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

Pull perf updates from Ingo Molnar:
 "This tree includes an x86 PMU scheduling fix, but most changes are
  late breaking tooling fixes and updates:

  User visible fixes:

   - Create config.detected into OUTPUT directory, fixing parallel
     builds sharing the same source directory (Aaro Kiskinen)

   - Allow to specify custom linker command, fixing some MIPS64 builds.
     (Aaro Kiskinen)

   - Fix to show proper convergence stats in 'perf bench numa' (Srikar
     Dronamraju)

  User visible changes:

   - Validate syscall list passed via -e argument to 'perf trace'.
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf stat --per-thread' (Jiri Olsa)

   - Check access permission for --kallsyms and --vmlinux (Li Zhang)

   - Move toggling event logic from 'perf top' and into hists browser,
     allowing freeze/unfreeze with event lists with more than one entry
     (Namhyung Kim)

   - Add missing newlines when dumping PERF_RECORD_FINISHED_ROUND and
     showing the Aggregated stats in 'perf report -D' (Adrian Hunter)

  Infrastructure fixes:

   - Add missing break for PERF_RECORD_ITRACE_START, which caused those
     events samples to be parsed as well as PERF_RECORD_LOST_SAMPLES.
     ITRACE_START only appears when Intel PT or BTS are present, so..
     (Jiri Olsa)

   - Call the perf_session destructor when bailing out in the inject,
     kmem, report, kvm and mem tools (Taeung Song)

  Infrastructure changes:

   - Move stuff out of 'perf stat' and into the lib for further use
     (Jiri Olsa)

   - Reference count the cpu_map and thread_map classes (Jiri Olsa)

   - Set evsel->{cpus,threads} from the evlist, if not set, allowing the
     generalization of some 'perf stat' functions that previously were
     accessing private static evlist variable (Jiri Olsa)

   - Delete an unnecessary check before the calling free_event_desc()
     (Markus Elfring)

   - Allow auxtrace data alignment (Adrian Hunter)

   - Allow events with dot (Andi Kleen)

   - Fix failure to 'perf probe' events on arm (He Kuang)

   - Add testing for Makefile.perf (Jiri Olsa)

   - Add test for make install with prefix (Jiri Olsa)

   - Fix single target build dependency check (Jiri Olsa)

   - Access thread_map entries via accessors, prep patch to hold more
     info per entry, for ongoing 'perf stat --per-thread' work (Jiri
     Olsa)

   - Use __weak definition from compiler.h (Sukadev Bhattiprolu)

   - Split perf_pmu__new_alias() (Sukadev Bhattiprolu)"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  perf tools: Allow to specify custom linker command
  perf tools: Create config.detected into OUTPUT directory
  perf mem: Fill in the missing session freeing after an error occurs
  perf kvm: Fill in the missing session freeing after an error occurs
  perf report: Fill in the missing session freeing after an error occurs
  perf kmem: Fill in the missing session freeing after an error occurs
  perf inject: Fill in the missing session freeing after an error occurs
  perf tools: Add missing break for PERF_RECORD_ITRACE_START
  perf/x86: Fix 'active_events' imbalance
  perf symbols: Check access permission when reading symbol files
  perf stat: Introduce --per-thread option
  perf stat: Introduce print_counters function
  perf stat: Using init_stats instead of memset
  perf stat: Rename print_interval to process_interval
  perf stat: Remove perf_evsel__read_cb function
  perf stat: Move perf_stat initialization counter process code
  perf stat: Move zero_per_pkg into counter process code
  perf stat: Separate counters reading and processing
  perf stat: Introduce read_counters function
  perf stat: Introduce perf_evsel__read function
  ...

54 files changed, 885 insertions, 422 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5801a14f7524..3658de47900f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -357,34 +357,24 @@ void x86_release_hardware(void)
  */
 int x86_add_exclusive(unsigned int what)
 {
-	int ret = -EBUSY, i;
-
-	if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what]))
-		return 0;
+	int i;
 
-	mutex_lock(&pmc_reserve_mutex);
-	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
-		if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
-			goto out;
+	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
+		mutex_lock(&pmc_reserve_mutex);
+		for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
+			if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
+				goto fail_unlock;
+		}
+		atomic_inc(&x86_pmu.lbr_exclusive[what]);
+		mutex_unlock(&pmc_reserve_mutex);
 	}
 
-	atomic_inc(&x86_pmu.lbr_exclusive[what]);
-	ret = 0;
+	atomic_inc(&active_events);
+	return 0;
 
-out:
+fail_unlock:
 	mutex_unlock(&pmc_reserve_mutex);
-
-	/*
-	 * Assuming that all exclusive events will share the PMI handler
-	 * (which checks active_events for whether there is work to do),
-	 * we can bump active_events counter right here, except for
-	 * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
-	 * path, which already bumps active_events for them.
-	 */
-	if (!ret && what != x86_lbr_exclusive_lbr)
-		atomic_inc(&active_events);
-
-	return ret;
+	return -EBUSY;
 }
 
 void x86_del_exclusive(unsigned int what)
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index a51244a8022f..faca2bf6a430 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -25,7 +25,7 @@ build-dir := $(srctree)/tools/build
 include $(build-dir)/Build.include
 
 # do not force detected configuration
--include .config-detected
+-include $(OUTPUT).config-detected
 
 # Init all relevant variables used in build files so
 # 1) they have correct type
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04e150d83e7d..47469abdcc1c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index d31a7bbd7cee..480546d5f13b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -83,8 +83,8 @@ build-test:
 #
 # All other targets get passed through:
 #
-%:
+%: FORCE
 	$(print_msg)
 	$(make)
 
-.PHONY: tags TAGS
+.PHONY: tags TAGS FORCE Makefile
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 1af0cfeb7a57..7a4b549214e3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -110,7 +110,7 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
 CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
+LD ?= $(CROSS_COMPILE)ld
 AR = $(CROSS_COMPILE)ar
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
@@ -545,7 +545,7 @@ config-clean:
 clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)$(RM) .config-detected
+	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 52ec66b23607..01b06492bd6a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -630,12 +630,13 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (inject.session == NULL)
 		return -1;
 
-	if (symbol__init(&inject.session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&inject.session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	ret = __cmd_inject(&inject);
 
+out_delete:
 	perf_session__delete(inject.session);
-
 	return ret;
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 950f296dfcf7..23b1faaaa4cc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1916,7 +1916,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
 							  "kmem:kmalloc")) {
 			pr_err(errmsg, "slab", "slab");
-			return -1;
+			goto out_delete;
 		}
 	}
 
@@ -1927,7 +1927,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 							     "kmem:mm_page_alloc");
 		if (evsel == NULL) {
 			pr_err(errmsg, "page", "page");
-			return -1;
+			goto out_delete;
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 74878cd75078..fc1cffb1b7a2 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1061,8 +1061,10 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 	symbol__init(&kvm->session->header.env);
 
-	if (!perf_session__has_traces(kvm->session, "kvm record"))
-		return -EINVAL;
+	if (!perf_session__has_traces(kvm->session, "kvm record")) {
+		ret = -EINVAL;
+		goto out_delete;
+	}
 
 	/*
 	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
@@ -1070,9 +1072,13 @@ static int read_events(struct perf_kvm_stat *kvm)
 	 */
 	ret = cpu_isa_config(kvm);
 	if (ret < 0)
-		return ret;
+		goto out_delete;
 
-	return perf_session__process_events(kvm->session);
+	ret = perf_session__process_events(kvm->session);
+
+out_delete:
+	perf_session__delete(kvm->session);
+	return ret;
 }
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index da2ec06f0742..80170aace5d4 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -124,7 +124,6 @@ static int report_raw_events(struct perf_mem *mem)
 		.mode = PERF_DATA_MODE_READ,
 		.force = mem->force,
 	};
-	int err = -EINVAL;
 	int ret;
 	struct perf_session *session = perf_session__new(&file, false,
 							 &mem->tool);
@@ -135,24 +134,21 @@ static int report_raw_events(struct perf_mem *mem)
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
-		if (ret)
+		if (ret < 0)
 			goto out_delete;
 	}
 
-	if (symbol__init(&session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
-	err = perf_session__process_events(session);
-	if (err)
-		return err;
-
-	return 0;
+	ret = perf_session__process_events(session);
 
 out_delete:
 	perf_session__delete(session);
-	return err;
+	return ret;
 }
 
 static int report_events(int argc, const char **argv, struct perf_mem *mem)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 32626ea3e227..95a47719aec3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -742,6 +742,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (symbol_conf.vmlinux_name &&
+	    access(symbol_conf.vmlinux_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
+		return -EINVAL;
+	}
+	if (symbol_conf.kallsyms_name &&
+	    access(symbol_conf.kallsyms_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
+		return -EINVAL;
+	}
+
 	if (report.use_stdio)
 		use_browser = 0;
 	else if (report.use_tui)
@@ -828,8 +839,10 @@ repeat:
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
-		if (report.header_only)
-			return 0;
+		if (report.header_only) {
+			ret = 0;
+			goto error;
+		}
 	} else if (use_browser == 0) {
 		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
 		      stdout);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fcf99bdeb19e..37e301a32f43 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -67,10 +67,7 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static void print_stat(int argc, const char **argv);
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
-static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr(char *prefix);
+static void print_counters(struct timespec *ts, int argc, const char **argv);
 
 /* Default events used for perf stat -T */
 static const char *transaction_attrs = {
@@ -141,96 +138,9 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static void perf_stat__reset_stats(void)
 {
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
-}
-
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
-{
-	return perf_evsel__cpus(evsel)->nr;
-}
-
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
-{
-	int i;
-	struct perf_stat *ps = evsel->priv;
-
-	for (i = 0; i < 3; i++)
-		init_stats(&ps->res_stats[i]);
-
-	perf_stat_evsel_id_init(evsel);
-}
-
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
-{
-	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel->priv == NULL)
-		return -ENOMEM;
-	perf_evsel__reset_stat_priv(evsel);
-	return 0;
-}
-
-static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
-{
-	zfree(&evsel->priv);
-}
-
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
-{
-	struct perf_counts *counts;
-
-	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
-	if (counts)
-		evsel->prev_raw_counts = counts;
-
-	return counts ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
-{
-	perf_counts__delete(evsel->prev_raw_counts);
-	evsel->prev_raw_counts = NULL;
-}
-
-static void perf_evlist__free_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__free_stat_priv(evsel);
-		perf_evsel__free_counts(evsel);
-		perf_evsel__free_prev_raw_counts(evsel);
-	}
-}
-
-static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
-		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
-		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	perf_evlist__free_stats(evlist);
-	return -1;
-}
-
-static void perf_stat__reset_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__reset_stat_priv(evsel);
-		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
-	}
-
+	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
 }
 
@@ -304,8 +214,9 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
 	return 0;
 }
 
-static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
-		   struct perf_counts_values *count)
+static int
+process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
+		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	static struct perf_counts_values zero;
@@ -320,13 +231,13 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_THREAD:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			perf_evsel__compute_deltas(evsel, cpu, count);
+			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, scale, NULL);
-		evsel->counts->cpu[cpu] = *count;
 		if (aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
@@ -343,26 +254,48 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 	return 0;
 }
 
-static int read_counter(struct perf_evsel *counter);
+static int process_counter_maps(struct perf_evsel *counter)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-/*
- * Read out the results of a single counter:
- * aggregate counts across CPUs in system-wide mode
- */
-static int read_counter_aggr(struct perf_evsel *counter)
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (process_counter_values(counter, cpu, thread,
+						   perf_counts(counter->counts, cpu, thread)))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int process_counter(struct perf_evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
-	int i;
+	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
+	init_stats(ps->res_stats);
 
-	if (read_counter(counter))
-		return -1;
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
+
+	ret = process_counter_maps(counter);
+	if (ret)
+		return ret;
+
+	if (aggr_mode != AGGR_GLOBAL)
+		return 0;
 
 	if (!counter->snapshot)
-		perf_evsel__compute_deltas(counter, -1, aggr);
+		perf_evsel__compute_deltas(counter, -1, -1, aggr);
 	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)
@@ -397,12 +330,12 @@ static int read_counter(struct perf_evsel *counter)
 	if (counter->system_wide)
 		nthreads = 1;
 
-	if (counter->per_pkg)
-		zero_per_pkg(counter);
-
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
-			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+			struct perf_counts_values *count;
+
+			count = perf_counts(counter->counts, cpu, thread);
+			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
 		}
 	}
@@ -410,68 +343,34 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void print_interval(void)
+static void read_counters(bool close)
 {
-	static int num_print_interval;
 	struct perf_evsel *counter;
-	struct perf_stat *ps;
-	struct timespec ts, rs;
-	char prefix[64];
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter_aggr(counter);
-		}
-	} else	{
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter(counter);
-		}
-	}
+	evlist__for_each(evsel_list, counter) {
+		if (read_counter(counter))
+			pr_warning("failed to read counter %s\n", counter->name);
 
-	clock_gettime(CLOCK_MONOTONIC, &ts);
-	diff_timespec(&rs, &ts, &ref_time);
-	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+		if (process_counter(counter))
+			pr_warning("failed to process counter %s\n", counter->name);
 
-	if (num_print_interval == 0 && !csv_output) {
-		switch (aggr_mode) {
-		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+		if (close) {
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
+					     thread_map__nr(evsel_list->threads));
 		}
 	}
+}
 
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
+static void process_interval(void)
+{
+	struct timespec ts, rs;
 
-	switch (aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(prefix);
-		break;
-	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
-		break;
-	case AGGR_GLOBAL:
-	default:
-		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, prefix);
-	}
+	read_counters(false);
 
-	fflush(output);
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+
+	print_counters(&rs, 0, NULL);
 }
 
 static void handle_initial_delay(void)
@@ -586,7 +485,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
-				print_interval();
+				process_interval();
 			}
 		}
 		wait(&status);
@@ -604,7 +503,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		while (!done) {
 			nanosleep(&ts, NULL);
 			if (interval)
-				print_interval();
+				process_interval();
 		}
 	}
 
@@ -612,18 +511,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     thread_map__nr(evsel_list->threads));
-		}
-	} else {
-		evlist__for_each(evsel_list, counter) {
-			read_counter(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-		}
-	}
+	read_counters(true);
 
 	return WEXITSTATUS(status);
 }
@@ -715,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_THREAD:
+		fprintf(output, "%*s-%*d%s",
+			csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -815,9 +711,9 @@ static void print_aggr(char *prefix)
 				s2 = aggr_get_id(evsel_list->cpus, cpu2);
 				if (s2 != id)
 					continue;
-				val += counter->counts->cpu[cpu].val;
-				ena += counter->counts->cpu[cpu].ena;
-				run += counter->counts->cpu[cpu].run;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+				ena += perf_counts(counter->counts, cpu, 0)->ena;
+				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
 			if (prefix)
@@ -863,6 +759,40 @@ static void print_aggr(char *prefix)
 	}
 }
 
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -925,9 +855,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = counter->counts->cpu[cpu].val;
-		ena = counter->counts->cpu[cpu].ena;
-		run = counter->counts->cpu[cpu].run;
+		val = perf_counts(counter->counts, cpu, 0)->val;
+		ena = perf_counts(counter->counts, cpu, 0)->ena;
+		run = perf_counts(counter->counts, cpu, 0)->run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -972,9 +902,38 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
-static void print_stat(int argc, const char **argv)
+static void print_interval(char *prefix, struct timespec *ts)
+{
+	static int num_print_interval;
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		switch (aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+		}
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(int argc, const char **argv)
 {
-	struct perf_evsel *counter;
 	int i;
 
 	fflush(stdout);
@@ -1000,36 +959,57 @@ static void print_stat(int argc, const char **argv)
 			fprintf(output, " (%d runs)", run_count);
 		fprintf(output, ":\n\n");
 	}
+}
+
+static void print_footer(void)
+{
+	if (!null_run)
+		fprintf(output, "\n");
+	fprintf(output, " %17.9f seconds time elapsed",
+			avg_stats(&walltime_nsecs_stats)/1e9);
+	if (run_count > 1) {
+		fprintf(output, "                                        ");
+		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+				avg_stats(&walltime_nsecs_stats));
+	}
+	fprintf(output, "\n\n");
+}
+
+static void print_counters(struct timespec *ts, int argc, const char **argv)
+{
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(prefix = buf, ts);
+	else
+		print_header(argc, argv);
 
 	switch (aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
-		print_aggr(NULL);
+		print_aggr(prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_thread(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, NULL);
+			print_counter_aggr(counter, prefix);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
-			print_counter(counter, NULL);
+			print_counter(counter, prefix);
 		break;
 	default:
 		break;
 	}
 
-	if (!csv_output) {
-		if (!null_run)
-			fprintf(output, "\n");
-		fprintf(output, " %17.9f seconds time elapsed",
-				avg_stats(&walltime_nsecs_stats)/1e9);
-		if (run_count > 1) {
-			fprintf(output, "                                        ");
-			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
-					avg_stats(&walltime_nsecs_stats));
-		}
-		fprintf(output, "\n\n");
-	}
+	if (!interval && !csv_output)
+		print_footer();
+
+	fflush(output);
 }
 
 static volatile int signr = -1;
@@ -1101,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void)
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_THREAD:
 	default:
 		break;
 	}
@@ -1325,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_END()
@@ -1416,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
+		fprintf(stderr, "The --per-thread option is only available "
+			"when monitoring via -p -t options.\n");
+		parse_options_usage(NULL, options, "p", 1);
+		parse_options_usage(NULL, options, "t", 1);
+		goto out;
+	}
+
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
@@ -1445,6 +1439,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		goto out;
 	}
+
+	/*
+	 * Initialize thread_map with comm names,
+	 * so we could print it out on output.
+	 */
+	if (aggr_mode == AGGR_THREAD)
+		thread_map__read_comms(evsel_list->threads);
+
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
 		parse_options_usage(stat_usage, options, "I", 1);
@@ -1478,13 +1480,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 		status = run_perf_stat(argc, argv);
 		if (forever && status != -1) {
-			print_stat(argc, argv);
-			perf_stat__reset_stats(evsel_list);
+			print_counters(NULL, argc, argv);
+			perf_stat__reset_stats();
 		}
 	}
 
 	if (!forever && status != -1 && !interval)
-		print_stat(argc, argv);
+		print_counters(NULL, argc, argv);
 
 	perf_evlist__free_stats(evsel_list);
 out:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 619a8696fda7..ecf319728f25 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -586,27 +586,9 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	while (true)  {
-		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
-							top->min_percent,
-							&top->session->header.env);
-
-		if (key != 'f')
-			break;
-
-		perf_evlist__toggle_enable(top->evlist);
-		/*
-		 * No need to refresh, resort/decay histogram entries
-		 * if we are not collecting samples:
-		 */
-		if (top->evlist->enabled) {
-			hbt.refresh = top->delay_secs;
-			help = "Press 'f' to disable the events or 'h' to see other hotkeys";
-		} else {
-			help = "Press 'f' again to re-enable the events";
-			hbt.refresh = 0;
-		}
-	}
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+				      top->min_percent,
+				      &top->session->header.env);
 
 	done = 1;
 	return NULL;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index de5d277d1ad7..39ad4d0ca884 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1617,6 +1617,34 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	return syscall__set_arg_fmts(sc);
 }
 
+static int trace__validate_ev_qualifier(struct trace *trace)
+{
+	int err = 0;
+	struct str_node *pos;
+
+	strlist__for_each(pos, trace->ev_qualifier) {
+		const char *sc = pos->s;
+
+		if (audit_name_to_syscall(sc, trace->audit.machine) < 0) {
+			if (err == 0) {
+				fputs("Error:\tInvalid syscall ", trace->output);
+				err = -EINVAL;
+			} else {
+				fputs(", ", trace->output);
+			}
+
+			fputs(sc, trace->output);
+		}
+	}
+
+	if (err < 0) {
+		fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
+		      "\nHint:\tand: 'man syscalls'\n", trace->output);
+	}
+
+	return err;
+}
+
 /*
  * args is to be interpreted as a series of longs but we need to handle
  * 8-byte unaligned accesses. args points to raw_data within the event
@@ -2325,7 +2353,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	 */
 	if (trace->filter_pids.nr > 0)
 		err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
-	else if (evlist->threads->map[0] == -1)
+	else if (thread_map__pid(evlist->threads, 0) == -1)
 		err = perf_evlist__set_filter_pid(evlist, getpid());
 
 	if (err < 0) {
@@ -2343,7 +2371,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (forks)
 		perf_evlist__start_workload(evlist);
 
-	trace->multiple_threads = evlist->threads->map[0] == -1 ||
+	trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
 				  evlist->threads->nr > 1 ||
 				  perf_evlist__first(evlist)->attr.inherit;
 again:
@@ -2862,6 +2890,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			err = -ENOMEM;
 			goto out_close;
 		}
+
+		err = trace__validate_ev_qualifier(&trace);
+		if (err)
+			goto out_close;
 	}
 
 	err = target__validate(&trace.opts.target);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 317001c94660..094ddaee104c 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -11,9 +11,9 @@ ifneq ($(obj-perf),)
 obj-perf := $(abspath $(obj-perf))/
 endif
 
-$(shell echo -n > .config-detected)
-detected     = $(shell echo "$(1)=y"       >> .config-detected)
-detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected)
+$(shell echo -n > $(OUTPUT).config-detected)
+detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
+detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index ee41e705b2eb..d20d6e6ab65b 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,6 +31,7 @@ perf-y += code-reading.o
 perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
+perf-y += thread-map.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 87b9961646e4..c1dde733c3a6 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -171,6 +171,10 @@ static struct test {
 		.func = test__kmod_path__parse,
 	},
 	{
+		.desc = "Test thread map",
+		.func = test__thread_map,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 22f8a00446e1..39c784a100a9 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -545,8 +545,8 @@ out_err:
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 5b171d1e338b..4d4b9837b630 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -144,8 +144,8 @@ out_err:
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 65280d28662e..729112f4cfaa 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,5 +1,16 @@
+ifndef MK
+ifeq ($(MAKECMDGOALS),)
+# no target specified, trigger the whole suite
+all:
+	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile
+	@echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf
+else
+# run only specific test over 'Makefile'
+%:
+	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile $@
+endif
+else
 PERF := .
-MK   := Makefile
 
 include config/Makefile.arch
 
@@ -47,6 +58,7 @@ make_install_man    := install-man
 make_install_html   := install-html
 make_install_info   := install-info
 make_install_pdf    := install-pdf
+make_install_prefix := install prefix=/tmp/krava
 make_static         := LDFLAGS=-static
 
 # all the NO_* variable combined
@@ -57,7 +69,12 @@ make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
 
 # $(run) contains all available tests
 run := make_pure
+# Targets 'clean all' can be run together only through top level
+# Makefile because we detect clean target in Makefile.perf and
+# disable features detection
+ifeq ($(MK),Makefile)
 run += make_clean_all
+endif
 run += make_python_perf_so
 run += make_debug
 run += make_no_libperl
@@ -83,6 +100,7 @@ run += make_util_map_o
 run += make_util_pmu_bison_o
 run += make_install
 run += make_install_bin
+run += make_install_prefix
 # FIXME 'install-*' commented out till they're fixed
 # run += make_install_doc
 # run += make_install_man
@@ -157,6 +175,12 @@ test_make_install_O     := $(call test_dest_files,$(installed_files_all))
 test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
 test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
 
+# We prefix all installed files for make_install_prefix
+# with '/tmp/krava' to match installed/prefix-ed files.
+installed_files_all_prefix := $(addprefix /tmp/krava/,$(installed_files_all))
+test_make_install_prefix   := $(call test_dest_files,$(installed_files_all_prefix))
+test_make_install_prefix_O := $(call test_dest_files,$(installed_files_all_prefix))
+
 # FIXME nothing gets installed
 test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
 test_make_install_man_O  := $(test_make_install_man)
@@ -226,13 +250,13 @@ tarpkg:
 	( eval $$cmd ) >> $@ 2>&1
 
 make_kernelsrc:
-	@echo " - make -C <kernelsrc> tools/perf"
+	@echo "- make -C <kernelsrc> tools/perf"
 	$(call clean); \
 	(make -C ../.. tools/perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
 
 make_kernelsrc_tools:
-	@echo " - make -C <kernelsrc>/tools perf"
+	@echo "- make -C <kernelsrc>/tools perf"
 	$(call clean); \
 	(make -C ../../tools perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
@@ -244,3 +268,4 @@ out: $(run_O)
 	@echo OK
 
 .PHONY: all $(run) $(run_O) tarpkg clean
+endif # ifndef MK
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5855cf471210..666b67a4df9d 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -140,8 +140,8 @@ out_delete_evlist:
 	cpus	= NULL;
 	threads = NULL;
 out_free_cpus:
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 out_free_threads:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 7f48efa7e295..145050e2e544 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -143,7 +143,7 @@ static int synth_process(struct machine *machine)
 						perf_event__process,
 						machine, 0, 500);
 
-	thread_map__delete(map);
+	thread_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 9a7a116e09b8..a572f87e9c8d 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -78,7 +78,7 @@ int test__openat_syscall_event_on_all_cpus(void)
 	 * we use the auto allocation it will allocate just for 1 cpu,
 	 * as we start by cpu 0.
 	 */
-	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+	if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
 		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
 		goto out_close_fd;
 	}
@@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void)
 		}
 
 		expected = nr_openat_calls + cpu;
-		if (evsel->counts->cpu[cpu].val != expected) {
+		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
-				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
 			err = -1;
 		}
 	}
@@ -111,6 +111,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 6245221479d7..01a19626c846 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -45,7 +45,7 @@ int test__syscall_openat_tp_fields(void)
 
 	perf_evsel__config(evsel, &opts);
 
-	evlist->threads->map[0] = getpid();
+	thread_map__set_pid(evlist->threads, 0, getpid());
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 9f9491bb8e48..c9a37bc6b33a 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -44,9 +44,9 @@ int test__openat_syscall_event(void)
 		goto out_close_fd;
 	}
 
-	if (evsel->counts->cpu[0].val != nr_openat_calls) {
+	if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_openat_calls, evsel->counts->cpu[0].val);
+			 nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val);
 		goto out_close_fd;
 	}
 
@@ -56,6 +56,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 0d31403ea593..e698742d4fec 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -560,8 +560,8 @@ out:
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8e5038b48ba8..ebb47d96bc0b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -61,6 +61,7 @@ int test__switch_tracking(void);
 int test__fdarray__filter(void);
 int test__fdarray__add(void);
 int test__kmod_path__parse(void);
+int test__thread_map(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
new file mode 100644
index 000000000000..5acf000939ea
--- /dev/null
+++ b/tools/perf/tests/thread-map.c
@@ -0,0 +1,38 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "thread_map.h"
+#include "debug.h"
+
+int test__thread_map(void)
+{
+	struct thread_map *map;
+
+	/* test map on current pid */
+	map = thread_map__new_by_pid(getpid());
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid",
+			thread_map__pid(map, 0) == getpid());
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "perf"));
+	thread_map__put(map);
+
+	/* test dummy pid */
+	map = thread_map__new_dummy();
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid", thread_map__pid(map, 0) == -1);
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "dummy"));
+	thread_map__put(map);
+	return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index c42adb600091..7629bef2fd79 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1902,8 +1902,23 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case CTRL('c'):
 			goto out_free_stack;
 		case 'f':
-			if (!is_report_browser(hbt))
-				goto out_free_stack;
+			if (!is_report_browser(hbt)) {
+				struct perf_top *top = hbt->arg;
+
+				perf_evlist__toggle_enable(top->evlist);
+				/*
+				 * No need to refresh, resort/decay histogram
+				 * entries if we are not collecting samples:
+				 */
+				if (top->evlist->enabled) {
+					helpline = "Press 'f' to disable the events or 'h' to see other hotkeys";
+					hbt->refresh = delay_secs;
+				} else {
+					helpline = "Press 'f' again to re-enable the events";
+					hbt->refresh = 0;
+				}
+				continue;
+			}
 			/* Fall thru */
 		default:
 			helpline = "Press '?' for help on key bindings";
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index df66966cfde7..7e7405c9b936 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -119,12 +119,12 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 	if (per_cpu) {
 		mp->cpu = evlist->cpus->map[idx];
 		if (evlist->threads)
-			mp->tid = evlist->threads->map[0];
+			mp->tid = thread_map__pid(evlist->threads, 0);
 		else
 			mp->tid = -1;
 	} else {
 		mp->cpu = -1;
-		mp->tid = evlist->threads->map[idx];
+		mp->tid = thread_map__pid(evlist->threads, idx);
 	}
 }
 
@@ -1182,6 +1182,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 		data2 = NULL;
 	}
 
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
 	padding = size & 7;
 	if (padding)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a171abbe7301..471aecbc4d68 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -303,6 +303,7 @@ struct auxtrace_record {
 				      const char *str);
 	u64 (*reference)(struct auxtrace_record *itr);
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
 };
 
 #ifdef HAVE_AUXTRACE_SUPPORT
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 85b523885f9d..2babddaa2481 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,11 +7,15 @@
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
+#ifdef __GLIBC_PREREQ
+#if !__GLIBC_PREREQ(2, 6)
 int __weak sched_getcpu(void)
 {
 	errno = ENOSYS;
 	return -1;
 }
+#endif
+#endif
 
 static int perf_flag_probe(void)
 {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index c4e55b71010c..3667e2123e5b 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
 {
@@ -22,6 +23,7 @@ static struct cpu_map *cpu_map__default_new(void)
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -35,6 +37,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -194,14 +197,32 @@ struct cpu_map *cpu_map__dummy_new(void)
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
 }
 
-void cpu_map__delete(struct cpu_map *map)
+static void cpu_map__delete(struct cpu_map *map)
 {
-	free(map);
+	if (map) {
+		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+			  "cpu_map refcnt unbalanced\n");
+		free(map);
+	}
+}
+
+struct cpu_map *cpu_map__get(struct cpu_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void cpu_map__put(struct cpu_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		cpu_map__delete(map);
 }
 
 int cpu_map__get_socket(struct cpu_map *map, int idx)
@@ -263,6 +284,7 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
+	atomic_set(&cpus->refcnt, 1);
 	*res = c;
 	return 0;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 61a654849002..0af9cecb4c51 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -3,18 +3,19 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/atomic.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
+	atomic_t refcnt;
 	int nr;
 	int map[];
 };
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
-void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
@@ -22,6 +23,9 @@ int cpu_map__get_core(struct cpu_map *map, int idx);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
+struct cpu_map *cpu_map__get(struct cpu_map *map);
+void cpu_map__put(struct cpu_map *map);
+
 static inline int cpu_map__socket(struct cpu_map *sock, int s)
 {
 	if (!sock || s > sock->nr || s < 0)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index d7d986d8f23e..67a977e5d0ab 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -504,7 +504,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
 					       fork_event,
-					       threads->map[thread], 0,
+					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
 			err = -1;
@@ -515,12 +515,12 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 		 * comm.pid is set to thread group id by
 		 * perf_event__synthesize_comm
 		 */
-		if ((int) comm_event->comm.pid != threads->map[thread]) {
+		if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
 			bool need_leader = true;
 
 			/* is thread group leader in thread_map? */
 			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == threads->map[j]) {
+				if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
 					need_leader = false;
 					break;
 				}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8366511b45f8..6cfdee68e763 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -114,8 +114,8 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 {
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
-	cpu_map__delete(evlist->cpus);
-	thread_map__delete(evlist->threads);
+	cpu_map__put(evlist->cpus);
+	thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
 	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
@@ -548,7 +548,7 @@ static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
 	else
 		sid->cpu = -1;
 	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = evlist->threads->map[thread];
+		sid->tid = thread_map__pid(evlist->threads, thread);
 	else
 		sid->tid = -1;
 }
@@ -1101,6 +1101,31 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
+static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
+				       struct target *target)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		/*
+		 * We already have cpus for evsel (via PMU sysfs) so
+		 * keep it, if there's no target cpu list defined.
+		 */
+		if (evsel->cpus && target->cpu_list)
+			cpu_map__put(evsel->cpus);
+
+		if (!evsel->cpus || target->cpu_list)
+			evsel->cpus = cpu_map__get(evlist->cpus);
+
+		evsel->threads = thread_map__get(evlist->threads);
+
+		if (!evsel->cpus || !evsel->threads)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
@@ -1117,10 +1142,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return 0;
+	return perf_evlist__propagate_maps(evlist, target);
 
 out_delete_threads:
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->threads = NULL;
 	return -1;
 }
@@ -1353,7 +1378,7 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 out:
 	return err;
 out_free_cpus:
-	cpu_map__delete(evlist->cpus);
+	cpu_map__put(evlist->cpus);
 	evlist->cpus = NULL;
 	goto out;
 }
@@ -1475,7 +1500,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 				__func__, __LINE__);
 			goto out_close_pipes;
 		}
-		evlist->threads->map[0] = evlist->workload.pid;
+		thread_map__set_pid(evlist->threads, 0, evlist->workload.pid);
 	}
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a8489b9d2812..037633c1da9d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -289,5 +289,4 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33449decf7bd..2936b3080722 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -885,6 +885,8 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
+	cpu_map__put(evsel->cpus);
+	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
@@ -896,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -908,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = evsel->prev_raw_counts->cpu[cpu];
-		evsel->prev_raw_counts->cpu[cpu] = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -937,20 +939,18 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb)
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count)
 {
-	struct perf_counts_values count;
-
-	memset(&count, 0, sizeof(count));
+	memset(count, 0, sizeof(*count));
 
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
 		return -errno;
 
-	return cb(evsel, cpu, thread, &count);
+	return 0;
 }
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
@@ -962,15 +962,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	evsel->counts->cpu[cpu] = count;
+	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
 }
 
@@ -1167,7 +1167,7 @@ retry_sample_id:
 			int group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
-				pid = threads->map[thread];
+				pid = thread_map__pid(threads, thread);
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index bb0579e8a10a..4a7ed5656cf0 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,23 +8,8 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "symbol.h"
-
-struct perf_counts_values {
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-};
-
-struct perf_counts {
-	s8		   	  scaled;
-	struct perf_counts_values aggr;
-	struct perf_counts_values cpu[];
-};
+#include "cpumap.h"
+#include "stat.h"
 
 struct perf_evsel;
 
@@ -82,6 +67,7 @@ struct perf_evsel {
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
@@ -113,10 +99,20 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return evsel->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
@@ -233,12 +229,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
-typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
-				    int cpu, int thread,
-				    struct perf_counts_values *count);
-
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb);
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count);
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 21a77e7a171e..03ace57a800c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1063,8 +1063,7 @@ out:
 	free(buf);
 	return events;
 error:
-	if (events)
-		free_event_desc(events);
+	free_event_desc(events);
 	events = NULL;
 	goto out;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 4744673aff1b..7ff682770fdb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1448,10 +1448,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 	case PERF_RECORD_AUX:
 		ret = machine__process_aux_event(machine, event); break;
 	case PERF_RECORD_ITRACE_START:
-		ret = machine__process_itrace_start_event(machine, event);
+		ret = machine__process_itrace_start_event(machine, event); break;
 	case PERF_RECORD_LOST_SAMPLES:
 		ret = machine__process_lost_samples_event(machine, event, sample); break;
-		break;
 	default:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2a4d1ec02846..09f8d2357108 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,7 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "cpumap.h"
 #include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
@@ -285,7 +286,9 @@ __add_event(struct list_head *list, int *idx,
 	if (!evsel)
 		return NULL;
 
-	evsel->cpus = cpus;
+	if (cpus)
+		evsel->cpus = cpu_map__get(cpus);
+
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 09e738fe9ea2..13cef3c65565 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -119,8 +119,8 @@ event		[^,{}/]+
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -165,7 +165,6 @@ modifier_bp	[rwx]{1,3}
 			return PE_EVENT_NAME;
 		}
 
-.		|
 <<EOF>>		{
 			BEGIN(INITIAL);
 			REWIND(0);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0fcc624eb767..7bcb8c315615 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,4 +1,5 @@
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -205,17 +206,12 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
+				 char *desc __maybe_unused, char *val)
 {
 	struct perf_pmu_alias *alias;
-	char buf[256];
 	int ret;
 
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-	buf[ret] = 0;
-
 	alias = malloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
@@ -225,26 +221,43 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 
-	ret = parse_events_terms(&alias->terms, buf);
+	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
+		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
 	alias->name = strdup(name);
-	/*
-	 * load unit name and scale if available
-	 */
-	perf_pmu__parse_unit(alias, dir, name);
-	perf_pmu__parse_scale(alias, dir, name);
-	perf_pmu__parse_per_pkg(alias, dir, name);
-	perf_pmu__parse_snapshot(alias, dir, name);
+	if (dir) {
+		/*
+		 * load unit name and scale if available
+		 */
+		perf_pmu__parse_unit(alias, dir, name);
+		perf_pmu__parse_scale(alias, dir, name);
+		perf_pmu__parse_per_pkg(alias, dir, name);
+		perf_pmu__parse_snapshot(alias, dir, name);
+	}
 
 	list_add_tail(&alias->list, list);
 
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+{
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+
+	buf[ret] = 0;
+
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf);
+}
+
 static inline bool pmu_alias_info_file(char *name)
 {
 	size_t len;
@@ -436,7 +449,7 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
-struct perf_event_attr *__attribute__((weak))
+struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 076527b639bd..381f23a443c7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -249,8 +249,12 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 static bool kprobe_blacklist__listed(unsigned long address);
 static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 {
+	u64 etext_addr;
+
 	/* Get the address of _etext for checking non-probable text symbol */
-	if (kernel_get_symbol_address_by_name("_etext", false) < address)
+	etext_addr = kernel_get_symbol_address_by_name("_etext", false);
+
+	if (etext_addr != 0 && etext_addr < address)
 		pr_warning("%s is out of .text, skip it.\n", symbol);
 	else if (kprobe_blacklist__listed(address))
 		pr_warning("%s is blacklisted function, skip it.\n", symbol);
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5925fec90562..e23ded40c79e 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -20,3 +20,4 @@ util/stat.c
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
+util/string.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index d906d0ad5d40..626422eda727 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -384,7 +384,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
 
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
-	cpu_map__delete(pcpus->cpus);
+	cpu_map__put(pcpus->cpus);
 	pcpus->ob_type->tp_free((PyObject*)pcpus);
 }
 
@@ -453,7 +453,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__delete(pthreads->threads);
+	thread_map__put(pthreads->threads);
 	pthreads->ob_type->tp_free((PyObject*)pthreads);
 }
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index d457c523a33d..1f7becbe5e18 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 
 	do {
 		ret = perf_do_probe_api(fn, cpu, try[i++]);
@@ -226,7 +226,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		struct cpu_map *cpus = cpu_map__new(NULL);
 
 		cpu =  cpus ? cpus->map[0] : 0;
-		cpu_map__delete(cpus);
+		cpu_map__put(cpus);
 	} else {
 		cpu = evlist->cpus->map[0];
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index aa482c10469d..ed9dc2555ec7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -686,6 +686,8 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event __maybe_unused,
 				  struct ordered_events *oe)
 {
+	if (dump_trace)
+		fprintf(stdout, "\n");
 	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
@@ -1726,7 +1728,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
 		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
 
-	ret = fprintf(fp, "Aggregated stats:%s\n", msg);
+	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
@@ -1893,7 +1895,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	err = 0;
 
 out_delete_map:
-	cpu_map__delete(map);
+	cpu_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4014b709f956..f2a0d1521e26 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,8 @@
 #include <math.h>
 #include "stat.h"
+#include "evlist.h"
 #include "evsel.h"
+#include "thread_map.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -95,33 +97,46 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-struct perf_counts *perf_counts__new(int ncpus)
+struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
-	int size = sizeof(struct perf_counts) +
-		   ncpus * sizeof(struct perf_counts_values);
+	struct perf_counts *counts = zalloc(sizeof(*counts));
 
-	return zalloc(size);
+	if (counts) {
+		struct xyarray *values;
+
+		values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
+		if (!values) {
+			free(counts);
+			return NULL;
+		}
+
+		counts->values = values;
+	}
+
+	return counts;
 }
 
 void perf_counts__delete(struct perf_counts *counts)
 {
-	free(counts);
+	if (counts) {
+		xyarray__delete(counts->values);
+		free(counts);
+	}
 }
 
-static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+static void perf_counts__reset(struct perf_counts *counts)
 {
-	memset(counts, 0, (sizeof(*counts) +
-	       (ncpus * sizeof(struct perf_counts_values))));
+	xyarray__reset(counts->values);
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+void perf_evsel__reset_counts(struct perf_evsel *evsel)
 {
-	perf_counts__reset(evsel->counts, ncpus);
+	perf_counts__reset(evsel->counts);
 }
 
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
-	evsel->counts = perf_counts__new(ncpus);
+	evsel->counts = perf_counts__new(ncpus, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
@@ -130,3 +145,96 @@ void perf_evsel__free_counts(struct perf_evsel *evsel)
 	perf_counts__delete(evsel->counts);
 	evsel->counts = NULL;
 }
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
+}
+
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel->priv == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
+}
+
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads)
+{
+	struct perf_counts *counts;
+
+	counts = perf_counts__new(ncpus, nthreads);
+	if (counts)
+		evsel->prev_raw_counts = counts;
+
+	return counts ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
+}
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+{
+	int ncpus = perf_evsel__nr_cpus(evsel);
+	int nthreads = thread_map__nr(evsel->threads);
+
+	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+	    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		return -ENOMEM;
+
+	return 0;
+}
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__alloc_stats(evsel, alloc_raw))
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
+}
+
+void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+void perf_evlist__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel);
+	}
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 093dc3cb28dd..1cfbe0a980ac 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include "xyarray.h"
 
 struct stats
 {
@@ -29,8 +30,32 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_THREAD,
 };
 
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8			  scaled;
+	struct perf_counts_values aggr;
+	struct xyarray		  *values;
+};
+
+static inline struct perf_counts_values*
+perf_counts(struct perf_counts *counts, int cpu, int thread)
+{
+	return xyarray__entry(counts->values, cpu, thread);
+}
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -46,6 +71,8 @@ static inline void init_stats(struct stats *stats)
 }
 
 struct perf_evsel;
+struct perf_evlist;
+
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 			   enum perf_stat_evsel_id id);
 
@@ -62,10 +89,24 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				   double avg, int cpu, enum aggr_mode aggr);
 
-struct perf_counts *perf_counts__new(int ncpus);
+struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads);
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
+void perf_evlist__free_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_stats(struct perf_evlist *evlist);
 #endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 283d3e73e2f2..eec6c1149f44 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -748,7 +748,7 @@ static int str_to_bitmap(char *s, cpumask_t *b)
 		set_bit(c, cpumask_bits(b));
 	}
 
-	cpu_map__delete(m);
+	cpu_map__put(m);
 
 	return ret;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 504f2d73b7ee..48b588c6951a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1132,8 +1132,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
-	if (fd < 0)
+	if (fd < 0) {
+		pr_err("%s requires CAP_SYS_RAWIO capability to access.\n",
+			kcore_filename);
 		return -EINVAL;
+	}
 
 	/* Read new maps into temporary lists */
 	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f4822bd03709..da7646d767fe 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,8 +8,11 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -20,11 +23,26 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static void thread_map__reset(struct thread_map *map, int start, int nr)
+{
+	size_t size = (nr - start) * sizeof(map->map[0]);
+
+	memset(&map->map[start], 0, size);
+}
+
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 {
-	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
+	int start = map ? map->nr : 0;
+
+	map = realloc(map, size);
+	/*
+	 * We only realloc to add more items, let's reset new items.
+	 */
+	if (map)
+		thread_map__reset(map, start, nr);
 
-	return realloc(map, size);
+	return map;
 }
 
 #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
@@ -45,8 +63,9 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -61,8 +80,9 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0] = tid;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, tid);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -84,6 +104,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -123,8 +144,10 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 			threads = tmp;
 		}
 
-		for (i = 0; i < items; i++)
-			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+		for (i = 0; i < items; i++) {
+			thread_map__set_pid(threads, threads->nr + i,
+					    atoi(namelist[i]->d_name));
+		}
 
 		for (i = 0; i < items; i++)
 			zfree(&namelist[i]);
@@ -201,7 +224,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			threads->map[j++] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -210,6 +233,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -227,8 +252,9 @@ struct thread_map *thread_map__new_dummy(void)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0]	= -1;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, -1);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -267,10 +293,12 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			goto out_free_threads;
 
 		threads = nt;
-		threads->map[ntasks - 1] = tid;
-		threads->nr		 = ntasks;
+		thread_map__set_pid(threads, ntasks - 1, tid);
+		threads->nr = ntasks;
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -290,9 +318,30 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	free(threads);
+	if (threads) {
+		int i;
+
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt unbalanced\n");
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
+		free(threads);
+	}
+}
+
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
@@ -301,7 +350,60 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }
+
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		map->map[i].comm = strdup("dummy");
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	map->map[i].comm = comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i)
+		comm_init(threads, i);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 95313f43cc0f..af679d8a50f8 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,10 +3,17 @@
 
 #include <sys/types.h>
 #include <stdio.h>
+#include <linux/atomic.h>
+
+struct thread_map_data {
+	pid_t    pid;
+	char	*comm;
+};
 
 struct thread_map {
+	atomic_t refcnt;
 	int nr;
-	pid_t map[];
+	struct thread_map_data map[];
 };
 
 struct thread_map *thread_map__new_dummy(void);
@@ -15,11 +22,12 @@ struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 
+struct thread_map *thread_map__get(struct thread_map *map);
+void thread_map__put(struct thread_map *map);
+
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
-void thread_map__delete(struct thread_map *threads);
-
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
@@ -27,4 +35,21 @@ static inline int thread_map__nr(struct thread_map *threads)
 	return threads ? threads->nr : 1;
 }
 
+static inline pid_t thread_map__pid(struct thread_map *map, int thread)
+{
+	return map->map[thread].pid;
+}
+
+static inline void
+thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
+{
+	map->map[thread].pid = pid;
+}
+
+static inline char *thread_map__comm(struct thread_map *map, int thread)
+{
+	return map->map[thread].comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads);
 #endif	/* __PERF_THREAD_MAP_H */