Merge tag 'perf-tools-for-v7.0-1-2026-02-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Introduce 'perf sched stats' tool with record/report/diff workflows
   using schedstat counters

 - Add a faster libdw based addr2line implementation and allow selecting
   it or its alternatives via 'perf config addr2line.style='

 - Data-type profiling fixes and improvements including the ability to
   select fields using 'perf report''s -F/-fields, e.g.:

     'perf report --fields overhead,type'

 - Add 'perf test' regression tests for Data-type profiling with C and
   Rust workloads

 - Fix srcline printing with inlines in callchains, make sure this has
   coverage in 'perf test'

 - Fix printing of leaf IP in LBR callchains

 - Fix display of metrics without sufficient permission in 'perf stat'

 - Print all machines in 'perf kvm report -vvv', not just the host

 - Switch from SHA-1 to BLAKE2s for build ID generation, remove SHA-1
   code

 - Fix 'perf report's histogram entry collapsing with '-F' option

 - Use system's cacheline size instead of a hardcoded value in 'perf
   report'

 - Allow filtering conversion by time range in 'perf data'

 - Cover conversion to CTF using 'perf data' in 'perf test'

 - Address newer glibc const-correctness (-Werror=discarded-qualifiers)
   issues

 - Fixes and improvements for ARM's CoreSight support, simplify ARM SPE
   event config in 'perf mem', update docs for 'perf c2c' including the
   ARM events it can be used with

 - Build support for generating metrics from arch specific python
   script, add extra AMD, Intel, ARM64 metrics using it

 - Add AMD Zen 6 events and metrics

 - Add JSON file with OpenHW Risc-V CVA6 hardware counters

 - Add 'perf kvm' stats live testing

 - Add more 'perf stat' tests to 'perf test'

 - Fix segfault in `perf lock contention -b/--use-bpf`

 - Fix various 'perf test' cases for s390

 - Build system cleanups, bump minimum shellcheck version to 0.7.2

 - Support building the capstone based annotation routines as a plugin

 - Allow passing extra Clang flags via EXTRA_BPF_FLAGS

* tag 'perf-tools-for-v7.0-1-2026-02-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (255 commits)
  perf test script: Add python script testing support
  perf test script: Add perl script testing support
  perf script: Allow the generated script to be a path
  perf test: perf data --to-ctf testing
  perf test: Test pipe mode with data conversion --to-json
  perf json: Pipe mode --to-ctf support
  perf json: Pipe mode --to-json support
  perf check: Add libbabeltrace to the listed features
  perf build: Allow passing extra Clang flags via EXTRA_BPF_FLAGS
  perf test data_type_profiling.sh: Skip just the Rust tests if code_with_type workload is missing
  tools build: Fix feature test for rust compiler
  perf libunwind: Fix calls to thread__e_machine()
  perf stat: Add no-affinity flag
  perf evlist: Reduce affinity use and move into iterator, fix no affinity
  perf evlist: Missing TPEBS close in evlist__close()
  perf evlist: Special map propagation for tool events that read on 1 CPU
  perf stat-shadow: In prepare_metric fix guard on reading NULL perf_stat_evsel
  Revert "perf tool_pmu: More accurately set the cpus for tool events"
  tools build: Emit dependencies file for test-rust.bin
  tools build: Make test-rust.bin be removed by the 'clean' target
  ...

tools/perf/tests/builtin-test.c

@@ -153,6 +153,11 @@ static struct test_workload *workloads[] = {
 	&workload__datasym,
 	&workload__landlock,
 	&workload__traploop,
+	&workload__inlineloop,
+
+#ifdef HAVE_RUST_SUPPORT
+	&workload__code_with_type,
+#endif
 };
 
 #define workloads__for_each(workload) \

tools/perf/tests/dlfilter-test.c

@@ -30,7 +30,6 @@
 #include "symbol.h"
 #include "synthetic-events.h"
 #include "util.h"
-#include "archinsn.h"
 #include "dlfilter.h"
 #include "tests.h"
 #include "util/sample.h"

tools/perf/tests/kallsyms-split.c

@@ -148,6 +148,7 @@ static int test__kallsyms_split(struct test_suite *test __maybe_unused,
 	ret = TEST_OK;
 
 out:
+	map__put(map);
 	remove_proc_dir(0);
 	machine__exit(&m);
 	return ret;

tools/perf/tests/make

@@ -70,6 +70,7 @@ make_python_perf_so := $(python_perf_so)
 make_debug          := DEBUG=1
 make_nondistro      := BUILD_NONDISTRO=1
 make_extra_tests    := EXTRA_TESTS=1
+make_no_jevents     := NO_JEVENTS=1
 make_jevents_all    := JEVENTS_ARCH=all
 make_no_bpf_skel    := BUILD_BPF_SKEL=0
 make_gen_vmlinux_h  := GEN_VMLINUX_H=1
@@ -83,9 +84,9 @@ make_no_demangle    := NO_DEMANGLE=1
 make_no_libelf      := NO_LIBELF=1
 make_no_libdw       := NO_LIBDW=1
 make_libunwind      := LIBUNWIND=1
-make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1
 make_no_backtrace   := NO_BACKTRACE=1
 make_no_libcapstone := NO_CAPSTONE=1
+make_libcapstone_dlopen := LIBCAPSTONE_DLOPEN=1
 make_no_libnuma     := NO_LIBNUMA=1
 make_no_libbionic   := NO_LIBBIONIC=1
 make_no_libbpf	    := NO_LIBBPF=1
@@ -120,9 +121,12 @@ make_static         := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX3
 make_minimal        := NO_LIBPYTHON=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBBIONIC=1 NO_LIBDW=1
-make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_LIBBPF=1
+make_minimal        += NO_LIBBPF=1
 make_minimal        += NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1
-make_minimal        += NO_LIBCAP=1 NO_CAPSTONE=1
+make_minimal        += NO_CAPSTONE=1
+
+# binutils 2_42 and newer have bfd_thread_init()
+new_libbfd := $(shell echo '#include <bfd.h>' | $(CC) -E -x c - | grep bfd_thread_init)
 
 # $(run) contains all available tests
 run := make_pure
@@ -137,8 +141,11 @@ MAKE_F := $(MAKE) -f $(MK)
 endif
 run += make_python_perf_so
 run += make_debug
+ifneq ($(new_libbfd),)
 run += make_nondistro
+endif
 run += make_extra_tests
+run += make_no_jevents
 run += make_jevents_all
 run += make_no_bpf_skel
 run += make_gen_vmlinux_h
@@ -155,6 +162,7 @@ run += make_libunwind
 run += make_no_libdw_dwarf_unwind
 run += make_no_backtrace
 run += make_no_libcapstone
+run += make_libcapstone_dlopen
 run += make_no_libnuma
 run += make_no_libbionic
 run += make_no_libbpf

tools/perf/tests/parse-events.c

@@ -2609,8 +2609,8 @@ static int test_events(const struct evlist_test *events, int cnt)
 	for (int i = 0; i < cnt; i++) {
 		struct evlist_test e = events[i];
 		int test_ret;
-		const char *pos = e.name;
-		char buf[1024], *buf_pos = buf, *end;
+		const char *pos = e.name, *end;
+		char buf[1024], *buf_pos = buf;
 
 		while ((end = strstr(pos, "default_core"))) {
 			size_t len = end - pos;
@@ -2627,7 +2627,7 @@ static int test_events(const struct evlist_test *events, int cnt)
 		pr_debug("running test %d '%s'\n", i, e.name);
 		test_ret = test_event(&e);
 		if (test_ret != TEST_OK) {
-			pr_debug("Event test failure: test %d '%s'", i, e.name);
+			pr_debug("Event test failure: test %d '%s'\n", i, e.name);
 			ret = combine_test_results(ret, test_ret);
 		}
 	}
@@ -2764,7 +2764,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 
 			test_ret = test_event(&e);
 			if (test_ret != TEST_OK) {
-				pr_debug("Test PMU event failed for '%s'", name);
+				pr_debug("Test PMU event failed for '%s'\n", name);
 				ret = combine_test_results(ret, test_ret);
 			}
 
@@ -2790,7 +2790,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 			e.check = test__checkevent_pmu_events_mix;
 			test_ret = test_event(&e);
 			if (test_ret != TEST_OK) {
-				pr_debug("Test PMU event failed for '%s'", name);
+				pr_debug("Test PMU event failed for '%s'\n", name);
 				ret = combine_test_results(ret, test_ret);
 			}
 		}

tools/perf/tests/parse-metric.c

@@ -41,6 +41,8 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals)
 		count = find_value(evsel->name, vals);
 		evsel->supported = true;
 		evsel->stats->aggr->counts.val = count;
+		evsel->stats->aggr->counts.ena = 1;
+		evsel->stats->aggr->counts.run = 1;
 	}
 }
 

tools/perf/tests/pmu.c

@@ -192,7 +192,6 @@ static int test__pmu_format(struct test_suite *test __maybe_unused, int subtest
 	}
 	if (attr.config2 != 0x0400000020041d07) {
 		pr_err("Unexpected config2 value %llx\n", attr.config2);
-		goto err_out;
 	}
 
 	ret = TEST_OK;
@@ -202,6 +201,97 @@ err_out:
 	return ret;
 }
 
+static int test__pmu_usr_chgs(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	const char *event = "perf-pmu-test/config=15,config1=4,krava02=170,"
+			    "krava03=1,krava11=27,krava12=1/";
+	struct parse_events_terms terms;
+	struct parse_events_error err;
+	LIST_HEAD(config_terms);
+	struct evlist *evlist;
+	struct perf_pmu *pmu;
+	struct evsel *evsel;
+	int ret = TEST_FAIL;
+	char dir[PATH_MAX];
+	u64 val;
+
+	pmu = test_pmu_get(dir, sizeof(dir));
+	if (!pmu)
+		return TEST_FAIL;
+
+	evlist = evlist__new();
+	if (evlist == NULL) {
+		pr_err("Failed allocation");
+		goto err_out;
+	}
+
+	parse_events_terms__init(&terms);
+	ret = parse_events(evlist, event, &err);
+	if (ret) {
+		pr_debug("failed to parse event '%s', err %d\n", event, ret);
+		parse_events_error__print(&err, event);
+		if (parse_events_error__contains(&err, "can't access trace events"))
+			ret = TEST_SKIP;
+		goto err_out;
+	}
+	evsel = evlist__first(evlist);
+
+	/*
+	 * Set via config=15, krava01 bits 0-1
+	 * Set via config1=4, krava11 bit 1
+	 * Set values: krava02=170, krava03=1, krava11=27, krava12=1
+	 *
+	 * Test that already set values aren't overwritten.
+	 */
+	evsel__set_config_if_unset(evsel, "krava01", 16);
+	evsel__get_config_val(evsel, "krava01", &val);
+	TEST_ASSERT_EQUAL("krava01 overwritten", (int) val, (15 & 0b11));
+
+	evsel__set_config_if_unset(evsel, "krava11", 45);
+	evsel__get_config_val(evsel, "krava11", &val);
+	TEST_ASSERT_EQUAL("krava11 overwritten", (int) val, (27 | (4 << 1)));
+
+	evsel__set_config_if_unset(evsel, "krava02", 32);
+	evsel__get_config_val(evsel, "krava02", &val);
+	TEST_ASSERT_EQUAL("krava02 overwritten", (int) val, 170);
+
+	evsel__set_config_if_unset(evsel, "krava03", 0);
+	evsel__get_config_val(evsel, "krava03", &val);
+	TEST_ASSERT_EQUAL("krava03 overwritten", (int) val, 1);
+
+	/*
+	 * krava13 doesn't have any bits set by either krava13= or config1=
+	 * but setting _any_ raw value for config1 implies that krava13
+	 * shouldn't be overwritten. So it's value should remain as 0.
+	 */
+	evsel__set_config_if_unset(evsel, "krava13", 5);
+	evsel__get_config_val(evsel, "krava13", &val);
+	TEST_ASSERT_EQUAL("krava13 overwritten", (int) val, 0);
+
+	/*
+	 * Unset values: krava21, krava22, krava23
+	 *
+	 * Test that unset values are overwritten.
+	 */
+	evsel__set_config_if_unset(evsel, "krava21", 13905);
+	evsel__get_config_val(evsel, "krava21", &val);
+	TEST_ASSERT_EQUAL("krava21 not overwritten", (int) val, 13905);
+
+	evsel__set_config_if_unset(evsel, "krava22", 11);
+	evsel__get_config_val(evsel, "krava22", &val);
+	TEST_ASSERT_EQUAL("krava22 not overwritten", (int) val, 11);
+
+	evsel__set_config_if_unset(evsel, "krava23", 0);
+	evsel__get_config_val(evsel, "krava23", &val);
+	TEST_ASSERT_EQUAL("krava23 not overwritten", (int) val, 0);
+	ret = TEST_OK;
+err_out:
+	parse_events_terms__exit(&terms);
+	evlist__delete(evlist);
+	test_pmu_put(dir, pmu);
+	return ret;
+}
+
 static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char dir[PATH_MAX];
@@ -539,6 +629,7 @@ static struct test_case tests__pmu[] = {
 	TEST_CASE("PMU name combining", name_len),
 	TEST_CASE("PMU name comparison", name_cmp),
 	TEST_CASE("PMU cmdline match", pmu_match),
+	TEST_CASE("PMU user config changes", pmu_usr_chgs),
 	{	.name = NULL, }
 };
 

tools/perf/tests/shell/addr2line_inlines.sh

@@ -0,0 +1,96 @@
+#!/bin/bash
+# test addr2line inline unwinding
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+test_dir=$(mktemp -d /tmp/perf-test-inline-addr2line.XXXXXXXXXX)
+perf_data="${test_dir}/perf.data"
+perf_script_txt="${test_dir}/perf_script.txt"
+
+cleanup() {
+    rm -rf "${test_dir}"
+    trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+    echo "Unexpected signal in ${FUNCNAME[1]}"
+    cleanup
+    exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+test_fp() {
+    echo "Inline unwinding fp verification test"
+    # Record data. Currently only dwarf callchains support inlined functions.
+    perf record --call-graph fp -e task-clock:u -o "${perf_data}" -- perf test -w inlineloop 1
+
+    # Check output with inline (default) and srcline
+    perf script -i "${perf_data}" --fields +srcline > "${perf_script_txt}"
+
+    # Expect the leaf and middle functions to occur on lines in the 20s, with
+    # the non-inlined parent function on a line in the 30s.
+    if grep -q "inlineloop.c:2. (inlined)" "${perf_script_txt}" &&
+       grep -q "inlineloop.c:3.$" "${perf_script_txt}"
+    then
+        echo "Inline unwinding fp verification test [Success]"
+    else
+        echo "Inline unwinding fp verification test [Failed missing inlined functions]"
+        err=1
+    fi
+}
+
+test_dwarf() {
+    echo "Inline unwinding dwarf verification test"
+    # Record data. Currently only dwarf callchains support inlined functions.
+    perf record --call-graph dwarf -e task-clock:u -o "${perf_data}" -- perf test -w inlineloop 1
+
+    # Check output with inline (default) and srcline
+    perf script -i "${perf_data}" --fields +srcline > "${perf_script_txt}"
+
+    # Expect the leaf and middle functions to occur on lines in the 20s, with
+    # the non-inlined parent function on a line in the 30s.
+    if grep -q "inlineloop.c:2. (inlined)" "${perf_script_txt}" &&
+       grep -q "inlineloop.c:3.$" "${perf_script_txt}"
+    then
+        echo "Inline unwinding dwarf verification test [Success]"
+    else
+        echo "Inline unwinding dwarf verification test [Failed missing inlined functions]"
+        err=1
+    fi
+}
+
+test_lbr() {
+    echo "Inline unwinding LBR verification test"
+    if [ ! -f /sys/bus/event_source/devices/cpu/caps/branches ] &&
+       [ ! -f /sys/bus/event_source/devices/cpu_core/caps/branches ]
+    then
+        echo "Skip: only x86 CPUs support LBR"
+        return
+    fi
+
+    # Record data. Currently only dwarf callchains support inlined functions.
+    perf record --call-graph lbr -e cycles:u -o "${perf_data}" -- perf test -w inlineloop 1
+
+    # Check output with inline (default) and srcline
+    perf script -i "${perf_data}" --fields +srcline > "${perf_script_txt}"
+
+    # Expect the leaf and middle functions to occur on lines in the 20s, with
+    # the non-inlined parent function on a line in the 30s.
+    if grep -q "inlineloop.c:2. (inlined)" "${perf_script_txt}" &&
+       grep -q "inlineloop.c:3.$" "${perf_script_txt}"
+    then
+        echo "Inline unwinding lbr verification test [Success]"
+    else
+        echo "Inline unwinding lbr verification test [Failed missing inlined functions]"
+        err=1
+    fi
+}
+
+test_fp
+test_dwarf
+test_lbr
+
+cleanup
+exit $err

tools/perf/tests/shell/data_type_profiling.sh

@@ -0,0 +1,89 @@
+#!/bin/bash
+# perf data type profiling tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# The logic below follows the same line as the annotate test, but looks for a
+# data type profiling manifestation
+
+# Values in testtypes and testprogs should match
+testtypes=("# data-type: struct Buf" "# data-type: struct _buf")
+testprogs=("perf test -w code_with_type" "perf test -w datasym")
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfout=$(mktemp /tmp/__perf_test.perf.out.XXXXX)
+
+cleanup() {
+  rm -rf "${perfdata}" "${perfout}"
+  rm -rf "${perfdata}".old
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+test_basic_annotate() {
+  mode=$1
+  runtime=$2
+
+  echo "${mode} ${runtime} perf annotate test"
+
+  case "x${runtime}" in
+    "xRust")
+    if ! perf check feature -q rust
+    then
+      echo "Skip: code_with_type workload not built in 'perf test'"
+      return
+    fi
+    index=0 ;;
+
+    "xC")
+    index=1 ;;
+  esac
+
+  if [ "x${mode}" == "xBasic" ]
+  then
+    perf mem record -o "${perfdata}" ${testprogs[$index]} 2> /dev/null
+  else
+    perf mem record -o - ${testprogs[$index]} 2> /dev/null > "${perfdata}"
+  fi
+  if [ "x$?" != "x0" ]
+  then
+    echo "${mode} annotate [Failed: perf record]"
+    err=1
+    return
+  fi
+
+  # Generate the annotated output file
+  if [ "x${mode}" == "xBasic" ]
+  then
+    perf annotate --code-with-type -i "${perfdata}" --stdio --percent-limit 1 2> /dev/null > "${perfout}"
+  else
+    perf annotate --code-with-type -i - --stdio 2> /dev/null --percent-limit 1 < "${perfdata}" > "${perfout}"
+  fi
+
+  # check if it has the target data type
+  if ! grep -q "${testtypes[$index]}" "${perfout}"
+  then
+    echo "${mode} annotate [Failed: missing target data type]"
+    cat "${perfout}"
+    err=1
+    return
+  fi
+  echo "${mode} annotate test [Success]"
+}
+
+test_basic_annotate Basic Rust
+test_basic_annotate Pipe Rust
+test_basic_annotate Basic C
+test_basic_annotate Pipe C
+
+cleanup
+exit $err

tools/perf/tests/shell/evlist.sh

@@ -21,13 +21,13 @@ trap trap_cleanup EXIT TERM INT
 
 test_evlist_simple() {
 	echo "Simple evlist test"
-	if ! perf record -e cycles -o "${perfdata}" true 2> /dev/null
+	if ! perf record -e cpu-clock -o "${perfdata}" true 2> /dev/null
 	then
 		echo "Simple evlist [Failed record]"
 		err=1
 		return
 	fi
-	if ! perf evlist -i "${perfdata}" | grep -q "cycles"
+	if ! perf evlist -i "${perfdata}" | grep -q "cpu-clock"
 	then
 		echo "Simple evlist [Failed to list event]"
 		err=1
@@ -38,13 +38,14 @@ test_evlist_simple() {
 
 test_evlist_group() {
 	echo "Group evlist test"
-	if ! perf record -e "{cycles,instructions}" -o "${perfdata}" true 2> /dev/null
+	if ! perf record -e "{cpu-clock,task-clock}" -o "${perfdata}" \
+		-- perf test -w noploop 2> /dev/null
 	then
 		echo "Group evlist [Skipped event group recording failed]"
 		return
 	fi
 
-	if ! perf evlist -i "${perfdata}" -g | grep -q "{.*cycles.*,.*instructions.*}"
+	if ! perf evlist -i "${perfdata}" -g | grep -q "{.*cpu-clock.*,.*task-clock.*}"
 	then
 		echo "Group evlist [Failed to list event group]"
 		err=1

tools/perf/tests/shell/inject-callchain.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+# perf inject to convert DWARF callchains to regular ones
+# SPDX-License-Identifier: GPL-2.0
+
+if ! perf check feature -q dwarf; then
+    echo "SKIP: DWARF support is not available"
+    exit 2
+fi
+
+TESTDATA=$(mktemp /tmp/perf-test.XXXXXX)
+
+err=0
+
+cleanup()
+{
+    trap - EXIT TERM INT
+    rm -f ${TESTDATA}*
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+echo "recording data with DWARF callchain"
+perf record -F 999 --call-graph dwarf -o "${TESTDATA}" -- perf test -w noploop
+
+echo "convert DWARF callchain using perf inject"
+perf inject -i "${TESTDATA}" --convert-callchain -o "${TESTDATA}.new"
+
+perf report -i "${TESTDATA}" --no-children -q --percent-limit=1 > ${TESTDATA}.out
+perf report -i "${TESTDATA}.new" --no-children -q --percent-limit=1 > ${TESTDATA}.new.out
+
+echo "compare the both result excluding inlined functions"
+if diff -u "${TESTDATA}.out" "${TESTDATA}.new.out" | grep "^- " | grep -qv "(inlined)"; then
+    echo "Found some differences"
+    diff -u "${TESTDATA}.out" "${TESTDATA}.new.out"
+    err=1
+fi
+
+cleanup
+exit $err

tools/perf/tests/shell/kvm.sh

@@ -7,9 +7,10 @@ set -e
 err=0
 perfdata=$(mktemp /tmp/__perf_kvm_test.perf.data.XXXXX)
 qemu_pid_file=$(mktemp /tmp/__perf_kvm_test.qemu.pid.XXXXX)
+log_file=$(mktemp /tmp/__perf_kvm_test.live_log.XXXXX)
 
 cleanup() {
-	rm -f "${perfdata}"
+	rm -f "${perfdata}" "${log_file}"
 	if [ -f "${qemu_pid_file}" ]; then
 		if [ -s "${qemu_pid_file}" ]; then
 			qemu_pid=$(cat "${qemu_pid_file}")
@@ -96,6 +97,32 @@ test_kvm_buildid_list() {
 	echo "perf kvm buildid-list test [Success]"
 }
 
+test_kvm_stat_live() {
+	echo "Testing perf kvm stat live"
+
+        # Run perf kvm live for 5 seconds, monitoring that PID
+	# Use sleep to keep stdin open but silent, preventing EOF loop or interactive spam
+	if ! sleep 10 | timeout 5s perf kvm stat live -p "${qemu_pid}" > "${log_file}" 2>&1; then
+		retval=$?
+		if [ $retval -ne 124 ] && [ $retval -ne 0 ]; then
+			echo "perf kvm stat live [Failed: perf kvm stat live failed to start or run (ret=$retval)]"
+			head -n 50 "${log_file}"
+			err=1
+			return
+		fi
+	fi
+
+	# Check for some sample data (percentage)
+	if ! grep -E -q "[0-9]+\.[0-9]+%" "${log_file}"; then
+		echo "perf kvm stat live [Failed: no sample percentage found]"
+		head -n 50 "${log_file}"
+		err=1
+		return
+	fi
+
+	echo "perf kvm stat live test [Success]"
+}
+
 setup_qemu() {
 	# Find qemu
 	if [ "$(uname -m)" = "x86_64" ]; then
@@ -148,6 +175,7 @@ if [ $err -eq 0 ]; then
 	test_kvm_stat
 	test_kvm_record_report
 	test_kvm_buildid_list
+	test_kvm_stat_live
 fi
 
 cleanup

tools/perf/tests/shell/perf_sched_stats.sh

@@ -0,0 +1,64 @@
+#!/bin/sh
+# perf sched stats tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+test_perf_sched_stats_record() {
+  echo "Basic perf sched stats record test"
+  if ! perf sched stats record true 2>&1 | \
+    grep -E -q "[ perf sched stats: Wrote samples to perf.data ]"
+  then
+    echo "Basic perf sched stats record test [Failed]"
+    err=1
+    return
+  fi
+  echo "Basic perf sched stats record test [Success]"
+}
+
+test_perf_sched_stats_report() {
+  echo "Basic perf sched stats report test"
+  perf sched stats record true > /dev/null
+  if ! perf sched stats report 2>&1 | grep -E -q "Description"
+  then
+    echo "Basic perf sched stats report test [Failed]"
+    err=1
+    rm perf.data
+    return
+  fi
+  rm perf.data
+  echo "Basic perf sched stats report test [Success]"
+}
+
+test_perf_sched_stats_live() {
+  echo "Basic perf sched stats live mode test"
+  if ! perf sched stats true 2>&1 | grep -E -q "Description"
+  then
+    echo "Basic perf sched stats live mode test [Failed]"
+    err=1
+    return
+  fi
+  echo "Basic perf sched stats live mode test [Success]"
+}
+
+test_perf_sched_stats_diff() {
+  echo "Basic perf sched stats diff test"
+  perf sched stats record true > /dev/null
+  perf sched stats record true > /dev/null
+  if ! perf sched stats diff > /dev/null
+  then
+    echo "Basic perf sched stats diff test [Failed]"
+    err=1
+    rm perf.data.old perf.data
+    return
+  fi
+  rm perf.data.old perf.data
+  echo "Basic perf sched stats diff test [Success]"
+}
+
+test_perf_sched_stats_record
+test_perf_sched_stats_report
+test_perf_sched_stats_live
+test_perf_sched_stats_diff
+exit $err

tools/perf/tests/shell/record.sh

@@ -260,7 +260,21 @@ test_uid() {
 
 test_leader_sampling() {
   echo "Basic leader sampling test"
-  if ! perf record -o "${perfdata}" -e "{cycles,cycles}:Su" -- \
+  events="{cycles,cycles}:Su"
+  [ "$(uname -m)" = "s390x" ] && {
+    [ ! -d /sys/devices/cpum_sf ] && {
+      echo "No CPUMF [Skipped record]"
+      return
+    }
+    events="{cpum_sf/SF_CYCLES_BASIC/,cycles}:Su"
+    perf record -o "${perfdata}" -e "$events" -- perf test -w brstack 2> /dev/null
+    # Perf grouping might be unsupported, depends on version.
+    [ "$?" -ne 0 ] && {
+      echo "Grouping not support [Skipped record]"
+      return
+    }
+  }
+  if ! perf record -o "${perfdata}" -e "$events" -- \
     perf test -w brstack 2> /dev/null
   then
     echo "Leader sampling [Failed record]"

tools/perf/tests/shell/sched.sh

@@ -53,7 +53,7 @@ start_noploops() {
 }
 
 cleanup_noploops() {
-  kill "$PID1" "$PID2"
+  kill "$PID1" "$PID2" || true
 }
 
 test_sched_record() {

tools/perf/tests/shell/script_dlfilter.sh

@@ -68,17 +68,17 @@ test_dlfilter() {
 	fi
 
 	# Build the dlfilter
-	if ! cc -c -I tools/perf/include -fpic -x c "${dlfilter_c}" -o "${dlfilter_so}.o"
+	if ! cc -c -I ${shelldir}/../../include -fpic -x c "${dlfilter_c}" -o "${dlfilter_so}.o"
 	then
-		echo "Basic --dlfilter test [Failed to build dlfilter object]"
-		err=1
+		echo "Basic --dlfilter test [Skip - failed to build dlfilter object]"
+		err=2
 		return
 	fi
 
 	if ! cc -shared -o "${dlfilter_so}" "${dlfilter_so}.o"
 	then
-		echo "Basic --dlfilter test [Failed to link dlfilter shared object]"
-		err=1
+		echo "Basic --dlfilter test [Skip - failed to link dlfilter shared object]"
+		err=2
 		return
 	fi
 

tools/perf/tests/shell/script_perl.sh

@@ -0,0 +1,102 @@
+#!/bin/bash
+# perf script perl tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# set PERF_EXEC_PATH to find scripts in the source directory
+perfdir=$(dirname "$0")/../..
+if [ -e "$perfdir/scripts/perl/Perf-Trace-Util" ]; then
+  export PERF_EXEC_PATH=$perfdir
+fi
+
+
+perfdata=$(mktemp /tmp/__perf_test_script_perl.perf.data.XXXXX)
+generated_script=$(mktemp /tmp/__perf_test_script.XXXXX.pl)
+
+cleanup() {
+  rm -f "${perfdata}"
+  rm -f "${generated_script}"
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+trap trap_cleanup TERM INT
+trap cleanup EXIT
+
+check_perl_support() {
+	if perf check feature -q libperl; then
+		return 0
+	fi
+	echo "perf script perl test [Skipped: no libperl support]"
+	return 2
+}
+
+test_script() {
+	local event_name=$1
+	local expected_output=$2
+	local record_opts=$3
+
+	echo "Testing event: $event_name"
+
+	# Try to record. If this fails, it might be permissions or lack of support.
+	# We return 2 to indicate "skip this event" rather than "fail test".
+	if ! perf record -o "${perfdata}" -e "$event_name" $record_opts -- perf test -w thloop > /dev/null 2>&1; then
+		echo "perf script perl test [Skipped: failed to record $event_name]"
+		return 2
+	fi
+
+	echo "Generating perl script..."
+	if ! perf script -i "${perfdata}" -g "${generated_script}"; then
+		echo "perf script perl test [Failed: script generation for $event_name]"
+		return 1
+	fi
+
+	if [ ! -f "${generated_script}" ]; then
+		echo "perf script perl test [Failed: script not generated for $event_name]"
+		return 1
+	fi
+
+	echo "Executing perl script..."
+	output=$(perf script -i "${perfdata}" -s "${generated_script}" 2>&1)
+
+	if echo "$output" | grep -q "$expected_output"; then
+		echo "perf script perl test [Success: $event_name triggered $expected_output]"
+		return 0
+	else
+		echo "perf script perl test [Failed: $event_name did not trigger $expected_output]"
+		echo "Output was:"
+		echo "$output" | head -n 20
+		return 1
+	fi
+}
+
+check_perl_support || exit 2
+
+# Try tracepoint first
+test_script "sched:sched_switch" "sched::sched_switch" "-c 1" && res=0 || res=$?
+
+if [ $res -eq 0 ]; then
+	exit 0
+elif [ $res -eq 1 ]; then
+	exit 1
+fi
+
+# If tracepoint skipped (res=2), try task-clock
+# For generic events like task-clock, the generated script uses process_event()
+# which dumps data using Data::Dumper. We check for "$VAR1" which is standard Dumper output.
+test_script "task-clock" "\$VAR1" "-c 100" && res=0 || res=$?
+
+if [ $res -eq 0 ]; then
+	exit 0
+elif [ $res -eq 1 ]; then
+	exit 1
+fi
+
+# If both skipped
+echo "perf script perl test [Skipped: Could not record tracepoint or task-clock]"
+exit 2

tools/perf/tests/shell/script_python.sh

@@ -0,0 +1,113 @@
+#!/bin/bash
+# perf script python tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# set PERF_EXEC_PATH to find scripts in the source directory
+perfdir=$(dirname "$0")/../..
+if [ -e "$perfdir/scripts/python/Perf-Trace-Util" ]; then
+  export PERF_EXEC_PATH=$perfdir
+fi
+
+
+perfdata=$(mktemp /tmp/__perf_test_script_python.perf.data.XXXXX)
+generated_script=$(mktemp /tmp/__perf_test_script.XXXXX.py)
+
+cleanup() {
+  rm -f "${perfdata}"
+  rm -f "${generated_script}"
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+trap trap_cleanup TERM INT
+trap cleanup EXIT
+
+check_python_support() {
+	if perf check feature -q libpython; then
+		return 0
+	fi
+	echo "perf script python test [Skipped: no libpython support]"
+	return 2
+}
+
+test_script() {
+	local event_name=$1
+	local expected_output=$2
+	local record_opts=$3
+
+	echo "Testing event: $event_name"
+
+	# Try to record. If this fails, it might be permissions or lack of
+	# support. Return 2 to indicate "skip this event" rather than "fail
+	# test".
+	if ! perf record -o "${perfdata}" -e "$event_name" $record_opts -- perf test -w thloop > /dev/null 2>&1; then
+		echo "perf script python test [Skipped: failed to record $event_name]"
+		return 2
+	fi
+
+	echo "Generating python script..."
+	if ! perf script -i "${perfdata}" -g "${generated_script}"; then
+		echo "perf script python test [Failed: script generation for $event_name]"
+		return 1
+	fi
+
+	if [ ! -f "${generated_script}" ]; then
+		echo "perf script python test [Failed: script not generated for $event_name]"
+		return 1
+	fi
+
+	# Perf script -g python doesn't generate process_event for generic
+	# events so append it manually to test that the callback works.
+	if ! grep -q "def process_event" "${generated_script}"; then
+		cat <<EOF >> "${generated_script}"
+
+def process_event(param_dict):
+	print("param_dict: %s" % param_dict)
+EOF
+	fi
+
+	echo "Executing python script..."
+	output=$(perf script -i "${perfdata}" -s "${generated_script}" 2>&1)
+
+	if echo "$output" | grep -q "$expected_output"; then
+		echo "perf script python test [Success: $event_name triggered $expected_output]"
+		return 0
+	else
+		echo "perf script python test [Failed: $event_name did not trigger $expected_output]"
+		echo "Output was:"
+		echo "$output" | head -n 20
+		return 1
+	fi
+}
+
+check_python_support || exit 2
+
+# Try tracepoint first
+test_script "sched:sched_switch" "sched__sched_switch" "-c 1" && res=0 || res=$?
+
+if [ $res -eq 0 ]; then
+	exit 0
+elif [ $res -eq 1 ]; then
+	exit 1
+fi
+
+# If tracepoint skipped (res=2), try task-clock
+# For generic events like task-clock, the generated script uses process_event()
+# which prints the param_dict.
+test_script "task-clock" "param_dict" "-c 100" && res=0 || res=$?
+
+if [ $res -eq 0 ]; then
+	exit 0
+elif [ $res -eq 1 ]; then
+	exit 1
+fi
+
+# If both skipped
+echo "perf script python test [Skipped: Could not record tracepoint or task-clock]"
+exit 2

tools/perf/tests/shell/stat.sh

@@ -5,6 +5,21 @@
 set -e
 
 err=0
+stat_output=$(mktemp /tmp/perf-stat-test-output.XXXXX)
+
+cleanup() {
+  rm -f "${stat_output}"
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
 test_default_stat() {
   echo "Basic stat command test"
   if ! perf stat true 2>&1 | grep -E -q "Performance counter stats for 'true':"
@@ -233,7 +248,7 @@ test_hybrid() {
   fi
 
   # Run default Perf stat
-  cycles_events=$(perf stat -a -- sleep 0.1 2>&1 | grep -E "/cpu-cycles/[uH]*|  cpu-cycles[:uH]*  " -c)
+  cycles_events=$(perf stat -a -- sleep 0.1 2>&1 | grep -E "/cpu-cycles/[uH]*|  cpu-cycles[:uH]*  "  | wc -l)
 
   # The expectation is that default output will have a cycles events on each
   # hybrid PMU. In situations with no cycles PMU events, like virtualized, this
@@ -248,6 +263,226 @@ test_hybrid() {
   echo "hybrid test [Success]"
 }
 
+test_stat_cpu() {
+  echo "stat -C <cpu> test"
+  # Test the full online CPU list (ranges and lists)
+  online_cpus=$(cat /sys/devices/system/cpu/online)
+  if ! perf stat -C "$online_cpus" -a true > "${stat_output}" 2>&1
+  then
+    echo "stat -C <cpu> test [Failed - command failed for cpus $online_cpus]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "Performance counter stats for" "${stat_output}"
+  then
+    echo "stat -C <cpu> test [Failed - missing output for cpus $online_cpus]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  # Test each individual online CPU
+  for cpu_dir in /sys/devices/system/cpu/cpu[0-9]*; do
+    cpu=${cpu_dir##*/cpu}
+    # Check if online
+    if [ -f "$cpu_dir/online" ] && [ "$(cat "$cpu_dir/online")" -eq 0 ]
+    then
+      continue
+    fi
+
+    if ! perf stat -C "$cpu" -a true > "${stat_output}" 2>&1
+    then
+      echo "stat -C <cpu> test [Failed - command failed for cpu $cpu]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+    if ! grep -E -q "Performance counter stats for" "${stat_output}"
+    then
+      echo "stat -C <cpu> test [Failed - missing output for cpu $cpu]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+  done
+
+  # Test synthetic list and range if cpu0 and cpu1 are online
+  c0_online=0
+  c1_online=0
+  if [ -d "/sys/devices/system/cpu/cpu0" ]
+  then
+    if [ ! -f "/sys/devices/system/cpu/cpu0/online" ] || [ "$(cat /sys/devices/system/cpu/cpu0/online)" -eq 1 ]
+    then
+      c0_online=1
+    fi
+  fi
+  if [ -d "/sys/devices/system/cpu/cpu1" ]
+  then
+    if [ ! -f "/sys/devices/system/cpu/cpu1/online" ] || [ "$(cat /sys/devices/system/cpu/cpu1/online)" -eq 1 ]
+    then
+      c1_online=1
+    fi
+  fi
+
+  if [ $c0_online -eq 1 ] && [ $c1_online -eq 1 ]
+  then
+    # Test list "0,1"
+    if ! perf stat -C "0,1" -a true > "${stat_output}" 2>&1
+    then
+      echo "stat -C <cpu> test [Failed - command failed for cpus 0,1]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+    if ! grep -E -q "Performance counter stats for" "${stat_output}"
+    then
+      echo "stat -C <cpu> test [Failed - missing output for cpus 0,1]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+
+    # Test range "0-1"
+    if ! perf stat -C "0-1" -a true > "${stat_output}" 2>&1
+    then
+      echo "stat -C <cpu> test [Failed - command failed for cpus 0-1]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+    if ! grep -E -q "Performance counter stats for" "${stat_output}"
+    then
+      echo "stat -C <cpu> test [Failed - missing output for cpus 0-1]"
+      cat "${stat_output}"
+      err=1
+      return
+    fi
+  fi
+
+  echo "stat -C <cpu> test [Success]"
+}
+
+test_stat_no_aggr() {
+  echo "stat -A test"
+  if ! perf stat -A -a true > "${stat_output}" 2>&1
+  then
+    echo "stat -A test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "CPU" "${stat_output}"
+  then
+    echo "stat -A test [Failed - missing CPU column]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+  echo "stat -A test [Success]"
+}
+
+test_stat_detailed() {
+  echo "stat -d test"
+  if ! perf stat -d true > "${stat_output}" 2>&1
+  then
+    echo "stat -d test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "Performance counter stats" "${stat_output}"
+  then
+    echo "stat -d test [Failed - missing output]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! perf stat -dd true > "${stat_output}" 2>&1
+  then
+    echo "stat -dd test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "Performance counter stats" "${stat_output}"
+  then
+    echo "stat -dd test [Failed - missing output]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! perf stat -ddd true > "${stat_output}" 2>&1
+  then
+    echo "stat -ddd test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "Performance counter stats" "${stat_output}"
+  then
+    echo "stat -ddd test [Failed - missing output]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  echo "stat -d test [Success]"
+}
+
+test_stat_repeat() {
+  echo "stat -r test"
+  if ! perf stat -r 2 true > "${stat_output}" 2>&1
+  then
+    echo "stat -r test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+
+  if ! grep -E -q "\([[:space:]]*\+-.*%[[:space:]]*\)" "${stat_output}"
+  then
+    echo "stat -r test [Failed - missing variance]"
+    cat "${stat_output}"
+    err=1
+    return
+  fi
+  echo "stat -r test [Success]"
+}
+
+test_stat_pid() {
+  echo "stat -p test"
+  sleep 1 &
+  pid=$!
+  if ! perf stat -p $pid > "${stat_output}" 2>&1
+  then
+    echo "stat -p test [Failed - command failed]"
+    cat "${stat_output}"
+    err=1
+    kill $pid 2>/dev/null || true
+    wait $pid 2>/dev/null || true
+    return
+  fi
+
+  if ! grep -E -q "Performance counter stats" "${stat_output}"
+  then
+    echo "stat -p test [Failed - missing output]"
+    cat "${stat_output}"
+    err=1
+  else
+    echo "stat -p test [Success]"
+  fi
+  kill $pid 2>/dev/null || true
+  wait $pid 2>/dev/null || true
+}
+
 test_default_stat
 test_null_stat
 test_offline_cpu_stat
@@ -258,4 +493,11 @@ test_topdown_groups
 test_topdown_weak_groups
 test_cputype
 test_hybrid
+test_stat_cpu
+test_stat_no_aggr
+test_stat_detailed
+test_stat_repeat
+test_stat_pid
+
+cleanup
 exit $err

tools/perf/tests/shell/stat_all_metricgroups.sh

@@ -12,31 +12,32 @@ if ParanoidAndNotRoot 0
 then
   system_wide_flag=""
 fi
-err=0
+
+err=3
+skip=0
 for m in $(perf list --raw-dump metricgroups)
 do
   echo "Testing $m"
   result=$(perf stat -M "$m" $system_wide_flag sleep 0.01 2>&1)
   result_err=$?
-  if [[ $result_err -gt 0 ]]
+  if [[ $result_err -eq 0 ]]
   then
+    if [[ "$err" -ne 1 ]]
+    then
+      err=0
+    fi
+  else
     if [[ "$result" =~ \
           "Access to performance monitoring and observability operations is limited" ]]
     then
       echo "Permission failure"
       echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
+      skip=1
     elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
     then
       echo "Permissions - need system wide mode"
       echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
+      skip=1
     elif [[ "$m" == @(Default2|Default3|Default4) ]]
     then
       echo "Ignoring failures in $m that may contain unsupported legacy events"
@@ -48,4 +49,9 @@ do
   fi
 done
 
+if [[ "$err" -eq 3 && "$skip" -eq 1 ]]
+then
+  err=2
+fi
+
 exit $err

tools/perf/tests/shell/stat_all_metrics.sh

@@ -15,7 +15,8 @@ then
   test_prog="perf test -w noploop"
 fi
 
-err=0
+skip=0
+err=3
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
   result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1)
@@ -23,6 +24,10 @@ for m in $(perf list --raw-dump metrics); do
   if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
     # No error result and metric shown.
+    if [[ "$err" -ne 1 ]]
+    then
+      err=0
+    fi
     continue
   fi
   if [[ "$result" =~ "Cannot resolve IDs for" || "$result" =~ "No supported events found" ]]
@@ -44,7 +49,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
@@ -53,7 +58,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "<not supported>" ]]
@@ -68,7 +73,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "<not counted>" ]]
@@ -77,7 +82,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
@@ -86,7 +91,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "PMM" ]]
@@ -95,7 +100,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   fi
@@ -106,6 +111,10 @@ for m in $(perf list --raw-dump metrics); do
   if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
     # No error result and metric shown.
+    if [[ "$err" -ne 1 ]]
+    then
+      err=0
+    fi
     continue
   fi
   echo "[Failed $m] has non-zero error '$result_err' or not printed in:"
@@ -113,4 +122,10 @@ for m in $(perf list --raw-dump metrics); do
   err=1
 done
 
+# return SKIP only if no success returned
+if [[ "$err" -eq 3 && "$skip" -eq 1 ]]
+then
+  err=2
+fi
+
 exit "$err"

tools/perf/tests/shell/test_arm_coresight.sh

@@ -198,6 +198,58 @@ arm_cs_etm_basic_test() {
 	arm_cs_report "CoreSight basic testing with '$*'" $err
 }
 
+arm_cs_etm_test_cpu_list() {
+	echo "Testing sparse CPU list: $1"
+	perf record -o ${perfdata} -e cs_etm//u -C $1 \
+		-- taskset --cpu-list $1 true > /dev/null 2>&1
+	perf_script_branch_samples true
+	err=$?
+	arm_cs_report "CoreSight sparse CPUs with '$*'" $err
+}
+
+arm_cs_etm_sparse_cpus_test() {
+	# Iterate for every ETM device
+	cpus=()
+	for dev in /sys/bus/event_source/devices/cs_etm/cpu*; do
+		# Canonicalize the path
+		dev=`readlink -f $dev`
+
+		# Find the ETM device belonging to which CPU
+		cpus+=("$(cat $dev/cpu)")
+	done
+
+	mapfile -t cpus < <(printf '%s\n' "${cpus[@]}" | sort -n)
+	total=${#cpus[@]}
+
+	# Need more than 1 to test
+	if [ $total -le 1 ]; then
+		return 0
+	fi
+
+	half=$((total / 2))
+
+	# First half
+	first_half=$(IFS=,; echo "${cpus[*]:0:$half}")
+	arm_cs_etm_test_cpu_list $first_half
+
+	# Second half
+	second_half=$(IFS=,; echo "${cpus[*]:$half}")
+	arm_cs_etm_test_cpu_list $second_half
+
+	# Odd list is the same as halves unless >= 4 CPUs
+	if [ $total -lt 4 ]; then
+		return 0
+	fi
+
+	# Odd indices
+	odd_cpus=()
+	for ((i=1; i<total; i+=2)); do
+		odd_cpus+=("${cpus[$i]}")
+	done
+	odd_list=$(IFS=,; echo "${odd_cpus[*]}")
+	arm_cs_etm_test_cpu_list $odd_list
+}
+
 arm_cs_etm_traverse_path_test
 arm_cs_etm_system_wide_test
 arm_cs_etm_snapshot_test
@@ -211,4 +263,6 @@ arm_cs_etm_basic_test -e cs_etm/timestamp=1/ -a
 arm_cs_etm_basic_test -e cs_etm/timestamp=0/
 arm_cs_etm_basic_test -e cs_etm/timestamp=1/
 
+arm_cs_etm_sparse_cpus_test
+
 exit $glb_err

tools/perf/tests/shell/test_java_symbol.sh

@@ -22,10 +22,13 @@ cleanup_files()
 
 trap cleanup_files exit term int
 
+PERF_DIR=$(dirname "$(which perf)")
 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 "$PERF_DIR/libperf-jvmti.so" ]; then
+	LIBJVMTI=$PERF_DIR/libperf-jvmti.so
 elif [ -e "$PREFIX/lib64/libperf-jvmti.so" ]; then
 	LIBJVMTI=$PREFIX/lib64/libperf-jvmti.so
 elif [ -e "$PREFIX/lib/libperf-jvmti.so" ]; then
@@ -34,6 +37,7 @@ elif [ -e "/usr/lib/linux-tools-$(uname -a | awk '{ print $3 }' | sed -r 's/-gen
 	LIBJVMTI=/usr/lib/linux-tools-$(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

tools/perf/tests/shell/test_perf_data_converter_ctf.sh

@@ -0,0 +1,104 @@
+#!/bin/bash
+# 'perf data convert --to-ctf' command test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+ctf_dir=$(mktemp -d /tmp/__perf_test.ctf.XXXXX)
+
+cleanup()
+{
+	rm -f "${perfdata}"
+	rm -rf "${ctf_dir}"
+	trap - exit term int
+}
+
+trap_cleanup()
+{
+	echo "Unexpected signal in ${FUNCNAME[1]}"
+	cleanup
+	exit ${err}
+}
+trap trap_cleanup exit term int
+
+check_babeltrace_support()
+{
+	if ! perf check feature libbabeltrace
+	then
+		echo "perf not linked with libbabeltrace, skipping test"
+		exit 2
+	fi
+}
+
+test_ctf_converter_file()
+{
+	echo "Testing Perf Data Conversion Command to CTF (File input)"
+	# Record some data
+	if ! perf record -o "$perfdata" -F 99 -g -- perf test -w noploop
+	then
+		echo "Failed to record perf data"
+		err=1
+		return
+	fi
+
+	# Cleanup previous ctf dir
+	rm -rf "${ctf_dir}"
+
+	# Convert
+	if ! perf data convert --to-ctf "$ctf_dir" --force -i "$perfdata"
+	then
+		echo "Perf Data Converter Command to CTF (File input) [FAILED]"
+		err=1
+		return
+	fi
+
+	if [ -d "${ctf_dir}" ] && [ "$(ls -A "${ctf_dir}")" ]
+	then
+		echo "Perf Data Converter Command to CTF (File input) [SUCCESS]"
+	else
+		echo "Perf Data Converter Command to CTF (File input) [FAILED]"
+		echo "    Output directory empty or missing"
+		err=1
+	fi
+}
+
+test_ctf_converter_pipe()
+{
+	echo "Testing Perf Data Conversion Command to CTF (Pipe mode)"
+
+	# Cleanup previous ctf dir
+	rm -rf "${ctf_dir}"
+
+	# Record to stdout and pipe to $perfdata file
+	if ! perf record -o - -F 99 -g -- perf test -w noploop > "$perfdata"
+	then
+		echo "Failed to record perf data"
+		err=1
+		return
+	fi
+
+	if ! perf data convert --to-ctf "$ctf_dir" --force -i "$perfdata"
+	then
+		echo "Perf Data Converter Command to CTF (Pipe mode) [FAILED]"
+		err=1
+		return
+	fi
+
+	if [ -d "${ctf_dir}" ] && [ "$(ls -A "${ctf_dir}")" ]
+	then
+		echo "Perf Data Converter Command to CTF (Pipe mode) [SUCCESS]"
+	else
+		echo "Perf Data Converter Command to CTF (Pipe mode) [FAILED]"
+		echo "    Output directory empty or missing"
+		err=1
+	fi
+}
+
+check_babeltrace_support
+test_ctf_converter_file
+test_ctf_converter_pipe
+
+exit ${err}

tools/perf/tests/shell/test_perf_data_converter_json.sh

@@ -15,29 +15,42 @@ result=$(mktemp /tmp/__perf_test.output.json.XXXXX)
 
 cleanup()
 {
-	rm -f "${perfdata}"
+	rm -f "${perfdata}*"
 	rm -f "${result}"
 	trap - exit term int
 }
 
 trap_cleanup()
 {
+	echo "Unexpected signal in ${FUNCNAME[1]}"
 	cleanup
-	exit ${err}
+	exit 1
 }
 trap trap_cleanup exit term int
 
 test_json_converter_command()
 {
-	echo "Testing Perf Data Convertion Command to JSON"
-	perf record -o "$perfdata" -F 99 -g -- perf test -w noploop > /dev/null 2>&1
-	perf data convert --to-json "$result" --force -i "$perfdata" >/dev/null 2>&1
+	echo "Testing Perf Data Conversion Command to JSON"
+	perf record -o "$perfdata" -F 99 -g -- perf test -w noploop
+	perf data convert --to-json "$result" --force -i "$perfdata"
 	if [ "$(cat ${result} | wc -l)" -gt "0" ] ; then
 		echo "Perf Data Converter Command to JSON [SUCCESS]"
 	else
 		echo "Perf Data Converter Command to JSON [FAILED]"
 		err=1
-		exit
+	fi
+}
+
+test_json_converter_pipe()
+{
+	echo "Testing Perf Data Conversion Command to JSON (Pipe mode)"
+	perf record -o - -F 99 -g -- perf test -w noploop > "$perfdata"
+	cat "$perfdata" | perf data convert --to-json "$result" --force -i -
+	if [ "$(cat ${result} | wc -l)" -gt "0" ] ; then
+		echo "Perf Data Converter Command to JSON (Pipe mode) [SUCCESS]"
+	else
+		echo "Perf Data Converter Command to JSON (Pipe mode) [FAILED]"
+		err=1
 	fi
 }
 
@@ -50,16 +63,18 @@ validate_json_format()
 		else
 			echo "The file does not contain valid JSON format [FAILED]"
 			err=1
-			exit
 		fi
 	else
 		echo "File not found [FAILED]"
-		err=2
-		exit
+		err=1
 	fi
 }
 
 test_json_converter_command
 validate_json_format
 
+test_json_converter_pipe
+validate_json_format
+
+cleanup
 exit ${err}

tools/perf/tests/subcmd-help.c

@@ -95,10 +95,36 @@ static int test__exclude_cmdnames(struct test_suite *test __maybe_unused,
 	return TEST_OK;
 }
 
+static int test__exclude_cmdnames_no_overlap(struct test_suite *test __maybe_unused,
+					     int subtest __maybe_unused)
+{
+	struct cmdnames cmds1 = {};
+	struct cmdnames cmds2 = {};
+
+	add_cmdname(&cmds1, "read-vdso32", 11);
+	add_cmdname(&cmds2, "archive", 7);
+
+	TEST_ASSERT_VAL("invalid original size", cmds1.cnt == 1);
+	TEST_ASSERT_VAL("invalid original size", cmds2.cnt == 1);
+
+	exclude_cmds(&cmds1, &cmds2);
+
+	TEST_ASSERT_VAL("invalid excluded size", cmds1.cnt == 1);
+	TEST_ASSERT_VAL("invalid excluded size", cmds2.cnt == 1);
+
+	TEST_ASSERT_VAL("cannot find cmd", is_in_cmdlist(&cmds1, "read-vdso32") == 1);
+	TEST_ASSERT_VAL("wrong cmd", is_in_cmdlist(&cmds1, "archive") == 0);
+
+	clean_cmdnames(&cmds1);
+	clean_cmdnames(&cmds2);
+	return TEST_OK;
+}
+
 static struct test_case tests__subcmd_help[] = {
 	TEST_CASE("Load subcmd names", load_cmdnames),
 	TEST_CASE("Uniquify subcmd names", uniq_cmdnames),
 	TEST_CASE("Exclude duplicate subcmd names", exclude_cmdnames),
+	TEST_CASE("Exclude disjoint subcmd names", exclude_cmdnames_no_overlap),
 	{	.name = NULL, }
 };
 

tools/perf/tests/sw-clock.c

@@ -5,6 +5,7 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
+#include <linux/compiler.h>
 #include <linux/string.h>
 
 #include "tests.h"
@@ -28,7 +29,7 @@
 static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 {
 	int i, err = -1;
-	volatile int tmp = 0;
+	volatile int tmp __maybe_unused = 0;
 	u64 total_periods = 0;
 	int nr_samples = 0;
 	char sbuf[STRERR_BUFSIZE];

tools/perf/tests/tests.h

@@ -240,6 +240,11 @@ DECLARE_WORKLOAD(brstack);
 DECLARE_WORKLOAD(datasym);
 DECLARE_WORKLOAD(landlock);
 DECLARE_WORKLOAD(traploop);
+DECLARE_WORKLOAD(inlineloop);
+
+#ifdef HAVE_RUST_SUPPORT
+DECLARE_WORKLOAD(code_with_type);
+#endif
 
 extern const char *dso_to_test;
 extern const char *test_objdump_path;

tools/perf/tests/util.c

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "tests.h"
+#include "util/blake2s.h"
 #include "util/debug.h"
-#include "util/sha1.h"
 
 #include <linux/compiler.h>
 #include <stdlib.h>
@@ -17,45 +17,72 @@ static int test_strreplace(char needle, const char *haystack,
 	return ret == 0;
 }
 
-#define MAX_LEN 512
+/* Maximum data length tested by test_blake2s() */
+#define MAX_DATA_LEN 512
 
-/* Test sha1() for all lengths from 0 to MAX_LEN inclusively. */
-static int test_sha1(void)
+/*
+ * Hash length tested by test_blake2s().  BLAKE2s supports variable-length
+ * hashes.  However, the only user of BLAKE2s in 'perf' uses 20-byte hashes,
+ * matching the length of the ELF build ID field.  So that's the length we test.
+ */
+#define HASH_LEN 20
+
+/* Test the implementation of the BLAKE2s hash algorithm. */
+static int test_blake2s(void)
 {
-	u8 data[MAX_LEN];
-	size_t digests_size = (MAX_LEN + 1) * SHA1_DIGEST_SIZE;
-	u8 *digests;
-	u8 digest_of_digests[SHA1_DIGEST_SIZE];
+	u8 data[MAX_DATA_LEN];
+	u8 hash[HASH_LEN];
+	u8 hash2[HASH_LEN];
+	struct blake2s_ctx main_ctx;
 	/*
-	 * The correctness of this value was verified by running this test with
-	 * sha1() replaced by OpenSSL's SHA1().
+	 * This value was generated by the following Python code:
+	 *
+	 * import hashlib
+	 *
+	 * data = bytes(i % 256 for i in range(513))
+	 * h = hashlib.blake2s(digest_size=20)
+	 * for i in range(513):
+	 *     h.update(hashlib.blake2s(data=data[:i], digest_size=20).digest())
+	 * print(h.hexdigest())
 	 */
-	static const u8 expected_digest_of_digests[SHA1_DIGEST_SIZE] = {
-		0x74, 0xcd, 0x4c, 0xb9, 0xd8, 0xa6, 0xd5, 0x95, 0x22, 0x8b,
-		0x7e, 0xd6, 0x8b, 0x7e, 0x46, 0x95, 0x31, 0x9b, 0xa2, 0x43,
+	static const u8 expected_hash_of_hashes[20] = {
+		0xef, 0x9b, 0x13, 0x98, 0x78, 0x8e, 0x74, 0x59, 0x9c, 0xd5,
+		0x0c, 0xf0, 0x33, 0x97, 0x79, 0x3d, 0x3e, 0xd0, 0x95, 0xa6
 	};
 	size_t i;
 
-	digests = malloc(digests_size);
-	TEST_ASSERT_VAL("failed to allocate digests", digests != NULL);
-
-	/* Generate MAX_LEN bytes of data. */
-	for (i = 0; i < MAX_LEN; i++)
+	/* Generate MAX_DATA_LEN bytes of data. */
+	for (i = 0; i < MAX_DATA_LEN; i++)
 		data[i] = i;
 
-	/* Calculate a SHA-1 for each length 0 through MAX_LEN inclusively. */
-	for (i = 0; i <= MAX_LEN; i++)
-		sha1(data, i, &digests[i * SHA1_DIGEST_SIZE]);
+	blake2s_init(&main_ctx, sizeof(hash));
+	for (i = 0; i <= MAX_DATA_LEN; i++) {
+		struct blake2s_ctx ctx;
 
-	/* Calculate digest of all digests calculated above. */
-	sha1(digests, digests_size, digest_of_digests);
+		/* Compute the BLAKE2s hash of 'i' data bytes. */
+		blake2s_init(&ctx, HASH_LEN);
+		blake2s_update(&ctx, data, i);
+		blake2s_final(&ctx, hash);
 
-	free(digests);
+		/* Verify that multiple updates produce the same result. */
+		blake2s_init(&ctx, HASH_LEN);
+		blake2s_update(&ctx, data, i / 2);
+		blake2s_update(&ctx, &data[i / 2], i - (i / 2));
+		blake2s_final(&ctx, hash2);
+		TEST_ASSERT_VAL("inconsistent BLAKE2s hashes",
+				memcmp(hash, hash2, HASH_LEN) == 0);
 
-	/* Check for the expected result. */
-	TEST_ASSERT_VAL("wrong output from sha1()",
-			memcmp(digest_of_digests, expected_digest_of_digests,
-			       SHA1_DIGEST_SIZE) == 0);
+		/*
+		 * Pass the hash to another BLAKE2s context, so that we
+		 * incrementally compute the hash of all the hashes.
+		 */
+		blake2s_update(&main_ctx, hash, HASH_LEN);
+	}
+
+	/* Verify the hash of all the hashes. */
+	blake2s_final(&main_ctx, hash);
+	TEST_ASSERT_VAL("wrong BLAKE2s hashes",
+			memcmp(hash, expected_hash_of_hashes, HASH_LEN) == 0);
 	return 0;
 }
 
@@ -68,7 +95,7 @@ static int test__util(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	TEST_ASSERT_VAL("replace long", test_strreplace('a', "abcabc", "longlong",
 							"longlongbclonglongbc"));
 
-	return test_sha1();
+	return test_blake2s();
 }
 
 DEFINE_SUITE("util", util);

tools/perf/tests/workloads/Build

@@ -8,9 +8,16 @@ perf-test-y += brstack.o
 perf-test-y += datasym.o
 perf-test-y += landlock.o
 perf-test-y += traploop.o
+perf-test-y += inlineloop.o
+
+ifeq ($(CONFIG_RUST_SUPPORT),y)
+    perf-test-y += code_with_type.o
+    perf-test-y += code_with_type.a
+endif
 
 CFLAGS_sqrtloop.o         = -g -O0 -fno-inline -U_FORTIFY_SOURCE
 CFLAGS_leafloop.o         = -g -O0 -fno-inline -fno-omit-frame-pointer -U_FORTIFY_SOURCE
 CFLAGS_brstack.o          = -g -O0 -fno-inline -U_FORTIFY_SOURCE
 CFLAGS_datasym.o          = -g -O0 -fno-inline -U_FORTIFY_SOURCE
 CFLAGS_traploop.o         = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_inlineloop.o       = -g -O2

tools/perf/tests/workloads/code_with_type.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+extern void test_rs(uint count);
+
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int code_with_type(int argc, const char **argv)
+{
+	int sec = 1, num_loops = 100;
+
+	pthread_setname_np(pthread_self(), "perf-code-with-type");
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	if (argc > 1)
+		num_loops = atoi(argv[1]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	/*
+	 * Rust doesn't have signal management in the standard library. To
+	 * not deal with any external crates, offload signal handling to the
+	 * outside code.
+	 */
+	while (!done) {
+		test_rs(num_loops);
+		continue;
+	}
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(code_with_type);

tools/perf/tests/workloads/code_with_type.rs

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// We're going to look for this structure in the data type profiling report
+#[allow(dead_code)]
+struct Buf {
+    data1: u64,
+    data2: String,
+    data3: u64,
+}
+
+#[no_mangle]
+pub extern "C" fn test_rs(count: u32) {
+    let mut b = Buf {
+        data1: 0,
+        data2: String::from("data"),
+        data3: 0,
+    };
+
+    for _ in 1..count {
+        b.data1 += 1;
+        if b.data1 == 123 {
+            b.data1 += 1;
+        }
+
+        b.data3 += b.data1;
+    }
+}

tools/perf/tests/workloads/inlineloop.c

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile int a;
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static inline void __attribute__((always_inline)) leaf(int b)
+{
+again:
+	a += b;
+	if (!done)
+		goto again;
+}
+
+static inline void __attribute__((always_inline)) middle(int b)
+{
+	leaf(b);
+}
+
+static noinline void parent(int b)
+{
+	middle(b);
+}
+
+static int inlineloop(int argc, const char **argv)
+{
+	int sec = 1;
+
+	pthread_setname_np(pthread_self(), "perf-inlineloop");
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	parent(sec);
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(inlineloop);