xen-netback: switch to NAPI + kthread 1:1 model

This patch implements 1:1 model netback. NAPI and kthread are utilized
to do the weight-lifting job:

- NAPI is used for guest side TX (host side RX)
- kthread is used for guest side RX (host side TX)

Xenvif and xen_netbk are made into one structure to reduce code size.

This model provides better scheduling fairness among vifs. It is also
prerequisite for implementing multiqueue for Xen netback.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 351 insertions, 507 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 8a4d77ee9c5..9c1f15872e1 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -45,31 +45,109 @@
 #include <xen/grant_table.h>
 #include <xen/xenbus.h>
 
-struct xen_netbk;
+typedef unsigned int pending_ring_idx_t;
+#define INVALID_PENDING_RING_IDX (~0U)
+
+/* For the head field in pending_tx_info: it is used to indicate
+ * whether this tx info is the head of one or more coalesced requests.
+ *
+ * When head != INVALID_PENDING_RING_IDX, it means the start of a new
+ * tx requests queue and the end of previous queue.
+ *
+ * An example sequence of head fields (I = INVALID_PENDING_RING_IDX):
+ *
+ * ...|0 I I I|5 I|9 I I I|...
+ * -->|<-INUSE----------------
+ *
+ * After consuming the first slot(s) we have:
+ *
+ * ...|V V V V|5 I|9 I I I|...
+ * -----FREE->|<-INUSE--------
+ *
+ * where V stands for "valid pending ring index". Any number other
+ * than INVALID_PENDING_RING_IDX is OK. These entries are considered
+ * free and can contain any number other than
+ * INVALID_PENDING_RING_IDX. In practice we use 0.
+ *
+ * The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the
+ * above example) number is the index into pending_tx_info and
+ * mmap_pages arrays.
+ */
+struct pending_tx_info {
+	struct xen_netif_tx_request req; /* coalesced tx request */
+	pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX
+				  * if it is head of one or more tx
+				  * reqs
+				  */
+};
+
+#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
+#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
+
+struct xenvif_rx_meta {
+	int id;
+	int size;
+	int gso_size;
+};
+
+/* Discriminate from any valid pending_idx value. */
+#define INVALID_PENDING_IDX 0xFFFF
+
+#define MAX_BUFFER_OFFSET PAGE_SIZE
+
+#define MAX_PENDING_REQS 256
 
 struct xenvif {
 	/* Unique identifier for this interface. */
 	domid_t          domid;
 	unsigned int     handle;
 
-	/* Reference to netback processing backend. */
-	struct xen_netbk *netbk;
+	/* Use NAPI for guest TX */
+	struct napi_struct napi;
+	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
+	unsigned int tx_irq;
+	/* Only used when feature-split-event-channels = 1 */
+	char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
+	struct xen_netif_tx_back_ring tx;
+	struct sk_buff_head tx_queue;
+	struct page *mmap_pages[MAX_PENDING_REQS];
+	pending_ring_idx_t pending_prod;
+	pending_ring_idx_t pending_cons;
+	u16 pending_ring[MAX_PENDING_REQS];
+	struct pending_tx_info pending_tx_info[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];
 
-	u8               fe_dev_addr[6];
 
+	/* Use kthread for guest RX */
+	struct task_struct *task;
+	wait_queue_head_t wq;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
-	unsigned int tx_irq;
 	unsigned int rx_irq;
 	/* Only used when feature-split-event-channels = 1 */
-	char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
 	char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
+	struct xen_netif_rx_back_ring rx;
+	struct sk_buff_head rx_queue;
 
-	/* List of frontends to notify after a batch of frames sent. */
-	struct list_head notify_list;
+	/* Allow xenvif_start_xmit() to peek ahead in the rx request
+	 * ring.  This is a prediction of what rx_req_cons will be
+	 * once all queued skbs are put on the ring.
+	 */
+	RING_IDX rx_req_cons_peek;
+
+	/* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
+	 * head/fragment page uses 2 copy operations because it
+	 * straddles two buffers in the frontend.
+	 */
+	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
+	struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
 
-	/* The shared rings and indexes. */
-	struct xen_netif_tx_back_ring tx;
-	struct xen_netif_rx_back_ring rx;
+
+	u8               fe_dev_addr[6];
 
 	/* Frontend feature information. */
 	u8 can_sg:1;
@@ -80,13 +158,6 @@ struct xenvif {
 	/* Internal feature information. */
 	u8 can_queue:1;	    /* can queue packets for receiver? */
 
-	/*
-	 * Allow xenvif_start_xmit() to peek ahead in the rx request
-	 * ring.  This is a prediction of what rx_req_cons will be
-	 * once all queued skbs are put on the ring.
-	 */
-	RING_IDX rx_req_cons_peek;
-
 	/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
 	unsigned long   credit_bytes;
 	unsigned long   credit_usec;
@@ -97,11 +168,7 @@ struct xenvif {
 	unsigned long rx_gso_checksum_fixup;
 
 	/* Miscellaneous private stuff. */
-	struct list_head schedule_list;
-	atomic_t         refcnt;
 	struct net_device *dev;
-
-	wait_queue_head_t waiting_to_free;
 };
 
 static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
@@ -109,9 +176,6 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
 	return to_xenbus_device(vif->dev->dev.parent);
 }
 
-#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
-#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
-
 struct xenvif *xenvif_alloc(struct device *parent,
 			    domid_t domid,
 			    unsigned int handle);
@@ -121,9 +185,6 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 		   unsigned int rx_evtchn);
 void xenvif_disconnect(struct xenvif *vif);
 
-void xenvif_get(struct xenvif *vif);
-void xenvif_put(struct xenvif *vif);
-
 int xenvif_xenbus_init(void);
 void xenvif_xenbus_fini(void);
 
@@ -139,18 +200,8 @@ int xen_netbk_map_frontend_rings(struct xenvif *vif,
 				 grant_ref_t tx_ring_ref,
 				 grant_ref_t rx_ring_ref);
 
-/* (De)Register a xenvif with the netback backend. */
-void xen_netbk_add_xenvif(struct xenvif *vif);
-void xen_netbk_remove_xenvif(struct xenvif *vif);
-
-/* (De)Schedule backend processing for a xenvif */
-void xen_netbk_schedule_xenvif(struct xenvif *vif);
-void xen_netbk_deschedule_xenvif(struct xenvif *vif);
-
 /* Check for SKBs from frontend and schedule backend processing */
 void xen_netbk_check_rx_xenvif(struct xenvif *vif);
-/* Receive an SKB from the frontend */
-void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb);
 
 /* Queue an SKB for transmission to the frontend */
 void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb);
@@ -163,6 +214,11 @@ void xenvif_carrier_off(struct xenvif *vif);
 /* Returns number of ring slots required to send an skb to the frontend */
 unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
 
+int xen_netbk_tx_action(struct xenvif *vif, int budget);
+void xen_netbk_rx_action(struct xenvif *vif);
+
+int xen_netbk_kthread(void *data);
+
 extern bool separate_tx_rx_irq;
 
 #endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 087d2db0389..44d6b707c77 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -30,6 +30,7 @@
 
 #include "common.h"
 
+#include <linux/kthread.h>
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
@@ -38,17 +39,7 @@
 #include <asm/xen/hypercall.h>
 
 #define XENVIF_QUEUE_LENGTH 32
-
-void xenvif_get(struct xenvif *vif)
-{
-	atomic_inc(&vif->refcnt);
-}
-
-void xenvif_put(struct xenvif *vif)
-{
-	if (atomic_dec_and_test(&vif->refcnt))
-		wake_up(&vif->waiting_to_free);
-}
+#define XENVIF_NAPI_WEIGHT  64
 
 int xenvif_schedulable(struct xenvif *vif)
 {
@@ -64,21 +55,55 @@ static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
 {
 	struct xenvif *vif = dev_id;
 
-	if (vif->netbk == NULL)
-		return IRQ_HANDLED;
-
-	xen_netbk_schedule_xenvif(vif);
+	if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
+		napi_schedule(&vif->napi);
 
 	return IRQ_HANDLED;
 }
 
+static int xenvif_poll(struct napi_struct *napi, int budget)
+{
+	struct xenvif *vif = container_of(napi, struct xenvif, napi);
+	int work_done;
+
+	work_done = xen_netbk_tx_action(vif, budget);
+
+	if (work_done < budget) {
+		int more_to_do = 0;
+		unsigned long flags;
+
+		/* It is necessary to disable IRQ before calling
+		 * RING_HAS_UNCONSUMED_REQUESTS. Otherwise we might
+		 * lose event from the frontend.
+		 *
+		 * Consider:
+		 *   RING_HAS_UNCONSUMED_REQUESTS
+		 *   <frontend generates event to trigger napi_schedule>
+		 *   __napi_complete
+		 *
+		 * This handler is still in scheduled state so the
+		 * event has no effect at all. After __napi_complete
+		 * this handler is descheduled and cannot get
+		 * scheduled again. We lose event in this case and the ring
+		 * will be completely stalled.
+		 */
+
+		local_irq_save(flags);
+
+		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
+		if (!more_to_do)
+			__napi_complete(napi);
+
+		local_irq_restore(flags);
+	}
+
+	return work_done;
+}
+
 static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
 {
 	struct xenvif *vif = dev_id;
 
-	if (vif->netbk == NULL)
-		return IRQ_HANDLED;
-
 	if (xenvif_rx_schedulable(vif))
 		netif_wake_queue(vif->dev);
 
@@ -99,7 +124,8 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	BUG_ON(skb->dev != dev);
 
-	if (vif->netbk == NULL)
+	/* Drop the packet if vif is not ready */
+	if (vif->task == NULL)
 		goto drop;
 
 	/* Drop the packet if the target domain has no receive buffers. */
@@ -108,7 +134,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Reserve ring slots for the worst-case number of fragments. */
 	vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb);
-	xenvif_get(vif);
 
 	if (vif->can_queue && xen_netbk_must_stop_queue(vif))
 		netif_stop_queue(dev);
@@ -123,11 +148,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb)
-{
-	netif_rx_ni(skb);
-}
-
 void xenvif_notify_tx_completion(struct xenvif *vif)
 {
 	if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
@@ -142,7 +162,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 
 static void xenvif_up(struct xenvif *vif)
 {
-	xen_netbk_add_xenvif(vif);
+	napi_enable(&vif->napi);
 	enable_irq(vif->tx_irq);
 	if (vif->tx_irq != vif->rx_irq)
 		enable_irq(vif->rx_irq);
@@ -151,12 +171,11 @@ static void xenvif_up(struct xenvif *vif)
 
 static void xenvif_down(struct xenvif *vif)
 {
+	napi_disable(&vif->napi);
 	disable_irq(vif->tx_irq);
 	if (vif->tx_irq != vif->rx_irq)
 		disable_irq(vif->rx_irq);
 	del_timer_sync(&vif->credit_timeout);
-	xen_netbk_deschedule_xenvif(vif);
-	xen_netbk_remove_xenvif(vif);
 }
 
 static int xenvif_open(struct net_device *dev)
@@ -272,11 +291,12 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	struct net_device *dev;
 	struct xenvif *vif;
 	char name[IFNAMSIZ] = {};
+	int i;
 
 	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
 	dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
 	if (dev == NULL) {
-		pr_warn("Could not allocate netdev\n");
+		pr_warn("Could not allocate netdev for %s\n", name);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -285,14 +305,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif = netdev_priv(dev);
 	vif->domid  = domid;
 	vif->handle = handle;
-	vif->netbk  = NULL;
 	vif->can_sg = 1;
 	vif->csum = 1;
-	atomic_set(&vif->refcnt, 1);
-	init_waitqueue_head(&vif->waiting_to_free);
 	vif->dev = dev;
-	INIT_LIST_HEAD(&vif->schedule_list);
-	INIT_LIST_HEAD(&vif->notify_list);
 
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
 	vif->credit_usec  = 0UL;
@@ -307,6 +322,16 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 
 	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
 
+	skb_queue_head_init(&vif->rx_queue);
+	skb_queue_head_init(&vif->tx_queue);
+
+	vif->pending_cons = 0;
+	vif->pending_prod = MAX_PENDING_REQS;
+	for (i = 0; i < MAX_PENDING_REQS; i++)
+		vif->pending_ring[i] = i;
+	for (i = 0; i < MAX_PENDING_REQS; i++)
+		vif->mmap_pages[i] = NULL;
+
 	/*
 	 * Initialise a dummy MAC address. We choose the numerically
 	 * largest non-broadcast address to prevent the address getting
@@ -316,6 +341,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	memset(dev->dev_addr, 0xFF, ETH_ALEN);
 	dev->dev_addr[0] &= ~0x01;
 
+	netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT);
+
 	netif_carrier_off(dev);
 
 	err = register_netdev(dev);
@@ -377,7 +404,14 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 		disable_irq(vif->rx_irq);
 	}
 
-	xenvif_get(vif);
+	init_waitqueue_head(&vif->wq);
+	vif->task = kthread_create(xen_netbk_kthread,
+				   (void *)vif, vif->dev->name);
+	if (IS_ERR(vif->task)) {
+		pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
+		err = PTR_ERR(vif->task);
+		goto err_rx_unbind;
+	}
 
 	rtnl_lock();
 	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
@@ -388,7 +422,13 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 		xenvif_up(vif);
 	rtnl_unlock();
 
+	wake_up_process(vif->task);
+
 	return 0;
+
+err_rx_unbind:
+	unbind_from_irqhandler(vif->rx_irq, vif);
+	vif->rx_irq = 0;
 err_tx_unbind:
 	unbind_from_irqhandler(vif->tx_irq, vif);
 	vif->tx_irq = 0;
@@ -408,7 +448,6 @@ void xenvif_carrier_off(struct xenvif *vif)
 	if (netif_running(dev))
 		xenvif_down(vif);
 	rtnl_unlock();
-	xenvif_put(vif);
 }
 
 void xenvif_disconnect(struct xenvif *vif)
@@ -422,9 +461,6 @@ void xenvif_disconnect(struct xenvif *vif)
 	if (netif_carrier_ok(vif->dev))
 		xenvif_carrier_off(vif);
 
-	atomic_dec(&vif->refcnt);
-	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
-
 	if (vif->tx_irq) {
 		if (vif->tx_irq == vif->rx_irq)
 			unbind_from_irqhandler(vif->tx_irq, vif);
@@ -438,6 +474,11 @@ void xenvif_disconnect(struct xenvif *vif)
 		need_module_put = 1;
 	}
 
+	if (vif->task)
+		kthread_stop(vif->task);
+
+	netif_napi_del(&vif->napi);
+
 	unregister_netdev(vif->dev);
 
 	xen_netbk_unmap_frontend_rings(vif);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 91f163d03a4..44ccc674c02 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -70,116 +70,25 @@ module_param(fatal_skb_slots, uint, 0444);
  */
 #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; /* 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
-				  */
-};
-
-struct netbk_rx_meta {
-	int id;
-	int size;
-	int gso_size;
-};
-
-#define MAX_PENDING_REQS 256
-
-/* Discriminate from any valid pending_idx value. */
-#define INVALID_PENDING_IDX 0xFFFF
-
-#define MAX_BUFFER_OFFSET PAGE_SIZE
-
-struct xen_netbk {
-	wait_queue_head_t wq;
-	struct task_struct *task;
-
-	struct sk_buff_head rx_queue;
-	struct sk_buff_head tx_queue;
-
-	struct timer_list net_timer;
-
-	struct page *mmap_pages[MAX_PENDING_REQS];
-
-	pending_ring_idx_t pending_prod;
-	pending_ring_idx_t pending_cons;
-	struct list_head net_schedule_list;
-
-	/* Protect the net_schedule_list in netif. */
-	spinlock_t net_schedule_list_lock;
-
-	atomic_t netfront_count;
-
-	struct pending_tx_info pending_tx_info[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];
-
-	/*
-	 * Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
-	 * head/fragment page uses 2 copy operations because it
-	 * straddles two buffers in the frontend.
-	 */
-	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
-	struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
-};
-
-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;
-	int min_netfront_count;
-	int min_group = 0;
-	struct xen_netbk *netbk;
-
-	min_netfront_count = atomic_read(&xen_netbk[0].netfront_count);
-	for (i = 0; i < xen_netbk_group_nr; i++) {
-		int netfront_count = atomic_read(&xen_netbk[i].netfront_count);
-		if (netfront_count < min_netfront_count) {
-			min_group = i;
-			min_netfront_count = netfront_count;
-		}
-	}
-
-	netbk = &xen_netbk[min_group];
-
-	vif->netbk = netbk;
-	atomic_inc(&netbk->netfront_count);
-}
-
-void xen_netbk_remove_xenvif(struct xenvif *vif)
+static inline int pending_tx_is_head(struct xenvif *vif, RING_IDX idx)
 {
-	struct xen_netbk *netbk = vif->netbk;
-	vif->netbk = NULL;
-	atomic_dec(&netbk->netfront_count);
+	return vif->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX;
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+static void xen_netbk_idx_release(struct xenvif *vif, u16 pending_idx,
 				  u8 status);
 static void make_tx_response(struct xenvif *vif,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
+
+static inline int tx_work_todo(struct xenvif *vif);
+static inline int rx_work_todo(struct xenvif *vif);
+
 static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
 					     u16      id,
 					     s8       st,
@@ -187,16 +96,16 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
 					     u16      size,
 					     u16      flags);
 
-static inline unsigned long idx_to_pfn(struct xen_netbk *netbk,
+static inline unsigned long idx_to_pfn(struct xenvif *vif,
 				       u16 idx)
 {
-	return page_to_pfn(netbk->mmap_pages[idx]);
+	return page_to_pfn(vif->mmap_pages[idx]);
 }
 
-static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk,
+static inline unsigned long idx_to_kaddr(struct xenvif *vif,
 					 u16 idx)
 {
-	return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx));
+	return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx));
 }
 
 /*
@@ -224,15 +133,10 @@ static inline pending_ring_idx_t pending_index(unsigned i)
 	return i & (MAX_PENDING_REQS-1);
 }
 
-static inline pending_ring_idx_t nr_pending_reqs(struct xen_netbk *netbk)
+static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
 {
 	return MAX_PENDING_REQS -
-		netbk->pending_prod + netbk->pending_cons;
-}
-
-static void xen_netbk_kick_thread(struct xen_netbk *netbk)
-{
-	wake_up(&netbk->wq);
+		vif->pending_prod + vif->pending_cons;
 }
 
 static int max_required_rx_slots(struct xenvif *vif)
@@ -364,15 +268,15 @@ struct netrx_pending_operations {
 	unsigned copy_prod, copy_cons;
 	unsigned meta_prod, meta_cons;
 	struct gnttab_copy *copy;
-	struct netbk_rx_meta *meta;
+	struct xenvif_rx_meta *meta;
 	int copy_off;
 	grant_ref_t copy_gref;
 };
 
-static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif,
-						struct netrx_pending_operations *npo)
+static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
+						 struct netrx_pending_operations *npo)
 {
-	struct netbk_rx_meta *meta;
+	struct xenvif_rx_meta *meta;
 	struct xen_netif_rx_request *req;
 
 	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
@@ -398,7 +302,7 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 				unsigned long offset, int *head)
 {
 	struct gnttab_copy *copy_gop;
-	struct netbk_rx_meta *meta;
+	struct xenvif_rx_meta *meta;
 	unsigned long bytes;
 
 	/* Data must not cross a page boundary. */
@@ -434,15 +338,15 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 
 		copy_gop = npo->copy + npo->copy_prod++;
 		copy_gop->flags = GNTCOPY_dest_gref;
+		copy_gop->len = bytes;
+
 		copy_gop->source.domid = DOMID_SELF;
 		copy_gop->source.u.gmfn = virt_to_mfn(page_address(page));
-
 		copy_gop->source.offset = offset;
-		copy_gop->dest.domid = vif->domid;
 
+		copy_gop->dest.domid = vif->domid;
 		copy_gop->dest.offset = npo->copy_off;
 		copy_gop->dest.u.ref = npo->copy_gref;
-		copy_gop->len = bytes;
 
 		npo->copy_off += bytes;
 		meta->size += bytes;
@@ -485,7 +389,7 @@ static int netbk_gop_skb(struct sk_buff *skb,
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	int i;
 	struct xen_netif_rx_request *req;
-	struct netbk_rx_meta *meta;
+	struct xenvif_rx_meta *meta;
 	unsigned char *data;
 	int head = 1;
 	int old_meta_prod;
@@ -565,7 +469,7 @@ static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots,
 }
 
 static void netbk_add_frag_responses(struct xenvif *vif, int status,
-				     struct netbk_rx_meta *meta,
+				     struct xenvif_rx_meta *meta,
 				     int nr_meta_slots)
 {
 	int i;
@@ -594,9 +498,13 @@ struct skb_cb_overlay {
 	int meta_slots_used;
 };
 
-static void xen_netbk_rx_action(struct xen_netbk *netbk)
+static void xen_netbk_kick_thread(struct xenvif *vif)
+{
+	wake_up(&vif->wq);
+}
+
+void xen_netbk_rx_action(struct xenvif *vif)
 {
-	struct xenvif *vif = NULL, *tmp;
 	s8 status;
 	u16 flags;
 	struct xen_netif_rx_response *resp;
@@ -608,17 +516,18 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 	int count;
 	unsigned long offset;
 	struct skb_cb_overlay *sco;
+	int need_to_notify = 0;
 
 	struct netrx_pending_operations npo = {
-		.copy  = netbk->grant_copy_op,
-		.meta  = netbk->meta,
+		.copy  = vif->grant_copy_op,
+		.meta  = vif->meta,
 	};
 
 	skb_queue_head_init(&rxq);
 
 	count = 0;
 
-	while ((skb = skb_dequeue(&netbk->rx_queue)) != NULL) {
+	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
 		vif = netdev_priv(skb->dev);
 		nr_frags = skb_shinfo(skb)->nr_frags;
 
@@ -635,27 +544,27 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 			break;
 	}
 
-	BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta));
+	BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
 
 	if (!npo.copy_prod)
 		return;
 
-	BUG_ON(npo.copy_prod > ARRAY_SIZE(netbk->grant_copy_op));
-	gnttab_batch_copy(netbk->grant_copy_op, npo.copy_prod);
+	BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op));
+	gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
 
 	while ((skb = __skb_dequeue(&rxq)) != NULL) {
 		sco = (struct skb_cb_overlay *)skb->cb;
 
 		vif = netdev_priv(skb->dev);
 
-		if (netbk->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
+		if (vif->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
 			resp = RING_GET_RESPONSE(&vif->rx,
-						vif->rx.rsp_prod_pvt++);
+						 vif->rx.rsp_prod_pvt++);
 
 			resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data;
 
-			resp->offset = netbk->meta[npo.meta_cons].gso_size;
-			resp->id = netbk->meta[npo.meta_cons].id;
+			resp->offset = vif->meta[npo.meta_cons].gso_size;
+			resp->id = vif->meta[npo.meta_cons].id;
 			resp->status = sco->meta_slots_used;
 
 			npo.meta_cons++;
@@ -680,12 +589,12 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 			flags |= XEN_NETRXF_data_validated;
 
 		offset = 0;
-		resp = make_rx_response(vif, netbk->meta[npo.meta_cons].id,
+		resp = make_rx_response(vif, vif->meta[npo.meta_cons].id,
 					status, offset,
-					netbk->meta[npo.meta_cons].size,
+					vif->meta[npo.meta_cons].size,
 					flags);
 
-		if (netbk->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
+		if (vif->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
 			struct xen_netif_extra_info *gso =
 				(struct xen_netif_extra_info *)
 				RING_GET_RESPONSE(&vif->rx,
@@ -693,7 +602,7 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 
 			resp->flags |= XEN_NETRXF_extra_info;
 
-			gso->u.gso.size = netbk->meta[npo.meta_cons].gso_size;
+			gso->u.gso.size = vif->meta[npo.meta_cons].gso_size;
 			gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
 			gso->u.gso.pad = 0;
 			gso->u.gso.features = 0;
@@ -703,112 +612,33 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
 		}
 
 		netbk_add_frag_responses(vif, status,
-					 netbk->meta + npo.meta_cons + 1,
+					 vif->meta + npo.meta_cons + 1,
 					 sco->meta_slots_used);
 
 		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
 
+		if (ret)
+			need_to_notify = 1;
+
 		xenvif_notify_tx_completion(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) {
+	if (need_to_notify)
 		notify_remote_via_irq(vif->rx_irq);
-		list_del_init(&vif->notify_list);
-		xenvif_put(vif);
-	}
 
 	/* More work to do? */
-	if (!skb_queue_empty(&netbk->rx_queue) &&
-			!timer_pending(&netbk->net_timer))
-		xen_netbk_kick_thread(netbk);
+	if (!skb_queue_empty(&vif->rx_queue))
+		xen_netbk_kick_thread(vif);
 }
 
 void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb)
 {
-	struct xen_netbk *netbk = vif->netbk;
+	skb_queue_tail(&vif->rx_queue, skb);
 
-	skb_queue_tail(&netbk->rx_queue, skb);
-
-	xen_netbk_kick_thread(netbk);
-}
-
-static void xen_netbk_alarm(unsigned long data)
-{
-	struct xen_netbk *netbk = (struct xen_netbk *)data;
-	xen_netbk_kick_thread(netbk);
-}
-
-static int __on_net_schedule_list(struct xenvif *vif)
-{
-	return !list_empty(&vif->schedule_list);
-}
-
-/* Must be called with net_schedule_list_lock held */
-static void remove_from_net_schedule_list(struct xenvif *vif)
-{
-	if (likely(__on_net_schedule_list(vif))) {
-		list_del_init(&vif->schedule_list);
-		xenvif_put(vif);
-	}
-}
-
-static struct xenvif *poll_net_schedule_list(struct xen_netbk *netbk)
-{
-	struct xenvif *vif = NULL;
-
-	spin_lock_irq(&netbk->net_schedule_list_lock);
-	if (list_empty(&netbk->net_schedule_list))
-		goto out;
-
-	vif = list_first_entry(&netbk->net_schedule_list,
-			       struct xenvif, schedule_list);
-	if (!vif)
-		goto out;
-
-	xenvif_get(vif);
-
-	remove_from_net_schedule_list(vif);
-out:
-	spin_unlock_irq(&netbk->net_schedule_list_lock);
-	return vif;
-}
-
-void xen_netbk_schedule_xenvif(struct xenvif *vif)
-{
-	unsigned long flags;
-	struct xen_netbk *netbk = vif->netbk;
-
-	if (__on_net_schedule_list(vif))
-		goto kick;
-
-	spin_lock_irqsave(&netbk->net_schedule_list_lock, flags);
-	if (!__on_net_schedule_list(vif) &&
-	    likely(xenvif_schedulable(vif))) {
-		list_add_tail(&vif->schedule_list, &netbk->net_schedule_list);
-		xenvif_get(vif);
-	}
-	spin_unlock_irqrestore(&netbk->net_schedule_list_lock, flags);
-
-kick:
-	smp_mb();
-	if ((nr_pending_reqs(netbk) < (MAX_PENDING_REQS/2)) &&
-	    !list_empty(&netbk->net_schedule_list))
-		xen_netbk_kick_thread(netbk);
-}
-
-void xen_netbk_deschedule_xenvif(struct xenvif *vif)
-{
-	struct xen_netbk *netbk = vif->netbk;
-	spin_lock_irq(&netbk->net_schedule_list_lock);
-	remove_from_net_schedule_list(vif);
-	spin_unlock_irq(&netbk->net_schedule_list_lock);
+	xen_netbk_kick_thread(vif);
 }
 
 void xen_netbk_check_rx_xenvif(struct xenvif *vif)
@@ -818,7 +648,7 @@ void xen_netbk_check_rx_xenvif(struct xenvif *vif)
 	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
 
 	if (more_to_do)
-		xen_netbk_schedule_xenvif(vif);
+		napi_schedule(&vif->napi);
 }
 
 static void tx_add_credit(struct xenvif *vif)
@@ -860,15 +690,12 @@ static void netbk_tx_err(struct xenvif *vif,
 		txp = RING_GET_REQUEST(&vif->tx, cons++);
 	} while (1);
 	vif->tx.req_cons = cons;
-	xen_netbk_check_rx_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,
@@ -969,19 +796,20 @@ static int netbk_count_requests(struct xenvif *vif,
 	return slots;
 }
 
-static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk,
+static struct page *xen_netbk_alloc_page(struct xenvif *vif,
 					 u16 pending_idx)
 {
 	struct page *page;
-	page = alloc_page(GFP_KERNEL|__GFP_COLD);
+
+	page = alloc_page(GFP_ATOMIC|__GFP_COLD);
 	if (!page)
 		return NULL;
-	netbk->mmap_pages[pending_idx] = page;
+	vif->mmap_pages[pending_idx] = page;
+
 	return page;
 }
 
-static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
-						  struct xenvif *vif,
+static struct gnttab_copy *xen_netbk_get_requests(struct xenvif *vif,
 						  struct sk_buff *skb,
 						  struct xen_netif_tx_request *txp,
 						  struct gnttab_copy *gop)
@@ -1012,9 +840,9 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 	for (shinfo->nr_frags = slot = start; slot < nr_slots;
 	     shinfo->nr_frags++) {
 		struct pending_tx_info *pending_tx_info =
-			netbk->pending_tx_info;
+			vif->pending_tx_info;
 
-		page = alloc_page(GFP_KERNEL|__GFP_COLD);
+		page = alloc_page(GFP_ATOMIC|__GFP_COLD);
 		if (!page)
 			goto err;
 
@@ -1049,21 +877,18 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 				gop->len = txp->size;
 				dst_offset += gop->len;
 
-				index = pending_index(netbk->pending_cons++);
+				index = pending_index(vif->pending_cons++);
 
-				pending_idx = netbk->pending_ring[index];
+				pending_idx = vif->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);
+				vif->mmap_pages[pending_idx] = (void *)(~0UL);
 				pending_tx_info[pending_idx].head =
 					INVALID_PENDING_RING_IDX;
 
@@ -1083,7 +908,7 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 		first->req.offset = 0;
 		first->req.size = dst_offset;
 		first->head = start_idx;
-		netbk->mmap_pages[head_idx] = page;
+		vif->mmap_pages[head_idx] = page;
 		frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx);
 	}
 
@@ -1093,18 +918,18 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 err:
 	/* Unwind, freeing all pages and sending error responses. */
 	while (shinfo->nr_frags-- > start) {
-		xen_netbk_idx_release(netbk,
+		xen_netbk_idx_release(vif,
 				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);
+		xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
 
 	return NULL;
 }
 
-static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
+static int xen_netbk_tx_check_gop(struct xenvif *vif,
 				  struct sk_buff *skb,
 				  struct gnttab_copy **gopp)
 {
@@ -1119,7 +944,7 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 	/* Check status of header. */
 	err = gop->status;
 	if (unlikely(err))
-		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
+		xen_netbk_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);
@@ -1129,7 +954,7 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 		pending_ring_idx_t head;
 
 		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
-		tx_info = &netbk->pending_tx_info[pending_idx];
+		tx_info = &vif->pending_tx_info[pending_idx];
 		head = tx_info->head;
 
 		/* Check error status: if okay then remember grant handle. */
@@ -1137,18 +962,19 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 			newerr = (++gop)->status;
 			if (newerr)
 				break;
-			peek = netbk->pending_ring[pending_index(++head)];
-		} while (!pending_tx_is_head(netbk, peek));
+			peek = vif->pending_ring[pending_index(++head)];
+		} while (!pending_tx_is_head(vif, peek));
 
 		if (likely(!newerr)) {