xen network backend driver

netback is the host side counterpart to the frontend driver in
drivers/net/xen-netfront.c. The PV protocol is also implemented by
frontend drivers in other OSes too, such as the BSDs and even Windows.

The patch is based on the driver from the xen.git pvops kernel tree but
has been put through the checkpatch.pl wringer plus several manual
cleanup passes and review iterations. The driver has been moved from
drivers/xen/netback to drivers/net/xen-netback.

One major change from xen.git is that the guest transmit path (i.e. what
looks like receive to netback) has been significantly reworked to remove
the dependency on the out of tree PageForeign page flag (a core kernel
patch which enables a per page destructor callback on the final
put_page). This page flag was used in order to implement a grant map
based transmit path (where guest pages are mapped directly into SKB
frags). Instead this version of netback uses grant copy operations into
regular memory belonging to the backend domain. Reinstating the grant
map functionality is something which I would like to revisit in the
future.

Note that this driver depends on 2e820f58f7ad "xen/irq: implement
bind_interdomain_evtchn_to_irqhandler for backend drivers" which is in
linux next via the "xen-two" tree and is intended for the 2.6.39 merge
window:
        git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git stable/backends
this branch has only that single commit since 2.6.38-rc2 and is safe for
cross merging into the net branch.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 2866 insertions, 16 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 46e1b1a28b8..797d6819672 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2953,12 +2953,38 @@ config XEN_NETDEV_FRONTEND
 	select XEN_XENBUS_FRONTEND
 	default y
 	help
-	  The network device frontend driver allows the kernel to
-	  access network devices exported exported by a virtual
-	  machine containing a physical network device driver. The
-	  frontend driver is intended for unprivileged guest domains;
-	  if you are compiling a kernel for a Xen guest, you almost
-	  certainly want to enable this.
+	  This driver provides support for Xen paravirtual network
+	  devices exported by a Xen network driver domain (often
+	  domain 0).
+
+	  The corresponding Linux backend driver is enabled by the
+	  CONFIG_XEN_NETDEV_BACKEND option.
+
+	  If you are compiling a kernel for use as Xen guest, you
+	  should say Y here. To compile this driver as a module, chose
+	  M here: the module will be called xen-netfront.
+
+config XEN_NETDEV_BACKEND
+	tristate "Xen backend network device"
+	depends on XEN_BACKEND
+	help
+	  This driver allows the kernel to act as a Xen network driver
+	  domain which exports paravirtual network devices to other
+	  Xen domains. These devices can be accessed by any operating
+	  system that implements a compatible front end.
+
+	  The corresponding Linux frontend driver is enabled by the
+	  CONFIG_XEN_NETDEV_FRONTEND configuration option.
+
+	  The backend driver presents a standard network device
+	  endpoint for each paravirtual network device to the driver
+	  domain network stack. These can then be bridged or routed
+	  etc in order to provide full network connectivity.
+
+	  If you are compiling a kernel to run in a Xen network driver
+	  domain (often this is domain 0) you should say Y here. To
+	  compile this driver as a module, chose M here: the module
+	  will be called xen-netback.
 
 config ISERIES_VETH
 	tristate "iSeries Virtual Ethernet driver support"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 7c2171179f9..01b604ad155 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -172,6 +172,7 @@ obj-$(CONFIG_SLIP) += slip.o
 obj-$(CONFIG_SLHC) += slhc.o
 
 obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o
+obj-$(CONFIG_XEN_NETDEV_BACKEND) += xen-netback/
 
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_IFB) += ifb.o
diff --git a/drivers/net/xen-netback/Makefile b/drivers/net/xen-netback/Makefile
new file mode 100644
index 00000000000..e346e8125ef
--- /dev/null
+++ b/drivers/net/xen-netback/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o
+
+xen-netback-y := netback.o xenbus.o interface.o
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
new file mode 100644
index 00000000000..5d7bbf2b2ee
--- /dev/null
+++ b/drivers/net/xen-netback/common.h
@@ -0,0 +1,161 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_NETBACK__COMMON_H__
+#define __XEN_NETBACK__COMMON_H__
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+
+#include <xen/interface/io/netif.h>
+#include <xen/interface/grant_table.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+
+struct xen_netbk;
+
+struct xenvif {
+	/* Unique identifier for this interface. */
+	domid_t          domid;
+	unsigned int     handle;
+
+	/* Reference to netback processing backend. */
+	struct xen_netbk *netbk;
+
+	u8               fe_dev_addr[6];
+
+	/* Physical parameters of the comms window. */
+	grant_handle_t   tx_shmem_handle;
+	grant_ref_t      tx_shmem_ref;
+	grant_handle_t   rx_shmem_handle;
+	grant_ref_t      rx_shmem_ref;
+	unsigned int     irq;
+
+	/* List of frontends to notify after a batch of frames sent. */
+	struct list_head notify_list;
+
+	/* The shared rings and indexes. */
+	struct xen_netif_tx_back_ring tx;
+	struct xen_netif_rx_back_ring rx;
+	struct vm_struct *tx_comms_area;
+	struct vm_struct *rx_comms_area;
+
+	/* Flags that must not be set in dev->features */
+	u32 features_disabled;
+
+	/* Frontend feature information. */
+	u8 can_sg:1;
+	u8 gso:1;
+	u8 gso_prefix:1;
+	u8 csum:1;
+
+	/* 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;
+	unsigned long   remaining_credit;
+	struct timer_list credit_timeout;
+
+	/* Statistics */
+	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;
+};
+
+#define XEN_NETIF_TX_RING_SIZE __RING_SIZE((struct xen_netif_tx_sring *)0, PAGE_SIZE)
+#define XEN_NETIF_RX_RING_SIZE __RING_SIZE((struct xen_netif_rx_sring *)0, PAGE_SIZE)
+
+struct xenvif *xenvif_alloc(struct device *parent,
+			    domid_t domid,
+			    unsigned int handle);
+
+int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int evtchn);
+void xenvif_disconnect(struct xenvif *vif);
+
+void xenvif_get(struct xenvif *vif);
+void xenvif_put(struct xenvif *vif);
+
+int xenvif_xenbus_init(void);
+
+int xenvif_schedulable(struct xenvif *vif);
+
+int xen_netbk_rx_ring_full(struct xenvif *vif);
+
+int xen_netbk_must_stop_queue(struct xenvif *vif);
+
+/* (Un)Map communication rings. */
+void xen_netbk_unmap_frontend_rings(struct xenvif *vif);
+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);
+/* Notify xenvif that ring now has space to send an skb to the frontend */
+void xenvif_notify_tx_completion(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);
+
+#endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
new file mode 100644
index 00000000000..de569cc19da
--- /dev/null
+++ b/drivers/net/xen-netback/interface.c
@@ -0,0 +1,424 @@
+/*
+ * Network-device interface management.
+ *
+ * Copyright (c) 2004-2005, Keir Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "common.h"
+
+#include <linux/ethtool.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+
+#include <xen/events.h>
+#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);
+}
+
+int xenvif_schedulable(struct xenvif *vif)
+{
+	return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
+}
+
+static int xenvif_rx_schedulable(struct xenvif *vif)
+{
+	return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif);
+}
+
+static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
+{
+	struct xenvif *vif = dev_id;
+
+	if (vif->netbk == NULL)
+		return IRQ_NONE;
+
+	xen_netbk_schedule_xenvif(vif);
+
+	if (xenvif_rx_schedulable(vif))
+		netif_wake_queue(vif->dev);
+
+	return IRQ_HANDLED;
+}
+
+static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+
+	BUG_ON(skb->dev != dev);
+
+	if (vif->netbk == NULL)
+		goto drop;
+
+	/* Drop the packet if the target domain has no receive buffers. */
+	if (!xenvif_rx_schedulable(vif))
+		goto drop;
+
+	/* 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);
+
+	xen_netbk_queue_tx_skb(vif, skb);
+
+	return NETDEV_TX_OK;
+
+ drop:
+	vif->dev->stats.tx_dropped++;
+	dev_kfree_skb(skb);
+	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))
+		netif_wake_queue(vif->dev);
+}
+
+static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	return &vif->dev->stats;
+}
+
+static void xenvif_up(struct xenvif *vif)
+{
+	xen_netbk_add_xenvif(vif);
+	enable_irq(vif->irq);
+	xen_netbk_check_rx_xenvif(vif);
+}
+
+static void xenvif_down(struct xenvif *vif)
+{
+	disable_irq(vif->irq);
+	xen_netbk_deschedule_xenvif(vif);
+	xen_netbk_remove_xenvif(vif);
+}
+
+static int xenvif_open(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (netif_carrier_ok(dev))
+		xenvif_up(vif);
+	netif_start_queue(dev);
+	return 0;
+}
+
+static int xenvif_close(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (netif_carrier_ok(dev))
+		xenvif_down(vif);
+	netif_stop_queue(dev);
+	return 0;
+}
+
+static int xenvif_change_mtu(struct net_device *dev, int mtu)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN;
+
+	if (mtu > max)
+		return -EINVAL;
+	dev->mtu = mtu;
+	return 0;
+}
+
+static void xenvif_set_features(struct xenvif *vif)
+{
+	struct net_device *dev = vif->dev;
+	u32 features = dev->features;
+
+	if (vif->can_sg)
+		features |= NETIF_F_SG;
+	if (vif->gso || vif->gso_prefix)
+		features |= NETIF_F_TSO;
+	if (vif->csum)
+		features |= NETIF_F_IP_CSUM;
+
+	features &= ~(vif->features_disabled);
+
+	if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN)
+		dev->mtu = ETH_DATA_LEN;
+
+	dev->features = features;
+}
+
+static int xenvif_set_tx_csum(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->csum)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_IP_CSUM;
+	} else {
+		vif->features_disabled |= NETIF_F_IP_CSUM;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static int xenvif_set_sg(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->can_sg)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_SG;
+	} else {
+		vif->features_disabled |= NETIF_F_SG;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static int xenvif_set_tso(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->gso && !vif->gso_prefix)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_TSO;
+	} else {
+		vif->features_disabled |= NETIF_F_TSO;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static const struct xenvif_stat {
+	char name[ETH_GSTRING_LEN];
+	u16 offset;
+} xenvif_stats[] = {
+	{
+		"rx_gso_checksum_fixup",
+		offsetof(struct xenvif, rx_gso_checksum_fixup)
+	},
+};
+
+static int xenvif_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(xenvif_stats);
+	default:
+		return -EINVAL;
+	}
+}
+
+static void xenvif_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *stats, u64 * data)
+{
+	void *vif = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
+		data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
+}
+
+static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
+			memcpy(data + i * ETH_GSTRING_LEN,
+			       xenvif_stats[i].name, ETH_GSTRING_LEN);
+		break;
+	}
+}
+
+static struct ethtool_ops xenvif_ethtool_ops = {
+	.get_tx_csum	= ethtool_op_get_tx_csum,
+	.set_tx_csum	= xenvif_set_tx_csum,
+	.get_sg		= ethtool_op_get_sg,
+	.set_sg		= xenvif_set_sg,
+	.get_tso	= ethtool_op_get_tso,
+	.set_tso	= xenvif_set_tso,
+	.get_link	= ethtool_op_get_link,
+
+	.get_sset_count = xenvif_get_sset_count,
+	.get_ethtool_stats = xenvif_get_ethtool_stats,
+	.get_strings = xenvif_get_strings,
+};
+
+static struct net_device_ops xenvif_netdev_ops = {
+	.ndo_start_xmit	= xenvif_start_xmit,
+	.ndo_get_stats	= xenvif_get_stats,
+	.ndo_open	= xenvif_open,
+	.ndo_stop	= xenvif_close,
+	.ndo_change_mtu	= xenvif_change_mtu,
+};
+
+struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
+			    unsigned int handle)
+{
+	int err;
+	struct net_device *dev;
+	struct xenvif *vif;
+	char name[IFNAMSIZ] = {};
+
+	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");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	SET_NETDEV_DEV(dev, parent);
+
+	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;
+	init_timer(&vif->credit_timeout);
+	/* Initialize 'expires' now: it's used to track the credit window. */
+	vif->credit_timeout.expires = jiffies;
+
+	dev->netdev_ops	= &xenvif_netdev_ops;
+	xenvif_set_features(vif);
+	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
+
+	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
+
+	/*
+	 * Initialise a dummy MAC address. We choose the numerically
+	 * largest non-broadcast address to prevent the address getting
+	 * stolen by an Ethernet bridge for STP purposes.
+	 * (FE:FF:FF:FF:FF:FF)
+	 */
+	memset(dev->dev_addr, 0xFF, ETH_ALEN);
+	dev->dev_addr[0] &= ~0x01;
+
+	netif_carrier_off(dev);
+
+	err = register_netdev(dev);
+	if (err) {
+		netdev_warn(dev, "Could not register device: err=%d\n", err);
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	netdev_dbg(dev, "Successfully created xenvif\n");
+	return vif;
+}
+
+int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int evtchn)
+{
+	int err = -ENOMEM;
+
+	/* Already connected through? */
+	if (vif->irq)
+		return 0;
+
+	xenvif_set_features(vif);
+
+	err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
+	if (err < 0)
+		goto err;
+
+	err = bind_interdomain_evtchn_to_irqhandler(
+		vif->domid, evtchn, xenvif_interrupt, 0,
+		vif->dev->name, vif);
+	if (err < 0)
+		goto err_unmap;
+	vif->irq = err;
+	disable_irq(vif->irq);
+
+	xenvif_get(vif);
+
+	rtnl_lock();
+	netif_carrier_on(vif->dev);
+	if (netif_running(vif->dev))
+		xenvif_up(vif);
+	rtnl_unlock();
+
+	return 0;
+err_unmap:
+	xen_netbk_unmap_frontend_rings(vif);
+err:
+	return err;
+}
+
+void xenvif_disconnect(struct xenvif *vif)
+{
+	struct net_device *dev = vif->dev;
+	if (netif_carrier_ok(dev)) {
+		rtnl_lock();
+		netif_carrier_off(dev); /* discard queued packets */
+		if (netif_running(dev))
+			xenvif_down(vif);
+		rtnl_unlock();
+		xenvif_put(vif);
+	}
+
+	atomic_dec(&vif->refcnt);
+	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
+
+	del_timer_sync(&vif->credit_timeout);
+
+	if (vif->irq)
+		unbind_from_irqhandler(vif->irq, vif);
+
+	unregister_netdev(vif->dev);
+
+	xen_netbk_unmap_frontend_rings(vif);
+
+	free_netdev(vif->dev);
+}
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
new file mode 100644
index 00000000000..0e4851b8a77
--- /dev/null
+++ b/drivers/net/xen-netback/netback.c
@@ -0,0 +1,1745 @@
+/*
+ * Back-end of the driver for virtual network devices. This portion of the
+ * driver exports a 'unified' network-device interface that can be accessed
+ * by any operating system that implements a compatible front end. A
+ * reference front-end implementation can be found in:
+ *  drivers/net/xen-netfront.c
+ *
+ * Copyright (c) 2002-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "common.h"
+
+#include <linux/kthread.h>
+#include <linux/if_vlan.h>
+#include <linux/udp.h>
+
+#include <net/tcp.h>
+
+#include <xen/events.h>
+#include <xen/interface/memory.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+struct pending_tx_info {
+	struct xen_netif_tx_request req;
+	struct xenvif *vif;
+};
+typedef unsigned int pending_ring_idx_t;
+
+struct netbk_rx_meta {
+	int id;
+	int size;
+	int gso_size;
+};
+
+#define MAX_PENDING_REQS 256
+
+#define MAX_BUFFER_OFFSET PAGE_SIZE
+
+/* extra field used in struct page */
+union page_ext {
+	struct {
+#if BITS_PER_LONG < 64
+#define IDX_WIDTH   8
+#define GROUP_WIDTH (BITS_PER_LONG - IDX_WIDTH)
+		unsigned int group:GROUP_WIDTH;
+		unsigned int idx:IDX_WIDTH;
+#else
+		unsigned int group, idx;
+#endif
+	} e;
+	void *mapping;
+};
+
+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];
+	struct gnttab_copy tx_copy_ops[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;
+
+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)
+{
+	struct xen_netbk *netbk = vif->netbk;
+	vif->netbk = NULL;
+	atomic_dec(&netbk->netfront_count);
+}
+
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
+static void make_tx_response(struct xenvif *vif,
+			     struct xen_netif_tx_request *txp,
+			     s8       st);
+static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
+					     u16      id,
+					     s8       st,
+					     u16      offset,
+					     u16      size,
+					     u16      flags);
+
+static inline unsigned long idx_to_pfn(struct xen_netbk *netbk,
+				       unsigned int idx)
+{
+	return page_to_pfn(netbk->mmap_pages[idx]);
+}
+
+static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk,
+					 unsigned int idx)
+{
+	return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx));
+}
+
+/* extra field used in struct page */
+static inline void set_page_ext(struct page *pg, struct xen_netbk *netbk,
+				unsigned int idx)
+{
+	unsigned int group = netbk - xen_netbk;
+	union page_ext ext = { .e = { .group = group + 1, .idx = idx } };
+
+	BUILD_BUG_ON(sizeof(ext) > sizeof(ext.mapping));
+	pg->mapping = ext.mapping;
+}
+
+static int get_page_ext(struct page *pg,
+			unsigned int *pgroup, unsigned int *pidx)
+{
+	union page_ext ext = { .mapping = pg->mapping };
+	struct xen_netbk *netbk;
+	unsigned int group, idx;
+
+	group = ext.e.group - 1;
+
+	if (group < 0 || group >= xen_netbk_group_nr)
+		return 0;
+
+	netbk = &xen_netbk[group];
+
+	idx = ext.e.idx;
+
+	if ((idx < 0) || (idx >= MAX_PENDING_REQS))
+		return 0;
+
+	if (netbk->mmap_pages[idx] != pg)
+		return 0;
+
+	*pgroup = group;
+	*pidx = idx;
+
+	return 1;
+}
+
+/*
+ * This is the amount of packet we copy rather than map, so that the
+ * guest can't fiddle with the contents of the headers while we do
+ * packet processing on them (netfilter, routing, etc).
+ */
+#define PKT_PROT_LEN    (ETH_HLEN + \
+			 VLAN_HLEN + \
+			 sizeof(struct iphdr) + MAX_IPOPTLEN + \
+			 sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE)
+
+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)
+{
+	return MAX_PENDING_REQS -
+		netbk->pending_prod + netbk->pending_cons;
+}
+
+static void xen_netbk_kick_thread(struct xen_netbk *netbk)
+{
+	wake_up(&netbk->wq);
+}
+
+static int max_required_rx_slots(struct xenvif *vif)
+{
+	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);
+
+	if (vif->can_sg || vif->gso || vif->gso_prefix)
+		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */
+
+	return max;
+}
+
+int xen_netbk_rx_ring_full(struct xenvif *vif)
+{
+	RING_IDX peek   = vif->rx_req_cons_peek;
+	RING_IDX needed = max_required_rx_slots(vif);
+
+	return ((vif->rx.sring->req_prod - peek) < needed) ||
+	       ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed);
+}
+
+int xen_netbk_must_stop_queue(struct xenvif *vif)
+{
+	if (!xen_netbk_rx_ring_full(vif))
+		return 0;
+
+	vif->rx.sring->req_event = vif->rx_req_cons_peek +
+		max_required_rx_slots(vif);
+	mb(); /* request notification /then/ check the queue */
+
+	return xen_netbk_rx_ring_full(vif);
+}
+
+/*
+ * Returns true if we should start a new receive buffer instead of
+ * adding 'size' bytes to a buffer which currently contains 'offset'
+ * bytes.
+ */
+static bool start_new_rx_buffer(int offset, unsigned long size, int head)
+{
+	/* simple case: we have completely filled the current buffer. */
+	if (offset == MAX_BUFFER_OFFSET)
+		return true;
+
+	/*
+	 * complex case: start a fresh buffer if the current frag
+	 * would overflow the current buffer but only if:
+	 *     (i)   this frag would fit completely in the next buffer
+	 * and (ii)  there is already some data in the current buffer
+	 * and (iii) this is not the head buffer.
+	 *
+	 * Where:
+	 * - (i) stops us splitting a frag into two copies
+	 *   unless the frag is too large for a single buffer.
+	 * - (ii) stops us from leaving a buffer pointlessly empty.
+	 * - (iii) stops us leaving the first buffer
+	 *   empty. Strictly speaking this is already covered
+	 *   by (ii) but is explicitly checked because
+	 *   netfront relies on the first buffer being
+	 *   non-empty and can crash otherwise.
+	 *
+	 * This means we will effectively linearise small
+	 * frags but do not needlessly split large buffers
+	 * into multiple copies tend to give large frags their
+	 * own buffers as before.
+	 */
+	if ((offset + size > MAX_BUFFER_OFFSET) &&
+	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+		return true;
+
+	return false;
+}
+
+/*
+ * Figure out how many ring slots we're going to need to send @skb to
+ * the guest. This function is essentially a dry run of
+ * netbk_gop_frag_copy.
+ */
+unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
+{
+	unsigned int count;
+	int i, copy_off;
+
+	count = DIV_ROUND_UP(
+			offset_in_page(skb->data)+skb_headlen(skb), PAGE_SIZE);
+
+	copy_off = skb_headlen(skb) % PAGE_SIZE;
+
+	if (skb_shinfo(skb)->gso_size)
+		count++;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		unsigned long size = skb_shinfo(skb)->frags[i].size;
+		unsigned long bytes;
+		while (size > 0) {
+			BUG_ON(copy_off > MAX_BUFFER_OFFSET);
+
+			if (start_new_rx_buffer(copy_off, size, 0)) {
+				count++;
+				copy_off = 0;
+			}
+
+			bytes = size;
+			if (copy_off + bytes > MAX_BUFFER_OFFSET)
+				bytes = MAX_BUFFER_OFFSET - copy_off;
+
+			copy_off += bytes;
+			size -= bytes;
+		}
+	}
+	return count;
+}
+
+struct netrx_pending_operations {
+	unsigned copy_prod, copy_cons;
+	unsigned meta_prod, meta_cons;
+	struct gnttab_copy *copy;
+	struct netbk_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)
+{
+	struct netbk_rx_meta *meta;
+	struct xen_netif_rx_request *req;
+
+	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+
+	meta = npo->meta + npo->meta_prod++;
+	meta->gso_size = 0;
+	meta->size = 0;
+	meta->id = req->id;
+
+	npo->copy_off = 0;
+	npo->copy_gref = req->gref;
+
+	return meta;
+}
+
+/*
+ * Set up the grant operations for this fragment. If it's a flipping
+ * interface, we also set up the unmap request from here.
+ */
+static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
+				struct netrx_pending_operations *npo,
+				struct page *page, unsigned long size,
+				unsigned long offset, int *head)
+{
+	struct gnttab_copy *copy_gop;
+	struct netbk_rx_meta *meta;
+	/*