7 files changed, 282 insertions, 242 deletions

diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 78ef7115be3d..a74521b79eaa 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,14 +1,13 @@
-perf-y += header.o
-perf-y += machine.o
-perf-y += perf_regs.o
-perf-y += tsc.o
-perf-y += pmu.o
-perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-$(CONFIG_DWARF)     += dwarf-regs.o
-perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
-perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+perf-util-y += header.o
+perf-util-y += machine.o
+perf-util-y += perf_regs.o
+perf-util-y += tsc.o
+perf-util-y += pmu.o
+perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
+perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
-perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
+perf-util-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
 			      ../../arm/util/cs-etm.o \
 			      arm-spe.o mem-events.o hisi-ptt.o
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 51ccbfd3d246..4f2833b62ff5 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <time.h>
 
@@ -22,9 +23,12 @@
 #include "../../../util/debug.h"
 #include "../../../util/auxtrace.h"
 #include "../../../util/record.h"
+#include "../../../util/header.h"
 #include "../../../util/arm-spe.h"
 #include <tools/libc_compat.h> // reallocarray
 
+#define ARM_SPE_CPU_MAGIC		0x1010101010101010ULL
+
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
 
@@ -36,11 +40,97 @@ struct arm_spe_recording {
 	bool			*wrapped;
 };
 
+/* Iterate config list to detect if the "freq" parameter is set */
+static bool arm_spe_is_set_freq(struct evsel *evsel)
+{
+	struct evsel_config_term *term;
+
+	list_for_each_entry(term, &evsel->config_terms, list) {
+		if (term->type == EVSEL__CONFIG_TERM_FREQ)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * arm_spe_find_cpus() returns a new cpu map, and the caller should invoke
+ * perf_cpu_map__put() to release the map after use.
+ */
+static struct perf_cpu_map *arm_spe_find_cpus(struct evlist *evlist)
+{
+	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
+	struct perf_cpu_map *intersect_cpus;
+
+	/* cpu map is not "any" CPU , we have specific CPUs to work with */
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
+	/* Event can be "any" CPU so count all CPUs. */
+	} else {
+		intersect_cpus = online_cpus;
+	}
+
+	return intersect_cpus;
+}
+
 static size_t
 arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
-		       struct evlist *evlist __maybe_unused)
+		       struct evlist *evlist)
 {
-	return ARM_SPE_AUXTRACE_PRIV_SIZE;
+	struct perf_cpu_map *cpu_map = arm_spe_find_cpus(evlist);
+	size_t size;
+
+	if (!cpu_map)
+		return 0;
+
+	size = ARM_SPE_AUXTRACE_PRIV_MAX +
+	       ARM_SPE_CPU_PRIV_MAX * perf_cpu_map__nr(cpu_map);
+	size *= sizeof(u64);
+
+	perf_cpu_map__put(cpu_map);
+	return size;
+}
+
+static int arm_spe_save_cpu_header(struct auxtrace_record *itr,
+				   struct perf_cpu cpu, __u64 data[])
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_pmu *pmu = NULL;
+	char *cpuid = NULL;
+	u64 val;
+
+	/* Read CPU MIDR */
+	cpuid = get_cpuid_allow_env_override(cpu);
+	if (!cpuid)
+		return -ENOMEM;
+	val = strtol(cpuid, NULL, 16);
+
+	data[ARM_SPE_MAGIC] = ARM_SPE_CPU_MAGIC;
+	data[ARM_SPE_CPU] = cpu.cpu;
+	data[ARM_SPE_CPU_NR_PARAMS] = ARM_SPE_CPU_PRIV_MAX - ARM_SPE_CPU_MIDR;
+	data[ARM_SPE_CPU_MIDR] = val;
+
+	/* Find the associate Arm SPE PMU for the CPU */
+	if (perf_cpu_map__has(sper->arm_spe_pmu->cpus, cpu))
+		pmu = sper->arm_spe_pmu;
+
+	if (!pmu) {
+		/* No Arm SPE PMU is found */
+		data[ARM_SPE_CPU_PMU_TYPE] = ULLONG_MAX;
+		data[ARM_SPE_CAP_MIN_IVAL] = 0;
+	} else {
+		data[ARM_SPE_CPU_PMU_TYPE] = pmu->type;
+
+		if (perf_pmu__scan_file(pmu, "caps/min_interval", "%lu", &val) != 1)
+			val = 0;
+		data[ARM_SPE_CAP_MIN_IVAL] = val;
+	}
+
+	free(cpuid);
+	return ARM_SPE_CPU_PRIV_MAX;
 }
 
 static int arm_spe_info_fill(struct auxtrace_record *itr,
@@ -48,20 +138,46 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 			     struct perf_record_auxtrace_info *auxtrace_info,
 			     size_t priv_size)
 {
+	int i, ret;
+	size_t offset;
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+	struct perf_cpu_map *cpu_map;
+	struct perf_cpu cpu;
+	__u64 *data;
 
-	if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
+	if (priv_size != arm_spe_info_priv_size(itr, session->evlist))
 		return -EINVAL;
 
 	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
+	cpu_map = arm_spe_find_cpus(session->evlist);
+	if (!cpu_map)
+		return -EINVAL;
+
 	auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
-	auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type;
+	auxtrace_info->priv[ARM_SPE_HEADER_VERSION] = ARM_SPE_HEADER_CURRENT_VERSION;
+	auxtrace_info->priv[ARM_SPE_HEADER_SIZE] =
+		ARM_SPE_AUXTRACE_PRIV_MAX - ARM_SPE_HEADER_VERSION;
+	auxtrace_info->priv[ARM_SPE_PMU_TYPE_V2] = arm_spe_pmu->type;
+	auxtrace_info->priv[ARM_SPE_CPUS_NUM] = perf_cpu_map__nr(cpu_map);
+
+	offset = ARM_SPE_AUXTRACE_PRIV_MAX;
+	perf_cpu_map__for_each_cpu(cpu, i, cpu_map) {
+		assert(offset < priv_size);
+		data = &auxtrace_info->priv[offset];
+		ret = arm_spe_save_cpu_header(itr, cpu, data);
+		if (ret < 0)
+			goto out;
+		offset += ret;
+	}
 
-	return 0;
+	ret = 0;
+out:
+	perf_cpu_map__put(cpu_map);
+	return ret;
 }
 
 static void
@@ -132,38 +248,48 @@ static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu)
 	return sample_period;
 }
 
-static int arm_spe_recording_options(struct auxtrace_record *itr,
-				     struct evlist *evlist,
-				     struct record_opts *opts)
+static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus)
 {
-	struct arm_spe_recording *sper =
-			container_of(itr, struct arm_spe_recording, itr);
-	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
-	struct evsel *evsel, *arm_spe_evsel = NULL;
-	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
-	bool privileged = perf_event_paranoid_check(-1);
-	struct evsel *tracking_evsel;
-	int err;
 	u64 bit;
 
-	sper->evlist = evlist;
+	evsel->core.attr.freq = 0;
+	evsel->core.attr.sample_period = arm_spe_pmu__sample_period(evsel->pmu);
+	evsel->needs_auxtrace_mmap = true;
 
-	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->core.attr.type == arm_spe_pmu->type) {
-			if (arm_spe_evsel) {
-				pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n");
-				return -EINVAL;
-			}
-			evsel->core.attr.freq = 0;
-			evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
-			evsel->needs_auxtrace_mmap = true;
-			arm_spe_evsel = evsel;
-			opts->full_auxtrace = true;
-		}
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	evlist__to_front(evsel->evlist, evsel);
+
+	/*
+	 * In the case of per-cpu mmaps, sample CPU for AUX event;
+	 * also enable the timestamp tracing for samples correlation.
+	 */
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
+		evsel__set_sample_bit(evsel, CPU);
+		evsel__set_config_if_unset(evsel->pmu, evsel, "ts_enable", 1);
 	}
 
-	if (!opts->full_auxtrace)
-		return 0;
+	/*
+	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
+	 * on the opening of the event or the SPE data produced.
+	 */
+	evsel__set_sample_bit(evsel, DATA_SRC);
+
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(evsel->pmu, "pa_enable");
+	if (evsel->core.attr.config & bit)
+		evsel__set_sample_bit(evsel, PHYS_ADDR);
+}
+
+static int arm_spe_setup_aux_buffer(struct record_opts *opts)
+{
+	bool privileged = perf_event_paranoid_check(-1);
 
 	/*
 	 * we are in snapshot mode.
@@ -193,6 +319,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
 			return -EINVAL;
 		}
+
+		pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME,
+			  opts->auxtrace_snapshot_size);
 	}
 
 	/* We are in full trace mode but '-m,xyz' wasn't specified */
@@ -218,40 +347,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		}
 	}
 
-	if (opts->auxtrace_snapshot_mode)
-		pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME,
-			  opts->auxtrace_snapshot_size);
-
-	/*
-	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
-	 * must come first.
-	 */
-	evlist__to_front(evlist, arm_spe_evsel);
-
-	/*
-	 * In the case of per-cpu mmaps, sample CPU for AUX event;
-	 * also enable the timestamp tracing for samples correlation.
-	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
-		evsel__set_sample_bit(arm_spe_evsel, CPU);
-		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
-					   "ts_enable", 1);
-	}
-
-	/*
-	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
-	 * on the opening of the event or the SPE data produced.
-	 */
-	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
+	return 0;
+}
 
-	/*
-	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
-	 * inform that the resulting output's SPE samples contain physical addresses
-	 * where applicable.
-	 */
-	bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable");
-	if (arm_spe_evsel->core.attr.config & bit)
-		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
+static int arm_spe_setup_tracking_event(struct evlist *evlist,
+					struct record_opts *opts)
+{
+	int err;
+	struct evsel *tracking_evsel;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 
 	/* Add dummy event to keep tracking */
 	err = parse_event(evlist, "dummy:u");
@@ -265,7 +369,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
 		evsel__set_sample_bit(tracking_evsel, CPU);
 
@@ -277,6 +381,60 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	return 0;
 }
 
+static int arm_spe_recording_options(struct auxtrace_record *itr,
+				     struct evlist *evlist,
+				     struct record_opts *opts)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct evsel *evsel, *tmp;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
+	bool discard = false;
+	int err;
+
+	sper->evlist = evlist;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel__is_aux_event(evsel)) {
+			if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) {
+				pr_err("Found unexpected auxtrace event: %s\n",
+				       evsel->pmu->name);
+				return -EINVAL;
+			}
+			opts->full_auxtrace = true;
+
+			if (opts->user_freq != UINT_MAX ||
+			    arm_spe_is_set_freq(evsel)) {
+				pr_err("Arm SPE: Frequency is not supported. "
+				       "Set period with -c option or PMU parameter (-e %s/period=NUM/).\n",
+				       evsel->pmu->name);
+				return -EINVAL;
+			}
+		}
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	evlist__for_each_entry_safe(evlist, tmp, evsel) {
+		if (evsel__is_aux_event(evsel)) {
+			arm_spe_setup_evsel(evsel, cpus);
+			if (evsel->core.attr.config &
+			    perf_pmu__format_bits(evsel->pmu, "discard"))
+				discard = true;
+		}
+	}
+
+	if (discard)
+		return 0;
+
+	err = arm_spe_setup_aux_buffer(opts);
+	if (err)
+		return err;
+
+	return arm_spe_setup_tracking_event(evlist, opts);
+}
+
 static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
 					 struct record_opts *opts,
 					 const char *str)
@@ -301,12 +459,16 @@ static int arm_spe_snapshot_start(struct auxtrace_record *itr)
 	struct arm_spe_recording *ptr =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct evsel *evsel;
+	int ret = -EINVAL;
 
 	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
-			return evsel__disable(evsel);
+		if (evsel__is_aux_event(evsel)) {
+			ret = evsel__disable(evsel);
+			if (ret < 0)
+				return ret;
+		}
 	}
-	return -EINVAL;
+	return ret;
 }
 
 static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
@@ -314,12 +476,16 @@ static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
 	struct arm_spe_recording *ptr =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct evsel *evsel;
+	int ret = -EINVAL;
 
 	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
-			return evsel__enable(evsel);
+		if (evsel__is_aux_event(evsel)) {
+			ret = evsel__enable(evsel);
+			if (ret < 0)
+				return ret;
+		}
 	}
-	return -EINVAL;
+	return ret;
 }
 
 static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx)
@@ -497,7 +663,6 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	}
 
 	sper->arm_spe_pmu = arm_spe_pmu;
-	sper->itr.pmu = arm_spe_pmu;
 	sper->itr.snapshot_start = arm_spe_snapshot_start;
 	sper->itr.snapshot_finish = arm_spe_snapshot_finish;
 	sper->itr.find_snapshot = arm_spe_find_snapshot;
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
deleted file mode 100644
index 917b97d7c5d3..000000000000
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ /dev/null
@@ -1,92 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 Will Deacon, ARM Ltd.
- */
-
-#include <errno.h>
-#include <stddef.h>
-#include <string.h>
-#include <dwarf-regs.h>
-#include <linux/ptrace.h> /* for struct user_pt_regs */
-#include <linux/stringify.h>
-
-struct pt_regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num) \
-	{.name = __stringify(%x##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-#define DWARFNUM2OFFSET(index) \
-	(index * sizeof((struct user_pt_regs *)0)->regs[0])
-
-/*
- * Reference:
- * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf
- */
-static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
-	GPR_DWARFNUM_NAME(0),
-	GPR_DWARFNUM_NAME(1),
-	GPR_DWARFNUM_NAME(2),
-	GPR_DWARFNUM_NAME(3),
-	GPR_DWARFNUM_NAME(4),
-	GPR_DWARFNUM_NAME(5),
-	GPR_DWARFNUM_NAME(6),
-	GPR_DWARFNUM_NAME(7),
-	GPR_DWARFNUM_NAME(8),
-	GPR_DWARFNUM_NAME(9),
-	GPR_DWARFNUM_NAME(10),
-	GPR_DWARFNUM_NAME(11),
-	GPR_DWARFNUM_NAME(12),
-	GPR_DWARFNUM_NAME(13),
-	GPR_DWARFNUM_NAME(14),
-	GPR_DWARFNUM_NAME(15),
-	GPR_DWARFNUM_NAME(16),
-	GPR_DWARFNUM_NAME(17),
-	GPR_DWARFNUM_NAME(18),
-	GPR_DWARFNUM_NAME(19),
-	GPR_DWARFNUM_NAME(20),
-	GPR_DWARFNUM_NAME(21),
-	GPR_DWARFNUM_NAME(22),
-	GPR_DWARFNUM_NAME(23),
-	GPR_DWARFNUM_NAME(24),
-	GPR_DWARFNUM_NAME(25),
-	GPR_DWARFNUM_NAME(26),
-	GPR_DWARFNUM_NAME(27),
-	GPR_DWARFNUM_NAME(28),
-	GPR_DWARFNUM_NAME(29),
-	REG_DWARFNUM_NAME("%lr", 30),
-	REG_DWARFNUM_NAME("%sp", 31),
-	REG_DWARFNUM_END,
-};
-
-/**
- * get_arch_regstr() - lookup register name from it's DWARF register number
- * @n:	the DWARF register number
- *
- * get_arch_regstr() returns the name of the register in struct
- * regdwarfnum_table from it's DWARF register number. If the register is not
- * found in the table, this returns NULL;
- */
-const char *get_arch_regstr(unsigned int n)
-{
-	const struct pt_regs_dwarfnum *roff;
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (roff->dwarfnum == n)
-			return roff->name;
-	return NULL;
-}
-
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_dwarfnum *roff;
-
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return DWARFNUM2OFFSET(roff->dwarfnum);
-	return -EINVAL;
-}
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 97037499152e..f445a2dd6293 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -4,8 +4,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
-#include <util/cpumap.h>
-#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include <errno.h>
 #include "debug.h"
@@ -16,76 +14,66 @@
 #define MIDR_REVISION_MASK      GENMASK(3, 0)
 #define MIDR_VARIANT_MASK	GENMASK(23, 20)
 
-static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
+	char path[PATH_MAX];
+	FILE *file;
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
-	int ret = EINVAL;
 
+	assert(cpu.cpu != -1);
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
 
-	cpus = perf_cpu_map__get(cpus);
+	scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, sysfs, cpu.cpu);
 
-	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
-		char path[PATH_MAX];
-		FILE *file;
-
-		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
-			  sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu);
-
-		file = fopen(path, "r");
-		if (!file) {
-			pr_debug("fopen failed for file %s\n", path);
-			continue;
-		}
+	file = fopen(path, "r");
+	if (!file) {
+		pr_debug("fopen failed for file %s\n", path);
+		return EINVAL;
+	}
 
-		if (!fgets(buf, MIDR_SIZE, file)) {
-			fclose(file);
-			continue;
-		}
+	if (!fgets(buf, MIDR_SIZE, file)) {
+		pr_debug("Failed to read file %s\n", path);
 		fclose(file);
-
-		/* got midr break loop */
-		ret = 0;
-		break;
+		return EINVAL;
 	}
-
-	perf_cpu_map__put(cpus);
-	return ret;
+	fclose(file);
+	return 0;
 }
 
-int get_cpuid(char *buf, size_t sz)
+int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
-	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
-	int ret;
+	struct perf_cpu_map *cpus;
+	int idx;
+
+	if (cpu.cpu != -1)
+		return _get_cpuid(buf, sz, cpu);
 
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return EINVAL;
 
-	ret = _get_cpuid(buf, sz, cpus);
-
-	perf_cpu_map__put(cpus);
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		int ret = _get_cpuid(buf, sz, cpu);
 
-	return ret;
+		if (ret == 0)
+			return 0;
+	}
+	return EINVAL;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+char *get_cpuid_str(struct perf_cpu cpu)
 {
-	char *buf = NULL;
+	char *buf = malloc(MIDR_SIZE);
 	int res;
 
-	if (!pmu || !pmu->cpus)
-		return NULL;
-
-	buf = malloc(MIDR_SIZE);
 	if (!buf)
 		return NULL;
 
 	/* read midr from list of cpus mapped to this pmu */
-	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	res = get_cpuid(buf, MIDR_SIZE, cpu);
 	if (res) {
-		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+		pr_err("failed to get cpuid string for CPU %d\n", cpu.cpu);
 		free(buf);
 		buf = NULL;
 	}
diff --git a/tools/perf/arch/arm64/util/hisi-ptt.c b/tools/perf/arch/arm64/util/hisi-ptt.c
index ba97c8a562a0..eac9739c87e6 100644
--- a/tools/perf/arch/arm64/util/hisi-ptt.c
+++ b/tools/perf/arch/arm64/util/hisi-ptt.c
@@ -174,7 +174,6 @@ struct auxtrace_record *hisi_ptt_recording_init(int *err,
 	}
 
 	pttr->hisi_ptt_pmu = hisi_ptt_pmu;
-	pttr->itr.pmu = hisi_ptt_pmu;
 	pttr->itr.recording_options = hisi_ptt_recording_options;
 	pttr->itr.info_priv_size = hisi_ptt_info_priv_size;
 	pttr->itr.info_fill = hisi_ptt_info_fill;
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index 2a4eab2d160e..895fb0d0610c 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -1,30 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <internal/cpumap.h>
-#include "../../../util/cpumap.h"
-#include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
+#include "../../../util/tool_pmu.h"
 #include <api/fs/fs.h>
-#include <math.h>
 
-const struct pmu_metrics_table *pmu_metrics_table__find(void)
-{
-	struct perf_pmu *pmu;
-
-	/* Metrics aren't currently supported on heterogeneous Arm systems */
-	if (perf_pmus__num_core_pmus() > 1)
-		return NULL;
-
-	/* Doesn't matter which one here because they'll all be the same */
-	pmu = perf_pmus__find_core_pmu();
-	if (pmu)
-		return perf_pmu__find_metrics_table(pmu);
-
-	return NULL;
-}
-
-double perf_pmu__cpu_slots_per_cycle(void)
+u64 tool_pmu__cpu_slots_per_cycle(void)
 {
 	char path[PATH_MAX];
 	unsigned long long slots = 0;
@@ -41,5 +22,5 @@ double perf_pmu__cpu_slots_per_cycle(void)
 		filename__read_ull(path, &slots);
 	}
 
-	return slots ? (double)slots : NAN;
+	return slots;
 }
diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c
index e056d50ab42e..b89b0a7e5ad9 100644
--- a/tools/perf/arch/arm64/util/unwind-libdw.c
+++ b/tools/perf/arch/arm64/util/unwind-libdw.c
@@ -8,7 +8,7 @@
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
 	struct unwind_info *ui = arg;
-	struct regs_dump *user_regs = &ui->sample->user_regs;
+	struct regs_dump *user_regs = perf_sample__user_regs(ui->sample);
 	Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc;
 
 #define REG(r) ({						\