From 490274b47468793e3e157c2df6b2da0e646cc4a9 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 21 Jun 2021 17:33:08 -0700 Subject: mptcp: avoid race on msk state changes The msk socket state is currently updated in a few spots without owning the msk socket lock itself. Some of such operations are safe, as they happens before exposing the msk socket to user-space and can't race with other changes. A couple of them, at connect time, can actually race with close() or shutdown(), leaving breaking the socket state machine. This change addresses the issue moving such update under the msk socket lock with the usual: scheme. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/56 Fixes: 8fd738049ac3 ("mptcp: fallback in case of simultaneous connect") Fixes: c3c123d16c0e ("net: mptcp: don't hang in mptcp_sendmsg() after TCP fallback") Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 037fba41e170..9f934603bfe8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -371,6 +371,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } +void __mptcp_set_connected(struct sock *sk) +{ + if (sk->sk_state == TCP_SYN_SENT) { + inet_sk_state_store(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + } +} + +static void mptcp_set_connected(struct sock *sk) +{ + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_set_connected(sk); + else + set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -379,10 +397,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) @@ -411,6 +425,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->remote_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); + mptcp_set_connected(parent); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -451,6 +466,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); + mptcp_set_connected(parent); } return; @@ -558,6 +574,7 @@ static void mptcp_sock_destruct(struct sock *sk) static void mptcp_force_close(struct sock *sk) { + /* the msk is not yet exposed to user-space */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); } @@ -1474,10 +1491,7 @@ static void subflow_state_change(struct sock *sk) mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); subflow->conn_finished = 1; - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } + mptcp_set_connected(parent); } /* as recvmsg() does not acquire the subflow socket for ssk selection -- cgit v1.2.3