[Patch v6 15/18] net/mana: add function to send packets

[Long Li]

> Subject: Re: [Patch v6 15/18] net/mana: add function to send packets
> 
> On 2022/8/31 6:51, longli at linuxonhyperv.com wrote:
> > From: Long Li <longli at microsoft.com>
> >
> > With all the TX queues created, MANA can send packets over those queues.
> >
> > Signed-off-by: Long Li <longli at microsoft.com>
> 
> ...
> 
> >  }
> > +
> > +uint16_t mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts,
> > +		       uint16_t nb_pkts)
> > +{
> > +	struct mana_txq *txq = dpdk_txq;
> > +	struct mana_priv *priv = txq->priv;
> > +	struct gdma_comp comp;
> > +	int ret;
> > +	void *db_page;
> > +
> > +	/* Process send completions from GDMA */
> > +	while (gdma_poll_completion_queue(&txq->gdma_cq, &comp) == 1) {
> > +		struct mana_txq_desc *desc =
> > +			&txq->desc_ring[txq->desc_ring_tail];
> > +		struct mana_tx_comp_oob *oob =
> > +			(struct mana_tx_comp_oob
> *)&comp.completion_data[0];
> > +
> > +		if (oob->cqe_hdr.cqe_type != CQE_TX_OKAY) {
> > +			DRV_LOG(ERR,
> > +				"mana_tx_comp_oob cqe_type %u
> vendor_err %u",
> > +				oob->cqe_hdr.cqe_type, oob-
> >cqe_hdr.vendor_err);
> > +			txq->stats.errors++;
> > +		} else {
> > +			DRV_LOG(DEBUG, "mana_tx_comp_oob
> CQE_TX_OKAY");
> > +			txq->stats.packets++;
> > +		}
> > +
> > +		if (!desc->pkt) {
> > +			DRV_LOG(ERR, "mana_txq_desc has a NULL pkt");
> > +		} else {
> > +			txq->stats.bytes += desc->pkt->data_len;
> > +			rte_pktmbuf_free(desc->pkt);
> > +		}
> > +
> > +		desc->pkt = NULL;
> > +		txq->desc_ring_tail = (txq->desc_ring_tail + 1) % txq->num_desc;
> > +		txq->gdma_sq.tail += desc->wqe_size_in_bu;
> > +	}
> > +
> > +	/* Post send requests to GDMA */
> > +	uint16_t pkt_idx;
> > +
> > +	for (pkt_idx = 0; pkt_idx < nb_pkts; pkt_idx++) {
> > +		struct rte_mbuf *m_pkt = tx_pkts[pkt_idx];
> > +		struct rte_mbuf *m_seg = m_pkt;
> > +		struct transmit_oob_v2 tx_oob = {0};
> > +		struct one_sgl sgl = {0};
> > +
> > +		/* Drop the packet if it exceeds max segments */
> > +		if (m_pkt->nb_segs > priv->max_send_sge) {
> > +			DRV_LOG(ERR, "send packet segments %d exceeding
> max",
> > +				m_pkt->nb_segs);
> 
> This branch violate rte_eth_tx_burst definition, which defined the return value is
> " *   The maximum number of packets to transmit."

Will fix this.

> 
> Also I notice the driver didn't implement tx-prepare, which could hold such
> checking in framework's definition.
> 
> > +			continue;
> > +		}
> > +
> > +		/* Fill in the oob */
> > +		tx_oob.short_oob.packet_format = short_packet_format;
> > +		tx_oob.short_oob.tx_is_outer_ipv4 =
> > +			m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4 ? 1 : 0;
> > +		tx_oob.short_oob.tx_is_outer_ipv6 =
> > +			m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6 ? 1 : 0;
> > +
> > +		tx_oob.short_oob.tx_compute_IP_header_checksum =
> > +			m_pkt->ol_flags & RTE_MBUF_F_TX_IP_CKSUM ? 1 : 0;
> > +
> > +		if ((m_pkt->ol_flags & RTE_MBUF_F_TX_L4_MASK) ==
> > +				RTE_MBUF_F_TX_TCP_CKSUM) {
> > +			struct rte_tcp_hdr *tcp_hdr;
> > +
> > +			/* HW needs partial TCP checksum */
> > +
> > +			tcp_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +					  struct rte_tcp_hdr *,
> > +					  m_pkt->l2_len + m_pkt->l3_len);
> > +
> > +			if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4) {
> > +				struct rte_ipv4_hdr *ip_hdr;
> > +
> > +				ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +						struct rte_ipv4_hdr *,
> > +						m_pkt->l2_len);
> > +				tcp_hdr->cksum = rte_ipv4_phdr_cksum(ip_hdr,
> > +							m_pkt->ol_flags);
> > +
> > +			} else if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6) {
> > +				struct rte_ipv6_hdr *ip_hdr;
> > +
> > +				ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +						struct rte_ipv6_hdr *,
> > +						m_pkt->l2_len);
> > +				tcp_hdr->cksum = rte_ipv6_phdr_cksum(ip_hdr,
> > +							m_pkt->ol_flags);
> > +			} else {
> > +				DRV_LOG(ERR, "Invalid input for TCP CKSUM");
> > +			}
> > +
> > +			tx_oob.short_oob.tx_compute_TCP_checksum = 1;
> > +			tx_oob.short_oob.tx_transport_header_offset =
> > +				m_pkt->l2_len + m_pkt->l3_len;
> > +		}
> > +
> > +		if ((m_pkt->ol_flags & RTE_MBUF_F_TX_L4_MASK) ==
> > +				RTE_MBUF_F_TX_UDP_CKSUM) {
> > +			struct rte_udp_hdr *udp_hdr;
> > +
> > +			/* HW needs partial UDP checksum */
> > +			udp_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +					struct rte_udp_hdr *,
> > +					m_pkt->l2_len + m_pkt->l3_len);
> > +
> > +			if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4) {
> > +				struct rte_ipv4_hdr *ip_hdr;
> > +
> > +				ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +						struct rte_ipv4_hdr *,
> > +						m_pkt->l2_len);
> > +
> > +				udp_hdr->dgram_cksum =
> > +					rte_ipv4_phdr_cksum(ip_hdr,
> > +							    m_pkt->ol_flags);
> > +
> > +			} else if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6) {
> > +				struct rte_ipv6_hdr *ip_hdr;
> > +
> > +				ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
> > +						struct rte_ipv6_hdr *,
> > +						m_pkt->l2_len);
> > +
> > +				udp_hdr->dgram_cksum =
> > +					rte_ipv6_phdr_cksum(ip_hdr,
> > +							    m_pkt->ol_flags);
> > +
> > +			} else {
> > +				DRV_LOG(ERR, "Invalid input for UDP CKSUM");
> > +			}
> > +
> > +			tx_oob.short_oob.tx_compute_UDP_checksum = 1;
> > +		}
> 
> Why not have TSO process, which was reported support in dev_info_get ?

TSO is currently not implemented. I'm changing BNIC_DEV_TX_OFFLOAD_SUPPORT to fix this.

> 
> > +
> > +		tx_oob.short_oob.suppress_tx_CQE_generation = 0;
> > +		tx_oob.short_oob.VCQ_number = txq->gdma_cq.id;
> > +
> > +		tx_oob.short_oob.VSQ_frame_num =
> > +			get_vsq_frame_num(txq->gdma_sq.id);
> > +		tx_oob.short_oob.short_vport_offset = txq->tx_vp_offset;
> > +
> > +		DRV_LOG(DEBUG, "tx_oob packet_format %u ipv4 %u ipv6 %u",
> > +			tx_oob.short_oob.packet_format,
> > +			tx_oob.short_oob.tx_is_outer_ipv4,
> > +			tx_oob.short_oob.tx_is_outer_ipv6);
> > +
> > +		DRV_LOG(DEBUG, "tx_oob checksum ip %u tcp %u udp %u
> offset %u",
> > +			tx_oob.short_oob.tx_compute_IP_header_checksum,
> > +			tx_oob.short_oob.tx_compute_TCP_checksum,
> > +			tx_oob.short_oob.tx_compute_UDP_checksum,
> > +			tx_oob.short_oob.tx_transport_header_offset);
> > +
> > +		DRV_LOG(DEBUG, "pkt[%d]: buf_addr 0x%p, nb_segs %d,
> pkt_len %d",
> > +			pkt_idx, m_pkt->buf_addr, m_pkt->nb_segs,
> > +			m_pkt->pkt_len);
> > +
> > +		/* Create SGL for packet data buffers */
> > +		for (uint16_t seg_idx = 0; seg_idx < m_pkt->nb_segs; seg_idx++)
> {
> > +			struct mana_mr_cache *mr =
> > +				mana_find_pmd_mr(&txq->mr_btree, priv,
> m_seg);
> > +
> > +			if (!mr) {
> > +				DRV_LOG(ERR, "failed to get MR, pkt_idx %u",
> > +					pkt_idx);
> > +				return pkt_idx;
> > +			}
> > +
> > +			sgl.gdma_sgl[seg_idx].address =
> > +				rte_cpu_to_le_64(rte_pktmbuf_mtod(m_seg,
> > +								  uint64_t));
> > +			sgl.gdma_sgl[seg_idx].size = m_seg->data_len;
> > +			sgl.gdma_sgl[seg_idx].memory_key = mr->lkey;
> > +
> > +			DRV_LOG(DEBUG,
> > +				"seg idx %u addr 0x%" PRIx64 " size %x key %x",
> > +				seg_idx, sgl.gdma_sgl[seg_idx].address,
> > +				sgl.gdma_sgl[seg_idx].size,
> > +				sgl.gdma_sgl[seg_idx].memory_key);
> > +
> > +			m_seg = m_seg->next;
> > +		}
> > +
> > +		struct gdma_work_request work_req = {0};
> > +		struct gdma_posted_wqe_info wqe_info = {0};
> > +
> > +		work_req.gdma_header.struct_size = sizeof(work_req);
> > +		wqe_info.gdma_header.struct_size = sizeof(wqe_info);
> > +
> > +		work_req.sgl = sgl.gdma_sgl;
> > +		work_req.num_sgl_elements = m_pkt->nb_segs;
> > +		work_req.inline_oob_size_in_bytes =
> > +			sizeof(struct transmit_short_oob_v2);
> > +		work_req.inline_oob_data = &tx_oob;
> > +		work_req.flags = 0;
> > +		work_req.client_data_unit = NOT_USING_CLIENT_DATA_UNIT;
> > +
> > +		ret = gdma_post_work_request(&txq->gdma_sq, &work_req,
> > +					     &wqe_info);
> > +		if (!ret) {
> > +			struct mana_txq_desc *desc =
> > +				&txq->desc_ring[txq->desc_ring_head];
> > +
> > +			/* Update queue for tracking pending requests */
> > +			desc->pkt = m_pkt;
> > +			desc->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
> > +			txq->desc_ring_head =
> > +				(txq->desc_ring_head + 1) % txq->num_desc;
> > +
> > +			DRV_LOG(DEBUG, "nb_pkts %u pkt[%d] sent",
> > +				nb_pkts, pkt_idx);
> > +		} else {
> > +			DRV_LOG(INFO, "pkt[%d] failed to post send ret %d",
> > +				pkt_idx, ret);
> > +			break;
> > +		}
> > +	}
> > +
> > +	/* Ring hardware door bell */
> > +	db_page = priv->db_page;
> > +	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
> > +		struct rte_eth_dev *dev =
> > +			&rte_eth_devices[priv->dev_data->port_id];
> > +		struct mana_process_priv *process_priv = dev->process_private;
> > +
> > +		db_page = process_priv->db_page;
> > +	}
> > +
> > +	ret = mana_ring_doorbell(db_page, gdma_queue_send,
> > +				 txq->gdma_sq.id,
> > +				 txq->gdma_sq.head *
> > +					GDMA_WQE_ALIGNMENT_UNIT_SIZE);
> > +	if (ret)
> > +		DRV_LOG(ERR, "mana_ring_doorbell failed ret %d", ret);
> > +
> > +	return pkt_idx;
> > +}
> >