6 files changed, 811 insertions, 69 deletions

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 9e33fc4da87..3dd6294d10b 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -1,8 +1,35 @@
 # Virtio always gets selected by whoever wants it.
 config VIRTIO
-	bool
+	tristate
 
 # Similarly the virtio ring implementation.
 config VIRTIO_RING
-	bool
+	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
index f70e40971dd..6738c446c19 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,2 +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/virtio.c b/drivers/virtio/virtio.c
index 69d7ea02cd4..b535483bc55 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -102,9 +102,13 @@ static int virtio_dev_remove(struct device *_d)
 	struct virtio_driver *drv = container_of(dev->dev.driver,
 						 struct virtio_driver, driver);
 
-	dev->config->set_status(dev, dev->config->get_status(dev)
-				& ~VIRTIO_CONFIG_S_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;
 }
 
@@ -130,6 +134,10 @@ int register_virtio_device(struct virtio_device *dev)
 	dev->dev.bus = &virtio_bus;
 	sprintf(dev->dev.bus_id, "%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);
 
@@ -148,55 +156,18 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
-int __virtio_config_val(struct virtio_device *vdev,
-			u8 type, void *val, size_t size)
-{
-	void *token;
-	unsigned int len;
-
-	token = vdev->config->find(vdev, type, &len);
-	if (!token)
-		return -ENOENT;
-
-	if (len != size)
-		return -EIO;
-
-	vdev->config->get(vdev, token, val, size);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__virtio_config_val);
-
-int virtio_use_bit(struct virtio_device *vdev,
-		   void *token, unsigned int len, unsigned int bitnum)
-{
-	unsigned long bits[16];
-
-	/* This makes it convenient to pass-through find() results. */
-	if (!token)
-		return 0;
-
-	/* bit not in range of this bitfield? */
-	if (bitnum * 8 >= len / 2)
-		return 0;
-
-	/* Giant feature bitfields are silly. */
-	BUG_ON(len > sizeof(bits));
-	vdev->config->get(vdev, token, bits, len);
-
-	if (!test_bit(bitnum, bits))
-		return 0;
-
-	/* Set acknowledge bit, and write it back. */
-	set_bit(bitnum + len * 8 / 2, bits);
-	vdev->config->set(vdev, token, bits, len);
-	return 1;
-}
-EXPORT_SYMBOL_GPL(virtio_use_bit);
-
 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 00000000000..c8a4332d113
--- /dev/null
+++ b/drivers/virtio/virtio_balloon.c
@@ -0,0 +1,285 @@
+/* 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>
+
+struct virtio_balloon
+{
+	struct virtio_device *vdev;
+	struct virtqueue *inflate_vq, *deflate_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;
+
+	/* Do we have to tell Host *before* we reuse pages? */
+	bool tell_host_first;
+
+	/* 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];
+};
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static void balloon_ack(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb;
+	unsigned int len;
+
+	vb = vq->vq_ops->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 (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) != 0)
+		BUG();
+	vq->vq_ops->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);
+		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_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_pfn(page);
+		vb->num_pages--;
+	}
+
+	if (vb->tell_host_first) {
+		tell_host(vb, vb->deflate_vq);
+		release_pages_by_pfn(vb->pfns, vb->num_pfns);
+	} else {
+		release_pages_by_pfn(vb->pfns, vb->num_pfns);
+		tell_host(vb, vb->deflate_vq);
+	}
+}
+
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	wake_up(&vb->config_change);
+}
+
+static inline int towards_target(struct virtio_balloon *vb)
+{
+	u32 v;
+	__virtio_config_val(vb->vdev,
+			    offsetof(struct virtio_balloon_config, num_pages),
+			    &v);
+	return 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()) {
+		int diff;
+
+		try_to_freeze();
+		wait_event_interruptible(vb->config_change,
+					 (diff = towards_target(vb)) != 0
+					 || kthread_should_stop());
+		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;
+	int err;
+
+	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;
+
+	/* We expect two virtqueues. */
+	vb->inflate_vq = vdev->config->find_vq(vdev, 0, balloon_ack);
+	if (IS_ERR(vb->inflate_vq)) {
+		err = PTR_ERR(vb->inflate_vq);
+		goto out_free_vb;
+	}
+
+	vb->deflate_vq = vdev->config->find_vq(vdev, 1, balloon_ack);
+	if (IS_ERR(vb->deflate_vq)) {
+		err = PTR_ERR(vb->deflate_vq);
+		goto out_del_inflate_vq;
+	}
+
+	vb->thread = kthread_run(balloon, vb, "vballoon");
+	if (IS_ERR(vb->thread)) {
+		err = PTR_ERR(vb->thread);
+		goto out_del_deflate_vq;
+	}
+
+	vb->tell_host_first
+		= vdev->config->feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+
+	return 0;
+
+out_del_deflate_vq:
+	vdev->config->del_vq(vb->deflate_vq);
+out_del_inflate_vq:
+	vdev->config->del_vq(vb->inflate_vq);
+out_free_vb:
+	kfree(vb);
+out:
+	return err;
+}
+
+static void 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_vq(vb->deflate_vq);
+	vdev->config->del_vq(vb->inflate_vq);
+	kfree(vb);
+}
+
+static struct virtio_driver virtio_balloon = {
+	.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);
+}
+
+static void __exit fini(void)
+{
+	unregister_virtio_driver(&virtio_balloon);
+}
+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 00000000000..26f787ddd5f
--- /dev/null
+++ b/drivers/virtio/virtio_pci.c
@@ -0,0 +1,446 @@
+/*
+ * 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/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 *ioaddr;
+
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+};
+
+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;
+};
+
+/* 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);
+
+/* A PCI device has it's own struct device and so does a virtio device so
+ * we create a place for the virtio devices to show up in sysfs.  I think it
+ * would make more sense for virtio to not insist on having it's own device. */
+static struct device virtio_pci_root = {
+	.parent		= NULL,
+	.bus_id		= "virtio-pci",
+};
+
+/* Unique numbering for devices under the kvm root */
+static unsigned int dev_index;
+
+/* 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->feature() implementation */
+static bool vp_feature(struct virtio_device *vdev, unsigned bit)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u32 mask;
+
+	/* Since this function is supposed to have the side effect of
+	 * enabling a queried feature, we simulate that by doing a read
+	 * from the host feature bitmask and then writing to the guest
+	 * feature bitmask */
+	mask = ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+	if (mask & (1 << bit)) {
+		mask |= (1 << bit);
+		iowrite32(mask, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+	}
+
+	return !!(mask & (1 << bit));
+}
+
+/* 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 *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + 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 *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + 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);
+	return 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. */
+	return 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);
+}
+
+/* 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;
+	struct virtio_pci_vq_info *info;
+	irqreturn_t ret = IRQ_NONE;
+	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) {
+		struct virtio_driver *drv;
+		drv = container_of(vp_dev->vdev.dev.driver,
+				   struct virtio_driver, driver);
+
+		if (drv->config_changed)
+			drv->config_changed(&vp_dev->vdev);
+	}
+
+	spin_lock(&vp_dev->lock);
+	list_for_each_entry(info, &vp_dev->virtqueues, node) {
+		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+	spin_unlock(&vp_dev->lock);
+
+	return ret;
+}
+
+/* the config->find_vq() implementation */
+static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
+				    void (*callback)(struct virtqueue *vq))
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info;
+	struct virtqueue *vq;
+	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->queue = kzalloc(PAGE_ALIGN(vring_size(num,PAGE_SIZE)), GFP_KERNEL);
+	if (info->queue == NULL) {
+		err = -ENOMEM;
+		goto out_info;
+	}
+
+	/* activate the queue */
+	iowrite32(virt_to_phys(info->queue) >> PAGE_SHIFT,
+		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(info->num, vdev, info->queue,
+				 vp_notify, callback);
+	if (!vq) {
+		err = -ENOMEM;
+		goto out_activate_queue;
+	}
+
+	vq->priv = info;
+	info->vq = vq;
+
+	spin_lock(&vp_dev->lock);
+	list_add(&info->node, &vp_dev->virtqueues);
+	spin_unlock(&vp_dev->lock);
+
+	return vq;
+
+out_activate_queue:
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	kfree(info->queue);
+out_info:
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+/* the config->del_vq() implementation */
+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;
+
+	spin_lock(&vp_dev->lock);
+	list_del(&info->node);
+	spin_unlock(&vp_dev->lock);
+
+	vring_del_virtqueue(vq);
+
+	/* Select and deactivate the queue */
+	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	kfree(info->queue);
+	kfree(info);
+}
+
+static struct virtio_config_ops virtio_pci_config_ops = {
+	.feature	= vp_feature,
+	.get		= vp_get,
+	.set		= vp_set,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vq	= vp_find_vq,
+	.del_vq		= vp_del_vq,
+};
+
+/* 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;
+
+	snprintf(vp_dev->vdev.dev.bus_id, BUS_ID_SIZE, "virtio%d", dev_index);
+	vp_dev->vdev.index = dev_index;
+	dev_index++;
+
+	vp_dev->vdev.dev.parent = &virtio_pci_root;
+	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);
+
+	/* 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);
+
+	/* 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 subsytem ids */
+	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+	vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+	/* register a handler for the queue with the PCI device's interrupt */
+	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
+			  vp_dev->vdev.dev.bus_id, vp_dev);
+	if (err)
+		goto out_set_drvdata;
+
+	/* finally register the virtio device */
+	err = register_virtio_device(&vp_dev->vdev);
+	if (err)
+		goto out_req_irq;
+
+	return 0;
+
+out_req_irq:
+	free_irq(pci_dev->irq, vp_dev);
+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);
+
+	free_irq(pci_dev->irq, vp_dev);
+	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		= virtio_pci_remove,
+#ifdef CONFIG_PM
+	.suspend	= virtio_pci_suspend,
+	.resume		= virtio_pci_resume,
+#endif
+};
+
+static int __init virtio_pci_init(void)
+{
+	int err;
+
+	err = device_register(&virtio_pci_root);
+	if (err)
+		return err;
+
+	err = pci_register_driver(&virtio_pci_driver);
+	if (err)
+		device_unregister(&virtio_pci_root);
+
+	return err;
+}
+
+module_init(virtio_pci_init);
+
+static void __exit virtio_pci_exit(void)
+{
+	device_unregister(&virtio_pci_root);
+	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
index 1dc04b6684e..3a28c138213 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -87,6 +87,8 @@ static int vring_add_buf(struct virtqueue *_vq,
 	if (vq->num_free < out + in) {
 		pr_debug("Can't add buf len %i - avail = %i\n",
 			 out + in, vq->num_free);
+		/* We notify *even if* VRING_USED_F_NO_NOTIFY is set here. */
+		vq->notify(&vq->vq);
 		END_USE(vq);
 		return -ENOSPC;
 	}
@@ -97,16 +99,14 @@ static int vring_add_buf(struct virtqueue *_vq,
 	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 = (page_to_pfn(sg_page(sg))<<PAGE_SHIFT)
-			+ sg->offset;
+		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 = (page_to_pfn(sg_page(sg))<<PAGE_SHIFT)
-			+ sg->offset;
+		vq->vring.desc[i].addr = sg_phys(sg);
 		vq->vring.desc[i].len = sg->length;
 		prev = i;
 		sg++;
@@ -171,16 +171,6 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 	vq->num_free++;
 }
 
-/* FIXME: We need to tell other side about removal, to synchronize. */
-static void vring_shutdown(struct virtqueue *_vq)
-{
-	struct vring_virtqueue *vq = to_vvq(_vq);
-	unsigned int i;
-
-	for (i = 0; i < vq->vring.num; i++)
-		detach_buf(vq, i);
-}
-
 static inline bool more_used(const struct vring_virtqueue *vq)
 {
 	return vq->last_used_idx != vq->vring.used->idx;
@@ -220,7 +210,17 @@ static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len)
 	return ret;
 }
 
-static bool vring_restart(struct virtqueue *_vq)
+static void vring_disable_cb(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	START_USE(vq);
+	BUG_ON(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT);
+	vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+	END_USE(vq);
+}
+
+static bool vring_enable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
@@ -253,26 +253,34 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 	if (unlikely(vq->broken))
 		return IRQ_HANDLED;
 
+	/* Other side may have missed us turning off the interrupt,
+	 * but we should preserve disable semantic for virtio users. */
+	if (unlikely(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+		pr_debug("virtqueue interrupt after disable for %p\n", vq);
+		return IRQ_HANDLED;
+	}
+
 	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
-	if (vq->vq.callback && !vq->vq.callback(&vq->vq))
-		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+	if (vq->vq.callback)
+		vq->vq.callback(&vq->vq);
 
 	return IRQ_HANDLED;
 }
+EXPORT_SYMBOL_GPL(vring_interrupt);
 
 static struct virtqueue_ops vring_vq_ops = {
 	.add_buf = vring_add_buf,
 	.get_buf = vring_get_buf,
 	.kick = vring_kick,
-	.restart = vring_restart,
-	.shutdown = vring_shutdown,
+	.disable_cb = vring_disable_cb,
+	.enable_cb = vring_enable_cb,
 };
 
 struct virtqueue *vring_new_virtqueue(unsigned int num,
 				      struct virtio_device *vdev,
 				      void *pages,
 				      void (*notify)(struct virtqueue *),
-				      bool (*callback)(struct virtqueue *))
+				      void (*callback)(struct virtqueue *))
 {
 	struct vring_virtqueue *vq;
 	unsigned int i;
@@ -311,9 +319,12 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 
 	return &vq->vq;
 }
+EXPORT_SYMBOL_GPL(vring_new_virtqueue);
 
 void vring_del_virtqueue(struct virtqueue *vq)
 {
 	kfree(to_vvq(vq));
 }
+EXPORT_SYMBOL_GPL(vring_del_virtqueue);
 
+MODULE_LICENSE("GPL");