ip_output.c

linux 内核源代码

			if (frag->len > mtu ||
			    ((frag->len & 7) && frag->next) ||
			    skb_headroom(frag) < hlen)
			    goto slow_path;

			/* Partially cloned skb? */
			if (skb_shared(frag))
				goto slow_path;

			BUG_ON(frag->sk);
			if (skb->sk) {
				sock_hold(skb->sk);
				frag->sk = skb->sk;
				frag->destructor = sock_wfree;
				skb->truesize -= frag->truesize;
			}
		}

		/* Everything is OK. Generate! */

		err = 0;
		offset = 0;
		frag = skb_shinfo(skb)->frag_list;
		skb_shinfo(skb)->frag_list = NULL;
		skb->data_len = first_len - skb_headlen(skb);
		skb->len = first_len;
		iph->tot_len = htons(first_len);
		iph->frag_off = htons(IP_MF);
		ip_send_check(iph);

		for (;;) {
			/* Prepare header of the next frame,
			 * before previous one went down. */
			if (frag) {
				frag->ip_summed = CHECKSUM_NONE;
				skb_reset_transport_header(frag);
				__skb_push(frag, hlen);
				skb_reset_network_header(frag);
				memcpy(skb_network_header(frag), iph, hlen);
				iph = ip_hdr(frag);
				iph->tot_len = htons(frag->len);
				ip_copy_metadata(frag, skb);
				if (offset == 0)
					ip_options_fragment(frag);
				offset += skb->len - hlen;
				iph->frag_off = htons(offset>>3);
				if (frag->next != NULL)
					iph->frag_off |= htons(IP_MF);
				/* Ready, complete checksum */
				ip_send_check(iph);
			}

			err = output(skb);

			if (!err)
				IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
			if (err || !frag)
				break;

			skb = frag;
			frag = skb->next;
			skb->next = NULL;
		}

		if (err == 0) {
			IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
			return 0;
		}

		while (frag) {
			skb = frag->next;
			kfree_skb(frag);
			frag = skb;
		}
		IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
		return err;
	}

slow_path:
	left = skb->len - hlen;		/* Space per frame */
	ptr = raw + hlen;		/* Where to start from */

	/* for bridged IP traffic encapsulated inside f.e. a vlan header,
	 * we need to make room for the encapsulating header
	 */
	pad = nf_bridge_pad(skb);
	ll_rs = LL_RESERVED_SPACE_EXTRA(rt->u.dst.dev, pad);
	mtu -= pad;

	/*
	 *	Fragment the datagram.
	 */

	offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
	not_last_frag = iph->frag_off & htons(IP_MF);

	/*
	 *	Keep copying data until we run out.
	 */

	while (left > 0) {
		len = left;
		/* IF: it doesn't fit, use 'mtu' - the data space left */
		if (len > mtu)
			len = mtu;
		/* IF: we are not sending upto and including the packet end
		   then align the next start on an eight byte boundary */
		if (len < left)	{
			len &= ~7;
		}
		/*
		 *	Allocate buffer.
		 */

		if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
			NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
			err = -ENOMEM;
			goto fail;
		}

		/*
		 *	Set up data on packet
		 */

		ip_copy_metadata(skb2, skb);
		skb_reserve(skb2, ll_rs);
		skb_put(skb2, len + hlen);
		skb_reset_network_header(skb2);
		skb2->transport_header = skb2->network_header + hlen;

		/*
		 *	Charge the memory for the fragment to any owner
		 *	it might possess
		 */

		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);

		/*
		 *	Copy the packet header into the new buffer.
		 */

		skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);

		/*
		 *	Copy a block of the IP datagram.
		 */
		if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
			BUG();
		left -= len;

		/*
		 *	Fill in the new header fields.
		 */
		iph = ip_hdr(skb2);
		iph->frag_off = htons((offset >> 3));

		/* ANK: dirty, but effective trick. Upgrade options only if
		 * the segment to be fragmented was THE FIRST (otherwise,
		 * options are already fixed) and make it ONCE
		 * on the initial skb, so that all the following fragments
		 * will inherit fixed options.
		 */
		if (offset == 0)
			ip_options_fragment(skb);

		/*
		 *	Added AC : If we are fragmenting a fragment that's not the
		 *		   last fragment then keep MF on each bit
		 */
		if (left > 0 || not_last_frag)
			iph->frag_off |= htons(IP_MF);
		ptr += len;
		offset += len;

		/*
		 *	Put this fragment into the sending queue.
		 */
		iph->tot_len = htons(len + hlen);

		ip_send_check(iph);

		err = output(skb2);
		if (err)
			goto fail;

		IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
	}
	kfree_skb(skb);
	IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
	return err;

fail:
	kfree_skb(skb);
	IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
	return err;
}

EXPORT_SYMBOL(ip_fragment);

int
ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct iovec *iov = from;

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		if (memcpy_fromiovecend(to, iov, offset, len) < 0)
			return -EFAULT;
	} else {
		__wsum csum = 0;
		if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
			return -EFAULT;
		skb->csum = csum_block_add(skb->csum, csum, odd);
	}
	return 0;
}

static inline __wsum
csum_page(struct page *page, int offset, int copy)
{
	char *kaddr;
	__wsum csum;
	kaddr = kmap(page);
	csum = csum_partial(kaddr + offset, copy, 0);
	kunmap(page);
	return csum;
}

static inline int ip_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 fragmentation 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 err;

		/* 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;
		sk->sk_sndmsg_off = 0;
	}

	err = skb_append_datato_frags(sk,skb, getfrag, from,
			       (length - transhdrlen));
	if (!err) {
		/* specify the length of each IP datagram fragment*/
		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
		__skb_queue_tail(&sk->sk_write_queue, skb);

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

/*
 *	ip_append_data() and ip_append_page() can make one large IP datagram
 *	from many pieces of data. Each pieces will be holded on the socket
 *	until ip_push_pending_frames() is called. Each piece can be a page
 *	or non-page data.
 *
 *	Not only UDP, other transport protocols - e.g. raw sockets - can use
 *	this interface potentially.
 *
 *	LATER: length must be adjusted by pad at tail, when it is required.
 */
int ip_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,
		   struct ipcm_cookie *ipc, struct rtable *rt,
		   unsigned int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sk_buff *skb;

	struct ip_options *opt = NULL;
	int hh_len;
	int exthdrlen;
	int mtu;
	int copy;
	int err;
	int offset = 0;
	unsigned int maxfraglen, fragheaderlen;
	int csummode = CHECKSUM_NONE;

	if (flags&MSG_PROBE)
		return 0;

	if (skb_queue_empty(&sk->sk_write_queue)) {
		/*
		 * setup for corking.
		 */
		opt = ipc->opt;
		if (opt) {
			if (inet->cork.opt == NULL) {
				inet->cork.opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation);
				if (unlikely(inet->cork.opt == NULL))
					return -ENOBUFS;
			}
			memcpy(inet->cork.opt, opt, sizeof(struct ip_options)+opt->optlen);
			inet->cork.flags |= IPCORK_OPT;
			inet->cork.addr = ipc->addr;
		}
		dst_hold(&rt->u.dst);
		inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
					    rt->u.dst.dev->mtu :
					    dst_mtu(rt->u.dst.path);
		inet->cork.rt = rt;
		inet->cork.length = 0;
		sk->sk_sndmsg_page = NULL;
		sk->sk_sndmsg_off = 0;
		if ((exthdrlen = rt->u.dst.header_len) != 0) {
			length += exthdrlen;
			transhdrlen += exthdrlen;
		}
	} else {
		rt = inet->cork.rt;
		if (inet->cork.flags & IPCORK_OPT)
			opt = inet->cork.opt;

		transhdrlen = 0;
		exthdrlen = 0;
		mtu = inet->cork.fragsize;
	}
	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);

	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;

	if (inet->cork.length + length > 0xFFFF - fragheaderlen) {
		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu-exthdrlen);
		return -EMSGSIZE;
	}

	/*
	 * transhdrlen > 0 means that this is the first fragment and we wish
	 * it won't be fragmented in the future.
	 */
	if (transhdrlen &&
	    length + fragheaderlen <= mtu &&
	    rt->u.dst.dev->features & NETIF_F_V4_CSUM &&
	    !exthdrlen)
		csummode = CHECKSUM_PARTIAL;

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

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

	/* So, what's going on in the loop below?
	 *
	 * We use calculated fragment length to generate chained skb,
	 * each of segments is IP fragment ready for sending to network after
	 * adding appropriate IP header.
	 */

	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 = mtu - 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;
			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 > mtu - 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, with MSG_MORE we overallocate on fragments,
			 * because we have no idea what fragment will be
			 * the last.
			 */
			if (datalen == length + fraggap)
				alloclen += rt->u.dst.trailer_len;

			if (transhdrlen) {
				skb = sock_alloc_send_skb(sk,
						alloclen + hh_len + 15,
						(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 + 15, 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;
			skb_reserve(skb, hh_len);

			/*
			 *	Find where to start putting bytes.
			 */
			data = skb_put(skb, fraglen);
			skb_set_network_header(skb, exthdrlen);
			skb->transport_header = (skb->network_header +
						 fragheaderlen);
			data += fragheaderlen;

			if (fraggap) {
				skb->csum = skb_copy_and_csum_bits(
					skb_prev, maxfraglen,