ip6_output.c

	 *
	 * FIXME: It may be fragmented into multiple chunks 
	 *        at once if non-fragmentable extension headers
	 *        are too large.
	 * --yoshfuji 
	 */

	inet->cork.length += length;
	if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
	    (rt->u.dst.dev->features & NETIF_F_UFO)) {

		err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
					  fragheaderlen, transhdrlen, mtu,
					  flags);
		if (err)
			goto error;
		return 0;
	}

	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
		goto alloc_new_skb;

	while (length > 0) {
		/* Check if the remaining data fits into current packet. */
		copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
		if (copy < length)
			copy = maxfraglen - skb->len;

		if (copy <= 0) {
			char *data;
			unsigned int datalen;
			unsigned int fraglen;
			unsigned int fraggap;
			unsigned int alloclen;
			struct sk_buff *skb_prev;
alloc_new_skb:
			skb_prev = skb;

			/* There's no room in the current skb */
			if (skb_prev)
				fraggap = skb_prev->len - maxfraglen;
			else
				fraggap = 0;

			/*
			 * If remaining data exceeds the mtu,
			 * we know we need more fragment(s).
			 */
			datalen = length + fraggap;
			if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
				datalen = maxfraglen - fragheaderlen;

			fraglen = datalen + fragheaderlen;
			if ((flags & MSG_MORE) &&
			    !(rt->u.dst.dev->features&NETIF_F_SG))
				alloclen = mtu;
			else
				alloclen = datalen + fragheaderlen;

			/*
			 * The last fragment gets additional space at tail.
			 * Note: we overallocate on fragments with MSG_MODE
			 * because we have no idea if we're the last one.
			 */
			if (datalen == length + fraggap)
				alloclen += rt->u.dst.trailer_len;

			/*
			 * We just reserve space for fragment header.
			 * Note: this may be overallocation if the message 
			 * (without MSG_MORE) fits into the MTU.
			 */
			alloclen += sizeof(struct frag_hdr);

			if (transhdrlen) {
				skb = sock_alloc_send_skb(sk,
						alloclen + hh_len,
						(flags & MSG_DONTWAIT), &err);
			} else {
				skb = NULL;
				if (atomic_read(&sk->sk_wmem_alloc) <=
				    2 * sk->sk_sndbuf)
					skb = sock_wmalloc(sk,
							   alloclen + hh_len, 1,
							   sk->sk_allocation);
				if (unlikely(skb == NULL))
					err = -ENOBUFS;
			}
			if (skb == NULL)
				goto error;
			/*
			 *	Fill in the control structures
			 */
			skb->ip_summed = csummode;
			skb->csum = 0;
			/* reserve for fragmentation */
			skb_reserve(skb, hh_len+sizeof(struct frag_hdr));

			/*
			 *	Find where to start putting bytes
			 */
			data = skb_put(skb, fraglen);
			skb->nh.raw = data + exthdrlen;
			data += fragheaderlen;
			skb->h.raw = data + exthdrlen;

			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;
			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_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 ipv6hdr *hdr;
	struct ipv6_txoptions *opt = np->cork.opt;
	struct rt6_info *rt = np->cork.rt;
	struct flowi *fl = &inet->cork.fl;
	unsigned char proto = fl->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->nh.raw)
		__skb_pull(skb, skb->nh.raw - skb->data);
	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
		__skb_pull(tmp_skb, skb->h.raw - skb->nh.raw);
		*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;
		__sock_put(tmp_skb->sk);
		tmp_skb->destructor = NULL;
		tmp_skb->sk = NULL;
	}

	ipv6_addr_copy(final_dst, &fl->fl6_dst);
	__skb_pull(skb, skb->h.raw - skb->nh.raw);
	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 |
		     htonl(0x60000000 | ((int)np->cork.tclass << 20));

	if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN)
		hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
	else
		hdr->payload_len = 0;
	hdr->hop_limit = np->cork.hop_limit;
	hdr->nexthdr = proto;
	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
	ipv6_addr_copy(&hdr->daddr, final_dst);

	skb->priority = sk->sk_priority;

	skb->dst = dst_clone(&rt->u.dst);
	IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);	
	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output);
	if (err) {
		if (err > 0)
			err = np->recverr ? net_xmit_errno(err) : 0;
		if (err)
			goto error;
	}

out:
	inet->cork.flags &= ~IPCORK_OPT;
	kfree(np->cork.opt);
	np->cork.opt = NULL;
	if (np->cork.rt) {
		dst_release(&np->cork.rt->u.dst);
		np->cork.rt = NULL;
		inet->cork.flags &= ~IPCORK_ALLFRAG;
	}
	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
	return err;
error:
	goto out;
}

void ip6_flush_pending_frames(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff *skb;

	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
		IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
		kfree_skb(skb);
	}

	inet->cork.flags &= ~IPCORK_OPT;

	kfree(np->cork.opt);
	np->cork.opt = NULL;
	if (np->cork.rt) {
		dst_release(&np->cork.rt->u.dst);
		np->cork.rt = NULL;
		inet->cork.flags &= ~IPCORK_ALLFRAG;
	}
	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
}