From mboxrd@z Thu Jan 1 00:00:00 1970 From: Matthew Wilcox Subject: Re: [parisc-linux] Strange newest LAB msg? Date: Sun, 2 Apr 2006 20:02:59 -0600 Message-ID: <20060403020259.GB8315@parisc-linux.org> References: <200604021129.31095.deller@gmx.de> <442FB31A.5040308@tiscali.be> <200604021515.04424.deller@gmx.de> <20060403012831.GB12037@colo.lackof.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Helge Deller , parisc-linux@lists.parisc-linux.org To: Grant Grundler Return-Path: In-Reply-To: <20060403012831.GB12037@colo.lackof.org> List-ID: On Sun, Apr 02, 2006 at 07:28:31PM -0600, Grant Grundler wrote: > > So, the problem is really the 64MB ioremap() from lba_pci.c:1216. > > Grant, Willy, ... : Is it possible to reduce it or to iounmap() it again ? > > Unfortunately not. Not unless you want to disable IO Port space access. > Each PCI bus controller routes 64MB of GMMIO space to 64KB of IO port space. > The first 4 bytes of each page maps to a unique 4 byte in IO Port space. > > On Astro platforms, we can use 64KB in LMMIO space to access > IO Port space for all busses. The difference is Astro only > has one SBA and IOC. N-class has two. There's more to this > and I'm not sure of all the details at the moment. > > 240MB is clearly not going to be enough on that machine. > Even on a "normal" machine, a couple of graphics cards > would exhaust the 240MB. A single infiniband card could > exhaust the 240MB space we have now. I think using page tables to map IO Port space isn't really necessary. We can use the (slightly inappropriately named) gsc_read/writeX to access that area. Also, there should be loads of virtual memory space available to us with a 64-bit kernel, and we should definitely look at increasing the amount of vmalloc space available with 64-bit.