Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull vhost updates from Michael Tsirkin:
 "virtio, vhost: optimizations, fixes

  Looks like a quiet cycle for vhost/virtio, just a couple of minor
  tweaks. Most notable is automatic interrupt affinity for blk and scsi.
  Hopefully other devices are not far behind"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio-console: avoid DMA from stack
  vhost: introduce O(1) vq metadata cache
  virtio_scsi: use virtio IRQ affinity
  virtio_blk: use virtio IRQ affinity
  blk-mq: provide a default queue mapping for virtio device
  virtio: provide a method to get the IRQ affinity mask for a virtqueue
  virtio: allow drivers to request IRQ affinity when creating VQs
  virtio_pci: simplify MSI-X setup
  virtio_pci: don't duplicate the msix_enable flag in struct pci_dev
  virtio_pci: use shared interrupts for virtqueues
  virtio_pci: remove struct virtio_pci_vq_info
  vhost: try avoiding avail index access when getting descriptor
  virtio_mmio: expose header to userspace

drivers/virtio/virtio_balloon.c

@@ -413,7 +413,8 @@ static int init_vqs(struct virtio_balloon *vb)
 	 * optionally stat.
 	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names,
+			NULL);
 	if (err)
 		return err;
 

drivers/virtio/virtio_input.c

@@ -173,7 +173,8 @@ static int virtinput_init_vqs(struct virtio_input *vi)
 	static const char * const names[] = { "events", "status" };
 	int err;
 
-	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names);
+	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names,
+			NULL);
 	if (err)
 		return err;
 	vi->evt = vqs[0];

drivers/virtio/virtio_mmio.c

@@ -70,7 +70,7 @@
 #include <linux/spinlock.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
-#include <linux/virtio_mmio.h>
+#include <uapi/linux/virtio_mmio.h>
 #include <linux/virtio_ring.h>
 
 
@@ -446,7 +446,8 @@ error_available:
 static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
-		       const char * const names[])
+		       const char * const names[],
+		       struct irq_affinity *desc)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);

drivers/virtio/virtio_pci_common.c

@@ -33,10 +33,8 @@ 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(pci_irq_vector(vp_dev->pci_dev, 0));
+	for (i = 1; i < vp_dev->msix_vectors; i++)
 		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
 }
 
@@ -62,16 +60,13 @@ static irqreturn_t vp_config_changed(int irq, void *opaque)
 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;
+	struct virtqueue *vq;
 
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_for_each_entry(info, &vp_dev->virtqueues, node) {
-		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+	list_for_each_entry(vq, &vp_dev->vdev.vqs, list) {
+		if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 	}
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
 	return ret;
 }
@@ -102,237 +97,185 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
 	return vp_vring_interrupt(irq, opaque);
 }
 
-static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
-				   bool per_vq_vectors)
+static void vp_remove_vqs(struct virtio_device *vdev)
 {
 	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;
+	struct virtqueue *vq, *n;
 
-	vp_dev->msix_vectors = nvectors;
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->msix_vector_map) {
+			int v = vp_dev->msix_vector_map[vq->index];
 
-	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;
-
-	err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
-			PCI_IRQ_MSIX);
-	if (err < 0)
-		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(pci_irq_vector(vp_dev->pci_dev, v),
-			  vp_config_changed, 0, vp_dev->msix_names[v],
-			  vp_dev);
-	if (err)
-		goto error;
-	++vp_dev->msix_used_vectors;
-
-	v = vp_dev->config_vector(vp_dev, v);
-	/* Verify we had enough resources to assign the vector */
-	if (v == VIRTIO_MSI_NO_VECTOR) {
-		err = -EBUSY;
-		goto error;
+			if (v != VIRTIO_MSI_NO_VECTOR)
+				free_irq(pci_irq_vector(vp_dev->pci_dev, v),
+					vq);
+		}
+		vp_dev->del_vq(vq);
 	}
-
-	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(pci_irq_vector(vp_dev->pci_dev, v),
-				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
-				  vp_dev);
-		if (err)
-			goto error;
-		++vp_dev->msix_used_vectors;
-	}
-	return 0;
-error:
-	return err;
-}
-
-static struct virtqueue *vp_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 = kmalloc(sizeof *info, GFP_KERNEL);
-	struct virtqueue *vq;
-	unsigned long flags;
-
-	/* fill out our structure that represents an active queue */
-	if (!info)
-		return ERR_PTR(-ENOMEM);
-
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec);
-	if (IS_ERR(vq))
-		goto out_info;
-
-	info->vq = vq;
-	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);
-	}
-
-	vp_dev->vqs[index] = info;
-	return vq;
-
-out_info:
-	kfree(info);
-	return vq;
-}
-
-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 = vp_dev->vqs[vq->index];
-	unsigned long flags;
-
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_del(&info->node);
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
-
-	vp_dev->del_vq(info);
-	kfree(info);
 }
 
 /* the config->del_vqs() implementation */
 void vp_del_vqs(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtqueue *vq, *n;
 	int i;
 
-	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
-		if (vp_dev->per_vq_vectors) {
-			int v = vp_dev->vqs[vq->index]->msix_vector;
+	if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs)))
+		return;
 
-			if (v != VIRTIO_MSI_NO_VECTOR)
-				free_irq(pci_irq_vector(vp_dev->pci_dev, v),
-					vq);
-		}
-		vp_del_vq(vq);
-	}
-	vp_dev->per_vq_vectors = false;
+	vp_remove_vqs(vdev);
 
-	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(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
-
-	for (i = 0; i < vp_dev->msix_vectors; i++)
-		if (vp_dev->msix_affinity_masks[i])
+	if (vp_dev->pci_dev->msix_enabled) {
+		for (i = 0; i < vp_dev->msix_vectors; i++)
 			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
 
-	if (vp_dev->msix_enabled) {
 		/* Disable the vector used for configuration */
 		vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
 
-		pci_free_irq_vectors(vp_dev->pci_dev);
-		vp_dev->msix_enabled = 0;
+		kfree(vp_dev->msix_affinity_masks);
+		kfree(vp_dev->msix_names);
+		kfree(vp_dev->msix_vector_map);
 	}
 
-	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_affinity_masks);
-	vp_dev->msix_affinity_masks = NULL;
-	kfree(vp_dev->vqs);
-	vp_dev->vqs = NULL;
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+	pci_free_irq_vectors(vp_dev->pci_dev);
 }
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
-			      struct virtqueue *vqs[],
-			      vq_callback_t *callbacks[],
-			      const char * const names[],
-			      bool per_vq_vectors)
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	int i, err = -ENOMEM, allocated_vectors, nvectors;
+	unsigned flags = PCI_IRQ_MSIX;
+	bool shared = false;
 	u16 msix_vec;
-	int i, err, nvectors, allocated_vectors;
 
-	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
-	if (!vp_dev->vqs)
-		return -ENOMEM;
-
-	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;
+	if (desc) {
+		flags |= PCI_IRQ_AFFINITY;
+		desc->pre_vectors++; /* virtio config vector */
 	}
 
-	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
-	if (err)
-		goto error_find;
+	nvectors = 1;
+	for (i = 0; i < nvqs; i++)
+		if (callbacks[i])
+			nvectors++;
 
-	vp_dev->per_vq_vectors = per_vq_vectors;
-	allocated_vectors = vp_dev->msix_used_vectors;
+	/* Try one vector per queue first. */
+	err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+			nvectors, flags, desc);
+	if (err < 0) {
+		/* Fallback to one vector for config, one shared for queues. */
+		shared = true;
+		err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
+				PCI_IRQ_MSIX);
+		if (err < 0)
+			return err;
+	}
+	if (err < 0)
+		return err;
+
+	vp_dev->msix_vectors = nvectors;
+	vp_dev->msix_names = kmalloc_array(nvectors,
+			sizeof(*vp_dev->msix_names), GFP_KERNEL);
+	if (!vp_dev->msix_names)
+		goto out_free_irq_vectors;
+
+	vp_dev->msix_affinity_masks = kcalloc(nvectors,
+			sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto out_free_msix_names;
+
+	for (i = 0; i < nvectors; ++i) {
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+				GFP_KERNEL))
+			goto out_free_msix_affinity_masks;
+	}
+
+	/* Set the vector used for configuration */
+	snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names),
+		 "%s-config", name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
+			0, vp_dev->msix_names[0], vp_dev);
+	if (err)
+		goto out_free_msix_affinity_masks;
+
+	/* Verify we had enough resources to assign the vector */
+	if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto out_free_config_irq;
+	}
+
+	vp_dev->msix_vector_map = kmalloc_array(nvqs,
+			sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
+	if (!vp_dev->msix_vector_map)
+		goto out_disable_config_irq;
+
+	allocated_vectors = 1; /* vector 0 is the config interrupt */
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
 
-		if (!callbacks[i])
-			msix_vec = VIRTIO_MSI_NO_VECTOR;
-		else if (vp_dev->per_vq_vectors)
-			msix_vec = allocated_vectors++;
+		if (callbacks[i])
+			msix_vec = allocated_vectors;
 		else
-			msix_vec = VP_MSIX_VQ_VECTOR;
-		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
+			msix_vec = VIRTIO_MSI_NO_VECTOR;
+
+		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
+				msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto error_find;
+			goto out_remove_vqs;
 		}
 
-		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			vp_dev->msix_vector_map[i] = 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",
+		snprintf(vp_dev->msix_names[i + 1],
+			 sizeof(*vp_dev->msix_names), "%s-%s",
 			 dev_name(&vp_dev->vdev.dev), names[i]);
 		err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
-				  vring_interrupt, 0,
-				  vp_dev->msix_names[msix_vec],
-				  vqs[i]);
-		if (err)
-			goto error_find;
+				  vring_interrupt, IRQF_SHARED,
+				  vp_dev->msix_names[i + 1], vqs[i]);
+		if (err) {
+			/* don't free this irq on error */
+			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
+			goto out_remove_vqs;
+		}
+		vp_dev->msix_vector_map[i] = msix_vec;
+
+		/*
+		 * Use a different vector for each queue if they are available,
+		 * else share the same vector for all VQs.
+		 */
+		if (!shared)
+			allocated_vectors++;
 	}
+
 	return 0;
 
-error_find:
-	vp_del_vqs(vdev);
+out_remove_vqs:
+	vp_remove_vqs(vdev);
+	kfree(vp_dev->msix_vector_map);
+out_disable_config_irq:
+	vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
+out_free_config_irq:
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+out_free_msix_affinity_masks:
+	for (i = 0; i < nvectors; i++) {
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	}
+	kfree(vp_dev->msix_affinity_masks);
+out_free_msix_names:
+	kfree(vp_dev->msix_names);
+out_free_irq_vectors:
+	pci_free_irq_vectors(vp_dev->pci_dev);
 	return err;
 }
 
@@ -343,53 +286,42 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err;
 
-	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
-	if (!vp_dev->vqs)
-		return -ENOMEM;
-
 	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vp_dev);
 	if (err)
-		goto out_del_vqs;
+		return err;
 
-	vp_dev->intx_enabled = 1;
-	vp_dev->per_vq_vectors = false;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
-		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
 				VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto out_del_vqs;
+			goto out_remove_vqs;
 		}
 	}
 
 	return 0;
-out_del_vqs:
-	vp_del_vqs(vdev);
+
+out_remove_vqs:
+	vp_remove_vqs(vdev);
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
 	return err;
 }
 
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		struct virtqueue *vqs[],
-		vq_callback_t *callbacks[],
-		const char * const names[])
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	int err;
 
-	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc);
 	if (!err)
 		return 0;
-	/* Fallback: MSI-X with one vector for config, one shared for queues. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false);
-	if (!err)
-		return 0;
-	/* Finally fall back to regular interrupts. */
 	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
 }
 
@@ -409,16 +341,15 @@ 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 = vp_dev->vqs[vq->index];
-	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 = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
+	if (vp_dev->pci_dev->msix_enabled) {
+		int vec = vp_dev->msix_vector_map[vq->index];
+		struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
+		unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
+
 		if (cpu == -1)
 			irq_set_affinity_hint(irq, NULL);
 		else {
@@ -430,6 +361,17 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	unsigned int *map = vp_dev->msix_vector_map;
+
+	if (!map || map[index] == VIRTIO_MSI_NO_VECTOR)
+		return NULL;
+
+	return pci_irq_get_affinity(vp_dev->pci_dev, map[index]);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int virtio_pci_freeze(struct device *dev)
 {
@@ -498,8 +440,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	vp_dev->vdev.dev.parent = &pci_dev->dev;
 	vp_dev->vdev.dev.release = virtio_pci_release_dev;
 	vp_dev->pci_dev = pci_dev;
-	INIT_LIST_HEAD(&vp_dev->virtqueues);
-	spin_lock_init(&vp_dev->lock);
 
 	/* enable the device */
 	rc = pci_enable_device(pci_dev);

drivers/virtio/virtio_pci_common.h

@@ -31,17 +31,6 @@
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 
-struct virtio_pci_vq_info {
-	/* the actual virtqueue */
-	struct virtqueue *vq;
-
-	/* the list node for the virtqueues list */
-	struct list_head node;
-
-	/* MSI-X vector (or none) */
-	unsigned msix_vector;
-};
-
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -75,47 +64,25 @@ struct virtio_pci_device {
 	/* 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;
-
-	/* array of all queues for house-keeping */
-	struct virtio_pci_vq_info **vqs;
-
-	/* MSI-X support */
-	int msix_enabled;
-	int intx_enabled;
 	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;
-
-	/* Whether we have vector per vq */
-	bool per_vq_vectors;
+	/* Total Number of MSI-X vectors (including per-VQ ones). */
+	int msix_vectors;
+	/* Map of per-VQ MSI-X vectors, may be NULL */
+	unsigned *msix_vector_map;
 
 	struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
-				      struct virtio_pci_vq_info *info,
 				      unsigned idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
 				      u16 msix_vec);
-	void (*del_vq)(struct virtio_pci_vq_info *info);
+	void (*del_vq)(struct virtqueue *vq);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
 };
 
-/* 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,
-};
-
 /* Convert a generic virtio device to our structure */
 static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 {
@@ -130,9 +97,8 @@ bool vp_notify(struct virtqueue *vq);
 void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		       struct virtqueue *vqs[],
-		       vq_callback_t *callbacks[],
-		       const char * const names[]);
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
 /* Setup the affinity for a virtqueue:
@@ -142,6 +108,8 @@ const char *vp_bus_name(struct virtio_device *vdev);
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
+
 #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
 int virtio_pci_legacy_probe(struct virtio_pci_device *);
 void virtio_pci_legacy_remove(struct virtio_pci_device *);

drivers/virtio/virtio_pci_legacy.c

@@ -112,7 +112,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -130,8 +129,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
 		return ERR_PTR(-ENOENT);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
@@ -162,14 +159,13 @@ out_deactivate:
 	return ERR_PTR(err);
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
 			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
 		/* Flush the write out to device */
@@ -194,6 +190,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /* the PCI probing function */

drivers/virtio/virtio_pci_modern.c

@@ -293,7 +293,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -323,8 +322,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* get offset of notification word for this vq */
 	off = vp_ioread16(&cfg->queue_notify_off);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
@@ -387,13 +384,12 @@ err_map_notify:
 }
 
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-			      struct virtqueue *vqs[],
-			      vq_callback_t *callbacks[],
-			      const char * const names[])
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc);
 
 	if (rc)
 		return rc;
@@ -409,14 +405,13 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
 			     &vp_dev->common->queue_msix_vector);
 		/* Flush the write out to device */
@@ -442,6 +437,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -457,6 +453,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /**