Re: [Patch v2 7/7] perf/x86/intel: Add support for rdpmc user disable feature

[Mi, Dapeng]

On 1/12/2026 6:57 PM, Peter Zijlstra wrote:
> On Mon, Jan 12, 2026 at 01:16:49PM +0800, Dapeng Mi wrote:
>
>> +static void intel_pmu_update_rdpmc_user_disable(struct perf_event *event)
>> +{
>> +	/*
>> +	 * Counter scope's user-space rdpmc is disabled by default
>> +	 * except two cases.
>> +	 * a. rdpmc = 2 (user space rdpmc enabled unconditionally)
>> +	 * b. rdpmc = 1 and the event is not a system-wide event.
>> +	 *    The count of non-system-wide events would be cleared when
>> +	 *    context switches, so no count data is leaked.
>> +	 */
>> +	if (x86_pmu_has_rdpmc_user_disable(event->pmu)) {
>> +		if (x86_pmu.attr_rdpmc == X86_USER_RDPMC_ALWAYS_ENABLE ||
>> +		    (x86_pmu.attr_rdpmc == X86_USER_RDPMC_CONDITIONAL_ENABLE &&
>> +		     event->ctx->task))
>> +			event->hw.config &= ~ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;
>> +		else
>> +			event->hw.config |= ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;
>> +	}
>> +}
> Is it not simpler to invert that condition?
>
> 	if (x86_pmu.attr_rdpmc == X86_USER_RDPMC_ALWAYS_NEVER ||
> 	    !event->ctx->task)
> 		event->hw.config |= ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;
> 	else
> 		event->hw.config &= ~ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;

Hmm, it seems the logic changes along with the code change. The system-wide
event should be allowed to read with rdpmc from user space when attr_rdpmc
== X86_USER_RDPMC_ALWAYS_ENABLE, but it doesn't with the new code.

If we don't change the logic and just invert the condition, the code
simplicity has no much change.

	if (x86_pmu.attr_rdpmc == X86_USER_RDPMC_ALWAYS_NEVER ||
            (x86_pmu.attr_rdpmc == X86_USER_RDPMC_CONDITIONAL_ENABLE &&
	    !event->ctx->task))
		event->hw.config |= ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;
	else
		event->hw.config &= ~ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE;