From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yongseok Koh Subject: [PATCH v2 2/2] net/mlx5: fix instruction hotspot on replenishing Rx buffer Date: Wed, 9 Jan 2019 05:19:08 -0800 Message-ID: <20190109131908.4949-2-yskoh@mellanox.com> References: <20190109085426.39965-1-yskoh@mellanox.com> <20190109131908.4949-1-yskoh@mellanox.com> Cc: dev@dpdk.org, david.marchand@redhat.com, stable@dpdk.org To: olivier.matz@6wind.com, shahafs@mellanox.com Return-path: Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by dpdk.org (Postfix) with ESMTP id 89C0A1B46D for ; Wed, 9 Jan 2019 14:19:22 +0100 (CET) In-Reply-To: <20190109131908.4949-1-yskoh@mellanox.com> List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed to be accessed as it is static and easily calculated from the mbuf address. Accessing the mbuf content causes unnecessary load stall and it is worsened on ARM. Fixes: 545b884b1da3 ("net/mlx5: fix buffer address posting in SSE Rx") Cc: stable@dpdk.org Signed-off-by: Yongseok Koh --- v2: * use the newly introduced API - rte_mbuf_buf_addr_default() * fix error in assert drivers/net/mlx5/mlx5_rxtx_vec.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.h b/drivers/net/mlx5/mlx5_rxtx_vec.h index fda7004e2d..154934d92d 100644 --- a/drivers/net/mlx5/mlx5_rxtx_vec.h +++ b/drivers/net/mlx5/mlx5_rxtx_vec.h @@ -102,8 +102,10 @@ mlx5_rx_replenish_bulk_mbuf(struct mlx5_rxq_data *rxq, uint16_t n) return; } for (i = 0; i < n; ++i) { - wq[i].addr = rte_cpu_to_be_64((uintptr_t)elts[i]->buf_addr + - RTE_PKTMBUF_HEADROOM); + void *buf_addr = rte_mbuf_buf_addr_default(elts[i], rxq->mp); + + assert(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]); -- 2.11.0