Re: [PATCH 07/10] perf: arm_spe: Add support for filtering on data source

[James Clark <james.clark@linaro.org>]

On 20/05/2025 12:43 pm, Leo Yan wrote:
> On Tue, May 06, 2025 at 12:41:39PM +0100, James Clark wrote:
>> SPE_FEAT_FDS adds the ability to filter on the data source of packets.
>> Like the other existing filters, enable filtering with PMSFCR_EL1.FDS
>> when any of the filter bits are set.
>>
>> Each bit maps to data sources 0-63 described by bits[0:5] in the data
>> source packet (although the full range of data source is 16 bits so
>> higher value data sources can't be filtered on). The filter is an OR of
>> all the bits, so for example setting bits 0 and 3 filters packets from
>> data sources 0 OR 3.
>>
>> Signed-off-by: James Clark <james.clark@linaro.org>
>> ---
>>   drivers/perf/arm_spe_pmu.c | 31 +++++++++++++++++++++++++++++++
>>   1 file changed, 31 insertions(+)
>>
>> diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
>> index 9309b846f642..d04318411f77 100644
>> --- a/drivers/perf/arm_spe_pmu.c
>> +++ b/drivers/perf/arm_spe_pmu.c
>> @@ -87,6 +87,7 @@ struct arm_spe_pmu {
>>   #define SPE_PMU_FEAT_INV_FILT_EVT		(1UL << 6)
>>   #define SPE_PMU_FEAT_DISCARD			(1UL << 7)
>>   #define SPE_PMU_FEAT_EFT			(1UL << 8)
>> +#define SPE_PMU_FEAT_FDS			(1UL << 9)
>>   #define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
>>   	u64					features;
>>   
>> @@ -232,6 +233,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
>>   #define ATTR_CFG_FLD_inv_event_filter_LO	0
>>   #define ATTR_CFG_FLD_inv_event_filter_HI	63
>>   
>> +#define ATTR_CFG_FLD_data_src_filter_CFG	config4	/* PMSDSFR_EL1 */
>> +#define ATTR_CFG_FLD_data_src_filter_LO	0
>> +#define ATTR_CFG_FLD_data_src_filter_HI	63
>> +
>>   GEN_PMU_FORMAT_ATTR(ts_enable);
>>   GEN_PMU_FORMAT_ATTR(pa_enable);
>>   GEN_PMU_FORMAT_ATTR(pct_enable);
>> @@ -248,6 +253,7 @@ GEN_PMU_FORMAT_ATTR(float_filter);
>>   GEN_PMU_FORMAT_ATTR(float_filter_mask);
>>   GEN_PMU_FORMAT_ATTR(event_filter);
>>   GEN_PMU_FORMAT_ATTR(inv_event_filter);
>> +GEN_PMU_FORMAT_ATTR(data_src_filter);
>>   GEN_PMU_FORMAT_ATTR(min_latency);
>>   GEN_PMU_FORMAT_ATTR(discard);
>>   
>> @@ -268,6 +274,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
>>   	&format_attr_float_filter_mask.attr,
>>   	&format_attr_event_filter.attr,
>>   	&format_attr_inv_event_filter.attr,
>> +	&format_attr_data_src_filter.attr,
>>   	&format_attr_min_latency.attr,
>>   	&format_attr_discard.attr,
>>   	NULL,
>> @@ -286,6 +293,9 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
>>   	if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
>>   		return 0;
>>   
>> +	if (attr == &format_attr_data_src_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_FDS))
>> +		return 0;
>> +
>>   	if ((attr == &format_attr_branch_filter_mask.attr ||
>>   	     attr == &format_attr_load_filter_mask.attr ||
>>   	     attr == &format_attr_store_filter_mask.attr ||
>> @@ -406,6 +416,9 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
>>   	if (ATTR_CFG_GET_FLD(attr, inv_event_filter))
>>   		reg |= PMSFCR_EL1_FnE;
>>   
>> +	if (ATTR_CFG_GET_FLD(attr, data_src_filter))
>> +		reg |= PMSFCR_EL1_FDS;
>> +
>>   	if (ATTR_CFG_GET_FLD(attr, min_latency))
>>   		reg |= PMSFCR_EL1_FL;
>>   
>> @@ -430,6 +443,12 @@ static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
>>   	return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency));
>>   }
>>   
>> +static u64 arm_spe_event_to_pmsdsfr(struct perf_event *event)
>> +{
>> +	struct perf_event_attr *attr = &event->attr;
>> +	return ATTR_CFG_GET_FLD(attr, data_src_filter);
>> +}
> 
> Seems to me, arm_spe_event_to_pmsdsfr() is not needed as it does not do
> any conversion from event config to register value.  So simply read the
> field value in opened code would be fine.
> 
> I am fine to keep it and would leave SPE driver maintainers to decide
> which is preferring.  Otherwise, LGTM:
> 
> Reviewed-by: Leo Yan <leo.yan@arm.com>
> 

It's purely for consistency with the existing code. See 
arm_spe_event_to_pmsevfr() etc.

>> +
>>   static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len)
>>   {
>>   	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
>> @@ -788,6 +807,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
>>   	if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
>>   		return -EOPNOTSUPP;
>>   
>> +	if (arm_spe_event_to_pmsdsfr(event) &&
>> +	    !(spe_pmu->features & SPE_PMU_FEAT_FDS))
>> +		return -EOPNOTSUPP;
>> +
>>   	if (attr->exclude_idle)
>>   		return -EOPNOTSUPP;
>>   
>> @@ -857,6 +880,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags)
>>   		write_sysreg_s(reg, SYS_PMSNEVFR_EL1);
>>   	}
>>   
>> +	if (spe_pmu->features & SPE_PMU_FEAT_FDS) {
>> +		reg = arm_spe_event_to_pmsdsfr(event);
>> +		write_sysreg_s(reg, SYS_PMSDSFR_EL1);
>> +	}
>> +
>>   	reg = arm_spe_event_to_pmslatfr(event);
>>   	write_sysreg_s(reg, SYS_PMSLATFR_EL1);
>>   
>> @@ -1116,6 +1144,9 @@ static void __arm_spe_pmu_dev_probe(void *info)
>>   	if (FIELD_GET(PMSIDR_EL1_EFT, reg))
>>   		spe_pmu->features |= SPE_PMU_FEAT_EFT;
>>   
>> +	if (FIELD_GET(PMSIDR_EL1_FDS, reg))
>> +		spe_pmu->features |= SPE_PMU_FEAT_FDS;
>> +
>>   	/* This field has a spaced out encoding, so just use a look-up */
>>   	fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg);
>>   	switch (fld) {
>>
>> -- 
>> 2.34.1
>>
>