C++ IP6_INC_STATS函数代码示例

int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
	     struct ipv6_txoptions *opt)
{
	struct ipv6_pinfo * np = sk ? &sk->net_pinfo.af_inet6 : NULL;
	struct in6_addr *first_hop = fl->nl_u.ip6_u.daddr;
	struct dst_entry *dst = skb->dst;
	struct ipv6hdr *hdr;
	u8  proto = fl->proto;
	int seg_len = skb->len;
	int hlimit;

	if (opt) {
		int head_room;

		/* First: exthdrs may take lots of space (~8K for now)
		   MAX_HEADER is not enough.
		 */
		head_room = opt->opt_nflen + opt->opt_flen;
		seg_len += head_room;
		head_room += sizeof(struct ipv6hdr) + ((dst->dev->hard_header_len + 15)&~15);

		if (skb_headroom(skb) < head_room) {
			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
			kfree_skb(skb);
			skb = skb2;
			if (skb == NULL)
				return -ENOBUFS;
			if (sk)
				skb_set_owner_w(skb, sk);
		}
		if (opt->opt_flen)
			ipv6_push_frag_opts(skb, opt, &proto);
		if (opt->opt_nflen)
			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
	}

	hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr));

	/*
	 *	Fill in the IPv6 header
	 */

	*(u32*)hdr = htonl(0x60000000) | fl->fl6_flowlabel;
	hlimit = -1;
	if (np)
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = ((struct rt6_info*)dst)->rt6i_hoplimit;

	hdr->payload_len = htons(seg_len);
	hdr->nexthdr = proto;
	hdr->hop_limit = hlimit;

	ipv6_addr_copy(&hdr->saddr, fl->nl_u.ip6_u.saddr);
	ipv6_addr_copy(&hdr->daddr, first_hop);

	if (skb->len <= dst->pmtu) {
		IP6_INC_STATS(Ip6OutRequests);
		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute);
	}

	if (net_ratelimit())
		printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
	skb->dev = dst->dev;
	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst->pmtu, skb->dev);
	kfree_skb(skb);
	return -EMSGSIZE;
}

//.........这里部分代码省略.........
					skb_prev, maxfraglen,
					data + transhdrlen, fraggap, 0);
				skb_prev->csum = csum_sub(skb_prev->csum,
							  skb->csum);
				data += fraggap;
				skb_trim(skb_prev, maxfraglen);
			}
			copy = datalen - transhdrlen - fraggap;
			if (copy < 0) {
				err = -EINVAL;
				kfree_skb(skb);
				goto error;
			} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
				err = -EFAULT;
				kfree_skb(skb);
				goto error;
			}

			offset += copy;
			length -= datalen - fraggap;
			transhdrlen = 0;
			exthdrlen = 0;
			csummode = CHECKSUM_NONE;

			/*
			 * Put the packet on the pending queue
			 */
			__skb_queue_tail(&sk->sk_write_queue, skb);
			continue;
		}

		if (copy > length)
			copy = length;

		if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
			unsigned int off;

			off = skb->len;
			if (getfrag(from, skb_put(skb, copy),
						offset, copy, off, skb) < 0) {
				__skb_trim(skb, off);
				err = -EFAULT;
				goto error;
			}
		} else {
			int i = skb_shinfo(skb)->nr_frags;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
			struct page *page = sk->sk_sndmsg_page;
			int off = sk->sk_sndmsg_off;
			unsigned int left;

			if (page && (left = PAGE_SIZE - off) > 0) {
				if (copy >= left)
					copy = left;
				if (page != frag->page) {
					if (i == MAX_SKB_FRAGS) {
						err = -EMSGSIZE;
						goto error;
					}
					get_page(page);
					skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
					frag = &skb_shinfo(skb)->frags[i];
				}
			} else if(i < MAX_SKB_FRAGS) {
				if (copy > PAGE_SIZE)
					copy = PAGE_SIZE;
				page = alloc_pages(sk->sk_allocation, 0);
				if (page == NULL) {
					err = -ENOMEM;
					goto error;
				}
				sk->sk_sndmsg_page = page;
				sk->sk_sndmsg_off = 0;

				skb_fill_page_desc(skb, i, page, 0, 0);
				frag = &skb_shinfo(skb)->frags[i];
				skb->truesize += PAGE_SIZE;
				atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
			} else {
				err = -EMSGSIZE;
				goto error;
			}
			if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
				err = -EFAULT;
				goto error;
			}
			sk->sk_sndmsg_off += copy;
			frag->size += copy;
			skb->len += copy;
			skb->data_len += copy;
		}
		offset += copy;
		length -= copy;
	}
	return 0;
error:
	inet->cork.length -= length;
	IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
	return err;
}

int ip6_forward(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct net *net = dev_net(dst->dev);
	u32 mtu;

	if (net->ipv6.devconf_all->forwarding == 0)
		goto error;

	if (skb_warn_if_lro(skb))
		goto drop;

	if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	skb_forward_csum(skb);

	/*
	 *	We DO NOT make any processing on
	 *	RA packets, pushing them to user level AS IS
	 *	without ane WARRANTY that application will be able
	 *	to interpret them. The reason is that we
	 *	cannot make anything clever here.
	 *
	 *	We are not end-node, so that if packet contains
	 *	AH/ESP, we cannot make anything.
	 *	Defragmentation also would be mistake, RA packets
	 *	cannot be fragmented, because there is no warranty
	 *	that different fragments will go along one path. --ANK
	 */
	if (opt->ra) {
		u8 *ptr = skb_network_header(skb) + opt->ra;
		if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
			return 0;
	}

	/*
	 *	check and decrement ttl
	 */
	if (hdr->hop_limit <= 1) {
		/* Force OUTPUT device used as source address */
		skb->dev = dst->dev;
		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
		IP6_INC_STATS_BH(net,
				 ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);

		kfree_skb(skb);
		return -ETIMEDOUT;
	}

	/* XXX: idev->cnf.proxy_ndp? */
	if ((net->ipv6.devconf_all->proxy_ndp == 1 &&
	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0))
	    || net->ipv6.devconf_all->proxy_ndp >= 2) {
		int proxied = ip6_forward_proxy_check(skb);
		if (proxied > 0)
			return ip6_input(skb);
		else if (proxied < 0) {
			IP6_INC_STATS(net, ip6_dst_idev(dst),
				      IPSTATS_MIB_INDISCARDS);
			goto drop;
		}
	}

	if (!xfrm6_route_forward(skb)) {
		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
		goto drop;
	}
	dst = skb_dst(skb);

	/* IPv6 specs say nothing about it, but it is clear that we cannot
	   send redirects to source routed frames.
	   We don't send redirects to frames decapsulated from IPsec.
	 */
	if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
		struct in6_addr *target = NULL;
		struct rt6_info *rt;

		/*
		 *	incoming and outgoing devices are the same
		 *	send a redirect.
		 */

		rt = (struct rt6_info *) dst;
		if (rt->rt6i_flags & RTF_GATEWAY)
			target = &rt->rt6i_gateway;
		else
			target = &hdr->daddr;

		if (!rt->rt6i_peer)
			rt6_bind_peer(rt, 1);

		/* Limit redirects both by destination (here)
//.........这里部分代码省略.........

//.........这里部分代码省略.........

			/*
			 *	Find where to start putting bytes
			 */
			data = skb_put(skb, fraglen);
			skb_set_network_header(skb, exthdrlen);
			data += fragheaderlen;
			skb->transport_header = (skb->network_header +
						 fragheaderlen);
			if (fraggap) {
				skb->csum = skb_copy_and_csum_bits(
					skb_prev, maxfraglen,
					data + transhdrlen, fraggap, 0);
				skb_prev->csum = csum_sub(skb_prev->csum,
							  skb->csum);
				data += fraggap;
				pskb_trim_unique(skb_prev, maxfraglen);
			}
			copy = datalen - transhdrlen - fraggap;

			if (copy < 0) {
				err = -EINVAL;
				kfree_skb(skb);
				goto error;
			} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
				err = -EFAULT;
				kfree_skb(skb);
				goto error;
			}

			offset += copy;
			length -= datalen - fraggap;
			transhdrlen = 0;
			exthdrlen = 0;
			dst_exthdrlen = 0;

			/*
			 * Put the packet on the pending queue
			 */
			__skb_queue_tail(queue, skb);
			continue;
		}

		if (copy > length)
			copy = length;

		if (!(rt->dst.dev->features&NETIF_F_SG)) {
			unsigned int off;

			off = skb->len;
			if (getfrag(from, skb_put(skb, copy),
						offset, copy, off, skb) < 0) {
				__skb_trim(skb, off);
				err = -EFAULT;
				goto error;
			}
		} else {
			int i = skb_shinfo(skb)->nr_frags;

			err = -ENOMEM;
			if (!sk_page_frag_refill(sk, pfrag))
				goto error;

			if (!skb_can_coalesce(skb, i, pfrag->page,
					      pfrag->offset)) {
				err = -EMSGSIZE;
				if (i == MAX_SKB_FRAGS)
					goto error;

				__skb_fill_page_desc(skb, i, pfrag->page,
						     pfrag->offset, 0);
				skb_shinfo(skb)->nr_frags = ++i;
				get_page(pfrag->page);
			}
			copy = min_t(int, copy, pfrag->size - pfrag->offset);
			if (getfrag(from,
				    page_address(pfrag->page) + pfrag->offset,
				    offset, copy, skb->len, skb) < 0)
				goto error_efault;

			pfrag->offset += copy;
			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
			skb->len += copy;
			skb->data_len += copy;
			skb->truesize += copy;
			atomic_add(copy, &sk->sk_wmem_alloc);
		}
		offset += copy;
		length -= copy;
	}

	return 0;

error_efault:
	err = -EFAULT;
error:
	cork->length -= length;
	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
	return err;
}

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int offset, end;
	struct net *net = dev_net(skb->dst->dev);

	if (fq->q.last_in & INET_FRAG_COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((u8 *)&fhdr->frag_off -
				   skb_network_header(skb)));
		return -1;
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		const unsigned char *nh = skb_network_header(skb);
		skb->csum = csum_sub(skb->csum,
				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
						  0));
	}

	/* Is this the final fragment? */
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < fq->q.len ||
		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
			goto err;
		fq->q.last_in |= INET_FRAG_LAST_IN;
		fq->q.len = end;
	} else {
		/* Check if the fragment is rounded to 8 bytes.
		 * Required by the RFC.
		 */
		if (end & 0x7) {
			/* RFC2460 says always send parameter problem in
			 * this case. -DaveM
			 */
			IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  offsetof(struct ipv6hdr, payload_len));
			return -1;
		}
		if (end > fq->q.len) {
			/* Some bits beyond end -> corruption. */
			if (fq->q.last_in & INET_FRAG_LAST_IN)
				goto err;
			fq->q.len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
		goto err;

	if (pskb_trim_rcsum(skb, end - offset))
		goto err;

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = NULL;
	for(next = fq->q.fragments; next != NULL; next = next->next) {
		if (FRAG6_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

	/* We found where to put this one.  Check for overlap with
	 * preceding fragment, and, if needed, align things so that
	 * any overlaps are eliminated.
	 */
	if (prev) {
		int i = (FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset)
				goto err;
			if (!pskb_pull(skb, i))
				goto err;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
//.........这里部分代码省略.........

int ip6_push_pending_frames(struct sock *sk)
{
	struct sk_buff *skb, *tmp_skb;
	struct sk_buff **tail_skb;
	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct net *net = sock_net(sk);
	struct ipv6hdr *hdr;
	struct ipv6_txoptions *opt = np->cork.opt;
	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
	unsigned char proto = fl6->flowi6_proto;
	int err = 0;

	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
		goto out;
	tail_skb = &(skb_shinfo(skb)->frag_list);

	/* move skb->data to ip header from ext header */
	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_network_header_len(skb));
		*tail_skb = tmp_skb;
		tail_skb = &(tmp_skb->next);
		skb->len += tmp_skb->len;
		skb->data_len += tmp_skb->len;
		skb->truesize += tmp_skb->truesize;
		tmp_skb->destructor = NULL;
		tmp_skb->sk = NULL;
	}

	/* Allow local fragmentation. */
	if (np->pmtudisc < IPV6_PMTUDISC_DO)
		skb->local_df = 1;

	*final_dst = fl6->daddr;
	__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_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	hdr = ipv6_hdr(skb);

	*(__be32*)hdr = fl6->flowlabel |
		     htonl(0x60000000 | ((int)np->cork.tclass << 20));

	hdr->hop_limit = np->cork.hop_limit;
	hdr->nexthdr = proto;
	hdr->saddr = fl6->saddr;
	hdr->daddr = *final_dst;

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;

	skb_dst_set(skb, dst_clone(&rt->dst));
	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
	if (proto == IPPROTO_ICMPV6) {
		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));

		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
	}

	err = ip6_local_out(skb);
	if (err) {
		if (err > 0)
			err = net_xmit_errno(err);
		if (err)
			goto error;
	}

out:
	ip6_cork_release(inet, np);
	return err;
error:
	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
	goto out;
}

static int ipv6_frag_rcv(struct sk_buff *skb)
{
	struct frag_hdr *fhdr;
	struct frag_queue *fq;
	const struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct net *net = dev_net(skb_dst(skb)->dev);
	int evicted;

	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
		goto fail_hdr;

	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);

	/* Jumbo payload inhibits frag. header */
	if (hdr->payload_len==0)
		goto fail_hdr;

	if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
				 sizeof(struct frag_hdr))))
		goto fail_hdr;

	hdr = ipv6_hdr(skb);
	fhdr = (struct frag_hdr *)skb_transport_header(skb);

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		/* It is not a fragmented frame */
		skb->transport_header += sizeof(struct frag_hdr);
		IP6_INC_STATS_BH(net,
				 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);

		IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
		IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
		return 1;
	}

	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
	if (evicted)
		IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
				 IPSTATS_MIB_REASMFAILS, evicted);

	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
		     ip6_frag_ecn(hdr));
	if (fq != NULL) {
		int ret;

		spin_lock(&fq->q.lock);

		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);

		spin_unlock(&fq->q.lock);
		inet_frag_put(&fq->q, &ip6_frags);
		return ret;
	}

	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -1;

fail_hdr:
	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
	icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
	return -1;
}

int ip6_route_me_harder(struct sk_buff *skb)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	unsigned int hh_len;
	struct dst_entry *dst;
	struct flowi6 fl6 = {
		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
		.flowi6_mark = skb->mark,
		.daddr = iph->daddr,
		.saddr = iph->saddr,
	};

	dst = ip6_route_output(net, skb->sk, &fl6);
	if (dst->error) {
		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
		dst_release(dst);
		return -EINVAL;
	}

	/* Drop old route. */
	skb_dst_drop(skb);

	skb_dst_set(skb, dst);

#ifdef CONFIG_XFRM
	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
	    xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
		skb_dst_set(skb, NULL);
		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
		if (IS_ERR(dst))
			return -1;
		skb_dst_set(skb, dst);
	}
#endif

	/* Change in oif may mean change in hh_len. */
	hh_len = skb_dst(skb)->dev->hard_header_len;
	if (skb_headroom(skb) < hh_len &&
	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
			     0, GFP_ATOMIC))
		return -1;

	return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);

/*
 * Extra routing may needed on local out, as the QUEUE target never
 * returns control to the table.
 */

struct ip6_rt_info {
	struct in6_addr daddr;
	struct in6_addr saddr;
	u_int32_t mark;
};

static void nf_ip6_saveroute(const struct sk_buff *skb,
			     struct nf_queue_entry *entry)
{
	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->hook == NF_INET_LOCAL_OUT) {
		const struct ipv6hdr *iph = ipv6_hdr(skb);

		rt_info->daddr = iph->daddr;
		rt_info->saddr = iph->saddr;
		rt_info->mark = skb->mark;
	}
}

static int nf_ip6_reroute(struct sk_buff *skb,
			  const struct nf_queue_entry *entry)
{
	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->hook == NF_INET_LOCAL_OUT) {
		const struct ipv6hdr *iph = ipv6_hdr(skb);
		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
		    skb->mark != rt_info->mark)
			return ip6_route_me_harder(skb);
	}
	return 0;
}

static int nf_ip6_route(struct net *net, struct dst_entry **dst,
			struct flowi *fl, bool strict)
{
	static const struct ipv6_pinfo fake_pinfo;
	static const struct inet_sock fake_sk = {
		/* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
		.sk.sk_bound_dev_if = 1,
		.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
	};
	const void *sk = strict ? &fake_sk : NULL;
	struct dst_entry *result;
	int err;
//.........这里部分代码省略.........

int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
	     struct ipv6_txoptions *opt, int tclass)
{
	struct net *net = sock_net(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *first_hop = &fl6->daddr;
	struct dst_entry *dst = skb_dst(skb);
	struct ipv6hdr *hdr;
	u8  proto = fl6->flowi6_proto;
	int seg_len = skb->len;
	int hlimit = -1;
	u32 mtu;

	if (opt) {
		unsigned int head_room;

		/* First: exthdrs may take lots of space (~8K for now)
		   MAX_HEADER is not enough.
		 */
		head_room = opt->opt_nflen + opt->opt_flen;
		seg_len += head_room;
		head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);

		if (skb_headroom(skb) < head_room) {
			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
			if (!skb2) {
				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
					      IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return -ENOBUFS;
			}
			consume_skb(skb);
			skb = skb2;
			skb_set_owner_w(skb, sk);
		}
		if (opt->opt_flen)
			ipv6_push_frag_opts(skb, opt, &proto);
		if (opt->opt_nflen)
			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
	}

	skb_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	hdr = ipv6_hdr(skb);

	/*
	 *	Fill in the IPv6 header
	 */
	if (np)
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = ip6_dst_hoplimit(dst);

	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
						     np->autoflowlabel, fl6));

	hdr->payload_len = htons(seg_len);
	hdr->nexthdr = proto;
	hdr->hop_limit = hlimit;

	hdr->saddr = fl6->saddr;
	hdr->daddr = *first_hop;

	skb->protocol = htons(ETH_P_IPV6);
	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;

	mtu = dst_mtu(dst);
	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
			      IPSTATS_MIB_OUT, skb->len);
		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
			       NULL, dst->dev, dst_output_sk);
	}

	skb->dev = dst->dev;
	ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
	kfree_skb(skb);
	return -EMSGSIZE;
}

static int ip6_dst_lookup_tail(struct sock *sk,
			       struct dst_entry **dst, struct flowi6 *fl6)
{
	struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
	struct neighbour *n;
	struct rt6_info *rt;
#endif
	int err;

	if (*dst == NULL)
		*dst = ip6_route_output(net, sk, fl6);

	if ((err = (*dst)->error))
		goto out_err_release;

	if (ipv6_addr_any(&fl6->saddr)) {
		struct rt6_info *rt = (struct rt6_info *) *dst;
		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
					  sk ? inet6_sk(sk)->srcprefs : 0,
					  &fl6->saddr);
		if (err)
			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
	 */
	rt = (struct rt6_info *) *dst;
	rcu_read_lock_bh();
	n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
	rcu_read_unlock_bh();

	if (err) {
		struct inet6_ifaddr *ifp;
		struct flowi6 fl_gw6;
		int redirect;

		ifp = ipv6_get_ifaddr(net, &fl6->saddr,
				      (*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_gw6, fl6, sizeof(struct flowi6));
			memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
			*dst = ip6_route_output(net, sk, &fl_gw6);
			if ((err = (*dst)->error))
				goto out_err_release;
		}
	}
#endif

	return 0;

out_err_release:
	if (err == -ENETUNREACH)
		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
	dst_release(*dst);
	*dst = NULL;
	return err;
}

static int ip6_finish_output2(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct net_device *dev = dst->dev;
	struct neighbour *neigh;
	struct in6_addr *nexthop;
	int ret;

	skb->protocol = htons(ETH_P_IPV6);
	skb->dev = dev;

	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));

		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
		    ((mroute6_socket(dev_net(dev), skb) &&
		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
		     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
			   is not supported in any case.
			 */
			if (newskb)
				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
					newskb, NULL, newskb->dev,
					dev_loopback_xmit);

			if (ipv6_hdr(skb)->hop_limit == 0) {
				IP6_INC_STATS(dev_net(dev), idev,
					      IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return 0;
			}
		}

		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
				skb->len);

		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
		    IPV6_ADDR_SCOPE_NODELOCAL &&
		    !(dev->flags & IFF_LOOPBACK)) {
			kfree_skb(skb);
			return 0;
		}
	}

	rcu_read_lock_bh();
	nexthop = rt6_nexthop((struct rt6_info *)dst);
	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
	if (unlikely(!neigh))
		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
	if (!IS_ERR(neigh)) {
		ret = dst_neigh_output(dst, neigh, skb);
		rcu_read_unlock_bh();
		return ret;
	}
	rcu_read_unlock_bh();

	IP6_INC_STATS(dev_net(dst->dev),
		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EINVAL;
}

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int offset, end;
	struct net *net = dev_net(skb_dst(skb)->dev);

	if (fq->q.last_in & INET_FRAG_COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((u8 *)&fhdr->frag_off -
				   skb_network_header(skb)));
		return -1;
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		const unsigned char *nh = skb_network_header(skb);
		skb->csum = csum_sub(skb->csum,
				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
						  0));
	}

	
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		if (end < fq->q.len ||
		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
			goto err;
		fq->q.last_in |= INET_FRAG_LAST_IN;
		fq->q.len = end;
	} else {
		if (end & 0x7) {
			IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  offsetof(struct ipv6hdr, payload_len));
			return -1;
		}
		if (end > fq->q.len) {
			
			if (fq->q.last_in & INET_FRAG_LAST_IN)
				goto err;
			fq->q.len = end;
		}
	}

	if (end == offset)
		goto err;

	
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
		goto err;

	if (pskb_trim_rcsum(skb, end - offset))
		goto err;

	prev = fq->q.fragments_tail;
	if (!prev || FRAG6_CB(prev)->offset < offset) {
		next = NULL;
		goto found;
	}
	prev = NULL;
	for(next = fq->q.fragments; next != NULL; next = next->next) {
		if (FRAG6_CB(next)->offset >= offset)
			break;	
		prev = next;
	}

found:

	
	if (prev &&
	    (FRAG6_CB(prev)->offset + prev->len) > offset)
		goto discard_fq;

	
	if (next && FRAG6_CB(next)->offset < end)
		goto discard_fq;

	FRAG6_CB(skb)->offset = offset;

	
	skb->next = next;
	if (!next)
		fq->q.fragments_tail = skb;
	if (prev)
		prev->next = skb;
	else
		fq->q.fragments = skb;

	dev = skb->dev;
	if (dev) {
//.........这里部分代码省略.........

static void __ndisc_send(struct net_device *dev,
			 struct neighbour *neigh,
			 struct in6_addr *daddr, struct in6_addr *saddr,
			 struct icmp6hdr *icmp6h, struct in6_addr *target,
			 int llinfo, int icmp6_mib_outnd)
{
	struct flowi fl;
	struct dst_entry *dst;
	struct sock *sk = ndisc_socket->sk;
	struct sk_buff *skb;
	struct icmp6hdr *hdr;
	struct inet6_dev *idev;
	int len;
	int err;
	u8 *opt;

	ndisc_flow_init(&fl, icmp6h->icmp6_type, saddr, daddr,
			dev->ifindex);

	dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output);
	if (!dst)
		return;

	err = xfrm_lookup(&dst, &fl, NULL, 0);
	if (err < 0)
		return;

	if (!dev->addr_len)
		llinfo = 0;

	len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0);
	if (llinfo)
		len += ndisc_opt_addr_space(dev);

	skb = sock_alloc_send_skb(sk,
				  (MAX_HEADER + sizeof(struct ipv6hdr) +
				   len + LL_RESERVED_SPACE(dev)),
				  1, &err);
	if (!skb) {
		ND_PRINTK0(KERN_ERR
			   "ICMPv6 ND: %s() failed to allocate an skb.\n",
			   __FUNCTION__);
		dst_release(dst);
		return;
	}

	skb_reserve(skb, LL_RESERVED_SPACE(dev));
	ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);

	skb->transport_header = skb->tail;
	skb_put(skb, len);

	hdr = (struct icmp6hdr *)skb_transport_header(skb);
	memcpy(hdr, icmp6h, sizeof(*hdr));

	opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
	if (target) {
		ipv6_addr_copy((struct in6_addr *)opt, target);
		opt += sizeof(*target);
	}

	if (llinfo)
		ndisc_fill_addr_option(opt, llinfo, dev->dev_addr,
				       dev->addr_len, dev->type);

	hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len,
					   IPPROTO_ICMPV6,
					   csum_partial((__u8 *) hdr,
							len, 0));

	skb->dst = dst;

	idev = in6_dev_get(dst->dev);
	IP6_INC_STATS(idev, IPSTATS_MIB_OUTREQUESTS);

	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output);
	if (!err) {
		ICMP6_INC_STATS(idev, icmp6_mib_outnd);
		ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS);
	}

	if (likely(idev != NULL))
		in6_dev_put(idev);
}

//.........这里部分代码省略.........
	struct rt6_info *rt;
#endif
	int err;
	int flags = 0;

	/* The correct way to handle this would be to do
	 * ip6_route_get_saddr, and then ip6_route_output; however,
	 * the route-specific preferred source forces the
	 * ip6_route_output call _before_ ip6_route_get_saddr.
	 *
	 * In source specific routing (no src=any default route),
	 * ip6_route_output will fail given src=any saddr, though, so
	 * that's why we try it again later.
	 */
	if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
		struct rt6_info *rt;
		bool had_dst = *dst != NULL;

		if (!had_dst)
			*dst = ip6_route_output(net, sk, fl6);
		rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
					  sk ? inet6_sk(sk)->srcprefs : 0,
					  &fl6->saddr);
		if (err)
			goto out_err_release;

		/* If we had an erroneous initial result, pretend it
		 * never existed and let the SA-enabled version take
		 * over.
		 */
		if (!had_dst && (*dst)->error) {
			dst_release(*dst);
			*dst = NULL;
		}

		if (fl6->flowi6_oif)
			flags |= RT6_LOOKUP_F_IFACE;
	}

	if (!*dst)
		*dst = ip6_route_output_flags(net, sk, fl6, flags);

	err = (*dst)->error;
	if (err)
		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
	 */
	rt = (struct rt6_info *) *dst;
	rcu_read_lock_bh();
	n = __ipv6_neigh_lookup_noref(rt->dst.dev,
				      rt6_nexthop(rt, &fl6->daddr));
	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
	rcu_read_unlock_bh();

	if (err) {
		struct inet6_ifaddr *ifp;
		struct flowi6 fl_gw6;
		int redirect;

		ifp = ipv6_get_ifaddr(net, &fl6->saddr,
				      (*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_gw6, fl6, sizeof(struct flowi6));
			memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
			*dst = ip6_route_output(net, sk, &fl_gw6);
			err = (*dst)->error;
			if (err)
				goto out_err_release;
		}
	}
#endif

	return 0;

out_err_release:
	if (err == -ENETUNREACH)
		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
	dst_release(*dst);
	*dst = NULL;
	return err;
}

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int offset, end;
	struct net *net = dev_net(skb_dst(skb)->dev);

	if (fq->q.last_in & INET_FRAG_COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((u8 *)&fhdr->frag_off -
				   skb_network_header(skb)));
		return -1;
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		const unsigned char *nh = skb_network_header(skb);
		skb->csum = csum_sub(skb->csum,
				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
						  0));
	}

	/* Is this the final fragment? */
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < fq->q.len ||
		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
			goto err;
		fq->q.last_in |= INET_FRAG_LAST_IN;
		fq->q.len = end;
	} else {
		/* Check if the fragment is rounded to 8 bytes.
		 * Required by the RFC.
		 */
		if (end & 0x7) {
			/* RFC2460 says always send parameter problem in
			 * this case. -DaveM
			 */
			IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  offsetof(struct ipv6hdr, payload_len));
			return -1;
		}
		if (end > fq->q.len) {
			/* Some bits beyond end -> corruption. */
			if (fq->q.last_in & INET_FRAG_LAST_IN)
				goto err;
			fq->q.len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
		goto err;

	if (pskb_trim_rcsum(skb, end - offset))
		goto err;

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = fq->q.fragments_tail;
	if (!prev || FRAG6_CB(prev)->offset < offset) {
		next = NULL;
		goto found;
	}
	prev = NULL;
	for(next = fq->q.fragments; next != NULL; next = next->next) {
		if (FRAG6_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

found:
	/* RFC5722, Section 4, amended by Errata ID : 3089
	 *                          When reassembling an IPv6 datagram, if
	 *   one or more its constituent fragments is determined to be an
	 *   overlapping fragment, the entire datagram (and any constituent
	 *   fragments) MUST be silently discarded.
	 */

	/* Check for overlap with preceding fragment. */
	if (prev &&
	    (FRAG6_CB(prev)->offset + prev->len) > offset)
//.........这里部分代码省略.........