From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>,
avi.kivity@gmail.com,
"pbonzini@redhat.com Bonzini" <pbonzini@redhat.com>,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Eric Dumazet <dada1@cosmosbay.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH v3 07/15] KVM: MMU: introduce nulls desc
Date: Tue, 26 Nov 2013 11:02:34 +0800 [thread overview]
Message-ID: <52940F4A.4040701@linux.vnet.ibm.com> (raw)
In-Reply-To: <20131125140803.GA1489@amt.cnet>
On 11/25/2013 10:08 PM, Marcelo Tosatti wrote:
> On Mon, Nov 25, 2013 at 02:11:31PM +0800, Xiao Guangrong wrote:
>>
>> On Nov 23, 2013, at 3:14 AM, Marcelo Tosatti <mtosatti@redhat.com> wrote:
>>
>>> On Wed, Oct 23, 2013 at 09:29:25PM +0800, Xiao Guangrong wrote:
>>>> It likes nulls list and we use the pte-list as the nulls which can help us to
>>>> detect whether the "desc" is moved to anther rmap then we can re-walk the rmap
>>>> if that happened
>>>>
>>>> kvm->slots_lock is held when we do lockless walking that prevents rmap
>>>> is reused (free rmap need to hold that lock) so that we can not see the same
>>>> nulls used on different rmaps
>>>>
>>>> Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
>>>
>>> How about simplified lockless walk on the slot while rmapp entry
>>> contains a single spte? (which should be the case with two-dimensional
>>> paging).
>>>
>>> That is, grab the lock when finding a rmap with more than one spte in
>>> it (and then keep it locked until the end).
>>
>> Hmm… that isn't straightforward and more complex than the approach
>> in this patchset. Also it can drop the improvement for shadow mmu that
>> gets great improvement by this patchset.
>
> It is not more complex, since it would remove list lockless walk. Only
> the spte pointer at rmap[spte] is accessed without a lock. Its much much
> simpler.
>
>>> For example, nothing prevents lockless walker to move into some
>>> parent_ptes chain, right?
>>
>> No.
>>
>> The nulls can help us to detect this case, for parent_ptes, the nulls points
>> to "shadow page" but for rmaps, the nulls points to slot.arch.rmap. There
>> is no chance that the “rmap" is used as shadow page when slot-lock is held.
>
> The SLAB cache is the same, so entries can be reused. What prevents
> a desc entry living in slot.arch.rmap to be freed and reused by a
> parent_ptes desc?
>
We will check is_last_spte(), all the sptes on parent_ptes should be failed.
And Gleb suggested to use a separate slab for rmap, that should be excellent.
next prev parent reply other threads:[~2013-11-26 3:02 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-10-23 13:29 [PATCH v3 00/15] KVM: MMU: locklessly write-protect Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 01/15] KVM: MMU: properly check last spte in fast_page_fault() Xiao Guangrong
2013-11-12 0:25 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 02/15] KVM: MMU: lazily drop large spte Xiao Guangrong
2013-11-12 22:44 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 03/15] KVM: MMU: flush tlb if the spte can be locklessly modified Xiao Guangrong
2013-11-13 0:10 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 04/15] KVM: MMU: flush tlb out of mmu lock when write-protect the sptes Xiao Guangrong
2013-11-14 0:36 ` Marcelo Tosatti
2013-11-14 5:15 ` Xiao Guangrong
2013-11-14 18:39 ` Marcelo Tosatti
2013-11-15 7:09 ` Xiao Guangrong
2013-11-19 0:19 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 05/15] KVM: MMU: update spte and add it into rmap before dirty log Xiao Guangrong
2013-11-15 0:08 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 06/15] KVM: MMU: redesign the algorithm of pte_list Xiao Guangrong
2013-11-19 0:48 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 07/15] KVM: MMU: introduce nulls desc Xiao Guangrong
2013-11-22 19:14 ` Marcelo Tosatti
2013-11-25 6:11 ` Xiao Guangrong
2013-11-25 6:29 ` Xiao Guangrong
2013-11-25 18:12 ` Marcelo Tosatti
2013-11-26 3:21 ` Xiao Guangrong
2013-11-26 10:12 ` Gleb Natapov
2013-11-26 19:31 ` Marcelo Tosatti
2013-11-28 8:53 ` Xiao Guangrong
2013-12-03 7:10 ` Xiao Guangrong
2013-12-05 13:50 ` Marcelo Tosatti
2013-12-05 15:30 ` Xiao Guangrong
2013-12-06 0:15 ` Marcelo Tosatti
2013-12-06 0:22 ` Marcelo Tosatti
2013-12-10 6:58 ` Xiao Guangrong
2013-11-25 10:19 ` Gleb Natapov
2013-11-25 10:25 ` Xiao Guangrong
2013-11-25 12:48 ` Avi Kivity
2013-11-25 14:23 ` Marcelo Tosatti
2013-11-25 14:29 ` Gleb Natapov
2013-11-25 18:06 ` Marcelo Tosatti
2013-11-26 3:10 ` Xiao Guangrong
2013-11-26 10:15 ` Gleb Natapov
2013-11-26 19:58 ` Marcelo Tosatti
2013-11-28 8:32 ` Xiao Guangrong
2013-11-25 14:08 ` Marcelo Tosatti
2013-11-26 3:02 ` Xiao Guangrong [this message]
2013-11-25 9:31 ` Peter Zijlstra
2013-11-25 10:59 ` Xiao Guangrong
2013-11-25 11:05 ` Peter Zijlstra
2013-11-25 11:29 ` Peter Zijlstra
2013-10-23 13:29 ` [PATCH v3 08/15] KVM: MMU: introduce pte-list lockless walker Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 09/15] KVM: MMU: initialize the pointers in pte_list_desc properly Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 10/15] KVM: MMU: allocate shadow pages from slab Xiao Guangrong
2013-10-24 9:19 ` Gleb Natapov
2013-10-24 9:29 ` Xiao Guangrong
2013-10-24 9:52 ` Gleb Natapov
2013-10-24 10:10 ` Xiao Guangrong
2013-10-24 10:39 ` Gleb Natapov
2013-10-24 11:01 ` Xiao Guangrong
2013-10-24 12:32 ` Gleb Natapov
2013-10-28 3:16 ` Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 11/15] KVM: MMU: locklessly access shadow page under rcu protection Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 12/15] KVM: MMU: check last spte with unawareness of mapping level Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 13/15] KVM: MMU: locklessly write-protect the page Xiao Guangrong
2013-10-24 9:17 ` Gleb Natapov
2013-10-24 9:24 ` Xiao Guangrong
2013-10-24 9:32 ` Gleb Natapov
2013-10-23 13:29 ` [PATCH v3 14/15] KVM: MMU: clean up spte_write_protect Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 15/15] KVM: MMU: use rcu functions to access the pointer Xiao Guangrong
2013-11-03 12:29 ` [PATCH v3 00/15] KVM: MMU: locklessly write-protect Gleb Natapov
2013-11-11 5:33 ` 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=52940F4A.4040701@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi.kivity@gmail.com \
--cc=dada1@cosmosbay.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
/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).