[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080809142918.GA30387@gondor.apana.org.au>
Date: Sat, 9 Aug 2008 22:29:18 +0800
From: Herbert Xu <herbert@...dor.apana.org.au>
To: Suresh Siddha <suresh.b.siddha@...el.com>
Cc: "H. Peter Anvin" <hpa@...or.com>,
Wolfgang Walter <wolfgang.walter@...m.de>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...e.hu>,
"viro@...IV.linux.org.uk" <viro@...IV.linux.org.uk>,
"vegard.nossum@...il.com" <vegard.nossum@...il.com>,
austin zhang <austin_zhang@...ux.intel.com>
Subject: Re: Kernel oops with 2.6.26, padlock and ipsec: probably problem with fpu state changes
On Sat, Aug 09, 2008 at 08:38:30AM +0800, Herbert Xu wrote:
>
> If there is a significant degradation I suggest that we back out
> the FPU changes. Making your competitor's processor go slow is
> not a nice thing to do, especially when you've just released a
> processor in the same space.
OK I take that back, Intel (and AMD) processors are equally affected
by this. For a start, the newly added Intel crc32c driver suffers
from exactly the same problem since the instruction used is also
SSE.
According to
http://softwarecommunity.intel.com/articles/eng/3788.htm
the Intel AES instructions are also SSE so they too will suffer
from this.
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@...dor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
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
Powered by blists - more mailing lists