Fixed MTP to work with TWRP

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

drivers/net/xen-netback/common.h

@@ -0,0 +1,344 @@
+/*
+ * 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>
+#include <linux/debugfs.h>
+
+typedef unsigned int pending_ring_idx_t;
+#define INVALID_PENDING_RING_IDX (~0U)
+
+struct pending_tx_info {
+	struct xen_netif_tx_request req; /* tx request */
+	/* Callback data for released SKBs. The callback is always
+	 * xenvif_zerocopy_callback, desc contains the pending_idx, which is
+	 * also an index in pending_tx_info array. It is initialized in
+	 * xenvif_alloc and it never changes.
+	 * skb_shinfo(skb)->destructor_arg points to the first mapped slot's
+	 * callback_struct in this array of struct pending_tx_info's, then ctx
+	 * to the next, or NULL if there is no more slot for this skb.
+	 * ubuf_to_vif is a helper which finds the struct xenvif from a pointer
+	 * to this field.
+	 */
+	struct ubuf_info callback_struct;
+};
+
+#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_type;
+	int gso_size;
+};
+
+#define GSO_BIT(type) \
+	(1 << XEN_NETIF_GSO_TYPE_ ## type)
+
+/* Discriminate from any valid pending_idx value. */
+#define INVALID_PENDING_IDX 0xFFFF
+
+#define MAX_BUFFER_OFFSET PAGE_SIZE
+
+#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE
+
+/* It's possible for an skb to have a maximal number of frags
+ * but still be less than MAX_BUFFER_OFFSET in size. Thus the
+ * worst-case number of copy operations is MAX_SKB_FRAGS per
+ * ring slot.
+ */
+#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+
+#define NETBACK_INVALID_HANDLE -1
+
+/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
+ * the maximum slots a valid packet can use. Now this value is defined
+ * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
+ * all backend.
+ */
+#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
+
+/* Queue name is interface name with "-qNNN" appended */
+#define QUEUE_NAME_SIZE (IFNAMSIZ + 5)
+
+/* IRQ name is queue name with "-tx" or "-rx" appended */
+#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+
+struct xenvif;
+
+struct xenvif_stats {
+	/* Stats fields to be updated per-queue.
+	 * A subset of struct net_device_stats that contains only the
+	 * fields that are updated in netback.c for each queue.
+	 */
+	unsigned int rx_bytes;
+	unsigned int rx_packets;
+	unsigned int tx_bytes;
+	unsigned int tx_packets;
+
+	/* Additional stats used by xenvif */
+	unsigned long rx_gso_checksum_fixup;
+	unsigned long tx_zerocopy_sent;
+	unsigned long tx_zerocopy_success;
+	unsigned long tx_zerocopy_fail;
+	unsigned long tx_frag_overflow;
+};
+
+struct xenvif_queue { /* Per-queue data for xenvif */
+	unsigned int id; /* Queue ID, 0-based */
+	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
+	struct xenvif *vif; /* Parent VIF */
+
+	/* 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[IRQ_NAME_SIZE]; /* DEVNAME-qN-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];
+	grant_handle_t grant_tx_handle[MAX_PENDING_REQS];
+
+	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];
+	struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS];
+	struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS];
+	/* passed to gnttab_[un]map_refs with pages under (un)mapping */
+	struct page *pages_to_map[MAX_PENDING_REQS];
+	struct page *pages_to_unmap[MAX_PENDING_REQS];
+
+	/* This prevents zerocopy callbacks  to race over dealloc_ring */
+	spinlock_t callback_lock;
+	/* This prevents dealloc thread and NAPI instance to race over response
+	 * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err
+	 * it only protect response creation
+	 */
+	spinlock_t response_lock;
+	pending_ring_idx_t dealloc_prod;
+	pending_ring_idx_t dealloc_cons;
+	u16 dealloc_ring[MAX_PENDING_REQS];
+	struct task_struct *dealloc_task;
+	wait_queue_head_t dealloc_wq;
+	atomic_t inflight_packets;
+
+	/* 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 rx_irq;
+	/* Only used when feature-split-event-channels = 1 */
+	char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
+	struct xen_netif_rx_back_ring rx;
+	struct sk_buff_head rx_queue;
+
+	unsigned int rx_queue_max;
+	unsigned int rx_queue_len;
+	unsigned long last_rx_time;
+	bool stalled;
+
+	struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS];
+
+	/* We create one meta structure per ring request we consume, so
+	 * the maximum number is the same as the ring size.
+	 */
+	struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
+
+	/* 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;
+	u64 credit_window_start;
+
+	/* Statistics */
+	struct xenvif_stats stats;
+};
+
+/* Maximum number of Rx slots a to-guest packet may use, including the
+ * slot needed for GSO meta-data.
+ */
+#define XEN_NETBK_RX_SLOTS_MAX (MAX_SKB_FRAGS + 1)
+
+enum state_bit_shift {
+	/* This bit marks that the vif is connected */
+	VIF_STATUS_CONNECTED,
+};
+
+struct xenvif {
+	/* Unique identifier for this interface. */
+	domid_t          domid;
+	unsigned int     handle;
+
+	u8               fe_dev_addr[6];
+
+	/* Frontend feature information. */
+	int gso_mask;
+	int gso_prefix_mask;
+
+	u8 can_sg:1;
+	u8 ip_csum:1;
+	u8 ipv6_csum:1;
+
+	/* Is this interface disabled? True when backend discovers
+	 * frontend is rogue.
+	 */
+	bool disabled;
+	unsigned long status;
+	unsigned long drain_timeout;
+	unsigned long stall_timeout;
+
+	/* Queues */
+	struct xenvif_queue *queues;
+	unsigned int num_queues; /* active queues, resource allocated */
+	unsigned int stalled_queues;
+
+	spinlock_t lock;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *xenvif_dbg_root;
+#endif
+
+	/* Miscellaneous private stuff. */
+	struct net_device *dev;
+};
+
+struct xenvif_rx_cb {
+	unsigned long expires;
+	int meta_slots_used;
+	bool full_coalesce;
+};
+
+#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
+
+static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
+{
+	return to_xenbus_device(vif->dev->dev.parent);
+}
+
+struct xenvif *xenvif_alloc(struct device *parent,
+			    domid_t domid,
+			    unsigned int handle);
+
+int xenvif_init_queue(struct xenvif_queue *queue);
+void xenvif_deinit_queue(struct xenvif_queue *queue);
+
+int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
+		   unsigned int rx_evtchn);
+void xenvif_disconnect(struct xenvif *vif);
+void xenvif_free(struct xenvif *vif);
+
+int xenvif_xenbus_init(void);
+void xenvif_xenbus_fini(void);
+
+int xenvif_schedulable(struct xenvif *vif);
+
+int xenvif_queue_stopped(struct xenvif_queue *queue);
+void xenvif_wake_queue(struct xenvif_queue *queue);
+
+/* (Un)Map communication rings. */
+void xenvif_unmap_frontend_rings(struct xenvif_queue *queue);
+int xenvif_map_frontend_rings(struct xenvif_queue *queue,
+			      grant_ref_t tx_ring_ref,
+			      grant_ref_t rx_ring_ref);
+
+/* Check for SKBs from frontend and schedule backend processing */
+void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue);
+
+/* Prevent the device from generating any further traffic. */
+void xenvif_carrier_off(struct xenvif *vif);
+
+int xenvif_tx_action(struct xenvif_queue *queue, int budget);
+
+int xenvif_kthread_guest_rx(void *data);
+void xenvif_kick_thread(struct xenvif_queue *queue);
+
+int xenvif_dealloc_kthread(void *data);
+
+void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);
+
+/* Determine whether the needed number of slots (req) are available,
+ * and set req_event if not.
+ */
+bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed);
+
+void xenvif_carrier_on(struct xenvif *vif);
+
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
+/* Unmap a pending page and release it back to the guest */
+void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
+
+static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
+{
+	return MAX_PENDING_REQS -
+		queue->pending_prod + queue->pending_cons;
+}
+
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
+irqreturn_t xenvif_interrupt(int irq, void *dev_id);
+
+extern bool separate_tx_rx_irq;
+
+extern unsigned int rx_drain_timeout_msecs;
+extern unsigned int rx_stall_timeout_msecs;
+extern unsigned int xenvif_max_queues;
+
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *xen_netback_dbg_root;
+#endif
+
+void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
+				 struct sk_buff *skb);
+void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue);
+
+#endif /* __XEN_NETBACK__COMMON_H__ */

drivers/net/xen-netback/interface.c

@@ -0,0 +1,688 @@
+/*
+ * 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/kthread.h>
+#include <linux/ethtool.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
+
+#include <xen/events.h>
+#include <asm/xen/hypercall.h>
+#include <xen/balloon.h>
+
+#define XENVIF_QUEUE_LENGTH 32
+#define XENVIF_NAPI_WEIGHT  64
+
+/* Number of bytes allowed on the internal guest Rx queue. */
+#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE)
+
+/* This function is used to set SKBTX_DEV_ZEROCOPY as well as
+ * increasing the inflight counter. We need to increase the inflight
+ * counter because core driver calls into xenvif_zerocopy_callback
+ * which calls xenvif_skb_zerocopy_complete.
+ */
+void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
+				 struct sk_buff *skb)
+{
+	skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+	atomic_inc(&queue->inflight_packets);
+}
+
+void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
+{
+	atomic_dec(&queue->inflight_packets);
+}
+
+int xenvif_schedulable(struct xenvif *vif)
+{
+	return netif_running(vif->dev) &&
+		test_bit(VIF_STATUS_CONNECTED, &vif->status) &&
+		!vif->disabled;
+}
+
+static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
+{
+	struct xenvif_queue *queue = dev_id;
+
+	if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))
+		napi_schedule(&queue->napi);
+
+	return IRQ_HANDLED;
+}
+
+int xenvif_poll(struct napi_struct *napi, int budget)
+{
+	struct xenvif_queue *queue =
+		container_of(napi, struct xenvif_queue, napi);
+	int work_done;
+
+	/* This vif is rogue, we pretend we've there is nothing to do
+	 * for this vif to deschedule it from NAPI. But this interface
+	 * will be turned off in thread context later.
+	 */
+	if (unlikely(queue->vif->disabled)) {
+		napi_complete(napi);
+		return 0;
+	}
+
+	work_done = xenvif_tx_action(queue, budget);
+
+	if (work_done < budget) {
+		napi_complete(napi);
+		xenvif_napi_schedule_or_enable_events(queue);
+	}
+
+	return work_done;
+}
+
+static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
+{
+	struct xenvif_queue *queue = dev_id;
+
+	xenvif_kick_thread(queue);
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t xenvif_interrupt(int irq, void *dev_id)
+{
+	xenvif_tx_interrupt(irq, dev_id);
+	xenvif_rx_interrupt(irq, dev_id);
+
+	return IRQ_HANDLED;
+}
+
+int xenvif_queue_stopped(struct xenvif_queue *queue)
+{
+	struct net_device *dev = queue->vif->dev;
+	unsigned int id = queue->id;
+	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id));
+}
+
+void xenvif_wake_queue(struct xenvif_queue *queue)
+{
+	struct net_device *dev = queue->vif->dev;
+	unsigned int id = queue->id;
+	netif_tx_wake_queue(netdev_get_tx_queue(dev, id));
+}
+
+static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	u16 index;
+	struct xenvif_rx_cb *cb;
+
+	BUG_ON(skb->dev != dev);
+
+	/* Drop the packet if queues are not set up */
+	if (num_queues < 1)
+		goto drop;
+
+	/* Obtain the queue to be used to transmit this packet */
+	index = skb_get_queue_mapping(skb);
+	if (index >= num_queues) {
+		pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.",
+				    index, vif->dev->name);
+		index %= num_queues;
+	}
+	queue = &vif->queues[index];
+
+	/* Drop the packet if queue is not ready */
+	if (queue->task == NULL ||
+	    queue->dealloc_task == NULL ||
+	    !xenvif_schedulable(vif))
+		goto drop;
+
+	cb = XENVIF_RX_CB(skb);
+	cb->expires = jiffies + vif->drain_timeout;
+
+	xenvif_rx_queue_tail(queue, skb);
+	xenvif_kick_thread(queue);
+
+	return NETDEV_TX_OK;
+
+ drop:
+	vif->dev->stats.tx_dropped++;
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned long rx_bytes = 0;
+	unsigned long rx_packets = 0;
+	unsigned long tx_bytes = 0;
+	unsigned long tx_packets = 0;
+	unsigned int index;
+
+	if (vif->queues == NULL)
+		goto out;
+
+	/* Aggregate tx and rx stats from each queue */
+	for (index = 0; index < num_queues; ++index) {
+		queue = &vif->queues[index];
+		rx_bytes += queue->stats.rx_bytes;
+		rx_packets += queue->stats.rx_packets;
+		tx_bytes += queue->stats.tx_bytes;
+		tx_packets += queue->stats.tx_packets;
+	}
+
+out:
+	vif->dev->stats.rx_bytes = rx_bytes;
+	vif->dev->stats.rx_packets = rx_packets;
+	vif->dev->stats.tx_bytes = tx_bytes;
+	vif->dev->stats.tx_packets = tx_packets;
+
+	return &vif->dev->stats;
+}
+
+static void xenvif_up(struct xenvif *vif)
+{
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		napi_enable(&queue->napi);
+		enable_irq(queue->tx_irq);
+		if (queue->tx_irq != queue->rx_irq)
+			enable_irq(queue->rx_irq);
+		xenvif_napi_schedule_or_enable_events(queue);
+	}
+}
+
+static void xenvif_down(struct xenvif *vif)
+{
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		napi_disable(&queue->napi);
+		disable_irq(queue->tx_irq);
+		if (queue->tx_irq != queue->rx_irq)
+			disable_irq(queue->rx_irq);
+		del_timer_sync(&queue->credit_timeout);
+	}
+}
+
+static int xenvif_open(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (test_bit(VIF_STATUS_CONNECTED, &vif->status))
+		xenvif_up(vif);
+	netif_tx_start_all_queues(dev);
+	return 0;
+}
+
+static int xenvif_close(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (test_bit(VIF_STATUS_CONNECTED, &vif->status))
+		xenvif_down(vif);
+	netif_tx_stop_all_queues(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 netdev_features_t xenvif_fix_features(struct net_device *dev,
+	netdev_features_t features)
+{
+	struct xenvif *vif = netdev_priv(dev);
+
+	if (!vif->can_sg)
+		features &= ~NETIF_F_SG;
+	if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4))
+		features &= ~NETIF_F_TSO;
+	if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6))
+		features &= ~NETIF_F_TSO6;
+	if (!vif->ip_csum)
+		features &= ~NETIF_F_IP_CSUM;
+	if (!vif->ipv6_csum)
+		features &= ~NETIF_F_IPV6_CSUM;
+
+	return features;
+}
+
+static const struct xenvif_stat {
+	char name[ETH_GSTRING_LEN];
+	u16 offset;
+} xenvif_stats[] = {
+	{
+		"rx_gso_checksum_fixup",
+		offsetof(struct xenvif_stats, rx_gso_checksum_fixup)
+	},
+	/* If (sent != success + fail), there are probably packets never
+	 * freed up properly!
+	 */
+	{
+		"tx_zerocopy_sent",
+		offsetof(struct xenvif_stats, tx_zerocopy_sent),
+	},
+	{
+		"tx_zerocopy_success",
+		offsetof(struct xenvif_stats, tx_zerocopy_success),
+	},
+	{
+		"tx_zerocopy_fail",
+		offsetof(struct xenvif_stats, tx_zerocopy_fail)
+	},
+	/* Number of packets exceeding MAX_SKB_FRAG slots. You should use
+	 * a guest with the same MAX_SKB_FRAG
+	 */
+	{
+		"tx_frag_overflow",
+		offsetof(struct xenvif_stats, tx_frag_overflow)
+	},
+};
+
+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)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	unsigned int num_queues = vif->num_queues;
+	int i;
+	unsigned int queue_index;
+	struct xenvif_stats *vif_stats;
+
+	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
+		unsigned long accum = 0;
+		for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+			vif_stats = &vif->queues[queue_index].stats;
+			accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset);
+		}
+		data[i] = accum;
+	}
+}
+
+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 const struct ethtool_ops xenvif_ethtool_ops = {
+	.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 const 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,
+	.ndo_fix_features = xenvif_fix_features,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr   = eth_validate_addr,
+};
+
+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);
+	/* Allocate a netdev with the max. supported number of queues.
+	 * When the guest selects the desired number, it will be updated
+	 * via netif_set_real_num_*_queues().
+	 */
+	dev = alloc_netdev_mq(sizeof(struct xenvif), name, NET_NAME_UNKNOWN,
+			      ether_setup, xenvif_max_queues);
+	if (dev == NULL) {
+		pr_warn("Could not allocate netdev for %s\n", name);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	SET_NETDEV_DEV(dev, parent);
+
+	vif = netdev_priv(dev);
+
+	vif->domid  = domid;
+	vif->handle = handle;
+	vif->can_sg = 1;
+	vif->ip_csum = 1;
+	vif->dev = dev;
+	vif->disabled = false;
+	vif->drain_timeout = msecs_to_jiffies(rx_drain_timeout_msecs);
+	vif->stall_timeout = msecs_to_jiffies(rx_stall_timeout_msecs);
+
+	/* Start out with no queues. */
+	vif->queues = NULL;
+	vif->num_queues = 0;
+
+	spin_lock_init(&vif->lock);
+
+	dev->netdev_ops	= &xenvif_netdev_ops;
+	dev->hw_features = NETIF_F_SG |
+		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+		NETIF_F_TSO | NETIF_F_TSO6;
+	dev->features = dev->hw_features | NETIF_F_RXCSUM;
+	dev->ethtool_ops = &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");
+
+	__module_get(THIS_MODULE);
+
+	return vif;
+}
+
+int xenvif_init_queue(struct xenvif_queue *queue)
+{
+	int err, i;
+
+	queue->credit_bytes = queue->remaining_credit = ~0UL;
+	queue->credit_usec  = 0UL;
+	init_timer(&queue->credit_timeout);
+	queue->credit_window_start = get_jiffies_64();
+
+	queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES;
+
+	skb_queue_head_init(&queue->rx_queue);
+	skb_queue_head_init(&queue->tx_queue);
+
+	queue->pending_cons = 0;
+	queue->pending_prod = MAX_PENDING_REQS;
+	for (i = 0; i < MAX_PENDING_REQS; ++i)
+		queue->pending_ring[i] = i;
+
+	spin_lock_init(&queue->callback_lock);
+	spin_lock_init(&queue->response_lock);
+
+	/* If ballooning is disabled, this will consume real memory, so you
+	 * better enable it. The long term solution would be to use just a
+	 * bunch of valid page descriptors, without dependency on ballooning
+	 */
+	err = alloc_xenballooned_pages(MAX_PENDING_REQS,
+				       queue->mmap_pages,
+				       false);
+	if (err) {
+		netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_PENDING_REQS; i++) {
+		queue->pending_tx_info[i].callback_struct = (struct ubuf_info)
+			{ .callback = xenvif_zerocopy_callback,
+			  .ctx = NULL,
+			  .desc = i };
+		queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
+	}
+
+	return 0;
+}
+
+void xenvif_carrier_on(struct xenvif *vif)
+{
+	rtnl_lock();
+	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
+		dev_set_mtu(vif->dev, ETH_DATA_LEN);
+	netdev_update_features(vif->dev);
+	set_bit(VIF_STATUS_CONNECTED, &vif->status);
+	if (netif_running(vif->dev))
+		xenvif_up(vif);
+	rtnl_unlock();
+}
+
+int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
+		   unsigned int rx_evtchn)
+{
+	struct task_struct *task;
+	int err = -ENOMEM;
+
+	BUG_ON(queue->tx_irq);
+	BUG_ON(queue->task);
+	BUG_ON(queue->dealloc_task);
+
+	err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref);
+	if (err < 0)
+		goto err;
+
+	init_waitqueue_head(&queue->wq);
+	init_waitqueue_head(&queue->dealloc_wq);
+	atomic_set(&queue->inflight_packets, 0);
+
+	netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
+			XENVIF_NAPI_WEIGHT);
+
+	if (tx_evtchn == rx_evtchn) {
+		/* feature-split-event-channels == 0 */
+		err = bind_interdomain_evtchn_to_irqhandler(
+			queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
+			queue->name, queue);
+		if (err < 0)
+			goto err_unmap;
+		queue->tx_irq = queue->rx_irq = err;
+		disable_irq(queue->tx_irq);
+	} else {
+		/* feature-split-event-channels == 1 */
+		snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
+			 "%s-tx", queue->name);
+		err = bind_interdomain_evtchn_to_irqhandler(
+			queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
+			queue->tx_irq_name, queue);
+		if (err < 0)
+			goto err_unmap;
+		queue->tx_irq = err;
+		disable_irq(queue->tx_irq);
+
+		snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
+			 "%s-rx", queue->name);
+		err = bind_interdomain_evtchn_to_irqhandler(
+			queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
+			queue->rx_irq_name, queue);
+		if (err < 0)
+			goto err_tx_unbind;
+		queue->rx_irq = err;
+		disable_irq(queue->rx_irq);
+	}
+
+	queue->stalled = true;
+
+	task = kthread_create(xenvif_kthread_guest_rx,
+			      (void *)queue, "%s-guest-rx", queue->name);
+	if (IS_ERR(task)) {
+		pr_warn("Could not allocate kthread for %s\n", queue->name);
+		err = PTR_ERR(task);
+		goto err_rx_unbind;
+	}
+	queue->task = task;
+
+	task = kthread_create(xenvif_dealloc_kthread,
+			      (void *)queue, "%s-dealloc", queue->name);
+	if (IS_ERR(task)) {
+		pr_warn("Could not allocate kthread for %s\n", queue->name);
+		err = PTR_ERR(task);
+		goto err_rx_unbind;
+	}
+	queue->dealloc_task = task;
+
+	wake_up_process(queue->task);
+	wake_up_process(queue->dealloc_task);
+
+	return 0;
+
+err_rx_unbind:
+	unbind_from_irqhandler(queue->rx_irq, queue);
+	queue->rx_irq = 0;
+err_tx_unbind:
+	unbind_from_irqhandler(queue->tx_irq, queue);
+	queue->tx_irq = 0;
+err_unmap:
+	xenvif_unmap_frontend_rings(queue);
+err:
+	module_put(THIS_MODULE);
+	return err;
+}
+
+void xenvif_carrier_off(struct xenvif *vif)
+{
+	struct net_device *dev = vif->dev;
+
+	rtnl_lock();
+	if (test_and_clear_bit(VIF_STATUS_CONNECTED, &vif->status)) {
+		netif_carrier_off(dev); /* discard queued packets */
+		if (netif_running(dev))
+			xenvif_down(vif);
+	}
+	rtnl_unlock();
+}
+
+void xenvif_disconnect(struct xenvif *vif)
+{
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	xenvif_carrier_off(vif);
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+
+		netif_napi_del(&queue->napi);
+
+		if (queue->task) {
+			kthread_stop(queue->task);
+			queue->task = NULL;
+		}
+
+		if (queue->dealloc_task) {
+			kthread_stop(queue->dealloc_task);
+			queue->dealloc_task = NULL;
+		}
+
+		if (queue->tx_irq) {
+			if (queue->tx_irq == queue->rx_irq)
+				unbind_from_irqhandler(queue->tx_irq, queue);
+			else {
+				unbind_from_irqhandler(queue->tx_irq, queue);
+				unbind_from_irqhandler(queue->rx_irq, queue);
+			}
+			queue->tx_irq = 0;
+		}
+
+		xenvif_unmap_frontend_rings(queue);
+	}
+}
+
+/* Reverse the relevant parts of xenvif_init_queue().
+ * Used for queue teardown from xenvif_free(), and on the
+ * error handling paths in xenbus.c:connect().
+ */
+void xenvif_deinit_queue(struct xenvif_queue *queue)
+{
+	free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
+}
+
+void xenvif_free(struct xenvif *vif)
+{
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	unregister_netdev(vif->dev);
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		xenvif_deinit_queue(queue);
+	}
+
+	vfree(vif->queues);
+	vif->queues = NULL;
+	vif->num_queues = 0;
+
+	free_netdev(vif->dev);
+
+	module_put(THIS_MODULE);
+}

drivers/net/xen-netback/xenbus.c

@@ -0,0 +1,975 @@
+/*
+ * Xenbus code for netif backend
+ *
+ * Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
+ * Copyright (C) 2005 XenSource Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include "common.h"
+#include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
+
+struct backend_info {
+	struct xenbus_device *dev;
+	struct xenvif *vif;
+
+	/* This is the state that will be reflected in xenstore when any
+	 * active hotplug script completes.
+	 */
+	enum xenbus_state state;
+
+	enum xenbus_state frontend_state;
+	struct xenbus_watch hotplug_status_watch;
+	u8 have_hotplug_status_watch:1;
+};
+
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
+static void connect(struct backend_info *be);
+static int read_xenbus_vif_flags(struct backend_info *be);
+static int backend_create_xenvif(struct backend_info *be);
+static void unregister_hotplug_status_watch(struct backend_info *be);
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state);
+
+#ifdef CONFIG_DEBUG_FS
+struct dentry *xen_netback_dbg_root = NULL;
+
+static int xenvif_read_io_ring(struct seq_file *m, void *v)
+{
+	struct xenvif_queue *queue = m->private;
+	struct xen_netif_tx_back_ring *tx_ring = &queue->tx;
+	struct xen_netif_rx_back_ring *rx_ring = &queue->rx;
+	struct netdev_queue *dev_queue;
+
+	if (tx_ring->sring) {
+		struct xen_netif_tx_sring *sring = tx_ring->sring;
+
+		seq_printf(m, "Queue %d\nTX: nr_ents %u\n", queue->id,
+			   tx_ring->nr_ents);
+		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
+			   sring->req_prod,
+			   sring->req_prod - sring->rsp_prod,
+			   tx_ring->req_cons,
+			   tx_ring->req_cons - sring->rsp_prod,
+			   sring->req_event,
+			   sring->req_event - sring->rsp_prod);
+		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n",
+			   sring->rsp_prod,
+			   tx_ring->rsp_prod_pvt,
+			   tx_ring->rsp_prod_pvt - sring->rsp_prod,
+			   sring->rsp_event,
+			   sring->rsp_event - sring->rsp_prod);
+		seq_printf(m, "pending prod %u pending cons %u nr_pending_reqs %u\n",
+			   queue->pending_prod,
+			   queue->pending_cons,
+			   nr_pending_reqs(queue));
+		seq_printf(m, "dealloc prod %u dealloc cons %u dealloc_queue %u\n\n",
+			   queue->dealloc_prod,
+			   queue->dealloc_cons,
+			   queue->dealloc_prod - queue->dealloc_cons);
+	}
+
+	if (rx_ring->sring) {
+		struct xen_netif_rx_sring *sring = rx_ring->sring;
+
+		seq_printf(m, "RX: nr_ents %u\n", rx_ring->nr_ents);
+		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
+			   sring->req_prod,
+			   sring->req_prod - sring->rsp_prod,
+			   rx_ring->req_cons,
+			   rx_ring->req_cons - sring->rsp_prod,
+			   sring->req_event,
+			   sring->req_event - sring->rsp_prod);
+		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n\n",
+			   sring->rsp_prod,
+			   rx_ring->rsp_prod_pvt,
+			   rx_ring->rsp_prod_pvt - sring->rsp_prod,
+			   sring->rsp_event,
+			   sring->rsp_event - sring->rsp_prod);
+	}
+
+	seq_printf(m, "NAPI state: %lx NAPI weight: %d TX queue len %u\n"
+		   "Credit timer_pending: %d, credit: %lu, usec: %lu\n"
+		   "remaining: %lu, expires: %lu, now: %lu\n",
+		   queue->napi.state, queue->napi.weight,
+		   skb_queue_len(&queue->tx_queue),
+		   timer_pending(&queue->credit_timeout),
+		   queue->credit_bytes,
+		   queue->credit_usec,
+		   queue->remaining_credit,
+		   queue->credit_timeout.expires,
+		   jiffies);
+
+	dev_queue = netdev_get_tx_queue(queue->vif->dev, queue->id);
+
+	seq_printf(m, "\nRx internal queue: len %u max %u pkts %u %s\n",
+		   queue->rx_queue_len, queue->rx_queue_max,
+		   skb_queue_len(&queue->rx_queue),
+		   netif_tx_queue_stopped(dev_queue) ? "stopped" : "running");
+
+	return 0;
+}
+
+#define XENVIF_KICK_STR "kick"
+#define BUFFER_SIZE     32
+
+static ssize_t
+xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count,
+		     loff_t *ppos)
+{
+	struct xenvif_queue *queue =
+		((struct seq_file *)filp->private_data)->private;
+	int len;
+	char write[BUFFER_SIZE];
+
+	/* don't allow partial writes and check the length */
+	if (*ppos != 0)
+		return 0;
+	if (count >= sizeof(write))
+		return -ENOSPC;
+
+	len = simple_write_to_buffer(write,
+				     sizeof(write) - 1,
+				     ppos,
+				     buf,
+				     count);
+	if (len < 0)
+		return len;
+
+	write[len] = '\0';
+
+	if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1))
+		xenvif_interrupt(0, (void *)queue);
+	else {
+		pr_warn("Unknown command to io_ring_q%d. Available: kick\n",
+			queue->id);
+		count = -EINVAL;
+	}
+	return count;
+}
+
+static int xenvif_dump_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+	void *queue = NULL;
+
+	if (inode->i_private)
+		queue = inode->i_private;
+	ret = single_open(filp, xenvif_read_io_ring, queue);
+	filp->f_mode |= FMODE_PWRITE;
+	return ret;
+}
+
+static const struct file_operations xenvif_dbg_io_ring_ops_fops = {
+	.owner = THIS_MODULE,
+	.open = xenvif_dump_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.write = xenvif_write_io_ring,
+};
+
+static void xenvif_debugfs_addif(struct xenvif *vif)
+{
+	struct dentry *pfile;
+	int i;
+
+	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
+		return;
+
+	vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name,
+						  xen_netback_dbg_root);
+	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) {
+		for (i = 0; i < vif->num_queues; ++i) {
+			char filename[sizeof("io_ring_q") + 4];
+
+			snprintf(filename, sizeof(filename), "io_ring_q%d", i);
+			pfile = debugfs_create_file(filename,
+						    S_IRUSR | S_IWUSR,
+						    vif->xenvif_dbg_root,
+						    &vif->queues[i],
+						    &xenvif_dbg_io_ring_ops_fops);
+			if (IS_ERR_OR_NULL(pfile))
+				pr_warn("Creation of io_ring file returned %ld!\n",
+					PTR_ERR(pfile));
+		}
+	} else
+		netdev_warn(vif->dev,
+			    "Creation of vif debugfs dir returned %ld!\n",
+			    PTR_ERR(vif->xenvif_dbg_root));
+}
+
+static void xenvif_debugfs_delif(struct xenvif *vif)
+{
+	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
+		return;
+
+	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root))
+		debugfs_remove_recursive(vif->xenvif_dbg_root);
+	vif->xenvif_dbg_root = NULL;
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static int netback_remove(struct xenbus_device *dev)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+	set_backend_state(be, XenbusStateClosed);
+
+	unregister_hotplug_status_watch(be);
+	if (be->vif) {
+		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
+		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
+		xenvif_free(be->vif);
+		be->vif = NULL;
+	}
+	kfree(be);
+	dev_set_drvdata(&dev->dev, NULL);
+	return 0;
+}
+
+
+/**
+ * Entry point to this code when a new device is created.  Allocate the basic
+ * structures and switch to InitWait.
+ */
+static int netback_probe(struct xenbus_device *dev,
+			 const struct xenbus_device_id *id)
+{
+	const char *message;
+	struct xenbus_transaction xbt;
+	int err;
+	int sg;
+	struct backend_info *be = kzalloc(sizeof(struct backend_info),
+					  GFP_KERNEL);
+	if (!be) {
+		xenbus_dev_fatal(dev, -ENOMEM,
+				 "allocating backend structure");
+		return -ENOMEM;
+	}
+
+	be->dev = dev;
+	dev_set_drvdata(&dev->dev, be);
+
+	sg = 1;
+
+	do {
+		err = xenbus_transaction_start(&xbt);
+		if (err) {
+			xenbus_dev_fatal(dev, err, "starting transaction");
+			goto fail;
+		}
+
+		err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", sg);
+		if (err) {
+			message = "writing feature-sg";
+			goto abort_transaction;
+		}
+
+		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4",
+				    "%d", sg);
+		if (err) {
+			message = "writing feature-gso-tcpv4";
+			goto abort_transaction;
+		}
+
+		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6",
+				    "%d", sg);
+		if (err) {
+			message = "writing feature-gso-tcpv6";
+			goto abort_transaction;
+		}
+
+		/* We support partial checksum setup for IPv6 packets */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-ipv6-csum-offload",
+				    "%d", 1);
+		if (err) {
+			message = "writing feature-ipv6-csum-offload";
+			goto abort_transaction;
+		}
+
+		/* We support rx-copy path. */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-rx-copy", "%d", 1);
+		if (err) {
+			message = "writing feature-rx-copy";
+			goto abort_transaction;
+		}
+
+		/*
+		 * We don't support rx-flip path (except old guests who don't
+		 * grok this feature flag).
+		 */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-rx-flip", "%d", 0);
+		if (err) {
+			message = "writing feature-rx-flip";
+			goto abort_transaction;
+		}
+
+		err = xenbus_transaction_end(xbt, 0);
+	} while (err == -EAGAIN);
+
+	if (err) {
+		xenbus_dev_fatal(dev, err, "completing transaction");
+		goto fail;
+	}
+
+	/*
+	 * Split event channels support, this is optional so it is not
+	 * put inside the above loop.
+	 */
+	err = xenbus_printf(XBT_NIL, dev->nodename,
+			    "feature-split-event-channels",
+			    "%u", separate_tx_rx_irq);
+	if (err)
+		pr_debug("Error writing feature-split-event-channels\n");
+
+	/* Multi-queue support: This is an optional feature. */
+	err = xenbus_printf(XBT_NIL, dev->nodename,
+			    "multi-queue-max-queues", "%u", xenvif_max_queues);
+	if (err)
+		pr_debug("Error writing multi-queue-max-queues\n");
+
+	err = xenbus_switch_state(dev, XenbusStateInitWait);
+	if (err)
+		goto fail;
+
+	be->state = XenbusStateInitWait;
+
+	/* This kicks hotplug scripts, so do it immediately. */
+	err = backend_create_xenvif(be);
+	if (err)
+		goto fail;
+
+	return 0;
+
+abort_transaction:
+	xenbus_transaction_end(xbt, 1);
+	xenbus_dev_fatal(dev, err, "%s", message);
+fail:
+	pr_debug("failed\n");
+	netback_remove(dev);
+	return err;
+}
+
+
+/*
+ * Handle the creation of the hotplug script environment.  We add the script
+ * and vif variables to the environment, for the benefit of the vif-* hotplug
+ * scripts.
+ */
+static int netback_uevent(struct xenbus_device *xdev,
+			  struct kobj_uevent_env *env)
+{
+	struct backend_info *be = dev_get_drvdata(&xdev->dev);
+	char *val;
+
+	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
+	if (IS_ERR(val)) {
+		int err = PTR_ERR(val);
+		xenbus_dev_fatal(xdev, err, "reading script");
+		return err;
+	} else {
+		if (add_uevent_var(env, "script=%s", val)) {
+			kfree(val);
+			return -ENOMEM;
+		}
+		kfree(val);
+	}
+
+	if (!be || !be->vif)
+		return 0;
+
+	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
+}
+
+
+static int backend_create_xenvif(struct backend_info *be)
+{
+	int err;
+	long handle;
+	struct xenbus_device *dev = be->dev;
+
+	if (be->vif != NULL)
+		return 0;
+
+	err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle);
+	if (err != 1) {
+		xenbus_dev_fatal(dev, err, "reading handle");
+		return (err < 0) ? err : -EINVAL;
+	}
+
+	be->vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle);
+	if (IS_ERR(be->vif)) {
+		err = PTR_ERR(be->vif);
+		be->vif = NULL;
+		xenbus_dev_fatal(dev, err, "creating interface");
+		return err;
+	}
+
+	kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
+	return 0;
+}
+
+static void backend_disconnect(struct backend_info *be)
+{
+	if (be->vif) {
+#ifdef CONFIG_DEBUG_FS
+		xenvif_debugfs_delif(be->vif);
+#endif /* CONFIG_DEBUG_FS */
+		xenvif_disconnect(be->vif);
+	}
+}
+
+static void backend_connect(struct backend_info *be)
+{
+	if (be->vif)
+		connect(be);
+}
+
+static inline void backend_switch_state(struct backend_info *be,
+					enum xenbus_state state)
+{
+	struct xenbus_device *dev = be->dev;
+
+	pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state));
+	be->state = state;
+
+	/* If we are waiting for a hotplug script then defer the
+	 * actual xenbus state change.
+	 */
+	if (!be->have_hotplug_status_watch)
+		xenbus_switch_state(dev, state);
+}
+
+/* Handle backend state transitions:
+ *
+ * The backend state starts in InitWait and the following transitions are
+ * allowed.
+ *
+ * InitWait -> Connected
+ *
+ *    ^    \         |
+ *    |     \        |
+ *    |      \       |
+ *    |       \      |
+ *    |        \     |
+ *    |         \    |
+ *    |          V   V
+ *
+ *  Closed  <-> Closing
+ *
+ * The state argument specifies the eventual state of the backend and the
+ * function transitions to that state via the shortest path.
+ */
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state)
+{
+	while (be->state != state) {
+		switch (be->state) {
+		case XenbusStateClosed:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+				pr_info("%s: prepare for reconnect\n",
+					be->dev->nodename);
+				backend_switch_state(be, XenbusStateInitWait);
+				break;
+			case XenbusStateClosing:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateInitWait:
+			switch (state) {
+			case XenbusStateConnected:
+				backend_connect(be);
+				backend_switch_state(be, XenbusStateConnected);
+				break;
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateConnected:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_disconnect(be);
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateClosing:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosed);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		default:
+			BUG();
+		}
+	}
+}
+
+/**
+ * Callback received when the frontend's state changes.
+ */
+static void frontend_changed(struct xenbus_device *dev,
+			     enum xenbus_state frontend_state)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+	pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state));
+
+	be->frontend_state = frontend_state;
+
+	switch (frontend_state) {
+	case XenbusStateInitialising:
+		set_backend_state(be, XenbusStateInitWait);
+		break;
+
+	case XenbusStateInitialised:
+		break;
+
+	case XenbusStateConnected:
+		set_backend_state(be, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+		set_backend_state(be, XenbusStateClosing);
+		break;
+
+	case XenbusStateClosed:
+		set_backend_state(be, XenbusStateClosed);
+		if (xenbus_dev_is_online(dev))
+			break;
+		/* fall through if not online */
+	case XenbusStateUnknown:
+		set_backend_state(be, XenbusStateClosed);
+		device_unregister(&dev->dev);
+		break;
+
+	default:
+		xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
+				 frontend_state);
+		break;
+	}
+}
+
+
+static void xen_net_read_rate(struct xenbus_device *dev,
+			      unsigned long *bytes, unsigned long *usec)
+{
+	char *s, *e;
+	unsigned long b, u;
+	char *ratestr;
+
+	/* Default to unlimited bandwidth. */
+	*bytes = ~0UL;
+	*usec = 0;
+
+	ratestr = xenbus_read(XBT_NIL, dev->nodename, "rate", NULL);
+	if (IS_ERR(ratestr))
+		return;
+
+	s = ratestr;
+	b = simple_strtoul(s, &e, 10);
+	if ((s == e) || (*e != ','))
+		goto fail;
+
+	s = e + 1;
+	u = simple_strtoul(s, &e, 10);
+	if ((s == e) || (*e != '\0'))
+		goto fail;
+
+	*bytes = b;
+	*usec = u;
+
+	kfree(ratestr);
+	return;
+
+ fail:
+	pr_warn("Failed to parse network rate limit. Traffic unlimited.\n");
+	kfree(ratestr);
+}
+
+static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
+{
+	char *s, *e, *macstr;
+	int i;
+
+	macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
+	if (IS_ERR(macstr))
+		return PTR_ERR(macstr);
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac[i] = simple_strtoul(s, &e, 16);
+		if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
+			kfree(macstr);
+			return -ENOENT;
+		}
+		s = e+1;
+	}
+
+	kfree(macstr);
+	return 0;
+}
+
+static void unregister_hotplug_status_watch(struct backend_info *be)
+{
+	if (be->have_hotplug_status_watch) {
+		unregister_xenbus_watch(&be->hotplug_status_watch);
+		kfree(be->hotplug_status_watch.node);
+	}
+	be->have_hotplug_status_watch = 0;
+}
+
+static void hotplug_status_changed(struct xenbus_watch *watch,
+				   const char **vec,
+				   unsigned int vec_size)
+{
+	struct backend_info *be = container_of(watch,
+					       struct backend_info,
+					       hotplug_status_watch);
+	char *str;
+	unsigned int len;
+
+	str = xenbus_read(XBT_NIL, be->dev->nodename, "hotplug-status", &len);
+	if (IS_ERR(str))
+		return;
+	if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
+		/* Complete any pending state change */
+		xenbus_switch_state(be->dev, be->state);
+
+		/* Not interested in this watch anymore. */
+		unregister_hotplug_status_watch(be);
+	}
+	kfree(str);
+}
+
+static void connect(struct backend_info *be)
+{
+	int err;
+	struct xenbus_device *dev = be->dev;
+	unsigned long credit_bytes, credit_usec;
+	unsigned int queue_index;
+	unsigned int requested_num_queues;
+	struct xenvif_queue *queue;
+
+	/* Check whether the frontend requested multiple queues
+	 * and read the number requested.
+	 */
+	err = xenbus_scanf(XBT_NIL, dev->otherend,
+			   "multi-queue-num-queues",
+			   "%u", &requested_num_queues);
+	if (err < 0) {
+		requested_num_queues = 1; /* Fall back to single queue */
+	} else if (requested_num_queues > xenvif_max_queues) {
+		/* buggy or malicious guest */
+		xenbus_dev_fatal(dev, err,
+				 "guest requested %u queues, exceeding the maximum of %u.",
+				 requested_num_queues, xenvif_max_queues);
+		return;
+	}
+
+	err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
+		return;
+	}
+
+	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
+	read_xenbus_vif_flags(be);
+
+	/* Use the number of queues requested by the frontend */
+	be->vif->queues = vzalloc(requested_num_queues *
+				  sizeof(struct xenvif_queue));
+	be->vif->num_queues = requested_num_queues;
+	be->vif->stalled_queues = requested_num_queues;
+
+	for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) {
+		queue = &be->vif->queues[queue_index];
+		queue->vif = be->vif;
+		queue->id = queue_index;
+		snprintf(queue->name, sizeof(queue->name), "%s-q%u",
+				be->vif->dev->name, queue->id);
+
+		err = xenvif_init_queue(queue);
+		if (err) {
+			/* xenvif_init_queue() cleans up after itself on
+			 * failure, but we need to clean up any previously
+			 * initialised queues. Set num_queues to i so that
+			 * earlier queues can be destroyed using the regular
+			 * disconnect logic.
+			 */
+			be->vif->num_queues = queue_index;
+			goto err;
+		}
+
+		queue->remaining_credit = credit_bytes;
+		queue->credit_usec = credit_usec;
+
+		err = connect_rings(be, queue);
+		if (err) {
+			/* connect_rings() cleans up after itself on failure,
+			 * but we need to clean up after xenvif_init_queue() here,
+			 * and also clean up any previously initialised queues.
+			 */
+			xenvif_deinit_queue(queue);
+			be->vif->num_queues = queue_index;
+			goto err;
+		}
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	xenvif_debugfs_addif(be->vif);
+#endif /* CONFIG_DEBUG_FS */
+
+	/* Initialisation completed, tell core driver the number of
+	 * active queues.
+	 */
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
+	netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues);
+	rtnl_unlock();
+
+	xenvif_carrier_on(be->vif);
+
+	unregister_hotplug_status_watch(be);
+	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
+				   hotplug_status_changed,
+				   "%s/%s", dev->nodename, "hotplug-status");
+	if (!err)
+		be->have_hotplug_status_watch = 1;
+
+	netif_tx_wake_all_queues(be->vif->dev);
+
+	return;
+
+err:
+	if (be->vif->num_queues > 0)
+		xenvif_disconnect(be->vif); /* Clean up existing queues */
+	vfree(be->vif->queues);
+	be->vif->queues = NULL;
+	be->vif->num_queues = 0;
+	return;
+}
+
+
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
+{
+	struct xenbus_device *dev = be->dev;
+	unsigned int num_queues = queue->vif->num_queues;
+	unsigned long tx_ring_ref, rx_ring_ref;
+	unsigned int tx_evtchn, rx_evtchn;
+	int err;
+	char *xspath;
+	size_t xspathsize;
+	const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */
+
+	/* If the frontend requested 1 queue, or we have fallen back
+	 * to single queue due to lack of frontend support for multi-
+	 * queue, expect the remaining XenStore keys in the toplevel
+	 * directory. Otherwise, expect them in a subdirectory called
+	 * queue-N.
+	 */
+	if (num_queues == 1) {
+		xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		strcpy(xspath, dev->otherend);
+	} else {
+		xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
+		xspath = kzalloc(xspathsize, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend,
+			 queue->id);
+	}
+
+	err = xenbus_gather(XBT_NIL, xspath,
+			    "tx-ring-ref", "%lu", &tx_ring_ref,
+			    "rx-ring-ref", "%lu", &rx_ring_ref, NULL);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "reading %s/ring-ref",
+				 xspath);
+		goto err;
+	}
+
+	/* Try split event channels first, then single event channel. */
+	err = xenbus_gather(XBT_NIL, xspath,
+			    "event-channel-tx", "%u", &tx_evtchn,
+			    "event-channel-rx", "%u", &rx_evtchn, NULL);
+	if (err < 0) {
+		err = xenbus_scanf(XBT_NIL, xspath,
+				   "event-channel", "%u", &tx_evtchn);
+		if (err < 0) {
+			xenbus_dev_fatal(dev, err,
+					 "reading %s/event-channel(-tx/rx)",
+					 xspath);
+			goto err;
+		}
+		rx_evtchn = tx_evtchn;
+	}
+
+	/* Map the shared frame, irq etc. */
+	err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref,
+			     tx_evtchn, rx_evtchn);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "mapping shared-frames %lu/%lu port tx %u rx %u",
+				 tx_ring_ref, rx_ring_ref,
+				 tx_evtchn, rx_evtchn);
+		goto err;
+	}
+
+	err = 0;
+err: /* Regular return falls through with err == 0 */
+	kfree(xspath);
+	return err;
+}
+
+static int read_xenbus_vif_flags(struct backend_info *be)
+{
+	struct xenvif *vif = be->vif;
+	struct xenbus_device *dev = be->dev;
+	unsigned int rx_copy;
+	int err, val;
+
+	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
+			   &rx_copy);
+	if (err == -ENOENT) {
+		err = 0;
+		rx_copy = 0;
+	}
+	if (err < 0) {
+		xenbus_dev_fatal(dev, err, "reading %s/request-rx-copy",
+				 dev->otherend);
+		return err;
+	}
+	if (!rx_copy)
+		return -EOPNOTSUPP;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend,
+			 "feature-rx-notify", "%d", &val) < 0)
+		val = 0;
+	if (!val) {
+		/* - Reduce drain timeout to poll more frequently for
+		 *   Rx requests.
+		 * - Disable Rx stall detection.
+		 */
+		be->vif->drain_timeout = msecs_to_jiffies(30);
+		be->vif->stall_timeout = 0;
+	}
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->can_sg = !!val;
+
+	vif->gso_mask = 0;
+	vif->gso_prefix_mask = 0;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_mask |= GSO_BIT(TCPV4);
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_prefix_mask |= GSO_BIT(TCPV4);
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_mask |= GSO_BIT(TCPV6);
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_prefix_mask |= GSO_BIT(TCPV6);
+
+	if (vif->gso_mask & vif->gso_prefix_mask) {
+		xenbus_dev_fatal(dev, err,
+				 "%s: gso and gso prefix flags are not "
+				 "mutually exclusive",
+				 dev->otherend);
+		return -EOPNOTSUPP;
+	}
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->ip_csum = !val;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->ipv6_csum = !!val;
+
+	return 0;
+}
+
+static const struct xenbus_device_id netback_ids[] = {
+	{ "vif" },
+	{ "" }
+};
+
+static struct xenbus_driver netback_driver = {
+	.ids = netback_ids,
+	.probe = netback_probe,
+	.remove = netback_remove,
+	.uevent = netback_uevent,
+	.otherend_changed = frontend_changed,
+};
+
+int xenvif_xenbus_init(void)
+{
+	return xenbus_register_backend(&netback_driver);
+}
+
+void xenvif_xenbus_fini(void)
+{
+	return xenbus_unregister_driver(&netback_driver);
+}