From 9c55c6bd86156d17df93bf947dc620222ee9f7e4 Mon Sep 17 00:00:00 2001 From: Yongseok Koh Date: Mon, 25 Mar 2019 12:13:10 -0700 Subject: [PATCH] net/mlx5: revert mbuf address calculation for x86 When replenishing mbufs on Rx, buffer address (mbuf->buf_addr) should be loaded. non-x86 processors (mostly RISC such as ARM and Power) are more vulnerable to load stall. For x86, reducing the number of instructions seems to matter most. For x86, this is simply a load but for other architectures, it is calculated from the address of mbuf structure by rte_mbuf_buf_addr() without having to load the first cacheline of the mbuf. Fixes: 12d468a62bc1 ("net/mlx5: fix instruction hotspot on replenishing Rx buffer") Cc: stable@dpdk.org Signed-off-by: Yongseok Koh Acked-by: Shahaf Shuler --- drivers/net/mlx5/mlx5_rxtx_vec.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.h b/drivers/net/mlx5/mlx5_rxtx_vec.h index 5df8e291e6..4220b08dd2 100644 --- a/drivers/net/mlx5/mlx5_rxtx_vec.h +++ b/drivers/net/mlx5/mlx5_rxtx_vec.h @@ -102,9 +102,21 @@ mlx5_rx_replenish_bulk_mbuf(struct mlx5_rxq_data *rxq, uint16_t n) return; } for (i = 0; i < n; ++i) { - void *buf_addr = rte_mbuf_buf_addr(elts[i], rxq->mp); + void *buf_addr; + /* + * Load the virtual address for Rx WQE. non-x86 processors + * (mostly RISC such as ARM and Power) are more vulnerable to + * load stall. For x86, reducing the number of instructions + * seems to matter most. + */ +#ifdef RTE_ARCH_X86_64 + buf_addr = elts[i]->buf_addr; + assert(buf_addr == rte_mbuf_buf_addr(elts[i], rxq->mp)); +#else + buf_addr = rte_mbuf_buf_addr(elts[i], rxq->mp); assert(buf_addr == elts[i]->buf_addr); +#endif 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. */