net/qede: get consumer index once

Calling ecore_chain_get_cons_idx repeatedly is slower than calling it
once and using the result for the remainder of qede_process_tx_compl.

Signed-off-by: Balazs Nemeth <bnemeth@redhat.com>
Reviewed-by: Igor Russkikh <irusskikh@marvell.com>

diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
index d2f77ed..0002e2c 100644 (file)
--- a/drivers/net/qede/qede_rxtx.c
+++ b/drivers/net/qede/qede_rxtx.c
@@ -882,12 +882,13 @@ qede_tx_queue_start(struct rte_eth_dev *eth_dev, uint16_t tx_queue_id)
        return rc;
 }
 
-static inline void
+static inline uint16_t
 qede_free_tx_pkt(struct qede_tx_queue *txq)
 {
        struct rte_mbuf *mbuf;
        uint16_t nb_segs;
        uint16_t idx;
+       uint16_t ret;
 
        idx = TX_CONS(txq);
        mbuf = txq->sw_tx_ring[idx];
@@ -895,20 +896,22 @@ qede_free_tx_pkt(struct qede_tx_queue *txq)
                nb_segs = mbuf->nb_segs;
                PMD_TX_LOG(DEBUG, txq, "nb_segs to free %u\n", nb_segs);
 
+               ret = nb_segs;
                while (nb_segs) {
                        /* It's like consuming rxbuf in recv() */
                        ecore_chain_consume(&txq->tx_pbl);
-                       txq->nb_tx_avail++;
                        nb_segs--;
                }
+
                rte_pktmbuf_free(mbuf);
                txq->sw_tx_ring[idx] = NULL;
                txq->sw_tx_cons++;
                PMD_TX_LOG(DEBUG, txq, "Freed tx packet\n");
        } else {
                ecore_chain_consume(&txq->tx_pbl);
-               txq->nb_tx_avail++;
+               ret = 1;
        }
+       return ret;
 }
 
 static inline void
@@ -916,19 +919,22 @@ qede_process_tx_compl(__rte_unused struct ecore_dev *edev,
                      struct qede_tx_queue *txq)
 {
        uint16_t hw_bd_cons;
-#ifdef RTE_LIBRTE_QEDE_DEBUG_TX
        uint16_t sw_tx_cons;
-#endif
+       uint16_t remaining;
 
        rte_compiler_barrier();
+       sw_tx_cons = ecore_chain_get_cons_idx(&txq->tx_pbl);
        hw_bd_cons = rte_le_to_cpu_16(*txq->hw_cons_ptr);
 #ifdef RTE_LIBRTE_QEDE_DEBUG_TX
-       sw_tx_cons = ecore_chain_get_cons_idx(&txq->tx_pbl);
        PMD_TX_LOG(DEBUG, txq, "Tx Completions = %u\n",
                   abs(hw_bd_cons - sw_tx_cons));
 #endif
-       while (hw_bd_cons !=  ecore_chain_get_cons_idx(&txq->tx_pbl))
-               qede_free_tx_pkt(txq);
+
+       remaining = hw_bd_cons - sw_tx_cons;
+       txq->nb_tx_avail += remaining;
+
+       while (remaining)
+               remaining -= qede_free_tx_pkt(txq);
 }
 
 static int qede_drain_txq(struct qede_dev *qdev,