Re: [PATCH 18/19] perf: Introduce positive capability for raw events

On 8/19/25 15:15, Robin Murphy wrote:
> On 13/08/2025 6:01 pm, Robin Murphy wrote:
>> Only a handful of CPU PMUs accept PERF_TYPE_{RAW,HARDWARE,HW_CACHE}
>> events without registering themselves as PERF_TYPE_RAW in the first
>> place. Add an explicit opt-in for these special cases, so that we can
>> make life easier for every other driver (and probably also speed up the
>> slow-path search) by having perf_try_init_event() do the basic type
>> checking to cover the majority of cases.
>>
>> Signed-off-by: Robin Murphy <[email protected]>
>> ---
>>
>> A further possibility is to automatically add the cap to PERF_TYPE_RAW
>> PMUs in perf_pmu_register() to have a single point-of-use condition; I'm
>> undecided...
>> ---
>>   arch/s390/kernel/perf_cpum_cf.c    |  1 +
>>   arch/s390/kernel/perf_pai_crypto.c |  2 +-
>>   arch/s390/kernel/perf_pai_ext.c    |  2 +-
>>   arch/x86/events/core.c             |  2 +-
>>   drivers/perf/arm_pmu.c             |  1 +
>>   include/linux/perf_event.h         |  1 +
>>   kernel/events/core.c               | 15 +++++++++++++++
>>   7 files changed, 21 insertions(+), 3 deletions(-)
>>
>> diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
>> index 1a94e0944bc5..782ab755ddd4 100644
>> --- a/arch/s390/kernel/perf_cpum_cf.c
>> +++ b/arch/s390/kernel/perf_cpum_cf.c
>> @@ -1054,6 +1054,7 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
>>   /* Performance monitoring unit for s390x */
>>   static struct pmu cpumf_pmu = {
>>       .task_ctx_nr  = perf_sw_context,
>> +    .capabilities = PERF_PMU_CAP_RAW_EVENTS,
>>       .pmu_enable   = cpumf_pmu_enable,
>>       .pmu_disable  = cpumf_pmu_disable,
>>       .event_init   = cpumf_pmu_event_init,
>> diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
>> index a64b6b056a21..b5b6d8b5d943 100644
>> --- a/arch/s390/kernel/perf_pai_crypto.c
>> +++ b/arch/s390/kernel/perf_pai_crypto.c
>> @@ -569,7 +569,7 @@ static const struct attribute_group *paicrypt_attr_groups[] = {
>>   /* Performance monitoring unit for mapped counters */
>>   static struct pmu paicrypt = {
>>       .task_ctx_nr  = perf_hw_context,
>> -    .capabilities = PERF_PMU_CAP_SAMPLING,
>> +    .capabilities = PERF_PMU_CAP_SAMPLING | PERF_PMU_CAP_RAW_EVENTS,
>>       .event_init   = paicrypt_event_init,
>>       .add          = paicrypt_add,
>>       .del          = paicrypt_del,
>> diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
>> index 1261f80c6d52..bcd28c38da70 100644
>> --- a/arch/s390/kernel/perf_pai_ext.c
>> +++ b/arch/s390/kernel/perf_pai_ext.c
>> @@ -595,7 +595,7 @@ static const struct attribute_group *paiext_attr_groups[] = {
>>   /* Performance monitoring unit for mapped counters */
>>   static struct pmu paiext = {
>>       .task_ctx_nr  = perf_hw_context,
>> -    .capabilities = PERF_PMU_CAP_SAMPLING,
>> +    .capabilities = PERF_PMU_CAP_SAMPLING | PERF_PMU_CAP_RAW_EVENTS,
>>       .event_init   = paiext_event_init,
>>       .add          = paiext_add,
>>       .del          = paiext_del,
>> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
>> index 789dfca2fa67..764728bb80ae 100644
>> --- a/arch/x86/events/core.c
>> +++ b/arch/x86/events/core.c
>> @@ -2697,7 +2697,7 @@ static bool x86_pmu_filter(struct pmu *pmu, int cpu)
>>   }
>>     static struct pmu pmu = {
>> -    .capabilities        = PERF_PMU_CAP_SAMPLING,
>> +    .capabilities        = PERF_PMU_CAP_SAMPLING | PERF_PMU_CAP_RAW_EVENTS,
>>         .pmu_enable        = x86_pmu_enable,
>>       .pmu_disable        = x86_pmu_disable,
>> diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
>> index 72d8f38d0aa5..bc772a3bf411 100644
>> --- a/drivers/perf/arm_pmu.c
>> +++ b/drivers/perf/arm_pmu.c
>> @@ -877,6 +877,7 @@ struct arm_pmu *armpmu_alloc(void)
>>            * specific PMU.
>>            */
>>           .capabilities    = PERF_PMU_CAP_SAMPLING |
>> +                  PERF_PMU_CAP_RAW_EVENTS |
>>                     PERF_PMU_CAP_EXTENDED_REGS |
>>                     PERF_PMU_CAP_EXTENDED_HW_TYPE,
>>       };
>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>> index 183b7c48b329..c6ad036c0037 100644
>> --- a/include/linux/perf_event.h
>> +++ b/include/linux/perf_event.h
>> @@ -305,6 +305,7 @@ struct perf_event_pmu_context;
>>   #define PERF_PMU_CAP_EXTENDED_HW_TYPE    0x0100
>>   #define PERF_PMU_CAP_AUX_PAUSE        0x0200
>>   #define PERF_PMU_CAP_AUX_PREFER_LARGE    0x0400
>> +#define PERF_PMU_CAP_RAW_EVENTS        0x0800
>>     /**
>>    * pmu::scope
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 71b2a6730705..2ecee76d2ae2 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -12556,11 +12556,26 @@ static inline bool has_extended_regs(struct perf_event *event)
>>              (event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK);
>>   }
>>   +static bool is_raw_pmu(const struct pmu *pmu)
>> +{
>> +    return pmu->type == PERF_TYPE_RAW ||
>> +           pmu->capabilities & PERF_PMU_CAP_RAW_EVENTS;
>> +}
>> +
>>   static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
>>   {
>>       struct perf_event_context *ctx = NULL;
>>       int ret;
>>   +    /*
>> +     * Before touching anything, we can safely skip:
>> +     * - any event for a specific PMU which is not this one
>> +     * - any common event if this PMU doesn't support them
>> +     */
>> +    if (event->attr.type != pmu->type &&
>> +        (event->attr.type >= PERF_TYPE_MAX || is_raw_pmu(pmu)))
> 
> Ah, that should be "!is_raw_pmu(pmu)" there (although it's not entirely the cause of the LKP report on the final patch.)
> 
> Thanks,
> Robin.
> 
>> +        return -ENOENT;
>> +
>>       if (!try_module_get(pmu->module))
>>           return -ENODEV;
>>   
> 
> 

Hi Robin,

what is the intention of that patch?
Can you explain that a bit more.

Thanks.

-- 
Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
--
IBM Deutschland Research & Development GmbH

Vorsitzender des Aufsichtsrats: Wolfgang Wendt

Geschäftsführung: David Faller

Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294