Merge tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Skip invalid hybrid PMU on hybrid systems when the atom (little) CPUs
   are offlined.

 - Fix 'perf test' problems related to the recently added hybrid
   (BIG/little) code.

 - Split ARM's coresight (hw tracing) decode by aux records to avoid
   fatal decoding errors.

 - Fix add event failure in 'perf probe' when running 32-bit perf in a
   64-bit kernel.

 - Fix 'perf sched record' failure when CONFIG_SCHEDSTATS is not set.

 - Fix memory and refcount leaks detected by ASAn when running 'perf
   test', should be clean of warnings now.

 - Remove broken definition of __LITTLE_ENDIAN from tools'
   linux/kconfig.h, which was breaking the build in some systems.

 - Cast PTHREAD_STACK_MIN to int as it may turn into 'long
   sysconf(__SC_THREAD_STACK_MIN_VALUE), breaking the build in some
   systems.

 - Fix libperf build error with LIBPFM4=1.

 - Sync UAPI files changed by the memfd_secret new syscall.

* tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (35 commits)
  perf sched: Fix record failure when CONFIG_SCHEDSTATS is not set
  perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel
  perf data: Close all files in close_dir()
  perf probe-file: Delete namelist in del_events() on the error path
  perf test bpf: Free obj_buf
  perf trace: Free strings in trace__parse_events_option()
  perf trace: Free syscall tp fields in evsel->priv
  perf trace: Free syscall->arg_fmt
  perf trace: Free malloc'd trace fields on exit
  perf lzma: Close lzma stream on exit
  perf script: Fix memory 'threads' and 'cpus' leaks on exit
  perf script: Release zstd data
  perf session: Cleanup trace_event
  perf inject: Close inject.output on exit
  perf report: Free generated help strings for sort option
  perf env: Fix memory leak of cpu_pmu_caps
  perf test maps__merge_in: Fix memory leak of maps
  perf dso: Fix memory leak in dso__new_map()
  perf test event_update: Fix memory leak of unit
  perf test event_update: Fix memory leak of evlist
  ...

36 files changed, 391 insertions, 98 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index f83a70e07df8..ce2ee8f1e361 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -20,5 +20,6 @@
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
 #define __ARCH_WANT_SYS_CLONE3
+#define __ARCH_WANT_MEMFD_SECRET
 
 #include <asm-generic/unistd.h>
diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h
index 1555a0c4f345..13b86bd3b746 100644
--- a/tools/include/linux/kconfig.h
+++ b/tools/include/linux/kconfig.h
@@ -4,12 +4,6 @@
 
 /* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
 
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define __BIG_ENDIAN 4321
-#else
-#define __LITTLE_ENDIAN 1234
-#endif
-
 #define __ARG_PLACEHOLDER_1 0,
 #define __take_second_arg(__ignored, val, ...) val
 
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f211961ce1da..a9d6fcd95f42 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -873,8 +873,13 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 
+#ifdef __ARCH_WANT_MEMFD_SECRET
+#define __NR_memfd_secret 447
+__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
+#endif
+
 #undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 448
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index af973e400053..f6b57799c1ea 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -368,6 +368,7 @@
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common	memfd_secret		sys_memfd_secret
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 5d6f583e2cd3..c88c61e7f8cc 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -361,9 +361,10 @@ static struct dso *findnew_dso(int pid, int tid, const char *filename,
 		dso = machine__findnew_dso_id(machine, filename, id);
 	}
 
-	if (dso)
+	if (dso) {
+		nsinfo__put(dso->nsinfo);
 		dso->nsinfo = nsi;
-	else
+	} else
 		nsinfo__put(nsi);
 
 	thread__put(thread);
@@ -992,8 +993,10 @@ int cmd_inject(int argc, const char **argv)
 
 	data.path = inject.input_name;
 	inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
-	if (IS_ERR(inject.session))
-		return PTR_ERR(inject.session);
+	if (IS_ERR(inject.session)) {
+		ret = PTR_ERR(inject.session);
+		goto out_close_output;
+	}
 
 	if (zstd_init(&(inject.session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed.\n");
@@ -1035,6 +1038,8 @@ int cmd_inject(int argc, const char **argv)
 out_delete:
 	zstd_fini(&(inject.session->zstd_data));
 	perf_session__delete(inject.session);
+out_close_output:
+	perf_data__close(&inject.output);
 	free(inject.itrace_synth_opts.vm_tm_corr_args);
 	return ret;
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 6386af6a2612..dc0364f671b9 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1175,6 +1175,8 @@ int cmd_report(int argc, const char **argv)
 		.annotation_opts	 = annotation__default_options,
 		.skip_empty		 = true,
 	};
+	char *sort_order_help = sort_help("sort by key(s):");
+	char *field_order_help = sort_help("output field(s): overhead period sample ");
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -1209,9 +1211,9 @@ int cmd_report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "header-only", &report.header_only,
 		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   sort_help("sort by key(s):")),
+		   sort_order_help),
 	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
-		   sort_help("output field(s): overhead period sample ")),
+		   field_order_help),
 	OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -1344,11 +1346,11 @@ int cmd_report(int argc, const char **argv)
 	char sort_tmp[128];
 
 	if (ret < 0)
-		return ret;
+		goto exit;
 
 	ret = perf_config(report__config, &report);
 	if (ret)
-		return ret;
+		goto exit;
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 	if (argc) {
@@ -1362,8 +1364,10 @@ int cmd_report(int argc, const char **argv)
 		report.symbol_filter_str = argv[0];
 	}
 
-	if (annotate_check_args(&report.annotation_opts) < 0)
-		return -EINVAL;
+	if (annotate_check_args(&report.annotation_opts) < 0) {
+		ret = -EINVAL;
+		goto exit;
+	}
 
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
@@ -1377,12 +1381,14 @@ int cmd_report(int argc, const char **argv)
 	if (symbol_conf.vmlinux_name &&
 	    access(symbol_conf.vmlinux_name, R_OK)) {
 		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 	if (symbol_conf.kallsyms_name &&
 	    access(symbol_conf.kallsyms_name, R_OK)) {
 		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	if (report.inverted_callchain)
@@ -1406,12 +1412,14 @@ int cmd_report(int argc, const char **argv)
 
 repeat:
 	session = perf_session__new(&data, false, &report.tool);
-	if (IS_ERR(session))
-		return PTR_ERR(session);
+	if (IS_ERR(session)) {
+		ret = PTR_ERR(session);
+		goto exit;
+	}
 
 	ret = evswitch__init(&report.evswitch, session->evlist, stderr);
 	if (ret)
-		return ret;
+		goto exit;
 
 	if (zstd_init(&(session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
@@ -1646,5 +1654,8 @@ error:
 
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
+exit:
+	free(sort_order_help);
+	free(field_order_help);
 	return ret;
 }
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 954ce2f594e9..1ff10d4bccf3 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched)
 	err = pthread_attr_init(&attr);
 	BUG_ON(err);
 	err = pthread_attr_setstacksize(&attr,
-			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
+			(size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN));
 	BUG_ON(err);
 	err = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(err);
@@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options
 	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
+static bool schedstat_events_exposed(void)
+{
+	/*
+	 * Select "sched:sched_stat_wait" event to check
+	 * whether schedstat tracepoints are exposed.
+	 */
+	return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ?
+		false : true;
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 		"-e", "sched:sched_switch",
-		"-e", "sched:sched_stat_wait",
-		"-e", "sched:sched_stat_sleep",
-		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
 		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
+
+	/*
+	 * The tracepoints trace_sched_stat_{wait, sleep, iowait}
+	 * are not exposed to user if CONFIG_SCHEDSTATS is not set,
+	 * to prevent "perf sched record" execution failure, determine
+	 * whether to record schedstat events according to actual situation.
+	 */
+	const char * const schedstat_args[] = {
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+	};
+	unsigned int schedstat_argc = schedstat_events_exposed() ?
+		ARRAY_SIZE(schedstat_args) : 0;
+
 	struct tep_event *waking_event;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
 	 * "-e", "sched:sched_waking"
 	 */
-	rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1;
+	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv)
 	else
 		rec_argv[i++] = strdup("sched:sched_wakeup");
 
+	for (j = 0; j < schedstat_argc; j++)
+		rec_argv[i++] = strdup(schedstat_args[j]);
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8c03a9862872..064da7f3618d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2601,6 +2601,12 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
 	}
 }
 
+static void perf_script__exit(struct perf_script *script)
+{
+	perf_thread_map__put(script->threads);
+	perf_cpu_map__put(script->cpus);
+}
+
 static int __cmd_script(struct perf_script *script)
 {
 	int ret;
@@ -4143,8 +4149,10 @@ out_delete:
 		zfree(&script.ptime_range);
 	}
 
+	zstd_fini(&(session->zstd_data));
 	evlist__free_stats(session->evlist);
 	perf_session__delete(session);
+	perf_script__exit(&script);
 
 	if (script_started)
 		cleanup_scripting();
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d25cb8088e8c..634375937db9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2445,9 +2445,6 @@ int cmd_stat(int argc, const char **argv)
 
 	evlist__check_cpu_maps(evsel_list);
 
-	if (perf_pmu__has_hybrid())
-		stat_config.no_merge = true;
-
 	/*
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7ec18ff57fc4..9c265fa96011 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2266,6 +2266,14 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam
 	return augmented_args;
 }
 
+static void syscall__exit(struct syscall *sc)
+{
+	if (!sc)
+		return;
+
+	free(sc->arg_fmt);
+}
+
 static int trace__sys_enter(struct trace *trace, struct evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
@@ -3095,6 +3103,21 @@ static struct evsel *evsel__new_pgfault(u64 config)
 	return evsel;
 }
 
+static void evlist__free_syscall_tp_fields(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct evsel_trace *et = evsel->priv;
+
+		if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls"))
+			continue;
+
+		free(et->fmt);
+		free(et);
+	}
+}
+
 static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
 {
 	const u32 type = event->header.type;
@@ -4130,7 +4153,7 @@ out_disable:
 
 out_delete_evlist:
 	trace__symbols__exit(trace);
-
+	evlist__free_syscall_tp_fields(evlist);
 	evlist__delete(evlist);
 	cgroup__put(trace->cgroup);
 	trace->evlist = NULL;
@@ -4636,6 +4659,9 @@ do_concat:
 		err = parse_events_option(&o, lists[0], 0);
 	}
 out:
+	free(strace_groups_dir);
+	free(lists[0]);
+	free(lists[1]);
 	if (sep)
 		*sep = ',';
 
@@ -4701,6 +4727,21 @@ out:
 	return err;
 }
 
+static void trace__exit(struct trace *trace)
+{
+	int i;
+
+	strlist__delete(trace->ev_qualifier);
+	free(trace->ev_qualifier_ids.entries);
+	if (trace->syscalls.table) {
+		for (i = 0; i <= trace->sctbl->syscalls.max_id; i++)
+			syscall__exit(&trace->syscalls.table[i]);
+		free(trace->syscalls.table);
+	}
+	syscalltbl__delete(trace->sctbl);
+	zfree(&trace->perfconfig_events);
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -5135,6 +5176,6 @@ out_close:
 	if (output_name != NULL)
 		fclose(trace.output);
 out:
-	zfree(&trace.perfconfig_events);
+	trace__exit(&trace);
 	return err;
 }
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 33bda9c26542..dbf5f5215abe 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/epoll.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -276,6 +277,7 @@ static int __test__bpf(int idx)
 	}
 
 out:
+	free(obj_buf);
 	bpf__clear();
 	return ret;
 }
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index 656218179222..44a50527f9d9 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -88,6 +88,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 	struct evsel *evsel;
 	struct event_name tmp;
 	struct evlist *evlist = evlist__new_default();
+	char *unit = strdup("KRAVA");
 
 	TEST_ASSERT_VAL("failed to get evlist", evlist);
 
@@ -98,7 +99,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 
 	perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);
 
-	evsel->unit = strdup("KRAVA");
+	evsel->unit = unit;
 
 	TEST_ASSERT_VAL("failed to synthesize attr update unit",
 			!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
@@ -118,6 +119,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 	TEST_ASSERT_VAL("failed to synthesize attr update cpus",
 			!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
 
-	perf_cpu_map__put(evsel->core.own_cpus);
+	free(unit);
+	evlist__delete(evlist);
 	return 0;
 }
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 5ebf56331904..4e09f0a312af 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -5,6 +5,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "pmu.h"
+#include "pmu-hybrid.h"
 #include <errno.h>
 #include <linux/kernel.h>
 
@@ -102,7 +103,7 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int
 {
 	int err = 0, ret = 0;
 
-	if (perf_pmu__has_hybrid())
+	if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom"))
 		return perf_evsel__name_array_test(evsel__hw_names, 2);
 
 	err = perf_evsel__name_array_test(evsel__hw_names, 1);
diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c
index edcbc70ff9d6..1ac72919fa35 100644
--- a/tools/perf/tests/maps.c
+++ b/tools/perf/tests/maps.c
@@ -116,5 +116,7 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus
 
 	ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps);
 	TEST_ASSERT_VAL("merge check failed", !ret);
+
+	maps__exit(&maps);
 	return TEST_OK;
 }
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 56a7b6a14195..8d4866739255 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -6,6 +6,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "pmu.h"
+#include "pmu-hybrid.h"
 #include <dirent.h>
 #include <errno.h>
 #include <sys/types.h>
@@ -1596,6 +1597,13 @@ static int test__hybrid_raw1(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
 
+	if (!perf_pmu__hybrid_mounted("cpu_atom")) {
+		TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+		TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+		TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config);
+		return 0;
+	}
+
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config);
@@ -1620,13 +1628,9 @@ static int test__hybrid_cache_event(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
 
-	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff));
-
-	evsel = evsel__next(evsel);
-	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
-	TEST_ASSERT_VAL("wrong config", 0x10002 == (evsel->core.attr.config & 0xffffffff));
 	return 0;
 }
 
@@ -2028,7 +2032,7 @@ static struct evlist_test test__hybrid_events[] = {
 		.id    = 7,
 	},
 	{
-		.name  = "cpu_core/LLC-loads/,cpu_atom/LLC-load-misses/",
+		.name  = "cpu_core/LLC-loads/",
 		.check = test__hybrid_cache_event,
 		.id    = 8,
 	},
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 85d75b9b25a1..7c56bc1f4cff 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -21,6 +21,7 @@
 #include "mmap.h"
 #include "tests.h"
 #include "pmu.h"
+#include "pmu-hybrid.h"
 
 #define CHECK__(x) {				\
 	while ((x) < 0) {			\
@@ -93,7 +94,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	 * For hybrid "cycles:u", it creates two events.
 	 * Init the second evsel here.
 	 */
-	if (perf_pmu__has_hybrid()) {
+	if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) {
 		evsel = evsel__next(evsel);
 		evsel->core.attr.comm = 1;
 		evsel->core.attr.disabled = 1;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index ec4e3b21b831..b5efe675b321 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -61,6 +61,7 @@ static int session_write_header(char *path)
 	TEST_ASSERT_VAL("failed to write header",
 			!perf_session__write_header(session, session->evlist, data.file.fd, true));
 
+	evlist__delete(session->evlist);
 	perf_session__delete(session);
 
 	return 0;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 32ad92d3e454..22f8326547eb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2683,6 +2683,172 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset,
 	return metadata;
 }
 
+/**
+ * Puts a fragment of an auxtrace buffer into the auxtrace queues based
+ * on the bounds of aux_event, if it matches with the buffer that's at
+ * file_offset.
+ *
+ * Normally, whole auxtrace buffers would be added to the queue. But we
+ * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder
+ * is reset across each buffer, so splitting the buffers up in advance has
+ * the same effect.
+ */
+static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz,
+				      struct perf_record_aux *aux_event, struct perf_sample *sample)
+{
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+	union perf_event *auxtrace_event_union;
+	struct perf_record_auxtrace *auxtrace_event;
+	union perf_event auxtrace_fragment;
+	__u64 aux_offset, aux_size;
+
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+
+	/*
+	 * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got
+	 * from looping through the auxtrace index.
+	 */
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL);
+	if (err)
+		return err;
+	auxtrace_event = &auxtrace_event_union->auxtrace;
+	if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE)
+		return -EINVAL;
+
+	if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) ||
+		auxtrace_event->header.size != sz) {
+		return -EINVAL;
+	}
+
+	/*
+	 * In per-thread mode, CPU is set to -1, but TID will be set instead. See
+	 * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match.
+	 */
+	if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) ||
+			auxtrace_event->cpu != sample->cpu)
+		return 1;
+
+	if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) {
+		/*
+		 * Clamp size in snapshot mode. The buffer size is clamped in
+		 * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect
+		 * the buffer size.
+		 */
+		aux_size = min(aux_event->aux_size, auxtrace_event->size);
+
+		/*
+		 * In this mode, the head also points to the end of the buffer so aux_offset
+		 * needs to have the size subtracted so it points to the beginning as in normal mode
+		 */
+		aux_offset = aux_event->aux_offset - aux_size;
+	} else {
+		aux_size = aux_event->aux_size;
+		aux_offset = aux_event->aux_offset;
+	}
+
+	if (aux_offset >= auxtrace_event->offset &&
+	    aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) {
+		/*
+		 * If this AUX event was inside this buffer somewhere, create a new auxtrace event
+		 * based on the sizes of the aux event, and queue that fragment.
+		 */
+		auxtrace_fragment.auxtrace = *auxtrace_event;
+		auxtrace_fragment.auxtrace.size = aux_size;
+		auxtrace_fragment.auxtrace.offset = aux_offset;
+		file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size;
+
+		pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64
+			  " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu);
+		return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment,
+						  file_offset, NULL);
+	}
+
+	/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
+	return 1;
+}
+
+static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event,
+					u64 offset __maybe_unused, void *data __maybe_unused)
+{
+	struct perf_sample sample;
+	int ret;
+	struct auxtrace_index_entry *ent;
+	struct auxtrace_index *auxtrace_index;
+	struct evsel *evsel;
+	size_t i;
+
+	/* Don't care about any other events, we're only queuing buffers for AUX events */
+	if (event->header.type != PERF_RECORD_AUX)
+		return 0;
+
+	if (event->header.size < sizeof(struct perf_record_aux))
+		return -EINVAL;
+
+	/* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */
+	if (!event->aux.aux_size)
+		return 0;
+
+	/*
+	 * Parse the sample, we need the sample_id_all data that comes after the event so that the
+	 * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID.
+	 */
+	evsel = evlist__event2evsel(session->evlist, event);
+	if (!evsel)
+		return -EINVAL;
+	ret = evsel__parse_sample(evsel, event, &sample);
+	if (ret)
+		return ret;
+
+	/*
+	 * Loop through the auxtrace index to find the buffer that matches up with this aux event.
+	 */
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			ent = &auxtrace_index->entries[i];
+			ret = cs_etm__queue_aux_fragment(session, ent->file_offset,
+							 ent->sz, &event->aux, &sample);
+			/*
+			 * Stop search on error or successful values. Continue search on
+			 * 1 ('not found')
+			 */
+			if (ret != 1)
+				return ret;
+		}
+	}
+
+	/*
+	 * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but
+	 * don't exit with an error because it will still be possible to decode other aux records.
+	 */
+	pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64
+	       " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu);
+	return 0;
+}
+
+static int cs_etm__queue_aux_records(struct perf_session *session)
+{
+	struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index,
+								struct auxtrace_index, list);
+	if (index && index->nr > 0)
+		return perf_session__peek_events(session, session->header.data_offset,
+						 session->header.data_size,
+						 cs_etm__queue_aux_records_cb, NULL);
+
+	/*
+	 * We would get here if there are no entries in the index (either no auxtrace
+	 * buffers or no index at all). Fail silently as there is the possibility of
+	 * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still
+	 * false.
+	 *
+	 * In that scenario, buffers will not be split by AUX records.
+	 */
+	return 0;
+}
+
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
@@ -2883,7 +3049,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
-	err = auxtrace_queues__process_index(&etm->queues, session);
+	err = cs_etm__queue_aux_records(session);
 	if (err)
 		goto err_delete_thread;
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index a9c102e8e3c0..f5d260b1df4d 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -20,7 +20,7 @@
 
 static void close_dir(struct perf_data_file *files, int nr)
 {
-	while (--nr >= 1) {
+	while (--nr >= 0) {
 		close(files[nr].fd);
 		zfree(&files[nr].path);
 	}
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d786cf6b0cfa..ee15db2be2f4 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1154,8 +1154,10 @@ struct map *dso__new_map(const char *name)
 	struct map *map = NULL;
 	struct dso *dso = dso__new(name);
 
-	if (dso)
+	if (dso) {
 		map = map__new2(0, dso);
+		dso__put(dso);
+	}
 
 	return map;
 }
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 7d2ba8419b0c..609ca1671501 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -113,14 +113,14 @@ static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr)
  *
  * Find a line number and file name for @addr in @cu_die.
  */
-int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr,
-		    const char **fname, int *lineno)
+int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr,
+		     const char **fname, int *lineno)
 {
 	Dwarf_Line *line;
 	Dwarf_Die die_mem;
 	Dwarf_Addr faddr;
 
-	if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem)
+	if (die_find_realfunc(cu_die, addr, &die_mem)
 	    && die_entrypc(&die_mem, &faddr) == 0 &&
 	    faddr == addr) {
 		*fname = dwarf_decl_file(&die_mem);
@@ -128,7 +128,7 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr,
 		goto out;
 	}
 
-	line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr);
+	line = cu_getsrc_die(cu_die, addr);
 	if (line && dwarf_lineno(line, lineno) == 0) {
 		*fname = dwarf_linesrc(line, NULL, NULL);
 		if (!*fname)
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index cb99646843a9..7ee0fa19b5c4 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -19,7 +19,7 @@ const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
 const char *cu_get_comp_dir(Dwarf_Die *cu_die);
 
 /* Get a line number and file name for given address */
-int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr,
 		     const char **fname, int *lineno);
 
 /* Walk on functions at given address */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index ebc5e9ad35db..cec2e6cad8aa 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -186,10 +186,12 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->cpuid);
 	zfree(&env->cmdline);
 	zfree(&env->cmdline_argv);
+	zfree(&env->sibling_dies);
 	zfree(&env->sibling_cores);
 	zfree(&env->sibling_threads);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+	zfree(&env->cpu_pmu_caps);
 	zfree(&env->numa_map);
 
 	for (i = 0; i < env->nr_numa_nodes; i++)
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 39062df02629..51424cdc3b68 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -69,7 +69,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (ferror(infile)) {
 				pr_err("lzma: read error: %s\n", strerror(errno));
-				goto err_fclose;
+				goto err_lzma_end;
 			}
 
 			if (feof(infile))
@@ -83,7 +83,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (writen(output_fd, buf_out, write_size) != write_size) {
 				pr_err("lzma: write error: %s\n", strerror(errno));
-				goto err_fclose;
+				goto err_lzma_end;
 			}
 
 			strm.next_out  = buf_out;
@@ -95,11 +95,13 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 				break;
 
 			pr_err("lzma: failed %s\n", lzma_strerror(ret));
-			goto err_fclose;
+			goto err_lzma_end;
 		}
 	}
 
 	err = 0;
+err_lzma_end:
+	lzma_end(&strm);
 err_fclose:
 	fclose(infile);
 	return err;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8af693d9678c..72e7f3616157 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -192,6 +192,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (!(prot & PROT_EXEC))
 				dso__set_loaded(dso);
 		}
+
+		nsinfo__put(dso->nsinfo);
 		dso->nsinfo = nsi;
 
 		if (build_id__is_defined(bid))
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index dd9ed56e0504..756295dedccc 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -99,7 +99,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str,
 			grp_leader = evsel;
 
 		if (grp_evt > -1) {
-			evsel->leader = grp_leader;
+			evsel__set_leader(evsel, grp_leader);
 			grp_leader->core.nr_members++;
 			grp_evt++;
 		}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 44b90d638ad5..a1bd7007a8b4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -950,6 +950,13 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(format);
 	LIST_HEAD(aliases);
 	__u32 type;
+	bool is_hybrid = perf_pmu__hybrid_mounted(name);
+
+	/*
+	 * Check pmu name for hybrid and the pmu may be invalid in sysfs
+	 */
+	if (!strncmp(name, "cpu_", 4) && !is_hybrid)
+		return NULL;
 
 	/*
 	 * The pmu data we store & need consists of the pmu
@@ -978,7 +985,7 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->is_uncore = pmu_is_uncore(name);
 	if (pmu->is_uncore)
 		pmu->id = pmu_id(name);
-	pmu->is_hybrid = perf_pmu__hybrid_mounted(name);
+	pmu->is_hybrid = is_hybrid;
 	pmu->max_precise = pmu_max_precise(name);
 	pmu_add_cpu_aliases(&aliases, pmu);
 	pmu_add_sys_aliases(&aliases, pmu);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c14e1d228e56..b2a02c9ab8ea 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -179,8 +179,10 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
 		struct map *map;
 
 		map = dso__new_map(target);
-		if (map && map->dso)
+		if (map && map->dso) {
+			nsinfo__put(map->dso->nsinfo);
 			map->dso->nsinfo = nsinfo__get(nsi);
+		}
 		return map;
 	} else {
 		return kernel_get_module_map(target);
@@ -237,8 +239,8 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 		clear_probe_trace_event(tevs + i);
 }
 
-static bool kprobe_blacklist__listed(unsigned long address);
-static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+static bool kprobe_blacklist__listed(u64 address);
+static bool kprobe_warn_out_range(const char *symbol, u64 address)
 {
 	struct map *map;
 	bool ret = false;
@@ -398,8 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 	pr_debug("Symbol %s address found : %" PRIx64 "\n",
 			pp->function, address);
 
-	ret = debuginfo__find_probe_point(dinfo, (unsigned long)address,
-					  result);
+	ret = debuginfo__find_probe_point(dinfo, address, result);
 	if (ret <= 0)
 		ret = (!ret) ? -ENOENT : ret;
 	else {
@@ -587,7 +588,7 @@ static void debuginfo_cache__exit(void)
 }
 
 
-static int get_text_start_address(const char *exec, unsigned long *address,
+static int get_text_start_address(const char *exec, u64 *address,
 				  struct nsinfo *nsi)
 {
 	Elf *elf;
@@ -632,7 +633,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 					    bool is_kprobe)
 {
 	struct debuginfo *dinfo = NULL;
-	unsigned long stext = 0;
+	u64 stext = 0;
 	u64 addr = tp->address;
 	int ret = -ENOENT;
 
@@ -660,8 +661,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 
 	dinfo = debuginfo_cache__open(tp->module, verbose <= 0);
 	if (dinfo)
-		ret = debuginfo__find_probe_point(dinfo,
-						 (unsigned long)addr, pp);
+		ret = debuginfo__find_probe_point(dinfo, addr, pp);
 	else
 		ret = -ENOENT;
 
@@ -676,7 +676,7 @@ error:
 
 /* Adjust symbol name and address */
 static int post_process_probe_trace_point(struct probe_trace_point *tp,
-					   struct map *map, unsigned long offs)
+					   struct map *map, u64 offs)
 {
 	struct symbol *sym;
 	u64 addr = tp->address - offs;
@@ -719,7 +719,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 					int ntevs, const char *pathname)
 {
 	struct map *map;
-	unsigned long stext = 0;
+	u64 stext = 0;
 	int i, ret = 0;
 
 	/* Prepare a map for offline binary */
@@ -745,7 +745,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  struct nsinfo *nsi)
 {
 	int i, ret = 0;
-	unsigned long stext = 0;
+	u64 stext = 0;
 
 	if (!exec)
 		return 0;
@@ -790,7 +790,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs,
 	mod_name = find_module_name(module);
 	for (i = 0; i < ntevs; i++) {
 		ret = post_process_probe_trace_point(&tevs[i].point,
-						map, (unsigned long)text_offs);
+						map, text_offs);
 		if (ret < 0)
 			break;
 		tevs[i].point.module =
@@ -1534,7 +1534,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		 * so tmp[1] should always valid (but could be '\0').
 		 */
 		if (tmp && !strncmp(tmp, "0x", 2)) {
-			pp->abs_address = strtoul(pp->function, &tmp, 0);
+			pp->abs_address = strtoull(pp->function, &tmp, 0);
 			if (*tmp != '\0') {
 				semantic_error("Invalid absolute address.\n");
 				return -EINVAL;
@@ -1909,7 +1909,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 			argv[i] = NULL;
 			argc -= 1;
 		} else
-			tp->address = strtoul(fmt1_str, NULL, 0);
+			tp->address = strtoull(fmt1_str, NULL, 0);
 	} else {
 		/* Only the symbol-based probe has offset */
 		tp->symbol = strdup(fmt1_str);
@@ -2155,7 +2155,7 @@ synthesize_uprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf)
 		return -EINVAL;
 
 	/* Use the tp->address for uprobes */
-	err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address);
+	err = strbuf_addf(buf, "%s:0x%" PRIx64, tp->module, tp->address);
 
 	if (err >= 0 && tp->ref_ctr_offset) {
 		if (!uprobe_ref_ctr_is_supported())
@@ -2170,7 +2170,7 @@ synthesize_kprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf)
 {
 	if (!strncmp(tp->symbol, "0x", 2)) {
 		/* Absolute address. See try_to_find_absolute_address() */
-		return strbuf_addf(buf, "%s%s0x%lx", tp->module ?: "",
+		return strbuf_addf(buf, "%s%s0x%" PRIx64, tp->module ?: "",
 				  tp->module ? ":" : "", tp->address);
 	} else {
 		return strbuf_addf(buf, "%s%s%s+%lu", tp->module ?: "",
@@ -2269,7 +2269,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp,
 		pp->function = strdup(tp->symbol);
 		pp->offset = tp->offset;
 	} else {
-		ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+		ret = e_snprintf(buf, 128, "0x%" PRIx64, tp->address);
 		if (ret < 0)
 			return ret;
 		pp->function = strdup(buf);
@@ -2450,8 +2450,8 @@ void clear_probe_trace_event(struct probe_trace_event *tev)
 
 struct kprobe_blacklist_node {
 	struct list_head list;
-	unsigned long start;
-	unsigned long end;
+	u64 start;
+	u64 end;
 	char *symbol;
 };
 
@@ -2496,7 +2496,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist)
 		}
 		INIT_LIST_HEAD(&node->list);
 		list_add_tail(&node->list, blacklist);
-		if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) {
+		if (sscanf(buf, "0x%" PRIx64 "-0x%" PRIx64, &node->start, &node->end) != 2) {
 			ret = -EINVAL;
 			break;
 		}
@@ -2512,7 +2512,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist)
 			ret = -ENOMEM;
 			break;
 		}
-		pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n",
+		pr_debug2("Blacklist: 0x%" PRIx64 "-0x%" PRIx64 ", %s\n",
 			  node->start, node->end, node->symbol);
 		ret++;
 	}
@@ -2524,8 +2524,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist)
 }
 
 static struct kprobe_blacklist_node *
-kprobe_blacklist__find_by_address(struct list_head *blacklist,
-				  unsigned long address)
+kprobe_blacklist__find_by_address(struct list_head *blacklist, u64 address)
 {
 	struct kprobe_blacklist_node *node;
 
@@ -2553,7 +2552,7 @@ static void kprobe_blacklist__release(void)
 	kprobe_blacklist__delete(&kprobe_blacklist);
 }
 
-static bool kprobe_blacklist__listed(unsigned long address)
+static bool kprobe_blacklist__listed(u64 address)
 {
 	return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
 }
@@ -3221,7 +3220,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
 	 * In __add_probe_trace_events, a NULL symbol is interpreted as
 	 * invalid.
 	 */
-	if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0)
+	if (asprintf(&tp->symbol, "0x%" PRIx64, tp->address) < 0)
 		goto errout;
 
 	/* For kprobe, check range */
@@ -3232,7 +3231,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
 		goto errout;
 	}
 
-	if (asprintf(&tp->realname, "abs_%lx", tp->address) < 0)
+	if (asprintf(&tp->realname, "abs_%" PRIx64, tp->address) < 0)
 		goto errout;
 
 	if (pev->target) {
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 65769d7949a3..8ad5b1579f1d 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -33,7 +33,7 @@ struct probe_trace_point {
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
 	unsigned long	ref_ctr_offset;	/* SDT reference counter offset */
-	unsigned long	address;	/* Actual address of the trace point */
+	u64		address;	/* Actual address of the trace point */
 	bool		retprobe;	/* Return probe flag */
 };
 
@@ -70,7 +70,7 @@ struct perf_probe_point {
 	bool		retprobe;	/* Return probe flag */
 	char		*lazy_line;	/* Lazy matching pattern */
 	unsigned long	offset;		/* Offset from function entry */
-	unsigned long	abs_address;	/* Absolute address of the point */
+	u64		abs_address;	/* Absolute address of the point */
 };
 
 /* Perf probe probing argument field chain */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index f9a6cbcd6415..3d50de3217d5 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -377,11 +377,11 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 
 	ret = probe_file__get_events(fd, filter, namelist);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = probe_file__del_strlist(fd, namelist);
+out:
 	strlist__delete(namelist);
-
 	return ret;
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 02ef0d78053b..50d861a80f57 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -668,7 +668,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 	}
 
 	tp->offset = (unsigned long)(paddr - eaddr);
-	tp->address = (unsigned long)paddr;
+	tp->address = paddr;
 	tp->symbol = strdup(symbol);
 	if (!tp->symbol)
 		return -ENOMEM;
@@ -1707,7 +1707,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
 }
 
 /* Reverse search */
-int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt)
 {
 	Dwarf_Die cudie, spdie, indie;
@@ -1720,14 +1720,14 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		pr_warning("Failed to find debug information for address %lx\n",
+		pr_warning("Failed to find debug information for address %" PRIx64 "\n",
 			   addr);
 		ret = -EINVAL;
 		goto end;
 	}
 
 	/* Find a corresponding line (filename and lineno) */
-	cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+	cu_find_lineinfo(&cudie, (Dwarf_Addr)addr, &fname, &lineno);
 	/* Don't care whether it failed or not */
 
 	/* Find a corresponding function (name, baseline and baseaddr) */
@@ -1742,7 +1742,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 		}
 
 		fname = dwarf_decl_file(&spdie);
-		if (addr == (unsigned long)baseaddr) {
+		if (addr == baseaddr) {
 			/* Function entry - Relative line number is 0 */
 			lineno = baseline;
 			goto post;
@@ -1788,7 +1788,7 @@ post:
 	if (lineno)
 		ppt->line = lineno - baseline;
 	else if (basefunc) {
-		ppt->offset = addr - (unsigned long)baseaddr;
+		ppt->offset = addr - baseaddr;
 		func = basefunc;
 	}
 
@@ -1828,8 +1828,7 @@ static int line_range_add_line(const char *src, unsigned int lineno,
 }
 
 static int line_range_walk_cb(const char *fname, int lineno,
-			      Dwarf_Addr addr __maybe_unused,
-			      void *data)
+			      Dwarf_Addr addr, void *data)
 {
 	struct line_finder *lf = data;
 	const char *__fname;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 2febb5875678..8bc1c80d3c1c 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,7 +46,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 				 struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
-int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt);
 
 int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index e9c929a39973..51f727402912 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -306,6 +306,7 @@ void perf_session__delete(struct perf_session *session)
 			evlist__delete(session->evlist);
 		perf_data__close(session->data);
 	}
+	trace_event__cleanup(&session->tevent);
 	free(session);
 }
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 88ce47f2547e..568a88c001c6 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3370,7 +3370,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int
 		add_key(sb, s[i].name, llen);
 }
 
-const char *sort_help(const char *prefix)
+char *sort_help(const char *prefix)
 {
 	struct strbuf sb;
 	char *s;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 87a092645aa7..b67c469aba79 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -302,7 +302,7 @@ void reset_output_field(void);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
-const char *sort_help(const char *prefix);
+char *sort_help(const char *prefix);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 83a2bc02df15..588601000f3f 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -596,6 +596,18 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
 	}
 }
 
+static bool is_uncore(struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+	return pmu && pmu->is_uncore;
+}
+
+static bool hybrid_uniquify(struct evsel *evsel)
+{
+	return perf_pmu__has_hybrid() && !is_uncore(evsel);
+}
+
 static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 			    void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
 				       bool first),
@@ -604,7 +616,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(config, counter, data, true);
-	if (config->no_merge)
+	if (config->no_merge || hybrid_uniquify(counter))
 		uniquify_event_name(counter);
 	else if (counter->auto_merge_stats)
 		collect_all_aliases(config, counter, cb, data);