+#define VHOST_ASYNC_BATCH_THRESHOLD 32
+
+static __rte_always_inline bool
+rxvq_is_mergeable(struct virtio_net *dev)
+{
+ return dev->features & (1ULL << VIRTIO_NET_F_MRG_RXBUF);
+}
+
+static __rte_always_inline bool
+virtio_net_is_inorder(struct virtio_net *dev)
+{
+ return dev->features & (1ULL << VIRTIO_F_IN_ORDER);
+}
+
+static bool
+is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t nr_vring)
+{
+ return (is_tx ^ (idx & 1)) == 0 && idx < nr_vring;
+}
+
+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];
+ }
+
+ rte_smp_wmb();
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ vq->desc_packed[vq->last_used_idx + i].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq, vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc) *
+ PACKED_BATCH_SIZE);
+ vhost_log_cache_sync(dev, vq);
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_batch_packed_inorder(struct vhost_virtqueue *vq,
+ uint16_t id)
+{
+ vq->shadow_used_packed[0].id = id;
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].flags =
+ PACKED_DESC_DEQUEUE_USED_FLAG(vq->used_wrap_counter);
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].count = 1;
+ vq->shadow_used_idx++;
+ }
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint16_t *ids)
+{
+ uint16_t flags;
+ uint16_t i;
+ uint16_t begin;
+
+ flags = PACKED_DESC_DEQUEUE_USED_FLAG(vq->used_wrap_counter);
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].id = ids[0];
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].count = 1;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ begin = 1;
+ } else
+ begin = 0;
+
+ vhost_for_each_try_unroll(i, begin, PACKED_BATCH_SIZE) {
+ vq->desc_packed[vq->last_used_idx + i].id = ids[i];
+ vq->desc_packed[vq->last_used_idx + i].len = 0;
+ }
+
+ rte_smp_wmb();
+ vhost_for_each_try_unroll(i, begin, PACKED_BATCH_SIZE)
+ vq->desc_packed[vq->last_used_idx + i].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq, vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc) *
+ PACKED_BATCH_SIZE);
+ vhost_log_cache_sync(dev, vq);
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_single_packed(struct vhost_virtqueue *vq,
+ uint16_t buf_id,
+ uint16_t count)
+{
+ uint16_t flags;
+
+ flags = vq->desc_packed[vq->last_used_idx].flags;
+ 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 (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+
+ vq->shadow_used_packed[0].id = buf_id;
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ } else {
+ vq->desc_packed[vq->last_used_idx].id = buf_id;
+ vq->desc_packed[vq->last_used_idx].len = 0;
+ vq->desc_packed[vq->last_used_idx].flags = flags;
+ }
+
+ vq_inc_last_used_packed(vq, count);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_single_packed_inorder(struct vhost_virtqueue *vq,
+ uint16_t buf_id,
+ uint16_t count)
+{
+ uint16_t flags;
+
+ vq->shadow_used_packed[0].id = buf_id;
+
+ flags = vq->desc_packed[vq->last_used_idx].flags;
+ 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 (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ }
+
+ vq_inc_last_used_packed(vq, count);
+}
+
+static __rte_always_inline void
+vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint32_t len[],
+ uint16_t id[],
+ uint16_t count[],
+ uint16_t num_buffers)
+{
+ uint16_t i;
+ for (i = 0; i < num_buffers; i++) {
+ /* enqueue shadow flush action aligned with batch num */
+ if (!vq->shadow_used_idx)
+ vq->shadow_aligned_idx = vq->last_used_idx &
+ PACKED_BATCH_MASK;
+ vq->shadow_used_packed[vq->shadow_used_idx].id = id[i];
+ vq->shadow_used_packed[vq->shadow_used_idx].len = len[i];
+ vq->shadow_used_packed[vq->shadow_used_idx].count = count[i];
+ vq->shadow_aligned_idx += count[i];
+ vq->shadow_used_idx++;
+ }
+
+ if (vq->shadow_aligned_idx >= PACKED_BATCH_SIZE) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+}
+
+/* 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
+virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
+{
+ uint64_t csum_l4 = m_buf->ol_flags & PKT_TX_L4_MASK;
+
+ if (m_buf->ol_flags & PKT_TX_TCP_SEG)
+ csum_l4 |= PKT_TX_TCP_CKSUM;
+
+ if (csum_l4) {
+ net_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ net_hdr->csum_start = m_buf->l2_len + m_buf->l3_len;
+
+ switch (csum_l4) {
+ case PKT_TX_TCP_CKSUM:
+ net_hdr->csum_offset = (offsetof(struct rte_tcp_hdr,
+ cksum));
+ break;
+ case PKT_TX_UDP_CKSUM:
+ net_hdr->csum_offset = (offsetof(struct rte_udp_hdr,
+ dgram_cksum));
+ break;
+ case PKT_TX_SCTP_CKSUM:
+ net_hdr->csum_offset = (offsetof(struct rte_sctp_hdr,
+ cksum));
+ break;
+ }
+ } else {
+ ASSIGN_UNLESS_EQUAL(net_hdr->csum_start, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->csum_offset, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->flags, 0);
+ }
+
+ /* IP cksum verification cannot be bypassed, then calculate here */
+ if (m_buf->ol_flags & PKT_TX_IP_CKSUM) {
+ struct rte_ipv4_hdr *ipv4_hdr;
+
+ ipv4_hdr = rte_pktmbuf_mtod_offset(m_buf, struct rte_ipv4_hdr *,
+ m_buf->l2_len);
+ ipv4_hdr->hdr_checksum = 0;
+ ipv4_hdr->hdr_checksum = rte_ipv4_cksum(ipv4_hdr);
+ }
+
+ if (m_buf->ol_flags & PKT_TX_TCP_SEG) {
+ if (m_buf->ol_flags & PKT_TX_IPV4)
+ net_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+ else
+ net_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ net_hdr->gso_size = m_buf->tso_segsz;
+ net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
+ + m_buf->l4_len;
+ } else if (m_buf->ol_flags & PKT_TX_UDP_SEG) {
+ net_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ net_hdr->gso_size = m_buf->tso_segsz;
+ net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len +
+ m_buf->l4_len;
+ } else {
+ ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->hdr_len, 0);
+ }
+}
+
+static __rte_always_inline int
+map_one_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct buf_vector *buf_vec, uint16_t *vec_idx,
+ uint64_t desc_iova, uint64_t desc_len, uint8_t perm)
+{
+ uint16_t vec_id = *vec_idx;
+
+ while (desc_len) {
+ uint64_t desc_addr;
+ uint64_t desc_chunck_len = desc_len;
+
+ if (unlikely(vec_id >= BUF_VECTOR_MAX))
+ return -1;
+
+ desc_addr = vhost_iova_to_vva(dev, vq,
+ desc_iova,
+ &desc_chunck_len,
+ perm);
+ if (unlikely(!desc_addr))
+ return -1;
+
+ rte_prefetch0((void *)(uintptr_t)desc_addr);
+
+ buf_vec[vec_id].buf_iova = desc_iova;
+ buf_vec[vec_id].buf_addr = desc_addr;
+ buf_vec[vec_id].buf_len = desc_chunck_len;
+
+ desc_len -= desc_chunck_len;
+ desc_iova += desc_chunck_len;
+ vec_id++;
+ }
+ *vec_idx = vec_id;
+
+ return 0;
+}
+
+static __rte_always_inline int
+fill_vec_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint32_t avail_idx, uint16_t *vec_idx,
+ struct buf_vector *buf_vec, uint16_t *desc_chain_head,
+ uint32_t *desc_chain_len, uint8_t perm)
+{
+ uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
+ uint16_t vec_id = *vec_idx;
+ uint32_t len = 0;
+ uint64_t dlen;
+ uint32_t nr_descs = vq->size;
+ uint32_t cnt = 0;
+ struct vring_desc *descs = vq->desc;
+ struct vring_desc *idesc = NULL;
+
+ if (unlikely(idx >= vq->size))
+ return -1;
+
+ *desc_chain_head = idx;
+
+ if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) {
+ dlen = vq->desc[idx].len;
+ nr_descs = dlen / sizeof(struct vring_desc);
+ if (unlikely(nr_descs > vq->size))
+ return -1;
+
+ descs = (struct vring_desc *)(uintptr_t)
+ vhost_iova_to_vva(dev, vq, vq->desc[idx].addr,
+ &dlen,
+ VHOST_ACCESS_RO);
+ if (unlikely(!descs))
+ return -1;
+
+ if (unlikely(dlen < vq->desc[idx].len)) {
+ /*
+ * The indirect desc table is not contiguous
+ * in process VA space, we have to copy it.
+ */
+ idesc = vhost_alloc_copy_ind_table(dev, vq,
+ vq->desc[idx].addr, vq->desc[idx].len);
+ if (unlikely(!idesc))
+ return -1;
+
+ descs = idesc;
+ }
+
+ idx = 0;
+ }
+
+ while (1) {
+ if (unlikely(idx >= nr_descs || cnt++ >= nr_descs)) {
+ free_ind_table(idesc);
+ return -1;
+ }
+
+ len += descs[idx].len;
+
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[idx].addr, descs[idx].len,
+ perm))) {
+ free_ind_table(idesc);
+ return -1;
+ }
+
+ if ((descs[idx].flags & VRING_DESC_F_NEXT) == 0)
+ break;
+
+ idx = descs[idx].next;
+ }
+
+ *desc_chain_len = len;
+ *vec_idx = vec_id;
+
+ if (unlikely(!!idesc))
+ free_ind_table(idesc);
+
+ return 0;
+}
+
+/*
+ * Returns -1 on fail, 0 on success
+ */
+static inline int
+reserve_avail_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint32_t size, struct buf_vector *buf_vec,
+ uint16_t *num_buffers, uint16_t avail_head,
+ uint16_t *nr_vec)
+{
+ uint16_t cur_idx;
+ uint16_t vec_idx = 0;
+ uint16_t max_tries, tries = 0;
+
+ uint16_t head_idx = 0;
+ uint32_t len = 0;
+
+ *num_buffers = 0;
+ cur_idx = vq->last_avail_idx;
+
+ if (rxvq_is_mergeable(dev))
+ max_tries = vq->size - 1;
+ else
+ max_tries = 1;
+
+ while (size > 0) {
+ if (unlikely(cur_idx == avail_head))
+ return -1;
+ /*
+ * if we tried all available ring items, and still
+ * can't get enough buf, it means something abnormal
+ * happened.
+ */
+ if (unlikely(++tries > max_tries))
+ return -1;
+
+ if (unlikely(fill_vec_buf_split(dev, vq, cur_idx,
+ &vec_idx, buf_vec,
+ &head_idx, &len,
+ VHOST_ACCESS_RW) < 0))
+ return -1;
+ len = RTE_MIN(len, size);
+ update_shadow_used_ring_split(vq, head_idx, len);
+ size -= len;
+
+ cur_idx++;
+ *num_buffers += 1;
+ }
+
+ *nr_vec = vec_idx;
+
+ return 0;
+}
+
+static __rte_always_inline int
+fill_vec_buf_packed_indirect(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct vring_packed_desc *desc, uint16_t *vec_idx,
+ struct buf_vector *buf_vec, uint32_t *len, uint8_t perm)
+{
+ uint16_t i;
+ uint32_t nr_descs;
+ uint16_t vec_id = *vec_idx;
+ uint64_t dlen;
+ struct vring_packed_desc *descs, *idescs = NULL;
+
+ dlen = desc->len;
+ descs = (struct vring_packed_desc *)(uintptr_t)
+ vhost_iova_to_vva(dev, vq, desc->addr, &dlen, VHOST_ACCESS_RO);
+ if (unlikely(!descs))
+ return -1;
+
+ if (unlikely(dlen < desc->len)) {
+ /*
+ * The indirect desc table is not contiguous
+ * in process VA space, we have to copy it.
+ */
+ idescs = vhost_alloc_copy_ind_table(dev,
+ vq, desc->addr, desc->len);
+ if (unlikely(!idescs))
+ return -1;
+
+ descs = idescs;
+ }
+
+ nr_descs = desc->len / sizeof(struct vring_packed_desc);
+ if (unlikely(nr_descs >= vq->size)) {
+ free_ind_table(idescs);
+ return -1;
+ }
+
+ for (i = 0; i < nr_descs; i++) {
+ if (unlikely(vec_id >= BUF_VECTOR_MAX)) {
+ free_ind_table(idescs);
+ return -1;
+ }
+
+ *len += descs[i].len;
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[i].addr, descs[i].len,
+ perm)))
+ return -1;
+ }
+ *vec_idx = vec_id;
+
+ if (unlikely(!!idescs))
+ free_ind_table(idescs);
+
+ return 0;
+}
+
+static __rte_always_inline int
+fill_vec_buf_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint16_t avail_idx, uint16_t *desc_count,
+ struct buf_vector *buf_vec, uint16_t *vec_idx,
+ uint16_t *buf_id, uint32_t *len, uint8_t perm)
+{
+ bool wrap_counter = vq->avail_wrap_counter;
+ struct vring_packed_desc *descs = vq->desc_packed;
+ uint16_t vec_id = *vec_idx;
+
+ if (avail_idx < vq->last_avail_idx)
+ wrap_counter ^= 1;
+
+ /*
+ * Perform a load-acquire barrier in desc_is_avail to
+ * enforce the ordering between desc flags and desc
+ * content.
+ */
+ if (unlikely(!desc_is_avail(&descs[avail_idx], wrap_counter)))
+ return -1;
+
+ *desc_count = 0;
+ *len = 0;
+
+ while (1) {
+ if (unlikely(vec_id >= BUF_VECTOR_MAX))
+ return -1;
+
+ if (unlikely(*desc_count >= vq->size))
+ return -1;
+
+ *desc_count += 1;
+ *buf_id = descs[avail_idx].id;
+
+ if (descs[avail_idx].flags & VRING_DESC_F_INDIRECT) {
+ if (unlikely(fill_vec_buf_packed_indirect(dev, vq,
+ &descs[avail_idx],
+ &vec_id, buf_vec,
+ len, perm) < 0))
+ return -1;
+ } else {
+ *len += descs[avail_idx].len;
+
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[avail_idx].addr,
+ descs[avail_idx].len,
+ perm)))
+ return -1;
+ }
+
+ if ((descs[avail_idx].flags & VRING_DESC_F_NEXT) == 0)
+ break;
+
+ if (++avail_idx >= vq->size) {
+ avail_idx -= vq->size;
+ wrap_counter ^= 1;
+ }
+ }
+
+ *vec_idx = vec_id;
+
+ return 0;
+}
+
+static __rte_noinline void
+copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct buf_vector *buf_vec,
+ struct virtio_net_hdr_mrg_rxbuf *hdr)
+{
+ uint64_t len;
+ uint64_t remain = dev->vhost_hlen;
+ uint64_t src = (uint64_t)(uintptr_t)hdr, dst;
+ uint64_t iova = buf_vec->buf_iova;
+
+ while (remain) {
+ len = RTE_MIN(remain,
+ buf_vec->buf_len);
+ dst = buf_vec->buf_addr;
+ rte_memcpy((void *)(uintptr_t)dst,
+ (void *)(uintptr_t)src,
+ len);
+
+ PRINT_PACKET(dev, (uintptr_t)dst,
+ (uint32_t)len, 0);
+ vhost_log_cache_write_iova(dev, vq,
+ iova, len);
+
+ remain -= len;
+ iova += len;
+ src += len;
+ buf_vec++;
+ }
+}
+
+static __rte_always_inline int
+copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mbuf *m, struct buf_vector *buf_vec,
+ uint16_t nr_vec, uint16_t num_buffers)
+{
+ uint32_t vec_idx = 0;
+ uint32_t mbuf_offset, mbuf_avail;
+ uint32_t buf_offset, buf_avail;
+ uint64_t buf_addr, buf_iova, buf_len;
+ uint32_t cpy_len;
+ uint64_t hdr_addr;
+ struct rte_mbuf *hdr_mbuf;
+ struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
+ struct virtio_net_hdr_mrg_rxbuf tmp_hdr, *hdr = NULL;
+ int error = 0;
+
+ if (unlikely(m == NULL)) {
+ error = -1;
+ goto out;
+ }
+
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+
+ if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
+ error = -1;
+ goto out;
+ }
+
+ hdr_mbuf = m;
+ hdr_addr = buf_addr;
+ if (unlikely(buf_len < dev->vhost_hlen))
+ hdr = &tmp_hdr;
+ else
+ hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)hdr_addr;
+
+ VHOST_LOG_DATA(DEBUG, "(%d) RX: num merge buffers %d\n",
+ dev->vid, num_buffers);
+
+ if (unlikely(buf_len < dev->vhost_hlen)) {
+ buf_offset = dev->vhost_hlen - buf_len;
+ vec_idx++;
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+ buf_avail = buf_len - buf_offset;
+ } else {
+ buf_offset = dev->vhost_hlen;
+ buf_avail = buf_len - dev->vhost_hlen;
+ }
+
+ mbuf_avail = rte_pktmbuf_data_len(m);
+ mbuf_offset = 0;
+ while (mbuf_avail != 0 || m->next != NULL) {
+ /* done with current buf, get the next one */
+ if (buf_avail == 0) {
+ vec_idx++;
+ if (unlikely(vec_idx >= nr_vec)) {
+ error = -1;
+ goto out;
+ }
+
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+
+ buf_offset = 0;
+ buf_avail = buf_len;
+ }
+
+ /* done with current mbuf, get the next one */
+ if (mbuf_avail == 0) {
+ m = m->next;
+
+ mbuf_offset = 0;
+ mbuf_avail = rte_pktmbuf_data_len(m);
+ }
+
+ if (hdr_addr) {
+ virtio_enqueue_offload(hdr_mbuf, &hdr->hdr);
+ if (rxvq_is_mergeable(dev))
+ ASSIGN_UNLESS_EQUAL(hdr->num_buffers,
+ num_buffers);
+
+ if (unlikely(hdr == &tmp_hdr)) {
+ copy_vnet_hdr_to_desc(dev, vq, buf_vec, hdr);
+ } else {
+ PRINT_PACKET(dev, (uintptr_t)hdr_addr,
+ dev->vhost_hlen, 0);
+ vhost_log_cache_write_iova(dev, vq,
+ buf_vec[0].buf_iova,
+ dev->vhost_hlen);
+ }
+
+ hdr_addr = 0;
+ }
+
+ cpy_len = RTE_MIN(buf_avail, mbuf_avail);
+
+ if (likely(cpy_len > MAX_BATCH_LEN ||
+ vq->batch_copy_nb_elems >= vq->size)) {
+ rte_memcpy((void *)((uintptr_t)(buf_addr + buf_offset)),
+ rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+ cpy_len);
+ vhost_log_cache_write_iova(dev, vq,
+ buf_iova + buf_offset,
+ cpy_len);
+ PRINT_PACKET(dev, (uintptr_t)(buf_addr + buf_offset),
+ cpy_len, 0);
+ } else {
+ batch_copy[vq->batch_copy_nb_elems].dst =
+ (void *)((uintptr_t)(buf_addr + buf_offset));
+ batch_copy[vq->batch_copy_nb_elems].src =
+ rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+ batch_copy[vq->batch_copy_nb_elems].log_addr =
+ buf_iova + buf_offset;
+ batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
+ vq->batch_copy_nb_elems++;
+ }
+
+ mbuf_avail -= cpy_len;
+ mbuf_offset += cpy_len;
+ buf_avail -= cpy_len;
+ buf_offset += cpy_len;
+ }
+
+out:
+
+ return error;
+}
+
+static __rte_always_inline void
+async_fill_vec(struct iovec *v, void *base, size_t len)