diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index bada8933fdd4..ad60c6ea1997 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -125,6 +125,8 @@ To limit the list use:
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
+. As a last resort, it will do a substring search in all event names.
+
 One or more types can be used at the same time, listing the events for the
 types specified.
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 47469abdcc1c..4e074a660826 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -128,8 +128,9 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m
 
 -I msecs::
 --interval-print msecs::
-	Print count deltas every N milliseconds (minimum: 100ms)
-	example: perf stat -I 1000 -e cycles -a sleep 5
+Print count deltas every N milliseconds (minimum: 10ms)
+The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
+	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 602414040344..bf679e2c978b 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -45,6 +45,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	for (i = 0; i < argc; ++i) {
+		char *sep, *s;
+
 		if (strcmp(argv[i], "tracepoint") == 0)
 			print_tracepoint_events(NULL, NULL, raw_dump);
 		else if (strcmp(argv[i], "hw") == 0 ||
@@ -60,8 +62,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, raw_dump);
-		else {
-			char *sep = strchr(argv[i], ':'), *s;
+		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;
 
 			if (sep == NULL) {
@@ -76,6 +77,19 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			s[sep_idx] = '\0';
 			print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
 			free(s);
+		} else {
+			if (asprintf(&s, "*%s*", argv[i]) < 0) {
+				printf("Critical: Not enough memory! Trying to continue...\n");
+				continue;
+			}
+			print_symbol_events(s, PERF_TYPE_HARDWARE,
+					    event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
+			print_symbol_events(s, PERF_TYPE_SOFTWARE,
+					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+			print_hwcache_events(s, raw_dump);
+			print_pmu_events(s, raw_dump);
+			print_tracepoint_events(NULL, s, raw_dump);
+			free(s);
 		}
 	}
 	return 0;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f7882ae9ebc6..530c3a28a58c 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -182,10 +182,8 @@ static int opt_set_target(const struct option *opt, const char *str,
 	if  (str) {
 		if (!strcmp(opt->long_name, "exec"))
 			params.uprobes = true;
-#ifdef HAVE_DWARF_SUPPORT
 		else if (!strcmp(opt->long_name, "module"))
 			params.uprobes = false;
-#endif
 		else
 			return ret;
 
@@ -490,9 +488,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
 		   "directory", "path to kernel source"),
-	OPT_CALLBACK('m', "module", NULL, "modname|path",
-		"target module name (for online) or path (for offline)",
-		opt_set_target),
 	OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
 		"Don't search inlined functions"),
 #endif
@@ -509,6 +504,9 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		     opt_set_filter),
 	OPT_CALLBACK('x', "exec", NULL, "executable|path",
 			"target executable name or path", opt_set_target),
+	OPT_CALLBACK('m', "module", NULL, "modname|path",
+		"target module name (for online) or path (for offline)",
+		opt_set_target),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a01c8ae1ee07..24ace2f318c1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,7 +49,7 @@ struct record {
 	int			realtime_prio;
 	bool			no_buildid;
 	bool			no_buildid_cache;
-	long			samples;
+	unsigned long long	samples;
 };
 
 static int record__write(struct record *rec, void *bf, size_t size)
@@ -637,17 +637,25 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * Let the child rip
 	 */
 	if (forks) {
-		union perf_event event;
+		union perf_event *event;
+
+		event = malloc(sizeof(event->comm) + machine->id_hdr_size);
+		if (event == NULL) {
+			err = -ENOMEM;
+			goto out_child;
+		}
+
 		/*
 		 * Some H/W events are generated before COMM event
 		 * which is emitted during exec(), so perf script
 		 * cannot see a correct process name for those events.
 		 * Synthesize COMM event to prevent it.
 		 */
-		perf_event__synthesize_comm(tool, &event,
+		perf_event__synthesize_comm(tool, event,
 					    rec->evlist->workload.pid,
 					    process_synthesized_event,
 					    machine);
+		free(event);
 
 		perf_evlist__start_workload(rec->evlist);
 	}
@@ -659,7 +667,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	auxtrace_snapshot_enabled = 1;
 	for (;;) {
-		int hits = rec->samples;
+		unsigned long long hits = rec->samples;
 
 		if (record__mmap_read_all(rec) < 0) {
 			auxtrace_snapshot_enabled = 0;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a96fb5c3bedb..5ef88f760b12 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1179,7 +1179,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 100)"),
+		    "print counts at regular interval in ms (>= 10)"),
 	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
@@ -1332,9 +1332,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		thread_map__read_comms(evsel_list->threads);
 
 	if (interval && interval < 100) {
-		pr_err("print interval must be >= 100ms\n");
-		parse_options_usage(stat_usage, options, "I", 1);
-		goto out;
+		if (interval < 10) {
+			pr_err("print interval must be >= 10ms\n");
+			parse_options_usage(stat_usage, options, "I", 1);
+			goto out;
+		} else
+			pr_warning("print interval < 100ms. "
+				   "The overhead percentage could be high in some cases. "
+				   "Please proceed with caution.\n");
 	}
 
 	if (perf_evlist__alloc_stats(evsel_list, interval))
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 38d4d6cac823..6f641fd68296 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -857,9 +857,12 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			 * TODO: we don't process guest user from host side
 			 * except simple counting.
 			 */
-			/* Fall thru */
-		default:
 			goto next_event;
+		default:
+			if (event->header.type == PERF_RECORD_SAMPLE)
+				goto next_event;
+			machine = &session->machines.host;
+			break;
 		}
 
 
@@ -961,6 +964,9 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
+	if (perf_session__register_idle_thread(top->session) == NULL)
+		goto out_delete;
+
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->threads, false, opts->proc_map_timeout);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0cad9e07c5b4..c346b331b892 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1151,7 +1151,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	struct perf_evsel *evsel = hists_to_evsel(hists);
 	bool use_callchain;
 
-	if (evsel && !symbol_conf.show_ref_callgraph)
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
 		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
 	else
 		use_callchain = symbol_conf.use_callchain;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 76fe167c359e..5ef90be2a249 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1831,7 +1831,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+	if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) {
 		pr_warning("corrupted callchain. skipping...\n");
 		return 0;
 	}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 41a356ba3cfe..e4b173dec4b9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1008,7 +1008,8 @@ void print_pmu_events(const char *event_glob, bool name_only)
 				goto out_enomem;
 			j++;
 		}
-		if (pmu->selectable) {
+		if (pmu->selectable &&
+		    (event_glob == NULL || strglobmatch(pmu->name, event_glob))) {
 			char *s;
 			if (asprintf(&s, "%s//", pmu->name) < 0)
 				goto out_enomem;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 3010abc071ff..b51a8bfb40f9 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2543,7 +2543,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		goto out;
 	}
 
-	if (!pev->uprobes && !pp->retprobe) {
+	/* Note that the symbols in the kmodule are not relocated */
+	if (!pev->uprobes && !pp->retprobe && !pev->target) {
 		reloc_sym = kernel_get_ref_reloc_sym();
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
@@ -2580,8 +2581,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		}
 		/* Add one probe point */
 		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
-		/* If we found a wrong one, mark it by NULL symbol */
-		if (!pev->uprobes &&
+
+		/* Check the kprobe (not in module) is within .text  */
+		if (!pev->uprobes && !pev->target &&
 		    kprobe_warn_out_range(sym->name, tp->address)) {
 			tp->symbol = NULL;	/* Skip it */
 			skipped++;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 84a02eae4394..428149bc64d2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1311,7 +1311,7 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
-static struct thread *perf_session__register_idle_thread(struct perf_session *session)
+struct thread *perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b44afc75d1cc..3e900c0efc73 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -89,6 +89,8 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_
 }
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
+struct thread *perf_session__register_idle_thread(struct perf_session *session);
+
 size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
 size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp);