Re: [PATCH tip/core/rcu 4/5] sys_membarrier: Add expedited option

[Peter Zijlstra]

On Tue, Jul 25, 2017 at 09:49:00AM -0700, Paul E. McKenney wrote:
> On Tue, Jul 25, 2017 at 06:33:18PM +0200, Peter Zijlstra wrote:
> > On Mon, Jul 24, 2017 at 02:58:16PM -0700, Paul E. McKenney wrote:
> > > The sys_membarrier() system call has proven too slow for some use
> > > cases, which has prompted users to instead rely on TLB shootdown.
> > > Although TLB shootdown is much faster, it has the slight disadvantage
> > > of not working at all on arm and arm64.  This commit therefore adds
> > > an expedited option to the sys_membarrier() system call.
> > 
> > > @@ -64,6 +65,10 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
> > >  		if (num_online_cpus() > 1)
> > >  			synchronize_sched();
> > >  		return 0;
> > > +	case MEMBARRIER_CMD_SHARED_EXPEDITED:
> > > +		if (num_online_cpus() > 1)
> > > +			synchronize_sched_expedited();
> > > +		return 0;
> > 
> > So you now give unprivileged userspace the means to IPI the entire
> > machine?
> > 
> > So what do we do when someone goes and does:
> > 
> > 	for (;;)
> > 		sys_membarrier(MEMBARRIER_CMD_SHARED_EXPEDITED, 0);
> > 
> > on us?
> 
> The same thing that happens when they call munmap().

munmap() TLB invalidate is limited to those CPUs that actually ran
threads of their process, while this is machine wide.