linux-kernel - Re: [PATCHv3 2/6] tty/ldsem: Update waiter->task before waking up reader

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]

Date:   Tue, 11 Sep 2018 13:43:59 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Sergey Senozhatsky <sergey.senozhatsky.work@...il.com>
Cc:     Dmitry Safonov <dima@...sta.com>, linux-kernel@...r.kernel.org,
        Dmitry Safonov <0x7f454c46@...il.com>,
        Daniel Axtens <dja@...ens.net>,
        Dmitry Vyukov <dvyukov@...gle.com>,
        Michael Neuling <mikey@...ling.org>,
        Mikulas Patocka <mpatocka@...hat.com>,
        Nathan March <nathan@...net>,
        Pasi Kärkkäinen <pasik@....fi>,
        Peter Hurley <peter@...leysoftware.com>,
        "Rong, Chen" <rong.a.chen@...el.com>,
        Tan Xiaojun <tanxiaojun@...wei.com>,
        Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>,
        stable@...r.kernel.org,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Jiri Slaby <jslaby@...e.com>,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: Re: [PATCHv3 2/6] tty/ldsem: Update waiter->task before waking up
 reader

On Tue, Sep 11, 2018 at 02:04:49PM +0900, Sergey Senozhatsky wrote:
> On (09/11/18 02:48), Dmitry Safonov wrote:
> > There is a couple of reports about lockup in ldsem_down_read() without
> > anyone holding write end of ldisc semaphore:
> > lkml.kernel.org/r/<20171121132855.ajdv4k6swzhvktl6@...-t540p.sh.intel.com>
> > lkml.kernel.org/r/<20180907045041.GF1110@...o2-debian>
> > 
> > They all looked like a missed wake up.
> > I wasn't lucky enough to reproduce it, but it seems like reader on
> > another CPU can miss waiter->task update and schedule again, resulting
> > in indefinite (MAX_SCHEDULE_TIMEOUT) sleep.
> 
> Certainly, something suspicious is going on.
> 
> > @@ -118,6 +118,8 @@ static void __ldsem_wake_readers(struct ld_semaphore *sem)
> >  		tsk = waiter->task;
> >  		smp_mb();
> >  		waiter->task = NULL;
> > +		/* Make sure down_read_failed() will see !waiter->task update */
> > +		smp_wmb();
> >  		wake_up_process(tsk);
> 
> Hmm. I think wake_up_process() executes a full memory barrier, because
> it accesses task state.
> 
> >  		put_task_struct(tsk);
> >  	}
> > @@ -217,7 +219,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout)
> >  	for (;;) {
> >  		set_current_state(TASK_UNINTERRUPTIBLE);
> 
> I think that set_current_state() also executes memory barrier. Just
> because it accesses task state.

In both cases, the rationale, 'because it accesses task state' is
utterly wrong.

The reasoning can be found in the comment near set_current_state().