From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Vrabel Subject: Re: [PATCHv6 2/2] x86/ept: defer the invalidation until the p2m lock is released Date: Mon, 1 Feb 2016 14:50:09 +0000 Message-ID: <56AF70A1.9060503@citrix.com> References: <1450446634-8762-1-git-send-email-david.vrabel@citrix.com> <1450446634-8762-3-git-send-email-david.vrabel@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta5.messagelabs.com ([195.245.231.135]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1aQFnz-0007iL-1f for xen-devel@lists.xenproject.org; Mon, 01 Feb 2016 14:50:15 +0000 In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: "Tian, Kevin" , David Vrabel , "xen-devel@lists.xenproject.org" Cc: George Dunlap , Andrew Cooper , Tim Deegan , "Nakajima, Jun" , Jan Beulich List-Id: xen-devel@lists.xenproject.org On 20/12/15 06:56, Tian, Kevin wrote: >> From: David Vrabel [mailto:david.vrabel@citrix.com] >> Sent: Friday, December 18, 2015 9:51 PM >> >> Holding the p2m lock while calling ept_sync_domain() is very expensive >> since it does a on_selected_cpus() call. IPIs on many socket machines >> can be very slows and on_selected_cpus() is serialized. >> >> It is safe to defer the invalidate until the p2m lock is released >> except for two cases: >> >> 1. When freeing a page table page (since partial translations may be >> cached). >> 2. When reclaiming a zero page as part of PoD. >> >> For these cases, add p2m_tlb_flush_sync() calls which will immediately >> perform the invalidate before the page is freed or reclaimed. >> >> Signed-off-by: David Vrabel > > In a quick glimpse the patch is OK. Will find a time to think about it more > carefully since this part is tricky (also allow others to comment before > my ack in EPT part). Ping? Did you get more time to think about this patch? David