linux-kernel - Re: [RFC PATCH 1/2] Fix: sched/membarrier: p->mm->membarrier

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: <20190904113920.GG2349@hirez.programming.kicks-ass.net>
Date:   Wed, 4 Sep 2019 13:39:20 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Oleg Nesterov <oleg@...hat.com>
Cc:     Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        "Paul E. McKenney" <paulmck@...ux.ibm.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        linux-kernel@...r.kernel.org,
        "Eric W. Biederman" <ebiederm@...ssion.com>,
        Russell King - ARM Linux admin <linux@...linux.org.uk>,
        Chris Metcalf <cmetcalf@...hip.com>,
        Christoph Lameter <cl@...ux.com>,
        Kirill Tkhai <tkhai@...dex.ru>, Mike Galbraith <efault@....de>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...nel.org>
Subject: Re: [RFC PATCH 1/2] Fix: sched/membarrier: p->mm->membarrier_state
 racy load

On Wed, Sep 04, 2019 at 12:53:49PM +0200, Oleg Nesterov wrote:
> On 09/03, Mathieu Desnoyers wrote:
> >
> > @@ -1130,6 +1130,10 @@ struct task_struct {
> >  	unsigned long			numa_pages_migrated;
> >  #endif /* CONFIG_NUMA_BALANCING */
> >
> > +#ifdef CONFIG_MEMBARRIER
> > +	atomic_t membarrier_state;
> > +#endif
> 
> ...
> 
> > +static inline void membarrier_prepare_task_switch(struct task_struct *t)
> > +{
> > +	if (!t->mm)
> > +		return;
> > +	atomic_set(&t->membarrier_state,
> > +		   atomic_read(&t->mm->membarrier_state));
> > +}
> 
> Why not
> 
> 	rq->membarrier_state = next->mm ? t->mm->membarrier_state : 0;
> 
> and
> 
> 	if (cpu_rq(cpu)->membarrier_state & MEMBARRIER_STATE_GLOBAL_EXPEDITED) {
> 		...
> 	}
> 
> in membarrier_global_expedited() ? (I removed atomic_ to simplify)
> 
> IOW, why this new member has to live in task_struct, not in rq?

It could be like the above; but then we're still reading
mm->membarrier_state in the scheduler path.

The patch I just send avoids event that, at the cost of doing a
do_each_thread/while_each_thread iteration in the uncommon case where we
register a process after it grows threads.