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

  - Callchain improvements from Andi Kleen including:
    * Enable printing the srcline in the history
    * Make get_srcline fall back to sym+offset

  - Allow to force redirect pr_debug to stderr. (Andi Kleen)

  - TUI hist_entry browser fixes, including showing missing overhead
    value for first level callchain. Detected comparing the output of
    --stdio/--gui (that matched) with --tui, that had this problem. (Namhyung Kim)

  - Fix segfault due to invalid kernel dso access (Namhyung Kim)

Infrastructure changes:

  - Move bfd_demangle stubbing to its only user (Arnaldo Carvalho de Melo)

  - 'perf stat' refactorings, moving stuff from it to evsel.c to use in
    per-pkg/snapshot format changes (Jiri Olsa)

  - Add per-pkg format file parsing (Matt Fleming)

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

tools/perf/ui/browsers/hists.c

@@ -227,10 +227,14 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no
 	}
 }
 
-static void callchain_node__init_have_children(struct callchain_node *node)
+static void callchain_node__init_have_children(struct callchain_node *node,
+					       bool has_sibling)
 {
 	struct callchain_list *chain;
 
+	chain = list_entry(node->val.next, struct callchain_list, list);
+	chain->ms.has_children = has_sibling;
+
 	if (!list_empty(&node->val)) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
@@ -241,11 +245,12 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 
 static void callchain__init_have_children(struct rb_root *root)
 {
-	struct rb_node *nd;
+	struct rb_node *nd = rb_first(root);
+	bool has_sibling = nd && rb_next(nd);
 
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-		callchain_node__init_have_children(node);
+		callchain_node__init_have_children(node, has_sibling);
 	}
 }
 
@@ -542,8 +547,11 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
 	u64 new_total;
+	bool need_percent;
 
 	node = rb_first(root);
+	need_percent = !!rb_next(node);
+
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
@@ -560,7 +568,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 
 			if (first)
 				first = false;
-			else if (level > 1)
+			else if (need_percent)
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
@@ -573,7 +581,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 			str = callchain_list__sym_name(chain, bf, sizeof(bf),
 						       browser->show_dso);
 
-			if (was_first && level > 1) {
+			if (was_first && need_percent) {
 				double percent = cumul * 100.0 / total;
 
 				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
@@ -790,6 +798,13 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			if (symbol_conf.cumulate_callchain)
+				total = entry->stat_acc->period;
+			else
+				total = entry->stat.period;
+		}
+
 		printed += hist_browser__show_callchain(browser,
 					&entry->sorted_chain, 1, row, total,
 					hist_browser__show_callchain_entry, &arg,

tools/perf/util/annotate.c

@@ -1192,7 +1192,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			goto next;
 
 		offset = start + i;
-		src_line->path = get_srcline(map->dso, offset);
+		src_line->path = get_srcline(map->dso, offset, NULL, false);
 		insert_source_line(&tmp_root, src_line);
 
 	next:

tools/perf/util/callchain.c

@@ -815,7 +815,17 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 	int printed;
 
 	if (cl->ms.sym) {
-		printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+		if (callchain_param.key == CCKEY_ADDRESS &&
+		    cl->ms.map && !cl->srcline)
+			cl->srcline = get_srcline(cl->ms.map->dso,
+						  map__rip_2objdump(cl->ms.map,
+								    cl->ip),
+						  cl->ms.sym, false);
+		if (cl->srcline)
+			printed = scnprintf(bf, bfsize, "%s %s",
+					cl->ms.sym->name, cl->srcline);
+		else
+			printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
 	} else
 		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 

tools/perf/util/callchain.h

@@ -70,6 +70,7 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
+	char		       *srcline;
 	struct list_head	list;
 };
 

tools/perf/util/debug.c

@@ -19,13 +19,14 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
+static int redirect_to_stderr;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
 	if (var >= level) {
-		if (use_browser >= 1)
+		if (use_browser >= 1 && !redirect_to_stderr)
 			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
@@ -145,6 +146,7 @@ static struct debug_variable {
 } debug_variables[] = {
 	{ .name = "verbose",		.ptr = &verbose },
 	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
+	{ .name = "stderr",		.ptr = &redirect_to_stderr},
 	{ .name = NULL, }
 };
 

tools/perf/util/evsel.c

@@ -876,9 +876,8 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-static inline void compute_deltas(struct perf_evsel *evsel,
-				  int cpu,
-				  struct perf_counts_values *count)
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
 
@@ -898,6 +897,42 @@ static inline void compute_deltas(struct perf_evsel *evsel,
 	count->run = count->run - tmp.run;
 }
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+		}
+	} else
+		count->ena = count->run = 0;
+
+	if (pscaled)
+		*pscaled = scaled;
+}
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb)
+{
+	struct perf_counts_values count;
+
+	memset(&count, 0, sizeof(count));
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+		return -errno;
+
+	return cb(evsel, cpu, thread, &count);
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
@@ -913,16 +948,8 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	compute_deltas(evsel, cpu, &count);
-
-	if (scale) {
-		if (count.run == 0)
-			count.val = 0;
-		else if (count.run < count.ena)
-			count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
-	} else
-		count.ena = count.run = 0;
-
+	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_counts_values__scale(&count, scale, NULL);
 	evsel->counts->cpu[cpu] = count;
 	return 0;
 }
@@ -956,23 +983,8 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 		}
 	}
 
-	compute_deltas(evsel, -1, aggr);
-
-	evsel->counts->scaled = 0;
-	if (scale) {
-		if (aggr->run == 0) {
-			evsel->counts->scaled = -1;
-			aggr->val = 0;
-			return 0;
-		}
-
-		if (aggr->run < aggr->ena) {
-			evsel->counts->scaled = 1;
-			aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
-		}
-	} else
-		aggr->ena = aggr->run = 0;
-
+	perf_evsel__compute_deltas(evsel, -1, aggr);
+	perf_counts_values__scale(aggr, scale, &evsel->counts->scaled);
 	return 0;
 }
 

tools/perf/util/evsel.h

@@ -73,6 +73,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
+	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -91,6 +92,7 @@ struct perf_evsel {
 	bool			immediate;
 	bool			system_wide;
 	bool			tracking;
+	bool			per_pkg;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
@@ -110,6 +112,12 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled);
+
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count);
+
 int perf_evsel__object_config(size_t object_size,
 			      int (*init)(struct perf_evsel *evsel),
 			      void (*fini)(struct perf_evsel *evsel));
@@ -227,6 +235,13 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
+typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
+				    int cpu, int thread,
+				    struct perf_counts_values *count);
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
 

tools/perf/util/machine.c

@@ -1106,8 +1106,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
-		if (strstr(dso->long_name, "vmlinux"))
-			dso__set_short_name(dso, "[kernel.vmlinux]", false);
+		if (strstr(kernel->long_name, "vmlinux"))
+			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
 		machine__set_kernel_mmap_len(machine, event);
 

tools/perf/util/map.c

@@ -360,7 +360,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
 	if (map && map->dso) {
 		srcline = get_srcline(map->dso,
-				      map__rip_2objdump(map, addr));
+				      map__rip_2objdump(map, addr), NULL, true);
 		if (srcline != SRCLINE_UNKNOWN)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);

tools/perf/util/parse-events.c

@@ -681,6 +681,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
+		evsel->per_pkg = info.per_pkg;
+		evsel->snapshot = info.snapshot;
 	}
 
 	return evsel ? 0 : -ENOMEM;

tools/perf/util/pmu.c

@@ -163,6 +163,41 @@ error:
 	return -1;
 }
 
+static int
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	close(fd);
+
+	alias->per_pkg = true;
+	return 0;
+}
+
+static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
+				    char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	alias->snapshot = true;
+	close(fd);
+	return 0;
+}
+
 static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;
@@ -181,6 +216,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
+	alias->per_pkg = false;
 
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {
@@ -194,6 +230,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	 */
 	perf_pmu__parse_unit(alias, dir, name);
 	perf_pmu__parse_scale(alias, dir, name);
+	perf_pmu__parse_per_pkg(alias, dir, name);
+	perf_pmu__parse_snapshot(alias, dir, name);
 
 	list_add_tail(&alias->list, list);
 
@@ -209,6 +247,10 @@ static inline bool pmu_alias_info_file(char *name)
 		return true;
 	if (len > 6 && !strcmp(name + len - 6, ".scale"))
 		return true;
+	if (len > 8 && !strcmp(name + len - 8, ".per-pkg"))
+		return true;
+	if (len > 9 && !strcmp(name + len - 9, ".snapshot"))
+		return true;
 
 	return false;
 }
@@ -617,23 +659,27 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 }
 
 
-static int check_unit_scale(struct perf_pmu_alias *alias,
-			    const char **unit, double *scale)
+static int check_info_data(struct perf_pmu_alias *alias,
+			   struct perf_pmu_info *info)
 {
 	/*
 	 * Only one term in event definition can
-	 * define unit and scale, fail if there's
-	 * more than one.
+	 * define unit, scale and snapshot, fail
+	 * if there's more than one.
 	 */
-	if ((*unit && alias->unit) ||
-	    (*scale && alias->scale))
+	if ((info->unit && alias->unit) ||
+	    (info->scale && alias->scale) ||
+	    (info->snapshot && alias->snapshot))
 		return -EINVAL;
 
 	if (alias->unit)
-		*unit = alias->unit;
+		info->unit = alias->unit;
 
 	if (alias->scale)
-		*scale = alias->scale;
+		info->scale = alias->scale;
+
+	if (alias->snapshot)
+		info->snapshot = alias->snapshot;
 
 	return 0;
 }
@@ -649,12 +695,15 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	info->per_pkg = false;
+
 	/*
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)
 	 */
-	info->unit   = NULL;
-	info->scale  = 0.0;
+	info->unit     = NULL;
+	info->scale    = 0.0;
+	info->snapshot = false;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -664,10 +713,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
-		ret = check_unit_scale(alias, &info->unit, &info->scale);
+		ret = check_info_data(alias, info);
 		if (ret)
 			return ret;
 
+		if (alias->per_pkg)
+			info->per_pkg = true;
+
 		list_del(&term->list);
 		free(term);
 	}

tools/perf/util/pmu.h

@@ -29,6 +29,8 @@ struct perf_pmu {
 struct perf_pmu_info {
 	const char *unit;
 	double scale;
+	bool per_pkg;
+	bool snapshot;
 };
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
@@ -39,6 +41,8 @@ struct perf_pmu_alias {
 	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
+	bool per_pkg;
+	bool snapshot;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);

tools/perf/util/sort.c

@@ -291,7 +291,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 		else {
 			struct map *map = left->ms.map;
 			left->srcline = get_srcline(map->dso,
-					    map__rip_2objdump(map, left->ip));
+					   map__rip_2objdump(map, left->ip),
+						    left->ms.sym, true);
 		}
 	}
 	if (!right->srcline) {
@@ -300,7 +301,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 		else {
 			struct map *map = right->ms.map;
 			right->srcline = get_srcline(map->dso,
-					    map__rip_2objdump(map, right->ip));
+					     map__rip_2objdump(map, right->ip),
+						     right->ms.sym, true);
 		}
 	}
 	return strcmp(right->srcline, left->srcline);

tools/perf/util/srcline.c

@@ -8,6 +8,8 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+#include "symbol.h"
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -250,7 +252,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, unsigned long addr)
+char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+		  bool show_sym)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -258,7 +261,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	const char *dso_name;
 
 	if (!dso->has_srcline)
-		return SRCLINE_UNKNOWN;
+		goto out;
 
 	if (dso->symsrc_filename)
 		dso_name = dso->symsrc_filename;
@@ -289,7 +292,13 @@ out:
 		dso->has_srcline = 0;
 		dso__free_a2l(dso);
 	}
-	return SRCLINE_UNKNOWN;
+	if (sym) {
+		if (asprintf(&srcline, "%s+%ld", show_sym ? sym->name : "",
+					addr - sym->start) < 0)
+			return SRCLINE_UNKNOWN;
+	} else if (asprintf(&srcline, "%s[%lx]", dso->short_name, addr) < 0)
+		return SRCLINE_UNKNOWN;
+	return srcline;
 }
 
 void free_srcline(char *srcline)

tools/perf/util/symbol-elf.c

@@ -11,6 +11,27 @@
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
+extern char *cplus_demangle(const char *, int);
+
+static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
+{
+	return cplus_demangle(c, i);
+}
+#else
+#ifdef NO_DEMANGLE
+static inline char *bfd_demangle(void __maybe_unused *v,
+				 const char __maybe_unused *c,
+				 int __maybe_unused i)
+{
+	return NULL;
+}
+#else
+#define PACKAGE 'perf'
+#include <bfd.h>
+#endif
+#endif
+
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
 static int elf_getphdrnum(Elf *elf, size_t *dst)
 {

tools/perf/util/symbol.h

@@ -23,27 +23,6 @@
 
 #include "dso.h"
 
-#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
-extern char *cplus_demangle(const char *, int);
-
-static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
-{
-	return cplus_demangle(c, i);
-}
-#else
-#ifdef NO_DEMANGLE
-static inline char *bfd_demangle(void __maybe_unused *v,
-				 const char __maybe_unused *c,
-				 int __maybe_unused i)
-{
-	return NULL;
-}
-#else
-#define PACKAGE 'perf'
-#include <bfd.h>
-#endif
-#endif
-
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:

tools/perf/util/util.h

@@ -337,8 +337,10 @@ static inline int path__join3(char *bf, size_t size,
 }
 
 struct dso;
+struct symbol;
 
-char *get_srcline(struct dso *dso, unsigned long addr);
+char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+		  bool show_sym);
 void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);