diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 75da965df343c5e0dada434a09a8f1de9be161ed..9ff0db4e2d0cd1bcc35d2ea137871093ebfcb405 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1034,7 +1034,8 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 
 static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		       struct hists *hists __maybe_unused,
-		       int line __maybe_unused)
+		       int line __maybe_unused,
+		       int *span __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 4a7aac8ed5ee90794a3554a83d49eaeddec68a05..22e48a3ebe2983cafb4b150f0dee1a73659df50b 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1514,6 +1514,7 @@ hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf,
 	struct perf_hpp_fmt *fmt;
 	size_t ret = 0;
 	int column = 0;
+	int span = 0;
 
 	if (symbol_conf.use_callchain) {
 		ret = scnprintf(buf, size, "  ");
@@ -1525,10 +1526,13 @@ hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf,
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists, line);
+		ret = fmt->header(fmt, &dummy_hpp, hists, line, &span);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
+		if (span)
+			continue;
+
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1562,7 +1566,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists, 0);
+		ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1599,7 +1603,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists, 0);
+			ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = trim(dummy_hpp.buf);
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 79cb5c4d5e2e664d435eae191a39a7ef26048e8c..a4f02de7c1b54d426bb1b3f50b7fc2ba39ae5fa8 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				strcat(buf, "+");
 			first_col = false;
 
-			fmt->header(fmt, &hpp, hists, 0);
+			fmt->header(fmt, &hpp, hists, 0, NULL);
 			strcat(buf, ltrim(rtrim(hpp.buf)));
 		}
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 30457c65980cfe4929c05534d132876f6bfa7d9e..b47fafc8ee2aab20878cba272666fd878fd18458 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -230,7 +230,8 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct hists *hists, int line __maybe_unused)
+			  struct hists *hists, int line __maybe_unused,
+			  int *span __maybe_unused)
 {
 	int len = hpp__width_fn(fmt, hpp, hists);
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 9b807cbb56b156701057553306a25f3fb44697fb..9b65f4a6b35a4b24877fac72e24e23a27ba10ae0 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -549,7 +549,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				    struct perf_hpp_list_node, list);
 
 	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists, 0);
+		fmt->header(fmt, hpp, hists, 0, NULL);
 		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
@@ -569,7 +569,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				header_width += fprintf(fp, "+");
 			first_col = false;
 
-			fmt->header(fmt, hpp, hists, 0);
+			fmt->header(fmt, hpp, hists, 0, NULL);
 
 			header_width += fprintf(fp, "%s", trim(hpp->buf));
 		}
@@ -645,18 +645,21 @@ static void fprintf_line(struct hists *hists, struct perf_hpp *hpp,
 	struct perf_hpp_fmt *fmt;
 	const char *sep = symbol_conf.field_sep;
 	bool first = true;
+	int span = 0;
 
 	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
-		if (!first)
+		if (!first && !span)
 			fprintf(fp, "%s", sep ?: "  ");
 		else
 			first = false;
 
-		fmt->header(fmt, hpp, hists, line);
-		fprintf(fp, "%s", hpp->buf);
+		fmt->header(fmt, hpp, hists, line, &span);
+
+		if (!span)
+			fprintf(fp, "%s", hpp->buf);
 	}
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 71a44c1c44de469b269adce757930b098a741beb..a002c93fe422ff61ec1cfce66e46a2972812f3f8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -230,7 +230,7 @@ struct perf_hpp {
 struct perf_hpp_fmt {
 	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		      struct hists *hists, int line);
+		      struct hists *hists, int line, int *span);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hists *hists);
 	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a556de751018ad471986f007ae6224023db547f6..5ae3d32a21d66d6ebbefed0ff5ed896a70d232e0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1492,7 +1492,8 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct hists *hists, int line __maybe_unused)
+			      struct hists *hists, int line __maybe_unused,
+			      int *span __maybe_unused)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1798,7 +1799,8 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 
 static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			      struct hists *hists __maybe_unused,
-			      int line __maybe_unused)
+			      int line __maybe_unused,
+			      int *span __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;