netback.c

	int nr_frags = shinfo->nr_frags;
	int i, err, start;
	u16 peek; /* peek into next tx request */

	/* Check status of header. */
	err = gop->status;
	if (unlikely(err))
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);

	/* Skip first skb fragment if it is on same page as header fragment. */
	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	for (i = start; i < nr_frags; i++) {
		int j, newerr;
		pending_ring_idx_t head;

		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
		tx_info = &vif->pending_tx_info[pending_idx];
		head = tx_info->head;

		/* Check error status: if okay then remember grant handle. */
		do {
			newerr = (++gop)->status;
			if (newerr)
				break;
			peek = vif->pending_ring[pending_index(++head)];
		} while (!pending_tx_is_head(vif, peek));

		if (likely(!newerr)) {
			/* Had a previous error? Invalidate this fragment. */
			if (unlikely(err))
				xenvif_idx_release(vif, pending_idx,
						   XEN_NETIF_RSP_OKAY);
			continue;
		}

		/* Error on this fragment: respond to client with an error. */
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);

		/* Not the first error? Preceding frags already invalidated. */
		if (err)
			continue;

		/* First error: invalidate header and preceding fragments. */
		pending_idx = *((u16 *)skb->data);
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
		for (j = start; j < i; j++) {
			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
			xenvif_idx_release(vif, pending_idx,
					   XEN_NETIF_RSP_OKAY);
		}

		/* Remember the error: invalidate all subsequent fragments. */
		err = newerr;
	}

	*gopp = gop + 1;
	return err;
}

static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	int i;

	for (i = 0; i < nr_frags; i++) {
		skb_frag_t *frag = shinfo->frags + i;
		struct xen_netif_tx_request *txp;
		struct page *page;
		u16 pending_idx;

		pending_idx = frag_get_pending_idx(frag);

		txp = &vif->pending_tx_info[pending_idx].req;
		page = virt_to_page(idx_to_kaddr(vif, pending_idx));
		__skb_fill_page_desc(skb, i, page, txp->offset, txp->size);
		skb->len += txp->size;
		skb->data_len += txp->size;
		skb->truesize += txp->size;

		/* Take an extra reference to offset xenvif_idx_release */
		get_page(vif->mmap_pages[pending_idx]);
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
	}
}

static int xenvif_get_extras(struct xenvif *vif,
				struct xen_netif_extra_info *extras,
				int work_to_do)
{
	struct xen_netif_extra_info extra;
	RING_IDX cons = vif->tx.req_cons;

	do {
		if (unlikely(work_to_do-- <= 0)) {
			netdev_err(vif->dev, "Missing extra info\n");
			xenvif_fatal_tx_err(vif);
			return -EBADR;
		}

		memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
		       sizeof(extra));
		if (unlikely(!extra.type ||
			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
			vif->tx.req_cons = ++cons;
			netdev_err(vif->dev,
				   "Invalid extra type: %d\n", extra.type);
			xenvif_fatal_tx_err(vif);
			return -EINVAL;
		}

		memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
		vif->tx.req_cons = ++cons;
	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);

	return work_to_do;
}

static int xenvif_set_skb_gso(struct xenvif *vif,
			      struct sk_buff *skb,
			      struct xen_netif_extra_info *gso)
{
	if (!gso->u.gso.size) {
		netdev_err(vif->dev, "GSO size must not be zero.\n");
		xenvif_fatal_tx_err(vif);
		return -EINVAL;
	}

	switch (gso->u.gso.type) {
	case XEN_NETIF_GSO_TYPE_TCPV4:
		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
		break;
	case XEN_NETIF_GSO_TYPE_TCPV6:
		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
		break;
	default:
		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
		xenvif_fatal_tx_err(vif);
		return -EINVAL;
	}

	skb_shinfo(skb)->gso_size = gso->u.gso.size;

	/* Header must be checked, and gso_segs computed. */
	skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
	skb_shinfo(skb)->gso_segs = 0;

	return 0;
}

static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len,
				  unsigned int max)
{
	if (skb_headlen(skb) >= len)
		return 0;

	/* If we need to pullup then pullup to the max, so we
	 * won't need to do it again.
	 */
	if (max > skb->len)
		max = skb->len;

	if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
		return -ENOMEM;

	if (skb_headlen(skb) < len)
		return -EPROTO;

	return 0;
}

/* This value should be large enough to cover a tagged ethernet header plus
 * maximally sized IP and TCP or UDP headers.
 */
#define MAX_IP_HDR_LEN 128

static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
			     int recalculate_partial_csum)
{
	unsigned int off;
	bool fragment;
	int err;

	fragment = false;

	err = maybe_pull_tail(skb,
			      sizeof(struct iphdr),
			      MAX_IP_HDR_LEN);
	if (err < 0)
		goto out;

	if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
		fragment = true;

	off = ip_hdrlen(skb);

	err = -EPROTO;

	switch (ip_hdr(skb)->protocol) {
	case IPPROTO_TCP:
		err = maybe_pull_tail(skb,
				      off + sizeof(struct tcphdr),
				      MAX_IP_HDR_LEN);
		if (err < 0)
			goto out;

		if (!skb_partial_csum_set(skb, off,
					  offsetof(struct tcphdr, check)))
			goto out;

		if (recalculate_partial_csum)
			tcp_hdr(skb)->check =
				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
						   ip_hdr(skb)->daddr,
						   skb->len - off,
						   IPPROTO_TCP, 0);
		break;
	case IPPROTO_UDP:
		err = maybe_pull_tail(skb,
				      off + sizeof(struct udphdr),
				      MAX_IP_HDR_LEN);
		if (err < 0)
			goto out;

		if (!skb_partial_csum_set(skb, off,
					  offsetof(struct udphdr, check)))
			goto out;

		if (recalculate_partial_csum)
			udp_hdr(skb)->check =
				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
						   ip_hdr(skb)->daddr,
						   skb->len - off,
						   IPPROTO_UDP, 0);
		break;
	default:
		goto out;
	}

	err = 0;

out:
	return err;
}

/* This value should be large enough to cover a tagged ethernet header plus
 * an IPv6 header, all options, and a maximal TCP or UDP header.
 */
#define MAX_IPV6_HDR_LEN 256

#define OPT_HDR(type, skb, off) \
	(type *)(skb_network_header(skb) + (off))

static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
			       int recalculate_partial_csum)
{
	int err;
	u8 nexthdr;
	unsigned int off;
	unsigned int len;
	bool fragment;
	bool done;

	fragment = false;
	done = false;

	off = sizeof(struct ipv6hdr);

	err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
	if (err < 0)
		goto out;

	nexthdr = ipv6_hdr(skb)->nexthdr;

	len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
	while (off <= len && !done) {
		switch (nexthdr) {
		case IPPROTO_DSTOPTS:
		case IPPROTO_HOPOPTS:
		case IPPROTO_ROUTING: {
			struct ipv6_opt_hdr *hp;

			err = maybe_pull_tail(skb,
					      off +
					      sizeof(struct ipv6_opt_hdr),
					      MAX_IPV6_HDR_LEN);
			if (err < 0)
				goto out;

			hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
			nexthdr = hp->nexthdr;
			off += ipv6_optlen(hp);
			break;
		}
		case IPPROTO_AH: {
			struct ip_auth_hdr *hp;

			err = maybe_pull_tail(skb,
					      off +
					      sizeof(struct ip_auth_hdr),
					      MAX_IPV6_HDR_LEN);
			if (err < 0)
				goto out;

			hp = OPT_HDR(struct ip_auth_hdr, skb, off);
			nexthdr = hp->nexthdr;
			off += ipv6_authlen(hp);
			break;
		}
		case IPPROTO_FRAGMENT: {
			struct frag_hdr *hp;

			err = maybe_pull_tail(skb,
					      off +
					      sizeof(struct frag_hdr),
					      MAX_IPV6_HDR_LEN);
			if (err < 0)
				goto out;

			hp = OPT_HDR(struct frag_hdr, skb, off);

			if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
				fragment = true;

			nexthdr = hp->nexthdr;
			off += sizeof(struct frag_hdr);
			break;
		}
		default:
			done = true;
			break;
		}
	}

	err = -EPROTO;

	if (!done || fragment)
		goto out;

	switch (nexthdr) {
	case IPPROTO_TCP:
		err = maybe_pull_tail(skb,
				      off + sizeof(struct tcphdr),
				      MAX_IPV6_HDR_LEN);
		if (err < 0)
			goto out;

		if (!skb_partial_csum_set(skb, off,
					  offsetof(struct tcphdr, check)))
			goto out;

		if (recalculate_partial_csum)
			tcp_hdr(skb)->check =
				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
						 &ipv6_hdr(skb)->daddr,
						 skb->len - off,
						 IPPROTO_TCP, 0);
		break;
	case IPPROTO_UDP:
		err = maybe_pull_tail(skb,
				      off + sizeof(struct udphdr),
				      MAX_IPV6_HDR_LEN);
		if (err < 0)
			goto out;

		if (!skb_partial_csum_set(skb, off,
					  offsetof(struct udphdr, check)))
			goto out;

		if (recalculate_partial_csum)
			udp_hdr(skb)->check =
				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
						 &ipv6_hdr(skb)->daddr,
						 skb->len - off,
						 IPPROTO_UDP, 0);
		break;
	default:
		goto out;
	}

	err = 0;

out:
	return err;
}

static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
{
	int err = -EPROTO;
	int recalculate_partial_csum = 0;

	/* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
	 * peers can fail to set NETRXF_csum_blank when sending a GSO
	 * frame. In this case force the SKB to CHECKSUM_PARTIAL and
	 * recalculate the partial checksum.
	 */
	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
		vif->rx_gso_checksum_fixup++;
		skb->ip_summed = CHECKSUM_PARTIAL;
		recalculate_partial_csum = 1;
	}

	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	if (skb->protocol == htons(ETH_P_IP))
		err = checksum_setup_ip(vif, skb, recalculate_partial_csum);
	else if (skb->protocol == htons(ETH_P_IPV6))
		err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum);

	return err;
}

static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
{
	u64 now = get_jiffies_64();
	u64 next_credit = vif->credit_window_start +
		msecs_to_jiffies(vif->credit_usec / 1000);

	/* Timer could already be pending in rare cases. */
	if (timer_pending(&vif->credit_timeout))
		return true;

	/* Passed the point where we can replenish credit? */
	if (time_after_eq64(now, next_credit)) {
		vif->credit_window_start = now;
		tx_add_credit(vif);
	}

	/* Still too big to send right now? Set a callback. */
	if (size > vif->remaining_credit) {
		vif->credit_timeout.data     =
			(unsigned long)vif;
		vif->credit_timeout.function =
			tx_credit_callback;
		mod_timer(&vif->credit_timeout,
			  next_credit);
		vif->credit_window_start = next_credit;

		return true;
	}

	return false;
}

static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
{
	struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop;
	struct sk_buff *skb;
	int ret;

	while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX
		< MAX_PENDING_REQS) &&
	       (skb_queue_len(&vif->tx_queue) < budget)) {
		struct xen_netif_tx_request txreq;
		struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX];
		struct page *page;
		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
		u16 pending_idx;
		RING_IDX idx;
		int work_to_do;
		unsigned int data_len;
		pending_ring_idx_t index;

		if (vif->tx.sring->req_prod - vif->tx.req_cons >
		    XEN_NETIF_TX_RING_SIZE) {
			netdev_err(vif->dev,
				   "Impossible number of requests. "
				   "req_prod %d, req_cons %d, size %ld\n",
				   vif->tx.sring->req_prod, vif->tx.req_cons,
				   XEN_NETIF_TX_RING_SIZE);
			xenvif_fatal_tx_err(vif);
			continue;
		}

		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
		if (!work_to_do)
			break;

		idx = vif->tx.req_cons;
		rmb(); /* Ensure that we see the request before we copy it. */
		memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));

		/* Credit-based scheduling. */
		if (txreq.size > vif->remaining_credit &&
		    tx_credit_exceeded(vif, txreq.size))
			break;

		vif->remaining_credit -= txreq.size;

		work_to_do--;
		vif->tx.req_cons = ++idx;

		memset(extras, 0, sizeof(extras));
		if (txreq.flags & XEN_NETTXF_extra_info) {
			work_to_do = xenvif_get_extras(vif, extras,
						       work_to_do);
			idx = vif->tx.req_cons;
			if (unlikely(work_to_do < 0))
				break;
		}

		ret = xenvif_count_requests(vif, &txreq, txfrags, work_to_do);
		if (unlikely(ret < 0))
			break;

		idx += ret;

		if (unlikely(txreq.size < ETH_HLEN)) {
			netdev_dbg(vif->dev,
				   "Bad packet size: %d\n", txreq.size);
			xenvif_tx_err(vif, &txreq, idx);
			break;
		}

		/* No crossing a page as the payload mustn't fragment. */
		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
			netdev_err(vif->dev,
				   "txreq.offset: %x, size: %u, end: %lu\n",
				   txreq.offset, txreq.size,
				   (txreq.offset&~PAGE_MASK) + txreq.size);
			xenvif_fatal_tx_err(vif);
			break;
		}

		index = pending_index(vif->pending_cons);
		pending_idx = vif->pending_ring[index];

		data_len = (txreq.size > PKT_PROT_LEN &&
			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
			PKT_PROT_LEN : txreq.size;

		skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,
				GFP_ATOMIC | __GFP_NOWARN);
		if (unlikely(skb == NULL)) {
			netdev_dbg(vif->dev,
				   "Can't allocate a skb in start_xmit.\n");
			xenvif_tx_err(vif, &txreq, idx);
			break;
		}

		/* Packets passed to netif_rx() must have some headroom. */
		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);

		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
			struct xen_netif_extra_info *gso;
			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];

			if (xenvif_set_skb_gso(vif, skb, gso)) {
				/* Failure in xenvif_set_skb_gso is fatal. */
				kfree_skb(skb);
				break;
			}
		}

		/* XXX could copy straight to head */
		page = xenvif_alloc_page(vif, pending_idx);
		if (!page) {
			kfree_skb(skb);
			xenvif_tx_err(vif, &txreq, idx);
			break;
		}

		gop->source.u.ref = txreq.gref;
		gop->source.domid = vif->domid;
		gop->source.offset = txreq.offset;

		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
		gop->dest.domid = DOMID_SELF;
		gop->dest.offset = txreq.offset;

		gop->len = txreq.size;
		gop->flags = GNTCOPY_source_gref;

		gop++;

		memcpy(&vif->pending_tx_info[pending_idx].req,
		       &txreq, sizeof(txreq));
		vif->pending_tx_info[pending_idx].head = index;
		*((u16 *)skb->data) = pending_idx;

		__skb_put(skb, data_len);

		skb_shinfo(skb)->nr_frags = ret;
		if (data_len < txreq.size) {
			skb_shinfo(skb)->nr_frags++;
			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
					     pending_idx);
		} else {
			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
					     INVALID_PENDING_IDX);
		}

		vif->pending_cons++;

		request_gop = xenvif_get_requests(vif, skb, txfrags, gop);
		if (request_gop == NULL) {
			kfree_skb(skb);
			xenvif_tx_err(vif, &txreq, idx);
			break;
		}
		gop = request_gop;

		__skb_queue_tail(&vif->tx_queue, skb);

		vif->tx.req_cons = idx;

		if ((gop-vif->tx_copy_ops) >= ARRAY_SIZE(vif->tx_copy_ops))
			break;
	}

	return gop - vif->tx_copy_ops;
}


static int xenvif_tx_submit(struct xenvif *vif)
{
	struct gnttab_copy *gop = vif->tx_copy_ops;
	struct sk_buff *skb;
	int work_done = 0;

	while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) {
		struct xen_netif_tx_request *txp;
		u16 pending_idx;
		unsigned data_len;

		pending_idx = *((u16 *)skb->data);
		txp = &vif->pending_tx_info[pending_idx].req;

		/* Check the remap error code. */
		if (unlikely(xenvif_tx_check_gop(vif, skb, &gop))) {
			netdev_dbg(vif->dev, "netback grant failed.\n");
			skb_shinfo(skb)->nr_frags = 0;
			kfree_skb(skb);
			continue;
		}

		data_len = skb->len;
		memcpy(skb->data,
		       (void *)(idx_to_kaddr(vif, pending_idx)|txp->offset),
		       data_len);
		if (data_len < txp->size) {
			/* Append the packet payload as a fragment. */
			txp->offset += data_len;
			txp->size -= data_len;
		} else {
			/* Schedule a response immediately. */
			xenvif_idx_release(vif, pending_idx,
					   XEN_NETIF_RSP_OKAY);
		}

		if (txp->flags & XEN_NETTXF_csum_blank)
			skb->ip_summed = CHECKSUM_PARTIAL;
		else if (txp->flags & XEN_NETTXF_data_validated)
			skb->ip_summed = CHECKSUM_UNNECESSARY;

		xenvif_fill_frags(vif, skb);

		if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) {
			int target = min_t(int, skb->len, PKT_PROT_LEN);
			__pskb_pull_tail(skb, target - skb_headlen(skb));
		}

		skb->dev      = vif->dev;
		skb->protocol = eth_type_trans(skb, skb->dev);
		skb_reset_network_header(skb);

		if (checksum_setup(vif, skb)) {
			netdev_dbg(vif->dev,
				   "Can't setup checksum in net_tx_action\n");
			kfree_skb(skb);
			continue;
		}

		skb_probe_transport_header(skb, 0);

		vif->dev->stats.rx_bytes += skb->len;
		vif->dev->stats.rx_packets++;

		work_done++;

		netif_receive_skb(skb);
	}

	return work_done;
}

/* Called after netfront has transmitted */
int xenvif_tx_action(struct xenvif *vif, int budget)
{
	unsigned nr_gops;
	int work_done;

	if (unlikely(!tx_work_todo(vif)))
		return 0;

	nr_gops = xenvif_tx_build_gops(vif, budget);

	if (nr_gops == 0)
		return 0;

	gnttab_batch_copy(vif->tx_copy_ops, nr_gops);

	work_done = xenvif_tx_submit(vif);

	return work_done;
}

static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
			       u8 status)
{
	struct pending_tx_info *pending_tx_info;
	pending_ring_idx_t head;
	u16 peek; /* peek into next tx request */

	BUG_ON(vif->mmap_pages[pending_idx] == (void *)(~0UL));

	/* Already complete? */
	if (vif->mmap_pages[pending_idx] == NULL)
		return;

	pending_tx_info = &vif->pending_tx_info[pending_idx];

	head = pending_tx_info->head;

	BUG_ON(!pending_tx_is_head(vif, head));
	BUG_ON(vif->pending_ring[pending_index(head)] != pending_idx);

	do {
		pending_ring_idx_t index;
		pending_ring_idx_t idx = pending_index(head);
		u16 info_idx = vif->pending_ring[idx];

		pending_tx_info = &vif->pending_tx_info[info_idx];
		make_tx_response(vif, &pending_tx_info->req, status);

		/* Setting any number other than
		 * INVALID_PENDING_RING_IDX indicates this slot is
		 * starting a new packet / ending a previous packet.
		 */
		pending_tx_info->head = 0;

		index = pending_index(vif->pending_prod++);
		vif->pending_ring[index] = vif->pending_ring[info_idx];

		peek = vif->pending_ring[pending_index(++head)];

	} while (!pending_tx_is_head(vif, peek));

	put_page(vif->mmap_pages[pending_idx]);
	vif->mmap_pages[pending_idx] = NULL;
}


static void make_tx_response(struct xenvif *vif,
			     struct xen_netif_tx_request *txp,
			     s8       st)
{
	RING_IDX i = vif->tx.rsp_prod_pvt;
	struct xen_netif_tx_response *resp;
	int notify;

	resp = RING_GET_RESPONSE(&vif->tx, i);
	resp->id     = txp->id;
	resp->status = st;

	if (txp->flags & XEN_NETTXF_extra_info)
		RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL;

	vif->tx.rsp_prod_pvt = ++i;
	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
	if (notify)
		notify_remote_via_irq(vif->tx_irq);
}

static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
					     u16      id,
					     s8       st,
					     u16      offset,
					     u16      size,
					     u16      flags)
{
	RING_IDX i = vif->rx.rsp_prod_pvt;
	struct xen_netif_rx_response *resp;

	resp = RING_GET_RESPONSE(&vif->rx, i);
	resp->offset     = offset;
	resp->flags      = flags;
	resp->id         = id;
	resp->status     = (s16)size;
	if (st < 0)
		resp->status = (s16)st;

	vif->rx.rsp_prod_pvt = ++i;

	return resp;
}

static inline int rx_work_todo(struct xenvif *vif)
{
	return !skb_queue_empty(&vif->rx_queue);
}

static inline int tx_work_todo(struct xenvif *vif)
{

	if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) &&
	    (nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX
	     < MAX_PENDING_REQS))
		return 1;

	return 0;
}

void xenvif_unmap_frontend_rings(struct xenvif *vif)
{
	if (vif->tx.sring)
		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
					vif->tx.sring);
	if (vif->rx.sring)
		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
					vif->rx.sring);
}

int xenvif_map_frontend_rings(struct xenvif *vif,
			      grant_ref_t tx_ring_ref,
			      grant_ref_t rx_ring_ref)
{
	void *addr;
	struct xen_netif_tx_sring *txs;
	struct xen_netif_rx_sring *rxs;

	int err = -ENOMEM;

	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
				     tx_ring_ref, &addr);
	if (err)
		goto err;

	txs = (struct xen_netif_tx_sring *)addr;
	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);

	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
				     rx_ring_ref, &addr);
	if (err)
		goto err;

	rxs = (struct xen_netif_rx_sring *)addr;
	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);

	vif->rx_req_cons_peek = 0;

	return 0;

err:
	xenvif_unmap_frontend_rings(vif);
	return err;
}

int xenvif_kthread(void *data)
{
	struct xenvif *vif = data;

	while (!kthread_should_stop()) {
		wait_event_interruptible(vif->wq,
					 rx_work_todo(vif) ||
					 kthread_should_stop());
		if (kthread_should_stop())
			break;

		if (rx_work_todo(vif))
			xenvif_rx_action(vif);

		cond_resched();
	}

	return 0;
}

static int __init netback_init(void)
{
	int rc = 0;

	if (!xen_domain())
		return -ENODEV;

	if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
		pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
			fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX);
		fatal_skb_slots = XEN_NETBK_LEGACY_SLOTS_MAX;
	}

	rc = xenvif_xenbus_init();
	if (rc)
		goto failed_init;

	return 0;

failed_init:
	return rc;
}

module_init(netback_init);

static void __exit netback_fini(void)
{
	xenvif_xenbus_fini();
}
module_exit(netback_fini);

MODULE_LICENSE("Dual BSD/GPL");
MODULE_ALIAS("xen-backend:vif");