Re: [PATCH 4/6] hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events

[Frederic Weisbecker <fweisbec@gmail.com>]

On Sat, Nov 07, 2009 at 09:03:00PM +1100, Paul Mackerras wrote:
> Frederic Weisbecker writes:
> 
> > On Thu, Nov 05, 2009 at 10:59:44AM +1100, Paul Mackerras wrote:
> > > What I haven't managed to understand yet is how you provide reliable
> > > breakpoints for debugging purposes.  If I'm debugging a program and I
> > > have set a breakpoint, I'll be very unhappy if the breakpoint should
> > > trigger but doesn't because the perf_event infrastructure has decided
> > > it can't schedule that breakpoint in.  If the breakpoint isn't going
> > > to work then I want to know that at the time that I set it.
> > 
> > 
> > 
> > That won't happen because of the set of constraints we have.
> > We never overcommit the debug register resources, except in
> > the case of non-pinned counter, but that's in their nature :)
> 
> Suppose you have 4 breakpoint registers per cpu and there are two
> pinned per-cpu breakpoint events, three non-pinned per-cpu breakpoint
> events, and one pinned per-task breakpoint event.  I believe your
> constraints will allow that situation.
> 
> What will happen is that the two pinned per-cpu breakpoint events will
> use two of the hardware registers, and the three non-pinned per-cpu
> breakpoint events will get round-robined onto the other two hardware
> registers.  The per-task breakpoint will never get to use a hardware
> register, because the code in perf_event.c schedules per-cpu events
> before it schedules per-task events (see for example
> perf_event_task_tick()).



Oh! :-(

 
> We will have to make the event scheduling in kernel/perf_event.c a bit
> more sophisticated before we can guarantee that a pinned breakpoint
> event will always get to use a hardware register.
> 
> Paul.


Ok, so the only solution for now (a part from fixing that into perf) is to
consider the non-pinned events as being pinned in the constraints.