+static inline uint32_t __attribute__((always_inline))
+copy_from_mbuf_to_vring(struct virtio_net *dev,
+ uint16_t res_base_idx, uint16_t res_end_idx,
+ struct rte_mbuf *pkt)
+{
+ uint32_t vec_idx = 0;
+ uint32_t entry_success = 0;
+ struct vhost_virtqueue *vq;
+ /* The virtio_hdr is initialised to 0. */
+ struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {
+ {0, 0, 0, 0, 0, 0}, 0};
+ uint16_t cur_idx = res_base_idx;
+ uint64_t vb_addr = 0;
+ uint64_t vb_hdr_addr = 0;
+ uint32_t seg_offset = 0;
+ uint32_t vb_offset = 0;
+ uint32_t seg_avail;
+ uint32_t vb_avail;
+ uint32_t cpy_len, entry_len;
+
+ if (pkt == NULL)
+ return 0;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| "
+ "End Index %d\n",
+ dev->device_fh, cur_idx, res_end_idx);
+
+ /*
+ * Convert from gpa to vva
+ * (guest physical addr -> vhost virtual addr)
+ */
+ vq = dev->virtqueue[VIRTIO_RXQ];
+ vb_addr =
+ gpa_to_vva(dev, vq->buf_vec[vec_idx].buf_addr);
+ vb_hdr_addr = vb_addr;
+
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+
+ virtio_hdr.num_buffers = res_end_idx - res_base_idx;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") RX: Num merge buffers %d\n",
+ dev->device_fh, virtio_hdr.num_buffers);
+
+ rte_memcpy((void *)(uintptr_t)vb_hdr_addr,
+ (const void *)&virtio_hdr, vq->vhost_hlen);
+
+ PRINT_PACKET(dev, (uintptr_t)vb_hdr_addr, vq->vhost_hlen, 1);
+
+ seg_avail = rte_pktmbuf_data_len(pkt);
+ vb_offset = vq->vhost_hlen;
+ vb_avail =
+ vq->buf_vec[vec_idx].buf_len - vq->vhost_hlen;
+
+ entry_len = vq->vhost_hlen;
+
+ if (vb_avail == 0) {
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vq->vhost_hlen;
+
+ if ((vq->desc[desc_idx].flags
+ & VRING_DESC_F_NEXT) == 0) {
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ }
+
+ vec_idx++;
+ vb_addr =
+ gpa_to_vva(dev, vq->buf_vec[vec_idx].buf_addr);
+
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+ vb_offset = 0;
+ vb_avail = vq->buf_vec[vec_idx].buf_len;
+ }
+
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+
+ while (cpy_len > 0) {
+ /* Copy mbuf data to vring buffer */
+ rte_memcpy((void *)(uintptr_t)(vb_addr + vb_offset),
+ (const void *)(rte_pktmbuf_mtod(pkt, char*) + seg_offset),
+ cpy_len);
+
+ PRINT_PACKET(dev,
+ (uintptr_t)(vb_addr + vb_offset),
+ cpy_len, 0);
+
+ seg_offset += cpy_len;
+ vb_offset += cpy_len;
+ seg_avail -= cpy_len;
+ vb_avail -= cpy_len;
+ entry_len += cpy_len;
+
+ if (seg_avail != 0) {
+ /*
+ * The virtio buffer in this vring
+ * entry reach to its end.
+ * But the segment doesn't complete.
+ */
+ if ((vq->desc[vq->buf_vec[vec_idx].desc_idx].flags &
+ VRING_DESC_F_NEXT) == 0) {
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ }
+
+ vec_idx++;
+ vb_addr = gpa_to_vva(dev,
+ vq->buf_vec[vec_idx].buf_addr);
+ vb_offset = 0;
+ vb_avail = vq->buf_vec[vec_idx].buf_len;
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ } else {
+ /*
+ * This current segment complete, need continue to
+ * check if the whole packet complete or not.
+ */
+ pkt = pkt->pkt.next;
+ if (pkt != NULL) {
+ /*
+ * There are more segments.
+ */
+ if (vb_avail == 0) {
+ /*
+ * This current buffer from vring is
+ * used up, need fetch next buffer
+ * from buf_vec.
+ */
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vb_offset;
+
+ if ((vq->desc[desc_idx].flags &
+ VRING_DESC_F_NEXT) == 0) {
+ uint16_t wrapped_idx =
+ cur_idx & (vq->size - 1);
+ /*
+ * Update used ring with the
+ * descriptor information
+ */
+ vq->used->ring[wrapped_idx].id
+ = desc_idx;
+ vq->used->ring[wrapped_idx].len
+ = entry_len;
+ entry_success++;
+ entry_len = 0;
+ cur_idx++;
+ }
+
+ /* Get next buffer from buf_vec. */
+ vec_idx++;
+ vb_addr = gpa_to_vva(dev,
+ vq->buf_vec[vec_idx].buf_addr);
+ vb_avail =
+ vq->buf_vec[vec_idx].buf_len;
+ vb_offset = 0;
+ }
+
+ seg_offset = 0;
+ seg_avail = rte_pktmbuf_data_len(pkt);
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ } else {
+ /*
+ * This whole packet completes.
+ */
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vb_offset;
+
+ while (vq->desc[desc_idx].flags &
+ VRING_DESC_F_NEXT) {
+ desc_idx = vq->desc[desc_idx].next;
+ vq->desc[desc_idx].len = 0;
+ }
+
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ seg_avail = 0;
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ }
+ }
+ }
+
+ return entry_success;
+}
+
+/*
+ * This function adds buffers to the virtio devices RX virtqueue. Buffers can
+ * be received from the physical port or from another virtio device. A packet
+ * count is returned to indicate the number of packets that were succesfully
+ * added to the RX queue. This function works for mergeable RX.
+ */
+static inline uint32_t __attribute__((always_inline))
+virtio_dev_merge_rx(struct virtio_net *dev, struct rte_mbuf **pkts,
+ uint32_t count)
+{
+ struct vhost_virtqueue *vq;
+ uint32_t pkt_idx = 0, entry_success = 0;
+ uint32_t retry = 0;
+ uint16_t avail_idx, res_cur_idx;
+ uint16_t res_base_idx, res_end_idx;
+ uint8_t success = 0;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_merge_rx()\n",
+ dev->device_fh);
+ vq = dev->virtqueue[VIRTIO_RXQ];
+ count = RTE_MIN((uint32_t)MAX_PKT_BURST, count);
+
+ if (count == 0)
+ return 0;
+
+ for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
+ uint32_t secure_len = 0;
+ uint16_t need_cnt;
+ uint32_t vec_idx = 0;
+ uint32_t pkt_len = pkts[pkt_idx]->pkt.pkt_len + vq->vhost_hlen;
+ uint16_t i, id;
+
+ do {
+ /*
+ * As many data cores may want access to available
+ * buffers, they need to be reserved.
+ */
+ res_base_idx = vq->last_used_idx_res;
+ res_cur_idx = res_base_idx;
+
+ do {
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+ if (unlikely(res_cur_idx == avail_idx)) {
+ /*
+ * If retry is enabled and the queue is
+ * full then we wait and retry to avoid
+ * packet loss.
+ */
+ if (enable_retry) {
+ uint8_t cont = 0;
+ for (retry = 0; retry < burst_rx_retry_num; retry++) {
+ rte_delay_us(burst_rx_delay_time);
+ avail_idx =
+ *((volatile uint16_t *)&vq->avail->idx);
+ if (likely(res_cur_idx != avail_idx)) {
+ cont = 1;
+ break;
+ }
+ }
+ if (cont == 1)
+ continue;
+ }
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") Failed "
+ "to get enough desc from "
+ "vring\n",
+ dev->device_fh);
+ return pkt_idx;
+ } else {
+ uint16_t wrapped_idx =
+ (res_cur_idx) & (vq->size - 1);
+ uint32_t idx =
+ vq->avail->ring[wrapped_idx];
+ uint8_t next_desc;
+
+ do {
+ next_desc = 0;
+ secure_len += vq->desc[idx].len;
+ if (vq->desc[idx].flags &
+ VRING_DESC_F_NEXT) {
+ idx = vq->desc[idx].next;
+ next_desc = 1;
+ }
+ } while (next_desc);
+
+ res_cur_idx++;
+ }
+ } while (pkt_len > secure_len);
+
+ /* vq->last_used_idx_res is atomically updated. */
+ success = rte_atomic16_cmpset(&vq->last_used_idx_res,
+ res_base_idx,
+ res_cur_idx);
+ } while (success == 0);
+
+ id = res_base_idx;
+ need_cnt = res_cur_idx - res_base_idx;
+
+ for (i = 0; i < need_cnt; i++, id++) {
+ uint16_t wrapped_idx = id & (vq->size - 1);
+ uint32_t idx = vq->avail->ring[wrapped_idx];
+ uint8_t next_desc;
+ do {
+ next_desc = 0;
+ vq->buf_vec[vec_idx].buf_addr =
+ vq->desc[idx].addr;
+ vq->buf_vec[vec_idx].buf_len =
+ vq->desc[idx].len;
+ vq->buf_vec[vec_idx].desc_idx = idx;
+ vec_idx++;
+
+ if (vq->desc[idx].flags & VRING_DESC_F_NEXT) {
+ idx = vq->desc[idx].next;
+ next_desc = 1;
+ }
+ } while (next_desc);
+ }
+
+ res_end_idx = res_cur_idx;
+
+ entry_success = copy_from_mbuf_to_vring(dev, res_base_idx,
+ res_end_idx, pkts[pkt_idx]);
+
+ rte_compiler_barrier();
+
+ /*
+ * Wait until it's our turn to add our buffer
+ * to the used ring.
+ */
+ while (unlikely(vq->last_used_idx != res_base_idx))
+ rte_pause();
+
+ *(volatile uint16_t *)&vq->used->idx += entry_success;
+ vq->last_used_idx = res_end_idx;
+
+ /* Kick the guest if necessary. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+ }
+
+ return count;
+}
+