selftest: bpf: Test bpf_sk_assign_tcp_reqsk().

This commit adds a sample selftest to demonstrate how we can use
bpf_sk_assign_tcp_reqsk() as the backend of SYN Proxy.

The test creates IPv4/IPv6 x TCP connections and transfer messages
over them on lo with BPF tc prog attached.

The tc prog will process SYN and returns SYN+ACK with the following
ISN and TS.  In a real use case, this part will be done by other
hosts.

        MSB                                   LSB
  ISN:  | 31 ... 8 | 7 6 |   5 |    4 | 3 2 1 0 |
        |   Hash_1 | MSS | ECN | SACK |  WScale |

  TS:   | 31 ... 8 |          7 ... 0           |
        |   Random |           Hash_2           |

  WScale in SYN is reused in SYN+ACK.

The client returns ACK, and tc prog will recalculate ISN and TS
from ACK and validate SYN Cookie.

If it's valid, the prog calls kfunc to allocate a reqsk for skb and
configure the reqsk based on the argument created from SYN Cookie.

Later, the reqsk will be processed in cookie_v[46]_check() to create
a connection.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240115205514.68364-7-kuniyu@amazon.comSigned-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/bpf_kfuncs.h

@@ -51,6 +51,16 @@ extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clo
 extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 				      const __u8 *sun_path, __u32 sun_path__sz) __ksym;
 
+/* Description
+ *  Allocate and configure a reqsk and link it with a listener and skb.
+ * Returns
+ *  Error code
+ */
+struct sock;
+struct bpf_tcp_req_attrs;
+extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
+				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
+
 void *bpf_cast_to_kern_ctx(void *) __ksym;
 
 void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym;

tools/testing/selftests/bpf/config

@@ -81,6 +81,7 @@ CONFIG_NF_NAT=y
 CONFIG_RC_CORE=y
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
+CONFIG_SYN_COOKIES=y
 CONFIG_TEST_BPF=m
 CONFIG_USERFAULTFD=y
 CONFIG_VSOCKETS=y

tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdlib.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "test_tcp_custom_syncookie.skel.h"
+
+static struct test_tcp_custom_syncookie_case {
+	int family, type;
+	char addr[16];
+	char name[10];
+} test_cases[] = {
+	{
+		.name = "IPv4 TCP",
+		.family = AF_INET,
+		.type = SOCK_STREAM,
+		.addr = "127.0.0.1",
+	},
+	{
+		.name = "IPv6 TCP",
+		.family = AF_INET6,
+		.type = SOCK_STREAM,
+		.addr = "::1",
+	},
+};
+
+static int setup_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "ip"))
+		goto err;
+
+	if (!ASSERT_OK(write_sysctl("/proc/sys/net/ipv4/tcp_ecn", "1"),
+		       "write_sysctl"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int setup_tc(struct test_tcp_custom_syncookie *skel)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
+		    .prog_fd = bpf_program__fd(skel->progs.tcp_custom_syncookie));
+
+	qdisc_lo.ifindex = if_nametoindex("lo");
+	if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact"))
+		goto err;
+
+	if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach),
+		       "filter add dev lo ingress"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+#define msg "Hello World"
+#define msglen 11
+
+static void transfer_message(int sender, int receiver)
+{
+	char buf[msglen];
+	int ret;
+
+	ret = send(sender, msg, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "send"))
+		return;
+
+	memset(buf, 0, sizeof(buf));
+
+	ret = recv(receiver, buf, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "recv"))
+		return;
+
+	ret = strncmp(buf, msg, msglen);
+	if (!ASSERT_EQ(ret, 0, "strncmp"))
+		return;
+}
+
+static void create_connection(struct test_tcp_custom_syncookie_case *test_case)
+{
+	int server, client, child;
+
+	server = start_server(test_case->family, test_case->type, test_case->addr, 0, 0);
+	if (!ASSERT_NEQ(server, -1, "start_server"))
+		return;
+
+	client = connect_to_fd(server, 0);
+	if (!ASSERT_NEQ(client, -1, "connect_to_fd"))
+		goto close_server;
+
+	child = accept(server, NULL, 0);
+	if (!ASSERT_NEQ(child, -1, "accept"))
+		goto close_client;
+
+	transfer_message(client, child);
+	transfer_message(child, client);
+
+	close(child);
+close_client:
+	close(client);
+close_server:
+	close(server);
+}
+
+void test_tcp_custom_syncookie(void)
+{
+	struct test_tcp_custom_syncookie *skel;
+	int i;
+
+	if (setup_netns())
+		return;
+
+	skel = test_tcp_custom_syncookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (setup_tc(skel))
+		goto destroy_skel;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		if (!test__start_subtest(test_cases[i].name))
+			continue;
+
+		skel->bss->handled_syn = false;
+		skel->bss->handled_ack = false;
+
+		create_connection(&test_cases[i]);
+
+		ASSERT_EQ(skel->bss->handled_syn, true, "SYN is not handled at tc.");
+		ASSERT_EQ(skel->bss->handled_ack, true, "ACK is not handled at tc");
+	}
+
+destroy_skel:
+	system("tc qdisc del dev lo clsact");
+
+	test_tcp_custom_syncookie__destroy(skel);
+}

tools/testing/selftests/bpf/progs/bpf_tracing_net.h

@@ -51,9 +51,25 @@
 #define ICSK_TIME_LOSS_PROBE	5
 #define ICSK_TIME_REO_TIMEOUT	6
 
+#define ETH_ALEN		6
 #define ETH_HLEN		14
+#define ETH_P_IP		0x0800
 #define ETH_P_IPV6		0x86DD
 
+#define NEXTHDR_TCP		6
+
+#define TCPOPT_NOP		1
+#define TCPOPT_EOL		0
+#define TCPOPT_MSS		2
+#define TCPOPT_WINDOW		3
+#define TCPOPT_TIMESTAMP	8
+#define TCPOPT_SACK_PERM	4
+
+#define TCPOLEN_MSS		4
+#define TCPOLEN_WINDOW		3
+#define TCPOLEN_TIMESTAMP	10
+#define TCPOLEN_SACK_PERM	2
+
 #define CHECKSUM_NONE		0
 #define CHECKSUM_PARTIAL	3
 

tools/testing/selftests/bpf/progs/test_siphash.h

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_SIPHASH_H
+#define _TEST_SIPHASH_H
+
+/* include/linux/bitops.h */
+static inline u64 rol64(u64 word, unsigned int shift)
+{
+	return (word << (shift & 63)) | (word >> ((-shift) & 63));
+}
+
+/* include/linux/siphash.h */
+#define SIPHASH_PERMUTATION(a, b, c, d) ( \
+	(a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \
+	(c) += (d), (d) = rol64((d), 16), (d) ^= (c), \
+	(a) += (d), (d) = rol64((d), 21), (d) ^= (a), \
+	(c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32))
+
+#define SIPHASH_CONST_0 0x736f6d6570736575ULL
+#define SIPHASH_CONST_1 0x646f72616e646f6dULL
+#define SIPHASH_CONST_2 0x6c7967656e657261ULL
+#define SIPHASH_CONST_3 0x7465646279746573ULL
+
+/* lib/siphash.c */
+#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3)
+
+#define PREAMBLE(len) \
+	u64 v0 = SIPHASH_CONST_0; \
+	u64 v1 = SIPHASH_CONST_1; \
+	u64 v2 = SIPHASH_CONST_2; \
+	u64 v3 = SIPHASH_CONST_3; \
+	u64 b = ((u64)(len)) << 56; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+static inline u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+#endif

tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_TCP_SYNCOOKIE_H
+#define _TEST_TCP_SYNCOOKIE_H
+
+#define __packed __attribute__((__packed__))
+#define __force
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+#define swap(a, b)				\
+	do {					\
+		typeof(a) __tmp = (a);		\
+		(a) = (b);			\
+		(b) = __tmp;			\
+	} while (0)
+
+#define swap_array(a, b)				\
+	do {						\
+		typeof(a) __tmp[sizeof(a)];		\
+		__builtin_memcpy(__tmp, a, sizeof(a));	\
+		__builtin_memcpy(a, b, sizeof(a));	\
+		__builtin_memcpy(b, __tmp, sizeof(a));	\
+	} while (0)
+
+/* asm-generic/unaligned.h */
+#define __get_unaligned_t(type, ptr) ({						\
+	const struct { type x; } __packed * __pptr = (typeof(__pptr))(ptr);	\
+	__pptr->x;								\
+})
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return bpf_ntohs(__get_unaligned_t(__be16, p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return bpf_ntohl(__get_unaligned_t(__be32, p));
+}
+
+/* lib/checksum.c */
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum)from64to32(s);
+}
+
+/* asm-generic/checksum.h */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/* net/ipv6/ip6_checksum.c */
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, __u8 proto, __wsum csum)
+{
+	int carry;
+	__u32 ulen;
+	__u32 uproto;
+	__u32 sum = (__force u32)csum;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	ulen = (__force u32)bpf_htonl((__u32)len);
+	sum += ulen;
+	carry = (sum < ulen);
+	sum += carry;
+
+	uproto = (__force u32)bpf_htonl(proto);
+	sum += uproto;
+	carry = (sum < uproto);
+	sum += carry;
+
+	return csum_fold((__force __wsum)sum);
+}
+#endif