Received-SPF: pass (google.com: domain of linux-kernel+bounces-203162-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Subject: Re: [net-next PATCH v5 7/7] net: ravb: Allocate RX buffers via page
 pool
To: Paul Barker <paul.barker.ct@bp.renesas.com>, "David S. Miller"
	<davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski
	<kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	=?UTF-8?Q?Niklas_S=c3=b6derlund?= <niklas.soderlund+renesas@ragnatech.se>,
	Simon Horman <horms@kernel.org>
CC: Biju Das <biju.das.jz@bp.renesas.com>, Claudiu Beznea
	<claudiu.beznea.uj@bp.renesas.com>, Yoshihiro Shimoda
	<yoshihiro.shimoda.uh@renesas.com>, <netdev@vger.kernel.org>,
	<linux-renesas-soc@vger.kernel.org>, <linux-kernel@vger.kernel.org>
References: <20240604072825.7490-1-paul.barker.ct@bp.renesas.com>
 <20240604072825.7490-8-paul.barker.ct@bp.renesas.com>
From: Sergey Shtylyov <s.shtylyov@omp.ru>
Organization: Open Mobile Platform
Message-ID: <49755f09-66de-71f2-bf66-ccd0d94d3f04@omp.ru>
Date: Wed, 5 Jun 2024 23:14:50 +0300
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101
 Thunderbird/78.10.1
Precedence: bulk
MIME-Version: 1.0
In-Reply-To: <20240604072825.7490-8-paul.barker.ct@bp.renesas.com>
Content-Type: text/plain; charset="utf-8"
Content-Language: en-US
Content-Transfer-Encoding: 7bit
X-KSE-Attachment-Filter-Triggered-Filters: Clean
X-KSE-BulkMessagesFiltering-Scan-Result: InTheLimit

On 6/4/24 10:28 AM, Paul Barker wrote:

> This patch makes multiple changes that can't be separated:
> 
>   1) Allocate plain RX buffers via a page pool instead of allocating
>      SKBs, then use build_skb() when a packet is received.
>   2) For GbEth IP, reduce the RX buffer size to 2kB.
>   3) For GbEth IP, merge packets which span more than one RX descriptor
>      as SKB fragments instead of copying data.
> 
> Implementing (1) without (2) would require the use of an order-1 page
> pool (instead of an order-0 page pool split into page fragments) for
> GbEth.
> 
> Implementing (2) without (3) would leave us no space to re-assemble
> packets which span more than one RX descriptor.
> 
> Implementing (3) without (1) would not be possible as the network stack
> expects to use put_page() or page_pool_put_page() to free SKB fragments
> after an SKB is consumed.
> 
> RX checksum offload support is adjusted to handle both linear and
> nonlinear (fragmented) packets.
> 
> This patch gives the following improvements during testing with iperf3.
> 
>   * RZ/G2L:
>     * TCP RX: same bandwidth at -43% CPU load (70% -> 40%)
>     * UDP RX: same bandwidth at -17% CPU load (88% -> 74%)
> 
>   * RZ/G2UL:
>     * TCP RX: +30% bandwidth (726Mbps -> 941Mbps)
>     * UDP RX: +417% bandwidth (108Mbps -> 558Mbps)
> 
>   * RZ/G3S:
>     * TCP RX: +64% bandwidth (562Mbps -> 920Mbps)
>     * UDP RX: +420% bandwidth (90Mbps -> 468Mbps)
> 
>   * RZ/Five:
>     * TCP RX: +217% bandwidth (145Mbps -> 459Mbps)
>     * UDP RX: +470% bandwidth (20Mbps -> 114Mbps)
> 
> There is no significant impact on bandwidth or CPU load in testing on
> RZ/G2H or R-Car M3N.
> 
> Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>

Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>

[...]

MBR, Sergey