Re: [PATCH v7 1/9] perf pmu: Add #slots literal support for arm64

[Jing Zhang]

在 2023/1/15 上午6:15, Ian Rogers 写道:
> On Fri, Jan 13, 2023 at 1:22 AM Jing Zhang <renyu.zj@xxxxxxxxxxxxxxxxx> wrote:
>>
>> The slots in each architecture may be different, so add #slots literal
>> to obtain the slots of different architectures, and the #slots can be
>> applied in the metric. Currently, The #slots just support for arm64,
>> and other architectures will return NAN.
>>
>> On arm64, the value of slots is from the register PMMIR_EL1.SLOT, which
>> I can read in /sys/bus/event_source/device/armv8_pmuv3_*/caps/slots.
>> PMMIR_EL1.SLOT might read as zero if the PMU version is lower than
>> ID_AA64DFR0_EL1_PMUVer_V3P4 or the STALL_SLOT event is not implemented.
>>
>> Signed-off-by: Jing Zhang <renyu.zj@xxxxxxxxxxxxxxxxx>
>> ---
>>  tools/perf/arch/arm64/util/pmu.c | 34 ++++++++++++++++++++++++++++++++--
>>  tools/perf/util/expr.c           |  5 +++++
>>  tools/perf/util/pmu.c            |  6 ++++++
>>  tools/perf/util/pmu.h            |  1 +
>>  4 files changed, 44 insertions(+), 2 deletions(-)
>>
>> diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
>> index 477e513..5f8667b 100644
>> --- a/tools/perf/arch/arm64/util/pmu.c
>> +++ b/tools/perf/arch/arm64/util/pmu.c
>> @@ -3,8 +3,9 @@
>>  #include <internal/cpumap.h>
>>  #include "../../../util/cpumap.h"
>>  #include "../../../util/pmu.h"
>> +#include <api/fs/fs.h>
>>
>> -const struct pmu_events_table *pmu_events_table__find(void)
>> +static struct perf_pmu *pmu_core__find_same(void)
> 
> I'm not sure "find_same" is the best name here. I suspect it should be
> "find_core_pmu" which would agree with is_arm_pmu_core. Unfortunately
> "core" has become an overloaded term sometimes used interchangeably
> with CPU, hyperthread or SMT thread, it was a model name for Intel and
> it is used to distinguish a set of SMT threads running together from a
> single one. Anyway, for consistency I think perf_pmu__find_core_pmu is
> the most appropriate name (or pmu__find_core_pmu, I'm not sure why we
> get the extra perf_ prefix sometimes, in general that indicates the
> functionality is in libperf).
> 

The reason for using "pmu_core__find_same" before is to indicate that we're
only dealing with homogeneous cores. And in the tools/perf/util/pmu.c file,
most of the static functions have "pmu_" prefix, maybe we can use
"pmu_find_same_core_pmu"? Ian, John, what do you think?

Thanks,
Jing

> Aside from that, lgtm. Thanks,
> Ian
> 
>>  {
>>         struct perf_pmu *pmu = NULL;
>>
>> @@ -19,8 +20,37 @@ const struct pmu_events_table *pmu_events_table__find(void)
>>                 if (pmu->cpus->nr != cpu__max_cpu().cpu)
>>                         return NULL;
>>
>> -               return perf_pmu__find_table(pmu);
>> +               return pmu;
>>         }
>>
>>         return NULL;
>>  }
>> +
>> +const struct pmu_events_table *pmu_events_table__find(void)
>> +{
>> +       struct perf_pmu *pmu = pmu_core__find_same();
>> +
>> +       if (pmu)
>> +               return perf_pmu__find_table(pmu);
>> +
>> +       return NULL;
>> +}
>> +
>> +double perf_pmu__cpu_slots_per_cycle(void)
>> +{
>> +       char path[PATH_MAX];
>> +       unsigned long long slots = 0;
>> +       struct perf_pmu *pmu = pmu_core__find_same();
>> +
>> +       if (pmu) {
>> +               scnprintf(path, PATH_MAX,
>> +                       EVENT_SOURCE_DEVICE_PATH "%s/caps/slots", pmu->name);
>> +               /*
>> +                * The value of slots is not greater than 32 bits, but sysfs__read_int
>> +                * can't read value with 0x prefix, so use sysfs__read_ull instead.
>> +                */
>> +               sysfs__read_ull(path, &slots);
>> +       }
>> +
>> +       return (double)slots;
>> +}
>> diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
>> index 00dcde3..9d3076a 100644
>> --- a/tools/perf/util/expr.c
>> +++ b/tools/perf/util/expr.c
>> @@ -19,6 +19,7 @@
>>  #include <linux/zalloc.h>
>>  #include <ctype.h>
>>  #include <math.h>
>> +#include "pmu.h"
>>
>>  #ifdef PARSER_DEBUG
>>  extern int expr_debug;
>> @@ -448,6 +449,10 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
>>                 result = topology->core_cpus_lists;
>>                 goto out;
>>         }
>> +       if (!strcmp("#slots", literal)) {
>> +               result = perf_pmu__cpu_slots_per_cycle() ?: NAN;
>> +               goto out;
>> +       }
>>
>>         pr_err("Unrecognized literal '%s'", literal);
>>  out:
>> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
>> index 2bdeb89..cbb4fbf 100644
>> --- a/tools/perf/util/pmu.c
>> +++ b/tools/perf/util/pmu.c
>> @@ -19,6 +19,7 @@
>>  #include <regex.h>
>>  #include <perf/cpumap.h>
>>  #include <fnmatch.h>
>> +#include <math.h>
>>  #include "debug.h"
>>  #include "evsel.h"
>>  #include "pmu.h"
>> @@ -1993,3 +1994,8 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
>>         *ucpus_ptr = unmatched_cpus;
>>         return 0;
>>  }
>> +
>> +double __weak perf_pmu__cpu_slots_per_cycle(void)
>> +{
>> +       return NAN;
>> +}
>> diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
>> index 69ca000..fd414ba 100644
>> --- a/tools/perf/util/pmu.h
>> +++ b/tools/perf/util/pmu.h
>> @@ -259,4 +259,5 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
>>
>>  char *pmu_find_real_name(const char *name);
>>  char *pmu_find_alias_name(const char *name);
>> +double perf_pmu__cpu_slots_per_cycle(void);
>>  #endif /* __PMU_H */
>> --
>> 1.8.3.1
>>