xen-netfront.c

linux 内核源代码

			err = -EINVAL;
		} else {
			memcpy(&extras[extra->type - 1], extra,
			       sizeof(*extra));
		}

		skb = xennet_get_rx_skb(np, cons);
		ref = xennet_get_rx_ref(np, cons);
		xennet_move_rx_slot(np, skb, ref);
	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);

	np->rx.rsp_cons = cons;
	return err;
}

static int xennet_get_responses(struct netfront_info *np,
				struct netfront_rx_info *rinfo, RING_IDX rp,
				struct sk_buff_head *list)
{
	struct xen_netif_rx_response *rx = &rinfo->rx;
	struct xen_netif_extra_info *extras = rinfo->extras;
	struct device *dev = &np->netdev->dev;
	RING_IDX cons = np->rx.rsp_cons;
	struct sk_buff *skb = xennet_get_rx_skb(np, cons);
	grant_ref_t ref = xennet_get_rx_ref(np, cons);
	int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
	int frags = 1;
	int err = 0;
	unsigned long ret;

	if (rx->flags & NETRXF_extra_info) {
		err = xennet_get_extras(np, extras, rp);
		cons = np->rx.rsp_cons;
	}

	for (;;) {
		if (unlikely(rx->status < 0 ||
			     rx->offset + rx->status > PAGE_SIZE)) {
			if (net_ratelimit())
				dev_warn(dev, "rx->offset: %x, size: %u\n",
					 rx->offset, rx->status);
			xennet_move_rx_slot(np, skb, ref);
			err = -EINVAL;
			goto next;
		}

		/*
		 * This definitely indicates a bug, either in this driver or in
		 * the backend driver. In future this should flag the bad
		 * situation to the system controller to reboot the backed.
		 */
		if (ref == GRANT_INVALID_REF) {
			if (net_ratelimit())
				dev_warn(dev, "Bad rx response id %d.\n",
					 rx->id);
			err = -EINVAL;
			goto next;
		}

		ret = gnttab_end_foreign_access_ref(ref, 0);
		BUG_ON(!ret);

		gnttab_release_grant_reference(&np->gref_rx_head, ref);

		__skb_queue_tail(list, skb);

next:
		if (!(rx->flags & NETRXF_more_data))
			break;

		if (cons + frags == rp) {
			if (net_ratelimit())
				dev_warn(dev, "Need more frags\n");
			err = -ENOENT;
			break;
		}

		rx = RING_GET_RESPONSE(&np->rx, cons + frags);
		skb = xennet_get_rx_skb(np, cons + frags);
		ref = xennet_get_rx_ref(np, cons + frags);
		frags++;
	}

	if (unlikely(frags > max)) {
		if (net_ratelimit())
			dev_warn(dev, "Too many frags\n");
		err = -E2BIG;
	}

	if (unlikely(err))
		np->rx.rsp_cons = cons + frags;

	return err;
}

static int xennet_set_skb_gso(struct sk_buff *skb,
			      struct xen_netif_extra_info *gso)
{
	if (!gso->u.gso.size) {
		if (net_ratelimit())
			printk(KERN_WARNING "GSO size must not be zero.\n");
		return -EINVAL;
	}

	/* Currently only TCPv4 S.O. is supported. */
	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
		if (net_ratelimit())
			printk(KERN_WARNING "Bad GSO type %d.\n", gso->u.gso.type);
		return -EINVAL;
	}

	skb_shinfo(skb)->gso_size = gso->u.gso.size;
	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;

	/* 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 RING_IDX xennet_fill_frags(struct netfront_info *np,
				  struct sk_buff *skb,
				  struct sk_buff_head *list)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	RING_IDX cons = np->rx.rsp_cons;
	skb_frag_t *frag = shinfo->frags + nr_frags;
	struct sk_buff *nskb;

	while ((nskb = __skb_dequeue(list))) {
		struct xen_netif_rx_response *rx =
			RING_GET_RESPONSE(&np->rx, ++cons);

		frag->page = skb_shinfo(nskb)->frags[0].page;
		frag->page_offset = rx->offset;
		frag->size = rx->status;

		skb->data_len += rx->status;

		skb_shinfo(nskb)->nr_frags = 0;
		kfree_skb(nskb);

		frag++;
		nr_frags++;
	}

	shinfo->nr_frags = nr_frags;
	return cons;
}

static int skb_checksum_setup(struct sk_buff *skb)
{
	struct iphdr *iph;
	unsigned char *th;
	int err = -EPROTO;

	if (skb->protocol != htons(ETH_P_IP))
		goto out;

	iph = (void *)skb->data;
	th = skb->data + 4 * iph->ihl;
	if (th >= skb_tail_pointer(skb))
		goto out;

	skb->csum_start = th - skb->head;
	switch (iph->protocol) {
	case IPPROTO_TCP:
		skb->csum_offset = offsetof(struct tcphdr, check);
		break;
	case IPPROTO_UDP:
		skb->csum_offset = offsetof(struct udphdr, check);
		break;
	default:
		if (net_ratelimit())
			printk(KERN_ERR "Attempting to checksum a non-"
			       "TCP/UDP packet, dropping a protocol"
			       " %d packet", iph->protocol);
		goto out;
	}

	if ((th + skb->csum_offset + 2) > skb_tail_pointer(skb))
		goto out;

	err = 0;

out:
	return err;
}

static int handle_incoming_queue(struct net_device *dev,
				 struct sk_buff_head *rxq)
{
	int packets_dropped = 0;
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(rxq)) != NULL) {
		struct page *page = NETFRONT_SKB_CB(skb)->page;
		void *vaddr = page_address(page);
		unsigned offset = NETFRONT_SKB_CB(skb)->offset;

		memcpy(skb->data, vaddr + offset,
		       skb_headlen(skb));

		if (page != skb_shinfo(skb)->frags[0].page)
			__free_page(page);

		/* Ethernet work: Delayed to here as it peeks the header. */
		skb->protocol = eth_type_trans(skb, dev);

		if (skb->ip_summed == CHECKSUM_PARTIAL) {
			if (skb_checksum_setup(skb)) {
				kfree_skb(skb);
				packets_dropped++;
				dev->stats.rx_errors++;
				continue;
			}
		}

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

		/* Pass it up. */
		netif_receive_skb(skb);
		dev->last_rx = jiffies;
	}

	return packets_dropped;
}

static int xennet_poll(struct napi_struct *napi, int budget)
{
	struct netfront_info *np = container_of(napi, struct netfront_info, napi);
	struct net_device *dev = np->netdev;
	struct sk_buff *skb;
	struct netfront_rx_info rinfo;
	struct xen_netif_rx_response *rx = &rinfo.rx;
	struct xen_netif_extra_info *extras = rinfo.extras;
	RING_IDX i, rp;
	int work_done;
	struct sk_buff_head rxq;
	struct sk_buff_head errq;
	struct sk_buff_head tmpq;
	unsigned long flags;
	unsigned int len;
	int err;

	spin_lock(&np->rx_lock);

	skb_queue_head_init(&rxq);
	skb_queue_head_init(&errq);
	skb_queue_head_init(&tmpq);

	rp = np->rx.sring->rsp_prod;
	rmb(); /* Ensure we see queued responses up to 'rp'. */

	i = np->rx.rsp_cons;
	work_done = 0;
	while ((i != rp) && (work_done < budget)) {
		memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx));
		memset(extras, 0, sizeof(rinfo.extras));

		err = xennet_get_responses(np, &rinfo, rp, &tmpq);

		if (unlikely(err)) {
err:
			while ((skb = __skb_dequeue(&tmpq)))
				__skb_queue_tail(&errq, skb);
			dev->stats.rx_errors++;
			i = np->rx.rsp_cons;
			continue;
		}

		skb = __skb_dequeue(&tmpq);

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

			if (unlikely(xennet_set_skb_gso(skb, gso))) {
				__skb_queue_head(&tmpq, skb);
				np->rx.rsp_cons += skb_queue_len(&tmpq);
				goto err;
			}
		}

		NETFRONT_SKB_CB(skb)->page = skb_shinfo(skb)->frags[0].page;
		NETFRONT_SKB_CB(skb)->offset = rx->offset;

		len = rx->status;
		if (len > RX_COPY_THRESHOLD)
			len = RX_COPY_THRESHOLD;
		skb_put(skb, len);

		if (rx->status > len) {
			skb_shinfo(skb)->frags[0].page_offset =
				rx->offset + len;
			skb_shinfo(skb)->frags[0].size = rx->status - len;
			skb->data_len = rx->status - len;
		} else {
			skb_shinfo(skb)->frags[0].page = NULL;
			skb_shinfo(skb)->nr_frags = 0;
		}

		i = xennet_fill_frags(np, skb, &tmpq);

		/*
		 * Truesize approximates the size of true data plus
		 * any supervisor overheads. Adding hypervisor
		 * overheads has been shown to significantly reduce
		 * achievable bandwidth with the default receive
		 * buffer size. It is therefore not wise to account
		 * for it here.
		 *
		 * After alloc_skb(RX_COPY_THRESHOLD), truesize is set
		 * to RX_COPY_THRESHOLD + the supervisor
		 * overheads. Here, we add the size of the data pulled
		 * in xennet_fill_frags().
		 *
		 * We also adjust for any unused space in the main
		 * data area by subtracting (RX_COPY_THRESHOLD -
		 * len). This is especially important with drivers
		 * which split incoming packets into header and data,
		 * using only 66 bytes of the main data area (see the
		 * e1000 driver for example.)  On such systems,
		 * without this last adjustement, our achievable
		 * receive throughout using the standard receive
		 * buffer size was cut by 25%(!!!).
		 */
		skb->truesize += skb->data_len - (RX_COPY_THRESHOLD - len);
		skb->len += skb->data_len;

		if (rx->flags & NETRXF_csum_blank)
			skb->ip_summed = CHECKSUM_PARTIAL;
		else if (rx->flags & NETRXF_data_validated)
			skb->ip_summed = CHECKSUM_UNNECESSARY;

		__skb_queue_tail(&rxq, skb);

		np->rx.rsp_cons = ++i;
		work_done++;
	}

	while ((skb = __skb_dequeue(&errq)))
		kfree_skb(skb);

	work_done -= handle_incoming_queue(dev, &rxq);

	/* If we get a callback with very few responses, reduce fill target. */
	/* NB. Note exponential increase, linear decrease. */
	if (((np->rx.req_prod_pvt - np->rx.sring->rsp_prod) >
	     ((3*np->rx_target) / 4)) &&
	    (--np->rx_target < np->rx_min_target))
		np->rx_target = np->rx_min_target;

	xennet_alloc_rx_buffers(dev);

	if (work_done < budget) {
		int more_to_do = 0;

		local_irq_save(flags);

		RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do);
		if (!more_to_do)
			__netif_rx_complete(dev, napi);

		local_irq_restore(flags);
	}

	spin_unlock(&np->rx_lock);

	return work_done;
}

static int xennet_change_mtu(struct net_device *dev, int mtu)
{
	int max = xennet_can_sg(dev) ? 65535 - ETH_HLEN : ETH_DATA_LEN;

	if (mtu > max)
		return -EINVAL;
	dev->mtu = mtu;
	return 0;
}

static void xennet_release_tx_bufs(struct netfront_info *np)
{
	struct sk_buff *skb;
	int i;

	for (i = 0; i < NET_TX_RING_SIZE; i++) {
		/* Skip over entries which are actually freelist references */
		if ((unsigned long)np->tx_skbs[i].skb < PAGE_OFFSET)
			continue;

		skb = np->tx_skbs[i].skb;
		gnttab_end_foreign_access_ref(np->grant_tx_ref[i],
					      GNTMAP_readonly);
		gnttab_release_grant_reference(&np->gref_tx_head,
					       np->grant_tx_ref[i]);
		np->grant_tx_ref[i] = GRANT_INVALID_REF;
		add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
		dev_kfree_skb_irq(skb);
	}
}

static void xennet_release_rx_bufs(struct netfront_info *np)
{
	struct mmu_update      *mmu = np->rx_mmu;
	struct multicall_entry *mcl = np->rx_mcl;
	struct sk_buff_head free_list;
	struct sk_buff *skb;
	unsigned long mfn;
	int xfer = 0, noxfer = 0, unused = 0;
	int id, ref;

	dev_warn(&np->netdev->dev, "%s: fix me for copying receiver.\n",
			 __func__);
	return;

	skb_queue_head_init(&free_list);

	spin_lock_bh(&np->rx_lock);

	for (id = 0; id < NET_RX_RING_SIZE; id++) {
		ref = np->grant_rx_ref[id];
		if (ref == GRANT_INVALID_REF) {
			unused++;
			continue;
		}

		skb = np->rx_skbs[id];
		mfn = gnttab_end_foreign_transfer_ref(ref);
		gnttab_release_grant_reference(&np->gref_rx_head, ref);
		np->grant_rx_ref[id] = GRANT_INVALID_REF;

		if (0 == mfn) {
			skb_shinfo(skb)->nr_frags = 0;
			dev_kfree_skb(skb);
			noxfer++;
			continue;
		}

		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
			/* Remap the page. */
			struct page *page = skb_shinfo(skb)->frags[0].page;
			unsigned long pfn = page_to_pfn(page);
			void *vaddr = page_address(page);

			MULTI_update_va_mapping(mcl, (unsigned long)vaddr,
						mfn_pte(mfn, PAGE_KERNEL),
						0);
			mcl++;
			mmu->ptr = ((u64)mfn << PAGE_SHIFT)
				| MMU_MACHPHYS_UPDATE;
			mmu->val = pfn;
			mmu++;

			set_phys_to_machine(pfn, mfn);
		}
		__skb_queue_tail(&free_list, skb);
		xfer++;
	}

	dev_info(&np->netdev->dev, "%s: %d xfer, %d noxfer, %d unused\n",
		 __func__, xfer, noxfer, unused);

	if (xfer) {
		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
			/* Do all the remapping work and M2P updates. */
			MULTI_mmu_update(mcl, np->rx_mmu, mmu - np->rx_mmu,
					 0, DOMID_SELF);
			mcl++;
			HYPERVISOR_multicall(np->rx_mcl, mcl - np->rx_mcl);
		}
	}

	while ((skb = __skb_dequeue(&free_list)) != NULL)
		dev_kfree_skb(skb);

	spin_unlock_bh(&np->rx_lock);
}

static void xennet_uninit(struct net_device *dev)
{
	struct netfront_info *np = netdev_priv(dev);
	xennet_release_tx_bufs(np);
	xennet_release_rx_bufs(np);
	gnttab_free_grant_references(np->gref_tx_head);
	gnttab_free_grant_references(np->gref_rx_head);
}

static struct net_device * __devinit xennet_create_dev(struct xenbus_device *dev)
{
	int i, err;
	struct net_device *netdev;
	struct netfront_info *np;

	netdev = alloc_etherdev(sizeof(struct netfront_info));
	if (!netdev) {
		printk(KERN_WARNING "%s> alloc_etherdev failed.\n",
		       __func__);
		return ERR_PTR(-ENOMEM);
	}

	np                   = netdev_priv(netdev);
	np->xbdev            = dev;

	spin_lock_init(&np->tx_lock);
	spin_lock_init(&np->rx_lock);

	skb_queue_head_init(&np->rx_batch);
	np->rx_target     = RX_DFL_MIN_TARGET;
	np->rx_min_target = RX_DFL_MIN_TARGET;
	np->rx_max_target = RX_MAX_TARGET;

	init_timer(&np->rx_refill_timer);
	np->rx_refill_timer.data = (unsigned long)netdev;
	np->rx_refill_timer.function = rx_refill_timeout;

	/* Initialise tx_skbs as a free chain containing every entry. */
	np->tx_skb_freelist = 0;
	for (i = 0; i < NET_TX_RING_SIZE; i++) {
		np->tx_skbs[i].link = i+1;
		np->grant_tx_ref[i] = GRANT_INVALID_REF;
	}

	/* Clear out rx_skbs */
	for (i = 0; i < NET_RX_RING_SIZE; i++) {
		np->rx_skbs[i] = NULL;
		np->grant_rx_ref[i] = GRANT_INVALID_REF;
	}

	/* A grant for every tx ring slot */
	if (gnttab_alloc_grant_references(TX_MAX_TARGET,
					  &np->gref_tx_head) < 0) {
		printk(KERN_ALERT "#### netfront can't alloc tx grant refs\n");
		err = -ENOMEM;
		goto exit;
	}
	/* A grant for every rx ring slot */
	if (gnttab_alloc_grant_references(RX_MAX_TARGET,
					  &np->gref_rx_head) < 0) {
		printk(KERN_ALERT "#### netfront can't alloc rx grant refs\n");
		err = -ENOMEM;
		goto exit_free_tx;
	}

	netdev->open            = xennet_open;
	netdev->hard_start_xmit = xennet_start_xmit;
	netdev->stop            = xennet_close;
	netif_napi_add(netdev, &np->napi, xennet_poll, 64);
	netdev->uninit          = xennet_uninit;
	netdev->change_mtu	= xennet_change_mtu;
	netdev->features        = NETIF_F_IP_CSUM;

	SET_ETHTOOL_OPS(netdev, &xennet_ethtool_ops);
	SET_NETDEV_DEV(netdev, &dev->dev);

	np->netdev = netdev;

	netif_carrier_off(netdev);

	return netdev;

 exit_free_tx:
	gnttab_free_grant_references(np->gref_tx_head);
 exit:
	free_netdev(netdev);
	return ERR_PTR(err);
}

/**
 * Entry point to this code when a new device is created.  Allocate the basic
 * structures and the ring buffers for communication with the backend, and
 * inform the backend of the appropriate details for those.
 */
static int __devinit netfront_probe(struct xenbus_device *dev,
				    const struct xenbus_device_id *id)
{
	int err;
	struct net_device *netdev;
	struct netfront_info *info;

	netdev = xennet_create_dev(dev);
	if (IS_ERR(netdev)) {
		err = PTR_ERR(netdev);
		xenbus_dev_fatal(dev, err, "creating netdev");
		return err;
	}

	info = netdev_priv(netdev);
	dev->dev.driver_data = info;

	err = register_netdev(info->netdev);
	if (err) {
		printk(KERN_WARNING "%s: register_netdev err=%d\n",
		       __func__, err);
		goto fail;
	}

	err = xennet_sysfs_addif(info->netdev);
	if (err) {
		unregister_netdev(info->netdev);