[RFC net-next 03/13] virtio_ring: packed: harden dma unmap for indirect

[Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx>]

1. this commit hardens dma unmap for indirect
2. the subsequent commit uses the struct extra to record whether the
   buffers need to be unmapped or not. So we need a struct extra for
   every desc, whatever it is indirect or not.

Signed-off-by: Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx>
---
 drivers/virtio/virtio_ring.c | 57 ++++++++++++++++++------------------
 1 file changed, 29 insertions(+), 28 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 1e037da542b9..5fb94f735edb 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -81,7 +81,7 @@ struct vring_desc_state_split {
 
 struct vring_desc_state_packed {
 	void *data;			/* Data for callback. */
-	struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
+	struct vring_desc_extra *indir; /* Indirect descriptor, if any. */
 	u16 num;			/* Descriptor list length. */
 	u16 last;			/* The last desc state in a list. */
 };
@@ -1238,27 +1238,13 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
 	}
 }
 
-static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
-				    const struct vring_packed_desc *desc)
-{
-	u16 flags;
-
-	if (!vring_need_unmap_buffer(vq))
-		return;
-
-	flags = le16_to_cpu(desc->flags);
-
-	dma_unmap_page(vring_dma_dev(vq),
-		       le64_to_cpu(desc->addr),
-		       le32_to_cpu(desc->len),
-		       (flags & VRING_DESC_F_WRITE) ?
-		       DMA_FROM_DEVICE : DMA_TO_DEVICE);
-}
-
 static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
+						       struct vring_desc_extra **pextra,
 						       gfp_t gfp)
 {
+	struct vring_desc_extra *extra;
 	struct vring_packed_desc *desc;
+	int i;
 
 	/*
 	 * We require lowmem mappings for the descriptors because
@@ -1267,7 +1253,14 @@ static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
 	 */
 	gfp &= ~__GFP_HIGHMEM;
 
-	desc = kmalloc_array(total_sg, sizeof(struct vring_packed_desc), gfp);
+	extra = kmalloc_array(total_sg, sizeof(*desc) + sizeof(*extra), gfp);
+
+	desc = (struct vring_packed_desc *)&extra[total_sg];
+
+	for (i = 0; i < total_sg; i++)
+		extra[i].next = i + 1;
+
+	*pextra = extra;
 
 	return desc;
 }
@@ -1280,6 +1273,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 					 void *data,
 					 gfp_t gfp)
 {
+	struct vring_desc_extra *extra;
 	struct vring_packed_desc *desc;
 	struct scatterlist *sg;
 	unsigned int i, n, err_idx;
@@ -1287,7 +1281,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	dma_addr_t addr;
 
 	head = vq->packed.next_avail_idx;
-	desc = alloc_indirect_packed(total_sg, gfp);
+	desc = alloc_indirect_packed(total_sg, &extra, gfp);
 	if (!desc)
 		return -ENOMEM;
 
@@ -1313,6 +1307,12 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 			desc[i].addr = cpu_to_le64(addr);
 			desc[i].len = cpu_to_le32(sg->length);
 			i++;
+
+			if (unlikely(vq->use_dma_api)) {
+				extra[i].addr = addr;
+				extra[i].len = sg->length;
+				extra[i].flags = n < out_sgs ?  0 : VRING_DESC_F_WRITE;
+			}
 		}
 	}
 
@@ -1367,7 +1367,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	/* Store token and indirect buffer state. */
 	vq->packed.desc_state[id].num = 1;
 	vq->packed.desc_state[id].data = data;
-	vq->packed.desc_state[id].indir_desc = desc;
+	vq->packed.desc_state[id].indir = extra;
 	vq->packed.desc_state[id].last = id;
 
 	vq->num_added += 1;
@@ -1381,7 +1381,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	err_idx = i;
 
 	for (i = 0; i < err_idx; i++)
-		vring_unmap_desc_packed(vq, &desc[i]);
+		vring_unmap_extra_packed(vq, &extra[i]);
 
 free_desc:
 	kfree(desc);
@@ -1504,7 +1504,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	/* Store token. */
 	vq->packed.desc_state[id].num = descs_used;
 	vq->packed.desc_state[id].data = data;
-	vq->packed.desc_state[id].indir_desc = ctx;
+	vq->packed.desc_state[id].indir = ctx;
 	vq->packed.desc_state[id].last = prev;
 
 	/*
@@ -1617,23 +1617,24 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
 	}
 
 	if (vq->indirect) {
+		struct vring_desc_extra *extra;
 		u32 len;
 
 		/* Free the indirect table, if any, now that it's unmapped. */
-		desc = state->indir_desc;
-		if (!desc)
+		extra = state->indir;
+		if (!extra)
 			return;
 
 		if (vring_need_unmap_buffer(vq)) {
 			len = vq->packed.desc_extra[id].len;
 			for (i = 0; i < len / sizeof(struct vring_packed_desc);
 					i++)
-				vring_unmap_desc_packed(vq, &desc[i]);
+				vring_unmap_extra_packed(vq, &extra[i]);
 		}
 		kfree(desc);
-		state->indir_desc = NULL;
+		state->indir = NULL;
 	} else if (ctx) {
-		*ctx = state->indir_desc;
+		*ctx = state->indir;
 	}
 }
 
-- 
2.32.0.3.g01195cf9f