+ /**
+ * 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;
+ struct rte_eth_dev *dev;
+
+ 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;
+
+ dev = ICE_VSI_TO_ETH_DEV(rxq->vsi);
+ 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;
+ struct rte_eth_dev *dev;
+
+ 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)) {
+ dev = ICE_VSI_TO_ETH_DEV(rxq->vsi);
+ 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_scattered_pkts_vec_avx512 ||
+#endif
+ dev->rx_pkt_burst == ice_recv_pkts_vec_avx2 ||
+ dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx2)
+ 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)