Skip to contentSkip to conversation

implement psock_update_sk_prot

PATCH RESEND Superseded Geliang Tang 2 participants 4 messages Mar 17

Subsystems (5)

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Geliang Tang

author reviewer
#0 lore raw

v2 cover implement psock_update_sk_prot

From: Geliang Tang <[email protected]>

RESEND:
- rebased.
- to trigger ai review.

v2:
- Include mptcp_bpf_update_proto within CONFIG_BPF_SYSCALL to fix the
compilation errors reported by the kernel test robot.
- Add checks for IS_ENABLED(CONFIG_MPTCP_IPV6).

Implement psock_update_sk_prot, for basic MPTCP BPF SOCKMAP support.

Geliang Tang (2):
mptcp: implement psock_update_sk_prot
selftests/bpf: Update sockmap tests for MPTCP

 net/mptcp/protocol.c                          | 105 ++++++++++++++++++
 .../testing/selftests/bpf/prog_tests/mptcp.c  |   4 +-
 2 files changed, 107 insertions(+), 2 deletions(-)
Signature · 1 line
2.53.0
author reviewer
#1 lore raw

PATCH RESEND v2 1/2 mptcp: implement psock_update_sk_prot

From: Geliang Tang <[email protected]>

Add MPTCP support for BPF sockmap by implementing psock_update_sk_prot callback. This allows MPTCP sockets to dynamically switch protocol handlers when attached to or detached from sockmap programs. Separate protocol structures are maintained for IPv4/IPv6 and TX/RX configurations.

tcp_bpf_update_proto() in net/ipv4/tcp_bpf.c is a frame of reference for this patch.

---
 net/mptcp/protocol.c | 105 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 105 insertions(+)
net/mptcp/protocol.c +105 -0
index b5676b37f8f4..5bbc67d1fa6d 100644
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/sched/signal.h>
 #include <linux/atomic.h>
+#include <linux/skmsg.h>
 #include <net/aligned_data.h>
 #include <net/rps.h>
 #include <net/sock.h>
@@ -4020,6 +4021,98 @@ static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
 	return 0;
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+enum {
+	MPTCP_BPF_IPV4,
+	MPTCP_BPF_IPV6,
+	MPTCP_BPF_NUM_PROTS,
+};
+
+enum {
+	MPTCP_BPF_BASE,
+	MPTCP_BPF_TX,
+	MPTCP_BPF_RX,
+	MPTCP_BPF_TXRX,
+	MPTCP_BPF_NUM_CFGS,
+};
+
+static struct proto mptcp_bpf_prots[MPTCP_BPF_NUM_PROTS][MPTCP_BPF_NUM_CFGS];
+
+static void mptcp_bpf_rebuild_protos(struct proto prot[MPTCP_BPF_NUM_CFGS],
+				     struct proto *base)
+{
+	prot[MPTCP_BPF_BASE]			= *base;
+	prot[MPTCP_BPF_BASE].destroy		= sock_map_destroy;
+	prot[MPTCP_BPF_BASE].close		= sock_map_close;
+	prot[MPTCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
+
+	prot[MPTCP_BPF_TX]			= prot[MPTCP_BPF_BASE];
+	prot[MPTCP_BPF_RX]			= prot[MPTCP_BPF_BASE];
+	prot[MPTCP_BPF_TXRX]			= prot[MPTCP_BPF_TX];
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static struct proto *mptcpv6_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(mptcpv6_prot_lock);
+
+static void mptcp_bpf_check_v6_needs_rebuild(struct proto *ops)
+{
+	/*
+	 * Load with acquire semantics to ensure we see the latest protocol
+	 * structure before checking for rebuild.
+	 */
+	if (unlikely(ops != smp_load_acquire(&mptcpv6_prot_saved))) {
+		spin_lock_bh(&mptcpv6_prot_lock);
+		if (likely(ops != mptcpv6_prot_saved)) {
+			mptcp_bpf_rebuild_protos(mptcp_bpf_prots[MPTCP_BPF_IPV6], ops);
+			/* Ensure mptcpv6_prot_saved update is visible before releasing lock */
+			smp_store_release(&mptcpv6_prot_saved, ops);
+		}
+		spin_unlock_bh(&mptcpv6_prot_lock);
+	}
+}
+
+static int mptcp_bpf_assert_proto_ops(struct proto *ops)
+{
+	/* In order to avoid retpoline, we make assumptions when we call
+	 * into ops if e.g. a psock is not present. Make sure they are
+	 * indeed valid assumptions.
+	 */
+	return ops->recvmsg  == mptcp_recvmsg &&
+	       ops->sendmsg  == mptcp_sendmsg ? 0 : -EOPNOTSUPP;
+}
+#endif
+
+static int mptcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+{
+	int family = sk->sk_family == AF_INET6 ? MPTCP_BPF_IPV6 : MPTCP_BPF_IPV4;
+	int config = psock->progs.msg_parser   ? MPTCP_BPF_TX   : MPTCP_BPF_BASE;
+
+	if (psock->progs.stream_verdict || psock->progs.skb_verdict)
+		config = (config == MPTCP_BPF_TX) ? MPTCP_BPF_TXRX : MPTCP_BPF_RX;
+
+	if (restore) {
+		sk->sk_write_space = psock->saved_write_space;
+		/* Pairs with lockless read in sk_clone_lock() */
+		sock_replace_proto(sk, psock->sk_proto);
+		return 0;
+	}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (mptcp_bpf_assert_proto_ops(psock->sk_proto))
+			return -EINVAL;
+
+		mptcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
+	}
+#endif
+
+	/* Pairs with lockless read in sk_clone_lock() */
+	sock_replace_proto(sk, &mptcp_bpf_prots[family][config]);
+	return 0;
+}
+#endif
+
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -4051,8 +4144,20 @@ static struct proto mptcp_prot = {
 	.obj_size	= sizeof(struct mptcp_sock),
 	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
 	.no_autobind	= true,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= mptcp_bpf_update_proto,
+#endif
 };
 
+#ifdef CONFIG_BPF_SYSCALL
+static int __init mptcp_bpf_v4_build_proto(void)
+{
+	mptcp_bpf_rebuild_protos(mptcp_bpf_prots[MPTCP_BPF_IPV4], &mptcp_prot);
+	return 0;
+}
+late_initcall(mptcp_bpf_v4_build_proto);
+#endif
+
 static int mptcp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
Signature · 1 line
2.53.0
author reviewer
#2 lore raw

PATCH RESEND v2 2/2 selftests/bpf: Update sockmap tests for MPTCP

In reply to Geliang Tang

From: Geliang Tang <[email protected]>

Update sockmap tests to reflect new MPTCP support. MPTCP sockets are now allowed in sockmap, so test expectations are adjusted accordingly.

---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/bpf/prog_tests/mptcp.c +2 -2
index 7f48fd9e94e1..217ecc59c8a2 100644
@@ -570,13 +570,13 @@ static void test_sockmap_reject_mptcp(struct mptcp_sockmap *skel)
 	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"))
+	if (!ASSERT_EQ(err, 0, "server should be allowed"))
 		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"))
+	if (!ASSERT_EQ(err, -EEXIST, "client should be allowed"))
 		goto end;
 end:
 	if (client_fd1 >= 0)
Signature · 1 line
2.53.0
#3 lore raw
In reply to Geliang Tang

Hi Geliang,

Thank you for your modifications, that's great!

Our CI did some validations and here is its report:

- KVM Validation: normal (except selftest_mptcp_join): Success! ✅
- KVM Validation: normal (only selftest_mptcp_join): Success! ✅
- KVM Validation: debug (except selftest_mptcp_join): Unstable: 1 failed test(s): packetdrill_sockopts 🔴
- KVM Validation: debug (only selftest_mptcp_join): Success! ✅
- KVM Validation: btf-normal (only bpftest_all): Success! ✅
- KVM Validation: btf-debug (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/23189108848

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/697c10324f1a
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=1067882

If there are some issues, you can reproduce them using the same environment as the one used by the CI thanks to a docker image, e.g.:

    $ cd [kernel source code]
    $ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
        --pull always mptcp/mptcp-upstream-virtme-docker:latest \
        auto-normal

For more details:

https://github.com/multipath-tcp/mptcp-upstream-virtme-docker

Please note that despite all the efforts that have been already done to have a stable tests suite when executed on a public CI like here, it is possible some reported issues are not due to your modifications. Still, do not hesitate to help us improve that ;-)

Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (NGI0 Core)