From 21d90f07bc85b031a0408be375dc7a2e514b1a4f Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Fri, 12 Jul 2019 22:25:07 -0700 Subject: [PATCH] ag71xx: rearrange ag71xx structs to remove holes Remove ____cacheline_aligned attribute to ring structs. This actually causes holes in the ag71xx struct as well as lower performance. Rearrange struct members to fall within respective cachelines. The RX ring struct now does not share a cacheline with the TX ring. The NAPI struct now takes up its own cachelines and does not share. According to pahole -C ag71xx -c 32 Before: struct ag71xx { /* size: 384, cachelines: 12, members: 22 */ /* sum members: 375, holes: 2, sum holes: 9 */ After: struct ag71xx { /* size: 376, cachelines: 12, members: 22 */ /* last cacheline: 24 bytes */ Signed-off-by: Rosen Penev Signed-off-by: Rui Salvaterra [Reword and fix typos] --- .../net/ethernet/atheros/ag71xx/ag71xx.h | 32 ++++++++++--------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/target/linux/ath79/files/drivers/net/ethernet/atheros/ag71xx/ag71xx.h b/target/linux/ath79/files/drivers/net/ethernet/atheros/ag71xx/ag71xx.h index fca072a83a4d3b..141c657f008c39 100644 --- a/target/linux/ath79/files/drivers/net/ethernet/atheros/ag71xx/ag71xx.h +++ b/target/linux/ath79/files/drivers/net/ethernet/atheros/ag71xx/ag71xx.h @@ -107,13 +107,16 @@ struct ag71xx_buf { }; struct ag71xx_ring { - struct ag71xx_buf *buf; - u8 *descs_cpu; - dma_addr_t descs_dma; - u16 desc_split; - u16 order; + /* "Hot" fields in the data path. */ unsigned int curr; unsigned int dirty; + + /* "Cold" fields - not used in the data path. */ + struct ag71xx_buf *buf; + u16 order; + u16 desc_split; + dma_addr_t descs_dma; + u8 *descs_cpu; }; struct ag71xx_int_stats { @@ -151,21 +154,20 @@ struct ag71xx { * Critical data related to the per-packet data path are clustered * early in this structure to help improve the D-cache footprint. */ - struct ag71xx_ring rx_ring ____cacheline_aligned; - struct ag71xx_ring tx_ring ____cacheline_aligned; + struct ag71xx_ring rx_ring; + u16 rx_buf_size; + u16 rx_buf_offset; + u32 msg_enable; + struct ag71xx_ring tx_ring; int mac_idx; - u16 desc_pktlen_mask; - u16 rx_buf_size; - u8 rx_buf_offset; u8 tx_hang_workaround:1; + struct napi_struct napi; struct net_device *dev; struct platform_device *pdev; spinlock_t lock; - struct napi_struct napi; - u32 msg_enable; /* * From this point onwards we're not looking at per-packet fields. @@ -184,12 +186,12 @@ struct ag71xx { unsigned int speed; int duplex; - struct delayed_work restart_work; - struct timer_list oom_timer; - struct reset_control *mac_reset; struct reset_control *mdio_reset; + struct delayed_work restart_work; + struct timer_list oom_timer; + u32 fifodata[3]; u32 plldata[3]; u32 pllreg[3];