[PATCH v11 2/2] net/i40e: replace put function

[Kamalakshitha Aligeri <kamalakshitha.aligeri@arm.com>]

Integrated zero-copy put API in mempool cache in i40e PMD.
On Ampere Altra server, l3fwd single core's performance improves by 5%
with the new API

Signed-off-by: Kamalakshitha Aligeri <kamalakshitha.aligeri@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Feifei Wang <feifei.wang2@arm.com>
---
 .mailmap                                |  1 +
 drivers/net/i40e/i40e_rxtx_vec_common.h | 27 ++++++++++++++++++++-----
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/.mailmap b/.mailmap
index a9f4f28fba..2581d0efe7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -677,6 +677,7 @@ Kai Ji <kai.ji@intel.com>
 Kaiwen Deng <kaiwenx.deng@intel.com>
 Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
 Kamalakannan R <kamalakannan.r@intel.com>
+Kamalakshitha Aligeri <kamalakshitha.aligeri@arm.com>
 Kamil Bednarczyk <kamil.bednarczyk@intel.com>
 Kamil Chalupnik <kamilx.chalupnik@intel.com>
 Kamil Rytarowski <kamil.rytarowski@caviumnetworks.com>
diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
index fe1a6ec75e..35cdb31b2e 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -95,18 +95,35 @@ i40e_tx_free_bufs(struct i40e_tx_queue *txq)

 	n = txq->tx_rs_thresh;

-	 /* first buffer to free from S/W ring is at index
-	  * tx_next_dd - (tx_rs_thresh-1)
-	  */
+	/* first buffer to free from S/W ring is at index
+	 * tx_next_dd - (tx_rs_thresh-1)
+	 */
 	txep = &txq->sw_ring[txq->tx_next_dd - (n - 1)];

 	if (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) {
+		struct rte_mempool *mp = txep[0].mbuf->pool;
+		struct rte_mempool_cache *cache = rte_mempool_default_cache(mp, rte_lcore_id());
+		void **cache_objs;
+
+		if (unlikely(!cache))
+			goto fallback;
+
+		cache_objs = rte_mempool_cache_zc_put_bulk(cache, mp, n);
+		if (unlikely(!cache_objs))
+			goto fallback;
+
 		for (i = 0; i < n; i++) {
-			free[i] = txep[i].mbuf;
+			cache_objs[i] = txep[i].mbuf;
 			/* no need to reset txep[i].mbuf in vector path */
 		}
-		rte_mempool_put_bulk(free[0]->pool, (void **)free, n);
 		goto done;
+
+fallback:
+		for (i = 0; i < n; i++)
+			free[i] = txep[i].mbuf;
+		rte_mempool_generic_put(mp, (void **)free, n, cache);
+		goto done;
+
 	}

 	m = rte_pktmbuf_prefree_seg(txep[0].mbuf);
--
2.25.1