[PATCH bpf-next v4 0/2] bpf: Fix bpf_get/setsockopt to tos for ipv4-mapped ipv6 socket

[PATCH bpf-next v4 0/2] bpf: Fix bpf_get/setsockopt to tos for ipv4-mapped ipv6 socket

[Leon Hwang]

When TCP over IPv4 via INET6 API, sk->sk_family is AF_INET6, but it is a
v4 pkt. inet_csk(sk)->icsk_af_ops is ipv6_mapped and use ip_queue_xmit.
The tos sockopt does not work for bpf [get,set]sockopt() helpers.

Changelog:
v3 -> v4:
* Add 'sk->sk_type != SOCK_RAW && !ipv6_only_sock(sk)' check.
* Re-implement test with LLM assistance.
* v3: https://lore.kernel.org/all/20240914103226.71109-1-zhoufeng.zf@bytedance.com/

v2->v3:
* Use sk_is_inet() helper. (Eric Dumazet)
* https://lore.kernel.org/bpf/CANn89i+9GmBLCdgsfH=WWe-tyFYpiO27wONyxaxiU6aOBC6G8g@mail.gmail.com/T/

v1->v2:
* Fix compilation error. (kernel test robot)
* https://lore.kernel.org/bpf/202408152058.YXAnhLgZ-lkp@intel.com/T/

Leon Hwang (2):
  bpf: Fix bpf_get/setsockopt to tos for ipv4-mapped ipv6 socket
  selftests/bpf: Add test to verify the fix for bpf_setsockopt() helper

 net/core/filter.c                             | 15 +++-
 .../selftests/bpf/prog_tests/setget_sockopt.c | 78 +++++++++++++++++++
 .../selftests/bpf/progs/setget_sockopt.c      | 23 ++++++
 3 files changed, 115 insertions(+), 1 deletion(-)

-- 
2.54.0

[PATCH bpf-next v4 1/2] bpf: Fix bpf_get/setsockopt to tos for ipv4-mapped ipv6 socket

[Leon Hwang]

When TCP over IPv4 via INET6 API, bpf_get/setsockopt with ipv4 will
fail, because sk->sk_family is AF_INET6. With ipv6 will success, not
take effect, because inet_csk(sk)->icsk_af_ops is ipv6_mapped and
use ip_queue_xmit, inet_sk(sk)->tos.

To relax this restriction, allow getting/setting tos for those possible
ipv4-mapped ipv6 sockets.

Fixes: ee7f1e1302f5 ("bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()")
Signed-off-by: Feng Zhou <zhoufeng.zf@bytedance.com>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 net/core/filter.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 9590877b0714..57b00c6cc8cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5544,11 +5544,24 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 				 KERNEL_SOCKPTR(optval), *optlen);
 }
 
+static bool sk_allows_sol_ip_sockopt(struct sock *sk)
+{
+	switch (sk->sk_family) {
+	case AF_INET:
+		return true;
+	case AF_INET6:
+		/* Allow getting/setting sockopt for possible ipv4-mapped ipv6 socket. */
+		return sk->sk_type != SOCK_RAW && !ipv6_only_sock(sk);
+	default:
+		return false;
+	}
+}
+
 static int sol_ip_sockopt(struct sock *sk, int optname,
 			  char *optval, int *optlen,
 			  bool getopt)
 {
-	if (sk->sk_family != AF_INET)
+	if (!sk_allows_sol_ip_sockopt(sk))
 		return -EINVAL;
 
 	switch (optname) {
-- 
2.54.0

[PATCH bpf-next v4 2/2] selftests/bpf: Add test to verify the fix for bpf_setsockopt() helper

[Leon Hwang]

Verify the fix by:

1. Attach cgroup sockops prog.
2. Build a tcp connection using ipv4 addr in ipv6 socket.
3. Verify the return value of bpf_setsockopt() helper.

Assisted-by: Codex:gpt-5.5-xhigh
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 .../selftests/bpf/prog_tests/setget_sockopt.c | 78 +++++++++++++++++++
 .../selftests/bpf/progs/setget_sockopt.c      | 23 ++++++
 2 files changed, 101 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index 77fe1bfb7504..4e91d9b615ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -199,6 +199,83 @@ static void test_nonstandard_opt(int family)
 	bpf_link__destroy(getsockopt_link);
 }
 
+static int connect_to_v4mapped_v6_fd(int server_fd)
+{
+	struct sockaddr_storage addr;
+	struct sockaddr_in *addr4 = (void *)&addr;
+	socklen_t addrlen = sizeof(addr);
+	struct sockaddr_in6 addr6 = {};
+	int fd = -1, v6only = 0, err;
+
+	err = getsockname(server_fd, (struct sockaddr *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "getsockname"))
+		return -1;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (!ASSERT_GE(fd, 0, "socket"))
+		return -1;
+
+	err = settimeo(fd, 0);
+	if (!ASSERT_OK(err, "settimeo"))
+		goto err_out;
+
+	err = setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &v6only, sizeof(v6only));
+	if (!ASSERT_OK(err, "clear_v6only"))
+		goto err_out;
+
+	addr6.sin6_family = AF_INET6;
+	addr6.sin6_port = addr4->sin_port;
+	addr6.sin6_addr.s6_addr[10] = 0xff;
+	addr6.sin6_addr.s6_addr[11] = 0xff;
+	memcpy(&addr6.sin6_addr.s6_addr[12], &addr4->sin_addr, sizeof(addr4->sin_addr));
+
+	err = connect(fd, (struct sockaddr *)&addr6, sizeof(addr6));
+	if (!ASSERT_OK(err, "connect"))
+		goto err_out;
+
+	return fd;
+
+err_out:
+	close(fd);
+	return -1;
+}
+
+static void test_v4mapped_v6_ip_tos(void)
+{
+	struct setget_sockopt__bss *bss = skel->bss;
+	int sfd = -1, fd = -1, got = 0, exp = 0x1c;
+	socklen_t optlen;
+
+	memset(bss, 0, sizeof(*bss));
+	bss->v4mapped_v6_ip_tos_enable = 1;
+	bss->v4mapped_v6_ip_tos_ret = -1;
+	bss->v4mapped_v6_ip_tos_val = exp;
+
+	sfd = start_server(AF_INET, SOCK_STREAM, addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		goto err_out;
+
+	fd = connect_to_v4mapped_v6_fd(sfd);
+	if (!ASSERT_GE(fd, 0, "connect_to_v4mapped_v6_fd"))
+		goto err_out;
+
+	ASSERT_GT(bss->v4mapped_v6_ip_tos_cnt, 0, "v4mapped_v6_ip_tos_cnt");
+	ASSERT_EQ(bss->v4mapped_v6_ip_tos_ret, 0, "v4mapped_v6_ip_tos_ret");
+
+	optlen = sizeof(got);
+	if (!ASSERT_OK(getsockopt(fd, SOL_IP, IP_TOS, &got, &optlen), "getsockopt_ip_tos"))
+		goto err_out;
+
+	ASSERT_EQ(got, exp, "ip_tos");
+
+err_out:
+	bss->v4mapped_v6_ip_tos_enable = 0;
+	if (fd >= 0)
+		close(fd);
+	if (sfd >= 0)
+		close(sfd);
+}
+
 void test_setget_sockopt(void)
 {
 	cg_fd = test__join_cgroup(CG_NAME);
@@ -238,6 +315,7 @@ void test_setget_sockopt(void)
 	test_ktls(AF_INET);
 	test_nonstandard_opt(AF_INET);
 	test_nonstandard_opt(AF_INET6);
+	test_v4mapped_v6_ip_tos();
 
 done:
 	setget_sockopt__destroy(skel);
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index d330b1511979..636a7cd8e2fa 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -387,6 +387,24 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	return 1;
 }
 
+int v4mapped_v6_ip_tos_enable;
+int v4mapped_v6_ip_tos_ret;
+int v4mapped_v6_ip_tos_cnt;
+int v4mapped_v6_ip_tos_val;
+
+static void test_v4mapped_v6_ip_tos(struct bpf_sock_ops *skops)
+{
+	int tos = v4mapped_v6_ip_tos_val;
+
+	if (!v4mapped_v6_ip_tos_enable || skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return;
+	if (skops->family != AF_INET6)
+		return;
+
+	v4mapped_v6_ip_tos_cnt++;
+	v4mapped_v6_ip_tos_ret = bpf_setsockopt(skops, IPPROTO_IP, IP_TOS, &tos, sizeof(tos));
+}
+
 SEC("sockops")
 int skops_sockopt(struct bpf_sock_ops *skops)
 {
@@ -401,6 +419,11 @@ int skops_sockopt(struct bpf_sock_ops *skops)
 	if (!sk)
 		return 1;
 
+	if (v4mapped_v6_ip_tos_enable) {
+		test_v4mapped_v6_ip_tos(skops);
+		return 1;
+	}
+
 	switch (skops->op) {
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
 		nr_listen += !(bpf_test_sockopt(skops, sk) ||
-- 
2.54.0

Re: [PATCH bpf-next v4 1/2] bpf: Fix bpf_get/setsockopt to tos for ipv4-mapped ipv6 socket

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 1105 bytes --]

> When TCP over IPv4 via INET6 API, bpf_get/setsockopt with ipv4 will
> fail, because sk->sk_family is AF_INET6. With ipv6 will success, not
> take effect, because inet_csk(sk)->icsk_af_ops is ipv6_mapped and
> use ip_queue_xmit, inet_sk(sk)->tos.
> To relax this restriction, allow getting/setting tos for those possible
> ipv4-mapped ipv6 sockets.
> Fixes: ee7f1e1302f5 ("bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()")
> Signed-off-by: Feng Zhou <zhoufeng.zf@bytedance.com>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>

In an earlier review round it was suggested that "bpf_get/setsockopt
with ipv4 will fail" should read "bpf_get/setsockopt with SOL_IP will
fail", since the call uses the SOL_IP level rather than an ipv4 option.

The body here still reads "with ipv4 will fail" - was the s/ipv4/SOL_IP/
reword intended to be picked up?


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/27472657322