Re: [patch 1/3] performance counters: core code

[Ingo Molnar <mingo@elte.hu>]

* Paul Mackerras <paulus@samba.org> wrote:

> Thomas Gleixner writes:
> 
> > +static void
> > +perf_install_in_context(struct perf_counter_context *ctx,
> > +			struct perf_counter *counter,
> > +			int cpu)
> > +{
> > +	struct task_struct *task = ctx->task;
> > +
> 
> [...]
> 
> > +	if (task) {
> > +		task_oncpu_function_call(task, __perf_install_in_context,
> > +					 counter);
> > +	} else {
> > +		smp_call_function_single(cpu, __perf_install_in_context,
> > +					 counter, 1);
> > +	}
> 
> What happens if we send an IPI to the cpu where the task is running, 
> but by the time the IPI arrives, the task has been migrated to another 
> cpu and is now running there?  Do you chase after it and send another 
> IPI to its new cpu, or is there some reason why it can't migrate? If 
> it's the former, where is that code?  I haven't seen it so far (at 
> least, task_oncpu_function_call doesn't seem to do it).

in that case the schedule-in method will install the perf counter 
automatically. No need to chase after it. The smp call is only for the 
case where the task does not schedule at all.

	Ingo