From: Izik Eidus <ieidus@redhat.com> To: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, avi@redhat.com, chrisw@redhat.com, mtosatti@redhat.com, hugh@veritas.com, kamezawa.hiroyu@jp.fujitsu.com Subject: Re: [PATCH 3/4] add replace_page(): change the page pte is pointing to. Date: Thu, 16 Apr 2009 01:48:48 +0300 [thread overview] Message-ID: <49E66450.3070404@redhat.com> (raw) In-Reply-To: <20090415112511.GH9809@random.random> Andrea Arcangeli wrote: > On Tue, Apr 14, 2009 at 03:09:25PM -0700, Andrew Morton wrote: > >> On Thu, 9 Apr 2009 06:58:40 +0300 >> Izik Eidus <ieidus@redhat.com> wrote: >> >> >>> replace_page() allow changing the mapping of pte from one physical page >>> into diffrent physical page. >>> >> At a high level, this is very similar to what page migration does. Yet >> this implementation shares nothing with the page migration code. >> >> Can this situation be improved? >> > > This was discussed last time too. Basically the thing is that using > migration entry with its special page fault paths, for this looks a > bit of an overkill complexity and unnecessary dependency on the > migration code. I agree about that. > All we need is to mark the pte readonly. replace_page > is a no brainer then. The brainer part is page_wrprotect > (page_wrprotect is like fork). > > The data visibility in the final memcmp you mentioned in the other > mail is supposedly taken care of by page_wrprotect too. It already > does flush_cache_page for the virtual indexed and not physically > tagged caches. page_wrprotect has to also IPI all CPUs to nuke any not > wrprotected tlb entry. I don't think we need further smp memory > barriers when we're guaranteed all tlb entries are wrprotected in the > other cpus and an IPI and invlpg run in them, to be sure we read the > data stable during memcmp even if we read through the kernel > pagetables and the last userland write happened through userland ptes > before they become effective wrprotected by the IPI. > Yup agree.
WARNING: multiple messages have this Message-ID (diff)
From: Izik Eidus <ieidus@redhat.com> To: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, avi@redhat.com, chrisw@redhat.com, mtosatti@redhat.com, hugh@veritas.com, kamezawa.hiroyu@jp.fujitsu.com Subject: Re: [PATCH 3/4] add replace_page(): change the page pte is pointing to. Date: Thu, 16 Apr 2009 01:48:48 +0300 [thread overview] Message-ID: <49E66450.3070404@redhat.com> (raw) In-Reply-To: <20090415112511.GH9809@random.random> Andrea Arcangeli wrote: > On Tue, Apr 14, 2009 at 03:09:25PM -0700, Andrew Morton wrote: > >> On Thu, 9 Apr 2009 06:58:40 +0300 >> Izik Eidus <ieidus@redhat.com> wrote: >> >> >>> replace_page() allow changing the mapping of pte from one physical page >>> into diffrent physical page. >>> >> At a high level, this is very similar to what page migration does. Yet >> this implementation shares nothing with the page migration code. >> >> Can this situation be improved? >> > > This was discussed last time too. Basically the thing is that using > migration entry with its special page fault paths, for this looks a > bit of an overkill complexity and unnecessary dependency on the > migration code. I agree about that. > All we need is to mark the pte readonly. replace_page > is a no brainer then. The brainer part is page_wrprotect > (page_wrprotect is like fork). > > The data visibility in the final memcmp you mentioned in the other > mail is supposedly taken care of by page_wrprotect too. It already > does flush_cache_page for the virtual indexed and not physically > tagged caches. page_wrprotect has to also IPI all CPUs to nuke any not > wrprotected tlb entry. I don't think we need further smp memory > barriers when we're guaranteed all tlb entries are wrprotected in the > other cpus and an IPI and invlpg run in them, to be sure we read the > data stable during memcmp even if we read through the kernel > pagetables and the last userland write happened through userland ptes > before they become effective wrprotected by the IPI. > Yup agree. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2009-04-15 22:51 UTC|newest] Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top 2009-04-09 3:58 [PATCH 0/4] ksm - dynamic page sharing driver for linux v3 Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 4/4] add ksm kernel shared memory driver Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-15 22:37 ` Izik Eidus 2009-04-15 22:37 ` Izik Eidus 2009-04-15 22:50 ` Andrew Morton 2009-04-15 22:50 ` Andrew Morton 2009-04-15 23:21 ` Andrea Arcangeli 2009-04-15 23:21 ` Andrea Arcangeli 2009-04-16 0:43 ` Jeremy Fitzhardinge 2009-04-16 0:43 ` Jeremy Fitzhardinge 2009-04-16 0:57 ` Izik Eidus 2009-04-16 0:57 ` Izik Eidus 2009-04-16 11:39 ` Andrea Arcangeli 2009-04-16 11:39 ` Andrea Arcangeli 2009-04-16 16:08 ` Jeremy Fitzhardinge 2009-04-16 16:08 ` Jeremy Fitzhardinge 2009-04-18 14:58 ` Andrea Arcangeli 2009-04-18 14:58 ` Andrea Arcangeli 2009-04-14 22:09 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-15 11:25 ` Andrea Arcangeli 2009-04-15 11:25 ` Andrea Arcangeli 2009-04-15 22:48 ` Izik Eidus [this message] 2009-04-15 22:48 ` Izik Eidus 2009-04-14 22:09 ` [PATCH 0/4] ksm - dynamic page sharing driver for linux v3 Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-16 17:55 ` Nick Piggin 2009-04-16 17:55 ` Nick Piggin 2009-04-16 18:25 ` Izik Eidus 2009-04-16 18:25 ` Izik Eidus 2009-04-17 7:08 ` Jared Hulbert 2009-04-17 7:08 ` Jared Hulbert 2009-04-21 2:59 ` Nick Piggin 2009-04-21 2:59 ` Nick Piggin -- strict thread matches above, loose matches on Subject: below -- 2009-04-04 14:35 [PATCH 0/4] ksm - dynamic page sharing driver for linux v2 Izik Eidus 2009-04-04 14:35 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-04-04 14:35 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-04-04 14:35 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-04-04 14:35 ` Izik Eidus 2009-03-30 23:59 [PATCH 0/4] ksm - dynamic page sharing driver for linux Izik Eidus 2009-03-30 23:59 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-03-30 23:59 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-03-30 23:59 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-03-30 23:59 ` Izik Eidus
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=49E66450.3070404@redhat.com \ --to=ieidus@redhat.com \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=avi@redhat.com \ --cc=chrisw@redhat.com \ --cc=hugh@veritas.com \ --cc=kamezawa.hiroyu@jp.fujitsu.com \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mtosatti@redhat.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.