Merge tag 'perf-core-for-mingo-20160623' 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 'callindent' option to 'perf script -F', to indent the Intel PT
  call stack, making this output more ftrace-like (Adrian Hunter, Andi Kleen)

User visible changes:

- Enlarge 'pid' column width, to cope with large pids (Jiri Olsa)

Infrastructure changes:

- Fix cross platform unwind (He Kuang)

- Make destructors accept NULL, behaving like free() (Arnaldo Carvalho de Melo)

- Remove reference to perl interpreted in the recently added 'perf script'
  stackcollapse python script (Arnaldo Carvalho de Melo)

- Rename CLASS__for_each() macros to CLASS__for_each_entry(), to use the
  list_for_each_entry() semantics, as most of these class specific loop helpers
  are list_for_each_entry*() wrappers  (Arnaldo Carvalho de Melo)

- Expose the hist_browser code, will be used with data structures other
  than perf_evsel (Jiri Olsa)

- Refactor 'perf config' (Taeung Song)

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

tools/perf/Documentation/perf-script.txt

@@ -170,7 +170,16 @@ OPTIONS
 	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
 	call, return, conditional, system, asynchronous, interrupt,
 	transaction abort, trace begin, trace end, and in transaction,
-	respectively.
+	respectively. Known combinations of flags are printed more nicely e.g.
+	"call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
+	"int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
+	"async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
+	"tr end" for "bE". However the "x" flag will be display separately in those
+	cases e.g. "jcc     (x)" for a condition branch within a transaction.
+
+	The callindent field is synthesized and may have a value when
+	Instruction Trace decoding. For calls and returns, it will display the
+	name of the symbol indented with spaces to reflect the stack depth.
 
 	Finally, a user may not set fields to none for all event types.
 	i.e., -F "" is not allowed.

tools/perf/Makefile.perf

@@ -254,7 +254,8 @@ PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
-	$(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
+        CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \

tools/perf/arch/x86/tests/perf-time-to-tsc.c

@@ -154,10 +154,6 @@ int test__perf_time_to_tsc(int subtest __maybe_unused)
 	err = 0;
 
 out_err:
-	if (evlist) {
-		perf_evlist__disable(evlist);
-		perf_evlist__delete(evlist);
-	}
-
+	perf_evlist__delete(evlist);
 	return err;
 }

tools/perf/arch/x86/util/auxtrace.c

@@ -37,7 +37,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
 	if (evlist) {
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (intel_pt_pmu &&
 			    evsel->attr.type == intel_pt_pmu->type)
 				found_pt = true;

tools/perf/arch/x86/util/intel-bts.c

@@ -124,7 +124,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	btsr->evlist = evlist;
 	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_bts_pmu->type) {
 			if (intel_bts_evsel) {
 				pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
@@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evsel__disable(evsel);
 	}
@@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evsel__enable(evsel);
 	}
@@ -422,7 +422,7 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evlist__enable_event_idx(btsr->evlist,
 							     evsel, idx);

tools/perf/arch/x86/util/intel-pt.c

@@ -131,7 +131,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str,
 	if (!mask)
 		return -EINVAL;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_pt_pmu->type) {
 			*res = intel_pt_masked_bits(mask, evsel->attr.config);
 			return 0;
@@ -511,7 +511,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	ptr->evlist = evlist;
 	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_pt_pmu->type) {
 			if (intel_pt_evsel) {
 				pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n");
@@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evsel__disable(evsel);
 	}
@@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evsel__enable(evsel);
 	}
@@ -1011,7 +1011,7 @@ static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
 							     idx);

tools/perf/builtin-annotate.c

@@ -236,7 +236,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		perf_session__fprintf_dsos(session, stdout);
 
 	total_nr_samples = 0;
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 

tools/perf/builtin-buildid-cache.c

@@ -209,7 +209,7 @@ static int build_id_cache__purge_path(const char *pathname)
 	if (err)
 		goto out;
 
-	strlist__for_each(pos, list) {
+	strlist__for_each_entry(pos, list) {
 		err = build_id_cache__remove_s(pos->s);
 		pr_debug("Removing %s %s: %s\n", pos->s, pathname,
 			 err ? "FAIL" : "Ok");
@@ -343,7 +343,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (add_name_list_str) {
 		list = strlist__new(add_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__add_file(pos->s)) {
 					if (errno == EEXIST) {
 						pr_debug("%s already in the cache\n",
@@ -361,7 +361,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (remove_name_list_str) {
 		list = strlist__new(remove_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__remove_file(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -379,7 +379,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (purge_name_list_str) {
 		list = strlist__new(purge_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__purge_path(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -400,7 +400,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (update_name_list_str) {
 		list = strlist__new(update_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__update_file(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -419,8 +419,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
 out:
-	if (session)
-		perf_session__delete(session);
+	perf_session__delete(session);
 
 	return ret;
 }

tools/perf/builtin-config.c

@@ -37,23 +37,16 @@ static int show_config(struct perf_config_set *set)
 {
 	struct perf_config_section *section;
 	struct perf_config_item *item;
-	struct list_head *sections;
 
 	if (set == NULL)
 		return -1;
 
-	sections = &set->sections;
-	if (list_empty(sections))
-		return -1;
-
-	list_for_each_entry(section, sections, node) {
-		list_for_each_entry(item, &section->items, node) {
-			char *value = item->value;
+	perf_config_set__for_each_entry(set, section, item) {
+		char *value = item->value;
 
-			if (value)
-				printf("%s.%s=%s\n", section->name,
-				       item->name, value);
-		}
+		if (value)
+			printf("%s.%s=%s\n", section->name,
+			       item->name, value);
 	}
 
 	return 0;
@@ -80,6 +73,10 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (use_user_config)
 		config_exclusive_filename = user_config;
 
+	/*
+	 * At only 'config' sub-command, individually use the config set
+	 * because of reinitializing with options config file location.
+	 */
 	set = perf_config_set__new();
 	if (!set) {
 		ret = -1;

tools/perf/builtin-diff.c

@@ -363,7 +363,7 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
 	struct perf_evsel *e;
 
-	evlist__for_each(evlist, e) {
+	evlist__for_each_entry(evlist, e) {
 		if (perf_evsel__match2(evsel, e))
 			return e;
 	}
@@ -375,7 +375,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
@@ -681,7 +681,7 @@ static void data_process(void)
 	struct perf_evsel *evsel_base;
 	bool first = true;
 
-	evlist__for_each(evlist_base, evsel_base) {
+	evlist__for_each_entry(evlist_base, evsel_base) {
 		struct hists *hists_base = evsel__hists(evsel_base);
 		struct data__file *d;
 		int i;
@@ -756,9 +756,7 @@ static int __cmd_diff(void)
 
  out_delete:
 	data__for_each_file(i, d) {
-		if (d->session)
-			perf_session__delete(d->session);
-
+		perf_session__delete(d->session);
 		data__free(d);
 	}
 

tools/perf/builtin-evlist.c

@@ -32,7 +32,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	if (session == NULL)
 		return -1;
 
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		perf_evsel__fprintf(pos, details, stdout);
 
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT)

tools/perf/builtin-help.c

@@ -4,7 +4,7 @@
  * Builtin help command
  */
 #include "perf.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "builtin.h"
 #include <subcmd/exec-cmd.h>
 #include "common-cmds.h"

tools/perf/builtin-inject.c

@@ -562,7 +562,7 @@ static void strip_init(struct perf_inject *inject)
 
 	inject->tool.context_switch = perf_event__drop;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evsel->handler = drop_sample;
 }
 
@@ -590,7 +590,7 @@ static bool ok_to_remove(struct perf_evlist *evlist,
 	if (!has_tracking(evsel_to_remove))
 		return true;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->handler != drop_sample) {
 			cnt += 1;
 			if ((evsel->attr.sample_type & COMPAT_MASK) ==
@@ -608,7 +608,7 @@ static void strip_fini(struct perf_inject *inject)
 	struct perf_evsel *evsel, *tmp;
 
 	/* Remove non-synthesized evsels if possible */
-	evlist__for_each_safe(evlist, tmp, evsel) {
+	evlist__for_each_entry_safe(evlist, tmp, evsel) {
 		if (evsel->handler == drop_sample &&
 		    ok_to_remove(evlist, evsel)) {
 			pr_debug("Deleting %s\n", perf_evsel__name(evsel));
@@ -643,7 +643,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
 
 			if (!strcmp(name, "sched:sched_switch")) {

tools/perf/builtin-kmem.c

@@ -4,7 +4,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
@@ -1354,7 +1354,7 @@ static int __cmd_kmem(struct perf_session *session)
 		goto out;
 	}
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
 		    perf_evsel__field(evsel, "pfn")) {
 			use_pfn = true;

tools/perf/builtin-kvm.c

@@ -988,7 +988,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	 * Note: exclude_{guest,host} do not apply here.
 	 *       This command processes KVM tracepoints from host only
 	 */
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct perf_event_attr *attr = &pos->attr;
 
 		/* make sure these *are* set */
@@ -1426,11 +1426,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	err = kvm_events_live_report(kvm);
 
 out:
-	if (kvm->session)
-		perf_session__delete(kvm->session);
+	perf_session__delete(kvm->session);
 	kvm->session = NULL;
-	if (kvm->evlist)
-		perf_evlist__delete(kvm->evlist);
+	perf_evlist__delete(kvm->evlist);
 
 	return err;
 }

tools/perf/builtin-probe.c

@@ -389,7 +389,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
 	ret = probe_file__get_events(kfd, filter, klist);
 	if (ret == 0) {
-		strlist__for_each(ent, klist)
+		strlist__for_each_entry(ent, klist)
 			pr_info("Removed event: %s\n", ent->s);
 
 		ret = probe_file__del_strlist(kfd, klist);
@@ -399,7 +399,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
-		strlist__for_each(ent, ulist)
+		strlist__for_each_entry(ent, ulist)
 			pr_info("Removed event: %s\n", ent->s);
 
 		ret2 = probe_file__del_strlist(ufd, ulist);

tools/perf/builtin-record.c

@@ -13,6 +13,7 @@
 #include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
+#include "util/config.h"
 
 #include "util/callchain.h"
 #include "util/cgroup.h"
@@ -352,7 +353,7 @@ static int record__open(struct record *rec)
 
 	perf_evlist__config(evlist, opts, &callchain_param);
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {

tools/perf/builtin-report.c

@@ -8,7 +8,7 @@
 #include "builtin.h"
 
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 
 #include "util/annotate.h"
 #include "util/color.h"
@@ -361,7 +361,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	struct perf_evsel *pos;
 
 	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 
@@ -478,7 +478,7 @@ static int report__collapse_hists(struct report *rep)
 
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
-	evlist__for_each(rep->session->evlist, pos) {
+	evlist__for_each_entry(rep->session->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 
 		if (pos->idx == 0)
@@ -511,7 +511,7 @@ static void report__output_resort(struct report *rep)
 
 	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
-	evlist__for_each(rep->session->evlist, pos)
+	evlist__for_each_entry(rep->session->evlist, pos)
 		perf_evsel__output_resort(pos, &prog);
 
 	ui_progress__finish();
@@ -552,7 +552,7 @@ static int __cmd_report(struct report *rep)
 
 	report__warn_kptr_restrict(rep);
 
-	evlist__for_each(session->evlist, pos)
+	evlist__for_each_entry(session->evlist, pos)
 		rep->nr_entries += evsel__hists(pos)->nr_entries;
 
 	if (use_browser == 0) {
@@ -583,7 +583,7 @@ static int __cmd_report(struct report *rep)
 	 * might be changed during the collapse phase.
 	 */
 	rep->nr_entries = 0;
-	evlist__for_each(session->evlist, pos)
+	evlist__for_each_entry(session->evlist, pos)
 		rep->nr_entries += evsel__hists(pos)->nr_entries;
 
 	if (rep->nr_entries == 0) {

tools/perf/builtin-script.c

@@ -21,6 +21,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/thread-stack.h"
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
 #include "asm/bug.h"
@@ -63,6 +64,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
+	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 };
 
 struct output_option {
@@ -89,6 +91,7 @@ struct output_option {
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
+	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -369,7 +372,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	if (!no_callchain) {
 		bool use_callchain = false;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
 			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 				use_callchain = true;
 				break;
@@ -389,7 +392,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 		j = PERF_TYPE_TRACEPOINT;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
 			if (evsel->attr.type != j)
 				continue;
 
@@ -562,6 +565,62 @@ static void print_sample_addr(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_callindent(struct perf_sample *sample,
+				    struct perf_evsel *evsel,
+				    struct thread *thread,
+				    struct addr_location *al)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	size_t depth = thread_stack__depth(thread);
+	struct addr_location addr_al;
+	const char *name = NULL;
+	static int spacing;
+	int len = 0;
+	u64 ip = 0;
+
+	/*
+	 * The 'return' has already been popped off the stack so the depth has
+	 * to be adjusted to match the 'call'.
+	 */
+	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
+		depth += 1;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				ip = sample->addr;
+		} else {
+			ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			ip = sample->ip;
+	}
+
+	if (name)
+		len = printf("%*s%s", (int)depth * 4, "", name);
+	else if (ip)
+		len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+
+	if (len < 0)
+		return;
+
+	/*
+	 * Try to keep the output length from changing frequently so that the
+	 * output lines up more nicely.
+	 */
+	if (len > spacing || (len && len < spacing - 52))
+		spacing = round_up(len + 4, 32);
+
+	if (len < spacing)
+		printf("%*s", spacing - len, "");
+}
+
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
@@ -570,6 +629,9 @@ static void print_sample_bts(struct perf_sample *sample,
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
 
+	if (PRINT_FIELD(CALLINDENT))
+		print_sample_callindent(sample, evsel, thread, al);
+
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
 		unsigned int print_opts = output[attr->type].print_ip_opts;
@@ -606,13 +668,42 @@ static void print_sample_bts(struct perf_sample *sample,
 	printf("\n");
 }
 
+static struct {
+	u32 flags;
+	const char *name;
+} sample_flags[] = {
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"},
+	{PERF_IP_FLAG_BRANCH, "jmp"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |	PERF_IP_FLAG_INTERRUPT, "hw int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"},
+	{0, NULL}
+};
+
 static void print_sample_flags(u32 flags)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
 	const int n = strlen(PERF_IP_FLAG_CHARS);
+	bool in_tx = flags & PERF_IP_FLAG_IN_TX;
+	const char *name = NULL;
 	char str[33];
 	int i, pos = 0;
 
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
+			name = sample_flags[i].name;
+			break;
+		}
+	}
+
 	for (i = 0; i < n; i++, flags >>= 1) {
 		if (flags & 1)
 			str[pos++] = chars[i];
@@ -622,7 +713,11 @@ static void print_sample_flags(u32 flags)
 			str[pos++] = '?';
 	}
 	str[pos] = 0;
-	printf("  %-4s ", str);
+
+	if (name)
+		printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
+	else
+		printf("  %-11s ", str);
 }
 
 struct printer_data {
@@ -720,7 +815,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int max = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		int len = strlen(perf_evsel__name(evsel));
 
 		max = MAX(len, max);
@@ -945,7 +1040,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	if (evsel->attr.type >= PERF_TYPE_MAX)
 		return 0;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->attr.type == evsel->attr.type && pos != evsel)
 			return 0;
 	}
@@ -1671,7 +1766,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 			snprintf(evname, len + 1, "%s", p);
 
 			match = 0;
-			evlist__for_each(session->evlist, pos) {
+			evlist__for_each_entry(session->evlist, pos) {
 				if (!strcmp(perf_evsel__name(pos), evname)) {
 					match = 1;
 					break;
@@ -1873,7 +1968,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
 
-	evlist__for_each(session->evlist, counter) {
+	evlist__for_each_entry(session->evlist, counter) {
 		perf_stat_process_counter(&stat_config, counter);
 		process_stat(counter, round->time);
 	}
@@ -2020,7 +2115,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+		     "callindent", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2259,6 +2355,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	script.session = session;
 	script__setup_sample_type(&script);
 
+	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+		itrace_synth_opts.thread_stack = true;
+
 	session->itrace_synth_opts = &itrace_synth_opts;
 
 	if (cpu_list) {

tools/perf/builtin-stat.c

@@ -331,7 +331,7 @@ static void read_counters(bool close_counters)
 {
 	struct perf_evsel *counter;
 
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		if (read_counter(counter))
 			pr_debug("failed to read counter %s\n", counter->name);
 
@@ -417,7 +417,7 @@ static int perf_stat_synthesize_config(bool is_pipe)
 	 * Synthesize other events stuff not carried within
 	 * attr event - unit, scale, name
 	 */
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		if (!counter->supported)
 			continue;
 
@@ -550,7 +550,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
@@ -1134,7 +1134,7 @@ static void aggr_update_shadow(void)
 
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			val = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 				s2 = aggr_get_id(evsel_list->cpus, cpu);
@@ -1173,7 +1173,7 @@ static void print_aggr(char *prefix)
 
 		id = aggr_map->map[s];
 		first = true;
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1292,7 +1292,7 @@ static void print_no_aggr_metric(char *prefix)
 
 		if (prefix)
 			fputs(prefix, stat_config.output);
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			if (first) {
 				aggr_printout(counter, cpu, 0);
 				first = false;
@@ -1346,7 +1346,7 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 	}
 
 	/* Print metrics headers only */
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
@@ -1482,11 +1482,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		print_aggr(prefix);
 		break;
 	case AGGR_THREAD:
-		evlist__for_each(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter)
 			print_aggr_thread(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
-		evlist__for_each(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
 		if (metric_only)
 			fputc('\n', stat_config.output);
@@ -1495,7 +1495,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		if (metric_only)
 			print_no_aggr_metric(prefix);
 		else {
-			evlist__for_each(evsel_list, counter)
+			evlist__for_each_entry(evsel_list, counter)
 				print_counter(counter, prefix);
 		}
 		break;
@@ -2149,7 +2149,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	const char **argv = session->header.env.cmdline_argv;
 	int argc = session->header.env.nr_cmdline;
 
-	evlist__for_each(evsel_list, counter)
+	evlist__for_each_entry(evsel_list, counter)
 		perf_stat_process_counter(&stat_config, counter);
 
 	if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)

tools/perf/builtin-top.c

@@ -22,7 +22,7 @@
 #include "perf.h"
 
 #include "util/annotate.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/color.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
@@ -479,7 +479,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
 				fprintf(stderr, "\nAvailable events:");
 
-				evlist__for_each(top->evlist, top->sym_evsel)
+				evlist__for_each_entry(top->evlist, top->sym_evsel)
 					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
 				prompt_integer(&counter, "Enter details event counter");
@@ -490,7 +490,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 					sleep(1);
 					break;
 				}
-				evlist__for_each(top->evlist, top->sym_evsel)
+				evlist__for_each_entry(top->evlist, top->sym_evsel)
 					if (top->sym_evsel->idx == counter)
 						break;
 			} else
@@ -583,7 +583,7 @@ static void *display_thread_tui(void *arg)
 	 * Zooming in/out UIDs. For now juse use whatever the user passed
 	 * via --uid.
 	 */
-	evlist__for_each(top->evlist, pos) {
+	evlist__for_each_entry(top->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
@@ -888,7 +888,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	perf_evlist__config(evlist, opts, &callchain_param);
 
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {

tools/perf/builtin-trace.c

@@ -1247,7 +1247,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
 	i = 0;
 
-	strlist__for_each(pos, trace->ev_qualifier) {
+	strlist__for_each_entry(pos, trace->ev_qualifier) {
 		const char *sc = pos->s;
 		int id = syscalltbl__id(trace->sctbl, sc);
 
@@ -2483,7 +2483,7 @@ static int trace__replay(struct trace *trace)
 		goto out;
 	}
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
 		    (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
 		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
@@ -2550,7 +2550,7 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 	printed += fprintf(fp, "                               (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- -------- --------- --------- --------- ---------     ------\n");
 
-	resort_rb__for_each(nd, syscall_stats) {
+	resort_rb__for_each_entry(nd, syscall_stats) {
 		struct stats *stats = syscall_stats_entry->stats;
 		if (stats) {
 			double min = (double)(stats->min) / NSEC_PER_MSEC;
@@ -2627,7 +2627,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 		return 0;
 	}
 
-	resort_rb__for_each(nd, threads)
+	resort_rb__for_each_entry(nd, threads)
 		printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
 	resort_rb__delete(threads);
@@ -2714,7 +2714,7 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evsel->handler = handler;
 }
 

tools/perf/perf.c

@@ -10,7 +10,7 @@
 
 #include "util/env.h"
 #include <subcmd/exec-cmd.h>
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/quote.h"
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
@@ -355,6 +355,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 
 	perf_env__set_cmdline(&perf_env, argc, argv);
 	status = p->fn(argc, argv, prefix);
+	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
 	bpf__clear();
@@ -522,6 +523,7 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
+	perf_config__init();
 	perf_config(perf_default_config, NULL);
 	set_buildid_dir(NULL);
 

tools/perf/scripts/python/stackcollapse.py

@@ -1,5 +1,3 @@
-#!/usr/bin/perl -w
-#
 # stackcollapse.py - format perf samples with one line per distinct call stack
 #
 # This script's output has two space-separated fields.  The first is a semicolon

tools/perf/tests/backward-ring-buffer.c

@@ -118,7 +118,7 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 	perf_evlist__config(evlist, &opts, NULL);
 
 	/* Set backward bit, ring buffer should be writing from end */
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evsel->attr.write_backward = 1;
 
 	err = perf_evlist__open(evlist);

tools/perf/tests/event-times.c

@@ -200,8 +200,7 @@ static int test_times(int (attach)(struct perf_evlist *),
 		 count.ena, count.run);
 
 out_err:
-	if (evlist)
-		perf_evlist__delete(evlist);
+	perf_evlist__delete(evlist);
 	return !err ? TEST_OK : TEST_FAIL;
 }
 

tools/perf/tests/evsel-roundtrip-name.c

@@ -80,7 +80,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
 	}
 
 	err = 0;
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
 			--err;
 			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);

tools/perf/tests/hists_filter.c

@@ -56,7 +56,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 	 * (perf [perf] main) will be collapsed to an existing entry
 	 * so total 9 entries will be in the tree.
 	 */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
 			struct hist_entry_iter iter = {
 				.evsel = evsel,
@@ -136,7 +136,7 @@ int test__hists_filter(int subtest __maybe_unused)
 	if (err < 0)
 		goto out;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);

tools/perf/tests/hists_link.c

@@ -72,7 +72,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 * However the second evsel also has a collapsed entry for
 	 * "bash [libc] malloc" so total 9 entries will be in the tree.
 	 */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
@@ -301,7 +301,7 @@ int test__hists_link(int subtest __maybe_unused)
 	if (err < 0)
 		goto out;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		hists = evsel__hists(evsel);
 		hists__collapse_resort(hists, NULL);
 

tools/perf/tests/mmap-basic.c

@@ -126,7 +126,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 	}
 
 	err = 0;
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],

tools/perf/tests/parse-events.c

@@ -32,7 +32,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
@@ -207,7 +207,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong exclude_user",
 				!evsel->attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel",

tools/perf/tests/parse-no-sample-id-all.c

@@ -44,8 +44,7 @@ static int process_events(union perf_event **events, size_t count)
 	for (i = 0; i < count && !err; i++)
 		err = process_event(&evlist, events[i]);
 
-	if (evlist)
-		perf_evlist__delete(evlist);
+	perf_evlist__delete(evlist);
 
 	return err;
 }

tools/perf/tests/switch-tracking.c

@@ -432,7 +432,7 @@ int test__switch_tracking(int subtest __maybe_unused)
 	}
 
 	/* Check non-tracking events are not tracking */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel != tracking_evsel) {
 			if (evsel->attr.mmap || evsel->attr.comm) {
 				pr_debug("Non-tracking event is tracking\n");

tools/perf/ui/browser.c

@@ -1,5 +1,5 @@
 #include "../util.h"
-#include "../cache.h"
+#include "../config.h"
 #include "../../perf.h"
 #include "libslang.h"
 #include "ui.h"

tools/perf/ui/browsers/annotate.c

@@ -8,6 +8,7 @@
 #include "../../util/sort.h"
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
+#include "../../util/config.h"
 #include <pthread.h>
 
 struct disasm_line_samples {

tools/perf/ui/browsers/hists.c

@@ -12,35 +12,17 @@
 #include "../../util/top.h"
 #include "../../arch/common.h"
 
-#include "../browser.h"
+#include "../browsers/hists.h"
 #include "../helpline.h"
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
 #include "annotate.h"
 
-struct hist_browser {
-	struct ui_browser   b;
-	struct hists	    *hists;
-	struct hist_entry   *he_selection;
-	struct map_symbol   *selection;
-	struct hist_browser_timer *hbt;
-	struct pstack	    *pstack;
-	struct perf_env *env;
-	int		     print_seq;
-	bool		     show_dso;
-	bool		     show_headers;
-	float		     min_pcnt;
-	u64		     nr_non_filtered_entries;
-	u64		     nr_hierarchy_entries;
-	u64		     nr_callchain_rows;
-};
-
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists,
-				struct hist_browser_timer *hbt,
-				char *bf, size_t size);
+static int perf_evsel_browser_title(struct hist_browser *browser,
+				    char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -585,7 +567,12 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser, const char *help)
+static int hist_browser__title(struct hist_browser *browser, char *bf, size_t size)
+{
+	return browser->title ? browser->title(browser, bf, size) : 0;
+}
+
+int hist_browser__run(struct hist_browser *browser, const char *help)
 {
 	int key;
 	char title[160];
@@ -595,7 +582,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hists__browser_title(browser->hists, hbt, title, sizeof(title));
+	hist_browser__title(browser, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
@@ -621,8 +608,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists,
-					     hbt, title, sizeof(title));
+			hist_browser__title(browser, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -2056,27 +2042,50 @@ static int hist_browser__dump(struct hist_browser *browser)
 	return 0;
 }
 
-static struct hist_browser *hist_browser__new(struct hists *hists,
-					      struct hist_browser_timer *hbt,
-					      struct perf_env *env)
+void hist_browser__init(struct hist_browser *browser,
+			struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+
+	browser->hists			= hists;
+	browser->b.refresh		= hist_browser__refresh;
+	browser->b.refresh_dimensions	= hist_browser__refresh_dimensions;
+	browser->b.seek			= ui_browser__hists_seek;
+	browser->b.use_navkeypressed	= true;
+	browser->show_headers		= symbol_conf.show_hist_headers;
+
+	hists__for_each_format(hists, fmt) {
+		perf_hpp__reset_width(fmt, hists);
+		++browser->b.columns;
+	}
+}
+
+struct hist_browser *hist_browser__new(struct hists *hists)
 {
 	struct hist_browser *browser = zalloc(sizeof(*browser));
 
+	if (browser)
+		hist_browser__init(browser, hists);
+
+	return browser;
+}
+
+static struct hist_browser *
+perf_evsel_browser__new(struct perf_evsel *evsel,
+			struct hist_browser_timer *hbt,
+			struct perf_env *env)
+{
+	struct hist_browser *browser = hist_browser__new(evsel__hists(evsel));
+
 	if (browser) {
-		browser->hists = hists;
-		browser->b.refresh = hist_browser__refresh;
-		browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
-		browser->b.seek = ui_browser__hists_seek;
-		browser->b.use_navkeypressed = true;
-		browser->show_headers = symbol_conf.show_hist_headers;
-		browser->hbt = hbt;
-		browser->env = env;
+		browser->hbt   = hbt;
+		browser->env   = env;
+		browser->title = perf_evsel_browser_title;
 	}
-
 	return browser;
 }
 
-static void hist_browser__delete(struct hist_browser *browser)
+void hist_browser__delete(struct hist_browser *browser)
 {
 	free(browser);
 }
@@ -2097,10 +2106,11 @@ static inline bool is_report_browser(void *timer)
 	return timer == NULL;
 }
 
-static int hists__browser_title(struct hists *hists,
-				struct hist_browser_timer *hbt,
+static int perf_evsel_browser_title(struct hist_browser *browser,
 				char *bf, size_t size)
 {
+	struct hist_browser_timer *hbt = browser->hbt;
+	struct hists *hists = browser->hists;
 	char unit;
 	int printed;
 	const struct dso *dso = hists->dso_filter;
@@ -2657,7 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    struct perf_env *env)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = hist_browser__new(hists, hbt, env);
+	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
 	struct branch_info *bi;
 #define MAX_OPTIONS  16
 	char *options[MAX_OPTIONS];
@@ -2666,7 +2676,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	int key = -1;
 	char buf[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
-	struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON					\
 	"h/?/F1        Show this window\n"				\
@@ -2725,18 +2734,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	memset(options, 0, sizeof(options));
 	memset(actions, 0, sizeof(actions));
 
-	hists__for_each_format(browser->hists, fmt) {
-		perf_hpp__reset_width(fmt, hists);
-		/*
-		 * This is done just once, and activates the horizontal scrolling
-		 * code in the ui_browser code, it would be better to have a the
-		 * counter in the perf_hpp code, but I couldn't find doing it here
-		 * works, FIXME by setting this in hist_browser__new, for now, be
-		 * clever 8-)
-		 */
-		++browser->b.columns;
-	}
-
 	if (symbol_conf.col_width_list_str)
 		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
 
@@ -3202,7 +3199,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
 	ui_helpline__push("Press ESC to exit");
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		const char *ev_name = perf_evsel__name(pos);
 		size_t line_len = strlen(ev_name) + 7;
 
@@ -3233,7 +3230,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 		struct perf_evsel *pos;
 
 		nr_entries = 0;
-		evlist__for_each(evlist, pos) {
+		evlist__for_each_entry(evlist, pos) {
 			if (perf_evsel__is_group_leader(pos))
 				nr_entries++;
 		}

tools/perf/ui/browsers/hists.h

@@ -0,0 +1,32 @@
+#ifndef _PERF_UI_BROWSER_HISTS_H_
+#define _PERF_UI_BROWSER_HISTS_H_ 1
+
+#include "ui/browser.h"
+
+struct hist_browser {
+	struct ui_browser   b;
+	struct hists	    *hists;
+	struct hist_entry   *he_selection;
+	struct map_symbol   *selection;
+	struct hist_browser_timer *hbt;
+	struct pstack	    *pstack;
+	struct perf_env	    *env;
+	int		     print_seq;
+	bool		     show_dso;
+	bool		     show_headers;
+	float		     min_pcnt;
+	u64		     nr_non_filtered_entries;
+	u64		     nr_hierarchy_entries;
+	u64		     nr_callchain_rows;
+
+	/* Get title string. */
+	int                  (*title)(struct hist_browser *browser,
+			     char *bf, size_t size);
+};
+
+struct hist_browser *hist_browser__new(struct hists *hists);
+void hist_browser__delete(struct hist_browser *browser);
+int hist_browser__run(struct hist_browser *browser, const char *help);
+void hist_browser__init(struct hist_browser *browser,
+			struct hists *hists);
+#endif /* _PERF_UI_BROWSER_HISTS_H_ */

tools/perf/ui/gtk/hists.c

@@ -627,7 +627,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
 	gtk_container_add(GTK_CONTAINER(window), vbox);
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;

tools/perf/ui/hist.c

@@ -766,7 +766,7 @@ int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
 	if (!symbol_conf.report_hierarchy)
 		return 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		hists = evsel__hists(evsel);
 
 		perf_hpp_list__for_each_sort_list(list, fmt) {

tools/perf/util/alias.c

@@ -1,4 +1,5 @@
 #include "cache.h"
+#include "config.h"
 
 static const char *alias_key;
 static char *alias_val;

tools/perf/util/auxtrace.h

@@ -63,6 +63,7 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
@@ -82,6 +83,7 @@ struct itrace_synth_opts {
 	bool			calls;
 	bool			returns;
 	bool			callchain;
+	bool			thread_stack;
 	bool			last_branch;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;

tools/perf/util/cache.h

@@ -18,17 +18,6 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
-extern const char *config_exclusive_filename;
-
-typedef int (*config_fn_t)(const char *, const char *, void *);
-int perf_default_config(const char *, const char *, void *);
-int perf_config(config_fn_t fn, void *);
-int perf_config_int(const char *, const char *);
-u64 perf_config_u64(const char *, const char *);
-int perf_config_bool(const char *, const char *);
-int config_error_nonbool(const char *);
-const char *perf_etc_perfconfig(void);
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 

tools/perf/util/cgroup.c

@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 		cgrp = counter->cgrp;
 		if (!cgrp)
 			continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	 * if add cgroup N, then need to find event N
 	 */
 	n = 0;
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 		if (n == nr_cgroups)
 			goto found;
 		n++;

tools/perf/util/color.c

@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include "cache.h"
+#include "config.h"
 #include "color.h"
 #include <math.h>
 

tools/perf/util/config.c

@@ -26,6 +26,7 @@ static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
+static struct perf_config_set *config_set;
 
 const char *config_exclusive_filename;
 
@@ -478,51 +479,6 @@ static int perf_config_global(void)
 	return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0);
 }
 
-int perf_config(config_fn_t fn, void *data)
-{
-	int ret = -1;
-	const char *home = NULL;
-
-	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
-	if (config_exclusive_filename)
-		return perf_config_from_file(fn, config_exclusive_filename, data);
-	if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
-		if (perf_config_from_file(fn, perf_etc_perfconfig(), data) < 0)
-			goto out;
-	}
-
-	home = getenv("HOME");
-	if (perf_config_global() && home) {
-		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		struct stat st;
-
-		if (user_config == NULL) {
-			warning("Not enough memory to process %s/.perfconfig, "
-				"ignoring it.", home);
-			goto out;
-		}
-
-		if (stat(user_config, &st) < 0)
-			goto out_free;
-
-		if (st.st_uid && (st.st_uid != geteuid())) {
-			warning("File %s not owned by current user or root, "
-				"ignoring it.", user_config);
-			goto out_free;
-		}
-
-		if (!st.st_size)
-			goto out_free;
-
-		ret = perf_config_from_file(fn, user_config, data);
-
-out_free:
-		free(user_config);
-	}
-out:
-	return ret;
-}
-
 static struct perf_config_section *find_section(struct list_head *sections,
 						const char *section_name)
 {
@@ -706,6 +662,52 @@ struct perf_config_set *perf_config_set__new(void)
 	return set;
 }
 
+int perf_config(config_fn_t fn, void *data)
+{
+	int ret = 0;
+	char key[BUFSIZ];
+	struct perf_config_section *section;
+	struct perf_config_item *item;
+
+	if (config_set == NULL)
+		return -1;
+
+	perf_config_set__for_each_entry(config_set, section, item) {
+		char *value = item->value;
+
+		if (value) {
+			scnprintf(key, sizeof(key), "%s.%s",
+				  section->name, item->name);
+			ret = fn(key, value, data);
+			if (ret < 0) {
+				pr_err("Error: wrong config key-value pair %s=%s\n",
+				       key, value);
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
+void perf_config__init(void)
+{
+	if (config_set == NULL)
+		config_set = perf_config_set__new();
+}
+
+void perf_config__exit(void)
+{
+	perf_config_set__delete(config_set);
+	config_set = NULL;
+}
+
+void perf_config__refresh(void)
+{
+	perf_config__exit();
+	perf_config__init();
+}
+
 static void perf_config_item__delete(struct perf_config_item *item)
 {
 	zfree(&item->name);

tools/perf/util/config.h

@@ -20,7 +20,47 @@ struct perf_config_set {
 	struct list_head sections;
 };
 
+extern const char *config_exclusive_filename;
+
+typedef int (*config_fn_t)(const char *, const char *, void *);
+int perf_default_config(const char *, const char *, void *);
+int perf_config(config_fn_t fn, void *);
+int perf_config_int(const char *, const char *);
+u64 perf_config_u64(const char *, const char *);
+int perf_config_bool(const char *, const char *);
+int config_error_nonbool(const char *);
+const char *perf_etc_perfconfig(void);
+
 struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
+void perf_config__init(void);
+void perf_config__exit(void);
+void perf_config__refresh(void);
+
+/**
+ * perf_config_sections__for_each - iterate thru all the sections
+ * @list: list_head instance to iterate
+ * @section: struct perf_config_section iterator
+ */
+#define perf_config_sections__for_each_entry(list, section)	\
+        list_for_each_entry(section, list, node)
+
+/**
+ * perf_config_items__for_each - iterate thru all the items
+ * @list: list_head instance to iterate
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_items__for_each_entry(list, item)	\
+        list_for_each_entry(item, list, node)
+
+/**
+ * perf_config_set__for_each - iterate thru all the config section-item pairs
+ * @set: evlist instance to iterate
+ * @section: struct perf_config_section iterator
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_set__for_each_entry(set, section, item)			\
+	perf_config_sections__for_each_entry(&set->sections, section)		\
+	perf_config_items__for_each_entry(&section->items, item)
 
 #endif /* __PERF_CONFIG_H */

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

@@ -997,7 +997,7 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	struct perf_evsel *evsel;
 	int ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		ret = add_event(cw, evsel);
 		if (ret)
 			return ret;
@@ -1010,7 +1010,7 @@ static void cleanup_events(struct perf_session *session)
 	struct perf_evlist *evlist = session->evlist;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct evsel_priv *priv;
 
 		priv = evsel->priv;

tools/perf/util/evlist.c

@@ -100,7 +100,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		perf_evsel__calc_id_pos(evsel);
 
 	perf_evlist__set_id_pos(evlist);
@@ -110,7 +110,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos, *n;
 
-	evlist__for_each_safe(evlist, n, pos) {
+	evlist__for_each_entry_safe(evlist, n, pos) {
 		list_del_init(&pos->node);
 		pos->evlist = NULL;
 		perf_evsel__delete(pos);
@@ -127,6 +127,9 @@ void perf_evlist__exit(struct perf_evlist *evlist)
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+	if (evlist == NULL)
+		return;
+
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
 	cpu_map__put(evlist->cpus);
@@ -161,7 +164,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evlist__propagate_maps(evlist, evsel);
 }
 
@@ -190,7 +193,7 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel, *temp;
 
-	__evlist__for_each_safe(list, temp, evsel) {
+	__evlist__for_each_entry_safe(list, temp, evsel) {
 		list_del_init(&evsel->node);
 		perf_evlist__add(evlist, evsel);
 	}
@@ -205,7 +208,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
 	leader->nr_members = evsel->idx - leader->idx + 1;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		evsel->leader = leader;
 	}
 }
@@ -296,7 +299,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 	return 0;
 
 out_delete_partial_list:
-	__evlist__for_each_safe(&head, n, evsel)
+	__evlist__for_each_entry_safe(&head, n, evsel)
 		perf_evsel__delete(evsel);
 	return -1;
 }
@@ -317,7 +320,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
 		    (int)evsel->attr.config == id)
 			return evsel;
@@ -332,7 +335,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
 		    (strcmp(evsel->name, name) == 0))
 			return evsel;
@@ -367,7 +370,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
@@ -380,7 +383,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__enable(pos);
@@ -448,7 +451,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	int nfds = 0;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->system_wide)
 			nfds += nr_cpus;
 		else
@@ -1012,7 +1015,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	struct perf_evsel *evsel;
 	int revent;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		int fd;
 
 		if (evsel->overwrite != (evlist->overwrite && evlist->backward))
@@ -1259,7 +1262,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -1335,7 +1338,7 @@ void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__set_sample_bit(evsel, bit);
 }
 
@@ -1344,7 +1347,7 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__reset_sample_bit(evsel, bit);
 }
 
@@ -1355,7 +1358,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 	const int ncpus = cpu_map__nr(evlist->cpus),
 		  nthreads = thread_map__nr(evlist->threads);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->filter == NULL)
 			continue;
 
@@ -1378,7 +1381,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -1432,7 +1435,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 	if (evlist->id_pos < 0 || evlist->is_pos < 0)
 		return false;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->id_pos != evlist->id_pos ||
 		    pos->is_pos != evlist->is_pos)
 			return false;
@@ -1448,7 +1451,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 	if (evlist->combined_sample_type)
 		return evlist->combined_sample_type;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evlist->combined_sample_type |= evsel->attr.sample_type;
 
 	return evlist->combined_sample_type;
@@ -1465,7 +1468,7 @@ u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	u64 branch_type = 0;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		branch_type |= evsel->attr.branch_sample_type;
 	return branch_type;
 }
@@ -1476,7 +1479,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
 	u64 read_format = first->attr.read_format;
 	u64 sample_type = first->attr.sample_type;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (read_format != pos->attr.read_format)
 			return false;
 	}
@@ -1533,7 +1536,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-	evlist__for_each_continue(evlist, pos) {
+	evlist__for_each_entry_continue(evlist, pos) {
 		if (first->attr.sample_id_all != pos->attr.sample_id_all)
 			return false;
 	}
@@ -1560,7 +1563,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	int nthreads = thread_map__nr(evlist->threads);
 	int n;
 
-	evlist__for_each_reverse(evlist, evsel) {
+	evlist__for_each_entry_reverse(evlist, evsel) {
 		n = evsel->cpus ? evsel->cpus->nr : ncpus;
 		perf_evsel__close(evsel, n, nthreads);
 	}
@@ -1614,7 +1617,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	perf_evlist__update_id_pos(evlist);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
 		if (err < 0)
 			goto out_err;
@@ -1775,7 +1778,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	struct perf_evsel *evsel;
 	size_t printed = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
 				   perf_evsel__name(evsel));
 	}
@@ -1877,7 +1880,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 	if (move_evsel == perf_evlist__first(evlist))
 		return;
 
-	evlist__for_each_safe(evlist, n, evsel) {
+	evlist__for_each_entry_safe(evlist, n, evsel) {
 		if (evsel->leader == move_evsel->leader)
 			list_move_tail(&evsel->node, &move);
 	}
@@ -1893,7 +1896,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 	if (tracking_evsel->tracking)
 		return;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel != tracking_evsel)
 			evsel->tracking = false;
 	}
@@ -1907,7 +1910,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (!evsel->name)
 			continue;
 		if (strcmp(str, evsel->name) == 0)

tools/perf/util/evlist.h

@@ -251,70 +251,70 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 			   struct perf_evsel *move_evsel);
 
 /**
- * __evlist__for_each - iterate thru all the evsels
+ * __evlist__for_each_entry - iterate thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each(list, evsel) \
+#define __evlist__for_each_entry(list, evsel) \
         list_for_each_entry(evsel, list, node)
 
 /**
- * evlist__for_each - iterate thru all the evsels
+ * evlist__for_each_entry - iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each(evlist, evsel) \
-	__evlist__for_each(&(evlist)->entries, evsel)
+#define evlist__for_each_entry(evlist, evsel) \
+	__evlist__for_each_entry(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_continue - continue iteration thru all the evsels
+ * __evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_continue(list, evsel) \
+#define __evlist__for_each_entry_continue(list, evsel) \
         list_for_each_entry_continue(evsel, list, node)
 
 /**
- * evlist__for_each_continue - continue iteration thru all the evsels
+ * evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_continue(evlist, evsel) \
-	__evlist__for_each_continue(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_continue(evlist, evsel) \
+	__evlist__for_each_entry_continue(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_reverse(list, evsel) \
+#define __evlist__for_each_entry_reverse(list, evsel) \
         list_for_each_entry_reverse(evsel, list, node)
 
 /**
- * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_reverse(evlist, evsel) \
-	__evlist__for_each_reverse(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_reverse(evlist, evsel) \
+	__evlist__for_each_entry_reverse(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_safe - safely iterate thru all the evsels
+ * __evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @list: list_head instance to iterate
  * @tmp: struct evsel temp iterator
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_safe(list, tmp, evsel) \
+#define __evlist__for_each_entry_safe(list, tmp, evsel) \
         list_for_each_entry_safe(evsel, tmp, list, node)
 
 /**
- * evlist__for_each_safe - safely iterate thru all the evsels
+ * evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  * @tmp: struct evsel temp iterator
  */
-#define evlist__for_each_safe(evlist, tmp, evsel) \
-	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
+	__evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel)
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);

tools/perf/util/header.c

@@ -336,7 +336,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		ret = do_write(fd, &evsel->attr, sz);
 		if (ret < 0)
 			return ret;
@@ -801,7 +801,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			const char *name = evsel->group_name ?: "{anon_group}";
@@ -1425,7 +1425,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
 	session = container_of(ph, struct perf_session, header);
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1703,7 +1703,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->idx == idx)
 			return evsel;
 	}
@@ -2075,7 +2075,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 	session->evlist->nr_groups = nr_groups;
 
 	i = nr = 0;
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->idx == (int) desc[i].leader_idx) {
 			evsel->leader = evsel;
 			/* {anon_group} is a dummy name */
@@ -2383,7 +2383,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	lseek(fd, sizeof(f_header), SEEK_SET);
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		evsel->id_offset = lseek(fd, 0, SEEK_CUR);
 		err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
 		if (err < 0) {
@@ -2394,7 +2394,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	attr_offset = lseek(fd, 0, SEEK_CUR);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		f_attr = (struct perf_file_attr){
 			.attr = evsel->attr,
 			.ids  = {
@@ -2828,7 +2828,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
 		    perf_evsel__prepare_tracepoint_event(pos, pevent))
 			return -1;
@@ -3127,7 +3127,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {

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

@@ -1,4 +1,5 @@
 #include "cache.h"
+#include "config.h"
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"

tools/perf/util/hist.c

@@ -79,7 +79,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
-		hists__set_col_len(hists, HISTC_THREAD, len + 6);
+		hists__set_col_len(hists, HISTC_THREAD, len + 8);
 
 	if (h->ms.map) {
 		len = dso__name_len(h->ms.map->dso);
@@ -2199,7 +2199,7 @@ size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
 	struct perf_evsel *pos;
 	size_t ret = 0;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
 		ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
 	}

tools/perf/util/intel-bts.c

@@ -422,7 +422,8 @@ static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
 }
 
 static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
-				    struct auxtrace_buffer *buffer)
+				    struct auxtrace_buffer *buffer,
+				    struct thread *thread)
 {
 	struct branch *branch;
 	size_t sz, bsz = sizeof(struct branch);
@@ -444,6 +445,12 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 		if (!branch->from && !branch->to)
 			continue;
 		intel_bts_get_branch_type(btsq, branch);
+		if (btsq->bts->synth_opts.thread_stack)
+			thread_stack__event(thread, btsq->sample_flags,
+					    le64_to_cpu(branch->from),
+					    le64_to_cpu(branch->to),
+					    btsq->intel_pt_insn.length,
+					    buffer->buffer_nr + 1);
 		if (filter && !(filter & btsq->sample_flags))
 			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
@@ -507,12 +514,13 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 		goto out_put;
 	}
 
-	if (!btsq->bts->synth_opts.callchain && thread &&
+	if (!btsq->bts->synth_opts.callchain &&
+	    !btsq->bts->synth_opts.thread_stack && thread &&
 	    (!old_buffer || btsq->bts->sampling_mode ||
 	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
 		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
 
-	err = intel_bts_process_buffer(btsq, buffer);
+	err = intel_bts_process_buffer(btsq, buffer, thread);
 
 	auxtrace_buffer__drop_data(buffer);
 
@@ -777,7 +785,7 @@ static int intel_bts_synth_events(struct intel_bts *bts,
 	u64 id;
 	int err;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == bts->pmu_type && evsel->ids) {
 			found = true;
 			break;
@@ -905,10 +913,14 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (dump_trace)
 		return 0;
 
-	if (session->itrace_synth_opts && session->itrace_synth_opts->set)
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
-	else
+	} else {
 		itrace_synth_opts__set_default(&bts->synth_opts);
+		if (session->itrace_synth_opts)
+			bts->synth_opts.thread_stack =
+				session->itrace_synth_opts->thread_stack;
+	}
 
 	if (bts->synth_opts.calls)
 		bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |

tools/perf/util/intel-pt.c

@@ -39,6 +39,7 @@
 #include "auxtrace.h"
 #include "tsc.h"
 #include "intel-pt.h"
+#include "config.h"
 
 #include "intel-pt-decoder/intel-pt-log.h"
 #include "intel-pt-decoder/intel-pt-decoder.h"
@@ -556,7 +557,7 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
 		    !evsel->attr.exclude_kernel)
 			return false;
@@ -572,7 +573,7 @@ static bool intel_pt_return_compression(struct intel_pt *pt)
 	if (!pt->noretcomp_bit)
 		return true;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
 		    (config & pt->noretcomp_bit))
 			return false;
@@ -592,7 +593,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 	for (shift = 0, config = pt->mtc_freq_bits; !(config & 1); shift++)
 		config >>= 1;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config))
 			return (config & pt->mtc_freq_bits) >> shift;
 	}
@@ -608,7 +609,7 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt)
 	if (!pt->tsc_bit || !pt->cap_user_time_zero)
 		return true;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
 			return true;
 		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
@@ -625,7 +626,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
 		    !evsel->attr.exclude_kernel)
 			return true;
@@ -642,7 +643,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt)
 	if (!pt->tsc_bit)
 		return false;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
 			if (config & pt->tsc_bit)
 				have_tsc = true;
@@ -1233,7 +1234,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->synth_opts.callchain)
+	if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
 		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
@@ -1850,7 +1851,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 	u64 id;
 	int err;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == pt->pmu_type && evsel->ids) {
 			found = true;
 			break;
@@ -1930,7 +1931,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		pt->sample_transactions = true;
 		pt->transactions_id = id;
 		id += 1;
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (evsel->id && evsel->id[0] == pt->transactions_id) {
 				if (evsel->name)
 					zfree(&evsel->name);
@@ -1968,7 +1969,7 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each_reverse(evlist, evsel) {
+	evlist__for_each_entry_reverse(evlist, evsel) {
 		const char *name = perf_evsel__name(evsel);
 
 		if (!strcmp(name, "sched:sched_switch"))
@@ -1982,7 +1983,7 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.context_switch)
 			return true;
 	}
@@ -2136,6 +2137,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
 		}
+		if (session->itrace_synth_opts)
+			pt->synth_opts.thread_stack =
+				session->itrace_synth_opts->thread_stack;
 	}
 
 	if (pt->synth_opts.log)

tools/perf/util/intlist.h

@@ -57,21 +57,21 @@ static inline struct int_node *intlist__next(struct int_node *in)
 }
 
 /**
- * intlist_for_each      - iterate over a intlist
+ * intlist__for_each_entry      - iterate over a intlist
  * @pos:	the &struct int_node to use as a loop cursor.
  * @ilist:	the &struct intlist for loop.
  */
-#define intlist__for_each(pos, ilist)	\
+#define intlist__for_each_entry(pos, ilist)	\
 	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
 
 /**
- * intlist_for_each_safe - iterate over a intlist safe against removal of
+ * intlist__for_each_entry_safe - iterate over a intlist safe against removal of
  *                         int_node
  * @pos:	the &struct int_node to use as a loop cursor.
  * @n:		another &struct int_node to use as temporary storage.
  * @ilist:	the &struct intlist for loop.
  */
-#define intlist__for_each_safe(pos, n, ilist)	\
+#define intlist__for_each_entry_safe(pos, n, ilist)	\
 	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
 	     pos = n, n = intlist__next(n))
 #endif /* __PERF_INTLIST_H */

tools/perf/util/jitdump.c

@@ -108,7 +108,7 @@ jit_validate_events(struct perf_session *session)
 	/*
 	 * check that all events use CLOCK_MONOTONIC
 	 */
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
 			return -1;
 	}

tools/perf/util/libunwind/arm64.c

@@ -13,7 +13,12 @@
 
 #define REMOTE_UNWIND_LIBUNWIND
 
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
 
 #include "unwind.h"
 #include "debug.h"

tools/perf/util/libunwind/x86_32.c

@@ -12,7 +12,13 @@
  */
 
 #define REMOTE_UNWIND_LIBUNWIND
+
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
 #include "unwind.h"
 #include "debug.h"

tools/perf/util/llvm-utils.c

@@ -8,6 +8,7 @@
 #include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
+#include "config.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\

tools/perf/util/machine.c

@@ -138,8 +138,10 @@ void machine__exit(struct machine *machine)
 
 void machine__delete(struct machine *machine)
 {
-	machine__exit(machine);
-	free(machine);
+	if (machine) {
+		machine__exit(machine);
+		free(machine);
+	}
 }
 
 void machines__init(struct machines *machines)

tools/perf/util/parse-events.c

@@ -1396,7 +1396,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 	if (!add && get_event_modifier(&mod, str, NULL))
 		return -EINVAL;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		if (add && get_event_modifier(&mod, str, evsel))
 			return -EINVAL;
 
@@ -1422,7 +1422,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
 	struct perf_evsel *evsel;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		if (!evsel->name)
 			evsel->name = strdup(name);
 	}

tools/perf/util/probe-event.c

@@ -102,10 +102,8 @@ int init_probe_symbol_maps(bool user_only)
 
 void exit_probe_symbol_maps(void)
 {
-	if (host_machine) {
-		machine__delete(host_machine);
-		host_machine = NULL;
-	}
+	machine__delete(host_machine);
+	host_machine = NULL;
 	symbol__exit();
 }
 
@@ -898,7 +896,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
 			goto end;
 	}
 
-	intlist__for_each(ln, lr->line_list) {
+	intlist__for_each_entry(ln, lr->line_list) {
 		for (; ln->i > l; l++) {
 			ret = show_one_line(fp, l - lr->offset);
 			if (ret < 0)
@@ -982,7 +980,7 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		zfree(&vl->point.symbol);
 		nvars = 0;
 		if (vl->vars) {
-			strlist__for_each(node, vl->vars) {
+			strlist__for_each_entry(node, vl->vars) {
 				var = strchr(node->s, '\t') + 1;
 				if (strfilter__compare(_filter, var)) {
 					fprintf(stdout, "\t\t%s\n", node->s);
@@ -2335,7 +2333,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe,
 	if (!rawlist)
 		return -ENOMEM;
 
-	strlist__for_each(ent, rawlist) {
+	strlist__for_each_entry(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
 			if (!filter_probe_trace_event(&tev, filter))

tools/perf/util/probe-file.c

@@ -178,7 +178,7 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
 	if (!rawlist)
 		return NULL;
 	sl = strlist__new(NULL, NULL);
-	strlist__for_each(ent, rawlist) {
+	strlist__for_each_entry(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret < 0)
 			break;
@@ -281,7 +281,7 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 	if (!namelist)
 		return -ENOENT;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
@@ -299,7 +299,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist)
 	int ret = 0;
 	struct str_node *ent;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		ret = __del_trace_probe_event(fd, ent);
 		if (ret < 0)
 			break;
@@ -612,7 +612,7 @@ static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
 	if (ret < (int)iov[1].iov_len + 2)
 		goto rollback;
 
-	strlist__for_each(snode, entry->tevlist) {
+	strlist__for_each_entry(snode, entry->tevlist) {
 		iov[0].iov_base = (void *)snode->s;
 		iov[0].iov_len = strlen(snode->s);
 		iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;

tools/perf/util/python.c

@@ -957,7 +957,7 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
 	if (i >= pevlist->evlist.nr_entries)
 		return NULL;
 
-	evlist__for_each(&pevlist->evlist, pos) {
+	evlist__for_each_entry(&pevlist->evlist, pos) {
 		if (i-- == 0)
 			break;
 	}

tools/perf/util/rb_resort.h

@@ -35,7 +35,7 @@ DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname,
 
 	struct rb_node *nd;
 
-	resort_rb__for_each(nd, threads) {
+	resort_rb__for_each_entry(nd, threads) {
 		struct thread *t = threads_entry;
 		printf("%s: %d\n", t->shortname, t->tid);
 	}
@@ -123,7 +123,7 @@ static void __name##_sorted__init_entry(struct rb_node *nd,			\
 struct __name##_sorted_entry *__name##_entry;					\
 struct __name##_sorted *__name = __name##_sorted__new
 
-#define resort_rb__for_each(__nd, __name)					\
+#define resort_rb__for_each_entry(__nd, __name)					\
 	for (__nd = rb_first(&__name->entries);					\
 	     __name##_entry = rb_entry(__nd, struct __name##_sorted_entry,	\
 				       rb_node), __nd;				\

tools/perf/util/record.c

@@ -148,7 +148,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 
 	use_comm_exec = perf_can_comm_exec();
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__config(evsel, opts, callchain);
 		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
@@ -161,18 +161,18 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 		 * match the id.
 		 */
 		use_sample_identifier = perf_can_sample_identifier();
-		evlist__for_each(evlist, evsel)
+		evlist__for_each_entry(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (evsel->attr.sample_type == first->attr.sample_type)
 				continue;
 			use_sample_identifier = perf_can_sample_identifier();
 			break;
 		}
-		evlist__for_each(evlist, evsel)
+		evlist__for_each_entry(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	}
 

tools/perf/util/session.c

@@ -83,7 +83,7 @@ static bool perf_session__has_comm_exec(struct perf_session *session)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.comm_exec)
 			return true;
 	}
@@ -178,6 +178,8 @@ static void perf_session__delete_threads(struct perf_session *session)
 
 void perf_session__delete(struct perf_session *session)
 {
+	if (session == NULL)
+		return;
 	auxtrace__free(session);
 	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
@@ -1870,7 +1872,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 	}
@@ -1952,7 +1954,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		if (pos->attr.type == type)
 			return pos;
 	}
@@ -2107,7 +2109,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
 	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
 		 sizeof(struct id_index_entry);
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		nr += evsel->ids;
 
 	n = nr > max_nr ? max_nr : nr;
@@ -2120,7 +2122,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
 	ev->id_index.header.size = sz;
 	ev->id_index.nr = n;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		u32 j;
 
 		for (j = 0; j < evsel->ids; j++) {

tools/perf/util/sort.c

@@ -79,8 +79,8 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 {
 	const char *comm = thread__comm_str(he->thread);
 
-	width = max(7U, width) - 6;
-	return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+	width = max(7U, width) - 8;
+	return repsep_snprintf(bf, size, "%7d:%-*.*s", he->thread->tid,
 			       width, width, comm ?: "");
 }
 
@@ -95,7 +95,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void
 }
 
 struct sort_entry sort_thread = {
-	.se_header	= "  Pid:Command",
+	.se_header	= "    Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
 	.se_filter	= hist_entry__thread_filter,
@@ -2069,7 +2069,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 	}
 
 	full_name = !!strchr(event_name, ':');
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		/* case 2 */
 		if (full_name && !strcmp(pos->name, event_name))
 			return pos;
@@ -2125,7 +2125,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
 	int ret;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -2143,7 +2143,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 	struct perf_evsel *evsel;
 	struct format_field *field;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -2456,7 +2456,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist)
 	if (evlist == NULL)
 		goto out_no_evlist;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			use_trace = false;
 			break;

tools/perf/util/stat.c

@@ -162,7 +162,7 @@ int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__alloc_stats(evsel, alloc_raw))
 			goto out_free;
 	}
@@ -178,7 +178,7 @@ void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__free_stat_priv(evsel);
 		perf_evsel__free_counts(evsel);
 		perf_evsel__free_prev_raw_counts(evsel);
@@ -189,7 +189,7 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__reset_stat_priv(evsel);
 		perf_evsel__reset_counts(evsel);
 	}

tools/perf/util/strlist.h

@@ -73,7 +73,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @pos:	the &struct str_node to use as a loop cursor.
  * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, slist)	\
+#define strlist__for_each_entry(pos, slist)	\
 	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
@@ -83,7 +83,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @n:		another &struct str_node to use as temporary storage.
  * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, slist)	\
+#define strlist__for_each_entry_safe(pos, n, slist)	\
 	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 #endif /* __PERF_STRLIST_H */

tools/perf/util/symbol.c

@@ -1626,7 +1626,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 	if (!dirs)
 		return -1;
 
-	strlist__for_each(nd, dirs) {
+	strlist__for_each_entry(nd, dirs) {
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
 			  "%s/%s/kallsyms", dir, nd->s);
 		if (!validate_kcore_addresses(kallsyms_filename, map)) {

tools/perf/util/thread-stack.c

@@ -616,3 +616,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	return err;
 }
+
+size_t thread_stack__depth(struct thread *thread)
+{
+	if (!thread->ts)
+		return 0;
+	return thread->ts->cnt;
+}

tools/perf/util/thread-stack.h

@@ -87,6 +87,7 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread);
 
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, void *data),

tools/perf/util/thread_map.c

@@ -202,7 +202,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 	if (!slist)
 		return NULL;
 
-	strlist__for_each(pos, slist) {
+	strlist__for_each_entry(pos, slist) {
 		pid = strtol(pos->s, &end_ptr, 10);
 
 		if (pid == INT_MIN || pid == INT_MAX ||
@@ -278,7 +278,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	if (!slist)
 		return NULL;
 
-	strlist__for_each(pos, slist) {
+	strlist__for_each_entry(pos, slist) {
 		tid = strtol(pos->s, &end_ptr, 10);
 
 		if (tid == INT_MIN || tid == INT_MAX ||

tools/perf/util/unwind-libunwind-local.c

@@ -462,7 +462,8 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 		return 0;
 	}
 
-	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	ret = perf_reg_value(&start, &ui->sample->user_regs,
+			     LIBUNWIND__ARCH_REG_SP);
 	if (ret)
 		return ret;
 
@@ -621,7 +622,8 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	unw_cursor_t c;
 	int ret, i = 0;
 
-	ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
+	ret = perf_reg_value(&val, &ui->sample->user_regs,
+			     LIBUNWIND__ARCH_REG_IP);
 	if (ret)
 		return ret;
 

tools/perf/util/unwind.h

@@ -32,6 +32,15 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #ifndef LIBUNWIND__ARCH_REG_ID
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
 #endif
+
+#ifndef LIBUNWIND__ARCH_REG_SP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP
+#endif
+
+#ifndef LIBUNWIND__ARCH_REG_IP
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP
+#endif
+
 int LIBUNWIND__ARCH_REG_ID(int regnum);
 int unwind__prepare_access(struct thread *thread, struct map *map);
 void unwind__flush_access(struct thread *thread);

tools/perf/util/vdso.c

@@ -134,8 +134,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
-#if BITS_PER_LONG == 64
-
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
@@ -156,6 +154,8 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
 	return dso_type;
 }
 
+#if BITS_PER_LONG == 64
+
 static int vdso__do_copy_compat(FILE *f, int fd)
 {
 	char buf[4096];
@@ -283,8 +283,38 @@ static int __machine__findnew_vdso_compat(struct machine *machine,
 
 #endif
 
+static struct dso *machine__find_vdso(struct machine *machine,
+				      struct thread *thread)
+{
+	struct dso *dso = NULL;
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+		if (!dso) {
+			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
+					   true);
+			if (dso && dso_type != dso__type(dso, machine))
+				dso = NULL;
+		}
+		break;
+	case DSO__TYPE_X32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+		break;
+	case DSO__TYPE_64BIT:
+	case DSO__TYPE_UNKNOWN:
+	default:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		break;
+	}
+
+	return dso;
+}
+
 struct dso *machine__findnew_vdso(struct machine *machine,
-				  struct thread *thread __maybe_unused)
+				  struct thread *thread)
 {
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
@@ -297,6 +327,10 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	if (!vdso_info)
 		goto out_unlock;
 
+	dso = machine__find_vdso(machine, thread);
+	if (dso)
+		goto out_unlock;
+
 #if BITS_PER_LONG == 64
 	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
 		goto out_unlock;