netdev - Re: [PATCH net] r8169: fix NAPI handling under high load

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]

Message-ID: <20181019072921.GP8580@marvin.atrad.com.au>
Date:   Fri, 19 Oct 2018 17:59:21 +1030
From:   Jonathan Woithe <jwoithe@...ad.com.au>
To:     Holger Hoffstätte 
        <holger@...lied-asynchrony.com>
Cc:     Heiner Kallweit <hkallweit1@...il.com>,
        Francois Romieu <romieu@...zoreil.com>,
        David Miller <davem@...emloft.net>,
        Realtek linux nic maintainers <nic_swsd@...ltek.com>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH net] r8169: fix NAPI handling under high load

On Thu, Oct 18, 2018 at 01:52:33PM +0200, Holger Hoffstätte wrote:
> On 10/18/18 08:15, Jonathan Woithe wrote:
> > On Thu, Oct 18, 2018 at 08:03:32AM +0200, Heiner Kallweit wrote:
> > > Proposed fix is here:
> > > https://patchwork.ozlabs.org/patch/985014/
> > > Would be good if you could test it. Thanks!
> > 
> > I should be able to do so tomorrow.  Which kernel would you like me to apply
> > the patch to?
> 
> Hi Jonathan,
> 
> I'm already running it on 4.18.15, so either that or latest 4.19-rc would
> work as well.

It turns out I couldn't compile 4.18.15 conveniently for the test system due
to the age of the compiler.  The compiler, like the rest of the
distribution, is ancient: the presence of the bug has prevented us updating
the system due to a need to support hardware in the field.  The bug has
affected the operation of our systems in all kernels since (I think) 3.3.

I could compile 4.14 though - I had previously confirmed that the problem
was still seen with that kernel.  I therefore applied the fix to 4.14 (which
was trivial) and started a test with that.  The system has been running
without exhibiting the effects of the bug for over five hours.  With an
unpatched 4.14, symptoms were typically seen within 30 minutes.

I will leave the system to operate over the weekend to be sure, but at this
stage it seems likely that the patch will resolve this long-standing
difficulty that we've experienced.  I will report back on Monday.

Regards
  jonathan