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

From: Peter Zijlstra
Date: Thu Apr 02 2009 - 05:35:38 EST


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.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/