[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <09442385-573c-4756-8c30-296631bc6272@lunn.ch>
Date: Sat, 25 Jan 2025 20:08:12 +0100
From: Andrew Lunn <andrew@...n.ch>
To: Furong Xu <0x1207@...il.com>
Cc: Ido Schimmel <idosch@...sch.org>, Brad Griffis <bgriffis@...dia.com>,
Jon Hunter <jonathanh@...dia.com>, netdev@...r.kernel.org,
linux-stm32@...md-mailman.stormreply.com,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
Alexander Lobakin <aleksander.lobakin@...el.com>,
Joe Damato <jdamato@...tly.com>,
Andrew Lunn <andrew+netdev@...n.ch>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
Maxime Coquelin <mcoquelin.stm32@...il.com>, xfr@...look.com,
"linux-tegra@...r.kernel.org" <linux-tegra@...r.kernel.org>
Subject: Re: [PATCH net-next v3 1/4] net: stmmac: Switch to zero-copy in
non-XDP RX path
> It is recommended to disable the "SPH feature" by default unless some
> certain cases depend on it. Like Ido said, two large buffers being
> allocated from the same page pool for each packet, this is a huge waste
> of memory, and brings performance drops for most of general cases.
I don't know this driver, but it looks like SPH is required for
NETIF_F_GRO? Can you add this flag to hw_features, but not
wanted_features and leave SPH disabled until ethtool is used to enable
GRO?
Are there other use cases where SPH is needed?
Andrew
Powered by blists - more mailing lists