+static inline void
+do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+ struct batch_copy_elem *elem = vq->batch_copy_elems;
+ uint16_t count = vq->batch_copy_nb_elems;
+ int i;
+
+ for (i = 0; i < count; i++) {
+ rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
+ vhost_log_cache_write_iova(dev, vq, elem[i].log_addr,
+ elem[i].len);
+ PRINT_PACKET(dev, (uintptr_t)elem[i].dst, elem[i].len, 0);
+ }
+
+ vq->batch_copy_nb_elems = 0;
+}
+
+static inline void
+do_data_copy_dequeue(struct vhost_virtqueue *vq)
+{
+ struct batch_copy_elem *elem = vq->batch_copy_elems;
+ uint16_t count = vq->batch_copy_nb_elems;
+ int i;
+
+ for (i = 0; i < count; i++)
+ rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
+
+ vq->batch_copy_nb_elems = 0;
+}
+
+static __rte_always_inline void
+do_flush_shadow_used_ring_split(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint16_t to, uint16_t from, uint16_t size)
+{
+ rte_memcpy(&vq->used->ring[to],
+ &vq->shadow_used_split[from],
+ size * sizeof(struct vring_used_elem));
+ vhost_log_cache_used_vring(dev, vq,
+ offsetof(struct vring_used, ring[to]),
+ size * sizeof(struct vring_used_elem));
+}
+
+static __rte_always_inline void
+flush_shadow_used_ring_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+ uint16_t used_idx = vq->last_used_idx & (vq->size - 1);
+
+ if (used_idx + vq->shadow_used_idx <= vq->size) {
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0,
+ vq->shadow_used_idx);
+ } else {
+ uint16_t size;
+
+ /* update used ring interval [used_idx, vq->size] */
+ size = vq->size - used_idx;
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0, size);
+
+ /* update the left half used ring interval [0, left_size] */
+ do_flush_shadow_used_ring_split(dev, vq, 0, size,
+ vq->shadow_used_idx - size);
+ }
+ vq->last_used_idx += vq->shadow_used_idx;
+
+ vhost_log_cache_sync(dev, vq);
+
+ __atomic_add_fetch(&vq->used->idx, vq->shadow_used_idx,
+ __ATOMIC_RELEASE);
+ vq->shadow_used_idx = 0;
+ vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
+ sizeof(vq->used->idx));
+}
+
+static __rte_always_inline void
+async_flush_shadow_used_ring_split(struct virtio_net *dev,
+ struct vhost_virtqueue *vq)
+{
+ uint16_t used_idx = vq->last_used_idx & (vq->size - 1);
+
+ if (used_idx + vq->shadow_used_idx <= vq->size) {
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0,
+ vq->shadow_used_idx);
+ } else {
+ uint16_t size;
+
+ /* update used ring interval [used_idx, vq->size] */
+ size = vq->size - used_idx;
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0, size);
+
+ /* update the left half used ring interval [0, left_size] */
+ do_flush_shadow_used_ring_split(dev, vq, 0, size,
+ vq->shadow_used_idx - size);
+ }
+
+ vq->last_used_idx += vq->shadow_used_idx;
+ vq->shadow_used_idx = 0;
+}
+
+static __rte_always_inline void
+update_shadow_used_ring_split(struct vhost_virtqueue *vq,
+ uint16_t desc_idx, uint32_t len)
+{
+ uint16_t i = vq->shadow_used_idx++;
+
+ vq->shadow_used_split[i].id = desc_idx;
+ vq->shadow_used_split[i].len = len;
+}
+
+static __rte_always_inline void
+vhost_flush_enqueue_shadow_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq)
+{
+ int i;
+ uint16_t used_idx = vq->last_used_idx;
+ uint16_t head_idx = vq->last_used_idx;
+ uint16_t head_flags = 0;
+
+ /* Split loop in two to save memory barriers */
+ for (i = 0; i < vq->shadow_used_idx; i++) {
+ vq->desc_packed[used_idx].id = vq->shadow_used_packed[i].id;
+ vq->desc_packed[used_idx].len = vq->shadow_used_packed[i].len;
+
+ used_idx += vq->shadow_used_packed[i].count;
+ if (used_idx >= vq->size)
+ used_idx -= vq->size;
+ }
+
+ rte_smp_wmb();
+
+ for (i = 0; i < vq->shadow_used_idx; i++) {
+ uint16_t flags;
+
+ if (vq->shadow_used_packed[i].len)
+ flags = VRING_DESC_F_WRITE;
+ else
+ flags = 0;
+
+ if (vq->used_wrap_counter) {
+ flags |= VRING_DESC_F_USED;
+ flags |= VRING_DESC_F_AVAIL;
+ } else {
+ flags &= ~VRING_DESC_F_USED;
+ flags &= ~VRING_DESC_F_AVAIL;
+ }
+
+ if (i > 0) {
+ vq->desc_packed[vq->last_used_idx].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq,
+ vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+ } else {
+ head_idx = vq->last_used_idx;
+ head_flags = flags;
+ }
+
+ vq_inc_last_used_packed(vq, vq->shadow_used_packed[i].count);
+ }
+
+ vq->desc_packed[head_idx].flags = head_flags;
+
+ vhost_log_cache_used_vring(dev, vq,
+ head_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+
+ vq->shadow_used_idx = 0;
+ vhost_log_cache_sync(dev, vq);
+}
+
+static __rte_always_inline void
+vhost_flush_dequeue_shadow_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq)
+{
+ struct vring_used_elem_packed *used_elem = &vq->shadow_used_packed[0];
+
+ vq->desc_packed[vq->shadow_last_used_idx].id = used_elem->id;
+ /* desc flags is the synchronization point for virtio packed vring */
+ __atomic_store_n(&vq->desc_packed[vq->shadow_last_used_idx].flags,
+ used_elem->flags, __ATOMIC_RELEASE);
+
+ vhost_log_cache_used_vring(dev, vq, vq->shadow_last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+ vq->shadow_used_idx = 0;
+ vhost_log_cache_sync(dev, vq);
+}
+
+static __rte_always_inline void
+vhost_flush_enqueue_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint64_t *lens,
+ uint16_t *ids)
+{
+ uint16_t i;
+ uint16_t flags;
+
+ if (vq->shadow_used_idx) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+
+ flags = PACKED_DESC_ENQUEUE_USED_FLAG(vq->used_wrap_counter);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ vq->desc_packed[vq->last_used_idx + i].id = ids[i];
+ vq->desc_packed[vq->last_used_idx + i].len = lens[i];
+ }