--- zzzz-none-000/linux-3.10.107/net/ipv6/tcp_ipv6.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv6/tcp_ipv6.c 2021-02-04 17:41:59.000000000 +0000 @@ -39,7 +39,8 @@ #include #include #include - +#include +#include #include #include #include @@ -59,12 +60,10 @@ #include #include #include -#include #include #include #include - -#include +#include #include #include @@ -72,8 +71,8 @@ #include #include -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb); -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); @@ -84,7 +83,7 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr) { return NULL; @@ -94,25 +93,13 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); - sk->sk_rx_dst = dst; - inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; - if (rt->rt6i_node) - inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; -} + if (dst && dst_hold_safe(dst)) { + const struct rt6_info *rt = (const struct rt6_info *)dst; -static void tcp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != TCP_CLOSE) { - if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { - tcp_prot.hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } } @@ -133,7 +120,7 @@ struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; - struct rt6_info *rt; + struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; @@ -153,9 +140,8 @@ if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; - usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -164,12 +150,12 @@ * connect() to INADDR_ANY means loopback (BSD'ism). */ - if(ipv6_addr_any(&usin->sin6_addr)) + if (ipv6_addr_any(&usin->sin6_addr)) usin->sin6_addr.s6_addr[15] = 0x1; addr_type = ipv6_addr_type(&usin->sin6_addr); - if(addr_type & IPV6_ADDR_MULTICAST) + if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { @@ -191,13 +177,13 @@ } if (tp->rx_opt.ts_recent_stamp && - !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) { + !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; tp->write_seq = 0; } - np->daddr = usin->sin6_addr; + sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -233,39 +219,37 @@ tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; - } else { - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &np->rcv_saddr); } + np->saddr = sk->sk_v6_rcv_saddr; return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; - final_p = fl6_update_dst(&fl6, np->opt, &final); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } - if (saddr == NULL) { + if (!saddr) { saddr = &fl6.saddr; - np->rcv_saddr = *saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ @@ -273,18 +257,17 @@ inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, NULL, NULL); - rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; - if (np->opt) - icsk->icsk_ext_hdr_len = (np->opt->opt_flen + - np->opt->opt_nflen); + if (opt) + icsk->icsk_ext_hdr_len = opt->opt_flen + + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); @@ -295,9 +278,11 @@ if (err) goto late_failure; + sk_set_txhash(sk); + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); @@ -336,19 +321,23 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); + struct net *net = dev_net(skb->dev); + struct request_sock *fastopen; struct ipv6_pinfo *np; + struct tcp_sock *tp; + __u32 seq, snd_una; struct sock *sk; + bool fatal; int err; - struct tcp_sock *tp; - __u32 seq; - struct net *net = dev_net(skb->dev); - sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, - th->dest, &hdr->saddr, th->source, skb->dev->ifindex); + sk = __inet6_lookup_established(net, &tcp_hashinfo, + &hdr->daddr, th->dest, + &hdr->saddr, ntohs(th->source), + skb->dev->ifindex); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -358,6 +347,10 @@ inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + fatal = icmpv6_err_convert(type, code, &err); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq, fatal); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -372,9 +365,11 @@ } tp = tcp_sk(sk); - seq = ntohl(th->seq); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = tp->fastopen_rsk; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { + !between(seq, snd_una, tp->snd_nxt)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -399,6 +394,9 @@ if (sk->sk_state == TCP_LISTEN) goto out; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + tp->mtu_info = ntohl(info); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); @@ -408,37 +406,17 @@ goto out; } - icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. + case TCP_SYN_SENT: + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * is already accepted it is treated as a connected one below. */ - WARN_ON(req->sk != NULL); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } + if (fastopen && !fastopen->sk) + break; - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - - case TCP_SYN_SENT: - case TCP_SYN_RECV: /* Cannot happen. - It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ @@ -461,28 +439,37 @@ } -static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, - struct flowi6 *fl6, +static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, + struct flowi *fl, struct request_sock *req, - u16 queue_mapping) + struct tcp_fastopen_cookie *foc, + bool attach_req) { - struct inet6_request_sock *treq = inet6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); - struct sk_buff * skb; + struct flowi6 *fl6 = &fl->u.ip6; + struct sk_buff *skb; int err = -ENOMEM; /* First, grab a route. */ - if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, + IPPROTO_TCP)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, NULL); + skb = tcp_make_synack(sk, dst, req, foc, attach_req); if (skb) { - __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); + __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, + &ireq->ir_v6_rmt_addr); - fl6->daddr = treq->rmt_addr; - skb_set_queue_mapping(skb, queue_mapping); - err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); + fl6->daddr = ireq->ir_v6_rmt_addr; + if (np->repflow && ireq->pktopts) + fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + + rcu_read_lock(); + err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), + np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -490,43 +477,27 @@ return err; } -static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) -{ - struct flowi6 fl6; - int res; - - res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0); - if (!res) - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return res; -} static void tcp_v6_reqsk_destructor(struct request_sock *req) { - kfree_skb(inet6_rsk(req)->pktopts); + kfree_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr) { return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); } -static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, - struct sock *addr_sk) +static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, + const struct sock *addr_sk) { - return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr); + return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, - struct request_sock *req) -{ - return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr); -} - -static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, + int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; @@ -610,9 +581,9 @@ return 1; } -static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v6_md5_hash_skb(char *md5_hash, + const struct tcp_md5sig_key *key, const struct sock *sk, - const struct request_sock *req, const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; @@ -620,12 +591,9 @@ struct hash_desc *desc; const struct tcphdr *th = tcp_hdr(skb); - if (sk) { - saddr = &inet6_sk(sk)->saddr; - daddr = &inet6_sk(sk)->daddr; - } else if (req) { - saddr = &inet6_rsk(req)->loc_addr; - daddr = &inet6_rsk(req)->rmt_addr; + if (sk) { /* valid for establish/request sockets */ + saddr = &sk->sk_v6_rcv_saddr; + daddr = &sk->sk_v6_daddr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; @@ -661,8 +629,12 @@ return 1; } -static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +#endif + +static bool tcp_v6_inbound_md5_hash(const struct sock *sk, + const struct sk_buff *skb) { +#ifdef CONFIG_TCP_MD5SIG const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -675,60 +647,105 @@ /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return 1; + return true; } if (!hash_expected && hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - return 1; + return true; } /* check the signature */ genhash = tcp_v6_md5_hash_skb(newhash, hash_expected, - NULL, NULL, skb); + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), &ip6h->daddr, ntohs(th->dest)); - return 1; + return true; } - return 0; -} #endif + return false; +} + +static void tcp_v6_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct inet_request_sock *ireq = inet_rsk(req); + const struct ipv6_pinfo *np = inet6_sk(sk_listener); + + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + + /* So that link locals have meaning */ + if (!sk_listener->sk_bound_dev_if && + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = tcp_v6_iif(skb); + + if (!TCP_SKB_CB(skb)->tcp_tw_isn && + (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || + np->rxopt.bits.rxinfo || + np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || + np->rxopt.bits.rxohlim || np->repflow)) { + atomic_inc(&skb->users); + ireq->pktopts = skb; + } +} + +static struct dst_entry *tcp_v6_route_req(const struct sock *sk, + struct flowi *fl, + const struct request_sock *req, + bool *strict) +{ + if (strict) + *strict = true; + return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); +} struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_rtx_synack, + .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, + .syn_ack_timeout = tcp_syn_ack_timeout, }; -#ifdef CONFIG_TCP_MD5SIG static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { - .md5_lookup = tcp_v6_reqsk_md5_lookup, + .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - + sizeof(struct ipv6hdr), +#ifdef CONFIG_TCP_MD5SIG + .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, -}; #endif + .init_req = tcp_v6_init_req, +#ifdef CONFIG_SYN_COOKIES + .cookie_init_seq = cookie_v6_init_sequence, +#endif + .route_req = tcp_v6_route_req, + .init_seq = tcp_v6_init_sequence, + .send_synack = tcp_v6_send_synack, +}; -static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 tsval, u32 tsecr, - struct tcp_md5sig_key *key, int rst, u8 tclass) +static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, + u32 ack, u32 win, u32 tsval, u32 tsecr, + int oif, struct tcp_md5sig_key *key, int rst, + u8 tclass, u32 label) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; struct sk_buff *buff; struct flowi6 fl6; - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); struct dst_entry *dst; @@ -743,7 +760,7 @@ buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); - if (buff == NULL) + if (!buff) return; skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); @@ -765,10 +782,10 @@ topt = (__be32 *)(t1 + 1); if (tsecr) { - *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - *topt++ = htonl(tsval); - *topt++ = htonl(tsecr); + put_unaligned_be32((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP, topt++); + put_unaligned_be32(tsval, topt++); + put_unaligned_be32(tsecr, topt++); } #ifdef CONFIG_TCP_MD5SIG @@ -784,6 +801,7 @@ memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; + fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; @@ -791,8 +809,11 @@ __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; - if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL) - fl6.flowi6_oif = inet6_iif(skb); + if (rt6_need_strict(&fl6.daddr) && !oif) + fl6.flowi6_oif = tcp_v6_iif(skb); + else + fl6.flowi6_oif = oif; + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); @@ -801,7 +822,7 @@ * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); @@ -814,7 +835,7 @@ kfree_skb(buff); } -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; @@ -826,11 +847,15 @@ int genhash; struct sock *sk1 = NULL; #endif + int oif; if (th->rst) return; - if (!ipv6_unicast_destination(skb)) + /* If sk not NULL, it means we did a successful lookup and incoming + * route had to be correct. prequeue might have dropped our dst. + */ + if (!sk && !ipv6_unicast_destination(skb)) return; #ifdef CONFIG_TCP_MD5SIG @@ -846,7 +871,7 @@ sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), &tcp_hashinfo, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), inet6_iif(skb)); + ntohs(th->source), tcp_v6_iif(skb)); if (!sk1) return; @@ -855,7 +880,7 @@ if (!key) goto release_sk1; - genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; } else { @@ -869,7 +894,8 @@ ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0); + oif = sk ? sk->sk_bound_dev_if : 0; + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -880,11 +906,13 @@ #endif } -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 tsval, u32 tsecr, - struct tcp_md5sig_key *key, u8 tclass) +static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, + u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, + struct tcp_md5sig_key *key, u8 tclass, + u32 label) { - tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass); + tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0, + tclass, label); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -892,208 +920,83 @@ struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), - tw->tw_tclass); + tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ /* RFC 7323 2.3 * The window field (SEG.WND) of every outgoing segment, with the * exception of segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ - tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, - req->rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp, req->ts_recent, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); + tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? + tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + 0, 0); } -static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) +static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { - struct request_sock *req, **prev; +#ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); - struct sock *nsk; - - /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, &prev, th->source, - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, inet6_iif(skb)); - if (req) - return tcp_check_req(sk, skb, req, prev, false); - - nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, - &ipv6_hdr(skb)->saddr, th->source, - &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); - - if (nsk) { - if (nsk->sk_state != TCP_TIME_WAIT) { - bh_lock_sock(nsk); - return nsk; - } - inet_twsk_put(inet_twsk(nsk)); - return NULL; - } -#ifdef CONFIG_SYN_COOKIES if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; } -/* FIXME: this is substantially similar to the ipv4 code. - * Can some kind of merge be done? -- erics - */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp_options_received tmp_opt; - struct request_sock *req; - struct inet6_request_sock *treq; - struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; - struct flowi6 fl6; - bool want_cookie = false; - if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); - if (!want_cookie) - goto drop; - } - - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); - goto drop; - } - - req = inet6_reqsk_alloc(&tcp6_request_sock_ops); - if (req == NULL) - goto drop; - -#ifdef CONFIG_TCP_MD5SIG - tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops; -#endif - - tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, NULL); - - if (want_cookie && !tmp_opt.saw_tstamp) - tcp_clear_options(&tmp_opt); - - tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - - treq = inet6_rsk(req); - treq->rmt_addr = ipv6_hdr(skb)->saddr; - treq->loc_addr = ipv6_hdr(skb)->daddr; - if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb, sock_net(sk)); - - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); - - if (!isn) { - if (ipv6_opt_accepted(sk, skb) || - np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { - atomic_inc(&skb->users); - treq->pktopts = skb; - } - - if (want_cookie) { - isn = cookie_v6_init_sequence(sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; - goto have_isn; - } - - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (tmp_opt.saw_tstamp && - tcp_death_row.sysctl_tw_recycle && - (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) { - if (!tcp_peer_is_proven(req, dst, true)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } - /* Kill the following clause, if you dislike this way. */ - else if (!sysctl_tcp_syncookies && - (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false)) { - /* Without syncookies last quarter of - * backlog is filled with destinations, - * proven to be alive. - * It means that we continue to communicate - * to destinations, already remembered - * to the moment of synflood. - */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", - &treq->rmt_addr, ntohs(tcp_hdr(skb)->source)); - goto drop_and_release; - } - - isn = tcp_v6_init_sequence(skb); - } -have_isn: - tcp_rsk(req)->snt_isn = isn; - - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_release; + return tcp_conn_request(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); - if (tcp_v6_send_synack(sk, dst, &fl6, req, - skb_get_queue_mapping(skb)) || - want_cookie) - goto drop_and_free; - - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->listener = NULL; - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - -drop_and_release: - dst_release(dst); -drop_and_free: - reqsk_free(req); drop: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } -static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +static void tcp_v6_restore_cb(struct sk_buff *skb) { - struct inet6_request_sock *treq; - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + +static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req) +{ + struct inet_request_sock *ireq; + struct ipv6_pinfo *newnp; + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; struct tcp_sock *newtp; @@ -1108,9 +1011,10 @@ * v6 mapped */ - newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst); + newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst, + req_unhash, own_req); - if (newsk == NULL) + if (!newsk) return NULL; newtcp6sk = (struct tcp6_sock *)newsk; @@ -1122,11 +1026,7 @@ memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newnp->rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1134,13 +1034,16 @@ newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; - newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1157,19 +1060,19 @@ return newsk; } - treq = inet6_rsk(req); + ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { - dst = inet6_csk_route_req(sk, &fl6, req); + dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } newsk = tcp_create_openreq_child(sk, req, skb); - if (newsk == NULL) + if (!newsk) goto out_nonewsk; /* @@ -1179,7 +1082,7 @@ */ newsk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(newsk, dst, NULL, NULL); + ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; @@ -1191,36 +1094,30 @@ memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->daddr = treq->rmt_addr; - newnp->saddr = treq->loc_addr; - newnp->rcv_saddr = treq->loc_addr; - newsk->sk_bound_dev_if = treq->iif; + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newnp->saddr = ireq->ir_v6_loc_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; + newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; - /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, - sk_gfp_atomic(sk, GFP_ATOMIC)); - consume_skb(treq->pktopts); - treq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); - } newnp->opt = NULL; - newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1228,15 +1125,18 @@ but we make one more one thing there: reattach optmem to newsk. */ - if (np->opt) - newnp->opt = ipv6_dup_options(newsk, np->opt); - + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt) - inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + - newnp->opt->opt_flen); + if (opt) + inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + + opt->opt_flen; + + tcp_ca_openreq_child(newsk, dst); - tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && @@ -1244,21 +1144,20 @@ newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != NULL) { + key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); + if (key) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, AF_INET6, key->key, key->keylen, sk_gfp_atomic(sk, GFP_ATOMIC)); } @@ -1269,7 +1168,22 @@ tcp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + if (*own_req) { + tcp_move_syn(newtp, req); + + /* Clone pktoptions received with SYN, if we own the req */ + if (ireq->pktopts) { + newnp->pktoptions = skb_clone(ireq->pktopts, + sk_gfp_atomic(sk, GFP_ATOMIC)); + consume_skb(ireq->pktopts); + ireq->pktopts = NULL; + if (newnp->pktoptions) { + tcp_v6_restore_cb(newnp->pktoptions); + skb_set_owner_r(newnp->pktoptions, newsk); + } + } + } return newsk; @@ -1282,28 +1196,8 @@ return NULL; } -static __sum16 tcp_v6_checksum_init(struct sk_buff *skb) -{ - if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - return 0; - } - } - - skb->csum = ~csum_unfold(tcp_v6_check(skb->len, - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, 0)); - - if (skb->len <= 76) { - return __skb_checksum_complete(skb); - } - return 0; -} - /* The socket must have it's spinlock held when we get - * here. + * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. @@ -1327,11 +1221,6 @@ if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); -#ifdef CONFIG_TCP_MD5SIG - if (tcp_v6_inbound_md5_hash (sk, skb)) - goto discard; -#endif - if (tcp_filter(sk, skb)) goto discard; @@ -1360,6 +1249,7 @@ struct dst_entry *dst = sk->sk_rx_dst; sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || dst->ops->check(dst, np->rx_dst_cookie) == NULL) { @@ -1368,28 +1258,24 @@ } } - if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) - goto reset; + tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); if (opt_skb) goto ipv6_pktoptions; return 0; } - if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb)) + if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { - struct sock *nsk = tcp_v6_hnd_req(sk, skb); + struct sock *nsk = tcp_v6_cookie_check(sk, skb); + if (!nsk) goto discard; - /* - * Queue it on the new socket if the new socket is active, - * otherwise we just shortcircuit this and continue with - * the new socket.. - */ - if(nsk != sk) { + if (nsk != sk) { sock_rps_save_rxhash(nsk, skb); + sk_mark_napi_id(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) @@ -1399,7 +1285,7 @@ } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) + if (tcp_rcv_state_process(sk, skb)) goto reset; if (opt_skb) goto ipv6_pktoptions; @@ -1430,13 +1316,16 @@ if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) - np->mcast_oif = inet6_iif(opt_skb); + np->mcast_oif = tcp_v6_iif(opt_skb); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; - if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb)); - if (ipv6_opt_accepted(sk, opt_skb)) { + if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) + np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); + if (np->repflow) + np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); + if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { skb_set_owner_r(opt_skb, sk); + tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); @@ -1448,6 +1337,28 @@ return 0; } +static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, + const struct tcphdr *th) +{ + /* This is tricky: we move IP6CB at its correct location into + * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because + * _decode_session6() uses IP6CB(). + * barrier() makes sure compiler won't play aliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), + sizeof(struct inet6_skb_parm)); + barrier(); + + TCP_SKB_CB(skb)->seq = ntohl(th->seq); + TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + + skb->len - th->doff*4); + TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; + TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); + TCP_SKB_CB(skb)->sacked = 0; +} + static int tcp_v6_rcv(struct sk_buff *skb) { const struct tcphdr *th; @@ -1474,20 +1385,15 @@ if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; - if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb)) + if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = tcp_hdr(skb); hdr = ipv6_hdr(skb); - TCP_SKB_CB(skb)->seq = ntohl(th->seq); - TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + - skb->len - th->doff*4); - TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); - TCP_SKB_CB(skb)->sacked = 0; - sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); +lookup: + sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest, + inet6_iif(skb)); if (!sk) goto no_tcp_socket; @@ -1495,6 +1401,37 @@ if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + struct sock *nsk; + + sk = req->rsk_listener; + tcp_v6_fill_cb(skb, hdr, th); + if (tcp_v6_inbound_md5_hash(sk, skb)) { + reqsk_put(req); + goto discard_it; + } + if (unlikely(sk->sk_state != TCP_LISTEN)) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); + if (!nsk) { + reqsk_put(req); + goto discard_and_relse; + } + if (nsk == sk) { + reqsk_put(req); + tcp_v6_restore_cb(skb); + } else if (tcp_child_process(sk, nsk, skb)) { + tcp_v6_send_reset(nsk, skb); + goto discard_and_relse; + } else { + sock_put(sk); + return 0; + } + } if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) { NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; @@ -1503,6 +1440,11 @@ if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; + tcp_v6_fill_cb(skb, hdr, th); + + if (tcp_v6_inbound_md5_hash(sk, skb)) + goto discard_and_relse; + if (tcp_filter(sk, skb)) goto discard_and_relse; th = (const struct tcphdr *)skb->data; @@ -1510,21 +1452,19 @@ skb->dev = NULL; + if (sk->sk_state == TCP_LISTEN) { + ret = tcp_v6_do_rcv(sk, skb); + goto put_and_return; + } + + sk_incoming_cpu_update(sk); + bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { -#ifdef CONFIG_NET_DMA - struct tcp_sock *tp = tcp_sk(sk); - if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = net_dma_find_channel(); - if (tp->ucopy.dma_chan) + if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); - else -#endif - { - if (!tcp_prequeue(sk, skb)) - ret = tcp_v6_do_rcv(sk, skb); - } } else if (unlikely(sk_add_backlog(sk, skb, sk->sk_rcvbuf + sk->sk_sndbuf))) { bh_unlock_sock(sk); @@ -1533,6 +1473,7 @@ } bh_unlock_sock(sk); +put_and_return: sock_put(sk); return ret ? -1 : 0; @@ -1540,7 +1481,9 @@ if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; - if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { + tcp_v6_fill_cb(skb, hdr, th); + + if (tcp_checksum_complete(skb)) { csum_error: TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -1563,10 +1506,8 @@ goto discard_it; } - if (skb->len < (th->doff<<2)) { - inet_twsk_put(inet_twsk(sk)); - goto bad_packet; - } + tcp_v6_fill_cb(skb, hdr, th); + if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; @@ -1580,12 +1521,12 @@ sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), inet6_iif(skb)); - if (sk2 != NULL) { + ntohs(th->dest), tcp_v6_iif(skb)); + if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); - inet_twsk_deschedule(tw, &tcp_death_row); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); sk = sk2; + tcp_v6_restore_cb(skb); goto process; } /* Fall through to ACK */ @@ -1594,8 +1535,10 @@ tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: + tcp_v6_restore_cb(skb); goto no_tcp_socket; - case TCP_TW_SUCCESS:; + case TCP_TW_SUCCESS: + ; } goto discard_it; } @@ -1618,6 +1561,7 @@ if (th->doff < sizeof(struct tcphdr) / 4) return; + /* Note : We use inet6_iif() here, not tcp_v6_iif() */ sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), @@ -1625,8 +1569,8 @@ if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); + if (sk_fullsock(sk)) { + struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1640,7 +1584,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, + .twsk_destructor = tcp_twsk_destructor, }; static const struct inet_connection_sock_af_ops ipv6_specific = { @@ -1675,7 +1619,6 @@ /* * TCP over IPv4 via INET6 API */ - static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, @@ -1731,31 +1674,32 @@ #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - const struct sock *sk, struct request_sock *req, int i, kuid_t uid) + const struct request_sock *req, int i) { - int ttd = req->expires - jiffies; - const struct in6_addr *src = &inet6_rsk(req)->loc_addr; - const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; + long ttd = req->rsk_timer.expires - jiffies; + const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; + const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], - ntohs(inet_rsk(req)->loc_port), + inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], - ntohs(inet_rsk(req)->rmt_port), + ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, - 0,0, /* could print option size, but that is af dependent. */ + 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, - from_kuid_munged(seq_user_ns(seq), uid), + from_kuid_munged(seq_user_ns(seq), + sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); @@ -1770,10 +1714,12 @@ const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - const struct ipv6_pinfo *np = inet6_sk(sp); + const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; + int rx_queue; + int state; - dest = &np->daddr; - src = &np->rcv_saddr; + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); @@ -1793,17 +1739,26 @@ timer_expires = jiffies; } + state = sk_state_load(sp); + if (state == TCP_LISTEN) + rx_queue = sp->sk_ack_backlog; + else + /* Because we don't lock the socket, + * we might find a transient negative value. + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - tp->write_seq-tp->snd_una, - (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), + state, + tp->write_seq - tp->snd_una, + rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -1813,22 +1768,23 @@ atomic_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh + state == TCP_LISTEN ? + fastopenq->max_qlen : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { + long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; - const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - long delta = tw->tw_ttd - jiffies; - dest = &tw6->tw_v6_daddr; - src = &tw6->tw_v6_rcv_saddr; + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); @@ -1848,6 +1804,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; + struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1860,18 +1817,12 @@ } st = seq->private; - switch (st->state) { - case TCP_SEQ_STATE_LISTENING: - case TCP_SEQ_STATE_ESTABLISHED: - get_tcp6_sock(seq, v, st->num); - break; - case TCP_SEQ_STATE_OPENREQ: - get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid); - break; - case TCP_SEQ_STATE_TIME_WAIT: + if (sk->sk_state == TCP_TIME_WAIT) get_timewait6_sock(seq, v, st->num); - break; - } + else if (sk->sk_state == TCP_NEW_SYN_RECV) + get_openreq6(seq, v, st->num); + else + get_tcp6_sock(seq, v, st->num); out: return 0; } @@ -1933,14 +1884,16 @@ .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .hash = tcp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, + .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, @@ -1972,7 +1925,6 @@ .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, };