Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Add 'trace' subcommand for 'perf ftrace', setting the stage for
     more 'perf ftrace' subcommands. Not using a subcommand yields the
     previous behaviour of 'perf ftrace'.

   - Add 'latency' subcommand to 'perf ftrace', that can use the
     function graph tracer or a BPF optimized one, via the -b/--use-bpf
     option.

     E.g.:

	$ sudo perf ftrace latency -a -T mutex_lock sleep 1
	#   DURATION     |      COUNT | GRAPH                          |
	     0 - 1    us |       4596 | ########################       |
	     1 - 2    us |       1680 | #########                      |
	     2 - 4    us |       1106 | #####                          |
	     4 - 8    us |        546 | ##                             |
	     8 - 16   us |        562 | ###                            |
	    16 - 32   us |          1 |                                |
	    32 - 64   us |          0 |                                |
	    64 - 128  us |          0 |                                |
	   128 - 256  us |          0 |                                |
	   256 - 512  us |          0 |                                |
	   512 - 1024 us |          0 |                                |
	     1 - 2    ms |          0 |                                |
	     2 - 4    ms |          0 |                                |
	     4 - 8    ms |          0 |                                |
	     8 - 16   ms |          0 |                                |
	    16 - 32   ms |          0 |                                |
	    32 - 64   ms |          0 |                                |
	    64 - 128  ms |          0 |                                |
	   128 - 256  ms |          0 |                                |
	   256 - 512  ms |          0 |                                |
	   512 - 1024 ms |          0 |                                |
	     1 - ...   s |          0 |                                |

     The original implementation of this command was in the bcc tool.

   - Support --cputype option for hybrid events in 'perf stat'.

  Improvements:

   - Call chain improvements for ARM64.

   - No need to do any affinity setup when profiling pids.

   - Reduce multiplexing with duration_time in 'perf stat' metrics.

   - Improve error message for uncore events, stating that some event
     groups are can only be used in system wide (-a) mode.

   - perf stat metric group leader fixes/improvements, including arch
     specific changes to better support Intel topdown events.

   - Probe non-deprecated sysfs path first, i.e. try the path
     /sys/devices/system/cpu/cpuN/topology/thread_siblings first, then
     the old /sys/devices/system/cpu/cpuN/topology/core_cpus.

   - Disable debuginfod by default in 'perf record', to avoid stalls on
     distros such as Fedora 35.

   - Use unbuffered output in 'perf bench' when pipe/tee'ing to a file.

   - Enable ignore_missing_thread in 'perf trace'

  Fixes:

   - Avoid TUI crash when navigating in the annotation of recursive
     functions.

   - Fix hex dump character output in 'perf script'.

   - Fix JSON indentation to 4 spaces standard in the ARM vendor event
     files.

   - Fix use after free in metric__new().

   - Fix IS_ERR_OR_NULL() usage in the perf BPF loader.

   - Fix up cross-arch register support, i.e. when printing register
     names take into account the architecture where the perf.data file
     was collected.

   - Fix SMT fallback with large core counts.

   - Don't lower case MetricExpr when parsing JSON files so as not to
     lose info such as the ":G" event modifier in metrics.

  perf test:

   - Add basic stress test for sigtrap handling to 'perf test'.

   - Fix 'perf test' failures on s/390

   - Enable system wide for metricgroups test in 'perf test´.

   - Use 3 digits for test numbering now we can have more tests.

  Arch specific:

   - Add events for Arm Neoverse N2 in the ARM JSON vendor event files

   - Support PERF_MEM_LVLNUM encodings in powerpc, that came from a
     single patch series, where I incorrectly merged the kernel bits,
     that were then reverted after coordination with Michael Ellerman
     and Stephen Rothwell.

   - Add ARM SPE total latency as PERF_SAMPLE_WEIGHT.

   - Update AMD documentation, with info on raw event encoding.

   - Add support for global and local variants of the "p_stage_cyc" sort
     key, applicable to perf.data files collected on powerpc.

   - Remove duplicate and incorrect aux size checks in the ARM CoreSight
     ETM code.

  Refactorings:

   - Add a perf_cpu abstraction to disambiguate CPUs and CPU map
     indexes, fixing problems along the way.

   - Document CPU map methods.

  UAPI sync:

   - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench
     mem memcpy'

   - Sync UAPI files with the kernel sources: drm, msr-index,
     cpufeatures.

  Build system

   - Enable warnings through HOSTCFLAGS.

   - Drop requirement for libstdc++.so for libopencsd check

  libperf:

   - Make libperf adopt perf_counts_values__scale() from tools/perf/util/.

   - Add a stat multiplexing test to libperf"

* tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits)
  perf record: Disable debuginfod by default
  perf evlist: No need to do any affinity setup when profiling pids
  perf cpumap: Add is_dummy() method
  perf metric: Fix metric_leader
  perf cputopo: Fix CPU topology reading on s/390
  perf metricgroup: Fix use after free in metric__new()
  libperf tests: Update a use of the new cpumap API
  perf arm: Fix off-by-one directory path
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Update tools's copy of drm.h header
  tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy'
  perf pmu-events: Don't lower case MetricExpr
  perf expr: Add debug logging for literals
  perf tools: Probe non-deprecated sysfs path 1st
  perf tools: Fix SMT fallback with large core counts
  perf cpumap: Give CPUs their own type
  perf stat: Correct first_shadow_cpu to return index
  perf script: Fix flipped index and cpu
  perf c2c: Use more intention revealing iterator
  ...

1 files changed, 160 insertions, 2 deletions

diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ce91a582f0e4..b3479dfa9a1c 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -21,6 +21,9 @@
 #include "tests.h"
 #include <internal/evsel.h>
 
+#define EVENT_NUM 15
+#define WAIT_COUNT 100000000UL
+
 static int libperf_print(enum libperf_print_level level,
 			 const char *fmt, va_list ap)
 {
@@ -331,7 +334,8 @@ static int test_mmap_cpus(void)
 	};
 	cpu_set_t saved_mask;
 	char path[PATH_MAX];
-	int id, err, cpu, tmp;
+	int id, err, tmp;
+	struct perf_cpu cpu;
 	union perf_event *event;
 	int count = 0;
 
@@ -374,7 +378,7 @@ static int test_mmap_cpus(void)
 		cpu_set_t mask;
 
 		CPU_ZERO(&mask);
-		CPU_SET(cpu, &mask);
+		CPU_SET(cpu.cpu, &mask);
 
 		err = sched_setaffinity(0, sizeof(mask), &mask);
 		__T("sched_setaffinity failed", err == 0);
@@ -413,6 +417,159 @@ static int test_mmap_cpus(void)
 	return 0;
 }
 
+static double display_error(long long average,
+			    long long high,
+			    long long low,
+			    long long expected)
+{
+	double error;
+
+	error = (((double)average - expected) / expected) * 100.0;
+
+	__T_VERBOSE("   Expected: %lld\n", expected);
+	__T_VERBOSE("   High: %lld   Low:  %lld   Average:  %lld\n",
+		    high, low, average);
+
+	__T_VERBOSE("   Average Error = %.2f%%\n", error);
+
+	return error;
+}
+
+static int test_stat_multiplexing(void)
+{
+	struct perf_counts_values expected_counts = { .val = 0 };
+	struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },};
+	struct perf_thread_map *threads;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type	     = PERF_TYPE_HARDWARE,
+		.config	     = PERF_COUNT_HW_INSTRUCTIONS,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+			       PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+	int err, i, nonzero = 0;
+	unsigned long count;
+	long long max = 0, min = 0, avg = 0;
+	double error = 0.0;
+	s8 scaled = 0;
+
+	/* read for non-multiplexing event count */
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	evsel = perf_evsel__new(&attr);
+	__T("failed to create evsel", evsel);
+
+	err = perf_evsel__open(evsel, NULL, threads);
+	__T("failed to open evsel", err == 0);
+
+	err = perf_evsel__enable(evsel);
+	__T("failed to enable evsel", err == 0);
+
+	/* wait loop */
+	count = WAIT_COUNT;
+	while (count--)
+		;
+
+	perf_evsel__read(evsel, 0, 0, &expected_counts);
+	__T("failed to read value for evsel", expected_counts.val != 0);
+	__T("failed to read non-multiplexing event count",
+	    expected_counts.ena == expected_counts.run);
+
+	err = perf_evsel__disable(evsel);
+	__T("failed to enable evsel", err == 0);
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+
+	perf_thread_map__put(threads);
+
+	/* read for multiplexing event count */
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	evlist = perf_evlist__new();
+	__T("failed to create evlist", evlist);
+
+	for (i = 0; i < EVENT_NUM; i++) {
+		evsel = perf_evsel__new(&attr);
+		__T("failed to create evsel", evsel);
+
+		perf_evlist__add(evlist, evsel);
+	}
+	perf_evlist__set_maps(evlist, NULL, threads);
+
+	err = perf_evlist__open(evlist);
+	__T("failed to open evsel", err == 0);
+
+	perf_evlist__enable(evlist);
+
+	/* wait loop */
+	count = WAIT_COUNT;
+	while (count--)
+		;
+
+	i = 0;
+	perf_evlist__for_each_evsel(evlist, evsel) {
+		perf_evsel__read(evsel, 0, 0, &counts[i]);
+		__T("failed to read value for evsel", counts[i].val != 0);
+		i++;
+	}
+
+	perf_evlist__disable(evlist);
+
+	min = counts[0].val;
+	for (i = 0; i < EVENT_NUM; i++) {
+		__T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n",
+			    i, counts[i].val, counts[i].run, counts[i].ena);
+
+		perf_counts_values__scale(&counts[i], true, &scaled);
+		if (scaled == 1) {
+			__T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n",
+				    counts[i].val,
+				    (double)counts[i].run / (double)counts[i].ena * 100.0,
+				    counts[i].run, counts[i].ena);
+		} else if (scaled == -1) {
+			__T_VERBOSE("\t Not Running\n");
+		} else {
+			__T_VERBOSE("\t Not Scaling\n");
+		}
+
+		if (counts[i].val > max)
+			max = counts[i].val;
+
+		if (counts[i].val < min)
+			min = counts[i].val;
+
+		avg += counts[i].val;
+
+		if (counts[i].val != 0)
+			nonzero++;
+	}
+
+	if (nonzero != 0)
+		avg = avg / nonzero;
+	else
+		avg = 0;
+
+	error = display_error(avg, max, min, expected_counts.val);
+
+	__T("Error out of range!", ((error <= 1.0) && (error >= -1.0)));
+
+	perf_evlist__close(evlist);
+	perf_evlist__delete(evlist);
+
+	perf_thread_map__put(threads);
+
+	return 0;
+}
+
 int test_evlist(int argc, char **argv)
 {
 	__T_START;
@@ -424,6 +581,7 @@ int test_evlist(int argc, char **argv)
 	test_stat_thread_enable();
 	test_mmap_thread();
 	test_mmap_cpus();
+	test_stat_multiplexing();
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;