Merge tag 'perf-core-for-mingo-5.7-20200317' of...

Merge tag 'perf-core-for-mingo-5.7-20200317' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf record:

  Alexey Budankov:

  - Fix binding of AIO user space buffers to nodes

maps:

  Dominik b. Czarnota:

  - Fix off by one in strncpy() size argument.

  Arnaldo Carvalho de Melo:

  - Use strstarts() to look for Android libraries.

  Ian Rogers:

  - Give synthetic mmap events an inode generation.

man pages:

  Ian Rogers:

  - Set man page date to last git commit.

perf test:

  Ian Rogers:

  - Print if shell directory isn't present.

perf report:

  Jin Yao:

  - Fix no branch type statistics report issue.

perf expr:

  Jiri Olsa:

  - Fix copy/paste mistake

vendor events:

  Kan Liang:

  - Support metric constraints.

vendor events intel:

  Kan Liang:

  - Add NO_NMI_WATCHDOG metric constraint.

vendor events s390:

  Thomas Richter:

 - Add new deflate counters for IBM z15.

ARM cs-etm:

  Leo Yan:

  - Last branch improvements.

intel-pt:

  Adrian Hunter:

  - Update intel-pt.txt file with new location of the documentation.

  - Add Intel PT man page references.

  - Rename intel-pt.txt and put it in man page format.

perl scripting:

  Michael Petlan:

 - Add common_callchain to fix argument order.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Conflicts:
	tools/perf/util/map.c

tools/perf/Documentation/Makefile

@@ -295,7 +295,10 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 $(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b docbook -d manpage \
-		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
+		-aperf_date=$(shell git log -1 --pretty="format:%cd" \
+				--date=short $<) \
+		-o $@+ $< && \
 	mv $@+ $@
 
 XSLT = docbook.xsl

tools/perf/Documentation/perf-inject.txt

@@ -66,4 +66,5 @@ include::itrace.txt[]
 
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1],
+linkperf:perf-intel-pt[1]

tools/perf/Documentation/perf-record.txt

@@ -589,4 +589,4 @@ appended unit character - B/K/M/G
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]

tools/perf/Documentation/perf-report.txt

@@ -546,4 +546,5 @@ include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1],
+linkperf:perf-intel-pt[1]

tools/perf/Documentation/perf-script.txt

@@ -429,4 +429,4 @@ include::itrace.txt[]
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-script-python[1]
+linkperf:perf-script-python[1], linkperf:perf-intel-pt[1]

tools/perf/builtin-report.c

@@ -186,24 +186,23 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 {
 	struct hist_entry *he = iter->he;
 	struct report *rep = arg;
-	struct branch_info *bi;
+	struct branch_info *bi = he->branch_info;
 	struct perf_sample *sample = iter->sample;
 	struct evsel *evsel = iter->evsel;
 	int err;
 
+	branch_type_count(&rep->brtype_stat, &bi->flags,
+			  bi->from.addr, bi->to.addr);
+
 	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
-	bi = he->branch_info;
 	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel);
 	if (err)
 		goto out;
 
 	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel);
 
-	branch_type_count(&rep->brtype_stat, &bi->flags,
-			  bi->from.addr, bi->to.addr);
-
 out:
 	return err;
 }

tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json

@@ -4,27 +4,27 @@
 		"EventCode": "80",
 		"EventName": "ECC_FUNCTION_COUNT",
 		"BriefDescription": "ECC Function Count",
-		"PublicDescription": "Long ECC function Count"
+		"PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions issued by the CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "81",
 		"EventName": "ECC_CYCLES_COUNT",
 		"BriefDescription": "ECC Cycles Count",
-		"PublicDescription": "Long ECC Function cycles count"
+		"PublicDescription": "This counter counts the total number of CPU cycles when the ECC coprocessor is busy performing the elliptic-curve cryptography (ECC) functions issued by the CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "82",
 		"EventName": "ECC_BLOCKED_FUNCTION_COUNT",
 		"BriefDescription": "Ecc Blocked Function Count",
-		"PublicDescription": "Long ECC blocked function count"
+		"PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions that are issued by the CPU and are blocked because the ECC coprocessor is busy performing a function issued by another CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "83",
 		"EventName": "ECC_BLOCKED_CYCLES_COUNT",
 		"BriefDescription": "ECC Blocked Cycles Count",
-		"PublicDescription": "Long ECC blocked cycles count"
+		"PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU."
 	},
 ]

tools/perf/pmu-events/arch/s390/cf_z15/extended.json

@@ -25,7 +25,7 @@
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
-		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page"
 	},
 	{
 		"Unit": "CPU-M-CF",
@@ -356,6 +356,34 @@
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "247",
+		"EventName": "DFLT_ACCESS",
+		"BriefDescription": "Cycles CPU spent obtaining access to Deflate unit",
+		"PublicDescription": "Cycles CPU spent obtaining access to Deflate unit"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "252",
+		"EventName": "DFLT_CYCLES",
+		"BriefDescription": "Cycles CPU is using Deflate unit",
+		"PublicDescription": "Cycles CPU is using Deflate unit"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "264",
+		"EventName": "DFLT_CC",
+		"BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed",
+		"PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "265",
+		"EventName": "DFLT_CCERROR",
+		"BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2",
+		"PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2"
+	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "448",

tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json

@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",

tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json

@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",

tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json

@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",

tools/perf/pmu-events/jevents.c

@@ -323,7 +323,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
 				    char *pmu, char *unit, char *perpkg,
 				    char *metric_expr,
 				    char *metric_name, char *metric_group,
-				    char *deprecated)
+				    char *deprecated, char *metric_constraint)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -357,6 +357,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
 	if (deprecated)
 		fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated);
+	if (metric_constraint)
+		fprintf(outfp, "\t.metric_constraint = \"%s\",\n", metric_constraint);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -375,6 +377,7 @@ struct event_struct {
 	char *metric_name;
 	char *metric_group;
 	char *deprecated;
+	char *metric_constraint;
 };
 
 #define ADD_EVENT_FIELD(field) do { if (field) {		\
@@ -422,7 +425,7 @@ static int save_arch_std_events(void *data, char *name, char *event,
 				char *desc, char *long_desc, char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
 				char *metric_name, char *metric_group,
-				char *deprecated)
+				char *deprecated, char *metric_constraint)
 {
 	struct event_struct *es;
 
@@ -486,7 +489,7 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc,
 	  char **name, char **long_desc, char **pmu, char **filter,
 	  char **perpkg, char **unit, char **metric_expr, char **metric_name,
 	  char **metric_group, unsigned long long eventcode,
-	  char **deprecated)
+	  char **deprecated, char **metric_constraint)
 {
 	/* try to find matching event from arch standard values */
 	struct event_struct *es;
@@ -515,7 +518,7 @@ int json_events(const char *fn,
 		      char *pmu, char *unit, char *perpkg,
 		      char *metric_expr,
 		      char *metric_name, char *metric_group,
-		      char *deprecated),
+		      char *deprecated, char *metric_constraint),
 	  void *data)
 {
 	int err;
@@ -545,6 +548,7 @@ int json_events(const char *fn,
 		char *metric_name = NULL;
 		char *metric_group = NULL;
 		char *deprecated = NULL;
+		char *metric_constraint = NULL;
 		char *arch_std = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
@@ -629,6 +633,8 @@ int json_events(const char *fn,
 				addfield(map, &metric_name, "", "", val);
 			} else if (json_streq(map, field, "MetricGroup")) {
 				addfield(map, &metric_group, "", "", val);
+			} else if (json_streq(map, field, "MetricConstraint")) {
+				addfield(map, &metric_constraint, "", "", val);
 			} else if (json_streq(map, field, "MetricExpr")) {
 				addfield(map, &metric_expr, "", "", val);
 				for (s = metric_expr; *s; s++)
@@ -670,13 +676,13 @@ int json_events(const char *fn,
 					&long_desc, &pmu, &filter, &perpkg,
 					&unit, &metric_expr, &metric_name,
 					&metric_group, eventcode,
-					&deprecated);
+					&deprecated, &metric_constraint);
 			if (err)
 				goto free_strings;
 		}
 		err = func(data, name, real_event(name, event), desc, long_desc,
 			   pmu, unit, perpkg, metric_expr, metric_name,
-			   metric_group, deprecated);
+			   metric_group, deprecated, metric_constraint);
 free_strings:
 		free(event);
 		free(desc);
@@ -691,6 +697,7 @@ int json_events(const char *fn,
 		free(metric_expr);
 		free(metric_name);
 		free(metric_group);
+		free(metric_constraint);
 		free(arch_std);
 
 		if (err)

tools/perf/pmu-events/jevents.h

@@ -8,7 +8,7 @@ int json_events(const char *fn,
 				char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
 				char *metric_name, char *metric_group,
-				char *deprecated),
+				char *deprecated, char *metric_constraint),
 		void *data);
 char *get_cpu_str(void);
 

tools/perf/pmu-events/pmu-events.h

@@ -18,6 +18,7 @@ struct pmu_event {
 	const char *metric_name;
 	const char *metric_group;
 	const char *deprecated;
+	const char *metric_constraint;
 };
 
 /*

tools/perf/scripts/perl/check-perf-trace.pl

@@ -28,7 +28,7 @@ sub trace_end
 sub irq::softirq_entry
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $vec) = @_;
 
 	print_header($event_name, $common_cpu, $common_secs, $common_nsecs,
@@ -43,7 +43,7 @@ sub irq::softirq_entry
 sub kmem::kmalloc
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $call_site, $ptr, $bytes_req, $bytes_alloc,
 	    $gfp_flags) = @_;
 
@@ -92,7 +92,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }

tools/perf/scripts/perl/failed-syscalls.pl

@@ -18,7 +18,7 @@ my %failed_syscalls;
 sub raw_syscalls::sys_exit
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $id, $ret) = @_;
 
 	if ($ret < 0) {

tools/perf/scripts/perl/rw-by-file.pl

@@ -28,7 +28,7 @@ my %writes;
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
 
     if ($common_comm eq $for_comm) {
 	$reads{$fd}{bytes_requested} += $count;
@@ -39,7 +39,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
 
     if ($common_comm eq $for_comm) {
 	$writes{$fd}{bytes_written} += $count;
@@ -98,7 +98,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }

tools/perf/scripts/perl/rw-by-pid.pl

@@ -24,7 +24,7 @@ my %writes;
 sub syscalls::sys_exit_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     if ($ret > 0) {
@@ -40,7 +40,7 @@ sub syscalls::sys_exit_read
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     $reads{$common_pid}{bytes_requested} += $count;
@@ -51,7 +51,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_exit_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     if ($ret <= 0) {
@@ -62,7 +62,7 @@ sub syscalls::sys_exit_write
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     $writes{$common_pid}{bytes_written} += $count;
@@ -178,7 +178,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }

tools/perf/scripts/perl/rwtop.pl

@@ -35,7 +35,7 @@ if (!$interval) {
 sub syscalls::sys_exit_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     print_check();
@@ -53,7 +53,7 @@ sub syscalls::sys_exit_read
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     print_check();
@@ -66,7 +66,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_exit_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     print_check();
@@ -79,7 +79,7 @@ sub syscalls::sys_exit_write
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     print_check();
@@ -197,7 +197,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }

tools/perf/scripts/perl/wakeup-latency.pl

@@ -28,7 +28,7 @@ my $total_wakeups = 0;
 sub sched::sched_switch
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$prev_comm, $prev_pid, $prev_prio, $prev_state, $next_comm, $next_pid,
 	$next_prio) = @_;
 
@@ -51,7 +51,7 @@ sub sched::sched_switch
 sub sched::sched_wakeup
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$comm, $pid, $prio, $success, $target_cpu) = @_;
 
     $last_wakeup{$target_cpu}{ts} = nsecs($common_secs, $common_nsecs);
@@ -101,7 +101,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }

tools/perf/tests/builtin-test.c

@@ -543,8 +543,11 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width)
 		return -1;
 
 	dir = opendir(st.dir);
-	if (!dir)
+	if (!dir) {
+		pr_err("failed to open shell test directory: %s\n",
+			st.dir);
 		return -1;
+	}
 
 	for_each_shell_test(dir, st.dir, ent) {
 		int curr = i++;

tools/perf/util/cs-etm.c

@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
 	return NULL;
 }
 
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+				struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *tmp;
+
+	if (etm->sample_branches || etm->synth_opts.last_branch ||
+	    etm->sample_instructions) {
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
+	}
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -945,7 +962,7 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
 	if (packet->isa == CS_ETM_ISA_T32) {
 		u64 addr = packet->start_addr;
 
-		while (offset > 0) {
+		while (offset) {
 			addr += cs_etm__t32_instr_size(etmq,
 						       trace_chan_id, addr);
 			offset--;
@@ -1134,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
 
-	if (etm->synth_opts.last_branch) {
-		cs_etm__copy_last_branch_rb(etmq, tidq);
+	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
-	}
 
 	if (etm->synth_opts.inject) {
 		ret = cs_etm__inject_event(event, &sample,
@@ -1153,9 +1168,6 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 			"CS ETM Trace: failed to deliver instruction event, error %d\n",
 			ret);
 
-	if (etm->synth_opts.last_branch)
-		cs_etm__reset_last_branch_rb(tidq);
-
 	return ret;
 }
 
@@ -1342,12 +1354,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
-	u64 instrs_executed = tidq->packet->instr_count;
+	u64 instrs_prev;
+
+	/* Get instructions remainder from previous packet */
+	instrs_prev = tidq->period_instructions;
 
-	tidq->period_instructions += instrs_executed;
+	tidq->period_instructions += tidq->packet->instr_count;
 
 	/*
 	 * Record a branch when the last instruction in
@@ -1365,26 +1379,80 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
-		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = tidq->period_instructions -
-			etm->instructions_sample_period;
+		/*
+		 * Below diagram demonstrates the instruction samples
+		 * generation flows:
+		 *
+		 *    Instrs     Instrs       Instrs       Instrs
+		 *   Sample(n)  Sample(n+1)  Sample(n+2)  Sample(n+3)
+		 *    |            |            |            |
+		 *    V            V            V            V
+		 *   --------------------------------------------------
+		 *            ^                                  ^
+		 *            |                                  |
+		 *         Period                             Period
+		 *    instructions(Pi)                   instructions(Pi')
+		 *
+		 *            |                                  |
+		 *            \---------------- -----------------/
+		 *                             V
+		 *                 tidq->packet->instr_count
+		 *
+		 * Instrs Sample(n...) are the synthesised samples occurring
+		 * every etm->instructions_sample_period instructions - as
+		 * defined on the perf command line.  Sample(n) is being the
+		 * last sample before the current etm packet, n+1 to n+3
+		 * samples are generated from the current etm packet.
+		 *
+		 * tidq->packet->instr_count represents the number of
+		 * instructions in the current etm packet.
+		 *
+		 * Period instructions (Pi) contains the the number of
+		 * instructions executed after the sample point(n) from the
+		 * previous etm packet.  This will always be less than
+		 * etm->instructions_sample_period.
+		 *
+		 * When generate new samples, it combines with two parts
+		 * instructions, one is the tail of the old packet and another
+		 * is the head of the new coming packet, to generate
+		 * sample(n+1); sample(n+2) and sample(n+3) consume the
+		 * instructions with sample period.  After sample(n+3), the rest
+		 * instructions will be used by later packet and it is assigned
+		 * to tidq->period_instructions for next round calculation.
+		 */
 
 		/*
-		 * Calculate the address of the sampled instruction (-1 as
-		 * sample is reported as though instruction has just been
-		 * executed, but PC has not advanced to next instruction)
+		 * Get the initial offset into the current packet instructions;
+		 * entry conditions ensure that instrs_prev is less than
+		 * etm->instructions_sample_period.
 		 */
-		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
-					      tidq->packet, offset);
+		u64 offset = etm->instructions_sample_period - instrs_prev;
+		u64 addr;
 
-		ret = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr, etm->instructions_sample_period);
-		if (ret)
-			return ret;
+		/* Prepare last branches for instruction sample */
+		if (etm->synth_opts.last_branch)
+			cs_etm__copy_last_branch_rb(etmq, tidq);
 
-		/* Carry remaining instructions into next sample period */
-		tidq->period_instructions = instrs_over;
+		while (tidq->period_instructions >=
+				etm->instructions_sample_period) {
+			/*
+			 * Calculate the address of the sampled instruction (-1
+			 * as sample is reported as though instruction has just
+			 * been executed, but PC has not advanced to next
+			 * instruction)
+			 */
+			addr = cs_etm__instr_addr(etmq, trace_chan_id,
+						  tidq->packet, offset - 1);
+			ret = cs_etm__synth_instruction_sample(
+				etmq, tidq, addr,
+				etm->instructions_sample_period);
+			if (ret)
+				return ret;
+
+			offset += etm->instructions_sample_period;
+			tidq->period_instructions -=
+				etm->instructions_sample_period;
+		}
 	}
 
 	if (etm->sample_branches) {
@@ -1406,15 +1474,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return 0;
 }
@@ -1443,7 +1503,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 
 	/* Handle start tracing packet */
 	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1451,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -1458,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
@@ -1478,15 +1542,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	}
 
 swap_packet:
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
+
+	/* Reset last branches after flush the trace */
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(tidq);
 
 	return err;
 }
@@ -1507,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Use the address of the end of the last reported execution
 		 * range.
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,

tools/perf/util/expr.l

@@ -79,10 +79,10 @@ symbol		{spec}*{sym}*{spec}*{sym}*
 	{
 		int start_token;
 
-		start_token = parse_events_get_extra(yyscanner);
+		start_token = expr_get_extra(yyscanner);
 
 		if (start_token) {
-			parse_events_set_extra(NULL, yyscanner);
+			expr_set_extra(NULL, yyscanner);
 			return start_token;
 		}
 	}

tools/perf/util/map.c

@@ -44,8 +44,8 @@ static inline int is_no_dso_memory(const char *filename)
 
 static inline int is_android_lib(const char *filename)
 {
-	return !strncmp(filename, "/data/app-lib", 13) ||
-	       !strncmp(filename, "/system/lib", 11);
+	return strstarts(filename, "/data/app-lib/") ||
+	       strstarts(filename, "/system/lib/");
 }
 
 static inline bool replace_android_lib(const char *filename, char *newfilename)
@@ -65,7 +65,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 
 	app_abi_length = strlen(app_abi);
 
-	if (!strncmp(filename, "/data/app-lib", 13)) {
+	if (strstarts(filename, "/data/app-lib/")) {
 		char *apk_path;
 
 		if (!app_abi_length)
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 12)) {
+	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;

tools/perf/util/metricgroup.c

@@ -22,6 +22,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
+#include <api/fs/fs.h>
+#include "util.h"
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
@@ -399,13 +401,85 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	strlist__delete(metriclist);
 }
 
+static void metricgroup__add_metric_weak_group(struct strbuf *events,
+					       const char **ids,
+					       int idnum)
+{
+	bool no_group = false;
+	int i;
+
+	for (i = 0; i < idnum; i++) {
+		pr_debug("found event %s\n", ids[i]);
+		/*
+		 * Duration time maps to a software event and can make
+		 * groups not count. Always use it outside a
+		 * group.
+		 */
+		if (!strcmp(ids[i], "duration_time")) {
+			if (i > 0)
+				strbuf_addf(events, "}:W,");
+			strbuf_addf(events, "duration_time");
+			no_group = true;
+			continue;
+		}
+		strbuf_addf(events, "%s%s",
+			i == 0 || no_group ? "{" : ",",
+			ids[i]);
+		no_group = false;
+	}
+	if (!no_group)
+		strbuf_addf(events, "}:W");
+}
+
+static void metricgroup__add_metric_non_group(struct strbuf *events,
+					      const char **ids,
+					      int idnum)
+{
+	int i;
+
+	for (i = 0; i < idnum; i++)
+		strbuf_addf(events, ",%s", ids[i]);
+}
+
+static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
+{
+	static bool violate_nmi_constraint;
+
+	if (!foot) {
+		pr_warning("Splitting metric group %s into standalone metrics.\n", name);
+		violate_nmi_constraint = true;
+		return;
+	}
+
+	if (!violate_nmi_constraint)
+		return;
+
+	pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
+		   "    echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+		   "    perf stat ...\n"
+		   "    echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+static bool metricgroup__has_constraint(struct pmu_event *pe)
+{
+	if (!pe->metric_constraint)
+		return false;
+
+	if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
+	    sysctl__nmi_watchdog_enabled()) {
+		metricgroup___watchdog_constraint_hint(pe->metric_name, false);
+		return true;
+	}
+
+	return false;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
-	int ret = -EINVAL;
-	int i, j;
+	int i, ret = -EINVAL;
 
 	if (!map)
 		return 0;
@@ -422,7 +496,6 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			const char **ids;
 			int idnum;
 			struct egroup *eg;
-			bool no_group = false;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
@@ -431,27 +504,11 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				continue;
 			if (events->len > 0)
 				strbuf_addf(events, ",");
-			for (j = 0; j < idnum; j++) {
-				pr_debug("found event %s\n", ids[j]);
-				/*
-				 * Duration time maps to a software event and can make
-				 * groups not count. Always use it outside a
-				 * group.
-				 */
-				if (!strcmp(ids[j], "duration_time")) {
-					if (j > 0)
-						strbuf_addf(events, "}:W,");
-					strbuf_addf(events, "duration_time");
-					no_group = true;
-					continue;
-				}
-				strbuf_addf(events, "%s%s",
-					j == 0 || no_group ? "{" : ",",
-					ids[j]);
-				no_group = false;
-			}
-			if (!no_group)
-				strbuf_addf(events, "}:W");
+
+			if (metricgroup__has_constraint(pe))
+				metricgroup__add_metric_non_group(events, ids, idnum);
+			else
+				metricgroup__add_metric_weak_group(events, ids, idnum);
 
 			eg = malloc(sizeof(struct egroup));
 			if (!eg) {
@@ -493,6 +550,10 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
 		}
 	}
 	free(nlist);
+
+	if (!ret)
+		metricgroup___watchdog_constraint_hint(NULL, true);
+
 	return ret;
 }
 

tools/perf/util/mmap.c

@@ -98,20 +98,29 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 {
 	void *data;
 	size_t mmap_len;
-	unsigned long node_mask;
+	unsigned long *node_mask;
+	unsigned long node_index;
+	int err = 0;
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
 		data = map->aio.data[idx];
 		mmap_len = mmap__mmap_len(map);
-		node_mask = 1UL << cpu__get_node(cpu);
-		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
-			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
-				data, data + mmap_len, cpu__get_node(cpu));
+		node_index = cpu__get_node(cpu);
+		node_mask = bitmap_alloc(node_index + 1);
+		if (!node_mask) {
+			pr_err("Failed to allocate node mask for mbind: error %m\n");
 			return -1;
 		}
+		set_bit(node_index, node_mask);
+		if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
+				data, data + mmap_len, node_index);
+			err = -1;
+		}
+		bitmap_free(node_mask);
 	}
 
-	return 0;
+	return err;
 }
 #else /* !HAVE_LIBNUMA_SUPPORT */
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)

tools/perf/util/stat-display.c

@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include "cgroup.h"
 #include <api/fs/fs.h>
+#include "util.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
-	int n;
 
 	if (!config->null_run)
 		fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
+	if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"

tools/perf/util/synthetic-events.c

@@ -345,6 +345,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			continue;
 
 		event->mmap2.ino = (u64)ino;
+		event->mmap2.ino_generation = 0;
 
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c

tools/perf/util/util.c

@@ -55,6 +55,24 @@ int sysctl__max_stack(void)
 	return sysctl_perf_event_max_stack;
 }
 
+bool sysctl__nmi_watchdog_enabled(void)
+{
+	static bool cached;
+	static bool nmi_watchdog;
+	int value;
+
+	if (cached)
+		return nmi_watchdog;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+		return false;
+
+	nmi_watchdog = (value > 0) ? true : false;
+	cached = true;
+
+	return nmi_watchdog;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;

tools/perf/util/util.h

@@ -29,6 +29,8 @@ size_t hex_width(u64 v);
 
 int sysctl__max_stack(void);
 
+bool sysctl__nmi_watchdog_enabled(void);
+
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
 #define KVER_VERSION(x)		(((x) >> 16) & 0xff)