Merge branch 'mptcp-fix-conflicts-between-mptcp-and-sockmap'

Jiayuan Chen says:

====================
mptcp: Fix conflicts between MPTCP and sockmap

Overall, we encountered a warning [1] that can be triggered by running the
selftest I provided.

sockmap works by replacing sk_data_ready, recvmsg, sendmsg operations and
implementing fast socket-level forwarding logic:
1. Users can obtain file descriptors through userspace socket()/accept()
   interfaces, then call BPF syscall to perform these replacements.
2. Users can also use the bpf_sock_hash_update helper (in sockops programs)
   to replace handlers when TCP connections enter ESTABLISHED state
  (BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB/BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB)

However, when combined with MPTCP, an issue arises: MPTCP creates subflow
sk's and performs TCP handshakes, so the BPF program obtains subflow sk's
and may incorrectly replace their sk_prot. We need to reject such
operations. In patch 1, we set psock_update_sk_prot to NULL in the
subflow's custom sk_prot.

Additionally, if the server's listening socket has MPTCP enabled and the
client's TCP also uses MPTCP, we should allow the combination of subflow
and sockmap. This is because the latest Golang programs have enabled MPTCP
for listening sockets by default [2]. For programs already using sockmap,
upgrading Golang should not cause sockmap functionality to fail.

Patch 2 prevents the WARNING from occurring.

Despite these patches fixing stream corruption, users of sockmap must set
GODEBUG=multipathtcp=0 to disable MPTCP until sockmap fully supports it.

[1] truncated warning:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 388 at net/mptcp/protocol.c:68 mptcp_stream_accept+0x34c/0x380
Modules linked in:
RIP: 0010:mptcp_stream_accept+0x34c/0x380
RSP: 0018:ffffc90000cf3cf8 EFLAGS: 00010202
PKRU: 55555554
Call Trace:
 <TASK>
 do_accept+0xeb/0x190
 ? __x64_sys_pselect6+0x61/0x80
 ? _raw_spin_unlock+0x12/0x30
 ? alloc_fd+0x11e/0x190
 __sys_accept4+0x8c/0x100
 __x64_sys_accept+0x1f/0x30
 x64_sys_call+0x202f/0x20f0
 do_syscall_64+0x72/0x9a0
 ? switch_fpu_return+0x60/0xf0
 ? irqentry_exit_to_user_mode+0xdb/0x1e0
 ? irqentry_exit+0x3f/0x50
 ? clear_bhb_loop+0x50/0xa0
 ? clear_bhb_loop+0x50/0xa0
 ? clear_bhb_loop+0x50/0xa0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
 </TASK>
---[ end trace 0000000000000000 ]---

[2]: https://go-review.googlesource.com/c/go/+/607715
====================

Link: https://patch.msgid.link/20251111060307.194196-1-jiayuan.chen@linux.dev
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

4 files changed, 195 insertions, 2 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2d6b8de35c44..90b4aeca2596 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -61,11 +61,13 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 
 static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk)
 {
+	unsigned short family = READ_ONCE(sk->sk_family);
+
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (sk->sk_prot == &tcpv6_prot)
+	if (family == AF_INET6)
 		return &inet6_stream_ops;
 #endif
-	WARN_ON_ONCE(sk->sk_prot != &tcp_prot);
+	WARN_ON_ONCE(family != AF_INET);
 	return &inet_stream_ops;
 }
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e8325890a322..af707ce0f624 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -2144,6 +2144,10 @@ void __init mptcp_subflow_init(void)
 	tcp_prot_override = tcp_prot;
 	tcp_prot_override.release_cb = tcp_release_cb_override;
 	tcp_prot_override.diag_destroy = tcp_abort_override;
+#ifdef CONFIG_BPF_SYSCALL
+	/* Disable sockmap processing for subflows */
+	tcp_prot_override.psock_update_sk_prot = NULL;
+#endif
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	/* In struct mptcp_subflow_request_sock, we assume the TCP request sock
@@ -2180,6 +2184,10 @@ void __init mptcp_subflow_init(void)
 	tcpv6_prot_override = tcpv6_prot;
 	tcpv6_prot_override.release_cb = tcp_release_cb_override;
 	tcpv6_prot_override.diag_destroy = tcp_abort_override;
+#ifdef CONFIG_BPF_SYSCALL
+	/* Disable sockmap processing for subflows */
+	tcpv6_prot_override.psock_update_sk_prot = NULL;
+#endif
 #endif
 
 	mptcp_diag_subflow_init(&subflow_ulp_ops);
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index f8eb7f9d4fd2..8fade8bdc451 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -6,11 +6,13 @@
 #include <netinet/in.h>
 #include <test_progs.h>
 #include <unistd.h>
+#include <errno.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 #include "mptcpify.skel.h"
 #include "mptcp_subflow.skel.h"
+#include "mptcp_sockmap.skel.h"
 
 #define NS_TEST "mptcp_ns"
 #define ADDR_1	"10.0.1.1"
@@ -436,6 +438,142 @@ close_cgroup:
 	close(cgroup_fd);
 }
 
+/* Test sockmap on MPTCP server handling non-mp-capable clients. */
+static void test_sockmap_with_mptcp_fallback(struct mptcp_sockmap *skel)
+{
+	int listen_fd = -1, client_fd1 = -1, client_fd2 = -1;
+	int server_fd1 = -1, server_fd2 = -1, sent, recvd;
+	char snd[9] = "123456789";
+	char rcv[10];
+
+	/* start server with MPTCP enabled */
+	listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (!ASSERT_OK_FD(listen_fd, "sockmap-fb:start_mptcp_server"))
+		return;
+
+	skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd));
+	skel->bss->sk_index = 0;
+	/* create client without MPTCP enabled */
+	client_fd1 = connect_to_fd_opts(listen_fd, NULL);
+	if (!ASSERT_OK_FD(client_fd1, "sockmap-fb:connect_to_fd"))
+		goto end;
+
+	server_fd1 = accept(listen_fd, NULL, 0);
+	skel->bss->sk_index = 1;
+	client_fd2 = connect_to_fd_opts(listen_fd, NULL);
+	if (!ASSERT_OK_FD(client_fd2, "sockmap-fb:connect_to_fd"))
+		goto end;
+
+	server_fd2 = accept(listen_fd, NULL, 0);
+	/* test normal redirect behavior: data sent by client_fd1 can be
+	 * received by client_fd2
+	 */
+	skel->bss->redirect_idx = 1;
+	sent = send(client_fd1, snd, sizeof(snd), 0);
+	if (!ASSERT_EQ(sent, sizeof(snd), "sockmap-fb:send(client_fd1)"))
+		goto end;
+
+	/* try to recv more bytes to avoid truncation check */
+	recvd = recv(client_fd2, rcv, sizeof(rcv), 0);
+	if (!ASSERT_EQ(recvd, sizeof(snd), "sockmap-fb:recv(client_fd2)"))
+		goto end;
+
+end:
+	if (client_fd1 >= 0)
+		close(client_fd1);
+	if (client_fd2 >= 0)
+		close(client_fd2);
+	if (server_fd1 >= 0)
+		close(server_fd1);
+	if (server_fd2 >= 0)
+		close(server_fd2);
+	close(listen_fd);
+}
+
+/* Test sockmap rejection of MPTCP sockets - both server and client sides. */
+static void test_sockmap_reject_mptcp(struct mptcp_sockmap *skel)
+{
+	int listen_fd = -1, server_fd = -1, client_fd1 = -1;
+	int err, zero = 0;
+
+	/* start server with MPTCP enabled */
+	listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (!ASSERT_OK_FD(listen_fd, "start_mptcp_server"))
+		return;
+
+	skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd));
+	skel->bss->sk_index = 0;
+	/* create client with MPTCP enabled */
+	client_fd1 = connect_to_fd(listen_fd, 0);
+	if (!ASSERT_OK_FD(client_fd1, "connect_to_fd client_fd1"))
+		goto end;
+
+	/* bpf_sock_map_update() called from sockops should reject MPTCP sk */
+	if (!ASSERT_EQ(skel->bss->helper_ret, -EOPNOTSUPP, "should reject"))
+		goto end;
+
+	server_fd = accept(listen_fd, NULL, 0);
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map),
+				  &zero, &server_fd, BPF_NOEXIST);
+	if (!ASSERT_EQ(err, -EOPNOTSUPP, "server should be disallowed"))
+		goto end;
+
+	/* MPTCP client should also be disallowed */
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map),
+				  &zero, &client_fd1, BPF_NOEXIST);
+	if (!ASSERT_EQ(err, -EOPNOTSUPP, "client should be disallowed"))
+		goto end;
+end:
+	if (client_fd1 >= 0)
+		close(client_fd1);
+	if (server_fd >= 0)
+		close(server_fd);
+	close(listen_fd);
+}
+
+static void test_mptcp_sockmap(void)
+{
+	struct mptcp_sockmap *skel;
+	struct netns_obj *netns;
+	int cgroup_fd, err;
+
+	cgroup_fd = test__join_cgroup("/mptcp_sockmap");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_sockmap"))
+		return;
+
+	skel = mptcp_sockmap__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_sockmap"))
+		goto close_cgroup;
+
+	skel->links.mptcp_sockmap_inject =
+		bpf_program__attach_cgroup(skel->progs.mptcp_sockmap_inject, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.mptcp_sockmap_inject, "attach sockmap"))
+		goto skel_destroy;
+
+	err = bpf_prog_attach(bpf_program__fd(skel->progs.mptcp_sockmap_redirect),
+			      bpf_map__fd(skel->maps.sock_map),
+			      BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto skel_destroy;
+
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_sockmap"))
+		goto skel_destroy;
+
+	if (endpoint_init("subflow") < 0)
+		goto close_netns;
+
+	test_sockmap_with_mptcp_fallback(skel);
+	test_sockmap_reject_mptcp(skel);
+
+close_netns:
+	netns_free(netns);
+skel_destroy:
+	mptcp_sockmap__destroy(skel);
+close_cgroup:
+	close(cgroup_fd);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
@@ -444,4 +582,6 @@ void test_mptcp(void)
 		test_mptcpify();
 	if (test__start_subtest("subflow"))
 		test_subflow();
+	if (test__start_subtest("sockmap"))
+		test_mptcp_sockmap();
 }
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sockmap.c b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c
new file mode 100644
index 000000000000..d4eef0cbadb9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+int sk_index;
+int redirect_idx;
+int trace_port;
+int helper_ret;
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} sock_map SEC(".maps");
+
+SEC("sockops")
+int mptcp_sockmap_inject(struct bpf_sock_ops *skops)
+{
+	struct bpf_sock *sk;
+
+	/* only accept specified connection */
+	if (skops->local_port != trace_port ||
+	    skops->op != BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
+		return 1;
+
+	sk = skops->sk;
+	if (!sk)
+		return 1;
+
+	/* update sk handler */
+	helper_ret = bpf_sock_map_update(skops, &sock_map, &sk_index, BPF_NOEXIST);
+
+	return 1;
+}
+
+SEC("sk_skb/stream_verdict")
+int mptcp_sockmap_redirect(struct __sk_buff *skb)
+{
+	/* redirect skb to the sk under sock_map[redirect_idx] */
+	return bpf_sk_redirect_map(skb, &sock_map, redirect_idx, 0);
+}