1 files changed, 511 insertions, 132 deletions

diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index c0df924766a..101db3faf5d 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -17,6 +17,7 @@
 #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>
@@ -42,6 +43,33 @@ struct virtio_pci_device
 	/* 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;
+	cpumask_var_t *msix_affinity_masks;
+	/* 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;
+
+	/* Status saved during hibernate/restore */
+	u8 saved_status;
+
+	/* 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
@@ -52,58 +80,51 @@ struct virtio_pci_vq_info
 	/* 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 },
+static DEFINE_PCI_DEVICE_TABLE(virtio_pci_id_table) = {
+	{ PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+	{ 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)
+/* virtio config->get_features() implementation */
+static u32 vp_get_features(struct virtio_device *vdev)
 {
 	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));
+	/* 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 */
@@ -111,7 +132,8 @@ 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 + offset;
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
 	u8 *ptr = buf;
 	int i;
 
@@ -125,7 +147,8 @@ 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 + offset;
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
 	const u8 *ptr = buf;
 	int i;
 
@@ -145,25 +168,74 @@ 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);
+	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+/* wait for pending irq handlers */
+static void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled)
+		synchronize_irq(vp_dev->pci_dev->irq);
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
+		synchronize_irq(vp_dev->msix_entries[i].vector);
 }
 
 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);
+	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSi-X interrupts, if any. */
+	ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
 }
 
 /* the notify function used when creating a virt queue */
-static void vp_notify(struct virtqueue *vq)
+static bool 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);
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	return true;
+}
+
+/* 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.
@@ -175,9 +247,6 @@ static void vp_notify(struct virtqueue *vq)
 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;
-	unsigned long flags;
 	u8 isr;
 
 	/* reading the ISR has the effect of also clearing it so it's very
@@ -189,33 +258,145 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
 		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 (isr & VIRTIO_PCI_ISR_CONFIG)
+		vp_config_changed(irq, opaque);
+
+	return vp_vring_interrupt(irq, opaque);
+}
 
-		if (drv->config_changed)
-			drv->config_changed(&vp_dev->vdev);
+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;
 	}
 
-	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;
+	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+		free_irq(vp_dev->msix_entries[i].vector, vp_dev);
+
+	for (i = 0; i < vp_dev->msix_vectors; i++)
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
+	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;
 	}
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
-	return ret;
+	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;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
 }
 
-/* the config->find_vq() implementation */
-static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
-				    void (*callback)(struct virtqueue *vq))
+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_vectors = nvectors;
+
+	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;
+	vp_dev->msix_affinity_masks
+		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+			  GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
+
+	for (i = 0; i < nvectors; ++i)
+		vp_dev->msix_entries[i].entry = i;
+
+	err = pci_enable_msix_exact(vp_dev->pci_dev,
+				    vp_dev->msix_entries, nvectors);
+	if (err)
+		goto error;
+	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;
+	unsigned long flags, size;
 	u16 num;
 	int err;
 
@@ -233,22 +414,23 @@ static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	info->queue_index = index;
 	info->num = num;
+	info->msix_vector = msix_vec;
 
-	info->queue = kzalloc(PAGE_ALIGN(vring_size(num,PAGE_SIZE)), GFP_KERNEL);
+	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) >> PAGE_SHIFT,
+	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, vdev, info->queue,
-				 vp_notify, callback);
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
+				 true, info->queue, vp_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto out_activate_queue;
@@ -257,55 +439,245 @@ static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
 	vq->priv = info;
 	info->vq = vq;
 
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_add(&info->node, &vp_dev->virtqueues);
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
+	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;
+		}
+	}
+
+	if (callback) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_add(&info->node, &vp_dev->virtqueues);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	} else {
+		INIT_LIST_HEAD(&info->node);
+	}
 
 	return vq;
 
+out_assign:
+	vring_del_virtqueue(vq);
 out_activate_queue:
 	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-	kfree(info->queue);
+	free_pages_exact(info->queue, size);
 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;
-	unsigned long flags;
+	unsigned long flags, size;
 
 	spin_lock_irqsave(&vp_dev->lock, flags);
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
+	iowrite16(vq->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 */
-	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
-	kfree(info->queue);
+	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
+	free_pages_exact(info->queue, size);
 	kfree(info);
 }
 
-static struct virtio_config_ops virtio_pci_config_ops = {
-	.feature	= vp_feature,
+/* 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 (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		} else 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 const char *vp_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return pci_name(vp_dev->pci_dev);
+}
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	struct cpumask *mask;
+	unsigned int irq;
+
+	if (!vq->callback)
+		return -EINVAL;
+
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = vp_dev->msix_entries[info->msix_vector].vector;
+		if (cpu == -1)
+			irq_set_affinity_hint(irq, NULL);
+		else {
+			cpumask_set_cpu(cpu, mask);
+			irq_set_affinity_hint(irq, mask);
+		}
+	}
+	return 0;
+}
+
+static const 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_vq	= vp_find_vq,
-	.del_vq		= vp_del_vq,
+	.find_vqs	= vp_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
 };
 
+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)
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id)
 {
 	struct virtio_pci_device *vp_dev;
 	int err;
@@ -325,16 +697,16 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
 	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.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)
@@ -345,35 +717,29 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
 		goto out_enable_device;
 
 	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
-	if (vp_dev->ioaddr == NULL)
+	if (vp_dev->ioaddr == NULL) {
+		err = -ENOMEM;
 		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 subsytem ids */
+	 * the subsystem 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;
+		goto out_set_drvdata;
 
 	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);
@@ -384,33 +750,70 @@ out:
 	return err;
 }
 
-static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
+static void 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);
-	free_irq(pci_dev->irq, vp_dev);
-	pci_set_drvdata(pci_dev, NULL);
+
+	vp_del_vqs(&vp_dev->vdev);
 	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)
+#ifdef CONFIG_PM_SLEEP
+static int virtio_pci_freeze(struct device *dev)
 {
-	pci_save_state(pci_dev);
-	pci_set_power_state(pci_dev, PCI_D3hot);
-	return 0;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = 0;
+	vp_dev->saved_status = vp_get_status(&vp_dev->vdev);
+	if (drv && drv->freeze)
+		ret = drv->freeze(&vp_dev->vdev);
+
+	if (!ret)
+		pci_disable_device(pci_dev);
+	return ret;
 }
 
-static int virtio_pci_resume(struct pci_dev *pci_dev)
+static int virtio_pci_restore(struct device *dev)
 {
-	pci_restore_state(pci_dev);
-	pci_set_power_state(pci_dev, PCI_D0);
-	return 0;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pci_dev);
+	vp_finalize_features(&vp_dev->vdev);
+
+	if (drv && drv->restore)
+		ret = drv->restore(&vp_dev->vdev);
+
+	/* Finally, tell the device we're all set */
+	if (!ret)
+		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+
+	return ret;
 }
+
+static const struct dev_pm_ops virtio_pci_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
+};
 #endif
 
 static struct pci_driver virtio_pci_driver = {
@@ -418,33 +821,9 @@ static struct pci_driver virtio_pci_driver = {
 	.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,
+#ifdef CONFIG_PM_SLEEP
+	.driver.pm	= &virtio_pci_pm_ops,
 #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);
+module_pci_driver(virtio_pci_driver);