netdev - Re: r8169 : always copying the rx buffer to new skb

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, 18 Apr 2011 18:27:56 +0100
From:	Ben Hutchings <bhutchings@...arflare.com>
To:	John Lumby <johnlumby@...mail.com>
Cc:	netdev@...r.kernel.org
Subject: Re: r8169 :  always copying the rx buffer to new skb

On Mon, 2011-04-18 at 13:08 -0400, John Lumby wrote:
> Summary  -  current r8169 always memcpy's every received buffer to new skb,
>              and I'd like to propose that it should not,
>              which can improve throughput / reduce CPU utilization by 
> around 10%

At least some variants of the hardware have a bug in RX DMA scatter that
can be exploited for denial-of-service.  The workaround is to allocate
huge RX buffers (16K).  Then, to avoid allocation failures later on (and
to save memory) the buffers must be copied rather than passed up the
stack and reallocated.

[...]
> As a second proposal (which I made before),  I'd like to suggest that 
> the number of rx buffers allocated at open should be configurable by 
> module param.
[...]

No, it should implement the ethtool set_ringparam operation.

Ben.

-- 
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html