[net-next,v3,0/7] bcm63xx_enet: major makeover of driver

Message

Sieng-Piaw Liew Jan. 6, 2021, 2:42 p.m. UTC

This patch series aim to improve the bcm63xx_enet driver by integrating the
latest networking features, i.e. batched rx processing, BQL, build_skb,
etc.

The newer enetsw SoCs are found to be able to do unaligned rx DMA by adding
NET_IP_ALIGN padding which, combined with these patches, improved packet
processing performance by ~50% on BCM6328.

Older non-enetsw SoCs still benefit mainly from rx batching. Performance
improvement of ~30% is observed on BCM6333.

The BCM63xx SoCs are designed for routers. As such, having BQL is
beneficial as well as trivial to add.

v3:
* Simplify xmit_more patch by not moving around the code needlessly.
* Fix indentation in xmit_more patch.
* Fix indentation in build_skb patch.
* Split rx ring cleanup patch from build_skb patch and precede build_skb
  patch for better understanding, as suggested by Florian Fainelli.

v2:
* Add xmit_more support and rx loop improvisation patches.
* Moved BQL netdev_reset_queue() to bcm_enet_stop()/bcm_enetsw_stop()
  functions as suggested by Florian Fainelli.
* Improved commit messages.

Sieng Piaw Liew (7):
  bcm63xx_enet: batch process rx path
  bcm63xx_enet: add BQL support
  bcm63xx_enet: add xmit_more support
  bcm63xx_enet: alloc rx skb with NET_IP_ALIGN
  bcm63xx_enet: consolidate rx SKB ring cleanup code
  bcm63xx_enet: convert to build_skb
  bcm63xx_enet: improve rx loop

 drivers/net/ethernet/broadcom/bcm63xx_enet.c | 186 +++++++++----------
 drivers/net/ethernet/broadcom/bcm63xx_enet.h |  14 +-
 2 files changed, 103 insertions(+), 97 deletions(-)

Comments

Florian Fainelli Jan. 6, 2021, 5:03 p.m. UTC | #1

On 1/6/21 6:42 AM, Sieng Piaw Liew wrote:
> This patch series aim to improve the bcm63xx_enet driver by integrating the
> latest networking features, i.e. batched rx processing, BQL, build_skb,
> etc.
> 
> The newer enetsw SoCs are found to be able to do unaligned rx DMA by adding
> NET_IP_ALIGN padding which, combined with these patches, improved packet
> processing performance by ~50% on BCM6328.
> 
> Older non-enetsw SoCs still benefit mainly from rx batching. Performance
> improvement of ~30% is observed on BCM6333.
> 
> The BCM63xx SoCs are designed for routers. As such, having BQL is
> beneficial as well as trivial to add.
> 
> v3:
> * Simplify xmit_more patch by not moving around the code needlessly.
> * Fix indentation in xmit_more patch.
> * Fix indentation in build_skb patch.
> * Split rx ring cleanup patch from build_skb patch and precede build_skb
>   patch for better understanding, as suggested by Florian Fainelli.

Thanks for addressing the feedback given, for patches that have not
changed, please carry forward any tag you have been given (Reviewed-by,
Acked-by, etc.) such that we don't have to reply to those patches again.

Jakub Kicinski Jan. 7, 2021, 8:41 p.m. UTC | #2

On Wed,  6 Jan 2021 22:42:01 +0800 Sieng Piaw Liew wrote:
> This patch series aim to improve the bcm63xx_enet driver by integrating the
> latest networking features, i.e. batched rx processing, BQL, build_skb,
> etc.
> 
> The newer enetsw SoCs are found to be able to do unaligned rx DMA by adding
> NET_IP_ALIGN padding which, combined with these patches, improved packet
> processing performance by ~50% on BCM6328.
> 
> Older non-enetsw SoCs still benefit mainly from rx batching. Performance
> improvement of ~30% is observed on BCM6333.
> 
> The BCM63xx SoCs are designed for routers. As such, having BQL is
> beneficial as well as trivial to add.
> 
> v3:
> * Simplify xmit_more patch by not moving around the code needlessly.
> * Fix indentation in xmit_more patch.
> * Fix indentation in build_skb patch.
> * Split rx ring cleanup patch from build_skb patch and precede build_skb
>   patch for better understanding, as suggested by Florian Fainelli.
> 
> v2:
> * Add xmit_more support and rx loop improvisation patches.
> * Moved BQL netdev_reset_queue() to bcm_enet_stop()/bcm_enetsw_stop()
>   functions as suggested by Florian Fainelli.
> * Improved commit messages.

Applied, thanks!