linux-kernel - Re: Refactoring mutex spin on owner code

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:	Thu, 29 Jan 2015 23:14:40 -0800
From:	Davidlohr Bueso <dave@...olabs.net>
To:	Jason Low <jason.low2@...com>
Cc:	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
	Michel Lespinasse <walken@...gle.com>,
	Tim Chen <tim.c.chen@...ux.intel.com>,
	linux-kernel@...r.kernel.org
Subject: Re: Refactoring mutex spin on owner code

On Thu, 2015-01-29 at 17:52 -0800, Jason Low wrote:
> On Thu, 2015-01-29 at 15:15 -0800, Davidlohr Bueso wrote:
> > On Thu, 2015-01-29 at 12:18 -0800, Jason Low wrote:
> > >  	/*
> > > -	 * We break out the loop above on need_resched() and when the
> > > -	 * owner changed, which is a sign for heavy contention. Return
> > > -	 * success only when lock->owner is NULL.
> > > +	 * We break out the loop above on either need_resched(), when
> > > +	 * the owner is not running, or when the lock owner changed.
> > > +	 * Return success only when the lock owner changed.
> > >  	 */
> > > -	return lock->owner == NULL;
> > > +	return lock->owner != owner;
> > >  }
> > 
> > Ideally we would refactor all this, along with getting rid of
> > owner_running() at some point. It no longer makes sense to split up
> > mutex_spin_on_owner() and we're doing duplicate owner checks. It would
> > also be simpler than having to guess why we broke out of the loop, for
> > example.
> 
> Sure, that makes sense. What do you think of this additional change for
> refactoring the mutex version?
> 
> ---
> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> index 8711505..b6a8633 100644
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -204,44 +204,45 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
>   * Mutex spinning code migrated from kernel/sched/core.c
>   */
>  
> -static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
> -{
> -	if (lock->owner != owner)
> -		return false;
> -
> -	/*
> -	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
> -	 * lock->owner still matches owner, if that fails, owner might
> -	 * point to free()d memory, if it still matches, the rcu_read_lock()
> -	 * ensures the memory stays valid.
> -	 */
> -	barrier();
> -
> -	return owner->on_cpu;
> -}
> -
>  /*
>   * Look out! "owner" is an entirely speculative pointer
>   * access and not reliable.
>   */
>  static noinline
> -int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
> +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
>  {
> +	bool ret;
> +
>  	rcu_read_lock();
> -	while (owner_running(lock, owner)) {
> -		if (need_resched())
> +	while (true) {
> +		/* Return success when the lock owner changed */
> +		if (lock->owner != owner) {

Shouldn't this be a READ_ONCE(lock->owner)? We're in a loop and need to
avoid gcc giving us stale data if the owner is updated after a few
iterations, no?

--
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/