linux-kernel - Re: [PATCH 4/4] exit: Lockless iteration over task list in mm_update_next

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1d7c0dd6-22d8-89ea-15cc-bc3d46024bbd@virtuozzo.com>
Date:   Thu, 26 Apr 2018 18:56:52 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Andrea Parri <andrea.parri@...rulasolutions.com>,
        akpm@...ux-foundation.org, oleg@...hat.com,
        viro@...iv.linux.org.uk, mingo@...nel.org,
        paulmck@...ux.vnet.ibm.com, keescook@...omium.org, riel@...hat.com,
        mhocko@...e.com, tglx@...utronix.de,
        kirill.shutemov@...ux.intel.com, marcos.souza.org@...il.com,
        hoeun.ryu@...il.com, pasha.tatashin@...cle.com, gs051095@...il.com,
        ebiederm@...ssion.com, dhowells@...hat.com,
        rppt@...ux.vnet.ibm.com, linux-kernel@...r.kernel.org,
        Alan Stern <stern@...land.harvard.edu>,
        Will Deacon <will.deacon@....com>,
        Boqun Feng <boqun.feng@...il.com>
Subject: Re: [PATCH 4/4] exit: Lockless iteration over task list in
 mm_update_next_owner()

On 26.04.2018 18:20, Peter Zijlstra wrote:
> On Thu, Apr 26, 2018 at 04:52:39PM +0300, Kirill Tkhai wrote:
>> In the patch I used the logic, that the below code:
>>
>> 	x = A;
>> 	spin_lock();
>> 	spin_unlock();
>> 	spin_lock();
>> 	spin_unlock();
>> 	y = B;
>>
>> cannot reorder much than:
>>
>> 	spin_lock();
>> 	x = A;		<- this can't become visible later, that spin_unlock()
>> 	spin_unlock();
>> 	spin_lock();
>> 	y = B;		<- this can't become visible earlier, than spin_lock()
>> 	spin_unlock();
>>
>> Is there a problem?
> 
> The two stores will be ordered, but only at the strength of an
> smp_wmb(). The above construct does not imply smp_mb(). The difference
> is observable on real hardware (Power).

Ah, thanks.

But hopefully, smp_rmb() should be enough here.