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, 69 insertions, 44 deletions

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index adaad3dddf6e..ee66760f1e63 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -10,15 +10,24 @@
 #include <ctype.h>
 #include <limits.h>
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 {
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
 
 	if (cpus != NULL) {
-		cpus->nr = 1;
-		cpus->map[0] = -1;
+		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
+
 	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+	if (cpus)
+		cpus->map[0].cpu = -1;
 
 	return cpus;
 }
@@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	if (nr_cpus < 0)
 		return NULL;
 
-	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
 
 		for (i = 0; i < nr_cpus; ++i)
-			cpus->map[i] = i;
-
-		cpus->nr = nr_cpus;
-		refcount_set(&cpus->refcnt, 1);
+			cpus->map[i].cpu = i;
 	}
 
 	return cpus;
@@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void)
 	return cpu_map__default_new();
 }
 
-static int cmp_int(const void *a, const void *b)
+
+static int cmp_cpu(const void *a, const void *b)
 {
-	return *(const int *)a - *(const int*)b;
+	const struct perf_cpu *cpu_a = a, *cpu_b = b;
+
+	return cpu_a->cpu - cpu_b->cpu;
 }
 
-static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
+static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
 {
-	size_t payload_size = nr_cpus * sizeof(int);
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+	size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
 	int i, j;
 
 	if (cpus != NULL) {
 		memcpy(cpus->map, tmp_cpus, payload_size);
-		qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+		qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
 		/* Remove dups */
 		j = 0;
 		for (i = 0; i < nr_cpus; i++) {
-			if (i == 0 || cpus->map[i] != cpus->map[i - 1])
-				cpus->map[j++] = cpus->map[i];
+			if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
+				cpus->map[j++].cpu = cpus->map[i].cpu;
 		}
 		cpus->nr = j;
 		assert(j <= nr_cpus);
-		refcount_set(&cpus->refcnt, 1);
 	}
-
 	return cpus;
 }
 
@@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 {
 	struct perf_cpu_map *cpus = NULL;
 	int nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
@@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 			if (new_max >= max_entries) {
 				max_entries = new_max + MAX_NR_CPUS / 2;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto out_free_tmp;
 				tmp_cpus = tmp;
 			}
 
 			while (++prev < cpu)
-				tmp_cpus[nr_cpus++] = prev;
+				tmp_cpus[nr_cpus++].cpu = prev;
 		}
 		if (nr_cpus == max_entries) {
 			max_entries += MAX_NR_CPUS;
-			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+			tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 			if (tmp == NULL)
 				goto out_free_tmp;
 			tmp_cpus = tmp;
 		}
 
-		tmp_cpus[nr_cpus++] = cpu;
+		tmp_cpus[nr_cpus++].cpu = cpu;
 		if (n == 2 && sep == '-')
 			prev = cpu;
 		else
@@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	unsigned long start_cpu, end_cpu = 0;
 	char *p = NULL;
 	int i, nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 
 	if (!cpu_list)
@@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i] == (int)start_cpu)
+				if (tmp_cpus[i].cpu == (int)start_cpu)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
 				max_entries += MAX_NR_CPUS;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto invalid;
 				tmp_cpus = tmp;
 			}
-			tmp_cpus[nr_cpus++] = (int)start_cpu;
+			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
 		}
 		if (*p)
 			++p;
@@ -250,12 +257,16 @@ out:
 	return cpus;
 }
 
-int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 {
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	if (cpus && idx < cpus->nr)
 		return cpus->map[idx];
 
-	return -1;
+	return result;
 }
 
 int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
@@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 
 bool perf_cpu_map__empty(const struct perf_cpu_map *map)
 {
-	return map ? map->map[0] == -1 : true;
+	return map ? map->map[0].cpu == -1 : true;
 }
 
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
-	int low = 0, high = cpus->nr;
+	int low, high;
 
+	if (!cpus)
+		return -1;
+
+	low = 0;
+	high = cpus->nr;
 	while (low < high) {
-		int idx = (low + high) / 2,
-		    cpu_at_idx = cpus->map[idx];
+		int idx = (low + high) / 2;
+		struct perf_cpu cpu_at_idx = cpus->map[idx];
 
-		if (cpu_at_idx == cpu)
+		if (cpu_at_idx.cpu == cpu.cpu)
 			return idx;
 
-		if (cpu_at_idx > cpu)
+		if (cpu_at_idx.cpu > cpu.cpu)
 			high = idx;
 		else
 			low = idx + 1;
@@ -288,10 +304,19 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
 	return -1;
 }
 
-int perf_cpu_map__max(struct perf_cpu_map *map)
+bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
+	return perf_cpu_map__idx(cpus, cpu) != -1;
+}
+
+struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+{
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return map->nr > 0 ? map->map[map->nr - 1] : -1;
+	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
 /*
@@ -305,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 					 struct perf_cpu_map *other)
 {
-	int *tmp_cpus;
+	struct perf_cpu *tmp_cpus;
 	int tmp_len;
 	int i, j, k;
 	struct perf_cpu_map *merged;
@@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	if (!other)
 		return orig;
 	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
 		return orig;
 
 	tmp_len = orig->nr + other->nr;
-	tmp_cpus = malloc(tmp_len * sizeof(int));
+	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
 	if (!tmp_cpus)
 		return NULL;
 
 	/* Standard merge algorithm from wikipedia */
 	i = j = k = 0;
 	while (i < orig->nr && j < other->nr) {
-		if (orig->map[i] <= other->map[j]) {
-			if (orig->map[i] == other->map[j])
+		if (orig->map[i].cpu <= other->map[j].cpu) {
+			if (orig->map[i].cpu == other->map[j].cpu)
 				j++;
 			tmp_cpus[k++] = orig->map[i++];
 		} else