diff options
Diffstat (limited to 'net/dccp/ipv6.c')
| -rw-r--r-- | net/dccp/ipv6.c | 610 |
1 files changed, 264 insertions, 346 deletions
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c7aaa2574f5..4db3c2a1679 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/random.h> +#include <linux/slab.h> #include <linux/xfrm.h> #include <net/addrconf.h> @@ -28,84 +29,82 @@ #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "dccp.h" #include "ipv6.h" #include "feat.h" -/* Socket used for sending RSTs and ACKs */ -static struct socket *dccp_v6_ctl_socket; +/* The per-net dccp.v6_ctl_sk is used for sending RSTs and ACKs */ -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 const struct inet_connection_sock_af_ops dccp_ipv6_mapped; +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; 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_hash(sk); + inet_hash(sk); return; } local_bh_disable(); - __inet6_hash(&dccp_hashinfo, sk); + __inet6_hash(sk, NULL); local_bh_enable(); } } /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, - struct in6_addr *saddr, - struct in6_addr *daddr) + const struct in6_addr *saddr, + const struct in6_addr *daddr) { return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } -static inline void dccp_v6_send_check(struct sock *sk, int unused_value, - struct sk_buff *skb) +static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); -} - -static inline __u32 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport ) -{ - return secure_tcpv6_sequence_number(saddr, daddr, sport, dport); + dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr); } -static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) +static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { - return secure_dccpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32, - skb->nh.ipv6h->saddr.s6_addr32, + return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, dccp_hdr(skb)->dccph_dport, dccp_hdr(skb)->dccph_sport ); } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + 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 dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; + struct net *net = dev_net(skb->dev); - sk = inet6_lookup(&dccp_hashinfo, &hdr->daddr, dh->dccph_dport, - &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); + if (skb->len < offset + sizeof(*dh) || + skb->len < offset + __dccp_basic_hdr_len(dh)) { + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); + return; + } + + sk = inet6_lookup(net, &dccp_hashinfo, + &hdr->daddr, dh->dccph_dport, + &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); if (sk == NULL) { - ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; } @@ -116,64 +115,51 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, bh_lock_sock(sk); if (sock_owned_by_user(sk)) - NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; + dp = dccp_sk(sk); + seq = dccp_hdr_seq(dh); + if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && + !between48(seq, dp->dccps_awl, dp->dccps_awh)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + np = inet6_sk(sk); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst) + dst->ops->redirect(dst, sk, skb); + goto out; + } + if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + 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; - security_sk_classify_flow(sk, &fl); - - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) { - sk->sk_err_soft = -err; - goto out; - } - - err = xfrm_lookup(&dst, &fl, sk, 0); - if (err < 0) { - sk->sk_err_soft = -err; - goto out; - } - } else - dst_hold(dst); + dst = inet6_csk_update_pmtu(sk, ntohl(info)); + if (!dst) + goto out; - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + if (inet_csk(sk)->icsk_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; @@ -191,10 +177,11 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); - if (seq != dccp_rsk(req)->dreq_iss) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -230,59 +217,34 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) { - struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct inet_request_sock *ireq = inet_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 in6_addr *final_p, final; + struct flowi6 fl6; int err = -1; + struct dst_entry *dst; - 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; - security_req_classify_flow(req, &fl); - - 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 != NULL && opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowlabel = 0; + fl6.flowi6_oif = ireq->ir_iif; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = htons(ireq->ir_num); + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - 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; + final_p = fl6_update_dst(&fl6, np->opt, &final); - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = xfrm_lookup(&dst, &fl, sk, 0); - if (err < 0) - goto done; + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto done; } skb = dccp_make_response(sk, dst, req); @@ -290,89 +252,65 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, struct dccp_hdr *dh = dccp_hdr(skb); dh->dccph_checksum = dccp_v6_csum_finish(skb, - &ireq6->loc_addr, - &ireq6->rmt_addr); - ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + &ireq->ir_v6_loc_addr, + &ireq->ir_v6_rmt_addr); + fl6.daddr = ireq->ir_v6_rmt_addr; + err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return err; } static void dccp_v6_reqsk_destructor(struct request_sock *req) { - if (inet6_rsk(req)->pktopts != NULL) - kfree_skb(inet6_rsk(req)->pktopts); + dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); + kfree_skb(inet_rsk(req)->pktopts); } static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) { - struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const u32 dccp_hdr_reset_len = sizeof(struct dccp_hdr) + - sizeof(struct dccp_hdr_ext) + - sizeof(struct dccp_hdr_reset); + const struct ipv6hdr *rxip6h; struct sk_buff *skb; - struct flowi fl; - u64 seqno = 0; + struct flowi6 fl6; + struct net *net = dev_net(skb_dst(rxskb)->dev); + struct sock *ctl_sk = net->dccp.v6_ctl_sk; + struct dst_entry *dst; - if (rxdh->dccph_type == DCCP_PKT_RESET) + if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; if (!ipv6_unicast_destination(rxskb)) return; - skb = alloc_skb(dccp_v6_ctl_socket->sk->sk_prot->max_header, - GFP_ATOMIC); + skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) - return; - - skb_reserve(skb, dccp_v6_ctl_socket->sk->sk_prot->max_header); - - dh = dccp_zeroed_hdr(skb, 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 RFC 4340 */ - 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); + return; - dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v6_csum_finish(skb, &rxskb->nh.ipv6h->saddr, - &rxskb->nh.ipv6h->daddr); + rxip6h = ipv6_hdr(rxskb); + dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr, + &rxip6h->daddr); - 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); + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = rxip6h->saddr; + fl6.saddr = rxip6h->daddr; - fl.proto = IPPROTO_DCCP; - fl.oif = inet6_iif(rxskb); - fl.fl_ip_dport = dh->dccph_dport; - fl.fl_ip_sport = dh->dccph_sport; - security_skb_classify_flow(rxskb, &fl); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.flowi6_oif = inet6_iif(rxskb); + fl6.fl6_dport = dccp_hdr(skb)->dccph_dport; + fl6.fl6_sport = dccp_hdr(skb)->dccph_sport; + security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* 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(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); - DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); - DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); - return; - } + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + if (!IS_ERR(dst)) { + skb_dst_set(skb, dst); + ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); + return; } kfree_skb(skb); @@ -385,12 +323,13 @@ static struct request_sock_ops dccp6_request_sock_ops = { .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v6_reqsk_destructor, .send_reset = dccp_v6_ctl_send_reset, + .syn_ack_timeout = dccp_syn_ack_timeout, }; 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; + const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *nsk; struct request_sock **prev; /* Find possible connection requests. */ @@ -402,7 +341,7 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) if (req != NULL) return dccp_check_req(sk, skb, req, prev); - nsk = __inet6_lookup_established(&dccp_hashinfo, + nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); @@ -422,25 +361,25 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct request_sock *req; struct dccp_request_sock *dreq; - struct inet6_request_sock *ireq6; + struct inet_request_sock *ireq; struct ipv6_pinfo *np = inet6_sk(sk); - const __be32 service = dccp_hdr_request(skb)->dccph_req_service; + const __be32 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; + return 0; /* discard, don't send a reset here */ if (dccp_bad_service_code(sk, service)) { - reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; + dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; - } + } /* * There are no SYN attacks on IPv6, yet... */ + dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; if (inet_csk_reqsk_queue_is_full(sk)) goto drop; @@ -451,46 +390,47 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (req == NULL) goto drop; - if (dccp_parse_options(sk, skb)) + if (dccp_reqsk_init(req, dccp_sk(sk), skb)) goto drop_and_free; - dccp_reqsk_init(req, skb); + dreq = dccp_rsk(req); + if (dccp_parse_options(sk, dreq, skb)) + goto drop_and_free; if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; - ireq6 = inet6_rsk(req); - ipv6_addr_copy(&ireq6->rmt_addr, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&ireq6->loc_addr, &skb->nh.ipv6h->daddr); - ireq6->pktopts = NULL; + ireq = inet_rsk(req); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; 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; + ireq->pktopts = skb; } - ireq6->iif = sk->sk_bound_dev_if; + ireq->ir_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); + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_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. + * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ - dreq = dccp_rsk(req); dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v6_init_sequence(skb); + dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; - if (dccp_v6_send_response(sk, req, NULL)) + if (dccp_v6_send_response(sk, req)) goto drop_and_free; inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); @@ -500,7 +440,6 @@ drop_and_free: reqsk_free(req); drop: DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); - dcb->dccpd_reset_code = reset_code; return -1; } @@ -509,13 +448,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { - struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct inet_request_sock *ireq = inet_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)) { /* @@ -526,27 +463,24 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, 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_v4mapped(newinet->inet_daddr, &newsk->sk_v6_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); + newsk->sk_v6_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; + newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -563,53 +497,32 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, return newsk; } - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; - if (np->rxopt.bits.osrcrt == 2 && opt == NULL && ireq6->pktopts) { - const 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 != NULL && opt->srcrt != NULL) { - const 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; - security_sk_classify_flow(sk, &fl); - - 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) + struct in6_addr *final_p, final; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + final_p = fl6_update_dst(&fl6, np->opt, &final); + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = htons(ireq->ir_num); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) goto out; } newsk = dccp_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 @@ -623,37 +536,36 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, 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; + 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->opt = NULL; + newinet->inet_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 (ireq->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + consume_skb(ireq->pktopts); + ireq->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; + newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; /* * Clone native IPv6 options from listening socket (if any) @@ -661,11 +573,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ - if (opt != NULL) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt != NULL) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt != NULL) @@ -674,20 +583,24 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, dccp_sync_mss(newsk, dst_mtu(dst)); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; - __inet6_hash(&dccp_hashinfo, newsk); - inet_inherit_port(&dccp_hashinfo, sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) { + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); + goto out; + } + __inet6_hash(newsk, NULL); return newsk; out_overflow: - NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); -out: - NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); + 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); return NULL; } @@ -734,7 +647,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. - --ANK (980728) + --ANK (980728) */ if (np->rxopt.all) /* @@ -787,7 +700,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * otherwise we just shortcircuit this and continue with * the new socket.. */ - if (nsk != sk) { + if (nsk != sk) { if (dccp_child_process(sk, nsk, skb)) goto reset; if (opt_skb != NULL) @@ -813,10 +726,9 @@ discard: return 0; } -static int dccp_v6_rcv(struct sk_buff **pskb) +static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; - struct sk_buff *skb = *pskb; struct sock *sk; int min_cov; @@ -826,15 +738,15 @@ static int dccp_v6_rcv(struct sk_buff **pskb) goto discard_it; /* Step 1: If header checksum is incorrect, drop packet and return. */ - if (dccp_v6_csum_finish(skb, &skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr)) { + if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); - DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(skb); + DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; if (dccp_packet_without_ack(skb)) @@ -843,14 +755,12 @@ static int dccp_v6_rcv(struct sk_buff **pskb) DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); /* Step 2: - * Look up flow ID in table and get corresponding socket */ - sk = __inet6_lookup(&dccp_hashinfo, &skb->nh.ipv6h->saddr, - dh->dccph_sport, - &skb->nh.ipv6h->daddr, ntohs(dh->dccph_dport), - inet6_iif(skb)); + * Look up flow ID in table and get corresponding socket */ + sk = __inet6_lookup_skb(&dccp_hashinfo, skb, + dh->dccph_sport, dh->dccph_dport); /* * Step 2: - * If no socket ... + * If no socket ... */ if (sk == NULL) { dccp_pr_debug("failed to look up flow ID in table and " @@ -860,7 +770,7 @@ static int dccp_v6_rcv(struct sk_buff **pskb) /* * Step 2: - * ... or S.state == TIMEWAIT, + * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ @@ -872,8 +782,8 @@ static int dccp_v6_rcv(struct sk_buff **pskb) /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage - * o if MinCsCov = 0, only packets with CsCov = 0 are accepted - * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov + * o if MinCsCov = 0, only packets with CsCov = 0 are accepted + * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { @@ -893,7 +803,7 @@ no_dccp_socket: goto discard_it; /* * Step 2: - * If no socket ... + * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ @@ -920,8 +830,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *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 in6_addr *saddr = NULL, *final_p, final; + struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; @@ -934,17 +844,16 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (usin->sin6_family != AF_INET6) 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); fl6_sock_release(flowlabel); } } @@ -977,8 +886,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); - np->flow_label = fl.fl6_flowlabel; + sk->sk_v6_daddr = usin->sin6_addr; + np->flow_label = fl6.flowlabel; /* * DCCP over IPv4 @@ -1005,54 +914,40 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->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); } + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_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; - security_sk_classify_flow(sk, &fl); - - if (np->opt != NULL && np->opt->srcrt != NULL) { - const 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; - } + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto failure; + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = sk->sk_v6_daddr; + fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.fl6_dport = usin->sin6_port; + fl6.fl6_sport = inet->inet_sport; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + final_p = fl6_update_dst(&fl6, np->opt, &final); - err = xfrm_lookup(&dst, &fl, sk, 0); - if (err < 0) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto failure; + } if (saddr == NULL) { - saddr = &fl.fl6_src; - ipv6_addr_copy(&np->rcv_saddr, saddr); + saddr = &fl6.saddr; + sk->sk_v6_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; __ip6_dst_store(sk, dst, NULL, NULL); @@ -1061,7 +956,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->icsk_ext_hdr_len = (np->opt->opt_flen + np->opt->opt_nflen); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; dccp_set_state(sk, DCCP_REQUESTING); err = inet6_hash_connect(&dccp_death_row, sk); @@ -1069,8 +964,9 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto late_failure; dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, - inet->sport, inet->dport); + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); err = dccp_connect(sk); if (err) goto late_failure; @@ -1081,12 +977,12 @@ late_failure: dccp_set_state(sk, DCCP_CLOSED); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } -static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .queue_xmit = inet6_csk_xmit, .send_check = dccp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -1097,6 +993,7 @@ static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, @@ -1106,7 +1003,7 @@ static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { /* * DCCP over IPv4 via INET6 API */ -static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { +static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1140,10 +1037,10 @@ static int dccp_v6_init_sock(struct sock *sk) return err; } -static int dccp_v6_destroy_sock(struct sock *sk) +static void dccp_v6_destroy_sock(struct sock *sk) { dccp_destroy_sock(sk); - return inet6_destroy_sock(sk); + inet6_destroy_sock(sk); } static struct timewait_sock_ops dccp6_timewait_sock_ops = { @@ -1164,29 +1061,31 @@ static struct proto dccp_v6_prot = { .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, .hash = dccp_v6_hash, - .unhash = dccp_unhash, + .unhash = inet_unhash, .accept = inet_csk_accept, - .get_port = dccp_v6_get_port, + .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, .destroy = dccp_v6_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, + .h.hashinfo = &dccp_hashinfo, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_dccp_setsockopt, .compat_getsockopt = compat_dccp_getsockopt, #endif }; -static struct inet6_protocol dccp_v6_protocol = { +static const struct inet6_protocol dccp_v6_protocol = { .handler = dccp_v6_rcv, .err_handler = dccp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; -static struct proto_ops inet6_dccp_ops = { +static const struct proto_ops inet6_dccp_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, @@ -1216,10 +1115,28 @@ static struct inet_protosw dccp_v6_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v6_prot, .ops = &inet6_dccp_ops, - .capability = -1, .flags = INET_PROTOSW_ICSK, }; +static int __net_init dccp_v6_init_net(struct net *net) +{ + if (dccp_hashinfo.bhash == NULL) + return -ESOCKTNOSUPPORT; + + return inet_ctl_sock_create(&net->dccp.v6_ctl_sk, PF_INET6, + SOCK_DCCP, IPPROTO_DCCP, net); +} + +static void __net_exit dccp_v6_exit_net(struct net *net) +{ + inet_ctl_sock_destroy(net->dccp.v6_ctl_sk); +} + +static struct pernet_operations dccp_v6_ops = { + .init = dccp_v6_init_net, + .exit = dccp_v6_exit_net, +}; + static int __init dccp_v6_init(void) { int err = proto_register(&dccp_v6_prot, 1); @@ -1233,13 +1150,13 @@ static int __init dccp_v6_init(void) inet6_register_protosw(&dccp_v6_protosw); - err = inet_csk_ctl_sock_create(&dccp_v6_ctl_socket, PF_INET6, - SOCK_DCCP, IPPROTO_DCCP); + err = register_pernet_subsys(&dccp_v6_ops); if (err != 0) - goto out_unregister_protosw; + goto out_destroy_ctl_sock; out: return err; -out_unregister_protosw: + +out_destroy_ctl_sock: inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); inet6_unregister_protosw(&dccp_v6_protosw); out_unregister_proto: @@ -1249,6 +1166,7 @@ out_unregister_proto: static void __exit dccp_v6_exit(void) { + unregister_pernet_subsys(&dccp_v6_ops); inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); @@ -1262,8 +1180,8 @@ module_exit(dccp_v6_exit); * values directly, Also cover the case where the protocol is not specified, * i.e. net-pf-PF_INET6-proto-0-type-SOCK_DCCP */ -MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-33-type-6"); -MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-0-type-6"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol"); |
