A new field is reserved in vfio_device_feature_dma_buf.flags to
request CPU-facing memory type attributes for mmap()s of the buffer.
Add a flag VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_WC, which results in WC
PTEs for the DMABUF's BAR region.

Signed-off-by: Matt Evans <mattev@meta.com>
---
 drivers/vfio/pci/vfio_pci_dmabuf.c | 18 ++++++++++++++----
 include/uapi/linux/vfio.h          | 12 +++++++++---
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index af30ca205f31..d66a918e9934 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -28,6 +28,7 @@ struct vfio_pci_dma_buf {
 	struct dma_buf_phys_vec *phys_vec;
 	struct p2pdma_provider *provider;
 	u32 nr_ranges;
+	u32 attrs;
 	enum vfio_pci_dma_buf_status status;
 };
 
@@ -286,13 +287,15 @@ static int vfio_pci_dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *
 		return -EINVAL;
 
 	vma->vm_private_data = priv;
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (priv->attrs == VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_WC)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
 
 	/*
 	 * See comments in vfio_pci_core_mmap() re VM_ALLOW_ANY_UNCACHED.
-	 *
-	 * FIXME: get mapping attributes from dmabuf?
 	 */
 	vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED | VM_IO | VM_PFNMAP |
 		     VM_DONTEXPAND | VM_DONTDUMP);
@@ -402,6 +405,12 @@ static int validate_dmabuf_input(struct vfio_device_feature_dma_buf *dma_buf,
 	size_t length = 0;
 	u32 i;
 
+	if ((dma_buf->flags != 0) &&
+	    ((dma_buf->flags & ~VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_MASK) ||
+	     ((dma_buf->flags & VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_MASK) !=
+	      VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_WC)))
+		return -EINVAL;
+
 	for (i = 0; i < dma_buf->nr_ranges; i++) {
 		u64 offset = dma_ranges[i].offset;
 		u64 len = dma_ranges[i].length;
@@ -446,7 +455,7 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 	if (copy_from_user(&get_dma_buf, arg, sizeof(get_dma_buf)))
 		return -EFAULT;
 
-	if (!get_dma_buf.nr_ranges || get_dma_buf.flags)
+	if (!get_dma_buf.nr_ranges)
 		return -EINVAL;
 
 	/*
@@ -490,6 +499,7 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 	priv->vdev = vdev;
 	priv->nr_ranges = get_dma_buf.nr_ranges;
 	priv->size = length;
+	priv->attrs = get_dma_buf.flags & VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_MASK;
 	ret = vdev->pci_ops->get_dmabuf_phys(vdev, &priv->provider,
 					     get_dma_buf.region_index,
 					     priv->phys_vec, dma_ranges,
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index ac2329f24141..9e0fbf333452 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1487,7 +1487,9 @@ struct vfio_device_feature_bus_master {
  * etc. offset/length specify a slice of the region to create the dmabuf from.
  * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf.
  *
- * flags should be 0.
+ * flags contains:
+ * - A field for userspace mapping attribute: by default, suitable for regular
+ *   MMIO. Alternate attributes (such as WC) can be selected.
  *
  * Return: The fd number on success, -1 and errno is set on failure.
  */
@@ -1501,8 +1503,12 @@ struct vfio_region_dma_range {
 struct vfio_device_feature_dma_buf {
 	__u32	region_index;
 	__u32	open_flags;
-	__u32   flags;
-	__u32   nr_ranges;
+	__u32	flags;
+	/* Flags sub-field reserved for attribute enum */
+#define VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_MASK		(0xf << 28)
+#define VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_UC		(0 << 28)
+#define VFIO_DEVICE_FEATURE_DMA_BUF_ATTR_WC		(1 << 28)
+	__u32	nr_ranges;
 	struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges);
 };
 
-- 
2.47.3