Date: Wed, 13 Jun 2012 14:51:22 -0700
From: Andi Kleen <ak@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Andi Kleen <andi@firstfloor.org>, x86@kernel.org,
        linux-kernel@vger.kernel.org, eranian@google.com
Subject: Re: [PATCH 2/4] x86: Track minimum microcode revision globally v2
Message-ID: <20120613215122.GF32604@tassilo.jf.intel.com>
References: <1339618842-26636-1-git-send-email-andi@firstfloor.org>
 <1339618842-26636-3-git-send-email-andi@firstfloor.org>
 <1339623321.8980.66.camel@twins>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1339623321.8980.66.camel@twins>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 860
Lines: 24

> This would really much better live in common code where it can be
> preemptible in some sites. There really is no need for this to be
> non-preemptible.

Okay I can look. But you're really optimizing the wrong things here.
Even on a 4096 CPU system such a loop is miniscule compared to the
actual cost of the microcode update, which stops the complete CPU
for quite some time.

Basically microcode updates and low latency are incompatible
Don't do it when it hurts.

Unfortunately i'm changing all the callers two patches further,
so it'll be messy too.

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/