From: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Avi Kivity <avi@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
KVM list <kvm@vger.kernel.org>
Subject: Re: [PATCH v2 8/10] KVM: MMU: prefetch ptes when intercepted guest #PF
Date: Wed, 30 Jun 2010 08:58:22 +0800 [thread overview]
Message-ID: <4C2A96AE.6020103@cn.fujitsu.com> (raw)
In-Reply-To: <20100629114446.GB26369@amt.cnet>
Marcelo Tosatti wrote:
>>> Also prefetch should be disabled for EPT, due to lack of accessed bit.
>>>
>> But we call mmu_set_spte() with speculative == false, it not touch the accessed bit.
>
> There is no accessed bit on EPT. So the aging code (kvm_age_rmapp)
> considers any present translation as accessed. There is no way to
> distinguish between actually accessed translations and prefetched (but
> unused) ones.
>
You are right, i'll disable the prefetch for EPT in the next version, thanks for
you point it out.
next prev parent reply other threads:[~2010-06-30 0:58 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4C2498EC.2010006@cn.fujitsu.com>
2010-06-25 12:05 ` [PATCH v2 2/10] KVM: MMU: fix conflict access permissions in direct sp Xiao Guangrong
2010-06-28 9:43 ` Avi Kivity
2010-06-28 9:49 ` Xiao Guangrong
2010-06-25 12:06 ` [PATCH v2 3/10] KVM: MMU: fix direct sp's access corruptted Xiao Guangrong
2010-06-28 9:50 ` Avi Kivity
2010-06-28 10:02 ` Xiao Guangrong
2010-06-28 11:13 ` Avi Kivity
2010-06-29 1:17 ` Xiao Guangrong
2010-06-29 7:06 ` Avi Kivity
2010-06-29 7:35 ` Xiao Guangrong
2010-06-29 8:49 ` Avi Kivity
2010-06-29 9:04 ` Xiao Guangrong
2010-06-29 9:13 ` Avi Kivity
2010-06-29 9:13 ` Xiao Guangrong
2010-06-29 7:38 ` Avi Kivity
2010-06-29 7:45 ` Xiao Guangrong
2010-06-29 8:51 ` Avi Kivity
2010-06-29 9:08 ` Xiao Guangrong
2010-06-25 12:06 ` [PATCH v2 4/10] KVM: MMU: fix forgot to flush all vcpu's tlb Xiao Guangrong
2010-06-28 9:55 ` Avi Kivity
2010-06-25 12:06 ` [PATCH v2 5/10] KVM: MMU: introduce gfn_to_pfn_atomic() function Xiao Guangrong
2010-06-25 12:06 ` [PATCH v2 6/10] KVM: MMU: introduce gfn_to_hva_many() function Xiao Guangrong
2010-06-25 12:06 ` [PATCH v2 7/10] KVM: MMU: introduce mmu_topup_memory_cache_atomic() Xiao Guangrong
2010-06-28 11:17 ` Avi Kivity
2010-06-29 1:18 ` Xiao Guangrong
2010-06-25 12:07 ` [PATCH v2 8/10] KVM: MMU: prefetch ptes when intercepted guest #PF Xiao Guangrong
2010-06-28 13:04 ` Marcelo Tosatti
2010-06-29 8:07 ` Xiao Guangrong
2010-06-29 11:44 ` Marcelo Tosatti
2010-06-30 0:58 ` Xiao Guangrong [this message]
2010-06-25 12:07 ` [PATCH v2 9/10] KVM: MMU: combine guest pte read between walk and pte prefetch Xiao Guangrong
2010-06-25 12:07 ` [PATCH v2 10/10] KVM: MMU: trace " 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=4C2A96AE.6020103@cn.fujitsu.com \
--to=xiaoguangrong@cn.fujitsu.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.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: 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