From 79d0dd9a45b72aa4a2edb1d66babe584669717c2 Mon Sep 17 00:00:00 2001 From: Furong Xu <0x1207@gmail.com> Date: Wed, 15 Jan 2025 11:27:04 +0800 Subject: [PATCH] net: stmmac: Optimize cache prefetch in RX path Current code prefetches cache lines for the received frame first, and then dma_sync_single_for_cpu() against this frame, this is wrong. Cache prefetch should be triggered after dma_sync_single_for_cpu(). This patch brings ~2.8% driver performance improvement in a TCP RX throughput test with iPerf tool on a single isolated Cortex-A65 CPU core, 2.84 Gbits/sec increased to 2.92 Gbits/sec. Signed-off-by: Furong Xu <0x1207@gmail.com> Reviewed-by: Alexander Lobakin Reviewed-by: Yanteng Si Signed-off-by: Paolo Abeni Signed-off-by: maoxiaochuan --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7bf275f12..74f2f7064 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5515,10 +5515,6 @@ read_again: /* Buffer is good. Go on. */ - prefetch(page_address(buf->page) + buf->page_offset); - if (buf->sec_page) - prefetch(page_address(buf->sec_page)); - buf1_len = stmmac_rx_buf1_len(priv, p, status, len); len += buf1_len; buf2_len = stmmac_rx_buf2_len(priv, p, status, len); @@ -5540,6 +5536,7 @@ read_again: dma_sync_single_for_cpu(priv->device, buf->addr, buf1_len, dma_dir); + prefetch(page_address(buf->page) + buf->page_offset); xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq); xdp_prepare_buff(&ctx.xdp, page_address(buf->page),