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

Pull virtio updates from Michael Tsirkin:
 "A small pull request this time around, mostly because the vduse
  network got postponed to next relase so we can be sure we got the
  security store right"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_ring: fix avail_wrap_counter in virtqueue_add_packed
  virtio_vdpa: build affinity masks conditionally
  virtio_net: merge dma operations when filling mergeable buffers
  virtio_ring: introduce dma sync api for virtqueue
  virtio_ring: introduce dma map api for virtqueue
  virtio_ring: introduce virtqueue_reset()
  virtio_ring: separate the logic of reset/enable from virtqueue_resize
  virtio_ring: correct the expression of the description of virtqueue_resize()
  virtio_ring: skip unmap for premapped
  virtio_ring: introduce virtqueue_dma_dev()
  virtio_ring: support add premapped buf
  virtio_ring: introduce virtqueue_set_dma_premapped()
  virtio_ring: put mapping error check in vring_map_one_sg
  virtio_ring: check use_dma_api before unmap desc for indirect
  vdpa_sim: offer VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
  vdpa: add get_backend_features vdpa operation
  vdpa: accept VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK backend feature
  vdpa: add VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK flag
  vdpa/mlx5: Remove unused function declarations

9 files changed, 624 insertions, 89 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 231ad91a919d1..fe7f314d65c97 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -132,6 +132,14 @@ struct virtnet_interrupt_coalesce {
 	u32 max_usecs;
 };
 
+/* The dma information of pages allocated at a time. */
+struct virtnet_rq_dma {
+	dma_addr_t addr;
+	u32 ref;
+	u16 len;
+	u16 need_sync;
+};
+
 /* Internal representation of a send virtqueue */
 struct send_queue {
 	/* Virtqueue associated with this send _queue */
@@ -185,6 +193,12 @@ struct receive_queue {
 	char name[16];
 
 	struct xdp_rxq_info xdp_rxq;
+
+	/* Record the last dma info to free after new pages is allocated. */
+	struct virtnet_rq_dma *last_dma;
+
+	/* Do dma by self */
+	bool do_dma;
 };
 
 /* This structure can contain rss message with maximum settings for indirection table and keysize
@@ -580,6 +594,156 @@ ok:
 	return skb;
 }
 
+static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len)
+{
+	struct page *page = virt_to_head_page(buf);
+	struct virtnet_rq_dma *dma;
+	void *head;
+	int offset;
+
+	head = page_address(page);
+
+	dma = head;
+
+	--dma->ref;
+
+	if (dma->ref) {
+		if (dma->need_sync && len) {
+			offset = buf - (head + sizeof(*dma));
+
+			virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset,
+								len, DMA_FROM_DEVICE);
+		}
+
+		return;
+	}
+
+	virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len,
+					 DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	put_page(page);
+}
+
+static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
+{
+	void *buf;
+
+	buf = virtqueue_get_buf_ctx(rq->vq, len, ctx);
+	if (buf && rq->do_dma)
+		virtnet_rq_unmap(rq, buf, *len);
+
+	return buf;
+}
+
+static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq)
+{
+	void *buf;
+
+	buf = virtqueue_detach_unused_buf(rq->vq);
+	if (buf && rq->do_dma)
+		virtnet_rq_unmap(rq, buf, 0);
+
+	return buf;
+}
+
+static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
+{
+	struct virtnet_rq_dma *dma;
+	dma_addr_t addr;
+	u32 offset;
+	void *head;
+
+	if (!rq->do_dma) {
+		sg_init_one(rq->sg, buf, len);
+		return;
+	}
+
+	head = page_address(rq->alloc_frag.page);
+
+	offset = buf - head;
+
+	dma = head;
+
+	addr = dma->addr - sizeof(*dma) + offset;
+
+	sg_init_table(rq->sg, 1);
+	rq->sg[0].dma_address = addr;
+	rq->sg[0].length = len;
+}
+
+static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
+{
+	struct page_frag *alloc_frag = &rq->alloc_frag;
+	struct virtnet_rq_dma *dma;
+	void *buf, *head;
+	dma_addr_t addr;
+
+	if (unlikely(!skb_page_frag_refill(size, alloc_frag, gfp)))
+		return NULL;
+
+	head = page_address(alloc_frag->page);
+
+	if (rq->do_dma) {
+		dma = head;
+
+		/* new pages */
+		if (!alloc_frag->offset) {
+			if (rq->last_dma) {
+				/* Now, the new page is allocated, the last dma
+				 * will not be used. So the dma can be unmapped
+				 * if the ref is 0.
+				 */
+				virtnet_rq_unmap(rq, rq->last_dma, 0);
+				rq->last_dma = NULL;
+			}
+
+			dma->len = alloc_frag->size - sizeof(*dma);
+
+			addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1,
+							      dma->len, DMA_FROM_DEVICE, 0);
+			if (virtqueue_dma_mapping_error(rq->vq, addr))
+				return NULL;
+
+			dma->addr = addr;
+			dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
+
+			/* Add a reference to dma to prevent the entire dma from
+			 * being released during error handling. This reference
+			 * will be freed after the pages are no longer used.
+			 */
+			get_page(alloc_frag->page);
+			dma->ref = 1;
+			alloc_frag->offset = sizeof(*dma);
+
+			rq->last_dma = dma;
+		}
+
+		++dma->ref;
+	}
+
+	buf = head + alloc_frag->offset;
+
+	get_page(alloc_frag->page);
+	alloc_frag->offset += size;
+
+	return buf;
+}
+
+static void virtnet_rq_set_premapped(struct virtnet_info *vi)
+{
+	int i;
+
+	/* disable for big mode */
+	if (!vi->mergeable_rx_bufs && vi->big_packets)
+		return;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (virtqueue_set_dma_premapped(vi->rq[i].vq))
+			continue;
+
+		vi->rq[i].do_dma = true;
+	}
+}
+
 static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
 	unsigned int len;
@@ -935,7 +1099,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 		void *buf;
 		int off;
 
-		buf = virtqueue_get_buf(rq->vq, &buflen);
+		buf = virtnet_rq_get_buf(rq, &buflen, NULL);
 		if (unlikely(!buf))
 			goto err_buf;
 
@@ -1155,7 +1319,7 @@ static void mergeable_buf_free(struct receive_queue *rq, int num_buf,
 	int len;
 
 	while (num_buf-- > 1) {
-		buf = virtqueue_get_buf(rq->vq, &len);
+		buf = virtnet_rq_get_buf(rq, &len, NULL);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
 				 dev->name, num_buf);
@@ -1263,7 +1427,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 		return -EINVAL;
 
 	while (--*num_buf > 0) {
-		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+		buf = virtnet_rq_get_buf(rq, &len, &ctx);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, *num_buf,
@@ -1492,7 +1656,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	while (--num_buf) {
 		int num_skb_frags;
 
-		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+		buf = virtnet_rq_get_buf(rq, &len, &ctx);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, num_buf,
@@ -1651,7 +1815,6 @@ frame_err:
 static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 			     gfp_t gfp)
 {
-	struct page_frag *alloc_frag = &rq->alloc_frag;
 	char *buf;
 	unsigned int xdp_headroom = virtnet_get_headroom(vi);
 	void *ctx = (void *)(unsigned long)xdp_headroom;
@@ -1660,17 +1823,21 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 
 	len = SKB_DATA_ALIGN(len) +
 	      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
+
+	buf = virtnet_rq_alloc(rq, len, gfp);
+	if (unlikely(!buf))
 		return -ENOMEM;
 
-	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
-	get_page(alloc_frag->page);
-	alloc_frag->offset += len;
-	sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom,
-		    vi->hdr_len + GOOD_PACKET_LEN);
+	virtnet_rq_init_one_sg(rq, buf + VIRTNET_RX_PAD + xdp_headroom,
+			       vi->hdr_len + GOOD_PACKET_LEN);
+
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
-	if (err < 0)
+	if (err < 0) {
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
+	}
+
 	return err;
 }
 
@@ -1747,23 +1914,22 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	unsigned int headroom = virtnet_get_headroom(vi);
 	unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
 	unsigned int room = SKB_DATA_ALIGN(headroom + tailroom);
-	char *buf;
+	unsigned int len, hole;
 	void *ctx;
+	char *buf;
 	int err;
-	unsigned int len, hole;
 
 	/* Extra tailroom is needed to satisfy XDP's assumption. This
 	 * means rx frags coalescing won't work, but consider we've
 	 * disabled GSO for XDP, it won't be a big issue.
 	 */
 	len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room);
-	if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp)))
+
+	buf = virtnet_rq_alloc(rq, len + room, gfp);
+	if (unlikely(!buf))
 		return -ENOMEM;
 
-	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
 	buf += headroom; /* advance address leaving hole at front of pkt */
-	get_page(alloc_frag->page);
-	alloc_frag->offset += len + room;
 	hole = alloc_frag->size - alloc_frag->offset;
 	if (hole < len + room) {
 		/* To avoid internal fragmentation, if there is very likely not
@@ -1777,11 +1943,15 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 		alloc_frag->offset += hole;
 	}
 
-	sg_init_one(rq->sg, buf, len);
+	virtnet_rq_init_one_sg(rq, buf, len);
+
 	ctx = mergeable_len_to_ctx(len + room, headroom);
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
-	if (err < 0)
+	if (err < 0) {
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
+	}
 
 	return err;
 }
@@ -1902,13 +2072,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 		void *ctx;
 
 		while (stats.packets < budget &&
-		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
+		       (buf = virtnet_rq_get_buf(rq, &len, &ctx))) {
 			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
 			stats.packets++;
 		}
 	} else {
 		while (stats.packets < budget &&
-		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+		       (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) {
 			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
 			stats.packets++;
 		}
@@ -3808,8 +3978,11 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 {
 	int i;
 	for (i = 0; i < vi->max_queue_pairs; i++)
-		if (vi->rq[i].alloc_frag.page)
+		if (vi->rq[i].alloc_frag.page) {
+			if (vi->rq[i].do_dma && vi->rq[i].last_dma)
+				virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0);
 			put_page(vi->rq[i].alloc_frag.page);
+		}
 }
 
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
@@ -3846,9 +4019,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		struct virtqueue *vq = vi->rq[i].vq;
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
-			virtnet_rq_free_unused_buf(vq, buf);
+		struct receive_queue *rq = &vi->rq[i];
+
+		while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL)
+			virtnet_rq_free_unused_buf(rq->vq, buf);
 		cond_resched();
 	}
 }
@@ -4022,6 +4196,8 @@ static int init_vqs(struct virtnet_info *vi)
 	if (ret)
 		goto err_free;
 
+	virtnet_rq_set_premapped(vi);
+
 	cpus_read_lock();
 	virtnet_set_affinity(vi);
 	cpus_read_unlock();
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index b53420e874acb..ca56242972b3a 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -100,9 +100,6 @@ struct mlx5_vdpa_dev {
 	bool suspended;
 };
 
-int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid);
-int mlx5_vdpa_dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid);
-int mlx5_vdpa_get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey);
 int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn);
 void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn);
 int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index d343af4fa60ee..76d41058add9a 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -18,6 +18,7 @@
 #include <linux/vdpa.h>
 #include <linux/vhost_iotlb.h>
 #include <uapi/linux/vdpa.h>
+#include <uapi/linux/vhost_types.h>
 
 #include "vdpa_sim.h"
 
@@ -410,6 +411,11 @@ static u64 vdpasim_get_device_features(struct vdpa_device *vdpa)
 	return vdpasim->dev_attr.supported_features;
 }
 
+static u64 vdpasim_get_backend_features(const struct vdpa_device *vdpa)
+{
+	return BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK);
+}
+
 static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -733,6 +739,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.get_vq_align           = vdpasim_get_vq_align,
 	.get_vq_group           = vdpasim_get_vq_group,
 	.get_device_features    = vdpasim_get_device_features,
+	.get_backend_features   = vdpasim_get_backend_features,
 	.set_driver_features    = vdpasim_set_driver_features,
 	.get_driver_features    = vdpasim_get_driver_features,
 	.set_config_cb          = vdpasim_set_config_cb,
@@ -770,6 +777,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_vq_align           = vdpasim_get_vq_align,
 	.get_vq_group           = vdpasim_get_vq_group,
 	.get_device_features    = vdpasim_get_device_features,
+	.get_backend_features   = vdpasim_get_backend_features,
 	.set_driver_features    = vdpasim_set_driver_features,
 	.get_driver_features    = vdpasim_get_driver_features,
 	.set_config_cb          = vdpasim_set_config_cb,
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index b43e8680eee8d..78379ffd23363 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -403,6 +403,17 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
 	return 0;
 }
 
+static u64 vhost_vdpa_get_backend_features(const struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (!ops->get_backend_features)
+		return 0;
+	else
+		return ops->get_backend_features(vdpa);
+}
+
 static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
 {
 	struct vdpa_device *vdpa = v->vdpa;
@@ -680,7 +691,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 			return -EFAULT;
 		if (features & ~(VHOST_VDPA_BACKEND_FEATURES |
 				 BIT_ULL(VHOST_BACKEND_F_SUSPEND) |
-				 BIT_ULL(VHOST_BACKEND_F_RESUME)))
+				 BIT_ULL(VHOST_BACKEND_F_RESUME) |
+				 BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK)))
 			return -EOPNOTSUPP;
 		if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) &&
 		     !vhost_vdpa_can_suspend(v))
@@ -741,6 +753,7 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 			features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND);
 		if (vhost_vdpa_can_resume(v))
 			features |= BIT_ULL(VHOST_BACKEND_F_RESUME);
+		features |= vhost_vdpa_get_backend_features(v);
 		if (copy_to_user(featurep, &features, sizeof(features)))
 			r = -EFAULT;
 		break;
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index c5310eaf8b468..51d8f3299c105 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -172,6 +172,14 @@ struct vring_virtqueue {
 	/* Host publishes avail event idx */
 	bool event;
 
+	/* Do DMA mapping by driver */
+	bool premapped;
+
+	/* Do unmap or not for desc. Just when premapped is False and
+	 * use_dma_api is true, this is true.
+	 */
+	bool do_unmap;
+
 	/* Head of free buffer list. */
 	unsigned int free_head;
 	/* Number we've added since last sync. */
@@ -355,10 +363,14 @@ static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
 }
 
 /* Map one sg entry. */
-static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
-				   struct scatterlist *sg,
-				   enum dma_data_direction direction)
+static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist *sg,
+			    enum dma_data_direction direction, dma_addr_t *addr)
 {
+	if (vq->premapped) {
+		*addr = sg_dma_address(sg);
+		return 0;
+	}
+
 	if (!vq->use_dma_api) {
 		/*
 		 * If DMA is not used, KMSAN doesn't know that the scatterlist
@@ -366,7 +378,8 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
 		 * depending on the direction.
 		 */
 		kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction);
-		return (dma_addr_t)sg_phys(sg);
+		*addr = (dma_addr_t)sg_phys(sg);
+		return 0;
 	}
 
 	/*
@@ -374,9 +387,14 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
 	 * the way it expects (we don't guarantee that the scatterlist
 	 * will exist for the lifetime of the mapping).
 	 */
-	return dma_map_page(vring_dma_dev(vq),
+	*addr = dma_map_page(vring_dma_dev(vq),
 			    sg_page(sg), sg->offset, sg->length,
 			    direction);
+
+	if (dma_mapping_error(vring_dma_dev(vq), *addr))
+		return -ENOMEM;
+
+	return 0;
 }
 
 static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
@@ -427,7 +445,7 @@ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
 {
 	u16 flags;
 
-	if (!vq->use_dma_api)
+	if (!vq->do_unmap)
 		return;
 
 	flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
@@ -445,18 +463,21 @@ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
 	struct vring_desc_extra *extra = vq->split.desc_extra;
 	u16 flags;
 
-	if (!vq->use_dma_api)
-		goto out;
-
 	flags = extra[i].flags;
 
 	if (flags & VRING_DESC_F_INDIRECT) {
+		if (!vq->use_dma_api)
+			goto out;
+
 		dma_unmap_single(vring_dma_dev(vq),
 				 extra[i].addr,
 				 extra[i].len,
 				 (flags & VRING_DESC_F_WRITE) ?
 				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	} else {
+		if (!vq->do_unmap)
+			goto out;
+
 		dma_unmap_page(vring_dma_dev(vq),
 			       extra[i].addr,
 			       extra[i].len,
@@ -588,8 +609,9 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 
 	for (n = 0; n < out_sgs; n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
-			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_TO_DEVICE);
-			if (vring_mapping_error(vq, addr))
+			dma_addr_t addr;
+
+			if (vring_map_one_sg(vq, sg, DMA_TO_DEVICE, &addr))
 				goto unmap_release;
 
 			prev = i;
@@ -603,8 +625,9 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	}
 	for (; n < (out_sgs + in_sgs); n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
-			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_FROM_DEVICE);
-			if (vring_mapping_error(vq, addr))
+			dma_addr_t addr;
+
+			if (vring_map_one_sg(vq, sg, DMA_FROM_DEVICE, &addr))
 				goto unmap_release;
 
 			prev = i;
@@ -620,7 +643,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	}
 	/* Last one doesn't continue. */
 	desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
-	if (!indirect && vq->use_dma_api)
+	if (!indirect && vq->do_unmap)
 		vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &=
 			~VRING_DESC_F_NEXT;
 
@@ -629,8 +652,12 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		dma_addr_t addr = vring_map_single(
 			vq, desc, total_sg * sizeof(struct vring_desc),
 			DMA_TO_DEVICE);
-		if (vring_mapping_error(vq, addr))
+		if (vring_mapping_error(vq, addr)) {
+			if (vq->premapped)
+				goto free_indirect;
+
 			goto unmap_release;
+		}
 
 		virtqueue_add_desc_split(_vq, vq->split.vring.desc,
 					 head, addr,
@@ -696,6 +723,7 @@ unmap_release:
 			i = vring_unmap_one_split(vq, i);
 	}
 
+free_indirect:
 	if (indirect)
 		kfree(desc);
 
@@ -774,8 +802,10 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 				VRING_DESC_F_INDIRECT));
 		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
 
-		for (j = 0; j < len / sizeof(struct vring_desc); j++)
-			vring_unmap_one_split_indirect(vq, &indir_desc[j]);
+		if (vq->do_unmap) {
+			for (j = 0; j < len / sizeof(struct vring_desc); j++)
+				vring_unmap_one_split_indirect(vq, &indir_desc[j]);
+		}
 
 		kfree(indir_desc);
 		vq->split.desc_state[head].indir_desc = NULL;
@@ -1195,17 +1225,20 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
 {
 	u16 flags;
 
-	if (!vq->use_dma_api)
-		return;
-
 	flags = extra->flags;
 
 	if (flags & VRING_DESC_F_INDIRECT) {
+		if (!vq->use_dma_api)
+			return;
+
 		dma_unmap_single(vring_dma_dev(vq),
 				 extra->addr, extra->len,
 				 (flags & VRING_DESC_F_WRITE) ?
 				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	} else {
+		if (!vq->do_unmap)
+			return;
+
 		dma_unmap_page(vring_dma_dev(vq),
 			       extra->addr, extra->len,
 			       (flags & VRING_DESC_F_WRITE) ?
@@ -1218,7 +1251,7 @@ static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
 {
 	u16 flags;
 
-	if (!vq->use_dma_api)
+	if (!vq->do_unmap)
 		return;
 
 	flags = le16_to_cpu(desc->flags);
@@ -1279,9 +1312,8 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 
 	for (n = 0; n < out_sgs + in_sgs; n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
-			addr = vring_map_one_sg(vq, sg, n < out_sgs ?
-					DMA_TO_DEVICE : DMA_FROM_DEVICE);
-			if (vring_mapping_error(vq, addr))
+			if (vring_map_one_sg(vq, sg, n < out_sgs ?
+					     DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr))
 				goto unmap_release;
 
 			desc[i].flags = cpu_to_le16(n < out_sgs ?
@@ -1296,15 +1328,19 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	addr = vring_map_single(vq, desc,
 			total_sg * sizeof(struct vring_packed_desc),
 			DMA_TO_DEVICE);
-	if (vring_mapping_error(vq, addr))
+	if (vring_mapping_error(vq, addr)) {
+		if (vq->premapped)
+			goto free_desc;
+
 		goto unmap_release;
+	}
 
 	vq->packed.vring.desc[head].addr = cpu_to_le64(addr);
 	vq->packed.vring.desc[head].len = cpu_to_le32(total_sg *
 				sizeof(struct vring_packed_desc));
 	vq->packed.vring.desc[head].id = cpu_to_le16(id);
 
-	if (vq->use_dma_api) {
+	if (vq->do_unmap) {
 		vq->packed.desc_extra[id].addr = addr;
 		vq->packed.desc_extra[id].len = total_sg *
 				sizeof(struct vring_packed_desc);
@@ -1355,6 +1391,7 @@ unmap_release:
 	for (i = 0; i < err_idx; i++)
 		vring_unmap_desc_packed(vq, &desc[i]);
 
+free_desc:
 	kfree(desc);
 
 	END_USE(vq);
@@ -1426,9 +1463,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	c = 0;
 	for (n = 0; n < out_sgs + in_sgs; n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
-			dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
-					DMA_TO_DEVICE : DMA_FROM_DEVICE);
-			if (vring_mapping_error(vq, addr))
+			dma_addr_t addr;
+
+			if (vring_map_one_sg(vq, sg, n < out_sgs ?
+					     DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr))
 				goto unmap_release;
 
 			flags = cpu_to_le16(vq->packed.avail_used_flags |
@@ -1443,7 +1481,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 			desc[i].len = cpu_to_le32(sg->length);
 			desc[i].id = cpu_to_le16(id);
 
-			if (unlikely(vq->use_dma_api)) {
+			if (unlikely(vq->do_unmap)) {
 				vq->packed.desc_extra[curr].addr = addr;
 				vq->packed.desc_extra[curr].len = sg->length;
 				vq->packed.desc_extra[curr].flags =
@@ -1461,7 +1499,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 		}
 	}
 
-	if (i < head)
+	if (i <= head)
 		vq->packed.avail_wrap_counter ^= 1;
 
 	/* We're using some buffers from the free list. */
@@ -1577,7 +1615,7 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
 	vq->free_head = id;
 	vq->vq.num_free += state->num;
 
-	if (unlikely(vq->use_dma_api)) {
+	if (unlikely(vq->do_unmap)) {
 		curr = id;
 		for (i = 0; i < state->num; i++) {
 			vring_unmap_extra_packed(vq,
@@ -1594,7 +1632,7 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
 		if (!desc)
 			return;
 
-		if (vq->use_dma_api) {
+		if (vq->do_unmap) {
 			len = vq->packed.desc_extra[id].len;
 			for (i = 0; i < len / sizeof(struct vring_packed_desc);
 					i++)
@@ -2052,6 +2090,8 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	vq->packed_ring = true;
 	vq->dma_dev = dma_dev;
 	vq->use_dma_api = vring_use_dma_api(vdev);
+	vq->premapped = false;
+	vq->do_unmap = vq->use_dma_api;
 
 	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
 		!context;
@@ -2112,6 +2152,43 @@ err_ring:
 	return -ENOMEM;
 }
 
+static int virtqueue_disable_and_recycle(struct virtqueue *_vq,
+					 void (*recycle)(struct virtqueue *vq, void *buf))
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct virtio_device *vdev = vq->vq.vdev;
+	void *buf;
+	int err;
+
+	if (!vq->we_own_ring)
+		return -EPERM;
+
+	if (!vdev->config->disable_vq_and_reset)
+		return -ENOENT;
+
+	if (!vdev->config->enable_vq_after_reset)
+		return -ENOENT;
+
+	err = vdev->config->disable_vq_and_reset(_vq);
+	if (err)
+		return err;
+
+	while ((buf = virtqueue_detach_unused_buf(_vq)) != NULL)
+		recycle(_vq, buf);
+
+	return 0;
+}
+
+static int virtqueue_enable_after_reset(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct virtio_device *vdev = vq->vq.vdev;
+
+	if (vdev->config->enable_vq_after_reset(_vq))
+		return -EBUSY;
+
+	return 0;
+}
 
 /*
  * Generic functions and exported symbols.
@@ -2238,6 +2315,23 @@ int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
 
 /**
+ * virtqueue_dma_dev - get the dma dev
+ * @_vq: the struct virtqueue we're talking about.
+ *
+ * Returns the dma dev. That can been used for dma api.
+ */
+struct device *virtqueue_dma_dev(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->use_dma_api)
+		return vring_dma_dev(vq);
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_dev);
+
+/**
  * virtqueue_kick_prepare - first half of split virtqueue_kick call.
  * @_vq: the struct virtqueue
  *
@@ -2541,6 +2635,8 @@ static struct virtqueue *__vring_new_virtqueue(unsigned int index,
 #endif
 	vq->dma_dev = dma_dev;
 	vq->use_dma_api = vring_use_dma_api(vdev);
+	vq->premapped = false;
+	vq->do_unmap = vq->use_dma_api;
 
 	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
 		!context;
@@ -2619,7 +2715,7 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma);
  * virtqueue_resize - resize the vring of vq
  * @_vq: the struct virtqueue we're talking about.
  * @num: new ring num
- * @recycle: callback for recycle the useless buffer
+ * @recycle: callback to recycle unused buffers
  *
  * When it is really necessary to create a new vring, it will set the current vq
  * into the reset state. Then call the passed callback to recycle the buffer
@@ -2643,13 +2739,8 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 		     void (*recycle)(struct virtqueue *vq, void *buf))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	struct virtio_device *vdev = vq->vq.vdev;
-	void *buf;
 	int err;
 
-	if (!vq->we_own_ring)
-		return -EPERM;
-
 	if (num > vq->vq.num_max)
 		return -E2BIG;
 
@@ -2659,31 +2750,101 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 	if ((vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num) == num)
 		return 0;
 
-	if (!vdev->config->disable_vq_and_reset)
-		return -ENOENT;
-
-	if (!vdev->config->enable_vq_after_reset)
-		return -ENOENT;
-
-	err = vdev->config->disable_vq_and_reset(_vq);
+	err = virtqueue_disable_and_recycle(_vq, recycle);
 	if (err)
 		return err;
 
-	while ((buf = virtqueue_detach_unused_buf(_vq)) != NULL)
-		recycle(_vq, buf);
-
 	if (vq->packed_ring)
 		err = virtqueue_resize_packed(_vq, num);
 	else
 		err = virtqueue_resize_split(_vq, num);
 
-	if (vdev->config->enable_vq_after_reset(_vq))
-		return -EBUSY;
-
-	return err;
+	return virtqueue_enable_after_reset(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_resize);
 
+/**
+ * virtqueue_set_dma_premapped - set the vring premapped mode
+ * @_vq: the struct virtqueue we're talking about.
+ *
+ * Enable the premapped mode of the vq.
+ *
+ * The vring in premapped mode does not do dma internally, so the driver must
+ * do dma mapping in advance. The driver must pass the dma_address through
+ * dma_address of scatterlist. When the driver got a used buffer from
+ * the vring, it has to unmap the dma address.
+ *
+ * This function must be called immediately after creating the vq, or after vq
+ * reset, and before adding any buffers to it.
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error.
+ * 0: success.
+ * -EINVAL: vring does not use the dma api, so we can not enable premapped mode.
+ */
+int virtqueue_set_dma_premapped(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u32 num;
+
+	START_USE(vq);
+
+	num = vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num;
+
+	if (num != vq->vq.num_free) {
+		END_USE(vq);
+		return -EINVAL;
+	}
+
+	if (!vq->use_dma_api) {
+		END_USE(vq);
+		return -EINVAL;
+	}
+
+	vq->premapped = true;
+	vq->do_unmap = false;
+
+	END_USE(vq);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtqueue_set_dma_premapped);
+
+/**
+ * virtqueue_reset - detach and recycle all unused buffers
+ * @_vq: the struct virtqueue we're talking about.
+ * @recycle: callback to recycle unused buffers
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error.
+ * 0: success.
+ * -EBUSY: Failed to sync with device, vq may not work properly
+ * -ENOENT: Transport or device not supported
+ * -EPERM: Operation not permitted
+ */
+int virtqueue_reset(struct virtqueue *_vq,
+		    void (*recycle)(struct virtqueue *vq, void *buf))
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	int err;
+
+	err = virtqueue_disable_and_recycle(_vq, recycle);
+	if (err)
+		return err;
+
+	if (vq->packed_ring)
+		virtqueue_reinit_packed(vq);
+	else
+		virtqueue_reinit_split(vq);
+
+	return virtqueue_enable_after_reset(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_reset);
+
 /* Only available for split ring */
 struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int num,
@@ -2945,4 +3106,149 @@ const struct vring *virtqueue_get_vring(const struct virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring);
 
+/**
+ * virtqueue_dma_map_single_attrs - map DMA for _vq
+ * @_vq: the struct virtqueue we're talking about.
+ * @ptr: the pointer of the buffer to do dma
+ * @size: the size of the buffer to do dma
+ * @dir: DMA direction
+ * @attrs: DMA Attrs
+ *
+ * The caller calls this to do dma mapping in advance. The DMA address can be
+ * passed to this _vq when it is in pre-mapped mode.
+ *
+ * return DMA address. Caller should check that by virtqueue_dma_mapping_error().
+ */
+dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr,
+					  size_t size,
+					  enum dma_data_direction dir,
+					  unsigned long attrs)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!vq->use_dma_api)
+		return (dma_addr_t)virt_to_phys(ptr);
+
+	return dma_map_single_attrs(vring_dma_dev(vq), ptr, size, dir, attrs);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_map_single_attrs);
+
+/**
+ * virtqueue_dma_unmap_single_attrs - unmap DMA for _vq
+ * @_vq: the struct virtqueue we're talking about.
+ * @addr: the dma address to unmap
+ * @size: the size of the buffer
+ * @dir: DMA direction
+ * @attrs: DMA Attrs
+ *
+ * Unmap the address that is mapped by the virtqueue_dma_map_* APIs.
+ *
+ */
+void virtqueue_dma_unmap_single_attrs(struct virtqueue *_vq, dma_addr_t addr,
+				      size_t size, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!vq->use_dma_api)
+		return;
+
+	dma_unmap_single_attrs(vring_dma_dev(vq), addr, size, dir, attrs);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_unmap_single_attrs);
+
+/**
+ * virtqueue_dma_mapping_error - check dma address
+ * @_vq: the struct virtqueue we're talking about.
+ * @addr: DMA address
+ *
+ * Returns 0 means dma valid. Other means invalid dma address.
+ */
+int virtqueue_dma_mapping_error(struct virtqueue *_vq, dma_addr_t addr)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!vq->use_dma_api)
+		return 0;
+
+	return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_mapping_error);
+
+/**
+ * virtqueue_dma_need_sync - check a dma address needs sync
+ * @_vq: the struct virtqueue we're talking about.
+ * @addr: DMA address
+ *
+ * Check if the dma address mapped by the virtqueue_dma_map_* APIs needs to be
+ * synchronized
+ *
+ * return bool
+ */
+bool virtqueue_dma_need_sync(struct virtqueue *_vq, dma_addr_t addr)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!vq->use_dma_api)
+		return false;
+
+	return dma_need_sync(vring_dma_dev(vq), addr);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_need_sync);
+
+/**
+ * virtqueue_dma_sync_single_range_for_cpu - dma sync for cpu
+ * @_vq: the struct virtqueue we're talking about.
+ * @addr: DMA address
+ * @offset: DMA address offset
+ * @size: buf size for sync
+ * @dir: DMA direction
+ *
+ * Before calling this function, use virtqueue_dma_need_sync() to confirm that
+ * the DMA address really needs to be synchronized
+ *
+ */
+void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq,
+					     dma_addr_t addr,
+					     unsigned long offset, size_t size,
+					     enum dma_data_direction dir)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct device *dev = vring_dma_dev(vq);
+
+	if (!vq->use_dma_api)
+		return;
+
+	dma_sync_single_range_for_cpu(dev, addr, offset, size,
+				      DMA_BIDIRECTIONAL);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu);
+
+/**
+ * virtqueue_dma_sync_single_range_for_device - dma sync for device
+ * @_vq: the struct virtqueue we're talking about.
+ * @addr: DMA address
+ * @offset: DMA address offset
+ * @size: buf size for sync
+ * @dir: DMA direction
+ *
+ * Before calling this function, use virtqueue_dma_need_sync() to confirm that
+ * the DMA address really needs to be synchronized
+ */
+void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq,
+						dma_addr_t addr,
+						unsigned long offset, size_t size,
+						enum dma_data_direction dir)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct device *dev = vring_dma_dev(vq);
+
+	if (!vq->use_dma_api)
+		return;
+
+	dma_sync_single_range_for_device(dev, addr, offset, size,
+					 DMA_BIDIRECTIONAL);
+}
+EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device);
+
 MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 961161da59000..06ce6d8c2e004 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -366,11 +366,14 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 	struct irq_affinity default_affd = { 0 };
 	struct cpumask *masks;
 	struct vdpa_callback cb;
+	bool has_affinity = desc && ops->set_vq_affinity;
 	int i, err, queue_idx = 0;
 
-	masks = create_affinity_masks(nvqs, desc ? desc : &default_affd);
-	if (!masks)
-		return -ENOMEM;
+	if (has_affinity) {
+		masks = create_affinity_masks(nvqs, desc ? desc : &default_affd);
+		if (!masks)
+			return -ENOMEM;
+	}
 
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
@@ -386,20 +389,22 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			goto err_setup_vq;
 		}
 
-		if (ops->set_vq_affinity)
+		if (has_affinity)
 			ops->set_vq_affinity(vdpa, i, &masks[i]);
 	}
 
 	cb.callback = virtio_vdpa_config_cb;
 	cb.private = vd_dev;
 	ops->set_config_cb(vdpa, &cb);
-	kfree(masks);
+	if (has_affinity)
+		kfree(masks);
 
 	return 0;
 
 err_setup_vq:
 	virtio_vdpa_del_vqs(vdev);
-	kfree(masks);
+	if (has_affinity)
+		kfree(masks);
 	return err;
 }
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index db1b0eaef4eb7..0e652026b776f 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -208,6 +208,9 @@ struct vdpa_map_file {
  *				@vdev: vdpa device
  *				Returns the virtio features support by the
  *				device
+ * @get_backend_features:	Get parent-specific backend features (optional)
+ *				Returns the vdpa features supported by the
+ *				device.
  * @set_driver_features:	Set virtio features supported by the driver
  *				@vdev: vdpa device
  *				@features: feature support by the driver
@@ -358,6 +361,7 @@ struct vdpa_config_ops {
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
 	u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx);
 	u64 (*get_device_features)(struct vdpa_device *vdev);
+	u64 (*get_backend_features)(const struct vdpa_device *vdev);
 	int (*set_driver_features)(struct vdpa_device *vdev, u64 features);
 	u64 (*get_driver_features)(struct vdpa_device *vdev);
 	void (*set_config_cb)(struct vdpa_device *vdev,
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index de6041deee372..1311a7fbe6752 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
+#include <linux/dma-mapping.h>
 
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
@@ -61,6 +62,8 @@ int virtqueue_add_sgs(struct virtqueue *vq,
 		      void *data,
 		      gfp_t gfp);
 
+struct device *virtqueue_dma_dev(struct virtqueue *vq);
+
 bool virtqueue_kick(struct virtqueue *vq);
 
 bool virtqueue_kick_prepare(struct virtqueue *vq);
@@ -78,6 +81,8 @@ bool virtqueue_enable_cb(struct virtqueue *vq);
 
 unsigned virtqueue_enable_cb_prepare(struct virtqueue *vq);
 
+int virtqueue_set_dma_premapped(struct virtqueue *_vq);
+
 bool virtqueue_poll(struct virtqueue *vq, unsigned);
 
 bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
@@ -95,6 +100,8 @@ dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq);
 
 int virtqueue_resize(struct virtqueue *vq, u32 num,
 		     void (*recycle)(struct virtqueue *vq, void *buf));
+int virtqueue_reset(struct virtqueue *vq,
+		    void (*recycle)(struct virtqueue *vq, void *buf));
 
 /**
  * struct virtio_device - representation of a device using virtio
@@ -206,4 +213,19 @@ void unregister_virtio_driver(struct virtio_driver *drv);
 #define module_virtio_driver(__virtio_driver) \
 	module_driver(__virtio_driver, register_virtio_driver, \
 			unregister_virtio_driver)
+
+dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr, size_t size,
+					  enum dma_data_direction dir, unsigned long attrs);
+void virtqueue_dma_unmap_single_attrs(struct virtqueue *_vq, dma_addr_t addr,
+				      size_t size, enum dma_data_direction dir,
+				      unsigned long attrs);
+int virtqueue_dma_mapping_error(struct virtqueue *_vq, dma_addr_t addr);
+
+bool virtqueue_dma_need_sync(struct virtqueue *_vq, dma_addr_t addr);
+void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t addr,
+					     unsigned long offset, size_t size,
+					     enum dma_data_direction dir);
+void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr,
+						unsigned long offset, size_t size,
+						enum dma_data_direction dir);
 #endif /* _LINUX_VIRTIO_H */
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index d3aad12ad1fa7..2d827d22cd99d 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -181,5 +181,9 @@ struct vhost_vdpa_iova_range {
 #define VHOST_BACKEND_F_SUSPEND  0x4
 /* Device can be resumed */
 #define VHOST_BACKEND_F_RESUME  0x5
+/* Device supports the driver enabling virtqueues both before and after
+ * DRIVER_OK
+ */
+#define VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK  0x6
 
 #endif