diff options
Diffstat (limited to '')
| -rw-r--r-- | net/mptcp/subflow.c | 187 |
1 files changed, 164 insertions, 23 deletions
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8b2338dfdc80..e1fbcab257e6 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -18,12 +18,15 @@ #include <net/tcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> +#include <net/transp_v6.h> #endif #include <net/mptcp.h> #include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" +static void mptcp_subflow_ops_undo_override(struct sock *ssk); + static void SUBFLOW_REQ_INC_STATS(struct request_sock *req, enum linux_mptcp_mib_field field) { @@ -61,11 +64,23 @@ static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk) } /* validate received token and create truncated hmac and nonce for SYN-ACK */ -static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, - const struct sk_buff *skb) +static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req) { - struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_sock *msk = subflow_req->msk; u8 hmac[SHA256_DIGEST_SIZE]; + + get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); + + subflow_generate_hmac(msk->local_key, msk->remote_key, + subflow_req->local_nonce, + subflow_req->remote_nonce, hmac); + + subflow_req->thmac = get_unaligned_be64(hmac); +} + +static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_sock *msk; int local_id; @@ -82,13 +97,6 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, } subflow_req->local_id = local_id; - get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); - - subflow_generate_hmac(msk->local_key, msk->remote_key, - subflow_req->local_nonce, - subflow_req->remote_nonce, hmac); - - subflow_req->thmac = get_unaligned_be64(hmac); return msk; } @@ -102,6 +110,11 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis mptcp_token_init_request(req); } +static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -171,12 +184,30 @@ again: subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; - subflow_req->msk = subflow_token_join_request(req, skb); + subflow_req->msk = subflow_token_join_request(req); /* Can't fall back to TCP in this case. */ if (!subflow_req->msk) return -EPERM; + if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { + 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)) { + sock_put((struct sock *)subflow_req->msk); + mptcp_token_destroy_request(req); + tcp_request_sock_ops.destructor(req); + subflow_req->msk = NULL; + subflow_req->mp_join = 0; + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); + return -EPERM; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); + } + + subflow_req_create_thmac(subflow_req); + if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); @@ -318,6 +349,11 @@ void mptcp_subflow_reset(struct sock *ssk) sock_put(sk); } +static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -335,6 +371,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (subflow->conn_finished) return; + mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -383,6 +420,13 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + + if (subflow_use_different_dport(mptcp_sk(parent), sk)) { + pr_debug("synack inet_dport=%d %d", + ntohs(inet_sk(sk)->inet_dport), + ntohs(inet_sk(parent)->inet_dport)); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); + } } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); @@ -419,6 +463,7 @@ drop: static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; static struct inet_connection_sock_af_ops subflow_v6_specific; static struct inet_connection_sock_af_ops subflow_v6m_specific; +static struct proto tcpv6_prot_override; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -500,6 +545,8 @@ static void subflow_ulp_fallback(struct sock *sk, icsk->icsk_ulp_ops = NULL; rcu_assign_pointer(icsk->icsk_ulp_data, NULL); tcp_sk(sk)->is_mptcp = 0; + + mptcp_subflow_ops_undo_override(sk); } static void subflow_drop_ctx(struct sock *ssk) @@ -620,7 +667,7 @@ create_child: * created mptcp socket */ new_msk->sk_destruct = mptcp_sock_destruct; - mptcp_pm_new_connection(mptcp_sk(new_msk), 1); + mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); ctx->conn = new_msk; new_msk = NULL; @@ -645,6 +692,17 @@ create_child: SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; + + if (subflow_use_different_sport(owner, 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)) { + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); + goto out; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); + } } } @@ -673,6 +731,7 @@ dispose_child: } static struct inet_connection_sock_af_ops subflow_specific; +static struct proto tcp_prot_override; enum mapping_status { MAPPING_OK, @@ -886,6 +945,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, subflow->map_valid = 0; } +/* sched mptcp worker to remove the subflow if no more data is pending */ +static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) +{ + struct sock *sk = (struct sock *)msk; + + if (likely(ssk->sk_state != TCP_CLOSE)) + return; + + if (skb_queue_empty(&ssk->sk_receive_queue) && + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { + sock_hold(sk); + if (!schedule_work(&msk->work)) + sock_put(sk); + } +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -924,11 +999,11 @@ static bool subflow_check_data_avail(struct sock *ssk) } if (status != MAPPING_OK) - return false; + goto no_data; skb = skb_peek(&ssk->sk_receive_queue); if (WARN_ON_ONCE(!skb)) - return false; + goto no_data; /* if msk lacks the remote key, this subflow must provide an * MP_CAPABLE-based mapping @@ -962,6 +1037,9 @@ static bool subflow_check_data_avail(struct sock *ssk) } return true; +no_data: + subflow_sched_work_if_closed(msk, ssk); + return false; fatal: /* fatal protocol error, close the socket */ /* This barrier is coupled with smp_rmb() in tcp_poll() */ @@ -1018,6 +1096,12 @@ static void subflow_data_ready(struct sock *sk) msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; @@ -1032,7 +1116,10 @@ static void subflow_data_ready(struct sock *sk) static void subflow_write_space(struct sock *ssk) { - /* we take action in __mptcp_clean_una() */ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); } void __mptcp_error_report(struct sock *sk) @@ -1105,22 +1192,32 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) } #endif -static void mptcp_info2sockaddr(const struct mptcp_addr_info *info, - struct sockaddr_storage *addr) +void mptcp_info2sockaddr(const struct mptcp_addr_info *info, + struct sockaddr_storage *addr, + unsigned short family) { memset(addr, 0, sizeof(*addr)); - addr->ss_family = info->family; + addr->ss_family = family; if (addr->ss_family == AF_INET) { struct sockaddr_in *in_addr = (struct sockaddr_in *)addr; - in_addr->sin_addr = info->addr; + if (info->family == AF_INET) + in_addr->sin_addr = info->addr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (ipv6_addr_v4mapped(&info->addr6)) + in_addr->sin_addr.s_addr = info->addr6.s6_addr32[3]; +#endif in_addr->sin_port = info->port; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->ss_family == AF_INET6) { struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr; - in6_addr->sin6_addr = info->addr6; + if (info->family == AF_INET) + ipv6_addr_set_v4mapped(info->addr.s_addr, + &in6_addr->sin6_addr); + else + in6_addr->sin6_addr = info->addr6; in6_addr->sin6_port = info->port; } #endif @@ -1164,11 +1261,11 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_key = msk->remote_key; subflow->local_key = msk->local_key; subflow->token = msk->token; - mptcp_info2sockaddr(loc, &addr); + mptcp_info2sockaddr(loc, &addr, ssk->sk_family); addrlen = sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (loc->family == AF_INET6) + if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif ssk->sk_bound_dev_if = loc->ifindex; @@ -1184,13 +1281,16 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP); - mptcp_info2sockaddr(remote, &addr); + mptcp_info2sockaddr(remote, &addr, ssk->sk_family); mptcp_add_pending_subflow(msk, subflow); err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); if (err && err != -EINPROGRESS) goto failed_unlink; + /* discard the subflow socket */ + mptcp_sock_graft(ssk, sk->sk_socket); + iput(SOCK_INODE(sf)); return err; failed_unlink: @@ -1228,6 +1328,25 @@ static void mptcp_attach_cgroup(struct sock *parent, struct sock *child) #endif /* CONFIG_SOCK_CGROUP_DATA */ } +static void mptcp_subflow_ops_override(struct sock *ssk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (ssk->sk_prot == &tcpv6_prot) + ssk->sk_prot = &tcpv6_prot_override; + else +#endif + ssk->sk_prot = &tcp_prot_override; +} + +static void mptcp_subflow_ops_undo_override(struct sock *ssk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (ssk->sk_prot == &tcpv6_prot_override) + ssk->sk_prot = &tcpv6_prot; + else +#endif + ssk->sk_prot = &tcp_prot; +} int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) { struct mptcp_subflow_context *subflow; @@ -1283,6 +1402,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) *new_sock = sf; sock_hold(sk); subflow->conn = sk; + mptcp_subflow_ops_override(sf->sk); return 0; } @@ -1299,6 +1419,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, rcu_assign_pointer(icsk->icsk_ulp_data, ctx); INIT_LIST_HEAD(&ctx->node); + INIT_LIST_HEAD(&ctx->delegated_node); pr_debug("subflow=%p", ctx); @@ -1331,6 +1452,7 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); if (subflow_simultaneous_connect(sk)) { + mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); @@ -1348,6 +1470,8 @@ static void subflow_state_change(struct sock *sk) if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + subflow_sched_work_if_closed(mptcp_sk(parent), sk); + if (__mptcp_check_fallback(mptcp_sk(parent)) && !subflow->rx_eof && subflow_is_done(sk)) { subflow->rx_eof = 1; @@ -1412,6 +1536,7 @@ static void subflow_ulp_release(struct sock *ssk) sock_put(sk); } + mptcp_subflow_ops_undo_override(ssk); if (release) kfree_rcu(ctx, rcu); } @@ -1466,6 +1591,16 @@ static void subflow_ulp_clone(const struct request_sock *req, } } +static void tcp_release_cb_override(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (mptcp_subflow_has_delegated_action(subflow)) + mptcp_subflow_process_delegated(ssk); + + tcp_release_cb(ssk); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -1506,6 +1641,9 @@ void __init mptcp_subflow_init(void) subflow_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_specific.sk_rx_dst_set = subflow_finish_connect; + tcp_prot_override = tcp_prot; + tcp_prot_override.release_cb = tcp_release_cb_override; + #if IS_ENABLED(CONFIG_MPTCP_IPV6) subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req; @@ -1521,6 +1659,9 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; subflow_v6m_specific.net_frag_header_len = 0; + + tcpv6_prot_override = tcpv6_prot; + tcpv6_prot_override.release_cb = tcp_release_cb_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); |