From patchwork Thu Feb 17 14:25:37 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12750269 X-Patchwork-Delegate: mat@martineau.name Received: from Chamillionaire.breakpoint.cc (Chamillionaire.breakpoint.cc [193.142.43.52]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 01310291C for ; Thu, 17 Feb 2022 14:26:02 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nKhjM-0004EG-94; Thu, 17 Feb 2022 15:26:00 +0100 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 4/5] mptcp: handle join requests via pernet listen socket Date: Thu, 17 Feb 2022 15:25:37 +0100 Message-Id: <20220217142538.7849-5-fw@strlen.de> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220217142538.7849-1-fw@strlen.de> References: <20220217142538.7849-1-fw@strlen.de> Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Currently mptcp adds kernel-based listener socket for all netlink-configured mptcp address endpoints. This has caveats because kernel may interfere with unrelated programs that use same address/port pairs. RFC 8684 says: Demultiplexing subflow SYNs MUST be done using the token; this is unlike traditional TCP, where the destination port is used for demultiplexing SYN packets. Once a subflow is set up, demultiplexing packets is done using the 5-tuple, as in traditional TCP. This patch deviates from this in that it retrains the existing checks of verifying the incoming requests destination vs. the list of announced addresses. This can be relaxed later if deemed appropriate. Furthermore, TCP-only listeners take precedence: An MPTCP peer MUST NOT announce address:port pairs that are already in use by a non-mptcp listener. This could be changed, but it requires move of mptcp_handle_join() hook *before* the tcp port demux, i.e. an additional conditional in hotpath. As-is, the additional conditional (syn && !rst && ...) is in the 'no socket found' path. The pernet 'listening' socket is hidden from userspace. It is not part of any hashes and not bound to any address or port. TPROXY-like semantics apply: If tcp demux cannot find a port for a given packet, check if the packet is a syn packet with a valid join token. If so, the pernet listener is returned and tcp processing resumes. Otherwise, handling is intentical. This patch does not cover timewait sockets. Signed-off-by: Florian Westphal Reported-by: kernel test robot Reported-by: kernel test robot --- include/net/mptcp.h | 10 ++ net/ipv6/tcp_ipv6.c | 19 ++-- net/mptcp/ctrl.c | 211 ++++++++++++++++++++++++++++++++++++++++++- net/mptcp/protocol.c | 2 +- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 3 + 6 files changed, 233 insertions(+), 14 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 5ee422b56902..49c188b978e1 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -189,6 +189,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, struct sk_buff *skb); __be32 mptcp_get_reset_option(const struct sk_buff *skb); +struct sock *__mptcp_handle_join(int af, struct sk_buff *skb); static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { @@ -199,6 +200,11 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) } static inline struct sock *mptcp_handle_join(int af, struct sk_buff *skb) { + const struct tcphdr *th = tcp_hdr(skb); + + if (th->syn && !th->ack && !th->rst && !th->fin) + return __mptcp_handle_join(af, skb); + return NULL; } #else @@ -283,9 +289,13 @@ static inline struct sock *mptcp_handle_join(int af, struct sk_buff *skb) { retu #if IS_ENABLED(CONFIG_MPTCP_IPV6) int mptcpv6_init(void); +int mptcpv6_init_net(struct net *net); +void mptcpv6_exit_net(struct net *net); void mptcpv6_handle_mapped(struct sock *sk, bool mapped); #elif IS_ENABLED(CONFIG_IPV6) static inline int mptcpv6_init(void) { return 0; } +static inline int mptcpv6_init_net(struct net *net) { return 0; } +static inline void mptcpv6_exit_net(struct net *net) { } static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { } #endif diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 788040db8e9e..3b8608d35dcd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2233,13 +2233,22 @@ static struct inet_protosw tcpv6_protosw = { static int __net_init tcpv6_net_init(struct net *net) { - return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, - SOCK_RAW, IPPROTO_TCP, net); + int err = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, + SOCK_RAW, IPPROTO_TCP, net); + if (err) + return err; + + err = mptcpv6_init_net(net); + if (err) + inet_ctl_sock_destroy(net->ipv6.tcp_sk); + + return err; } static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); + mptcpv6_exit_net(net); } static struct pernet_operations tcpv6_net_ops = { @@ -2264,15 +2273,9 @@ int __init tcpv6_init(void) if (ret) goto out_tcpv6_protosw; - ret = mptcpv6_init(); - if (ret) - goto out_tcpv6_pernet_subsys; - out: return ret; -out_tcpv6_pernet_subsys: - unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index ae20b7d92e28..6358c803ba12 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -21,6 +21,12 @@ static int mptcp_pernet_id; static int mptcp_pm_type_max = __MPTCP_PM_TYPE_MAX; #endif +struct mptcp_join_sk { + struct sock *sk; + struct inet_bind_bucket *tb; + struct inet_bind_hashbucket head; +}; + struct mptcp_pernet { #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_hdr; @@ -32,6 +38,18 @@ struct mptcp_pernet { u8 checksum_enabled; u8 allow_join_initial_addr_port; u8 pm_type; + + /* pernet listener to handle mptcp join requests + * based on the mptcp token. + * + * Has to be pernet because tcp uses + * sock_net(sk_listener) to obtain the net namespace for + * the syn/ack route lookup. + */ + struct mptcp_join_sk join4; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + struct mptcp_join_sk join6; +#endif }; static struct mptcp_pernet *mptcp_get_pernet(const struct net *net) @@ -185,13 +203,173 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} #endif /* CONFIG_SYSCTL */ +struct sock *__mptcp_handle_join(int af, struct sk_buff *skb) +{ + struct mptcp_options_received mp_opt; + struct mptcp_pernet *pernet; + struct socket *ssock; + struct sock *lsk; + struct net *net; + + /* paranoia check: don't allow 0 destination port, + * else __inet_inherit_port will insert the child socket + * into the phony hash slot of the pernet listener. + */ + if (tcp_hdr(skb)->dest == 0) + return NULL; + + mptcp_get_options(skb, &mp_opt); + + if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) + return NULL; + + net = dev_net(skb_dst(skb)->dev); + if (!mptcp_is_enabled(net)) + return NULL; + + /* RFC8684: If the token is unknown [..], the receiver will send + * back a reset (RST) signal, analogous to an unknown port in TCP, + * containing an MP_TCPRST option (Section 3.6) [..] + */ + if (!mptcp_token_exists(net, mp_opt.token)) { + struct mptcp_ext *ext = skb_ext_add(skb, SKB_EXT_MPTCP); + + if (ext) { + memset(ext, 0, sizeof(*ext)); + ext->reset_reason = MPTCP_RST_EMPTCP; + } + return NULL; + } + + pernet = mptcp_get_pernet(net); + + switch (af) { + case AF_INET: + lsk = pernet->join4.sk; + break; + case AF_INET6: + lsk = pernet->join6.sk; + break; + default: + WARN_ON_ONCE(1); + return NULL; + } + + ssock = __mptcp_nmpc_socket(mptcp_sk(lsk)); + if (WARN_ON(!ssock)) + return NULL; + + return ssock->sk; +} + +static struct socket *mptcp_create_join_listen_socket(struct net *net, int af) +{ + struct socket *s, *ssock; + int err; + + err = sock_create_kern(net, af, SOCK_STREAM, IPPROTO_MPTCP, &s); + if (err) + return ERR_PTR(err); + + ssock = __mptcp_nmpc_socket(mptcp_sk(s->sk)); + if (!ssock) { + err = -EINVAL; + goto out; + } + + ssock->sk->sk_max_ack_backlog = SOMAXCONN; + inet_sk_state_store(ssock->sk, TCP_LISTEN); + + s->sk->sk_max_ack_backlog = SOMAXCONN; + inet_sk_state_store(s->sk, TCP_LISTEN); + + s->sk->sk_net_refcnt = 1; + get_net_track(net, &s->sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + + return s; +out: + sock_release(s); + return ERR_PTR(err); +} + +static int mptcp_init_join_sk(struct net *net, struct sock *sk, struct mptcp_join_sk *join_sk) +{ + struct socket *ssock = __mptcp_nmpc_socket(mptcp_sk(sk)); + struct inet_hashinfo *table = ssock->sk->sk_prot->h.hashinfo; + struct inet_bind_bucket *tb; + + spin_lock_init(&join_sk->head.lock); + INIT_HLIST_HEAD(&join_sk->head.chain); + + /* Our "listen socket" isn't bound to any address or port. + * Conceptually, SYN packet with mptcp join request are steered to + * this pernet socket just like TPROXY steals arbitrary connection + * requests to assign them to listening socket with different + * address or port. + * + * The bind_bucket is needed for sake of __inet_inherit_port(), + * so it can place the new child socket in the correct + * bind_bucket slot. + * + * A phony head is used to hide this socket from normal sk loookup. + */ + tb = inet_bind_bucket_create(table->bind_bucket_cachep, + net, &join_sk->head, 0, 0); + if (!tb) + return -ENOMEM; + + inet_csk(ssock->sk)->icsk_bind_hash = tb; + return 0; +} + static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); + struct socket *sock; + int err; mptcp_pernet_set_defaults(pernet); - return mptcp_pernet_new_table(net, pernet); + err = mptcp_pernet_new_table(net, pernet); + if (err) + return err; + + sock = mptcp_create_join_listen_socket(net, AF_INET); + if (IS_ERR(sock)) { + err = PTR_ERR(sock); + goto out_table; + } + + err = mptcp_init_join_sk(net, sock->sk, &pernet->join4); + if (err) { + sock_release(sock); + goto out_table; + } + + /* struct sock is still reachable via sock->sk_socket backpointer */ + pernet->join4.sk = sock->sk; + return err; + +out_table: + if (!net_eq(net, &init_net)) + mptcp_pernet_del_table(pernet); + return err; +} + +static void __net_exit mptcp_exit_join_sk(struct mptcp_join_sk *jsk) +{ + struct socket *ssock = __mptcp_nmpc_socket(mptcp_sk(jsk->sk)); + struct inet_bind_bucket *tb; + struct inet_hashinfo *table; + + table = ssock->sk->sk_prot->h.hashinfo; + + tb = inet_csk(ssock->sk)->icsk_bind_hash; + inet_bind_bucket_destroy(table->bind_bucket_cachep, tb); + + ssock = jsk->sk->sk_socket; + sock_release(ssock); } /* Note: the callback will only be called per extra netns */ @@ -200,6 +378,7 @@ static void __net_exit mptcp_net_exit(struct net *net) struct mptcp_pernet *pernet = mptcp_get_pernet(net); mptcp_pernet_del_table(pernet); + mptcp_exit_join_sk(&pernet->join4); } static struct pernet_operations mptcp_pernet_ops = { @@ -219,12 +398,36 @@ void __init mptcp_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) -int __init mptcpv6_init(void) +int __net_init mptcpv6_init_net(struct net *net) { + struct mptcp_pernet *pernet = mptcp_get_pernet(net); + struct socket *sock; int err; - err = mptcp_proto_v6_init(); + if (net_eq(net, &init_net)) { + err = mptcp_proto_v6_init(); + if (err) + return err; + } - return err; + sock = mptcp_create_join_listen_socket(net, AF_INET6); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + err = mptcp_init_join_sk(net, sock->sk, &pernet->join6); + if (err) { + sock_release(sock); + return err; + } + + pernet->join6.sk = sock->sk; + return 0; +} + +void __net_exit mptcpv6_exit_net(struct net *net) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(net); + + mptcp_exit_join_sk(&pernet->join6); } #endif diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4599bde215b2..5b54e3c8efea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3777,7 +3777,7 @@ static struct inet_protosw mptcp_v6_protosw = { .flags = INET_PROTOSW_ICSK, }; -int __init mptcp_proto_v6_init(void) +int __net_init mptcp_proto_v6_init(void) { int err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7bd064b68b51..6a81e2a21301 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -647,7 +647,7 @@ static inline bool mptcp_has_another_subflow(struct sock *ssk) void __init mptcp_proto_init(void); #if IS_ENABLED(CONFIG_MPTCP_IPV6) -int __init mptcp_proto_v6_init(void); +int __net_init mptcp_proto_v6_init(void); #endif struct sock *mptcp_sk_clone(const struct sock *sk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8be20f7b76df..4696d27a8994 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -116,6 +116,9 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk) { + if (inet_sk(sk)->inet_sport == 0) + return true; + return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport; }