Re: [PATCH RFC 01/13] vhost: option to fetch descriptors through an independent struct

From: Jason Wang
Date: Wed Jun 03 2020 - 08:05:03 EST


On 2020/6/3 äå5:48, Michael S. Tsirkin wrote:
On Wed, Jun 03, 2020 at 03:13:56PM +0800, Jason Wang wrote:
On 2020/6/2 äå9:05, Michael S. Tsirkin wrote:


[...]


+
+static int fetch_indirect_descs(struct vhost_virtqueue *vq,
+ struct vhost_desc *indirect,
+ u16 head)
+{
+ struct vring_desc desc;
+ unsigned int i = 0, count, found = 0;
+ u32 len = indirect->len;
+ struct iov_iter from;
+ int ret;
+
+ /* Sanity check */
+ if (unlikely(len % sizeof desc)) {
+ vq_err(vq, "Invalid length in indirect descriptor: "
+ "len 0x%llx not multiple of 0x%zx\n",
+ (unsigned long long)len,
+ sizeof desc);
+ return -EINVAL;
+ }
+
+ ret = translate_desc(vq, indirect->addr, len, vq->indirect,
+ UIO_MAXIOV, VHOST_ACCESS_RO);
+ if (unlikely(ret < 0)) {
+ if (ret != -EAGAIN)
+ vq_err(vq, "Translation failure %d in indirect.\n", ret);
+ return ret;
+ }
+ iov_iter_init(&from, READ, vq->indirect, ret, len);
+
+ /* We will use the result as an address to read from, so most
+ * architectures only need a compiler barrier here. */
+ read_barrier_depends();
+
+ count = len / sizeof desc;
+ /* Buffers are chained via a 16 bit next field, so
+ * we can have at most 2^16 of these. */
+ if (unlikely(count > USHRT_MAX + 1)) {
+ vq_err(vq, "Indirect buffer length too big: %d\n",
+ indirect->len);
+ return -E2BIG;
+ }
+ if (unlikely(vq->ndescs + count > vq->max_descs)) {
+ vq_err(vq, "Too many indirect + direct descs: %d + %d\n",
+ vq->ndescs, indirect->len);
+ return -E2BIG;
+ }
+
+ do {
+ if (unlikely(++found > count)) {
+ vq_err(vq, "Loop detected: last one at %u "
+ "indirect size %u\n",
+ i, count);
+ return -EINVAL;
+ }
+ if (unlikely(!copy_from_iter_full(&desc, sizeof(desc), &from))) {
+ vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
+ i, (size_t)indirect->addr + i * sizeof desc);
+ return -EINVAL;
+ }
+ if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
+ vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
+ i, (size_t)indirect->addr + i * sizeof desc);
+ return -EINVAL;
+ }
+
+ push_split_desc(vq, &desc, head);

The error is ignored.
See above:

if (unlikely(vq->ndescs + count > vq->max_descs))

So it can't fail here, we never fetch unless there's space.

I guess we can add a WARN_ON here.


Yes.



+ } while ((i = next_desc(vq, &desc)) != -1);
+ return 0;
+}
+
+static int fetch_descs(struct vhost_virtqueue *vq)
+{
+ unsigned int i, head, found = 0;
+ struct vhost_desc *last;
+ struct vring_desc desc;
+ __virtio16 avail_idx;
+ __virtio16 ring_head;
+ u16 last_avail_idx;
+ int ret;
+
+ /* Check it isn't doing very strange things with descriptor numbers. */
+ last_avail_idx = vq->last_avail_idx;
+
+ if (vq->avail_idx == vq->last_avail_idx) {
+ if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
+ vq_err(vq, "Failed to access avail idx at %p\n",
+ &vq->avail->idx);
+ return -EFAULT;
+ }
+ vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
+
+ if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
+ vq_err(vq, "Guest moved used index from %u to %u",
+ last_avail_idx, vq->avail_idx);
+ return -EFAULT;
+ }
+
+ /* If there's nothing new since last we looked, return
+ * invalid.
+ */
+ if (vq->avail_idx == last_avail_idx)
+ return vq->num;
+
+ /* Only get avail ring entries after they have been
+ * exposed by guest.
+ */
+ smp_rmb();
+ }
+
+ /* Grab the next descriptor number they're advertising */
+ if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) {
+ vq_err(vq, "Failed to read head: idx %d address %p\n",
+ last_avail_idx,
+ &vq->avail->ring[last_avail_idx % vq->num]);
+ return -EFAULT;
+ }
+
+ head = vhost16_to_cpu(vq, ring_head);
+
+ /* If their number is silly, that's an error. */
+ if (unlikely(head >= vq->num)) {
+ vq_err(vq, "Guest says index %u > %u is available",
+ head, vq->num);
+ return -EINVAL;
+ }
+
+ i = head;
+ do {
+ if (unlikely(i >= vq->num)) {
+ vq_err(vq, "Desc index is %u > %u, head = %u",
+ i, vq->num, head);
+ return -EINVAL;
+ }
+ if (unlikely(++found > vq->num)) {
+ vq_err(vq, "Loop detected: last one at %u "
+ "vq size %u head %u\n",
+ i, vq->num, head);
+ return -EINVAL;
+ }
+ ret = vhost_get_desc(vq, &desc, i);
+ if (unlikely(ret)) {
+ vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
+ i, vq->desc + i);
+ return -EFAULT;
+ }
+ ret = push_split_desc(vq, &desc, head);
+ if (unlikely(ret)) {
+ vq_err(vq, "Failed to save descriptor: idx %d\n", i);
+ return -EINVAL;
+ }
+ } while ((i = next_desc(vq, &desc)) != -1);
+
+ last = peek_split_desc(vq);
+ if (unlikely(last->flags & VRING_DESC_F_INDIRECT)) {
+ pop_split_desc(vq);
+ ret = fetch_indirect_descs(vq, last, head);

Note that this means we don't supported chained indirect descriptors which
complies the spec but we support this in vhost_get_vq_desc().
Well the spec says:
A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT and VIRTQ_DESC_F_NEXT in flags.

Did I miss anything?


No, but I meant current vhost_get_vq_desc() supports chained indirect descriptor. Not sure if there's an application that depends on this silently.

Thanks