+ rxq = dev->data->rx_queues[queue_id];
+
+ qinfo->mp = rxq->mp;
+ qinfo->scattered_rx = dev->data->scattered_rx;
+ qinfo->nb_desc = rxq->nb_rx_desc;
+
+ qinfo->conf.rx_free_thresh = rxq->rx_free_thresh;
+ qinfo->conf.rx_drop_en = rxq->drop_en;
+ qinfo->conf.rx_deferred_start = rxq->rx_deferred_start;
+}
+
+void
+ice_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+ struct rte_eth_txq_info *qinfo)
+{
+ struct ice_tx_queue *txq;
+
+ txq = dev->data->tx_queues[queue_id];
+
+ qinfo->nb_desc = txq->nb_tx_desc;
+
+ qinfo->conf.tx_thresh.pthresh = txq->pthresh;
+ qinfo->conf.tx_thresh.hthresh = txq->hthresh;
+ qinfo->conf.tx_thresh.wthresh = txq->wthresh;
+
+ qinfo->conf.tx_free_thresh = txq->tx_free_thresh;
+ qinfo->conf.tx_rs_thresh = txq->tx_rs_thresh;
+ qinfo->conf.offloads = txq->offloads;
+ qinfo->conf.tx_deferred_start = txq->tx_deferred_start;
+}
+
+uint32_t
+ice_rx_queue_count(struct rte_eth_dev *dev, uint16_t rx_queue_id)
+{
+#define ICE_RXQ_SCAN_INTERVAL 4
+ volatile union ice_rx_flex_desc *rxdp;
+ struct ice_rx_queue *rxq;
+ uint16_t desc = 0;
+
+ rxq = dev->data->rx_queues[rx_queue_id];
+ rxdp = &rxq->rx_ring[rxq->rx_tail];
+ while ((desc < rxq->nb_rx_desc) &&
+ rte_le_to_cpu_16(rxdp->wb.status_error0) &
+ (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S)) {
+ /**
+ * Check the DD bit of a rx descriptor of each 4 in a group,
+ * to avoid checking too frequently and downgrading performance
+ * too much.
+ */
+ desc += ICE_RXQ_SCAN_INTERVAL;
+ rxdp += ICE_RXQ_SCAN_INTERVAL;
+ if (rxq->rx_tail + desc >= rxq->nb_rx_desc)
+ rxdp = &(rxq->rx_ring[rxq->rx_tail +
+ desc - rxq->nb_rx_desc]);
+ }
+
+ return desc;
+}
+
+#define ICE_RX_FLEX_ERR0_BITS \
+ ((1 << ICE_RX_FLEX_DESC_STATUS0_HBO_S) | \
+ (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) | \
+ (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S) | \
+ (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S) | \
+ (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S) | \
+ (1 << ICE_RX_FLEX_DESC_STATUS0_RXE_S))
+
+/* Rx L3/L4 checksum */
+static inline uint64_t
+ice_rxd_error_to_pkt_flags(uint16_t stat_err0)
+{
+ uint64_t flags = 0;
+
+ /* check if HW has decoded the packet and checksum */
+ if (unlikely(!(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))))
+ return 0;
+
+ if (likely(!(stat_err0 & ICE_RX_FLEX_ERR0_BITS))) {
+ flags |= (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD);
+ return flags;
+ }
+
+ if (unlikely(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S)))
+ flags |= PKT_RX_IP_CKSUM_BAD;
+ else
+ flags |= PKT_RX_IP_CKSUM_GOOD;
+
+ if (unlikely(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S)))
+ flags |= PKT_RX_L4_CKSUM_BAD;
+ else
+ flags |= PKT_RX_L4_CKSUM_GOOD;
+
+ if (unlikely(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))
+ flags |= PKT_RX_OUTER_IP_CKSUM_BAD;
+
+ if (unlikely(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S)))
+ flags |= PKT_RX_OUTER_L4_CKSUM_BAD;
+ else
+ flags |= PKT_RX_OUTER_L4_CKSUM_GOOD;
+
+ return flags;
+}
+
+static inline void
+ice_rxd_to_vlan_tci(struct rte_mbuf *mb, volatile union ice_rx_flex_desc *rxdp)
+{
+ if (rte_le_to_cpu_16(rxdp->wb.status_error0) &
+ (1 << ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S)) {
+ mb->ol_flags |= PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED;
+ mb->vlan_tci =
+ rte_le_to_cpu_16(rxdp->wb.l2tag1);
+ PMD_RX_LOG(DEBUG, "Descriptor l2tag1: %u",
+ rte_le_to_cpu_16(rxdp->wb.l2tag1));
+ } else {
+ mb->vlan_tci = 0;
+ }
+
+#ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
+ if (rte_le_to_cpu_16(rxdp->wb.status_error1) &
+ (1 << ICE_RX_FLEX_DESC_STATUS1_L2TAG2P_S)) {
+ mb->ol_flags |= PKT_RX_QINQ_STRIPPED | PKT_RX_QINQ |
+ PKT_RX_VLAN_STRIPPED | PKT_RX_VLAN;
+ mb->vlan_tci_outer = mb->vlan_tci;
+ mb->vlan_tci = rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd);
+ PMD_RX_LOG(DEBUG, "Descriptor l2tag2_1: %u, l2tag2_2: %u",
+ rte_le_to_cpu_16(rxdp->wb.l2tag2_1st),
+ rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd));
+ } else {
+ mb->vlan_tci_outer = 0;
+ }
+#endif
+ PMD_RX_LOG(DEBUG, "Mbuf vlan_tci: %u, vlan_tci_outer: %u",
+ mb->vlan_tci, mb->vlan_tci_outer);
+}
+
+#define ICE_LOOK_AHEAD 8
+#if (ICE_LOOK_AHEAD != 8)
+#error "PMD ICE: ICE_LOOK_AHEAD must be 8\n"
+#endif
+static inline int
+ice_rx_scan_hw_ring(struct ice_rx_queue *rxq)
+{
+ volatile union ice_rx_flex_desc *rxdp;
+ struct ice_rx_entry *rxep;
+ struct rte_mbuf *mb;
+ uint16_t stat_err0;
+ uint16_t pkt_len;
+ int32_t s[ICE_LOOK_AHEAD], nb_dd;
+ int32_t i, j, nb_rx = 0;
+ uint64_t pkt_flags = 0;
+ uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
+
+ rxdp = &rxq->rx_ring[rxq->rx_tail];
+ rxep = &rxq->sw_ring[rxq->rx_tail];
+
+ stat_err0 = rte_le_to_cpu_16(rxdp->wb.status_error0);
+
+ /* Make sure there is at least 1 packet to receive */
+ if (!(stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S)))
+ return 0;
+
+ /**
+ * Scan LOOK_AHEAD descriptors at a time to determine which
+ * descriptors reference packets that are ready to be received.
+ */
+ for (i = 0; i < ICE_RX_MAX_BURST; i += ICE_LOOK_AHEAD,
+ rxdp += ICE_LOOK_AHEAD, rxep += ICE_LOOK_AHEAD) {
+ /* Read desc statuses backwards to avoid race condition */
+ for (j = ICE_LOOK_AHEAD - 1; j >= 0; j--)
+ s[j] = rte_le_to_cpu_16(rxdp[j].wb.status_error0);
+
+ rte_smp_rmb();
+
+ /* Compute how many status bits were set */
+ for (j = 0, nb_dd = 0; j < ICE_LOOK_AHEAD; j++)
+ nb_dd += s[j] & (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S);
+
+ nb_rx += nb_dd;
+
+ /* Translate descriptor info to mbuf parameters */
+ for (j = 0; j < nb_dd; j++) {
+ mb = rxep[j].mbuf;
+ pkt_len = (rte_le_to_cpu_16(rxdp[j].wb.pkt_len) &
+ ICE_RX_FLX_DESC_PKT_LEN_M) - rxq->crc_len;
+ mb->data_len = pkt_len;
+ mb->pkt_len = pkt_len;
+ mb->ol_flags = 0;
+ stat_err0 = rte_le_to_cpu_16(rxdp[j].wb.status_error0);
+ pkt_flags = ice_rxd_error_to_pkt_flags(stat_err0);
+ mb->packet_type = ptype_tbl[ICE_RX_FLEX_DESC_PTYPE_M &
+ rte_le_to_cpu_16(rxdp[j].wb.ptype_flex_flags0)];
+ ice_rxd_to_vlan_tci(mb, &rxdp[j]);
+ rxq->rxd_to_pkt_fields(rxq, mb, &rxdp[j]);
+
+ mb->ol_flags |= pkt_flags;
+ }
+
+ for (j = 0; j < ICE_LOOK_AHEAD; j++)
+ rxq->rx_stage[i + j] = rxep[j].mbuf;
+
+ if (nb_dd != ICE_LOOK_AHEAD)
+ break;
+ }
+
+ /* Clear software ring entries */
+ for (i = 0; i < nb_rx; i++)
+ rxq->sw_ring[rxq->rx_tail + i].mbuf = NULL;
+
+ PMD_RX_LOG(DEBUG, "ice_rx_scan_hw_ring: "
+ "port_id=%u, queue_id=%u, nb_rx=%d",
+ rxq->port_id, rxq->queue_id, nb_rx);
+
+ return nb_rx;
+}
+
+static inline uint16_t
+ice_rx_fill_from_stage(struct ice_rx_queue *rxq,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t i;
+ struct rte_mbuf **stage = &rxq->rx_stage[rxq->rx_next_avail];
+
+ nb_pkts = (uint16_t)RTE_MIN(nb_pkts, rxq->rx_nb_avail);
+
+ for (i = 0; i < nb_pkts; i++)
+ rx_pkts[i] = stage[i];
+
+ rxq->rx_nb_avail = (uint16_t)(rxq->rx_nb_avail - nb_pkts);
+ rxq->rx_next_avail = (uint16_t)(rxq->rx_next_avail + nb_pkts);
+
+ return nb_pkts;
+}
+
+static inline int
+ice_rx_alloc_bufs(struct ice_rx_queue *rxq)
+{
+ volatile union ice_rx_flex_desc *rxdp;
+ struct ice_rx_entry *rxep;
+ struct rte_mbuf *mb;
+ uint16_t alloc_idx, i;
+ uint64_t dma_addr;
+ int diag;
+
+ /* Allocate buffers in bulk */
+ alloc_idx = (uint16_t)(rxq->rx_free_trigger -
+ (rxq->rx_free_thresh - 1));
+ rxep = &rxq->sw_ring[alloc_idx];
+ diag = rte_mempool_get_bulk(rxq->mp, (void *)rxep,
+ rxq->rx_free_thresh);
+ if (unlikely(diag != 0)) {
+ PMD_RX_LOG(ERR, "Failed to get mbufs in bulk");
+ return -ENOMEM;
+ }
+
+ rxdp = &rxq->rx_ring[alloc_idx];
+ for (i = 0; i < rxq->rx_free_thresh; i++) {
+ if (likely(i < (rxq->rx_free_thresh - 1)))
+ /* Prefetch next mbuf */
+ rte_prefetch0(rxep[i + 1].mbuf);
+
+ mb = rxep[i].mbuf;
+ rte_mbuf_refcnt_set(mb, 1);
+ mb->next = NULL;
+ mb->data_off = RTE_PKTMBUF_HEADROOM;
+ mb->nb_segs = 1;
+ mb->port = rxq->port_id;
+ dma_addr = rte_cpu_to_le_64(rte_mbuf_data_iova_default(mb));
+ rxdp[i].read.hdr_addr = 0;
+ rxdp[i].read.pkt_addr = dma_addr;
+ }
+
+ /* Update rx tail regsiter */
+ ICE_PCI_REG_WRITE(rxq->qrx_tail, rxq->rx_free_trigger);
+
+ rxq->rx_free_trigger =
+ (uint16_t)(rxq->rx_free_trigger + rxq->rx_free_thresh);
+ if (rxq->rx_free_trigger >= rxq->nb_rx_desc)
+ rxq->rx_free_trigger = (uint16_t)(rxq->rx_free_thresh - 1);
+
+ return 0;
+}
+
+static inline uint16_t
+rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+ struct ice_rx_queue *rxq = (struct ice_rx_queue *)rx_queue;
+ uint16_t nb_rx = 0;
+
+ if (!nb_pkts)
+ return 0;
+
+ if (rxq->rx_nb_avail)
+ return ice_rx_fill_from_stage(rxq, rx_pkts, nb_pkts);
+
+ nb_rx = (uint16_t)ice_rx_scan_hw_ring(rxq);
+ rxq->rx_next_avail = 0;
+ rxq->rx_nb_avail = nb_rx;
+ rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_rx);
+
+ if (rxq->rx_tail > rxq->rx_free_trigger) {
+ if (ice_rx_alloc_bufs(rxq) != 0) {
+ uint16_t i, j;
+
+ rxq->vsi->adapter->pf.dev_data->rx_mbuf_alloc_failed +=
+ rxq->rx_free_thresh;
+ PMD_RX_LOG(DEBUG, "Rx mbuf alloc failed for "
+ "port_id=%u, queue_id=%u",
+ rxq->port_id, rxq->queue_id);
+ rxq->rx_nb_avail = 0;
+ rxq->rx_tail = (uint16_t)(rxq->rx_tail - nb_rx);
+ for (i = 0, j = rxq->rx_tail; i < nb_rx; i++, j++)
+ rxq->sw_ring[j].mbuf = rxq->rx_stage[i];
+
+ return 0;
+ }
+ }
+
+ if (rxq->rx_tail >= rxq->nb_rx_desc)
+ rxq->rx_tail = 0;
+
+ if (rxq->rx_nb_avail)
+ return ice_rx_fill_from_stage(rxq, rx_pkts, nb_pkts);
+
+ return 0;
+}
+
+static uint16_t
+ice_recv_pkts_bulk_alloc(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t nb_rx = 0;
+ uint16_t n;
+ uint16_t count;
+
+ if (unlikely(nb_pkts == 0))
+ return nb_rx;
+
+ if (likely(nb_pkts <= ICE_RX_MAX_BURST))
+ return rx_recv_pkts(rx_queue, rx_pkts, nb_pkts);
+
+ while (nb_pkts) {
+ n = RTE_MIN(nb_pkts, ICE_RX_MAX_BURST);
+ count = rx_recv_pkts(rx_queue, &rx_pkts[nb_rx], n);
+ nb_rx = (uint16_t)(nb_rx + count);
+ nb_pkts = (uint16_t)(nb_pkts - count);
+ if (count < n)
+ break;
+ }
+
+ return nb_rx;
+}
+
+static uint16_t
+ice_recv_scattered_pkts(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ struct ice_rx_queue *rxq = rx_queue;
+ volatile union ice_rx_flex_desc *rx_ring = rxq->rx_ring;
+ volatile union ice_rx_flex_desc *rxdp;
+ union ice_rx_flex_desc rxd;
+ struct ice_rx_entry *sw_ring = rxq->sw_ring;
+ struct ice_rx_entry *rxe;
+ struct rte_mbuf *first_seg = rxq->pkt_first_seg;
+ struct rte_mbuf *last_seg = rxq->pkt_last_seg;
+ struct rte_mbuf *nmb; /* new allocated mbuf */
+ struct rte_mbuf *rxm; /* pointer to store old mbuf in SW ring */
+ uint16_t rx_id = rxq->rx_tail;
+ uint16_t nb_rx = 0;
+ uint16_t nb_hold = 0;
+ uint16_t rx_packet_len;
+ uint16_t rx_stat_err0;
+ uint64_t dma_addr;
+ uint64_t pkt_flags;
+ uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
+
+ while (nb_rx < nb_pkts) {
+ rxdp = &rx_ring[rx_id];
+ rx_stat_err0 = rte_le_to_cpu_16(rxdp->wb.status_error0);
+
+ /* Check the DD bit first */
+ if (!(rx_stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S)))
+ break;
+
+ /* allocate mbuf */
+ nmb = rte_mbuf_raw_alloc(rxq->mp);
+ if (unlikely(!nmb)) {
+ rxq->vsi->adapter->pf.dev_data->rx_mbuf_alloc_failed++;
+ break;
+ }
+ rxd = *rxdp; /* copy descriptor in ring to temp variable*/
+
+ nb_hold++;
+ rxe = &sw_ring[rx_id]; /* get corresponding mbuf in SW ring */
+ rx_id++;
+ if (unlikely(rx_id == rxq->nb_rx_desc))
+ rx_id = 0;
+
+ /* Prefetch next mbuf */
+ rte_prefetch0(sw_ring[rx_id].mbuf);
+
+ /**
+ * When next RX descriptor is on a cache line boundary,
+ * prefetch the next 4 RX descriptors and next 8 pointers
+ * to mbufs.
+ */
+ if ((rx_id & 0x3) == 0) {
+ rte_prefetch0(&rx_ring[rx_id]);
+ rte_prefetch0(&sw_ring[rx_id]);
+ }
+
+ rxm = rxe->mbuf;
+ rxe->mbuf = nmb;
+ dma_addr =
+ rte_cpu_to_le_64(rte_mbuf_data_iova_default(nmb));
+
+ /* Set data buffer address and data length of the mbuf */
+ rxdp->read.hdr_addr = 0;
+ rxdp->read.pkt_addr = dma_addr;
+ rx_packet_len = rte_le_to_cpu_16(rxd.wb.pkt_len) &
+ ICE_RX_FLX_DESC_PKT_LEN_M;
+ rxm->data_len = rx_packet_len;
+ rxm->data_off = RTE_PKTMBUF_HEADROOM;
+
+ /**
+ * If this is the first buffer of the received packet, set the
+ * pointer to the first mbuf of the packet and initialize its
+ * context. Otherwise, update the total length and the number
+ * of segments of the current scattered packet, and update the
+ * pointer to the last mbuf of the current packet.
+ */
+ if (!first_seg) {
+ first_seg = rxm;
+ first_seg->nb_segs = 1;
+ first_seg->pkt_len = rx_packet_len;
+ } else {
+ first_seg->pkt_len =
+ (uint16_t)(first_seg->pkt_len +
+ rx_packet_len);
+ first_seg->nb_segs++;
+ last_seg->next = rxm;
+ }
+
+ /**
+ * If this is not the last buffer of the received packet,
+ * update the pointer to the last mbuf of the current scattered
+ * packet and continue to parse the RX ring.
+ */
+ if (!(rx_stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_EOF_S))) {
+ last_seg = rxm;
+ continue;
+ }
+
+ /**
+ * This is the last buffer of the received packet. If the CRC
+ * is not stripped by the hardware:
+ * - Subtract the CRC length from the total packet length.
+ * - If the last buffer only contains the whole CRC or a part
+ * of it, free the mbuf associated to the last buffer. If part
+ * of the CRC is also contained in the previous mbuf, subtract
+ * the length of that CRC part from the data length of the
+ * previous mbuf.
+ */
+ rxm->next = NULL;
+ if (unlikely(rxq->crc_len > 0)) {
+ first_seg->pkt_len -= RTE_ETHER_CRC_LEN;
+ if (rx_packet_len <= RTE_ETHER_CRC_LEN) {
+ rte_pktmbuf_free_seg(rxm);
+ first_seg->nb_segs--;
+ last_seg->data_len =
+ (uint16_t)(last_seg->data_len -
+ (RTE_ETHER_CRC_LEN - rx_packet_len));
+ last_seg->next = NULL;
+ } else
+ rxm->data_len = (uint16_t)(rx_packet_len -
+ RTE_ETHER_CRC_LEN);
+ }
+
+ first_seg->port = rxq->port_id;
+ first_seg->ol_flags = 0;
+ first_seg->packet_type = ptype_tbl[ICE_RX_FLEX_DESC_PTYPE_M &
+ rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)];
+ ice_rxd_to_vlan_tci(first_seg, &rxd);
+ rxq->rxd_to_pkt_fields(rxq, first_seg, &rxd);
+ pkt_flags = ice_rxd_error_to_pkt_flags(rx_stat_err0);
+ first_seg->ol_flags |= pkt_flags;
+ /* Prefetch data of first segment, if configured to do so. */
+ rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr,
+ first_seg->data_off));
+ rx_pkts[nb_rx++] = first_seg;
+ first_seg = NULL;
+ }
+
+ /* Record index of the next RX descriptor to probe. */
+ rxq->rx_tail = rx_id;
+ rxq->pkt_first_seg = first_seg;
+ rxq->pkt_last_seg = last_seg;
+
+ /**
+ * If the number of free RX descriptors is greater than the RX free
+ * threshold of the queue, advance the Receive Descriptor Tail (RDT)
+ * register. Update the RDT with the value of the last processed RX
+ * descriptor minus 1, to guarantee that the RDT register is never
+ * equal to the RDH register, which creates a "full" ring situtation
+ * from the hardware point of view.
+ */
+ nb_hold = (uint16_t)(nb_hold + rxq->nb_rx_hold);
+ if (nb_hold > rxq->rx_free_thresh) {
+ rx_id = (uint16_t)(rx_id == 0 ?
+ (rxq->nb_rx_desc - 1) : (rx_id - 1));
+ /* write TAIL register */
+ ICE_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
+ nb_hold = 0;
+ }
+ rxq->nb_rx_hold = nb_hold;
+
+ /* return received packet in the burst */
+ return nb_rx;
+}
+
+const uint32_t *
+ice_dev_supported_ptypes_get(struct rte_eth_dev *dev)
+{
+ struct ice_adapter *ad =
+ ICE_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+ const uint32_t *ptypes;
+
+ static const uint32_t ptypes_os[] = {
+ /* refers to ice_get_default_pkt_type() */
+ RTE_PTYPE_L2_ETHER,
+ RTE_PTYPE_L2_ETHER_TIMESYNC,
+ RTE_PTYPE_L2_ETHER_LLDP,
+ RTE_PTYPE_L2_ETHER_ARP,
+ RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_L4_FRAG,
+ RTE_PTYPE_L4_ICMP,
+ RTE_PTYPE_L4_NONFRAG,
+ RTE_PTYPE_L4_SCTP,
+ RTE_PTYPE_L4_TCP,
+ RTE_PTYPE_L4_UDP,
+ RTE_PTYPE_TUNNEL_GRENAT,
+ RTE_PTYPE_TUNNEL_IP,
+ RTE_PTYPE_INNER_L2_ETHER,
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L4_FRAG,
+ RTE_PTYPE_INNER_L4_ICMP,
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ RTE_PTYPE_INNER_L4_SCTP,
+ RTE_PTYPE_INNER_L4_TCP,
+ RTE_PTYPE_INNER_L4_UDP,
+ RTE_PTYPE_UNKNOWN
+ };
+
+ static const uint32_t ptypes_comms[] = {
+ /* refers to ice_get_default_pkt_type() */
+ RTE_PTYPE_L2_ETHER,
+ RTE_PTYPE_L2_ETHER_TIMESYNC,
+ RTE_PTYPE_L2_ETHER_LLDP,
+ RTE_PTYPE_L2_ETHER_ARP,
+ RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_L4_FRAG,
+ RTE_PTYPE_L4_ICMP,
+ RTE_PTYPE_L4_NONFRAG,
+ RTE_PTYPE_L4_SCTP,
+ RTE_PTYPE_L4_TCP,
+ RTE_PTYPE_L4_UDP,
+ RTE_PTYPE_TUNNEL_GRENAT,
+ RTE_PTYPE_TUNNEL_IP,
+ RTE_PTYPE_INNER_L2_ETHER,
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L4_FRAG,
+ RTE_PTYPE_INNER_L4_ICMP,
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ RTE_PTYPE_INNER_L4_SCTP,
+ RTE_PTYPE_INNER_L4_TCP,
+ RTE_PTYPE_INNER_L4_UDP,
+ RTE_PTYPE_TUNNEL_GTPC,
+ RTE_PTYPE_TUNNEL_GTPU,
+ RTE_PTYPE_L2_ETHER_PPPOE,
+ RTE_PTYPE_UNKNOWN
+ };
+
+ if (ad->active_pkg_type == ICE_PKG_TYPE_COMMS)
+ ptypes = ptypes_comms;
+ else
+ ptypes = ptypes_os;
+
+ if (dev->rx_pkt_burst == ice_recv_pkts ||
+ dev->rx_pkt_burst == ice_recv_pkts_bulk_alloc ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts)
+ return ptypes;
+
+#ifdef RTE_ARCH_X86
+ if (dev->rx_pkt_burst == ice_recv_pkts_vec ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec ||
+#ifdef CC_AVX512_SUPPORT
+ dev->rx_pkt_burst == ice_recv_pkts_vec_avx512 ||
+ dev->rx_pkt_burst == ice_recv_pkts_vec_avx512_offload ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx512 ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx512_offload ||
+#endif
+ dev->rx_pkt_burst == ice_recv_pkts_vec_avx2 ||
+ dev->rx_pkt_burst == ice_recv_pkts_vec_avx2_offload ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx2 ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx2_offload)
+ return ptypes;
+#endif
+
+ return NULL;
+}
+
+int
+ice_rx_descriptor_status(void *rx_queue, uint16_t offset)
+{
+ volatile union ice_rx_flex_desc *rxdp;
+ struct ice_rx_queue *rxq = rx_queue;
+ uint32_t desc;
+
+ if (unlikely(offset >= rxq->nb_rx_desc))
+ return -EINVAL;
+
+ if (offset >= rxq->nb_rx_desc - rxq->nb_rx_hold)
+ return RTE_ETH_RX_DESC_UNAVAIL;
+
+ desc = rxq->rx_tail + offset;
+ if (desc >= rxq->nb_rx_desc)
+ desc -= rxq->nb_rx_desc;
+
+ rxdp = &rxq->rx_ring[desc];
+ if (rte_le_to_cpu_16(rxdp->wb.status_error0) &
+ (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S))
+ return RTE_ETH_RX_DESC_DONE;
+
+ return RTE_ETH_RX_DESC_AVAIL;
+}
+
+int
+ice_tx_descriptor_status(void *tx_queue, uint16_t offset)
+{
+ struct ice_tx_queue *txq = tx_queue;
+ volatile uint64_t *status;
+ uint64_t mask, expect;
+ uint32_t desc;
+
+ if (unlikely(offset >= txq->nb_tx_desc))
+ return -EINVAL;
+
+ desc = txq->tx_tail + offset;
+ /* go to next desc that has the RS bit */
+ desc = ((desc + txq->tx_rs_thresh - 1) / txq->tx_rs_thresh) *
+ txq->tx_rs_thresh;
+ if (desc >= txq->nb_tx_desc) {
+ desc -= txq->nb_tx_desc;
+ if (desc >= txq->nb_tx_desc)
+ desc -= txq->nb_tx_desc;
+ }
+
+ status = &txq->tx_ring[desc].cmd_type_offset_bsz;
+ mask = rte_cpu_to_le_64(ICE_TXD_QW1_DTYPE_M);
+ expect = rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DESC_DONE <<
+ ICE_TXD_QW1_DTYPE_S);
+ if ((*status & mask) == expect)
+ return RTE_ETH_TX_DESC_DONE;
+
+ return RTE_ETH_TX_DESC_FULL;
+}
+
+void
+ice_free_queues(struct rte_eth_dev *dev)
+{
+ uint16_t i;
+
+ PMD_INIT_FUNC_TRACE();
+
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ if (!dev->data->rx_queues[i])
+ continue;
+ ice_rx_queue_release(dev->data->rx_queues[i]);
+ dev->data->rx_queues[i] = NULL;
+ rte_eth_dma_zone_free(dev, "rx_ring", i);
+ }
+ dev->data->nb_rx_queues = 0;
+
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ if (!dev->data->tx_queues[i])
+ continue;
+ ice_tx_queue_release(dev->data->tx_queues[i]);
+ dev->data->tx_queues[i] = NULL;
+ rte_eth_dma_zone_free(dev, "tx_ring", i);
+ }
+ dev->data->nb_tx_queues = 0;
+}
+
+#define ICE_FDIR_NUM_TX_DESC ICE_MIN_RING_DESC
+#define ICE_FDIR_NUM_RX_DESC ICE_MIN_RING_DESC
+
+int
+ice_fdir_setup_tx_resources(struct ice_pf *pf)
+{
+ struct ice_tx_queue *txq;
+ const struct rte_memzone *tz = NULL;
+ uint32_t ring_size;
+ struct rte_eth_dev *dev;
+
+ if (!pf) {
+ PMD_DRV_LOG(ERR, "PF is not available");
+ return -EINVAL;
+ }
+
+ dev = &rte_eth_devices[pf->adapter->pf.dev_data->port_id];
+
+ /* Allocate the TX queue data structure. */
+ txq = rte_zmalloc_socket("ice fdir tx queue",
+ sizeof(struct ice_tx_queue),
+ RTE_CACHE_LINE_SIZE,
+ SOCKET_ID_ANY);
+ if (!txq) {
+ PMD_DRV_LOG(ERR, "Failed to allocate memory for "
+ "tx queue structure.");
+ return -ENOMEM;
+ }
+
+ /* Allocate TX hardware ring descriptors. */
+ ring_size = sizeof(struct ice_tx_desc) * ICE_FDIR_NUM_TX_DESC;
+ ring_size = RTE_ALIGN(ring_size, ICE_DMA_MEM_ALIGN);
+
+ tz = rte_eth_dma_zone_reserve(dev, "fdir_tx_ring",
+ ICE_FDIR_QUEUE_ID, ring_size,
+ ICE_RING_BASE_ALIGN, SOCKET_ID_ANY);
+ if (!tz) {
+ ice_tx_queue_release(txq);
+ PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX.");
+ return -ENOMEM;
+ }
+
+ txq->nb_tx_desc = ICE_FDIR_NUM_TX_DESC;
+ txq->queue_id = ICE_FDIR_QUEUE_ID;
+ txq->reg_idx = pf->fdir.fdir_vsi->base_queue;
+ txq->vsi = pf->fdir.fdir_vsi;
+
+ txq->tx_ring_dma = tz->iova;
+ txq->tx_ring = (struct ice_tx_desc *)tz->addr;
+ /*
+ * don't need to allocate software ring and reset for the fdir
+ * program queue just set the queue has been configured.
+ */
+ txq->q_set = true;
+ pf->fdir.txq = txq;
+
+ txq->tx_rel_mbufs = _ice_tx_queue_release_mbufs;
+
+ return ICE_SUCCESS;
+}
+
+int
+ice_fdir_setup_rx_resources(struct ice_pf *pf)
+{
+ struct ice_rx_queue *rxq;
+ const struct rte_memzone *rz = NULL;
+ uint32_t ring_size;
+ struct rte_eth_dev *dev;
+
+ if (!pf) {
+ PMD_DRV_LOG(ERR, "PF is not available");
+ return -EINVAL;
+ }
+
+ dev = &rte_eth_devices[pf->adapter->pf.dev_data->port_id];
+
+ /* Allocate the RX queue data structure. */
+ rxq = rte_zmalloc_socket("ice fdir rx queue",
+ sizeof(struct ice_rx_queue),
+ RTE_CACHE_LINE_SIZE,
+ SOCKET_ID_ANY);
+ if (!rxq) {
+ PMD_DRV_LOG(ERR, "Failed to allocate memory for "
+ "rx queue structure.");
+ return -ENOMEM;
+ }
+
+ /* Allocate RX hardware ring descriptors. */
+ ring_size = sizeof(union ice_32byte_rx_desc) * ICE_FDIR_NUM_RX_DESC;
+ ring_size = RTE_ALIGN(ring_size, ICE_DMA_MEM_ALIGN);
+
+ rz = rte_eth_dma_zone_reserve(dev, "fdir_rx_ring",
+ ICE_FDIR_QUEUE_ID, ring_size,
+ ICE_RING_BASE_ALIGN, SOCKET_ID_ANY);
+ if (!rz) {
+ ice_rx_queue_release(rxq);
+ PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for RX.");
+ return -ENOMEM;
+ }
+
+ rxq->nb_rx_desc = ICE_FDIR_NUM_RX_DESC;
+ rxq->queue_id = ICE_FDIR_QUEUE_ID;
+ rxq->reg_idx = pf->fdir.fdir_vsi->base_queue;
+ rxq->vsi = pf->fdir.fdir_vsi;
+
+ rxq->rx_ring_dma = rz->iova;
+ memset(rz->addr, 0, ICE_FDIR_NUM_RX_DESC *
+ sizeof(union ice_32byte_rx_desc));
+ rxq->rx_ring = (union ice_rx_flex_desc *)rz->addr;
+
+ /*
+ * Don't need to allocate software ring and reset for the fdir
+ * rx queue, just set the queue has been configured.
+ */
+ rxq->q_set = true;
+ pf->fdir.rxq = rxq;
+
+ rxq->rx_rel_mbufs = _ice_rx_queue_release_mbufs;
+
+ return ICE_SUCCESS;
+}
+
+uint16_t
+ice_recv_pkts(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ struct ice_rx_queue *rxq = rx_queue;
+ volatile union ice_rx_flex_desc *rx_ring = rxq->rx_ring;
+ volatile union ice_rx_flex_desc *rxdp;
+ union ice_rx_flex_desc rxd;
+ struct ice_rx_entry *sw_ring = rxq->sw_ring;
+ struct ice_rx_entry *rxe;
+ struct rte_mbuf *nmb; /* new allocated mbuf */
+ struct rte_mbuf *rxm; /* pointer to store old mbuf in SW ring */
+ uint16_t rx_id = rxq->rx_tail;
+ uint16_t nb_rx = 0;
+ uint16_t nb_hold = 0;
+ uint16_t rx_packet_len;
+ uint16_t rx_stat_err0;
+ uint64_t dma_addr;
+ uint64_t pkt_flags;
+ uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
+
+ while (nb_rx < nb_pkts) {
+ rxdp = &rx_ring[rx_id];
+ rx_stat_err0 = rte_le_to_cpu_16(rxdp->wb.status_error0);
+
+ /* Check the DD bit first */
+ if (!(rx_stat_err0 & (1 << ICE_RX_FLEX_DESC_STATUS0_DD_S)))
+ break;
+
+ /* allocate mbuf */
+ nmb = rte_mbuf_raw_alloc(rxq->mp);
+ if (unlikely(!nmb)) {
+ rxq->vsi->adapter->pf.dev_data->rx_mbuf_alloc_failed++;
+ break;
+ }
+ rxd = *rxdp; /* copy descriptor in ring to temp variable*/
+
+ nb_hold++;
+ rxe = &sw_ring[rx_id]; /* get corresponding mbuf in SW ring */
+ rx_id++;
+ if (unlikely(rx_id == rxq->nb_rx_desc))
+ rx_id = 0;
+ rxm = rxe->mbuf;
+ rxe->mbuf = nmb;
+ dma_addr =
+ rte_cpu_to_le_64(rte_mbuf_data_iova_default(nmb));
+
+ /**
+ * fill the read format of descriptor with physic address in
+ * new allocated mbuf: nmb
+ */
+ rxdp->read.hdr_addr = 0;
+ rxdp->read.pkt_addr = dma_addr;
+
+ /* calculate rx_packet_len of the received pkt */
+ rx_packet_len = (rte_le_to_cpu_16(rxd.wb.pkt_len) &
+ ICE_RX_FLX_DESC_PKT_LEN_M) - rxq->crc_len;
+
+ /* fill old mbuf with received descriptor: rxd */
+ rxm->data_off = RTE_PKTMBUF_HEADROOM;
+ rte_prefetch0(RTE_PTR_ADD(rxm->buf_addr, RTE_PKTMBUF_HEADROOM));
+ rxm->nb_segs = 1;
+ rxm->next = NULL;
+ rxm->pkt_len = rx_packet_len;
+ rxm->data_len = rx_packet_len;
+ rxm->port = rxq->port_id;
+ rxm->packet_type = ptype_tbl[ICE_RX_FLEX_DESC_PTYPE_M &
+ rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)];
+ ice_rxd_to_vlan_tci(rxm, &rxd);
+ rxq->rxd_to_pkt_fields(rxq, rxm, &rxd);
+ pkt_flags = ice_rxd_error_to_pkt_flags(rx_stat_err0);
+ rxm->ol_flags |= pkt_flags;
+ /* copy old mbuf to rx_pkts */
+ rx_pkts[nb_rx++] = rxm;
+ }
+ rxq->rx_tail = rx_id;
+ /**
+ * If the number of free RX descriptors is greater than the RX free
+ * threshold of the queue, advance the receive tail register of queue.
+ * Update that register with the value of the last processed RX
+ * descriptor minus 1.
+ */
+ nb_hold = (uint16_t)(nb_hold + rxq->nb_rx_hold);
+ if (nb_hold > rxq->rx_free_thresh) {
+ rx_id = (uint16_t)(rx_id == 0 ?
+ (rxq->nb_rx_desc - 1) : (rx_id - 1));
+ /* write TAIL register */
+ ICE_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
+ nb_hold = 0;
+ }
+ rxq->nb_rx_hold = nb_hold;
+
+ /* return received packet in the burst */
+ return nb_rx;
+}
+
+static inline void
+ice_parse_tunneling_params(uint64_t ol_flags,
+ union ice_tx_offload tx_offload,
+ uint32_t *cd_tunneling)
+{
+ /* EIPT: External (outer) IP header type */
+ if (ol_flags & PKT_TX_OUTER_IP_CKSUM)
+ *cd_tunneling |= ICE_TX_CTX_EIPT_IPV4;
+ else if (ol_flags & PKT_TX_OUTER_IPV4)
+ *cd_tunneling |= ICE_TX_CTX_EIPT_IPV4_NO_CSUM;
+ else if (ol_flags & PKT_TX_OUTER_IPV6)
+ *cd_tunneling |= ICE_TX_CTX_EIPT_IPV6;
+
+ /* EIPLEN: External (outer) IP header length, in DWords */
+ *cd_tunneling |= (tx_offload.outer_l3_len >> 2) <<
+ ICE_TXD_CTX_QW0_EIPLEN_S;
+
+ /* L4TUNT: L4 Tunneling Type */
+ switch (ol_flags & PKT_TX_TUNNEL_MASK) {
+ case PKT_TX_TUNNEL_IPIP:
+ /* for non UDP / GRE tunneling, set to 00b */
+ break;
+ case PKT_TX_TUNNEL_VXLAN:
+ case PKT_TX_TUNNEL_GTP:
+ case PKT_TX_TUNNEL_GENEVE:
+ *cd_tunneling |= ICE_TXD_CTX_UDP_TUNNELING;
+ break;
+ case PKT_TX_TUNNEL_GRE:
+ *cd_tunneling |= ICE_TXD_CTX_GRE_TUNNELING;
+ break;
+ default:
+ PMD_TX_LOG(ERR, "Tunnel type not supported");
+ return;
+ }
+
+ /* L4TUNLEN: L4 Tunneling Length, in Words
+ *
+ * We depend on app to set rte_mbuf.l2_len correctly.
+ * For IP in GRE it should be set to the length of the GRE
+ * header;
+ * For MAC in GRE or MAC in UDP it should be set to the length
+ * of the GRE or UDP headers plus the inner MAC up to including
+ * its last Ethertype.
+ * If MPLS labels exists, it should include them as well.
+ */
+ *cd_tunneling |= (tx_offload.l2_len >> 1) <<
+ ICE_TXD_CTX_QW0_NATLEN_S;
+
+ /**
+ * Calculate the tunneling UDP checksum.
+ * Shall be set only if L4TUNT = 01b and EIPT is not zero
+ */
+ if (!(*cd_tunneling & ICE_TX_CTX_EIPT_NONE) &&
+ (*cd_tunneling & ICE_TXD_CTX_UDP_TUNNELING))
+ *cd_tunneling |= ICE_TXD_CTX_QW0_L4T_CS_M;
+}
+
+static inline void
+ice_txd_enable_checksum(uint64_t ol_flags,
+ uint32_t *td_cmd,
+ uint32_t *td_offset,
+ union ice_tx_offload tx_offload)
+{
+ /* Set MACLEN */
+ if (ol_flags & PKT_TX_TUNNEL_MASK)
+ *td_offset |= (tx_offload.outer_l2_len >> 1)
+ << ICE_TX_DESC_LEN_MACLEN_S;
+ else
+ *td_offset |= (tx_offload.l2_len >> 1)
+ << ICE_TX_DESC_LEN_MACLEN_S;
+
+ /* Enable L3 checksum offloads */
+ if (ol_flags & PKT_TX_IP_CKSUM) {
+ *td_cmd |= ICE_TX_DESC_CMD_IIPT_IPV4_CSUM;
+ *td_offset |= (tx_offload.l3_len >> 2) <<
+ ICE_TX_DESC_LEN_IPLEN_S;
+ } else if (ol_flags & PKT_TX_IPV4) {
+ *td_cmd |= ICE_TX_DESC_CMD_IIPT_IPV4;
+ *td_offset |= (tx_offload.l3_len >> 2) <<
+ ICE_TX_DESC_LEN_IPLEN_S;
+ } else if (ol_flags & PKT_TX_IPV6) {
+ *td_cmd |= ICE_TX_DESC_CMD_IIPT_IPV6;
+ *td_offset |= (tx_offload.l3_len >> 2) <<
+ ICE_TX_DESC_LEN_IPLEN_S;
+ }
+
+ if (ol_flags & PKT_TX_TCP_SEG) {
+ *td_cmd |= ICE_TX_DESC_CMD_L4T_EOFT_TCP;
+ *td_offset |= (tx_offload.l4_len >> 2) <<
+ ICE_TX_DESC_LEN_L4_LEN_S;
+ return;
+ }
+
+ /* Enable L4 checksum offloads */
+ switch (ol_flags & PKT_TX_L4_MASK) {
+ case PKT_TX_TCP_CKSUM:
+ *td_cmd |= ICE_TX_DESC_CMD_L4T_EOFT_TCP;
+ *td_offset |= (sizeof(struct rte_tcp_hdr) >> 2) <<
+ ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+ case PKT_TX_SCTP_CKSUM:
+ *td_cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
+ *td_offset |= (sizeof(struct rte_sctp_hdr) >> 2) <<
+ ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+ case PKT_TX_UDP_CKSUM:
+ *td_cmd |= ICE_TX_DESC_CMD_L4T_EOFT_UDP;
+ *td_offset |= (sizeof(struct rte_udp_hdr) >> 2) <<
+ ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+ default:
+ break;
+ }
+}
+
+static inline int
+ice_xmit_cleanup(struct ice_tx_queue *txq)
+{
+ struct ice_tx_entry *sw_ring = txq->sw_ring;
+ volatile struct ice_tx_desc *txd = txq->tx_ring;
+ uint16_t last_desc_cleaned = txq->last_desc_cleaned;
+ uint16_t nb_tx_desc = txq->nb_tx_desc;
+ uint16_t desc_to_clean_to;
+ uint16_t nb_tx_to_clean;
+
+ /* Determine the last descriptor needing to be cleaned */
+ desc_to_clean_to = (uint16_t)(last_desc_cleaned + txq->tx_rs_thresh);
+ if (desc_to_clean_to >= nb_tx_desc)
+ desc_to_clean_to = (uint16_t)(desc_to_clean_to - nb_tx_desc);
+
+ /* Check to make sure the last descriptor to clean is done */
+ desc_to_clean_to = sw_ring[desc_to_clean_to].last_id;
+ if (!(txd[desc_to_clean_to].cmd_type_offset_bsz &
+ rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DESC_DONE))) {
+ PMD_TX_LOG(DEBUG, "TX descriptor %4u is not done "
+ "(port=%d queue=%d) value=0x%"PRIx64"\n",
+ desc_to_clean_to,
+ txq->port_id, txq->queue_id,
+ txd[desc_to_clean_to].cmd_type_offset_bsz);
+ /* Failed to clean any descriptors */
+ return -1;
+ }
+
+ /* Figure out how many descriptors will be cleaned */
+ if (last_desc_cleaned > desc_to_clean_to)
+ nb_tx_to_clean = (uint16_t)((nb_tx_desc - last_desc_cleaned) +
+ desc_to_clean_to);
+ else
+ nb_tx_to_clean = (uint16_t)(desc_to_clean_to -
+ last_desc_cleaned);
+
+ /* The last descriptor to clean is done, so that means all the
+ * descriptors from the last descriptor that was cleaned
+ * up to the last descriptor with the RS bit set
+ * are done. Only reset the threshold descriptor.
+ */
+ txd[desc_to_clean_to].cmd_type_offset_bsz = 0;
+
+ /* Update the txq to reflect the last descriptor that was cleaned */
+ txq->last_desc_cleaned = desc_to_clean_to;
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + nb_tx_to_clean);
+
+ return 0;
+}
+
+/* Construct the tx flags */
+static inline uint64_t
+ice_build_ctob(uint32_t td_cmd,
+ uint32_t td_offset,
+ uint16_t size,
+ uint32_t td_tag)
+{
+ return rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DATA |
+ ((uint64_t)td_cmd << ICE_TXD_QW1_CMD_S) |
+ ((uint64_t)td_offset << ICE_TXD_QW1_OFFSET_S) |
+ ((uint64_t)size << ICE_TXD_QW1_TX_BUF_SZ_S) |
+ ((uint64_t)td_tag << ICE_TXD_QW1_L2TAG1_S));
+}
+
+/* Check if the context descriptor is needed for TX offloading */
+static inline uint16_t
+ice_calc_context_desc(uint64_t flags)
+{
+ static uint64_t mask = PKT_TX_TCP_SEG |
+ PKT_TX_QINQ |
+ PKT_TX_OUTER_IP_CKSUM |
+ PKT_TX_TUNNEL_MASK;
+
+ return (flags & mask) ? 1 : 0;
+}
+
+/* set ice TSO context descriptor */
+static inline uint64_t
+ice_set_tso_ctx(struct rte_mbuf *mbuf, union ice_tx_offload tx_offload)
+{
+ uint64_t ctx_desc = 0;
+ uint32_t cd_cmd, hdr_len, cd_tso_len;
+
+ if (!tx_offload.l4_len) {
+ PMD_TX_LOG(DEBUG, "L4 length set to 0");
+ return ctx_desc;
+ }
+
+ hdr_len = tx_offload.l2_len + tx_offload.l3_len + tx_offload.l4_len;
+ hdr_len += (mbuf->ol_flags & PKT_TX_TUNNEL_MASK) ?
+ tx_offload.outer_l2_len + tx_offload.outer_l3_len : 0;
+
+ cd_cmd = ICE_TX_CTX_DESC_TSO;
+ cd_tso_len = mbuf->pkt_len - hdr_len;
+ ctx_desc |= ((uint64_t)cd_cmd << ICE_TXD_CTX_QW1_CMD_S) |
+ ((uint64_t)cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
+ ((uint64_t)mbuf->tso_segsz << ICE_TXD_CTX_QW1_MSS_S);
+
+ return ctx_desc;
+}
+
+/* HW requires that TX buffer size ranges from 1B up to (16K-1)B. */
+#define ICE_MAX_DATA_PER_TXD \
+ (ICE_TXD_QW1_TX_BUF_SZ_M >> ICE_TXD_QW1_TX_BUF_SZ_S)
+/* Calculate the number of TX descriptors needed for each pkt */
+static inline uint16_t
+ice_calc_pkt_desc(struct rte_mbuf *tx_pkt)
+{
+ struct rte_mbuf *txd = tx_pkt;
+ uint16_t count = 0;
+
+ while (txd != NULL) {
+ count += DIV_ROUND_UP(txd->data_len, ICE_MAX_DATA_PER_TXD);
+ txd = txd->next;
+ }
+
+ return count;
+}
+
+uint16_t
+ice_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ struct ice_tx_queue *txq;
+ volatile struct ice_tx_desc *tx_ring;
+ volatile struct ice_tx_desc *txd;
+ struct ice_tx_entry *sw_ring;
+ struct ice_tx_entry *txe, *txn;
+ struct rte_mbuf *tx_pkt;
+ struct rte_mbuf *m_seg;
+ uint32_t cd_tunneling_params;
+ uint16_t tx_id;
+ uint16_t nb_tx;
+ uint16_t nb_used;
+ uint16_t nb_ctx;
+ uint32_t td_cmd = 0;
+ uint32_t td_offset = 0;
+ uint32_t td_tag = 0;
+ uint16_t tx_last;
+ uint16_t slen;
+ uint64_t buf_dma_addr;
+ uint64_t ol_flags;
+ union ice_tx_offload tx_offload = {0};
+
+ txq = tx_queue;
+ sw_ring = txq->sw_ring;
+ tx_ring = txq->tx_ring;
+ tx_id = txq->tx_tail;
+ txe = &sw_ring[tx_id];
+
+ /* Check if the descriptor ring needs to be cleaned. */
+ if (txq->nb_tx_free < txq->tx_free_thresh)
+ (void)ice_xmit_cleanup(txq);
+
+ for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) {
+ tx_pkt = *tx_pkts++;
+
+ td_cmd = 0;
+ td_tag = 0;
+ td_offset = 0;
+ ol_flags = tx_pkt->ol_flags;
+ tx_offload.l2_len = tx_pkt->l2_len;
+ tx_offload.l3_len = tx_pkt->l3_len;
+ tx_offload.outer_l2_len = tx_pkt->outer_l2_len;
+ tx_offload.outer_l3_len = tx_pkt->outer_l3_len;
+ tx_offload.l4_len = tx_pkt->l4_len;
+ tx_offload.tso_segsz = tx_pkt->tso_segsz;
+ /* Calculate the number of context descriptors needed. */
+ nb_ctx = ice_calc_context_desc(ol_flags);
+
+ /* The number of descriptors that must be allocated for
+ * a packet equals to the number of the segments of that
+ * packet plus the number of context descriptor if needed.
+ * Recalculate the needed tx descs when TSO enabled in case
+ * the mbuf data size exceeds max data size that hw allows
+ * per tx desc.
+ */
+ if (ol_flags & PKT_TX_TCP_SEG)
+ nb_used = (uint16_t)(ice_calc_pkt_desc(tx_pkt) +
+ nb_ctx);
+ else
+ nb_used = (uint16_t)(tx_pkt->nb_segs + nb_ctx);
+ tx_last = (uint16_t)(tx_id + nb_used - 1);
+
+ /* Circular ring */
+ if (tx_last >= txq->nb_tx_desc)
+ tx_last = (uint16_t)(tx_last - txq->nb_tx_desc);
+
+ if (nb_used > txq->nb_tx_free) {
+ if (ice_xmit_cleanup(txq) != 0) {
+ if (nb_tx == 0)
+ return 0;
+ goto end_of_tx;
+ }
+ if (unlikely(nb_used > txq->tx_rs_thresh)) {
+ while (nb_used > txq->nb_tx_free) {
+ if (ice_xmit_cleanup(txq) != 0) {
+ if (nb_tx == 0)
+ return 0;
+ goto end_of_tx;
+ }
+ }
+ }
+ }
+
+ /* Descriptor based VLAN insertion */
+ if (ol_flags & (PKT_TX_VLAN | PKT_TX_QINQ)) {
+ td_cmd |= ICE_TX_DESC_CMD_IL2TAG1;
+ td_tag = tx_pkt->vlan_tci;
+ }
+
+ /* Fill in tunneling parameters if necessary */
+ cd_tunneling_params = 0;
+ if (ol_flags & PKT_TX_TUNNEL_MASK)
+ ice_parse_tunneling_params(ol_flags, tx_offload,
+ &cd_tunneling_params);
+
+ /* Enable checksum offloading */
+ if (ol_flags & ICE_TX_CKSUM_OFFLOAD_MASK)
+ ice_txd_enable_checksum(ol_flags, &td_cmd,
+ &td_offset, tx_offload);
+
+ if (nb_ctx) {
+ /* Setup TX context descriptor if required */
+ volatile struct ice_tx_ctx_desc *ctx_txd =
+ (volatile struct ice_tx_ctx_desc *)
+ &tx_ring[tx_id];
+ uint16_t cd_l2tag2 = 0;
+ uint64_t cd_type_cmd_tso_mss = ICE_TX_DESC_DTYPE_CTX;
+
+ txn = &sw_ring[txe->next_id];
+ RTE_MBUF_PREFETCH_TO_FREE(txn->mbuf);
+ if (txe->mbuf) {
+ rte_pktmbuf_free_seg(txe->mbuf);
+ txe->mbuf = NULL;
+ }
+
+ if (ol_flags & PKT_TX_TCP_SEG)
+ cd_type_cmd_tso_mss |=
+ ice_set_tso_ctx(tx_pkt, tx_offload);
+
+ ctx_txd->tunneling_params =
+ rte_cpu_to_le_32(cd_tunneling_params);
+
+ /* TX context descriptor based double VLAN insert */
+ if (ol_flags & PKT_TX_QINQ) {
+ cd_l2tag2 = tx_pkt->vlan_tci_outer;
+ cd_type_cmd_tso_mss |=
+ ((uint64_t)ICE_TX_CTX_DESC_IL2TAG2 <<
+ ICE_TXD_CTX_QW1_CMD_S);
+ }
+ ctx_txd->l2tag2 = rte_cpu_to_le_16(cd_l2tag2);
+ ctx_txd->qw1 =
+ rte_cpu_to_le_64(cd_type_cmd_tso_mss);
+
+ txe->last_id = tx_last;
+ tx_id = txe->next_id;
+ txe = txn;
+ }
+ m_seg = tx_pkt;
+
+ do {
+ txd = &tx_ring[tx_id];
+ txn = &sw_ring[txe->next_id];
+
+ if (txe->mbuf)
+ rte_pktmbuf_free_seg(txe->mbuf);
+ txe->mbuf = m_seg;
+
+ /* Setup TX Descriptor */
+ slen = m_seg->data_len;
+ buf_dma_addr = rte_mbuf_data_iova(m_seg);
+
+ while ((ol_flags & PKT_TX_TCP_SEG) &&
+ unlikely(slen > ICE_MAX_DATA_PER_TXD)) {
+ txd->buf_addr = rte_cpu_to_le_64(buf_dma_addr);
+ txd->cmd_type_offset_bsz =
+ rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DATA |
+ ((uint64_t)td_cmd << ICE_TXD_QW1_CMD_S) |
+ ((uint64_t)td_offset << ICE_TXD_QW1_OFFSET_S) |
+ ((uint64_t)ICE_MAX_DATA_PER_TXD <<
+ ICE_TXD_QW1_TX_BUF_SZ_S) |
+ ((uint64_t)td_tag << ICE_TXD_QW1_L2TAG1_S));
+
+ buf_dma_addr += ICE_MAX_DATA_PER_TXD;
+ slen -= ICE_MAX_DATA_PER_TXD;
+
+ txe->last_id = tx_last;
+ tx_id = txe->next_id;
+ txe = txn;
+ txd = &tx_ring[tx_id];
+ txn = &sw_ring[txe->next_id];
+ }
+
+ txd->buf_addr = rte_cpu_to_le_64(buf_dma_addr);
+ txd->cmd_type_offset_bsz =
+ rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DATA |
+ ((uint64_t)td_cmd << ICE_TXD_QW1_CMD_S) |
+ ((uint64_t)td_offset << ICE_TXD_QW1_OFFSET_S) |
+ ((uint64_t)slen << ICE_TXD_QW1_TX_BUF_SZ_S) |
+ ((uint64_t)td_tag << ICE_TXD_QW1_L2TAG1_S));
+
+ txe->last_id = tx_last;
+ tx_id = txe->next_id;
+ txe = txn;
+ m_seg = m_seg->next;
+ } while (m_seg);
+
+ /* fill the last descriptor with End of Packet (EOP) bit */
+ td_cmd |= ICE_TX_DESC_CMD_EOP;
+ txq->nb_tx_used = (uint16_t)(txq->nb_tx_used + nb_used);
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_used);
+
+ /* set RS bit on the last descriptor of one packet */
+ if (txq->nb_tx_used >= txq->tx_rs_thresh) {
+ PMD_TX_LOG(DEBUG,
+ "Setting RS bit on TXD id="
+ "%4u (port=%d queue=%d)",
+ tx_last, txq->port_id, txq->queue_id);
+
+ td_cmd |= ICE_TX_DESC_CMD_RS;
+
+ /* Update txq RS bit counters */
+ txq->nb_tx_used = 0;
+ }
+ txd->cmd_type_offset_bsz |=
+ rte_cpu_to_le_64(((uint64_t)td_cmd) <<
+ ICE_TXD_QW1_CMD_S);
+ }
+end_of_tx:
+ /* update Tail register */
+ ICE_PCI_REG_WRITE(txq->qtx_tail, tx_id);
+ txq->tx_tail = tx_id;
+
+ return nb_tx;
+}
+
+static __rte_always_inline int
+ice_tx_free_bufs(struct ice_tx_queue *txq)
+{
+ struct ice_tx_entry *txep;
+ uint16_t i;
+
+ if ((txq->tx_ring[txq->tx_next_dd].cmd_type_offset_bsz &
+ rte_cpu_to_le_64(ICE_TXD_QW1_DTYPE_M)) !=
+ rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DESC_DONE))
+ return 0;
+
+ txep = &txq->sw_ring[txq->tx_next_dd - (txq->tx_rs_thresh - 1)];
+
+ for (i = 0; i < txq->tx_rs_thresh; i++)
+ rte_prefetch0((txep + i)->mbuf);
+
+ if (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE) {
+ for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
+ rte_mempool_put(txep->mbuf->pool, txep->mbuf);
+ txep->mbuf = NULL;
+ }
+ } else {
+ for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
+ rte_pktmbuf_free_seg(txep->mbuf);
+ txep->mbuf = NULL;
+ }
+ }
+
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
+ txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);
+ if (txq->tx_next_dd >= txq->nb_tx_desc)
+ txq->tx_next_dd = (uint16_t)(txq->tx_rs_thresh - 1);
+
+ return txq->tx_rs_thresh;
+}
+
+static int
+ice_tx_done_cleanup_full(struct ice_tx_queue *txq,
+ uint32_t free_cnt)
+{
+ struct ice_tx_entry *swr_ring = txq->sw_ring;
+ uint16_t i, tx_last, tx_id;
+ uint16_t nb_tx_free_last;
+ uint16_t nb_tx_to_clean;
+ uint32_t pkt_cnt;
+
+ /* Start free mbuf from the next of tx_tail */
+ tx_last = txq->tx_tail;
+ tx_id = swr_ring[tx_last].next_id;
+
+ if (txq->nb_tx_free == 0 && ice_xmit_cleanup(txq))
+ return 0;
+
+ nb_tx_to_clean = txq->nb_tx_free;
+ nb_tx_free_last = txq->nb_tx_free;
+ if (!free_cnt)
+ free_cnt = txq->nb_tx_desc;
+
+ /* Loop through swr_ring to count the amount of
+ * freeable mubfs and packets.
+ */
+ for (pkt_cnt = 0; pkt_cnt < free_cnt; ) {
+ for (i = 0; i < nb_tx_to_clean &&
+ pkt_cnt < free_cnt &&
+ tx_id != tx_last; i++) {
+ if (swr_ring[tx_id].mbuf != NULL) {
+ rte_pktmbuf_free_seg(swr_ring[tx_id].mbuf);
+ swr_ring[tx_id].mbuf = NULL;
+
+ /*
+ * last segment in the packet,
+ * increment packet count
+ */
+ pkt_cnt += (swr_ring[tx_id].last_id == tx_id);
+ }
+
+ tx_id = swr_ring[tx_id].next_id;
+ }
+
+ if (txq->tx_rs_thresh > txq->nb_tx_desc -
+ txq->nb_tx_free || tx_id == tx_last)
+ break;
+
+ if (pkt_cnt < free_cnt) {
+ if (ice_xmit_cleanup(txq))
+ break;
+
+ nb_tx_to_clean = txq->nb_tx_free - nb_tx_free_last;
+ nb_tx_free_last = txq->nb_tx_free;
+ }
+ }
+
+ return (int)pkt_cnt;
+}
+
+#ifdef RTE_ARCH_X86
+static int
+ice_tx_done_cleanup_vec(struct ice_tx_queue *txq __rte_unused,
+ uint32_t free_cnt __rte_unused)
+{
+ return -ENOTSUP;
+}
+#endif
+
+static int
+ice_tx_done_cleanup_simple(struct ice_tx_queue *txq,
+ uint32_t free_cnt)
+{
+ int i, n, cnt;
+
+ if (free_cnt == 0 || free_cnt > txq->nb_tx_desc)
+ free_cnt = txq->nb_tx_desc;
+
+ cnt = free_cnt - free_cnt % txq->tx_rs_thresh;
+
+ for (i = 0; i < cnt; i += n) {
+ if (txq->nb_tx_desc - txq->nb_tx_free < txq->tx_rs_thresh)
+ break;
+
+ n = ice_tx_free_bufs(txq);
+
+ if (n == 0)
+ break;
+ }
+
+ return i;
+}
+
+int
+ice_tx_done_cleanup(void *txq, uint32_t free_cnt)
+{
+ struct ice_tx_queue *q = (struct ice_tx_queue *)txq;
+ struct rte_eth_dev *dev = &rte_eth_devices[q->port_id];
+ struct ice_adapter *ad =
+ ICE_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+
+#ifdef RTE_ARCH_X86
+ if (ad->tx_vec_allowed)
+ return ice_tx_done_cleanup_vec(q, free_cnt);
+#endif
+ if (ad->tx_simple_allowed)
+ return ice_tx_done_cleanup_simple(q, free_cnt);
+ else
+ return ice_tx_done_cleanup_full(q, free_cnt);
+}
+
+/* Populate 4 descriptors with data from 4 mbufs */
+static inline void
+tx4(volatile struct ice_tx_desc *txdp, struct rte_mbuf **pkts)
+{
+ uint64_t dma_addr;
+ uint32_t i;
+
+ for (i = 0; i < 4; i++, txdp++, pkts++) {
+ dma_addr = rte_mbuf_data_iova(*pkts);
+ txdp->buf_addr = rte_cpu_to_le_64(dma_addr);
+ txdp->cmd_type_offset_bsz =
+ ice_build_ctob((uint32_t)ICE_TD_CMD, 0,
+ (*pkts)->data_len, 0);
+ }
+}
+
+/* Populate 1 descriptor with data from 1 mbuf */
+static inline void
+tx1(volatile struct ice_tx_desc *txdp, struct rte_mbuf **pkts)
+{
+ uint64_t dma_addr;
+
+ dma_addr = rte_mbuf_data_iova(*pkts);
+ txdp->buf_addr = rte_cpu_to_le_64(dma_addr);
+ txdp->cmd_type_offset_bsz =
+ ice_build_ctob((uint32_t)ICE_TD_CMD, 0,
+ (*pkts)->data_len, 0);
+}
+
+static inline void
+ice_tx_fill_hw_ring(struct ice_tx_queue *txq, struct rte_mbuf **pkts,
+ uint16_t nb_pkts)
+{
+ volatile struct ice_tx_desc *txdp = &txq->tx_ring[txq->tx_tail];
+ struct ice_tx_entry *txep = &txq->sw_ring[txq->tx_tail];
+ const int N_PER_LOOP = 4;
+ const int N_PER_LOOP_MASK = N_PER_LOOP - 1;
+ int mainpart, leftover;
+ int i, j;
+
+ /**
+ * Process most of the packets in chunks of N pkts. Any
+ * leftover packets will get processed one at a time.
+ */
+ mainpart = nb_pkts & ((uint32_t)~N_PER_LOOP_MASK);
+ leftover = nb_pkts & ((uint32_t)N_PER_LOOP_MASK);
+ for (i = 0; i < mainpart; i += N_PER_LOOP) {
+ /* Copy N mbuf pointers to the S/W ring */
+ for (j = 0; j < N_PER_LOOP; ++j)
+ (txep + i + j)->mbuf = *(pkts + i + j);
+ tx4(txdp + i, pkts + i);
+ }
+
+ if (unlikely(leftover > 0)) {
+ for (i = 0; i < leftover; ++i) {
+ (txep + mainpart + i)->mbuf = *(pkts + mainpart + i);
+ tx1(txdp + mainpart + i, pkts + mainpart + i);
+ }
+ }
+}
+
+static inline uint16_t
+tx_xmit_pkts(struct ice_tx_queue *txq,
+ struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ volatile struct ice_tx_desc *txr = txq->tx_ring;
+ uint16_t n = 0;
+
+ /**
+ * Begin scanning the H/W ring for done descriptors when the number
+ * of available descriptors drops below tx_free_thresh. For each done
+ * descriptor, free the associated buffer.
+ */
+ if (txq->nb_tx_free < txq->tx_free_thresh)
+ ice_tx_free_bufs(txq);
+
+ /* Use available descriptor only */
+ nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
+ if (unlikely(!nb_pkts))
+ return 0;
+
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
+ if ((txq->tx_tail + nb_pkts) > txq->nb_tx_desc) {
+ n = (uint16_t)(txq->nb_tx_desc - txq->tx_tail);
+ ice_tx_fill_hw_ring(txq, tx_pkts, n);
+ txr[txq->tx_next_rs].cmd_type_offset_bsz |=
+ rte_cpu_to_le_64(((uint64_t)ICE_TX_DESC_CMD_RS) <<
+ ICE_TXD_QW1_CMD_S);
+ txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
+ txq->tx_tail = 0;
+ }
+
+ /* Fill hardware descriptor ring with mbuf data */
+ ice_tx_fill_hw_ring(txq, tx_pkts + n, (uint16_t)(nb_pkts - n));
+ txq->tx_tail = (uint16_t)(txq->tx_tail + (nb_pkts - n));
+
+ /* Determin if RS bit needs to be set */
+ if (txq->tx_tail > txq->tx_next_rs) {
+ txr[txq->tx_next_rs].cmd_type_offset_bsz |=
+ rte_cpu_to_le_64(((uint64_t)ICE_TX_DESC_CMD_RS) <<
+ ICE_TXD_QW1_CMD_S);
+ txq->tx_next_rs =
+ (uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
+ if (txq->tx_next_rs >= txq->nb_tx_desc)
+ txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
+ }
+
+ if (txq->tx_tail >= txq->nb_tx_desc)
+ txq->tx_tail = 0;
+
+ /* Update the tx tail register */
+ ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+
+ return nb_pkts;
+}
+
+static uint16_t
+ice_xmit_pkts_simple(void *tx_queue,
+ struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t nb_tx = 0;
+
+ if (likely(nb_pkts <= ICE_TX_MAX_BURST))
+ return tx_xmit_pkts((struct ice_tx_queue *)tx_queue,
+ tx_pkts, nb_pkts);
+
+ while (nb_pkts) {
+ uint16_t ret, num = (uint16_t)RTE_MIN(nb_pkts,
+ ICE_TX_MAX_BURST);
+
+ ret = tx_xmit_pkts((struct ice_tx_queue *)tx_queue,
+ &tx_pkts[nb_tx], num);
+ nb_tx = (uint16_t)(nb_tx + ret);
+ nb_pkts = (uint16_t)(nb_pkts - ret);
+ if (ret < num)
+ break;
+ }
+
+ return nb_tx;
+}
+
+void __rte_cold
+ice_set_rx_function(struct rte_eth_dev *dev)
+{
+ PMD_INIT_FUNC_TRACE();
+ struct ice_adapter *ad =
+ ICE_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+#ifdef RTE_ARCH_X86
+ struct ice_rx_queue *rxq;
+ int i;
+ int rx_check_ret = -1;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ ad->rx_use_avx512 = false;
+ ad->rx_use_avx2 = false;
+ rx_check_ret = ice_rx_vec_dev_check(dev);
+ if (rx_check_ret >= 0 && ad->rx_bulk_alloc_allowed &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128) {
+ ad->rx_vec_allowed = true;
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ rxq = dev->data->rx_queues[i];
+ if (rxq && ice_rxq_vec_setup(rxq)) {
+ ad->rx_vec_allowed = false;
+ break;
+ }
+ }
+
+ if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512 &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1 &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) == 1)
+#ifdef CC_AVX512_SUPPORT
+ ad->rx_use_avx512 = true;
+#else
+ PMD_DRV_LOG(NOTICE,
+ "AVX512 is not supported in build env");
+#endif
+ if (!ad->rx_use_avx512 &&
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2) == 1 ||
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1) &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_256)
+ ad->rx_use_avx2 = true;
+
+ } else {
+ ad->rx_vec_allowed = false;
+ }
+ }
+
+ if (ad->rx_vec_allowed) {
+ if (dev->data->scattered_rx) {
+ if (ad->rx_use_avx512) {
+#ifdef CC_AVX512_SUPPORT
+ if (rx_check_ret == ICE_VECTOR_OFFLOAD_PATH) {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX512 OFFLOAD Vector Scattered Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_scattered_pkts_vec_avx512_offload;
+ } else {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX512 Vector Scattered Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_scattered_pkts_vec_avx512;
+ }
+#endif
+ } else if (ad->rx_use_avx2) {
+ if (rx_check_ret == ICE_VECTOR_OFFLOAD_PATH) {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX2 OFFLOAD Vector Scattered Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_scattered_pkts_vec_avx2_offload;
+ } else {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX2 Vector Scattered Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_scattered_pkts_vec_avx2;
+ }
+ } else {
+ PMD_DRV_LOG(DEBUG,
+ "Using Vector Scattered Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst = ice_recv_scattered_pkts_vec;
+ }
+ } else {
+ if (ad->rx_use_avx512) {
+#ifdef CC_AVX512_SUPPORT
+ if (rx_check_ret == ICE_VECTOR_OFFLOAD_PATH) {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX512 OFFLOAD Vector Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_pkts_vec_avx512_offload;
+ } else {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX512 Vector Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_pkts_vec_avx512;
+ }
+#endif
+ } else if (ad->rx_use_avx2) {
+ if (rx_check_ret == ICE_VECTOR_OFFLOAD_PATH) {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX2 OFFLOAD Vector Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_pkts_vec_avx2_offload;
+ } else {
+ PMD_DRV_LOG(NOTICE,
+ "Using AVX2 Vector Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst =
+ ice_recv_pkts_vec_avx2;
+ }
+ } else {
+ PMD_DRV_LOG(DEBUG,
+ "Using Vector Rx (port %d).",
+ dev->data->port_id);
+ dev->rx_pkt_burst = ice_recv_pkts_vec;
+ }
+ }
+ return;
+ }