diff options
Diffstat (limited to 'net/ipv6/tcp_ipv6.c')
| -rw-r--r-- | net/ipv6/tcp_ipv6.c | 1195 |
1 files changed, 525 insertions, 670 deletions
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 21d100b68b19..5c71501fc917 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -38,6 +38,7 @@ #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> +#include <linux/slab.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -60,6 +61,9 @@ #include <net/timewait_sock.h> #include <net/netdma.h> #include <net/inet_common.h> +#include <net/secure_seq.h> +#include <net/tcp_memcontrol.h> +#include <net/busy_poll.h> #include <asm/uaccess.h> @@ -82,12 +86,24 @@ 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, - struct in6_addr *addr) + const struct in6_addr *addr) { return NULL; } #endif +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; +} + static void tcp_v6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { @@ -96,20 +112,12 @@ static void tcp_v6_hash(struct sock *sk) return; } local_bh_disable(); - __inet6_hash(sk); + __inet6_hash(sk, NULL); local_bh_enable(); } } -static __inline__ __sum16 tcp_v6_check(int len, - struct in6_addr *saddr, - struct in6_addr *daddr, - __wsum base) -{ - return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); -} - -static __u32 tcp_v6_init_sequence(struct sk_buff *skb) +static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, @@ -125,8 +133,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct inet_connection_sock *icsk = inet_csk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct in6_addr *saddr = NULL, *final_p = NULL, final; - struct flowi fl; + struct in6_addr *saddr = NULL, *final_p, final; + struct rt6_info *rt; + struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; @@ -135,19 +144,19 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; if (usin->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - IP6_ECN_flow_init(fl.fl6_flowlabel); - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; + IP6_ECN_flow_init(fl6.flowlabel); + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -189,8 +198,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->write_seq = 0; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); - np->flow_label = fl.fl6_flowlabel; + np->daddr = usin->sin6_addr; + np->flow_label = fl6.flowlabel; /* * TCP over IPv4 @@ -226,10 +235,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, #endif goto failure; } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); } return err; @@ -238,49 +246,42 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!ipv6_addr_any(&np->rcv_saddr)) saddr = &np->rcv_saddr; - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, - (saddr ? saddr : &np->saddr)); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + fl6.flowi6_proto = IPPROTO_TCP; + fl6.daddr = np->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; - security_sk_classify_flow(sk, &fl); + final_p = fl6_update_dst(&fl6, np->opt, &final); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto failure; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto failure; } if (saddr == NULL) { - saddr = &fl.fl6_src; - ipv6_addr_copy(&np->rcv_saddr, saddr); + saddr = &fl6.saddr; + np->rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + np->saddr = *saddr; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; __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)) + tcp_fetch_timewait_stamp(sk, dst); + icsk->icsk_ext_hdr_len = 0; if (np->opt) icsk->icsk_ext_hdr_len = (np->opt->opt_flen + @@ -288,18 +289,18 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(&tcp_death_row, sk); if (err) goto late_failure; - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, - inet->sport, - inet->dport); + inet->inet_sport, + inet->inet_dport); err = tcp_connect(sk); if (err) @@ -311,15 +312,32 @@ late_failure: tcp_set_state(sk, TCP_CLOSE); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } +static void tcp_v6_mtu_reduced(struct sock *sk) +{ + struct dst_entry *dst; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + + dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + if (!dst) + return; + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + tcp_sync_mss(sk, dst_mtu(dst)); + tcp_simple_retransmit(sk); + } +} + static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; @@ -343,12 +361,17 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } bh_lock_sock(sk); - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; + if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + tp = tcp_sk(sk); seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && @@ -359,52 +382,28 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); - if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst = NULL; - - if (sock_owned_by_user(sk)) - goto out; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) - goto out; - - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi fl; - - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; - security_skb_classify_flow(skb, &fl); - - if ((err = ip6_dst_lookup(sk, &dst, &fl))) { - sk->sk_err_soft = -err; - goto out; - } - - if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) { - sk->sk_err_soft = -err; - goto out; - } + if (dst) + dst->ops->redirect(dst, sk, skb); + goto out; + } - } else - dst_hold(dst); + if (type == ICMPV6_PKT_TOOBIG) { + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { - tcp_sync_mss(sk, dst_mtu(dst)); - tcp_simple_retransmit(sk); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); + tp->mtu_info = ntohl(info); + if (!sock_owned_by_user(sk)) + tcp_v6_mtu_reduced(sk); + else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, + &tp->tsq_flags)) + sock_hold(sk); goto out; } @@ -433,6 +432,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -460,75 +460,44 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, + struct flowi6 *fl6, + struct request_sock *req, + u16 queue_mapping) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; - struct ipv6_txoptions *opt = NULL; - struct in6_addr * final_p = NULL, final; - struct flowi fl; - struct dst_entry *dst; - int err = -1; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.fl6_flowlabel = 0; - fl.oif = treq->iif; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); - - opt = np->opt; - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + int err = -ENOMEM; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto done; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + /* First, grab a route. */ + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req); - if (skb) { - struct tcphdr *th = tcp_hdr(skb); + skb = tcp_make_synack(sk, dst, req, NULL); - th->check = tcp_v6_check(skb->len, - &treq->loc_addr, &treq->rmt_addr, - csum_partial(th, skb->len, skb->csum)); + if (skb) { + __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + fl6->daddr = treq->rmt_addr; + skb_set_queue_mapping(skb, queue_mapping); + err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return err; } -static inline void syn_flood_warning(struct sk_buff *skb) +static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) { -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) - printk(KERN_INFO - "TCPv6: Possible SYN flooding on port %d. " - "Sending cookies.\n", ntohs(tcp_hdr(skb)->dest)); - else -#endif - printk(KERN_INFO - "TCPv6: Possible SYN flooding on port %d. " - "Dropping request.\n", ntohs(tcp_hdr(skb)->dest)); + 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) @@ -538,21 +507,9 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, - struct in6_addr *addr) + const struct in6_addr *addr) { - struct tcp_sock *tp = tcp_sk(sk); - int i; - - BUG_ON(tp == NULL); - - if (!tp->md5sig_info || !tp->md5sig_info->entries6) - return NULL; - - for (i = 0; i < tp->md5sig_info->entries6; i++) { - if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, addr)) - return &tp->md5sig_info->keys6[i].base; - } - return NULL; + 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, @@ -567,135 +524,11 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr); } -static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, - char *newkey, u8 newkeylen) -{ - /* Add key to the list */ - struct tcp_md5sig_key *key; - struct tcp_sock *tp = tcp_sk(sk); - struct tcp6_md5sig_key *keys; - - key = tcp_v6_md5_do_lookup(sk, peer); - if (key) { - /* modify existing entry - just update that one */ - kfree(key->key); - key->key = newkey; - key->keylen = newkeylen; - } else { - /* reallocate new list if current one is full. */ - if (!tp->md5sig_info) { - tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC); - if (!tp->md5sig_info) { - kfree(newkey); - return -ENOMEM; - } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - } - if (tcp_alloc_md5sig_pool(sk) == NULL) { - kfree(newkey); - return -ENOMEM; - } - if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) { - keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) * - (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC); - - if (!keys) { - tcp_free_md5sig_pool(); - kfree(newkey); - return -ENOMEM; - } - - if (tp->md5sig_info->entries6) - memmove(keys, tp->md5sig_info->keys6, - (sizeof (tp->md5sig_info->keys6[0]) * - tp->md5sig_info->entries6)); - - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = keys; - tp->md5sig_info->alloced6++; - } - - ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, - peer); - tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; - tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; - - tp->md5sig_info->entries6++; - } - return 0; -} - -static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk, - u8 *newkey, __u8 newkeylen) -{ - return tcp_v6_md5_do_add(sk, &inet6_sk(addr_sk)->daddr, - newkey, newkeylen); -} - -static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer) -{ - struct tcp_sock *tp = tcp_sk(sk); - int i; - - for (i = 0; i < tp->md5sig_info->entries6; i++) { - if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, peer)) { - /* Free the key */ - kfree(tp->md5sig_info->keys6[i].base.key); - tp->md5sig_info->entries6--; - - if (tp->md5sig_info->entries6 == 0) { - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = NULL; - tp->md5sig_info->alloced6 = 0; - } else { - /* shrink the database */ - if (tp->md5sig_info->entries6 != i) - memmove(&tp->md5sig_info->keys6[i], - &tp->md5sig_info->keys6[i+1], - (tp->md5sig_info->entries6 - i) - * sizeof (tp->md5sig_info->keys6[0])); - } - tcp_free_md5sig_pool(); - return 0; - } - } - return -ENOENT; -} - -static void tcp_v6_clear_md5_list (struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - int i; - - if (tp->md5sig_info->entries6) { - for (i = 0; i < tp->md5sig_info->entries6; i++) - kfree(tp->md5sig_info->keys6[i].base.key); - tp->md5sig_info->entries6 = 0; - tcp_free_md5sig_pool(); - } - - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = NULL; - tp->md5sig_info->alloced6 = 0; - - if (tp->md5sig_info->entries4) { - for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4 = 0; - tcp_free_md5sig_pool(); - } - - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; -} - 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; - u8 *newkey; if (optlen < sizeof(cmd)) return -EINVAL; @@ -707,49 +540,35 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, return -EINVAL; if (!cmd.tcpm_keylen) { - if (!tcp_sk(sk)->md5sig_info) - return -ENOENT; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) - return tcp_v4_md5_do_del(sk, sin6->sin6_addr.s6_addr32[3]); - return tcp_v6_md5_do_del(sk, &sin6->sin6_addr); + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET); + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - if (!tcp_sk(sk)->md5sig_info) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p; - - p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL); - if (!p) - return -ENOMEM; - - tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - } + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - if (!newkey) - return -ENOMEM; - if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { - return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3], - newkey, cmd.tcpm_keylen); - } - return tcp_v6_md5_do_add(sk, &sin6->sin6_addr, newkey, cmd.tcpm_keylen); + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, - struct in6_addr *daddr, - struct in6_addr *saddr, int nbytes) + const struct in6_addr *daddr, + const struct in6_addr *saddr, int nbytes) { struct tcp6_pseudohdr *bp; struct scatterlist sg; bp = &hp->md5_blk.ip6; /* 1. TCP pseudo-header (RFC2460) */ - ipv6_addr_copy(&bp->saddr, saddr); - ipv6_addr_copy(&bp->daddr, daddr); + bp->saddr = *saddr; + bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); @@ -758,8 +577,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, } static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, - struct in6_addr *daddr, struct in6_addr *saddr, - struct tcphdr *th) + const struct in6_addr *daddr, struct in6_addr *saddr, + const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct hash_desc *desc; @@ -791,13 +610,14 @@ clear_hash_noput: } static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - struct sock *sk, struct request_sock *req, - struct sk_buff *skb) + const struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb) { - struct in6_addr *saddr, *daddr; + const struct in6_addr *saddr, *daddr; struct tcp_md5sig_pool *hp; struct hash_desc *desc; - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); if (sk) { saddr = &inet6_sk(sk)->saddr; @@ -806,7 +626,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, saddr = &inet6_rsk(req)->loc_addr; daddr = &inet6_rsk(req)->rmt_addr; } else { - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } @@ -840,12 +660,12 @@ clear_hash_noput: return 1; } -static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) +static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { - __u8 *hash_location = NULL; + const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); int genhash; u8 newhash[16]; @@ -872,12 +692,10 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) NULL, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash %s for (%pI6, %u)->(%pI6, %u)\n", - genhash ? "failed" : "mismatch", - &ip6h->saddr, ntohs(th->source), - &ip6h->daddr, ntohs(th->dest)); - } + 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 0; @@ -887,10 +705,11 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) 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_send_synack, + .rtx_syn_ack = tcp_v6_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, - .send_reset = tcp_v6_send_reset + .send_reset = tcp_v6_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -900,95 +719,21 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -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, -}; - -static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct tcphdr *th = tcp_hdr(skb); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, - csum_partial(th, th->doff<<2, - skb->csum)); - } -} - -static int tcp_v6_gso_send_check(struct sk_buff *skb) -{ - struct ipv6hdr *ipv6h; - struct tcphdr *th; - - if (!pskb_may_pull(skb, sizeof(*th))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_TCP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - return 0; -} - -static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - struct ipv6hdr *iph = skb_gro_network_header(skb); - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - - /* fall through */ - case CHECKSUM_NONE: - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - } - - return tcp_gro_receive(head, skb); -} - -static int tcp6_gro_complete(struct sk_buff *skb) -{ - struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); - - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - - return tcp_gro_complete(skb); -} - static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 ts, struct tcp_md5sig_key *key, int rst) + u32 tsval, u32 tsecr, + struct tcp_md5sig_key *key, int rst, u8 tclass) { - struct tcphdr *th = tcp_hdr(skb), *t1; + const struct tcphdr *th = tcp_hdr(skb); + struct tcphdr *t1; struct sk_buff *buff; - struct flowi fl; + struct flowi6 fl6; struct net *net = 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; __be32 *topt; - if (ts) + if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (key) @@ -1003,7 +748,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); t1 = (struct tcphdr *) skb_push(buff, tot_len); - skb_reset_transport_header(skb); + skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); @@ -1018,11 +763,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, topt = (__be32 *)(t1 + 1); - if (ts) { + if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - *topt++ = htonl(tcp_time_stamp); - *topt++ = htonl(ts); + *topt++ = htonl(tsval); + *topt++ = htonl(tsecr); } #ifdef CONFIG_TCP_MD5SIG @@ -1035,35 +780,34 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, } #endif - buff->csum = csum_partial(t1, tot_len, 0); + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = ipv6_hdr(skb)->saddr; + fl6.saddr = ipv6_hdr(skb)->daddr; - memset(&fl, 0, sizeof(fl)); - ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr); + buff->ip_summed = CHECKSUM_PARTIAL; + buff->csum = 0; - t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, - tot_len, IPPROTO_TCP, - buff->csum); + __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); - fl.proto = IPPROTO_TCP; - fl.oif = inet6_iif(skb); - fl.fl_ip_dport = t1->dest; - fl.fl_ip_sport = t1->source; - security_skb_classify_flow(skb, &fl); + fl6.flowi6_proto = IPPROTO_TCP; + if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL) + fl6.flowi6_oif = inet6_iif(skb); + fl6.fl6_dport = t1->dest; + fl6.fl6_sport = t1->source; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ - if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { - if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { - skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl, NULL, 0); - TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - if (rst) - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); - return; - } + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); + if (!IS_ERR(dst)) { + skb_dst_set(buff, dst); + ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + if (rst) + TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); + return; } kfree_skb(buff); @@ -1071,9 +815,16 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; +#ifdef CONFIG_TCP_MD5SIG + const __u8 *hash_location = NULL; + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; +#endif if (th->rst) return; @@ -1082,8 +833,33 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) return; #ifdef CONFIG_TCP_MD5SIG - if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr); + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, &ipv6h->saddr, + th->source, &ipv6h->daddr, + ntohs(th->source), inet6_iif(skb)); + if (!sk1) + return; + + rcu_read_lock(); + key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr); + if (!key) + goto release_sk1; + + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; + } #endif if (th->ack) @@ -1092,13 +868,22 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1); + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0); + +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif } -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, - struct tcp_md5sig_key *key) +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) { - tcp_v6_send_response(skb, seq, ack, win, ts, key, 0); + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -1108,7 +893,9 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw)); + tcp_time_stamp + tcptw->tw_ts_offset, + tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), + tw->tw_tclass); inet_twsk_put(tw); } @@ -1116,8 +903,9 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr)); + tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, + req->rcv_wnd, tcp_time_stamp, req->ts_recent, + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); } @@ -1132,7 +920,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, inet6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, @@ -1148,7 +936,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) } #ifdef CONFIG_SYN_COOKIES - if (!th->rst && !th->syn && th->ack) + if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; @@ -1159,17 +947,15 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) */ 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_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; -#ifdef CONFIG_SYN_COOKIES - int want_cookie = 0; -#else -#define want_cookie 0 -#endif + 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); @@ -1177,19 +963,17 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { - if (net_ratelimit()) - syn_flood_warning(skb); -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) - want_cookie = 1; - else -#endif - goto drop; + if ((sysctl_tcp_syncookies == 2 || + 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) + 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) @@ -1202,8 +986,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) 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); + tcp_parse_options(skb, &tmp_opt, 0, NULL); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1212,47 +995,90 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); treq = inet6_rsk(req); - ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); - if (!want_cookie) - TCP_ECN_create_request(req, tcp_hdr(skb)); - - if (want_cookie) { - isn = cookie_v6_init_sequence(sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; - } else if (!isn) { + 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; } - 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 (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; - security_inet_conn_request(sk, skb, req); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_release; - if (tcp_v6_send_synack(sk, req)) - goto drop; + if (tcp_v6_send_synack(sk, dst, &fl6, req, + skb_get_queue_mapping(skb)) || + want_cookie) + goto drop_and_free; - if (!want_cookie) { - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - } + 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: - if (req) - reqsk_free(req); - + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } @@ -1266,10 +1092,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; - struct ipv6_txoptions *opt; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -1290,13 +1116,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newnp->rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1304,10 +1128,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1325,43 +1152,19 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } treq = inet6_rsk(req); - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; - if (dst == NULL) { - struct in6_addr *final_p = NULL, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); - - if (ip6_dst_lookup(sk, &dst, &fl)) - goto out; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + if (!dst) { + dst = inet6_csk_route_req(sk, &fl6, req); + if (!dst) goto out; } newsk = tcp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -1371,6 +1174,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(newsk, dst, NULL, NULL); + inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; @@ -1381,16 +1185,17 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newnp->daddr = treq->rmt_addr; + newnp->saddr = treq->loc_addr; + newnp->rcv_saddr = treq->loc_addr; newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... First: no IPv4 options. */ - newinet->opt = NULL; + newinet->inet_opt = NULL; + newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ @@ -1399,8 +1204,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); - kfree_skb(treq->pktopts); + 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); @@ -1408,6 +1214,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1415,11 +1222,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, but we make one more one thing there: reattach optmem to newsk. */ - if (opt) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt) @@ -1428,10 +1232,15 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); - newtp->advmss = dst_metric(dst, RTAX_ADVMSS); + newtp->advmss = dst_metric_advmss(dst); + if (tcp_sk(sk)->rx_opt.user_mss && + tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) + newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; + tcp_initialize_rcv_mss(newsk); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + 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 */ @@ -1441,25 +1250,27 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); - if (newkey != NULL) - tcp_v6_md5_do_add(newsk, &newnp->daddr, - newkey, key->keylen); + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, + AF_INET6, key->key, key->keylen, + sk_gfp_atomic(sk, GFP_ATOMIC)); } #endif - __inet6_hash(newsk); - __inet_inherit_port(sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) { + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto out; + } + __inet6_hash(newsk, NULL); return newsk; out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +out_nonewsk: + dst_release(dst); out: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return NULL; } @@ -1535,13 +1346,21 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - TCP_CHECK_TIMER(sk); - if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) - goto reset; - TCP_CHECK_TIMER(sk); + struct dst_entry *dst = sk->sk_rx_dst; + + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + + tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); if (opt_skb) goto ipv6_pktoptions; return 0; @@ -1561,18 +1380,18 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) __kfree_skb(opt_skb); return 0; } - } + } else + sock_rps_save_rxhash(sk, skb); - TCP_CHECK_TIMER(sk); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; - TCP_CHECK_TIMER(sk); if (opt_skb) goto ipv6_pktoptions; return 0; @@ -1585,6 +1404,7 @@ discard: kfree_skb(skb); return 0; csum_err: + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1604,6 +1424,8 @@ ipv6_pktoptions: np->mcast_oif = inet6_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)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1619,7 +1441,8 @@ ipv6_pktoptions: static int tcp_v6_rcv(struct sk_buff *skb) { - struct tcphdr *th; + const struct tcphdr *th; + const struct ipv6hdr *hdr; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); @@ -1643,15 +1466,16 @@ static int tcp_v6_rcv(struct sk_buff *skb) goto discard_it; if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb)) - goto bad_packet; + 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)->flags = ipv6_get_dsfield(ipv6_hdr(skb)); + 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); @@ -1662,12 +1486,18 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto discard_and_relse; + } + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; if (sk_filter(sk, skb)) goto discard_and_relse; + sk_mark_napi_id(sk, skb); skb->dev = NULL; bh_lock_sock_nested(sk); @@ -1676,7 +1506,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v6_do_rcv(sk, skb); else @@ -1685,8 +1515,12 @@ process: if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); } - } else - sk_add_backlog(sk, skb); + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { + bh_unlock_sock(sk); + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); + goto discard_and_relse; + } bh_unlock_sock(sk); sock_put(sk); @@ -1697,6 +1531,8 @@ no_tcp_socket: goto discard_it; if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { +csum_error: + TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: TCP_INC_STATS_BH(net, TCP_MIB_INERRS); } else { @@ -1704,11 +1540,6 @@ bad_packet: } discard_it: - - /* - * Discard frame - */ - kfree_skb(skb); return 0; @@ -1722,10 +1553,13 @@ do_time_wait: goto discard_it; } - if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { - TCP_INC_STATS_BH(net, TCP_MIB_INERRS); + if (skb->len < (th->doff<<2)) { inet_twsk_put(inet_twsk(sk)); - goto discard_it; + goto bad_packet; + } + if (tcp_checksum_complete(skb)) { + inet_twsk_put(inet_twsk(sk)); + goto csum_error; } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { @@ -1734,6 +1568,7 @@ do_time_wait: struct sock *sk2; 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) { @@ -1755,20 +1590,58 @@ do_time_wait: goto discard_it; } -static int tcp_v6_remember_stamp(struct sock *sk) +static void tcp_v6_early_demux(struct sk_buff *skb) { - /* Alas, not yet... */ - return 0; + const struct ipv6hdr *hdr; + const struct tcphdr *th; + struct sock *sk; + + if (skb->pkt_type != PACKET_HOST) + return; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; + + hdr = ipv6_hdr(skb); + th = tcp_hdr(skb); + + if (th->doff < sizeof(struct tcphdr) / 4) + return; + + sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + inet6_iif(skb)); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst && + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) + skb_dst_set_noref(skb, dst); + } + } } +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, +}; + static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, + .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v6_remember_stamp, .net_header_len = sizeof(struct ipv6hdr), + .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, @@ -1784,7 +1657,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, - .md5_add = tcp_v6_md5_add_func, .md5_parse = tcp_v6_parse_md5_keys, }; #endif @@ -1797,9 +1669,9 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, @@ -1816,7 +1688,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, - .md5_add = tcp_v6_md5_add_func, .md5_parse = tcp_v6_parse_md5_keys, }; #endif @@ -1827,60 +1698,20 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = 2; - - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; - - tp->reordering = sysctl_tcp_reordering; - sk->sk_state = TCP_CLOSE; + tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); #ifdef CONFIG_TCP_MD5SIG - tp->af_specific = &tcp_sock_ipv6_specific; + tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); - local_bh_enable(); - return 0; } static void tcp_v6_destroy_sock(struct sock *sk) { -#ifdef CONFIG_TCP_MD5SIG - /* Clean up the MD5 key list */ - if (tcp_sk(sk)->md5sig_info) - tcp_v6_clear_md5_list(sk); -#endif tcp_v4_destroy_sock(sk); inet6_destroy_sock(sk); } @@ -1888,18 +1719,18 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct sock *sk, struct request_sock *req, int i, int uid) + const struct sock *sk, struct request_sock *req, int i, kuid_t uid) { int ttd = req->expires - jiffies; - struct in6_addr *src = &inet6_rsk(req)->loc_addr; - struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; + const struct in6_addr *src = &inet6_rsk(req)->loc_addr; + const struct in6_addr *dest = &inet6_rsk(req)->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 %p\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], @@ -1911,8 +1742,8 @@ static void get_openreq6(struct seq_file *seq, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), - req->retrans, - uid, + req->num_timeout, + from_kuid_munged(seq_user_ns(seq), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); @@ -1920,19 +1751,19 @@ static void get_openreq6(struct seq_file *seq, static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; - struct inet_sock *inet = inet_sk(sp); - struct tcp_sock *tp = tcp_sk(sp); + 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); - struct ipv6_pinfo *np = inet6_sk(sp); + const struct ipv6_pinfo *np = inet6_sk(sp); dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -1950,7 +1781,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %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, @@ -1960,9 +1791,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) tp->write_seq-tp->snd_una, (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, - sock_i_uid(sp), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, @@ -1977,13 +1808,10 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; - struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + 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; @@ -1992,14 +1820,14 @@ static void get_timewait6_sock(struct seq_file *seq, seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\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, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw); } @@ -2034,18 +1862,24 @@ out: return 0; } +static const struct file_operations tcp6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = tcp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct tcp_seq_afinfo tcp6_seq_afinfo = { .name = "tcp6", .family = AF_INET6, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &tcp6_afinfo_seq_fops, .seq_ops = { .show = tcp6_seq_show, }, }; -int tcp6_proc_init(struct net *net) +int __net_init tcp6_proc_init(struct net *net) { return tcp_proc_register(net, &tcp6_seq_afinfo); } @@ -2056,6 +1890,17 @@ void tcp6_proc_exit(struct net *net) } #endif +static void tcp_v6_clear_sk(struct sock *sk, int size) +{ + struct inet_sock *inet = inet_sk(sk); + + /* we do not want to clear pinet6 field, because of RCU lookups */ + sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6)); + + size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); + memset(&inet->pinet6 + 1, 0, size); +} + struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, @@ -2070,16 +1915,20 @@ struct proto tcpv6_prot = { .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .recvmsg = tcp_recvmsg, + .sendmsg = tcp_sendmsg, + .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, + .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_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, @@ -2088,19 +1937,21 @@ struct proto tcpv6_prot = { .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = &tcp_hashinfo, + .no_autobind = true, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_MEMCG_KMEM + .proto_cgroup = tcp_proto_cgroup, +#endif + .clear_sk = tcp_v6_clear_sk, }; static const struct inet6_protocol tcpv6_protocol = { + .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -2109,27 +1960,31 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; -static int tcpv6_net_init(struct net *net) +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); } -static void tcpv6_net_exit(struct net *net) +static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6); +} + +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } static struct pernet_operations tcpv6_net_ops = { - .init = tcpv6_net_init, - .exit = tcpv6_net_exit, + .init = tcpv6_net_init, + .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) @@ -2151,10 +2006,10 @@ int __init tcpv6_init(void) out: return ret; -out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); +out_tcpv6_protocol: + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); goto out; } |