Merge tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "perf stat:

   - Add support for hybrid PMUs to support systems such as Intel
     Alderlake and its BIG/little core/atom cpus.

   - Introduce 'bperf' to share hardware PMCs with BPF.

   - New --iostat option to collect and present IO stats on Intel
     hardware.

     This functionality is based on recently introduced sysfs attributes
     for Intel® Xeon® Scalable processor family (code name Skylake-SP)
     in commit bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore
     unit to IIO PMON mapping")

     It is intended to provide four I/O performance metrics in MB per
     each PCIe root port:

       - Inbound Read: I/O devices below root port read from the host memory
       - Inbound Write: I/O devices below root port write to the host memory
       - Outbound Read: CPU reads from I/O devices below root port
       - Outbound Write: CPU writes to I/O devices below root port

   - Align CSV output for summary.

   - Clarify --null use cases: Assess raw overhead of 'perf stat' or
     measure just wall clock time.

   - Improve readability of shadow stats.

  perf record:

   - Change the COMM when starting tha workload so that --exclude-perf
     doesn't seem to be not honoured.

   - Improve 'Workload failed' message printing events + what was
     exec'ed.

   - Fix cross-arch support for TIME_CONV.

  perf report:

   - Add option to disable raw event ordering.

   - Dump the contents of PERF_RECORD_TIME_CONV in 'perf report -D'.

   - Improvements to --stat output, that shows information about
     PERF_RECORD_ events.

   - Preserve identifier id in OCaml demangler.

  perf annotate:

   - Show full source location with 'l' hotkey in the 'perf annotate'
     TUI.

   - Add line number like in TUI and source location at EOL to the 'perf
     annotate' --stdio mode.

   - Add --demangle and --demangle-kernel to 'perf annotate'.

   - Allow configuring annotate.demangle{,_kernel} in 'perf config'.

   - Fix sample events lost in stdio mode.

  perf data:

   - Allow converting a perf.data file to JSON.

  libperf:

   - Add support for user space counter access.

   - Update topdown documentation to permit rdpmc calls.

  perf test:

   - Add 'perf test' for 'perf stat' CSV output.

   - Add 'perf test' entries to test the hybrid PMU support.

   - Cleanup 'perf test daemon' if its 'perf test' is interrupted.

   - Handle metric reuse in pmu-events parsing 'perf test' entry.

   - Add test for PE executable support.

   - Add timeout for wait for daemon start in its 'perf test' entries.

  Build:

   - Enable libtraceevent dynamic linking.

   - Improve feature detection output.

   - Fix caching of feature checks caching.

   - First round of updates for tools copies of kernel headers.

   - Enable warnings when compiling BPF programs.

  Vendor specific events:

   - Intel:
      - Add missing skylake & icelake model numbers.

   - arm64:
      - Add Hisi hip08 L1, L2 and L3 metrics.
      - Add Fujitsu A64FX PMU events.

   - PowerPC:
      - Initial JSON/events list for power10 platform.
      - Remove unsupported power9 metrics.

   - AMD:
      - Add Zen3 events.
      - Fix broken L2 Cache Hits from L2 HWPF metric.
      - Use lowercases for all the eventcodes and umasks.

  Hardware tracing:

   - arm64:
      - Update CoreSight ETM metadata format.
      - Fix bitmap for CS-ETM option.
      - Support PID tracing in config.
      - Detect pid in VMID for kernel running at EL2.

  Arch specific updates:

   - MIPS:
      - Support MIPS unwinding and dwarf-regs.
      - Generate mips syscalls_n64.c syscall table.

   - PowerPC:
      - Add support for PERF_SAMPLE_WEIGH_STRUCT on PowerPC.
      - Support pipeline stage cycles for powerpc.

  libbeauty:

   - Fix fsconfig generator"

* tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (132 commits)
  perf build: Defer printing detected features to the end of all feature checks
  tools build: Allow deferring printing the results of feature detection
  perf build: Regenerate the FEATURE_DUMP file after extra feature checks
  perf session: Dump PERF_RECORD_TIME_CONV event
  perf session: Add swap operation for event TIME_CONV
  perf jit: Let convert_timestamp() to be backwards-compatible
  perf tools: Change fields type in perf_record_time_conv
  perf tools: Enable libtraceevent dynamic linking
  perf Documentation: Document intel-hybrid support
  perf tests: Skip 'perf stat metrics (shadow stat) test' for hybrid
  perf tests: Support 'Convert perf time to TSC' test for hybrid
  perf tests: Support 'Session topology' test for hybrid
  perf tests: Support 'Parse and process metrics' test for hybrid
  perf tests: Support 'Track with sched_switch' test for hybrid
  perf tests: Skip 'Setup struct perf_event_attr' test for hybrid
  perf tests: Add hybrid cases for 'Roundtrip evsel->name' test
  perf tests: Add hybrid cases for 'Parse event definition strings' test
  perf record: Uniquify hybrid event name
  perf stat: Warn group events from different hybrid PMU
  perf stat: Filter out unmatched aggregation for hybrid event
  ...

13 files changed, 327 insertions, 5 deletions

diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 0c74c30ed23a..63ae5e0195ce 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -136,6 +136,9 @@ SYNOPSIS
                        struct perf_thread_map *threads);
   void perf_evsel__close(struct perf_evsel *evsel);
   void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+  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,
                        struct perf_counts_values *count);
   int perf_evsel__enable(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 4dc06289f4c7..bd8c2f19ef74 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -11,10 +11,12 @@
 #include <stdlib.h>
 #include <internal/xyarray.h>
 #include <internal/cpumap.h>
+#include <internal/mmap.h>
 #include <internal/threadmap.h>
 #include <internal/lib.h>
 #include <linux/string.h>
 #include <sys/ioctl.h>
+#include <sys/mman.h>
 
 void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr)
 {
@@ -38,6 +40,7 @@ void perf_evsel__delete(struct perf_evsel *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)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
@@ -55,6 +58,13 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
+static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->mmap = xyarray__new(ncpus, nthreads, sizeof(struct perf_mmap));
+
+	return evsel->mmap != NULL ? 0 : -ENOMEM;
+}
+
 static int
 sys_perf_event_open(struct perf_event_attr *attr,
 		    pid_t pid, int cpu, int group_fd,
@@ -156,6 +166,72 @@ void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
 	perf_evsel__close_fd_cpu(evsel, cpu);
 }
 
+void perf_evsel__munmap(struct perf_evsel *evsel)
+{
+	int cpu, thread;
+
+	if (evsel->fd == NULL || evsel->mmap == NULL)
+		return;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+			int fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+
+			if (fd < 0)
+				continue;
+
+			perf_mmap__munmap(map);
+		}
+	}
+
+	xyarray__delete(evsel->mmap);
+	evsel->mmap = NULL;
+}
+
+int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
+{
+	int ret, cpu, thread;
+	struct perf_mmap_param mp = {
+		.prot = PROT_READ | PROT_WRITE,
+		.mask = (pages * page_size) - 1,
+	};
+
+	if (evsel->fd == NULL || evsel->mmap)
+		return -EINVAL;
+
+	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 (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+			int fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+
+			if (fd < 0)
+				continue;
+
+			perf_mmap__init(map, NULL, false, NULL);
+
+			ret = perf_mmap__mmap(map, &mp, fd, cpu);
+			if (ret) {
+				perf_evsel__munmap(evsel);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+{
+	if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL)
+		return NULL;
+
+	return MMAP(evsel, cpu, thread)->base;
+}
+
 int perf_evsel__read_size(struct perf_evsel *evsel)
 {
 	u64 read_format = evsel->attr.read_format;
@@ -191,6 +267,10 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
+	if (MMAP(evsel, cpu, thread) &&
+	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+		return 0;
+
 	if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
 		return -errno;
 
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1ffd083b235e..1c067d088bc6 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -41,6 +41,7 @@ struct perf_evsel {
 	struct perf_cpu_map	*own_cpus;
 	struct perf_thread_map	*threads;
 	struct xyarray		*fd;
+	struct xyarray		*mmap;
 	struct xyarray		*sample_id;
 	u64			*id;
 	u32			 ids;
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index be7556e0a2b2..5e3422f40ed5 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -11,6 +11,7 @@
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
 struct perf_mmap;
+struct perf_counts_values;
 
 typedef void (*libperf_unmap_cb_t)(struct perf_mmap *map);
 
@@ -52,4 +53,6 @@ void perf_mmap__put(struct perf_mmap *map);
 
 u64 perf_mmap__read_head(struct perf_mmap *map);
 
+int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count);
+
 #endif /* __LIBPERF_INTERNAL_MMAP_H */
diff --git a/tools/lib/perf/include/internal/tests.h b/tools/lib/perf/include/internal/tests.h
index 2093e8868a67..29425c2dabe1 100644
--- a/tools/lib/perf/include/internal/tests.h
+++ b/tools/lib/perf/include/internal/tests.h
@@ -3,11 +3,32 @@
 #define __LIBPERF_INTERNAL_TESTS_H
 
 #include <stdio.h>
+#include <unistd.h>
 
 int tests_failed;
+int tests_verbose;
+
+static inline int get_verbose(char **argv, int argc)
+{
+	int c;
+	int verbose = 0;
+
+	while ((c = getopt(argc, argv, "v")) != -1) {
+		switch (c)
+		{
+		case 'v':
+			verbose = 1;
+			break;
+		default:
+			break;
+		}
+	}
+	return verbose;
+}
 
 #define __T_START					\
 do {							\
+	tests_verbose = get_verbose(argv, argc);	\
 	fprintf(stdout, "- running %s...", __FILE__);	\
 	fflush(NULL);					\
 	tests_failed = 0;				\
@@ -30,4 +51,15 @@ do {
 	}                                                                        \
 } while (0)
 
+#define __T_VERBOSE(...)						\
+do {									\
+	if (tests_verbose) {						\
+		if (tests_verbose == 1) {				\
+			fputc('\n', stderr);				\
+			tests_verbose++;				\
+		}							\
+		fprintf(stderr, ##__VA_ARGS__);				\
+	}								\
+} while (0)
+
 #endif /* __LIBPERF_INTERNAL_TESTS_H */
diff --git a/tools/lib/perf/include/internal/xyarray.h b/tools/lib/perf/include/internal/xyarray.h
index 51e35d6c8ec4..f10af3da7b21 100644
--- a/tools/lib/perf/include/internal/xyarray.h
+++ b/tools/lib/perf/include/internal/xyarray.h
@@ -18,11 +18,18 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
 void xyarray__delete(struct xyarray *xy);
 void xyarray__reset(struct xyarray *xy);
 
-static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
+static inline void *__xyarray__entry(struct xyarray *xy, int x, int y)
 {
 	return &xy->contents[x * xy->row_size + y * xy->entry_size];
 }
 
+static inline void *xyarray__entry(struct xyarray *xy, size_t x, size_t y)
+{
+	if (x >= xy->max_x || y >= xy->max_y)
+		return NULL;
+	return __xyarray__entry(xy, x, y);
+}
+
 static inline int xyarray__max_y(struct xyarray *xy)
 {
 	return xy->max_y;
diff --git a/tools/lib/perf/include/perf/bpf_perf.h b/tools/lib/perf/include/perf/bpf_perf.h
new file mode 100644
index 000000000000..e7cf6ba7b674
--- /dev/null
+++ b/tools/lib/perf/include/perf/bpf_perf.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __LIBPERF_BPF_PERF_H
+#define __LIBPERF_BPF_PERF_H
+
+#include <linux/types.h>  /* for __u32 */
+
+/*
+ * bpf_perf uses a hashmap, the attr_map, to track all the leader programs.
+ * The hashmap is pinned in bpffs. flock() on this file is used to ensure
+ * no concurrent access to the attr_map.  The key of attr_map is struct
+ * perf_event_attr, and the value is struct perf_event_attr_map_entry.
+ *
+ * struct perf_event_attr_map_entry contains two __u32 IDs, bpf_link of the
+ * leader prog, and the diff_map. Each perf-stat session holds a reference
+ * to the bpf_link to make sure the leader prog is attached to sched_switch
+ * tracepoint.
+ *
+ * Since the hashmap only contains IDs of the bpf_link and diff_map, it
+ * does not hold any references to the leader program. Once all perf-stat
+ * sessions of these events exit, the leader prog, its maps, and the
+ * perf_events will be freed.
+ */
+struct perf_event_attr_map_entry {
+	__u32 link_id;
+	__u32 diff_map_id;
+};
+
+/* default attr_map name */
+#define BPF_PERF_DEFAULT_ATTR_MAP_PATH "perf_attr_map"
+
+#endif /* __LIBPERF_BPF_PERF_H */
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index d82054225fcc..4d0c02ba3f7d 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -8,6 +8,8 @@
 #include <linux/bpf.h>
 #include <sys/types.h> /* pid_t */
 
+#define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
+
 struct perf_record_mmap {
 	struct perf_event_header header;
 	__u32			 pid, tid;
@@ -346,8 +348,9 @@ struct perf_record_time_conv {
 	__u64			 time_zero;
 	__u64			 time_cycles;
 	__u64			 time_mask;
-	bool			 cap_user_time_zero;
-	bool			 cap_user_time_short;
+	__u8			 cap_user_time_zero;
+	__u8			 cap_user_time_short;
+	__u8			 reserved[6];	/* For alignment */
 };
 
 struct perf_record_header_feature {
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index c82ec39a4ad0..60eae25076d3 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -27,6 +27,9 @@ LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *
 				 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 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,
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 7be1af8a546c..c0c7ceb11060 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -23,6 +23,9 @@ LIBPERF_0.0.1 {
 		perf_evsel__disable;
 		perf_evsel__open;
 		perf_evsel__close;
+		perf_evsel__mmap;
+		perf_evsel__munmap;
+		perf_evsel__mmap_base;
 		perf_evsel__read;
 		perf_evsel__cpus;
 		perf_evsel__threads;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 79d5ed6c38cc..c89dfa5f67b3 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -8,9 +8,11 @@
 #include <linux/perf_event.h>
 #include <perf/mmap.h>
 #include <perf/event.h>
+#include <perf/evsel.h>
 #include <internal/mmap.h>
 #include <internal/lib.h>
 #include <linux/kernel.h>
+#include <linux/math64.h>
 #include "internal.h"
 
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
@@ -273,3 +275,89 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 
 	return event;
 }
+
+#if defined(__i386__) || defined(__x86_64__)
+static u64 read_perf_counter(unsigned int counter)
+{
+	unsigned int low, high;
+
+	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 read_timestamp(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+#else
+static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
+static u64 read_timestamp(void) { return 0; }
+#endif
+
+int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count)
+{
+	struct perf_event_mmap_page *pc = map->base;
+	u32 seq, idx, time_mult = 0, time_shift = 0;
+	u64 cnt, cyc = 0, time_offset = 0, time_cycles = 0, time_mask = ~0ULL;
+
+	if (!pc || !pc->cap_user_rdpmc)
+		return -1;
+
+	do {
+		seq = READ_ONCE(pc->lock);
+		barrier();
+
+		count->ena = READ_ONCE(pc->time_enabled);
+		count->run = READ_ONCE(pc->time_running);
+
+		if (pc->cap_user_time && count->ena != count->run) {
+			cyc = read_timestamp();
+			time_mult = READ_ONCE(pc->time_mult);
+			time_shift = READ_ONCE(pc->time_shift);
+			time_offset = READ_ONCE(pc->time_offset);
+
+			if (pc->cap_user_time_short) {
+				time_cycles = READ_ONCE(pc->time_cycles);
+				time_mask = READ_ONCE(pc->time_mask);
+			}
+		}
+
+		idx = READ_ONCE(pc->index);
+		cnt = READ_ONCE(pc->offset);
+		if (pc->cap_user_rdpmc && idx) {
+			s64 evcnt = read_perf_counter(idx - 1);
+			u16 width = READ_ONCE(pc->pmc_width);
+
+			evcnt <<= 64 - width;
+			evcnt >>= 64 - width;
+			cnt += evcnt;
+		} else
+			return -1;
+
+		barrier();
+	} while (READ_ONCE(pc->lock) != seq);
+
+	if (count->ena != count->run) {
+		u64 delta;
+
+		/* Adjust for cap_usr_time_short, a nop if not */
+		cyc = time_cycles + ((cyc - time_cycles) & time_mask);
+
+		delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift);
+
+		count->ena += delta;
+		if (idx)
+			count->run += delta;
+
+		cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
+	}
+
+	count->val = cnt;
+
+	return 0;
+}
diff --git a/tools/lib/perf/tests/Makefile b/tools/lib/perf/tests/Makefile
index 96841775feaf..b536cc9a26dd 100644
--- a/tools/lib/perf/tests/Makefile
+++ b/tools/lib/perf/tests/Makefile
@@ -5,6 +5,8 @@ TESTS = test-cpumap test-threadmap test-evlist test-evsel
 TESTS_SO := $(addsuffix -so,$(TESTS))
 TESTS_A  := $(addsuffix -a,$(TESTS))
 
+TEST_ARGS := $(if $(V),-v)
+
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
@@ -28,9 +30,9 @@ all: $(TESTS_A) $(TESTS_SO)
 
 run:
 	@echo "running static:"
-	@for i in $(TESTS_A); do ./$$i; done
+	@for i in $(TESTS_A); do ./$$i $(TEST_ARGS); done
 	@echo "running dynamic:"
-	@for i in $(TESTS_SO); do LD_LIBRARY_PATH=../ ./$$i; done
+	@for i in $(TESTS_SO); do LD_LIBRARY_PATH=../ ./$$i $(TEST_ARGS); done
 
 clean:
 	$(call QUIET_CLEAN, tests)$(RM) $(TESTS_A) $(TESTS_SO)
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 0ad82d7a2a51..288b5feaefe2 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -120,6 +120,70 @@ static int test_stat_thread_enable(void)
 	return 0;
 }
 
+static int test_stat_user_read(int event)
+{
+	struct perf_counts_values counts = { .val = 0 };
+	struct perf_thread_map *threads;
+	struct perf_evsel *evsel;
+	struct perf_event_mmap_page *pc;
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_HARDWARE,
+		.config	= event,
+	};
+	int err, i;
+
+	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__mmap(evsel, 0);
+	__T("failed to mmap evsel", err == 0);
+
+	pc = perf_evsel__mmap_base(evsel, 0, 0);
+
+#if defined(__i386__) || defined(__x86_64__)
+	__T("userspace counter access not supported", pc->cap_user_rdpmc);
+	__T("userspace counter access not enabled", pc->index);
+	__T("userspace counter width not set", pc->pmc_width >= 32);
+#endif
+
+	perf_evsel__read(evsel, 0, 0, &counts);
+	__T("failed to read value for evsel", counts.val != 0);
+
+	for (i = 0; i < 5; i++) {
+		volatile int count = 0x10000 << i;
+		__u64 start, end, last = 0;
+
+		__T_VERBOSE("\tloop = %u, ", count);
+
+		perf_evsel__read(evsel, 0, 0, &counts);
+		start = counts.val;
+
+		while (count--) ;
+
+		perf_evsel__read(evsel, 0, 0, &counts);
+		end = counts.val;
+
+		__T("invalid counter data", (end - start) > last);
+		last = end - start;
+		__T_VERBOSE("count = %llu\n", end - start);
+	}
+
+	perf_evsel__munmap(evsel);
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+
+	perf_thread_map__put(threads);
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	__T_START;
@@ -129,6 +193,8 @@ int main(int argc, char **argv)
 	test_stat_cpu();
 	test_stat_thread();
 	test_stat_thread_enable();
+	test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
+	test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;