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
  ...

13 files changed, 353 insertions, 123 deletions

diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 63ae5e0195ce..32c5051c24eb 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -48,6 +48,7 @@ SYNOPSIS
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
   bool perf_cpu_map__empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
+  bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
   #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)
 --
@@ -135,16 +136,16 @@ SYNOPSIS
   int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
                        struct perf_thread_map *threads);
   void perf_evsel__close(struct perf_evsel *evsel);
-  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
   void perf_evsel__munmap(struct perf_evsel *evsel);
-  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-  int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+  int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
                        struct perf_counts_values *count);
   int perf_evsel__enable(struct perf_evsel *evsel);
-  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__disable(struct perf_evsel *evsel);
-  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
   struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
   struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
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
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e37dfad31383..9a770bfdc804 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
 
 static int
 perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-			  int output, int cpu)
+			  int output, struct perf_cpu cpu)
 {
 	return perf_mmap__mmap(map, mp, output, cpu);
 }
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
 	       int thread, int *_output, int *_output_overwrite)
 {
-	int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
 	return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
 }
 
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
 {
-	struct perf_evsel *evsel, *leader;
+	struct perf_evsel *first, *last, *evsel;
 
-	leader = list_entry(list->next, struct perf_evsel, node);
-	evsel = list_entry(list->prev, struct perf_evsel, node);
+	first = list_first_entry(list, struct perf_evsel, node);
+	last = list_last_entry(list, struct perf_evsel, node);
 
-	leader->nr_members = evsel->idx - leader->idx + 1;
+	leader->nr_members = last->idx - first->idx + 1;
 
 	__perf_evlist__for_each_entry(list, evsel)
 		evsel->leader = leader;
@@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
 	if (evlist->nr_entries) {
+		struct perf_evsel *first = list_entry(evlist->entries.next,
+						struct perf_evsel, node);
+
 		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->entries);
+		__perf_evlist__set_leader(&evlist->entries, first);
 	}
 }
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8441e3e1aaac..7ea86a44eae5 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
-#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
+#define FD(_evsel, _cpu_map_idx, _thread)				\
+	((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
+#define MMAP(_evsel, _cpu_map_idx, _thread)				\
+	(_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
+		      : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
-		int cpu, thread;
-		for (cpu = 0; cpu < ncpus; cpu++) {
+		int idx, thread;
+
+		for (idx = 0; idx < ncpus; idx++) {
 			for (thread = 0; thread < nthreads; thread++) {
-				int *fd = FD(evsel, cpu, thread);
+				int *fd = FD(evsel, idx, thread);
 
 				if (fd)
 					*fd = -1;
@@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre
 
 static int
 sys_perf_event_open(struct perf_event_attr *attr,
-		    pid_t pid, int cpu, int group_fd,
+		    pid_t pid, struct perf_cpu cpu, int group_fd,
 		    unsigned long flags)
 {
-	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
 }
 
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
+static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
 {
 	struct perf_evsel *leader = evsel->leader;
 	int *fd;
@@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 	if (!leader->fd)
 		return -ENOTCONN;
 
-	fd = FD(leader, cpu, thread);
+	fd = FD(leader, cpu_map_idx, thread);
 	if (fd == NULL || *fd == -1)
 		return -EBADF;
 
@@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		     struct perf_thread_map *threads)
 {
-	int cpu, thread, err = 0;
+	struct perf_cpu cpu;
+	int idx, thread, err = 0;
 
 	if (cpus == NULL) {
 		static struct perf_cpu_map *empty_cpu_map;
@@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		for (thread = 0; thread < threads->nr; thread++) {
 			int fd, group_fd, *evsel_fd;
 
-			evsel_fd = FD(evsel, cpu, thread);
+			evsel_fd = FD(evsel, idx, thread);
 			if (evsel_fd == NULL)
 				return -EINVAL;
 
-			err = get_group_fd(evsel, cpu, thread, &group_fd);
+			err = get_group_fd(evsel, idx, thread, &group_fd);
 			if (err < 0)
 				return err;
 
 			fd = sys_perf_event_open(&evsel->attr,
 						 threads->map[thread].pid,
-						 cpus->map[cpu], group_fd, 0);
+						 cpu, group_fd, 0);
 
 			if (fd < 0)
 				return -errno;
@@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	return err;
 }
 
-static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd && *fd >= 0) {
 			close(*fd);
@@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
 
 void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
-	int cpu;
-
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
-		perf_evsel__close_fd_cpu(evsel, cpu);
+	for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
+		perf_evsel__close_fd_cpu(evsel, idx);
 }
 
 void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 }
 
-void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	if (evsel->fd == NULL)
 		return;
 
-	perf_evsel__close_fd_cpu(evsel, cpu);
+	perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
 }
 
 void perf_evsel__munmap(struct perf_evsel *evsel)
 {
-	int cpu, thread;
+	int idx, thread;
 
 	if (evsel->fd == NULL || evsel->mmap == NULL)
 		return;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			perf_mmap__munmap(MMAP(evsel, cpu, thread));
+			perf_mmap__munmap(MMAP(evsel, idx, thread));
 		}
 	}
 
@@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
 
 int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 {
-	int ret, cpu, thread;
+	int ret, idx, thread;
 	struct perf_mmap_param mp = {
 		.prot = PROT_READ | PROT_WRITE,
 		.mask = (pages * page_size) - 1,
@@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 			struct perf_mmap *map;
+			struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			map = MMAP(evsel, cpu, thread);
+			map = MMAP(evsel, idx, thread);
 			perf_mmap__init(map, NULL, false, NULL);
 
 			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
@@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	return 0;
 }
 
-void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
 {
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
-	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
+	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
 		return NULL;
 
-	return MMAP(evsel, cpu, thread)->base;
+	return MMAP(evsel, cpu_map_idx, thread)->base;
 }
 
 int perf_evsel__read_size(struct perf_evsel *evsel)
@@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
-	if (MMAP(evsel, cpu, thread) &&
-	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
 	if (readn(*fd, count->values, size) <= 0)
@@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 				 int ioc,  void *arg,
-				 int cpu)
+				 int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
 		int err;
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd == NULL || *fd < 0)
 			return -1;
@@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 	return 0;
 }
 
-int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__enable(struct perf_evsel *evsel)
@@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel)
 	return err;
 }
 
-int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
@@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
 	zfree(&evsel->id);
 	evsel->ids = 0;
 }
+
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, __s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double)count->val * count->ena / count->run);
+		}
+	}
+
+	if (pscaled)
+		*pscaled = scaled;
+}
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 840d4032587b..581f9ffb4237 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -4,16 +4,30 @@
 
 #include <linux/refcount.h>
 
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+	int cpu;
+};
+
+/**
+ * A sized, reference counted, sorted array of integers representing CPU
+ * numbers. This is commonly used to capture which CPUs a PMU is associated
+ * with. The indices into the cpumap are frequently used as they avoid having
+ * gaps if CPU numbers were used. For events associated with a pid, rather than
+ * a CPU, a single dummy map with an entry of -1 is used.
+ */
 struct perf_cpu_map {
 	refcount_t	refcnt;
+	/** Length of the map array. */
 	int		nr;
-	int		map[];
+	/** The CPU values. */
+	struct perf_cpu	map[];
 };
 
 #ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS	2048
 #endif
 
-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);
 
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index f366dbad6a88..4cefade540bd 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -4,6 +4,7 @@
 
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <internal/cpumap.h>
 #include <internal/evsel.h>
 
 #define PERF_EVLIST__HLIST_BITS 8
@@ -36,7 +37,7 @@ typedef void
 typedef struct perf_mmap*
 (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
 typedef int
-(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int);
+(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu);
 
 struct perf_evlist_mmap_ops {
 	perf_evlist_mmap__cb_idx_t	idx;
@@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 
 void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
 
-void __perf_evlist__set_leader(struct list_head *list);
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader);
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1f3eacbad2e8..cfc9ebd7968e 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -6,8 +6,8 @@
 #include <linux/perf_event.h>
 #include <stdbool.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 
-struct perf_cpu_map;
 struct perf_thread_map;
 struct xyarray;
 
@@ -27,7 +27,7 @@ struct perf_sample_id {
 	* queue number.
 	*/
 	int			 idx;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	pid_t			 tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5e3422f40ed5..5a062af8e9d8 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -6,6 +6,7 @@
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <stdbool.h>
+#include <internal/cpumap.h>
 
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
@@ -24,7 +25,7 @@ struct perf_mmap {
 	void			*base;
 	int			 mask;
 	int			 fd;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	refcount_t		 refcnt;
 	u64			 prev;
 	u64			 start;
@@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map);
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb);
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-		    int fd, int cpu);
+		    int fd, struct perf_cpu cpu);
 void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 7c27766ea0bf..15b8faafd615 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,11 +3,10 @@
 #define __LIBPERF_CPUMAP_H
 
 #include <perf/core.h>
+#include <perf/cpumap.h>
 #include <stdio.h>
 #include <stdbool.h>
 
-struct perf_cpu_map;
-
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
@@ -16,10 +15,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 						     struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
 	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 60eae25076d3..2a9516b42d15 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -4,6 +4,8 @@
 
 #include <stdint.h>
 #include <perf/core.h>
+#include <stdbool.h>
+#include <linux/types.h>
 
 struct perf_evsel;
 struct perf_event_attr;
@@ -26,18 +28,20 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 				 struct perf_thread_map *threads);
 LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
-LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
 LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel);
-LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
 LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
 LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
+LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count,
+					   bool scale, __s8 *pscaled);
 
 #endif /* __LIBPERF_EVSEL_H */
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 71468606e8a7..93696affda2e 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -10,6 +10,7 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__cpu;
 		perf_cpu_map__empty;
 		perf_cpu_map__max;
+		perf_cpu_map__has;
 		perf_thread_map__new_dummy;
 		perf_thread_map__set_pid;
 		perf_thread_map__comm;
@@ -50,6 +51,7 @@ LIBPERF_0.0.1 {
 		perf_mmap__read_init;
 		perf_mmap__read_done;
 		perf_mmap__read_event;
+		perf_counts_values__scale;
 	local:
 		*;
 };
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index c89dfa5f67b3..f7ee07cb5818 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -32,7 +32,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-		    int fd, int cpu)
+		    int fd, struct perf_cpu cpu)
 {
 	map->prev = 0;
 	map->mask = mp->mask;
@@ -353,8 +353,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count
 		count->ena += delta;
 		if (idx)
 			count->run += delta;
-
-		cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
 	}
 
 	count->val = cnt;
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;