From mboxrd@z Thu Jan 1 00:00:00 1970 From: Julien Grall Subject: Re: [PATCH v2 3/4] xen/arm: clean and invalidate all guest caches by VMID after domain build. Date: Thu, 06 Feb 2014 15:41:21 +0000 Message-ID: <52F3AD21.5030607@linaro.org> References: <1391616214.23098.9.camel@kazak.uk.xensource.com> <1391616235-22703-3-git-send-email-ian.campbell@citrix.com> <52F3A0D4.5070406@linaro.org> <1391699058.25128.50.camel@kazak.uk.xensource.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1391699058.25128.50.camel@kazak.uk.xensource.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ian Campbell Cc: keir@xen.org, stefano.stabellini@eu.citrix.com, ian.jackson@eu.citrix.com, tim@xen.org, xen-devel@lists.xen.org, jbeulich@suse.com List-Id: xen-devel@lists.xenproject.org On 06/02/14 15:04, Ian Campbell wrote: > On Thu, 2014-02-06 at 14:48 +0000, Julien Grall wrote: >> >> On 05/02/14 16:03, Ian Campbell wrote: >> > +void sync_page_to_ram(unsigned long mfn) >>> +{ >>> + void *v = map_domain_page(mfn); >>> + >>> + flush_xen_dcache_va_range(v, PAGE_SIZE); >>> + >> >> flush_xen_dcache_va_range uses DCCMVAC (for ARM32 bits), which only >> clean the cache. >> >> Following your commit message, we might want to use DCCIMVAC. > > Yes, I think you are right, I thought this function invalidated as well. I was wondering if we can change the behaviour of flush_xen_dcache_va_range. Invalidate the cache should not harm the other call-site. -- Julien Grall