19 files changed, 1063 insertions, 0 deletions

diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build
new file mode 100644
index 000000000..a7dd46a5b
--- /dev/null
+++ b/tools/perf/arch/arm64/Build
@@ -0,0 +1,2 @@
+perf-y += util/
+perf-y += tests/
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
new file mode 100644
index 000000000..dbef716a1
--- /dev/null
+++ b/tools/perf/arch/arm64/Makefile
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
+PERF_HAVE_JITDUMP := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
new file mode 100644
index 000000000..037e292ec
--- /dev/null
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <regex.h>
+#include <stdlib.h>
+
+struct arm64_annotate {
+	regex_t call_insn,
+		jump_insn;
+};
+
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+			    struct ins_operands *ops,
+			    struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	*s = ' ';
+	ops->target.name = strdup(s);
+	*s = '<';
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops, int max_ins_name);
+
+static struct ins_ops arm64_mov_ops = {
+	.parse	   = arm64_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
+static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct arm64_annotate *arm = arch->priv;
+	struct ins_ops *ops;
+	regmatch_t match[2];
+
+	if (!regexec(&arm->jump_insn, name, 2, match, 0))
+		ops = &jump_ops;
+	else if (!regexec(&arm->call_insn, name, 2, match, 0))
+		ops = &call_ops;
+	else if (!strcmp(name, "ret"))
+		ops = &ret_ops;
+	else
+		ops = &arm64_mov_ops;
+
+	arch__associate_ins_ops(arch, name, ops);
+	return ops;
+}
+
+static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	struct arm64_annotate *arm;
+	int err;
+
+	if (arch->initialized)
+		return 0;
+
+	arm = zalloc(sizeof(*arm));
+	if (!arm)
+		return ENOMEM;
+
+	/* bl, blr */
+	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
+	if (err)
+		goto out_free_arm;
+	/* b, b.cond, br, cbz/cbnz, tbz/tbnz */
+	err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$",
+		      REG_EXTENDED);
+	if (err)
+		goto out_free_call;
+
+	arch->initialized = true;
+	arch->priv	  = arm;
+	arch->associate_instruction_ops   = arm64__associate_instruction_ops;
+	arch->objdump.comment_char	  = '/';
+	arch->objdump.skip_functions_char = '+';
+	return 0;
+
+out_free_call:
+	regfree(&arm->call_insn);
+out_free_arm:
+	free(arm);
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
+}
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000..459469b72
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+incpath=$3
+input=$4
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c -I $incpath/include/uapi $input \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h
new file mode 100644
index 000000000..90ec4c8cb
--- /dev/null
+++ b/tools/perf/arch/arm64/include/arch-tests.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
new file mode 100644
index 000000000..177b2855f
--- /dev/null
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const aarch64_regstr_tbl[] = {
+	"%x0", "%x1", "%x2", "%x3", "%x4",
+	"%x5", "%x6", "%x7", "%x8", "%x9",
+	"%x10", "%x11", "%x12", "%x13", "%x14",
+	"%x15", "%x16", "%x17", "%x18", "%x19",
+	"%x20", "%x21", "%x22", "%x23", "%x24",
+	"%x25", "%x26", "%x27", "%x28", "%x29",
+	"%lr", "%sp",
+};
+#endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
new file mode 100644
index 000000000..fa3e07459
--- /dev/null
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
+
+#define PERF_REG_IP	PERF_REG_ARM64_PC
+#define PERF_REG_SP	PERF_REG_ARM64_SP
+
+static inline const char *__perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build
new file mode 100644
index 000000000..a61c06bdb
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/Build
@@ -0,0 +1,4 @@
+perf-y += regs_load.o
+perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+perf-y += arch-tests.o
diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c
new file mode 100644
index 000000000..5b1543c98
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/arch-tests.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "DWARF unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
new file mode 100644
index 000000000..46147a483
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "maps.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+		struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+	map = maps__find(thread->maps, (u64)sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+		struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
new file mode 100644
index 000000000..d49de40b6
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+
+.text
+.type perf_regs_load,%function
+#define STR_REG(r)	str x##r, [x0, 8 * r]
+#define LDR_REG(r)	ldr x##r, [x0, 8 * r]
+#define SP	(8 * 31)
+#define PC	(8 * 32)
+SYM_FUNC_START(perf_regs_load)
+	STR_REG(0)
+	STR_REG(1)
+	STR_REG(2)
+	STR_REG(3)
+	STR_REG(4)
+	STR_REG(5)
+	STR_REG(6)
+	STR_REG(7)
+	STR_REG(8)
+	STR_REG(9)
+	STR_REG(10)
+	STR_REG(11)
+	STR_REG(12)
+	STR_REG(13)
+	STR_REG(14)
+	STR_REG(15)
+	STR_REG(16)
+	STR_REG(17)
+	STR_REG(18)
+	STR_REG(19)
+	STR_REG(20)
+	STR_REG(21)
+	STR_REG(22)
+	STR_REG(23)
+	STR_REG(24)
+	STR_REG(25)
+	STR_REG(26)
+	STR_REG(27)
+	STR_REG(28)
+	STR_REG(29)
+	STR_REG(30)
+	mov x1, sp
+	str x1, [x0, #SP]
+	str x30, [x0, #PC]
+	LDR_REG(1)
+	ret
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
new file mode 100644
index 000000000..eddaf9bf5
--- /dev/null
+++ b/tools/perf/arch/arm64/util/Build
@@ -0,0 +1,11 @@
+perf-y += header.o
+perf-y += perf_regs.o
+perf-y += tsc.o
+perf-$(CONFIG_DWARF)     += dwarf-regs.o
+perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
+			      ../../arm/util/auxtrace.o \
+			      ../../arm/util/cs-etm.o \
+			      arm-spe.o
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
new file mode 100644
index 000000000..37765e2bd
--- /dev/null
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/zalloc.h>
+#include <time.h>
+
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/session.h"
+#include <internal/lib.h> // page_size
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/arm-spe.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+
+struct arm_spe_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*arm_spe_pmu;
+	struct evlist		*evlist;
+};
+
+static size_t
+arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+		       struct evlist *evlist __maybe_unused)
+{
+	return ARM_SPE_AUXTRACE_PRIV_SIZE;
+}
+
+static int arm_spe_info_fill(struct auxtrace_record *itr,
+			     struct perf_session *session,
+			     struct perf_record_auxtrace_info *auxtrace_info,
+			     size_t priv_size)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+
+	if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->core.nr_mmaps)
+		return -EINVAL;
+
+	auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
+	auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type;
+
+	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 perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+	struct evsel *evsel, *arm_spe_evsel = NULL;
+	bool privileged = perf_event_paranoid_check(-1);
+	struct evsel *tracking_evsel;
+	int err;
+
+	sper->evlist = evlist;
+
+	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 = 1;
+			arm_spe_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	/* We are in full trace mode but '-m,xyz' wasn't specified */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for ARM SPE: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	perf_evlist__to_front(evlist, arm_spe_evsel);
+
+	evsel__set_sample_bit(arm_spe_evsel, CPU);
+	evsel__set_sample_bit(arm_spe_evsel, TIME);
+	evsel__set_sample_bit(arm_spe_evsel, TID);
+
+	/*
+	 * 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);
+
+	/* Add dummy event to keep tracking */
+	err = parse_events(evlist, "dummy:u", NULL);
+	if (err)
+		return err;
+
+	tracking_evsel = evlist__last(evlist);
+	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->core.attr.freq = 0;
+	tracking_evsel->core.attr.sample_period = 1;
+	evsel__set_sample_bit(tracking_evsel, TIME);
+	evsel__set_sample_bit(tracking_evsel, CPU);
+	evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+	return 0;
+}
+
+static u64 arm_spe_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC_RAW, &ts);
+
+	return ts.tv_sec ^ ts.tv_nsec;
+}
+
+static void arm_spe_recording_free(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+
+	free(sper);
+}
+
+struct auxtrace_record *arm_spe_recording_init(int *err,
+					       struct perf_pmu *arm_spe_pmu)
+{
+	struct arm_spe_recording *sper;
+
+	if (!arm_spe_pmu) {
+		*err = -ENODEV;
+		return NULL;
+	}
+
+	sper = zalloc(sizeof(struct arm_spe_recording));
+	if (!sper) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.pmu = arm_spe_pmu;
+	sper->itr.recording_options = arm_spe_recording_options;
+	sper->itr.info_priv_size = arm_spe_info_priv_size;
+	sper->itr.info_fill = arm_spe_info_fill;
+	sper->itr.free = arm_spe_recording_free;
+	sper->itr.reference = arm_spe_reference;
+	sper->itr.read_finish = auxtrace_record__read_finish;
+	sper->itr.alignment = 0;
+
+	*err = 0;
+	return &sper->itr;
+}
+
+struct perf_event_attr
+*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu)
+{
+	struct perf_event_attr *attr;
+
+	attr = zalloc(sizeof(struct perf_event_attr));
+	if (!attr) {
+		pr_err("arm_spe default config cannot allocate a perf_event_attr\n");
+		return NULL;
+	}
+
+	/*
+	 * If kernel driver doesn't advertise a minimum,
+	 * use max allowable by PMSIDR_EL1.INTERVAL
+	 */
+	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
+				  &attr->sample_period) != 1) {
+		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
+		attr->sample_period = 4096;
+	}
+
+	arm_spe_pmu->selectable = true;
+	arm_spe_pmu->is_uncore = false;
+
+	return attr;
+}
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
new file mode 100644
index 000000000..917b97d7c
--- /dev/null
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -0,0 +1,92 @@
+// 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
new file mode 100644
index 000000000..d730666ab
--- /dev/null
+++ b/tools/perf/arch/arm64/util/header.c
@@ -0,0 +1,101 @@
+#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"
+#include "header.h"
+
+#define MIDR "/regs/identification/midr_el1"
+#define MIDR_SIZE 19
+#define MIDR_REVISION_MASK      0xf
+#define MIDR_VARIANT_SHIFT      20
+#define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
+
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
+{
+	const char *sysfs = sysfs__mountpoint();
+	u64 midr = 0;
+	int cpu;
+
+	if (!sysfs || sz < MIDR_SIZE)
+		return EINVAL;
+
+	cpus = perf_cpu_map__get(cpus);
+
+	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, cpus->map[cpu]);
+
+		file = fopen(path, "r");
+		if (!file) {
+			pr_debug("fopen failed for file %s\n", path);
+			continue;
+		}
+
+		if (!fgets(buf, MIDR_SIZE, file)) {
+			fclose(file);
+			continue;
+		}
+		fclose(file);
+
+		/* Ignore/clear Variant[23:20] and
+		 * Revision[3:0] of MIDR
+		 */
+		midr = strtoul(buf, NULL, 16);
+		midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK));
+		scnprintf(buf, MIDR_SIZE, "0x%016lx", midr);
+		/* got midr break loop */
+		break;
+	}
+
+	perf_cpu_map__put(cpus);
+
+	if (!midr)
+		return EINVAL;
+
+	return 0;
+}
+
+int get_cpuid(char *buf, size_t sz)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	int ret;
+
+	if (!cpus)
+		return EINVAL;
+
+	ret = _get_cpuid(buf, sz, cpus);
+
+	perf_cpu_map__put(cpus);
+
+	return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+	char *buf = NULL;
+	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);
+	if (res) {
+		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+		free(buf);
+		buf = NULL;
+	}
+
+	return buf;
+}
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
new file mode 100644
index 000000000..2833e101a
--- /dev/null
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/arm64/util/tsc.c b/tools/perf/arch/arm64/util/tsc.c
new file mode 100644
index 000000000..cc85bd9e7
--- /dev/null
+++ b/tools/perf/arch/arm64/util/tsc.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+
+#include "../../../util/tsc.h"
+
+u64 rdtsc(void)
+{
+	u64 val;
+
+	/*
+	 * According to ARM DDI 0487F.c, from Armv8.0 to Armv8.5 inclusive, the
+	 * system counter is at least 56 bits wide; from Armv8.6, the counter
+	 * must be 64 bits wide.  So the system counter could be less than 64
+	 * bits wide and it is attributed with the flag 'cap_user_time_short'
+	 * is true.
+	 */
+	asm volatile("mrs %0, cntvct_el0" : "=r" (val));
+
+	return val;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c
new file mode 100644
index 000000000..a50941629
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libdw.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <elfutils/libdwfl.h>
+#include "../../../util/unwind-libdw.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/event.h"
+
+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;
+	Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(X0);
+	dwarf_regs[1]  = REG(X1);
+	dwarf_regs[2]  = REG(X2);
+	dwarf_regs[3]  = REG(X3);
+	dwarf_regs[4]  = REG(X4);
+	dwarf_regs[5]  = REG(X5);
+	dwarf_regs[6]  = REG(X6);
+	dwarf_regs[7]  = REG(X7);
+	dwarf_regs[8]  = REG(X8);
+	dwarf_regs[9]  = REG(X9);
+	dwarf_regs[10] = REG(X10);
+	dwarf_regs[11] = REG(X11);
+	dwarf_regs[12] = REG(X12);
+	dwarf_regs[13] = REG(X13);
+	dwarf_regs[14] = REG(X14);
+	dwarf_regs[15] = REG(X15);
+	dwarf_regs[16] = REG(X16);
+	dwarf_regs[17] = REG(X17);
+	dwarf_regs[18] = REG(X18);
+	dwarf_regs[19] = REG(X19);
+	dwarf_regs[20] = REG(X20);
+	dwarf_regs[21] = REG(X21);
+	dwarf_regs[22] = REG(X22);
+	dwarf_regs[23] = REG(X23);
+	dwarf_regs[24] = REG(X24);
+	dwarf_regs[25] = REG(X25);
+	dwarf_regs[26] = REG(X26);
+	dwarf_regs[27] = REG(X27);
+	dwarf_regs[28] = REG(X28);
+	dwarf_regs[29] = REG(X29);
+	dwarf_regs[30] = REG(LR);
+	dwarf_regs[31] = REG(SP);
+
+	if (!dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX,
+					 dwarf_regs))
+		return false;
+
+	dwarf_pc = REG(PC);
+	dwfl_thread_state_register_pc(thread, dwarf_pc);
+
+	return true;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
new file mode 100644
index 000000000..1495a9523
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+
+#ifndef REMOTE_UNWIND_LIBUNWIND
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+#endif
+#include "../../util/debug.h"
+
+int LIBUNWIND__ARCH_REG_ID(int regnum)
+{
+	switch (regnum) {
+	case UNW_AARCH64_X0:
+		return PERF_REG_ARM64_X0;
+	case UNW_AARCH64_X1:
+		return PERF_REG_ARM64_X1;
+	case UNW_AARCH64_X2:
+		return PERF_REG_ARM64_X2;
+	case UNW_AARCH64_X3:
+		return PERF_REG_ARM64_X3;
+	case UNW_AARCH64_X4:
+		return PERF_REG_ARM64_X4;
+	case UNW_AARCH64_X5:
+		return PERF_REG_ARM64_X5;
+	case UNW_AARCH64_X6:
+		return PERF_REG_ARM64_X6;
+	case UNW_AARCH64_X7:
+		return PERF_REG_ARM64_X7;
+	case UNW_AARCH64_X8:
+		return PERF_REG_ARM64_X8;
+	case UNW_AARCH64_X9:
+		return PERF_REG_ARM64_X9;
+	case UNW_AARCH64_X10:
+		return PERF_REG_ARM64_X10;
+	case UNW_AARCH64_X11:
+		return PERF_REG_ARM64_X11;
+	case UNW_AARCH64_X12:
+		return PERF_REG_ARM64_X12;
+	case UNW_AARCH64_X13:
+		return PERF_REG_ARM64_X13;
+	case UNW_AARCH64_X14:
+		return PERF_REG_ARM64_X14;
+	case UNW_AARCH64_X15:
+		return PERF_REG_ARM64_X15;
+	case UNW_AARCH64_X16:
+		return PERF_REG_ARM64_X16;
+	case UNW_AARCH64_X17:
+		return PERF_REG_ARM64_X17;
+	case UNW_AARCH64_X18:
+		return PERF_REG_ARM64_X18;
+	case UNW_AARCH64_X19:
+		return PERF_REG_ARM64_X19;
+	case UNW_AARCH64_X20:
+		return PERF_REG_ARM64_X20;
+	case UNW_AARCH64_X21:
+		return PERF_REG_ARM64_X21;
+	case UNW_AARCH64_X22:
+		return PERF_REG_ARM64_X22;
+	case UNW_AARCH64_X23:
+		return PERF_REG_ARM64_X23;
+	case UNW_AARCH64_X24:
+		return PERF_REG_ARM64_X24;
+	case UNW_AARCH64_X25:
+		return PERF_REG_ARM64_X25;
+	case UNW_AARCH64_X26:
+		return PERF_REG_ARM64_X26;
+	case UNW_AARCH64_X27:
+		return PERF_REG_ARM64_X27;
+	case UNW_AARCH64_X28:
+		return PERF_REG_ARM64_X28;
+	case UNW_AARCH64_X29:
+		return PERF_REG_ARM64_X29;
+	case UNW_AARCH64_X30:
+		return PERF_REG_ARM64_LR;
+	case UNW_AARCH64_SP:
+		return PERF_REG_ARM64_SP;
+	case UNW_AARCH64_PC:
+		return PERF_REG_ARM64_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}