netdev - Re: [PATCH] ARM: net: JIT compiler for packet filters

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: <20111221143602.GA3229@swarm.cs.pub.ro>
Date:	Wed, 21 Dec 2011 16:36:03 +0200
From:	Mircea Gherzan <mgherzan@...il.com>
To:	Nicolas Pitre <nico@...xnic.net>
Cc:	Rob Herring <robherring2@...il.com>, netdev@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org, linux@....linux.org.uk
Subject: Re: [PATCH] ARM: net: JIT compiler for packet filters

On Mon, Dec 19, 2011 at 12:31:19PM -0500, Nicolas Pitre wrote:
> On Sun, 18 Dec 2011, Rob Herring wrote:
> 
> > On 12/18/2011 05:49 PM, Mircea Gherzan wrote:
> > > +	select HAVE_BPF_JIT if (!THUMB2_KERNEL && AEABI)
> > 
> > No thumb2. That's a shame...
> 
> I think this would be more sensible to make a Thumb2 kernel properly 
> interoperate with this and keep the JIT code simple rather than having 
> to duplicate all this for Thumb2.

The JITed code interoperates properly with a Thumb2 kernel as of v3 of
the patch.

> > BLX is v5+ only. It probably fine to make the JIT v5+ only. There's
> > probably not much v4 h/w that would use this.
> 
> While you might be right, I don't think it is that big a cost to make 
> this support ARMv4 too.  In fact, if slow ARMv4 systems are still 
> routing packets out there, they are likely to see a huge benefit from 
> this.

This has also been addressed in v3.

Mircea
--
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