xen-netfront: Factor queue-specific data into queue struct.

In preparation for multi-queue support in xen-netfront, move the
queue-specific data from struct netfront_info to struct netfront_queue,
and update the rest of the code to use this.

Also adds loops over queues where appropriate, even though only one is
configured at this point, and uses alloc_etherdev_mq() and the
corresponding multi-queue netif wake/start/stop functions in preparation
for multiple active queues.

Finally, implements a trivial queue selection function suitable for
ndo_select_queue, which simply returns 0, selecting the first (and
only) queue.

Signed-off-by: Andrew J. Bennieston <andrew.bennieston@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 579 insertions, 393 deletions

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 895355de8ac4..af8cd95ec76b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -73,6 +73,12 @@ struct netfront_cb {
 #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
 #define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256)
 
+/* Queue name is interface name with "-qNNN" appended */
+#define QUEUE_NAME_SIZE (IFNAMSIZ + 6)
+
+/* IRQ name is queue name with "-tx" or "-rx" appended */
+#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+
 struct netfront_stats {
 	u64			rx_packets;
 	u64			tx_packets;
@@ -81,9 +87,12 @@ struct netfront_stats {
 	struct u64_stats_sync	syncp;
 };
 
-struct netfront_info {
-	struct list_head list;
-	struct net_device *netdev;
+struct netfront_info;
+
+struct netfront_queue {
+	unsigned int id; /* Queue ID, 0-based */
+	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
+	struct netfront_info *info;
 
 	struct napi_struct napi;
 
@@ -93,10 +102,8 @@ struct netfront_info {
 	unsigned int tx_evtchn, rx_evtchn;
 	unsigned int tx_irq, rx_irq;
 	/* Only used when split event channels support is enabled */
-	char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
-	char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
-
-	struct xenbus_device *xbdev;
+	char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */
+	char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
 
 	spinlock_t   tx_lock;
 	struct xen_netif_tx_front_ring tx;
@@ -140,11 +147,21 @@ struct netfront_info {
 	unsigned long rx_pfn_array[NET_RX_RING_SIZE];
 	struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1];
 	struct mmu_update rx_mmu[NET_RX_RING_SIZE];
+};
+
+struct netfront_info {
+	struct list_head list;
+	struct net_device *netdev;
+
+	struct xenbus_device *xbdev;
+
+	/* Multi-queue support */
+	struct netfront_queue *queues;
 
 	/* Statistics */
 	struct netfront_stats __percpu *stats;
 
-	unsigned long rx_gso_checksum_fixup;
+	atomic_t rx_gso_checksum_fixup;
 };
 
 struct netfront_rx_info {
@@ -187,21 +204,21 @@ static int xennet_rxidx(RING_IDX idx)
 	return idx & (NET_RX_RING_SIZE - 1);
 }
 
-static struct sk_buff *xennet_get_rx_skb(struct netfront_info *np,
+static struct sk_buff *xennet_get_rx_skb(struct netfront_queue *queue,
 					 RING_IDX ri)
 {
 	int i = xennet_rxidx(ri);
-	struct sk_buff *skb = np->rx_skbs[i];
-	np->rx_skbs[i] = NULL;
+	struct sk_buff *skb = queue->rx_skbs[i];
+	queue->rx_skbs[i] = NULL;
 	return skb;
 }
 
-static grant_ref_t xennet_get_rx_ref(struct netfront_info *np,
+static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue,
 					    RING_IDX ri)
 {
 	int i = xennet_rxidx(ri);
-	grant_ref_t ref = np->grant_rx_ref[i];
-	np->grant_rx_ref[i] = GRANT_INVALID_REF;
+	grant_ref_t ref = queue->grant_rx_ref[i];
+	queue->grant_rx_ref[i] = GRANT_INVALID_REF;
 	return ref;
 }
 
@@ -221,41 +238,40 @@ static bool xennet_can_sg(struct net_device *dev)
 
 static void rx_refill_timeout(unsigned long data)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netfront_info *np = netdev_priv(dev);
-	napi_schedule(&np->napi);
+	struct netfront_queue *queue = (struct netfront_queue *)data;
+	napi_schedule(&queue->napi);
 }
 
-static int netfront_tx_slot_available(struct netfront_info *np)
+static int netfront_tx_slot_available(struct netfront_queue *queue)
 {
-	return (np->tx.req_prod_pvt - np->tx.rsp_cons) <
+	return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) <
 		(TX_MAX_TARGET - MAX_SKB_FRAGS - 2);
 }
 
-static void xennet_maybe_wake_tx(struct net_device *dev)
+static void xennet_maybe_wake_tx(struct netfront_queue *queue)
 {
-	struct netfront_info *np = netdev_priv(dev);
+	struct net_device *dev = queue->info->netdev;
+	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, queue->id);
 
-	if (unlikely(netif_queue_stopped(dev)) &&
-	    netfront_tx_slot_available(np) &&
+	if (unlikely(netif_tx_queue_stopped(dev_queue)) &&
+	    netfront_tx_slot_available(queue) &&
 	    likely(netif_running(dev)))
-		netif_wake_queue(dev);
+		netif_tx_wake_queue(netdev_get_tx_queue(dev, queue->id));
 }
 
-static void xennet_alloc_rx_buffers(struct net_device *dev)
+static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 {
 	unsigned short id;
-	struct netfront_info *np = netdev_priv(dev);
 	struct sk_buff *skb;
 	struct page *page;
 	int i, batch_target, notify;
-	RING_IDX req_prod = np->rx.req_prod_pvt;
+	RING_IDX req_prod = queue->rx.req_prod_pvt;
 	grant_ref_t ref;
 	unsigned long pfn;
 	void *vaddr;
 	struct xen_netif_rx_request *req;
 
-	if (unlikely(!netif_carrier_ok(dev)))
+	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
 		return;
 
 	/*
@@ -264,9 +280,10 @@ static void xennet_alloc_rx_buffers(struct net_device *dev)
 	 * allocator, so should reduce the chance of failed allocation requests
 	 * both for ourself and for other kernel subsystems.
 	 */
-	batch_target = np->rx_target - (req_prod - np->rx.rsp_cons);
-	for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) {
-		skb = __netdev_alloc_skb(dev, RX_COPY_THRESHOLD + NET_IP_ALIGN,
+	batch_target = queue->rx_target - (req_prod - queue->rx.rsp_cons);
+	for (i = skb_queue_len(&queue->rx_batch); i < batch_target; i++) {
+		skb = __netdev_alloc_skb(queue->info->netdev,
+					 RX_COPY_THRESHOLD + NET_IP_ALIGN,
 					 GFP_ATOMIC | __GFP_NOWARN);
 		if (unlikely(!skb))
 			goto no_skb;
@@ -279,7 +296,7 @@ static void xennet_alloc_rx_buffers(struct net_device *dev)
 			kfree_skb(skb);
 no_skb:
 			/* Could not allocate any skbuffs. Try again later. */
-			mod_timer(&np->rx_refill_timer,
+			mod_timer(&queue->rx_refill_timer,
 				  jiffies + (HZ/10));
 
 			/* Any skbuffs queued for refill? Force them out. */
@@ -289,44 +306,44 @@ no_skb:
 		}
 
 		skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
-		__skb_queue_tail(&np->rx_batch, skb);
+		__skb_queue_tail(&queue->rx_batch, skb);
 	}
 
 	/* Is the batch large enough to be worthwhile? */
-	if (i < (np->rx_target/2)) {
-		if (req_prod > np->rx.sring->req_prod)
+	if (i < (queue->rx_target/2)) {
+		if (req_prod > queue->rx.sring->req_prod)
 			goto push;
 		return;
 	}
 
 	/* Adjust our fill target if we risked running out of buffers. */
-	if (((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) &&
-	    ((np->rx_target *= 2) > np->rx_max_target))
-		np->rx_target = np->rx_max_target;
+	if (((req_prod - queue->rx.sring->rsp_prod) < (queue->rx_target / 4)) &&
+	    ((queue->rx_target *= 2) > queue->rx_max_target))
+		queue->rx_target = queue->rx_max_target;
 
  refill:
 	for (i = 0; ; i++) {
-		skb = __skb_dequeue(&np->rx_batch);
+		skb = __skb_dequeue(&queue->rx_batch);
 		if (skb == NULL)
 			break;
 
-		skb->dev = dev;
+		skb->dev = queue->info->netdev;
 
 		id = xennet_rxidx(req_prod + i);
 
-		BUG_ON(np->rx_skbs[id]);
-		np->rx_skbs[id] = skb;
+		BUG_ON(queue->rx_skbs[id]);
+		queue->rx_skbs[id] = skb;
 
-		ref = gnttab_claim_grant_reference(&np->gref_rx_head);
+		ref = gnttab_claim_grant_reference(&queue->gref_rx_head);
 		BUG_ON((signed short)ref < 0);
-		np->grant_rx_ref[id] = ref;
+		queue->grant_rx_ref[id] = ref;
 
 		pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
 		vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0]));
 
-		req = RING_GET_REQUEST(&np->rx, req_prod + i);
+		req = RING_GET_REQUEST(&queue->rx, req_prod + i);
 		gnttab_grant_foreign_access_ref(ref,
-						np->xbdev->otherend_id,
+						queue->info->xbdev->otherend_id,
 						pfn_to_mfn(pfn),
 						0);
 
@@ -337,72 +354,77 @@ no_skb:
 	wmb();		/* barrier so backend seens requests */
 
 	/* Above is a suitable barrier to ensure backend will see requests. */
-	np->rx.req_prod_pvt = req_prod + i;
+	queue->rx.req_prod_pvt = req_prod + i;
  push:
-	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify);
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify);
 	if (notify)
-		notify_remote_via_irq(np->rx_irq);
+		notify_remote_via_irq(queue->rx_irq);
 }
 
 static int xennet_open(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-
-	napi_enable(&np->napi);
-
-	spin_lock_bh(&np->rx_lock);
-	if (netif_carrier_ok(dev)) {
-		xennet_alloc_rx_buffers(dev);
-		np->rx.sring->rsp_event = np->rx.rsp_cons + 1;
-		if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
-			napi_schedule(&np->napi);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i = 0;
+	struct netfront_queue *queue = NULL;
+
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		napi_enable(&queue->napi);
+
+		spin_lock_bh(&queue->rx_lock);
+		if (netif_carrier_ok(dev)) {
+			xennet_alloc_rx_buffers(queue);
+			queue->rx.sring->rsp_event = queue->rx.rsp_cons + 1;
+			if (RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))
+				napi_schedule(&queue->napi);
+		}
+		spin_unlock_bh(&queue->rx_lock);
 	}
-	spin_unlock_bh(&np->rx_lock);
 
-	netif_start_queue(dev);
+	netif_tx_start_all_queues(dev);
 
 	return 0;
 }
 
-static void xennet_tx_buf_gc(struct net_device *dev)
+static void xennet_tx_buf_gc(struct netfront_queue *queue)
 {
 	RING_IDX cons, prod;
 	unsigned short id;
-	struct netfront_info *np = netdev_priv(dev);
 	struct sk_buff *skb;
 
-	BUG_ON(!netif_carrier_ok(dev));
+	BUG_ON(!netif_carrier_ok(queue->info->netdev));
 
 	do {
-		prod = np->tx.sring->rsp_prod;
+		prod = queue->tx.sring->rsp_prod;
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
-		for (cons = np->tx.rsp_cons; cons != prod; cons++) {
+		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
 			struct xen_netif_tx_response *txrsp;
 
-			txrsp = RING_GET_RESPONSE(&np->tx, cons);
+			txrsp = RING_GET_RESPONSE(&queue->tx, cons);
 			if (txrsp->status == XEN_NETIF_RSP_NULL)
 				continue;
 
 			id  = txrsp->id;
-			skb = np->tx_skbs[id].skb;
+			skb = queue->tx_skbs[id].skb;
 			if (unlikely(gnttab_query_foreign_access(
-				np->grant_tx_ref[id]) != 0)) {
+				queue->grant_tx_ref[id]) != 0)) {
 				pr_alert("%s: warning -- grant still in use by backend domain\n",
 					 __func__);
 				BUG();
 			}
 			gnttab_end_foreign_access_ref(
-				np->grant_tx_ref[id], GNTMAP_readonly);
+				queue->grant_tx_ref[id], GNTMAP_readonly);
 			gnttab_release_grant_reference(
-				&np->gref_tx_head, np->grant_tx_ref[id]);
-			np->grant_tx_ref[id] = GRANT_INVALID_REF;
-			np->grant_tx_page[id] = NULL;
-			add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id);
+				&queue->gref_tx_head, queue->grant_tx_ref[id]);
+			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
+			queue->grant_tx_page[id] = NULL;
+			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
 			dev_kfree_skb_irq(skb);
 		}
 
-		np->tx.rsp_cons = prod;
+		queue->tx.rsp_cons = prod;
 
 		/*
 		 * Set a new event, then check for race with update of tx_cons.
@@ -412,21 +434,20 @@ static void xennet_tx_buf_gc(struct net_device *dev)
 		 * data is outstanding: in such cases notification from Xen is
 		 * likely to be the only kick that we'll get.
 		 */
-		np->tx.sring->rsp_event =
-			prod + ((np->tx.sring->req_prod - prod) >> 1) + 1;
+		queue->tx.sring->rsp_event =
+			prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1;
 		mb();		/* update shared area */
-	} while ((cons == prod) && (prod != np->tx.sring->rsp_prod));
+	} while ((cons == prod) && (prod != queue->tx.sring->rsp_prod));
 
-	xennet_maybe_wake_tx(dev);
+	xennet_maybe_wake_tx(queue);
 }
 
-static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
+static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue,
 			      struct xen_netif_tx_request *tx)
 {
-	struct netfront_info *np = netdev_priv(dev);
 	char *data = skb->data;
 	unsigned long mfn;
-	RING_IDX prod = np->tx.req_prod_pvt;
+	RING_IDX prod = queue->tx.req_prod_pvt;
 	int frags = skb_shinfo(skb)->nr_frags;
 	unsigned int offset = offset_in_page(data);
 	unsigned int len = skb_headlen(skb);
@@ -443,19 +464,19 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		data += tx->size;
 		offset = 0;
 
-		id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
-		np->tx_skbs[id].skb = skb_get(skb);
-		tx = RING_GET_REQUEST(&np->tx, prod++);
+		id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+		queue->tx_skbs[id].skb = skb_get(skb);
+		tx = RING_GET_REQUEST(&queue->tx, prod++);
 		tx->id = id;
-		ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+		ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 		BUG_ON((signed short)ref < 0);
 
 		mfn = virt_to_mfn(data);
-		gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
+		gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 						mfn, GNTMAP_readonly);
 
-		np->grant_tx_page[id] = virt_to_page(data);
-		tx->gref = np->grant_tx_ref[id] = ref;
+		queue->grant_tx_page[id] = virt_to_page(data);
+		tx->gref = queue->grant_tx_ref[id] = ref;
 		tx->offset = offset;
 		tx->size = len;
 		tx->flags = 0;
@@ -487,21 +508,21 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 
 			tx->flags |= XEN_NETTXF_more_data;
 
-			id = get_id_from_freelist(&np->tx_skb_freelist,
-						  np->tx_skbs);
-			np->tx_skbs[id].skb = skb_get(skb);
-			tx = RING_GET_REQUEST(&np->tx, prod++);
+			id = get_id_from_freelist(&queue->tx_skb_freelist,
+						  queue->tx_skbs);
+			queue->tx_skbs[id].skb = skb_get(skb);
+			tx = RING_GET_REQUEST(&queue->tx, prod++);
 			tx->id = id;
-			ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+			ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 			BUG_ON((signed short)ref < 0);
 
 			mfn = pfn_to_mfn(page_to_pfn(page));
 			gnttab_grant_foreign_access_ref(ref,
-							np->xbdev->otherend_id,
+							queue->info->xbdev->otherend_id,
 							mfn, GNTMAP_readonly);
 
-			np->grant_tx_page[id] = page;
-			tx->gref = np->grant_tx_ref[id] = ref;
+			queue->grant_tx_page[id] = page;
+			tx->gref = queue->grant_tx_ref[id] = ref;
 			tx->offset = offset;
 			tx->size = bytes;
 			tx->flags = 0;
@@ -518,7 +539,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	np->tx.req_prod_pvt = prod;
+	queue->tx.req_prod_pvt = prod;
 }
 
 /*
@@ -544,6 +565,12 @@ static int xennet_count_skb_frag_slots(struct sk_buff *skb)
 	return pages;
 }
 
+static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	/* Stub for later implementation of queue selection */
+	return 0;
+}
+
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	unsigned short id;
@@ -559,6 +586,16 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int offset = offset_in_page(data);
 	unsigned int len = skb_headlen(skb);
 	unsigned long flags;
+	struct netfront_queue *queue = NULL;
+	unsigned int num_queues = dev->real_num_tx_queues;
+	u16 queue_index;
+
+	/* Drop the packet if no queues are set up */
+	if (num_queues < 1)
+		goto drop;
+	/* Determine which queue to transmit this SKB on */
+	queue_index = skb_get_queue_mapping(skb);
+	queue = &np->queues[queue_index];
 
 	/* If skb->len is too big for wire format, drop skb and alert
 	 * user about misconfiguration.
@@ -578,30 +615,30 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	spin_lock_irqsave(&np->tx_lock, flags);
+	spin_lock_irqsave(&queue->tx_lock, flags);
 
 	if (unlikely(!netif_carrier_ok(dev) ||
 		     (slots > 1 && !xennet_can_sg(dev)) ||
 		     netif_needs_gso(skb, netif_skb_features(skb)))) {
-		spin_unlock_irqrestore(&np->tx_lock, flags);
+		spin_unlock_irqrestore(&queue->tx_lock, flags);
 		goto drop;
 	}
 
-	i = np->tx.req_prod_pvt;
+	i = queue->tx.req_prod_pvt;
 
-	id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
-	np->tx_skbs[id].skb = skb;
+	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	queue->tx_skbs[id].skb = skb;
 
-	tx = RING_GET_REQUEST(&np->tx, i);
+	tx = RING_GET_REQUEST(&queue->tx, i);
 
 	tx->id   = id;
-	ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	BUG_ON((signed short)ref < 0);
 	mfn = virt_to_mfn(data);
 	gnttab_grant_foreign_access_ref(
-		ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
-	np->grant_tx_page[id] = virt_to_page(data);
-	tx->gref = np->grant_tx_ref[id] = ref;
+		ref, queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly);
+	queue->grant_tx_page[id] = virt_to_page(data);
+	tx->gref = queue->grant_tx_ref[id] = ref;
 	tx->offset = offset;
 	tx->size = len;
 
@@ -617,7 +654,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct xen_netif_extra_info *gso;
 
 		gso = (struct xen_netif_extra_info *)
-			RING_GET_REQUEST(&np->tx, ++i);
+			RING_GET_REQUEST(&queue->tx, ++i);
 
 		tx->flags |= XEN_NETTXF_extra_info;
 
@@ -632,14 +669,14 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		gso->flags = 0;
 	}
 
-	np->tx.req_prod_pvt = i + 1;
+	queue->tx.req_prod_pvt = i + 1;
 
-	xennet_make_frags(skb, dev, tx);
+	xennet_make_frags(skb, queue, tx);
 	tx->size = skb->len;
 
-	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify);
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
-		notify_remote_via_irq(np->tx_irq);
+		notify_remote_via_irq(queue->tx_irq);
 
 	u64_stats_update_begin(&stats->syncp);
 	stats->tx_bytes += skb->len;
@@ -647,12 +684,12 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	u64_stats_update_end(&stats->syncp);
 
 	/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
-	xennet_tx_buf_gc(dev);
+	xennet_tx_buf_gc(queue);
 
-	if (!netfront_tx_slot_available(np))
-		netif_stop_queue(dev);
+	if (!netfront_tx_slot_available(queue))
+		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
 
-	spin_unlock_irqrestore(&np->tx_lock, flags);
+	spin_unlock_irqrestore(&queue->tx_lock, flags);
 
 	return NETDEV_TX_OK;
 
@@ -665,32 +702,38 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 static int xennet_close(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-	netif_stop_queue(np->netdev);
-	napi_disable(&np->napi);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i;
+	struct netfront_queue *queue;
+	netif_tx_stop_all_queues(np->netdev);
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		napi_disable(&queue->napi);
+	}
 	return 0;
 }
 
-static void xennet_move_rx_slot(struct netfront_info *np, struct sk_buff *skb,
+static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb,
 				grant_ref_t ref)
 {
-	int new = xennet_rxidx(np->rx.req_prod_pvt);
-
-	BUG_ON(np->rx_skbs[new]);
-	np->rx_skbs[new] = skb;
-	np->grant_rx_ref[new] = ref;
-	RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->id = new;
-	RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->gref = ref;
-	np->rx.req_prod_pvt++;
+	int new = xennet_rxidx(queue->rx.req_prod_pvt);
+
+	BUG_ON(queue->rx_skbs[new]);
+	queue->rx_skbs[new] = skb;
+	queue->grant_rx_ref[new] = ref;
+	RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->id = new;
+	RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->gref = ref;
+	queue->rx.req_prod_pvt++;
 }
 
-static int xennet_get_extras(struct netfront_info *np,
+static int xennet_get_extras(struct netfront_queue *queue,
 			     struct xen_netif_extra_info *extras,
 			     RING_IDX rp)
 
 {
 	struct xen_netif_extra_info *extra;
-	struct device *dev = &np->netdev->dev;
-	RING_IDX cons = np->rx.rsp_cons;
+	struct device *dev = &queue->info->netdev->dev;
+	RING_IDX cons = queue->rx.rsp_cons;
 	int err = 0;
 
 	do {
@@ -705,7 +748,7 @@ static int xennet_get_extras(struct netfront_info *np,
 		}
 
 		extra = (struct xen_netif_extra_info *)
-			RING_GET_RESPONSE(&np->rx, ++cons);
+			RING_GET_RESPONSE(&queue->rx, ++cons);
 
 		if (unlikely(!extra->type ||
 			     extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
@@ -718,33 +761,33 @@ static int xennet_get_extras(struct netfront_info *np,
 			       sizeof(*extra));
 		}
 
-		skb = xennet_get_rx_skb(np, cons);
-		ref = xennet_get_rx_ref(np, cons);
-		xennet_move_rx_slot(np, skb, ref);
+		skb = xennet_get_rx_skb(queue, cons);
+		ref = xennet_get_rx_ref(queue, cons);
+		xennet_move_rx_slot(queue, skb, ref);
 	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
-	np->rx.rsp_cons = cons;
+	queue->rx.rsp_cons = cons;
 	return err;
 }
 
-static int xennet_get_responses(struct netfront_info *np,
+static int xennet_get_responses(struct netfront_queue *queue,
 				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);
+	struct device *dev = &queue->info->netdev->dev;
+	RING_IDX cons = queue->rx.rsp_cons;
+	struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
+	grant_ref_t ref = xennet_get_rx_ref(queue, cons);
 	int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
 	int slots = 1;
 	int err = 0;
 	unsigned long ret;
 
 	if (rx->flags & XEN_NETRXF_extra_info) {
-		err = xennet_get_extras(np, extras, rp);
-		cons = np->rx.rsp_cons;
+		err = xennet_get_extras(queue, extras, rp);
+		cons = queue->rx.rsp_cons;
 	}
 
 	for (;;) {
@@ -753,7 +796,7 @@ static int xennet_get_responses(struct netfront_info *np,
 			if (net_ratelimit())
 				dev_warn(dev, "rx->offset: %x, size: %u\n",
 					 rx->offset, rx->status);
-			xennet_move_rx_slot(np, skb, ref);
+			xennet_move_rx_slot(queue, skb, ref);
 			err = -EINVAL;
 			goto next;
 		}
@@ -774,7 +817,7 @@ static int xennet_get_responses(struct netfront_info *np,
 		ret = gnttab_end_foreign_access_ref(ref, 0);
 		BUG_ON(!ret);
 
-		gnttab_release_grant_reference(&np->gref_rx_head, ref);
+		gnttab_release_grant_reference(&queue->gref_rx_head, ref);
 
 		__skb_queue_tail(list, skb);
 
@@ -789,9 +832,9 @@ next:
 			break;
 		}
 
-		rx = RING_GET_RESPONSE(&np->rx, cons + slots);
-		skb = xennet_get_rx_skb(np, cons + slots);
-		ref = xennet_get_rx_ref(np, cons + slots);
+		rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+		skb = xennet_get_rx_skb(queue, cons + slots);
+		ref = xennet_get_rx_ref(queue, cons + slots);
 		slots++;
 	}
 
@@ -802,7 +845,7 @@ next:
 	}
 
 	if (unlikely(err))
-		np->rx.rsp_cons = cons + slots;
+		queue->rx.rsp_cons = cons + slots;
 
 	return err;
 }
@@ -836,17 +879,17 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_info *np,
+static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 				  struct sk_buff *skb,
 				  struct sk_buff_head *list)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	RING_IDX cons = np->rx.rsp_cons;
+	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
 
 	while ((nskb = __skb_dequeue(list))) {
 		struct xen_netif_rx_response *rx =
-			RING_GET_RESPONSE(&np->rx, ++cons);
+			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
 		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
@@ -879,7 +922,7 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		struct netfront_info *np = netdev_priv(dev);
-		np->rx_gso_checksum_fixup++;
+		atomic_inc(&np->rx_gso_checksum_fixup);
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		recalculate_partial_csum = true;
 	}
@@ -891,11 +934,10 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 	return skb_checksum_setup(skb, recalculate_partial_csum);
 }
 
-static int handle_incoming_queue(struct net_device *dev,
+static int handle_incoming_queue(struct netfront_queue *queue,
 				 struct sk_buff_head *rxq)
 {
-	struct netfront_info *np = netdev_priv(dev);
-	struct netfront_stats *stats = this_cpu_ptr(np->stats);
+	struct netfront_stats *stats = this_cpu_ptr(queue->info->stats);
 	int packets_dropped = 0;
 	struct sk_buff *skb;
 
@@ -906,13 +948,13 @@ static int handle_incoming_queue(struct net_device *dev,
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
-		skb->protocol = eth_type_trans(skb, dev);
+		skb->protocol = eth_type_trans(skb, queue->info->netdev);
 		skb_reset_network_header(skb);
 
-		if (checksum_setup(dev, skb)) {
+		if (checksum_setup(queue->info->netdev, skb)) {
 			kfree_skb(skb);
 			packets_dropped++;
-			dev->stats.rx_errors++;
+			queue->info->netdev->stats.rx_errors++;
 			continue;
 		}
 
@@ -922,7 +964,7 @@ static int handle_incoming_queue(struct net_device *dev,
 		u64_stats_update_end(&stats->syncp);
 
 		/* Pass it up. */
-		napi_gro_receive(&np->napi, skb);
+		napi_gro_receive(&queue->napi, skb);
 	}
 
 	return packets_dropped;
@@ -930,8 +972,8 @@ static int handle_incoming_queue(struct net_device *dev,
 
 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 netfront_queue *queue = container_of(napi, struct netfront_queue, napi);
+	struct net_device *dev = queue->info->netdev;
 	struct sk_buff *skb;
 	struct netfront_rx_info rinfo;
 	struct xen_netif_rx_response *rx = &rinfo.rx;
@@ -944,29 +986,29 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 	int err;
 
-	spin_lock(&np->rx_lock);
+	spin_lock(&queue->rx_lock);
 
 	skb_queue_head_init(&rxq);
 	skb_queue_head_init(&errq);
 	skb_queue_head_init(&tmpq);
 
-	rp = np->rx.sring->rsp_prod;
+	rp = queue->rx.sring->rsp_prod;
 	rmb(); /* Ensure we see queued responses up to 'rp'. */
 
-	i = np->rx.rsp_cons;
+	i = queue->rx.rsp_cons;
 	work_done = 0;
 	while ((i != rp) && (work_done < budget)) {
-		memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx));
+		memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
 		memset(extras, 0, sizeof(rinfo.extras));
 
-		err = xennet_get_responses(np, &rinfo, rp, &tmpq);
+		err = xennet_get_responses(queue, &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;
+			i = queue->rx.rsp_cons;
 			continue;
 		}
 
@@ -978,7 +1020,7 @@ err:
 
 			if (unlikely(xennet_set_skb_gso(skb, gso))) {
 				__skb_queue_head(&tmpq, skb);
-				np->rx.rsp_cons += skb_queue_len(&tmpq);
+				queue->rx.rsp_cons += skb_queue_len(&tmpq);
 				goto err;
 			}
 		}
@@ -992,7 +1034,7 @@ err:
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(np, skb, &tmpq);
+		i = xennet_fill_frags(queue, skb, &tmpq);
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
 			skb->ip_summed = CHECKSUM_PARTIAL;
@@ -1001,22 +1043,22 @@ err:
 
 		__skb_queue_tail(&rxq, skb);
 
-		np->rx.rsp_cons = ++i;
+		queue->rx.rsp_cons = ++i;
 		work_done++;
 	}
 
 	__skb_queue_purge(&errq);
 
-	work_done -= handle_incoming_queue(dev, &rxq);
+	work_done -= handle_incoming_queue(queue, &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;
+	if (((queue->rx.req_prod_pvt - queue->rx.sring->rsp_prod) >
+	     ((3*queue->rx_target) / 4)) &&
+	    (--queue->rx_target < queue->rx_min_target))
+		queue->rx_target = queue->rx_min_target;
 
-	xennet_alloc_rx_buffers(dev);
+	xennet_alloc_rx_buffers(queue);
 
 	if (work_done < budget) {
 		int more_to_do = 0;
@@ -1025,14 +1067,14 @@ err:
 
 		local_irq_save(flags);
 
-		RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do);
+		RING_FINAL_CHECK_FOR_RESPONSES(&queue->rx, more_to_do);
 		if (!more_to_do)
 			__napi_complete(napi);
 
 		local_irq_restore(flags);
 	}
 
-	spin_unlock(&np->rx_lock);
+	spin_unlock(&queue->rx_lock);
 
 	return work_done;
 }
@@ -1080,43 +1122,43 @@ static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev,
 	return tot;
 }
 
-static void xennet_release_tx_bufs(struct netfront_info *np)
+static void xennet_release_tx_bufs(struct netfront_queue *queue)
 {
 	struct sk_buff *skb;
 	int i;
 
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		/* Skip over entries which are actually freelist references */
-		if (skb_entry_is_link(&np->tx_skbs[i]))
+		if (skb_entry_is_link(&queue->tx_skbs[i]))
 			continue;
 
-		skb = np->tx_skbs[i].skb;
-		get_page(np->grant_tx_page[i]);
-		gnttab_end_foreign_access(np->grant_tx_ref[i],
+		skb = queue->tx_skbs[i].skb;
+		get_page(queue->grant_tx_page[i]);
+		gnttab_end_foreign_access(queue->grant_tx_ref[i],
 					  GNTMAP_readonly,
-					  (unsigned long)page_address(np->grant_tx_page[i]));
-		np->grant_tx_page[i] = NULL;
-		np->grant_tx_ref[i] = GRANT_INVALID_REF;
-		add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
+					  (unsigned long)page_address(queue->grant_tx_page[i]));
+		queue->grant_tx_page[i] = NULL;
+		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
+		add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
 		dev_kfree_skb_irq(skb);
 	}
 }
 
-static void xennet_release_rx_bufs(struct netfront_info *np)
+static void xennet_release_rx_bufs(struct netfront_queue *queue)
 {
 	int id, ref;
 
-	spin_lock_bh(&np->rx_lock);
+	spin_lock_bh(&queue->rx_lock);
 
 	for (id = 0; id < NET_RX_RING_SIZE; id++) {
 		struct sk_buff *skb;
 		struct page *page;
 
-		skb = np->rx_skbs[id];
+		skb = queue->rx_skbs[id];
 		if (!skb)
 			continue;
 
-		ref = np->grant_rx_ref[id];
+		ref = queue->grant_rx_ref[id];
 		if (ref == GRANT_INVALID_REF)
 			continue;
 
@@ -1128,21 +1170,28 @@ static void xennet_release_rx_bufs(struct netfront_info *np)
 		get_page(page);
 		gnttab_end_foreign_access(ref, 0,
 					  (unsigned long)page_address(page));
-		np->grant_rx_ref[id] = GRANT_INVALID_REF;
+		queue->grant_rx_ref[id] = GRANT_INVALID_REF;
 
 		kfree_skb(skb);
 	}
 
-	spin_unlock_bh(&np->rx_lock);
+	spin_unlock_bh(&queue->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);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	struct netfront_queue *queue;
+	unsigned int i;
+
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		xennet_release_tx_bufs(queue);
+		xennet_release_rx_bufs(queue);
+		gnttab_free_grant_references(queue->gref_tx_head);
+		gnttab_free_grant_references(queue->gref_rx_head);
+	}
 }
 
 static netdev_features_t xennet_fix_features(struct net_device *dev,
@@ -1203,25 +1252,24 @@ static int xennet_set_features(struct net_device *dev,
 
 static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
 {
-	struct netfront_info *np = dev_id;
-	struct net_device *dev = np->netdev;
+	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
-	spin_lock_irqsave(&np->tx_lock, flags);
-	xennet_tx_buf_gc(dev);
-	spin_unlock_irqrestore(&np->tx_lock, flags);
+	spin_lock_irqsave(&queue->tx_lock, flags);
+	xennet_tx_buf_gc(queue);
+	spin_unlock_irqrestore(&queue->tx_lock, flags);
 
 	return IRQ_HANDLED;
 }
 
 static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
 {
-	struct netfront_info *np = dev_id;
-	struct net_device *dev = np->netdev;
+	struct netfront_queue *queue = dev_id;
+	struct net_device *dev = queue->info->netdev;
 
 	if (likely(netif_carrier_ok(dev) &&
-		   RING_HAS_UNCONSUMED_RESPONSES(&np->rx)))
-			napi_schedule(&np->napi);
+		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
+			napi_schedule(&queue->napi);
 
 	return IRQ_HANDLED;
 }
@@ -1236,7 +1284,12 @@ static irqreturn_t xennet_interrupt(int irq, void *dev_id)
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void xennet_poll_controller(struct net_device *dev)
 {
-	xennet_interrupt(0, dev);
+	/* Poll each queue */
+	struct netfront_info *info = netdev_priv(dev);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i;
+	for (i = 0; i < num_queues; ++i)
+		xennet_interrupt(0, &info->queues[i]);
 }
 #endif
 
@@ -1251,6 +1304,7 @@ static const struct net_device_ops xennet_netdev_ops = {
 	.ndo_validate_addr   = eth_validate_addr,
 	.ndo_fix_features    = xennet_fix_features,
 	.ndo_set_features    = xennet_set_features,
+	.ndo_select_queue    = xennet_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = xennet_poll_controller,
 #endif
@@ -1258,66 +1312,30 @@ static const struct net_device_ops xennet_netdev_ops = {
 
 static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 {
-	int i, err;
+	int err;
 	struct net_device *netdev;
 	struct netfront_info *np;
 
-	netdev = alloc_etherdev(sizeof(struct netfront_info));