X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Fip6_output.c;h=31dafaf0b652d7fc1ff965a092884bb43748d1fe;hb=e1931b784a8de324abf310fa3b5e3f25d3988233;hp=b2be749d22172d540d85093ea4d059cc9f289a70;hpb=74553b09dcd9194cbda737016f0b89f245145670;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b2be749..31dafaf 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1,9 +1,9 @@ /* * IPv6 output functions - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque + * Pedro Roque * * $Id: ip6_output.c,v 1.34 2002/02/01 22:01:04 davem Exp $ * @@ -72,23 +72,14 @@ static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *f static inline int ip6_output_finish(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct hh_cache *hh = dst->hh; - - if (hh) { - int hh_alen; - - read_lock_bh(&hh->hh_lock); - hh_alen = HH_DATA_ALIGN(hh->hh_len); - memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); - read_unlock_bh(&hh->hh_lock); - skb_push(skb, hh->hh_len); - return hh->hh_output(skb); - } else if (dst->neighbour) + + if (dst->hh) + return neigh_hh_output(dst->hh, skb); + else if (dst->neighbour) return dst->neighbour->output(skb); - IP6_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; @@ -97,8 +88,8 @@ static inline int ip6_output_finish(struct sk_buff *skb) /* dev_loopback_xmit for use with netfilter. */ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) { - newskb->mac.raw = newskb->data; - __skb_pull(newskb, newskb->nh.raw - newskb->data); + skb_reset_mac_header(newskb); + __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; BUG_TRAP(newskb->dst); @@ -116,12 +107,13 @@ static int ip6_output2(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr)) { + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct inet6_dev *idev = ip6_dst_idev(skb->dst); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && - ipv6_chk_mcast_addr(dev, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr)) { + ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr)) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing @@ -132,22 +124,30 @@ static int ip6_output2(struct sk_buff *skb) newskb->dev, ip6_dev_loopback_xmit); - if (skb->nh.ipv6h->hop_limit == 0) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + if (ipv6_hdr(skb)->hop_limit == 0) { + IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS); } return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb,NULL, skb->dev,ip6_output_finish); } +static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +{ + struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + + return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? + skb->dst->dev->mtu : dst_mtu(skb->dst); +} + int ip6_output(struct sk_buff *skb) { - if ((skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) || + if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb->dst)) return ip6_fragment(skb, ip6_output2); else @@ -182,12 +182,14 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - kfree_skb(skb); - skb = skb2; - if (skb == NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + if (skb2 == NULL) { + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); return -ENOBUFS; } + kfree_skb(skb); + skb = skb2; if (sk) skb_set_owner_w(skb, sk); } @@ -197,7 +199,9 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); } - hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header @@ -217,7 +221,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (tclass < 0) tclass = 0; - *(u32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; + *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -230,7 +234,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, mtu = dst_mtu(dst); if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) { - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTREQUESTS); return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } @@ -239,11 +244,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } +EXPORT_SYMBOL(ip6_xmit); + /* * To avoid extra problems ND packets are send through this * routine. It's code duplication but I really want to avoid @@ -264,10 +271,11 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, totlen = len + sizeof(struct ipv6hdr); - hdr = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); - skb->nh.ipv6h = hdr; + skb_reset_network_header(skb); + skb_put(skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(skb); - *(u32*)hdr = htonl(0x60000000); + *(__be32*)hdr = htonl(0x60000000); hdr->payload_len = htons(len); hdr->nexthdr = proto; @@ -310,7 +318,7 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel) static int ip6_forward_proxy_check(struct sk_buff *skb) { - struct ipv6hdr *hdr = skb->nh.ipv6h; + struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; int offset; @@ -324,10 +332,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) if (nexthdr == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6; - if (!pskb_may_pull(skb, skb->nh.raw + offset + 1 - skb->data)) + if (!pskb_may_pull(skb, (skb_network_header(skb) + + offset + 1 - skb->data))) return 0; - icmp6 = (struct icmp6hdr *)(skb->nh.raw + offset); + icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case NDISC_ROUTER_SOLICITATION: @@ -366,18 +375,18 @@ static inline int ip6_forward_finish(struct sk_buff *skb) int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb->dst; - struct ipv6hdr *hdr = skb->nh.ipv6h; + struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); - + if (ipv6_devconf.forwarding == 0) goto error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } - skb->ip_summed = CHECKSUM_NONE; + skb_forward_csum(skb); /* * We DO NOT make any processing on @@ -393,7 +402,7 @@ int ip6_forward(struct sk_buff *skb) * that different fragments will go along one path. --ANK */ if (opt->ra) { - u8 *ptr = skb->nh.raw + opt->ra; + u8 *ptr = skb_network_header(skb) + opt->ra; if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3])) return 0; } @@ -406,24 +415,26 @@ int ip6_forward(struct sk_buff *skb) skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; } - if (pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) { + /* XXX: idev->cnf.proxy_ndp? */ + if (ipv6_devconf.proxy_ndp && + pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb->dst; @@ -452,38 +463,45 @@ int ip6_forward(struct sk_buff *skb) */ if (xrlim_allow(dst, 1*HZ)) ndisc_send_redirect(skb, n, target); - } else if (ipv6_addr_type(&hdr->saddr)&(IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK - |IPV6_ADDR_LINKLOCAL)) { + } else { + int addrtype = ipv6_addr_type(&hdr->saddr); + /* This check is security critical. */ - goto error; + if (addrtype & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK)) + goto error; + if (addrtype & IPV6_ADDR_LINKLOCAL) { + icmpv6_send(skb, ICMPV6_DEST_UNREACH, + ICMPV6_NOT_NEIGHBOUR, 0, skb->dev); + goto error; + } } if (skb->len > dst_mtu(dst)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev); - IP6_INC_STATS_BH(IPSTATS_MIB_INTOOBIGERRORS); - IP6_INC_STATS_BH(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } - hdr = skb->nh.ipv6h; + hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ - + hdr->hop_limit--; - IP6_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); error: - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; @@ -497,38 +515,23 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) dst_release(to->dst); to->dst = dst_clone(from->dst); to->dev = from->dev; + to->mark = from->mark; #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif -#ifdef CONFIG_NETFILTER - to->nfmark = from->nfmark; - /* Connection association is same as pre-frag packet */ - nf_conntrack_put(to->nfct); - to->nfct = from->nfct; - nf_conntrack_get(to->nfct); - to->nfctinfo = from->nfctinfo; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put_reasm(to->nfct_reasm); - to->nfct_reasm = from->nfct_reasm; - nf_conntrack_get_reasm(to->nfct_reasm); -#endif -#ifdef CONFIG_BRIDGE_NETFILTER - nf_bridge_put(to->nf_bridge); - to->nf_bridge = from->nf_bridge; - nf_bridge_get(to->nf_bridge); -#endif -#endif + nf_copy(to, from); skb_copy_secmark(to, from); } int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1); - unsigned int packet_len = skb->tail - skb->nh.raw; + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb->tail - skb->network_header; int found_rhdr = 0; - *nexthdr = &skb->nh.ipv6h->nexthdr; + *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset + 1 <= packet_len) { @@ -540,7 +543,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) found_rhdr = 1; break; case NEXTHDR_DEST: -#ifdef CONFIG_IPV6_MIP6 +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) break; #endif @@ -553,7 +556,8 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) offset += ipv6_optlen(exthdr); *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); } return offset; @@ -569,7 +573,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; - u32 frag_id = 0; + __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; @@ -577,7 +581,20 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; - mtu = dst_mtu(&rt->u.dst); + mtu = ip6_skb_dst_mtu(skb); + + /* We must not fragment if the socket is set to force MTU discovery + * or if the skb it not generated by a local socket. (This last + * check should be redundant, but it's free.) + */ + if (!np || np->pmtudisc >= IPV6_PMTUDISC_DO) { + skb->dev = skb->dst->dev; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); + return -EMSGSIZE; + } + if (np && np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; @@ -618,18 +635,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_shinfo(skb)->frag_list = NULL; /* BUILD HEADER */ - tmp_hdr = kmalloc(hlen, GFP_ATOMIC); + *prevhdr = NEXTHDR_FRAGMENT; + tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } - *prevhdr = NEXTHDR_FRAGMENT; - memcpy(tmp_hdr, skb->nh.raw, hlen); __skb_pull(skb, hlen); fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr)); - skb->nh.raw = __skb_push(skb, hlen); - memcpy(skb->nh.raw, tmp_hdr, hlen); + __skb_push(skb, hlen); + skb_reset_network_header(skb); + memcpy(skb_network_header(skb), tmp_hdr, hlen); ipv6_select_ident(skb, fh); fh->nexthdr = nexthdr; @@ -640,18 +657,22 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; - skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - + ipv6_hdr(skb)->payload_len = htons(first_len - + sizeof(struct ipv6hdr)); + + dst_hold(&rt->u.dst); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; - frag->h.raw = frag->data; + skb_reset_transport_header(frag); fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr)); - frag->nh.raw = __skb_push(frag, hlen); - memcpy(frag->nh.raw, tmp_hdr, hlen); + __skb_push(frag, hlen); + skb_reset_network_header(frag); + memcpy(skb_network_header(frag), tmp_hdr, + hlen); offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = nexthdr; fh->reserved = 0; @@ -659,13 +680,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->next != NULL) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; - frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + ipv6_hdr(frag)->payload_len = + htons(frag->len - + sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } - + err = output(skb); if(!err) - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; @@ -678,7 +701,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) kfree(tmp_hdr); if (err == 0) { - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGOKS); + dst_release(&rt->u.dst); return 0; } @@ -688,7 +712,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb; } - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGFAILS); + dst_release(&rt->u.dst); return err; } @@ -721,7 +746,8 @@ slow_path: if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -733,9 +759,10 @@ slow_path: ip6_copy_metadata(frag, skb); skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev)); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); - frag->nh.raw = frag->data; - fh = (struct frag_hdr*)(frag->data + hlen); - frag->h.raw = frag->data + hlen + sizeof(struct frag_hdr); + skb_reset_network_header(frag); + fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); + frag->transport_header = (frag->network_header + hlen + + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner @@ -747,7 +774,7 @@ slow_path: /* * Copy the packet header into the new buffer. */ - memcpy(frag->nh.raw, skb->data, hlen); + skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); /* * Build fragment header. @@ -763,14 +790,15 @@ slow_path: /* * Copy a block of the IP datagram. */ - if (skb_copy_bits(skb, ptr, frag->h.raw, len)) + if (skb_copy_bits(skb, ptr, skb_transport_header(skb), len)) BUG(); left -= len; fh->frag_off = htons(offset); if (left > 0) fh->frag_off |= htons(IP6_MF); - frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + ipv6_hdr(frag)->payload_len = htons(frag->len - + sizeof(struct ipv6hdr)); ptr += len; offset += len; @@ -782,15 +810,17 @@ slow_path: if (err) goto fail; - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGCREATES); } + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGOKS); kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); return err; fail: - kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); return err; } @@ -859,6 +889,41 @@ static int ip6_dst_lookup_tail(struct sock *sk, goto out_err_release; } +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + /* + * Here if the dst entry we've looked up + * has a neighbour entry that is in the INCOMPLETE + * state and the src address from the flow is + * marked as OPTIMISTIC, we release the found + * dst entry and replace it instead with the + * dst entry of the nexthop router + */ + if (!((*dst)->neighbour->nud_state & NUD_VALID)) { + struct inet6_ifaddr *ifp; + struct flowi fl_gw; + int redirect; + + ifp = ipv6_get_ifaddr(&fl->fl6_src, (*dst)->dev, 1); + + redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); + if (ifp) + in6_ifa_put(ifp); + + if (redirect) { + /* + * We need to get the dst entry for the + * default router instead + */ + dst_release(*dst); + memcpy(&fl_gw, fl, sizeof(struct flowi)); + memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr)); + *dst = ip6_route_output(sk, &fl_gw); + if ((err = (*dst)->error)) + goto out_err_release; + } + } +#endif + return 0; out_err_release: @@ -937,10 +1002,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_put(skb,fragheaderlen + transhdrlen); /* initialize network header pointer */ - skb->nh.raw = skb->data; + skb_reset_network_header(skb); /* initialize protocol header pointer */ - skb->h.raw = skb->data + fragheaderlen; + skb->transport_header = skb->network_header + fragheaderlen; skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; @@ -953,7 +1018,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, struct frag_hdr fhdr; /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->gso_size = mtu - fragheaderlen - + skb_shinfo(skb)->gso_size = mtu - fragheaderlen - sizeof(struct frag_hdr); skb_shinfo(skb)->gso_type = SKB_GSO_UDP; ipv6_select_ident(skb, &fhdr); @@ -1013,7 +1078,8 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, inet->cork.fl = *fl; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; - mtu = dst_mtu(rt->u.dst.path); + mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; @@ -1056,13 +1122,13 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail of - * of the buffer to the new fragment when we split + * of the buffer to the new fragment when we split * the message. * - * FIXME: It may be fragmented into multiple chunks + * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. - * --yoshfuji + * --yoshfuji */ inet->cork.length += length; @@ -1127,7 +1193,7 @@ alloc_new_skb: /* * We just reserve space for fragment header. - * Note: this may be overallocation if the message + * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloclen += sizeof(struct frag_hdr); @@ -1160,10 +1226,10 @@ alloc_new_skb: * Find where to start putting bytes */ data = skb_put(skb, fraglen); - skb->nh.raw = data + exthdrlen; + skb_set_network_header(skb, exthdrlen); data += fragheaderlen; - skb->h.raw = data + exthdrlen; - + skb->transport_header = (skb->network_header + + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, @@ -1263,7 +1329,7 @@ alloc_new_skb: return 0; error: inet->cork.length -= length; - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } @@ -1286,10 +1352,10 @@ int ip6_push_pending_frames(struct sock *sk) tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ - if (skb->data < skb->nh.raw) - __skb_pull(skb, skb->nh.raw - skb->data); + if (skb->data < skb_network_header(skb)) + __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { - __skb_pull(tmp_skb, skb->h.raw - skb->nh.raw); + __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; @@ -1301,15 +1367,17 @@ int ip6_push_pending_frames(struct sock *sk) } ipv6_addr_copy(final_dst, &fl->fl6_dst); - __skb_pull(skb, skb->h.raw - skb->nh.raw); + __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst); - skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr)); - - *(u32*)hdr = fl->fl6_flowlabel | + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); + + *(__be32*)hdr = fl->fl6_flowlabel | htonl(0x60000000 | ((int)np->cork.tclass << 20)); if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) @@ -1324,7 +1392,7 @@ int ip6_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->dst = dst_clone(&rt->u.dst); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output); if (err) { if (err > 0) @@ -1355,7 +1423,8 @@ void ip6_flush_pending_frames(struct sock *sk) struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); }