[RFC PATCH 19/27] net/intel: avoid writing the final pkt descriptor twice

[Bruce Richardson]

In the scalar datapath, there is a loop to handle multi-segment, and
multi-descriptor packets on Tx. After that loop, the end-of-packet bit
was written to the descriptor separately, meaning that for each
single-descriptor packet there were two writes to the second quad-word -
basically 3 x 64-bit writes rather than just 2. Adjusting the code to
compute the EOP bit inside the loop saves that extra write per packet
and so improves performance.

Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
---
 drivers/net/intel/common/tx_scalar_fns.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/intel/common/tx_scalar_fns.h b/drivers/net/intel/common/tx_scalar_fns.h
index 6079a558e4..7b643fcf44 100644
--- a/drivers/net/intel/common/tx_scalar_fns.h
+++ b/drivers/net/intel/common/tx_scalar_fns.h
@@ -378,6 +378,10 @@ ci_xmit_pkts(struct ci_tx_queue *txq,
 				txn = &sw_ring[txe->next_id];
 			}
 
+			/* fill the last descriptor with End of Packet (EOP) bit */
+			if (m_seg->next == NULL)
+				td_cmd |= CI_TX_DESC_CMD_EOP;
+
 			txd->buffer_addr = rte_cpu_to_le_64(buf_dma_addr);
 			txd->cmd_type_offset_bsz = rte_cpu_to_le_64(CI_TX_DESC_DTYPE_DATA |
 				((uint64_t)td_cmd << CI_TXD_QW1_CMD_S) |
@@ -390,21 +394,17 @@ ci_xmit_pkts(struct ci_tx_queue *txq,
 			txe = txn;
 			m_seg = m_seg->next;
 		} while (m_seg);
-
-		/* fill the last descriptor with End of Packet (EOP) bit */
-		td_cmd |= CI_TX_DESC_CMD_EOP;
 		txq->nb_tx_used = (uint16_t)(txq->nb_tx_used + nb_used);
 		txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_used);
 
 		/* set RS bit on the last descriptor of one packet */
 		if (txq->nb_tx_used >= txq->tx_rs_thresh) {
-			td_cmd |= CI_TX_DESC_CMD_RS;
+			txd->cmd_type_offset_bsz |=
+					rte_cpu_to_le_64(CI_TX_DESC_CMD_RS << CI_TXD_QW1_CMD_S);
 
 			/* Update txq RS bit counters */
 			txq->nb_tx_used = 0;
 		}
-		txd->cmd_type_offset_bsz |=
-				rte_cpu_to_le_64(((uint64_t)td_cmd) << CI_TXD_QW1_CMD_S);
 
 		if (ts_fns != NULL)
 			ts_id = ts_fns->write_ts_desc(txq, tx_pkt, tx_id, ts_id);
-- 
2.51.0