initial_commit

7 files changed, 1930 insertions, 0 deletions

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
new file mode 100644
index 00000000..3dd6294d
--- /dev/null
+++ b/drivers/virtio/Kconfig
@@ -0,0 +1,35 @@
+# Virtio always gets selected by whoever wants it.
+config VIRTIO
+	tristate
+
+# Similarly the virtio ring implementation.
+config VIRTIO_RING
+	tristate
+	depends on VIRTIO
+
+config VIRTIO_PCI
+	tristate "PCI driver for virtio devices (EXPERIMENTAL)"
+	depends on PCI && EXPERIMENTAL
+	select VIRTIO
+	select VIRTIO_RING
+	---help---
+	  This drivers provides support for virtio based paravirtual device
+	  drivers over PCI.  This requires that your VMM has appropriate PCI
+	  virtio backends.  Most QEMU based VMMs should support these devices
+	  (like KVM or Xen).
+
+	  Currently, the ABI is not considered stable so there is no guarantee
+	  that this version of the driver will work with your VMM.
+
+	  If unsure, say M.
+
+config VIRTIO_BALLOON
+	tristate "Virtio balloon driver (EXPERIMENTAL)"
+	select VIRTIO
+	select VIRTIO_RING
+	---help---
+	 This driver supports increasing and decreasing the amount
+	 of memory within a KVM guest.
+
+	 If unsure, say M.
+
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
new file mode 100644
index 00000000..6738c446
--- /dev/null
+++ b/drivers/virtio/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_VIRTIO) += virtio.o
+obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
+obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/config.c b/drivers/virtio/config.c
new file mode 100644
index 00000000..983d482f
--- /dev/null
+++ b/drivers/virtio/config.c
@@ -0,0 +1,13 @@
+/* Configuration space parsing helpers for virtio.
+ *
+ * The configuration is [type][len][... len bytes ...] fields.
+ *
+ * Copyright 2007 Rusty Russell, IBM Corporation.
+ * GPL v2 or later.
+ */
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/bug.h>
+#include <asm/system.h>
+
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
new file mode 100644
index 00000000..efb35aa8
--- /dev/null
+++ b/drivers/virtio/virtio.c
@@ -0,0 +1,236 @@
+#include <linux/virtio.h>
+#include <linux/spinlock.h>
+#include <linux/virtio_config.h>
+
+/* Unique numbering for virtio devices. */
+static unsigned int dev_index;
+
+static ssize_t device_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	return sprintf(buf, "0x%04x\n", dev->id.device);
+}
+static ssize_t vendor_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	return sprintf(buf, "0x%04x\n", dev->id.vendor);
+}
+static ssize_t status_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+}
+static ssize_t modalias_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+
+	return sprintf(buf, "virtio:d%08Xv%08X\n",
+		       dev->id.device, dev->id.vendor);
+}
+static ssize_t features_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = container_of(_d, struct virtio_device, dev);
+	unsigned int i;
+	ssize_t len = 0;
+
+	/* We actually represent this as a bitstring, as it could be
+	 * arbitrary length in future. */
+	for (i = 0; i < ARRAY_SIZE(dev->features)*BITS_PER_LONG; i++)
+		len += sprintf(buf+len, "%c",
+			       test_bit(i, dev->features) ? '1' : '0');
+	len += sprintf(buf+len, "\n");
+	return len;
+}
+static struct device_attribute virtio_dev_attrs[] = {
+	__ATTR_RO(device),
+	__ATTR_RO(vendor),
+	__ATTR_RO(status),
+	__ATTR_RO(modalias),
+	__ATTR_RO(features),
+	__ATTR_NULL
+};
+
+static inline int virtio_id_match(const struct virtio_device *dev,
+				  const struct virtio_device_id *id)
+{
+	if (id->device != dev->id.device && id->device != VIRTIO_DEV_ANY_ID)
+		return 0;
+
+	return id->vendor == VIRTIO_DEV_ANY_ID || id->vendor == dev->id.vendor;
+}
+
+/* This looks through all the IDs a driver claims to support.  If any of them
+ * match, we return 1 and the kernel will call virtio_dev_probe(). */
+static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
+{
+	unsigned int i;
+	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+	const struct virtio_device_id *ids;
+
+	ids = container_of(_dr, struct virtio_driver, driver)->id_table;
+	for (i = 0; ids[i].device; i++)
+		if (virtio_id_match(dev, &ids[i]))
+			return 1;
+	return 0;
+}
+
+static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env)
+{
+	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+
+	return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
+			      dev->id.device, dev->id.vendor);
+}
+
+static void add_status(struct virtio_device *dev, unsigned status)
+{
+	dev->config->set_status(dev, dev->config->get_status(dev) | status);
+}
+
+void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
+					 unsigned int fbit)
+{
+	unsigned int i;
+	struct virtio_driver *drv = container_of(vdev->dev.driver,
+						 struct virtio_driver, driver);
+
+	for (i = 0; i < drv->feature_table_size; i++)
+		if (drv->feature_table[i] == fbit)
+			return;
+	BUG();
+}
+EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
+
+static int virtio_dev_probe(struct device *_d)
+{
+	int err, i;
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_driver *drv = container_of(dev->dev.driver,
+						 struct virtio_driver, driver);
+	u32 device_features;
+
+	/* We have a driver! */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	/* Figure out what features the device supports. */
+	device_features = dev->config->get_features(dev);
+
+	/* Features supported by both device and driver into dev->features. */
+	memset(dev->features, 0, sizeof(dev->features));
+	for (i = 0; i < drv->feature_table_size; i++) {
+		unsigned int f = drv->feature_table[i];
+		BUG_ON(f >= 32);
+		if (device_features & (1 << f))
+			set_bit(f, dev->features);
+	}
+
+	/* Transport features always preserved to pass to finalize_features. */
+	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
+		if (device_features & (1 << i))
+			set_bit(i, dev->features);
+
+	dev->config->finalize_features(dev);
+
+	err = drv->probe(dev);
+	if (err)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	else
+		add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	return err;
+}
+
+static int virtio_dev_remove(struct device *_d)
+{
+	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_driver *drv = container_of(dev->dev.driver,
+						 struct virtio_driver, driver);
+
+	drv->remove(dev);
+
+	/* Driver should have reset device. */
+	BUG_ON(dev->config->get_status(dev));
+
+	/* Acknowledge the device's existence again. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+	return 0;
+}
+
+static struct bus_type virtio_bus = {
+	.name  = "virtio",
+	.match = virtio_dev_match,
+	.dev_attrs = virtio_dev_attrs,
+	.uevent = virtio_uevent,
+	.probe = virtio_dev_probe,
+	.remove = virtio_dev_remove,
+};
+
+int register_virtio_driver(struct virtio_driver *driver)
+{
+	/* Catch this early. */
+	BUG_ON(driver->feature_table_size && !driver->feature_table);
+	driver->driver.bus = &virtio_bus;
+	return driver_register(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(register_virtio_driver);
+
+void unregister_virtio_driver(struct virtio_driver *driver)
+{
+	driver_unregister(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_driver);
+
+int register_virtio_device(struct virtio_device *dev)
+{
+	int err;
+
+	dev->dev.bus = &virtio_bus;
+
+	/* Assign a unique device index and hence name. */
+	dev->index = dev_index++;
+	dev_set_name(&dev->dev, "virtio%u", dev->index);
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up.  This also tests that code path a little. */
+	dev->config->reset(dev);
+
+	/* Acknowledge that we've seen the device. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	INIT_LIST_HEAD(&dev->vqs);
+
+	/* device_register() causes the bus infrastructure to look for a
+	 * matching driver. */
+	err = device_register(&dev->dev);
+	if (err)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_virtio_device);
+
+void unregister_virtio_device(struct virtio_device *dev)
+{
+	device_unregister(&dev->dev);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_device);
+
+static int virtio_init(void)
+{
+	if (bus_register(&virtio_bus) != 0)
+		panic("virtio bus registration failed");
+	return 0;
+}
+
+static void __exit virtio_exit(void)
+{
+	bus_unregister(&virtio_bus);
+}
+core_initcall(virtio_init);
+module_exit(virtio_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
new file mode 100644
index 00000000..e058ace2
--- /dev/null
+++ b/drivers/virtio/virtio_balloon.c
@@ -0,0 +1,383 @@
+/* Virtio balloon implementation, inspired by Dor Loar and Marcelo
+ * Tosatti's implementations.
+ *
+ *  Copyright 2008 Rusty Russell IBM Corporation
+ *
+ *  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, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+//#define DEBUG
+#include <linux/virtio.h>
+#include <linux/virtio_balloon.h>
+#include <linux/swap.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+
+struct virtio_balloon
+{
+	struct virtio_device *vdev;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+
+	/* Where the ballooning thread waits for config to change. */
+	wait_queue_head_t config_change;
+
+	/* The thread servicing the balloon. */
+	struct task_struct *thread;
+
+	/* Waiting for host to ack the pages we released. */
+	struct completion acked;
+
+	/* The pages we've told the Host we're not using. */
+	unsigned int num_pages;
+	struct list_head pages;
+
+	/* The array of pfns we tell the Host about. */
+	unsigned int num_pfns;
+	u32 pfns[256];
+
+	/* Memory statistics */
+	int need_stats_update;
+	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+};
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static u32 page_to_balloon_pfn(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+
+	BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
+	/* Convert pfn from Linux page size to balloon page size. */
+	return pfn >> (PAGE_SHIFT - VIRTIO_BALLOON_PFN_SHIFT);
+}
+
+static void balloon_ack(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb;
+	unsigned int len;
+
+	vb = virtqueue_get_buf(vq, &len);
+	if (vb)
+		complete(&vb->acked);
+}
+
+static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
+{
+	struct scatterlist sg;
+
+	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
+
+	init_completion(&vb->acked);
+
+	/* We should always be able to add one buffer to an empty queue. */
+	if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0)
+		BUG();
+	virtqueue_kick(vq);
+
+	/* When host has read buffer, this completes via balloon_ack */
+	wait_for_completion(&vb->acked);
+}
+
+static void fill_balloon(struct virtio_balloon *vb, size_t num)
+{
+	/* We can only do one array worth at a time. */
+	num = min(num, ARRAY_SIZE(vb->pfns));
+
+	for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
+		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
+					__GFP_NOMEMALLOC | __GFP_NOWARN);
+		if (!page) {
+			if (printk_ratelimit())
+				dev_printk(KERN_INFO, &vb->vdev->dev,
+					   "Out of puff! Can't get %zu pages\n",
+					   num);
+			/* Sleep for at least 1/5 of a second before retry. */
+			msleep(200);
+			break;
+		}
+		vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
+		totalram_pages--;
+		vb->num_pages++;
+		list_add(&page->lru, &vb->pages);
+	}
+
+	/* Didn't get any?  Oh well. */
+	if (vb->num_pfns == 0)
+		return;
+
+	tell_host(vb, vb->inflate_vq);
+}
+
+static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++) {
+		__free_page(pfn_to_page(pfns[i]));
+		totalram_pages++;
+	}
+}
+
+static void leak_balloon(struct virtio_balloon *vb, size_t num)
+{
+	struct page *page;
+
+	/* We can only do one array worth at a time. */
+	num = min(num, ARRAY_SIZE(vb->pfns));
+
+	for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
+		page = list_first_entry(&vb->pages, struct page, lru);
+		list_del(&page->lru);
+		vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
+		vb->num_pages--;
+	}
+
+
+	/*
+	 * Note that if
+	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+	 * is true, we *have* to do it in this order
+	 */
+	tell_host(vb, vb->deflate_vq);
+	release_pages_by_pfn(vb->pfns, vb->num_pfns);
+}
+
+static inline void update_stat(struct virtio_balloon *vb, int idx,
+			       u16 tag, u64 val)
+{
+	BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
+	vb->stats[idx].tag = tag;
+	vb->stats[idx].val = val;
+}
+
+#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
+
+static void update_balloon_stats(struct virtio_balloon *vb)
+{
+	unsigned long events[NR_VM_EVENT_ITEMS];
+	struct sysinfo i;
+	int idx = 0;
+
+	all_vm_events(events);
+	si_meminfo(&i);
+
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
+				pages_to_bytes(events[PSWPIN]));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
+				pages_to_bytes(events[PSWPOUT]));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
+				pages_to_bytes(i.freeram));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
+				pages_to_bytes(i.totalram));
+}
+
+/*
+ * While most virtqueues communicate guest-initiated requests to the hypervisor,
+ * the stats queue operates in reverse.  The driver initializes the virtqueue
+ * with a single buffer.  From that point forward, all conversations consist of
+ * a hypervisor request (a call to this function) which directs us to refill
+ * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
+ * we notify our kthread which does the actual work via stats_handle_request().
+ */
+static void stats_request(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb;
+	unsigned int len;
+
+	vb = virtqueue_get_buf(vq, &len);
+	if (!vb)
+		return;
+	vb->need_stats_update = 1;
+	wake_up(&vb->config_change);
+}
+
+static void stats_handle_request(struct virtio_balloon *vb)
+{
+	struct virtqueue *vq;
+	struct scatterlist sg;
+
+	vb->need_stats_update = 0;
+	update_balloon_stats(vb);
+
+	vq = vb->stats_vq;
+	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+	if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0)
+		BUG();
+	virtqueue_kick(vq);
+}
+
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	wake_up(&vb->config_change);
+}
+
+static inline s64 towards_target(struct virtio_balloon *vb)
+{
+	u32 v;
+	vb->vdev->config->get(vb->vdev,
+			      offsetof(struct virtio_balloon_config, num_pages),
+			      &v, sizeof(v));
+	return (s64)v - vb->num_pages;
+}
+
+static void update_balloon_size(struct virtio_balloon *vb)
+{
+	__le32 actual = cpu_to_le32(vb->num_pages);
+
+	vb->vdev->config->set(vb->vdev,
+			      offsetof(struct virtio_balloon_config, actual),
+			      &actual, sizeof(actual));
+}
+
+static int balloon(void *_vballoon)
+{
+	struct virtio_balloon *vb = _vballoon;
+
+	set_freezable();
+	while (!kthread_should_stop()) {
+		s64 diff;
+
+		try_to_freeze();
+		wait_event_interruptible(vb->config_change,
+					 (diff = towards_target(vb)) != 0
+					 || vb->need_stats_update
+					 || kthread_should_stop()
+					 || freezing(current));
+		if (vb->need_stats_update)
+			stats_handle_request(vb);
+		if (diff > 0)
+			fill_balloon(vb, diff);
+		else if (diff < 0)
+			leak_balloon(vb, -diff);
+		update_balloon_size(vb);
+	}
+	return 0;
+}
+
+static int virtballoon_probe(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb;
+	struct virtqueue *vqs[3];
+	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
+	const char *names[] = { "inflate", "deflate", "stats" };
+	int err, nvqs;
+
+	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
+	if (!vb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&vb->pages);
+	vb->num_pages = 0;
+	init_waitqueue_head(&vb->config_change);
+	vb->vdev = vdev;
+	vb->need_stats_update = 0;
+
+	/* We expect two virtqueues: inflate and deflate,
+	 * and optionally stat. */
+	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
+	if (err)
+		goto out_free_vb;
+
+	vb->inflate_vq = vqs[0];
+	vb->deflate_vq = vqs[1];
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+		struct scatterlist sg;
+		vb->stats_vq = vqs[2];
+
+		/*
+		 * Prime this virtqueue with one buffer so the hypervisor can
+		 * use it to signal us later.
+		 */
+		sg_init_one(&sg, vb->stats, sizeof vb->stats);
+		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb) < 0)
+			BUG();
+		virtqueue_kick(vb->stats_vq);
+	}
+
+	vb->thread = kthread_run(balloon, vb, "vballoon");
+	if (IS_ERR(vb->thread)) {
+		err = PTR_ERR(vb->thread);
+		goto out_del_vqs;
+	}
+
+	return 0;
+
+out_del_vqs:
+	vdev->config->del_vqs(vdev);
+out_free_vb:
+	kfree(vb);
+out:
+	return err;
+}
+
+static void __devexit virtballoon_remove(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	kthread_stop(vb->thread);
+
+	/* There might be pages left in the balloon: free them. */
+	while (vb->num_pages)
+		leak_balloon(vb, vb->num_pages);
+
+	/* Now we reset the device so we can clean up the queues. */
+	vdev->config->reset(vdev);
+
+	vdev->config->del_vqs(vdev);
+	kfree(vb);
+}
+
+static unsigned int features[] = {
+	VIRTIO_BALLOON_F_MUST_TELL_HOST,
+	VIRTIO_BALLOON_F_STATS_VQ,
+};
+
+static struct virtio_driver virtio_balloon_driver = {
+	.feature_table = features,
+	.feature_table_size = ARRAY_SIZE(features),
+	.driver.name =	KBUILD_MODNAME,
+	.driver.owner =	THIS_MODULE,
+	.id_table =	id_table,
+	.probe =	virtballoon_probe,
+	.remove =	__devexit_p(virtballoon_remove),
+	.config_changed = virtballoon_changed,
+};
+
+static int __init init(void)
+{
+	return register_virtio_driver(&virtio_balloon_driver);
+}
+
+static void __exit fini(void)
+{
+	unregister_virtio_driver(&virtio_balloon_driver);
+}
+module_init(init);
+module_exit(fini);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio balloon driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
new file mode 100644
index 00000000..ecb92541
--- /dev/null
+++ b/drivers/virtio/virtio_pci.c
@@ -0,0 +1,727 @@
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+
+MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
+MODULE_DESCRIPTION("virtio-pci");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1");
+
+/* Our device structure */
+struct virtio_pci_device
+{
+	struct virtio_device vdev;
+	struct pci_dev *pci_dev;
+
+	/* the IO mapping for the PCI config space */
+	void __iomem *ioaddr;
+
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+
+	/* MSI-X support */
+	int msix_enabled;
+	int intx_enabled;
+	struct msix_entry *msix_entries;
+	/* Name strings for interrupts. This size should be enough,
+	 * and I'm too lazy to allocate each name separately. */
+	char (*msix_names)[256];
+	/* Number of available vectors */
+	unsigned msix_vectors;
+	/* Vectors allocated, excluding per-vq vectors if any */
+	unsigned msix_used_vectors;
+	/* Whether we have vector per vq */
+	bool per_vq_vectors;
+};
+
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+	VP_MSIX_CONFIG_VECTOR = 0,
+	VP_MSIX_VQ_VECTOR = 1,
+};
+
+struct virtio_pci_vq_info
+{
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the number of entries in the queue */
+	int num;
+
+	/* the index of the queue */
+	int queue_index;
+
+	/* the virtual address of the ring queue */
+	void *queue;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+
+	/* MSI-X vector (or none) */
+	unsigned msix_vector;
+};
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static struct pci_device_id virtio_pci_id_table[] = {
+	{ 0x1af4, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
+	{ 0 },
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+	return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* virtio config->get_features() implementation */
+static u32 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* When someone needs more than 32 feature bits, we'll need to
+	 * steal a bit to indicate that the rest are somewhere else. */
+	return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+
+/* virtio config->finalize_features() implementation */
+static void vp_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	/* We only support 32 feature bits. */
+	BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
+	iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
+	u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation.  it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
+	const u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* 0 status means a reset. */
+	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+/* the notify function used when creating a virt queue */
+static void vp_notify(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+
+	/* we write the queue's selector into the notification register to
+	 * signal the other end */
+	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+}
+
+/* Handle a configuration change: Tell driver if it wants to know. */
+static irqreturn_t vp_config_changed(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	struct virtio_driver *drv;
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	if (drv && drv->config_changed)
+		drv->config_changed(&vp_dev->vdev);
+	return IRQ_HANDLED;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	struct virtio_pci_vq_info *info;
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->virtqueues, node) {
+		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	return ret;
+}
+
+/* A small wrapper to also acknowledge the interrupt when it's handled.
+ * I really need an EIO hook for the vring so I can ack the interrupt once we
+ * know that we'll be handling the IRQ but before we invoke the callback since
+ * the callback may notify the host which results in the host attempting to
+ * raise an interrupt that we would then mask once we acknowledged the
+ * interrupt. */
+static irqreturn_t vp_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	u8 isr;
+
+	/* reading the ISR has the effect of also clearing it so it's very
+	 * important to save off the value. */
+	isr = ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+
+	/* It's definitely not us if the ISR was not high */
+	if (!isr)
+		return IRQ_NONE;
+
+	/* Configuration change?  Tell driver if it wants to know. */
+	if (isr & VIRTIO_PCI_ISR_CONFIG)
+		vp_config_changed(irq, opaque);
+
+	return vp_vring_interrupt(irq, opaque);
+}
+
+static void vp_free_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled) {
+		free_irq(vp_dev->pci_dev->irq, vp_dev);
+		vp_dev->intx_enabled = 0;
+	}
+
+	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+		free_irq(vp_dev->msix_entries[i].vector, vp_dev);
+
+	if (vp_dev->msix_enabled) {
+		/* Disable the vector used for configuration */
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+		/* Flush the write out to device */
+		ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+
+		pci_disable_msix(vp_dev->pci_dev);
+		vp_dev->msix_enabled = 0;
+		vp_dev->msix_vectors = 0;
+	}
+
+	vp_dev->msix_used_vectors = 0;
+	kfree(vp_dev->msix_names);
+	vp_dev->msix_names = NULL;
+	kfree(vp_dev->msix_entries);
+	vp_dev->msix_entries = NULL;
+}
+
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+				   bool per_vq_vectors)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	unsigned i, v;
+	int err = -ENOMEM;
+
+	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
+				       GFP_KERNEL);
+	if (!vp_dev->msix_entries)
+		goto error;
+	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+				     GFP_KERNEL);
+	if (!vp_dev->msix_names)
+		goto error;
+
+	for (i = 0; i < nvectors; ++i)
+		vp_dev->msix_entries[i].entry = i;
+
+	/* pci_enable_msix returns positive if we can't get this many. */
+	err = pci_enable_msix(vp_dev->pci_dev, vp_dev->msix_entries, nvectors);
+	if (err > 0)
+		err = -ENOSPC;
+	if (err)
+		goto error;
+	vp_dev->msix_vectors = nvectors;
+	vp_dev->msix_enabled = 1;
+
+	/* Set the vector used for configuration */
+	v = vp_dev->msix_used_vectors;
+	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+		 "%s-config", name);
+	err = request_irq(vp_dev->msix_entries[v].vector,
+			  vp_config_changed, 0, vp_dev->msix_names[v],
+			  vp_dev);
+	if (err)
+		goto error;
+	++vp_dev->msix_used_vectors;
+
+	iowrite16(v, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	/* Verify we had enough resources to assign the vector */
+	v = ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	if (v == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto error;
+	}
+
+	if (!per_vq_vectors) {
+		/* Shared vector for all VQs */
+		v = vp_dev->msix_used_vectors;
+		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+			 "%s-virtqueues", name);
+		err = request_irq(vp_dev->msix_entries[v].vector,
+				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
+				  vp_dev);
+		if (err)
+			goto error;
+		++vp_dev->msix_used_vectors;
+	}
+	return 0;
+error:
+	vp_free_vectors(vdev);
+	return err;
+}
+
+static int vp_request_intx(struct virtio_device *vdev)
+{
+	int err;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
+			  IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
+	if (!err)
+		vp_dev->intx_enabled = 1;
+	return err;
+}
+
+static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name,
+				  u16 msix_vec)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info;
+	struct virtqueue *vq;
+	unsigned long flags, size;
+	u16 num;
+	int err;
+
+	/* Select the queue we're interested in */
+	iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+	/* Check if queue is either not available or already active. */
+	num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+		return ERR_PTR(-ENOENT);
+
+	/* allocate and fill out our structure the represents an active
+	 * queue */
+	info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->queue_index = index;
+	info->num = num;
+	info->msix_vector = msix_vec;
+
+	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
+	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
+	if (info->queue == NULL) {
+		err = -ENOMEM;
+		goto out_info;
+	}
+
+	/* activate the queue */
+	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN,
+				 vdev, info->queue, vp_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto out_activate_queue;
+	}
+
+	vq->priv = info;
+	info->vq = vq;
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto out_assign;
+		}
+	}
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_add(&info->node, &vp_dev->virtqueues);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	return vq;
+
+out_assign:
+	vring_del_virtqueue(vq);
+out_activate_queue:
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	free_pages_exact(info->queue, size);
+out_info:
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	unsigned long flags, size;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+	if (vp_dev->msix_enabled) {
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		/* Flush the write out to device */
+		ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+	}
+
+	vring_del_virtqueue(vq);
+
+	/* Select and deactivate the queue */
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info);
+}
+
+/* the config->del_vqs() implementation */
+static void vp_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq, *n;
+	struct virtio_pci_vq_info *info;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		info = vq->priv;
+		if (vp_dev->per_vq_vectors &&
+			info->msix_vector != VIRTIO_MSI_NO_VECTOR)
+			free_irq(vp_dev->msix_entries[info->msix_vector].vector,
+				 vq);
+		vp_del_vq(vq);
+	}
+	vp_dev->per_vq_vectors = false;
+
+	vp_free_vectors(vdev);
+}
+
+static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char *names[],
+			      bool use_msix,
+			      bool per_vq_vectors)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u16 msix_vec;
+	int i, err, nvectors, allocated_vectors;
+
+	if (!use_msix) {
+		/* Old style: one normal interrupt for change and all vqs. */
+		err = vp_request_intx(vdev);
+		if (err)
+			goto error_request;
+	} else {
+		if (per_vq_vectors) {
+			/* Best option: one for change interrupt, one per vq. */
+			nvectors = 1;
+			for (i = 0; i < nvqs; ++i)
+				if (callbacks[i])
+					++nvectors;
+		} else {
+			/* Second best: one for change, shared for all vqs. */
+			nvectors = 2;
+		}
+
+		err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
+		if (err)
+			goto error_request;
+	}
+
+	vp_dev->per_vq_vectors = per_vq_vectors;
+	allocated_vectors = vp_dev->msix_used_vectors;
+	for (i = 0; i < nvqs; ++i) {
+		if (!callbacks[i] || !vp_dev->msix_enabled)
+			msix_vec = VIRTIO_MSI_NO_VECTOR;
+		else if (vp_dev->per_vq_vectors)
+			msix_vec = allocated_vectors++;
+		else
+			msix_vec = VP_MSIX_VQ_VECTOR;
+		vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto error_find;
+		}
+
+		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+			continue;
+
+		/* allocate per-vq irq if available and necessary */
+		snprintf(vp_dev->msix_names[msix_vec],
+			 sizeof *vp_dev->msix_names,
+			 "%s-%s",
+			 dev_name(&vp_dev->vdev.dev), names[i]);
+		err = request_irq(vp_dev->msix_entries[msix_vec].vector,
+				  vring_interrupt, 0,
+				  vp_dev->msix_names[msix_vec],
+				  vqs[i]);
+		if (err) {
+			vp_del_vq(vqs[i]);
+			goto error_find;
+		}
+	}
+	return 0;
+
+error_find:
+	vp_del_vqs(vdev);
+
+error_request:
+	return err;
+}
+
+/* the config->find_vqs() implementation */
+static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+		       struct virtqueue *vqs[],
+		       vq_callback_t *callbacks[],
+		       const char *names[])
+{
+	int err;
+
+	/* Try MSI-X with one vector per queue. */
+	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
+	if (!err)
+		return 0;
+	/* Fallback: MSI-X with one vector for config, one shared for queues. */
+	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+				 true, false);
+	if (!err)
+		return 0;
+	/* Finally fall back to regular interrupts. */
+	return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+				  false, false);
+}
+
+static struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+};
+
+static void virtio_pci_release_dev(struct device *_d)
+{
+	/*
+	 * No need for a release method as we allocate/free
+	 * all devices together with the pci devices.
+	 * Provide an empty one to avoid getting a warning from core.
+	 */
+}
+
+/* the PCI probing function */
+static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
+				      const struct pci_device_id *id)
+{
+	struct virtio_pci_device *vp_dev;
+	int err;
+
+	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+		return -ENODEV;
+
+	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
+		printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
+		       VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
+		return -ENODEV;
+	}
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+	if (vp_dev == NULL)
+		return -ENOMEM;
+
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	spin_lock_init(&vp_dev->lock);
+
+	/* Disable MSI/MSIX to bring device to a known good state. */
+	pci_msi_off(pci_dev);
+
+	/* enable the device */
+	err = pci_enable_device(pci_dev);
+	if (err)
+		goto out;
+
+	err = pci_request_regions(pci_dev, "virtio-pci");
+	if (err)
+		goto out_enable_device;
+
+	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
+	if (vp_dev->ioaddr == NULL)
+		goto out_req_regions;
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	pci_set_master(pci_dev);
+
+	/* we use the subsystem vendor/device id as the virtio vendor/device
+	 * id.  this allows us to use the same PCI vendor/device id for all
+	 * virtio devices and to identify the particular virtio driver by
+	 * the subsystem ids */
+	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+	vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+	/* finally register the virtio device */
+	err = register_virtio_device(&vp_dev->vdev);
+	if (err)
+		goto out_set_drvdata;
+
+	return 0;
+
+out_set_drvdata:
+	pci_set_drvdata(pci_dev, NULL);
+	pci_iounmap(pci_dev, vp_dev->ioaddr);
+out_req_regions:
+	pci_release_regions(pci_dev);
+out_enable_device:
+	pci_disable_device(pci_dev);
+out:
+	kfree(vp_dev);
+	return err;
+}
+
+static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	vp_del_vqs(&vp_dev->vdev);
+	pci_set_drvdata(pci_dev, NULL);
+	pci_iounmap(pci_dev, vp_dev->ioaddr);
+	pci_release_regions(pci_dev);
+	pci_disable_device(pci_dev);
+	kfree(vp_dev);
+}
+
+#ifdef CONFIG_PM
+static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state)
+{
+	pci_save_state(pci_dev);
+	pci_set_power_state(pci_dev, PCI_D3hot);
+	return 0;
+}
+
+static int virtio_pci_resume(struct pci_dev *pci_dev)
+{
+	pci_restore_state(pci_dev);
+	pci_set_power_state(pci_dev, PCI_D0);
+	return 0;
+}
+#endif
+
+static struct pci_driver virtio_pci_driver = {
+	.name		= "virtio-pci",
+	.id_table	= virtio_pci_id_table,
+	.probe		= virtio_pci_probe,
+	.remove		= __devexit_p(virtio_pci_remove),
+#ifdef CONFIG_PM
+	.suspend	= virtio_pci_suspend,
+	.resume		= virtio_pci_resume,
+#endif
+};
+
+static int __init virtio_pci_init(void)
+{
+	return pci_register_driver(&virtio_pci_driver);
+}
+
+module_init(virtio_pci_init);
+
+static void __exit virtio_pci_exit(void)
+{
+	pci_unregister_driver(&virtio_pci_driver);
+}
+
+module_exit(virtio_pci_exit);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
new file mode 100644
index 00000000..68b91368
--- /dev/null
+++ b/drivers/virtio/virtio_ring.c
@@ -0,0 +1,532 @@
+/* Virtio ring implementation.
+ *
+ *  Copyright 2007 Rusty Russell IBM Corporation
+ *
+ *  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, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include <linux/virtio.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_config.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+
+/* virtio guest is communicating with a virtual "device" that actually runs on
+ * a host processor.  Memory barriers are used to control SMP effects. */
+#ifdef CONFIG_SMP
+/* Where possible, use SMP barriers which are more lightweight than mandatory
+ * barriers, because mandatory barriers control MMIO effects on accesses
+ * through relaxed memory I/O windows (which virtio does not use). */
+#define virtio_mb() smp_mb()
+#define virtio_rmb() smp_rmb()
+#define virtio_wmb() smp_wmb()
+#else
+/* We must force memory ordering even if guest is UP since host could be
+ * running on another CPU, but SMP barriers are defined to barrier() in that
+ * configuration. So fall back to mandatory barriers instead. */
+#define virtio_mb() mb()
+#define virtio_rmb() rmb()
+#define virtio_wmb() wmb()
+#endif
+
+#ifdef DEBUG
+/* For development, we want to crash whenever the ring is screwed. */
+#define BAD_RING(_vq, fmt, args...)				\
+	do {							\
+		dev_err(&(_vq)->vq.vdev->dev,			\
+			"%s:"fmt, (_vq)->vq.name, ##args);	\
+		BUG();						\
+	} while (0)
+/* Caller is supposed to guarantee no reentry. */
+#define START_USE(_vq)						\
+	do {							\
+		if ((_vq)->in_use)				\
+			panic("%s:in_use = %i\n",		\
+			      (_vq)->vq.name, (_vq)->in_use);	\
+		(_vq)->in_use = __LINE__;			\
+	} while (0)
+#define END_USE(_vq) \
+	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
+#else
+#define BAD_RING(_vq, fmt, args...)				\
+	do {							\
+		dev_err(&_vq->vq.vdev->dev,			\
+			"%s:"fmt, (_vq)->vq.name, ##args);	\
+		(_vq)->broken = true;				\
+	} while (0)
+#define START_USE(vq)
+#define END_USE(vq)
+#endif
+
+struct vring_virtqueue
+{
+	struct virtqueue vq;
+
+	/* Actual memory layout for this queue */
+	struct vring vring;
+
+	/* Other side has made a mess, don't try any more. */
+	bool broken;
+
+	/* Host supports indirect buffers */
+	bool indirect;
+
+	/* Host publishes avail event idx */
+	bool event;
+
+	/* Number of free buffers */
+	unsigned int num_free;
+	/* Head of free buffer list. */
+	unsigned int free_head;
+	/* Number we've added since last sync. */
+	unsigned int num_added;
+
+	/* Last used index we've seen. */
+	u16 last_used_idx;
+
+	/* How to notify other side. FIXME: commonalize hcalls! */
+	void (*notify)(struct virtqueue *vq);
+
+#ifdef DEBUG
+	/* They're supposed to lock for us. */
+	unsigned int in_use;
+#endif
+
+	/* Tokens for callbacks. */
+	void *data[];
+};
+
+#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+
+/* Set up an indirect table of descriptors and add it to the queue. */
+static int vring_add_indirect(struct vring_virtqueue *vq,
+			      struct scatterlist sg[],
+			      unsigned int out,
+			      unsigned int in,
+			      gfp_t gfp)
+{
+	struct vring_desc *desc;
+	unsigned head;
+	int i;
+
+	desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
+	if (!desc)
+		return -ENOMEM;
+
+	/* Transfer entries from the sg list into the indirect page */
+	for (i = 0; i < out; i++) {
+		desc[i].flags = VRING_DESC_F_NEXT;
+		desc[i].addr = sg_phys(sg);
+		desc[i].len = sg->length;
+		desc[i].next = i+1;
+		sg++;
+	}
+	for (; i < (out + in); i++) {
+		desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+		desc[i].addr = sg_phys(sg);
+		desc[i].len = sg->length;
+		desc[i].next = i+1;
+		sg++;
+	}
+
+	/* Last one doesn't continue. */
+	desc[i-1].flags &= ~VRING_DESC_F_NEXT;
+	desc[i-1].next = 0;
+
+	/* We're about to use a buffer */
+	vq->num_free--;
+
+	/* Use a single buffer which doesn't continue */
+	head = vq->free_head;
+	vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
+	vq->vring.desc[head].addr = virt_to_phys(desc);
+	vq->vring.desc[head].len = i * sizeof(struct vring_desc);
+
+	/* Update free pointer */
+	vq->free_head = vq->vring.desc[head].next;
+
+	return head;
+}
+
+int virtqueue_add_buf_gfp(struct virtqueue *_vq,
+			  struct scatterlist sg[],
+			  unsigned int out,
+			  unsigned int in,
+			  void *data,
+			  gfp_t gfp)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i, avail, uninitialized_var(prev);
+	int head;
+
+	START_USE(vq);
+
+	BUG_ON(data == NULL);
+
+	/* If the host supports indirect descriptor tables, and we have multiple
+	 * buffers, then go indirect. FIXME: tune this threshold */
+	if (vq->indirect && (out + in) > 1 && vq->num_free) {
+		head = vring_add_indirect(vq, sg, out, in, gfp);
+		if (likely(head >= 0))
+			goto add_head;
+	}
+
+	BUG_ON(out + in > vq->vring.num);
+	BUG_ON(out + in == 0);
+
+	if (vq->num_free < out + in) {
+		pr_debug("Can't add buf len %i - avail = %i\n",
+			 out + in, vq->num_free);
+		/* FIXME: for historical reasons, we force a notify here if
+		 * there are outgoing parts to the buffer.  Presumably the
+		 * host should service the ring ASAP. */
+		if (out)
+			vq->notify(&vq->vq);
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	/* We're about to use some buffers from the free list. */
+	vq->num_free -= out + in;
+
+	head = vq->free_head;
+	for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
+		vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
+		vq->vring.desc[i].addr = sg_phys(sg);
+		vq->vring.desc[i].len = sg->length;
+		prev = i;
+		sg++;
+	}
+	for (; in; i = vq->vring.desc[i].next, in--) {
+		vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+		vq->vring.desc[i].addr = sg_phys(sg);
+		vq->vring.desc[i].len = sg->length;
+		prev = i;
+		sg++;
+	}
+	/* Last one doesn't continue. */
+	vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+
+	/* Update free pointer */
+	vq->free_head = i;
+
+add_head:
+	/* Set token. */
+	vq->data[head] = data;
+
+	/* Put entry in available array (but don't update avail->idx until they
+	 * do sync).  FIXME: avoid modulus here? */
+	avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num;
+	vq->vring.avail->ring[avail] = head;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return vq->num_free;
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp);
+
+void virtqueue_kick(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old;
+	START_USE(vq);
+	/* Descriptors and available array need to be set before we expose the
+	 * new available array entries. */
+	virtio_wmb();
+
+	old = vq->vring.avail->idx;
+	new = vq->vring.avail->idx = old + vq->num_added;
+	vq->num_added = 0;
+
+	/* Need to update avail index before checking if we should notify */
+	virtio_mb();
+
+	if (vq->event ?
+	    vring_need_event(vring_avail_event(&vq->vring), new, old) :
+	    !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+		/* Prod other side to tell it about changes. */
+		vq->notify(&vq->vq);
+
+	END_USE(vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick);
+
+static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+{
+	unsigned int i;
+
+	/* Clear data ptr. */
+	vq->data[head] = NULL;
+
+	/* Put back on free list: find end */
+	i = head;
+
+	/* Free the indirect table */
+	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT)
+		kfree(phys_to_virt(vq->vring.desc[i].addr));
+
+	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
+		i = vq->vring.desc[i].next;
+		vq->num_free++;
+	}
+
+	vq->vring.desc[i].next = vq->free_head;
+	vq->free_head = head;
+	/* Plus final descriptor */
+	vq->num_free++;
+}
+
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+	return vq->last_used_idx != vq->vring.used->idx;
+}
+
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	void *ret;
+	unsigned int i;
+
+	START_USE(vq);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return NULL;
+	}
+
+	if (!more_used(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	/* Only get used array entries after they have been exposed by host. */
+	virtio_rmb();
+
+	i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
+	*len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
+
+	if (unlikely(i >= vq->vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", i);
+		return NULL;
+	}
+	if (unlikely(!vq->data[i])) {
+		BAD_RING(vq, "id %u is not a head!\n", i);
+		return NULL;
+	}
+
+	/* detach_buf clears data, so grab it now. */
+	ret = vq->data[i];
+	detach_buf(vq, i);
+	vq->last_used_idx++;
+	/* If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call. */
+	if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vring_used_event(&vq->vring) = vq->last_used_idx;
+		virtio_mb();
+	}
+
+	END_USE(vq);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf);
+
+void virtqueue_disable_cb(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+}
+EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
+
+bool virtqueue_enable_cb(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	vring_used_event(&vq->vring) = vq->last_used_idx;
+	virtio_mb();
+	if (unlikely(more_used(vq))) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
+
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 bufs;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	/* TODO: tune this threshold */
+	bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+	vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+	virtio_mb();
+	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
+void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+	void *buf;
+
+	START_USE(vq);
+
+	for (i = 0; i < vq->vring.num; i++) {
+		if (!vq->data[i])
+			continue;
+		/* detach_buf clears data, so grab it now. */
+		buf = vq->data[i];
+		detach_buf(vq, i);
+		vq->vring.avail->idx--;
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->num_free != vq->vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
+
+irqreturn_t vring_interrupt(int irq, void *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!more_used(vq)) {
+		pr_debug("virtqueue interrupt with no work for %p\n", vq);
+		return IRQ_NONE;
+	}
+
+	if (unlikely(vq->broken))
+		return IRQ_HANDLED;
+
+	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
+	if (vq->vq.callback)
+		vq->vq.callback(&vq->vq);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(vring_interrupt);
+
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+				      unsigned int vring_align,
+				      struct virtio_device *vdev,
+				      void *pages,
+				      void (*notify)(struct virtqueue *),
+				      void (*callback)(struct virtqueue *),
+				      const char *name)
+{
+	struct vring_virtqueue *vq;
+	unsigned int i;
+
+	/* We assume num is a power of 2. */
+	if (num & (num - 1)) {
+		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+		return NULL;
+	}
+
+	vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL);
+	if (!vq)
+		return NULL;
+
+	vring_init(&vq->vring, num, pages, vring_align);
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.name = name;
+	vq->notify = notify;
+	vq->broken = false;
+	vq->last_used_idx = 0;
+	vq->num_added = 0;
+	list_add_tail(&vq->vq.list, &vdev->vqs);
+#ifdef DEBUG
+	vq->in_use = false;
+#endif
+
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!callback)
+		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+
+	/* Put everything in free lists. */
+	vq->num_free = num;
+	vq->free_head = 0;
+	for (i = 0; i < num-1; i++) {
+		vq->vring.desc[i].next = i+1;
+		vq->data[i] = NULL;
+	}
+	vq->data[i] = NULL;
+
+	return &vq->vq;
+}
+EXPORT_SYMBOL_GPL(vring_new_virtqueue);
+
+void vring_del_virtqueue(struct virtqueue *vq)
+{
+	list_del(&vq->list);
+	kfree(to_vvq(vq));
+}
+EXPORT_SYMBOL_GPL(vring_del_virtqueue);
+
+/* Manipulates transport-specific feature bits. */
+void vring_transport_features(struct virtio_device *vdev)
+{
+	unsigned int i;
+
+	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) {
+		switch (i) {
+		case VIRTIO_RING_F_INDIRECT_DESC:
+			break;
+		case VIRTIO_RING_F_EVENT_IDX:
+			break;
+		default:
+			/* We don't understand this bit. */
+			clear_bit(i, vdev->features);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(vring_transport_features);
+
+MODULE_LICENSE("GPL");