1 files changed, 367 insertions, 118 deletions

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index f2d6b78d901d..64828de25d9a 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -47,11 +47,40 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 
+/* Provide an option to disable split event channels at load time as
+ * event channels are limited resource. Split event channels are
+ * enabled by default.
+ */
+bool separate_tx_rx_irq = 1;
+module_param(separate_tx_rx_irq, bool, 0644);
+
+/*
+ * This is the maximum slots a skb can have. If a guest sends a skb
+ * which exceeds this limit it is considered malicious.
+ */
+#define FATAL_SKB_SLOTS_DEFAULT 20
+static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
+module_param(fatal_skb_slots, uint, 0444);
+
+/*
+ * To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
+ * the maximum slots a valid packet can use. Now this value is defined
+ * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
+ * all backend.
+ */
+#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
+
+typedef unsigned int pending_ring_idx_t;
+#define INVALID_PENDING_RING_IDX (~0U)
+
 struct pending_tx_info {
-	struct xen_netif_tx_request req;
+	struct xen_netif_tx_request req; /* coalesced tx request */
 	struct xenvif *vif;
+	pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX
+				  * if it is head of one or more tx
+				  * reqs
+				  */
 };
-typedef unsigned int pending_ring_idx_t;
 
 struct netbk_rx_meta {
 	int id;
@@ -102,7 +131,11 @@ struct xen_netbk {
 	atomic_t netfront_count;
 
 	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
-	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];
+	/* Coalescing tx requests before copying makes number of grant
+	 * copy ops greater or equal to number of slots required. In
+	 * worst case a tx request consumes 2 gnttab_copy.
+	 */
+	struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS];
 
 	u16 pending_ring[MAX_PENDING_REQS];
 
@@ -118,6 +151,16 @@ struct xen_netbk {
 static struct xen_netbk *xen_netbk;
 static int xen_netbk_group_nr;
 
+/*
+ * If head != INVALID_PENDING_RING_IDX, it means this tx request is head of
+ * one or more merged tx requests, otherwise it is the continuation of
+ * previous tx request.
+ */
+static inline int pending_tx_is_head(struct xen_netbk *netbk, RING_IDX idx)
+{
+	return netbk->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX;
+}
+
 void xen_netbk_add_xenvif(struct xenvif *vif)
 {
 	int i;
@@ -147,7 +190,8 @@ void xen_netbk_remove_xenvif(struct xenvif *vif)
 	atomic_dec(&netbk->netfront_count);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status);
 static void make_tx_response(struct xenvif *vif,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
@@ -249,6 +293,7 @@ static int max_required_rx_slots(struct xenvif *vif)
 {
 	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);
 
+	/* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */
 	if (vif->can_sg || vif->gso || vif->gso_prefix)
 		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */
 
@@ -624,7 +669,7 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 {
 	struct xenvif *vif = NULL, *tmp;
 	s8 status;
-	u16 irq, flags;
+	u16 flags;
 	struct xen_netif_rx_response *resp;
 	struct sk_buff_head rxq;
 	struct sk_buff *skb;
@@ -656,6 +701,7 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 		__skb_queue_tail(&rxq, skb);
 
 		/* Filled the batch queue? */
+		/* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */
 		if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE)
 			break;
 	}
@@ -732,20 +778,21 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 					 sco->meta_slots_used);
 
 		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
-		irq = vif->irq;
-		if (ret && list_empty(&vif->notify_list))
-			list_add_tail(&vif->notify_list, &notify);
 
 		xenvif_notify_tx_completion(vif);
 
-		xenvif_put(vif);
+		if (ret && list_empty(&vif->notify_list))
+			list_add_tail(&vif->notify_list, &notify);
+		else
+			xenvif_put(vif);
 		npo.meta_cons += sco->meta_slots_used;
 		dev_kfree_skb(skb);
 	}
 
 	list_for_each_entry_safe(vif, tmp, &notify, notify_list) {
-		notify_remote_via_irq(vif->irq);
+		notify_remote_via_irq(vif->rx_irq);
 		list_del_init(&vif->notify_list);
+		xenvif_put(vif);
 	}
 
 	/* More work to do? */
@@ -879,7 +926,7 @@ static void netbk_tx_err(struct xenvif *vif,
 
 	do {
 		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		if (cons >= end)
+		if (cons == end)
 			break;
 		txp = RING_GET_REQUEST(&vif->tx, cons++);
 	} while (1);
@@ -888,49 +935,112 @@ static void netbk_tx_err(struct xenvif *vif,
 	xenvif_put(vif);
 }
 
+static void netbk_fatal_tx_err(struct xenvif *vif)
+{
+	netdev_err(vif->dev, "fatal error; disabling device\n");
+	xenvif_carrier_off(vif);
+	xenvif_put(vif);
+}
+
 static int netbk_count_requests(struct xenvif *vif,
 				struct xen_netif_tx_request *first,
 				struct xen_netif_tx_request *txp,
 				int work_to_do)
 {
 	RING_IDX cons = vif->tx.req_cons;
-	int frags = 0;
+	int slots = 0;
+	int drop_err = 0;
+	int more_data;
 
 	if (!(first->flags & XEN_NETTXF_more_data))
 		return 0;
 
 	do {
-		if (frags >= work_to_do) {
-			netdev_dbg(vif->dev, "Need more frags\n");
-			return -frags;
+		struct xen_netif_tx_request dropped_tx = { 0 };
+
+		if (slots >= work_to_do) {
+			netdev_err(vif->dev,
+				   "Asked for %d slots but exceeds this limit\n",
+				   work_to_do);
+			netbk_fatal_tx_err(vif);
+			return -ENODATA;
 		}
 
-		if (unlikely(frags >= MAX_SKB_FRAGS)) {
-			netdev_dbg(vif->dev, "Too many frags\n");
-			return -frags;
+		/* This guest is really using too many slots and
+		 * considered malicious.
+		 */
+		if (unlikely(slots >= fatal_skb_slots)) {
+			netdev_err(vif->dev,
+				   "Malicious frontend using %d slots, threshold %u\n",
+				   slots, fatal_skb_slots);
+			netbk_fatal_tx_err(vif);
+			return -E2BIG;
+		}
+
+		/* Xen network protocol had implicit dependency on
+		 * MAX_SKB_FRAGS. XEN_NETBK_LEGACY_SLOTS_MAX is set to
+		 * the historical MAX_SKB_FRAGS value 18 to honor the
+		 * same behavior as before. Any packet using more than
+		 * 18 slots but less than fatal_skb_slots slots is
+		 * dropped
+		 */
+		if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) {
+			if (net_ratelimit())
+				netdev_dbg(vif->dev,
+					   "Too many slots (%d) exceeding limit (%d), dropping packet\n",
+					   slots, XEN_NETBK_LEGACY_SLOTS_MAX);
+			drop_err = -E2BIG;
 		}
 
-		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
+		if (drop_err)
+			txp = &dropped_tx;
+
+		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + slots),
 		       sizeof(*txp));
-		if (txp->size > first->size) {
-			netdev_dbg(vif->dev, "Frags galore\n");
-			return -frags;
+
+		/* If the guest submitted a frame >= 64 KiB then
+		 * first->size overflowed and following slots will
+		 * appear to be larger than the frame.
+		 *
+		 * This cannot be fatal error as there are buggy
+		 * frontends that do this.
+		 *
+		 * Consume all slots and drop the packet.
+		 */
+		if (!drop_err && txp->size > first->size) {
+			if (net_ratelimit())
+				netdev_dbg(vif->dev,
+					   "Invalid tx request, slot size %u > remaining size %u\n",
+					   txp->size, first->size);
+			drop_err = -EIO;
 		}
 
 		first->size -= txp->size;
-		frags++;
+		slots++;
 
 		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n",
+			netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
 				 txp->offset, txp->size);
-			return -frags;
+			netbk_fatal_tx_err(vif);
+			return -EINVAL;
 		}
-	} while ((txp++)->flags & XEN_NETTXF_more_data);
-	return frags;
+
+		more_data = txp->flags & XEN_NETTXF_more_data;
+
+		if (!drop_err)
+			txp++;
+
+	} while (more_data);
+
+	if (drop_err) {
+		netbk_tx_err(vif, first, cons + slots);
+		return drop_err;
+	}
+
+	return slots;
 }
 
 static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk,
-					 struct sk_buff *skb,
 					 u16 pending_idx)
 {
 	struct page *page;
@@ -951,43 +1061,120 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	skb_frag_t *frags = shinfo->frags;
 	u16 pending_idx = *((u16 *)skb->data);
-	int i, start;
+	u16 head_idx = 0;
+	int slot, start;
+	struct page *page;
+	pending_ring_idx_t index, start_idx = 0;
+	uint16_t dst_offset;
+	unsigned int nr_slots;
+	struct pending_tx_info *first = NULL;
+
+	/* At this point shinfo->nr_frags is in fact the number of
+	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
+	 */
+	nr_slots = shinfo->nr_frags;
 
 	/* 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 < shinfo->nr_frags; i++, txp++) {
-		struct page *page;
-		pending_ring_idx_t index;
+	/* Coalesce tx requests, at this point the packet passed in
+	 * should be <= 64K. Any packets larger than 64K have been
+	 * handled in netbk_count_requests().
+	 */
+	for (shinfo->nr_frags = slot = start; slot < nr_slots;
+	     shinfo->nr_frags++) {
 		struct pending_tx_info *pending_tx_info =
 			netbk->pending_tx_info;
 
-		index = pending_index(netbk->pending_cons++);
-		pending_idx = netbk->pending_ring[index];
-		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
+		page = alloc_page(GFP_KERNEL|__GFP_COLD);
 		if (!page)
-			return NULL;
-
-		gop->source.u.ref = txp->gref;
-		gop->source.domid = vif->domid;
-		gop->source.offset = txp->offset;
+			goto err;
+
+		dst_offset = 0;
+		first = NULL;
+		while (dst_offset < PAGE_SIZE && slot < nr_slots) {
+			gop->flags = GNTCOPY_source_gref;
+
+			gop->source.u.ref = txp->gref;
+			gop->source.domid = vif->domid;
+			gop->source.offset = txp->offset;
+
+			gop->dest.domid = DOMID_SELF;
+
+			gop->dest.offset = dst_offset;
+			gop->dest.u.gmfn = virt_to_mfn(page_address(page));
+
+			if (dst_offset + txp->size > PAGE_SIZE) {
+				/* This page can only merge a portion
+				 * of tx request. Do not increment any
+				 * pointer / counter here. The txp
+				 * will be dealt with in future
+				 * rounds, eventually hitting the
+				 * `else` branch.
+				 */
+				gop->len = PAGE_SIZE - dst_offset;
+				txp->offset += gop->len;
+				txp->size -= gop->len;
+				dst_offset += gop->len; /* quit loop */
+			} else {
+				/* This tx request can be merged in the page */
+				gop->len = txp->size;
+				dst_offset += gop->len;
+
+				index = pending_index(netbk->pending_cons++);
+
+				pending_idx = netbk->pending_ring[index];
+
+				memcpy(&pending_tx_info[pending_idx].req, txp,
+				       sizeof(*txp));
+				xenvif_get(vif);
+
+				pending_tx_info[pending_idx].vif = vif;
+
+				/* Poison these fields, corresponding
+				 * fields for head tx req will be set
+				 * to correct values after the loop.
+				 */
+				netbk->mmap_pages[pending_idx] = (void *)(~0UL);
+				pending_tx_info[pending_idx].head =
+					INVALID_PENDING_RING_IDX;
+
+				if (!first) {
+					first = &pending_tx_info[pending_idx];
+					start_idx = index;
+					head_idx = pending_idx;
+				}
+
+				txp++;
+				slot++;
+			}
 
-		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
-		gop->dest.domid = DOMID_SELF;
-		gop->dest.offset = txp->offset;
+			gop++;
+		}
 
-		gop->len = txp->size;
-		gop->flags = GNTCOPY_source_gref;
+		first->req.offset = 0;
+		first->req.size = dst_offset;
+		first->head = start_idx;
+		set_page_ext(page, netbk, head_idx);
+		netbk->mmap_pages[head_idx] = page;
+		frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx);
+	}
 
-		gop++;
+	BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);
 
-		memcpy(&pending_tx_info[pending_idx].req, txp, sizeof(*txp));
-		xenvif_get(vif);
-		pending_tx_info[pending_idx].vif = vif;
-		frag_set_pending_idx(&frags[i], pending_idx);
+	return gop;
+err:
+	/* Unwind, freeing all pages and sending error responses. */
+	while (shinfo->nr_frags-- > start) {
+		xen_netbk_idx_release(netbk,
+				frag_get_pending_idx(&frags[shinfo->nr_frags]),
+				XEN_NETIF_RSP_ERROR);
 	}
+	/* The head too, if necessary. */
+	if (start)
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
-	return gop;
+	return NULL;
 }
 
 static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
@@ -996,48 +1183,45 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 {
 	struct gnttab_copy *gop = *gopp;
 	u16 pending_idx = *((u16 *)skb->data);
-	struct pending_tx_info *pending_tx_info = netbk->pending_tx_info;
-	struct xenvif *vif = pending_tx_info[pending_idx].vif;
-	struct xen_netif_tx_request *txp;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	struct pending_tx_info *tx_info;
 	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)) {
-		pending_ring_idx_t index;
-		index = pending_index(netbk->pending_prod++);
-		txp = &pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
-	}
+	if (unlikely(err))
+		xen_netbk_idx_release(netbk, 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 index;
+		pending_ring_idx_t head;
 
 		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
+		tx_info = &netbk->pending_tx_info[pending_idx];
+		head = tx_info->head;
 
 		/* Check error status: if okay then remember grant handle. */
-		newerr = (++gop)->status;
+		do {
+			newerr = (++gop)->status;
+			if (newerr)
+				break;
+			peek = netbk->pending_ring[pending_index(++head)];
+		} while (!pending_tx_is_head(netbk, peek));
+
 		if (likely(!newerr)) {
 			/* Had a previous error? Invalidate this fragment. */
 			if (unlikely(err))
-				xen_netbk_idx_release(netbk, pending_idx);
+				xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 			continue;
 		}
 
 		/* Error on this fragment: respond to client with an error. */
-		txp = &netbk->pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		index = pending_index(netbk->pending_prod++);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
 		/* Not the first error? Preceding frags already invalidated. */
 		if (err)
@@ -1045,10 +1229,10 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 
 		/* First error: invalidate header and preceding fragments. */
 		pending_idx = *((u16 *)skb->data);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		for (j = start; j < i; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		/* Remember the error: invalidate all subsequent fragments. */
@@ -1082,7 +1266,7 @@ static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb)
 
 		/* Take an extra reference to offset xen_netbk_idx_release */
 		get_page(netbk->mmap_pages[pending_idx]);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 	}
 }
 
@@ -1095,7 +1279,8 @@ static int xen_netbk_get_extras(struct xenvif *vif,
 
 	do {
 		if (unlikely(work_to_do-- <= 0)) {
-			netdev_dbg(vif->dev, "Missing extra info\n");
+			netdev_err(vif->dev, "Missing extra info\n");
+			netbk_fatal_tx_err(vif);
 			return -EBADR;
 		}
 
@@ -1104,8 +1289,9 @@ static int xen_netbk_get_extras(struct xenvif *vif,
 		if (unlikely(!extra.type ||
 			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			vif->tx.req_cons = ++cons;
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "Invalid extra type: %d\n", extra.type);
+			netbk_fatal_tx_err(vif);
 			return -EINVAL;
 		}
 
@@ -1121,13 +1307,15 @@ static int netbk_set_skb_gso(struct xenvif *vif,
 			     struct xen_netif_extra_info *gso)
 {
 	if (!gso->u.gso.size) {
-		netdev_dbg(vif->dev, "GSO size must not be zero.\n");
+		netdev_err(vif->dev, "GSO size must not be zero.\n");
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
 	/* Currently only TCPv4 S.O. is supported. */
 	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
-		netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
@@ -1144,7 +1332,6 @@ static int netbk_set_skb_gso(struct xenvif *vif,
 static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 {
 	struct iphdr *iph;
-	unsigned char *th;
 	int err = -EPROTO;
 	int recalculate_partial_csum = 0;
 
@@ -1168,27 +1355,26 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 		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);
+		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
+					  offsetof(struct tcphdr, check)))
+			goto out;
 
 		if (recalculate_partial_csum) {
-			struct tcphdr *tcph = (struct tcphdr *)th;
+			struct tcphdr *tcph = tcp_hdr(skb);
 			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
 							 skb->len - iph->ihl*4,
 							 IPPROTO_TCP, 0);
 		}
 		break;
 	case IPPROTO_UDP:
-		skb->csum_offset = offsetof(struct udphdr, check);
+		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
+					  offsetof(struct udphdr, check)))
+			goto out;
 
 		if (recalculate_partial_csum) {
-			struct udphdr *udph = (struct udphdr *)th;
+			struct udphdr *udph = udp_hdr(skb);
 			udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
 							 skb->len - iph->ihl*4,
 							 IPPROTO_UDP, 0);
@@ -1202,9 +1388,6 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 		goto out;
 	}
 
-	if ((th + skb->csum_offset + 2) > skb_tail_pointer(skb))
-		goto out;
-
 	err = 0;
 
 out:
@@ -1249,11 +1432,12 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 	struct sk_buff *skb;
 	int ret;
 
-	while (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
+	while ((nr_pending_reqs(netbk) + XEN_NETBK_LEGACY_SLOTS_MAX
+		< MAX_PENDING_REQS) &&
 		!list_empty(&netbk->net_schedule_list)) {
 		struct xenvif *vif;
 		struct xen_netif_tx_request txreq;
-		struct xen_netif_tx_request txfrags[MAX_SKB_FRAGS];
+		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;
@@ -1264,9 +1448,25 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 
 		/* Get a netif from the list with work to do. */
 		vif = poll_net_schedule_list(netbk);
+		/* This can sometimes happen because the test of
+		 * list_empty(net_schedule_list) at the top of the
+		 * loop is unlocked.  Just go back and have another
+		 * look.
+		 */
 		if (!vif)
 			continue;
 
+		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);
+			netbk_fatal_tx_err(vif);
+			continue;
+		}
+
 		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
 		if (!work_to_do) {
 			xenvif_put(vif);
@@ -1294,17 +1494,14 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 			work_to_do = xen_netbk_get_extras(vif, extras,
 							  work_to_do);
 			idx = vif->tx.req_cons;
-			if (unlikely(work_to_do < 0)) {
-				netbk_tx_err(vif, &txreq, idx);
+			if (unlikely(work_to_do < 0))
 				continue;
-			}
 		}
 
 		ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do);
-		if (unlikely(ret < 0)) {
-			netbk_tx_err(vif, &txreq, idx - ret);
+		if (unlikely(ret < 0))
 			continue;
-		}
+
 		idx += ret;
 
 		if (unlikely(txreq.size < ETH_HLEN)) {
@@ -1316,11 +1513,11 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 
 		/* No crossing a page as the payload mustn't fragment. */
 		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "txreq.offset: %x, size: %u, end: %lu\n",
 				   txreq.offset, txreq.size,
 				   (txreq.offset&~PAGE_MASK) + txreq.size);
-			netbk_tx_err(vif, &txreq, idx);
+			netbk_fatal_tx_err(vif);
 			continue;
 		}
 
@@ -1328,7 +1525,7 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 		pending_idx = netbk->pending_ring[index];
 
 		data_len = (txreq.size > PKT_PROT_LEN &&
-			    ret < MAX_SKB_FRAGS) ?
+			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
 			PKT_PROT_LEN : txreq.size;
 
 		skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,
@@ -1348,14 +1545,14 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
 
 			if (netbk_set_skb_gso(vif, skb, gso)) {
+				/* Failure in netbk_set_skb_gso is fatal. */
 				kfree_skb(skb);
-				netbk_tx_err(vif, &txreq, idx);
 				continue;
 			}
 		}
 
 		/* XXX could copy straight to head */
-		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
+		page = xen_netbk_alloc_page(netbk, pending_idx);
 		if (!page) {
 			kfree_skb(skb);
 			netbk_tx_err(vif, &txreq, idx);
@@ -1378,6 +1575,7 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 		memcpy(&netbk->pending_tx_info[pending_idx].req,
 		       &txreq, sizeof(txreq));
 		netbk->pending_tx_info[pending_idx].vif = vif;
+		netbk->pending_tx_info[pending_idx].head = index;
 		*((u16 *)skb->data) = pending_idx;
 
 		__skb_put(skb, data_len);
@@ -1448,7 +1646,7 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk)
 			txp->size -= data_len;
 		} else {
 			/* Schedule a response immediately. */
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		if (txp->flags & XEN_NETTXF_csum_blank)
@@ -1470,6 +1668,7 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk)
 
 		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,
@@ -1478,6 +1677,8 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk)
 			continue;
 		}
 
+		skb_probe_transport_header(skb, 0);
+
 		vif->dev->stats.rx_bytes += skb->len;
 		vif->dev->stats.rx_packets++;
 
@@ -1500,11 +1701,15 @@ static void xen_netbk_tx_action(struct xen_netbk *netbk)
 	xen_netbk_tx_submit(netbk);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status)
 {
 	struct xenvif *vif;
 	struct pending_tx_info *pending_tx_info;
-	pending_ring_idx_t index;
+	pending_ring_idx_t head;
+	u16 peek; /* peek into next tx request */
+
+	BUG_ON(netbk->mmap_pages[pending_idx] == (void *)(~0UL));
 
 	/* Already complete? */
 	if (netbk->mmap_pages[pending_idx] == NULL)
@@ -1513,19 +1718,40 @@ static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
 	pending_tx_info = &netbk->pending_tx_info[pending_idx];
 
 	vif = pending_tx_info->vif;
+	head = pending_tx_info->head;
 
-	make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY);
+	BUG_ON(!pending_tx_is_head(netbk, head));
+	BUG_ON(netbk->pending_ring[pending_index(head)] != pending_idx);
 
-	index = pending_index(netbk->pending_prod++);
-	netbk->pending_ring[index] = pending_idx;
+	do {
+		pending_ring_idx_t index;
+		pending_ring_idx_t idx = pending_index(head);
+		u16 info_idx = netbk->pending_ring[idx];
 
-	xenvif_put(vif);
+		pending_tx_info = &netbk->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(netbk->pending_prod++);
+		netbk->pending_ring[index] = netbk->pending_ring[info_idx];
+
+		xenvif_put(vif);
+
+		peek = netbk->pending_ring[pending_index(++head)];
+
+	} while (!pending_tx_is_head(netbk, peek));
 
 	netbk->mmap_pages[pending_idx]->mapping = 0;
 	put_page(netbk->mmap_pages[pending_idx]);
 	netbk->mmap_pages[pending_idx] = NULL;
 }
 
+
 static void make_tx_response(struct xenvif *vif,
 			     struct xen_netif_tx_request *txp,
 			     s8       st)
@@ -1544,7 +1770,7 @@ static void make_tx_response(struct xenvif *vif,
 	vif->tx.rsp_prod_pvt = ++i;
 	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
 	if (notify)
-		notify_remote_via_irq(vif->irq);
+		notify_remote_via_irq(vif->tx_irq);
 }
 
 static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
@@ -1578,8 +1804,9 @@ static inline int rx_work_todo(struct xen_netbk *netbk)
 static inline int tx_work_todo(struct xen_netbk *netbk)
 {
 
-	if (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
-			!list_empty(&netbk->net_schedule_list))
+	if ((nr_pending_reqs(netbk) + XEN_NETBK_LEGACY_SLOTS_MAX
+	     < MAX_PENDING_REQS) &&
+	     !list_empty(&netbk->net_schedule_list))
 		return 1;
 
 	return 0;
@@ -1662,6 +1889,12 @@ static int __init netback_init(void)
 	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;
+	}
+
 	xen_netbk_group_nr = num_online_cpus();
 	xen_netbk = vzalloc(sizeof(struct xen_netbk) * xen_netbk_group_nr);
 	if (!xen_netbk)
@@ -1687,7 +1920,7 @@ static int __init netback_init(void)
 					     "netback/%u", group);
 
 		if (IS_ERR(netbk->task)) {
-			printk(KERN_ALERT "kthread_create() fails at netback\n");
+			pr_alert("kthread_create() fails at netback\n");
 			del_timer(&netbk->net_timer);
 			rc = PTR_ERR(netbk->task);
 			goto failed_init;
@@ -1713,10 +1946,6 @@ static int __init netback_init(void)
 failed_init:
 	while (--group >= 0) {
 		struct xen_netbk *netbk = &xen_netbk[group];
-		for (i = 0; i < MAX_PENDING_REQS; i++) {
-			if (netbk->mmap_pages[i])
-				__free_page(netbk->mmap_pages[i]);
-		}
 		del_timer(&netbk->net_timer);
 		kthread_stop(netbk->task);
 	}
@@ -1727,5 +1956,25 @@ failed_init:
 
 module_init(netback_init);
 
+static void __exit netback_fini(void)
+{
+	int i, j;
+
+	xenvif_xenbus_fini();
+
+	for (i = 0; i < xen_netbk_group_nr; i++) {
+		struct xen_netbk *netbk = &xen_netbk[i];
+		del_timer_sync(&netbk->net_timer);
+		kthread_stop(netbk->task);
+		for (j = 0; j < MAX_PENDING_REQS; j++) {
+			if (netbk->mmap_pages[j])
+				__free_page(netbk->mmap_pages[j]);
+		}
+	}
+
+	vfree(xen_netbk);
+}
+module_exit(netback_fini);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("xen-backend:vif");