From owner-freebsd-hackers Thu Aug 2 11:31:37 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from perninha.conectiva.com.br (perninha.conectiva.com.br [200.250.58.156]) by hub.freebsd.org (Postfix) with ESMTP id 5A66437B405 for ; Thu, 2 Aug 2001 11:30:27 -0700 (PDT) (envelope-from riel@conectiva.com.br) Received: from burns.conectiva (burns.conectiva [10.0.0.4]) by perninha.conectiva.com.br (Postfix) with SMTP id C51A938D18 for ; Thu, 2 Aug 2001 15:30:18 -0300 (EST) Received: (qmail 13833 invoked by uid 0); 2 Aug 2001 18:29:23 -0000 Received: from duckman.distro.conectiva (HELO duckman.conectiva.com.br) (root@10.0.17.2) by burns.conectiva with SMTP; 2 Aug 2001 18:29:23 -0000 Received: from localhost (riel@localhost) by duckman.conectiva.com.br (8.11.4/8.11.3) with ESMTP id f72IUHI05323; Thu, 2 Aug 2001 15:30:17 -0300 X-Authentication-Warning: duckman.distro.conectiva: riel owned process doing -bs Date: Thu, 2 Aug 2001 15:30:17 -0300 (BRST) From: Rik van Riel X-X-Sender: To: Julian Elischer Cc: Terry Lambert , craig , Subject: Re: How to visit physical memory above 4G? In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On Thu, 2 Aug 2001, Julian Elischer wrote: > On Thu, 2 Aug 2001, Rik van Riel wrote: > > > > On the really large machines, this can lead to the > > situation where even the page tables hardly fit into > > KVA. 4MB pages seem like the only solution ... > > There is no reason why we need to keep the kernel and the user > process in the same 4GB map except for efficiency. > > There have been many UNIX machines in the past which put them in > separate virtual spaces That was on machines where the CPU could actually address two separate spaces at once, right ? (like eg. m68k) > The kernel would haev 4GB for itself and each process would have 4BG. > > System calls would be come more expensive as each would require > a full page-table swap and a TLB flush. > However it might be worth it for some people. Interrupt handling would also require a full page table swap and TLB flush. Considering that, I think the number of people for whom this will be worth it has probably dropped a bit ;) Rik -- Executive summary of a recent Microsoft press release: "we are concerned about the GNU General Public License (GPL)" http://www.surriel.com/ http://www.conectiva.com/ http://distro.conectiva.com/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message