netdev - Re: [PATCH net-next] r8169: make use of xmit

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 12 Aug 2019 11:59:09 +0200
From:   Holger Hoffstätte <holger@...lied-asynchrony.com>
To:     Eric Dumazet <edumazet@...gle.com>
Cc:     Heiner Kallweit <hkallweit1@...il.com>,
        Realtek linux nic maintainers <nic_swsd@...ltek.com>,
        David Miller <davem@...emloft.net>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        Sander Eikelenboom <linux@...elenboom.it>
Subject: Re: [PATCH net-next] r8169: make use of xmit_more

On 8/9/19 10:52 AM, Holger Hoffstätte wrote:
> On 8/9/19 10:25 AM, Eric Dumazet wrote:
> (snip)
>>>
>>> So that didn't take long - got another timeout this morning during some
>>> random light usage, despite sg/tso being disabled this time.
>>> Again the only common element is the xmit_more patch. :(
>>> Not sure whether you want to revert this right away or wait for 5.4-rc1
>>> feedback. Maybe this too is chipset-specific?
>>>
>>>> Thanks a lot for the analysis and testing. Then I'll submit the disabling
>>>> of SG on RTL8168evl (on your behalf), independent of whether it fixes
>>>> the timeout issue.
>>>
>>> Got it, thanks!
>>>
>>> Holger
>>
>> I would try this fix maybe ?
>>
>> diff --git a/drivers/net/ethernet/realtek/r8169_main.c
>> b/drivers/net/ethernet/realtek/r8169_main.c
>> index b2a275d8504cf099cff738f2f7554efa9658fe32..e77628813daba493ad50dab9ac1e3703e38b560c
>> 100644
>> --- a/drivers/net/ethernet/realtek/r8169_main.c
>> +++ b/drivers/net/ethernet/realtek/r8169_main.c
>> @@ -5691,6 +5691,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
>>                   */
>>                  smp_wmb();
>>                  netif_stop_queue(dev);
>> +               door_bell = true;
>>          }
>>
>>          if (door_bell)
>>
> 
> Thanks Eric, I'll give that a try and see how it fares over the next few days.
> It suspiciously looks like it could help..

Good news everyone!

After three days non-stop action between two machines and hundreds of GBs
pushed back and forth: not a single timeout or hiccup. Nice! \o/
Eric, please send this as a proper patch for -next. Feel free to add my
Tested-by.

cheers
Holger