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

Pull virtio updates from Michael Tsirkin:

 - A huge patchset supporting vq resize using the new vq reset
   capability

 - Features, fixes, and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (88 commits)
  vdpa/mlx5: Fix possible uninitialized return value
  vdpa_sim_blk: add support for discard and write-zeroes
  vdpa_sim_blk: add support for VIRTIO_BLK_T_FLUSH
  vdpa_sim_blk: make vdpasim_blk_check_range usable by other requests
  vdpa_sim_blk: check if sector is 0 for commands other than read or write
  vdpa_sim: Implement suspend vdpa op
  vhost-vdpa: uAPI to suspend the device
  vhost-vdpa: introduce SUSPEND backend feature bit
  vdpa: Add suspend operation
  virtio-blk: Avoid use-after-free on suspend/resume
  virtio_vdpa: support the arg sizes of find_vqs()
  vhost-vdpa: Call ida_simple_remove() when failed
  vDPA: fix 'cast to restricted le16' warnings in vdpa.c
  vDPA: !FEATURES_OK should not block querying device config space
  vDPA/ifcvf: support userspace to query features and MQ of a management device
  vDPA/ifcvf: get_config_size should return a value no greater than dev implementation
  vhost scsi: Allow user to control num virtqueues
  vhost-scsi: Fix max number of virtqueues
  vdpa/mlx5: Support different address spaces for control and data
  vdpa/mlx5: Implement susupend virtqueue callback
  ...

10 files changed, 791 insertions, 261 deletions

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 56c77f63cd22..0a53a61231c2 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -35,11 +35,12 @@ if VIRTIO_MENU
 
 config VIRTIO_HARDEN_NOTIFICATION
         bool "Harden virtio notification"
+        depends on BROKEN
         help
           Enable this to harden the device notifications and suppress
           those that happen at a time where notifications are illegal.
 
-          Experimental: Note that several drivers still have bugs that
+          Experimental: Note that several drivers still have issues that
           may cause crashes or hangs when correct handling of
           notifications is enforced; depending on the subset of
           drivers and devices you use, this may or may not work.
@@ -126,9 +127,11 @@ config VIRTIO_MEM
 	 This driver provides access to virtio-mem paravirtualized memory
 	 devices, allowing to hotplug and hotunplug memory.
 
-	 This driver was only tested under x86-64 and arm64, but should
-	 theoretically work on all architectures that support memory hotplug
-	 and hotremove.
+	 This driver currently only supports x86-64 and arm64. Although it
+	 should compile on other architectures that implement memory
+	 hot(un)plug, architecture-specific and/or common
+	 code changes may be required for virtio-mem, kdump and kexec to work as
+	 expected.
 
 	 If unsure, say M.
 
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 14c142d77fba..828ced060742 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -428,7 +428,9 @@ int register_virtio_device(struct virtio_device *dev)
 		goto out;
 
 	dev->index = err;
-	dev_set_name(&dev->dev, "virtio%u", dev->index);
+	err = dev_set_name(&dev->dev, "virtio%u", dev->index);
+	if (err)
+		goto out_ida_remove;
 
 	err = virtio_device_of_init(dev);
 	if (err)
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 083ff1eb743d..c492a57531c6 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -360,7 +360,7 @@ static void vm_synchronize_cbs(struct virtio_device *vdev)
 
 static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
-				  const char *name, bool ctx)
+				  const char *name, u32 size, bool ctx)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct virtio_mmio_vq_info *info;
@@ -395,14 +395,19 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 		goto error_new_virtqueue;
 	}
 
+	if (!size || size > num)
+		size = num;
+
 	/* Create the vring */
-	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+	vq = vring_create_virtqueue(index, size, VIRTIO_MMIO_VRING_ALIGN, vdev,
 				 true, true, ctx, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto error_new_virtqueue;
 	}
 
+	vq->num_max = num;
+
 	/* Activate the queue */
 	writel(virtqueue_get_vring_size(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
 	if (vm_dev->version == 1) {
@@ -472,6 +477,7 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
 		       const char * const names[],
+		       u32 sizes[],
 		       const bool *ctx,
 		       struct irq_affinity *desc)
 {
@@ -487,6 +493,9 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 	if (err)
 		return err;
 
+	if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source"))
+		enable_irq_wake(irq);
+
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
@@ -494,6 +503,7 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		}
 
 		vqs[i] = vm_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
+				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			vm_del_vqs(vdev);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index ca51fcc9daab..00ad476a815d 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -174,6 +174,7 @@ error:
 static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
 				     void (*callback)(struct virtqueue *vq),
 				     const char *name,
+				     u32 size,
 				     bool ctx,
 				     u16 msix_vec)
 {
@@ -186,7 +187,7 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int in
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, size, ctx,
 			      msix_vec);
 	if (IS_ERR(vq))
 		goto out_info;
@@ -214,9 +215,15 @@ static void vp_del_vq(struct virtqueue *vq)
 	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);
+	/*
+	 * If it fails during re-enable reset vq. This way we won't rejoin
+	 * info->node to the queue. Prevent unexpected irqs.
+	 */
+	if (!vq->reset) {
+		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);
@@ -277,7 +284,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], bool per_vq_vectors,
+		const char * const names[], u32 sizes[], bool per_vq_vectors,
 		const bool *ctx,
 		struct irq_affinity *desc)
 {
@@ -320,8 +327,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		else
 			msix_vec = VP_MSIX_VQ_VECTOR;
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     ctx ? ctx[i] : false,
-				     msix_vec);
+				     sizes ? sizes[i] : 0,
+				     ctx ? ctx[i] : false, msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto error_find;
@@ -351,7 +358,7 @@ error_find:
 
 static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], const bool *ctx)
+		const char * const names[], u32 sizes[], const bool *ctx)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err, queue_idx = 0;
@@ -373,6 +380,7 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 			continue;
 		}
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
+				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false,
 				     VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
@@ -390,21 +398,21 @@ out_del_vqs:
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], const bool *ctx,
+		const char * const names[], u32 sizes[], const bool *ctx,
 		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, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, true, ctx, 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, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, false, ctx, desc);
 	if (!err)
 		return 0;
 	/* Finally fall back to regular interrupts. */
-	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
+	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, sizes, ctx);
 }
 
 const char *vp_bus_name(struct virtio_device *vdev)
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 23112d84218f..c0448378b698 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -80,6 +80,7 @@ struct virtio_pci_device {
 				      unsigned int idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
+				      u32 size,
 				      bool ctx,
 				      u16 msix_vec);
 	void (*del_vq)(struct virtio_pci_vq_info *info);
@@ -110,7 +111,7 @@ void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], const bool *ctx,
+		const char * const names[], u32 sizes[], const bool *ctx,
 		struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index a5e5721145c7..d75e5c4e637f 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -112,6 +112,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
+				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -125,16 +126,21 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index))
 		return ERR_PTR(-ENOENT);
 
+	if (!size || size > num)
+		size = num;
+
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, num,
+	vq = vring_create_virtqueue(index, size,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
 				    true, false, ctx,
 				    vp_notify, callback, name);
 	if (!vq)
 		return ERR_PTR(-ENOMEM);
 
+	vq->num_max = num;
+
 	q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
 	if (q_pfn >> 32) {
 		dev_err(&vp_dev->pci_dev->dev,
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 623906b4996c..f7965c5dd36b 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -34,6 +34,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 	if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
 			pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
 		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
+
+	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
+		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
 }
 
 /* virtio config->finalize_features() implementation */
@@ -176,6 +179,110 @@ static void vp_reset(struct virtio_device *vdev)
 	vp_synchronize_vectors(vdev);
 }
 
+static int vp_active_vq(struct virtqueue *vq, u16 msix_vec)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	unsigned long index;
+
+	index = vq->index;
+
+	/* activate the queue */
+	vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq));
+	vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
+				virtqueue_get_avail_addr(vq),
+				virtqueue_get_used_addr(vq));
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		msix_vec = vp_modern_queue_vector(mdev, index, msix_vec);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int vp_modern_disable_vq_and_reset(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_vq_info *info;
+	unsigned long flags;
+
+	if (!virtio_has_feature(vq->vdev, VIRTIO_F_RING_RESET))
+		return -ENOENT;
+
+	vp_modern_set_queue_reset(mdev, vq->index);
+
+	info = vp_dev->vqs[vq->index];
+
+	/* delete vq from irq handler */
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	INIT_LIST_HEAD(&info->node);
+
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	__virtqueue_break(vq);
+#endif
+
+	/* For the case where vq has an exclusive irq, call synchronize_irq() to
+	 * wait for completion.
+	 *
+	 * note: We can't use disable_irq() since it conflicts with the affinity
+	 * managed IRQ that is used by some drivers.
+	 */
+	if (vp_dev->per_vq_vectors && info->msix_vector != VIRTIO_MSI_NO_VECTOR)
+		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, info->msix_vector));
+
+	vq->reset = true;
+
+	return 0;
+}
+
+static int vp_modern_enable_vq_after_reset(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_vq_info *info;
+	unsigned long flags, index;
+	int err;
+
+	if (!vq->reset)
+		return -EBUSY;
+
+	index = vq->index;
+	info = vp_dev->vqs[index];
+
+	if (vp_modern_get_queue_reset(mdev, index))
+		return -EBUSY;
+
+	if (vp_modern_get_queue_enable(mdev, index))
+		return -EBUSY;
+
+	err = vp_active_vq(vq, info->msix_vector);
+	if (err)
+		return err;
+
+	if (vq->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);
+	}
+
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	__virtqueue_unbreak(vq);
+#endif
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, index, true);
+	vq->reset = false;
+
+	return 0;
+}
+
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
 	return vp_modern_config_vector(&vp_dev->mdev, vector);
@@ -186,6 +293,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
+				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -203,47 +311,39 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (num & (num - 1)) {
-		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
+	if (!size || size > num)
+		size = num;
+
+	if (size & (size - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", size);
 		return ERR_PTR(-EINVAL);
 	}
 
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, num,
+	vq = vring_create_virtqueue(index, size,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
 				    true, true, ctx,
 				    vp_notify, callback, name);
 	if (!vq)
 		return ERR_PTR(-ENOMEM);
 
-	/* activate the queue */
-	vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq));
-	vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
-				virtqueue_get_avail_addr(vq),
-				virtqueue_get_used_addr(vq));
+	vq->num_max = num;
+
+	err = vp_active_vq(vq, msix_vec);
+	if (err)
+		goto err;
 
 	vq->priv = (void __force *)vp_modern_map_vq_notify(mdev, index, NULL);
 	if (!vq->priv) {
 		err = -ENOMEM;
-		goto err_map_notify;
-	}
-
-	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
-		msix_vec = vp_modern_queue_vector(mdev, index, msix_vec);
-		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
-			err = -EBUSY;
-			goto err_assign_vector;
-		}
+		goto err;
 	}
 
 	return vq;
 
-err_assign_vector:
-	if (!mdev->notify_base)
-		pci_iounmap(mdev->pci_dev, (void __iomem __force *)vq->priv);
-err_map_notify:
+err:
 	vring_del_virtqueue(vq);
 	return ERR_PTR(err);
 }
@@ -251,12 +351,15 @@ err_map_notify:
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			      struct virtqueue *vqs[],
 			      vq_callback_t *callbacks[],
-			      const char * const names[], const bool *ctx,
+			      const char * const names[],
+			      u32 sizes[],
+			      const bool *ctx,
 			      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, ctx, desc);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, sizes, ctx,
+			     desc);
 
 	if (rc)
 		return rc;
@@ -401,6 +504,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
 	.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,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -419,6 +524,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
 	.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,
 };
 
 /* the PCI probing function */
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index fa2a9445bb18..869cb46bef96 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -3,6 +3,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 
 /*
  * vp_modern_map_capability - map a part of virtio pci capability
@@ -475,6 +476,44 @@ void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
 EXPORT_SYMBOL_GPL(vp_modern_set_status);
 
 /*
+ * vp_modern_get_queue_reset - get the queue reset status
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ */
+int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+
+	vp_iowrite16(index, &cfg->cfg.queue_select);
+	return vp_ioread16(&cfg->queue_reset);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_reset);
+
+/*
+ * vp_modern_set_queue_reset - reset the queue
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ */
+void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+
+	vp_iowrite16(index, &cfg->cfg.queue_select);
+	vp_iowrite16(1, &cfg->queue_reset);
+
+	while (vp_ioread16(&cfg->queue_reset))
+		msleep(1);
+
+	while (vp_ioread16(&cfg->cfg.queue_enable))
+		msleep(1);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_reset);
+
+/*
  * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
  * @mdev: the modern virtio-pci device
  * @index: queue index
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 643ca779fcc6..d66c8e6d0ef3 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -85,6 +85,71 @@ struct vring_desc_extra {
 	u16 next;			/* The next desc state in a list. */
 };
 
+struct vring_virtqueue_split {
+	/* Actual memory layout for this queue. */
+	struct vring vring;
+
+	/* Last written value to avail->flags */
+	u16 avail_flags_shadow;
+
+	/*
+	 * Last written value to avail->idx in
+	 * guest byte order.
+	 */
+	u16 avail_idx_shadow;
+
+	/* Per-descriptor state. */
+	struct vring_desc_state_split *desc_state;
+	struct vring_desc_extra *desc_extra;
+
+	/* DMA address and size information */
+	dma_addr_t queue_dma_addr;
+	size_t queue_size_in_bytes;
+
+	/*
+	 * The parameters for creating vrings are reserved for creating new
+	 * vring.
+	 */
+	u32 vring_align;
+	bool may_reduce_num;
+};
+
+struct vring_virtqueue_packed {
+	/* Actual memory layout for this queue. */
+	struct {
+		unsigned int num;
+		struct vring_packed_desc *desc;
+		struct vring_packed_desc_event *driver;
+		struct vring_packed_desc_event *device;
+	} vring;
+
+	/* Driver ring wrap counter. */
+	bool avail_wrap_counter;
+
+	/* Avail used flags. */
+	u16 avail_used_flags;
+
+	/* Index of the next avail descriptor. */
+	u16 next_avail_idx;
+
+	/*
+	 * Last written value to driver->flags in
+	 * guest byte order.
+	 */
+	u16 event_flags_shadow;
+
+	/* Per-descriptor state. */
+	struct vring_desc_state_packed *desc_state;
+	struct vring_desc_extra *desc_extra;
+
+	/* DMA address and size information */
+	dma_addr_t ring_dma_addr;
+	dma_addr_t driver_event_dma_addr;
+	dma_addr_t device_event_dma_addr;
+	size_t ring_size_in_bytes;
+	size_t event_size_in_bytes;
+};
+
 struct vring_virtqueue {
 	struct virtqueue vq;
 
@@ -124,64 +189,10 @@ struct vring_virtqueue {
 
 	union {
 		/* Available for split ring */
-		struct {
-			/* Actual memory layout for this queue. */
-			struct vring vring;
-
-			/* Last written value to avail->flags */
-			u16 avail_flags_shadow;
-
-			/*
-			 * Last written value to avail->idx in
-			 * guest byte order.
-			 */
-			u16 avail_idx_shadow;
-
-			/* Per-descriptor state. */
-			struct vring_desc_state_split *desc_state;
-			struct vring_desc_extra *desc_extra;
-
-			/* DMA address and size information */
-			dma_addr_t queue_dma_addr;
-			size_t queue_size_in_bytes;
-		} split;
+		struct vring_virtqueue_split split;
 
 		/* Available for packed ring */
-		struct {
-			/* Actual memory layout for this queue. */
-			struct {
-				unsigned int num;
-				struct vring_packed_desc *desc;
-				struct vring_packed_desc_event *driver;
-				struct vring_packed_desc_event *device;
-			} vring;
-
-			/* Driver ring wrap counter. */
-			bool avail_wrap_counter;
-
-			/* Avail used flags. */
-			u16 avail_used_flags;
-
-			/* Index of the next avail descriptor. */
-			u16 next_avail_idx;
-
-			/*
-			 * Last written value to driver->flags in
-			 * guest byte order.
-			 */
-			u16 event_flags_shadow;
-
-			/* Per-descriptor state. */
-			struct vring_desc_state_packed *desc_state;
-			struct vring_desc_extra *desc_extra;
-
-			/* DMA address and size information */
-			dma_addr_t ring_dma_addr;
-			dma_addr_t driver_event_dma_addr;
-			dma_addr_t device_event_dma_addr;
-			size_t ring_size_in_bytes;
-			size_t event_size_in_bytes;
-		} packed;
+		struct vring_virtqueue_packed packed;
 	};
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
@@ -200,6 +211,16 @@ struct vring_virtqueue {
 #endif
 };
 
+static struct virtqueue *__vring_new_virtqueue(unsigned int index,
+					       struct vring_virtqueue_split *vring_split,
+					       struct virtio_device *vdev,
+					       bool weak_barriers,
+					       bool context,
+					       bool (*notify)(struct virtqueue *),
+					       void (*callback)(struct virtqueue *),
+					       const char *name);
+static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num);
+static void vring_free(struct virtqueue *_vq);
 
 /*
  * Helpers.
@@ -364,6 +385,24 @@ static int vring_mapping_error(const struct vring_virtqueue *vq,
 	return dma_mapping_error(vring_dma_dev(vq), addr);
 }
 
+static void virtqueue_init(struct vring_virtqueue *vq, u32 num)
+{
+	vq->vq.num_free = num;
+
+	if (vq->packed_ring)
+		vq->last_used_idx = 0 | (1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+	else
+		vq->last_used_idx = 0;
+
+	vq->event_triggered = false;
+	vq->num_added = 0;
+
+#ifdef DEBUG
+	vq->in_use = false;
+	vq->last_add_time_valid = false;
+#endif
+}
+
 
 /*
  * Split ring specific functions - *_split().
@@ -907,28 +946,107 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 	return NULL;
 }
 
-static struct virtqueue *vring_create_virtqueue_split(
-	unsigned int index,
-	unsigned int num,
-	unsigned int vring_align,
-	struct virtio_device *vdev,
-	bool weak_barriers,
-	bool may_reduce_num,
-	bool context,
-	bool (*notify)(struct virtqueue *),
-	void (*callback)(struct virtqueue *),
-	const char *name)
+static void virtqueue_vring_init_split(struct vring_virtqueue_split *vring_split,
+				       struct vring_virtqueue *vq)
+{
+	struct virtio_device *vdev;
+
+	vdev = vq->vq.vdev;
+
+	vring_split->avail_flags_shadow = 0;
+	vring_split->avail_idx_shadow = 0;
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!vq->vq.callback) {
+		vring_split->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		if (!vq->event)
+			vring_split->vring.avail->flags = cpu_to_virtio16(vdev,
+					vring_split->avail_flags_shadow);
+	}
+}
+
+static void virtqueue_reinit_split(struct vring_virtqueue *vq)
+{
+	int num;
+
+	num = vq->split.vring.num;
+
+	vq->split.vring.avail->flags = 0;
+	vq->split.vring.avail->idx = 0;
+
+	/* reset avail event */
+	vq->split.vring.avail->ring[num] = 0;
+
+	vq->split.vring.used->flags = 0;
+	vq->split.vring.used->idx = 0;
+
+	/* reset used event */
+	*(__virtio16 *)&(vq->split.vring.used->ring[num]) = 0;
+
+	virtqueue_init(vq, num);
+
+	virtqueue_vring_init_split(&vq->split, vq);
+}
+
+static void virtqueue_vring_attach_split(struct vring_virtqueue *vq,
+					 struct vring_virtqueue_split *vring_split)
+{
+	vq->split = *vring_split;
+
+	/* Put everything in free lists. */
+	vq->free_head = 0;
+}
+
+static int vring_alloc_state_extra_split(struct vring_virtqueue_split *vring_split)
+{
+	struct vring_desc_state_split *state;
+	struct vring_desc_extra *extra;
+	u32 num = vring_split->vring.num;
+
+	state = kmalloc_array(num, sizeof(struct vring_desc_state_split), GFP_KERNEL);
+	if (!state)
+		goto err_state;
+
+	extra = vring_alloc_desc_extra(num);
+	if (!extra)
+		goto err_extra;
+
+	memset(state, 0, num * sizeof(struct vring_desc_state_split));
+
+	vring_split->desc_state = state;
+	vring_split->desc_extra = extra;
+	return 0;
+
+err_extra:
+	kfree(state);
+err_state:
+	return -ENOMEM;
+}
+
+static void vring_free_split(struct vring_virtqueue_split *vring_split,
+			     struct virtio_device *vdev)
+{
+	vring_free_queue(vdev, vring_split->queue_size_in_bytes,
+			 vring_split->vring.desc,
+			 vring_split->queue_dma_addr);
+
+	kfree(vring_split->desc_state);
+	kfree(vring_split->desc_extra);
+}
+
+static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split,
+				   struct virtio_device *vdev,
+				   u32 num,
+				   unsigned int vring_align,
+				   bool may_reduce_num)
 {
-	struct virtqueue *vq;
 	void *queue = NULL;
 	dma_addr_t dma_addr;
-	size_t queue_size_in_bytes;
-	struct vring vring;
 
 	/* We assume num is a power of 2. */
 	if (num & (num - 1)) {
 		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
-		return NULL;
+		return -EINVAL;
 	}
 
 	/* TODO: allocate each queue chunk individually */
@@ -939,11 +1057,11 @@ static struct virtqueue *vring_create_virtqueue_split(
 		if (queue)
 			break;
 		if (!may_reduce_num)
-			return NULL;
+			return -ENOMEM;
 	}
 
 	if (!num)
-		return NULL;
+		return -ENOMEM;
 
 	if (!queue) {
 		/* Try to get a single page. You are my only hope! */
@@ -951,26 +1069,85 @@ static struct virtqueue *vring_create_virtqueue_split(
 					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
 	}
 	if (!queue)
-		return NULL;
+		return -ENOMEM;
+
+	vring_init(&vring_split->vring, num, queue, vring_align);
+
+	vring_split->queue_dma_addr = dma_addr;
+	vring_split->queue_size_in_bytes = vring_size(num, vring_align);
 
-	queue_size_in_bytes = vring_size(num, vring_align);
-	vring_init(&vring, num, queue, vring_align);
+	vring_split->vring_align = vring_align;
+	vring_split->may_reduce_num = may_reduce_num;
 
-	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
-				   notify, callback, name);
+	return 0;
+}
+
+static struct virtqueue *vring_create_virtqueue_split(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct vring_virtqueue_split vring_split = {};
+	struct virtqueue *vq;
+	int err;
+
+	err = vring_alloc_queue_split(&vring_split, vdev, num, vring_align,
+				      may_reduce_num);
+	if (err)
+		return NULL;
+
+	vq = __vring_new_virtqueue(index, &vring_split, vdev, weak_barriers,
+				   context, notify, callback, name);
 	if (!vq) {
-		vring_free_queue(vdev, queue_size_in_bytes, queue,
-				 dma_addr);
+		vring_free_split(&vring_split, vdev);
 		return NULL;
 	}
 
-	to_vvq(vq)->split.queue_dma_addr = dma_addr;
-	to_vvq(vq)->split.queue_size_in_bytes = queue_size_in_bytes;
 	to_vvq(vq)->we_own_ring = true;
 
 	return vq;
 }
 
+static int virtqueue_resize_split(struct virtqueue *_vq, u32 num)
+{
+	struct vring_virtqueue_split vring_split = {};
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct virtio_device *vdev = _vq->vdev;
+	int err;
+
+	err = vring_alloc_queue_split(&vring_split, vdev, num,
+				      vq->split.vring_align,
+				      vq->split.may_reduce_num);