From patchwork Thu Feb 17 14:25:34 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12750267 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 5B443291C for ; Thu, 17 Feb 2022 14:25:55 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nKhj9-0004Da-Qv; Thu, 17 Feb 2022 15:25:47 +0100 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 1/5] mptcp: check netns in mptcp_token_exists Date: Thu, 17 Feb 2022 15:25:34 +0100 Message-Id: <20220217142538.7849-2-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 This will be used by a followup patch to check if the token specified in mp_join option exists in the current netns. At this time, tokens are unique across all namespaces, but we need to treat a token that exists in netns x as 'does not exist' when doing existence check from netns y. Signed-off-by: Florian Westphal --- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 4 +++- net/mptcp/token.c | 5 +++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 18ca0248c084..c43ca46dbc27 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -725,7 +725,7 @@ void mptcp_token_destroy_request(struct request_sock *req); int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); -bool mptcp_token_exists(u32 token); +bool mptcp_token_exists(const struct net *net, u32 token); struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e727d838da0e..be43077fe76e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -176,10 +176,12 @@ static int subflow_check_req(struct request_sock *req, } while (subflow_req->local_key == 0); if (unlikely(req->syncookie)) { + const struct net *net = read_pnet(&inet_rsk(req)->ireq_net); + mptcp_crypto_key_sha(subflow_req->local_key, &subflow_req->token, &subflow_req->idsn); - if (mptcp_token_exists(subflow_req->token)) { + if (mptcp_token_exists(net, subflow_req->token)) { if (retries-- > 0) goto again; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT); diff --git a/net/mptcp/token.c b/net/mptcp/token.c index f52ee7b26aed..0593c83385e0 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -203,7 +203,7 @@ void mptcp_token_accept(struct mptcp_subflow_request_sock *req, spin_unlock_bh(&bucket->lock); } -bool mptcp_token_exists(u32 token) +bool mptcp_token_exists(const struct net *net, u32 token) { struct hlist_nulls_node *pos; struct token_bucket *bucket; @@ -216,7 +216,8 @@ bool mptcp_token_exists(u32 token) again: sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { msk = mptcp_sk(sk); - if (READ_ONCE(msk->token) == token) + if (READ_ONCE(msk->token) == token && + net_eq(sock_net(sk), net)) goto found; } if (get_nulls_value(pos) != (token & token_mask)) From patchwork Thu Feb 17 14:25:35 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12750266 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 9ABA73B29 for ; Thu, 17 Feb 2022 14:25:53 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nKhjD-0004Di-Vu; Thu, 17 Feb 2022 15:25:52 +0100 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 2/5] mptcp: prefer ip address in syn skb instead of listen sk bound address Date: Thu, 17 Feb 2022 15:25:35 +0100 Message-Id: <20220217142538.7849-3-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 Once we change mptcp to use tproxy-like scheme to steer mptcp join requests to a special pernet socket, the 'sk bound address' becomes meaningless because it will never be identical to the tcp dport/ip daddr of the on-wire packet. Prepare for this: pass the skbuff and use the packet data instead of the address the listener socket is bound to. Signed-off-by: Florian Westphal --- net/mptcp/pm_netlink.c | 17 +++++++++++++++-- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 5 +++-- 3 files changed, 19 insertions(+), 5 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 56f5603c10f2..614b5d05aa62 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -279,13 +279,26 @@ mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, return NULL; } -bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk) +static void skb_fetch_src_address(const struct sk_buff *skb, + struct mptcp_addr_info *addr) +{ + addr->port = tcp_hdr(skb)->dest; + if (addr->family == AF_INET) + addr->addr.s_addr = ip_hdr(skb)->daddr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (addr->family == AF_INET6) + addr->addr6 = ipv6_hdr(skb)->daddr; +#endif +} + +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, int af, const struct sk_buff *skb) { struct mptcp_pm_add_entry *entry; struct mptcp_addr_info saddr; bool ret = false; - local_address((struct sock_common *)sk, &saddr); + saddr.family = af; + skb_fetch_src_address(skb, &saddr); spin_lock_bh(&msk->pm.lock); list_for_each_entry(entry, &msk->pm.anno_list, list) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c43ca46dbc27..7bd064b68b51 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -760,7 +760,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); -bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, int af, const struct sk_buff *skb); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool check_id); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index be43077fe76e..8be20f7b76df 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -218,7 +218,8 @@ static int subflow_check_req(struct request_sock *req, pr_debug("syn inet_sport=%d %d", ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); - if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { + if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, + sk_listener->sk_family, skb)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); return -EPERM; } @@ -750,7 +751,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, pr_debug("ack inet_sport=%d %d", ntohs(inet_sk(sk)->inet_sport), ntohs(inet_sk((struct sock *)owner)->inet_sport)); - if (!mptcp_pm_sport_in_anno_list(owner, sk)) { + if (!mptcp_pm_sport_in_anno_list(owner, sk->sk_family, skb)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); goto dispose_child; } From patchwork Thu Feb 17 14:25:36 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12750268 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 C368A291C for ; Thu, 17 Feb 2022 14:25:57 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nKhjI-0004Ds-3j; Thu, 17 Feb 2022 15:25:56 +0100 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 3/5] tcp: add mptcp join demultiplex hooks Date: Thu, 17 Feb 2022 15:25:36 +0100 Message-Id: <20220217142538.7849-4-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 Split from the next patch to make core tcp changes more obvious: add a dummy function that gets called after tcp socket demux came up empty. This will be used by mptcp to check if a tcp syn contains an mptcp join option with a valid token (connection id). If so, a hidden pernet mptcp listener socket is returned and packet resumes normally. This patch series does not cover timewait sockets so far. Signed-off-by: Florian Westphal --- include/net/mptcp.h | 5 +++++ net/ipv4/tcp_ipv4.c | 4 ++++ net/ipv6/tcp_ipv6.c | 4 ++++ 3 files changed, 13 insertions(+) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..5ee422b56902 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -197,6 +197,10 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) return htonl(0u); } +static inline struct sock *mptcp_handle_join(int af, struct sk_buff *skb) +{ + return NULL; +} #else static inline void mptcp_init(void) @@ -274,6 +278,7 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req, } static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { return htonl(0u); } +static inline struct sock *mptcp_handle_join(int af, struct sk_buff *skb) { return NULL; } #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6873f46fc8ba..6e6675a09443 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2140,6 +2140,10 @@ int tcp_v4_rcv(struct sk_buff *skb) if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; + sk = mptcp_handle_join(AF_INET, skb); + if (sk) + goto process; + tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0c648bf07f39..788040db8e9e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1782,6 +1782,10 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; + sk = mptcp_handle_join(AF_INET6, skb); + if (sk) + goto process; + tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { 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; } From patchwork Thu Feb 17 14:25:38 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12750270 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 14C7C291C for ; Thu, 17 Feb 2022 14:26:06 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nKhjQ-0004Eb-D6; Thu, 17 Feb 2022 15:26:04 +0100 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 5/5] mptcp: remove per-address listening sockets Date: Thu, 17 Feb 2022 15:25:38 +0100 Message-Id: <20220217142538.7849-6-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 Not required anymore, syn packets with a join requests are redirected to pernet mptcp pseudo-listening socket. Signed-off-by: Florian Westphal --- net/mptcp/pm_netlink.c | 65 ------------------------------------------ 1 file changed, 65 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 614b5d05aa62..8a26c7177054 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry { struct mptcp_addr_info addr; u8 flags; int ifindex; - struct socket *lsk; }; struct mptcp_pm_add_entry { @@ -954,57 +953,6 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, return ret; } -static int mptcp_pm_nl_create_listen_socket(struct sock *sk, - struct mptcp_pm_addr_entry *entry) -{ - int addrlen = sizeof(struct sockaddr_in); - struct sockaddr_storage addr; - struct mptcp_sock *msk; - struct socket *ssock; - int backlog = 1024; - int err; - - err = sock_create_kern(sock_net(sk), entry->addr.family, - SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk); - if (err) - return err; - - msk = mptcp_sk(entry->lsk->sk); - if (!msk) { - err = -EINVAL; - goto out; - } - - ssock = __mptcp_nmpc_socket(msk); - if (!ssock) { - err = -EINVAL; - goto out; - } - - mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (entry->addr.family == AF_INET6) - addrlen = sizeof(struct sockaddr_in6); -#endif - err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen); - if (err) { - pr_warn("kernel_bind error, err=%d", err); - goto out; - } - - err = kernel_listen(ssock, backlog); - if (err) { - pr_warn("kernel_listen error, err=%d", err); - goto out; - } - - return 0; - -out: - sock_release(entry->lsk); - return err; -} - int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) { struct mptcp_pm_addr_entry *entry; @@ -1050,7 +998,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->addr.port = 0; entry->ifindex = 0; entry->flags = 0; - entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) kfree(entry); @@ -1258,19 +1205,9 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) } *entry = addr; - if (entry->addr.port) { - ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); - if (ret) { - GENL_SET_ERR_MSG(info, "create listen socket error"); - kfree(entry); - return ret; - } - } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); - if (entry->lsk) - sock_release(entry->lsk); kfree(entry); return ret; } @@ -1375,8 +1312,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, /* caller must ensure the RCU grace period is already elapsed */ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { - if (entry->lsk) - sock_release(entry->lsk); kfree(entry); }