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:

New features:

  - Add option in 'perf sched' to merge like comms to lat output (Josef Bacik)

  - Improve 'perf probe' error messages when not finding a
    suitable vmlinux (Masami Hiramatsu)

Infrastructure changes:

  - Use atomic.h for various pre-existing reference counts (Arnaldo Carvalho de Melo)

  - Leg work for refcounting 'struct map' (Arnaldo Carvalho de Melo)

  - Assign default value for some pointers (Martin Liška)

  - Improve setting of gcc debug option (Martin Liška)

  - Separate the tests and tools in installation (Nam T. Nguyen)

  - Reduce number of arguments of hist_entry_iter__add() (Namhyung Kim)

  - DSO data cache fixes (Namhyung Kim)

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

33 files changed, 332 insertions, 204 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 03409cc02117..5816a3bb7e9f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -464,7 +464,7 @@ check: $(OUTPUT)common-cmds.h
 
 install-gtk:
 
-install-bin: all install-gtk
+install-tools: all install-gtk
 	$(call QUIET_INSTALL, binaries) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
@@ -502,12 +502,16 @@ endif
 	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
 		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+
+install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
+install-bin: install-tools install-tests
+
 install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 49776f190abf..b7bb42c44694 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -61,7 +61,7 @@ const char *const mips_triplets[] = {
 static bool lookup_path(char *name)
 {
 	bool found = false;
-	char *path, *tmp;
+	char *path, *tmp = NULL;
 	char buf[PATH_MAX];
 	char *env = getenv("PATH");
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 92fca2157e5e..56025d90622f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -139,8 +139,10 @@ static int process_sample_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	struct hist_entry_iter iter = {
-		.hide_unresolved = rep->hide_unresolved,
-		.add_entry_cb = hist_iter__report_callback,
+		.evsel 			= evsel,
+		.sample 		= sample,
+		.hide_unresolved 	= rep->hide_unresolved,
+		.add_entry_cb 		= hist_iter__report_callback,
 	};
 	int ret = 0;
 
@@ -168,8 +170,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
-				   rep);
+	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
 	if (ret < 0)
 		pr_debug("problem adding hist entry, skipping event\n");
 out_put:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 79273ecf92eb..33962612a5e9 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -95,6 +95,7 @@ struct work_atoms {
 	u64			total_lat;
 	u64			nb_atoms;
 	u64			total_runtime;
+	int			num_merged;
 };
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
@@ -168,9 +169,10 @@ struct perf_sched {
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root;
+	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
+	bool skip_merge;
 };
 
 static u64 get_nsecs(void)
@@ -1182,7 +1184,10 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
+	if (work_list->num_merged > 1)
+		ret = printf("  %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged);
+	else
+		ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1302,17 +1307,22 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-
+	struct rb_root *root = &sched->atom_root;
+again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&sched->atom_root);
+		node = rb_first(root);
 		if (!node)
 			break;
 
-		rb_erase(node, &sched->atom_root);
+		rb_erase(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
+	if (root == &sched->atom_root) {
+		root = &sched->merged_atom_root;
+		goto again;
+	}
 }
 
 static int process_sched_wakeup_event(struct perf_tool *tool,
@@ -1572,6 +1582,59 @@ static void print_bad_events(struct perf_sched *sched)
 	}
 }
 
+static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct work_atoms *this;
+	const char *comm = thread__comm_str(data->thread), *this_comm;
+
+	while (*new) {
+		int cmp;
+
+		this = container_of(*new, struct work_atoms, node);
+		parent = *new;
+
+		this_comm = thread__comm_str(this->thread);
+		cmp = strcmp(comm, this_comm);
+		if (cmp > 0) {
+			new = &((*new)->rb_left);
+		} else if (cmp < 0) {
+			new = &((*new)->rb_right);
+		} else {
+			this->num_merged++;
+			this->total_runtime += data->total_runtime;
+			this->nb_atoms += data->nb_atoms;
+			this->total_lat += data->total_lat;
+			list_splice(&data->work_list, &this->work_list);
+			if (this->max_lat < data->max_lat) {
+				this->max_lat = data->max_lat;
+				this->max_lat_at = data->max_lat_at;
+			}
+			zfree(&data);
+			return;
+		}
+	}
+
+	data->num_merged++;
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void perf_sched__merge_lat(struct perf_sched *sched)
+{
+	struct work_atoms *data;
+	struct rb_node *node;
+
+	if (sched->skip_merge)
+		return;
+
+	while ((node = rb_first(&sched->atom_root))) {
+		rb_erase(node, &sched->atom_root);
+		data = rb_entry(node, struct work_atoms, node);
+		__merge_work_atoms(&sched->merged_atom_root, data);
+	}
+}
+
 static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
@@ -1581,6 +1644,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 	if (perf_sched__read_events(sched))
 		return -1;
 
+	perf_sched__merge_lat(sched);
 	perf_sched__sort_lat(sched);
 
 	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
@@ -1732,6 +1796,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.profile_cpu	      = -1,
 		.next_shortname1      = 'A',
 		.next_shortname2      = '0',
+		.skip_merge           = 0,
 	};
 	const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
@@ -1742,6 +1807,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "CPU to profile on"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN('p', "pids", &sched.skip_merge,
+		    "latency stats per pid instead of per comm"),
 	OPT_END()
 	};
 	const struct option replay_options[] = {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a19351728f0f..6b987424d015 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -775,7 +775,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (al.sym == NULL || !al.sym->ignore) {
 		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
-			.add_entry_cb = hist_iter__top_callback,
+			.evsel		= evsel,
+			.sample 	= sample,
+			.add_entry_cb 	= hist_iter__top_callback,
 		};
 
 		if (symbol_conf.cumulate_callchain)
@@ -785,8 +787,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		pthread_mutex_lock(&hists->lock);
 
-		err = hist_entry_iter__add(&iter, &al, evsel, sample,
-					   top->max_stack, top);
+		err = hist_entry_iter__add(&iter, &al, top->max_stack, top);
 		if (err < 0)
 			pr_err("Problem incrementing symbol period, skipping event\n");
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1b957a1272d0..317001c94660 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -32,7 +32,7 @@ ifeq ($(ARCH),x86)
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
     $(call detected,CONFIG_X86_64)
   else
-    LIBUNWIND_LIBS = -lunwind -lunwind-x86
+    LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
   endif
   NO_PERF_REGS := 0
 endif
@@ -130,6 +130,8 @@ endif
 
 ifeq ($(DEBUG),0)
   CFLAGS += -O6
+else
+  CFLAGS += $(call cc-option,-Og,-O0)
 endif
 
 ifdef PARSER_DEBUG
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index c16ce833079c..0ebef09c0842 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -177,3 +177,22 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-run
+# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
+# Exit code chooses option. "$$TMP" is can be used as temporary file and
+# is automatically cleaned up.
+try-run = $(shell set -e;		\
+	TMP="$(TMPOUT).$$$$.tmp";	\
+	TMPO="$(TMPOUT).$$$$.o";	\
+	if ($(1)) >/dev/null 2>&1;	\
+	then echo "$(2)";		\
+	else echo "$(3)";		\
+	fi;				\
+	rm -f "$$TMP" "$$TMPO")
+
+# cc-option
+# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
+
+cc-option = $(call try-run,\
+	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 513e5febbe5a..3e41c61bd861 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -99,6 +99,17 @@ struct test_data_offset offsets[] = {
 	},
 };
 
+/* move it from util/dso.c for compatibility */
+static int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int fd = dso__data_get_fd(dso, machine);
+
+	if (fd >= 0)
+		dso__data_put_fd(dso);
+
+	return fd;
+}
+
 int test__dso_data(void)
 {
 	struct machine machine;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 620f626e5b35..7d82c8be5e36 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -87,6 +87,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample	= &sample,
 			.hide_unresolved = false,
 		};
 
@@ -104,8 +106,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
 			addr_location__put(&al);
 			goto out;
 		}
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 82e1ee52e024..ce48775e6ada 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -63,6 +63,8 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				},
 			};
 			struct hist_entry_iter iter = {
+				.evsel = evsel,
+				.sample = &sample,
 				.ops = &hist_iter_normal,
 				.hide_unresolved = false,
 			};
@@ -81,7 +83,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 							  &sample) < 0)
 				goto out;
 
-			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+			if (hist_entry_iter__add(&iter, &al,
 						 PERF_MAX_STACK_DEPTH, NULL) < 0) {
 				addr_location__put(&al);
 				goto out;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index fd7ec4f9aeb4..adbebc852cc8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -57,6 +57,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample = &sample,
 			.ops = &hist_iter_normal,
 			.hide_unresolved = false,
 		};
@@ -70,8 +72,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
 			addr_location__put(&al);
 			goto out;
 		}
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 3d9088003a5b..94ac6924df65 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -23,9 +23,10 @@ int test__vmlinux_matches_kallsyms(void)
 	int err = -1;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
+	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
+	struct rb_root *maps = &vmlinux.kmaps.maps[type];
 	u64 mem_start, mem_end;
 
 	/*
@@ -184,8 +185,8 @@ detour:
 
 	pr_info("Maps only in vmlinux:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *
 		/*
 		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
 		 * the kernel will have the path for the vmlinux file being used,
@@ -193,22 +194,22 @@ detour:
 		 * both cases.
 		 */
 		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
-						(pos->dso->kernel ?
-							pos->dso->short_name :
-							pos->dso->name));
+						(map->dso->kernel ?
+							map->dso->short_name :
+							map->dso->name));
 		if (pair)
 			pair->priv = 1;
 		else
-			map__fprintf(pos, stderr);
+			map__fprintf(map, stderr);
 	}
 
 	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *pair;
 
-		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
-		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
 
 		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
 		if (pair == NULL || pair->priv)
@@ -217,7 +218,7 @@ detour:
 		if (pair->start == mem_start) {
 			pair->priv = 1;
 			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				pos->start, pos->end, pos->pgoff, pos->dso->name);
+				map->start, map->end, map->pgoff, map->dso->name);
 			if (mem_end != pair->end)
 				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);
@@ -228,12 +229,11 @@ detour:
 
 	pr_info("Maps only in kallsyms:\n");
 
-	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
-	     nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	maps = &kallsyms.kmaps.maps[type];
 
-		if (!pos->priv)
-			map__fprintf(pos, stderr);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		if (!map->priv)
+			map__fprintf(map, stderr);
 	}
 out:
 	machine__exit(&kallsyms);
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index b2bb59df65e1..21b7ff382c3f 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -2,24 +2,27 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	int ref;
+	atomic_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
 
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	cs->ref++;
+	if (cs)
+		atomic_inc(&cs->refcnt);
+	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (!--cs->ref) {
+	if (cs && atomic_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -40,6 +43,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
+	atomic_set(&cs->refcnt, 0);
+
 	return cs;
 }
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 1b96c8d18435..7e11a700303f 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -440,15 +440,7 @@ void dso__data_close(struct dso *dso)
 	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
@@ -457,13 +449,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
-	pthread_mutex_lock(&dso__data_open_lock);
-
 	if (dso->data.fd >= 0)
-		goto out;
+		return;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
@@ -483,11 +470,38 @@ out:
 		dso->data.status = DSO_DATA_STATUS_OK;
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_get_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.  It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
+ */
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+		return -1;
+
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0)
+		pthread_mutex_unlock(&dso__data_open_lock);
 
-	pthread_mutex_unlock(&dso__data_open_lock);
 	return dso->data.fd;
 }
 
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+	pthread_mutex_unlock(&dso__data_open_lock);
+}
+
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;
@@ -609,13 +623,12 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		 * dso->data.fd might be closed if other thread opened another
 		 * file (dso) due to open file limit (RLIMIT_NOFILE).
 		 */
+		try_to_open_dso(dso, machine);
+
 		if (dso->data.fd < 0) {
-			dso->data.fd = open_dso(dso, machine);
-			if (dso->data.fd < 0) {
-				ret = -errno;
-				dso->data.status = DSO_DATA_STATUS_ERROR;
-				break;
-			}
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
+			break;
 		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
@@ -702,19 +715,21 @@ static int data_file_size(struct dso *dso, struct machine *machine)
 	if (dso->data.file_size)
 		return 0;
 
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
 	 * dso->data.fd might be closed if other thread opened another
 	 * file (dso) due to open file limit (RLIMIT_NOFILE).
 	 */
+	try_to_open_dso(dso, machine);
+
 	if (dso->data.fd < 0) {
-		dso->data.fd = open_dso(dso, machine);
-		if (dso->data.fd < 0) {
-			ret = -errno;
-			dso->data.status = DSO_DATA_STATUS_ERROR;
-			goto out;
-		}
+		ret = -errno;
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
 	}
 
 	if (fstat(dso->data.fd, &st) < 0) {
@@ -740,12 +755,6 @@ out:
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return fd;
-
 	if (data_file_size(dso, machine))
 		return -1;
 
@@ -1200,12 +1209,15 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 enum dso_type dso__type(struct dso *dso, struct machine *machine)
 {
 	int fd;
+	enum dso_type type = DSO__TYPE_UNKNOWN;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return DSO__TYPE_UNKNOWN;
+	fd = dso__data_get_fd(dso, machine);
+	if (fd >= 0) {
+		type = dso__type_fd(fd);
+		dso__data_put_fd(dso);
+	}
 
-	return dso__type_fd(fd);
+	return type;
 }
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b26ec3ab1336..bcec06ad73a2 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -240,7 +240,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 
 /*
  * The dso__data_* external interface provides following functions:
- *   dso__data_fd
+ *   dso__data_get_fd
+ *   dso__data_put_fd
  *   dso__data_close
  *   dso__data_size
  *   dso__data_read_offset
@@ -257,8 +258,11 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * The current usage of the dso__data_* interface is as follows:
  *
  * Get DSO's fd:
- *   int fd = dso__data_fd(dso, machine);
- *   USE 'fd' SOMEHOW
+ *   int fd = dso__data_get_fd(dso, machine);
+ *   if (fd >= 0) {
+ *       USE 'fd' SOMEHOW
+ *       dso__data_put_fd(dso);
+ *   }
  *
  * Read DSO's data:
  *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
@@ -277,7 +281,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  *
  * TODO
 */
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index a513a51f7330..9d3bba175423 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -329,8 +329,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 				   struct machine *machine)
 {
 	int rc = 0;
-	struct rb_node *nd;
+	struct map *pos;
 	struct map_groups *kmaps = &machine->kmaps;
+	struct rb_root *maps = &kmaps->maps[MAP__FUNCTION];
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -350,10 +351,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	else
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
-	     nd; nd = rb_next(nd)) {
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
-		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 338770679863..f53d017c7c22 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -362,10 +362,10 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-					 struct hist_entry *entry,
-					 struct addr_location *al,
-					 bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -468,7 +468,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, sample_self);
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
 static int
@@ -548,9 +548,9 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 
 out:
 	/*
-	 *