perf pmu: Add #slots literal support for arm64

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.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrew Kilroy <andrew.kilroy@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuai Xue <xueshuai@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Zhuo Song <zhuo.song@linux.alibaba.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/1673940573-90503-2-git-send-email-renyu.zj@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/arm64/util/pmu.c

@@ -3,8 +3,10 @@
 #include <internal/cpumap.h>
 #include "../../../util/cpumap.h"
 #include "../../../util/pmu.h"
+#include <api/fs/fs.h>
+#include <math.h>
 
-const struct pmu_events_table *pmu_events_table__find(void)
+static struct perf_pmu *pmu__find_core_pmu(void)
 {
 	struct perf_pmu *pmu = NULL;
 
@@ -19,8 +21,37 @@ 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__find_core_pmu();
+
+	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__find_core_pmu();
+
+	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 slots ? (double)slots : NAN;
+}

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();
+		goto out;
+	}
 
 	pr_err("Unrecognized literal '%s'", literal);
 out:

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;
+}

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 */