From: Marcelo Tosatti <mtosatti@redhat.com>
To: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
KVM <kvm@vger.kernel.org>
Subject: Re: [PATCH v3 05/19] KVM: MMU: optimize to handle dirty bit
Date: Wed, 6 Jul 2011 13:51:34 -0300 [thread overview]
Message-ID: <20110706165134.GC24417@amt.cnet> (raw)
In-Reply-To: <4E13B8D4.3050704@cn.fujitsu.com>
On Wed, Jul 06, 2011 at 09:22:28AM +0800, Xiao Guangrong wrote:
> On 07/06/2011 03:27 AM, Marcelo Tosatti wrote:
> > On Thu, Jun 30, 2011 at 04:21:30PM +0800, Xiao Guangrong wrote:
> >> If dirty bit is not set, we can make the pte access read-only to avoid handing
> >> dirty bit everywhere
> >>
> >> Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
> >
> >> -static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte)
> >> +static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte,
> >> + bool last)
> >> {
> >> unsigned access;
> >>
> >> access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
> >> + if (last && !is_dirty_gpte(gpte))
> >> + access &= ~ACC_WRITE_MASK;
> >> +
> >
> > What if the walker marks the dirty bit on the gpte?
> >
>
> Actually, we get guest pte access after mark the dirty bit:
>
> if (write_fault && unlikely(!is_dirty_gpte(pte))) {
> int ret;
>
> trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
> ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
> pte, pte|PT_DIRTY_MASK);
> if (unlikely(ret < 0)) {
> present = false;
> goto error;
> } else if (ret)
> goto walk;
>
> mark_page_dirty(vcpu->kvm, table_gfn);
> pte |= PT_DIRTY_MASK;
> walker->ptes[walker->level - 1] = pte;
> }
>
> pte_access = pt_access & FNAME(gpte_access)(vcpu, pte, true);
>
> So, i think it works well :-)
I think you meant after marking the accessed bit. The dirty bit is set
just before returning.
next prev parent reply other threads:[~2011-07-06 17:39 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-30 8:19 [PATCH v3 01/19] KVM: MMU: fix walking shadow page table Xiao Guangrong
2011-06-30 8:19 ` [PATCH v3 02/19] KVM: MMU: do not update slot bitmap if spte is nonpresent Xiao Guangrong
2011-06-30 8:20 ` [PATCH v3 03/19] KVM: x86: introduce vcpu_mmio_gva_to_gpa to cleanup the code Xiao Guangrong
2011-06-30 8:20 ` [PATCH v3 04/19] KVM: MMU: cache mmio info on page fault path Xiao Guangrong
2011-07-05 19:04 ` Marcelo Tosatti
2011-07-06 1:17 ` Xiao Guangrong
2011-06-30 8:21 ` [PATCH v3 05/19] KVM: MMU: optimize to handle dirty bit Xiao Guangrong
2011-07-05 19:27 ` Marcelo Tosatti
2011-07-06 1:22 ` Xiao Guangrong
2011-07-06 16:51 ` Marcelo Tosatti [this message]
2011-07-06 19:12 ` Xiao Guangrong
2011-07-07 8:15 ` Marcelo Tosatti
2011-06-30 8:21 ` [PATCH v3 06/19] KVM: MMU: cleanup for FNAME(fetch) Xiao Guangrong
2011-06-30 8:22 ` [PATCH v3 07/19] KVM: MMU: rename 'pt_write' to 'emulate' Xiao Guangrong
2011-06-30 8:22 ` [PATCH v3 08/19] KVM: MMU: count used shadow pages on prepareing path Xiao Guangrong
2011-06-30 8:23 ` [PATCH v3 09/19] KVM: MMU: split kvm_mmu_free_page Xiao Guangrong
2011-06-30 8:23 ` [PATCH v3 10/19] KVM: MMU: remove bypass_guest_pf Xiao Guangrong
2011-06-30 8:24 ` [PATCH v3 11/19] KVM: MMU: filter out the mmio pfn from the fault pfn Xiao Guangrong
2011-07-06 17:17 ` Marcelo Tosatti
2011-07-06 19:13 ` Xiao Guangrong
2011-06-30 8:24 ` [PATCH v3 12/19] KVM: MMU: abstract some functions to handle " Xiao Guangrong
2011-06-30 8:25 ` [PATCH v3 13/19] KVM: MMU: introduce the rules to modify shadow page table Xiao Guangrong
2011-06-30 8:25 ` [PATCH v3 14/19] KVM: MMU: clean up spte updating and clearing Xiao Guangrong
2011-07-06 17:39 ` Marcelo Tosatti
2011-07-06 19:18 ` Xiao Guangrong
2011-07-07 8:16 ` Marcelo Tosatti
2011-07-07 9:30 ` Xiao Guangrong
2011-06-30 8:26 ` [PATCH v3 15/19] KVM: MMU: do not need atomicly to set/clear spte Xiao Guangrong
2011-06-30 8:26 ` [PATCH v3 16/19] KVM: MMU: lockless walking shadow page table Xiao Guangrong
2011-07-06 18:08 ` Marcelo Tosatti
2011-07-06 19:26 ` Xiao Guangrong
2011-07-07 8:18 ` Marcelo Tosatti
2011-06-30 8:26 ` [PATCH v3 17/19] KVM: MMU: reorganize struct kvm_shadow_walk_iterator Xiao Guangrong
2011-06-30 8:27 ` [PATCH v3 18/19] KVM: MMU: mmio page fault support Xiao Guangrong
2011-07-06 18:52 ` Marcelo Tosatti
2011-07-06 19:59 ` Xiao Guangrong
2011-07-07 8:49 ` Marcelo Tosatti
2011-06-30 8:28 ` [PATCH v3 19/19] KVM: MMU: trace mmio page fault Xiao Guangrong
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=20110706165134.GC24417@amt.cnet \
--to=mtosatti@redhat.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=xiaoguangrong@cn.fujitsu.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox