Date: Fri, 08 Jul 2005 15:51:32 -0600 From: Scott Long <scottl@samsco.org> To: "Wilkinson, Alex" <alex.wilkinson@dsto.defence.gov.au> Cc: arch@freebsd.org, Sue Howard <howardsue@gmail.com>, freebsd-arch@freebsd.org Subject: Re: Kernel Dump Message-ID: <42CEF564.3060503@samsco.org> In-Reply-To: <20050623074453.GA71779@squash.dsto.defence.gov.au> References: <1e89cd51050616062241e9e201@mail.gmail.com> <200506222323.26666.peter@wemm.org> <20050623074453.GA71779@squash.dsto.defence.gov.au>
next in thread | previous in thread | raw e-mail | index | archive | help
Wilkinson, Alex wrote: > 0n Wed, Jun 22, 2005 at 11:23:25PM -0700, Peter Wemm wrote: > > >I've just rewritten the AMD64 crashdump support to use ELF like ia64. > >In fact, I reused most of the ia64 code. We ran into serious problems > >at work, first on the amd64 platform and now also the i386 platform. > >The problem is that x86 machines are increasinly having memory holes. > >The simplistic dump code has no way to skip the memory hole and tries > >to dump things like the AGP frame buffer, pci card MMIO space, > >PCI-Express configuration space (this means accessing hardware!!) and > >so on. > > Curious, why is it that x86 creates memory holes in the first place ? > > - aW Some holes are mandated by the architecture. There is the classic hole from 640k to 1MB where the video framebuffer, option ROM, and BIOS goes. There is also the PCI memory hole from (typically) 3.75GB to 4GB where memio registers as well as platform features platform like the APIC are addressed. PCI Express adds a new hole at (typically) 3.5GB to 3.75GB for the extended config space registers. There are other holes, and most of them are dictated by the chipset. The BIOS SMAP table lists them, and you can see this table by doing a verbose boot. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?42CEF564.3060503>