk, info, sk, &rnextkeyid); + key_info = __tcp_authopt_select_key(sk, info, sk, &rnextkeyid, false); if (!key_info) return 0; *optptr = htonl((TCPOPT_AUTHOPT << 24) | (TCPOLEN_AUTHOPT_OUTPUT << 16) | (key_info->send_id << 8) | diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 68f9545e4347..bb21f11f4246 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -920,11 +920,12 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 else authopt_info = rcu_dereference(tcp_sk(sk)->authopt_info);

if (authopt_info) { authopt_key_info = __tcp_authopt_select_key(sk, authopt_info, sk, - &authopt_rnextkeyid); + &authopt_rnextkeyid, + false); if (authopt_key_info) { tot_len += TCPOLEN_AUTHOPT_OUTPUT; /* Don't use MD5 */ key = NULL; }

This is a parallel feature to tcp_md5sig.tcpm_ifindex support and allows applications to server multiple VRFs with a single socket.

The ifindex argument must be the ifindex of a VRF device and must match exactly, keys with ifindex == 0 (outside of VRF) will not match for connections inside a VRF.

Keys without the TCP_AUTHOPT_KEY_IFINDEX will ignore ifindex and match both inside and outside VRF.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- include/net/tcp_authopt.h | 2 ++ include/uapi/linux/tcp.h | 11 ++++++ net/ipv4/tcp_authopt.c | 76 +++++++++++++++++++++++++++++++++++---- 3 files changed, 82 insertions(+), 7 deletions(-)

diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h index 9341e10ef542..072d5383f14b 100644 --- a/include/net/tcp_authopt.h +++ b/include/net/tcp_authopt.h @@ -39,10 +39,12 @@ struct tcp_authopt_key_info { u8 alg_id; /** @keylen: Same as &tcp_authopt_key.keylen */ u8 keylen; /** @key: Same as &tcp_authopt_key.key */ u8 key[TCP_AUTHOPT_MAXKEYLEN]; + /** @l3index: Same as &tcp_authopt_key.ifindex */ + int l3index; /** @addr: Same as &tcp_authopt_key.addr */ struct sockaddr_storage addr; /** @alg: Algorithm implementation matching alg_id */ struct tcp_authopt_alg_imp *alg; }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index e02176390519..a7f5f918ed5a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -400,15 +400,17 @@ struct tcp_authopt { * enum tcp_authopt_key_flag - flags for `tcp_authopt.flags` * * @TCP_AUTHOPT_KEY_DEL: Delete the key and ignore non-id fields * @TCP_AUTHOPT_KEY_EXCLUDE_OPTS: Exclude TCP options from signature * @TCP_AUTHOPT_KEY_ADDR_BIND: Key only valid for `tcp_authopt.addr` + * @TCP_AUTHOPT_KEY_IFINDEX: Key only valid for `tcp_authopt.ifindex` */ enum tcp_authopt_key_flag { TCP_AUTHOPT_KEY_DEL = (1 << 0), TCP_AUTHOPT_KEY_EXCLUDE_OPTS = (1 << 1), TCP_AUTHOPT_KEY_ADDR_BIND = (1 << 2), + TCP_AUTHOPT_KEY_IFINDEX = (1 << 3), };

/** * enum tcp_authopt_alg - Algorithms for TCP Authentication Option */ @@ -450,10 +452,19 @@ struct tcp_authopt_key { * @addr: Key is only valid for this address * * Ignored unless TCP_AUTHOPT_KEY_ADDR_BIND flag is set */ struct __kernel_sockaddr_storage addr; + /** + * @ifindex: ifindex of vrf (l3mdev_master) interface + * + * If the TCP_AUTHOPT_KEY_IFINDEX flag is set then key only applies for + * connections through this interface. Interface must be an vrf master. + * + * This is similar to `tcp_msg5sig.tcpm_ifindex` + */ + int ifindex; };

/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */

#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c index a02fe0d14b63..f497537ce16c 100644 --- a/net/ipv4/tcp_authopt.c +++ b/net/ipv4/tcp_authopt.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-or-later

+#include "linux/net.h" #include <linux/kernel.h> #include <net/tcp.h> #include <net/tcp_authopt.h> #include <crypto/hash.h>

@@ -190,10 +191,14 @@ static bool tcp_authopt_key_match_exact(struct tcp_authopt_key_info *info, { if (info->send_id != key->send_id) return false; if (info->recv_id != key->recv_id) return false; + if ((info->flags & TCP_AUTHOPT_KEY_IFINDEX) != (key->flags & TCP_AUTHOPT_KEY_IFINDEX)) + return false; + if ((info->flags & TCP_AUTHOPT_KEY_IFINDEX) && info->l3index != key->ifindex) + return false; if ((info->flags & TCP_AUTHOPT_KEY_ADDR_BIND) != (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND)) return false; if (info->flags & TCP_AUTHOPT_KEY_ADDR_BIND) if (!ipvx_addr_match(&info->addr, &key->addr)) return false; @@ -257,26 +262,49 @@ static struct tcp_authopt_key_info *tcp_authopt_key_lookup_exact(const struct so return key_info;

return NULL; }

+static bool better_key_match(struct tcp_authopt_key_info *old, struct tcp_authopt_key_info *new) +{ + if (!old) + return true; + + /* l3index always overrides non-l3index */ + if (old->l3index && new->l3index == 0) + return false; + if (old->l3index == 0 && new->l3index) + return true; + + return false; +} + static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct tcp_authopt_info *info, const struct sock *addr_sk, int send_id) { struct tcp_authopt_key_info *result = NULL; struct tcp_authopt_key_info *key; + int l3index = -1;

hlist_for_each_entry_rcu(key, &info->head, node, 0) { if (send_id >= 0 && key->send_id != send_id) continue; if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND) if (!tcp_authopt_key_match_sk_addr(key, addr_sk)) continue; - if (result && net_ratelimit()) - pr_warn("ambiguous tcp authentication keys configured for send\n"); - result = key; + if (key->flags & TCP_AUTHOPT_KEY_IFINDEX) { + if (l3index < 0) + l3index = l3mdev_master_ifindex_by_index(sock_net(addr_sk), + addr_sk->sk_bound_dev_if); + if (l3index != key->l3index) + continue; + } + if (better_key_match(result, key)) + result = key; + else if (result) + net_warn_ratelimited("ambiguous tcp authentication keys configured for send\n"); }

return result; }

@@ -527,18 +555,20 @@ void tcp_authopt_clear(struct sock *sk) }

#define TCP_AUTHOPT_KEY_KNOWN_FLAGS ( \ TCP_AUTHOPT_KEY_DEL | \ TCP_AUTHOPT_KEY_EXCLUDE_OPTS | \ - TCP_AUTHOPT_KEY_ADDR_BIND) + TCP_AUTHOPT_KEY_ADDR_BIND | \ + TCP_AUTHOPT_KEY_IFINDEX)

int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen) { struct tcp_authopt_key opt; struct tcp_authopt_info *info; struct tcp_authopt_key_info *key_info, *old_key_info; struct tcp_authopt_alg_imp *alg; + int l3index = 0; int err;

sock_owned_by_me(sk); if (!sysctl_tcp_authopt) return -EPERM; @@ -584,10 +614,24 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen) return -EINVAL; err = tcp_authopt_alg_require(alg); if (err) return err;

+ /* check ifindex is valid (zero is always valid) */ + if (opt.flags & TCP_AUTHOPT_KEY_IFINDEX && opt.ifindex) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), opt.ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + rcu_read_unlock(); + + if (!l3index) + return -EINVAL; + } + key_info = sock_kmalloc(sk, sizeof(*key_info), GFP_KERNEL | __GFP_ZERO); if (!key_info) return -ENOMEM; /* If an old key exists with exact ID then remove and replace. * RCU-protected readers might observe both and pick any. @@ -601,10 +645,11 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen) key_info->alg_id = opt.alg; key_info->alg = alg; key_info->keylen = opt.keylen; memcpy(key_info->key, opt.key, opt.keylen); memcpy(&key_info->addr, &opt.addr, sizeof(key_info->addr)); + key_info->l3index = l3index; hlist_add_head_rcu(&key_info->node, &info->head);

return 0; }

@@ -1436,21 +1481,38 @@ static struct tcp_authopt_key_info *tcp_authopt_lookup_recv(struct sock *sk, struct tcp_authopt_info *info, int recv_id) { struct tcp_authopt_key_info *result = NULL; struct tcp_authopt_key_info *key; + int l3index = -1;

/* multiple matches will cause occasional failures */ hlist_for_each_entry_rcu(key, &info->head, node, 0) { if (recv_id >= 0 && key->recv_id != recv_id) continue; if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND && !tcp_authopt_key_match_skb_addr(key, skb)) continue; - if (result && net_ratelimit()) - pr_warn("ambiguous tcp authentication keys configured for receive\n"); - result = key; + if (key->flags & TCP_AUTHOPT_KEY_IFINDEX) { + if (l3index < 0) { + if (skb->protocol == htons(ETH_P_IP)) { + l3index = inet_sdif(skb) ? inet_iif(skb) : 0; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + l3index = inet6_sdif(skb) ? inet6_iif(skb) : 0; + } else { + WARN_ONCE(1, "unexpected skb->protocol=%x", skb->protocol); + continue; + } + } + + if (l3index != key->l3index) + continue; + } + if (better_key_match(result, key)) + result = key; + else if (result) + net_warn_ratelimited("ambiguous tcp authentication keys configured for send\n"); }

return result; }

This is in preparation for reusing the same option for TCP-AO

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- tools/testing/selftests/net/nettest.c | 50 +++++++++++++-------------- 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index b599003eb5ba..525a439ce3b3 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -93,17 +93,17 @@ struct sock_args { const char *clientns; const char *serverns;

const char *password; const char *client_pw; - /* prefix for MD5 password */ - const char *md5_prefix_str; + /* prefix for MD5/AO*/ + const char *key_addr_prefix_str; union { struct sockaddr_in v4; struct sockaddr_in6 v6; - } md5_prefix; - unsigned int prefix_len; + } key_addr; + unsigned int key_addr_prefix_len; /* 0: default, -1: force off, +1: force on */ int bind_key_ifindex;

/* expected addresses and device index for connection */ const char *expected_dev; @@ -263,16 +263,16 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args int rc;

md5sig.tcpm_keylen = keylen; memcpy(md5sig.tcpm_key, args->password, keylen);

- if (args->prefix_len) { + if (args->key_addr_prefix_len) { opt = TCP_MD5SIG_EXT; md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_PREFIX;

- md5sig.tcpm_prefixlen = args->prefix_len; - addr = &args->md5_prefix; + md5sig.tcpm_prefixlen = args->key_addr_prefix_len; + addr = &args->key_addr; } memcpy(&md5sig.tcpm_addr, addr, alen);

if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { opt = TCP_MD5SIG_EXT; @@ -308,17 +308,17 @@ static int tcp_md5_remote(int sd, struct sock_args *args) int alen;

switch (args->version) { case AF_INET: sin.sin_port = htons(args->port); - sin.sin_addr = args->md5_prefix.v4.sin_addr; + sin.sin_addr = args->key_addr.v4.sin_addr; addr = &sin; alen = sizeof(sin); break; case AF_INET6: sin6.sin6_port = htons(args->port); - sin6.sin6_addr = args->md5_prefix.v6.sin6_addr; + sin6.sin6_addr = args->key_addr.v6.sin6_addr; addr = &sin6; alen = sizeof(sin6); break; default: log_error("unknown address family\n"); @@ -681,11 +681,11 @@ enum addr_type { ADDR_TYPE_LOCAL, ADDR_TYPE_REMOTE, ADDR_TYPE_MCAST, ADDR_TYPE_EXPECTED_LOCAL, ADDR_TYPE_EXPECTED_REMOTE, - ADDR_TYPE_MD5_PREFIX, + ADDR_TYPE_KEY_PREFIX, };

static int convert_addr(struct sock_args *args, const char *_str, enum addr_type atype) { @@ -721,32 +721,32 @@ static int convert_addr(struct sock_args *args, const char *_str, break; case ADDR_TYPE_EXPECTED_REMOTE: desc = "expected remote"; addr = &args->expected_raddr; break; - case ADDR_TYPE_MD5_PREFIX: - desc = "md5 prefix"; + case ADDR_TYPE_KEY_PREFIX: + desc = "key addr prefix"; if (family == AF_INET) { - args->md5_prefix.v4.sin_family = AF_INET; - addr = &args->md5_prefix.v4.sin_addr; + args->key_addr.v4.sin_family = AF_INET; + addr = &args->key_addr.v4.sin_addr; } else if (family == AF_INET6) { - args->md5_prefix.v6.sin6_family = AF_INET6; - addr = &args->md5_prefix.v6.sin6_addr; + args->key_addr.v6.sin6_family = AF_INET6; + addr = &args->key_addr.v6.sin6_addr; } else return 1;

sep = strchr(str, '/'); if (sep) { *sep = '\0'; sep++; if (str_to_uint(sep, 1, pfx_len_max, - &args->prefix_len) != 0) { - fprintf(stderr, "Invalid port\n"); + &args->key_addr_prefix_len) != 0) { + fprintf(stderr, "Invalid prefix\n"); return 1; } } else { - args->prefix_len = 0; + args->key_addr_prefix_len = 0; } break; default: log_error("unknown address type\n"); exit(1); @@ -811,13 +811,13 @@ static int validate_addresses(struct sock_args *args)

if (args->remote_addr_str && convert_addr(args, args->remote_addr_str, ADDR_TYPE_REMOTE) < 0) return 1;

- if (args->md5_prefix_str && - convert_addr(args, args->md5_prefix_str, - ADDR_TYPE_MD5_PREFIX) < 0) + if (args->key_addr_prefix_str && + convert_addr(args, args->key_addr_prefix_str, + ADDR_TYPE_KEY_PREFIX) < 0) return 1;

if (args->expected_laddr_str && convert_addr(args, args->expected_laddr_str, ADDR_TYPE_EXPECTED_LOCAL)) @@ -1992,11 +1992,11 @@ int main(int argc, char *argv[]) break; case 'X': args.client_pw = optarg; break; case 'm': - args.md5_prefix_str = optarg; + args.key_addr_prefix_str = optarg; break; case 'S': args.use_setsockopt = 1; break; case 'C': @@ -2048,17 +2048,17 @@ int main(int argc, char *argv[]) return 1; } }

if (args.password && - ((!args.has_remote_ip && !args.md5_prefix_str) || + ((!args.has_remote_ip && !args.key_addr_prefix_str) || args.type != SOCK_STREAM)) { log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); return 1; }

- if (args.md5_prefix_str && !args.password) { + if (args.key_addr_prefix_str && !args.password) { log_error("Prefix range for MD5 protection specified without a password\n"); return 1; }

if (iter == 0) {

Add support for configuring TCP Authentication Option. Only a single key is supported with default options.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- tools/testing/selftests/net/nettest.c | 75 ++++++++++++++++++++++++--- 1 file changed, 69 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index 525a439ce3b3..837a45921845 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -103,10 +103,12 @@ struct sock_args { } key_addr; unsigned int key_addr_prefix_len; /* 0: default, -1: force off, +1: force on */ int bind_key_ifindex;

+ const char *authopt_password; + /* expected addresses and device index for connection */ const char *expected_dev; const char *expected_server_dev; int expected_ifindex;

@@ -253,10 +255,54 @@ static int switch_ns(const char *ns) close(fd);

return ret; }

+static int tcp_set_authopt(int sd, struct sock_args *args) +{ + struct tcp_authopt_key key; + int rc; + + memset(&key, 0, sizeof(key)); + strcpy((char *)key.key, args->authopt_password); + key.keylen = strlen(args->authopt_password); + key.alg = TCP_AUTHOPT_ALG_HMAC_SHA_1_96; + + if (args->key_addr_prefix_str) { + key.flags |= TCP_AUTHOPT_KEY_ADDR_BIND; + switch (args->version) { + case AF_INET: + memcpy(&key.addr, &args->key_addr.v4, sizeof(args->key_addr.v4)); + break; + case AF_INET6: + memcpy(&key.addr, &args->key_addr.v6, sizeof(args->key_addr.v6)); + break; + default: + log_error("unknown address family\n"); + exit(1); + } + if (args->key_addr_prefix_len) { + log_error("TCP_AUTHOPT does not support prefix length\n"); + exit(1); + } + } + + if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { + key.flags |= TCP_AUTHOPT_KEY_IFINDEX; + key.ifindex = args->ifindex; + log_msg("TCP_AUTHOPT_KEY_IFINDEX set ifindex=%d\n", key.ifindex); + } else { + log_msg("TCP_AUTHOPT_KEY_IFINDEX off\n", key.ifindex); + } + + rc = setsockopt(sd, IPPROTO_TCP, TCP_AUTHOPT_KEY, &key, sizeof(key)); + if (rc < 0) + log_err_errno("setsockopt(TCP_AUTHOPT_KEY)"); + + return rc; +} + static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args) { int keylen = strlen(args->password); struct tcp_md5sig md5sig = {}; int opt = TCP_MD5SIG; @@ -1514,10 +1560,15 @@ static int do_server(struct sock_args *args, int ipc_fd) if (args->password && tcp_md5_remote(lsd, args)) { close(lsd); goto err_exit; }

+ if (args->authopt_password && tcp_set_authopt(lsd, args)) { + close(lsd); + goto err_exit; + } + ipc_write(ipc_fd, 1); while (1) { log_msg("waiting for client connection.\n"); FD_ZERO(&rfds); FD_SET(lsd, &rfds); @@ -1636,10 +1687,13 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) goto out;

if (args->password && tcp_md5sig(sd, addr, alen, args)) goto err;

+ if (args->authopt_password && tcp_set_authopt(sd, args)) + goto err; + if (args->bind_test_only) goto out;

if (connect(sd, addr, alen) < 0) { if (errno != EINPROGRESS) { @@ -1825,11 +1879,11 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)

wait(&status); return client_status; }

-#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:A:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002

static struct option long_opts[] = { {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, @@ -1869,14 +1923,15 @@ static void print_usage(char *prog) " -L len send random message of given length\n" " -n num number of times to send message\n" "\n" " -M password use MD5 sum protection\n" " -X password MD5 password for client mode\n" - " -m prefix/len prefix and length to use for MD5 key\n" - " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" - " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" + " -m prefix/len prefix and length to use for MD5/AO key\n" + " --no-bind-key-ifindex: Force disable binding key to ifindex\n" + " --force-bind-key-ifindex: Force enable binding key to ifindex\n" " (default: only if -I is passed)\n" + " -A password use RFC5925 TCP Authentication Option with password\n" "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" " -0 addr Expected local address\n" @@ -1994,10 +2049,13 @@ int main(int argc, char *argv[]) args.client_pw = optarg; break; case 'm': args.key_addr_prefix_str = optarg; break; + case 'A': + args.authopt_password = optarg; + break; case 'S': args.use_setsockopt = 1; break; case 'C': args.use_cmsg = 1; @@ -2054,12 +2112,17 @@ int main(int argc, char *argv[]) args.type != SOCK_STREAM)) { log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); return 1; }

- if (args.key_addr_prefix_str && !args.password) { - log_error("Prefix range for MD5 protection specified without a password\n"); + if (args.key_addr_prefix_str && !args.password && !args.authopt_password) { + log_error("Prefix range for authentication requires -M or -A\n"); + return 1; + } + + if (args.key_addr_prefix_len && args.authopt_password) { + log_error("TCP-AO does not support prefix match, only full address\n"); return 1; }

if (iter == 0) { fprintf(stderr, "Invalid number of messages to send\n");

Tests are mostly copied from tcp_md5 with minor changes.

It covers VRF support but only based on binding multiple servers: not multiple keys bound to different interfaces.

Also add a specific -t tcp_authopt to run only these tests specifically.

Signed-off-by: Leonard Crestez cdleonard@gmail.com --- tools/testing/selftests/net/fcnal-test.sh | 249 ++++++++++++++++++++++ 1 file changed, 249 insertions(+)

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 3313566ce906..d7afd9f40848 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -800,10 +800,252 @@ ipv4_ping() }

################################################################################ # IPv4 TCP

+# +# TCP Authentication Option Tests +# + +# try to enable tcp_authopt sysctl +enable_tcp_authopt() +{ + if [[ -e /proc/sys/net/ipv4/tcp_authopt ]]; then + sysctl -w net.ipv4.tcp_authopt=1 + fi +} + +# check if tcp_authopt is compiled with a client-side bind test +has_tcp_authopt() +{ + run_cmd_nsb nettest -b -A ${MD5_PW} -r ${NSA_IP} +} + +ipv4_tcp_authopt_novrf() +{ + enable_tcp_authopt + if ! has_tcp_authopt; then + echo "TCP-AO appears to be missing, skip" + return 0 + fi + + log_start + run_cmd nettest -s -A ${MD5_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: Single address config" + + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 2 "AO: Server no config, client uses password" + + log_start + run_cmd nettest -s -A ${MD5_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_WRONG_PW} + log_test $? 2 "AO: Client uses wrong password" + + log_start + run_cmd nettest -s -A ${MD5_PW} -m ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 2 "AO: Client address does not match address configured on server" + + # no prefixlen for AO yet +} + +ipv6_tcp_authopt_novrf() +{ + enable_tcp_authopt + if ! has_tcp_authopt; then + echo "TCP-AO appears to be missing, skip" + return 0 + fi + + log_start + run_cmd nettest -6 -s -A ${MD5_PW} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 0 "AO: Simple correct config" + + log_start + run_cmd nettest -6 -s + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 2 "AO: Server no config, client uses password" + + log_start + run_cmd nettest -6 -s -A ${MD5_PW} -m ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_WRONG_PW} + log_test $? 2 "AO: Client uses wrong password" + + log_start + run_cmd nettest -6 -s -A ${MD5_PW} -m ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 2 "AO: Client address does not match address configured on server" + + # no prefixlen for AO yet +} + +ipv4_tcp_authopt_vrf() +{ + enable_tcp_authopt + if ! has_tcp_authopt; then + echo "TCP-AO appears to be missing, skip" + return 0 + fi + + log_start + run_cmd nettest -s -I ${VRF} -A ${MD5_PW} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Simple config" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP} & + run_cmd nettest -s -A ${MD5_WRONG_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Servers in default-VRF and VRF, client in VRF" + + log_start + run_cmd nettest -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP} & + run_cmd nettest -s -A ${MD5_WRONG_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -A ${MD5_WRONG_PW} + log_test $? 0 "AO: VRF: Servers in default-VRF and VRF, client in default-VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP} & + run_cmd nettest -s -A ${MD5_WRONG_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 2 "AO: VRF: Servers in default VRF and VRF, conn in default-VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP} & + run_cmd nettest -s -A ${MD5_WRONG_PW} -m ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_WRONG_PW} + log_test $? 2 "AO: VRF: Servers in default VRF and VRF, conn in VRF with default-VRF pw" + + test_ipv4_tcp_authopt_vrf__global_server__bind_ifindex0 +} + +test_ipv4_tcp_authopt_vrf__global_server__bind_ifindex0() +{ + # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections + local old_tcp_l3mdev_accept + old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept) + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + log_start + run_cmd nettest -s -A ${MD5_PW} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 2 "AO: VRF: Global server, Key bound to ifindex=0 rejects VRF connection" + + log_start + run_cmd nettest -s -A ${MD5_PW} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection" + log_start + + run_cmd nettest -s -A ${MD5_PW} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Global server, key not bound to ifindex accepts VRF connection" + + log_start + run_cmd nettest -s -A ${MD5_PW} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Global server, key not bound to ifindex accepts non-VRF connection" + + # restore value + set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" +} + +ipv6_tcp_authopt_vrf() +{ + enable_tcp_authopt + if ! has_tcp_authopt; then + echo "TCP-AO appears to be missing, skip" + return 0 + fi + + log_start + run_cmd nettest -6 -s -I ${VRF} -A ${MD5_PW} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Simple config" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -6 -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP6} & + run_cmd nettest -6 -s -A ${MD5_WRONG_PW} -m ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 0 "AO: VRF: Servers in default-VRF and VRF, client in VRF" + + log_start + run_cmd nettest -6 -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP6} & + run_cmd nettest -6 -s -A ${MD5_WRONG_PW} -m ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -A ${MD5_WRONG_PW} + log_test $? 0 "AO: VRF: Servers in default-VRF and VRF, client in default-VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP6} & + run_cmd nettest -6 -s -A ${MD5_WRONG_PW} -m ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -A ${MD5_PW} + log_test $? 2 "AO: VRF: Servers in default VRF and VRF, conn in default-VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -I ${VRF} -A ${MD5_PW} -m ${NSB_IP6} & + run_cmd nettest -6 -s -A ${MD5_WRONG_PW} -m ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -A ${MD5_WRONG_PW} + log_test $? 2 "AO: VRF: Servers in default VRF and VRF, conn in VRF with default-VRF pw" +} + +only_tcp_authopt() +{ + log_section "TCP Authentication Option" + + setup + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + log_subsection "TCP-AO IPv4 no VRF" + ipv4_tcp_authopt_novrf + log_subsection "TCP-AO IPv6 no VRF" + ipv6_tcp_authopt_novrf + + setup "yes" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + log_subsection "TCP-AO IPv4 VRF" + ipv4_tcp_authopt_vrf + log_subsection "TCP-AO IPv6 VRF" + ipv6_tcp_authopt_vrf +} + # # MD5 tests without VRF # ipv4_tcp_md5_novrf() { @@ -1185,10 +1427,11 @@ ipv4_tcp_novrf() show_hint "Should fail 'Connection refused'" run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn"

ipv4_tcp_md5_novrf + ipv4_tcp_authopt_novrf }

ipv4_tcp_vrf() { local a @@ -1239,10 +1482,12 @@ ipv4_tcp_vrf() run_cmd nettest -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection"

# run MD5 tests ipv4_tcp_md5 + # run AO tests + ipv6_tcp_md5_vrf

# # enable VRF global server # log_subsection "VRF Global server enabled" @@ -2648,10 +2893,11 @@ ipv6_tcp_novrf() run_cmd nettest -6 -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" done

ipv6_tcp_md5_novrf + ipv6_tcp_authopt_novrf }

ipv6_tcp_vrf() { local a @@ -2718,10 +2964,12 @@ ipv6_tcp_vrf() run_cmd nettest -6 -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection"

# run MD5 tests ipv6_tcp_md5 + # run AO tests + ipv6_tcp_authopt_vrf

# # enable VRF global server # log_subsection "VRF Global server enabled" @@ -4062,10 +4310,11 @@ do ipv6_bind|bind6) ipv6_addr_bind;; ipv6_runtime) ipv6_runtime;; ipv6_netfilter) ipv6_netfilter;;

use_cases) use_cases;; + tcp_authopt) only_tcp_authopt;;

# setup namespaces and config, but do not run any tests setup) setup; exit 0;; vrf_setup) setup "yes"; exit 0;;