Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

33 files changed, 413 insertions, 210 deletions

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 3b12595193..6bf2468f59 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -71,6 +71,7 @@ counted. The following modifiers exist:
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
  e - group or event are exclusive and do not share the PMU
+ b - use BPF aggregration (see perf stat --bpf-counters)
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 04d89d2ed2..d769aa447f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -458,18 +458,19 @@ SHELL = $(SHELL_PATH)
 
 arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
 ifneq ($(OUTPUT),)
-  arm64_gen_sysreg_outdir := $(OUTPUT)
+  arm64_gen_sysreg_outdir := $(abspath $(OUTPUT))
 else
   arm64_gen_sysreg_outdir := $(CURDIR)
 endif
 
 arm64-sysreg-defs: FORCE
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir)
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
+		prefix= subdir=
 
 arm64-sysreg-defs-clean:
 	$(call QUIET_CLEAN,arm64-sysreg-defs)
 	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
-		clean > /dev/null
+		prefix= subdir= clean > /dev/null
 
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index 49331743c7..a759eb2328 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -362,7 +362,7 @@ static int inject_build_id(struct bench_data *data, u64 *max_rss)
 		return -1;
 
 	for (i = 0; i < nr_mmaps; i++) {
-		int idx = rand() % (nr_dsos - 1);
+		int idx = rand() % nr_dsos;
 		struct bench_dso *dso = &dsos[idx];
 		u64 timestamp = rand() % 1000000;
 
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index 5c71fdc419..b722ff88fe 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -47,7 +47,7 @@ static const char * const bench_uprobe_usage[] = {
 #define bench_uprobe__attach_uprobe(prog) \
 	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
 							   /*pid=*/-1, \
-							   /*binary_path=*/"/lib64/libc.so.6", \
+							   /*binary_path=*/"libc.so.6", \
 							   /*func_offset=*/0, \
 							   /*opts=*/&uprobe_opts); \
 	if (!skel->links.prog) { \
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6c1cc79769..9cd97fd76b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -809,8 +809,6 @@ int cmd_annotate(int argc, const char **argv)
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
-	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
-		    "Show event group information together"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 83954af367..de76bbc50b 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -523,7 +523,7 @@ static int daemon_session__control(struct daemon_session *session,
 		  session->base, SESSION_CONTROL);
 
 	control = open(control_path, O_WRONLY|O_NONBLOCK);
-	if (!control)
+	if (control < 0)
 		return -1;
 
 	if (do_ack) {
@@ -532,7 +532,7 @@ static int daemon_session__control(struct daemon_session *session,
 			  session->base, SESSION_ACK);
 
 		ack = open(ack_path, O_RDONLY, O_NONBLOCK);
-		if (!ack) {
+		if (ack < 0) {
 			close(control);
 			return -1;
 		}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ff7e1d6cfc..45c755fb50 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1355,8 +1355,6 @@ static int record__open(struct record *rec)
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	evlist__config(evlist, opts, &callchain_param);
-
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
@@ -1958,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec)
 
 				if (count.lost) {
 					if (!lost) {
-						lost = zalloc(sizeof(*lost) +
-							      session->machines.host.id_hdr_size);
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 						if (!lost) {
 							pr_debug("Memory allocation failed\n");
 							return;
@@ -1975,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec)
 		lost_count = perf_bpf_filter__lost_count(evsel);
 		if (lost_count) {
 			if (!lost) {
-				lost = zalloc(sizeof(*lost) +
-					      session->machines.host.id_hdr_size);
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 				if (!lost) {
 					pr_debug("Memory allocation failed\n");
 					return;
@@ -2483,6 +2479,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	evlist__uniquify_name(rec->evlist);
 
+	evlist__config(rec->evlist, opts, &callchain_param);
+
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
 	if (record__open(rec) != 0) {
@@ -2881,10 +2879,10 @@ out_delete_session:
 	}
 #endif
 	zstd_fini(&session->zstd_data);
-	perf_session__delete(session);
-
 	if (!opts->no_bpf_event)
 		evlist__stop_sb_thread(rec->sb_evlist);
+
+	perf_session__delete(session);
 	return status;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dcd93ee5fc..5b684d2ab4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -428,7 +428,7 @@ static int report__setup_sample_type(struct report *rep)
 		 * compatibility, set the bit if it's an old perf data file.
 		 */
 		evlist__for_each_entry(session->evlist, evsel) {
-			if (strstr(evsel->name, "arm_spe") &&
+			if (strstr(evsel__name(evsel), "arm_spe") &&
 				!(sample_type & PERF_SAMPLE_DATA_SRC)) {
 				evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC;
 				sample_type |= PERF_SAMPLE_DATA_SRC;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b248c43352..1bfb223473 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2963,8 +2963,11 @@ static int timehist_check_attr(struct perf_sched *sched,
 			return -1;
 		}
 
-		if (sched->show_callchain && !evsel__has_callchain(evsel)) {
-			pr_info("Samples do not have callchains.\n");
+		/* only need to save callchain related to sched_switch event */
+		if (sched->show_callchain &&
+		    evsel__name_is(evsel, "sched:sched_switch") &&
+		    !evsel__has_callchain(evsel)) {
+			pr_info("Samples of sched_switch event do not have callchains.\n");
 			sched->show_callchain = 0;
 			symbol_conf.use_callchain = 0;
 		}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 37088cc0ff..2e7148d667 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3806,7 +3806,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	itrace_parse_synth_opts(opt, "i0ns", 0);
+	itrace_parse_synth_opts(opt, "i0nse", 0);
 	symbol_conf.nanosecs = true;
 	return 0;
 }
diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
index ec2ff78e2b..3ab1d3a663 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
@@ -2,71 +2,71 @@
   {
     "BriefDescription": "Transaction count",
     "MetricName": "transaction",
-    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL if has_event(TX_C_TEND) else 0"
   },
   {
     "BriefDescription": "Cycles per Instruction",
     "MetricName": "cpi",
-    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS"
+    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Problem State Instruction Ratio",
     "MetricName": "prbstate",
-    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100"
+    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Level One Miss per 100 Instructions",
     "MetricName": "l1mp",
-    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100"
+    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 2 cache",
     "MetricName": "l2p",
-    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 3 on same chip cache",
     "MetricName": "l3p",
-    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_CHIP_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Local cache on same book",
     "MetricName": "l4lp",
-    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_DRAWER_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book",
     "MetricName": "l4rp",
-    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_OFF_DRAWER) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
-    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_ON_CHIP_MEMORY) else 0"
   },
   {
     "BriefDescription": "Cycles per Instructions from Finite cache/memory",
     "MetricName": "finite_cpi",
-    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
     "MetricName": "est_cpi",
-    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS) if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
     "MetricName": "scpl1m",
-    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES) if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
     "MetricName": "tlb_percent",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100 if has_event(CPU_CYCLES) else 0"
   },
   {
     "BriefDescription": "Estimated Cycles per TLB Miss",
     "MetricName": "tlb_miss",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) if has_event(DTLB2_MISSES) else 0"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index a918e1af77..b22648d127 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -5,4 +5,4 @@ Family-model,Version,Filename,EventType
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
 ^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
-^IBM.393[12].*3\.7.[[:xdigit:]]+$,3,cf_z16,core
+^IBM.393[12].*$,3,cf_z16,core
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d13ee7683d..e05b370b1e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -274,11 +274,8 @@ static int finish_test(struct child_test *child_test, int width)
 	struct test_suite *t = child_test->test;
 	int i = child_test->test_num;
 	int subi = child_test->subtest;
-	int out = child_test->process.out;
 	int err = child_test->process.err;
-	bool out_done = out <= 0;
 	bool err_done = err <= 0;
-	struct strbuf out_output = STRBUF_INIT;
 	struct strbuf err_output = STRBUF_INIT;
 	int ret;
 
@@ -290,11 +287,9 @@ static int finish_test(struct child_test *child_test, int width)
 		pr_info("%3d: %-*s:\n", i + 1, width, test_description(t, -1));
 
 	/*
-	 * Busy loop reading from the child's stdout and stderr that are set to
-	 * be non-blocking until EOF.
+	 * Busy loop reading from the child's stdout/stderr that are set to be
+	 * non-blocking until EOF.
 	 */
-	if (!out_done)
-		fcntl(out, F_SETFL, O_NONBLOCK);
 	if (!err_done)
 		fcntl(err, F_SETFL, O_NONBLOCK);
 	if (verbose > 1) {
@@ -303,11 +298,8 @@ static int finish_test(struct child_test *child_test, int width)
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
 	}
-	while (!out_done || !err_done) {
-		struct pollfd pfds[2] = {
-			{ .fd = out,
-			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
-			},
+	while (!err_done) {
+		struct pollfd pfds[1] = {
 			{ .fd = err,
 			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
 			},
@@ -317,21 +309,7 @@ static int finish_test(struct child_test *child_test, int width)
 
 		/* Poll to avoid excessive spinning, timeout set for 1000ms. */
 		poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/1000);
-		if (!out_done && pfds[0].revents) {
-			errno = 0;
-			len = read(out, buf, sizeof(buf) - 1);
-
-			if (len <= 0) {
-				out_done = errno != EAGAIN;
-			} else {
-				buf[len] = '\0';
-				if (verbose > 1)
-					fprintf(stdout, "%s", buf);
-				else
-					strbuf_addstr(&out_output, buf);
-			}
-		}
-		if (!err_done && pfds[1].revents) {
+		if (!err_done && pfds[0].revents) {
 			errno = 0;
 			len = read(err, buf, sizeof(buf) - 1);
 
@@ -354,14 +332,10 @@ static int finish_test(struct child_test *child_test, int width)
 			pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi));
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
-		fprintf(stdout, "%s", out_output.buf);
 		fprintf(stderr, "%s", err_output.buf);
 	}
-	strbuf_release(&out_output);
 	strbuf_release(&err_output);
 	print_test_result(t, i, subi, ret, width);
-	if (out > 0)
-		close(out);
 	if (err > 0)
 		close(err);
 	return 0;
@@ -394,6 +368,7 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 		(*child)->process.no_stdout = 1;
 		(*child)->process.no_stderr = 1;
 	} else {
+		(*child)->process.stdout_to_stderr = 1;
 		(*child)->process.out = -1;
 		(*child)->process.err = -1;
 	}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 7a3a7bbbec..29d2f3ee4e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -637,11 +637,11 @@ static int do_test_code_reading(bool try_kcore)
 
 		evlist__config(evlist, &opts, NULL);
 
-		evsel = evlist__first(evlist);
-
-		evsel->core.attr.comm = 1;
-		evsel->core.attr.disabled = 1;
-		evsel->core.attr.enable_on_exec = 0;
+		evlist__for_each_entry(evlist, evsel) {
+			evsel->core.attr.comm = 1;
+			evsel->core.attr.disabled = 1;
+			evsel->core.attr.enable_on_exec = 0;
+		}
 
 		ret = evlist__open(evlist);
 		if (ret < 0) {
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 65dd852071..3302ea0b96 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -188,7 +188,7 @@ arm_cs_etm_snapshot_test() {
 
 arm_cs_etm_basic_test() {
 	echo "Recording trace with '$*'"
-	perf record -o ${perfdata} "$@" -- ls > /dev/null 2>&1
+	perf record -o ${perfdata} "$@" -m,8M -- ls > /dev/null 2>&1
 
 	perf_script_branch_samples ls &&
 	perf_report_branch_samples ls &&
diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c
index ddd40bc634..8e08fc75a9 100644
--- a/tools/perf/tests/workloads/datasym.c
+++ b/tools/perf/tests/workloads/datasym.c
@@ -16,6 +16,22 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused)
 {
 	for (;;) {
 		buf1.data1++;
+		if (buf1.data1 == 123) {
+			/*
+			 * Add some 'noise' in the loop to work around errata
+			 * 1694299 on Arm N1.
+			 *
+			 * Bias exists in SPE sampling which can cause the load
+			 * and store instructions to be skipped entirely. This
+			 * comes and goes randomly depending on the offset the
+			 * linker places the datasym loop at in the Perf binary.
+			 * With an extra branch in the middle of the loop that
+			 * isn't always taken, the instruction stream is no
+			 * longer a continuous repeating pattern that interacts
+			 * badly with the bias.
+			 */
+			buf1.data1++;
+		}
 		buf1.data2 += buf1.data1;
 	}
 	return 0;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 603d11283c..19503e8387 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -203,7 +203,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser)
 void ui_browser__handle_resize(struct ui_browser *browser)
 {
 	ui__refresh_dimensions(false);
-	ui_browser__show(browser, browser->title, ui_helpline__current);
+	ui_browser__show(browser, browser->title ?: "", ui_helpline__current);
 	ui_browser__refresh(browser);
 }
 
@@ -287,7 +287,8 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	mutex_lock(&ui__lock);
 	__ui_browser__show_title(browser, title);
 
-	browser->title = title;
+	free(browser->title);
+	browser->title = strdup(title);
 	zfree(&browser->helpline);
 
 	va_start(ap, helpline);
@@ -304,6 +305,7 @@ void ui_browser__hide(struct ui_browser *browser)
 	mutex_lock(&ui__lock);
 	ui_helpline__pop();
 	zfree(&browser->helpline);
+	zfree(&browser->title);
 	mutex_unlock(&ui__lock);
 }
 
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 510ce45540..6e98d5f8f7 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -21,7 +21,7 @@ struct ui_browser {
 	u8	      extra_title_lines;
 	int	      current_color;
 	void	      *priv;
-	const char    *title;
+	char	      *title;
 	char	      *helpline;
 	const char    *no_samples_msg;
 	void 	      (*refresh_dimensions)(struct ui_browser *browser);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 50ca92255f..79d082155c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -887,10 +887,17 @@ static struct annotated_source *annotated_source__new(void)
 
 static __maybe_unused void annotated_source__delete(struct annotated_source *src)
 {
+	struct hashmap_entry *cur;
+	size_t bkt;
+
 	if (src == NULL)
 		return;
 
-	hashmap__free(src->samples);
+	if (src->samples) {
+		hashmap__for_each_entry(src->samples, cur, bkt)
+			zfree(&cur->pvalue);
+		hashmap__free(src->samples);
+	}
 	zfree(&src->histograms);
 	free(src);
 }
@@ -3025,7 +3032,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 	annotation__update_column_widths(notes);
 }
 
-static void annotation__calc_lines(struct annotation *notes, struct map *map,
+static void annotation__calc_lines(struct annotation *notes, struct map_symbol *ms,
 				   struct rb_root *root)
 {
 	struct annotation_line *al;
@@ -3033,6 +3040,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		double percent_max = 0.0;
+		u64 addr;
 		int i;
 
 		for (i = 0; i < al->data_nr; i++) {
@@ -3048,8 +3056,9 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 		if (percent_max <= 0.5)
 			continue;
 
-		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
-				       false, true, notes->start + al->offset);
+		addr = map__rip_2objdump(ms->map, ms->sym->start);
+		al->path = get_srcline(map__dso(ms->map), addr + al->offset, NULL,
+				       false, true, ms->sym->start + al->offset);
 		insert_source_line(&tmp_root, al);
 	}
 
@@ -3060,7 +3069,7 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root);
+	annotation__calc_lines(notes, ms, root);
 }
 
 int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3684e6009b..ef314a5797 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1466,6 +1466,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 	char *endptr;
 	bool period_type_set = false;
 	bool period_set = false;
+	bool iy = false;
 
 	synth_opts->set = true;
 
@@ -1484,6 +1485,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		switch (*p++) {
 		case 'i':
 		case 'y':
+			iy = true;
 			if (p[-1] == 'y')
 				synth_opts->cycles = true;
 			else
@@ -1649,7 +1651,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		}
 	}
 out:
-	if (synth_opts->instructions || synth_opts->cycles) {
+	if (iy) {
 		if (!period_type_set)
 			synth_opts->period_type =
 					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2791126069..f93e57e2fc 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1136,6 +1136,68 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
+#if defined(HAVE_DWARF_GETLOCATIONS_SUPPORT) || defined(HAVE_DWARF_CFI_SUPPORT)
+static int reg_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+		return op->atom - DW_OP_reg0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->atom - DW_OP_breg0;
+	case DW_OP_regx:
+	case DW_OP_bregx:
+		return op->number;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static int offset_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+	case DW_OP_regx:
+		return 0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->number;
+	case DW_OP_bregx:
+		return op->number2;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
+{
+	/* The first op is checked separately */
+	ops++;
+	nops--;
+
+	/*
+	 * It needs to make sure if the location expression matches to the given
+	 * register and offset exactly.  Thus it rejects any complex expressions
+	 * and only allows a few of selected operators that doesn't change the
+	 * location.
+	 */
+	while (nops) {
+		switch (ops->atom) {
+		case DW_OP_stack_value:
+		case DW_OP_deref_size:
+		case DW_OP_deref:
+		case DW_OP_piece:
+			break;
+		default:
+			return false;
+		}
+		ops++;
+		nops--;
+	}
+	return true;
+}
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT || HAVE_DWARF_CFI_SUPPORT */
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
@@ -1280,7 +1342,7 @@ struct find_var_data {
 #define DWARF_OP_DIRECT_REGS  32
 
 static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
-			     u64 addr_offset, u64 addr_type)
+			     u64 addr_offset, u64 addr_type, bool is_pointer)
 {
 	Dwarf_Die type_die;
 	Dwarf_Word size;
@@ -1294,6 +1356,12 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	if (die_get_real_type(die_mem, &type_die) == NULL)
 		return false;
 
+	if (is_pointer && dwarf_tag(&type_die) == DW_TAG_pointer_type) {
+		/* Get the target type of the pointer */
+		if (die_get_real_type(&type_die, &type_die) == NULL)
+			return false;
+	}
+
 	if (dwarf_aggregate_size(&type_die, &size) < 0)
 		return false;
 
@@ -1305,34 +1373,6 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	return true;
 }
 
-static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
-{
-	/* The first op is checked separately */
-	ops++;
-	nops--;
-
-	/*
-	 * It needs to make sure if the location expression matches to the given
-	 * register and offset exactly.  Thus it rejects any complex expressions
-	 * and only allows a few of selected operators that doesn't change the
-	 * location.
-	 */
-	while (nops) {
-		switch (ops->atom) {
-		case DW_OP_stack_value:
-		case DW_OP_deref_size:
-		case DW_OP_deref:
-		case DW_OP_piece:
-			break;
-		default:
-			return false;
-		}
-		ops++;
-		nops--;
-	}
-	return true;
-}
-
 /* Only checks direct child DIEs in the given scope. */
 static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 {
@@ -1361,31 +1401,38 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
 		    data->offset >= (int)ops->number &&
 		    check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->offset, ops->number))
+		    match_var_offset(die_mem, data, data->offset, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 
 		/* Only match with a simple case */
 		if (data->reg < DWARF_OP_DIRECT_REGS) {
 			/* pointer variables saved in a register 0 to 31 */
 			if (ops->atom == (DW_OP_reg0 + data->reg) &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == (DW_OP_breg0 + data->reg) &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number))
+			    match_var_offset(die_mem, data, data->offset, ops->number,
+					     /*is_pointer=*/false))
 				return DIE_FIND_CB_END;
 		} else {
 			/* pointer variables saved in a register 32 or above */
 			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number2))
+			    match_var_offset(die_mem, data, data->offset, ops->number2,
+					     /*is_poitner=*/false))
 				return DIE_FIND_CB_END;
 		}
 	}
@@ -1447,7 +1494,8 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 			continue;
 
 		if (check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->addr, ops->number))
+		    match_var_offset(die_mem, data, data->addr, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 	}
 	return DIE_FIND_CB_SIBLING;
@@ -1479,41 +1527,69 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
 		*offset = data.offset;
 	return result;
 }
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
-#ifdef HAVE_DWARF_CFI_SUPPORT
-static int reg_from_dwarf_op(Dwarf_Op *op)
+static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-		return op->atom - DW_OP_reg0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->atom - DW_OP_breg0;
-	case DW_OP_regx:
-	case DW_OP_bregx:
-		return op->number;
-	default:
-		break;
-	}
-	return -1;
+	struct die_var_type **var_types = arg;
+	Dwarf_Die type_die;
+	int tag = dwarf_tag(die_mem);
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+	struct die_var_type *vt;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	/*
+	 * Only collect the first location as it can reconstruct the
+	 * remaining state by following the instructions.
+	 * start = 0 means it covers the whole range.
+	 */
+	if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0)
+		return DIE_FIND_CB_SIBLING;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	vt = malloc(sizeof(*vt));
+	if (vt == NULL)
+		return DIE_FIND_CB_END;
+
+	vt->die_off = dwarf_dieoffset(&type_die);
+	vt->addr = start;
+	vt->reg = reg_from_dwarf_op(ops);
+	vt->offset = offset_from_dwarf_op(ops);
+	vt->next = *var_types;
+	*var_types = vt;
+
+	return DIE_FIND_CB_SIBLING;
 }
 
-static int offset_from_dwarf_op(Dwarf_Op *op)
+/**
+ * die_collect_vars - Save all variables and parameters
+ * @sc_die: a scope DIE
+ * @var_types: a pointer to save the resulting list
+ *
+ * Save all variables and parameters in the @sc_die and save them to @var_types.
+ * The @var_types is a singly-linked list containing type and location info.
+ * Actual type can be retrieved using dwarf_offdie() with 'die_off' later.
+ *
+ * Callers should free @var_types.
+ */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-	case DW_OP_regx:
-		return 0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->number;
-	case DW_OP_bregx:
-		return op->number2;
-	default:
-		break;
-	}
-	return -1;
+	Dwarf_Die die_mem;
+
+	die_find_child(sc_die, __die_collect_vars_cb, (void *)var_types, &die_mem);
 }
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
+#ifdef HAVE_DWARF_CFI_SUPPORT
 /**
  * die_get_cfa - Get frame base information
  * @dwarf: a Dwarf info
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 85dd527ae1..efafd3a1f5 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -135,6 +135,15 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 /* Get the list of including scopes */
 int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
 
+/* Variable type information */
+struct die_var_type {
+	struct die_var_type *next;
+	u64 die_off;
+	u64 addr;
+	int reg;
+	int offset;
+};
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */
@@ -150,6 +159,9 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
 				     Dwarf_Addr addr, Dwarf_Die *die_mem,
 				     int *offset);
 
+/* Save all variables and parameters in this scope */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
+
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
@@ -178,6 +190,11 @@ static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unu
 	return NULL;
 }
 
+static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
+				    struct die_var_type **var_types __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #ifdef HAVE_DWARF_CFI_SUPPORT
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index b450178e34..e733f6b1f7 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1319,6 +1319,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder, bool no_tip)
 	bool ret = false;
 
 	decoder->state.type &= ~INTEL_PT_BRANCH;
+	decoder->state.insn_op = INTEL_PT_OP_OTHER;
+	decoder->state.insn_len = 0;
 
 	if (decoder->set_fup_cfe_ip || decoder->set_fup_cfe) {
 		bool ip = decoder->set_fup_cfe_ip;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index f38893e0b0..4db9a098f5 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -764,6 +764,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 	addr_location__init(&al);
 	intel_pt_insn->length = 0;
+	intel_pt_insn->op = INTEL_PT_OP_OTHER;
 
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
@@ -898,6 +899,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 			if (to_ip && *ip == to_ip) {
 				intel_pt_insn->length = 0;
+				intel_pt_insn->op = INTEL_PT_OP_OTHER;
 				goto out_no_cache;
 			}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527517db31..07c22f765f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1549,8 +1549,8 @@ static int machine__update_kernel_mmap(struct machine *machine,
 	updated = map__get(orig);
 
 	machine->vmlinux_map = updated;
-	machine__set_kernel_mmap(machine, start, end);
 	maps__remove(machine__kernel_maps(machine), orig);
+	machine__set_kernel_mmap(machine, start, end);
 	err = maps__insert(machine__kernel_maps(machine), updated);
 	map__put(orig);
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 8f04d3b7f3..59fbbba796 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -7,6 +7,8 @@
 #include <linux/types.h>
 #include <linux/perf_event.h>
 #include "util/evsel_fprintf.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
 #include "trace-event.h"
 
 struct bit_names {
@@ -75,9 +77,12 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 }
 
 #define ENUM_ID_TO_STR_CASE(x) case x: return (#x);
-static const char *stringify_perf_type_id(u64 value)
+static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type)
 {
-	switch (value) {
+	if (pmu)
+		return pmu->name;
+
+	switch (type) {
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT)
@@ -175,9 +180,9 @@ do {								\
 #define print_id_unsigned(_s)	PRINT_ID(_s, "%"PRIu64)
 #define print_id_hex(_s)	PRINT_ID(_s, "%#"PRIx64)
 
-static void __p_type_id(char *buf, size_t size, u64 value)
+static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value)
 {
-	print_id_unsigned(stringify_perf_type_id(value));
+	print_id_unsigned(stringify_perf_type_id(pmu, value));
 }
 
 static void __p_config_hw_id(char *buf, size_t size, u64 value)
@@ -217,8 +222,14 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value)
 }
 #endif
 
-static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
+static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value)
 {
+	const char *name = perf_pmu__name_from_config(pmu, value);
+
+	if (name) {
+		print_id_hex(name);
+		return;
+	}
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
 		return __p_config_hw_id(buf, size, value);
@@ -246,8 +257,8 @@ static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
 #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
 #define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
-#define p_type_id(val)		__p_type_id(buf, BUF_SIZE, val)
-#define p_config_id(val)	__p_config_id(buf, BUF_SIZE, attr->type, val)
+#define p_type_id(val)		__p_type_id(pmu, buf, BUF_SIZE, val)
+#define p_config_id(val)	__p_config_id(pmu, buf, BUF_SIZE, attr->type, val)
 
 #define PRINT_ATTRn(_n, _f, _p, _a)			\
 do {							\
@@ -262,6 +273,7 @@ do {							\
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv)
 {
+	struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 	char buf[BUF_SIZE];
 	int ret = 0;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f39cbbc1a7..cc349d9cb0 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -36,6 +36,18 @@ struct perf_pmu perf_pmu__fake = {
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
 
+enum event_source {
+	/* An event loaded from /sys/devices/<pmu>/events. */
+	EVENT_SRC_SYSFS,
+	/* An event loaded from a CPUID matched json file. */
+	EVENT_SRC_CPU_JSON,
+	/*
+	 * An event loaded from a /sys/devices/<pmu>/identifier matched json
+	 * file.
+	 */
+	EVENT_SRC_SYS_JSON,
+};
+
 /**
  * struct perf_pmu_alias - An event either read from sysfs or builtin in
  * pmu-events.c, created by parsing the pmu-events json files.
@@ -425,9 +437,30 @@ static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
 {
 	struct perf_pmu_alias *alias;
 
-	if (load && !pmu->sysfs_aliases_loaded)
-		pmu_aliases_parse(pmu);
+	if (load && !pmu->sysfs_aliases_loaded) {
+		bool has_sysfs_event;
+		char event_file_name[FILENAME_MAX + 8];
+
+		/*
+		 * Test if alias/event 'name' exists in the PMU's sysfs/events
+		 * directory. If not skip parsing the sysfs aliases. Sysfs event
+		 * name must be all lower or all upper case.
+		 */
+		scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name);
+		for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+			event_file_name[i] = tolower(event_file_name[i]);
+
+		has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
+		if (!has_sysfs_event) {
+			for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+				event_file_name[i] = toupper(event_file_name[i]);
+
+			has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
+		}
+		if (has_sysfs_event)
+			pmu_aliases_parse(pmu);
 
+	}
 	list_for_each_entry(alias, &pmu->aliases, list) {
 		if (!strcasecmp(alias->name, name))
 			return alias;
@@ -500,7 +533,7 @@ static int update_alias(const struct pmu_event *pe,
 
 static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
-				const struct pmu_event *pe)
+			        const struct pmu_event *pe, enum event_source src)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -552,25 +585,30 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		}
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
-	if (!pe) {
-		/* Update an event from sysfs with json data. */
-		struct update_alias_data data = {
-			.pmu = pmu,
-			.alias = alias,
-		};
-
+	switch (src) {
+	default:
+	case EVENT_SRC_SYSFS:
 		alias->from_sysfs = true;
 		if (pmu->events_table) {
+			/* Update an event from sysfs with json data. */
+			struct update_alias_data data = {
+				.pmu = pmu,
+				.alias = alias,
+			};
 			if (pmu_events_table__find_event(pmu->events_table, pmu, name,
 							 update_alias, &data) == 0)
-				pmu->loaded_json_aliases++;
+				pmu->cpu_json_aliases++;
 		}
-	}
-
-	if (!pe)
 		pmu->sysfs_aliases++;
-	else
-		pmu->loaded_json_aliases++;
+		break;
+	case  EVENT_SRC_CPU_JSON:
+		pmu->cpu_json_aliases++;
+		break;
+	case  EVENT_SRC_SYS_JSON:
+		pmu->sys_json_aliases++;
+		break;
+
+	}
 	list_add_tail(&alias->list, &pmu->aliases);
 	return 0;
 }
@@ -646,7 +684,8 @@ static int pmu_aliases_parse(struct perf_pmu *pmu)
 		}
 
 		if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL,
-					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
+					/*val=*/ NULL, file, /*pe=*/ NULL,
+					EVENT_SRC_SYSFS) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
@@ -900,7 +939,8 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 {
 	struct perf_pmu *pmu = vdata;
 
-	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
+	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL,
+			    pe, EVENT_SRC_CPU_JSON);
 	return 0;
 }
 
@@ -935,13 +975,14 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 		return 0;
 
 	if (pmu_uncore_alias_match(pe->pmu, pmu->name) &&
-			pmu_uncore_identifier_match(pe->compat, pmu->id)) {
+	    pmu_uncore_identifier_match(pe->compat, pmu->id)) {
 		perf_pmu__new_alias(pmu,
 				pe->name,
 				pe->desc,
 				pe->event,
 				/*val_fd=*/ NULL,
-				pe);
+				pe,
+				EVENT_SRC_SYS_JSON);
 	}
 
 	return 0;
@@ -1035,6 +1076,12 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
 	pmu->alias_name = pmu_find_alias_name(pmu, dirfd);
 	pmu->events_table = perf_pmu__find_events_table(pmu);
+	/*
+	 * Load the sys json events/aliases when loading the PMU as each event
+	 * may have a different compat regular expression. We therefore can't
+	 * know the number of sys json events/aliases without computing the
+	 * regular expressions for them all.
+	 */
 	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
 
@@ -1632,15 +1679,15 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
 	size_t nr;
 
-	if (!pmu->sysfs_aliases_loaded)
-		pmu_aliases_parse(pmu);
-
-	nr = pmu->sysfs_aliases;
+	pmu_aliases_parse(pmu);
+	nr = pmu->sysfs_aliases + pmu->sys_json_aliases;;
 
 	if (pmu->cpu_aliases_added)
-		 nr += pmu->loaded_json_aliases;
+		 nr += pmu->cpu_json_aliases;
 	else if (pmu->events_table)
-		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases;
+		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases;
+	else
+		assert(pmu->cpu_json_aliases == 0);
 
 	return pmu->selectable ? nr + 1 : nr;
 }
@@ -1693,6 +1740,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	struct strbuf sb;
 
 	strbuf_init(&sb, /*hint=*/ 0);
+	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
@@ -2085,3 +2133,22 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->id);
 	free(pmu);
 }
+
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
+{
+	struct perf_pmu_alias *event;
+
+	if (!pmu)
+		return NULL;
+
+	pmu_aliases_parse(pmu);
+	pmu_add_cpu_aliases(pmu);
+	list_for_each_entry(event, &pmu->aliases, list) {
+		struct perf_event_attr attr = {.config = 0,};
+		int ret = perf_pmu__config(pmu, &attr, &event->terms, NULL);
+
+		if (ret == 0 && config == attr.config)
+			return event->name;
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index e35d985206..77c59ebc05 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,8 +123,10 @@ struct perf_pmu {
 	const struct pmu_events_table *events_table;
 	/** @sysfs_aliases: Number of sysfs aliases loaded. */
 	uint32_t sysfs_aliases;
-	/** @sysfs_aliases: Number of json event aliases loaded. */
-	uint32_t loaded_json_aliases;
+	/** @cpu_json_aliases: Number of json event aliases loaded specific to the CPUID. */
+	uint32_t cpu_json_aliases;
+	/** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */
+	uint32_t sys_json_aliases;
 	/** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */
 	bool sysfs_aliases_loaded;
 	/**
@@ -273,5 +275,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2a0ad9ecf0..5c12459e97 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -11,6 +11,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <libgen.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 075c0f79b1..0aeb97c11c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -103,6 +103,16 @@ int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char
 	return EOF;
 }
 
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused)
+{
+	return NULL;
+}
+
+struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused)
+{
+	return NULL;
+}
+
 int perf_pmus__num_core_pmus(void)
 {
 	return 1;
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bfc1d705f4..91d2f7f65d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -1223,6 +1223,9 @@ static void print_metric_headers(struct perf_stat_config *config,
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evlist, counter) {
+		if (config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
+			continue;
+
 		os.evsel = counter;
 
 		perf_stat__print_shadow_stats(config, counter, 0,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 9ebdb8e13c..68dbeae8d2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1287,7 +1287,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 {
 	struct maps *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
-	struct map *replacement_map = NULL;
+	struct map *map_ref, *replacement_map = NULL;
 	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
@@ -1365,6 +1365,24 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	if (!replacement_map)
 		replacement_map = list_entry(md.maps.next, struct map_list_node, node)->map;
 
+	/*
+	 * Update addresses of vmlinux map. Re-insert it to ensure maps are
+	 * correctly ordered. Do this before using maps__merge_in() for the
+	 * remaining maps so vmlinux gets split if necessary.
+	 */
+	map_ref = map__get(map);
+	maps__remove(kmaps, map_ref);
+
+	map__set_start(map_ref, map__start(replacement_map));
+	map__set_end(map_ref, map__end(replacement_map));
+	map__set_pgoff(map_ref, map__pgoff(replacement_map));
+	map__set_mapping_type(map_ref, map__mapping_type(replacement_map));
+
+	err = maps__insert(kmaps, map_ref);
+	map__put(map_ref);
+	if (err)
+		goto out_err;
+
 	/* Add new maps */
 	while (!list_empty(&md.maps)) {
 		struct map_list_node *new_node = list_entry(md.maps.next, struct map_list_node, node);
@@ -1372,22 +1390,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 		list_del_init(&new_node->node);
 
-		if (RC_CHK_EQUAL(new_map, replacement_map)) {
-			struct map *map_ref;
-
-			map__set_start(map, map__start(new_map));
-			map__set_end(map, map__end(new_map));
-			map__set_pgoff(map, map__pgoff(new_map));
-			map__set_mapping_type(map, map__mapping_type(new_map));
-			/* Ensure maps are correctly ordered */
-			map_ref = map__get(map);
-			maps__remove(kmaps, map_ref);
-			err = maps__insert(kmaps, map_ref);
-			map__put(map_ref);
-			map__put(new_map);
-			if (err)
-				goto out_err;
-		} else {
+		/* skip if replacement_map, already inserted above */
+		if (!RC_CHK_EQUAL(new_map, replacement_map)) {
 			/*
 			 * Merge kcore map into existing maps,
 			 * and ensure that current maps (eBPF)
@@ -1969,6 +1973,10 @@ out:
 	return ret;
 }
 
+/*
+ * Always takes ownership of vmlinux when vmlinux_allocated == true, even if
+ * it returns an error.
+ */
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated)
 {
@@ -1987,8 +1995,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	else
 		symtab_type = DSO_BINARY_TYPE__VMLINUX;
 
-	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
+	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) {
+		if (vmlinux_allocated)
+			free((char *) vmlinux);
 		return -1;
+	}
 
 	/*
 	 * dso__load_sym() may copy 'dso' which will result in the copies having
@@ -2031,7 +2042,6 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map)
 		err = dso__load_vmlinux(dso, map, filename, true);
 		if (err > 0)
 			goto out;
-		free(filename);
 	}
 out:
 	return err;
@@ -2183,7 +2193,6 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
 		err = dso__load_vmlinux(dso, map, filename, true);
 		if (err > 0)
 			return err;
-		free(filename);
 	}
 
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1aa8962dcf..515726489e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -39,12 +39,13 @@ int thread__init_maps(struct thread *thread, struct machine *machine)
 
 struct thread *thread__new(pid_t pid, pid_t tid)
 {
-	char *comm_str;
-	struct comm *comm;
 	RC_STRUCT(thread) *_thread = zalloc(sizeof(*_thread));
 	struct thread *thread;
 
 	if (ADD_RC_CHK(thread, _thread) != NULL) {
+		struct comm *comm;
+		char comm_str[32];
+
 		thread__set_pid(thread, pid);
 		thread__set_tid(thread, tid);
 		thread__set_ppid(thread, -1);
@@ -56,13 +57,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		init_rwsem(thread__namespaces_lock(thread));
 		init_rwsem(thread__comm_lock(thread));
 
-		comm_str = malloc(32);
-		if (!comm_str)
-			goto err_thread;
-
-		snprintf(comm_str, 32, ":%d", tid);
+		snprintf(comm_str, sizeof(comm_str), ":%d", tid);
 		comm = comm__new(comm_str, 0, false);
-		free(comm_str);
 		if (!comm)
 			goto err_thread;
 
@@ -76,7 +72,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 	return thread;
 
 err_thread:
-	free(thread);
+	thread__delete(thread);
 	return NULL;
 }