[PATCH v4 1/2] arm64: perf: Add support caps in sysfs

[Shaokun Zhang]

Hi Will,

在 2020/7/21 16:21, Will Deacon 写道:
> On Tue, Jul 21, 2020 at 03:44:47PM +0800, Shaokun Zhang wrote:
>> ARMv8.4-PMU introduces the PMMIR_EL1 registers and some new PMU events,
>> like STALL_SLOT etc, are related to it. Let's add a caps directory to
>> /sys/bus/event_source/devices/armv8_pmuv3_0/ and support slots from
>> PMMIR_EL1 registers in this entry. The user programs can get the slots
>> from sysfs directly.
>>
>> Cc: Will Deacon <will at kernel.org>
>> Cc: Mark Rutland <mark.rutland at arm.com>
>> Signed-off-by: Shaokun Zhang <zhangshaokun at hisilicon.com>
>> ---
>> ChangeLog in v4:
>>     * Address Will's comments.
>>
>> ChangeLog in v3:
>>     * Fix one typo in patch3
>>
>> ChangeLog in v2:
>>     * Add caps entry in sysfs
>>     * Fix the PMU events typos
>>     * Add one new patch to correct event ID in sysfs
>>
>>  arch/arm64/include/asm/sysreg.h |   2 +
>>  arch/arm64/kernel/perf_event.c  | 125 ++++++++++++++++++++++++++++------------
>>  include/linux/perf/arm_pmu.h    |   1 +
>>  3 files changed, 91 insertions(+), 37 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
>> index 463175f80341..56c45a9207c7 100644
>> --- a/arch/arm64/include/asm/sysreg.h
>> +++ b/arch/arm64/include/asm/sysreg.h
>> @@ -321,6 +321,8 @@
>>  #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
>>  #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
>>  
>> +#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
>> +
>>  #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
>>  #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
>>  
>> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
>> index 4d7879484cec..ed0012979271 100644
>> --- a/arch/arm64/kernel/perf_event.c
>> +++ b/arch/arm64/kernel/perf_event.c
>> @@ -277,6 +277,51 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
>>  	.attrs = armv8_pmuv3_format_attrs,
>>  };
>>  
>> +static int armv8pmu_get_pmu_version(void)
>> +{
>> +	int pmuver;
>> +	u64 dfr0;
>> +
>> +	dfr0 = read_sysreg(id_aa64dfr0_el1);
>> +	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
>> +			ID_AA64DFR0_PMUVER_SHIFT);
>> +
>> +	return pmuver;
>> +}
>> +
>> +static umode_t
>> +armv8pmu_caps_attr_is_visible(struct kobject *kobj, struct attribute *attr,
>> +			      int unused)
>> +{
>> +	int pmuver = armv8pmu_get_pmu_version();
>> +
>> +	if (pmuver >= ID_AA64DFR0_PMUVER_8_4)
>> +		return attr->mode;
>> +
>> +	return 0;
>> +}
>> +
>> +static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
>> +			  char *buf)
>> +{
>> +	int slots = read_sysreg_s(SYS_PMMIR_EL1) & 0xFF;
> 
> I'm still worried that this might trigger an UNDEF and panic the kernel
> if STALL_SLOTS is not supported. The Arm ARM isn't clear about the
> behaviour, so I think we have to assume the worst and check that STALL_SLOTS

Got it.

> is supported as well in armv8pmu_caps_attr_is_visible().
> 
> In other words, I think we have to check PMCEID1_EL0 as well as

In fact, I did this in v4, but I removed it when I did more check on SLOTS
meaning that I have replied in v3 thread. I will add it in next version.

Thanks,
Shaokun

> AA64DFR0_EL1.
> 
> Will
> 
> .
>