6 files changed, 289 insertions, 58 deletions

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d7e727345dab..135d6ce88fb3 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -754,7 +754,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				hbt->timer(hbt->arg);
 
 			if (delay_secs != 0) {
-				symbol__annotate_decay_histogram(sym, evsel->core.idx);
+				symbol__annotate_decay_histogram(sym, evsel);
 				hists__scnprintf_title(hists, title, sizeof(title));
 				annotate_browser__show(&browser->b, title, help);
 			}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 49ba82bf3391..992d1c822a97 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1226,7 +1226,7 @@ int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 	return ret;
 }
 
-#define __HPP_COLOR_PERCENT_FN(_type, _field)				\
+#define __HPP_COLOR_PERCENT_FN(_type, _field, _fmttype)			\
 static u64 __hpp_get_##_field(struct hist_entry *he)			\
 {									\
 	return he->stat._field;						\
@@ -1238,10 +1238,10 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct hist_entry *he)			\
 {									\
 	return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%",	\
-			__hpp__slsmg_color_printf, true);		\
+			__hpp__slsmg_color_printf, _fmttype);		\
 }
 
-#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype)		\
 static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
 {									\
 	return he->stat_acc->_field;					\
@@ -1262,15 +1262,18 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 		return ret;						\
 	}								\
 	return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field,		\
-			" %*.2f%%", __hpp__slsmg_color_printf, true);	\
+			" %*.2f%%", __hpp__slsmg_color_printf,		\
+			_fmttype);					\
 }
 
-__HPP_COLOR_PERCENT_FN(overhead, period)
-__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
-__HPP_COLOR_PERCENT_FN(overhead_us, period_us)
-__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
-__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
-__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
+__HPP_COLOR_PERCENT_FN(overhead, period, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_PERCENT_FN(latency, latency, PERF_HPP_FMT_TYPE__LATENCY)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT)
+__HPP_COLOR_ACC_PERCENT_FN(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY)
 
 #undef __HPP_COLOR_PERCENT_FN
 #undef __HPP_COLOR_ACC_PERCENT_FN
@@ -1279,6 +1282,8 @@ void hist_browser__init_hpp(void)
 {
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
 				hist_browser__hpp_color_overhead;
+	perf_hpp__format[PERF_HPP__LATENCY].color =
+				hist_browser__hpp_color_latency;
 	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
 				hist_browser__hpp_color_overhead_sys;
 	perf_hpp__format[PERF_HPP__OVERHEAD_US].color =
@@ -1289,6 +1294,8 @@ void hist_browser__init_hpp(void)
 				hist_browser__hpp_color_overhead_guest_us;
 	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
 				hist_browser__hpp_color_overhead_acc;
+	perf_hpp__format[PERF_HPP__LATENCY_ACC].color =
+				hist_browser__hpp_color_latency_acc;
 
 	res_sample_init();
 }
@@ -3267,10 +3274,10 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 				/*
 				 * No need to set actions->dso here since
 				 * it's just to remove the current filter.
-				 * Ditto for thread below.
 				 */
 				do_zoom_dso(browser, actions);
 			} else if (top == &browser->hists->thread_filter) {
+				actions->thread = thread;
 				do_zoom_thread(browser, actions);
 			} else if (top == &browser->hists->socket_filter) {
 				do_zoom_socket(browser, actions);
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index e437d7889de6..2d04ece833aa 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,16 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../builtin.h"
-#include "../../perf.h"
 #include "../../util/util.h" // perf_exe()
 #include "../util.h"
+#include "../../util/evlist.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
+#include "../../util/session.h"
 #include "../../util/symbol.h"
 #include "../browser.h"
 #include "../libslang.h"
 #include "config.h"
+#include <linux/err.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
+#include <subcmd/exec-cmd.h>
 #include <stdlib.h>
 
 #define SCRIPT_NAMELEN	128
@@ -78,6 +80,177 @@ static int scripts_config(const char *var, const char *value, void *data)
 }
 
 /*
+ * Some scripts specify the required events in their "xxx-record" file,
+ * this function will check if the events in perf.data match those
+ * mentioned in the "xxx-record".
+ *
+ * Fixme: All existing "xxx-record" are all in good formats "-e event ",
+ * which is covered well now. And new parsing code should be added to
+ * cover the future complex formats like event groups etc.
+ */
+static int check_ev_match(int dir_fd, const char *scriptname, struct perf_session *session)
+{
+	char line[BUFSIZ];
+	FILE *fp;
+
+	{
+		char filename[FILENAME_MAX + 5];
+		int fd;
+
+		scnprintf(filename, sizeof(filename), "bin/%s-record", scriptname);
+		fd = openat(dir_fd, filename, O_RDONLY);
+		if (fd == -1)
+			return -1;
+		fp = fdopen(fd, "r");
+		if (!fp)
+			return -1;
+	}
+
+	while (fgets(line, sizeof(line), fp)) {
+		char *p = skip_spaces(line);
+
+		if (*p == '#')
+			continue;
+
+		while (strlen(p)) {
+			int match, len;
+			struct evsel *pos;
+			char evname[128];
+
+			p = strstr(p, "-e");
+			if (!p)
+				break;
+
+			p += 2;
+			p = skip_spaces(p);
+			len = strcspn(p, " \t");
+			if (!len)
+				break;
+
+			snprintf(evname, len + 1, "%s", p);
+
+			match = 0;
+			evlist__for_each_entry(session->evlist, pos) {
+				if (evsel__name_is(pos, evname)) {
+					match = 1;
+					break;
+				}
+			}
+
+			if (!match) {
+				fclose(fp);
+				return -1;
+			}
+		}
+	}
+
+	fclose(fp);
+	return 0;
+}
+
+/*
+ * Return -1 if none is found, otherwise the actual scripts number.
+ *
+ * Currently the only user of this function is the script browser, which
+ * will list all statically runnable scripts, select one, execute it and
+ * show the output in a perf browser.
+ */
+static int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+		 int pathlen)
+{
+	struct dirent *script_dirent, *lang_dirent;
+	int scripts_dir_fd, lang_dir_fd;
+	DIR *scripts_dir, *lang_dir;
+	struct perf_session *session;
+	struct perf_data data = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	char *temp;
+	int i = 0;
+	const char *exec_path = get_argv_exec_path();
+
+	session = perf_session__new(&data, NULL);
+	if (IS_ERR(session))
+		return PTR_ERR(session);
+
+	{
+		char scripts_path[PATH_MAX];
+
+		snprintf(scripts_path, sizeof(scripts_path), "%s/scripts", exec_path);
+		scripts_dir_fd = open(scripts_path, O_DIRECTORY);
+		pr_err("Failed to open directory '%s'", scripts_path);
+		if (scripts_dir_fd == -1) {
+			perf_session__delete(session);
+			return -1;
+		}
+	}
+	scripts_dir = fdopendir(scripts_dir_fd);
+	if (!scripts_dir) {
+		close(scripts_dir_fd);
+		perf_session__delete(session);
+		return -1;
+	}
+
+	while ((lang_dirent = readdir(scripts_dir)) != NULL) {
+		if (lang_dirent->d_type != DT_DIR &&
+		    (lang_dirent->d_type == DT_UNKNOWN &&
+		     !is_directory_at(scripts_dir_fd, lang_dirent->d_name)))
+			continue;
+		if (!strcmp(lang_dirent->d_name, ".") || !strcmp(lang_dirent->d_name, ".."))
+			continue;
+
+#ifndef HAVE_LIBPERL_SUPPORT
+		if (strstr(lang_dirent->d_name, "perl"))
+			continue;
+#endif
+#ifndef HAVE_LIBPYTHON_SUPPORT
+		if (strstr(lang_dirent->d_name, "python"))
+			continue;
+#endif
+
+		lang_dir_fd = openat(scripts_dir_fd, lang_dirent->d_name, O_DIRECTORY);
+		if (lang_dir_fd == -1)
+			continue;
+		lang_dir = fdopendir(lang_dir_fd);
+		if (!lang_dir) {
+			close(lang_dir_fd);
+			continue;
+		}
+		while ((script_dirent = readdir(lang_dir)) != NULL) {
+			if (script_dirent->d_type == DT_DIR)
+				continue;
+			if (script_dirent->d_type == DT_UNKNOWN &&
+			    is_directory_at(lang_dir_fd, script_dirent->d_name))
+				continue;
+			/* Skip those real time scripts: xxxtop.p[yl] */
+			if (strstr(script_dirent->d_name, "top."))
+				continue;
+			if (i >= num)
+				break;
+			scnprintf(scripts_path_array[i], pathlen, "%s/scripts/%s/%s",
+				exec_path,
+				lang_dirent->d_name,
+				script_dirent->d_name);
+			temp = strchr(script_dirent->d_name, '.');
+			snprintf(scripts_array[i],
+				(temp - script_dirent->d_name) + 1,
+				"%s", script_dirent->d_name);
+
+			if (check_ev_match(lang_dir_fd, scripts_array[i], session))
+				continue;
+
+			i++;
+		}
+		closedir(lang_dir);
+	}
+
+	closedir(scripts_dir);
+	perf_session__delete(session);
+	return i;
+}
+
+/*
  * When success, will copy the full path of the selected script
  * into  the buffer pointed by script_name, and return 0.
  * Return -1 on failure.
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 6da24aa039eb..8920e298420a 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -3,6 +3,7 @@
 #include "util/sort.h"
 #include "util/debug.h"
 #include "util/annotate.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/map.h"
 #include "util/dso.h"
@@ -26,7 +27,7 @@ static const char *const col_names[] = {
 };
 
 static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
-				 struct disasm_line *dl, int evidx)
+				 struct disasm_line *dl, const struct evsel *evsel)
 {
 	struct annotation *notes;
 	struct sym_hist *symhist;
@@ -42,8 +43,8 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
 		return 0;
 
 	notes = symbol__annotation(sym);
-	symhist = annotation__histogram(notes, evidx);
-	entry = annotated_source__hist_entry(notes->src, evidx, dl->al.offset);
+	symhist = annotation__histogram(notes, evsel);
+	entry = annotated_source__hist_entry(notes->src, evsel, dl->al.offset);
 	if (entry)
 		nr_samples = entry->nr_samples;
 
@@ -139,16 +140,17 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms,
 		gtk_list_store_append(store, &iter);
 
 		if (evsel__is_group_event(evsel)) {
-			for (i = 0; i < evsel->core.nr_members; i++) {
+			struct evsel *cur_evsel;
+
+			for_each_group_evsel(cur_evsel, evsel__leader(evsel)) {
 				ret += perf_gtk__get_percent(s + ret,
 							     sizeof(s) - ret,
 							     sym, pos,
-							     evsel->core.idx + i);
+							     cur_evsel);
 				ret += scnprintf(s + ret, sizeof(s) - ret, " ");
 			}
 		} else {
-			ret = perf_gtk__get_percent(s, sizeof(s), sym, pos,
-						    evsel->core.idx);
+			ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, evsel);
 		}
 
 		if (ret)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index e5491995adf0..ae3b7fe1dadc 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -27,9 +27,10 @@ static int __hpp__fmt_print(struct perf_hpp *hpp, struct hists *hists, u64 val,
 			    int nr_samples, const char *fmt, int len,
 			    hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype)
 {
-	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT) {
+	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT || fmtype == PERF_HPP_FMT_TYPE__LATENCY) {
 		double percent = 0.0;
-		u64 total = hists__total_period(hists);
+		u64 total = fmtype == PERF_HPP_FMT_TYPE__PERCENT ? hists__total_period(hists) :
+			hists__total_latency(hists);
 
 		if (total)
 			percent = 100.0 * val / total;
@@ -121,14 +122,14 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     const char *fmtstr, hpp_snprint_fn print_fn,
 	     enum perf_hpp_fmt_type fmtype)
 {
-	int len = fmt->user_len ?: fmt->len;
+	int len = max(fmt->user_len ?: fmt->len, (int)strlen(fmt->name));
 
 	if (symbol_conf.field_sep) {
 		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
 				  print_fn, fmtype);
 	}
 
-	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT)
+	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT || fmtype == PERF_HPP_FMT_TYPE__LATENCY)
 		len -= 2; /* 2 for a space and a % sign */
 	else
 		len -= 1;
@@ -356,7 +357,7 @@ static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	return (ret >= ssize) ? (ssize - 1) : ret;
 }
 
-#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+#define __HPP_COLOR_PERCENT_FN(_type, _field, _fmttype)				\
 static u64 he_get_##_field(struct hist_entry *he)				\
 {										\
 	return he->stat._field;							\
@@ -366,15 +367,15 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
-			hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
+			hpp_color_scnprintf, _fmttype);				\
 }
 
-#define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
+#define __HPP_ENTRY_PERCENT_FN(_type, _field, _fmttype)				\
 static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
-			hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
+			hpp_entry_scnprintf, _fmttype);	\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
@@ -384,7 +385,7 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
 	return __hpp__sort(a, b, he_get_##_field);				\
 }
 
-#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype)			\
 static u64 he_get_acc_##_field(struct hist_entry *he)				\
 {										\
 	return he->stat_acc->_field;						\
@@ -394,15 +395,15 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
-			    hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
+			    hpp_color_scnprintf, _fmttype);			\
 }
 
-#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field, _fmttype)			\
 static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",	\
-			    hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
+			    hpp_entry_scnprintf, _fmttype);			\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
@@ -453,14 +454,14 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
 }
 
 
-#define HPP_PERCENT_FNS(_type, _field)					\
-__HPP_COLOR_PERCENT_FN(_type, _field)					\
-__HPP_ENTRY_PERCENT_FN(_type, _field)					\
+#define HPP_PERCENT_FNS(_type, _field, _fmttype)			\
+__HPP_COLOR_PERCENT_FN(_type, _field, _fmttype)				\
+__HPP_ENTRY_PERCENT_FN(_type, _field, _fmttype)				\
 __HPP_SORT_FN(_type, _field)
 
-#define HPP_PERCENT_ACC_FNS(_type, _field)				\
-__HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
-__HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+#define HPP_PERCENT_ACC_FNS(_type, _field, _fmttype)			\
+__HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype)			\
+__HPP_ENTRY_ACC_PERCENT_FN(_type, _field, _fmttype)			\
 __HPP_SORT_ACC_FN(_type, _field)
 
 #define HPP_RAW_FNS(_type, _field)					\
@@ -471,12 +472,14 @@ __HPP_SORT_RAW_FN(_type, _field)
 __HPP_ENTRY_AVERAGE_FN(_type, _field)					\
 __HPP_SORT_AVERAGE_FN(_type, _field)
 
-HPP_PERCENT_FNS(overhead, period)
-HPP_PERCENT_FNS(overhead_sys, period_sys)
-HPP_PERCENT_FNS(overhead_us, period_us)
-HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
-HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
-HPP_PERCENT_ACC_FNS(overhead_acc, period)
+HPP_PERCENT_FNS(overhead, period, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_FNS(latency, latency, PERF_HPP_FMT_TYPE__LATENCY)
+HPP_PERCENT_FNS(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_FNS(overhead_us, period_us, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_ACC_FNS(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT)
+HPP_PERCENT_ACC_FNS(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY)
 
 HPP_RAW_FNS(samples, nr_events)
 HPP_RAW_FNS(period, period)
@@ -548,11 +551,13 @@ static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 
 struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
+	HPP__COLOR_PRINT_FNS("Latency", latency, LATENCY),
 	HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS),
 	HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US),
 	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS),
 	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
 	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
+	HPP__COLOR_ACC_PRINT_FNS("Latency", latency_acc, LATENCY_ACC),
 	HPP__PRINT_FNS("Samples", samples, SAMPLES),
 	HPP__PRINT_FNS("Period", period, PERIOD),
 	HPP__PRINT_FNS("Weight1", weight1, WEIGHT1),
@@ -601,6 +606,11 @@ static void fmt_free(struct perf_hpp_fmt *fmt)
 		fmt->free(fmt);
 }
 
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	return a->equal && a->equal(a, b);
+}
+
 void perf_hpp__init(void)
 {
 	int i;
@@ -621,28 +631,48 @@ void perf_hpp__init(void)
 	if (is_strict_order(field_order))
 		return;
 
+	/*
+	 * Overhead and latency columns are added in setup_overhead(),
+	 * so they are added implicitly here only if they were added
+	 * by setup_overhead() before (have was_taken flag set).
+	 * This is required because setup_overhead() has more complex
+	 * logic, in particular it does not add "overhead" if user
+	 * specified "latency" in sort order, and vise versa.
+	 */
 	if (symbol_conf.cumulate_callchain) {
-		hpp_dimension__add_output(PERF_HPP__OVERHEAD_ACC);
+		/*
+		 * Addition of fields is idempotent, so we add latency
+		 * column twice to get desired order with simpler logic.
+		 */
+		if (symbol_conf.prefer_latency)
+			hpp_dimension__add_output(PERF_HPP__LATENCY_ACC, true);
+		hpp_dimension__add_output(PERF_HPP__OVERHEAD_ACC, true);
+		if (symbol_conf.enable_latency)
+			hpp_dimension__add_output(PERF_HPP__LATENCY_ACC, true);
 		perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
 	}
 
-	hpp_dimension__add_output(PERF_HPP__OVERHEAD);
+	if (symbol_conf.prefer_latency)
+		hpp_dimension__add_output(PERF_HPP__LATENCY, true);
+	hpp_dimension__add_output(PERF_HPP__OVERHEAD, true);
+	if (symbol_conf.enable_latency)
+		hpp_dimension__add_output(PERF_HPP__LATENCY, true);
 
 	if (symbol_conf.show_cpu_utilization) {
-		hpp_dimension__add_output(PERF_HPP__OVERHEAD_SYS);
-		hpp_dimension__add_output(PERF_HPP__OVERHEAD_US);
+		hpp_dimension__add_output(PERF_HPP__OVERHEAD_SYS, false);
+		hpp_dimension__add_output(PERF_HPP__OVERHEAD_US, false);
 
 		if (perf_guest) {
-			hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_SYS);
-			hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_US);
+			hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_SYS, false);
+			hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_US, false);
 		}
 	}
 
 	if (symbol_conf.show_nr_samples)
-		hpp_dimension__add_output(PERF_HPP__SAMPLES);
+		hpp_dimension__add_output(PERF_HPP__SAMPLES, false);
 
 	if (symbol_conf.show_total_period)
-		hpp_dimension__add_output(PERF_HPP__PERIOD);
+		hpp_dimension__add_output(PERF_HPP__PERIOD, false);
 }
 
 void perf_hpp_list__column_register(struct perf_hpp_list *list,
@@ -671,28 +701,42 @@ static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 
 void perf_hpp__cancel_cumulate(void)
 {
-	struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp;
+	struct perf_hpp_fmt *fmt, *acc, *ovh, *acc_lat, *tmp;
 
 	if (is_strict_order(field_order))
 		return;
 
 	ovh = &perf_hpp__format[PERF_HPP__OVERHEAD];
 	acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC];
+	acc_lat = &perf_hpp__format[PERF_HPP__LATENCY_ACC];
 
 	perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
-		if (acc->equal(acc, fmt)) {
+		if (fmt_equal(acc, fmt) || fmt_equal(acc_lat, fmt)) {
 			perf_hpp__column_unregister(fmt);
 			continue;
 		}
 
-		if (ovh->equal(ovh, fmt))
+		if (fmt_equal(ovh, fmt))
 			fmt->name = "Overhead";
 	}
 }
 
-static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+void perf_hpp__cancel_latency(void)
 {
-	return a->equal && a->equal(a, b);
+	struct perf_hpp_fmt *fmt, *lat, *acc, *tmp;
+
+	if (is_strict_order(field_order))
+		return;
+	if (sort_order && strstr(sort_order, "latency"))
+		return;
+
+	lat = &perf_hpp__format[PERF_HPP__LATENCY];
+	acc = &perf_hpp__format[PERF_HPP__LATENCY_ACC];
+
+	perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
+		if (fmt_equal(lat, fmt) || fmt_equal(acc, fmt))
+			perf_hpp__column_unregister(fmt);
+	}
 }
 
 void perf_hpp__setup_output_field(struct perf_hpp_list *list)
@@ -819,6 +863,7 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 
 	switch (fmt->idx) {
 	case PERF_HPP__OVERHEAD:
+	case PERF_HPP__LATENCY:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
 	case PERF_HPP__OVERHEAD_ACC:
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 74b2c619c56c..7ac4b98e28bc 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/string.h>
@@ -24,6 +25,9 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 	int i;
 	int ret = fprintf(fp, "            ");
 
+	if (left_margin > USHRT_MAX)
+		left_margin = USHRT_MAX;
+
 	for (i = 0; i < left_margin; i++)
 		ret += fprintf(fp, " ");