Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <1580466455-27288-1-git-send-email-harini.katakam@xilinx.com>
 <1580466455-27288-3-git-send-email-harini.katakam@xilinx.com> <29c67f4f-9dd9-3786-689f-c0b6eeb40f49@microchip.com>
In-Reply-To: <29c67f4f-9dd9-3786-689f-c0b6eeb40f49@microchip.com>
From:   Harini Katakam <harinik@xilinx.com>
Date:   Fri, 31 Jan 2020 21:44:20 +0530
Message-ID: <CAFcVEC+sg++cQuB-tEzC4DDgYwd1nTHyA=R7CGkrjCOCAbkroQ@mail.gmail.com>
Subject: Re: [PATCH 2/2] net: macb: Limit maximum GEM TX length in TSO
To:     Claudiu Beznea <Claudiu.Beznea@microchip.com>
Cc:     Harini Katakam <harini.katakam@xilinx.com>,
        Nicolas Ferre <Nicolas.Ferre@microchip.com>,
        David Miller <davem@davemloft.net>, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org,
        Michal Simek <michal.simek@xilinx.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi Claudiu,

On Fri, Jan 31, 2020 at 8:27 PM <Claudiu.Beznea@microchip.com> wrote:
>
>
>
> On 31.01.2020 12:27, Harini Katakam wrote:
> > EXTERNAL EMAIL: Do not click links or open attachments unless you know the content is safe
> >
> > GEM_MAX_TX_LEN currently resolves to 0x3FF8 for any IP version supporting
> > TSO with full 14bits of length field in payload descriptor. But an IP
> > errata causes false amba_error (bit 6 of ISR) when length in payload
> > descriptors is specified above 16387. The error occurs because the DMA
> > falsely concludes that there is not enough space in SRAM for incoming
> > payload. These errors were observed continuously under stress of large
> > packets using iperf on a version where SRAM was 16K for each queue. This
> > errata will be documented shortly and affects all versions since TSO
> > functionality was added. Hence limit the max length to 0x3FC0 (rounded).
> >
> > Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
> > ---
<snip>
> > -               bp->max_tx_length = GEM_MAX_TX_LEN;
> > +               bp->max_tx_length = min(GEM_MAX_TX_LEN, GEM_MAX_TX_LEN_ERRATA);
>
> Isn't this always resolved to GEM_MAX_TX_LEN_ERRATA?

Sorry, yes it does. I accidentally concluded that this was
version specific. Will just default to 0x3fc0 in v2.
Thanks for the review.

Regards,
Harini