vdpa: Support transferring virtual addressing during DMA mapping

This patch introduces an attribute for vDPA device to indicate
whether virtual address can be used. If vDPA device driver set
it, vhost-vdpa bus driver will not pin user page and transfer
userspace virtual address instead of physical address during
DMA mapping. And corresponding vma->vm_file and offset will be
also passed as an opaque pointer.

Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Xie Yongji <xieyongji@bytedance.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20210831103634.33-11-xieyongji@bytedance.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 88 insertions, 11 deletions

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index ad50d52d6655..f41d081777f5 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -526,8 +526,28 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 	}
 }
 
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+	struct vhost_iotlb_map *map;
+	struct vdpa_map_file *map_file;
+
+	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		fput(map_file->file);
+		kfree(map_file);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+}
+
 static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 {
+	struct vdpa_device *vdpa = v->vdpa;
+
+	if (vdpa->use_va)
+		return vhost_vdpa_va_unmap(v, start, last);
+
 	return vhost_vdpa_pa_unmap(v, start, last);
 }
 
@@ -562,21 +582,21 @@ static int perm_to_iommu_flags(u32 perm)
 	return flags | IOMMU_CACHE;
 }
 
-static int vhost_vdpa_map(struct vhost_vdpa *v,
-			  u64 iova, u64 size, u64 pa, u32 perm)
+static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,
+			  u64 size, u64 pa, u32 perm, void *opaque)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	int r = 0;
 
-	r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1,
-				  pa, perm);
+	r = vhost_iotlb_add_range_ctx(dev->iotlb, iova, iova + size - 1,
+				      pa, perm, opaque);
 	if (r)
 		return r;
 
 	if (ops->dma_map) {
-		r = ops->dma_map(vdpa, iova, size, pa, perm, NULL);
+		r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
 			r = ops->set_map(vdpa, dev->iotlb);
@@ -584,13 +604,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
 	}
-
-	if (r)
+	if (r) {
 		vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
-	else
+		return r;
+	}
+
+	if (!vdpa->use_va)
 		atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm);
 
-	return r;
+	return 0;
 }
 
 static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
@@ -611,6 +633,56 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
 	}
 }
 
+static int vhost_vdpa_va_map(struct vhost_vdpa *v,
+			     u64 iova, u64 size, u64 uaddr, u32 perm)
+{
+	struct vhost_dev *dev = &v->vdev;
+	u64 offset, map_size, map_iova = iova;
+	struct vdpa_map_file *map_file;
+	struct vm_area_struct *vma;
+	int ret;
+
+	mmap_read_lock(dev->mm);
+
+	while (size) {
+		vma = find_vma(dev->mm, uaddr);
+		if (!vma) {
+			ret = -EINVAL;
+			break;
+		}
+		map_size = min(size, vma->vm_end - uaddr);
+		if (!(vma->vm_file && (vma->vm_flags & VM_SHARED) &&
+			!(vma->vm_flags & (VM_IO | VM_PFNMAP))))
+			goto next;
+
+		map_file = kzalloc(sizeof(*map_file), GFP_KERNEL);
+		if (!map_file) {
+			ret = -ENOMEM;
+			break;
+		}
+		offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start;
+		map_file->offset = offset;
+		map_file->file = get_file(vma->vm_file);
+		ret = vhost_vdpa_map(v, map_iova, map_size, uaddr,
+				     perm, map_file);
+		if (ret) {
+			fput(map_file->file);
+			kfree(map_file);
+			break;
+		}
+next:
+		size -= map_size;
+		uaddr += map_size;
+		map_iova += map_size;
+	}
+	if (ret)
+		vhost_vdpa_unmap(v, iova, map_iova - iova);
+
+	mmap_read_unlock(dev->mm);
+
+	return ret;
+}
+
 static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 			     u64 iova, u64 size, u64 uaddr, u32 perm)
 {
@@ -677,7 +749,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 				csize = PFN_PHYS(last_pfn - map_pfn + 1);
 				ret = vhost_vdpa_map(v, iova, csize,
 						     PFN_PHYS(map_pfn),
-						     perm);
+						     perm, NULL);
 				if (ret) {
 					/*
 					 * Unpin the pages that are left unmapped
@@ -706,7 +778,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 
 	/* Pin the rest chunk */
 	ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1),
-			     PFN_PHYS(map_pfn), perm);
+			     PFN_PHYS(map_pfn), perm, NULL);
 out:
 	if (ret) {
 		if (nchunks) {
@@ -739,6 +811,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 					   struct vhost_iotlb_msg *msg)
 {
 	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
 	struct vhost_iotlb *iotlb = dev->iotlb;
 
 	if (msg->iova < v->range.first || !msg->size ||
@@ -750,6 +823,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 				    msg->iova + msg->size - 1))
 		return -EEXIST;
 
+	if (vdpa->use_va)
+		return vhost_vdpa_va_map(v, msg->iova, msg->size,
+					 msg->uaddr, msg->perm);
+
 	return vhost_vdpa_pa_map(v, msg->iova, msg->size, msg->uaddr,
 				 msg->perm);
 }