Merge branch 'email/acme' into perf/core

Merge perf/core improvements and fixes from Arnaldo Carvalho de Melo:

    User visible changes:

 - Allow grouping multiple sort keys per 'perf report/top --hierarchy'
   level (Namhyung Kim)

 - Document 'perf stat --detailed' option (Borislav Petkov)

Infrastructure changes:

 - jitdump prep work for supporting it with Intel PT (Adrian Hunter)

 - Use 64-bit shifts with (TSC) time conversion (Adrian Hunter)

Fixes:

 - Explicitly declare inc_group_count as a void function (Colin Ian King)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 514 insertions, 314 deletions

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 52ef7a9..14d9e8f 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -69,6 +69,14 @@ report::
 --scale::
 	scale/normalize counter values
 
+-d::
+--detailed::
+	print more detailed statistics, can be specified up to 3 times
+
+	   -d:          detailed events, L1 and LLC data cache
+        -d -d:     more detailed events, dTLB and iTLB events
+     -d -d -d:     very detailed events, adding prefetch events
+
 -r::
 --repeat=<n>::
 	repeat command and print average + stddev (max: 100). 0 means forever.
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 7945462..72193f19 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -59,7 +59,7 @@ static u64 mmap_read_self(void *addr)
 		u64 quot, rem;
 
 		quot = (cyc >> time_shift);
-		rem = cyc & ((1 << time_shift) - 1);
+		rem = cyc & (((u64)1 << time_shift) - 1);
 		delta = time_offset + quot * time_mult +
 			((rem * time_mult) >> time_shift);
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b38445f..b288577 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -253,12 +253,16 @@ static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	u64 n = 0;
+	int ret;
 
 	/*
 	 * if jit marker, then inject jit mmaps and generate ELF images
 	 */
-	if (!jit_process(inject->session, &inject->output, machine,
-			 event->mmap.filename, sample->pid, &n)) {
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
 		inject->bytes_written += n;
 		return 0;
 	}
@@ -287,12 +291,16 @@ static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	u64 n = 0;
+	int ret;
 
 	/*
 	 * if jit marker, then inject jit mmaps and generate ELF images
 	 */
-	if (!jit_process(inject->session, &inject->output, machine,
-			  event->mmap2.filename, sample->pid, &n)) {
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap2.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
 		inject->bytes_written += n;
 		return 0;
 	}
@@ -679,12 +687,16 @@ static int __cmd_inject(struct perf_inject *inject)
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids) {
+		if (inject->build_ids)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
-			if (inject->have_auxtrace)
-				dsos__hit_all(session);
-		}
+		/*
+		 * Keep all buildids when there is unprocessed AUX data because
+		 * it is not known which ones the AUX trace hits.
+		 */
+		if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
+		    inject->have_auxtrace && !inject->itrace_synth_opts.set)
+			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag and
@@ -717,23 +729,6 @@ static int __cmd_inject(struct perf_inject *inject)
 	return ret;
 }
 
-#ifdef HAVE_LIBELF_SUPPORT
-static int
-jit_validate_events(struct perf_session *session)
-{
-	struct perf_evsel *evsel;
-
-	/*
-	 * check that all events use CLOCK_MONOTONIC
-	 */
-	evlist__for_each(session->evlist, evsel) {
-		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
-			return -1;
-	}
-	return 0;
-}
-#endif
-
 int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_inject inject = {
@@ -840,13 +835,6 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 #ifdef HAVE_LIBELF_SUPPORT
 	if (inject.jit_mode) {
-		/*
-		 * validate event is using the correct clockid
-		 */
-		if (jit_validate_events(inject.session)) {
-			fprintf(stderr, "error, jitted code must be sampled with perf record -k 1\n");
-			return -1;
-		}
 		inject.tool.mmap2	   = perf_event__jit_repipe_mmap2;
 		inject.tool.mmap	   = perf_event__jit_repipe_mmap;
 		inject.tool.ordered_events = true;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 5ffffcb..e0e217e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1280,7 +1280,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 					      struct hist_entry *entry,
 					      unsigned short row,
-					      int level, int nr_sort_keys)
+					      int level)
 {
 	int printed = 0;
 	int width = browser->b.width;
@@ -1289,12 +1289,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 	off_t row_offset = entry->row_offset;
 	bool first = true;
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	struct hpp_arg arg = {
 		.b		= &browser->b,
 		.current_entry	= current_entry,
 	};
 	int column = 0;
-	int hierarchy_indent = (nr_sort_keys - 1) * HIERARCHY_INDENT;
+	int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
 
 	if (current_entry) {
 		browser->he_selection = entry;
@@ -1320,7 +1321,10 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
 	width -= level * HIERARCHY_INDENT;
 
-	hists__for_each_format(entry->hists, fmt) {
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&entry->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		char s[2048];
 		struct perf_hpp hpp = {
 			.buf		= s,
@@ -1332,10 +1336,6 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		    column++ < browser->b.horiz_scroll)
 			continue;
 
-		if (perf_hpp__is_sort_entry(fmt) ||
-		    perf_hpp__is_dynamic_entry(fmt))
-			break;
-
 		if (current_entry && browser->b.navkeypressed) {
 			ui_browser__set_color(&browser->b,
 					      HE_COLORSET_SELECTED);
@@ -1388,25 +1388,26 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 					      HE_COLORSET_NORMAL);
 		}
 
-		ui_browser__write_nstring(&browser->b, "", 2);
-		width -= 2;
+		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
+			ui_browser__write_nstring(&browser->b, "", 2);
+			width -= 2;
 
-		/*
-		 * No need to call hist_entry__snprintf_alignment()
-		 * since this fmt is always the last column in the
-		 * hierarchy mode.
-		 */
-		fmt = entry->fmt;
-		if (fmt->color) {
-			width -= fmt->color(fmt, &hpp, entry);
-		} else {
-			int i = 0;
+			/*
+			 * No need to call hist_entry__snprintf_alignment()
+			 * since this fmt is always the last column in the
+			 * hierarchy mode.
+			 */
+			if (fmt->color) {
+				width -= fmt->color(fmt, &hpp, entry);
+			} else {
+				int i = 0;
 
-			width -= fmt->entry(fmt, &hpp, entry);
-			ui_browser__printf(&browser->b, "%s", ltrim(s));
+				width -= fmt->entry(fmt, &hpp, entry);
+				ui_browser__printf(&browser->b, "%s", ltrim(s));
 
-			while (isspace(s[i++]))
-				width++;
+				while (isspace(s[i++]))
+					width++;
+			}
 		}
 	}
 
@@ -1435,8 +1436,7 @@ show_callchain:
 }
 
 static int hist_browser__show_no_entry(struct hist_browser *browser,
-				       unsigned short row,
-				       int level, int nr_sort_keys)
+				       unsigned short row, int level)
 {
 	int width = browser->b.width;
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
@@ -1444,6 +1444,8 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
 	int column = 0;
 	int ret;
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	int indent = browser->hists->nr_hpp_node - 2;
 
 	if (current_entry) {
 		browser->he_selection = NULL;
@@ -1460,15 +1462,14 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
 	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
 	width -= level * HIERARCHY_INDENT;
 
-	hists__for_each_format(browser->hists, fmt) {
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&browser->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		if (perf_hpp__should_skip(fmt, browser->hists) ||
 		    column++ < browser->b.horiz_scroll)
 			continue;
 
-		if (perf_hpp__is_sort_entry(fmt) ||
-		    perf_hpp__is_dynamic_entry(fmt))
-			break;
-
 		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
 
 		if (first) {
@@ -1484,8 +1485,8 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
 		width -= ret;
 	}
 
-	ui_browser__write_nstring(&browser->b, "", nr_sort_keys * HIERARCHY_INDENT);
-	width -= nr_sort_keys * HIERARCHY_INDENT;
+	ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT);
+	width -= indent * HIERARCHY_INDENT;
 
 	if (column >= browser->b.horiz_scroll) {
 		char buf[32];
@@ -1550,22 +1551,23 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		.size   = size,
 	};
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	size_t ret = 0;
 	int column = 0;
-	int nr_sort_keys = hists->nr_sort_keys;
-	bool first = true;
+	int indent = hists->nr_hpp_node - 2;
+	bool first_node, first_col;
 
 	ret = scnprintf(buf, size, " ");
 	if (advance_hpp_check(&dummy_hpp, ret))
 		return ret;
 
-	hists__for_each_format(hists, fmt) {
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
-			break;
-
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1576,38 +1578,46 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	}
 
 	ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
-			(nr_sort_keys - 1) * HIERARCHY_INDENT, "");
+			indent * HIERARCHY_INDENT, "");
 	if (advance_hpp_check(&dummy_hpp, ret))
 		return ret;
 
-	hists__for_each_format(hists, fmt) {
-		char *start;
-
-		if (!perf_hpp__is_sort_entry(fmt) && !perf_hpp__is_dynamic_entry(fmt))
-			continue;
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
-
-		if (first) {
-			first = false;
-		} else {
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node) {
 			ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / ");
 			if (advance_hpp_check(&dummy_hpp, ret))
 				break;
 		}
+		first_node = false;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
-		dummy_hpp.buf[ret] = '\0';
-		rtrim(dummy_hpp.buf);
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			char *start;
 
-		start = ltrim(dummy_hpp.buf);
-		ret = strlen(start);
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col) {
+				ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+");
+				if (advance_hpp_check(&dummy_hpp, ret))
+					break;
+			}
+			first_col = false;
 
-		if (start != dummy_hpp.buf)
-			memmove(dummy_hpp.buf, start, ret + 1);
+			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			dummy_hpp.buf[ret] = '\0';
+			rtrim(dummy_hpp.buf);
 
-		if (advance_hpp_check(&dummy_hpp, ret))
-			break;
+			start = ltrim(dummy_hpp.buf);
+			ret = strlen(start);
+
+			if (start != dummy_hpp.buf)
+				memmove(dummy_hpp.buf, start, ret + 1);
+
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
 	}
 
 	return ret;
@@ -1644,7 +1654,6 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	u16 header_offset = 0;
 	struct rb_node *nd;
 	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
-	int nr_sort = hb->hists->nr_sort_keys;
 
 	if (hb->show_headers) {
 		hist_browser__show_headers(hb);
@@ -1671,14 +1680,12 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 
 		if (symbol_conf.report_hierarchy) {
 			row += hist_browser__show_hierarchy_entry(hb, h, row,
-								  h->depth,
-								  nr_sort);
+								  h->depth);
 			if (row == browser->rows)
 				break;
 
 			if (h->has_no_entry) {
-				hist_browser__show_no_entry(hb, row, h->depth,
-							    nr_sort);
+				hist_browser__show_no_entry(hb, row, h->depth + 1);
 				row++;
 			}
 		} else {
@@ -1934,7 +1941,7 @@ static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
 	struct perf_hpp_fmt *fmt;
 	bool first = true;
 	int ret;
-	int hierarchy_indent = (nr_sort_keys + 1) * HIERARCHY_INDENT;
+	int hierarchy_indent = nr_sort_keys * HIERARCHY_INDENT;
 
 	printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, "");
 
@@ -1962,9 +1969,13 @@ static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
 	ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, "");
 	advance_hpp(&hpp, ret);
 
-	fmt = he->fmt;
-	ret = fmt->entry(fmt, &hpp, he);
-	advance_hpp(&hpp, ret);
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		ret = scnprintf(hpp.buf, hpp.size, "  ");
+		advance_hpp(&hpp, ret);
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
 
 	printed += fprintf(fp, "%s\n", rtrim(s));
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index a5758fd..bd9bf7e 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -407,11 +407,14 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists,
 	struct rb_node *node;
 	struct hist_entry *he;
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	u64 total = hists__total_period(hists);
+	int size;
 
 	for (node = rb_first(root); node; node = rb_next(node)) {
 		GtkTreeIter iter;
 		float percent;
+		char *bf;
 
 		he = rb_entry(node, struct hist_entry, rb_node);
 		if (he->filtered)
@@ -424,11 +427,11 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists,
 		gtk_tree_store_append(store, &iter, parent);
 
 		col_idx = 0;
-		hists__for_each_format(hists, fmt) {
-			if (perf_hpp__is_sort_entry(fmt) ||
-			    perf_hpp__is_dynamic_entry(fmt))
-				break;
 
+		/* the first hpp_list_node is for overhead columns */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 			if (fmt->color)
 				fmt->color(fmt, hpp, he);
 			else
@@ -437,15 +440,26 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists,
 			gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1);
 		}
 
-		fmt = he->fmt;
-		if (fmt->color)
-			fmt->color(fmt, hpp, he);
-		else
-			fmt->entry(fmt, hpp, he);
+		bf = hpp->buf;
+		size = hpp->size;
+		perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+			int ret;
+
+			if (fmt->color)
+				ret = fmt->color(fmt, hpp, he);
+			else
+				ret = fmt->entry(fmt, hpp, he);
 
-		gtk_tree_store_set(store, &iter, col_idx, rtrim(hpp->buf), -1);
+			snprintf(hpp->buf + ret, hpp->size - ret, "  ");
+			advance_hpp(hpp, ret + 2);
+		}
+
+		gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
 
 		if (!he->leaf) {
+			hpp->buf = bf;
+			hpp->size = size;
+
 			perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
 							store, &iter, hpp,
 							min_pcnt);
@@ -478,6 +492,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				     float min_pcnt)
 {
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	GType col_types[MAX_COLUMNS];
 	GtkCellRenderer *renderer;
 	GtkTreeStore *store;
@@ -486,7 +501,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 	int nr_cols = 0;
 	char s[512];
 	char buf[512];
-	bool first = true;
+	bool first_node, first_col;
 	struct perf_hpp hpp = {
 		.buf		= s,
 		.size		= sizeof(s),
@@ -506,11 +521,11 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 	renderer = gtk_cell_renderer_text_new();
 
 	col_idx = 0;
-	hists__for_each_format(hists, fmt) {
-		if (perf_hpp__is_sort_entry(fmt) ||
-		    perf_hpp__is_dynamic_entry(fmt))
-			break;
 
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
 							    -1, fmt->name,
 							    renderer, "markup",
@@ -519,20 +534,24 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 
 	/* construct merged column header since sort keys share single column */
 	buf[0] = '\0';
-	hists__for_each_format(hists ,fmt) {
-		if (!perf_hpp__is_sort_entry(fmt) &&
-		    !perf_hpp__is_dynamic_entry(fmt))
-			continue;
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
-
-		if (first)
-			first = false;
-		else
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
 			strcat(buf, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
 
-		fmt->header(fmt, &hpp, hists_to_evsel(hists));
-		strcat(buf, rtrim(hpp.buf));
+			if (!first_col)
+				strcat(buf, "+");
+			first_col = false;
+
+			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			strcat(buf, ltrim(rtrim(hpp.buf)));
+		}
 	}
 
 	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 7c0585c..f03c4f7 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -5,6 +5,7 @@
 #include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
+#include "../util/evlist.h"
 
 /* hist period print (hpp) functions */
 
@@ -715,3 +716,71 @@ void perf_hpp__set_user_width(const char *width_list_str)
 			break;
 	}
 }
+
+static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_list_node *node = NULL;
+	struct perf_hpp_fmt *fmt_copy;
+	bool found = false;
+	bool skip = perf_hpp__should_skip(fmt, hists);
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		if (node->level == fmt->level) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		node = malloc(sizeof(*node));
+		if (node == NULL)
+			return -1;
+
+		node->skip = skip;
+		node->level = fmt->level;
+		perf_hpp_list__init(&node->hpp);
+
+		hists->nr_hpp_node++;
+		list_add_tail(&node->list, &hists->hpp_formats);
+	}
+
+	fmt_copy = perf_hpp_fmt__dup(fmt);
+	if (fmt_copy == NULL)
+		return -1;
+
+	if (!skip)
+		node->skip = false;
+
+	list_add_tail(&fmt_copy->list, &node->hpp.fields);
+	list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts);
+
+	return 0;
+}
+
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct perf_hpp_fmt *fmt;
+	struct hists *hists;
+	int ret;
+
+	if (!symbol_conf.report_hierarchy)
+		return 0;
+
+	evlist__for_each(evlist, evsel) {
+		hists = evsel__hists(evsel);
+
+		perf_hpp_list__for_each_sort_list(list, fmt) {
+			if (perf_hpp__is_dynamic_entry(fmt) &&
+			    !perf_hpp__defined_dynamic_entry(fmt, hists))
+				continue;
+
+			ret = add_hierarchy_fmt(hists, fmt);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 6d06fbb..7aff5ac 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -412,11 +412,12 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 
 static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 					 struct perf_hpp *hpp,
-					 int nr_sort_key, struct hists *hists,
+					 struct hists *hists,
 					 FILE *fp)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	char *buf = hpp->buf;
 	size_t size = hpp->size;
 	int ret, printed = 0;
@@ -428,10 +429,10 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 	ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
 	advance_hpp(hpp, ret);
 
-	hists__for_each_format(he->hists, fmt) {
-		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
-			break;
-
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		/*
 		 * If there's no field_sep, we still need
 		 * to display initial '  '.
@@ -451,33 +452,33 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 		advance_hpp(hpp, ret);
 	}
 
-	if (sep)
-		ret = scnprintf(hpp->buf, hpp->size, "%s", sep);
-	else
+	if (!sep)
 		ret = scnprintf(hpp->buf, hpp->size, "%*s",
-				(nr_sort_key - 1) * HIERARCHY_INDENT + 2, "");
+				(hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
 	advance_hpp(hpp, ret);
 
 	printed += fprintf(fp, "%s", buf);
 
-	hpp->buf  = buf;
-	hpp->size = size;
-
-	/*
-	 * No need to call hist_entry__snprintf_alignment() since this
-	 * fmt is always the last column in the hierarchy mode.
-	 */
-	fmt = he->fmt;
-	if (perf_hpp__use_color() && fmt->color)
-		fmt->color(fmt, hpp, he);
-	else
-		fmt->entry(fmt, hpp, he);
-
-	/*
-	 * dynamic entries are right-aligned but we want left-aligned
-	 * in the hierarchy mode
-	 */
-	printed += fprintf(fp, "%s\n", ltrim(buf));
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		hpp->buf  = buf;
+		hpp->size = size;
+
+		/*
+		 * No need to call hist_entry__snprintf_alignment() since this
+		 * fmt is always the last column in the hierarchy mode.
+		 */
+		if (perf_hpp__use_color() && fmt->color)
+			fmt->color(fmt, hpp, he);
+		else
+			fmt->entry(fmt, hpp, he);
+
+		/*
+		 * dynamic entries are right-aligned but we want left-aligned
+		 * in the hierarchy mode
+		 */
+		printed += fprintf(fp, "%s%s", sep ?: "  ", ltrim(buf));
+	}
+	printed += putc('\n', fp);
 
 	if (symbol_conf.use_callchain && he->leaf) {
 		u64 total = hists__total_period(hists);
@@ -504,12 +505,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
-	if (symbol_conf.report_hierarchy) {
-		int nr_sort = hists->nr_sort_keys;
-
-		return hist_entry__hierarchy_fprintf(he, &hpp, nr_sort,
-						     hists, fp);
-	}
+	if (symbol_conf.report_hierarchy)
+		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
 
 	hist_entry__snprintf(he, &hpp);
 
@@ -521,92 +518,97 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	return ret;
 }
 
-static int print_hierarchy_indent(const char *sep, int nr_sort,
+static int print_hierarchy_indent(const char *sep, int indent,
 				  const char *line, FILE *fp)
 {
-	if (sep != NULL || nr_sort < 1)
+	if (sep != NULL || indent < 2)
 		return 0;
 
-	return fprintf(fp, "%-.*s", (nr_sort - 1) * HIERARCHY_INDENT, line);
+	return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
 }
 
 static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				  const char *sep, FILE *fp)
 {
-	bool first = true;
-	int nr_sort;
+	bool first_node, first_col;
+	int indent;
 	int depth;
 	unsigned width = 0;
 	unsigned header_width = 0;
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 
-	nr_sort = hists->nr_sort_keys;
+	indent = hists->nr_hpp_node;
 
 	/* preserve max indent depth for column headers */
-	print_hierarchy_indent(sep, nr_sort, spaces, fp);
+	print_hierarchy_indent(sep, indent, spaces, fp);
 
-	hists__for_each_format(hists, fmt) {
-		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
-			break;
-
-		if (!first)
-			fprintf(fp, "%s", sep ?: "  ");
-		else
-			first = false;
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
 
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		fmt->header(fmt, hpp, hists_to_evsel(hists));
-		fprintf(fp, "%s", hpp->buf);
+		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
 	/* combine sort headers with ' / ' */
-	first = true;
-	hists__for_each_format(hists, fmt) {
-		if (!perf_hpp__is_sort_entry(fmt) && !perf_hpp__is_dynamic_entry(fmt))
-			continue;
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
-
-		if (!first)
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
 			header_width += fprintf(fp, " / ");
-		else {
-			fprintf(fp, "%s", sep ?: "  ");
-			first = false;
-		}
+		first_node = false;
 
-		fmt->header(fmt, hpp, hists_to_evsel(hists));
-		rtrim(hpp->buf);
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				header_width += fprintf(fp, "+");
+			first_col = false;
 
-		header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			rtrim(hpp->buf);
+
+			header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+		}
 	}
 
 	fprintf(fp, "\n# ");
 
 	/* preserve max indent depth for initial dots */
-	print_hierarchy_indent(sep, nr_sort, dots, fp);
+	print_hierarchy_indent(sep, indent, dots, fp);
 
-	first = true;
-	hists__for_each_format(hists, fmt) {
-		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
-			break;
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
 
-		if (!first)
-			fprintf(fp, "%s", sep ?: "  ");
-		else
-			first = false;
+	first_col = true;
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first_col)
+			fprintf(fp, "%s", sep ?: "..");
+		first_col = false;
 
 		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
 		fprintf(fp, "%.*s", width, dots);
 	}
 
 	depth = 0;
-	hists__for_each_format(hists, fmt) {
-		if (!perf_hpp__is_sort_entry(fmt) && !perf_hpp__is_dynamic_entry(fmt))
-			continue;
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		first_col = true;
+		width = depth * HIERARCHY_INDENT;
 
-		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
-		width += depth * HIERARCHY_INDENT;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				width++;  /* for '+' sign between column header */
+			first_col = false;
+
+			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+		}
 
 		if (width > header_width)
 			header_width = width;
@@ -625,6 +627,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
@@ -654,6 +657,10 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	fprintf(fp, "# ");
 
 	if (symbol_conf.report_hierarchy) {
+		list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+				perf_hpp__reset_width(fmt, hists);
+		}
 		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
 		goto print_entries;
 	}
@@ -738,9 +745,9 @@ print_entries:
 		 * display "no entry >= x.xx%" message.
 		 */
 		if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
-			int nr_sort = hists->nr_sort_keys;
+			int depth = hists->nr_hpp_node + h->depth + 1;
 
-			print_hierarchy_indent(sep, nr_sort + h->depth + 1, spaces, fp);
+			print_hierarchy_indent(sep, depth, spaces, fp);
 			fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
 
 			if (max_rows && ++nr_rows >= max_rows)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4b8b67b..29da9e0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1091,18 +1091,25 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
 static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 						 struct rb_root *root,
 						 struct hist_entry *he,
-						 struct perf_hpp_fmt *fmt)
+						 struct perf_hpp_list *hpp_list)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter, *new;
+	struct perf_hpp_fmt *fmt;
 	int64_t cmp;
 
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = fmt->collapse(fmt, iter, he);
+		cmp = 0;
+		perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, iter, he);
+			if (cmp)
+				break;
+		}
+
 		if (!cmp) {
 			he_stat__add_stat(&iter->stat, &he->stat);
 			return iter;
@@ -1121,24 +1128,26 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 	hists__apply_filters(hists, new);
 	hists->nr_entries++;
 
-	/* save related format for output */
-	new->fmt = fmt;
+	/* save related format list for output */
+	new->hpp_list = hpp_list;
 
 	/* some fields are now passed to 'new' */
-	if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
-		he->trace_output = NULL;
-	else
-		new->trace_output = NULL;
+	perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+		if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+			he->trace_output = NULL;
+		else
+			new->trace_output = NULL;
 
-	if (perf_hpp__is_srcline_entry(fmt))
-		he->srcline = NULL;
-	else
-		new->srcline = NULL;
+		if (perf_hpp__is_srcline_entry(fmt))
+			he->srcline = NULL;
+		else
+			new->srcline = NULL;
 
-	if (perf_hpp__is_srcfile_entry(fmt))
-		he->srcfile = NULL;
-	else
-		new->srcfile = NULL;
+		if (perf_hpp__is_srcfile_entry(fmt))
+			he->srcfile = NULL;
+		else
+			new->srcfile = NULL;
+	}
 
 	rb_link_node(&new->rb_node_in, parent, p);
 	rb_insert_color(&new->rb_node_in, root);
@@ -1149,21 +1158,19 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 					 struct rb_root *root,
 					 struct hist_entry *he)
 {
-	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *node;
 	struct hist_entry *new_he = NULL;
 	struct hist_entry *parent = NULL;
 	int depth = 0;
 	int ret = 0;
 
-	hists__for_each_sort_list(hists, fmt) {
-		if (!perf_hpp__is_sort_entry(fmt) &&
-		    !perf_hpp__is_dynamic_entry(fmt))
-			continue;
-		if (perf_hpp__should_skip(fmt, hists))
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		/* skip period (overhead) and elided columns */
+		if (node->level == 0 || node->skip)
 			continue;
 
 		/* insert copy of 'he' for each fmt into the hierarchy */
-		new_he = hierarchy_insert_entry(hists, root, he, fmt);
+		new_he = hierarchy_insert_entry(hists, root, he, &node->hpp);
 		if (new_he == NULL) {
 			ret = -1;
 			break;
@@ -1358,6 +1365,7 @@ static void hierarchy_insert_output_entry(struct rb_root *root,
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1373,8 +1381,10 @@ static void hierarchy_insert_output_entry(struct rb_root *root,
 	rb_insert_color(&he->rb_node, root);
 
 	/* update column width of dynamic entry */
-	if (perf_hpp__is_dynamic_entry(he->fmt))
-		he->fmt->sort(he->fmt, he, NULL);
+	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt))
+			fmt->sort(fmt, he, NULL);
+	}
 }
 
 static void hists__hierarchy_output_resort(struct hists *hists,
@@ -2105,6 +2115,7 @@ int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
 	hists->hpp_list = hpp_list;
+	INIT_LIST_HEAD(&hists->hpp_formats);
 	return 0;
 }
 
@@ -2133,8 +2144,19 @@ static void hists__delete_all_entries(struct hists *hists)
 static void hists_evsel__exit(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_hpp_fmt *fmt, *pos;
+	struct perf_hpp_list_node *node, *tmp;
 
 	hists__delete_all_entries(hists);
+
+	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
+			list_del(&fmt->list);
+			free(fmt);
+		}
+		list_del(&node->list);
+		free(node);
+	}
 }
 
 static int hists_evsel__init(struct perf_evsel *evsel)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index da5e505..2cb017f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -78,7 +78,9 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 	int			socket_filter;
 	struct perf_hpp_list	*hpp_list;
+	struct list_head	hpp_formats;
 	int			nr_sort_keys;
+	int			nr_hpp_node;
 };
 
 struct hist_entry_iter;
@@ -233,6 +235,7 @@ struct perf_hpp_fmt {
 	int len;
 	int user_len;
 	int idx;
+	int level;
 };
 
 struct perf_hpp_list {
@@ -243,6 +246,13 @@ struct perf_hpp_list {
 
 extern struct perf_hpp_list perf_hpp_list;
 
+struct perf_hpp_list_node {
+	struct list_head	list;
+	struct perf_hpp_list	hpp;
+	int			level;
+	bool			skip;
+};
+
 void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
@@ -298,6 +308,8 @@ void perf_hpp__cancel_cumulate(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
 void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist);
 
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
@@ -307,6 +319,8 @@ bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
 bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
 bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
+
 int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 99fa5ee..cd272cc 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -99,6 +99,21 @@ jit_close(struct jit_buf_desc *jd)
 }
 
 static int
+jit_validate_events(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	/*
+	 * check that all events use CLOCK_MONOTONIC
+	 */
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+			return -1;
+	}
+	return 0;
+}
+
+static int
 jit_open(struct jit_buf_desc *jd, const char *name)
 {
 	struct jitheader header;
@@ -157,6 +172,14 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 		goto error;
 	}
 
+	/*
+	 * validate event is using the correct clockid
+	 */
+	if (jit_validate_events(jd->session)) {
+		pr_err("error, jitted code must be sampled with perf record -k 1\n");
+		goto error;
+	}
+
 	bs = header.total_size - sizeof(header);
 
 	if (bs > bsz) {
@@ -647,7 +670,7 @@ jit_process(struct perf_session *session,
 	 * first, detect marker mmap (i.e., the jitdump mmap)
 	 */
 	if (jit_detect(filename, pid))
-		return -1;
+		return 0;
 
 	memset(&jd, 0, sizeof(jd));
 
@@ -665,8 +688,10 @@ jit_process(struct perf_session *session,
 	*nbytes = 0;
 
 	ret = jit_inject(&jd, filename);
-	if (!ret)
+	if (!ret) {
 		*nbytes = jd.bytes_written;
+		ret = 1;
+	}
 
 	return ret;
 }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 85c44ba..5be4a5f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,7 +28,7 @@ do { \
 	INIT_LIST_HEAD(list);         \
 } while (0)
 
-static inc_group_count(struct list_head *list,
+static void inc_group_count(struct list_head *list,
 		       struct parse_events_evlist *data)
 {
 	/* Count groups only have more than 1 members */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d..60b3593 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
 				       struct ordered_events *oe __maybe_unused)
@@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct ordered_events *oe);
 
-static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *perf_session
-				 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
-				struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int skipn(int fd, off_t n)
 {
 	char buf[4096];
@@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static
-int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event __maybe_unused,
-				      struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_build_id_stub;
+		tool->build_id = process_event_op2_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 	if (tool->id_index == NULL)
-		tool->id_index = process_id_index_stub;
+		tool->id_index = process_event_op2_stub;
 	if (tool->auxtrace_info == NULL)
-		tool->auxtrace_info = process_event_auxtrace_info_stub;
+		tool->auxtrace_info = process_event_op2_stub;
 	if (tool->auxtrace == NULL)
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
-		tool->auxtrace_error = process_event_auxtrace_error_stub;
+		tool->auxtrace_error = process_event_op2_stub;
 	if (tool->thread_map == NULL)
 		tool->thread_map = process_event_thread_map_stub;
 	if (tool->cpu_map == NULL)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4380a28..041f236 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1544,7 +1544,7 @@ static void hse_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_sort_entry *
-__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1572,6 +1572,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	hse->hpp.elide = false;
 	hse->hpp.len = 0;
 	hse->hpp.user_len = 0;
+	hse->hpp.level = level;
 
 	return hse;
 }
@@ -1581,7 +1582,8 @@ static void hpp_free(struct perf_hpp_fmt *fmt)
 	free(fmt);
 }
 
-static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd)
+static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd,
+						       int level)
 {
 	struct perf_hpp_fmt *fmt;
 
@@ -1590,6 +1592,7 @@ static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd)
 		INIT_LIST_HEAD(&fmt->list);
 		INIT_LIST_HEAD(&fmt->sort_list);
 		fmt->free = hpp_free;
+		fmt->level = level;
 	}
 
 	return fmt;
@@ -1611,9 +1614,9 @@ int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
 	return hse->se->se_filter(he, type, arg);
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd, int level)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
@@ -1625,7 +1628,7 @@ static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
 static int __sort_dimension__add_hpp_output(struct perf_hpp_list *list,
 					    struct sort_dimension *sd)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
 	if (hse == NULL)
 		return -1;
@@ -1868,7 +1871,8 @@ static void hde_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+		      int level)
 {
 	struct hpp_dynamic_entry *hde;
 
@@ -1899,10 +1903,39 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
 	hde->hpp.elide = false;
 	hde->hpp.len = 0;
 	hde->hpp.user_len = 0;
+	hde->hpp.level = level;
 
 	return hde;
 }
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_fmt *new_fmt = NULL;
+
+	if (perf_hpp__is_sort_entry(fmt)) {
+		struct hpp_sort_entry *hse, *new_hse;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		new_hse = memdup(hse, sizeof(*hse));
+		if (new_hse)
+			new_fmt = &new_hse->hpp;
+	} else if (perf_hpp__is_dynamic_entry(fmt)) {
+		struct hpp_dynamic_entry *hde, *new_hde;
+
+		hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+		new_hde = memdup(hde, sizeof(*hde));
+		if (new_hde)
+			new_fmt = &new_hde->hpp;
+	} else {
+		new_fmt = memdup(fmt, sizeof(*fmt));
+	}
+
+	INIT_LIST_HEAD(&new_fmt->list);
+	INIT_LIST_HEAD(&new_fmt->sort_list);
+
+	return new_fmt;
+}
+
 static int parse_field_name(char *str, char **event, char **field, char **opt)
 {
 	char *event_name, *field_name, *opt_name;
@@ -1974,11 +2007,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
 				    struct format_field *field,
-				    bool raw_trace)
+				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
 
-	hde = __alloc_dynamic_entry(evsel, field);
+	hde = __alloc_dynamic_entry(evsel, field, level);
 	if (hde == NULL)
 		return -ENOMEM;
 
@@ -1988,14 +2021,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 	return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
 	struct format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			return ret;
 
@@ -2004,7 +2037,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
 	return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+				  int level)
 {
 	int ret;
 	struct perf_evsel *evsel;
@@ -2013,7 +2047,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 		if (ret < 0)
 			return ret;
 	}
@@ -2021,7 +2055,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 }
 
 static int add_all_matching_fields(struct perf_evlist *evlist,
-				   char *field_name, bool raw_trace)
+				   char *field_name, bool raw_trace, int level)
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
@@ -2035,14 +2069,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 		if (field == NULL)
 			continue;
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			break;
 	}
 	return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+			     int level)
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
@@ -2072,12 +2107,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "trace_fields")) {
-		ret = add_all_dynamic_fields(evlist, raw_trace);
+		ret = add_all_dynamic_fields(evlist, raw_trace, level);
 		goto out;
 	}
 
 	if (event_name == NULL) {
-		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
 		goto out;
 	}
 
@@ -2095,7 +2130,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "*")) {
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 	} else {
 		field = pevent_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL) {
@@ -2104,7 +2139,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 			return -ENOENT;
 		}
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 	}
 
 out:
@@ -2112,12 +2147,12 @@ out:
 	return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd)
+static int __sort_dimension__add(struct sort_dimension *sd, int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_sort(sd) < 0)
+	if (__sort_dimension__add_hpp_sort(sd, level) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -2128,14 +2163,14 @@ static int __sort_dimension__add(struct sort_dimension *sd)
 	return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd)
+static int __hpp_dimension__add(struct hpp_dimension *hd, int level)
 {
 	struct perf_hpp_fmt *fmt;
 
 	if (hd->taken)
 		return 0;
 
-	fmt = __hpp_dimension__alloc_hpp(hd);
+	fmt = __hpp_dimension__alloc_hpp(hd, level);
 	if (!fmt)
 		return -1;
 
@@ -2165,7 +2200,7 @@ static int __hpp_dimension__add_output(struct perf_hpp_list *list,
 	if (hd->taken)
 		return 0;
 
-	fmt = __hpp_dimension__alloc_hpp(hd);
+	fmt = __hpp_dimension__alloc_hpp(hd, 0);
 	if (!fmt)
 		return -1;
 
@@ -2180,8 +2215,8 @@ int hpp_dimension__add_output(unsigned col)
 	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(const char *tok,
-			       struct perf_evlist *evlist __maybe_unused)
+static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
+			       int level)
 {
 	unsigned int i;
 
@@ -2220,7 +2255,7 @@ static int sort_dimension__add(const char *tok,
 			sort__has_thread = 1;
 		}
 
-		return __sort_dimension__add(sd);
+		return __sort_dimension__add(sd, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2229,7 +2264,7 @@ static int sort_dimension__add(const char *tok,
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add(hd);
+		return __hpp_dimension__add(hd, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2244,7 +2279,7 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, level);
 		return 0;
 	}
 
@@ -2260,11 +2295,11 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_mem_daddr_sym)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, level);
 		return 0;
 	}
 
-	if (!add_dynamic_entry(evlist, tok))
+	if (!add_dynamic_entry(evlist, tok, level))
 		return 0;
 
 	return -ESRCH;
@@ -2274,18 +2309,41 @@ static int setup_sort_list(char *str, struct perf_evlist *evlist)
 {
 	char *tmp, *tok;
 	int ret = 0;
+	int level = 0;
+	int next_level = 1;
+	bool in_group = false;
+
+	do {
+		tok = str;
+		tmp = strpbrk(str, "{}, ");
+		if (tmp) {
+			if (in_group)
+				next_level = level;
+			else
+				next_level = level + 1;
+
+			if (*tmp == '{')
+				in_group = true;
+			else if (*tmp == '}')
+				in_group = false;
+
+			*tmp = '\0';
+			str = tmp + 1;
+		}
 
-	for (tok = strtok_r(str, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok, evlist);
-		if (ret == -EINVAL) {
-			error("Invalid --sort key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --sort key: `%s'", tok);
-			break;
+		if (*tok) {
+			ret = sort_dimension__add(tok, evlist, level);
+			if (ret == -EINVAL) {
+				error("Invalid --sort key: `%s'", tok);
+				break;
+			} else if (ret == -ESRCH) {
+				error("Unknown --sort key: `%s'", tok);
+				break;
+			}
 		}
-	}
+
+		level = next_level;
+	} while (tmp);
 
 	return ret;
 }
@@ -2667,7 +2725,7 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent", evlist);
+		err = sort_dimension__add("parent", evlist, -1);
 		if (err < 0)
 			return err;
 	}
@@ -2692,6 +2750,10 @@ int setup_sorting(struct perf_evlist *evlist)
 	/* and then copy output fields to sort keys */
 	perf_hpp__append_sort_keys(&perf_hpp_list);
 
+	/* setup hists-specific output fields */
+	if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0)
+		return -1;
+
 	return 0;
 }
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 25a5529..ea1f722 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -130,6 +130,7 @@ struct hist_entry {
 	u32			raw_size;
 	void			*trace_output;
 	struct perf_hpp_fmt	*fmt;
+	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	union {
 		/* this is for hierarchical entry structure */
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 4d4210d..1b74164 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 	u64 quot, rem;
 
 	quot = cyc >> tc->time_shift;
-	rem  = cyc & ((1 << tc->time_shift) - 1);
+	rem  = cyc & (((u64)1 << tc->time_shift) - 1);
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }