From 6cbf3d4abc2023412665b16eda557be5dee36e58 Mon Sep 17 00:00:00 2001 From: Furong Xu <0x1207@gmail.com> Date: Wed, 15 Jan 2025 11:27:05 +0800 Subject: [PATCH] net: stmmac: Convert prefetch() to net_prefetch() for received frames mainline inclusion from mainline-6.14-rc1 category: performance The size of DMA descriptors is 32 bytes at most. net_prefetch() for received frames, and keep prefetch() for descriptors. This patch brings ~4.8% driver performance improvement in a TCP RX throughput test with iPerf tool on a single isolated Cortex-A65 CPU core, 2.92 Gbits/sec increased to 3.06 Gbits/sec. Suggested-by: Joe Damato Signed-off-by: Furong Xu <0x1207@gmail.com> Reviewed-by: Yanteng Si Reviewed-by: Larysa Zaremba Reviewed-by: Joe Damato Signed-off-by: Paolo Abeni (cherry picked from commit 204182edb3107f87a40f34affb3de8851e1c5d68) Signed-off-by: Wentao Guan --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a13fd053c4f6..49efd5ca011d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5429,7 +5429,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dma_sync_single_for_cpu(priv->device, buf->addr, buf1_len, dma_dir); - prefetch(page_address(buf->page) + buf->page_offset); + net_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),