X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Fmlx5_rxtx_vec.h;h=6ddcbfb0ad28faf65cd4802fecc46a06b9c4f938;hb=c52ff36686a408fd5196452380e359120c2d1ed5;hp=44856bbffec7db1b8460e99145f55dfb0ce6de6a;hpb=8fd92a66c60a7310cf5ab91996b9b09447512a61;p=dpdk.git

diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.h b/drivers/net/mlx5/mlx5_rxtx_vec.h
index 44856bbffe..6ddcbfb0ad 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-3-Clause
  * Copyright 2017 6WIND S.A.
- * Copyright 2017 Mellanox.
+ * Copyright 2017 Mellanox Technologies, Ltd
  */
 
 #ifndef RTE_PMD_MLX5_RXTX_VEC_H_
@@ -9,8 +9,11 @@
 #include <rte_common.h>
 #include <rte_mbuf.h>
 
+#include <mlx5_prm.h>
+
 #include "mlx5_autoconf.h"
-#include "mlx5_prm.h"
+
+#include "mlx5_mr.h"
 
 /* HW checksum offload capabilities of vectorized Tx. */
 #define MLX5_VEC_TX_CKSUM_OFFLOAD_CAP \
@@ -19,11 +22,6 @@
 	 DEV_TX_OFFLOAD_TCP_CKSUM | \
 	 DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM)
 
-/* HW offload capabilities of vectorized Tx. */
-#define MLX5_VEC_TX_OFFLOAD_CAP \
-	(MLX5_VEC_TX_CKSUM_OFFLOAD_CAP | \
-	 DEV_TX_OFFLOAD_MULTI_SEGS)
-
 /*
  * Compile time sanity check for vectorized functions.
  */
@@ -59,13 +57,11 @@ S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, pkt_info) == 0);
 #endif
 S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, rx_hash_res) ==
 		  offsetof(struct mlx5_cqe, pkt_info) + 12);
-S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, rsvd1) +
-		  sizeof(((struct mlx5_cqe *)0)->rsvd1) ==
+S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, rsvd1) + 11 ==
 		  offsetof(struct mlx5_cqe, hdr_type_etc));
 S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, vlan_info) ==
 		  offsetof(struct mlx5_cqe, hdr_type_etc) + 2);
-S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, rsvd2) +
-		  sizeof(((struct mlx5_cqe *)0)->rsvd2) ==
+S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, lro_num_seg) + 12 ==
 		  offsetof(struct mlx5_cqe, byte_cnt));
 S_ASSERT_MLX5_CQE(offsetof(struct mlx5_cqe, sop_drop_qpn) ==
 		  RTE_ALIGN(offsetof(struct mlx5_cqe, sop_drop_qpn), 8));
@@ -87,21 +83,36 @@ mlx5_rx_replenish_bulk_mbuf(struct mlx5_rxq_data *rxq, uint16_t n)
 	const uint16_t q_mask = q_n - 1;
 	uint16_t elts_idx = rxq->rq_ci & q_mask;
 	struct rte_mbuf **elts = &(*rxq->elts)[elts_idx];
-	volatile struct mlx5_wqe_data_seg *wq = &(*rxq->wqes)[elts_idx];
+	volatile struct mlx5_wqe_data_seg *wq =
+		&((volatile struct mlx5_wqe_data_seg *)rxq->wqes)[elts_idx];
 	unsigned int i;
 
-	assert(n >= MLX5_VPMD_RXQ_RPLNSH_THRESH);
-	assert(n <= (uint16_t)(q_n - (rxq->rq_ci - rxq->rq_pi)));
-	assert(MLX5_VPMD_RXQ_RPLNSH_THRESH > MLX5_VPMD_DESCS_PER_LOOP);
+	MLX5_ASSERT(n >= MLX5_VPMD_RXQ_RPLNSH_THRESH(q_n));
+	MLX5_ASSERT(n <= (uint16_t)(q_n - (rxq->rq_ci - rxq->rq_pi)));
+	MLX5_ASSERT(MLX5_VPMD_RXQ_RPLNSH_THRESH(q_n) >
+		    MLX5_VPMD_DESCS_PER_LOOP);
 	/* Not to cross queue end. */
 	n = RTE_MIN(n - MLX5_VPMD_DESCS_PER_LOOP, q_n - elts_idx);
 	if (rte_mempool_get_bulk(rxq->mp, (void *)elts, n) < 0) {
 		rxq->stats.rx_nombuf += n;
 		return;
 	}
-	for (i = 0; i < n; ++i)
-		wq[i].addr = rte_cpu_to_be_64((uintptr_t)elts[i]->buf_addr +
+	for (i = 0; i < n; ++i) {
+		void *buf_addr;
+
+		/*
+		 * In order to support the mbufs with external attached
+		 * data buffer we should use the buf_addr pointer instead of
+		 * rte_mbuf_buf_addr(). It touches the mbuf itself and may
+		 * impact the performance.
+		 */
+		buf_addr = elts[i]->buf_addr;
+		wq[i].addr = rte_cpu_to_be_64((uintptr_t)buf_addr +
 					      RTE_PKTMBUF_HEADROOM);
+		/* If there's only one MR, no need to replace LKey in WQE. */
+		if (unlikely(mlx5_mr_btree_len(&rxq->mr_ctrl.cache_bh) > 1))
+			wq[i].lkey = mlx5_rx_mb2mr(rxq, elts[i]);
+	}
 	rxq->rq_ci += n;
 	/* Prevent overflowing into consumed mbufs. */
 	elts_idx = rxq->rq_ci & q_mask;