net/mlx5: adjust hash bucket size

[dpdk.git] / drivers / net / bnxt / bnxt_rxtx_vec_neon.c

diff --git a/drivers/net/bnxt/bnxt_rxtx_vec_neon.c b/drivers/net/bnxt/bnxt_rxtx_vec_neon.c
index a6fbc0b..263e6ec 100644 (file)
--- a/drivers/net/bnxt/bnxt_rxtx_vec_neon.c
+++ b/drivers/net/bnxt/bnxt_rxtx_vec_neon.c
@@ -158,9 +158,8 @@ descs_to_mbufs(uint32x4_t mm_rxcmp[4], uint32x4_t mm_rxcmp1[4],
        vst1q_u32((uint32_t *)&mbuf[3]->rx_descriptor_fields1, tmp);
 }
 
-uint16_t
-bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
-                  uint16_t nb_pkts)
+static uint16_t
+recv_burst_vec_neon(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 {
        struct bnxt_rx_queue *rxq = rx_queue;
        struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
@@ -185,9 +184,6 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
        if (rxq->rxrearm_nb >= rxq->rx_free_thresh)
                bnxt_rxq_rearm(rxq, rxr);
 
-       /* Return no more than RTE_BNXT_MAX_RX_BURST per call. */
-       nb_pkts = RTE_MIN(nb_pkts, RTE_BNXT_MAX_RX_BURST);
-
        cons = raw_cons & (cp_ring_size - 1);
        mbcons = (raw_cons / 2) & (rx_ring_size - 1);
 
@@ -204,17 +200,20 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
         * maximum number of packets to receive to be a multiple of the per-
         * loop count.
         */
-       if (nb_pkts < RTE_BNXT_DESCS_PER_LOOP)
-               desc_valid_mask >>= 16 * (RTE_BNXT_DESCS_PER_LOOP - nb_pkts);
-       else
-               nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_BNXT_DESCS_PER_LOOP);
+       if (nb_pkts < BNXT_RX_DESCS_PER_LOOP_VEC128) {
+               desc_valid_mask >>=
+                       16 * (BNXT_RX_DESCS_PER_LOOP_VEC128 - nb_pkts);
+       } else {
+               nb_pkts =
+                       RTE_ALIGN_FLOOR(nb_pkts, BNXT_RX_DESCS_PER_LOOP_VEC128);
+       }
 
        /* Handle RX burst request */
-       for (i = 0; i < nb_pkts; i += RTE_BNXT_DESCS_PER_LOOP,
-                                 cons += RTE_BNXT_DESCS_PER_LOOP * 2,
-                                 mbcons += RTE_BNXT_DESCS_PER_LOOP) {
-               uint32x4_t rxcmp1[RTE_BNXT_DESCS_PER_LOOP];
-               uint32x4_t rxcmp[RTE_BNXT_DESCS_PER_LOOP];
+       for (i = 0; i < nb_pkts; i += BNXT_RX_DESCS_PER_LOOP_VEC128,
+                                 cons += BNXT_RX_DESCS_PER_LOOP_VEC128 * 2,
+                                 mbcons += BNXT_RX_DESCS_PER_LOOP_VEC128) {
+               uint32x4_t rxcmp1[BNXT_RX_DESCS_PER_LOOP_VEC128];
+               uint32x4_t rxcmp[BNXT_RX_DESCS_PER_LOOP_VEC128];
                uint32x4_t info3_v;
                uint64x2_t t0, t1;
                uint32_t num_valid;
@@ -230,7 +229,7 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 #endif
 
                /* Prefetch four descriptor pairs for next iteration. */
-               if (i + RTE_BNXT_DESCS_PER_LOOP < nb_pkts) {
+               if (i + BNXT_RX_DESCS_PER_LOOP_VEC128 < nb_pkts) {
                        rte_prefetch0(&cp_desc_ring[cons + 8]);
                        rte_prefetch0(&cp_desc_ring[cons + 12]);
                }
@@ -288,7 +287,7 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                               rxr);
                nb_rx_pkts += num_valid;
 
-               if (num_valid < RTE_BNXT_DESCS_PER_LOOP)
+               if (num_valid < BNXT_RX_DESCS_PER_LOOP_VEC128)
                        break;
        }
 
@@ -297,14 +296,33 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 
                rxq->rxrearm_nb += nb_rx_pkts;
                cpr->cp_raw_cons += 2 * nb_rx_pkts;
-               cpr->valid =
-                       !!(cpr->cp_raw_cons & cpr->cp_ring_struct->ring_size);
                bnxt_db_cq(cpr);
        }
 
        return nb_rx_pkts;
 }
 
+uint16_t
+bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+       uint16_t cnt = 0;
+
+       while (nb_pkts > RTE_BNXT_MAX_RX_BURST) {
+               uint16_t burst;
+
+               burst = recv_burst_vec_neon(rx_queue, rx_pkts + cnt,
+                                           RTE_BNXT_MAX_RX_BURST);
+
+               cnt += burst;
+               nb_pkts -= burst;
+
+               if (burst < RTE_BNXT_MAX_RX_BURST)
+                       return cnt;
+       }
+
+       return cnt + recv_burst_vec_neon(rx_queue, rx_pkts + cnt, nb_pkts);
+}
+
 static void
 bnxt_handle_tx_cp_vec(struct bnxt_tx_queue *txq)
 {
@@ -333,7 +351,6 @@ bnxt_handle_tx_cp_vec(struct bnxt_tx_queue *txq)
                raw_cons = NEXT_RAW_CMP(raw_cons);
        } while (nb_tx_pkts < ring_mask);
 
-       cpr->valid = !!(raw_cons & cp_ring_struct->ring_size);
        if (nb_tx_pkts) {
                if (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
                        bnxt_tx_cmp_vec_fast(txq, nb_tx_pkts);