Skip to contentSkip to conversation

implement psock_update_sk_prot

PATCH Superseded Geliang Tang 3 participants 7 messages Dec 25, 2025 – Dec 26, 2025

Subsystems (5)

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Geliang Tang

author reviewer
#0 lore raw

cover implement psock_update_sk_prot

From: Geliang Tang <[email protected]>

Implement psock_update_sk_prot, for basic MPTCP BPF SOCKMAP support.

Geliang Tang (3):
mptcp: implement psock_update_sk_prot
mptcp: allow overridden write_space to be invoked selftests/bpf: Update sockmap tests for MPTCP

 net/mptcp/protocol.c                          | 96 +++++++++++++++++++
 net/mptcp/protocol.h                          |  2 +-
 .../testing/selftests/bpf/prog_tests/mptcp.c  |  4 +-
 3 files changed, 99 insertions(+), 3 deletions(-)
Signature · 1 line
2.51.0
author reviewer
#1 lore raw

PATCH 1/3 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 | 96 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)
net/mptcp/protocol.c +96 -0
index 900f26e21acd..d8fb71301bb4 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>
@@ -4017,6 +4018,91 @@ static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
 	return 0;
 }
 
+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 *mptcpv6_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(mptcpv6_prot_lock);
+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];
+}
+
+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;
+}
+
+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 (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);
+	}
+
+	/* Pairs with lockless read in sk_clone_lock() */
+	sock_replace_proto(sk, &mptcp_bpf_prots[family][config]);
+	return 0;
+}
+
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -4048,8 +4134,18 @@ 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
 };
 
+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);
+
 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
2.51.0
#2 lore raw

Re: [PATCH mptcp-next 1/3] mptcp: implement psock_update_sk_prot

kernel test robot noticed the following build warnings:

Hi Geliang,

kernel test robot noticed the following build warnings:

[auto build test WARNING on mptcp/export]
[also build test WARNING on mptcp/export-net linus/master v6.19-rc2 next-20251219] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Geliang-Tang/mptcp-implement-psock_update_sk_prot/20251225-170243
base:   https://github.com/multipath-tcp/mptcp_net-next.git export
patch link:    https://lore.kernel.org/r/f2508c5923c4ed365d6c12800e43a16761ed615a.1766653030.git.tanggeliang%40kylinos.cn
patch subject: [PATCH mptcp-next 1/3] mptcp: implement psock_update_sk_prot
config: arc-defconfig (https://download.01.org/0day-ci/archive/20251226/[email protected]/config)
compiler: arc-linux-gcc (GCC) 15.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251226/[email protected]/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/

All warnings (new ones prefixed by >>):

net/mptcp/protocol.c: In function 'mptcp_bpf_rebuild_protos':
net/mptcp/protocol.c:4043:51: error: 'sock_map_destroy' undeclared (first use in this function); did you mean 'sock_diag_destroy'?

    4043 |         prot[MPTCP_BPF_BASE].destroy            = sock_map_destroy;
         |                                                   ^~~~~~~~~~~~~~~~
         |                                                   sock_diag_destroy
   net/mptcp/protocol.c:4043:51: note: each undeclared identifier is reported only once for each function it appears in
   net/mptcp/protocol.c:4044:51: error: 'sock_map_close' undeclared (first use in this function); did you mean 'sk_msg_clone'?
    4044 |         prot[MPTCP_BPF_BASE].close              = sock_map_close;
         |                                                   ^~~~~~~~~~~~~~
         |                                                   sk_msg_clone
   net/mptcp/protocol.c: At top level:
>> net/mptcp/protocol.c:4079:12: warning: 'mptcp_bpf_update_proto' defined but not used [-Wunused-function]

4079 | static int mptcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
| ^~~~~~~~~~~~~~~~~~~~~~

vim +/mptcp_bpf_update_proto +4079 net/mptcp/protocol.c

4078

> 4079	static int mptcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)

4080 {
4081 int family = sk->sk_family == AF_INET6 ? MPTCP_BPF_IPV6 : MPTCP_BPF_IPV4;
4082 int config = psock->progs.msg_parser ? MPTCP_BPF_TX : MPTCP_BPF_BASE;
4083
4084 if (psock->progs.stream_verdict || psock->progs.skb_verdict)
4085 config = (config == MPTCP_BPF_TX) ? MPTCP_BPF_TXRX : MPTCP_BPF_RX;
4086
4087 if (restore) {
4088 sk->sk_write_space = psock->saved_write_space;
4089 /* Pairs with lockless read in sk_clone_lock() */
4090 sock_replace_proto(sk, psock->sk_proto);
4091 return 0;
4092 }
4093
4094 if (sk->sk_family == AF_INET6) {
4095 if (mptcp_bpf_assert_proto_ops(psock->sk_proto))
4096 return -EINVAL;
4097
4098 mptcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
4099 }
4100
4101 /* Pairs with lockless read in sk_clone_lock() */
4102 sock_replace_proto(sk, &mptcp_bpf_prots[family][config]);
4103 return 0;
4104 }
4105

Signature · 2 lines
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
#3 lore raw

Re: [PATCH mptcp-next 1/3] mptcp: implement psock_update_sk_prot

In reply to Geliang Tang
kernel test robot noticed the following build errors:

Hi Geliang,

kernel test robot noticed the following build errors:

[auto build test ERROR on mptcp/export]
[also build test ERROR on mptcp/export-net linus/master v6.19-rc2 next-20251219] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Geliang-Tang/mptcp-implement-psock_update_sk_prot/20251225-170243
base:   https://github.com/multipath-tcp/mptcp_net-next.git export
patch link:    https://lore.kernel.org/r/f2508c5923c4ed365d6c12800e43a16761ed615a.1766653030.git.tanggeliang%40kylinos.cn
patch subject: [PATCH mptcp-next 1/3] mptcp: implement psock_update_sk_prot
config: arc-defconfig (https://download.01.org/0day-ci/archive/20251226/[email protected]/config)
compiler: arc-linux-gcc (GCC) 15.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251226/[email protected]/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/

All errors (new ones prefixed by >>):

net/mptcp/protocol.c: In function 'mptcp_bpf_rebuild_protos':

>> net/mptcp/protocol.c:4043:51: error: 'sock_map_destroy' undeclared (first use in this function); did you mean 'sock_diag_destroy'?
    4043 |         prot[MPTCP_BPF_BASE].destroy            = sock_map_destroy;
         |                                                   ^~~~~~~~~~~~~~~~
         |                                                   sock_diag_destroy
   net/mptcp/protocol.c:4043:51: note: each undeclared identifier is reported only once for each function it appears in
>> net/mptcp/protocol.c:4044:51: error: 'sock_map_close' undeclared (first use in this function); did you mean 'sk_msg_clone'?
    4044 |         prot[MPTCP_BPF_BASE].close              = sock_map_close;
         |                                                   ^~~~~~~~~~~~~~
         |                                                   sk_msg_clone

net/mptcp/protocol.c: At top level:
net/mptcp/protocol.c:4079:12: warning: 'mptcp_bpf_update_proto' defined but not used [-Wunused-function]
4079 | static int mptcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
| ^~~~~~~~~~~~~~~~~~~~~~

vim +4043 net/mptcp/protocol.c

4038
4039 static void mptcp_bpf_rebuild_protos(struct proto prot[MPTCP_BPF_NUM_CFGS],
4040 struct proto *base)
4041 {
4042 prot[MPTCP_BPF_BASE] = *base;

> 4043		prot[MPTCP_BPF_BASE].destroy		= sock_map_destroy;
> 4044		prot[MPTCP_BPF_BASE].close		= sock_map_close;

4045 prot[MPTCP_BPF_BASE].sock_is_readable = sk_msg_is_readable;
4046
4047 prot[MPTCP_BPF_TX] = prot[MPTCP_BPF_BASE];
4048 prot[MPTCP_BPF_RX] = prot[MPTCP_BPF_BASE];
4049 prot[MPTCP_BPF_TXRX] = prot[MPTCP_BPF_TX];
4050 }
4051

Signature · 2 lines
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
author reviewer
#4 lore raw

PATCH 2/3 mptcp: allow overridden write_space to be invoked

In reply to Geliang Tang

From: Geliang Tang <[email protected]>

psock may override its own sk_write_space functions. This patch ensures that the overridden sk_write_space can be invoked by MPTCP.

Note: This patch was initially included in the NVME MPTCP set.

---
 net/mptcp/protocol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/protocol.h +1 -1
index cd5266099993..f5d4d7d030f2 100644
@@ -1014,7 +1014,7 @@ static inline void mptcp_write_space(struct sock *sk)
 	/* pairs with memory barrier in mptcp_poll */
 	smp_mb();
 	if (mptcp_stream_memory_free(sk, 1))
-		sk_stream_write_space(sk);
+		INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk);
 }
 
 static inline void __mptcp_sync_sndbuf(struct sock *sk)
Signature · 1 line
2.51.0
author reviewer
#5 lore raw

PATCH 3/3 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
2.51.0
#6 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): Success! ✅
- KVM Validation: debug (only selftest_mptcp_join): Success! ✅
- KVM Validation: btf-normal (only bpftest_all): Critical: Global Timeout ❌
- KVM Validation: btf-debug (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/20502612231

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/274e726fda82
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=1036539

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)