Re: [PATCH 2/9] perf_counter: fix update_userpage()

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Thu, 2009-04-02 at 20:15 +1100, Paul Mackerras wrote:
> Peter Zijlstra writes:
> 
> > > That means that we don't need any CPU memory barriers on either side.
> > > All the kernel needs to do is to increment `lock' when it updates
> > > things, and the user side can be:
> > > 
> > > 	do {
> > > 		seq = pc->lock;
> > > 		index = pc->index;
> > > 		offset = pc->offset;
> > > 		barrier();
> > > 	} while (pc->lock != seq);
> > > 
> > > and all that's needed is a compiler barrier to stop the compiler from
> > > optimizing too much.
> > 
> > Can this work at all?
> > 
> > I mean, user-space could get preempted/rescheduled after we read the
> > mmap() data using that seqlock and before we actually did the read-pmc
> > bit.
> > 
> > In that case, the counter can have changed underneath us and we're
> > reading rubbish.
> 
> Good point.  This should work, though:
> 
> 	do {
> 		seq = pc->lock;
> 		barrier();
> 		value = read_pmc(pc->index) + pc->offset;
> 		barrier();
> 	} while (pc->lock != seq);
> 	return value;

I don't think you need the first barrier(), all you need to avoid is it
reusing the first pc->lock read, so one should suffice.

Also, you need to handle the !pc->index case.

But yeah.