diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 052f7c4dc00c..43b42c4f4a91 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -201,6 +201,12 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
+--force-per-cpu::
+Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
+-t or -u options) per-thread mmaps are created.  This option overrides that and
+forces per-cpu mmaps.  A side-effect of that is that inheritance is
+automatically enabled.  Add the -i option also to disable inheritance.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 89acc17cf2a0..6ea9e85bdc00 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -325,6 +325,8 @@ int 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_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+		    "Disable symbol demangling"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4d644fe2d5b7..7c8020a32784 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -888,6 +888,8 @@ const struct option record_options[] = {
 		    "sample by weight (on special events only)"),
 	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
 		    "sample transaction flags (special events only)"),
+	OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
+		    "force the use of per-cpu mmaps"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b8f8e29db332..71e6402729a8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1172,7 +1172,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	status = target__validate(target);
 	if (status) {
 		target__strerror(target, status, errbuf, BUFSIZ);
-		ui__warning("%s", errbuf);
+		ui__warning("%s\n", errbuf);
 	}
 
 	status = target__parse_uid(target);
@@ -1180,7 +1180,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		int saved_errno = errno;
 
 		target__strerror(target, status, errbuf, BUFSIZ);
-		ui__error("%s", errbuf);
+		ui__error("%s\n", errbuf);
 
 		status = -saved_errno;
 		goto out_delete_evlist;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6b230af940e2..8be17fc462ba 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2112,9 +2112,9 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 
 	printed += fprintf(fp, "\n");
 
-	printed += fprintf(fp, "                                                    msec/call\n");
-	printed += fprintf(fp, "   syscall            calls      min      avg      max stddev\n");
-	printed += fprintf(fp, "   --------------- -------- -------- -------- -------- ------\n");
+	printed += fprintf(fp, "   syscall            calls      min       avg       max      stddev\n");
+	printed += fprintf(fp, "                               (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- -------- --------- --------- ---------     ------\n");
 
 	/* each int_node is a syscall */
 	while (inode) {
@@ -2131,9 +2131,9 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 
 			sc = &trace->syscalls.table[inode->i];
 			printed += fprintf(fp, "   %-15s", sc->name);
-			printed += fprintf(fp, " %8" PRIu64 " %8.3f %8.3f",
+			printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f",
 					   n, min, avg);
-			printed += fprintf(fp, " %8.3f %6.2f\n", max, pct);
+			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 		}
 
 		inode = intlist__next(inode);
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index ef671cd41bb3..3cbd10496087 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -441,9 +441,8 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist)
 
 static int test__checkevent_pmu_events(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
 
-	evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong exclude_user",
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index bbc782e364b0..cbaa7af45513 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -569,7 +569,7 @@ void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence)
 		browser->top = browser->top + browser->top_idx + offset;
 		break;
 	case SEEK_END:
-		browser->top = browser->top + browser->nr_entries + offset;
+		browser->top = browser->top + browser->nr_entries - 1 + offset;
 		break;
 	default:
 		return;
@@ -680,7 +680,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 	if (end >= browser->top_idx + browser->height)
 		end_row = browser->height - 1;
 	else
-		end_row = end - browser->top_idx;;
+		end_row = end - browser->top_idx;
 
 	ui_browser__gotorc(browser, row, column);
 	SLsmg_draw_vline(end_row - row + 1);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 16848bb4c418..a440e03cd8c2 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1847,15 +1847,15 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 			switch (key) {
 			case K_TAB:
 				if (pos->node.next == &evlist->entries)
-					pos = list_entry(evlist->entries.next, struct perf_evsel, node);
+					pos = perf_evlist__first(evlist);
 				else
-					pos = list_entry(pos->node.next, struct perf_evsel, node);
+					pos = perf_evsel__next(pos);
 				goto browse_hists;
 			case K_UNTAB:
 				if (pos->node.prev == &evlist->entries)
-					pos = list_entry(evlist->entries.prev, struct perf_evsel, node);
+					pos = perf_evlist__last(evlist);
 				else
-					pos = list_entry(pos->node.prev, struct perf_evsel, node);
+					pos = perf_evsel__prev(pos);
 				goto browse_hists;
 			case K_ESC:
 				if (!ui_browser__dialog_yesno(&menu->b,
@@ -1943,8 +1943,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 
 single_entry:
 	if (nr_entries == 1) {
-		struct perf_evsel *first = list_entry(evlist->entries.next,
-						      struct perf_evsel, node);
+		struct perf_evsel *first = perf_evlist__first(evlist);
 		const char *ev_name = perf_evsel__name(first);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6e3a846aed0e..bb788c109fe6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -209,8 +209,10 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		       &event->mmap.start, &event->mmap.len, prot,
 		       &event->mmap.pgoff,
 		       execname);
-
-		if (n != 5)
+		/*
+ 		 * Anon maps don't have the execname.
+ 		 */
+		if (n < 4)
 			continue;
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dc6fa3fbb180..bbc746aa5716 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,7 +819,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target__has_task(target))
+	if (target->force_per_cpu)
+		evlist->cpus = cpu_map__new(target->cpu_list);
+	else if (target__has_task(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else if (!target__has_cpu(target) && !target->uses_mmap)
 		evlist->cpus = cpu_map__dummy_new();
@@ -1148,7 +1150,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 				   perf_evsel__name(evsel));
 	}
 
-	return printed + fprintf(fp, "\n");;
+	return printed + fprintf(fp, "\n");
 }
 
 int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 18f7c188ff63..46dd4c2a41ce 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -645,7 +645,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (target__has_cpu(&opts->target))
+	if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -653,7 +653,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target)))
+	     target__has_cpu(&opts->target) || opts->target.force_per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f5029653dcd7..1ea7c92e6e33 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -279,6 +279,11 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
 
+static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel)
+{
+	return list_entry(evsel->node.prev, struct perf_evsel, node);
+}
+
 /**
  * perf_evsel__is_group_leader - Return whether given evsel is a leader event
  *
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 0393912d8033..84cdb072ac83 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1368,7 +1368,7 @@ int machine__resolve_callchain(struct machine *machine,
 
 	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
 				   thread, evsel->attr.sample_regs_user,
-				   sample);
+				   sample, max_stack);
 
 }
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 89bab7129de4..2d0c50690892 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,6 +12,7 @@ struct target {
 	uid_t	     uid;
 	bool	     system_wide;
 	bool	     uses_mmap;
+	bool	     force_per_cpu;
 };
 
 enum target_errno {
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 5390d0b8862a..0efd5393de85 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -559,7 +559,7 @@ static unw_accessors_t accessors = {
 };
 
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-		       void *arg)
+		       void *arg, int max_stack)
 {
 	unw_addr_space_t addr_space;
 	unw_cursor_t c;
@@ -575,7 +575,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	if (ret)
 		display_error(ret);
 
-	while (!ret && (unw_step(&c) > 0)) {
+	while (!ret && (unw_step(&c) > 0) && max_stack--) {
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
@@ -588,7 +588,8 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine, struct thread *thread,
-			u64 sample_uregs, struct perf_sample *data)
+			u64 sample_uregs, struct perf_sample *data,
+			int max_stack)
 {
 	unw_word_t ip;
 	struct unwind_info ui = {
@@ -610,5 +611,5 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (ret)
 		return -ENOMEM;
 
-	return get_entries(&ui, cb, arg);
+	return get_entries(&ui, cb, arg, max_stack);
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index ec0c71a2ca2e..d5966f49e22c 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -18,7 +18,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine,
 			struct thread *thread,
 			u64 sample_uregs,
-			struct perf_sample *data);
+			struct perf_sample *data, int max_stack);
 int unwind__arch_reg_id(int regnum);
 #else
 static inline int
@@ -27,7 +27,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    u64 sample_uregs __maybe_unused,
-		    struct perf_sample *data __maybe_unused)
+		    struct perf_sample *data __maybe_unused,
+		    int max_stack __maybe_unused)
 {
 	return 0;
 }