From: Ruide Cao TCP request migration clones pending request sockets with inet_reqsk_clone(). For MPTCP MP_CAPABLE requests this byte-copies the token_node hlist state into the clone even though the token table still names the original request. Moving the token only after inet_ehash_insert() succeeds leaves a window where the cloned request is already globally visible from the ehash but the token table still points at the original request. Reordering the move after clone but before ehash exposure closes that window, but concurrent RX can still race on the old request and observe that the token was already moved. Move MP_CAPABLE token request ownership during MPTCP request cloning under the token bucket lock. Make mptcp_token_accept() and mptcp_token_destroy_request() re-check token_node under the same lock and treat an already moved or removed request as a normal race instead of warning. If the passive MP_CAPABLE socket cannot claim the token, fail mptcp_sk_clone_init() and let the subflow fall back instead of installing a socket with mismatched token ownership. Keep token publication after the cloned msk has its first subflow and connection list initialized. If token accept still fails, tear the cloned MPTCP socket down by open-coding the inet-level forced-close preparation, avoiding TCP-only helpers such as tcp_done() or inet_csk_prepare_forced_close() on the MPTCP master socket. Fixes: c905dee62232 ("tcp: Migrate TCP_NEW_SYN_RECV requests at retransmitting SYN+ACKs.") Cc: stable@vger.kernel.org Reported-by: Vega Assisted-by: Codex:gpt-5.4 Reported-by: Sashiko Closes: https://sashiko.dev/#/patchset/86e2514b533bf4d55d4aa2fdbf1404022e8c9430.1776149210.git.caoruide123%40gmail.com Signed-off-by: Ruide Cao Signed-off-by: Ren Wei --- net/mptcp/protocol.c | 31 +++++++++++++++++---- net/mptcp/protocol.h | 4 ++- net/mptcp/subflow.c | 2 ++ net/mptcp/token.c | 61 +++++++++++++++++++++++++++++++++++++----- net/mptcp/token_test.c | 4 +-- 5 files changed, 87 insertions(+), 15 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7c8180d8d5ef..b05c8d37a083 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3561,6 +3561,24 @@ static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) rcu_read_unlock(); } +static void mptcp_sk_clone_destroy(struct sock *nsk) +{ + struct mptcp_sock *msk = mptcp_sk(nsk); + + mptcp_release_sched(msk); + mptcp_set_state(nsk, TCP_CLOSE); + /* inet_csk_prepare_forced_close() clears TCP sock_ops state via + * tcp_sk(), but nsk is an MPTCP master socket; keep the inet-level + * destroy preparation here. + */ + bh_unlock_sock(nsk); + sock_put(nsk); + sock_set_flag(nsk, SOCK_DEAD); + tcp_orphan_count_inc(); + inet_sk(nsk)->inet_num = 0; + inet_csk_destroy_sock(nsk); +} + struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, @@ -3620,11 +3638,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - mptcp_token_accept(subflow_req, msk); - /* set msk addresses early to ensure mptcp_pm_get_local_id() * uses the correct data */ @@ -3633,6 +3646,14 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, mptcp_rcv_space_init(msk, ssk); msk->rcvq_space.time = mptcp_stamp(); + if (!mptcp_token_accept(subflow_req, msk)) { + list_del_init(&subflow->node); + WRITE_ONCE(msk->first, NULL); + sock_put(ssk); + mptcp_sk_clone_destroy(nsk); + return NULL; + } + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 1b80f2d6ec5a..69d531c770c4 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1076,9 +1076,11 @@ static inline void mptcp_token_init_request(struct request_sock *req) } int mptcp_token_new_request(struct request_sock *req); +void mptcp_token_move_request(struct request_sock *req, + struct request_sock *new_req); void mptcp_token_destroy_request(struct request_sock *req); int mptcp_token_new_connect(struct sock *ssk); -void mptcp_token_accept(struct mptcp_subflow_request_sock *r, +bool mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8f8e1229766d..d40ab09ab75b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -56,6 +56,8 @@ void mptcp_subflow_reqsk_clone(struct request_sock *req, if (subflow_req->msk) sock_hold((struct sock *)subflow_req->msk); + + mptcp_token_move_request(req, new_req); } static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, diff --git a/net/mptcp/token.c b/net/mptcp/token.c index f1a50f367add..24877a2c3772 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -180,6 +180,36 @@ int mptcp_token_new_connect(struct sock *ssk) return 0; } +void mptcp_token_move_request(struct request_sock *req, + struct request_sock *new_req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_subflow_request_sock *new_subflow_req; + struct mptcp_subflow_request_sock *pos; + struct token_bucket *bucket; + + new_subflow_req = mptcp_subflow_rsk(new_req); + + if (hlist_nulls_unhashed_lockless(&subflow_req->token_node)) { + mptcp_token_init_request(new_req); + return; + } + + bucket = token_bucket(subflow_req->token); + spin_lock_bh(&bucket->lock); + if (hlist_nulls_unhashed(&subflow_req->token_node)) { + mptcp_token_init_request(new_req); + } else { + pos = __token_lookup_req(bucket, subflow_req->token); + if (pos == subflow_req) + hlist_nulls_replace_init_rcu(&subflow_req->token_node, + &new_subflow_req->token_node); + else + mptcp_token_init_request(new_req); + } + spin_unlock_bh(&bucket->lock); +} + /** * mptcp_token_accept - replace a req sk with full sock in token hash * @req: the request socket to be removed @@ -187,24 +217,36 @@ int mptcp_token_new_connect(struct sock *ssk) * * Called when a SYN packet creates a new logical connection, i.e. * is not a join request. + * + * Return: true on success. */ -void mptcp_token_accept(struct mptcp_subflow_request_sock *req, +bool mptcp_token_accept(struct mptcp_subflow_request_sock *req, struct mptcp_sock *msk) { struct mptcp_subflow_request_sock *pos; struct sock *sk = (struct sock *)msk; struct token_bucket *bucket; + bool ret = false; - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); bucket = token_bucket(req->token); spin_lock_bh(&bucket->lock); + if (hlist_nulls_unhashed(&req->token_node)) + goto unlock; - /* pedantic lookup check for the moved token */ pos = __token_lookup_req(bucket, req->token); - if (!WARN_ON_ONCE(pos != req)) - hlist_nulls_del_init_rcu(&req->token_node); + if (pos != req) + goto unlock; + + hlist_nulls_del_init_rcu(&req->token_node); __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); + ret = true; + +unlock: spin_unlock_bh(&bucket->lock); + if (ret) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + + return ret; } bool mptcp_token_exists(u32 token) @@ -355,16 +397,21 @@ void mptcp_token_destroy_request(struct request_sock *req) struct mptcp_subflow_request_sock *pos; struct token_bucket *bucket; - if (hlist_nulls_unhashed(&subflow_req->token_node)) + if (hlist_nulls_unhashed_lockless(&subflow_req->token_node)) return; bucket = token_bucket(subflow_req->token); spin_lock_bh(&bucket->lock); + if (hlist_nulls_unhashed(&subflow_req->token_node)) + goto unlock; + pos = __token_lookup_req(bucket, subflow_req->token); - if (!WARN_ON_ONCE(pos != subflow_req)) { + if (pos == subflow_req) { hlist_nulls_del_init_rcu(&pos->token_node); bucket->chain_len--; } + +unlock: spin_unlock_bh(&bucket->lock); } diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index 4fc39fa2e262..be9acce8a567 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -99,7 +99,7 @@ static void mptcp_token_test_accept(struct kunit *test) KUNIT_ASSERT_EQ(test, 0, mptcp_token_new_request((struct request_sock *)req)); msk->token = req->token; - mptcp_token_accept(req, msk); + KUNIT_EXPECT_TRUE(test, mptcp_token_accept(req, msk)); KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* this is now a no-op */ @@ -122,7 +122,7 @@ static void mptcp_token_test_destroyed(struct kunit *test) KUNIT_ASSERT_EQ(test, 0, mptcp_token_new_request((struct request_sock *)req)); msk->token = req->token; - mptcp_token_accept(req, msk); + KUNIT_EXPECT_TRUE(test, mptcp_token_accept(req, msk)); /* simulate race on removal */ refcount_set(&sk->sk_refcnt, 0); -- 2.43.0