From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Andres Lagar-Cavilla" Subject: Re: RFC: AMD support for paging Date: Tue, 14 Feb 2012 13:33:27 -0800 Message-ID: References: <91f45eaceac6f38f9df39ed7d60c47a7.squirrel@webmail.lagarcavilla.org> <20120214192249.GA10224@aepfle.de> <2aee3454239cd9f663b5c8ee43b2e2bc.squirrel@webmail.lagarcavilla.org> <20120214212655.GA23901@aepfle.de> Reply-To: andres@lagarcavilla.org Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20120214212655.GA23901@aepfle.de> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Olaf Hering Cc: xen-devel@lists.xensource.com, tim@xen.org, keir.xen@gmail.com, jbeulich@suse.com, adin@gridcentric.ca List-Id: xen-devel@lists.xenproject.org > On Tue, Feb 14, Andres Lagar-Cavilla wrote: > >> > On Tue, Feb 14, Andres Lagar-Cavilla wrote: >> > >> >> Finally, the triple fault. >> > >> > "Me too!" >> > Thats how far I got as well in my attempt. >> >> Hey, awesome you're trying this out so quickly :) > > I meant my attempt a few weeks ago. > >> If you have a couple cycles... > > Does your pager do anything? I just get this: > > xc: detail: xenpaging init > xc: detail: watching '/local/domain/1/memory/target-tot_pages' > xc: detail: max_pages = 263168 > xc: detail: starting /usr/lib/xen/bin/xenpaging for domain_id 1 with > pagefile /dev/shm/pagefile-sles11sp2_full_xenpaging > xc: detail: confirming startup in /local/domain/1/xenpaging/state > xc: detail: Got event from xenstore > xc: detail: path '@releaseDomain' token '1' > xc: detail: Got event from evtchn > xc: detail: Got event from xenstore > xc: detail: path '/local/domain/1/memory/target-tot_pages' token '' > xc: detail: new target_tot_pages 59904 > xc: detail: Got event from Xen > xc: detail: Need to evict 202213 pages to reach 59904 target_tot_pages > xc: error: Error mapping page 20201 (22 = Invalid argument): Internal > error Those are the kinds of errors I was getting until I finished my patch. Basically, the p2m gets confused and returns p2m_mmio_dm as the type for anything it doesn't understand. If you end up giving my patch a spin, let me know if it gets you past that hump. Andres > xc: debug: hypercall buffer: total allocations:9 total releases:9 > xc: debug: hypercall buffer: current allocations:0 maximum allocations:2 > xc: debug: hypercall buffer: cache current size:2 > xc: debug: hypercall buffer: cache hits:7 misses:2 toobig:0 > > > Olaf >