Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
Message-ID: <trinity-0dbbc59b-1e7d-4f58-8611-adb281a82477-1626354270982@3c-app-gmx-bap31>
From:   Lino Sanfilippo <LinoSanfilippo@gmx.de>
To:     Vladimir Oltean <olteanv@gmail.com>
Cc:     Andrew Lunn <andrew@lunn.ch>, woojung.huh@microchip.com,
        UNGLinuxDriver@microchip.com, vivien.didelot@gmail.com,
        f.fainelli@gmail.com, davem@davemloft.net, kuba@kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Aw: Re: [PATCH 2/2] net: dsa: tag_ksz: dont let the hardware
 process the layer 4 checksum
Content-Type: text/plain; charset=UTF-8
Date:   Thu, 15 Jul 2021 15:04:31 +0200
Importance: normal
Sensitivity: Normal
In-Reply-To: <20210715114908.ripblpevmdujkf2m@skbuf>
References: <20210714191723.31294-1-LinoSanfilippo@gmx.de>
 <20210714191723.31294-3-LinoSanfilippo@gmx.de>
 <20210714194812.stay3oqyw3ogshhj@skbuf> <YO9F2LhTizvr1l11@lunn.ch>
 <20210715065455.7nu7zgle2haa6wku@skbuf>
 <trinity-84a570e8-7b5f-44f7-b10c-169d4307d653-1626347772540@3c-app-gmx-bap31>
 <20210715114908.ripblpevmdujkf2m@skbuf>
Content-Transfer-Encoding: quoted-printable
Precedence: bulk


> Gesendet: Donnerstag, 15. Juli 2021 um 13:49 Uhr
> Von: "Vladimir Oltean" <olteanv@gmail.com>
> An: "Lino Sanfilippo" <LinoSanfilippo@gmx.de>
> Cc: "Andrew Lunn" <andrew@lunn.ch>, woojung.huh@microchip.com, UNGLinuxD=
river@microchip.com, vivien.didelot@gmail.com, f.fainelli@gmail.com, davem=
@davemloft.net, kuba@kernel.org, netdev@vger.kernel.org, linux-kernel@vger=
.kernel.org
> Betreff: Re: [PATCH 2/2] net: dsa: tag_ksz: dont let the hardware proces=
s the layer 4 checksum
>
> On Thu, Jul 15, 2021 at 01:16:12PM +0200, Lino Sanfilippo wrote:
> > Sure, I will test this solution. But I think NETIF_F_FRAGLIST should a=
lso be
> > cleared in this case, right?
>
> Hmm, interesting question. I think only hns3 makes meaningful use of
> NETIF_F_FRAGLIST, right? I'm looking at hns3_fill_skb_to_desc().
> Other drivers seem to set it for ridiculous reasons - looking at commit
> 66aa0678efc2 ("ibmveth: Support to enable LSO/CSO for Trunk VEA.") -
> they set NETIF_F_FRAGLIST and then linearize the skb chain anyway. The
> claimed 4x throughput benefit probably has to do with less skbs
> traversing the stack? I don't know.
>
> Anyway, it is hard to imagine all the things that could go wrong with
> chains of IP fragments on a DSA interface, precisely because I have so
> few examples to look at. I would say, header taggers are probably fine,
> tail taggers not so much, so apply the same treatment as for NETIF_F_SG?
>

Please note that skb_put() asserts that the SKB is linearized. So I think =
we
should rather clear both NETIF_F_FRAGLIST and NETIF_F_SG unconditionally s=
ince also
header taggers use some form of skb_put() dont they?