+static __rte_always_inline void
+flush_shadow_used_ring_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->last_used_idx += vq->shadow_used_packed[i].count;
+ if (vq->last_used_idx >= vq->size) {
+ vq->used_wrap_counter ^= 1;
+ vq->last_used_idx -= vq->size;
+ }
+ }
+
+ 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
+update_shadow_used_ring_packed(struct vhost_virtqueue *vq,
+ uint16_t desc_idx, uint32_t len, uint16_t count)
+{
+ uint16_t i = vq->shadow_used_idx++;
+
+ vq->shadow_used_packed[i].id = desc_idx;
+ vq->shadow_used_packed[i].len = len;
+ vq->shadow_used_packed[i].count = count;
+}
+
+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(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;
+}
+
+/* avoid write operation when necessary, to lessen cache issues */
+#define ASSIGN_UNLESS_EQUAL(var, val) do { \
+ if ((var) != (val)) \
+ (var) = (val); \
+} while (0)
+
+static __rte_always_inline void