From: Lennert Buytenhek Date: Sun, 14 Sep 2008 13:50:32 +0000 (+0200) Subject: mv643xx_eth: avoid reading ->byte_cnt twice during receive processing X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=6b8f90c276ac25cd37f143a00d467a8ccb19c4c6;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git mv643xx_eth: avoid reading ->byte_cnt twice during receive processing Currently, the receive processing reads ->byte_cnt twice (once to update interface statistics and once to properly size the data area of the received skb), but since receive descriptors live in uncached memory, caching this value in a local variable saves one uncached access, and increases routing performance a tiny little bit more. Signed-off-by: Lennert Buytenhek --- diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index 4fbd62e45ae9..6564be122acf 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -477,6 +477,7 @@ static int rxq_process(struct rx_queue *rxq, int budget) struct rx_desc *rx_desc; unsigned int cmd_sts; struct sk_buff *skb; + u16 byte_cnt; rx_desc = &rxq->rx_desc_area[rxq->rx_curr_desc]; @@ -499,6 +500,8 @@ static int rxq_process(struct rx_queue *rxq, int budget) mp->work_rx_refill |= 1 << rxq->index; + byte_cnt = rx_desc->byte_cnt; + /* * Update statistics. * @@ -508,7 +511,7 @@ static int rxq_process(struct rx_queue *rxq, int budget) * byte CRC at the end of the packet (which we do count). */ stats->rx_packets++; - stats->rx_bytes += rx_desc->byte_cnt - 2; + stats->rx_bytes += byte_cnt - 2; /* * In case we received a packet without first / last bits @@ -537,7 +540,7 @@ static int rxq_process(struct rx_queue *rxq, int budget) * The -4 is for the CRC in the trailer of the * received packet */ - skb_put(skb, rx_desc->byte_cnt - 2 - 4); + skb_put(skb, byte_cnt - 2 - 4); if (cmd_sts & LAYER_4_CHECKSUM_OK) { skb->ip_summed = CHECKSUM_UNNECESSARY;