From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: Gleb Natapov <gleb@redhat.com>
Cc: avi.kivity@gmail.com, mtosatti@redhat.com, pbonzini@redhat.com,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH 09/12] KVM: MMU: introduce pte-list lockless walker
Date: Wed, 28 Aug 2013 18:13:43 +0800 [thread overview]
Message-ID: <521DCD57.7000401@linux.vnet.ibm.com> (raw)
In-Reply-To: <20130828094630.GR22899@redhat.com>
On 08/28/2013 05:46 PM, Gleb Natapov wrote:
> On Wed, Aug 28, 2013 at 05:33:49PM +0800, Xiao Guangrong wrote:
>>> Or what if desc is moved to another rmap, but then it
>>> is moved back to initial rmap (but another place in the desc list) so
>>> the check here will not catch that we need to restart walking?
>>
>> It is okay. We always add the new desc to the head, then we will walk
>> all the entires under this case.
>>
> Which races another question: What if desc is added in front of the list
> behind the point where lockless walker currently is?
That case is new spte is being added into the rmap. We need not to care the
new sptes since it will set the dirty-bitmap then they can be write-protected
next time.
>
>> Right?
> Not sure. While lockless walker works on a desc rmap can be completely
> destroyed and recreated again. It can be any order.
I think the thing is very similar as include/linux/rculist_nulls.h
next prev parent reply other threads:[~2013-08-28 10:13 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-30 13:01 [RFC PATCH 00/12] KVM: MMU: locklessly wirte-protect Xiao Guangrong
2013-07-30 13:01 ` [PATCH 01/12] KVM: MMU: remove unused parameter Xiao Guangrong
2013-08-29 7:22 ` Gleb Natapov
2013-07-30 13:02 ` [PATCH 02/12] KVM: MMU: properly check last spte in fast_page_fault() Xiao Guangrong
2013-07-30 13:02 ` [PATCH 03/12] KVM: MMU: lazily drop large spte Xiao Guangrong
2013-08-02 14:55 ` Marcelo Tosatti
2013-08-02 15:42 ` Xiao Guangrong
2013-08-02 20:27 ` Marcelo Tosatti
2013-08-02 22:56 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 04/12] KVM: MMU: log dirty page after marking spte writable Xiao Guangrong
2013-07-30 13:26 ` Paolo Bonzini
2013-07-31 7:25 ` Xiao Guangrong
2013-08-07 1:48 ` Marcelo Tosatti
2013-08-07 4:06 ` Xiao Guangrong
2013-08-08 15:06 ` Marcelo Tosatti
2013-08-08 16:26 ` Xiao Guangrong
2013-11-20 0:29 ` Marcelo Tosatti
2013-11-20 0:35 ` Marcelo Tosatti
2013-11-20 14:20 ` Xiao Guangrong
2013-11-20 19:47 ` Marcelo Tosatti
2013-11-21 4:26 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 05/12] KVM: MMU: add spte into rmap before logging dirty page Xiao Guangrong
2013-07-30 13:27 ` Paolo Bonzini
2013-07-31 7:33 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 06/12] KVM: MMU: flush tlb if the spte can be locklessly modified Xiao Guangrong
2013-08-28 7:23 ` Gleb Natapov
2013-08-28 7:50 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 07/12] KVM: MMU: redesign the algorithm of pte_list Xiao Guangrong
2013-08-28 8:12 ` Gleb Natapov
2013-08-28 8:37 ` Xiao Guangrong
2013-08-28 8:58 ` Gleb Natapov
2013-08-28 9:19 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 08/12] KVM: MMU: introduce nulls desc Xiao Guangrong
2013-08-28 8:40 ` Gleb Natapov
2013-08-28 8:54 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 09/12] KVM: MMU: introduce pte-list lockless walker Xiao Guangrong
2013-08-28 9:20 ` Gleb Natapov
2013-08-28 9:33 ` Xiao Guangrong
2013-08-28 9:46 ` Gleb Natapov
2013-08-28 10:13 ` Xiao Guangrong [this message]
2013-08-28 10:49 ` Gleb Natapov
2013-08-28 12:15 ` Xiao Guangrong
2013-08-28 13:36 ` Gleb Natapov
2013-08-29 6:50 ` Xiao Guangrong
2013-08-29 9:08 ` Gleb Natapov
2013-08-29 9:31 ` Xiao Guangrong
2013-08-29 9:51 ` Gleb Natapov
2013-08-29 11:26 ` Xiao Guangrong
2013-08-30 11:38 ` Gleb Natapov
2013-09-02 7:02 ` Xiao Guangrong
2013-08-29 9:31 ` Gleb Natapov
2013-08-29 11:33 ` Xiao Guangrong
2013-08-29 12:02 ` Xiao Guangrong
2013-08-30 11:44 ` Gleb Natapov
2013-09-02 8:50 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 10/12] KVM: MMU: allow locklessly access shadow page table out of vcpu thread Xiao Guangrong
2013-08-07 13:09 ` Takuya Yoshikawa
2013-08-07 13:19 ` Xiao Guangrong
2013-08-29 9:10 ` Gleb Natapov
2013-08-29 9:25 ` Xiao Guangrong
2013-07-30 13:02 ` [PATCH 11/12] KVM: MMU: locklessly write-protect the page Xiao Guangrong
2013-07-30 13:02 ` [PATCH 12/12] KVM: MMU: clean up spte_write_protect Xiao Guangrong
2013-07-30 13:11 ` [RFC PATCH 00/12] KVM: MMU: locklessly wirte-protect Xiao Guangrong
2013-08-03 5:09 ` Takuya Yoshikawa
2013-08-04 14:15 ` Xiao Guangrong
2013-08-29 7:16 ` Gleb Natapov
2013-08-06 13:16 ` Xiao Guangrong
2013-08-08 17:38 ` Paolo Bonzini
2013-08-09 4:51 ` 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=521DCD57.7000401@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi.kivity@gmail.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@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;
as well as URLs for NNTP newsgroup(s).