Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates and fixes from Ingo Molnar:
 "It's mostly fixes, but there's also two late items:

   - preliminary GTK GUI support for perf report
   - PMU raw event format descriptors in sysfs, to be parsed by tooling

  The raw event format in sysfs is a new ABI.  For example for the 'CPU'
  PMU we have:

    aldebaran:~> ll /sys/bus/event_source/devices/cpu/format/*
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/any
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/cmask
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/edge
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/event
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/inv
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/offcore_rsp
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/pc
    -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/umask

  those lists of fields contain a specific format:

    aldebaran:~> cat /sys/bus/event_source/devices/cpu/format/offcore_rsp
    config1:0-63

  So, those who wish to specify raw events can now use the following
  event format:

    -e cpu/cmask=1,event=2,umask=3

  Most people will not want to specify any events (let alone raw
  events), they'll just use whatever default event the tools use.

  But for more obscure PMU events that have no cross-architecture
  generic events the above syntax is more usable and a bit more
  structured than specifying hex numbers."

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  perf tools: Remove auto-generated bison/flex files
  perf annotate: Fix off by one symbol hist size allocation and hit accounting
  perf tools: Add missing ref-cycles event back to event parser
  perf annotate: addr2line wants addresses in same format as objdump
  perf probe: Finder fails to resolve function name to address
  tracing: Fix ent_size in trace output
  perf symbols: Handle NULL dso in dso__name_len
  perf symbols: Do not include libgen.h
  perf tools: Fix bug in raw sample parsing
  perf tools: Fix display of first level of callchains
  perf tools: Switch module.h into export.h
  perf: Move mmap page data_head offset assertion out of header
  perf: Fix mmap_page capabilities and docs
  perf diff: Fix to work with new hists design
  perf tools: Fix modifier to be applied on correct events
  perf tools: Fix various casting issues for 32 bits
  perf tools: Simplify event_read_id exit path
  tracing: Fix ftrace stack trace entries
  tracing: Move the tracing_on/off() declarations into CONFIG_TRACING
  perf report: Add a simple GTK2-based 'perf report' browser
  ...

1 files changed, 132 insertions, 68 deletions

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3dc99a9b71f5..2ec4b60aff6c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -10,11 +10,14 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he);
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he);
 
 enum hist_filter {
 	HIST_FILTER__DSO,
 	HIST_FILTER__THREAD,
 	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
 };
 
 struct callchain_param	callchain_param = {
@@ -420,6 +423,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 {
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
+	hists__filter_entry_by_symbol(hists, he);
 }
 
 static void __hists__collapse_resort(struct hists *hists, bool threaded)
@@ -603,7 +607,7 @@ static void init_rem_hits(void)
 	rem_hits.ms.sym = rem_sq_bracket;
 }
 
-static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 					 u64 total_samples, int depth,
 					 int depth_mask, int left_margin)
 {
@@ -611,21 +615,16 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_node *child;
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
-	u64 new_total;
 	u64 remaining;
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = self->children_hit;
-	else
-		new_total = total_samples;
-
-	remaining = new_total;
+	remaining = total_samples;
 
-	node = rb_first(&self->rb_root);
+	node = rb_first(root);
 	while (node) {
+		u64 new_total;
 		u64 cumul;
 
 		child = rb_entry(node, struct callchain_node, rb_node);
@@ -653,11 +652,17 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		list_for_each_entry(chain, &child->val, list) {
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
-						      new_total,
+						      total_samples,
 						      cumul,
 						      left_margin);
 		}
-		ret += __callchain__fprintf_graph(fp, child, new_total,
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			new_total = child->children_hit;
+		else
+			new_total = total_samples;
+
+		ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
 						  depth + 1,
 						  new_depth_mask | (1 << depth),
 						  left_margin);
@@ -667,61 +672,75 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	}
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
-		remaining && remaining != new_total) {
+		remaining && remaining != total_samples) {
 
 		if (!rem_sq_bracket)
 			return ret;
 
 		new_depth_mask &= ~(1 << (depth - 1));
-
 		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
-					      new_depth_mask, 0, new_total,
+					      new_depth_mask, 0, total_samples,
 					      remaining, left_margin);
 	}
 
 	return ret;
 }
 
-static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 				       u64 total_samples, int left_margin)
 {
+	struct callchain_node *cnode;
 	struct callchain_list *chain;
+	u32 entries_printed = 0;
 	bool printed = false;
+	struct rb_node *node;
 	int i = 0;
-	int ret = 0;
-	u32 entries_printed = 0;
-
-	list_for_each_entry(chain, &self->val, list) {
-		if (!i++ && sort__first_dimension == SORT_SYM)
-			continue;
-
-		if (!printed) {
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "|\n");
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "---");
-
-			left_margin += 3;
-			printed = true;
-		} else
-			ret += callchain__fprintf_left_margin(fp, left_margin);
+	int ret;
 
-		if (chain->ms.sym)
-			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+	/*
+	 * If have one single callchain root, don't bother printing
+	 * its percentage (100 % in fractal mode and the same percentage
+	 * than the hist in graph mode). This also avoid one level of column.
+	 */
+	node = rb_first(root);
+	if (node && !rb_next(node)) {
+		cnode = rb_entry(node, struct callchain_node, rb_node);
+		list_for_each_entry(chain, &cnode->val, list) {
+			/*
+			 * If we sort by symbol, the first entry is the same than
+			 * the symbol. No need to print it otherwise it appears as
+			 * displayed twice.
+			 */
+			if (!i++ && sort__first_dimension == SORT_SYM)
+				continue;
+			if (!printed) {
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "|\n");
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "---");
+				left_margin += 3;
+				printed = true;
+			} else
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			if (chain->ms.sym)
+				ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+			else
+				ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
 
-		if (++entries_printed == callchain_param.print_limit)
-			break;
+			if (++entries_printed == callchain_param.print_limit)
+				break;
+		}
+		root = &cnode->rb_root;
 	}
 
-	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
-
-	return ret;
+	return __callchain__fprintf_graph(fp, root, total_samples,
+					  1, 1, left_margin);
 }
 
-static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
-				      u64 total_samples)
+static size_t __callchain__fprintf_flat(FILE *fp,
+					struct callchain_node *self,
+					u64 total_samples)
 {
 	struct callchain_list *chain;
 	size_t ret = 0;
@@ -729,7 +748,7 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	if (!self)
 		return 0;
 
-	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
+	ret += __callchain__fprintf_flat(fp, self->parent, total_samples);
 
 
 	list_for_each_entry(chain, &self->val, list) {
@@ -745,44 +764,58 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	return ret;
 }
 
-static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
-					    u64 total_samples, int left_margin,
-					    FILE *fp)
+static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self,
+				      u64 total_samples)
 {
-	struct rb_node *rb_node;
-	struct callchain_node *chain;
 	size_t ret = 0;
 	u32 entries_printed = 0;
+	struct rb_node *rb_node;
+	struct callchain_node *chain;
 
-	rb_node = rb_first(&he->sorted_chain);
+	rb_node = rb_first(self);
 	while (rb_node) {
 		double percent;
 
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
 		percent = chain->hit * 100.0 / total_samples;
-		switch (callchain_param.mode) {
-		case CHAIN_FLAT:
-			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
-						     percent);
-			ret += callchain__fprintf_flat(fp, chain, total_samples);
-			break;
-		case CHAIN_GRAPH_ABS: /* Falldown */
-		case CHAIN_GRAPH_REL:
-			ret += callchain__fprintf_graph(fp, chain, total_samples,
-							left_margin);
-		case CHAIN_NONE:
-		default:
-			break;
-		}
+
+		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+		ret += __callchain__fprintf_flat(fp, chain, total_samples);
 		ret += fprintf(fp, "\n");
 		if (++entries_printed == callchain_param.print_limit)
 			break;
+
 		rb_node = rb_next(rb_node);
 	}
 
 	return ret;
 }
 
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+					    u64 total_samples, int left_margin,
+					    FILE *fp)
+{
+	switch (callchain_param.mode) {
+	case CHAIN_GRAPH_REL:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, he->period,
+						left_margin);
+		break;
+	case CHAIN_GRAPH_ABS:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						left_margin);
+		break;
+	case CHAIN_FLAT:
+		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
+		break;
+	case CHAIN_NONE:
+		break;
+	default:
+		pr_err("Bad callchain mode\n");
+	}
+
+	return 0;
+}
+
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 {
 	struct rb_node *next = rb_first(&hists->entries);
@@ -887,9 +920,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 		diff = new_percent - old_percent;
 
 		if (fabs(diff) >= 0.01)
-			ret += scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
+			scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
 		else
-			ret += scnprintf(bf, sizeof(bf), " ");
+			scnprintf(bf, sizeof(bf), " ");
 
 		if (sep)
 			ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -898,9 +931,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 
 		if (show_displacement) {
 			if (displacement)
-				ret += scnprintf(bf, sizeof(bf), "%+4ld", displacement);
+				scnprintf(bf, sizeof(bf), "%+4ld", displacement);
 			else
-				ret += scnprintf(bf, sizeof(bf), " ");
+				scnprintf(bf, sizeof(bf), " ");
 
 			if (sep)
 				ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -1247,6 +1280,37 @@ void hists__filter_by_thread(struct hists *hists)
 	}
 }
 
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if (hists->symbol_filter_str != NULL &&
+	    (!he->ms.sym || strstr(he->ms.sym->name,
+				   hists->symbol_filter_str) == NULL)) {
+		he->filtered |= (1 << HIST_FILTER__SYMBOL);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	struct rb_node *nd;
+
+	hists->nr_entries = hists->stats.total_period = 0;
+	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (hists__filter_entry_by_symbol(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+	}
+}
+
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);