diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1381f54bbee79ab9aa17f2495342ab56a26da89e..f87bffb86878a867fffdcdc9789b370f17499321 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -751,6 +751,8 @@ struct perf_event {
 	struct pid_namespace		*ns;
 	u64				id;
 
+	atomic64_t			lost_samples;
+
 	u64				(*clock)(void);
 	perf_overflow_handler_t		overflow_handler;
 	void				*overflow_handler_context;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 73c1589fa140d6989e62ab36e457a8d591e80a60..748574ce82742e6092ac3ff61ad5c20ea1970071 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -313,6 +313,7 @@ enum {
  *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
+ *	  { u64		lost;         } && PERF_FORMAT_LOST
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
@@ -320,6 +321,7 @@ enum {
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
+ *	    { u64	lost;         } && PERF_FORMAT_LOST
  *	  }		cntr[nr];
  *	} && PERF_FORMAT_GROUP
  * };
@@ -329,8 +331,9 @@ enum perf_event_read_format {
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
 	PERF_FORMAT_GROUP			= 1U << 3,
+	PERF_FORMAT_LOST			= 1U << 4,
 
-	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 5,		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 405856d12ed21d6b1967e73d83955828e6501fc0..a40c6840b3a3c6e0fdf276e70c78f768f76c3098 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1149,6 +1149,11 @@ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
 	return 0;
 }
 
+static int perf_mux_hrtimer_restart_ipi(void *arg)
+{
+	return perf_mux_hrtimer_restart(arg);
+}
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -1834,6 +1839,9 @@ static int __perf_event_read_size(u64 read_format, int nr_siblings)
 	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
+	if (read_format & PERF_FORMAT_LOST)
+		entry += sizeof(u64);
+
 	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
@@ -3759,7 +3767,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		return;
 
-	if (is_active ^ EVENT_TIME) {
+	if (!(is_active & EVENT_TIME)) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
 		perf_cgroup_set_timestamp(cpuctx);
@@ -5207,11 +5215,15 @@ static int __perf_read_group_add(struct perf_event *leader,
 	values[n++] += perf_event_count(leader);
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
+	if (read_format & PERF_FORMAT_LOST)
+		values[n++] = atomic64_read(&leader->lost_samples);
 
 	for_each_sibling_event(sub, leader) {
 		values[n++] += perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
+		if (read_format & PERF_FORMAT_LOST)
+			values[n++] = atomic64_read(&sub->lost_samples);
 	}
 
 unlock:
@@ -5265,7 +5277,7 @@ static int perf_read_one(struct perf_event *event,
 				 u64 read_format, char __user *buf)
 {
 	u64 enabled, running;
-	u64 values[4];
+	u64 values[5];
 	int n = 0;
 
 	values[n++] = __perf_event_read_value(event, &enabled, &running);
@@ -5275,6 +5287,8 @@ static int perf_read_one(struct perf_event *event,
 		values[n++] = running;
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(event);
+	if (read_format & PERF_FORMAT_LOST)
+		values[n++] = atomic64_read(&event->lost_samples);
 
 	if (copy_to_user(buf, values, n * sizeof(u64)))
 		return -EFAULT;
@@ -6754,7 +6768,7 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 				 u64 enabled, u64 running)
 {
 	u64 read_format = event->attr.read_format;
-	u64 values[4];
+	u64 values[5];
 	int n = 0;
 
 	values[n++] = perf_event_count(event);
@@ -6768,6 +6782,8 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 	}
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(event);
+	if (read_format & PERF_FORMAT_LOST)
+		values[n++] = atomic64_read(&event->lost_samples);
 
 	__output_copy(handle, values, n * sizeof(u64));
 }
@@ -6778,9 +6794,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
-	u64 values[5];
+	unsigned long flags;
+	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -6796,6 +6819,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	values[n++] = perf_event_count(leader);
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
+	if (read_format & PERF_FORMAT_LOST)
+		values[n++] = atomic64_read(&leader->lost_samples);
 
 	__output_copy(handle, values, n * sizeof(u64));
 
@@ -6809,9 +6834,13 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 		values[n++] = perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
+		if (read_format & PERF_FORMAT_LOST)
+			values[n++] = atomic64_read(&sub->lost_samples);
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
@@ -8785,7 +8814,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, data, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8815,7 +8844,7 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 				PERF_RECORD_KSYMBOL_TYPE_BPF,
 				(u64)(unsigned long)subprog->bpf_func,
 				subprog->jited_len, unregister,
-				prog->aux->ksym.name);
+				subprog->aux->ksym.name);
 		}
 	}
 }
@@ -9031,8 +9060,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle)
 		hwc->interrupts = 1;
 	} else {
 		hwc->interrupts++;
-		if (unlikely(throttle
-			     && hwc->interrupts >= max_samples_per_tick)) {
+		if (unlikely(throttle &&
+			     hwc->interrupts > max_samples_per_tick)) {
 			__this_cpu_inc(perf_throttled_count);
 			tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 			hwc->interrupts = MAX_INTERRUPTS;
@@ -10878,8 +10907,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
 
-		cpu_function_call(cpu,
-			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
+		cpu_function_call(cpu, perf_mux_hrtimer_restart_ipi, cpuctx);
 	}
 	cpus_read_unlock();
 	mutex_unlock(&mux_interval_mutex);
@@ -10891,9 +10919,30 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms);
 static struct attribute *pmu_dev_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_perf_event_mux_interval_ms.attr,
+	&dev_attr_nr_addr_filters.attr,
+	NULL,
+};
+
+static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pmu *pmu = dev_get_drvdata(dev);
+
+	if (n == 2 && !pmu->nr_addr_filters)
+		return 0;
+
+	return a->mode;
+}
+
+static struct attribute_group pmu_dev_attr_group = {
+	.is_visible = pmu_dev_is_visible,
+	.attrs = pmu_dev_attrs,
+};
+
+static const struct attribute_group *pmu_dev_groups[] = {
+	&pmu_dev_attr_group,
 	NULL,
 };
-ATTRIBUTE_GROUPS(pmu_dev);
 
 static int pmu_bus_running;
 static struct bus_type pmu_bus = {
@@ -10916,29 +10965,24 @@ static int pmu_dev_alloc(struct pmu *pmu)
 
 	pmu->dev->groups = pmu->attr_groups;
 	device_initialize(pmu->dev);
-	ret = dev_set_name(pmu->dev, "%s", pmu->name);
-	if (ret)
-		goto free_dev;
 
 	dev_set_drvdata(pmu->dev, pmu);
 	pmu->dev->bus = &pmu_bus;
 	pmu->dev->release = pmu_dev_release;
-	ret = device_add(pmu->dev);
+
+	ret = dev_set_name(pmu->dev, "%s", pmu->name);
 	if (ret)
 		goto free_dev;
 
-	/* For PMUs with address filters, throw in an extra attribute: */
-	if (pmu->nr_addr_filters)
-		ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters);
-
+	ret = device_add(pmu->dev);
 	if (ret)
-		goto del_dev;
+		goto free_dev;
 
-	if (pmu->attr_update)
+	if (pmu->attr_update) {
 		ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
-
-	if (ret)
-		goto del_dev;
+		if (ret)
+			goto del_dev;
+	}
 
 out:
 	return ret;
@@ -11742,7 +11786,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 	/*
 	 * If its not a per-cpu rb, it must be the same task.
 	 */
-	if (output_event->cpu == -1 && output_event->ctx != event->ctx)
+	if (output_event->cpu == -1 && output_event->hw.target != event->hw.target)
 		goto out;
 
 	/*
@@ -11901,12 +11945,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
-	/* Do we allow access to perf_event_open(2) ? */
-	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
 
-	err = perf_copy_attr(attr_uptr, &attr);
+	/* Do we allow access to perf_event_open(2) ? */
+	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
 	if (err)
 		return err;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 4032cd47500013ccad44618e5a5cefb9e8657052..ca27946fdaaf2faf5d7fc31a1da53b14cf89df0f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -172,8 +172,10 @@ __perf_output_begin(struct perf_output_handle *handle,
 		goto out;
 
 	if (unlikely(rb->paused)) {
-		if (rb->nr_pages)
+		if (rb->nr_pages) {
 			local_inc(&rb->lost);
+			atomic64_inc(&event->lost_samples);
+		}
 		goto out;
 	}
 
@@ -254,6 +256,7 @@ __perf_output_begin(struct perf_output_handle *handle,
 
 fail:
 	local_inc(&rb->lost);
+	atomic64_inc(&event->lost_samples);
 	perf_output_put_handle(handle);
 out:
 	rcu_read_unlock();
@@ -691,6 +694,12 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 		max_order--;
 	}
 
+	/*
+	 * kcalloc_node() is unable to allocate buffer if the size is larger
+	 * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+	 */
+	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+		return -ENOMEM;
 	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
 				     node);
 	if (!rb->aux_pages)
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index b25e150a257a66b77524a7f85ddeeb86b1d4d25e..446d86332dfa438cd03cf3a0a87b91d860ac560e 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -227,10 +227,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist)
 
 static void perf_evlist__id_hash(struct perf_evlist *evlist,
 				 struct perf_evsel *evsel,
-				 int cpu, int thread, u64 id)
+				 int cpu_map_idx, int thread, u64 id)
 {
 	int hash;
-	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+	struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread);
 
 	sid->id = id;
 	sid->evsel = evsel;
@@ -240,21 +240,27 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist,
 
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id)
+			 int cpu_map_idx, int thread, u64 id)
 {
-	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+	if (!SID(evsel, cpu_map_idx, thread))
+		return;
+
+	perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id);
 	evsel->id[evsel->ids++] = id;
 }
 
 int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd)
+			   int cpu_map_idx, int thread, int fd)
 {
 	u64 read_data[4] = { 0, };
 	int id_idx = 1; /* The first entry is the counter value */
 	u64 id;
 	int ret;
 
+	if (!SID(evsel, cpu_map_idx, thread))
+		return -1;
+
 	ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
 	if (!ret)
 		goto add;
@@ -283,7 +289,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 	id = read_data[id_idx];
 
 add:
-	perf_evlist__id_add(evlist, evsel, cpu, thread, id);
+	perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id);
 	return 0;
 }
 
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 2d0fa02b036f604646663ca5703bd13c12a00ae2..8999f2cc8ee44385e732fec8b7ef9044be3c0866 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -118,10 +118,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist);
 
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id);
+			 int cpu_map_idx, int thread, u64 id);
 
 int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd);
+			   int cpu_map_idx, int thread, int fd);
 
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 18d064026c1005fc7e63778eb87b729d82998366..ee273d65fd8d49c833eb1d47392c3e77ca6a40b7 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -261,7 +261,7 @@ endif
 # defined. get-executable-or-default fails with an error if the first argument is supplied but
 # doesn't exist.
 override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs  = $(filter-out -l%,$(1))
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 62a7b7420a448517a2474c816ec3f5bb5a88800e..fb3029495c23ccee66e5fa45e6ff1e8f27661b4c 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -21,6 +21,7 @@
 #include "builtin.h"
 #include "bench/bench.h"
 
+#include <locale.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -225,7 +226,6 @@ static void run_collection(struct collection *coll)
 		if (!bench->fn)
 			break;
 		printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
-		fflush(stdout);
 
 		argv[1] = bench->name;
 		run_bench(coll->name, bench->name, bench->fn, 1, argv);
@@ -246,6 +246,10 @@ int cmd_bench(int argc, const char **argv)
 	struct collection *coll;
 	int ret = 0;
 
+	/* Unbuffered output */
+	setvbuf(stdout, NULL, _IONBF, 0);
+	setlocale(LC_ALL, "");
+
 	if (argc < 2) {
 		/* No collection specified. */
 		print_usage();
@@ -299,7 +303,6 @@ int cmd_bench(int argc, const char **argv)
 
 			if (bench_format == BENCH_FORMAT_DEFAULT)
 				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
-			fflush(stdout);
 			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
 			goto end;
 		}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 08f1c2aeeedb24d661e8ca69b031149233962751..96c6a52d7f09fea4b88134306c44d3c379d170b3 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1264,8 +1264,8 @@ static int
 record__switch_output(struct record *rec, bool at_exit)
 {
 	struct perf_data *data = &rec->data;
+	char *new_filename = NULL;
 	int fd, err;
-	char *new_filename;
 
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 83b6ca10cc8f34103477d721a6f30a792fbfdeae..0a0aa3cf1dadea39cf45314ec435d877eb61b3f7 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);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8d55de9f1d3c54444ab279ec69632c36f627b051..ec22f7c50712b990d439a6b18939015afd8e689c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -295,8 +295,7 @@ static inline struct evsel_script *evsel_script(struct evsel *evsel)
 	return (struct evsel_script *)evsel->priv;
 }
 
-static struct evsel_script *perf_evsel_script__new(struct evsel *evsel,
-							struct perf_data *data)
+static struct evsel_script *evsel_script__new(struct evsel *evsel, struct perf_data *data)
 {
 	struct evsel_script *es = zalloc(sizeof(*es));
 
@@ -316,7 +315,7 @@ static struct evsel_script *perf_evsel_script__new(struct evsel *evsel,
 	return NULL;
 }
 
-static void perf_evsel_script__delete(struct evsel_script *es)
+static void evsel_script__delete(struct evsel_script *es)
 {
 	zfree(&es->filename);
 	fclose(es->fp);
@@ -324,7 +323,7 @@ static void perf_evsel_script__delete(struct evsel_script *es)
 	free(es);
 }
 
-static int perf_evsel_script__fprintf(struct evsel_script *es, FILE *fp)
+static int evsel_script__fprintf(struct evsel_script *es, FILE *fp)
 {
 	struct stat st;
 
@@ -2148,6 +2147,9 @@ static int process_sample_event(struct perf_tool *tool,
 	return 0;
 }
 
+// Used when scr->per_event_dump is not set
+static struct evsel_script es_stdout;
+
 static int process_attr(struct perf_tool *tool, union perf_event *event,
 			struct evlist **pevlist)
 {
@@ -2156,7 +2158,6 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct evsel *evsel, *pos;
 	u64 sample_type;
 	int err;
-	static struct evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -2167,14 +2168,12 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 
 	if (!evsel->priv) {
 		if (scr->per_event_dump) {
-			evsel->priv = perf_evsel_script__new(evsel,
-						scr->session->data);
-		} else {
-			es = zalloc(sizeof(*es));
-			if (!es)
+			evsel->priv = evsel_script__new(evsel, scr->session->data);
+			if (!evsel->priv)
 				return -ENOMEM;
-			es->fp = stdout;
-			evsel->priv = es;
+		} else { // Replicate what is done in perf_script__setup_per_event_dump()
+			es_stdout.fp = stdout;
+			evsel->priv = &es_stdout;
 		}
 	}
 
@@ -2423,7 +2422,7 @@ static void perf_script__fclose_per_event_dump(struct perf_script *script)
 	evlist__for_each_entry(evlist, evsel) {
 		if (!evsel->priv)
 			break;
-		perf_evsel_script__delete(evsel->priv);
+		evsel_script__delete(evsel->priv);
 		evsel->priv = NULL;
 	}
 }
@@ -2443,7 +2442,7 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 		if (evsel->priv != NULL)
 			continue;
 
-		evsel->priv = perf_evsel_script__new(evsel, script->session->data);
+		evsel->priv = evsel_script__new(evsel, script->session->data);
 		if (evsel->priv == NULL)
 			goto out_err_fclose;
 	}
@@ -2458,7 +2457,6 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 static int perf_script__setup_per_event_dump(struct perf_script *script)
 {
 	struct evsel *evsel;
-	static struct evsel_script es_stdout;
 
 	if (script->per_event_dump)
 		return perf_script__fopen_per_event_dump(script);
@@ -2478,8 +2476,8 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
 	evlist__for_each_entry(script->session->evlist, evsel) {
 		struct evsel_script *es = evsel->priv;
 
-		perf_evsel_script__fprintf(es, stdout);
-		perf_evsel_script__delete(es);
+		evsel_script__fprintf(es, stdout);
+		evsel_script__delete(es);
 		evsel->priv = NULL;
 	}
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a19887186a00e738d13921d47c99f66931243b76..c653de8f92e452250b32227283b632e613bfe4a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1739,6 +1739,7 @@ int cmd_top(int argc, const char **argv)
 	top.session = perf_session__new(NULL, false, NULL);
 	if (IS_ERR(top.session)) {
 		status = PTR_ERR(top.session);
+		top.session = NULL;
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a463ce8fb8e09b3c01d72ef83b32b4ec1cc47dd4..d037bd4fd298ff4c602370e5e856163585675c38 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -87,6 +87,8 @@
 # define F_LINUX_SPECIFIC_BASE	1024
 #endif
 
+#define RAW_SYSCALL_ARGS_NUM	6
+
 /*
  * strtoul: Go from a string to a value, i.e. for msr: MSR_FS_BASE to 0xc0000100
  */
@@ -107,7 +109,7 @@ struct syscall_fmt {
 		const char *sys_enter,
 			   *sys_exit;
 	}	   bpf_prog_name;
-	struct syscall_arg_fmt arg[6];
+	struct syscall_arg_fmt arg[RAW_SYSCALL_ARGS_NUM];
 	u8	   nr_args;
 	bool	   errpid;
 	bool	   timeout;
@@ -1216,7 +1218,7 @@ struct syscall {
  */
 struct bpf_map_syscall_entry {
 	bool	enabled;
-	u16	string_args_len[6];
+	u16	string_args_len[RAW_SYSCALL_ARGS_NUM];
 };
 
 /*
@@ -1641,7 +1643,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 {
 	int idx;
 
-	if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
+	if (nr_args == RAW_SYSCALL_ARGS_NUM && sc->fmt && sc->fmt->nr_args != 0)
 		nr_args = sc->fmt->nr_args;
 
 	sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
@@ -1774,11 +1776,11 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 #endif
 	sc = trace->syscalls.table + id;
 	if (sc->nonexistent)
-		return 0;
+		return -EEXIST;
 
 	if (name == NULL) {
 		sc->nonexistent = true;
-		return 0;
+		return -EEXIST;
 	}
 
 	sc->name = name;
@@ -1792,11 +1794,18 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 		sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 	}
 
-	if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
-		return -ENOMEM;
-
-	if (IS_ERR(sc->tp_format))
+	/*
+	 * Fails to read trace point format via sysfs node, so the trace point
+	 * doesn't exist.  Set the 'nonexistent' flag as true.
+	 */
+	if (IS_ERR(sc->tp_format)) {
+		sc->nonexistent = true;
 		return PTR_ERR(sc->tp_format);
+	}
+
+	if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ?
+					RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields))
+		return -ENOMEM;
 
 	sc->args = sc->tp_format->format.fields;
 	/*
@@ -2114,11 +2123,8 @@ static struct syscall *trace__syscall_info(struct trace *trace,
 	    (err = trace__read_syscall_info(trace, id)) != 0)
 		goto out_cant_read;
 
-	if (trace->syscalls.table[id].name == NULL) {
-		if (trace->syscalls.table[id].nonexistent)
-			return NULL;
+	if (trace->syscalls.table && trace->syscalls.table[id].nonexistent)
 		goto out_cant_read;
-	}
 
 	return &trace->syscalls.table[id];
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 132bdb3e6c31a0cb4e4d668b10445d992c92484b..73c911dd0c2cae2c9dae310363ad09c5fc281293 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -793,6 +793,9 @@ int cmd_test(int argc, const char **argv)
         if (ret < 0)
                 return ret;
 
+	/* Unbuffered output */
+	setvbuf(stdout, NULL, _IONBF, 0);
+
 	argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
 	if (argc >= 1 && !strcmp(argv[0], "list"))
 		return perf_test__list(argc - 1, argv + 1);
diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh
new file mode 100644
index 0000000000000000000000000000000000000000..00d2e0e2e0c28d65eb6ce8696d63936ef8aa86b2
--- /dev/null
+++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# test perf probe of function from different CU
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX)
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then
+		echo "--- Cleaning up ---"
+		perf probe -x ${temp_dir}/testfile -d foo
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+        cleanup
+        exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+cat > ${temp_dir}/testfile-foo.h << EOF
+struct t
+{
+  int *p;
+  int c;
+};
+
+extern int foo (int i, struct t *t);
+EOF
+
+cat > ${temp_dir}/testfile-foo.c << EOF
+#include "testfile-foo.h"
+
+int
+foo (int i, struct t *t)
+{
+  int j, res = 0;
+  for (j = 0; j < i && j < t->c; j++)
+    res += t->p[j];
+
+  return res;
+}
+EOF
+
+cat > ${temp_dir}/testfile-main.c << EOF
+#include "testfile-foo.h"
+
+static struct t g;
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  int j[argc];
+  g.c = argc;
+  g.p = j;
+  for (i = 0; i < argc; i++)
+    j[i] = (int) argv[i][0];
+  return foo (3, &g);
+}
+EOF
+
+gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o
+gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o
+gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o
+
+perf probe -x ${temp_dir}/testfile --funcs foo
+perf probe -x ${temp_dir}/testfile foo
+
+cleanup
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 933ce4f006944f56979f5aadd6d2175e7a38aa42..63d4ce691d9f58822dad8b6e4b6eacea4f91df77 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -407,11 +407,6 @@ static bool hist_browser__selection_has_children(struct hist_browser *browser)
 	return container_of(ms, struct callchain_list, ms)->has_children;
 }
 
-static bool hist_browser__he_selection_unfolded(struct hist_browser *browser)
-{
-	return browser->he_selection ? browser->he_selection->unfolded : false;
-}
-
 static bool hist_browser__selection_unfolded(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
 	return n;
 }
 
-static void __hist_entry__set_folding(struct hist_entry *he,
-				      struct hist_browser *hb, bool unfold)
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
@@ -603,34 +598,12 @@ static void __hist_entry__set_folding(struct hist_entry *he,
 		he->nr_rows = 0;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he,
-				    struct hist_browser *browser, bool unfold)
-{
-	double percent;
-
-	percent = hist_entry__get_percent_limit(he);
-	if (he->filtered || percent < browser->min_pcnt)
-		return;
-
-	__hist_entry__set_folding(he, browser, unfold);
-
-	if (!he->depth || unfold)
-		browser->nr_hierarchy_entries++;
-	if (he->leaf)
-		browser->nr_callchain_rows += he->nr_rows;
-	else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-		browser->nr_hierarchy_entries++;
-		he->has_no_entry = true;
-		he->nr_rows = 1;
-	} else
-		he->has_no_entry = false;
-}
-
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
 	struct hist_entry *he;
+	double percent;
 
 	nd = rb_first_cached(&browser->hists->entries);
 	while (nd) {
@@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
 
 		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
@@ -659,8 +647,10 @@ static void hist_browser__set_folding_selected(struct hist_browser *browser, boo
 	if (!browser->he_selection)
 		return;
 
-	hist_entry__set_folding(browser->he_selection, browser, unfold);
-	browser->b.nr_entries = hist_browser__nr_entries(browser);
+	if (unfold == browser->he_selection->unfolded)
+		return;
+
+	hist_browser__toggle_fold(browser);
 }
 
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
@@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l
 		hist_browser__set_folding(browser, true);
 		break;
 	case 'e':
-		/* Expand the selected entry. */
-		hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser));
+		/* Toggle expand/collapse the selected entry. */
+		hist_browser__toggle_fold(browser);
 		break;
 	case 'H':
 		browser->show_headers = !browser->show_headers;
@@ -1779,7 +1769,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 	hists_browser__scnprintf_hierarchy_headers(browser, headers,
 						   sizeof(headers));
 
-	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__gotorc_title(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b9edf33e4c6992db516c6076d03c9b133bf86bf5..1fe618a68691f58bc70651e0a3f01d60d1a81d63 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1730,8 +1730,11 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	perf_exe(tpath, sizeof(tpath));
 
 	bfdf = bfd_openr(tpath, NULL);
-	assert(bfdf);
-	assert(bfd_check_format(bfdf, bfd_object));
+	if (bfdf == NULL)
+		abort();
+
+	if (!bfd_check_format(bfdf, bfd_object))
+		abort();
 
 	s = open_memstream(&buf, &buf_size);
 	if (!s) {
@@ -1779,7 +1782,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 #else
 	disassemble = disassembler(bfdf);
 #endif
-	assert(disassemble);
+	if (disassemble == NULL)
+		abort();
 
 	fflush(s);
 	do {
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 6e43f665577d3732a903f614186ad6247bb161de..fb136eeea4471fc3ca1483e30d1b3d56dbb1eece 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -2289,11 +2289,19 @@ struct sym_args {
 	bool		near;
 };
 
+static bool kern_sym_name_match(const char *kname, const char *name)
+{
+	size_t n = strlen(name);
+
+	return !strcmp(kname, name) ||
+	       (!strncmp(kname, name, n) && kname[n] == '\t');
+}
+
 static bool kern_sym_match(struct sym_args *args, const char *name, char type)
 {
 	/* A function with the same name, and global or the n'th found or any */
 	return kallsyms__is_function(type) &&
-	       !strcmp(name, args->name) &&
+	       kern_sym_name_match(name, args->name) &&
 	       ((args->global && isupper(type)) ||
 		(args->selected && ++(args->cnt) == args->idx) ||
 		(!args->global && !args->selected));
@@ -2396,6 +2404,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
 			       char type, u64 start)
 {
 	struct sym_args *args = arg;
+	u64 size;
 
 	if (!kallsyms__is_function(type))
 		return 0;
@@ -2405,7 +2414,9 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
 		args->start = start;
 	}
 	/* Don't know exactly where the kernel ends, so we add a page */
-	args->size = round_up(start, page_size) + page_size - args->start;
+	size = round_up(start, page_size) + page_size - args->start;
+	if (size > args->size)
+		args->size = size;
 
 	return 0;
 }
@@ -2566,7 +2577,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 				*size = sym->start - *start;
 			if (idx > 0) {
 				if (*size)
-					return 1;
+					return 0;
 			} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
 				print_duplicate_syms(dso, sym_name);
 				return -EINVAL;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index c785191ec9b873263d4a7b258b30dec083f1f693..fccc4bf20c74f3aa69345a908ce3ad182eb5c28c 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -533,9 +533,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp)
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp)
 {
 	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
 	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
@@ -551,7 +551,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	if (info->btf_id) {
 		struct btf_node *node;
 
-		node = perf_env__find_btf(env, info->btf_id);
+		node = __perf_env__find_btf(env, info->btf_id);
 		if (node)
 			btf = btf__new((__u8 *)(node->data),
 				       node->data_size);
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 68f315c3df5bed03c85b7d4e758fe0fd66d7e3bc..50f7412464dfc25f71186568797cfdbd4a2f99a6 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -34,9 +34,9 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp);
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp);
 #else
 static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 				       union perf_event *event __maybe_unused,
@@ -51,9 +51,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
-						  struct perf_env *env __maybe_unused,
-						  FILE *fp __maybe_unused)
+static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						    struct perf_env *env __maybe_unused,
+						    FILE *fp __maybe_unused)
 {
 
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index d2c93063085735ed4bd976c6859faf78525257aa..b11219b68359b4029efbab0964e5040e3979081a 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -127,6 +127,7 @@ int perf_data__open_dir(struct perf_data *data)
 		file->size = st.st_size;
 	}
 
+	closedir(dir);
 	if (!files)
 		return -EINVAL;
 
@@ -135,6 +136,7 @@ int perf_data__open_dir(struct perf_data *data)
 	return 0;
 
 out_err:
+	closedir(dir);
 	close_dir(files, nr);
 	return ret;
 }
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 0af163abaa62b87f3d5a4fb841f64e8f84be394d..854dd3d2d8de395ae48e288e1a9b7e6e0f2fc02d 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -207,6 +207,10 @@ int perf_quiet_option(void)
 		opt++;
 	}
 
+	/* For debug variables that are used as bool types, set to 0. */
+	redirect_to_stderr = 0;
+	debug_peo_args = 0;
+
 	return 0;
 }
 
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 183a81d5b2f92c8dead68962fdd7d33862aa03a4..2db91121bdafee4154365cc74565d5dd51aa0ae1 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -20,8 +20,19 @@ static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
 	if (a->ino > b->ino) return -1;
 	if (a->ino < b->ino) return 1;
 
-	if (a->ino_generation > b->ino_generation) return -1;
-	if (a->ino_generation < b->ino_generation) return 1;
+	/*
+	 * Synthesized MMAP events have zero ino_generation, avoid comparing
+	 * them with MMAP events with actual ino_generation.
+	 *
+	 * I found it harmful because the mismatch resulted in a new
+	 * dso that did not have a build ID whereas the original dso did have a
+	 * build ID. The build ID was essential because the object was not found
+	 * otherwise. - Adrian
+	 */
+	if (a->ino_generation && b->ino_generation) {
+		if (a->ino_generation > b->ino_generation) return -1;
+		if (a->ino_generation < b->ino_generation) return 1;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 4343356f3cf9a3c6a7c13058f79986ffd657976c..443374a77c8dc6cc8433dbd3a3795e342166fc36 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -308,26 +308,13 @@ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name,
 {
 	Dwarf_Attribute attr;
 
-	if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+	if (dwarf_attr_integrate(tp_die, attr_name, &attr) == NULL ||
 	    dwarf_formudata(&attr, result) != 0)
 		return -ENOENT;
 
 	return 0;
 }
 
-/* Get attribute and translate it as a sdata */
-static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name,
-			      Dwarf_Sword *result)
-{
-	Dwarf_Attribute attr;
-
-	if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
-	    dwarf_formsdata(&attr, result) != 0)
-		return -ENOENT;
-
-	return 0;
-}
-
 /**
  * die_is_signed_type - Check whether a type DIE is signed or not
  * @tp_die: a DIE of a type
@@ -467,9 +454,9 @@ int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
 /* Get the call file index number in CU DIE */
 static int die_get_call_fileno(Dwarf_Die *in_die)
 {
-	Dwarf_Sword idx;
+	Dwarf_Word idx;
 
-	if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0)
+	if (die_get_attr_udata(in_die, DW_AT_call_file, &idx) == 0)
 		return (int)idx;
 	else
 		return -ENOENT;
@@ -478,9 +465,9 @@ static int die_get_call_fileno(Dwarf_Die *in_die)
 /* Get the declared file index number in CU DIE */
 static int die_get_decl_fileno(Dwarf_Die *pdie)
 {
-	Dwarf_Sword idx;
+	Dwarf_Word idx;
 
-	if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0)
+	if (die_get_attr_udata(pdie, DW_AT_decl_file, &idx) == 0)
 		return (int)idx;
 	else
 		return -ENOENT;
@@ -1094,7 +1081,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		ret = strbuf_add(buf, " (unknown_type)", 14);
+		ret = strbuf_add(buf, "(unknown_type)", 14);
 	}
 
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index b66e24fff0e4e19b5993abcf3998ec8721d0c30d..d9047177c06d7456950b364d15a7ae5c77d00b78 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -20,13 +20,19 @@ struct perf_env perf_env;
 
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node)
+{
+	down_write(&env->bpf_progs.lock);
+	__perf_env__insert_bpf_prog_info(env, info_node);
+	up_write(&env->bpf_progs.lock);
+}
+
+void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
 {
 	__u32 prog_id = info_node->info_linear->info.id;
 	struct bpf_prog_info_node *node;
 	struct rb_node *parent = NULL;
 	struct rb_node **p;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.infos.rb_node;
 
 	while (*p != NULL) {
@@ -38,15 +44,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env,
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated bpf prog info %u\n", prog_id);
-			goto out;
+			return;
 		}
 	}
 
 	rb_link_node(&info_node->rb_node, parent, p);
 	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
 	env->bpf_progs.infos_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
 }
 
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
@@ -75,14 +79,22 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 }
 
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
+	bool ret;
+
+	down_write(&env->bpf_progs.lock);
+	ret = __perf_env__insert_btf(env, btf_node);
+	up_write(&env->bpf_progs.lock);
+	return ret;
+}
+
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 {
 	struct rb_node *parent = NULL;
 	__u32 btf_id = btf_node->id;
 	struct btf_node *node;
 	struct rb_node **p;
-	bool ret = true;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.btfs.rb_node;
 
 	while (*p != NULL) {
@@ -94,25 +106,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated btf %u\n", btf_id);
-			ret = false;
-			goto out;
+			return false;
 		}
 	}
 
 	rb_link_node(&btf_node->rb_node, parent, p);
 	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
 	env->bpf_progs.btfs_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
-	return ret;
+	return true;
 }
 
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
+	struct btf_node *res;
+
+	down_read(&env->bpf_progs.lock);
+	res = __perf_env__find_btf(env, btf_id);
+	up_read(&env->bpf_progs.lock);
+	return res;
+}
+
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 {
 	struct btf_node *node = NULL;
 	struct rb_node *n;
 
-	down_read(&env->bpf_progs.lock);
 	n = env->bpf_progs.btfs.rb_node;
 
 	while (n) {
@@ -122,13 +140,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			goto out;
+			return node;
 	}
-	node = NULL;
-
-out:
-	up_read(&env->bpf_progs.lock);
-	return node;
+	return NULL;
 }
 
 /* purge data in bpf_progs.infos tree */
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1d847fea6a41b65e18a531eee54f8fce3c9b012c..8209c87743e7844d75d1f922cfc65c74ce5f241d 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -169,12 +169,16 @@ const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
 void perf_env__init(struct perf_env *env);
+void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, int cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0025e121969edf80fe4772a989d4b6efe6d14ea0..cf5fda44b49f7dd006d32b7e87ffc4aeb013e7de 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2174,7 +2174,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	data->period = evsel->core.attr.sample_period;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	data->misc    = event->header.misc;
-	data->id = -1ULL;
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index aed49806a09bab8f9a835fc965bca33fec796c2c..3a43997b03a75f5dd8522597912affca192c6e50 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -247,6 +247,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	Elf_Data *d;
 	Elf_Scn *scn;
 	Elf_Ehdr *ehdr;
+	Elf_Phdr *phdr;
 	Elf_Shdr *shdr;
 	uint64_t eh_frame_base_offset;
 	char *strsym = NULL;
@@ -281,6 +282,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	ehdr->e_version = EV_CURRENT;
 	ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */
 
+	/*
+	 * setup program header
+	 */
+	phdr = elf_newphdr(e, 1);
+	phdr[0].p_type = PT_LOAD;
+	phdr[0].p_offset = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_filesz = csize;
+	phdr[0].p_memsz = csize;
+	phdr[0].p_flags = PF_X | PF_R;
+	phdr[0].p_align = 8;
+
 	/*
 	 * setup text section
 	 */
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index fdeef73cf85f4458cce1d8e040ce6d6fa2291c43..43dac6998d2b5d02dae4a40de3a89190ca660101 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -53,8 +53,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 
 #if GEN_ELF_CLASS == ELFCLASS64
 #define elf_newehdr	elf64_newehdr
+#define elf_newphdr	elf64_newphdr
 #define elf_getshdr	elf64_getshdr
 #define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Phdr	Elf64_Phdr
 #define Elf_Shdr	Elf64_Shdr
 #define Elf_Sym		Elf64_Sym
 #define ELF_ST_TYPE(a)	ELF64_ST_TYPE(a)
@@ -62,8 +64,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #define ELF_ST_VIS(a)	ELF64_ST_VISIBILITY(a)
 #else
 #define elf_newehdr	elf32_newehdr
+#define elf_newphdr	elf32_newphdr
 #define elf_getshdr	elf32_getshdr
 #define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Phdr	Elf32_Phdr
 #define Elf_Shdr	Elf32_Shdr
 #define Elf_Sym		Elf32_Sym
 #define ELF_ST_TYPE(a)	ELF32_ST_TYPE(a)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8ef6fefea33978adc252b0e146f70cecb8184d91..7e10ccd940ef04263a424e404b4f1df8b6ed25ea 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1757,8 +1757,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		bpf_event__print_bpf_prog_info(&node->info_linear->info,
-					       env, fp);
+		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
+						 env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -3082,7 +3082,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		/* after reading from file, translate offset to address */
 		bpf_program__bpil_offs_to_addr(info_linear);
 		info_node->info_linear = info_linear;
-		perf_env__insert_bpf_prog_info(env, info_node);
+		__perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
 	up_write(&env->bpf_progs.lock);
@@ -3129,7 +3129,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 		if (__do_read(ff, node->data, data_size))
 			goto out;
 
-		perf_env__insert_btf(env, node);
+		__perf_env__insert_btf(env, node);
 		node = NULL;
 	}
 
@@ -4262,7 +4262,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct evlist **pevlist)
 {
-	u32 i, ids, n_ids;
+	u32 i, n_ids;
+	u64 *ids;
 	struct evsel *evsel;
 	struct evlist *evlist = *pevlist;
 
@@ -4278,9 +4279,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 
 	evlist__add(evlist, evsel);
 
-	ids = event->header.size;
-	ids -= (void *)&event->attr.id - (void *)event;
-	n_ids = ids / sizeof(u64);
+	n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+	n_ids = n_ids / sizeof(u64);
 	/*
 	 * We don't have the cpu and thread maps on the header, so
 	 * for allocating the perf_sample_id table we fake 1 cpu and
@@ -4289,8 +4289,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
+	ids = (void *)&event->attr.attr + event->attr.attr.size;
 	for (i = 0; i < n_ids; i++) {
-		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
 	}
 
 	return 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3d11fa6221261438f79a276145ed7b13a5cfd54c..9f1267734b1502b676e977bdf759ef10ae28d0b2 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2638,8 +2638,6 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 
 	/* If we have branch cycles always annotate them. */
 	if (bs && bs->nr && entries[0].flags.cycles) {
-		int i;
-
 		bi = sample__resolve_bstack(sample, al);
 		if (bi) {
 			struct addr_map_symbol *prev = NULL;
@@ -2654,7 +2652,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			 * Note that perf stores branches reversed from
 			 * program order!
 			 */
-			for (i = bs->nr - 1; i >= 0; i--) {
+			for (int i = bs->nr - 1; i >= 0; i--) {
 				addr_map_symbol__account_cycles(&bi[i].from,
 					nonany_branch_mode ? NULL : prev,
 					bi[i].flags.cycles);
@@ -2663,6 +2661,12 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 				if (total_cycles)
 					*total_cycles += bi[i].flags.cycles;
 			}
+			for (unsigned int i = 0; i < bs->nr; i++) {
+				map__put(bi[i].to.ms.map);
+				maps__put(bi[i].to.ms.maps);
+				map__put(bi[i].from.ms.map);
+				maps__put(bi[i].from.ms.maps);
+			}
 			free(bi);
 		}
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e4c485f92c0289c77d2e8e4fc52433a80234bfbf..48fda1a19ab5b34407bae703c2590052ce47155d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1639,6 +1639,8 @@ static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
 
 	decoder->cbr = cbr;
 	decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr;
+	decoder->cyc_ref_timestamp = decoder->timestamp;
+	decoder->cycle_cnt = 0;
 
 	intel_pt_mtc_cyc_cnt_cbr(decoder);
 }
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 9454beeffae17d474468f8e7e868ef23c5a3d32a..306d17a3f4c7d1097901a73c08046e65397848b6 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -3295,6 +3295,7 @@ static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_SNAPSHOT_MODE]	= "  Snapshot mode       %"PRId64"\n",
 	[INTEL_PT_PER_CPU_MMAPS]	= "  Per-cpu maps        %"PRId64"\n",
 	[INTEL_PT_MTC_BIT]		= "  MTC bit             %#"PRIx64"\n",
+	[INTEL_PT_MTC_FREQ_BITS]	= "  MTC freq bits       %#"PRIx64"\n",
 	[INTEL_PT_TSC_CTC_N]		= "  TSC:CTC numerator   %"PRIu64"\n",
 	[INTEL_PT_TSC_CTC_D]		= "  TSC:CTC denominator %"PRIu64"\n",
 	[INTEL_PT_CYC_BIT]		= "  CYC bit             %#"PRIx64"\n",
@@ -3309,8 +3310,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish)
 	if (!dump_trace)
 		return;
 
-	for (i = start; i <= finish; i++)
-		fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
+	for (i = start; i <= finish; i++) {
+		const char *fmt = intel_pt_info_fmts[i];
+
+		if (fmt)
+			fprintf(stdout, fmt, arr[i]);
+	}
 }
 
 static void intel_pt_print_info_str(const char *name, const char *str)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61b27ee56a9f85503e031fb23703a547daf8d81f..84e2ccc2fe1fe0138caf57708d4968e449f96b6d 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2398,16 +2398,18 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 		save_lbr_cursor_node(thread, cursor, i);
 	}
 
-	/* Add LBR ip from first entries.to */
-	ip = entries[0].to;
-	flags = &entries[0].flags;
-	*branch_from = entries[0].from;
-	err = add_callchain_ip(thread, cursor, parent,
-			       root_al, &cpumode, ip,
-			       true, flags, NULL,
-			       *branch_from);
-	if (err)
-		return err;
+	if (lbr_nr > 0) {
+		/* Add LBR ip from first entries.to */
+		ip = entries[0].to;
+		flags = &entries[0].flags;
+		*branch_from = entries[0].from;
+		err = add_callchain_ip(thread, cursor, parent,
+				root_al, &cpumode, ip,
+				true, flags, NULL,
+				*branch_from);
+		if (err)
+			return err;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 93a02864ba3896b134c8933e6962880c45274917..91a99957feb6d79ff580ffab7a087905eeccc3bf 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -361,6 +361,9 @@ __add_event(struct list_head *list, int *idx,
 	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
+	if (pmu)
+		perf_pmu__warn_invalid_formats(pmu);
+
 	if (pmu && attr->type == PERF_TYPE_RAW)
 		perf_pmu__warn_invalid_config(pmu, attr->config, name);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f827299f7249038235c0919987a4ccf558b75661..530055f15554cc6ac47ebfa91ab18300068d928d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -983,6 +983,23 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	return pmu;
 }
 
+void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
+{
+	struct perf_pmu_format *format;
+
+	/* fake pmu doesn't have format list */
+	if (pmu == &perf_pmu__fake)
+		return;
+
+	list_for_each_entry(format, &pmu->format, list)
+		if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) {
+			pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'"
+				   "which is not supported by this version of perf!\n",
+				   pmu->name, format->name, format->value);
+			return;
+		}
+}
+
 static struct perf_pmu *pmu_find(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -1774,7 +1791,7 @@ static int perf_pmu__new_caps(struct list_head *list, char *name, char *value)
 	return 0;
 
 free_name:
-	zfree(caps->name);
+	zfree(&caps->name);
 free_caps:
 	free(caps);
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 3fba6048182b639559dcb5e3fde3eceefc6de756..fc7bcb3404612c01dca630969bc791b3f7e0d8bf 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -16,6 +16,7 @@ enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
 	PERF_PMU_FORMAT_VALUE_CONFIG1,
 	PERF_PMU_FORMAT_VALUE_CONFIG2,
+	PERF_PMU_FORMAT_VALUE_CONFIG_END,
 };
 
 #define PERF_PMU_FORMAT_BITS 64
@@ -136,5 +137,6 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *name);
 double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__match(char *pattern, char *name, char *tok);
+void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l
index a15d9fbd7c0ed99512b0163ffe26bdb8eaf313bf..58b4926cfaca906dab6f6f85bd7f359c943f166d 100644
--- a/tools/perf/util/pmu.l
+++ b/tools/perf/util/pmu.l
@@ -27,8 +27,6 @@ num_dec         [0-9]+
 
 {num_dec}	{ return value(10); }
 config		{ return PP_CONFIG; }
-config1		{ return PP_CONFIG1; }
-config2		{ return PP_CONFIG2; }
 -		{ return '-'; }
 :		{ return ':'; }
 ,		{ return ','; }
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index bfd7e8509869b64b53fbcbcddafe89a4a73b93b3..283efe059819d81ddb12c35c7147a20d8300ff0b 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -20,7 +20,7 @@ do { \
 
 %}
 
-%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_CONFIG
 %token PP_VALUE PP_ERROR
 %type <num> PP_VALUE
 %type <bits> bit_term
@@ -47,18 +47,11 @@ PP_CONFIG ':' bits
 				      $3));
 }
 |
-PP_CONFIG1 ':' bits
+PP_CONFIG PP_VALUE ':' bits
 {
 	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG1,
-				      $3));
-}
-|
-PP_CONFIG2 ':' bits
-{
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG2,
-				      $3));
+				      $2,
+				      $4));
 }
 
 bits:
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d103084fcd56cbf5db6df63b305a716a12aea3dc..97e2a72bd6f5e2fe5b6672d3a3682a8adb77c6e4 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1760,8 +1760,10 @@ int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev)
 	if (!pev->event && pev->point.function && pev->point.line
 			&& !pev->point.lazy_line && !pev->point.offset) {
 		if (asprintf(&pev->event, "%s_L%d", pev->point.function,
-			pev->point.line) < 0)
-			return -ENOMEM;
+			pev->point.line) < 0) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	/* Copy arguments and ensure return probe has no C argument */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 6eca56ff5684c26d5e0c1befdc82e39cffe137b7..d323e4b8b77e76877e9fec6263c68f38fc7028e7 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -873,8 +873,7 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct addr_map_symbol *from_l = &left->branch_info->from;
-	struct addr_map_symbol *from_r = &right->branch_info->from;
+	struct addr_map_symbol *from_l, *from_r;
 
 	if (!left->branch_info || !right->branch_info)
 		return cmp_null(left->branch_info, right->branch_info);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 96fe9c1af33644b71393dffb16d1c5c86a0a5342..4a866e6a081500b18974fce7fca35e17328e4dd7 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -271,7 +271,7 @@ static void print_metric_only(struct perf_stat_config *config,
 	if (color)
 		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
 
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val);
 	fprintf(out, "%*s ", mlen, str);
 }
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 94809aed8b447c6ffd71f7e553ff6cf2581f26d2..b171d134ce87aaa2789d6b01ab54863baa58225a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -232,6 +232,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
+{
+	size_t i, phdrnum;
+	u64 sz;
+
+	if (elf_getphdrnum(elf, &phdrnum))
+		return -1;
+
+	for (i = 0; i < phdrnum; i++) {
+		if (gelf_getphdr(elf, i, phdr) == NULL)
+			return -1;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		sz = max(phdr->p_memsz, phdr->p_filesz);
+		if (!sz)
+			continue;
+
+		if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz))
+			return 0;
+	}
+
+	/* Not found any valid program header */
+	return -1;
+}
+
 static bool want_demangle(bool is_kernel_sym)
 {
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
@@ -521,7 +548,7 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 				size_t sz = min(size, descsz);
 				memcpy(bf, ptr, sz);
 				memset(bf + sz, 0, size - sz);
-				err = descsz;
+				err = sz;
 				break;
 			}
 		}
@@ -1181,6 +1208,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 					sym.st_value);
 			used_opd = true;
 		}
+
 		/*
 		 * When loading symbols in a data mapping, ABS symbols (which
 		 * has a value of SHN_ABS in its st_shndx) failed at
@@ -1217,11 +1245,33 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
-			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
-				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
-				  (u64)sym.st_value, (u64)shdr.sh_addr,
-				  (u64)shdr.sh_offset);
-			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+			GElf_Phdr phdr;
+
+			if (elf_read_program_header(runtime_ss->elf,
+						    (u64)sym.st_value, &phdr)) {
+				pr_debug4("%s: failed to find program header for "
+					   "symbol: %s st_value: %#" PRIx64 "\n",
+					   __func__, elf_name, (u64)sym.st_value);
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)shdr.sh_addr,
+					(u64)shdr.sh_offset);
+				/*
+				 * Fail to find program header, let's rollback
+				 * to use shdr.sh_addr and shdr.sh_offset to
+				 * calibrate symbol's file address, though this
+				 * is not necessary for normal C ELF file, we
+				 * still need to handle java JIT symbols in this
+				 * case.
+				 */
+				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+			} else {
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+					(u64)phdr.p_offset);
+				sym.st_value -= phdr.p_vaddr - phdr.p_offset;
+			}
 		}
 
 		demangled = demangle_sym(dso, kmodule, elf_name);
@@ -1952,8 +2002,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
  * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
  * is not the same for the kernel map and the modules map.  That happens because
  * the data is copied adjacently whereas the original kcore has gaps.  Finally,
- * kallsyms and modules files are compared with their copies to check that
- * modules have not been loaded or unloaded while the copies were taking place.
+ * kallsyms file is compared with its copy to check that modules have not been
+ * loaded or unloaded while the copies were taking place.
  *
  * Return: %0 on success, %-1 on failure.
  */
@@ -2016,9 +2066,6 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 			goto out_extract_close;
 	}
 
-	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
-		goto out_extract_close;
-
 	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
 		goto out_extract_close;
 
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index c9bfe4696943b10e4c8a04abd5ed1a55d6207545..cee7fc3b5bb0c0b731e6a5946b9dbc42ca060168 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -279,13 +279,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		threads->nr = ntasks;
 	}
 out:
+	strlist__delete(slist);
 	if (threads)
 		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
 	zfree(&threads);
-	strlist__delete(slist);
 	goto out;
 }