Merge tag 'perf-tools-fixes-for-v6.0-2022-08-27' of git://git.kernel.…

…org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fixup setup of weak groups when using 'perf stat --repeat', add a
   'perf test' for it.

 - Fix memory leaks in 'perf sched record' detected with
   -fsanitize=address.

 - Fix build when PYTHON_CONFIG is user supplied.

 - Capitalize topdown metrics' names in 'perf stat', so that the output,
   sometimes parsed, matches the Intel SDM docs.

 - Make sure the documentation for the save_type filter about Intel
   systems with Arch LBR support (12th-Gen+ client or 4th-Gen Xeon+
   server) reflects recent related kernel changes.

 - Fix 'perf record' man page formatting of description of support to
   hybrid systems.

 - Update arm64´s KVM header from the kernel sources.

* tag 'perf-tools-fixes-for-v6.0-2022-08-27' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf stat: Capitalize topdown metrics' names
  perf docs: Update the documentation for the save_type filter
  perf sched: Fix memory leaks in __cmd_record detected with -fsanitize=address
  perf record: Fix manpage formatting of description of support to hybrid systems
  perf test: Stat test for repeat with a weak group
  perf stat: Clear evsel->reset_group for each stat run
  tools kvm headers arm64: Update KVM header from the kernel sources
  perf python: Fix build when PYTHON_CONFIG is user supplied

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0

tools/perf/Documentation/intel-hybrid.txt

@@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus
 
 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus.
 
-Quickstart
-
-List hybrid event
------------------
-
 As before, use perf-list to list the symbolic event.
 
 perf list
@@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can
 be supported.
 
 Enable hybrid event with a specific pmu
----------------------------------------
 
 To enable a core only event or atom only event, following syntax is supported:
 
@@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus.
 	perf stat -e cpu_core/cycles/
 
 Create two events for one hardware event automatically
-------------------------------------------------------
 
 When creating one event and the event is available on both atom and core,
 two events are created automatically. One is for atom, the other is for
@@ -132,7 +125,6 @@ For perf-stat result, it displays two events:
 The first 'cycles' is core event, the second 'cycles' is atom event.
 
 Thread mode example:
---------------------
 
 perf-stat reports the scaled counts for hybrid event and with a percentage
 displayed. The percentage is the event's running time/enabling time.
@@ -176,14 +168,12 @@ perf_event_attr:
        604,097,080      cpu_atom/cycles/                                              (99.57%)
 
 perf-record:
-------------
 
 If there is no '-e' specified in perf record, on hybrid platform,
 it creates two default 'cycles' and adds them to event list. One
 is for core, the other is for atom.
 
 perf-stat:
-----------
 
 If there is no '-e' specified in perf stat, on hybrid platform,
 besides of software events, following events are created and

tools/perf/Documentation/perf-record.txt

@@ -397,6 +397,9 @@ following filters are defined:
 	- abort_tx: only when the target is a hardware transaction abort
 	- cond: conditional branches
 	- save_type: save branch type during sampling in case binary is not available later
+		     For the platforms with Intel Arch LBR support (12th-Gen+ client or
+		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
+		     when the taken branch stack sampling is enabled.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
@@ -757,8 +760,6 @@ events in data directory files. Option specified with no or empty value
 defaults to CPU layout. Masks defined or provided by the option value are
 filtered through the mask provided by -C option.
 
-include::intel-hybrid.txt[]
-
 --debuginfod[=URLs]::
 	Specify debuginfod URL to be used when cacheing perf.data binaries,
 	it follows the same syntax as the DEBUGINFOD_URLS variable, like:
@@ -778,6 +779,8 @@ include::intel-hybrid.txt[]
 	only, as of now.  So the applications built without the frame
 	pointer might see bogus addresses.
 
+include::intel-hybrid.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]

tools/perf/Makefile.config

@@ -265,7 +265,7 @@ endif
 # defined. get-executable-or-default fails with an error if the first argument is supplied but
 # doesn't exist.
 override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs  = $(filter-out -l%,$(1))

tools/perf/builtin-sched.c

@@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void)
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
-	const char **rec_argv;
+	char **rec_argv;
+	const char **rec_argv_copy;
 	const char * const record_args[] = {
 		"record",
 		"-a",
@@ -3384,21 +3385,26 @@ static int __cmd_record(int argc, const char **argv)
 		ARRAY_SIZE(schedstat_args) : 0;
 
 	struct tep_event *waking_event;
+	int ret;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
 	 * "-e", "sched:sched_waking"
 	 */
 	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
-
 	if (rec_argv == NULL)
 		return -ENOMEM;
+	rec_argv_copy = calloc(rec_argc + 1, sizeof(char *));
+	if (rec_argv_copy == NULL) {
+		free(rec_argv);
+		return -ENOMEM;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
-	rec_argv[i++] = "-e";
+	rec_argv[i++] = strdup("-e");
 	waking_event = trace_event__tp_format("sched", "sched_waking");
 	if (!IS_ERR(waking_event))
 		rec_argv[i++] = strdup("sched:sched_waking");
@@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv)
 		rec_argv[i++] = strdup(schedstat_args[j]);
 
 	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+		rec_argv[i] = strdup(argv[j]);
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv);
+	memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc);
+	ret = cmd_record(rec_argc, rec_argv_copy);
+
+	for (i = 0; i < rec_argc; i++)
+		free(rec_argv[i]);
+	free(rec_argv);
+	free(rec_argv_copy);
+
+	return ret;
 }
 
 int cmd_sched(int argc, const char **argv)

tools/perf/builtin-stat.c

@@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	}
 
 	evlist__for_each_entry(evsel_list, counter) {
+		counter->reset_group = false;
 		if (bpf_counter__load(counter, &target))
 			return -1;
 		if (!evsel__is_bpf(counter))

tools/perf/tests/shell/stat.sh

@@ -28,6 +28,24 @@ test_stat_record_report() {
   echo "stat record and report test [Success]"
 }
 
+test_stat_repeat_weak_groups() {
+  echo "stat repeat weak groups test"
+  if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+     true 2>&1 | grep -q 'seconds time elapsed'
+  then
+    echo "stat repeat weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+    true > /dev/null 2>&1
+  then
+    echo "stat repeat weak groups test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat repeat weak groups test [Success]"
+}
+
 test_topdown_groups() {
   # Topdown events must be grouped with the slots event first. Test that
   # parse-events reorders this.
@@ -75,6 +93,7 @@ test_topdown_weak_groups() {
 
 test_default_stat
 test_stat_record_report
+test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
 exit $err

tools/perf/util/stat-shadow.c

@@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "Retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (retiring > 0.7 && heavy_ops > 0.1)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "heavy operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations",
 				heavy_ops * 100.);
 		if (retiring > 0.7 && light_ops > 0.6)
 			color = PERF_COLOR_GREEN;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "light operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Light Operations",
 				light_ops * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (bad_spec > 0.1 && br_mis > 0.05)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict",
+		print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict",
 				br_mis * 100.);
 		if (bad_spec > 0.1 && m_clears > 0.05)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
+		print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears",
 				m_clears * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (fe_bound > 0.2 && fetch_lat > 0.15)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch latency",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency",
 				fetch_lat * 100.);
 		if (fe_bound > 0.2 && fetch_bw > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth",
 				fetch_bw * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2 && mem_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "memory bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound",
 				mem_bound * 100.);
 		if (be_bound > 0.2 && core_bound > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "Core bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Core Bound",
 				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,