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

Pull virtio fixes from Michael Tsirkin:
 "The biggest thing here is the adminq change - but it looks like the
  only way to avoid headq blocking causing indefinite stalls.

  This fixes three issues:

   - Prevent admin commands on one VF blocking another.

     This prevents a bad VF from blocking a good one, as well as fixing
     a scalability issue with large # of VFs

   - Correctly return error on command failure on octeon. We used to
     treat failed commands as a success.

   - Fix modpost warning when building virtio_dma_buf. Harmless, but the
     fix is trivial"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_pci_modern: remove admin queue serialization lock
  virtio_pci_modern: use completion instead of busy loop to wait on admin cmd result
  virtio_pci_modern: pass cmd as an identification token
  virtio_pci_modern: create admin queue of queried size
  virtio: create admin queues alongside other virtqueues
  virtio_pci: pass vq info as an argument to vp_setup_vq()
  virtio: push out code to vp_avq_index()
  virtio_pci_modern: treat vp_dev->admin_vq.info.vq pointer as static
  virtio_pci: introduce vector allocation fallback for slow path virtqueues
  virtio_pci: pass vector policy enum to vp_find_one_vq_msix()
  virtio_pci: pass vector policy enum to vp_find_vqs_msix()
  virtio_pci: simplify vp_request_msix_vectors() call a bit
  virtio_pci: push out single vq find code to vp_find_one_vq_msix()
  vdpa/octeon_ep: Fix error code in octep_process_mbox()
  virtio: add missing MODULE_DESCRIPTION() macro

drivers/vdpa/octeon_ep/octep_vdpa_hw.c

@@ -140,7 +140,7 @@ static int octep_process_mbox(struct octep_hw *oct_hw, u16 id, u16 qid, void *bu
 	val = octep_read_sig(mbox);
 	if ((val & 0xFFFF) != MBOX_RSP_SIG) {
 		dev_warn(&pdev->dev, "Invalid Signature from mbox : %d response\n", id);
-		return ret;
+		return -EINVAL;
 	}
 
 	val = octep_read_sts(mbox);

drivers/virtio/virtio.c

@@ -305,15 +305,9 @@ static int virtio_dev_probe(struct device *_d)
 	if (err)
 		goto err;
 
-	if (dev->config->create_avq) {
-		err = dev->config->create_avq(dev);
-		if (err)
-			goto err;
-	}
-
 	err = drv->probe(dev);
 	if (err)
-		goto err_probe;
+		goto err;
 
 	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -326,9 +320,6 @@ static int virtio_dev_probe(struct device *_d)
 
 	return 0;
 
-err_probe:
-	if (dev->config->destroy_avq)
-		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
@@ -344,9 +335,6 @@ static void virtio_dev_remove(struct device *_d)
 
 	drv->remove(dev);
 
-	if (dev->config->destroy_avq)
-		dev->config->destroy_avq(dev);
-
 	/* Driver should have reset device. */
 	WARN_ON_ONCE(dev->config->get_status(dev));
 
@@ -524,9 +512,6 @@ int virtio_device_freeze(struct virtio_device *dev)
 		}
 	}
 
-	if (dev->config->destroy_avq)
-		dev->config->destroy_avq(dev);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(virtio_device_freeze);
@@ -562,16 +547,10 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
-	if (dev->config->create_avq) {
-		ret = dev->config->create_avq(dev);
-		if (ret)
-			goto err;
-	}
-
 	if (drv->restore) {
 		ret = drv->restore(dev);
 		if (ret)
-			goto err_restore;
+			goto err;
 	}
 
 	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
@@ -582,9 +561,6 @@ int virtio_device_restore(struct virtio_device *dev)
 
 	return 0;
 
-err_restore:
-	if (dev->config->destroy_avq)
-		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;

drivers/virtio/virtio_pci_common.c

@@ -46,12 +46,26 @@ bool vp_notify(struct virtqueue *vq)
 	return true;
 }
 
+/* Notify all slow path virtqueues on an interrupt. */
+static void vp_vring_slow_path_interrupt(int irq,
+					 struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_vq_info *info;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->slow_virtqueues, node)
+		vring_interrupt(irq, info->vq);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+}
+
 /* 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;
 
 	virtio_config_changed(&vp_dev->vdev);
+	vp_vring_slow_path_interrupt(irq, vp_dev);
 	return IRQ_HANDLED;
 }
 
@@ -125,6 +139,9 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 					GFP_KERNEL))
 			goto error;
 
+	if (!per_vq_vectors)
+		desc = NULL;
+
 	if (desc) {
 		flags |= PCI_IRQ_AFFINITY;
 		desc->pre_vectors++; /* virtio config vector */
@@ -171,11 +188,17 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 	return err;
 }
 
+static bool vp_is_slow_path_vector(u16 msix_vec)
+{
+	return msix_vec == VP_MSIX_CONFIG_VECTOR;
+}
+
 static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
 				     void (*callback)(struct virtqueue *vq),
 				     const char *name,
 				     bool ctx,
-				     u16 msix_vec)
+				     u16 msix_vec,
+				     struct virtio_pci_vq_info **p_info)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
@@ -194,13 +217,16 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int in
 	info->vq = vq;
 	if (callback) {
 		spin_lock_irqsave(&vp_dev->lock, flags);
-		list_add(&info->node, &vp_dev->virtqueues);
+		if (!vp_is_slow_path_vector(msix_vec))
+			list_add(&info->node, &vp_dev->virtqueues);
+		else
+			list_add(&info->node, &vp_dev->slow_virtqueues);
 		spin_unlock_irqrestore(&vp_dev->lock, flags);
 	} else {
 		INIT_LIST_HEAD(&info->node);
 	}
 
-	vp_dev->vqs[index] = info;
+	*p_info = info;
 	return vq;
 
 out_info:
@@ -236,13 +262,11 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
-		if (vp_dev->is_avq && vp_dev->is_avq(vdev, vq->index))
-			continue;
-
 		if (vp_dev->per_vq_vectors) {
 			int v = vp_dev->vqs[vq->index]->msix_vector;
 
-			if (v != VIRTIO_MSI_NO_VECTOR) {
+			if (v != VIRTIO_MSI_NO_VECTOR &&
+			    !vp_is_slow_path_vector(v)) {
 				int irq = pci_irq_vector(vp_dev->pci_dev, v);
 
 				irq_update_affinity_hint(irq, NULL);
@@ -284,21 +308,85 @@ void vp_del_vqs(struct virtio_device *vdev)
 	vp_dev->vqs = NULL;
 }
 
+enum vp_vq_vector_policy {
+	VP_VQ_VECTOR_POLICY_EACH,
+	VP_VQ_VECTOR_POLICY_SHARED_SLOW,
+	VP_VQ_VECTOR_POLICY_SHARED,
+};
+
+static struct virtqueue *
+vp_find_one_vq_msix(struct virtio_device *vdev, int queue_idx,
+		    vq_callback_t *callback, const char *name, bool ctx,
+		    bool slow_path, int *allocated_vectors,
+		    enum vp_vq_vector_policy vector_policy,
+		    struct virtio_pci_vq_info **p_info)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq;
+	u16 msix_vec;
+	int err;
+
+	if (!callback)
+		msix_vec = VIRTIO_MSI_NO_VECTOR;
+	else if (vector_policy == VP_VQ_VECTOR_POLICY_EACH ||
+		 (vector_policy == VP_VQ_VECTOR_POLICY_SHARED_SLOW &&
+		 !slow_path))
+		msix_vec = (*allocated_vectors)++;
+	else if (vector_policy != VP_VQ_VECTOR_POLICY_EACH &&
+		 slow_path)
+		msix_vec = VP_MSIX_CONFIG_VECTOR;
+	else
+		msix_vec = VP_MSIX_VQ_VECTOR;
+	vq = vp_setup_vq(vdev, queue_idx, callback, name, ctx, msix_vec,
+			 p_info);
+	if (IS_ERR(vq))
+		return vq;
+
+	if (vector_policy == VP_VQ_VECTOR_POLICY_SHARED ||
+	    msix_vec == VIRTIO_MSI_NO_VECTOR ||
+	    vp_is_slow_path_vector(msix_vec))
+		return vq;
+
+	/* 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), name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
+			  vring_interrupt, 0,
+			  vp_dev->msix_names[msix_vec], vq);
+	if (err) {
+		vp_del_vq(vq);
+		return ERR_PTR(err);
+	}
+
+	return vq;
+}
+
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 			    struct virtqueue *vqs[],
 			    struct virtqueue_info vqs_info[],
-			    bool per_vq_vectors,
+			    enum vp_vq_vector_policy vector_policy,
 			    struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq;
 	struct virtqueue_info *vqi;
-	u16 msix_vec;
 	int i, err, nvectors, allocated_vectors, queue_idx = 0;
+	struct virtqueue *vq;
+	bool per_vq_vectors;
+	u16 avq_num = 0;
 
 	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
 	if (!vp_dev->vqs)
 		return -ENOMEM;
 
+	if (vp_dev->avq_index) {
+		err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num);
+		if (err)
+			goto error_find;
+	}
+
+	per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED;
+
 	if (per_vq_vectors) {
 		/* Best option: one for change interrupt, one per vq. */
 		nvectors = 1;
@@ -307,13 +395,14 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 			if (vqi->name && vqi->callback)
 				++nvectors;
 		}
+		if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH)
+			++nvectors;
 	} else {
 		/* Second best: one for change, shared for all vqs. */
 		nvectors = 2;
 	}
 
-	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors,
-				      per_vq_vectors ? desc : NULL);
+	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, desc);
 	if (err)
 		goto error_find;
 
@@ -325,37 +414,27 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 			vqs[i] = NULL;
 			continue;
 		}
-
-		if (!vqi->callback)
-			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] = vp_setup_vq(vdev, queue_idx++, vqi->callback,
-				     vqi->name, vqi->ctx, msix_vec);
+		vqs[i] = vp_find_one_vq_msix(vdev, queue_idx++, vqi->callback,
+					     vqi->name, vqi->ctx, false,
+					     &allocated_vectors, vector_policy,
+					     &vp_dev->vqs[i]);
 		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), vqi->name);
-		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) {
-			vp_del_vq(vqs[i]);
-			goto error_find;
-		}
+	if (!avq_num)
+		return 0;
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done,
+				 avq->name, false, true, &allocated_vectors,
+				 vector_policy, &vp_dev->admin_vq.info);
+	if (IS_ERR(vq)) {
+		err = PTR_ERR(vq);
+		goto error_find;
 	}
+
 	return 0;
 
 error_find:
@@ -368,12 +447,21 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 			    struct virtqueue_info vqs_info[])
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq;
 	int i, err, queue_idx = 0;
+	struct virtqueue *vq;
+	u16 avq_num = 0;
 
 	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
 	if (!vp_dev->vqs)
 		return -ENOMEM;
 
+	if (vp_dev->avq_index) {
+		err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num);
+		if (err)
+			goto out_del_vqs;
+	}
+
 	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vp_dev);
 	if (err)
@@ -390,13 +478,24 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 		}
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, vqi->callback,
 				     vqi->name, vqi->ctx,
-				     VIRTIO_MSI_NO_VECTOR);
+				     VIRTIO_MSI_NO_VECTOR, &vp_dev->vqs[i]);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto out_del_vqs;
 		}
 	}
 
+	if (!avq_num)
+		return 0;
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name,
+			 false, VIRTIO_MSI_NO_VECTOR,
+			 &vp_dev->admin_vq.info);
+	if (IS_ERR(vq)) {
+		err = PTR_ERR(vq);
+		goto out_del_vqs;
+	}
+
 	return 0;
 out_del_vqs:
 	vp_del_vqs(vdev);
@@ -411,11 +510,20 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 	int err;
 
 	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, true, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_EACH, desc);
+	if (!err)
+		return 0;
+	/* Fallback: MSI-X with one shared vector for config and
+	 * slow path queues, one vector per queue for the rest.
+	 */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_SHARED_SLOW, 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, vqs_info, false, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_SHARED, desc);
 	if (!err)
 		return 0;
 	/* Is there an interrupt? If not give up. */
@@ -466,7 +574,8 @@ const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 
 	if (!vp_dev->per_vq_vectors ||
-	    vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR)
+	    vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR ||
+	    vp_is_slow_path_vector(vp_dev->vqs[index]->msix_vector))
 		return NULL;
 
 	return pci_irq_get_affinity(vp_dev->pci_dev,
@@ -574,6 +683,7 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	vp_dev->vdev.dev.release = virtio_pci_release_dev;
 	vp_dev->pci_dev = pci_dev;
 	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	INIT_LIST_HEAD(&vp_dev->slow_virtqueues);
 	spin_lock_init(&vp_dev->lock);
 
 	/* enable the device */

drivers/virtio/virtio_pci_common.h

@@ -35,7 +35,7 @@ struct virtio_pci_vq_info {
 	/* the actual virtqueue */
 	struct virtqueue *vq;
 
-	/* the list node for the virtqueues list */
+	/* the list node for the virtqueues or slow_virtqueues list */
 	struct list_head node;
 
 	/* MSI-X vector (or none) */
@@ -44,9 +44,9 @@ struct virtio_pci_vq_info {
 
 struct virtio_pci_admin_vq {
 	/* Virtqueue info associated with this admin queue. */
-	struct virtio_pci_vq_info info;
-	/* serializing admin commands execution and virtqueue deletion */
-	struct mutex cmd_lock;
+	struct virtio_pci_vq_info *info;
+	/* Protects virtqueue access. */
+	spinlock_t lock;
 	u64 supported_cmds;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
@@ -66,9 +66,12 @@ struct virtio_pci_device {
 	/* Where to read and clear interrupt */
 	u8 __iomem *isr;
 
-	/* a list of queues so we can dispatch IRQs */
+	/* Lists of queues and potentially slow path queues
+	 * so we can dispatch IRQs.
+	 */
 	spinlock_t lock;
 	struct list_head virtqueues;
+	struct list_head slow_virtqueues;
 
 	/* Array of all virtqueues reported in the
 	 * PCI common config num_queues field
@@ -102,7 +105,7 @@ struct virtio_pci_device {
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
-	bool (*is_avq)(struct virtio_device *vdev, unsigned int index);
+	int (*avq_index)(struct virtio_device *vdev, u16 *index, u16 *num);
 };
 
 /* Constants for MSI-X */
@@ -175,6 +178,7 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
 #define VIRTIO_ADMIN_CMD_BITMAP 0
 #endif
 
+void vp_modern_avq_done(struct virtqueue *vq);
 int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
 			     struct virtio_admin_cmd *cmd);
 

drivers/virtio/virtio_pci_modern.c

@@ -28,6 +28,21 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return vp_modern_get_features(&vp_dev->mdev);
 }
 
+static int vp_avq_index(struct virtio_device *vdev, u16 *index, u16 *num)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	*num = 0;
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return 0;
+
+	*num = vp_modern_avq_num(&vp_dev->mdev);
+	if (!(*num))
+		return -EINVAL;
+	*index = vp_modern_avq_index(&vp_dev->mdev);
+	return 0;
+}
+
 static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -38,17 +53,35 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 	return index == vp_dev->admin_vq.vq_index;
 }
 
+void vp_modern_avq_done(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+	struct virtio_admin_cmd *cmd;
+	unsigned long flags;
+	unsigned int len;
+
+	spin_lock_irqsave(&admin_vq->lock, flags);
+	do {
+		virtqueue_disable_cb(vq);
+		while ((cmd = virtqueue_get_buf(vq, &len)))
+			complete(&cmd->completion);
+	} while (!virtqueue_enable_cb(vq));
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
+}
+
 static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 				    u16 opcode,
 				    struct scatterlist **sgs,
 				    unsigned int out_num,
 				    unsigned int in_num,
-				    void *data)
+				    struct virtio_admin_cmd *cmd)
 {
 	struct virtqueue *vq;
-	int ret, len;
+	unsigned long flags;
+	int ret;
 
-	vq = admin_vq->info.vq;
+	vq = admin_vq->info->vq;
 	if (!vq)
 		return -EIO;
 
@@ -57,21 +90,33 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 	    !((1ULL << opcode) & admin_vq->supported_cmds))
 		return -EOPNOTSUPP;
 
-	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
-	if (ret < 0)
-		return -EIO;
+	init_completion(&cmd->completion);
 
-	if (unlikely(!virtqueue_kick(vq)))
+again:
+	if (virtqueue_is_broken(vq))
 		return -EIO;
 
-	while (!virtqueue_get_buf(vq, &len) &&
-	       !virtqueue_is_broken(vq))
-		cpu_relax();
+	spin_lock_irqsave(&admin_vq->lock, flags);
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL);
+	if (ret < 0) {
+		if (ret == -ENOSPC) {
+			spin_unlock_irqrestore(&admin_vq->lock, flags);
+			cpu_relax();
+			goto again;
+		}
+		goto unlock_err;
+	}
+	if (!virtqueue_kick(vq))
+		goto unlock_err;
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
 
-	if (virtqueue_is_broken(vq))
-		return -EIO;
+	wait_for_completion(&cmd->completion);
 
-	return 0;
+	return cmd->ret;
+
+unlock_err:
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
+	return -EIO;
 }
 
 int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
@@ -122,12 +167,9 @@ int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
 		in_num++;
 	}
 
-	mutex_lock(&vp_dev->admin_vq.cmd_lock);
 	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq,
 				       le16_to_cpu(cmd->opcode),
-				       sgs, out_num, in_num, sgs);
-	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
-
+				       sgs, out_num, in_num, cmd);
 	if (ret) {
 		dev_err(&vdev->dev,
 			"Failed to execute command on admin vq: %d\n.", ret);
@@ -188,25 +230,29 @@ static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev)
 
 static void vp_modern_avq_activate(struct virtio_device *vdev)
 {
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
-
 	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
 		return;
 
-	__virtqueue_unbreak(admin_vq->info.vq);
 	virtio_pci_admin_cmd_list_init(vdev);
 }
 
-static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+static void vp_modern_avq_cleanup(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+	struct virtio_admin_cmd *cmd;
+	struct virtqueue *vq;
 
 	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
 		return;
 
-	__virtqueue_break(admin_vq->info.vq);
+	vq = vp_dev->vqs[vp_dev->admin_vq.vq_index]->vq;
+	if (!vq)
+		return;
+
+	while ((cmd = virtqueue_detach_unused_buf(vq))) {
+		cmd->ret = -EIO;
+		complete(&cmd->completion);
+	}
 }
 
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
@@ -403,7 +449,7 @@ static void vp_reset(struct virtio_device *vdev)
 	while (vp_modern_get_status(mdev))
 		msleep(1);
 
-	vp_modern_avq_deactivate(vdev);
+	vp_modern_avq_cleanup(vdev);
 
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
@@ -552,8 +598,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (index >= vp_modern_get_num_queues(mdev) && !is_avq)
 		return ERR_PTR(-EINVAL);
 
-	num = is_avq ?
-		VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index);
+	num = vp_modern_get_queue_size(mdev, index);
 	/* Check if queue is either not available or already active. */
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
@@ -580,12 +625,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
-	if (is_avq) {
-		mutex_lock(&vp_dev->admin_vq.cmd_lock);
-		vp_dev->admin_vq.info.vq = vq;
-		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
-	}
-
 	return vq;
 
 err:
@@ -620,12 +659,6 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
-	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
-		mutex_lock(&vp_dev->admin_vq.cmd_lock);
-		vp_dev->admin_vq.info.vq = NULL;
-		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
-	}
-
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
 				       VIRTIO_MSI_NO_VECTOR);
@@ -735,45 +768,6 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
-static int vp_modern_create_avq(struct virtio_device *vdev)
-{
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_admin_vq *avq;
-	struct virtqueue *vq;
-	u16 admin_q_num;
-
-	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
-		return 0;
-
-	admin_q_num = vp_modern_avq_num(&vp_dev->mdev);
-	if (!admin_q_num)
-		return -EINVAL;
-
-	avq = &vp_dev->admin_vq;
-	avq->vq_index = vp_modern_avq_index(&vp_dev->mdev);
-	sprintf(avq->name, "avq.%u", avq->vq_index);
-	vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL,
-			      avq->name, NULL, VIRTIO_MSI_NO_VECTOR);
-	if (IS_ERR(vq)) {
-		dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld",
-			PTR_ERR(vq));
-		return PTR_ERR(vq);
-	}
-
-	vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true);
-	return 0;
-}
-
-static void vp_modern_destroy_avq(struct virtio_device *vdev)
-{
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
-	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
-		return;
-
-	vp_dev->del_vq(&vp_dev->admin_vq.info);
-}
-
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -792,8 +786,6 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
-	.create_avq = vp_modern_create_avq,
-	.destroy_avq = vp_modern_destroy_avq,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -814,8 +806,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
-	.create_avq = vp_modern_create_avq,
-	.destroy_avq = vp_modern_destroy_avq,
 };
 
 /* the PCI probing function */
@@ -839,11 +829,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
 	vp_dev->del_vq = del_vq;
-	vp_dev->is_avq = vp_is_avq;
+	vp_dev->avq_index = vp_avq_index;
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
-	mutex_init(&vp_dev->admin_vq.cmd_lock);
+	spin_lock_init(&vp_dev->admin_vq.lock);
 	return 0;
 }
 
@@ -851,6 +841,5 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
-	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }

include/linux/virtio.h

@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/completion.h>
 
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
@@ -109,6 +110,8 @@ struct virtio_admin_cmd {
 	__le64 group_member_id;
 	struct scatterlist *data_sg;
 	struct scatterlist *result_sg;
+	struct completion completion;
+	int ret;
 };
 
 /**

include/linux/virtio_config.h

@@ -104,8 +104,6 @@ struct virtqueue_info {
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
- * @create_avq: create admin virtqueue resource.
- * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -133,8 +131,6 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
-	int (*create_avq)(struct virtio_device *vdev);
-	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */