[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <52A6BB84.30706@gmail.com>
Date: Tue, 10 Dec 2013 14:58:12 +0800
From: Xiao Guangrong <xiaoguangrong.eric@...il.com>
To: Marcelo Tosatti <mtosatti@...hat.com>
CC: Gleb Natapov <gleb@...hat.com>, avi.kivity@...il.com,
"pbonzini@...hat.com Bonzini" <pbonzini@...hat.com>,
linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
Eric Dumazet <dada1@...mosbay.com>,
Peter Zijlstra <peterz@...radead.org>
Subject: Re: [PATCH v3 07/15] KVM: MMU: introduce nulls desc
On 12/06/2013 08:22 AM, Marcelo Tosatti wrote:
> On Thu, Dec 05, 2013 at 11:30:27PM +0800, Xiao Guangrong wrote:
>> In some cases, the lockless walker will do endless-walking on desc and
>> without rewalk, consider this case:
>>
>> there are two descs: desc1 and desc2 who is pointed by desc1->next:
>> desc1->next = desc2.
>>
>> CPU 0 CPU 1
>>
>> lockless walk on desc1
>> deleting desc1 from the rmap
>> lockless walk on desc2 (desc1->next)
>> delete desc2 from the rmap
>> add desc1
>> add desc2, then desc2->next = desc1
>>
>> lockless walk on desc1
>> delete desc2
>> delete desc1
>> add desc2
>> add desc1; the desc1->next = desc2
>> lockless walk on desc2
>>
>> ……
>>
>> Then, the walker is endlessly walking on desc1 and desc2 without any rewalk.
>
> The counter can be local to the walker. If its more than maximum rmap
> size, break.
>
> (but still, please consider carefully whether lockless list walking is
> really necessary or can be avoided).
Yep, Marcelo, you're right.
After thinking more, i do not have any idea to simplify this. Your approach
(lockless on the first level) seems a better solution. Will do it based on that
ways.
Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists