net/bnxt: fix Rx burst size constraint

The burst receive function should return all packets currently
present in the receive ring up to the requested burst size,
update vector mode receive functions accordingly.

Fixes: 398358341419 ("net/bnxt: support NEON")
Fixes: bc4a000f2f53 ("net/bnxt: implement SSE vector mode")
Cc: stable@dpdk.org
Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>

diff --git a/drivers/net/bnxt/bnxt_rxtx_vec_neon.c b/drivers/net/bnxt/bnxt_rxtx_vec_neon.c
index a6fbc0b..a6e630e 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);
 
@@ -305,6 +301,27 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
        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)
 {

diff --git a/drivers/net/bnxt/bnxt_rxtx_vec_sse.c b/drivers/net/bnxt/bnxt_rxtx_vec_sse.c
index 6dd18a0..fe074f8 100644 (file)
--- a/drivers/net/bnxt/bnxt_rxtx_vec_sse.c
+++ b/drivers/net/bnxt/bnxt_rxtx_vec_sse.c
@@ -149,9 +149,8 @@ descs_to_mbufs(__m128i mm_rxcmp[4], __m128i mm_rxcmp1[4],
        _mm_store_si128((void *)&mbuf[3]->rx_descriptor_fields1, t0);
 }
 
-uint16_t
-bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
-                  uint16_t nb_pkts)
+static uint16_t
+recv_burst_vec_sse(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 {
        struct bnxt_rx_queue *rxq = rx_queue;
        const __m128i mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer);
@@ -176,9 +175,6 @@ 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);
 
@@ -286,6 +282,27 @@ bnxt_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
        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_sse(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_sse(rx_queue, rx_pkts + cnt, nb_pkts);
+}
+
 static void
 bnxt_handle_tx_cp_vec(struct bnxt_tx_queue *txq)
 {