diff options
author | Arnaldo Carvalho de Melo <acme@mandriva.com> | 2005-12-13 23:24:53 -0800 |
---|---|---|
committer | David S. Miller <davem@sunset.davemloft.net> | 2006-01-03 13:10:52 -0800 |
commit | 3df80d9320bcaea72b1b4761a319c79cb3fdaf5f (patch) | |
tree | 20ca32dc85b1ec211c6bb91acd325e039bdb496f /net | |
parent | 399c07def62a77678d633f5b3005431423a424a8 (diff) |
[DCCP]: Introduce DCCPv6
Still needs mucho polishing, specially in the checksum code, but works
just fine, inet_diag/iproute2 and all 8)
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/dccp/Makefile | 4 | ||||
-rw-r--r-- | net/dccp/ipv6.c | 1438 | ||||
-rw-r--r-- | net/dccp/ipv6.h | 37 | ||||
-rw-r--r-- | net/dccp/minisocks.c | 13 |
4 files changed, 1491 insertions, 1 deletions
diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 344a8da153fc..87b27fff6e3b 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,3 +1,7 @@ +obj-$(CONFIG_IPV6) += dccp_ipv6.o + +dccp_ipv6-y := ipv6.o + obj-$(CONFIG_IP_DCCP) += dccp.o dccp-y := ccid.o input.o ipv4.o minisocks.o options.o output.o proto.o \ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c new file mode 100644 index 000000000000..a7d2aee5b3af --- /dev/null +++ b/net/dccp/ipv6.c @@ -0,0 +1,1438 @@ +/* + * DCCP over IPv6 + * Linux INET6 implementation + * + * Based on net/dccp6/ipv6.c + * + * Arnaldo Carvalho de Melo <acme@ghostprotocols.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/xfrm.h> + +#include <net/addrconf.h> +#include <net/inet_common.h> +#include <net/inet_hashtables.h> +#include <net/inet6_connection_sock.h> +#include <net/inet6_hashtables.h> +#include <net/ip6_route.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/transp_v6.h> +#include <net/xfrm.h> + +#include "dccp.h" +#include "ipv6.h" + +static void dccp_v6_ctl_send_reset(struct sk_buff *skb); +static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, + struct request_sock *req); +static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb); + +static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); + +static struct inet_connection_sock_af_ops dccp_ipv6_mapped; +static struct inet_connection_sock_af_ops dccp_ipv6_af_ops; + +static int dccp_v6_get_port(struct sock *sk, unsigned short snum) +{ + return inet_csk_get_port(&dccp_hashinfo, sk, snum, + inet6_csk_bind_conflict); +} + +static void dccp_v6_hash(struct sock *sk) +{ + if (sk->sk_state != DCCP_CLOSED) { + if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { + dccp_prot.hash(sk); + return; + } + local_bh_disable(); + __inet6_hash(&dccp_hashinfo, sk); + local_bh_enable(); + } +} + +static inline u16 dccp_v6_check(struct dccp_hdr *dh, int len, + struct in6_addr *saddr, + struct in6_addr *daddr, + unsigned long base) +{ + return csum_ipv6_magic(saddr, daddr, len, IPPROTO_DCCP, base); +} + +static __u32 dccp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + + if (skb->protocol == htons(ETH_P_IPV6)) + return secure_tcpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32, + skb->nh.ipv6h->saddr.s6_addr32, + dh->dccph_dport, + dh->dccph_sport); + else + return secure_dccp_sequence_number(skb->nh.iph->daddr, + skb->nh.iph->saddr, + dh->dccph_dport, + dh->dccph_sport); +} + +static int __dccp_v6_check_established(struct sock *sk, const __u16 lport, + struct inet_timewait_sock **twp) +{ + struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); + const struct in6_addr *daddr = &np->rcv_saddr; + const struct in6_addr *saddr = &np->daddr; + const int dif = sk->sk_bound_dev_if; + const u32 ports = INET_COMBINED_PORTS(inet->dport, lport); + const unsigned int hash = inet6_ehashfn(daddr, inet->num, + saddr, inet->dport); + struct inet_ehash_bucket *head = inet_ehash_bucket(&dccp_hashinfo, hash); + struct sock *sk2; + const struct hlist_node *node; + struct inet_timewait_sock *tw; + + prefetch(head->chain.first); + write_lock(&head->lock); + + /* Check TIME-WAIT sockets first. */ + sk_for_each(sk2, node, &(head + dccp_hashinfo.ehash_size)->chain) { + const struct inet6_timewait_sock *tw6 = inet6_twsk(sk2); + + tw = inet_twsk(sk2); + + if(*((__u32 *)&(tw->tw_dport)) == ports && + sk2->sk_family == PF_INET6 && + ipv6_addr_equal(&tw6->tw_v6_daddr, saddr) && + ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) && + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) + goto not_unique; + } + tw = NULL; + + /* And established part... */ + sk_for_each(sk2, node, &head->chain) { + if (INET6_MATCH(sk2, hash, saddr, daddr, ports, dif)) + goto not_unique; + } + + BUG_TRAP(sk_unhashed(sk)); + __sk_add_node(sk, &head->chain); + sk->sk_hash = hash; + sock_prot_inc_use(sk->sk_prot); + write_unlock(&head->lock); + + if (twp) { + *twp = tw; + NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); + } else if (tw) { + /* Silly. Should hash-dance instead... */ + inet_twsk_deschedule(tw, &dccp_death_row); + NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); + + inet_twsk_put(tw); + } + return 0; + +not_unique: + write_unlock(&head->lock); + return -EADDRNOTAVAIL; +} + +static inline u32 dccp_v6_port_offset(const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); + + return secure_tcpv6_port_ephemeral(np->rcv_saddr.s6_addr32, + np->daddr.s6_addr32, + inet->dport); +} + +static int dccp_v6_hash_connect(struct sock *sk) +{ + const unsigned short snum = inet_sk(sk)->num; + struct inet_bind_hashbucket *head; + struct inet_bind_bucket *tb; + int ret; + + if (snum == 0) { + int low = sysctl_local_port_range[0]; + int high = sysctl_local_port_range[1]; + int range = high - low; + int i; + int port; + static u32 hint; + u32 offset = hint + dccp_v6_port_offset(sk); + struct hlist_node *node; + struct inet_timewait_sock *tw = NULL; + + local_bh_disable(); + for (i = 1; i <= range; i++) { + port = low + (i + offset) % range; + head = &dccp_hashinfo.bhash[inet_bhashfn(port, + dccp_hashinfo.bhash_size)]; + spin_lock(&head->lock); + + /* Does not bother with rcv_saddr checks, + * because the established check is already + * unique enough. + */ + inet_bind_bucket_for_each(tb, node, &head->chain) { + if (tb->port == port) { + BUG_TRAP(!hlist_empty(&tb->owners)); + if (tb->fastreuse >= 0) + goto next_port; + if (!__dccp_v6_check_established(sk, + port, + &tw)) + goto ok; + goto next_port; + } + } + + tb = inet_bind_bucket_create(dccp_hashinfo.bind_bucket_cachep, + head, port); + if (!tb) { + spin_unlock(&head->lock); + break; + } + tb->fastreuse = -1; + goto ok; + + next_port: + spin_unlock(&head->lock); + } + local_bh_enable(); + + return -EADDRNOTAVAIL; +ok: + hint += i; + + /* Head lock still held and bh's disabled */ + inet_bind_hash(sk, tb, port); + if (sk_unhashed(sk)) { + inet_sk(sk)->sport = htons(port); + __inet6_hash(&dccp_hashinfo, sk); + } + spin_unlock(&head->lock); + + if (tw) { + inet_twsk_deschedule(tw, &dccp_death_row); + inet_twsk_put(tw); + } + + ret = 0; + goto out; + } + + head = &dccp_hashinfo.bhash[inet_bhashfn(snum, + dccp_hashinfo.bhash_size)]; + tb = inet_csk(sk)->icsk_bind_hash; + spin_lock_bh(&head->lock); + + if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { + __inet6_hash(&dccp_hashinfo, sk); + spin_unlock_bh(&head->lock); + return 0; + } else { + spin_unlock(&head->lock); + /* No definite answer... Walk to established hash table */ + ret = __dccp_v6_check_established(sk, snum, NULL); +out: + local_bh_enable(); + return ret; + } +} + +static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); + struct in6_addr *saddr = NULL, *final_p = NULL, final; + struct flowi fl; + struct dst_entry *dst; + int addr_type; + int err; + + dp->dccps_role = DCCP_ROLE_CLIENT; + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + if (usin->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + + memset(&fl, 0, sizeof(fl)); + + 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) { + struct ip6_flowlabel *flowlabel; + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + if (flowlabel == NULL) + return -EINVAL; + ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + fl6_sock_release(flowlabel); + } + } + + /* + * connect() to INADDR_ANY means loopback (BSD'ism). + */ + + 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) + return -ENETUNREACH; + + if (addr_type & IPV6_ADDR_LINKLOCAL) { + if (addr_len >= sizeof(struct sockaddr_in6) && + usin->sin6_scope_id) { + /* If interface is set while binding, indices + * must coincide. + */ + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != usin->sin6_scope_id) + return -EINVAL; + + sk->sk_bound_dev_if = usin->sin6_scope_id; + } + + /* Connect to link-local address requires an interface */ + if (!sk->sk_bound_dev_if) + return -EINVAL; + } + + ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->flow_label = fl.fl6_flowlabel; + + /* + * DCCP over IPv4 + */ + + if (addr_type == IPV6_ADDR_MAPPED) { + u32 exthdrlen = dp->dccps_ext_header_len; + struct sockaddr_in sin; + + SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); + + if (__ipv6_only_sock(sk)) + return -ENETUNREACH; + + sin.sin_family = AF_INET; + sin.sin_port = usin->sin6_port; + sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; + + inet_csk(sk)->icsk_af_ops = &dccp_ipv6_mapped; + sk->sk_backlog_rcv = dccp_v4_do_rcv; + + err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); + + if (err) { + dp->dccps_ext_header_len = exthdrlen; + inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_backlog_rcv = dccp_v6_do_rcv; + 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); + } + + return err; + } + + if (!ipv6_addr_any(&np->rcv_saddr)) + saddr = &np->rcv_saddr; + + fl.proto = IPPROTO_DCCP; + 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; + } + + err = ip6_dst_lookup(sk, &dst, &fl); + if (err) + goto failure; + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + goto failure; + + if (saddr == NULL) { + saddr = &fl.fl6_src; + ipv6_addr_copy(&np->rcv_saddr, saddr); + } + + /* set the source address */ + ipv6_addr_copy(&np->saddr, saddr); + inet->rcv_saddr = LOOPBACK4_IPV6; + + ip6_dst_store(sk, dst, NULL); + + dp->dccps_ext_header_len = 0; + if (np->opt) + dp->dccps_ext_header_len = np->opt->opt_flen + np->opt->opt_nflen; + + inet->dport = usin->sin6_port; + + dccp_set_state(sk, DCCP_REQUESTING); + err = dccp_v6_hash_connect(sk); + if (err) + goto late_failure; + /* FIXME */ +#if 0 + dp->dccps_gar = secure_dccp_v6_sequence_number(np->saddr.s6_addr32, + np->daddr.s6_addr32, + inet->sport, + inet->dport); +#endif + err = dccp_connect(sk); + if (err) + goto late_failure; + + return 0; + +late_failure: + dccp_set_state(sk, DCCP_CLOSED); + __sk_dst_reset(sk); +failure: + inet->dport = 0; + sk->sk_route_caps = 0; + return err; +} + +static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + int type, int code, int offset, __u32 info) +{ + struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; + const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + struct ipv6_pinfo *np; + struct sock *sk; + int err; + __u64 seq; + + sk = inet6_lookup(&dccp_hashinfo, &hdr->daddr, dh->dccph_dport, + &hdr->saddr, dh->dccph_sport, skb->dev->ifindex); + + if (sk == NULL) { + ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return; + } + + if (sk->sk_state == DCCP_TIME_WAIT) { + inet_twsk_put((struct inet_timewait_sock *)sk); + return; + } + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + + if (sk->sk_state == DCCP_CLOSED) + goto out; + + np = inet6_sk(sk); + + if (type == ICMPV6_PKT_TOOBIG) { + struct dccp_sock *dp = dccp_sk(sk); + struct dst_entry *dst = NULL; + + if (sock_owned_by_user(sk)) + goto out; + if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) + goto out; + + /* icmp should have updated the destination cache 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_DCCP; + 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; + + if ((err = ip6_dst_lookup(sk, &dst, &fl))) { + sk->sk_err_soft = -err; + goto out; + } + + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + sk->sk_err_soft = -err; + goto out; + } + + } else + dst_hold(dst); + + if (dp->dccps_pmtu_cookie > dst_mtu(dst)) { + dccp_sync_mss(sk, dst_mtu(dst)); + } /* else let the usual retransmit timer handle it */ + dst_release(dst); + goto out; + } + + icmpv6_err_convert(type, code, &err); + + seq = DCCP_SKB_CB(skb)->dccpd_seq; + /* Might be for an request_sock */ + switch (sk->sk_state) { + struct request_sock *req, **prev; + case DCCP_LISTEN: + if (sock_owned_by_user(sk)) + goto out; + + req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, + &hdr->daddr, &hdr->saddr, + inet6_iif(skb)); + if (!req) + goto out; + + /* ICMPs are not backlogged, hence we cannot get + * an established socket here. + */ + BUG_TRAP(req->sk == NULL); + + if (seq != dccp_rsk(req)->dreq_iss) { + NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + + inet_csk_reqsk_queue_drop(sk, req, prev); + goto out; + + case DCCP_REQUESTING: + case DCCP_RESPOND: /* Cannot happen. + It can, it SYNs are crossed. --ANK */ + if (!sock_owned_by_user(sk)) { + DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); + sk->sk_err = err; + /* + * Wake people up to see the error + * (see connect in sock.c) + */ + sk->sk_error_report(sk); + + dccp_done(sk); + } else + sk->sk_err_soft = err; + goto out; + } + + if (!sock_owned_by_user(sk) && np->recverr) { + sk->sk_err = err; + sk->sk_error_report(sk); + } else + sk->sk_err_soft = err; + +out: + bh_unlock_sock(sk); + sock_put(sk); +} + + +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, + struct dst_entry *dst) +{ + struct inet6_request_sock *ireq6 = 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; + int err = -1; + + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); + ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); + fl.fl6_flowlabel = 0; + fl.oif = ireq6->iif; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; + fl.fl_ip_sport = inet_sk(sk)->sport; + + if (dst == NULL) { + opt = np->opt; + if (opt == NULL && + np->rxopt.bits.osrcrt == 2 && + ireq6->pktopts) { + struct sk_buff *pktopts = ireq6->pktopts; + struct inet6_skb_parm *rxopt = IP6CB(pktopts); + if (rxopt->srcrt) + opt = ipv6_invert_rthdr(sk, + (struct ipv6_rt_hdr *)(pktopts->nh.raw + + rxopt->srcrt)); + } + + 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; + } + + 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(&dst, &fl, sk, 0)) < 0) + goto done; + } + + skb = dccp_make_response(sk, dst, req); + if (skb != NULL) { + struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v6_check(dh, skb->len, + &ireq6->loc_addr, + &ireq6->rmt_addr, + csum_partial((char *)dh, + skb->len, + skb->csum)); + ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); + err = ip6_xmit(sk, skb, &fl, opt, 0); + if (err == NET_XMIT_CN) + err = 0; + } + +done: + if (opt && opt != np->opt) + sock_kfree_s(sk, opt, opt->tot_len); + return err; +} + +static void dccp_v6_reqsk_destructor(struct request_sock *req) +{ + if (inet6_rsk(req)->pktopts != NULL) + kfree_skb(inet6_rsk(req)->pktopts); +} + +static struct request_sock_ops dccp6_request_sock_ops = { + .family = AF_INET6, + .obj_size = sizeof(struct dccp6_request_sock), + .rtx_syn_ack = dccp_v6_send_response, + .send_ack = dccp_v6_reqsk_send_ack, + .destructor = dccp_v6_reqsk_destructor, + .send_reset = dccp_v6_ctl_send_reset, +}; + +static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct dccp_hdr *dh = dccp_hdr(skb); + + dh->dccph_checksum = csum_ipv6_magic(&np->saddr, &np->daddr, + len, IPPROTO_DCCP, + csum_partial((char *)dh, + dh->dccph_doff << 2, + skb->csum)); +} + +static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) +{ + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const int dccp_hdr_reset_len = sizeof(struct dccp_hdr) + + sizeof(struct dccp_hdr_ext) + + sizeof(struct dccp_hdr_reset); + struct sk_buff *skb; + struct flowi fl; + u64 seqno; + + if (rxdh->dccph_type == DCCP_PKT_RESET) + return; + + if (!ipv6_unicast_destination(rxskb)) + return; + + /* + * We need to grab some memory, and put together an RST, + * and then put it into the queue to be sent. + */ + + skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_reset_len, GFP_ATOMIC); + if (skb == NULL) + return; + + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_reset_len); + + skb->h.raw = skb_push(skb, dccp_hdr_reset_len); + dh = dccp_hdr(skb); + memset(dh, 0, dccp_hdr_reset_len); + + /* Swap the send and the receive. */ + dh->dccph_type = DCCP_PKT_RESET; + dh->dccph_sport = rxdh->dccph_dport; + dh->dccph_dport = rxdh->dccph_sport; + dh->dccph_doff = dccp_hdr_reset_len / 4; + dh->dccph_x = 1; + dccp_hdr_reset(skb)->dccph_reset_code = + DCCP_SKB_CB(rxskb)->dccpd_reset_code; + + /* See "8.3.1. Abnormal Termination" in draft-ietf-dccp-spec-11 */ + seqno = 0; + if (DCCP_SKB_CB(rxskb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) + dccp_set_seqno(&seqno, DCCP_SKB_CB(rxskb)->dccpd_ack_seq + 1); + + dccp_hdr_set_seq(dh, seqno); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), + DCCP_SKB_CB(rxskb)->dccpd_seq); + + memset(&fl, 0, sizeof(fl)); + ipv6_addr_copy(&fl.fl6_dst, &rxskb->nh.ipv6h->saddr); + ipv6_addr_copy(&fl.fl6_src, &rxskb->nh.ipv6h->daddr); + dh->dccph_checksum = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, + sizeof(*dh), IPPROTO_DCCP, + skb->csum); + fl.proto = IPPROTO_DCCP; + fl.oif = inet6_iif(rxskb); + fl.fl_ip_dport = dh->dccph_dport; + fl.fl_ip_sport = dh->dccph_sport; + + /* sk = NULL, but it is safe for now. RST socket required. */ + if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { + if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, skb, &fl, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); + return; + } + } + + kfree_skb(skb); +} + +static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) +{ + struct flowi fl; + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + sizeof(struct dccp_hdr_ext) + + sizeof(struct dccp_hdr_ack_bits); + struct sk_buff *skb; + + skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_ack_len, GFP_ATOMIC); + if (skb == NULL) + return; + + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_ack_len); + + skb->h.raw = skb_push(skb, dccp_hdr_ack_len); + dh = dccp_hdr(skb); + memset(dh, 0, dccp_hdr_ack_len); + + /* Build DCCP header and checksum it. */ + dh->dccph_type = DCCP_PKT_ACK; + dh->dccph_sport = rxdh->dccph_dport; + dh->dccph_dport = rxdh->dccph_sport; + dh->dccph_doff = dccp_hdr_ack_len / 4; + dh->dccph_x = 1; + + dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), + DCCP_SKB_CB(rxskb)->dccpd_seq); + + memset(&fl, 0, sizeof(fl)); + ipv6_addr_copy(&fl.fl6_dst, &rxskb->nh.ipv6h->saddr); + ipv6_addr_copy(&fl.fl6_src, &rxskb->nh.ipv6h->daddr); + + /* FIXME: calculate checksum, IPv4 also should... */ + + fl.proto = IPPROTO_DCCP; + fl.oif = inet6_iif(rxskb); + fl.fl_ip_dport = dh->dccph_dport; + fl.fl_ip_sport = dh->dccph_sport; + + if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { + if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, skb, &fl, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + return; + } + } + + kfree_skb(skb); +} + +static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, + struct request_sock *req) +{ + dccp_v6_ctl_send_ack(skb); +} + +static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + const struct ipv6hdr *iph = skb->nh.ipv6h; + struct sock *nsk; + struct request_sock **prev; + /* Find possible connection requests. */ + struct request_sock *req = inet6_csk_search_req(sk, &prev, + dh->dccph_sport, + &iph->saddr, + &iph->daddr, + inet6_iif(skb)); + if (req != NULL) + return dccp_check_req(sk, skb, req, prev); + + nsk = __inet6_lookup_established(&dccp_hashinfo, + &iph->saddr, dh->dccph_sport, + &iph->daddr, ntohs(dh->dccph_dport), + inet6_iif(skb)); + + if (nsk != NULL) { + if (nsk->sk_state != DCCP_TIME_WAIT) { + bh_lock_sock(nsk); + return nsk; + } + inet_twsk_put((struct inet_timewait_sock *)nsk); + return NULL; + } + + return sk; +} + +static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) +{ + struct inet_request_sock *ireq; + struct dccp_sock dp; + struct request_sock *req; + struct dccp_request_sock *dreq; + struct inet6_request_sock *ireq6; + struct ipv6_pinfo *np = inet6_sk(sk); + const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); + __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; + + if (skb->protocol == htons(ETH_P_IP)) + return dccp_v4_conn_request(sk, skb); + + if (!ipv6_unicast_destination(skb)) + goto drop; + + if (dccp_bad_service_code(sk, service)) { + reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; + goto drop; + } + /* + * There are no SYN attacks on IPv6, yet... + */ + if (inet_csk_reqsk_queue_is_full(sk)) + goto drop; + + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + goto drop; + + req = inet6_reqsk_alloc(sk->sk_prot->rsk_prot); + if (req == NULL) + goto drop; + + /* FIXME: process options */ + + dccp_openreq_init(req, &dp, skb); + + ireq6 = inet6_rsk(req); + ireq = inet_rsk(req); + ipv6_addr_copy(&ireq6->rmt_addr, &skb->nh.ipv6h->saddr); + ipv6_addr_copy(&ireq6->loc_addr, &skb->nh.ipv6h->daddr); + req->rcv_wnd = 100; /* Fake, option parsing will get the + right value */ + ireq6->pktopts = NULL; + + 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); + ireq6->pktopts = skb; + } + ireq6->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq6->iif = inet6_iif(skb); + + /* + * Step 3: Process LISTEN state + * + * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie + * + * In fact we defer setting S.GSR, S.SWL, S.SWH to + * dccp_create_openreq_child. + */ + dreq = dccp_rsk(req); + dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_iss = dccp_v6_init_sequence(sk, skb); + dreq->dreq_service = service; + + if (dccp_v6_send_response(sk, req, NULL)) + goto drop_and_free; + + inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + return 0; + +drop_and_free: + reqsk_free(req); +drop: + DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); + dcb->dccpd_reset_code = reset_code; + return -1; +} + +static struct sock *dccp_v6_request_recv_sock(struct sock *sk, + struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) +{ + struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct inet_sock *newinet; + struct dccp_sock *newdp; + struct dccp6_sock *newdp6; + struct sock *newsk; + struct ipv6_txoptions *opt; + + if (skb->protocol == htons(ETH_P_IP)) { + /* + * v6 mapped + */ + + newsk = dccp_v4_request_recv_sock(sk, skb, req, dst); + if (newsk == NULL) + return NULL; + + newdp6 = (struct dccp6_sock *)newsk; + newdp = dccp_sk(newsk); + newinet = inet_sk(newsk); + newinet->pinet6 = &newdp6->inet6; + newnp = inet6_sk(newsk); + + memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + + ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), + newinet->daddr); + + ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), + newinet->saddr); + + ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + + inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; + newsk->sk_backlog_rcv = dccp_v4_do_rcv; + newnp->pktoptions = NULL; + newnp->opt = NULL; + newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + + /* + * No need to charge this sock to the relevant IPv6 refcnt debug socks count + * here, dccp_create_openreq_child now does this for us, see the comment in + * that function for the gory details. -acme + */ + + /* It is tricky place. Until this moment IPv4 tcp + worked with IPv6 icsk.icsk_af_ops. + Sync it now. + */ + dccp_sync_mss(newsk, newdp->dccps_pmtu_cookie); + + return newsk; + } + + opt = np->opt; + + if (sk_acceptq_is_full(sk)) + goto out_overflow; + + if (np->rxopt.bits.osrcrt == 2 && + opt == NULL && ireq6->pktopts) { + struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (rxopt->srcrt) + opt = ipv6_invert_rthdr(sk, + (struct ipv6_rt_hdr *)(ireq6->pktopts->nh.raw + + rxopt->srcrt)); + } + + if (dst == NULL) { + struct in6_addr *final_p = NULL, final; + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &ireq6->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, &ireq6->loc_addr); + fl.oif = sk->sk_bound_dev_if; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; + fl.fl_ip_sport = inet_sk(sk)->sport; + + if (ip6_dst_lookup(sk, &dst, &fl)) + goto out; + + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + goto out; + } + + newsk = dccp_create_openreq_child(sk, req, skb); + if (newsk == NULL) + goto out; + + /* + * No need to charge this sock to the relevant IPv6 refcnt debug socks + * count here, dccp_create_openreq_child now does this for us, see the + * comment in that function for the gory details. -acme + */ + + ip6_dst_store(newsk, dst, NULL); + newsk->sk_route_caps = dst->dev->features & + ~(NETIF_F_IP_CSUM | NETIF_F_TSO); + + newdp6 = (struct dccp6_sock *)newsk; + newinet = inet_sk(newsk); + newinet->pinet6 = &newdp6->inet6; + newdp = dccp_sk(newsk); + newnp = inet6_sk(newsk); + + memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + + ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr); + ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr); + ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); + newsk->sk_bound_dev_if = ireq6->iif; + + /* Now IPv6 options... + + First: no IPv4 options. + */ + newinet->opt = NULL; + + /* Clone RX bits */ + newnp->rxopt.all = np->rxopt.all; + + /* Clone pktoptions received with SYN */ + newnp->pktoptions = NULL; + if (ireq6->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC); + kfree_skb(ireq6->pktopts); + ireq6->pktopts = NULL; + if (newnp->pktoptions) + skb_set_owner_r(newnp->pktoptions, newsk); + } + newnp->opt = NULL; + newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + + /* Clone native IPv6 options from listening socket (if any) + + Yes, keeping reference count would be much more clever, + 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); + } + + newdp->dccps_ext_header_len = 0; + if (newnp->opt) + newdp->dccps_ext_header_len = newnp->opt->opt_nflen + + newnp->opt->opt_flen; + + dccp_sync_mss(newsk, dst_mtu(dst)); + + newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + + __inet6_hash(&dccp_hashinfo, newsk); + inet_inherit_port(&dccp_hashinfo, sk, newsk); + + return newsk; + +out_overflow: + NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); +out: + NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); + if (opt && opt != np->opt) + sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); + return NULL; +} + +/* The socket must have it's spinlock held when we get + * here. + * + * We have a potential double-lock case here, so even when + * doing backlog processing we use the BH locking scheme. + * This is because we cannot sleep with the original spinlock + * held. + */ +static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *opt_skb = NULL; + + /* Imagine: socket is IPv6. IPv4 packet arrives, + goes to IPv4 receive handler and backlogged. + From backlog it always goes here. Kerboom... + Fortunately, dccp_rcv_established and rcv_established + handle them correctly, but it is not case with + dccp_v6_hnd_req and dccp_v6_ctl_send_reset(). --ANK + */ + + if (skb->protoco |