Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

54 files changed, 4377 insertions, 0 deletions

diff --git a/tools/perf/tests/shell/buildid.sh b/tools/perf/tests/shell/buildid.sh
new file mode 100755
index 000000000..f05670d1e
--- /dev/null
+++ b/tools/perf/tests/shell/buildid.sh
@@ -0,0 +1,158 @@
+#!/bin/sh
+# build id cache operations
+# SPDX-License-Identifier: GPL-2.0
+
+# skip if there's no readelf
+if ! [ -x "$(command -v readelf)" ]; then
+	echo "failed: no readelf, install binutils"
+	exit 2
+fi
+
+# skip if there's no compiler
+if ! [ -x "$(command -v cc)" ]; then
+	echo "failed: no compiler, install gcc"
+	exit 2
+fi
+
+# check what we need to test windows binaries
+add_pe=1
+run_pe=1
+if ! perf version --build-options | grep -q 'libbfd: .* on '; then
+	echo "WARNING: perf not built with libbfd. PE binaries will not be tested."
+	add_pe=0
+	run_pe=0
+fi
+if ! which wine > /dev/null; then
+	echo "WARNING: wine not found. PE binaries will not be run."
+	run_pe=0
+fi
+
+# set up wine
+if [ ${run_pe} -eq 1 ]; then
+	wineprefix=$(mktemp -d /tmp/perf.wineprefix.XXX)
+	export WINEPREFIX=${wineprefix}
+	# clear display variables to prevent wine from popping up dialogs
+	unset DISPLAY
+	unset WAYLAND_DISPLAY
+fi
+
+ex_md5=$(mktemp /tmp/perf.ex.MD5.XXX)
+ex_sha1=$(mktemp /tmp/perf.ex.SHA1.XXX)
+ex_pe=$(dirname $0)/../pe-file.exe
+
+echo 'int main(void) { return 0; }' | cc -Wl,--build-id=sha1 -o ${ex_sha1} -x c -
+echo 'int main(void) { return 0; }' | cc -Wl,--build-id=md5 -o ${ex_md5} -x c -
+
+echo "test binaries: ${ex_sha1} ${ex_md5} ${ex_pe}"
+
+check()
+{
+	case $1 in
+	*.exe)
+		# We don't have a tool that can pull a nicely formatted build-id out of
+		# a PE file, but we can extract the whole section with objcopy and
+		# format it ourselves. The .buildid section is a Debug Directory
+		# containing a CodeView entry:
+		#     https://docs.microsoft.com/en-us/windows/win32/debug/pe-format#debug-directory-image-only
+		#     https://github.com/dotnet/runtime/blob/da94c022576a5c3bbc0e896f006565905eb137f9/docs/design/specs/PE-COFF.md
+		# The build-id starts at byte 33 and must be rearranged into a GUID.
+		id=`objcopy -O binary --only-section=.buildid $1 /dev/stdout | \
+			cut -c 33-48 | hexdump -ve '/1 "%02x"' | \
+			sed 's@^\(..\)\(..\)\(..\)\(..\)\(..\)\(..\)\(..\)\(..\)\(.*\)0a$@\4\3\2\1\6\5\8\7\9@'`
+		;;
+	*)
+		id=`readelf -n ${1} 2>/dev/null | grep 'Build ID' | awk '{print $3}'`
+		;;
+	esac
+	echo "build id: ${id}"
+
+	link=${build_id_dir}/.build-id/${id:0:2}/${id:2}
+	echo "link: ${link}"
+
+	if [ ! -h $link ]; then
+		echo "failed: link ${link} does not exist"
+		exit 1
+	fi
+
+	file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf
+	echo "file: ${file}"
+
+	if [ ! -x $file ]; then
+		echo "failed: file ${file} does not exist"
+		exit 1
+	fi
+
+	diff ${file} ${1}
+	if [ $? -ne 0 ]; then
+		echo "failed: ${file} do not match"
+		exit 1
+	fi
+
+	${perf} buildid-cache -l | grep ${id}
+	if [ $? -ne 0 ]; then
+		echo "failed: ${id} is not reported by \"perf buildid-cache -l\""
+		exit 1
+	fi
+
+	echo "OK for ${1}"
+}
+
+test_add()
+{
+	build_id_dir=$(mktemp -d /tmp/perf.debug.XXX)
+	perf="perf --buildid-dir ${build_id_dir}"
+
+	${perf} buildid-cache -v -a ${1}
+	if [ $? -ne 0 ]; then
+		echo "failed: add ${1} to build id cache"
+		exit 1
+	fi
+
+	check ${1}
+
+	rm -rf ${build_id_dir}
+}
+
+test_record()
+{
+	data=$(mktemp /tmp/perf.data.XXX)
+	build_id_dir=$(mktemp -d /tmp/perf.debug.XXX)
+	log=$(mktemp /tmp/perf.log.XXX)
+	perf="perf --buildid-dir ${build_id_dir}"
+
+	echo "running: perf record $@"
+	${perf} record --buildid-all -o ${data} $@ &> ${log}
+	if [ $? -ne 0 ]; then
+		echo "failed: record $@"
+		echo "see log: ${log}"
+		exit 1
+	fi
+
+	check ${@: -1}
+
+	rm -f ${log}
+	rm -rf ${build_id_dir}
+	rm -rf ${data}
+}
+
+# add binaries manual via perf buildid-cache -a
+test_add ${ex_sha1}
+test_add ${ex_md5}
+if [ ${add_pe} -eq 1 ]; then
+	test_add ${ex_pe}
+fi
+
+# add binaries via perf record post processing
+test_record ${ex_sha1}
+test_record ${ex_md5}
+if [ ${run_pe} -eq 1 ]; then
+	test_record wine ${ex_pe}
+fi
+
+# cleanup
+rm ${ex_sha1} ${ex_md5}
+if [ ${run_pe} -eq 1 ]; then
+	rm -r ${wineprefix}
+fi
+
+exit ${err}
diff --git a/tools/perf/tests/shell/coresight/Makefile b/tools/perf/tests/shell/coresight/Makefile
new file mode 100644
index 000000000..b070e7797
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/Makefile
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+include ../../../../../tools/scripts/Makefile.include
+include ../../../../../tools/scripts/Makefile.arch
+include ../../../../../tools/scripts/utilities.mak
+
+SUBDIRS = \
+	asm_pure_loop \
+	memcpy_thread \
+	thread_loop \
+	unroll_loop_thread
+
+all: $(SUBDIRS)
+$(SUBDIRS):
+	@$(MAKE) -C $@ >/dev/null
+
+INSTALLDIRS = $(SUBDIRS:%=install-%)
+
+install-tests: $(INSTALLDIRS)
+$(INSTALLDIRS):
+	@$(MAKE) -C $(@:install-%=%) install-tests >/dev/null
+
+CLEANDIRS = $(SUBDIRS:%=clean-%)
+
+clean: $(CLEANDIRS)
+$(CLEANDIRS):
+	$(call QUIET_CLEAN, test-$(@:clean-%=%)) $(Q)$(MAKE) -C $(@:clean-%=%) clean >/dev/null
+
+.PHONY: all clean $(SUBDIRS) $(CLEANDIRS) $(INSTALLDIRS)
diff --git a/tools/perf/tests/shell/coresight/Makefile.miniconfig b/tools/perf/tests/shell/coresight/Makefile.miniconfig
new file mode 100644
index 000000000..5f72a9cb4
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/Makefile.miniconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+ifndef DESTDIR
+prefix ?= $(HOME)
+endif
+
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+INSTALL = install
+INSTDIR_SUB = tests/shell/coresight
+
+include ../../../../../scripts/Makefile.include
+include ../../../../../scripts/Makefile.arch
+include ../../../../../scripts/utilities.mak
diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop.sh b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
new file mode 100755
index 000000000..569e9d461
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
@@ -0,0 +1,18 @@
+#!/bin/sh -e
+# CoreSight / ASM Pure Loop
+
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+TEST="asm_pure_loop"
+. $(dirname $0)/../lib/coresight.sh
+ARGS=""
+DATV="out"
+DATA="$DATD/perf-$TEST-$DATV.data"
+
+perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS
+
+perf_dump_aux_verify "$DATA" 10 10 10
+
+err=$?
+exit $err
diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/.gitignore b/tools/perf/tests/shell/coresight/asm_pure_loop/.gitignore
new file mode 100644
index 000000000..468673ac3
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop/.gitignore
@@ -0,0 +1 @@
+asm_pure_loop
diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/Makefile b/tools/perf/tests/shell/coresight/asm_pure_loop/Makefile
new file mode 100644
index 000000000..206849e92
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop/Makefile
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+include ../Makefile.miniconfig
+
+# Binary to produce
+BIN=asm_pure_loop
+# Any linking/libraries needed for the binary - empty if none needed
+LIB=
+
+all: $(BIN)
+
+$(BIN): $(BIN).S
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Build line - this is raw asm with no libc to have an always exact binary
+	$(Q)$(CC) $(BIN).S -nostdlib -static -o $(BIN) $(LIB)
+endif
+endif
+
+install-tests: all
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Install the test tool in the right place
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)'; \
+		$(INSTALL) $(BIN) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)/$(BIN)'
+endif
+endif
+
+clean:
+	$(Q)$(RM) -f $(BIN)
+
+.PHONY: all clean install-tests
diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S
new file mode 100644
index 000000000..75cf084a9
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Tamas Zsoldos <tamas.zsoldos@arm.com>, 2021 */
+
+.globl _start
+_start:
+	mov	x0, 0x0000ffff
+	mov	x1, xzr
+loop:
+	nop
+	nop
+	cbnz	x1, noskip
+	nop
+	nop
+	adrp	x2, skip
+	add 	x2, x2, :lo12:skip
+	br	x2
+	nop
+	nop
+noskip:
+	nop
+	nop
+skip:
+	sub	x0, x0, 1
+	cbnz	x0, loop
+
+	mov	x0, #0
+	mov	x8, #93 // __NR_exit syscall
+	svc	#0
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/.gitignore b/tools/perf/tests/shell/coresight/memcpy_thread/.gitignore
new file mode 100644
index 000000000..f8217e560
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/.gitignore
@@ -0,0 +1 @@
+memcpy_thread
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/Makefile b/tools/perf/tests/shell/coresight/memcpy_thread/Makefile
new file mode 100644
index 000000000..2db637eb2
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+include ../Makefile.miniconfig
+
+# Binary to produce
+BIN=memcpy_thread
+# Any linking/libraries needed for the binary - empty if none needed
+LIB=-pthread
+
+all: $(BIN)
+
+$(BIN): $(BIN).c
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Build line
+	$(Q)$(CC) $(BIN).c -o $(BIN) $(LIB)
+endif
+endif
+
+install-tests: all
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Install the test tool in the right place
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)'; \
+		$(INSTALL) $(BIN) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)/$(BIN)'
+endif
+endif
+
+clean:
+	$(Q)$(RM) -f $(BIN)
+
+.PHONY: all clean install-tests
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
new file mode 100644
index 000000000..a7e169d1b
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+// Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <pthread.h>
+
+struct args {
+	unsigned long loops;
+	unsigned long size;
+	pthread_t th;
+	void *ret;
+};
+
+static void *thrfn(void *arg)
+{
+	struct args *a = arg;
+	unsigned long i, len = a->loops;
+	unsigned char *src, *dst;
+
+	src = malloc(a->size * 1024);
+	dst = malloc(a->size * 1024);
+	if ((!src) || (!dst)) {
+		printf("ERR: Can't allocate memory\n");
+		exit(1);
+	}
+	for (i = 0; i < len; i++)
+		memcpy(dst, src, a->size * 1024);
+}
+
+static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
+{
+	pthread_t t;
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	pthread_create(&t, &attr, fn, arg);
+	return t;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long i, len, size, thr;
+	pthread_t threads[256];
+	struct args args[256];
+	long long v;
+
+	if (argc < 4) {
+		printf("ERR: %s [copysize Kb] [numthreads] [numloops (hundreds)]\n", argv[0]);
+		exit(1);
+	}
+
+	v = atoll(argv[1]);
+	if ((v < 1) || (v > (1024 * 1024))) {
+		printf("ERR: max memory 1GB (1048576 KB)\n");
+		exit(1);
+	}
+	size = v;
+	thr = atol(argv[2]);
+	if ((thr < 1) || (thr > 256)) {
+		printf("ERR: threads 1-256\n");
+		exit(1);
+	}
+	v = atoll(argv[3]);
+	if ((v < 1) || (v > 40000000000ll)) {
+		printf("ERR: loops 1-40000000000 (hundreds)\n");
+		exit(1);
+	}
+	len = v * 100;
+	for (i = 0; i < thr; i++) {
+		args[i].loops = len;
+		args[i].size = size;
+		args[i].th = new_thr(thrfn, &(args[i]));
+	}
+	for (i = 0; i < thr; i++)
+		pthread_join(args[i].th, &(args[i].ret));
+	return 0;
+}
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
new file mode 100755
index 000000000..d21ba8545
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
@@ -0,0 +1,18 @@
+#!/bin/sh -e
+# CoreSight / Memcpy 16k 10 Threads
+
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+TEST="memcpy_thread"
+. $(dirname $0)/../lib/coresight.sh
+ARGS="16 10 1"
+DATV="16k_10"
+DATA="$DATD/perf-$TEST-$DATV.data"
+
+perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS
+
+perf_dump_aux_verify "$DATA" 10 10 10
+
+err=$?
+exit $err
diff --git a/tools/perf/tests/shell/coresight/thread_loop/.gitignore b/tools/perf/tests/shell/coresight/thread_loop/.gitignore
new file mode 100644
index 000000000..6d4c33eaa
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/thread_loop/.gitignore
@@ -0,0 +1 @@
+thread_loop
diff --git a/tools/perf/tests/shell/coresight/thread_loop/Makefile b/tools/perf/tests/shell/coresight/thread_loop/Makefile
new file mode 100644
index 000000000..ea846c038
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/thread_loop/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+include ../Makefile.miniconfig
+
+# Binary to produce
+BIN=thread_loop
+# Any linking/libraries needed for the binary - empty if none needed
+LIB=-pthread
+
+all: $(BIN)
+
+$(BIN): $(BIN).c
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Build line
+	$(Q)$(CC) $(BIN).c -o $(BIN) $(LIB)
+endif
+endif
+
+install-tests: all
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Install the test tool in the right place
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)'; \
+		$(INSTALL) $(BIN) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)/$(BIN)'
+endif
+endif
+
+clean:
+	$(Q)$(RM) -f $(BIN)
+
+.PHONY: all clean install-tests
diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
new file mode 100644
index 000000000..c0158fac7
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+// Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+// define this for gettid()
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <pthread.h>
+#include <sys/syscall.h>
+#ifndef SYS_gettid
+// gettid is 178 on arm64
+# define SYS_gettid 178
+#endif
+#define gettid() syscall(SYS_gettid)
+
+struct args {
+	unsigned int loops;
+	pthread_t th;
+	void *ret;
+};
+
+static void *thrfn(void *arg)
+{
+	struct args *a = arg;
+	int i = 0, len = a->loops;
+
+	if (getenv("SHOW_TID")) {
+		unsigned long long tid = gettid();
+
+		printf("%llu\n", tid);
+	}
+	asm volatile(
+		"loop:\n"
+		"add %[i], %[i], #1\n"
+		"cmp %[i], %[len]\n"
+		"blt loop\n"
+		: /* out */
+		: /* in */ [i] "r" (i), [len] "r" (len)
+		: /* clobber */
+	);
+	return (void *)(long)i;
+}
+
+static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
+{
+	pthread_t t;
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	pthread_create(&t, &attr, fn, arg);
+	return t;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int i, len, thr;
+	pthread_t threads[256];
+	struct args args[256];
+
+	if (argc < 3) {
+		printf("ERR: %s [numthreads] [numloops (millions)]\n", argv[0]);
+		exit(1);
+	}
+
+	thr = atoi(argv[1]);
+	if ((thr < 1) || (thr > 256)) {
+		printf("ERR: threads 1-256\n");
+		exit(1);
+	}
+	len = atoi(argv[2]);
+	if ((len < 1) || (len > 4000)) {
+		printf("ERR: max loops 4000 (millions)\n");
+		exit(1);
+	}
+	len *= 1000000;
+	for (i = 0; i < thr; i++) {
+		args[i].loops = len;
+		args[i].th = new_thr(thrfn, &(args[i]));
+	}
+	for (i = 0; i < thr; i++)
+		pthread_join(args[i].th, &(args[i].ret));
+	return 0;
+}
diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
new file mode 100755
index 000000000..7c13636fc
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
@@ -0,0 +1,19 @@
+#!/bin/sh -e
+# CoreSight / Thread Loop 10 Threads - Check TID
+
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+TEST="thread_loop"
+. $(dirname $0)/../lib/coresight.sh
+ARGS="10 1"
+DATV="check-tid-10th"
+DATA="$DATD/perf-$TEST-$DATV.data"
+STDO="$DATD/perf-$TEST-$DATV.stdout"
+
+SHOW_TID=1 perf record -s $PERFRECOPT -o "$DATA" "$BIN" $ARGS > $STDO
+
+perf_dump_aux_tid_verify "$DATA" "$STDO"
+
+err=$?
+exit $err
diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
new file mode 100755
index 000000000..a067145af
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
@@ -0,0 +1,19 @@
+#!/bin/sh -e
+# CoreSight / Thread Loop 2 Threads - Check TID
+
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+TEST="thread_loop"
+. $(dirname $0)/../lib/coresight.sh
+ARGS="2 20"
+DATV="check-tid-2th"
+DATA="$DATD/perf-$TEST-$DATV.data"
+STDO="$DATD/perf-$TEST-$DATV.stdout"
+
+SHOW_TID=1 perf record -s $PERFRECOPT -o "$DATA" "$BIN" $ARGS > $STDO
+
+perf_dump_aux_tid_verify "$DATA" "$STDO"
+
+err=$?
+exit $err
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/.gitignore b/tools/perf/tests/shell/coresight/unroll_loop_thread/.gitignore
new file mode 100644
index 000000000..2cb4e996d
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/.gitignore
@@ -0,0 +1 @@
+unroll_loop_thread
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/Makefile b/tools/perf/tests/shell/coresight/unroll_loop_thread/Makefile
new file mode 100644
index 000000000..6264c4e3a
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+include ../Makefile.miniconfig
+
+# Binary to produce
+BIN=unroll_loop_thread
+# Any linking/libraries needed for the binary - empty if none needed
+LIB=-pthread
+
+all: $(BIN)
+
+$(BIN): $(BIN).c
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Build line
+	$(Q)$(CC) $(BIN).c -o $(BIN) $(LIB)
+endif
+endif
+
+install-tests: all
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Install the test tool in the right place
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)'; \
+		$(INSTALL) $(BIN) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)/$(BIN)'
+endif
+endif
+
+clean:
+	$(Q)$(RM) -f $(BIN)
+
+.PHONY: all clean install-tests
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
new file mode 100644
index 000000000..8f6d38420
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+// Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <pthread.h>
+
+struct args {
+	pthread_t th;
+	unsigned int in;
+	void *ret;
+};
+
+static void *thrfn(void *arg)
+{
+	struct args *a = arg;
+	unsigned int i, in = a->in;
+
+	for (i = 0; i < 10000; i++) {
+		asm volatile (
+// force an unroll of thia add instruction so we can test long runs of code
+#define SNIP1 "add %[in], %[in], #1\n"
+// 10
+#define SNIP2 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1
+// 100
+#define SNIP3 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2
+// 1000
+#define SNIP4 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3
+// 10000
+#define SNIP5 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4
+// 100000
+			SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5
+			: /* out */
+			: /* in */ [in] "r" (in)
+			: /* clobber */
+		);
+	}
+}
+
+static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
+{
+	pthread_t t;
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	pthread_create(&t, &attr, fn, arg);
+	return t;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int i, thr;
+	pthread_t threads[256];
+	struct args args[256];
+
+	if (argc < 2) {
+		printf("ERR: %s [numthreads]\n", argv[0]);
+		exit(1);
+	}
+
+	thr = atoi(argv[1]);
+	if ((thr > 256) || (thr < 1)) {
+		printf("ERR: threads 1-256\n");
+		exit(1);
+	}
+	for (i = 0; i < thr; i++) {
+		args[i].in = rand();
+		args[i].th = new_thr(thrfn, &(args[i]));
+	}
+	for (i = 0; i < thr; i++)
+		pthread_join(args[i].th, &(args[i].ret));
+	return 0;
+}
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
new file mode 100755
index 000000000..f48c85230
--- /dev/null
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
@@ -0,0 +1,18 @@
+#!/bin/sh -e
+# CoreSight / Unroll Loop Thread 10
+
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+TEST="unroll_loop_thread"
+. $(dirname $0)/../lib/coresight.sh
+ARGS="10"
+DATV="10"
+DATA="$DATD/perf-$TEST-$DATV.data"
+
+perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS
+
+perf_dump_aux_verify "$DATA" 10 10 10
+
+err=$?
+exit $err
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
new file mode 100755
index 000000000..45fc24af5
--- /dev/null
+++ b/tools/perf/tests/shell/daemon.sh
@@ -0,0 +1,487 @@
+#!/bin/bash
+# daemon operations
+# SPDX-License-Identifier: GPL-2.0
+
+check_line_first()
+{
+	local line=$1
+	local name=$2
+	local base=$3
+	local output=$4
+	local lock=$5
+	local up=$6
+
+	local line_name=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $2 }'`
+	local line_base=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $3 }'`
+	local line_output=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $4 }'`
+	local line_lock=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $5 }'`
+	local line_up=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $6 }'`
+
+	if [ "${name}" != "${line_name}" ]; then
+		echo "FAILED: wrong name"
+		error=1
+	fi
+
+	if [ "${base}" != "${line_base}" ]; then
+		echo "FAILED: wrong base"
+		error=1
+	fi
+
+	if [ "${output}" != "${line_output}" ]; then
+		echo "FAILED: wrong output"
+		error=1
+	fi
+
+	if [ "${lock}" != "${line_lock}" ]; then
+		echo "FAILED: wrong lock"
+		error=1
+	fi
+
+	if [ "${up}" != "${line_up}" ]; then
+		echo "FAILED: wrong up"
+		error=1
+	fi
+}
+
+check_line_other()
+{
+	local line=$1
+	local name=$2
+	local run=$3
+	local base=$4
+	local output=$5
+	local control=$6
+	local ack=$7
+	local up=$8
+
+	local line_name=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $2 }'`
+	local line_run=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $3 }'`
+	local line_base=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $4 }'`
+	local line_output=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $5 }'`
+	local line_control=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $6 }'`
+	local line_ack=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $7 }'`
+	local line_up=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $8 }'`
+
+	if [ "${name}" != "${line_name}" ]; then
+		echo "FAILED: wrong name"
+		error=1
+	fi
+
+	if [ "${run}" != "${line_run}" ]; then
+		echo "FAILED: wrong run"
+		error=1
+	fi
+
+	if [ "${base}" != "${line_base}" ]; then
+		echo "FAILED: wrong base"
+		error=1
+	fi
+
+	if [ "${output}" != "${line_output}" ]; then
+		echo "FAILED: wrong output"
+		error=1
+	fi
+
+	if [ "${control}" != "${line_control}" ]; then
+		echo "FAILED: wrong control"
+		error=1
+	fi
+
+	if [ "${ack}" != "${line_ack}" ]; then
+		echo "FAILED: wrong ack"
+		error=1
+	fi
+
+	if [ "${up}" != "${line_up}" ]; then
+		echo "FAILED: wrong up"
+		error=1
+	fi
+}
+
+daemon_exit()
+{
+	local config=$1
+
+	local line=`perf daemon --config ${config} -x: | head -1`
+	local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'`
+
+	# Reset trap handler.
+	trap - SIGINT SIGTERM
+
+	# stop daemon
+	perf daemon stop --config ${config}
+
+	# ... and wait for the pid to go away
+	tail --pid=${pid} -f /dev/null
+}
+
+daemon_start()
+{
+	local config=$1
+	local session=$2
+
+	perf daemon start --config ${config}
+
+	# Clean up daemon if interrupted.
+	trap "echo 'FAILED: Signal caught'; daemon_exit ${config}; exit 1" SIGINT SIGTERM
+
+	# wait for the session to ping
+	local state="FAIL"
+	local retries=0
+	while [ "${state}" != "OK" ]; do
+		state=`perf daemon ping --config ${config} --session ${session} | awk '{ print $1 }'`
+		sleep 0.05
+		retries=$((${retries} +1))
+		if [ ${retries} -ge 600 ]; then
+			echo "FAILED: Timeout waiting for daemon to ping"
+			daemon_exit ${config}
+			exit 1
+		fi
+	done
+}
+
+test_list()
+{
+	echo "test daemon list"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+
+[session-time]
+run = -e task-clock -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} size
+
+	# check first line
+	# pid:daemon:base:base/output:base/lock
+	local line=`perf daemon --config ${config} -x: | head -1`
+	check_line_first ${line} daemon ${base} ${base}/output ${base}/lock "0"
+
+	# check 1st session
+	# pid:size:-e cpu-clock:base/size:base/size/output:base/size/control:base/size/ack:0
+	local line=`perf daemon --config ${config} -x: | head -2 | tail -1`
+	check_line_other "${line}" size "-e cpu-clock -m 1 sleep 10" ${base}/session-size \
+			 ${base}/session-size/output ${base}/session-size/control \
+			 ${base}/session-size/ack "0"
+
+	# check 2nd session
+	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
+	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
+			 ${base}/session-time/output ${base}/session-time/control \
+			 ${base}/session-time/ack "0"
+
+	# stop daemon
+	daemon_exit ${config}
+
+	rm -rf ${base}
+	rm -f ${config}
+}
+
+test_reconfig()
+{
+	echo "test daemon reconfig"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	# prepare config
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+
+[session-time]
+run = -e task-clock -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} size
+
+	# check 2nd session
+	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
+	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
+			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
+	local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'`
+
+	# prepare new config
+	local config_new=${config}.new
+	cat <<EOF > ${config_new}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+
+[session-time]
+run = -e cpu-clock -m 1 sleep 10
+EOF
+
+	# TEST 1 - change config
+
+	sed -i -e "s|BASE|${base}|" ${config_new}
+	cp ${config_new} ${config}
+
+	# wait for old session to finish
+	tail --pid=${pid} -f /dev/null
+
+	# wait for new one to start
+	local state="FAIL"
+	while [ "${state}" != "OK" ]; do
+		state=`perf daemon ping --config ${config} --session time | awk '{ print $1 }'`
+	done
+
+	# check reconfigured 2nd session
+	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
+	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
+	check_line_other "${line}" time "-e cpu-clock -m 1 sleep 10" ${base}/session-time \
+			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
+
+	# TEST 2 - empty config
+
+	local config_empty=${config}.empty
+	cat <<EOF > ${config_empty}
+[daemon]
+base=BASE
+EOF
+
+	# change config
+	sed -i -e "s|BASE|${base}|" ${config_empty}
+	cp ${config_empty} ${config}
+
+	# wait for sessions to finish
+	local state="OK"
+	while [ "${state}" != "FAIL" ]; do
+		state=`perf daemon ping --config ${config} --session time | awk '{ print $1 }'`
+	done
+
+	local state="OK"
+	while [ "${state}" != "FAIL" ]; do
+		state=`perf daemon ping --config ${config} --session size | awk '{ print $1 }'`
+	done
+
+	local one=`perf daemon --config ${config} -x: | wc -l`
+
+	if [ ${one} -ne "1" ]; then
+		echo "FAILED: wrong list output"
+		error=1
+	fi
+
+	# TEST 3 - config again
+
+	cp ${config_new} ${config}
+
+	# wait for size to start
+	local state="FAIL"
+	while [ "${state}" != "OK" ]; do
+		state=`perf daemon ping --config ${config} --session size | awk '{ print $1 }'`
+	done
+
+	# wait for time to start
+	local state="FAIL"
+	while [ "${state}" != "OK" ]; do
+		state=`perf daemon ping --config ${config} --session time | awk '{ print $1 }'`
+	done
+
+	# stop daemon
+	daemon_exit ${config}
+
+	rm -rf ${base}
+	rm -f ${config}
+	rm -f ${config_new}
+	rm -f ${config_empty}
+}
+
+test_stop()
+{
+	echo "test daemon stop"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	# prepare config
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+
+[session-time]
+run = -e task-clock -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} size
+
+	local pid_size=`perf daemon --config ${config} -x: | head -2 | tail -1 | awk 'BEGIN { FS = ":" } ; { print $1 }'`
+	local pid_time=`perf daemon --config ${config} -x: | head -3 | tail -1 | awk 'BEGIN { FS = ":" } ; { print $1 }'`
+
+	# check that sessions are running
+	if [ ! -d "/proc/${pid_size}" ]; then
+		echo "FAILED: session size not up"
+	fi
+
+	if [ ! -d "/proc/${pid_time}" ]; then
+		echo "FAILED: session time not up"
+	fi
+
+	# stop daemon
+	daemon_exit ${config}
+
+	# check that sessions are gone
+	if [ -d "/proc/${pid_size}" ]; then
+		echo "FAILED: session size still up"
+	fi
+
+	if [ -d "/proc/${pid_time}" ]; then
+		echo "FAILED: session time still up"
+	fi
+
+	rm -rf ${base}
+	rm -f ${config}
+}
+
+test_signal()
+{
+	echo "test daemon signal"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	# prepare config
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-test]
+run = -e cpu-clock --switch-output -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} test
+
+	# send 2 signals
+	perf daemon signal --config ${config} --session test
+	perf daemon signal --config ${config}
+
+	# stop daemon
+	daemon_exit ${config}
+
+	# count is 2 perf.data for signals and 1 for perf record finished
+	count=`ls ${base}/session-test/ | grep perf.data | wc -l`
+	if [ ${count} -ne 3 ]; then
+		error=1
+		echo "FAILED: perf data no generated"
+	fi
+
+	rm -rf ${base}
+	rm -f ${config}
+}
+
+test_ping()
+{
+	echo "test daemon ping"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	# prepare config
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+
+[session-time]
+run = -e task-clock -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} size
+
+	size=`perf daemon ping --config ${config} --session size | awk '{ print $1 }'`
+	type=`perf daemon ping --config ${config} --session time | awk '{ print $1 }'`
+
+	if [ ${size} != "OK" -o ${type} != "OK" ]; then
+		error=1
+		echo "FAILED: daemon ping failed"
+	fi
+
+	# stop daemon
+	daemon_exit ${config}
+
+	rm -rf ${base}
+	rm -f ${config}
+}
+
+test_lock()
+{
+	echo "test daemon lock"
+
+	local config=$(mktemp /tmp/perf.daemon.config.XXX)
+	local base=$(mktemp -d /tmp/perf.daemon.base.XXX)
+
+	# prepare config
+	cat <<EOF > ${config}
+[daemon]
+base=BASE
+
+[session-size]
+run = -e cpu-clock -m 1 sleep 10
+EOF
+
+	sed -i -e "s|BASE|${base}|" ${config}
+
+	# start daemon
+	daemon_start ${config} size
+
+	# start second daemon over the same config/base
+	failed=`perf daemon start --config ${config} 2>&1 | awk '{ print $1 }'`
+
+	# check that we failed properly
+	if [ ${failed} != "failed:" ]; then
+		error=1
+		echo "FAILED: daemon lock failed"
+	fi
+
+	# stop daemon
+	daemon_exit ${config}
+
+	rm -rf ${base}
+	rm -f ${config}
+}
+
+error=0
+
+test_list
+test_reconfig
+test_stop
+test_signal
+test_ping
+test_lock
+
+exit ${error}
diff --git a/tools/perf/tests/shell/lib/coresight.sh b/tools/perf/tests/shell/lib/coresight.sh
new file mode 100644
index 000000000..45a147725
--- /dev/null
+++ b/tools/perf/tests/shell/lib/coresight.sh
@@ -0,0 +1,132 @@
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <carsten.haitzler@arm.com>, 2021
+
+# This is sourced from a driver script so no need for #!/bin... etc. at the
+# top - the assumption below is that it runs as part of sourcing after the
+# test sets up some basic env vars to say what it is.
+
+# This currently works with ETMv4 / ETF not any other packet types at thi
+# point. This will need changes if that changes.
+
+# perf record options for the perf tests to use
+PERFRECMEM="-m ,16M"
+PERFRECOPT="$PERFRECMEM -e cs_etm//u"
+
+TOOLS=$(dirname $0)
+DIR="$TOOLS/$TEST"
+BIN="$DIR/$TEST"
+# If the test tool/binary does not exist and is executable then skip the test
+if ! test -x "$BIN"; then exit 2; fi
+DATD="."
+# If the data dir env is set then make the data dir use that instead of ./
+if test -n "$PERF_TEST_CORESIGHT_DATADIR"; then
+	DATD="$PERF_TEST_CORESIGHT_DATADIR";
+fi
+# If the stat dir env is set then make the data dir use that instead of ./
+STATD="."
+if test -n "$PERF_TEST_CORESIGHT_STATDIR"; then
+	STATD="$PERF_TEST_CORESIGHT_STATDIR";
+fi
+
+# Called if the test fails - error code 1
+err() {
+	echo "$1"
+	exit 1
+}
+
+# Check that some statistics from our perf
+check_val_min() {
+	STATF="$4"
+	if test "$2" -lt "$3"; then
+		echo ", FAILED" >> "$STATF"
+		err "Sanity check number of $1 is too low ($2 < $3)"
+	fi
+}
+
+perf_dump_aux_verify() {
+	# Some basic checking that the AUX chunk contains some sensible data
+	# to see that we are recording something and at least a minimum
+	# amount of it. We should almost always see Fn packets in just about
+	# anything but certainly we will see some trace info and async
+	# packets
+	DUMP="$DATD/perf-tmp-aux-dump.txt"
+	perf report --stdio --dump -i "$1" | \
+		grep -o -e I_ATOM_F -e I_ASYNC -e I_TRACE_INFO > "$DUMP"
+	# Simply count how many of these packets we find to see that we are
+	# producing a reasonable amount of data - exact checks are not sane
+	# as this is a lossy process where we may lose some blocks and the
+	# compiler may produce different code depending on the compiler and
+	# optimization options, so this is rough just to see if we're
+	# either missing almost all the data or all of it
+	ATOM_FX_NUM=`grep I_ATOM_F "$DUMP" | wc -l`
+	ASYNC_NUM=`grep I_ASYNC "$DUMP" | wc -l`
+	TRACE_INFO_NUM=`grep I_TRACE_INFO "$DUMP" | wc -l`
+	rm -f "$DUMP"
+
+	# Arguments provide minimums for a pass
+	CHECK_FX_MIN="$2"
+	CHECK_ASYNC_MIN="$3"
+	CHECK_TRACE_INFO_MIN="$4"
+
+	# Write out statistics, so over time you can track results to see if
+	# there is a pattern - for example we have less "noisy" results that
+	# produce more consistent amounts of data each run, to see if over
+	# time any techinques to  minimize data loss are having an effect or
+	# not
+	STATF="$STATD/stats-$TEST-$DATV.csv"
+	if ! test -f "$STATF"; then
+		echo "ATOM Fx Count, Minimum, ASYNC Count, Minimum, TRACE INFO Count, Minimum" > "$STATF"
+	fi
+	echo -n "$ATOM_FX_NUM, $CHECK_FX_MIN, $ASYNC_NUM, $CHECK_ASYNC_MIN, $TRACE_INFO_NUM, $CHECK_TRACE_INFO_MIN" >> "$STATF"
+
+	# Actually check to see if we passed or failed.
+	check_val_min "ATOM_FX" "$ATOM_FX_NUM" "$CHECK_FX_MIN" "$STATF"
+	check_val_min "ASYNC" "$ASYNC_NUM" "$CHECK_ASYNC_MIN" "$STATF"
+	check_val_min "TRACE_INFO" "$TRACE_INFO_NUM" "$CHECK_TRACE_INFO_MIN" "$STATF"
+	echo ", Ok" >> "$STATF"
+}
+
+perf_dump_aux_tid_verify() {
+	# Specifically crafted test will produce a list of Tread ID's to
+	# stdout that need to be checked to  see that they have had trace
+	# info collected in AUX blocks in the perf data. This will go
+	# through all the TID's that are listed as CID=0xabcdef and see
+	# that all the Thread IDs the test tool reports are  in the perf
+	# data AUX chunks
+
+	# The TID test tools will print a TID per stdout line that are being
+	# tested
+	TIDS=`cat "$2"`
+	# Scan the perf report to find the TIDs that are actually CID in hex
+	# and build a list of the ones found
+	FOUND_TIDS=`perf report --stdio --dump -i "$1" | \
+			grep -o "CID=0x[0-9a-z]\+" | sed 's/CID=//g' | \
+			uniq | sort | uniq`
+	# No CID=xxx found - maybe your kernel is reporting these as
+	# VMID=xxx so look there
+	if test -z "$FOUND_TIDS"; then
+		FOUND_TIDS=`perf report --stdio --dump -i "$1" | \
+				grep -o "VMID=0x[0-9a-z]\+" | sed 's/VMID=//g' | \
+				uniq | sort | uniq`
+	fi
+
+	# Iterate over the list of TIDs that the test says it has and find
+	# them in the TIDs found in the perf report
+	MISSING=""
+	for TID2 in $TIDS; do
+		FOUND=""
+		for TIDHEX in $FOUND_TIDS; do
+			TID=`printf "%i" $TIDHEX`
+			if test "$TID" -eq "$TID2"; then
+				FOUND="y"
+				break
+			fi
+		done
+		if test -z "$FOUND"; then
+			MISSING="$MISSING $TID"
+		fi
+	done
+	if test -n "$MISSING"; then
+		err "Thread IDs $MISSING not found in perf AUX data"
+	fi
+}
diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
new file mode 100644
index 000000000..d90f8d102
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py
@@ -0,0 +1,96 @@
+#!/usr/bin/python
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Basic sanity check of perf JSON output as specified in the man page.
+
+import argparse
+import sys
+import json
+
+ap = argparse.ArgumentParser()
+ap.add_argument('--no-args', action='store_true')
+ap.add_argument('--interval', action='store_true')
+ap.add_argument('--system-wide-no-aggr', action='store_true')
+ap.add_argument('--system-wide', action='store_true')
+ap.add_argument('--event', action='store_true')
+ap.add_argument('--per-core', action='store_true')
+ap.add_argument('--per-thread', action='store_true')
+ap.add_argument('--per-die', action='store_true')
+ap.add_argument('--per-node', action='store_true')
+ap.add_argument('--per-socket', action='store_true')
+args = ap.parse_args()
+
+Lines = sys.stdin.readlines()
+
+def isfloat(num):
+  try:
+    float(num)
+    return True
+  except ValueError:
+    return False
+
+
+def isint(num):
+  try:
+    int(num)
+    return True
+  except ValueError:
+    return False
+
+def is_counter_value(num):
+  return isfloat(num) or num == '<not counted>' or num == '<not supported>'
+
+def check_json_output(expected_items):
+  if expected_items != -1:
+    for line in Lines:
+      if 'failed' not in line:
+        count = 0
+        count = line.count(',')
+        if count != expected_items and count >= 1 and count <= 3 and 'metric-value' in line:
+          # Events that generate >1 metric may have isolated metric
+          # values and possibly other prefixes like interval, core and
+          # aggregate-number.
+          continue
+        if count != expected_items:
+          raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}'
+                             f' in \'{line}\'')
+  checks = {
+      'aggregate-number': lambda x: isfloat(x),
+      'core': lambda x: True,
+      'counter-value': lambda x: is_counter_value(x),
+      'cgroup': lambda x: True,
+      'cpu': lambda x: isint(x),
+      'die': lambda x: True,
+      'event': lambda x: True,
+      'event-runtime': lambda x: isfloat(x),
+      'interval': lambda x: isfloat(x),
+      'metric-unit': lambda x: True,
+      'metric-value': lambda x: isfloat(x),
+      'node': lambda x: True,
+      'pcnt-running': lambda x: isfloat(x),
+      'socket': lambda x: True,
+      'thread': lambda x: True,
+      'unit': lambda x: True,
+  }
+  input = '[\n' + ','.join(Lines) + '\n]'
+  for item in json.loads(input):
+    for key, value in item.items():
+      if key not in checks:
+        raise RuntimeError(f'Unexpected key: key={key} value={value}')
+      if not checks[key](value):
+        raise RuntimeError(f'Check failed for: key={key} value={value}')
+
+
+try:
+  if args.no_args or args.system_wide or args.event:
+    expected_items = 6
+  elif args.interval or args.per_thread or args.system_wide_no_aggr:
+    expected_items = 7
+  elif args.per_core or args.per_socket or args.per_node or args.per_die:
+    expected_items = 8
+  else:
+    # If no option is specified, don't check the number of items.
+    expected_items = -1
+  check_json_output(expected_items)
+except:
+  print('Test failed for input:\n' + '\n'.join(Lines))
+  raise
diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh
new file mode 100644
index 000000000..51e3f60ba
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe.sh
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+skip_if_no_perf_probe() {
+	perf probe 2>&1 | grep -q 'is not a perf-command' && return 2
+	return 0
+}
+
+skip_if_no_perf_trace() {
+	perf trace -h 2>&1 | grep -q -e 'is not a perf-command' -e 'trace command not available' && return 2
+	return 0
+}
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
new file mode 100644
index 000000000..b616d42bd
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -0,0 +1,24 @@
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+perf probe -l 2>&1 | grep -q probe:vfs_getname
+had_vfs_getname=$?
+
+cleanup_probe_vfs_getname() {
+	if [ $had_vfs_getname -eq 1 ] ; then
+		perf probe -q -d probe:vfs_getname*
+	fi
+}
+
+add_probe_vfs_getname() {
+	local verbose=$1
+	if [ $had_vfs_getname -eq 1 ] ; then
+		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
+		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
+	fi
+}
+
+skip_if_no_debuginfo() {
+	add_probe_vfs_getname -v 2>&1 | egrep -q "^(Failed to find the path for the kernel|Debuginfo-analysis is not supported)|(file has no debug information)" && return 2
+	return 1
+}
diff --git a/tools/perf/tests/shell/lib/waiting.sh b/tools/perf/tests/shell/lib/waiting.sh
new file mode 100644
index 000000000..e7a39134a
--- /dev/null
+++ b/tools/perf/tests/shell/lib/waiting.sh
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: GPL-2.0
+
+tenths=date\ +%s%1N
+
+# Wait for PID $1 to have $2 number of threads started
+# Time out after $3 tenths of a second or 5 seconds if $3 is ""
+wait_for_threads()
+{
+	tm_out=$3 ; [ -n "${tm_out}" ] || tm_out=50
+	start_time=$($tenths)
+	while [ -e "/proc/$1/task" ] ; do
+		th_cnt=$(find "/proc/$1/task" -mindepth 1 -maxdepth 1 -printf x | wc -c)
+		if [ "${th_cnt}" -ge "$2" ] ; then
+			return 0
+		fi
+		# Wait at most tm_out tenths of a second
+		if [ $(($($tenths) - start_time)) -ge $tm_out ] ; then
+			echo "PID $1 does not have $2 threads"
+			return 1
+		fi
+	done
+	return 1
+}
+
+# Wait for perf record -vvv 2>$2 with PID $1 to start by looking at file $2
+# It depends on capturing perf record debug message "perf record has started"
+# Time out after $3 tenths of a second or 5 seconds if $3 is ""
+wait_for_perf_to_start()
+{
+	tm_out=$3 ; [ -n "${tm_out}" ] || tm_out=50
+	echo "Waiting for \"perf record has started\" message"
+	start_time=$($tenths)
+	while [ -e "/proc/$1" ] ; do
+		if grep -q "perf record has started" "$2" ; then
+			echo OK
+			break
+		fi
+		# Wait at most tm_out tenths of a second
+		if [ $(($($tenths) - start_time)) -ge $tm_out ] ; then
+			echo "perf recording did not start"
+			return 1
+		fi
+	done
+	return 0
+}
+
+# Wait for process PID %1 to exit
+# Time out after $2 tenths of a second or 5 seconds if $2 is ""
+wait_for_process_to_exit()
+{
+	tm_out=$2 ; [ -n "${tm_out}" ] || tm_out=50
+	start_time=$($tenths)
+	while [ -e "/proc/$1" ] ; do
+		# Wait at most tm_out tenths of a second
+		if [ $(($($tenths) - start_time)) -ge $tm_out ] ; then
+			echo "PID $1 did not exit as expected"
+			return 1
+		fi
+	done
+	return 0
+}
+
+# Check if PID $1 is still running after $2 tenths of a second
+# or 0.3 seconds if $2 is ""
+is_running()
+{
+	tm_out=$2 ; [ -n "${tm_out}" ] || tm_out=3
+	start_time=$($tenths)
+	while [ -e "/proc/$1" ] ; do
+		# Check for at least tm_out tenths of a second
+		if [ $(($($tenths) - start_time)) -gt $tm_out ] ; then
+			return 0
+		fi
+	done
+	echo "PID $1 exited prematurely"
+	return 1
+}
diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh
new file mode 100755
index 000000000..04bf604e3
--- /dev/null
+++ b/tools/perf/tests/shell/lock_contention.sh
@@ -0,0 +1,73 @@
+#!/bin/sh
+# kernel lock contention analysis test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+result=$(mktemp /tmp/__perf_test.result.XXXXX)
+
+cleanup() {
+	rm -f ${perfdata}
+	rm -f ${result}
+	trap - exit term int
+}
+
+trap_cleanup() {
+	cleanup
+	exit ${err}
+}
+trap trap_cleanup exit term int
+
+check() {
+	if [ `id -u` != 0 ]; then
+		echo "[Skip] No root permission"
+		err=2
+		exit
+	fi
+
+	if ! perf list | grep -q lock:contention_begin; then
+		echo "[Skip] No lock contention tracepoints"
+		err=2
+		exit
+	fi
+}
+
+test_record()
+{
+	echo "Testing perf lock record and perf lock contention"
+	perf lock record -o ${perfdata} -- perf bench sched messaging > /dev/null 2>&1
+	# the output goes to the stderr and we expect only 1 output (-E 1)
+	perf lock contention -i ${perfdata} -E 1 -q 2> ${result}
+	if [ $(cat "${result}" | wc -l) != "1" ]; then
+		echo "[Fail] Recorded result count is not 1:" $(cat "${result}" | wc -l)
+		err=1
+		exit
+	fi
+}
+
+test_bpf()
+{
+	echo "Testing perf lock contention --use-bpf"
+
+	if ! perf lock con -b true > /dev/null 2>&1 ; then
+		echo "[Skip] No BPF support"
+		exit
+	fi
+
+	# the perf lock contention output goes to the stderr
+	perf lock con -a -b -E 1 -q -- perf bench sched messaging > /dev/null 2> ${result}
+	if [ $(cat "${result}" | wc -l) != "1" ]; then
+		echo "[Fail] BPF result count is not 1:" $(cat "${result}" | wc -l)
+		err=1
+		exit
+	fi
+}
+
+check
+
+test_record
+test_bpf
+
+exit ${err}
diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
new file mode 100755
index 000000000..1b32b4f28
--- /dev/null
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -0,0 +1,69 @@
+#!/bin/sh
+# perf pipe recording and injection test
+# SPDX-License-Identifier: GPL-2.0
+
+# skip if there's no compiler
+if ! [ -x "$(command -v cc)" ]; then
+	echo "failed: no compiler, install gcc"
+	exit 2
+fi
+
+file=$(mktemp /tmp/test.file.XXXXXX)
+data=$(mktemp /tmp/perf.data.XXXXXX)
+
+cat <<EOF | cc -o ${file} -x c -
+#include <signal.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+volatile int done;
+
+void sigalrm(int sig) {
+	done = 1;
+}
+
+__attribute__((noinline)) void noploop(void) {
+	while (!done)
+		continue;
+}
+
+int main(int argc, char *argv[]) {
+	int sec = 1;
+
+	if (argc > 1)
+		sec = atoi(argv[1]);
+
+	signal(SIGALRM, sigalrm);
+	alarm(sec);
+
+	noploop();
+	return 0;
+}
+EOF
+
+
+if ! perf record -e task-clock:u -o - ${file} | perf report -i - --task | grep test.file; then
+	echo "cannot find the test file in the perf report"
+	exit 1
+fi
+
+if ! perf record -e task-clock:u -o - ${file} | perf inject -b | perf report -i - | grep noploop; then
+	echo "cannot find noploop function in pipe #1"
+	exit 1
+fi
+
+perf record -e task-clock:u -o - ${file} | perf inject -b -o ${data}
+if ! perf report -i ${data} | grep noploop; then
+	echo "cannot find noploop function in pipe #2"
+	exit 1
+fi
+
+perf record -e task-clock:u -o ${data} ${file}
+if ! perf inject -b -i ${data} | perf report -i - | grep noploop; then
+	echo "cannot find noploop function in pipe #3"
+	exit 1
+fi
+
+
+rm -f ${file} ${data} ${data}.old
+exit 0
diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
new file mode 100755
index 000000000..5d1b63d3f
--- /dev/null
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# Add vfs_getname probe to get syscall args filenames
+
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
new file mode 100755
index 000000000..f12a4e217
--- /dev/null
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -0,0 +1,96 @@
+#!/bin/sh
+# probe libc's inet_pton & backtrace it with ping
+
+# Installs a probe on libc's inet_pton function, that will use uprobes,
+# then use 'perf trace' on a ping to localhost asking for just one packet
+# with the a backtrace 3 levels deep, check that it is what we expect.
+# This needs no debuginfo package, all is done using the libc ELF symtab
+# and the CFI info in the binaries.
+
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
+
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
+trace_libc_inet_pton_backtrace() {
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+	case "$(uname -m)" in
+	s390x)
+		eventattr='call-graph=dwarf,max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
+	*)
+		eventattr='max-stack=3'
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
+	esac
+
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
+
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
+		echo $line
+		echo "$line" | egrep -q "$pattern"
+		if [ $? -ne 0 ] ; then
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
+			return 1
+		fi
+	done
+
+	# If any statements are executed from this point onwards,
+	# the exit code of the last among these will be reflected
+	# in err below. If the exit code is 0, the test will pass
+	# even if the perf script output does not match.
+}
+
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
+skip_if_no_perf_probe && \
+add_libc_inet_pton_event && \
+trace_libc_inet_pton_backtrace
+err=$?
+rm -f ${perf_data} ${perf_script} ${expected}
+delete_libc_inet_pton_event
+exit $err
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
new file mode 100755
index 000000000..8d9c04e45
--- /dev/null
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -0,0 +1,43 @@
+#!/bin/sh
+# Use vfs_getname probe to get syscall args filenames
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf record' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname probe in the generated
+# perf.data file, with the temp file name as the pathname argument.
+
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+record_open_file() {
+	echo "Recording open file:"
+	perf record -o ${perfdata} -e probe:vfs_getname\* touch $file
+}
+
+perf_script_filenames() {
+	echo "Looking at perf.data file for vfs_getname records for the file we touched:"
+	perf script -i ${perfdata} | \
+	egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname[_0-9]*: +\([[:xdigit:]]+\) +pathname=\"${file}\""
+}
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+	exit $err
+fi
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+record_open_file && perf_script_filenames
+err=$?
+rm -f ${perfdata}
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
new file mode 100755
index 000000000..49bd875d5
--- /dev/null
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -0,0 +1,37 @@
+#!/bin/sh
+# Zstd perf.data compression/decompression
+
+# SPDX-License-Identifier: GPL-2.0
+
+trace_file=$(mktemp /tmp/perf.data.XXX)
+perf_tool=perf
+
+skip_if_no_z_record() {
+	$perf_tool record -h 2>&1 | grep -q '\-z, \-\-compression\-level'
+}
+
+collect_z_record() {
+	echo "Collecting compressed record file:"
+	[ "$(uname -m)" != s390x ] && gflag='-g'
+	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
+		dd count=500 if=/dev/urandom of=/dev/null
+}
+
+check_compressed_stats() {
+	echo "Checking compressed events stats:"
+	$perf_tool report -i $trace_file --header --stats | \
+		grep -E "(# compressed : Zstd,)|(COMPRESSED events:)"
+}
+
+check_compressed_output() {
+	$perf_tool inject -i $trace_file -o $trace_file.decomp &&
+	$perf_tool report -i $trace_file --stdio -F comm,dso,sym | head -n -3 > $trace_file.comp.output &&
+	$perf_tool report -i $trace_file.decomp --stdio -F comm,dso,sym | head -n -3 > $trace_file.decomp.output &&
+	diff $trace_file.comp.output $trace_file.decomp.output
+}
+
+skip_if_no_z_record || exit 2
+collect_z_record && check_compressed_stats && check_compressed_output
+err=$?
+rm -f $trace_file*
+exit $err
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
new file mode 100755
index 000000000..301f95427
--- /dev/null
+++ b/tools/perf/tests/shell/record.sh
@@ -0,0 +1,80 @@
+#!/bin/sh
+# perf record tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+
+cleanup() {
+  rm -f ${perfdata}
+  rm -f ${perfdata}.old
+  trap - exit term int
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup exit term int
+
+test_per_thread() {
+  echo "Basic --per-thread mode test"
+  if ! perf record -e instructions:u -o ${perfdata} --quiet true 2> /dev/null
+  then
+    echo "Per-thread record [Skipped instructions:u not supported]"
+    if [ $err -ne 1 ]
+    then
+      err=2
+    fi
+    return
+  fi
+  if ! perf record -e instructions:u --per-thread -o ${perfdata} true 2> /dev/null
+  then
+    echo "Per-thread record of instructions:u [Failed]"
+    err=1
+    return
+  fi
+  if ! perf report -i ${perfdata} -q | egrep -q true
+  then
+    echo "Per-thread record [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic --per-thread mode test [Success]"
+}
+
+test_register_capture() {
+  echo "Register capture test"
+  if ! perf list | egrep -q 'br_inst_retired.near_call'
+  then
+    echo "Register capture test [Skipped missing instruction]"
+    if [ $err -ne 1 ]
+    then
+      err=2
+    fi
+    return
+  fi
+  if ! perf record --intr-regs=\? 2>&1 | egrep -q 'available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15'
+  then
+    echo "Register capture test [Skipped missing registers]"
+    return
+  fi
+  if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \
+    -c 1000 --per-thread true 2> /dev/null \
+    | perf script -F ip,sym,iregs -i - 2> /dev/null \
+    | egrep -q "DI:"
+  then
+    echo "Register capture test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Register capture test [Success]"
+}
+
+test_per_thread
+test_register_capture
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
new file mode 100755
index 000000000..054272750
--- /dev/null
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -0,0 +1,103 @@
+#!/bin/sh
+# perf record offcpu profiling tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+
+cleanup() {
+  rm -f ${perfdata}
+  rm -f ${perfdata}.old
+  trap - exit term int
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup exit term int
+
+test_offcpu_priv() {
+  echo "Checking off-cpu privilege"
+
+  if [ `id -u` != 0 ]
+  then
+    echo "off-cpu test [Skipped permission]"
+    err=2
+    return
+  fi
+  if perf record --off-cpu -o /dev/null --quiet true 2>&1 | grep BUILD_BPF_SKEL
+  then
+    echo "off-cpu test [Skipped missing BPF support]"
+    err=2
+    return
+  fi
+}
+
+test_offcpu_basic() {
+  echo "Basic off-cpu test"
+
+  if ! perf record --off-cpu -e dummy -o ${perfdata} sleep 1 2> /dev/null
+  then
+    echo "Basic off-cpu test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf evlist -i ${perfdata} | grep -q "offcpu-time"
+  then
+    echo "Basic off-cpu test [Failed no event]"
+    err=1
+    return
+  fi
+  if ! perf report -i ${perfdata} -q --percent-limit=90 | egrep -q sleep
+  then
+    echo "Basic off-cpu test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic off-cpu test [Success]"
+}
+
+test_offcpu_child() {
+  echo "Child task off-cpu test"
+
+  # perf bench sched messaging creates 400 processes
+  if ! perf record --off-cpu -e dummy -o ${perfdata} -- \
+    perf bench sched messaging -g 10 > /dev/null 2>&1
+  then
+    echo "Child task off-cpu test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf evlist -i ${perfdata} | grep -q "offcpu-time"
+  then
+    echo "Child task off-cpu test [Failed no event]"
+    err=1
+    return
+  fi
+  # each process waits for read and write, so it should be more than 800 events
+  if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \
+    awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }'
+  then
+    echo "Child task off-cpu test [Failed invalid output]"
+    err=1
+    return
+  fi
+  echo "Child task off-cpu test [Success]"
+}
+
+
+test_offcpu_priv
+
+if [ $err = 0 ]; then
+  test_offcpu_basic
+fi
+
+if [ $err = 0 ]; then
+  test_offcpu_child
+fi
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
new file mode 100755
index 000000000..b7f050aa6
--- /dev/null
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+# perf stat CSV output linter
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Tests various perf stat CSV output commands for the
+# correct number of fields and the CSV separator set to ','.
+
+set -e
+
+skip_test=0
+
+function commachecker()
+{
+	local -i cnt=0
+	local exp=0
+
+	case "$1"
+	in "--no-args")		exp=6
+	;; "--system-wide")	exp=6
+	;; "--event")		exp=6
+	;; "--interval")	exp=7
+	;; "--per-thread")	exp=7
+	;; "--system-wide-no-aggr")	exp=7
+				[ $(uname -m) = "s390x" ] && exp='^[6-7]$'
+	;; "--per-core")	exp=8
+	;; "--per-socket")	exp=8
+	;; "--per-node")	exp=8
+	;; "--per-die")		exp=8
+	esac
+
+	while read line
+	do
+		# Check for lines beginning with Failed
+		x=${line:0:6}
+		[ "$x" = "Failed" ] && continue
+
+		# Count the number of commas
+		x=$(echo $line | tr -d -c ',')
+		cnt="${#x}"
+		# echo $line $cnt
+		[[ ! "$cnt" =~ $exp ]] && {
+			echo "wrong number of fields. expected $exp in $line" 1>&2
+			exit 1;
+		}
+	done
+	return 0
+}
+
+# Return true if perf_event_paranoid is > $1 and not running as root.
+function ParanoidAndNotRoot()
+{
+	 [ $(id -u) != 0 ] && [ $(cat /proc/sys/kernel/perf_event_paranoid) -gt $1 ]
+}
+
+check_no_args()
+{
+	echo -n "Checking CSV output: no args "
+	perf stat -x, true 2>&1 | commachecker --no-args
+	echo "[Success]"
+}
+
+check_system_wide()
+{
+	echo -n "Checking CSV output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, -a true 2>&1 | commachecker --system-wide
+	echo "[Success]"
+}
+
+check_system_wide_no_aggr()
+{
+	echo -n "Checking CSV output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	echo -n "Checking CSV output: system wide no aggregation "
+	perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr
+	echo "[Success]"
+}
+
+check_interval()
+{
+	echo -n "Checking CSV output: interval "
+	perf stat -x, -I 1000 true 2>&1 | commachecker --interval
+	echo "[Success]"
+}
+
+
+check_event()
+{
+	echo -n "Checking CSV output: event "
+	perf stat -x, -e cpu-clock true 2>&1 | commachecker --event
+	echo "[Success]"
+}
+
+check_per_core()
+{
+	echo -n "Checking CSV output: per core "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-core -a true 2>&1 | commachecker --per-core
+	echo "[Success]"
+}
+
+check_per_thread()
+{
+	echo -n "Checking CSV output: per thread "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread
+	echo "[Success]"
+}
+
+check_per_die()
+{
+	echo -n "Checking CSV output: per die "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-die -a true 2>&1 | commachecker --per-die
+	echo "[Success]"
+}
+
+check_per_node()
+{
+	echo -n "Checking CSV output: per node "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-node -a true 2>&1 | commachecker --per-node
+	echo "[Success]"
+}
+
+check_per_socket()
+{
+	echo -n "Checking CSV output: per socket "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket
+	echo "[Success]"
+}
+
+# The perf stat options for per-socket, per-core, per-die
+# and -A ( no_aggr mode ) uses the info fetched from this
+# directory: "/sys/devices/system/cpu/cpu*/topology". For
+# example, socket value is fetched from "physical_package_id"
+# file in topology directory.
+# Reference: cpu__get_topology_int in util/cpumap.c
+# If the platform doesn't expose topology information, values
+# will be set to -1. For example, incase of pSeries platform
+# of powerpc, value for  "physical_package_id" is restricted
+# and set to -1. Check here validates the socket-id read from
+# topology file before proceeding further
+
+FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
+FILE_NAME="physical_package_id"
+
+check_for_topology()
+{
+	if ! ParanoidAndNotRoot 0
+	then
+		socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
+		[ -z $socket_file ] && return 0
+		socket_id=`cat $socket_file`
+		[ $socket_id == -1 ] && skip_test=1
+		return 0
+	fi
+}
+
+check_for_topology
+check_no_args
+check_system_wide
+check_interval
+check_event
+check_per_thread
+check_per_node
+if [ $skip_test -ne 1 ]
+then
+	check_system_wide_no_aggr
+	check_per_core
+	check_per_die
+	check_per_socket
+else
+	echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
+fi
+exit 0
diff --git a/tools/perf/tests/shell/stat+csv_summary.sh b/tools/perf/tests/shell/stat+csv_summary.sh
new file mode 100755
index 000000000..5571ff75e
--- /dev/null
+++ b/tools/perf/tests/shell/stat+csv_summary.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+# perf stat csv summary test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+#
+#     1.001364330 9224197  cycles 8012885033 100.00
+#         summary 9224197  cycles 8012885033 100.00
+#
+perf stat -e cycles  -x' ' -I1000 --interval-count 1 --summary 2>&1 | \
+grep -e summary | \
+while read summary num event run pct
+do
+	if [ $summary != "summary" ]; then
+		exit 1
+	fi
+done
+
+#
+#     1.001360298 9148534  cycles 8012853854 100.00
+#9148534  cycles 8012853854 100.00
+#
+perf stat -e cycles  -x' ' -I1000 --interval-count 1 --summary --no-csv-summary 2>&1 | \
+grep -e summary | \
+while read num event run pct
+do
+	exit 1
+done
+
+exit 0
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
new file mode 100755
index 000000000..2c4212c64
--- /dev/null
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -0,0 +1,182 @@
+#!/bin/bash
+# perf stat JSON output linter
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Checks various perf stat JSON output commands for the
+# correct number of fields.
+
+set -e
+
+skip_test=0
+
+pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
+if [ "x$PYTHON" == "x" ]
+then
+	if which python3 > /dev/null
+	then
+		PYTHON=python3
+	elif which python > /dev/null
+	then
+		PYTHON=python
+	else
+		echo Skipping test, python not detected please set environment variable PYTHON.
+		exit 2
+	fi
+fi
+
+# Return true if perf_event_paranoid is > $1 and not running as root.
+function ParanoidAndNotRoot()
+{
+	 [ $(id -u) != 0 ] && [ $(cat /proc/sys/kernel/perf_event_paranoid) -gt $1 ]
+}
+
+check_no_args()
+{
+	echo -n "Checking json output: no args "
+	perf stat -j true 2>&1 | $PYTHON $pythonchecker --no-args
+	echo "[Success]"
+}
+
+check_system_wide()
+{
+	echo -n "Checking json output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j -a true 2>&1 | $PYTHON $pythonchecker --system-wide
+	echo "[Success]"
+}
+
+check_system_wide_no_aggr()
+{
+	echo -n "Checking json output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	echo -n "Checking json output: system wide no aggregation "
+	perf stat -j -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr
+	echo "[Success]"
+}
+
+check_interval()
+{
+	echo -n "Checking json output: interval "
+	perf stat -j -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval
+	echo "[Success]"
+}
+
+
+check_event()
+{
+	echo -n "Checking json output: event "
+	perf stat -j -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event
+	echo "[Success]"
+}
+
+check_per_core()
+{
+	echo -n "Checking json output: per core "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core
+	echo "[Success]"
+}
+
+check_per_thread()
+{
+	echo -n "Checking json output: per thread "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread
+	echo "[Success]"
+}
+
+check_per_die()
+{
+	echo -n "Checking json output: per die "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die
+	echo "[Success]"
+}
+
+check_per_node()
+{
+	echo -n "Checking json output: per node "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node
+	echo "[Success]"
+}
+
+check_per_socket()
+{
+	echo -n "Checking json output: per socket "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoia and not root"
+		return
+	fi
+	perf stat -j --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket
+	echo "[Success]"
+}
+
+# The perf stat options for per-socket, per-core, per-die
+# and -A ( no_aggr mode ) uses the info fetched from this
+# directory: "/sys/devices/system/cpu/cpu*/topology". For
+# example, socket value is fetched from "physical_package_id"
+# file in topology directory.
+# Reference: cpu__get_topology_int in util/cpumap.c
+# If the platform doesn't expose topology information, values
+# will be set to -1. For example, incase of pSeries platform
+# of powerpc, value for  "physical_package_id" is restricted
+# and set to -1. Check here validates the socket-id read from
+# topology file before proceeding further
+
+FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
+FILE_NAME="physical_package_id"
+
+check_for_topology()
+{
+	if ! ParanoidAndNotRoot 0
+	then
+		socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
+		[ -z $socket_file ] && return 0
+		socket_id=`cat $socket_file`
+		[ $socket_id == -1 ] && skip_test=1
+		return 0
+	fi
+}
+
+check_for_topology
+check_no_args
+check_system_wide
+check_interval
+check_event
+check_per_thread
+check_per_node
+if [ $skip_test -ne 1 ]
+then
+	check_system_wide_no_aggr
+	check_per_core
+	check_per_die
+	check_per_socket
+else
+	echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
+fi
+exit 0
diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
new file mode 100755
index 000000000..e6e35fc6c
--- /dev/null
+++ b/tools/perf/tests/shell/stat+shadow_stat.sh
@@ -0,0 +1,81 @@
+#!/bin/sh
+# perf stat metrics (shadow stat) test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# skip if system-wide mode is forbidden
+perf stat -a true > /dev/null 2>&1 || exit 2
+
+# skip if on hybrid platform
+perf stat -a -e cycles sleep 1 2>&1 | grep -e cpu_core && exit 2
+
+test_global_aggr()
+{
+	perf stat -a --no-big-num -e cycles,instructions sleep 1  2>&1 | \
+	grep -e cycles -e instructions | \
+	while read num evt hash ipc rest
+	do
+		# skip not counted events
+		if [ "$num" = "<not" ]; then
+			continue
+		fi
+
+		# save cycles count
+		if [ "$evt" = "cycles" ]; then
+			cyc=$num
+			continue
+		fi
+
+		# skip if no cycles
+		if [ -z "$cyc" ]; then
+			continue
+		fi
+
+		# use printf for rounding and a leading zero
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
+			echo "IPC is different: $res != $ipc  ($num / $cyc)"
+			exit 1
+		fi
+	done
+}
+
+test_no_aggr()
+{
+	perf stat -a -A --no-big-num -e cycles,instructions sleep 1  2>&1 | \
+	grep ^CPU | \
+	while read cpu num evt hash ipc rest
+	do
+		# skip not counted events
+		if [ "$num" = "<not" ]; then
+			continue
+		fi
+
+		# save cycles count
+		if [ "$evt" = "cycles" ]; then
+			results="$results $cpu:$num"
+			continue
+		fi
+
+		cyc=${results##* $cpu:}
+		cyc=${cyc%% *}
+
+		# skip if no cycles
+		if [ -z "$cyc" ]; then
+			continue
+		fi
+
+		# use printf for rounding and a leading zero
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
+			echo "IPC is different for $cpu: $res != $ipc  ($num / $cyc)"
+			exit 1
+		fi
+	done
+}
+
+test_global_aggr
+test_no_aggr
+
+exit 0
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
new file mode 100755
index 000000000..26a51b48a
--- /dev/null
+++ b/tools/perf/tests/shell/stat.sh
@@ -0,0 +1,99 @@
+#!/bin/sh
+# perf stat tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+test_default_stat() {
+  echo "Basic stat command test"
+  if ! perf stat true 2>&1 | egrep -q "Performance counter stats for 'true':"
+  then
+    echo "Basic stat command test [Failed]"
+    err=1
+    return
+  fi
+  echo "Basic stat command test [Success]"
+}
+
+test_stat_record_report() {
+  echo "stat record and report test"
+  if ! perf stat record -o - true | perf stat report -i - 2>&1 | \
+    egrep -q "Performance counter stats for 'pipe':"
+  then
+    echo "stat record and report test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat record and report test [Success]"
+}
+
+test_stat_repeat_weak_groups() {
+  echo "stat repeat weak groups test"
+  if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+     true 2>&1 | grep -q 'seconds time elapsed'
+  then
+    echo "stat repeat weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+    true > /dev/null 2>&1
+  then
+    echo "stat repeat weak groups test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat repeat weak groups test [Success]"
+}
+
+test_topdown_groups() {
+  # Topdown events must be grouped with the slots event first. Test that
+  # parse-events reorders this.
+  echo "Topdown event group test"
+  if ! perf stat -e '{slots,topdown-retiring}' true > /dev/null 2>&1
+  then
+    echo "Topdown event group test [Skipped event parsing failed]"
+    return
+  fi
+  if perf stat -e '{slots,topdown-retiring}' true 2>&1 | egrep -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed events not supported]"
+    err=1
+    return
+  fi
+  if perf stat -e '{topdown-retiring,slots}' true 2>&1 | egrep -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed slots not reordered first]"
+    err=1
+    return
+  fi
+  echo "Topdown event group test [Success]"
+}
+
+test_topdown_weak_groups() {
+  # Weak groups break if the perf_event_open of multiple grouped events
+  # fails. Breaking a topdown group causes the events to fail. Test a very large
+  # grouping to see that the topdown events aren't broken out.
+  echo "Topdown weak groups test"
+  ok_grouping="{slots,topdown-bad-spec,topdown-be-bound,topdown-fe-bound,topdown-retiring},branch-instructions,branch-misses,bus-cycles,cache-misses,cache-references,cpu-cycles,instructions,mem-loads,mem-stores,ref-cycles,cache-misses,cache-references"
+  if ! perf stat --no-merge -e "$ok_grouping" true > /dev/null 2>&1
+  then
+    echo "Topdown weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  group_needs_break="{slots,topdown-bad-spec,topdown-be-bound,topdown-fe-bound,topdown-retiring,branch-instructions,branch-misses,bus-cycles,cache-misses,cache-references,cpu-cycles,instructions,mem-loads,mem-stores,ref-cycles,cache-misses,cache-references}:W"
+  if perf stat --no-merge -e "$group_needs_break" true 2>&1 | egrep -q "<not supported>"
+  then
+    echo "Topdown weak groups test [Failed events not supported]"
+    err=1
+    return
+  fi
+  echo "Topdown weak groups test [Success]"
+}
+
+test_default_stat
+test_stat_record_report
+test_stat_repeat_weak_groups
+test_topdown_groups
+test_topdown_weak_groups
+exit $err
diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
new file mode 100755
index 000000000..cb35e4888
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+# perf all metricgroups test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+for m in $(perf list --raw-dump metricgroups); do
+  echo "Testing $m"
+  perf stat -M "$m" -a true
+done
+
+exit 0
diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh
new file mode 100755
index 000000000..22e9cb294
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_metrics.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+# perf all metrics test
+# SPDX-License-Identifier: GPL-2.0
+
+err=0
+for m in $(perf list --raw-dump metrics); do
+  echo "Testing $m"
+  result=$(perf stat -M "$m" true 2>&1)
+  if [[ "$result" =~ "${m:0:50}" ]] || [[ "$result" =~ "<not supported>" ]]
+  then
+    continue
+  fi
+  # Failed so try system wide.
+  result=$(perf stat -M "$m" -a sleep 0.01 2>&1)
+  if [[ "$result" =~ "${m:0:50}" ]]
+  then
+    continue
+  fi
+  # Failed again, possibly the workload was too small so retry with something
+  # longer.
+  result=$(perf stat -M "$m" perf bench internals synthesize 2>&1)
+  if [[ "$result" =~ "${m:0:50}" ]]
+  then
+    continue
+  fi
+  echo "Metric '$m' not printed in:"
+  echo "$result"
+  if [[ "$err" != "1" ]]
+  then
+    err=2
+    if [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+    then
+      echo "Skip, not fail, for FP issues"
+    elif [[ "$result" =~ "PMM" ]]
+    then
+      echo "Skip, not fail, for Optane memory issues"
+    else
+      err=1
+    fi
+  fi
+done
+
+exit "$err"
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
new file mode 100755
index 000000000..c77955419
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+# perf all PMU test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# Test all PMU events; however exclude parametrized ones (name contains '?')
+for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do
+  echo "Testing $p"
+  result=$(perf stat -e "$p" true 2>&1)
+  if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then
+    # We failed to see the event and it is supported. Possibly the workload was
+    # too small so retry with something longer.
+    result=$(perf stat -e "$p" perf bench internals synthesize 2>&1)
+    if ! echo "$result" | grep -q "$p" ; then
+      echo "Event '$p' not printed in:"
+      echo "$result"
+      exit 1
+    fi
+  fi
+done
+
+exit 0
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
new file mode 100755
index 000000000..6bf24b852
--- /dev/null
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -0,0 +1,45 @@
+#!/bin/sh
+# perf stat --bpf-counters test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# check whether $2 is within +/- 10% of $1
+compare_number()
+{
+       first_num=$1
+       second_num=$2
+
+       # upper bound is first_num * 110%
+       upper=$(expr $first_num + $first_num / 10 )
+       # lower bound is first_num * 90%
+       lower=$(expr $first_num - $first_num / 10 )
+
+       if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
+               echo "The difference between $first_num and $second_num are greater than 10%."
+               exit 1
+       fi
+}
+
+# skip if --bpf-counters is not supported
+if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
+	if [ "$1" = "-v" ]; then
+		echo "Skipping: --bpf-counters not supported"
+		perf --no-pager stat -e cycles --bpf-counters true || true
+	fi
+	exit 2
+fi
+
+base_cycles=$(perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
+if [ "$base_cycles" == "<not" ]; then
+	echo "Skipping: cycles event not counted"
+	exit 2
+fi
+bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
+if [ "$bpf_cycles" == "<not" ]; then
+	echo "Failed: cycles not counted with --bpf-counters"
+	exit 1
+fi
+
+compare_number $base_cycles $bpf_cycles
+exit 0
diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
new file mode 100755
index 000000000..e75d0780d
--- /dev/null
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -0,0 +1,79 @@
+#!/bin/sh
+# perf stat --bpf-counters --for-each-cgroup test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+test_cgroups=
+if [ "$1" = "-v" ]; then
+	verbose="1"
+fi
+
+# skip if --bpf-counters --for-each-cgroup is not supported
+check_bpf_counter()
+{
+	if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then
+		if [ "${verbose}" = "1" ]; then
+			echo "Skipping: --bpf-counters --for-each-cgroup not supported"
+			perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true
+		fi
+		exit 2
+	fi
+}
+
+# find two cgroups to measure
+find_cgroups()
+{
+	# try usual systemd slices first
+	if [ -d /sys/fs/cgroup/system.slice ] && [ -d /sys/fs/cgroup/user.slice ]; then
+		test_cgroups="system.slice,user.slice"
+		return
+	fi
+
+	# try root and self cgroups
+	find_cgroups_self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
+	if [ -z ${find_cgroups_self_cgrp} ]; then
+		# cgroup v2 doesn't specify perf_event
+		find_cgroups_self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
+	fi
+
+	if [ -z ${find_cgroups_self_cgrp} ]; then
+		test_cgroups="/"
+	else
+		test_cgroups="/,${find_cgroups_self_cgrp}"
+	fi
+}
+
+# As cgroup events are cpu-wide, we cannot simply compare the result.
+# Just check if it runs without failure and has non-zero results.
+check_system_wide_counted()
+{
+	check_system_wide_counted_output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)
+	if echo ${check_system_wide_counted_output} | grep -q -F "<not "; then
+		echo "Some system-wide events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${check_system_wide_counted_output}
+		fi
+		exit 1
+	fi
+}
+
+check_cpu_list_counted()
+{
+	check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
+	if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then
+		echo "Some CPU events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${check_cpu_list_counted_output}
+		fi
+		exit 1
+	fi
+}
+
+check_bpf_counter
+find_cgroups
+
+check_system_wide_counted
+check_cpu_list_counted
+
+exit 0
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
new file mode 100755
index 000000000..ec108d45d
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -0,0 +1,68 @@
+#!/bin/sh
+# Check Arm64 callgraphs are complete in fp mode
+# SPDX-License-Identifier: GPL-2.0
+
+lscpu | grep -q "aarch64" || exit 2
+
+if ! [ -x "$(command -v cc)" ]; then
+	echo "failed: no compiler, install gcc"
+	exit 2
+fi
+
+PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+TEST_PROGRAM_SOURCE=$(mktemp /tmp/test_program.XXXXX.c)
+TEST_PROGRAM=$(mktemp /tmp/test_program.XXXXX)
+
+cleanup_files()
+{
+	rm -f $PERF_DATA
+	rm -f $TEST_PROGRAM_SOURCE
+	rm -f $TEST_PROGRAM
+}
+
+trap cleanup_files exit term int
+
+cat << EOF > $TEST_PROGRAM_SOURCE
+int a = 0;
+void leaf(void) {
+  for (;;)
+    a += a;
+}
+void parent(void) {
+  leaf();
+}
+int main(void) {
+  parent();
+  return 0;
+}
+EOF
+
+echo " + Compiling test program ($TEST_PROGRAM)..."
+
+CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
+cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
+
+# Add a 1 second delay to skip samples that are not in the leaf() function
+perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
+PID=$!
+
+echo " + Recording (PID=$PID)..."
+sleep 2
+echo " + Stopping perf-record..."
+
+kill $PID
+wait $PID
+
+# expected perf-script output:
+#
+# program
+# 	728 leaf
+# 	753 parent
+# 	76c main
+# ...
+
+perf script -i $PERF_DATA -F comm,ip,sym | head -n4
+perf script -i $PERF_DATA -F comm,ip,sym | head -n4 | \
+	awk '{ if ($2 != "") sym[i++] = $2 } END { if (sym[0] != "leaf" ||
+						       sym[1] != "parent" ||
+						       sym[2] != "main") exit 1 }'
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
new file mode 100755
index 000000000..daad786cf
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -0,0 +1,188 @@
+#!/bin/sh
+# Check Arm CoreSight trace data recording and synthesized samples
+
+# Uses the 'perf record' to record trace data with Arm CoreSight sinks;
+# then verify if there have any branch samples and instruction samples
+# are generated by CoreSight with 'perf script' and 'perf report'
+# commands.
+
+# SPDX-License-Identifier: GPL-2.0
+# Leo Yan <leo.yan@linaro.org>, 2020
+
+glb_err=0
+
+skip_if_no_cs_etm_event() {
+	perf list | grep -q 'cs_etm//' && return 0
+
+	# cs_etm event doesn't exist
+	return 2
+}
+
+skip_if_no_cs_etm_event || exit 2
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+cleanup_files()
+{
+	rm -f ${perfdata}
+	rm -f ${file}
+	rm -f "${perfdata}.old"
+	trap - exit term int
+	exit $glb_err
+}
+
+trap cleanup_files exit term int
+
+record_touch_file() {
+	echo "Recording trace (only user mode) with path: CPU$2 => $1"
+	rm -f $file
+	perf record -o ${perfdata} -e cs_etm/@$1/u --per-thread \
+		-- taskset -c $2 touch $file > /dev/null 2>&1
+}
+
+perf_script_branch_samples() {
+	echo "Looking at perf.data file for dumping branch samples:"
+
+	# Below is an example of the branch samples dumping:
+	#   touch  6512          1         branches:u:      ffffb220824c strcmp+0xc (/lib/aarch64-linux-gnu/ld-2.27.so)
+	#   touch  6512          1         branches:u:      ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
+	#   touch  6512          1         branches:u:      ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
+	perf script -F,-time -i ${perfdata} 2>&1 | \
+		egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" > /dev/null 2>&1
+}
+
+perf_report_branch_samples() {
+	echo "Looking at perf.data file for reporting branch samples:"
+
+	# Below is an example of the branch samples reporting:
+	#   73.04%    73.04%  touch    libc-2.27.so      [.] _dl_addr
+	#    7.71%     7.71%  touch    libc-2.27.so      [.] getenv
+	#    2.59%     2.59%  touch    ld-2.27.so        [.] strcmp
+	perf report --stdio -i ${perfdata} 2>&1 | \
+		egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " > /dev/null 2>&1
+}
+
+perf_report_instruction_samples() {
+	echo "Looking at perf.data file for instruction samples:"
+
+	# Below is an example of the instruction samples reporting:
+	#   68.12%  touch    libc-2.27.so   [.] _dl_addr
+	#    5.80%  touch    libc-2.27.so   [.] getenv
+	#    4.35%  touch    ld-2.27.so     [.] _dl_fixup
+	perf report --itrace=i20i --stdio -i ${perfdata} 2>&1 | \
+		egrep " +[0-9]+\.[0-9]+% +$1" > /dev/null 2>&1
+}
+
+arm_cs_report() {
+	if [ $2 != 0 ]; then
+		echo "$1: FAIL"
+		glb_err=$2
+	else
+		echo "$1: PASS"
+	fi
+}
+
+is_device_sink() {
+	# If the node of "enable_sink" is existed under the device path, this
+	# means the device is a sink device.  Need to exclude 'tpiu' since it
+	# cannot support perf PMU.
+	echo "$1" | egrep -q -v "tpiu"
+
+	if [ $? -eq 0 -a -e "$1/enable_sink" ]; then
+
+		pmu_dev="/sys/bus/event_source/devices/cs_etm/sinks/$2"
+
+		# Warn if the device is not supported by PMU
+		if ! [ -f $pmu_dev ]; then
+			echo "PMU doesn't support $pmu_dev"
+		fi
+
+		return 0
+	fi
+
+	# Otherwise, it's not a sink device
+	return 1
+}
+
+arm_cs_iterate_devices() {
+	for dev in $1/connections/out\:*; do
+
+		# Skip testing if it's not a directory
+		! [ -d $dev ] && continue;
+
+		# Read out its symbol link file name
+		path=`readlink -f $dev`
+
+		# Extract device name from path, e.g.
+		#   path = '/sys/devices/platform/20010000.etf/tmc_etf0'
+		#     `> device_name = 'tmc_etf0'
+		device_name=$(basename $path)
+
+		if is_device_sink $path $device_name; then
+
+			record_touch_file $device_name $2 &&
+			perf_script_branch_samples touch &&
+			perf_report_branch_samples touch &&
+			perf_report_instruction_samples touch
+
+			err=$?
+			arm_cs_report "CoreSight path testing (CPU$2 -> $device_name)" $err
+		fi
+
+		arm_cs_iterate_devices $dev $2
+	done
+}
+
+arm_cs_etm_traverse_path_test() {
+	# Iterate for every ETM device
+	for dev in /sys/bus/coresight/devices/etm*; do
+
+		# Find the ETM device belonging to which CPU
+		cpu=`cat $dev/cpu`
+
+		# Use depth-first search (DFS) to iterate outputs
+		arm_cs_iterate_devices $dev $cpu
+	done
+}
+
+arm_cs_etm_system_wide_test() {
+	echo "Recording trace with system wide mode"
+	perf record -o ${perfdata} -e cs_etm// -a -- ls > /dev/null 2>&1
+
+	perf_script_branch_samples perf &&
+	perf_report_branch_samples perf &&
+	perf_report_instruction_samples perf
+
+	err=$?
+	arm_cs_report "CoreSight system wide testing" $err
+}
+
+arm_cs_etm_snapshot_test() {
+	echo "Recording trace with snapshot mode"
+	perf record -o ${perfdata} -e cs_etm// -S \
+		-- dd if=/dev/zero of=/dev/null > /dev/null 2>&1 &
+	PERFPID=$!
+
+	# Wait for perf program
+	sleep 1
+
+	# Send signal to snapshot trace data
+	kill -USR2 $PERFPID
+
+	# Stop perf program
+	kill $PERFPID
+	wait $PERFPID
+
+	perf_script_branch_samples dd &&
+	perf_report_branch_samples dd &&
+	perf_report_instruction_samples dd
+
+	err=$?
+	arm_cs_report "CoreSight snapshot testing" $err
+}
+
+arm_cs_etm_traverse_path_test
+arm_cs_etm_system_wide_test
+arm_cs_etm_snapshot_test
+exit $glb_err
diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh
new file mode 100755
index 000000000..0d47479ad
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_spe.sh
@@ -0,0 +1,113 @@
+#!/bin/sh
+# Check Arm SPE trace data recording and synthesized samples
+
+# Uses the 'perf record' to record trace data of Arm SPE events;
+# then verify if any SPE event samples are generated by SPE with
+# 'perf script' and 'perf report' commands.
+
+# SPDX-License-Identifier: GPL-2.0
+# German Gomez <german.gomez@arm.com>, 2021
+
+skip_if_no_arm_spe_event() {
+	perf list | egrep -q 'arm_spe_[0-9]+//' && return 0
+
+	# arm_spe event doesn't exist
+	return 2
+}
+
+skip_if_no_arm_spe_event || exit 2
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+glb_err=0
+
+cleanup_files()
+{
+	rm -f ${perfdata}
+	rm -f ${perfdata}.old
+	exit $glb_err
+}
+
+trap cleanup_files exit term int
+
+arm_spe_report() {
+	if [ $2 = 0 ]; then
+		echo "$1: PASS"
+	elif [ $2 = 2 ]; then
+		echo "$1: SKIPPED"
+	else
+		echo "$1: FAIL"
+		glb_err=$2
+	fi
+}
+
+perf_script_samples() {
+	echo "Looking at perf.data file for dumping samples:"
+
+	# from arm-spe.c/arm_spe_synth_events()
+	events="(ld1-miss|ld1-access|llc-miss|lld-access|tlb-miss|tlb-access|branch-miss|remote-access|memory)"
+
+	# Below is an example of the samples dumping:
+	#	dd  3048 [002]          1    l1d-access:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	#	dd  3048 [002]          1    tlb-access:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	#	dd  3048 [002]          1        memory:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	perf script -F,-time -i ${perfdata} 2>&1 | \
+		egrep " +$1 +[0-9]+ .* +${events}:(.*:)? +" > /dev/null 2>&1
+}
+
+perf_report_samples() {
+	echo "Looking at perf.data file for reporting samples:"
+
+	# Below is an example of the samples reporting:
+	#   73.04%    73.04%  dd    libc-2.27.so      [.] _dl_addr
+	#    7.71%     7.71%  dd    libc-2.27.so      [.] getenv
+	#    2.59%     2.59%  dd    ld-2.27.so        [.] strcmp
+	perf report --stdio -i ${perfdata} 2>&1 | \
+		egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " > /dev/null 2>&1
+}
+
+arm_spe_snapshot_test() {
+	echo "Recording trace with snapshot mode $perfdata"
+	perf record -o ${perfdata} -e arm_spe// -S \
+		-- dd if=/dev/zero of=/dev/null > /dev/null 2>&1 &
+	PERFPID=$!
+
+	# Wait for perf program
+	sleep 1
+
+	# Send signal to snapshot trace data
+	kill -USR2 $PERFPID
+
+	# Stop perf program
+	kill $PERFPID
+	wait $PERFPID
+
+	perf_script_samples dd &&
+	perf_report_samples dd
+
+	err=$?
+	arm_spe_report "SPE snapshot testing" $err
+}
+
+arm_spe_system_wide_test() {
+	echo "Recording trace with system-wide mode $perfdata"
+
+	perf record -o - -e dummy -a -B true > /dev/null 2>&1
+	if [ $? != 0 ]; then
+		arm_spe_report "SPE system-wide testing" 2
+		return
+	fi
+
+	perf record -o ${perfdata} -e arm_spe// -a --no-bpf-event \
+		-- dd if=/dev/zero of=/dev/null count=100000 > /dev/null 2>&1
+
+	perf_script_samples dd &&
+	perf_report_samples dd
+
+	err=$?
+	arm_spe_report "SPE system-wide testing" $err
+}
+
+arm_spe_snapshot_test
+arm_spe_system_wide_test
+
+exit $glb_err
diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh
new file mode 100755
index 000000000..c920d3583
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_spe_fork.sh
@@ -0,0 +1,92 @@
+#!/bin/sh
+# Check Arm SPE doesn't hang when there are forks
+
+# SPDX-License-Identifier: GPL-2.0
+# German Gomez <german.gomez@arm.com>, 2022
+
+skip_if_no_arm_spe_event() {
+	perf list | egrep -q 'arm_spe_[0-9]+//' && return 0
+	return 2
+}
+
+skip_if_no_arm_spe_event || exit 2
+
+# skip if there's no compiler
+if ! [ -x "$(command -v cc)" ]; then
+	echo "failed: no compiler, install gcc"
+	exit 2
+fi
+
+TEST_PROGRAM_SOURCE=$(mktemp /tmp/__perf_test.program.XXXXX.c)
+TEST_PROGRAM=$(mktemp /tmp/__perf_test.program.XXXXX)
+PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+PERF_RECORD_LOG=$(mktemp /tmp/__perf_test.log.XXXXX)
+
+cleanup_files()
+{
+	echo "Cleaning up files..."
+	rm -f ${PERF_RECORD_LOG}
+	rm -f ${PERF_DATA}
+	rm -f ${TEST_PROGRAM_SOURCE}
+	rm -f ${TEST_PROGRAM}
+}
+
+trap cleanup_files exit term int
+
+# compile test program
+cat << EOF > $TEST_PROGRAM_SOURCE
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+int workload() {
+  while (1)
+    sqrt(rand());
+  return 0;
+}
+
+int main() {
+  switch (fork()) {
+    case 0:
+      return workload();
+    case -1:
+      return 1;
+    default:
+      wait(NULL);
+  }
+  return 0;
+}
+EOF
+
+echo "Compiling test program..."
+CFLAGS="-lm"
+cc $TEST_PROGRAM_SOURCE $CFLAGS -o $TEST_PROGRAM || exit 1
+
+echo "Recording workload..."
+perf record -o ${PERF_DATA} -e arm_spe/period=65536/ -vvv -- $TEST_PROGRAM > ${PERF_RECORD_LOG} 2>&1 &
+PERFPID=$!
+
+# Check if perf hangs by checking the perf-record logs.
+sleep 1
+log0=$(wc -l $PERF_RECORD_LOG)
+echo Log lines = $log0
+sleep 1
+log1=$(wc -l $PERF_RECORD_LOG)
+echo Log lines after 1 second = $log1
+
+kill $PERFPID
+wait $PERFPID
+# test program may leave an orphan process running the workload
+killall $(basename $TEST_PROGRAM)
+
+if [ "$log0" = "$log1" ];
+then
+        echo "SPE hang test: FAIL"
+        exit 1
+else
+        echo "SPE hang test: PASS"
+fi
+
+exit 0
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
new file mode 100755
index 000000000..d7ff5c4b4
--- /dev/null
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -0,0 +1,118 @@
+#!/bin/sh
+# Check branch stack sampling
+
+# SPDX-License-Identifier: GPL-2.0
+# German Gomez <german.gomez@arm.com>, 2022
+
+# we need a C compiler to build the test programs
+# so bail if none is found
+if ! [ -x "$(command -v cc)" ]; then
+	echo "failed: no compiler, install gcc"
+	exit 2
+fi
+
+# skip the test if the hardware doesn't support branch stack sampling
+# and if the architecture doesn't support filter types: any,save_type,u
+if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then
+	echo "skip: system doesn't support filter types: any,save_type,u"
+	exit 2
+fi
+
+TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
+
+cleanup() {
+	rm -rf $TMPDIR
+}
+
+trap cleanup exit term int
+
+gen_test_program() {
+	# generate test program
+	cat << EOF > $1
+#define BENCH_RUNS 999999
+int cnt;
+void bar(void) {
+}			/* return */
+void foo(void) {
+	bar();		/* call */
+}			/* return */
+void bench(void) {
+  void (*foo_ind)(void) = foo;
+  if ((cnt++) % 3)	/* branch (cond) */
+    foo();		/* call */
+  bar();		/* call */
+  foo_ind();		/* call (ind) */
+}
+int main(void)
+{
+  int cnt = 0;
+  while (1) {
+    if ((cnt++) > BENCH_RUNS)
+      break;
+    bench();		/* call */
+  }			/* branch (uncond) */
+  return 0;
+}
+EOF
+}
+
+test_user_branches() {
+	echo "Testing user branch stack sampling"
+
+	gen_test_program "$TEMPDIR/program.c"
+	cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out
+
+	perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1
+	perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
+
+	# example of branch entries:
+	# 	foo+0x14/bar+0x40/P/-/-/0/CALL
+
+	set -x
+	egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/IND_CALL$"	$TMPDIR/perf.script
+	egrep -m1 "^foo\+[^ ]*/bar\+[^ ]*/CALL$"	$TMPDIR/perf.script
+	egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/CALL$"	$TMPDIR/perf.script
+	egrep -m1 "^bench\+[^ ]*/bar\+[^ ]*/CALL$"	$TMPDIR/perf.script
+	egrep -m1 "^bar\+[^ ]*/foo\+[^ ]*/RET$"		$TMPDIR/perf.script
+	egrep -m1 "^foo\+[^ ]*/bench\+[^ ]*/RET$"	$TMPDIR/perf.script
+	egrep -m1 "^bench\+[^ ]*/bench\+[^ ]*/COND$"	$TMPDIR/perf.script
+	egrep -m1 "^main\+[^ ]*/main\+[^ ]*/UNCOND$"	$TMPDIR/perf.script
+	set +x
+
+	# some branch types are still not being tested:
+	# IND COND_CALL COND_RET SYSCALL SYSRET IRQ SERROR NO_TX
+}
+
+# first argument <arg0> is the argument passed to "--branch-stack <arg0>,save_type,u"
+# second argument are the expected branch types for the given filter
+test_filter() {
+	local filter=$1
+	local expect=$2
+
+	echo "Testing branch stack filtering permutation ($filter,$expect)"
+
+	gen_test_program "$TEMPDIR/program.c"
+	cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out
+
+	perf record -o $TMPDIR/perf.data --branch-filter $filter,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1
+	perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
+
+	# fail if we find any branch type that doesn't match any of the expected ones
+	# also consider UNKNOWN branch types (-)
+	if egrep -vm1 "^[^ ]*/($expect|-|( *))$" $TMPDIR/perf.script; then
+		return 1
+	fi
+}
+
+set -e
+
+test_user_branches
+
+test_filter "any_call"	"CALL|IND_CALL|COND_CALL|SYSCALL|IRQ"
+test_filter "call"	"CALL|SYSCALL"
+test_filter "cond"	"COND"
+test_filter "any_ret"	"RET|COND_RET|SYSRET|ERET"
+
+test_filter "call,cond"		"CALL|SYSCALL|COND"
+test_filter "any_call,cond"		"CALL|IND_CALL|COND_CALL|IRQ|SYSCALL|COND"
+test_filter "cond,any_call,any_ret"	"COND|CALL|IND_CALL|COND_CALL|SYSCALL|IRQ|RET|COND_RET|SYSRET|ERET"
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
new file mode 100755
index 000000000..cd6eb54d2
--- /dev/null
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -0,0 +1,93 @@
+#!/bin/bash
+# Test data symbol
+
+# SPDX-License-Identifier: GPL-2.0
+# Leo Yan <leo.yan@linaro.org>, 2022
+
+skip_if_no_mem_event() {
+	perf mem record -e list 2>&1 | egrep -q 'available' && return 0
+	return 2
+}
+
+skip_if_no_mem_event || exit 2
+
+# skip if there's no compiler
+if ! [ -x "$(command -v cc)" ]; then
+	echo "skip: no compiler, install gcc"
+	exit 2
+fi
+
+TEST_PROGRAM=$(mktemp /tmp/__perf_test.program.XXXXX)
+PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+
+check_result() {
+	# The memory report format is as below:
+	#    99.92%  ...  [.] buf1+0x38
+	result=$(perf mem report -i ${PERF_DATA} -s symbol_daddr -q 2>&1 |
+		 awk '/buf1/ { print $4 }')
+
+	# Testing is failed if has no any sample for "buf1"
+	[ -z "$result" ] && return 1
+
+	while IFS= read -r line; do
+		# The "data1" and "data2" fields in structure "buf1" have
+		# offset "0x0" and "0x38", returns failure if detect any
+		# other offset value.
+		if [ "$line" != "buf1+0x0" ] && [ "$line" != "buf1+0x38" ]; then
+			return 1
+		fi
+	done <<< "$result"
+
+	return 0
+}
+
+cleanup_files()
+{
+	echo "Cleaning up files..."
+	rm -f ${PERF_DATA}
+	rm -f ${TEST_PROGRAM}
+}
+
+trap cleanup_files exit term int
+
+# compile test program
+echo "Compiling test program..."
+cat << EOF | cc -o ${TEST_PROGRAM} -x c -
+typedef struct _buf {
+	char data1;
+	char reserved[55];
+	char data2;
+} buf __attribute__((aligned(64)));
+
+static buf buf1;
+
+int main(void) {
+	for (;;) {
+		buf1.data1++;
+		buf1.data2 += buf1.data1;
+	}
+	return 0;
+}
+EOF
+
+echo "Recording workload..."
+
+# perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't support
+# user/kernel filtering and per-process monitoring, spin program on
+# specific CPU and test in per-CPU mode.
+is_amd=$(egrep -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo)
+if (($is_amd >= 1)); then
+	perf mem record -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM &
+else
+	perf mem record --all-user -o ${PERF_DATA} -- $TEST_PROGRAM &
+fi
+
+PERFPID=$!
+
+sleep 1
+
+kill $PERFPID
+wait $PERFPID
+
+check_result
+exit $?
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
new file mode 100755
index 000000000..f5ed7b1af
--- /dev/null
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -0,0 +1,663 @@
+#!/bin/sh
+# Miscellaneous Intel PT testing
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# Skip if no Intel PT
+perf list | grep -q 'intel_pt//' || exit 2
+
+shelldir=$(dirname "$0")
+. "${shelldir}"/lib/waiting.sh
+
+skip_cnt=0
+ok_cnt=0
+err_cnt=0
+
+temp_dir=$(mktemp -d /tmp/perf-test-intel-pt-sh.XXXXXXXXXX)
+
+tmpfile="${temp_dir}/tmp-perf.data"
+perfdatafile="${temp_dir}/test-perf.data"
+outfile="${temp_dir}/test-out.txt"
+errfile="${temp_dir}/test-err.txt"
+workload="${temp_dir}/workload"
+awkscript="${temp_dir}/awkscript"
+jitdump_workload="${temp_dir}/jitdump_workload"
+maxbrstack="${temp_dir}/maxbrstack.py"
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	sane=$(echo "${temp_dir}" | cut -b 1-26)
+	if [ "${sane}" = "/tmp/perf-test-intel-pt-sh" ] ; then
+		echo "--- Cleaning up ---"
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+# perf record for testing without decoding
+perf_record_no_decode()
+{
+	# Options to speed up recording: no post-processing, no build-id cache update,
+	# and no BPF events.
+	perf record -B -N --no-bpf-event "$@"
+}
+
+# perf record for testing should not need BPF events
+perf_record_no_bpf()
+{
+	# Options for no BPF events
+	perf record --no-bpf-event "$@"
+}
+
+have_workload=false
+cat << _end_of_file_ | /usr/bin/cc -o "${workload}" -xc - -pthread && have_workload=true
+#include <time.h>
+#include <pthread.h>
+
+void work(void) {
+	struct timespec tm = {
+		.tv_nsec = 1000000,
+	};
+	int i;
+
+	/* Run for about 30 seconds */
+	for (i = 0; i < 30000; i++)
+		nanosleep(&tm, NULL);
+}
+
+void *threadfunc(void *arg) {
+	work();
+	return NULL;
+}
+
+int main(void) {
+	pthread_t th;
+
+	pthread_create(&th, NULL, threadfunc, NULL);
+	work();
+	pthread_join(th, NULL);
+	return 0;
+}
+_end_of_file_
+
+can_cpu_wide()
+{
+	echo "Checking for CPU-wide recording on CPU $1"
+	if ! perf_record_no_decode -o "${tmpfile}" -e dummy:u -C "$1" true >/dev/null 2>&1 ; then
+		echo "No so skipping"
+		return 2
+	fi
+	echo OK
+	return 0
+}
+
+test_system_wide_side_band()
+{
+	echo "--- Test system-wide sideband ---"
+
+	# Need CPU 0 and CPU 1
+	can_cpu_wide 0 || return $?
+	can_cpu_wide 1 || return $?
+
+	# Record on CPU 0 a task running on CPU 1
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname
+
+	# Should get MMAP events from CPU 1 because they can be needed to decode
+	mmap_cnt=$(perf script -i "${perfdatafile}" --no-itrace --show-mmap-events -C 1 2>/dev/null | grep -c MMAP)
+
+	if [ "${mmap_cnt}" -gt 0 ] ; then
+		echo OK
+		return 0
+	fi
+
+	echo "Failed to record MMAP events on CPU 1 when tracing CPU 0"
+	return 1
+}
+
+can_kernel()
+{
+	if [ -z "${can_kernel_trace}" ] ; then
+		can_kernel_trace=0
+		perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 && can_kernel_trace=1
+	fi
+	if [ ${can_kernel_trace} -eq 0 ] ; then
+		echo "SKIP: no kernel tracing"
+		return 2
+	fi
+	return 0
+}
+
+test_per_thread()
+{
+	k="$1"
+	desc="$2"
+
+	echo "--- Test per-thread ${desc}recording ---"
+
+	if ! $have_workload ; then
+		echo "No workload, so skipping"
+		return 2
+	fi
+
+	if [ "${k}" = "k" ] ; then
+		can_kernel || return 2
+	fi
+
+	cat <<- "_end_of_file_" > "${awkscript}"
+	BEGIN {
+		s = "[ ]*"
+		u = s"[0-9]+"s
+		d = s"[0-9-]+"s
+		x = s"[0-9a-fA-FxX]+"s
+		mmapping = "idx"u": mmapping fd"u
+		set_output = "idx"u": set output fd"u"->"u
+		perf_event_open = "sys_perf_event_open: pid"d"cpu"d"group_fd"d"flags"x"="u
+	}
+
+	/perf record opening and mmapping events/ {
+		if (!done)
+			active = 1
+	}
+
+	/perf record done opening and mmapping events/ {
+		active = 0
+		done = 1
+	}
+
+	$0 ~ perf_event_open && active {
+		match($0, perf_event_open)
+		$0 = substr($0, RSTART, RLENGTH)
+		pid = $3
+		cpu = $5
+		fd = $11
+		print "pid " pid " cpu " cpu " fd " fd " : " $0
+		fd_array[fd] = fd
+		pid_array[fd] = pid
+		cpu_array[fd] = cpu
+	}
+
+	$0 ~ mmapping && active  {
+		match($0, mmapping)
+		$0 = substr($0, RSTART, RLENGTH)
+		fd = $5
+		print "fd " fd " : " $0
+		if (fd in fd_array) {
+			mmap_array[fd] = 1
+		} else {
+			print "Unknown fd " fd
+			exit 1
+		}
+	}
+
+	$0 ~ set_output && active {
+		match($0, set_output)
+		$0 = substr($0, RSTART, RLENGTH)
+		fd = $6
+		fd_to = $8
+		print "fd " fd " fd_to " fd_to " : " $0
+		if (fd in fd_array) {
+			if (fd_to in fd_array) {
+				set_output_array[fd] = fd_to
+			} else {
+				print "Unknown fd " fd_to
+				exit 1
+			}
+		} else {
+			print "Unknown fd " fd
+			exit 1
+		}
+	}
+
+	END {
+		print "Checking " length(fd_array) " fds"
+		for (fd in fd_array) {
+			if (fd in mmap_array) {
+				pid = pid_array[fd]
+				if (pid != -1) {
+					if (pid in pids) {
+						print "More than 1 mmap for PID " pid
+						exit 1
+					}
+					pids[pid] = 1
+				}
+				cpu = cpu_array[fd]
+				if (cpu != -1) {
+					if (cpu in cpus) {
+						print "More than 1 mmap for CPU " cpu
+						exit 1
+					}
+					cpus[cpu] = 1
+				}
+			} else if (!(fd in set_output_array)) {
+				print "No mmap for fd " fd
+				exit 1
+			}
+		}
+		n = length(pids)
+		if (n != thread_cnt) {
+			print "Expected " thread_cnt " per-thread mmaps - found " n
+			exit 1
+		}
+	}
+	_end_of_file_
+
+	$workload &
+	w1=$!
+	$workload &
+	w2=$!
+	echo "Workload PIDs are $w1 and $w2"
+	wait_for_threads ${w1} 2
+	wait_for_threads ${w2} 2
+
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" &
+	ppid=$!
+	echo "perf PID is $ppid"
+	wait_for_perf_to_start ${ppid} "${errfile}" || return 1
+
+	kill ${w1}
+	wait_for_process_to_exit ${w1} || return 1
+	is_running ${ppid} || return 1
+
+	kill ${w2}
+	wait_for_process_to_exit ${w2} || return 1
+	wait_for_process_to_exit ${ppid} || return 1
+
+	awk -v thread_cnt=4 -f "${awkscript}" "${errfile}" || return 1
+
+	echo OK
+	return 0
+}
+
+test_jitdump()
+{
+	echo "--- Test tracing self-modifying code that uses jitdump ---"
+
+	script_path=$(realpath "$0")
+	script_dir=$(dirname "$script_path")
+	jitdump_incl_dir="${script_dir}/../../util"
+	jitdump_h="${jitdump_incl_dir}/jitdump.h"
+
+	if [ ! -e "${jitdump_h}" ] ; then
+		echo "SKIP: Include file jitdump.h not found"
+		return 2
+	fi
+
+	if [ -z "${have_jitdump_workload}" ] ; then
+		have_jitdump_workload=false
+		# Create a workload that uses self-modifying code and generates its own jitdump file
+		cat <<- "_end_of_file_" | /usr/bin/cc -o "${jitdump_workload}" -I "${jitdump_incl_dir}" -xc - -pthread && have_jitdump_workload=true
+		#define _GNU_SOURCE
+		#include <sys/mman.h>
+		#include <sys/types.h>
+		#include <stddef.h>
+		#include <stdio.h>
+		#include <stdint.h>
+		#include <unistd.h>
+		#include <string.h>
+
+		#include "jitdump.h"
+
+		#define CHK_BYTE 0x5a
+
+		static inline uint64_t rdtsc(void)
+		{
+			unsigned int low, high;
+
+			asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+			return low | ((uint64_t)high) << 32;
+		}
+
+		static FILE *open_jitdump(void)
+		{
+			struct jitheader header = {
+				.magic      = JITHEADER_MAGIC,
+				.version    = JITHEADER_VERSION,
+				.total_size = sizeof(header),
+				.pid        = getpid(),
+				.timestamp  = rdtsc(),
+				.flags      = JITDUMP_FLAGS_ARCH_TIMESTAMP,
+			};
+			char filename[256];
+			FILE *f;
+			void *m;
+
+			snprintf(filename, sizeof(filename), "jit-%d.dump", getpid());
+			f = fopen(filename, "w+");
+			if (!f)
+				goto err;
+			/* Create an MMAP event for the jitdump file. That is how perf tool finds it. */
+			m = mmap(0, 4096, PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(f), 0);
+			if (m == MAP_FAILED)
+				goto err_close;
+			munmap(m, 4096);
+			if (fwrite(&header,sizeof(header),1,f) != 1)
+				goto err_close;
+			return f;
+
+		err_close:
+			fclose(f);
+		err:
+			return NULL;
+		}
+
+		static int write_jitdump(FILE *f, void *addr, const uint8_t *dat, size_t sz, uint64_t *idx)
+		{
+			struct jr_code_load rec = {
+				.p.id          = JIT_CODE_LOAD,
+				.p.total_size  = sizeof(rec) + sz,
+				.p.timestamp   = rdtsc(),
+				.pid	       = getpid(),
+				.tid	       = gettid(),
+				.vma           = (unsigned long)addr,
+				.code_addr     = (unsigned long)addr,
+				.code_size     = sz,
+				.code_index    = ++*idx,
+			};
+
+			if (fwrite(&rec,sizeof(rec),1,f) != 1 ||
+			fwrite(dat, sz, 1, f) != 1)
+				return -1;
+			return 0;
+		}
+
+		static void close_jitdump(FILE *f)
+		{
+			fclose(f);
+		}
+
+		int main()
+		{
+			/* Get a memory page to store executable code */
+			void *addr = mmap(0, 4096, PROT_WRITE | PROT_EXEC, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+			/* Code to execute: mov CHK_BYTE, %eax ; ret */
+			uint8_t dat[] = {0xb8, CHK_BYTE, 0x00, 0x00, 0x00, 0xc3};
+			FILE *f = open_jitdump();
+			uint64_t idx = 0;
+			int ret = 1;
+
+			if (!f)
+				return 1;
+			/* Copy executable code to executable memory page */
+			memcpy(addr, dat, sizeof(dat));
+			/* Record it in the jitdump file */
+			if (write_jitdump(f, addr, dat, sizeof(dat), &idx))
+				goto out_close;
+			/* Call it */
+			ret = ((int (*)(void))addr)() - CHK_BYTE;
+		out_close:
+			close_jitdump(f);
+			return ret;
+		}
+		_end_of_file_
+	fi
+
+	if ! $have_jitdump_workload ; then
+		echo "SKIP: No jitdump workload"
+		return 2
+	fi
+
+	# Change to temp_dir so jitdump collateral files go there
+	cd "${temp_dir}"
+	perf_record_no_bpf -o "${tmpfile}" -e intel_pt//u "${jitdump_workload}"
+	perf inject -i "${tmpfile}" -o "${perfdatafile}" --jit
+	decode_br_cnt=$(perf script -i "${perfdatafile}" --itrace=b | wc -l)
+	# Note that overflow and lost errors are suppressed for the error count
+	decode_err_cnt=$(perf script -i "${perfdatafile}" --itrace=e-o-l | grep -ci error)
+	cd -
+	# Should be thousands of branches
+	if [ "${decode_br_cnt}" -lt 1000 ] ; then
+		echo "Decode failed, only ${decode_br_cnt} branches"
+		return 1
+	fi
+	# Should be no errors
+	if [ "${decode_err_cnt}" -ne 0 ] ; then
+		echo "Decode failed, ${decode_err_cnt} errors"
+		perf script -i "${perfdatafile}" --itrace=e-o-l --show-mmap-events | cat
+		return 1
+	fi
+
+	echo OK
+	return 0
+}
+
+test_packet_filter()
+{
+	echo "--- Test with MTC and TSC disabled ---"
+	# Disable MTC and TSC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/mtc=0,tsc=0/u uname
+	# Should not get MTC packet
+	mtc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "MTC 0x")
+	if [ "${mtc_cnt}" -ne 0 ] ; then
+		echo "Failed to filter with mtc=0"
+		return 1
+	fi
+	# Should not get TSC package
+	tsc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TSC 0x")
+	if [ "${tsc_cnt}" -ne 0 ] ; then
+		echo "Failed to filter with tsc=0"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_disable_branch()
+{
+	echo "--- Test with branches disabled ---"
+	# Disable branch
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/branch=0/u uname
+	# Should not get branch related packets
+	tnt_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TNT 0x")
+	tip_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TIP 0x")
+	fup_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "FUP 0x")
+	if [ "${tnt_cnt}" -ne 0 ] || [ "${tip_cnt}" -ne 0 ] || [ "${fup_cnt}" -ne 0 ] ; then
+		echo "Failed to disable branches"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_time_cyc()
+{
+	echo "--- Test with/without CYC ---"
+	# Check if CYC is supported
+	cyc=$(cat /sys/bus/event_source/devices/intel_pt/caps/psb_cyc)
+	if [ "${cyc}" != "1" ] ; then
+		echo "SKIP: CYC is not supported"
+		return 2
+	fi
+	# Enable CYC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/cyc/u uname
+	# should get CYC packets
+	cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x")
+	if [ "${cyc_cnt}" = "0" ] ; then
+		echo "Failed to get CYC packet"
+		return 1
+	fi
+	# Without CYC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u uname
+	# Should not get CYC packets
+	cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x")
+	if [ "${cyc_cnt}" -gt 0 ] ; then
+		echo "Still get CYC packet without cyc"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_sample()
+{
+	echo "--- Test recording with sample mode ---"
+	# Check if recording with sample mode is working
+	if ! perf_record_no_decode -o "${perfdatafile}" --aux-sample=8192 -e '{intel_pt//u,branch-misses:u}' uname ; then
+		echo "perf record failed with --aux-sample"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_kernel_trace()
+{
+	echo "--- Test with kernel trace ---"
+	# Check if recording with kernel trace is working
+	can_kernel || return 2
+	if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt//k -m1,128 uname ; then
+		echo "perf record failed with intel_pt//k"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_virtual_lbr()
+{
+	echo "--- Test virtual LBR ---"
+	# Check if python script is supported
+	libpython=$(perf version --build-options | grep python | grep -cv OFF)
+	if [ "${libpython}" != "1" ] ; then
+		echo "SKIP: python scripting is not supported"
+		return 2
+	fi
+
+	# Python script to determine the maximum size of branch stacks
+	cat << "_end_of_file_" > "${maxbrstack}"
+from __future__ import print_function
+
+bmax = 0
+
+def process_event(param_dict):
+	if "brstack" in param_dict:
+		brstack = param_dict["brstack"]
+		n = len(brstack)
+		global bmax
+		if n > bmax:
+			bmax = n
+
+def trace_end():
+	print("max brstack", bmax)
+_end_of_file_
+
+	# Check if virtual lbr is working
+	perf_record_no_bpf -o "${perfdatafile}" --aux-sample -e '{intel_pt//,cycles}:u' uname
+	times_val=$(perf script -i "${perfdatafile}" --itrace=L -s "${maxbrstack}" 2>/dev/null | grep "max brstack " | cut -d " " -f 3)
+	case "${times_val}" in
+		[0-9]*)	;;
+		*)	times_val=0;;
+	esac
+	if [ "${times_val}" -lt 2 ] ; then
+		echo "Failed with virtual lbr"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_power_event()
+{
+	echo "--- Test power events ---"
+	# Check if power events are supported
+	power_event=$(cat /sys/bus/event_source/devices/intel_pt/caps/power_event_trace)
+	if [ "${power_event}" != "1" ] ; then
+		echo "SKIP: power_event_trace is not supported"
+		return 2
+	fi
+	if ! perf_record_no_decode -o "${perfdatafile}" -a -e intel_pt/pwr_evt/u uname ; then
+		echo "perf record failed with pwr_evt"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_no_tnt()
+{
+	echo "--- Test with TNT packets disabled  ---"
+	# Check if TNT disable is supported
+	notnt=$(cat /sys/bus/event_source/devices/intel_pt/caps/tnt_disable)
+	if [ "${notnt}" != "1" ] ; then
+		echo "SKIP: tnt_disable is not supported"
+		return 2
+	fi
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/notnt/u uname
+	# Should be no TNT packets
+	tnt_cnt=$(perf script -i "${perfdatafile}" -D | grep -c TNT)
+	if [ "${tnt_cnt}" -ne 0 ] ; then
+		echo "TNT packets still there after notnt"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_event_trace()
+{
+	echo "--- Test with event_trace ---"
+	# Check if event_trace is supported
+	event_trace=$(cat /sys/bus/event_source/devices/intel_pt/caps/event_trace)
+	if [ "${event_trace}" != 1 ] ; then
+		echo "SKIP: event_trace is not supported"
+		return 2
+	fi
+	if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/event/u uname ; then
+		echo "perf record failed with event trace"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+count_result()
+{
+	if [ "$1" -eq 2 ] ; then
+		skip_cnt=$((skip_cnt + 1))
+		return
+	fi
+	if [ "$1" -eq 0 ] ; then
+		ok_cnt=$((ok_cnt + 1))
+		return
+	fi
+	err_cnt=$((err_cnt + 1))
+}
+
+ret=0
+test_system_wide_side_band		|| ret=$? ; count_result $ret ; ret=0
+test_per_thread "" ""			|| ret=$? ; count_result $ret ; ret=0
+test_per_thread "k" "(incl. kernel) "	|| ret=$? ; count_result $ret ; ret=0
+test_jitdump				|| ret=$? ; count_result $ret ; ret=0
+test_packet_filter			|| ret=$? ; count_result $ret ; ret=0
+test_disable_branch			|| ret=$? ; count_result $ret ; ret=0
+test_time_cyc				|| ret=$? ; count_result $ret ; ret=0
+test_sample				|| ret=$? ; count_result $ret ; ret=0
+test_kernel_trace			|| ret=$? ; count_result $ret ; ret=0
+test_virtual_lbr			|| ret=$? ; count_result $ret ; ret=0
+test_power_event			|| ret=$? ; count_result $ret ; ret=0
+test_no_tnt				|| ret=$? ; count_result $ret ; ret=0
+test_event_trace			|| ret=$? ; count_result $ret ; ret=0
+
+cleanup
+
+echo "--- Done ---"
+
+if [ ${err_cnt} -gt 0 ] ; then
+	exit 1
+fi
+
+if [ ${ok_cnt} -gt 0 ] ; then
+	exit 0
+fi
+
+exit 2
diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh
new file mode 100755
index 000000000..f22122580
--- /dev/null
+++ b/tools/perf/tests/shell/test_java_symbol.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+# Test java symbol
+
+# SPDX-License-Identifier: GPL-2.0
+# Leo Yan <leo.yan@linaro.org>, 2022
+
+# skip if there's no jshell
+if ! [ -x "$(command -v jshell)" ]; then
+	echo "skip: no jshell, install JDK"
+	exit 2
+fi
+
+PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+PERF_INJ_DATA=$(mktemp /tmp/__perf_test.perf.data.inj.XXXXX)
+
+cleanup_files()
+{
+	echo "Cleaning up files..."
+	rm -f ${PERF_DATA}
+	rm -f ${PERF_INJ_DATA}
+}
+
+trap cleanup_files exit term int
+
+if [ -e "$PWD/tools/perf/libperf-jvmti.so" ]; then
+	LIBJVMTI=$PWD/tools/perf/libperf-jvmti.so
+elif [ -e "$PWD/libperf-jvmti.so" ]; then
+	LIBJVMTI=$PWD/libperf-jvmti.so
+elif [ -e "$PREFIX/lib64/libperf-jvmti.so" ]; then
+	LIBJVMTI=$PREFIX/lib64/libperf-jvmti.so
+elif [ -e "$PREFIX/lib/libperf-jvmti.so" ]; then
+	LIBJVMTI=$PREFIX/lib/libperf-jvmti.so
+elif [ -e "/usr/lib/linux-tools-$(uname -a | awk '{ print $3 }' | sed -r 's/-generic//')/libperf-jvmti.so" ]; then
+	LIBJVMTI=/usr/lib/linux-tools-$(uname -a | awk '{ print $3 }' | sed -r 's/-generic//')/libperf-jvmti.so
+else
+	echo "Fail to find libperf-jvmti.so"
+	# JVMTI is a build option, skip the test if fail to find lib
+	exit 2
+fi
+
+cat <<EOF | perf record -k 1 -o $PERF_DATA jshell -s -J-agentpath:$LIBJVMTI
+int fib(int x) {
+	return x > 1 ? fib(x - 2) + fib(x - 1) : 1;
+}
+
+int q = 0;
+
+for (int i = 0; i < 10; i++)
+	q += fib(i);
+
+System.out.println(q);
+EOF
+
+if [ $? -ne 0 ]; then
+	echo "Fail to record for java program"
+	exit 1
+fi
+
+if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then
+	echo "Fail to inject samples"
+	exit 1
+fi
+
+# Below is an example of the instruction samples reporting:
+#   8.18%  jshell           jitted-50116-29.so    [.] Interpreter
+#   0.75%  Thread-1         jitted-83602-1670.so  [.] jdk.internal.jimage.BasicImageReader.getString(int)
+perf report --stdio -i ${PERF_INJ_DATA} 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+% .* (Interpreter|jdk\.internal).*" > /dev/null 2>&1
+
+if [ $? -ne 0 ]; then
+	echo "Fail to find java symbols"
+	exit 1
+fi
+
+exit 0
diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh
new file mode 100644
index 000000000..319f36ebb
--- /dev/null
+++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh
@@ -0,0 +1,83 @@
+#!/bin/bash
+# test perf probe of function from different CU
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# skip if there's no gcc
+if ! [ -x "$(command -v gcc)" ]; then
+        echo "failed: no gcc compiler"
+        exit 2
+fi
+
+temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX)
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then
+		echo "--- Cleaning up ---"
+		perf probe -x ${temp_dir}/testfile -d foo || true
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+        cleanup
+        exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+cat > ${temp_dir}/testfile-foo.h << EOF
+struct t
+{
+  int *p;
+  int c;
+};
+
+extern int foo (int i, struct t *t);
+EOF
+
+cat > ${temp_dir}/testfile-foo.c << EOF
+#include "testfile-foo.h"
+
+int
+foo (int i, struct t *t)
+{
+  int j, res = 0;
+  for (j = 0; j < i && j < t->c; j++)
+    res += t->p[j];
+
+  return res;
+}
+EOF
+
+cat > ${temp_dir}/testfile-main.c << EOF
+#include "testfile-foo.h"
+
+static struct t g;
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  int j[argc];
+  g.c = argc;
+  g.p = j;
+  for (i = 0; i < argc; i++)
+    j[i] = (int) argv[i][0];
+  return foo (3, &g);
+}
+EOF
+
+gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o
+gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o
+gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o
+
+perf probe -x ${temp_dir}/testfile --funcs foo
+perf probe -x ${temp_dir}/testfile foo
+
+cleanup
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
new file mode 100755
index 000000000..3d60e993d
--- /dev/null
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -0,0 +1,43 @@
+#!/bin/sh
+# Check open filename arg using perf trace + vfs_getname
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf trace' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname was used by 'perf trace',
+# that already handles "probe:vfs_getname" if present, and used in the
+# "open" syscall "filename" argument beautifier.
+
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+skip_if_no_perf_trace || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+trace_open_vfs_getname() {
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	perf trace -e $evts touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+}
+
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+	exit $err
+fi
+
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+# Do not use whatever ~/.perfconfig file, it may change the output
+# via trace.{show_timestamp,show_prefix,etc}
+export PERF_CONFIG=/dev/null
+
+trace_open_vfs_getname
+err=$?
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err