virtio-ring: store DMA metadata in desc_extra for split virtqueue

For split virtqueue, we used to depend on the address, length and
flags stored in the descriptor ring for DMA unmapping. This is unsafe
for the case since the device can manipulate the behavior of virtio
driver, IOMMU drivers and swiotlb.

For safety, maintain the DMA address, DMA length, descriptor flags and
next filed of the non indirect descriptors in vring_desc_state_extra
when DMA API is used for virtio as we did for packed virtqueue and use
those metadata for performing DMA operations. Indirect descriptors
should be safe since they are using streaming mappings.

With this the descriptor ring is write only form the view of the
driver.

This slight increase the footprint of the drive but it's not noticed
through pktgen (64B) test and netperf test in the case of virtio-net.

Signed-off-by: Jason Wang <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Michael S. Tsirkin <[e-mail]>

drivers/virtio/virtio_ring.c

···
 
 			/* 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;
···
  * Split ring specific functions - *_split().
  */
 
-static void vring_unmap_one_split(const struct vring_virtqueue *vq,
-				  struct vring_desc *desc)
+static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
+					   struct vring_desc *desc)
 {
 	u16 flags;
 
···
 			       (flags & VRING_DESC_F_WRITE) ?
 			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	}
+}
+
+static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
+					  unsigned int i)
+{
+	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) {
+		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 {
+		dma_unmap_page(vring_dma_dev(vq),
+			       extra[i].addr,
+			       extra[i].len,
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+
+out:
+	return extra[i].next;
 }
 
 static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
···
 						    unsigned int i,
 						    dma_addr_t addr,
 						    unsigned int len,
-						    u16 flags)
+						    u16 flags,
+						    bool indirect)
 {
+	struct vring_virtqueue *vring = to_vvq(vq);
+	struct vring_desc_extra *extra = vring->split.desc_extra;
+	u16 next;
+
 	desc[i].flags = cpu_to_virtio16(vq->vdev, flags);
 	desc[i].addr = cpu_to_virtio64(vq->vdev, addr);
 	desc[i].len = cpu_to_virtio32(vq->vdev, len);
 
-	return virtio16_to_cpu(vq->vdev, desc[i].next);
+	if (!indirect) {
+		next = extra[i].next;
+		desc[i].next = cpu_to_virtio16(vq->vdev, next);
+
+		extra[i].addr = addr;
+		extra[i].len = len;
+		extra[i].flags = flags;
+	} else
+		next = virtio16_to_cpu(vq->vdev, desc[i].next);
+
+	return next;
 }
 
 static inline int virtqueue_add_split(struct virtqueue *_vq,
···
 				goto unmap_release;
 
 			prev = i;
+			/* Note that we trust indirect descriptor
+			 * table since it use stream DMA mapping.
+			 */
 			i = virtqueue_add_desc_split(_vq, desc, i, addr, sg->length,
-						     VRING_DESC_F_NEXT);
+						     VRING_DESC_F_NEXT,
+						     indirect);
 		}
 	}
 	for (; n < (out_sgs + in_sgs); n++) {
···
 				goto unmap_release;
 
 			prev = i;
+			/* Note that we trust indirect descriptor
+			 * table since it use stream DMA mapping.
+			 */
 			i = virtqueue_add_desc_split(_vq, desc, i, addr,
 						     sg->length,
 						     VRING_DESC_F_NEXT |
-						     VRING_DESC_F_WRITE);
+						     VRING_DESC_F_WRITE,
+						     indirect);
 		}
 	}
 	/* Last one doesn't continue. */
 	desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
+	if (!indirect && vq->use_dma_api)
+		vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags =
+			~VRING_DESC_F_NEXT;
 
 	if (indirect) {
 		/* Now that the indirect table is filled in, map it. */
···
 		virtqueue_add_desc_split(_vq, vq->split.vring.desc,
 					 head, addr,
 					 total_sg * sizeof(struct vring_desc),
-			                 VRING_DESC_F_INDIRECT);
+					 VRING_DESC_F_INDIRECT,
+					 false);
 	}
 
 	/* We're using some buffers from the free list. */
···
 
 	/* Update free pointer */
 	if (indirect)
-		vq->free_head = virtio16_to_cpu(_vq->vdev,
-					vq->split.vring.desc[head].next);
+		vq->free_head = vq->split.desc_extra[head].next;
 	else
 		vq->free_head = i;
 
···
 	for (n = 0; n < total_sg; n++) {
 		if (i == err_idx)
 			break;
-		vring_unmap_one_split(vq, &desc[i]);
-		i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+		if (indirect) {
+			vring_unmap_one_split_indirect(vq, &desc[i]);
+			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+		} else
+			i = vring_unmap_one_split(vq, i);
 	}
 
 	if (indirect)
···
 	i = head;
 
 	while (vq->split.vring.desc[i].flags & nextflag) {
-		vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
-		i = virtio16_to_cpu(vq->vq.vdev, vq->split.vring.desc[i].next);
+		vring_unmap_one_split(vq, i);
+		i = vq->split.desc_extra[i].next;
 		vq->vq.num_free++;
 	}
 
-	vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
-	vq->split.vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev,
-						vq->free_head);
+	vring_unmap_one_split(vq, i);
+	vq->split.desc_extra[i].next = vq->free_head;
 	vq->free_head = head;
 
 	/* Plus final descriptor */
···
 		if (!indir_desc)
 			return;
 
-		len = virtio32_to_cpu(vq->vq.vdev,
-				vq->split.vring.desc[head].len);
+		len = vq->split.desc_extra[head].len;
 
-		BUG_ON(!(vq->split.vring.desc[head].flags &
-			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+		BUG_ON(!(vq->split.desc_extra[head].flags &
+				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(vq, &indir_desc[j]);
+			vring_unmap_one_split_indirect(vq, &indir_desc[j]);
 
 		kfree(indir_desc);
 		vq->split.desc_state[head].indir_desc = NULL;
···
 					void (*callback)(struct virtqueue *),
 					const char *name)
 {
-	unsigned int i;
 	struct vring_virtqueue *vq;
 
 	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
···
 	if (!vq->split.desc_state)
 		goto err_state;
 
+	vq->split.desc_extra = vring_alloc_desc_extra(vq, vring.num);
+	if (!vq->split.desc_extra)
+		goto err_extra;
+
 	/* Put everything in free lists. */
 	vq->free_head = 0;
-	for (i = 0; i < vring.num-1; i++)
-		vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
 	memset(vq->split.desc_state, 0, vring.num *
 			sizeof(struct vring_desc_state_split));
 
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 	return &vq->vq;
 
+err_extra:
+	kfree(vq->split.desc_state);
 err_state:
 	kfree(vq);
 	return NULL;
···
 					 vq->split.queue_dma_addr);
 		}
 	}
-	if (!vq->packed_ring)
+	if (!vq->packed_ring) {
 		kfree(vq->split.desc_state);
+		kfree(vq->split.desc_extra);
+	}
 	list_del(&_vq->list);
 	kfree(vq);
 }