[PATCH net-next v2 1/2] net: ethernet: mtk_eth_soc: use prefetch methods

[Elad Yifee <eladwf@gmail.com>]

Utilize kernel prefetch methods for faster cache line access.
This change boosts driver performance,
allowing the CPU to handle about 5% more packets/sec.

Signed-off-by: Elad Yifee <eladwf@gmail.com>
---
Changes in v2:
	- use net_prefetchw as suggested by Joe Damato
	- add (NET_SKB_PAD + eth->ip_align) offset to prefetched data
	- use eth->ip_align instead of NET_IP_ALIGN as it could be 0,
	depending on the platform 
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 16ca427cf4c3..4d0052dbe3f4 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1963,6 +1963,7 @@ static u32 mtk_xdp_run(struct mtk_eth *eth, struct mtk_rx_ring *ring,
 	if (!prog)
 		goto out;
 
+	net_prefetchw(xdp->data_hard_start);
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_PASS:
@@ -2038,6 +2039,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 		idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size);
 		rxd = ring->dma + idx * eth->soc->rx.desc_size;
+		prefetch(rxd);
 		data = ring->data[idx];
 
 		if (!mtk_rx_get_desc(eth, &trxd, rxd))
@@ -2105,6 +2107,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			if (ret != XDP_PASS)
 				goto skip_rx;
 
+			net_prefetch(xdp.data_meta);
 			skb = build_skb(data, PAGE_SIZE);
 			if (unlikely(!skb)) {
 				page_pool_put_full_page(ring->page_pool,
@@ -2113,6 +2116,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 				goto skip_rx;
 			}
 
+			net_prefetchw(skb->data);
 			skb_reserve(skb, xdp.data - xdp.data_hard_start);
 			skb_put(skb, xdp.data_end - xdp.data);
 			skb_mark_for_recycle(skb);
@@ -2143,6 +2147,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			dma_unmap_single(eth->dma_dev, ((u64)trxd.rxd1 | addr64),
 					 ring->buf_size, DMA_FROM_DEVICE);
 
+			net_prefetch(data + NET_SKB_PAD + eth->ip_align);
 			skb = build_skb(data, ring->frag_size);
 			if (unlikely(!skb)) {
 				netdev->stats.rx_dropped++;
@@ -2150,7 +2155,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 				goto skip_rx;
 			}
 
-			skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+			net_prefetchw(skb->data);
+			skb_reserve(skb, NET_SKB_PAD + eth->ip_align);
 			skb_put(skb, pktlen);
 		}
 
-- 
2.45.2