Re: [PATCH v4 0/2] perf, x86: handle overlapping counters

[Robert Richter <robert.richter@amd.com>]

On 22.11.11 16:26:07, Peter Zijlstra wrote:
> @@ -574,16 +574,25 @@ static bool __perf_sched_find_counter(st
>  
>  	c = sched->constraints[sched->state.event];
>  
> +	/* Prefer fixed purpose counters */
> +	if (x86_pmu.num_counters_fixed) {
> +		idx = X86_PMC_IDX_FIXED;
> +		for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) {
> +			if (!__test_and_set_bit(idx, sched->state.used))
> +				goto done;
> +		}
> +	}
>  	/* Grab the first unused counter starting with idx */
>  	idx = sched->state.counter;
> -	for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) {
> +	for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
>  		if (!__test_and_set_bit(idx, sched->state.used))
> -			break;
> +			goto done;
>  	}
> -	sched->state.counter = idx;
>  
> -	if (idx >= X86_PMC_IDX_MAX)
> -		return false;
> +	return false;
> +
> +done:
> +	sched->state.counter = idx;

Yes, we don't need to save this on failure. Looks ok.

-Robert

>  
>  	if (c->overlap)
>  		perf_sched_save_state(sched);
> 
> 

-- 
Advanced Micro Devices, Inc.
Operating System Research Center