Date: Mon, 5 Sep 2005 23:45:27 -0700
From: Deepak Saxena <dsaxena@plexity.net>
To: Andrew Morton <akpm@osdl.org>, Linus Torvalds <torvalds@osdl.org>,
       linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Allow for arch-specific IOREMAP_MAX_ORDER
Message-ID: <20050906064527.GA18916@plexity.net>
Reply-To: dsaxena@plexity.net
References: <20050824221202.GA28977@plexity.net> <20050828183902.D14294@flint.arm.linux.org.uk>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20050828183902.D14294@flint.arm.linux.org.uk>
Organization: Plexity Networks
User-Agent: Mutt/1.5.5.1+cvs20040105i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1242
Lines: 27

On Aug 28 2005, at 18:39, Russell King was caught saying:
> On Wed, Aug 24, 2005 at 03:12:02PM -0700, Deepak Saxena wrote:
> > Version 6 of the ARM architecture introduces the concept of 16MB pages
> > (supersections) and 36-bit (40-bit actually, but nobody uses this)
> > physical addresses. 36-bit addressed memory and I/O and ARMv6 can
> > only be mapped using supersections and the requirement on these is
> > that both virtual and physical addresses be 16MB aligned.
> 
> Have we sorted out how we handle the issue of IO vs memory outside the
> normal 4GB?  We can only map one or other depending on how the domains
> are setup and get the correct permission behaviour.

That's an arch-specific issue that we'll have to handle in the ARM code
and really shouldn't impact this patch itself. FYI, all the 36-bit CPUs
I know of (from Intel) only have I/O above 4G.

~Deepak

-- 
Deepak Saxena - dsaxena@plexity.net - http://www.plexity.net

Even a stopped clock gives the right time twice a day.
-
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/