perf/core improvements and fixes:

User visible:
 
 - Show extra line telling no entries below --percent-limit are
   at that --hierarchy level (Namhyung Kim)
 
 - 'perf report/top --hierarchy' assorted alignment fixes (Namhyung Kim)
 
 - Handle empty print fmts in 'perf script -s' i.e. when running
   python or perl scripts (Taeung Song)
 
 - Improve support for bpf-output events in 'perf trace' (Wang Nan)
 
 - Fix parsing of pmu events with empty list of modifiers, this
   cures a perf/core-only regression where '-e intel_pt//' got
   broken (Arnaldo Carvalho de Melo)
 
 Infrastructure:
 
 - Improve missing OpenJDK devel files error message in jvmti
   Makefile (Stephane Eranian)
 
 - Remove duplicated code and needless script_spec__findnew() (Taeung Song)
 
 - Bring perf_default_config to the very beginning at main(), removing
   the need for each subcommand to do this (Wang Nan)
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJW0NtjAAoJENZQFvNTUqpA6VIQAJs4PKyXGm3NcqUNHhml/beN
 xLBz1o6JKxg72sKRHIm8IimPUIXm3ysqxQWQjKniXKqrznpAYlT180c+gUvJUghj
 ZbsHO8cNgaDjNOUMRhxiZTrQ4kJNdE9TmvPkoWwbAFgAxT1+CMHpjgwydWb0JLIv
 0c7AxqKSg1FVTQSKDW67AYbWcp9IqoBoYpefLQNUKy2QJ/cqJtGcZXCaH9gKv5Vl
 mtiw+6bX7BCb+pLvZPcZ/69xvLrvhswGxBetjMS6ddTh63arvVvw4IzPW9XCI0gz
 MLSLAj8G0sG+mFFidl1/Mka03qy7+XKndhKEDhrKdEcf7T0FnHuArdWOLXfeHIa9
 GpTEl6MTR2SSvp8zvwLDxCFZKgBPkvPrS014VL2kExc/sdcAW7Dpz+GGxHM7K+Rn
 QsgBMmMwtsodOzdqjfH9YJTIhc73gDdytucrzfsO9S9iUkwK+UbahPEJmmU9Y0WY
 6Pb/JAcznt7j1AnRIlBq5n8M758CxRqy7aHIDOST5rF/rSPFWLBF+41NodhybcKL
 9uOq9n+e8qbXlQxithvom6H3aA+Aw1siu2q1/gTIAXBwg3VIWQeqQWFIGPPaBW3u
 JLb8lEMTFBJILTAWWy8W/nNwfYi31aI1EP4eRm9hcOZTGj8O3TxzCiZFYHohvE/O
 QAkPbInvsLDds2BeDtWp
 =tvYO
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-20160226' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

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

User visible changes:

 - Show extra line telling no entries below --percent-limit are
   at that --hierarchy level (Namhyung Kim)

 - 'perf report/top --hierarchy' assorted alignment fixes (Namhyung Kim)

 - Handle empty print fmts in 'perf script -s' i.e. when running
   python or perl scripts (Taeung Song)

 - Improve support for bpf-output events in 'perf trace' (Wang Nan)

 - Fix parsing of pmu events with empty list of modifiers, this
   cures a perf/core-only regression where '-e intel_pt//' got
   broken (Arnaldo Carvalho de Melo)

Infrastructure changes:

 - Improve missing OpenJDK devel files error message in jvmti
   Makefile (Stephane Eranian)

 - Remove duplicated code and needless script_spec__findnew() (Taeung Song)

 - Bring perf_default_config to the very beginning at main(), removing
   the need for each subcommand to do this (Wang Nan)

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

tools/perf/builtin-diff.c

@@ -1264,8 +1264,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (ret < 0)
 		return ret;
 
-	perf_config(perf_default_config, NULL);
-
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
 	if (symbol__init(NULL) < 0)

tools/perf/builtin-help.c

@@ -272,7 +272,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "man."))
 		return add_man_viewer_info(var, value);
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static struct cmdnames main_cmds, other_cmds;

tools/perf/builtin-kmem.c

@@ -1834,7 +1834,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int kmem_config(const char *var, const char *value, void *cb)
+static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "kmem.default")) {
 		if (!strcmp(value, "slab"))
@@ -1847,7 +1847,7 @@ static int kmem_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)

tools/perf/builtin-report.c

@@ -90,7 +90,7 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int hist_iter__report_callback(struct hist_entry_iter *iter,

tools/perf/builtin-script.c

@@ -1212,23 +1212,6 @@ static struct script_spec *script_spec__find(const char *spec)
 	return NULL;
 }
 
-static struct script_spec *script_spec__findnew(const char *spec,
-						struct scripting_ops *ops)
-{
-	struct script_spec *s = script_spec__find(spec);
-
-	if (s)
-		return s;
-
-	s = script_spec__new(spec, ops);
-	if (!s)
-		return NULL;
-
-	script_spec__add(s);
-
-	return s;
-}
-
 int script_spec_register(const char *spec, struct scripting_ops *ops)
 {
 	struct script_spec *s;
@@ -1237,9 +1220,11 @@ int script_spec_register(const char *spec, struct scripting_ops *ops)
 	if (s)
 		return -1;
 
-	s = script_spec__findnew(spec, ops);
+	s = script_spec__new(spec, ops);
 	if (!s)
 		return -1;
+	else
+		script_spec__add(s);
 
 	return 0;
 }

tools/perf/builtin-top.c

@@ -1065,7 +1065,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return parse_callchain_top_opt(arg);
 }
 
-static int perf_top_config(const char *var, const char *value, void *cb)
+static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "top.call-graph"))
 		var = "call-graph.record-mode"; /* fall-through */
@@ -1074,7 +1074,7 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int

tools/perf/builtin-trace.c

@@ -33,6 +33,7 @@
 #include "util/stat.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
+#include "util/bpf-loader.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -2177,6 +2178,37 @@ out_dump:
 	return 0;
 }
 
+static void bpf_output__printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	FILE *output = extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_CHAR_DATA:
+		fprintf(output, "%c", isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_DATA_BEGIN:
+	case BINARY_PRINT_LINE_BEGIN:
+	case BINARY_PRINT_ADDR:
+	case BINARY_PRINT_NUM_DATA:
+	case BINARY_PRINT_NUM_PAD:
+	case BINARY_PRINT_SEP:
+	case BINARY_PRINT_CHAR_PAD:
+	case BINARY_PRINT_LINE_END:
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void bpf_output__fprintf(struct trace *trace,
+				struct perf_sample *sample)
+{
+	print_binary(sample->raw_data, sample->raw_size, 8,
+		     bpf_output__printer, trace->output);
+}
+
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
@@ -2189,7 +2221,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 
 	fprintf(trace->output, "%s:", evsel->name);
 
-	if (evsel->tp_format) {
+	if (perf_evsel__is_bpf_output(evsel)) {
+		bpf_output__fprintf(trace, sample);
+	} else if (evsel->tp_format) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
 				      sample->raw_data, sample->raw_size,
 				      trace->output);
@@ -2586,6 +2620,16 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_error_open;
+	}
+
 	/*
 	 * Better not use !target__has_task() here because we need to cover the
 	 * case where no threads were specified in the command line, but a

tools/perf/jvmti/Makefile

@@ -35,12 +35,21 @@ SOLIBEXT=so
 
 # The following works at least on fedora 23, you may need the next
 # line for other distros.
-ifeq (,$(wildcard /usr/sbin/update-java-alternatives))
+ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
-JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
-else
 JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+else
+  ifneq (,$(wildcard /usr/sbin/alternatives))
+    JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+  endif
 endif
-
+ifndef JDIR
+$(error Could not find alternatives command, you need to set JDIR= to point to the root of your Java directory)
+else
+  ifeq (,$(wildcard $(JDIR)/include/jvmti.h))
+  $(error the openjdk development package appears to me missing, install and try again)
+  endif
+endif
+$(info Using Java from $(JDIR))
 # -lrt required in 32-bit mode for clock_gettime()
 LIBS=-lelf -lrt
 INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux

tools/perf/perf.c

@@ -454,11 +454,12 @@ static void handle_internal_command(int argc, const char **argv)
 
 static void execv_dashed_external(const char **argv)
 {
-	struct strbuf cmd = STRBUF_INIT;
+	char *cmd;
 	const char *tmp;
 	int status;
 
-	strbuf_addf(&cmd, "perf-%s", argv[0]);
+	if (asprintf(&cmd, "perf-%s", argv[0]) < 0)
+		goto do_die;
 
 	/*
 	 * argv[0] must be the perf command, but the argv array
@@ -467,7 +468,7 @@ static void execv_dashed_external(const char **argv)
 	 * restore it on error.
 	 */
 	tmp = argv[0];
-	argv[0] = cmd.buf;
+	argv[0] = cmd;
 
 	/*
 	 * if we fail because the command is not found, it is
@@ -475,15 +476,16 @@ static void execv_dashed_external(const char **argv)
 	 */
 	status = run_command_v_opt(argv, 0);
 	if (status != -ERR_RUN_COMMAND_EXEC) {
-		if (IS_RUN_COMMAND_ERR(status))
+		if (IS_RUN_COMMAND_ERR(status)) {
+do_die:
 			die("unable to run '%s'", argv[0]);
+		}
 		exit(-status);
 	}
 	errno = ENOENT; /* as if we called execvp */
 
 	argv[0] = tmp;
-
+	zfree(&cmd);
-	strbuf_release(&cmd);
 }
 
 static int run_argv(int *argcp, const char ***argv)
@@ -546,6 +548,8 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
+	perf_config(perf_default_config, NULL);
+
 	/* get debugfs/tracefs mount point from /proc/mounts */
 	tracing_path_mount();
 

tools/perf/tests/llvm.c

@@ -6,12 +6,6 @@
 #include "tests.h"
 #include "debug.h"
 
-static int perf_config_cb(const char *var, const char *val,
-			  void *arg __maybe_unused)
-{
-	return perf_default_config(var, val, arg);
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
@@ -77,8 +71,6 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 	if (should_load_fail)
 		*should_load_fail = bpf_source_table[idx].should_load_fail;
 
-	perf_config(perf_config_cb, NULL);
-
 	/*
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
 	 * and clang is not found in $PATH, and this is not perf test -v

tools/perf/ui/browsers/hists.c

@@ -260,6 +260,9 @@ static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he,
 	if (he->leaf)
 		return callchain__count_rows(&he->sorted_chain);
 
+	if (he->has_no_entry)
+		return 1;
+
 	node = rb_first(&he->hroot_out);
 	while (node) {
 		float percent;
@@ -409,10 +412,18 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 			/* account grand children */
 			if (symbol_conf.report_hierarchy)
 				browser->b.nr_entries += child_rows - he->nr_rows;
+
+			if (!he->leaf && he->nr_rows == 0) {
+				he->has_no_entry = true;
+				he->nr_rows = 1;
+			}
 		} else {
 			if (symbol_conf.report_hierarchy)
 				browser->b.nr_entries -= child_rows - he->nr_rows;
 
+			if (he->has_no_entry)
+				he->has_no_entry = false;
+
 			he->nr_rows = 0;
 		}
 
@@ -545,6 +556,12 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 			browser->nr_hierarchy_entries++;
 		if (he->leaf)
 			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
@@ -1383,8 +1400,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		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", s);
+			ui_browser__printf(&browser->b, "%s", ltrim(s));
+
+			while (isspace(s[i++]))
+				width++;
 		}
 	}
 
@@ -1412,6 +1434,75 @@ show_callchain:
 	return printed;
 }
 
+static int hist_browser__show_no_entry(struct hist_browser *browser,
+				       unsigned short row,
+				       int level, int nr_sort_keys)
+{
+	int width = browser->b.width;
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	bool first = true;
+	int column = 0;
+	int ret;
+	struct perf_hpp_fmt *fmt;
+
+	if (current_entry) {
+		browser->he_selection = NULL;
+		browser->selection = NULL;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	hists__for_each_format(browser->hists, 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) {
+			/* for folded sign */
+			first = false;
+			ret++;
+		} else {
+			/* space between columns */
+			ret += 2;
+		}
+
+		ui_browser__write_nstring(&browser->b, "", ret);
+		width -= ret;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", nr_sort_keys * HIERARCHY_INDENT);
+	width -= nr_sort_keys * HIERARCHY_INDENT;
+
+	if (column >= browser->b.horiz_scroll) {
+		char buf[32];
+
+		ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt);
+		ui_browser__printf(&browser->b, "  %s", buf);
+		width -= ret + 2;
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+	return 1;
+}
+
 static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 {
 	advance_hpp(hpp, inc);
@@ -1461,7 +1552,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	struct perf_hpp_fmt *fmt;
 	size_t ret = 0;
 	int column = 0;
-	int nr_sort_keys = hists->hpp_list->nr_sort_keys;
+	int nr_sort_keys = hists->nr_sort_keys;
 	bool first = true;
 
 	ret = scnprintf(buf, size, " ");
@@ -1490,6 +1581,8 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		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))
@@ -1507,7 +1600,12 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		dummy_hpp.buf[ret] = '\0';
 		rtrim(dummy_hpp.buf);
 
-		ret = strlen(dummy_hpp.buf);
+		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;
 	}
@@ -1546,7 +1644,7 @@ 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->hpp_list->nr_sort_keys;
+	int nr_sort = hb->hists->nr_sort_keys;
 
 	if (hb->show_headers) {
 		hist_browser__show_headers(hb);
@@ -1575,6 +1673,14 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 			row += hist_browser__show_hierarchy_entry(hb, h, row,
 								  h->depth,
 								  nr_sort);
+			if (row == browser->rows)
+				break;
+
+			if (h->has_no_entry) {
+				hist_browser__show_no_entry(hb, row, h->depth,
+							    nr_sort);
+				row++;
+			}
 		} else {
 			row += hist_browser__show_entry(hb, h, row);
 		}
@@ -1875,7 +1981,7 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
 						   browser->min_pcnt);
 	int printed = 0;
-	int nr_sort = browser->hists->hpp_list->nr_sort_keys;
+	int nr_sort = browser->hists->nr_sort_keys;
 
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
@@ -2461,6 +2567,11 @@ static void hist_browser__update_percent_limit(struct hist_browser *hb,
 	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		he = rb_entry(nd, struct hist_entry, rb_node);
 
+		if (he->has_no_entry) {
+			he->has_no_entry = false;
+			he->nr_rows = 0;
+		}
+
 		if (!he->leaf || !symbol_conf.use_callchain)
 			goto next;
 
@@ -2477,12 +2588,7 @@ static void hist_browser__update_percent_limit(struct hist_browser *hb,
 				     min_callchain_hits, &callchain_param);
 
 next:
-		/*
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
-		 * Tentatively set unfolded so that the rb_hierarchy_next()
-		 * can toggle children of folded entries too.
-		 */
-		he->unfolded = he->has_children;
-		nd = rb_hierarchy_next(nd);
 
 		/* force to re-evaluate folding state of callchains */
 		he->init_have_children = false;

tools/perf/ui/gtk/hists.c

@@ -449,6 +449,17 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists,
 			perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
 							store, &iter, hpp,
 							min_pcnt);
+
+			if (!hist_entry__has_hierarchy_children(he, min_pcnt)) {
+				char buf[32];
+				GtkTreeIter child;
+
+				snprintf(buf, sizeof(buf), "no entry >= %.2f%%",
+					 min_pcnt);
+
+				gtk_tree_store_append(store, &child, &iter);
+				gtk_tree_store_set(store, &child, col_idx, buf, -1);
+			}
 		}
 
 		if (symbol_conf.use_callchain && he->leaf) {

tools/perf/ui/hist.c

@@ -643,6 +643,28 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	return ret;
 }
 
+unsigned int hists__overhead_width(struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+	int ret = 0;
+	bool first = true;
+	struct perf_hpp dummy_hpp;
+
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+			break;
+
+		if (first)
+			first = false;
+		else
+			ret += 2;
+
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+	}
+
+	return ret;
+}
+
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	if (perf_hpp__is_sort_entry(fmt))

tools/perf/ui/stdio/hist.c

@@ -418,6 +418,7 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
 	char *buf = hpp->buf;
+	size_t size = hpp->size;
 	int ret, printed = 0;
 	bool first = true;
 
@@ -457,6 +458,11 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 				(nr_sort_key - 1) * HIERARCHY_INDENT + 2, "");
 	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.
@@ -467,7 +473,11 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 	else
 		fmt->entry(fmt, hpp, he);
 
-	printed += fprintf(fp, "%s\n", buf);
+	/*
+	 * dynamic entries are right-aligned but we want left-aligned
+	 * in the hierarchy mode
+	 */
+	printed += fprintf(fp, "%s\n", ltrim(buf));
 
 	if (symbol_conf.use_callchain && he->leaf) {
 		u64 total = hists__total_period(hists);
@@ -495,7 +505,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		size = hpp.size = bfsz;
 
 	if (symbol_conf.report_hierarchy) {
-		int nr_sort = hists->hpp_list->nr_sort_keys;
+		int nr_sort = hists->nr_sort_keys;
 
 		return hist_entry__hierarchy_fprintf(he, &hpp, nr_sort,
 						     hists, fp);
@@ -525,11 +535,12 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 {
 	bool first = true;
 	int nr_sort;
+	int depth;
 	unsigned width = 0;
 	unsigned header_width = 0;
 	struct perf_hpp_fmt *fmt;
 
-	nr_sort = hists->hpp_list->nr_sort_keys;
+	nr_sort = hists->nr_sort_keys;
 
 	/* preserve max indent depth for column headers */
 	print_hierarchy_indent(sep, nr_sort, spaces, fp);
@@ -558,19 +569,16 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 		if (!first)
 			header_width += fprintf(fp, " / ");
 		else {
-			header_width += fprintf(fp, "%s", sep ?: "  ");
+			fprintf(fp, "%s", sep ?: "  ");
 			first = false;
 		}
 
 		fmt->header(fmt, hpp, hists_to_evsel(hists));
 		rtrim(hpp->buf);
 
-		header_width += fprintf(fp, "%s", hpp->buf);
+		header_width += fprintf(fp, "%s", ltrim(hpp->buf));
 	}
 
-	/* preserve max indent depth for combined sort headers */
-	print_hierarchy_indent(sep, nr_sort, spaces, fp);
-
 	fprintf(fp, "\n# ");
 
 	/* preserve max indent depth for initial dots */
@@ -590,6 +598,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 		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;
@@ -597,15 +606,16 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 			continue;
 
 		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		width += depth * HIERARCHY_INDENT;
+
 		if (width > header_width)
 			header_width = width;
+
+		depth++;
 	}
 
 	fprintf(fp, "%s%-.*s", sep ?: "  ", header_width, dots);
 
-	/* preserve max indent depth for dots under sort headers */
-	print_hierarchy_indent(sep, nr_sort, dots, fp);
-
 	fprintf(fp, "\n#\n");
 
 	return 2;
@@ -628,6 +638,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	bool first = true;
 	size_t linesz;
 	char *line = NULL;
+	unsigned indent;
 
 	init_rem_hits();
 
@@ -704,6 +715,8 @@ print_entries:
 		goto out;
 	}
 
+	indent = hists__overhead_width(hists) + 4;
+
 	for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
@@ -720,6 +733,20 @@ print_entries:
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
 
+		/*
+		 * If all children are filtered out or percent-limited,
+		 * display "no entry >= x.xx%" message.
+		 */
+		if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
+			int nr_sort = hists->nr_sort_keys;
+
+			print_hierarchy_indent(sep, nr_sort + h->depth + 1, spaces, fp);
+			fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
+
+			if (max_rows && ++nr_rows >= max_rows)
+				break;
+		}
+
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(h->thread->mg,
 						   MAP__FUNCTION, fp);

tools/perf/util/color.c

@@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 	return 0;
 }
 
-int perf_color_default_config(const char *var, const char *value, void *cb)
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
 {
 	if (!strcmp(var, "color.ui")) {
 		perf_use_color_default = perf_config_colorbool(var, value, -1);
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int __color_vsnprintf(char *bf, size_t size, const char *color,

tools/perf/util/data-convert-bt.c

@@ -1117,7 +1117,7 @@ static int convert__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)

tools/perf/util/evlist.c

@@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	int err = 0;
 
 	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
 		err = perf_evsel__set_filter(evsel, filter);
 		if (err)
 			break;

tools/perf/util/help-unknown-cmd.c

@@ -6,7 +6,8 @@
 static int autocorrect;
 static struct cmdnames aliases;
 
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+static int perf_unknown_cmd_config(const char *var, const char *value,
+				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
@@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "alias."))
 		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int levenshtein_compare(const void *p1, const void *p2)

tools/perf/util/hist.c

@@ -1002,6 +1002,10 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 	int64_t cmp = 0;
 
 	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -1018,6 +1022,10 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	int64_t cmp = 0;
 
 	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -1117,7 +1125,7 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 	new->fmt = fmt;
 
 	/* some fields are now passed to 'new' */
-	if (perf_hpp__is_trace_entry(fmt))
+	if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
 		he->trace_output = NULL;
 	else
 		new->trace_output = NULL;
@@ -1363,6 +1371,10 @@ static void hierarchy_insert_output_entry(struct rb_root *root,
 
 	rb_link_node(&he->rb_node, parent, p);
 	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);
 }
 
 static void hists__hierarchy_output_resort(struct hists *hists,
@@ -1432,6 +1444,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
 
 	if (use_callchain) {
 		if (callchain_param.mode == CHAIN_GRAPH_REL) {
@@ -1458,6 +1471,12 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, entries);
+
+	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    perf_hpp__defined_dynamic_entry(fmt, he->hists))
+			fmt->sort(fmt, he, NULL);  /* update column width */
+	}
 }
 
 static void output_resort(struct hists *hists, struct ui_progress *prog,
@@ -1582,6 +1601,31 @@ struct rb_node *rb_hierarchy_prev(struct rb_node *node)
 	return &he->rb_node;
 }
 
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
+{
+	struct rb_node *node;
+	struct hist_entry *child;
+	float percent;
+
+	if (he->leaf)
+		return false;
+
+	node = rb_first(&he->hroot_out);
+	child = rb_entry(node, struct hist_entry, rb_node);
+
+	while (node && child->filtered) {
+		node = rb_next(node);
+		child = rb_entry(node, struct hist_entry, rb_node);
+	}
+
+	if (node)
+		percent = hist_entry__get_percent_limit(child);
+	else
+		percent = 0;
+
+	return node && percent >= limit;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
@@ -1600,6 +1644,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 
 			/* force fold unfiltered entry for simplicity */
 			parent->unfolded = false;
+			parent->has_no_entry = false;
 			parent->row_offset = 0;
 			parent->nr_rows = 0;
 next:
@@ -1612,6 +1657,7 @@ next:
 
 	/* force fold unfiltered entry for simplicity */
 	h->unfolded = false;
+	h->has_no_entry = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 

tools/perf/util/hist.h

@@ -78,6 +78,7 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 	int			socket_filter;
 	struct perf_hpp_list	*hpp_list;
+	int			nr_sort_keys;
 };
 
 struct hist_entry_iter;
@@ -410,6 +411,7 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+unsigned int hists__overhead_width(struct hists *hists);
 
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  struct perf_sample *sample, bool nonany_branch_mode);
@@ -439,4 +441,6 @@ static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
 
 #define HIERARCHY_INDENT  3
 
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+
 #endif	/* __PERF_HIST_H */

tools/perf/util/parse-events.y

@@ -217,14 +217,14 @@ event_def: event_pmu |
 	   event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
-	parse_events_terms__delete($3);
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |

tools/perf/util/scripting-engines/trace-event-perl.c

@@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;

tools/perf/util/scripting-engines/trace-event-python.c

@@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;

tools/perf/util/sort.c

@@ -1764,6 +1764,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	if (hde->raw_trace)
 		goto raw_field;
 
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
 	field = hde->field;
 	namelen = strlen(field->name);
 	str = he->trace_output;
@@ -1813,6 +1816,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
 
+	if (b == NULL) {
+		update_dynamic_len(hde, a);
+		return 0;
+	}
+
 	field = hde->field;
 	if (field->flags & FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
@@ -1827,9 +1835,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	} else {
 		offset = field->offset;
 		size = field->size;
-
-		update_dynamic_len(hde, a);
-		update_dynamic_len(hde, b);
 	}
 
 	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
@@ -2633,6 +2638,9 @@ out:
 int setup_sorting(struct perf_evlist *evlist)
 {
 	int err;
+	struct hists *hists;
+	struct perf_evsel *evsel;
+	struct perf_hpp_fmt *fmt;
 
 	err = __setup_sorting(evlist);
 	if (err < 0)
@@ -2644,6 +2652,22 @@ int setup_sorting(struct perf_evlist *evlist)
 			return err;
 	}
 
+	evlist__for_each(evlist, evsel) {
+		hists = evsel__hists(evsel);
+		hists->nr_sort_keys = perf_hpp_list.nr_sort_keys;
+
+		/*
+		 * If dynamic entries were used, it might add multiple
+		 * entries to each evsel for a single field name.  Set
+		 * actual number of sort keys for each hists.
+		 */
+		perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+			if (perf_hpp__is_dynamic_entry(fmt) &&
+			    !perf_hpp__defined_dynamic_entry(fmt, hists))
+				hists->nr_sort_keys--;
+		}
+	}
+
 	reset_dimensions();
 
 	/*

tools/perf/util/sort.h

@@ -117,6 +117,7 @@ struct hist_entry {
 			bool	init_have_children;
 			bool	unfolded;
 			bool	has_children;
+			bool	has_no_entry;
 		};
 	};
 	char			*srcline;