Re: [PATCH 5/6] hw-breakpoints: Arbitrate access to pmu following registers constraints

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Thu, 2009-11-05 at 21:58 +1100, Paul Mackerras wrote:
> Frederic Weisbecker writes:
> 
> > Allow or refuse to build a counter using the breakpoints pmu following
> > given constraints.
> 
> As far as I can see, you assume each CPU has HBP_NUM breakpoint
> registers which are all interchangeable and can all be used either for
> data breakpoints or instruction breakpoints.  Is that accurate?
> 
> If so, we'll need to extend it a bit for Power since we have some CPUs
> that have one data breakpoint register and one instruction breakpoint
> register.  In general on powerpc the instruction and data breakpoint
> facilities are separate, i.e. we have no registers that can be used
> for either.

Additionally, we have more fancy facilities that I don't see exposed at
all through this interface (we are building an ad-hoc ptrace based
interface today so that gdb can make use of them) and we have one guy
with crazy constraints that we don't know yet how to deal with:

Among others features:

 - Pairing of two data or instruction breakpoints to create a ranges
breakpoint
 - Data value compare option
 - Instruction value compare option

And now the crazy constraints:

 - On one embedded core at least we have a case where the core has 4
threads, but the data (4) and instruction (2) breakpoint registers are
shared. The 'enable' bits are split so a given data breakpoint can be
enabled only on some HW threads but that's about it.

I'm not sure if there's a realistic way to handle the later constraint
though other than just not allowing use of the HW breakpoint function on
those cores at all.

Ben.

> > +static void toggle_bp_slot(struct perf_event *bp, bool enable)
> > +{
> > +	int cpu = bp->cpu;
> > +	unsigned int *nr;
> > +	struct task_struct *tsk = bp->ctx->task;
> > +
> > +	/* Flexible */
> > +	if (!bp->attr.pinned) {
> > +		if (cpu >= 0) {
> > +			nr = &per_cpu(nr_bp_flexible, cpu);
> > +			goto toggle;
> > +		}
> > +
> > +		for_each_online_cpu(cpu) {
> > +			nr = &per_cpu(nr_bp_flexible, cpu);
> > +			goto toggle;
> 
> ...
> 
> > +toggle:
> > +	*nr = enable ? *nr + 1 : *nr - 1;
> > +}
> 
> This won't do what I think you want.  In the case where
> !bp->attr.pinned and cpu == -1, it will only update the count for the
> first online cpu, not all of them.
> 
> Paul.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/