ip6_output.c

int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6)
{
	*dst = NULL;
	return ip6_dst_lookup_tail(sk, dst, fl6);
}
EXPORT_SYMBOL_GPL(ip6_dst_lookup);

/**
 *	ip6_dst_lookup_flow - perform route lookup on flow with ipsec
 *	@sk: socket which provides route info
 *	@fl6: flow to lookup
 *	@final_dst: final destination address for ipsec lookup
 *	@can_sleep: we are in a sleepable context
 *
 *	This function performs a route lookup on the given flow.
 *
 *	It returns a valid dst pointer on success, or a pointer encoded
 *	error code.
 */
struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
				      const struct in6_addr *final_dst,
				      bool can_sleep)
{
	struct dst_entry *dst = NULL;
	int err;

	err = ip6_dst_lookup_tail(sk, &dst, fl6);
	if (err)
		return ERR_PTR(err);
	if (final_dst)
		ipv6_addr_copy(&fl6->daddr, final_dst);
	if (can_sleep)
		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;

	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);

/**
 *	ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow
 *	@sk: socket which provides the dst cache and route info
 *	@fl6: flow to lookup
 *	@final_dst: final destination address for ipsec lookup
 *	@can_sleep: we are in a sleepable context
 *
 *	This function performs a route lookup on the given flow with the
 *	possibility of using the cached route in the socket if it is valid.
 *	It will take the socket dst lock when operating on the dst cache.
 *	As a result, this function can only be used in process context.
 *
 *	It returns a valid dst pointer on success, or a pointer encoded
 *	error code.
 */
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
					 const struct in6_addr *final_dst,
					 bool can_sleep)
{
	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
	int err;

	dst = ip6_sk_dst_check(sk, dst, fl6);

	err = ip6_dst_lookup_tail(sk, &dst, fl6);
	if (err)
		return ERR_PTR(err);
	if (final_dst)
		ipv6_addr_copy(&fl6->daddr, final_dst);
	if (can_sleep)
		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;

	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);

static inline int ip6_ufo_append_data(struct sock *sk,
			int getfrag(void *from, char *to, int offset, int len,
			int odd, struct sk_buff *skb),
			void *from, int length, int hh_len, int fragheaderlen,
			int transhdrlen, int mtu,unsigned int flags)

{
	struct sk_buff *skb;
	int err;

	/* There is support for UDP large send offload by network
	 * device, so create one single skb packet containing complete
	 * udp datagram
	 */
	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
		skb = sock_alloc_send_skb(sk,
			hh_len + fragheaderlen + transhdrlen + 20,
			(flags & MSG_DONTWAIT), &err);
		if (skb == NULL)
			return -ENOMEM;

		/* reserve space for Hardware header */
		skb_reserve(skb, hh_len);

		/* create space for UDP/IP header */
		skb_put(skb,fragheaderlen + transhdrlen);

		/* initialize network header pointer */
		skb_reset_network_header(skb);

		/* initialize protocol header pointer */
		skb->transport_header = skb->network_header + fragheaderlen;

		skb->ip_summed = CHECKSUM_PARTIAL;
		skb->csum = 0;
	}

	err = skb_append_datato_frags(sk,skb, getfrag, from,
				      (length - transhdrlen));
	if (!err) {
		struct frag_hdr fhdr;

		/* Specify the length of each IPv6 datagram fragment.
		 * It has to be a multiple of 8.
		 */
		skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
					     sizeof(struct frag_hdr)) & ~7;
		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
		ipv6_select_ident(&fhdr);
		skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
		__skb_queue_tail(&sk->sk_write_queue, skb);

		return 0;
	}
	/* There is not enough support do UPD LSO,
	 * so follow normal path
	 */
	kfree_skb(skb);

	return err;
}

static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
					       gfp_t gfp)
{
	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}

static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
						gfp_t gfp)
{
	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}

int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
	int offset, int len, int odd, struct sk_buff *skb),
	void *from, int length, int transhdrlen,
	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
	struct rt6_info *rt, unsigned int flags, int dontfrag)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet_cork *cork;
	struct sk_buff *skb;
	unsigned int maxfraglen, fragheaderlen;
	int exthdrlen;
	int hh_len;
	int mtu;
	int copy;
	int err;
	int offset = 0;
	int csummode = CHECKSUM_NONE;
	__u8 tx_flags = 0;

	if (flags&MSG_PROBE)
		return 0;
	cork = &inet->cork.base;
	if (skb_queue_empty(&sk->sk_write_queue)) {
		/*
		 * setup for corking
		 */
		if (opt) {
			if (WARN_ON(np->cork.opt))
				return -EINVAL;

			np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
			if (unlikely(np->cork.opt == NULL))
				return -ENOBUFS;

			np->cork.opt->tot_len = opt->tot_len;
			np->cork.opt->opt_flen = opt->opt_flen;
			np->cork.opt->opt_nflen = opt->opt_nflen;

			np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
							    sk->sk_allocation);
			if (opt->dst0opt && !np->cork.opt->dst0opt)
				return -ENOBUFS;

			np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
							    sk->sk_allocation);
			if (opt->dst1opt && !np->cork.opt->dst1opt)
				return -ENOBUFS;

			np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
							   sk->sk_allocation);
			if (opt->hopopt && !np->cork.opt->hopopt)
				return -ENOBUFS;

			np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
							    sk->sk_allocation);
			if (opt->srcrt && !np->cork.opt->srcrt)
				return -ENOBUFS;

			/* need source address above miyazawa*/
		}
		dst_hold(&rt->dst);
		cork->dst = &rt->dst;
		inet->cork.fl.u.ip6 = *fl6;
		np->cork.hop_limit = hlimit;
		np->cork.tclass = tclass;
		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
		if (np->frag_size < mtu) {
			if (np->frag_size)
				mtu = np->frag_size;
		}
		cork->fragsize = mtu;
		if (dst_allfrag(rt->dst.path))
			cork->flags |= IPCORK_ALLFRAG;
		cork->length = 0;
		sk->sk_sndmsg_page = NULL;
		sk->sk_sndmsg_off = 0;
		exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
			    rt->rt6i_nfheader_len;
		length += exthdrlen;
		transhdrlen += exthdrlen;
	} else {
		rt = (struct rt6_info *)cork->dst;
		fl6 = &inet->cork.fl.u.ip6;
		opt = np->cork.opt;
		transhdrlen = 0;
		exthdrlen = 0;
		mtu = cork->fragsize;
	}

	hh_len = LL_RESERVED_SPACE(rt->dst.dev);

	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
			(opt ? opt->opt_nflen : 0);
	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);

	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
		if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
			ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
			return -EMSGSIZE;
		}
	}

	/* For UDP, check if TX timestamp is enabled */
	if (sk->sk_type == SOCK_DGRAM) {
		err = sock_tx_timestamp(sk, &tx_flags);
		if (err)
			goto error;
	}

	/*
	 * Let's try using as much space as possible.
	 * Use MTU if total length of the message fits into the MTU.
	 * Otherwise, we need to reserve fragment header and
	 * 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
	 * the message.
	 *
	 * FIXME: It may be fragmented into multiple chunks
	 *        at once if non-fragmentable extension headers
	 *        are too large.
	 * --yoshfuji
	 */

	cork->length += length;
	if (length > mtu) {
		int proto = sk->sk_protocol;
		if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
			ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
			return -EMSGSIZE;
		}

		if (proto == IPPROTO_UDP &&
		    (rt->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 = (cork->length <= mtu && !(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 > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
				datalen = maxfraglen - fragheaderlen;

			fraglen = datalen + fragheaderlen;
			if ((flags & MSG_MORE) &&
			    !(rt->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->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;
				else {
					/* Only the initial fragment
					 * is time stamped.
					 */
					tx_flags = 0;
				}
			}
			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));

			if (sk->sk_type == SOCK_DGRAM)
				skb_shinfo(skb)->tx_flags = tx_flags;

			/*
			 *	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;
			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->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];
			} 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;
			skb->truesize += copy;
			atomic_add(copy, &sk->sk_wmem_alloc);
		}
		offset += copy;
		length -= copy;
	}
	return 0;
error:
	cork->length -= length;
	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
	return err;
}

static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
{
	if (np->cork.opt) {
		kfree(np->cork.opt->dst0opt);
		kfree(np->cork.opt->dst1opt);
		kfree(np->cork.opt->hopopt);
		kfree(np->cork.opt->srcrt);
		kfree(np->cork.opt);
		np->cork.opt = NULL;
	}

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

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;

	ipv6_addr_copy(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;
	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
	ipv6_addr_copy(&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_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
		ICMP6_INC_STATS_BH(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;
}

void ip6_flush_pending_frames(struct sock *sk)
{
	struct sk_buff *skb;

	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
		if (skb_dst(skb))
			IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)),
				      IPSTATS_MIB_OUTDISCARDS);
		kfree_skb(skb);
	}

	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
}