21 files changed, 387 insertions, 139 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index f5b81d439387..1ef45d803024 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -48,8 +48,6 @@ libbpf/
 libperf/
 libsubcmd/
 libsymbol/
-libtraceevent/
-libtraceevent_plugins/
 fixdep
 Documentation/doc.dep
 python_ext_build/
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b102a4c525e4..a2034fa18325 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -569,6 +569,8 @@ ifndef NO_LIBELF
     ifeq ($(feature-libdebuginfod), 1)
       CFLAGS += -DHAVE_DEBUGINFOD_SUPPORT
       EXTLIBS += -ldebuginfod
+    else
+      $(warning No elfutils/debuginfod.h found, no debuginfo server support, please install libdebuginfod-dev/elfutils-debuginfod-client-devel or equivalent)
     endif
   endif
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8ee59ecb1411..b61c355fbdee 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1143,7 +1143,8 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
-		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.txt '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' ; \
 		$(INSTALL) tests/shell/coresight/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight'
 	$(Q)$(MAKE) -C tests/shell/coresight install-tests
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index adbaf80b398c..ab9035573a15 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -3471,7 +3471,7 @@ static struct option __record_options[] = {
 		    "sample selected machine registers on interrupt,"
 		    " use '-I?' to list register names", parse_intr_regs),
 	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
-		    "sample selected machine registers on interrupt,"
+		    "sample selected machine registers in user space,"
 		    " use '--user-regs=?' to list register names", parse_user_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5981cc51abc8..64bf3ac237f2 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -999,7 +999,7 @@ thread_atoms_search(struct rb_root_cached *root, struct thread *thread,
 		else if (cmp < 0)
 			node = node->rb_right;
 		else {
-			BUG_ON(thread != atoms->thread);
+			BUG_ON(!RC_CHK_EQUAL(thread, atoms->thread));
 			return atoms;
 		}
 	}
@@ -1116,6 +1116,21 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp)
 	atoms->nb_atoms++;
 }
 
+static void free_work_atoms(struct work_atoms *atoms)
+{
+	struct work_atom *atom, *tmp;
+
+	if (atoms == NULL)
+		return;
+
+	list_for_each_entry_safe(atom, tmp, &atoms->work_list, list) {
+		list_del(&atom->list);
+		free(atom);
+	}
+	thread__zput(atoms->thread);
+	free(atoms);
+}
+
 static int latency_switch_event(struct perf_sched *sched,
 				struct evsel *evsel,
 				struct perf_sample *sample,
@@ -1639,6 +1654,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	const char *color = PERF_COLOR_NORMAL;
 	char stimestamp[32];
 	const char *str;
+	int ret = -1;
 
 	BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
 
@@ -1669,17 +1685,20 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	sched_in = map__findnew_thread(sched, machine, -1, next_pid);
 	sched_out = map__findnew_thread(sched, machine, -1, prev_pid);
 	if (sched_in == NULL || sched_out == NULL)
-		return -1;
+		goto out;
 
 	tr = thread__get_runtime(sched_in);
-	if (tr == NULL) {
-		thread__put(sched_in);
-		return -1;
-	}
+	if (tr == NULL)
+		goto out;
+
+	thread__put(sched->curr_thread[this_cpu.cpu]);
+	thread__put(sched->curr_out_thread[this_cpu.cpu]);
 
 	sched->curr_thread[this_cpu.cpu] = thread__get(sched_in);
 	sched->curr_out_thread[this_cpu.cpu] = thread__get(sched_out);
 
+	ret = 0;
+
 	str = thread__comm_str(sched_in);
 	new_shortname = 0;
 	if (!tr->shortname[0]) {
@@ -1774,12 +1793,10 @@ sched_out:
 	color_fprintf(stdout, color, "\n");
 
 out:
-	if (sched->map.task_name)
-		thread__put(sched_out);
-
+	thread__put(sched_out);
 	thread__put(sched_in);
 
-	return 0;
+	return ret;
 }
 
 static int process_sched_switch_event(const struct perf_tool *tool,
@@ -2023,6 +2040,16 @@ static u64 evsel__get_time(struct evsel *evsel, u32 cpu)
 	return r->last_time[cpu];
 }
 
+static void timehist__evsel_priv_destructor(void *priv)
+{
+	struct evsel_runtime *r = priv;
+
+	if (r) {
+		free(r->last_time);
+		free(r);
+	}
+}
+
 static int comm_width = 30;
 
 static char *timehist_get_commstr(struct thread *thread)
@@ -3276,6 +3303,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 
 	setup_pager();
 
+	evsel__set_priv_destructor(timehist__evsel_priv_destructor);
+
 	/* prefer sched_waking if it is captured */
 	if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking"))
 		handlers[1].handler = timehist_sched_wakeup_ignore;
@@ -3376,13 +3405,13 @@ static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *d
 			this->total_runtime += data->total_runtime;
 			this->nb_atoms += data->nb_atoms;
 			this->total_lat += data->total_lat;
-			list_splice(&data->work_list, &this->work_list);
+			list_splice_init(&data->work_list, &this->work_list);
 			if (this->max_lat < data->max_lat) {
 				this->max_lat = data->max_lat;
 				this->max_lat_start = data->max_lat_start;
 				this->max_lat_end = data->max_lat_end;
 			}
-			zfree(&data);
+			free_work_atoms(data);
 			return;
 		}
 	}
@@ -3461,7 +3490,6 @@ static int perf_sched__lat(struct perf_sched *sched)
 		work_list = rb_entry(next, struct work_atoms, node);
 		output_lat_thread(sched, work_list);
 		next = rb_next(next);
-		thread__zput(work_list->thread);
 	}
 
 	printf(" -----------------------------------------------------------------------------------------------------------------\n");
@@ -3475,6 +3503,13 @@ static int perf_sched__lat(struct perf_sched *sched)
 
 	rc = 0;
 
+	while ((next = rb_first_cached(&sched->sorted_atom_root))) {
+		struct work_atoms *data;
+
+		data = rb_entry(next, struct work_atoms, node);
+		rb_erase_cached(next, &sched->sorted_atom_root);
+		free_work_atoms(data);
+	}
 out_free_cpus_switch_event:
 	free_cpus_switch_event(sched);
 	return rc;
@@ -3546,10 +3581,10 @@ static int perf_sched__map(struct perf_sched *sched)
 
 	sched->curr_out_thread = calloc(MAX_CPUS, sizeof(*(sched->curr_out_thread)));
 	if (!sched->curr_out_thread)
-		return rc;
+		goto out_free_curr_thread;
 
 	if (setup_cpus_switch_event(sched))
-		goto out_free_curr_thread;
+		goto out_free_curr_out_thread;
 
 	if (setup_map_cpus(sched))
 		goto out_free_cpus_switch_event;
@@ -3580,7 +3615,14 @@ out_put_map_cpus:
 out_free_cpus_switch_event:
 	free_cpus_switch_event(sched);
 
+out_free_curr_out_thread:
+	for (int i = 0; i < MAX_CPUS; i++)
+		thread__put(sched->curr_out_thread[i]);
+	zfree(&sched->curr_out_thread);
+
 out_free_curr_thread:
+	for (int i = 0; i < MAX_CPUS; i++)
+		thread__put(sched->curr_thread[i]);
 	zfree(&sched->curr_thread);
 	return rc;
 }
@@ -3887,13 +3929,15 @@ int cmd_sched(int argc, const char **argv)
 	if (!argc)
 		usage_with_options(sched_usage, sched_options);
 
+	thread__set_priv_destructor(free);
+
 	/*
 	 * Aliased to 'perf script' for now:
 	 */
 	if (!strcmp(argv[0], "script")) {
-		return cmd_script(argc, argv);
+		ret = cmd_script(argc, argv);
 	} else if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) {
-		return __cmd_record(argc, argv);
+		ret = __cmd_record(argc, argv);
 	} else if (strlen(argv[0]) > 2 && strstarts("latency", argv[0])) {
 		sched.tp_handler = &lat_ops;
 		if (argc > 1) {
@@ -3902,7 +3946,7 @@ int cmd_sched(int argc, const char **argv)
 				usage_with_options(latency_usage, latency_options);
 		}
 		setup_sorting(&sched, latency_options, latency_usage);
-		return perf_sched__lat(&sched);
+		ret = perf_sched__lat(&sched);
 	} else if (!strcmp(argv[0], "map")) {
 		if (argc) {
 			argc = parse_options(argc, argv, map_options, map_usage, 0);
@@ -3913,13 +3957,14 @@ int cmd_sched(int argc, const char **argv)
 				sched.map.task_names = strlist__new(sched.map.task_name, NULL);
 				if (sched.map.task_names == NULL) {
 					fprintf(stderr, "Failed to parse task names\n");
-					return -1;
+					ret = -1;
+					goto out;
 				}
 			}
 		}
 		sched.tp_handler = &map_ops;
 		setup_sorting(&sched, latency_options, latency_usage);
-		return perf_sched__map(&sched);
+		ret = perf_sched__map(&sched);
 	} else if (strlen(argv[0]) > 2 && strstarts("replay", argv[0])) {
 		sched.tp_handler = &replay_ops;
 		if (argc) {
@@ -3927,7 +3972,7 @@ int cmd_sched(int argc, const char **argv)
 			if (argc)
 				usage_with_options(replay_usage, replay_options);
 		}
-		return perf_sched__replay(&sched);
+		ret = perf_sched__replay(&sched);
 	} else if (!strcmp(argv[0], "timehist")) {
 		if (argc) {
 			argc = parse_options(argc, argv, timehist_options,
@@ -3943,19 +3988,19 @@ int cmd_sched(int argc, const char **argv)
 				parse_options_usage(NULL, timehist_options, "w", true);
 			if (sched.show_next)
 				parse_options_usage(NULL, timehist_options, "n", true);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 		ret = symbol__validate_sym_arguments();
-		if (ret)
-			return ret;
-
-		return perf_sched__timehist(&sched);
+		if (!ret)
+			ret = perf_sched__timehist(&sched);
 	} else {
 		usage_with_options(sched_usage, sched_options);
 	}
 
+out:
 	/* free usage string allocated by parse_options_subcommand */
 	free((void *)sched_usage[0]);
 
-	return 0;
+	return ret;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ecd26e058baf..f77e4f4b6f03 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1327,7 +1327,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
 		   [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ },
 		   [4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, },
-	{ .name	    = "rseq",	    .errpid = true,
+	{ .name	    = "rseq",
 	  .arg = { [0] = { .from_user = true /* rseq */, }, }, },
 	{ .name	    = "rt_sigaction",
 	  .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
@@ -1351,7 +1351,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "sendto",
 	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
 		   [4] = SCA_SOCKADDR_FROM_USER(addr), }, },
-	{ .name	    = "set_robust_list",	    .errpid = true,
+	{ .name	    = "set_robust_list",
 	  .arg = { [0] = { .from_user = true /* head */, }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
@@ -2873,8 +2873,8 @@ errno_print: {
 	else if (sc->fmt->errpid) {
 		struct thread *child = machine__find_thread(trace->host, ret, ret);
 
+		fprintf(trace->output, "%ld", ret);
 		if (child != NULL) {
-			fprintf(trace->output, "%ld", ret);
 			if (thread__comm_set(child))
 				fprintf(trace->output, " (%s)", thread__comm_str(child));
 			thread__put(child);
@@ -3986,10 +3986,13 @@ static int trace__set_filter_loop_pids(struct trace *trace)
 		if (!strcmp(thread__comm_str(parent), "sshd") ||
 		    strstarts(thread__comm_str(parent), "gnome-terminal")) {
 			pids[nr++] = thread__tid(parent);
+			thread__put(parent);
 			break;
 		}
+		thread__put(thread);
 		thread = parent;
 	}
+	thread__put(thread);
 
 	err = evlist__append_tp_filter_pids(trace->evlist, nr, pids);
 	if (!err && trace->filter_pids.map)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 121cf61ba1b3..e0b2e7268ef6 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -680,7 +680,10 @@ class CallGraphModelBase(TreeModel):
 				s = value.replace("%", "\\%")
 				s = s.replace("_", "\\_")
 				# Translate * and ? into SQL LIKE pattern characters % and _
-				trans = string.maketrans("*?", "%_")
+				if sys.version_info[0] == 3:
+					trans = str.maketrans("*?", "%_")
+				else:
+					trans = string.maketrans("*?", "%_")
 				match = " LIKE '" + str(s).translate(trans) + "'"
 			else:
 				match = " GLOB '" + str(value) + "'"
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index 4cb7d486b5c1..047433c977bc 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -104,6 +104,7 @@ static int bp_accounting(int wp_cnt, int share)
 		fd_wp = wp_event((void *)&the_var, &attr_new);
 		TEST_ASSERT_VAL("failed to create max wp\n", fd_wp != -1);
 		pr_debug("wp max created\n");
+		close(fd_wp);
 	}
 
 	for (i = 0; i < wp_cnt; i++)
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 5cab17a1942e..ee43d8fa2ed6 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -258,7 +258,7 @@ static int compar(const void *a, const void *b)
 	const struct event_node *nodeb = b;
 	s64 cmp = nodea->event_time - nodeb->event_time;
 
-	return cmp;
+	return cmp < 0 ? -1 : (cmp > 0 ? 1 : 0);
 }
 
 static int process_events(struct evlist *evlist,
diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
index ed114b044293..b6986d50dde6 100644
--- a/tools/perf/tests/tests-scripts.c
+++ b/tools/perf/tests/tests-scripts.c
@@ -255,6 +255,7 @@ static void append_scripts_in_dir(int dir_fd,
 			continue; /* Skip scripts that have a separate driver. */
 		fd = openat(dir_fd, ent->d_name, O_PATH);
 		append_scripts_in_dir(fd, result, result_sz);
+		close(fd);
 	}
 	for (i = 0; i < n_dirs; i++) /* Clean up */
 		zfree(&entlist[i]);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 49ba82bf3391..3283b6313bab 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -3267,10 +3267,10 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 				/*
 				 * No need to set actions->dso here since
 				 * it's just to remove the current filter.
-				 * Ditto for thread below.
 				 */
 				do_zoom_dso(browser, actions);
 			} else if (top == &browser->hists->thread_filter) {
+				actions->thread = thread;
 				do_zoom_thread(browser, actions);
 			} else if (top == &browser->hists->socket_filter) {
 				do_zoom_socket(browser, actions);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e763e8d99a43..ee00313d5d7e 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -864,7 +864,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 	char *allocated_name = NULL;
 	int ret = 0;
 
-	if (!dso__has_build_id(dso))
+	if (!dso__has_build_id(dso) || !dso__hit(dso))
 		return 0;
 
 	if (dso__is_kcore(dso)) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbf9c8cee3c5..6d7249cc1a99 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1477,6 +1477,15 @@ static void evsel__free_config_terms(struct evsel *evsel)
 	free_config_terms(&evsel->config_terms);
 }
 
+static void (*evsel__priv_destructor)(void *priv);
+
+void evsel__set_priv_destructor(void (*destructor)(void *priv))
+{
+	assert(evsel__priv_destructor == NULL);
+
+	evsel__priv_destructor = destructor;
+}
+
 void evsel__exit(struct evsel *evsel)
 {
 	assert(list_empty(&evsel->core.node));
@@ -1502,6 +1511,8 @@ void evsel__exit(struct evsel *evsel)
 	hashmap__free(evsel->per_pkg_mask);
 	evsel->per_pkg_mask = NULL;
 	zfree(&evsel->metric_events);
+	if (evsel__priv_destructor)
+		evsel__priv_destructor(evsel->priv);
 	perf_evsel__object.fini(evsel);
 	if (evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
 	    evsel__tool_event(evsel) == PERF_TOOL_USER_TIME)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 15e745a9a798..26574a33a725 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -282,6 +282,8 @@ void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
 void evsel__exit(struct evsel *evsel);
 void evsel__delete(struct evsel *evsel);
 
+void evsel__set_priv_destructor(void (*destructor)(void *priv));
+
 struct callchain_param;
 
 void evsel__config(struct evsel *evsel, struct record_opts *opts,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fd2597613f3d..61f10578e121 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -127,6 +127,7 @@ struct intel_pt {
 
 	bool single_pebs;
 	bool sample_pebs;
+	int pebs_data_src_fmt;
 	struct evsel *pebs_evsel;
 
 	u64 evt_sample_type;
@@ -175,6 +176,7 @@ enum switch_state {
 struct intel_pt_pebs_event {
 	struct evsel *evsel;
 	u64 id;
+	int data_src_fmt;
 };
 
 struct intel_pt_queue {
@@ -2232,7 +2234,146 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack,
 	}
 }
 
-static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id)
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
+
+/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */
+static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),         /* L3 miss|SNP N/A */
+	OP_LH | P(LVL, L1)  | LEVEL(L1)  | P(SNOOP, NONE),             /* L1 hit|SNP None */
+	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),             /* LFB/MAB hit|SNP None */
+	OP_LH | P(LVL, L2)  | LEVEL(L2)  | P(SNOOP, NONE),             /* L2 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, NONE),             /* L3 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HIT),              /* L3 hit|SNP Hit */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),             /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),             /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOPX, FWD),             /* L3 hit|SNP Fwd */
+	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM),   /* Remote L3 hit|SNP HitM */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, HIT),         /* RAM hit|SNP Hit */
+	OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT),    /* Remote L3 hit|SNP Hit */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | SNOOP_NONE_MISS,       /* RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, IO)  | LEVEL(NA) | P(SNOOP, NONE),              /* I/O hit|SNP None */
+	OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE),              /* Uncached hit|SNP None */
+};
+
+/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */
+static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),       /* L3 miss|SNP N/A */
+	OP_LH | P(LVL, L1)  | LEVEL(L1)  | P(SNOOP, NONE),           /* L1 hit|SNP None */
+	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),           /* LFB/MAB hit|SNP None */
+	OP_LH | P(LVL, L2)  | LEVEL(L2)  | P(SNOOP, NONE),           /* L2 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, NONE),           /* L3 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, MISS),           /* L3 hit|SNP Hit */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HIT),            /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOPX, FWD),           /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),           /* L3 hit|SNP Fwd */
+	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, NONE),      /* RAM hit|SNP Hit */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE),                   /* Remote L3 hit|SNP Hit */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD),                   /* RAM hit|SNP None or Miss */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM),                   /* Remote RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, IO)  | LEVEL(NA) | P(SNOOP, NONE),            /* I/O hit|SNP None */
+	OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE),            /* Uncached hit|SNP None */
+};
+
+/* Based on kernel pebs_set_tlb_lock() */
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+	/*
+	 * TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (tlb)
+		*val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		*val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/* locked prefix */
+	if (lock)
+		*val |= P(LOCK, LOCKED);
+}
+
+/* Based on kernel __grt_latency_data() */
+static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk,
+				     const u64 *pebs_data_source)
+{
+	u64 val;
+
+	dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
+	val = pebs_data_source[dse];
+
+	pebs_set_tlb_lock(&val, tlb, lock);
+
+	if (blk)
+		val |= P(BLK, DATA);
+	else
+		val |= P(BLK, NA);
+
+	return val;
+}
+
+/* Default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)    |\
+		     PERF_MEM_S(LVL, NA)   |\
+		     PERF_MEM_S(SNOOP, NA) |\
+		     PERF_MEM_S(LOCK, NA)  |\
+		     PERF_MEM_S(TLB, NA)   |\
+		     PERF_MEM_S(LVLNUM, NA))
+
+enum DATA_SRC_FORMAT {
+	DATA_SRC_FORMAT_ERR  = -1,
+	DATA_SRC_FORMAT_NA   =  0,
+	DATA_SRC_FORMAT_GRT  =  1,
+	DATA_SRC_FORMAT_CMT  =  2,
+};
+
+/* Based on kernel grt_latency_data() and cmt_latency_data */
+static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt)
+{
+	switch (data_src_fmt) {
+	case DATA_SRC_FORMAT_GRT: {
+		union {
+			u64 val;
+			struct {
+				unsigned int dse:4;
+				unsigned int locked:1;
+				unsigned int stlb_miss:1;
+				unsigned int fwd_blk:1;
+				unsigned int reserved:25;
+			};
+		} x = {.val = mem_aux_info};
+		return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+						 pebs_data_source_grt);
+	}
+	case DATA_SRC_FORMAT_CMT: {
+		union {
+			u64 val;
+			struct {
+				unsigned int dse:5;
+				unsigned int locked:1;
+				unsigned int stlb_miss:1;
+				unsigned int fwd_blk:1;
+				unsigned int reserved:24;
+			};
+		} x = {.val = mem_aux_info};
+		return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+						 pebs_data_source_cmt);
+	}
+	default:
+		return PERF_MEM_NA;
+	}
+}
+
+static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel,
+					 u64 id, int data_src_fmt)
 {
 	const struct intel_pt_blk_items *items = &ptq->state->items;
 	struct perf_sample sample = { .ip = 0, };
@@ -2350,6 +2491,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_DATA_SRC) {
+		if (items->has_mem_aux_info && data_src_fmt) {
+			if (data_src_fmt < 0) {
+				pr_err("Intel PT missing data_src info\n");
+				return -1;
+			}
+			sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt);
+		} else {
+			sample.data_src = PERF_MEM_NA;
+		}
+	}
+
 	if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
 		u64 ax = items->has_rax ? items->rax : 0;
 		/* Refer kernel's intel_hsw_transaction() */
@@ -2368,9 +2521,10 @@ static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	struct evsel *evsel = pt->pebs_evsel;
+	int data_src_fmt = pt->pebs_data_src_fmt;
 	u64 id = evsel->core.id[0];
 
-	return intel_pt_do_synth_pebs_sample(ptq, evsel, id);
+	return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt);
 }
 
 static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
@@ -2395,7 +2549,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 				       hw_id);
 			return intel_pt_synth_single_pebs_sample(ptq);
 		}
-		err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id);
+		err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt);
 		if (err)
 			return err;
 	}
@@ -3355,6 +3509,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt,
 					event->itrace_start.tid);
 }
 
+/*
+ * Events with data_src are identified by L1_Hit_Indication
+ * refer https://github.com/intel/perfmon
+ */
+static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel)
+{
+	struct perf_env *env = pt->machine->env;
+	int fmt = DATA_SRC_FORMAT_NA;
+
+	if (!env->cpuid)
+		return DATA_SRC_FORMAT_ERR;
+
+	/*
+	 * PEBS-via-PT is only supported on E-core non-hybrid. Of those only
+	 * Gracemont and Crestmont have data_src. Check for:
+	 *	Alderlake N   (Gracemont)
+	 *	Sierra Forest (Crestmont)
+	 *	Grand Ridge   (Crestmont)
+	 */
+
+	if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19))
+		fmt = DATA_SRC_FORMAT_GRT;
+
+	if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) ||
+	    !strncmp(env->cpuid, "GenuineIntel,6,182,", 19))
+		fmt = DATA_SRC_FORMAT_CMT;
+
+	if (fmt == DATA_SRC_FORMAT_NA)
+		return fmt;
+
+	/*
+	 * Only data_src events are:
+	 *	mem-loads	event=0xd0,umask=0x5
+	 *	mem-stores	event=0xd0,umask=0x6
+	 */
+	if (evsel->core.attr.type == PERF_TYPE_RAW &&
+	    ((evsel->core.attr.config & 0xffff) == 0x5d0 ||
+	     (evsel->core.attr.config & 0xffff) == 0x6d0))
+		return fmt;
+
+	return DATA_SRC_FORMAT_NA;
+}
+
 static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
 					     union perf_event *event,
 					     struct perf_sample *sample)
@@ -3375,6 +3572,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
 
 	ptq->pebs[hw_id].evsel = evsel;
 	ptq->pebs[hw_id].id = sample->id;
+	ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
 
 	return 0;
 }
@@ -3924,6 +4122,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt)
 			}
 			pt->single_pebs = true;
 			pt->sample_pebs = true;
+			pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
 			pt->pebs_evsel = evsel;
 		}
 	}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9be2f4479f52..20fd742984e3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1974,7 +1974,7 @@ static void ip__resolve_ams(struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, ip, &al);
+	thread__find_cpumode_addr_location(thread, ip, /*symbols=*/true, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -2076,7 +2076,7 @@ static int add_callchain_ip(struct thread *thread,
 	al.sym = NULL;
 	al.srcline = NULL;
 	if (!cpumode) {
-		thread__find_cpumode_addr_location(thread, ip, &al);
+		thread__find_cpumode_addr_location(thread, ip, symbols, &al);
 	} else {
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
@@ -2104,6 +2104,8 @@ static int add_callchain_ip(struct thread *thread,
 		}
 		if (symbols)
 			thread__find_symbol(thread, *cpumode, ip, &al);
+		else
+			thread__find_map(thread, *cpumode, ip, &al);
 	}
 
 	if (al.sym != NULL) {
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index 81e0135cddf0..a1c71d9793bd 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -282,6 +282,7 @@ bool is_event_supported(u8 type, u64 config)
 			ret = evsel__open(evsel, NULL, tmap) >= 0;
 		}
 
+		evsel__close(evsel);
 		evsel__delete(evsel);
 	}
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index c6f369b5d893..36c1d3090689 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -90,11 +90,23 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 {
 	FILE *fp;
 	int ret = -1;
-	bool need_swap = false;
+	bool need_swap = false, elf32;
 	u8 e_ident[EI_NIDENT];
-	size_t buf_size;
-	void *buf;
 	int i;
+	union {
+		struct {
+			Elf32_Ehdr ehdr32;
+			Elf32_Phdr *phdr32;
+		};
+		struct {
+			Elf64_Ehdr ehdr64;
+			Elf64_Phdr *phdr64;
+		};
+	} hdrs;
+	void *phdr;
+	size_t phdr_size;
+	void *buf = NULL;
+	size_t buf_size = 0;
 
 	fp = fopen(filename, "r");
 	if (fp == NULL)
@@ -108,117 +120,79 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 		goto out;
 
 	need_swap = check_need_swap(e_ident[EI_DATA]);
+	elf32 = e_ident[EI_CLASS] == ELFCLASS32;
 
-	/* for simplicity */
-	fseek(fp, 0, SEEK_SET);
-
-	if (e_ident[EI_CLASS] == ELFCLASS32) {
-		Elf32_Ehdr ehdr;
-		Elf32_Phdr *phdr;
-
-		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
-			goto out;
+	if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64,
+		  elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64),
+		  1, fp) != 1)
+		goto out;
 
-		if (need_swap) {
-			ehdr.e_phoff = bswap_32(ehdr.e_phoff);
-			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
-			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+	if (need_swap) {
+		if (elf32) {
+			hdrs.ehdr32.e_phoff = bswap_32(hdrs.ehdr32.e_phoff);
+			hdrs.ehdr32.e_phentsize = bswap_16(hdrs.ehdr32.e_phentsize);
+			hdrs.ehdr32.e_phnum = bswap_16(hdrs.ehdr32.e_phnum);
+		} else {
+			hdrs.ehdr64.e_phoff = bswap_64(hdrs.ehdr64.e_phoff);
+			hdrs.ehdr64.e_phentsize = bswap_16(hdrs.ehdr64.e_phentsize);
+			hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum);
 		}
+	}
+	phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum
+			  : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum;
+	phdr = malloc(phdr_size);
+	if (phdr == NULL)
+		goto out;
 
-		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
-		buf = malloc(buf_size);
-		if (buf == NULL)
-			goto out;
-
-		fseek(fp, ehdr.e_phoff, SEEK_SET);
-		if (fread(buf, buf_size, 1, fp) != 1)
-			goto out_free;
-
-		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
-			void *tmp;
-			long offset;
-
-			if (need_swap) {
-				phdr->p_type = bswap_32(phdr->p_type);
-				phdr->p_offset = bswap_32(phdr->p_offset);
-				phdr->p_filesz = bswap_32(phdr->p_filesz);
-			}
-
-			if (phdr->p_type != PT_NOTE)
-				continue;
-
-			buf_size = phdr->p_filesz;
-			offset = phdr->p_offset;
-			tmp = realloc(buf, buf_size);
-			if (tmp == NULL)
-				goto out_free;
-
-			buf = tmp;
-			fseek(fp, offset, SEEK_SET);
-			if (fread(buf, buf_size, 1, fp) != 1)
-				goto out_free;
+	fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
+	if (fread(phdr, phdr_size, 1, fp) != 1)
+		goto out_free;
 
-			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0) {
-				ret = bid->size;
-				break;
-			}
-		}
-	} else {
-		Elf64_Ehdr ehdr;
-		Elf64_Phdr *phdr;
+	if (elf32)
+		hdrs.phdr32 = phdr;
+	else
+		hdrs.phdr64 = phdr;
 
-		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
-			goto out;
+	for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) {
+		size_t p_filesz;
 
 		if (need_swap) {
-			ehdr.e_phoff = bswap_64(ehdr.e_phoff);
-			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
-			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+			if (elf32) {
+				hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type);
+				hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset);
+				hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset);
+			} else {
+				hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type);
+				hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset);
+				hdrs.phdr64[i].p_filesz = bswap_64(hdrs.phdr64[i].p_filesz);
+			}
 		}
+		if ((elf32 ? hdrs.phdr32[i].p_type : hdrs.phdr64[i].p_type) != PT_NOTE)
+			continue;
 
-		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
-		buf = malloc(buf_size);
-		if (buf == NULL)
-			goto out;
-
-		fseek(fp, ehdr.e_phoff, SEEK_SET);
-		if (fread(buf, buf_size, 1, fp) != 1)
-			goto out_free;
-
-		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+		p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz;
+		if (p_filesz > buf_size) {
 			void *tmp;
-			long offset;
-
-			if (need_swap) {
-				phdr->p_type = bswap_32(phdr->p_type);
-				phdr->p_offset = bswap_64(phdr->p_offset);
-				phdr->p_filesz = bswap_64(phdr->p_filesz);
-			}
 
-			if (phdr->p_type != PT_NOTE)
-				continue;
-
-			buf_size = phdr->p_filesz;
-			offset = phdr->p_offset;
+			buf_size = p_filesz;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
-
 			buf = tmp;
-			fseek(fp, offset, SEEK_SET);
-			if (fread(buf, buf_size, 1, fp) != 1)
-				goto out_free;
+		}
+		fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
+		if (fread(buf, p_filesz, 1, fp) != 1)
+			goto out_free;
 
-			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0) {
-				ret = bid->size;
-				break;
-			}
+		ret = read_build_id(buf, p_filesz, bid, need_swap);
+		if (ret == 0) {
+			ret = bid->size;
+			break;
 		}
 	}
 out_free:
 	free(buf);
+	free(phdr);
 out:
 	fclose(fp);
 	return ret;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3bbf173ad822..c0ec5ed4f1aa 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1405,6 +1405,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 				goto out_err;
 			}
 		}
+		map__zput(new_node->map);
 		free(new_node);
 	}
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0ffdd52d86d7..309d573eac9a 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -406,7 +406,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
-					struct addr_location *al)
+					bool symbols, struct addr_location *al)
 {
 	size_t i;
 	const u8 cpumodes[] = {
@@ -417,7 +417,11 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_symbol(thread, cpumodes[i], addr, al);
+		if (symbols)
+			thread__find_symbol(thread, cpumodes[i], addr, al);
+		else
+			thread__find_map(thread, cpumodes[i], addr, al);
+
 		if (al->map)
 			break;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 6cbf6eb2812e..1fb32e7d62a4 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -122,7 +122,7 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
 				      u64 addr, struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
-					struct addr_location *al);
+					bool symbols, struct addr_location *al);
 
 int thread__memcpy(struct thread *thread, struct machine *machine,
 		   void *buf, u64 ip, int len, bool *is64bit);