Merge tag 'perf-core-for-mingo-20160310' 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:

  - Implement 'perf stat --metric-only' (Andi Kleen)

  - Fix perf script python database export crash (Chris Phlipot)

Infrastructure changes:

  - perf top/report --hierarchy assorted fixes for problems introduced in this
    perf/core cycle (Namhyung Kim)

  - Support '~' operation in libtraceevent (Steven Rosted)

Build fixes:

  - Fix bulding of jitdump on opensuse on ubuntu systems when the DWARF
    devel files are not installed (Arnaldo Carvalho de Melo)

  - Do not try building jitdump on unsupported arches (Jiri Olsa)

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

7 files changed, 210 insertions, 102 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index df2b690970ac..eea25e2424e9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -107,9 +107,12 @@ libperf-y += scripting-engines/
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 libperf-y += demangle-java.o
+
+ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
 libperf-$(CONFIG_LIBELF) += genelf.o
 libperf-$(CONFIG_LIBELF) += genelf_debug.o
+endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 # avoid compiler warnings in 32-bit mode
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index efad78f811ad..501ea6e565f1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -93,10 +93,8 @@ struct perf_evsel {
 	const char		*unit;
 	struct event_format	*tp_format;
 	off_t			id_offset;
-	union {
-		void		*priv;
-		u64		db_id;
-	};
+	void			*priv;
+	u64			db_id;
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 29da9e0d8db9..290b3cbf6877 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1087,10 +1087,103 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
  */
 
 static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he,
+				       enum hist_filter type);
+
+typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt);
+
+static bool check_thread_entry(struct perf_hpp_fmt *fmt)
+{
+	return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt);
+}
+
+static void hist_entry__check_and_remove_filter(struct hist_entry *he,
+						enum hist_filter type,
+						fmt_chk_fn check)
+{
+	struct perf_hpp_fmt *fmt;
+	bool type_match = false;
+	struct hist_entry *parent = he->parent_he;
+
+	switch (type) {
+	case HIST_FILTER__THREAD:
+		if (symbol_conf.comm_list == NULL &&
+		    symbol_conf.pid_list == NULL &&
+		    symbol_conf.tid_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__DSO:
+		if (symbol_conf.dso_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__SYMBOL:
+		if (symbol_conf.sym_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__PARENT:
+	case HIST_FILTER__GUEST:
+	case HIST_FILTER__HOST:
+	case HIST_FILTER__SOCKET:
+	default:
+		return;
+	}
+
+	/* if it's filtered by own fmt, it has to have filter bits */
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (check(fmt)) {
+			type_match = true;
+			break;
+		}
+	}
+
+	if (type_match) {
+		/*
+		 * If the filter is for current level entry, propagate
+		 * filter marker to parents.  The marker bit was
+		 * already set by default so it only needs to clear
+		 * non-filtered entries.
+		 */
+		if (!(he->filtered & (1 << type))) {
+			while (parent) {
+				parent->filtered &= ~(1 << type);
+				parent = parent->parent_he;
+			}
+		}
+	} else {
+		/*
+		 * If current entry doesn't have matching formats, set
+		 * filter marker for upper level entries.  it will be
+		 * cleared if its lower level entries is not filtered.
+		 *
+		 * For lower-level entries, it inherits parent's
+		 * filter bit so that lower level entries of a
+		 * non-filtered entry won't set the filter marker.
+		 */
+		if (parent == NULL)
+			he->filtered |= (1 << type);
+		else
+			he->filtered |= (parent->filtered & (1 << type));
+	}
+}
+
+static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
+{
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD,
+					    check_thread_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO,
+					    perf_hpp__is_dso_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL,
+					    perf_hpp__is_sym_entry);
+
+	hists__apply_filters(he->hists, he);
+}
 
 static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 						 struct rb_root *root,
 						 struct hist_entry *he,
+						 struct hist_entry *parent_he,
 						 struct perf_hpp_list *hpp_list)
 {
 	struct rb_node **p = &root->rb_node;
@@ -1125,11 +1218,13 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 	if (new == NULL)
 		return NULL;
 
-	hists__apply_filters(hists, new);
 	hists->nr_entries++;
 
 	/* save related format list for output */
 	new->hpp_list = hpp_list;
+	new->parent_he = parent_he;
+
+	hist_entry__apply_hierarchy_filters(new);
 
 	/* some fields are now passed to 'new' */
 	perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
@@ -1170,14 +1265,13 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 			continue;
 
 		/* insert copy of 'he' for each fmt into the hierarchy */
-		new_he = hierarchy_insert_entry(hists, root, he, &node->hpp);
+		new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp);
 		if (new_he == NULL) {
 			ret = -1;
 			break;
 		}
 
 		root = &new_he->hroot_in;
-		new_he->parent_he = parent;
 		new_he->depth = depth++;
 		parent = new_he;
 	}
@@ -1359,6 +1453,31 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 	hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_recalc_total_periods(struct hists *hists)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	node = rb_first(&hists->entries);
+
+	hists->stats.total_period = 0;
+	hists->stats.total_non_filtered_period = 0;
+
+	/*
+	 * recalculate total period using top-level entries only
+	 * since lower level entries only see non-filtered entries
+	 * but upper level entries have sum of both entries.
+	 */
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node);
+		node = rb_next(node);
+
+		hists->stats.total_period += he->stat.period;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period += he->stat.period;
+	}
+}
+
 static void hierarchy_insert_output_entry(struct rb_root *root,
 					  struct hist_entry *he)
 {
@@ -1424,11 +1543,6 @@ static void hists__hierarchy_output_resort(struct hists *hists,
 			continue;
 		}
 
-		/* only update stat for leaf entries to avoid duplication */
-		hists__inc_stats(hists, he);
-		if (!he->filtered)
-			hists__calc_col_len(hists, he);
-
 		if (!use_callchain)
 			continue;
 
@@ -1508,11 +1622,13 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	hists__reset_col_len(hists);
 
 	if (symbol_conf.report_hierarchy) {
-		return hists__hierarchy_output_resort(hists, prog,
-						      &hists->entries_collapsed,
-						      &hists->entries,
-						      min_callchain_hits,
-						      use_callchain);
+		hists__hierarchy_output_resort(hists, prog,
+					       &hists->entries_collapsed,
+					       &hists->entries,
+					       min_callchain_hits,
+					       use_callchain);
+		hierarchy_recalc_total_periods(hists);
+		return;
 	}
 
 	if (sort__need_collapse)
@@ -1833,6 +1949,8 @@ static void hists__filter_hierarchy(struct hists *hists, int type, const void *a
 		}
 	}
 
+	hierarchy_recalc_total_periods(hists);
+
 	/*
 	 * resort output after applying a new filter since filter in a lower
 	 * hierarchy can change periods in a upper hierarchy.
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 2cb017f28f9e..ead18c82294f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -79,7 +79,6 @@ struct hists {
 	int			socket_filter;
 	struct perf_hpp_list	*hpp_list;
 	struct list_head	hpp_formats;
-	int			nr_sort_keys;
 	int			nr_hpp_node;
 };
 
@@ -241,7 +240,6 @@ struct perf_hpp_fmt {
 struct perf_hpp_list {
 	struct list_head fields;
 	struct list_head sorts;
-	int nr_sort_keys;
 };
 
 extern struct perf_hpp_list perf_hpp_list;
@@ -318,6 +316,10 @@ bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *his
 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);
+bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt);
 
 struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d8cd038baed2..adef23b1352e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	const char *lc;
+	char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -146,7 +146,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
 
-	free((char *) lc);
+	free(lc);
 
 	ret = 0;
 error:
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 041f236379e0..93fa136b0025 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -27,6 +27,7 @@ int		sort__has_sym = 0;
 int		sort__has_dso = 0;
 int		sort__has_socket = 0;
 int		sort__has_thread = 0;
+int		sort__has_comm = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 /*
@@ -1488,38 +1489,26 @@ bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
 	return format->header == __sort__hpp_header;
 }
 
-bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt)
-{
-	struct hpp_sort_entry *hse;
-
-	if (!perf_hpp__is_sort_entry(fmt))
-		return false;
-
-	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	return hse->se == &sort_trace;
+#define MK_SORT_ENTRY_CHK(key)					\
+bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt)	\
+{								\
+	struct hpp_sort_entry *hse;				\
+								\
+	if (!perf_hpp__is_sort_entry(fmt))			\
+		return false;					\
+								\
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);	\
+	return hse->se == &sort_ ## key ;			\
 }
 
-bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt)
-{
-	struct hpp_sort_entry *hse;
+MK_SORT_ENTRY_CHK(trace)
+MK_SORT_ENTRY_CHK(srcline)
+MK_SORT_ENTRY_CHK(srcfile)
+MK_SORT_ENTRY_CHK(thread)
+MK_SORT_ENTRY_CHK(comm)
+MK_SORT_ENTRY_CHK(dso)
+MK_SORT_ENTRY_CHK(sym)
 
-	if (!perf_hpp__is_sort_entry(fmt))
-		return false;
-
-	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	return hse->se == &sort_srcline;
-}
-
-bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt)
-{
-	struct hpp_sort_entry *hse;
-
-	if (!perf_hpp__is_sort_entry(fmt))
-		return false;
-
-	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	return hse->se == &sort_srcfile;
-}
 
 static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 {
@@ -1602,31 +1591,47 @@ int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
 {
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
+	int ret = -1;
+	int r;
 
-	fmt = he->fmt;
-	if (fmt == NULL || !perf_hpp__is_sort_entry(fmt))
-		return -1;
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
 
-	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	if (hse->se->se_filter == NULL)
-		return -1;
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_filter == NULL)
+			continue;
+
+		/*
+		 * hist entry is filtered if any of sort key in the hpp list
+		 * is applied.  But it should skip non-matched filter types.
+		 */
+		r = hse->se->se_filter(he, type, arg);
+		if (r >= 0) {
+			if (ret < 0)
+				ret = 0;
+			ret |= r;
+		}
+	}
 
-	return hse->se->se_filter(he, type, arg);
+	return ret;
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd, int level)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
+					  struct perf_hpp_list *list,
+					  int level)
 {
 	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__register_sort_field(&hse->hpp);
+	perf_hpp_list__register_sort_field(list, &hse->hpp);
 	return 0;
 }
 
-static int __sort_dimension__add_hpp_output(struct perf_hpp_list *list,
-					    struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
+					    struct perf_hpp_list *list)
 {
 	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
@@ -2147,12 +2152,14 @@ out:
 	return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd, int level)
+static int __sort_dimension__add(struct sort_dimension *sd,
+				 struct perf_hpp_list *list,
+				 int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_sort(sd, level) < 0)
+	if (__sort_dimension__add_hpp_sort(sd, list, level) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -2163,7 +2170,9 @@ static int __sort_dimension__add(struct sort_dimension *sd, int level)
 	return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd, int level)
+static int __hpp_dimension__add(struct hpp_dimension *hd,
+				struct perf_hpp_list *list,
+				int level)
 {
 	struct perf_hpp_fmt *fmt;
 
@@ -2175,7 +2184,7 @@ static int __hpp_dimension__add(struct hpp_dimension *hd, int level)
 		return -1;
 
 	hd->taken = 1;
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp_list__register_sort_field(list, fmt);
 	return 0;
 }
 
@@ -2185,7 +2194,7 @@ static int __sort_dimension__add_output(struct perf_hpp_list *list,
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_output(list, sd) < 0)
+	if (__sort_dimension__add_hpp_output(sd, list) < 0)
 		return -1;
 
 	sd->taken = 1;
@@ -2215,7 +2224,8 @@ 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,
+static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			       struct perf_evlist *evlist __maybe_unused,
 			       int level)
 {
 	unsigned int i;
@@ -2253,9 +2263,11 @@ static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
 			sort__has_socket = 1;
 		} else if (sd->entry == &sort_thread) {
 			sort__has_thread = 1;
+		} else if (sd->entry == &sort_comm) {
+			sort__has_comm = 1;
 		}
 
-		return __sort_dimension__add(sd, level);
+		return __sort_dimension__add(sd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2264,7 +2276,7 @@ static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add(hd, level);
+		return __hpp_dimension__add(hd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2279,7 +2291,7 @@ static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd, level);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
@@ -2295,7 +2307,7 @@ static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
 		if (sd->entry == &sort_mem_daddr_sym)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd, level);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
@@ -2305,7 +2317,8 @@ static int sort_dimension__add(const char *tok, struct perf_evlist *evlist,
 	return -ESRCH;
 }
 
-static int setup_sort_list(char *str, struct perf_evlist *evlist)
+static int setup_sort_list(struct perf_hpp_list *list, char *str,
+			   struct perf_evlist *evlist)
 {
 	char *tmp, *tok;
 	int ret = 0;
@@ -2332,7 +2345,7 @@ static int setup_sort_list(char *str, struct perf_evlist *evlist)
 		}
 
 		if (*tok) {
-			ret = sort_dimension__add(tok, evlist, level);
+			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
 				error("Invalid --sort key: `%s'", tok);
 				break;
@@ -2480,7 +2493,7 @@ static int __setup_sorting(struct perf_evlist *evlist)
 		}
 	}
 
-	ret = setup_sort_list(str, evlist);
+	ret = setup_sort_list(&perf_hpp_list, str, evlist);
 
 	free(str);
 	return ret;
@@ -2693,29 +2706,6 @@ out:
 	return ret;
 }
 
-static void evlist__set_hists_nr_sort_keys(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		struct perf_hpp_fmt *fmt;
-		struct hists *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--;
-		}
-	}
-}
-
 int setup_sorting(struct perf_evlist *evlist)
 {
 	int err;
@@ -2725,14 +2715,11 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent", evlist, -1);
+		err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
 		if (err < 0)
 			return err;
 	}
 
-	if (evlist != NULL)
-		evlist__set_hists_nr_sort_keys(evlist);
-
 	reset_dimensions();
 
 	/*
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ea1f722cffea..3f4e35998119 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -37,6 +37,7 @@ extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
 extern int sort__has_thread;
+extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -129,7 +130,6 @@ struct hist_entry {
 	void			*raw_data;
 	u32			raw_size;
 	void			*trace_output;
-	struct perf_hpp_fmt	*fmt;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	union {