X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=sidebyside;f=drivers%2Fnet%2Fmlx5%2Fmlx5_rxtx_vec.h;h=4220b08dd21c6f951ae7e8fc5701d54f0f95c43f;hb=e2b4925ef7c11c4271b2c8fb46154d347cba26e2;hp=5df8e291e60a1dc2a336bfe83a23cd18332b8b83;hpb=12d468a62bc19ca08ee9964dcb923f67f87fba7d;p=dpdk.git

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. */