| To: | David Chinner <dgc@xxxxxxx> |
|---|---|
| Subject: | Re: Interaction between Xen and XFS: stray RW mappings |
| From: | Andi Kleen <andi@xxxxxxxxxxxxxx> |
| Date: | Mon, 15 Oct 2007 11:36:50 +0200 |
| Cc: | Jeremy Fitzhardinge <jeremy@xxxxxxxx>, xfs@xxxxxxxxxxx, Xen-devel <xen-devel@xxxxxxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, Mark Williamson <mark.williamson@xxxxxxxxxxxx>, Morten Bøgeskov <xen-users@xxxxxxxxxxxxxxxxxx>, xfs-masters@xxxxxxxxxxx, nickpiggin@xxxxxxxxxxxx |
| In-reply-to: | <20071014225618.GN23367404@sgi.com> (David Chinner's message of "Mon\, 15 Oct 2007 08\:56\:18 +1000") |
| References: | <470FA7C3.90404@goop.org> <20071014225618.GN23367404@sgi.com> |
| Sender: | xfs-bounce@xxxxxxxxxxx |
| User-agent: | Gnus/5.11 (Gnus v5.11) Emacs/22.1 (gnu/linux) |
David Chinner <dgc@xxxxxxx> writes: > > And yes, we delay unmapping pages until we have a batch of them > to unmap. vmap and vunmap do not scale, so this is batching helps > alleviate some of the worst of the problems. You're keeping vmaps around for already freed pages? That will be a big problem for proper PAT support, which needs to track all mappings to memory. It's not just a problem for Xen. In fact I suspect it is already broken with DRM or AGP for example which can use UC and WC mappings -- if you keep the mapping around and DRM or AGP turns the page in another mapping uncacheable you're creating an illegal cache attribute alias. These are known to occasionally create cache corruptions on several x86s; giving ___VERY___ hard to debug bugs once a blue moon. Probably it'll require some generic VM batching mechanism where Xen or PAT code can hook into the list or force unmap the mappings as needed. Definitely needs to be fixed if true. You're lucky that Xen caught it in time. -Andi |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: XFS regression?, David Chinner |
|---|---|
| Next by Date: | Re: XFS regression?, Bhagi rathi |
| Previous by Thread: | Latencies in XFS., Andrew Clayton |
| Next by Thread: | Review: Fix dbflush panic in xfs_qm_sync, Donald Douwsma |
| Indexes: | [Date] [Thread] [Top] [All Lists] |