net/bnxt: fix scalar Tx completion handling

[ upstream commit 2b5a36f ]

Preserve the raw (unmasked) transmit completion ring
consumer index.

Remove cache prefetches that have no measurable performance
benefit.

Fixes: c7de419 ("net/bnxt: modify ring index logic")

Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>

drivers/net/bnxt/bnxt_txr.c

@@ -398,40 +398,38 @@ static void bnxt_tx_cmp(struct bnxt_tx_queue *txq, int nr_pkts)
 
 static int bnxt_handle_tx_cp(struct bnxt_tx_queue *txq)
 {
+	uint32_t nb_tx_pkts = 0, cons, ring_mask, opaque;
 	struct bnxt_cp_ring_info *cpr = txq->cp_ring;
 	uint32_t raw_cons = cpr->cp_raw_cons;
-	uint32_t cons;
-	uint32_t nb_tx_pkts = 0;
+	struct bnxt_ring *cp_ring_struct;
 	struct tx_cmpl *txcmp;
-	struct cmpl_base *cp_desc_ring = cpr->cp_desc_ring;
-	struct bnxt_ring *cp_ring_struct = cpr->cp_ring_struct;
-	uint32_t ring_mask = cp_ring_struct->ring_mask;
-	uint32_t opaque = 0;
 
 	if (bnxt_tx_bds_in_hw(txq) < txq->tx_free_thresh)
 		return 0;
 
+	cp_ring_struct = cpr->cp_ring_struct;
+	ring_mask = cp_ring_struct->ring_mask;
+
 	do {
 		cons = RING_CMPL(ring_mask, raw_cons);
 		txcmp = (struct tx_cmpl *)&cpr->cp_desc_ring[cons];
-		rte_prefetch_non_temporal(&cp_desc_ring[(cons + 2) &
-							ring_mask]);
 
-		if (!CMPL_VALID(txcmp, cpr->valid))
+		if (!CMP_VALID(txcmp, raw_cons, cp_ring_struct))
 			break;
-		opaque = rte_cpu_to_le_32(txcmp->opaque);
-		NEXT_CMPL(cpr, cons, cpr->valid, 1);
-		rte_prefetch0(&cp_desc_ring[cons]);
+
+		opaque = rte_le_to_cpu_32(txcmp->opaque);
 
 		if (CMP_TYPE(txcmp) == TX_CMPL_TYPE_TX_L2)
 			nb_tx_pkts += opaque;
 		else
 			RTE_LOG_DP(ERR, PMD,
 					"Unhandled CMP type %02x\n",
 					CMP_TYPE(txcmp));
-		raw_cons = cons;
+		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) {
 		bnxt_tx_cmp(txq, nb_tx_pkts);
 		cpr->cp_raw_cons = raw_cons;