@@ -5497,10 +5497,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
/* 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);
@@ -5522,6 +5518,7 @@ 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);
xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq);
xdp_prepare_buff(&ctx.xdp, page_address(buf->page),
@@ -5596,6 +5593,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
} else if (buf1_len) {
dma_sync_single_for_cpu(priv->device, buf->addr,
buf1_len, dma_dir);
+ prefetch(page_address(buf->page) + buf->page_offset);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
buf->page, buf->page_offset, buf1_len,
priv->dma_conf.dma_buf_sz);
@@ -5608,6 +5606,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
if (buf2_len) {
dma_sync_single_for_cpu(priv->device, buf->sec_addr,
buf2_len, dma_dir);
+ prefetch(page_address(buf->sec_page));
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
buf->sec_page, 0, buf2_len,
priv->dma_conf.dma_buf_sz);
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> --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)