Merge tag 'perf-core-for-mingo-4.16-20171206' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Improve build messages for files needed by Intel-PT, originally copied
  from the kernel sources, that drifted from its original (Adrian Hunter)

- Allow computing 'perf stat' style metrics in 'perf script' (Andi Kleen)

- Fix 'perf report -D' output for user metadata events (Arnaldo Carvalho de Melo)

- Add feature test for pthread_barrier_t availability (Arnaldo Carvalho de Melo)

- Allow again using x86's asm.h when building for the 'bpf' clang target,
  making some 'perf test' LLVM/BPF entries work again (Arnaldo Carvalho de Melo)

- Use cpumaps in 'perf bench futex', eliminating some code duplication
  (Davidlohr Bueso)

- Improve PMU infrastructure to support amp64's ThunderX2 implementation
  defined core events (Ganapatrao Kulkarni)

- Add hint about how to add USDT probes for Node.js (Hansuk Hong)

- s/390 needs -fPIC to be incrementally linked or linked to shared
  libraries (Hendrik Brueckner)

- Use pthread_barrier to synch 'perf bench futex wake-parallel' waker
  threads (James Yang)

- Fix up build in hardened environments, such as Fedora 27 (Jiri Olsa)

- Add a tip about cacheline events in 'perf c2c' (Sangwon Hong)

- Set browser mode right before setup_browser(), because we may have
  errors printed before that, which were getting lost (Seokho Song)

- s390x doesn't support PERF_TYPE_BREAKPOINT, so disable 'perf test'
  cases 19 and 20 on s390x, that tests that feature (Thomas Richter)

- Fix unnecessary memory allocation for s390x 'perf annotate' objdump
  parsing, which could lead to thousands of needless entries in the
  instruction handling array (Thomas Richter)

- Fix objdump comment parsing for Intel mov dissassembly (Thomas Richter)

- Clarify usage of 'overwrite' and 'backward' in the evlist/mmap code,
  removing the 'overwrite' parameter from several functions as it was
  always used it as 'false' (Wang Nan)

- Fix 'perf record' backward recording, it wasn't doing what was
  expected: overwriting records when the ring buffer gets full (Wang Nan)

- Use more flexible pattern matching for CPU identification for perf
  vendor event's mapfile.csv, removing the need for a new perf binary
  for a sligthly different chip revision that shares the same set of
  counters (William Cohen)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

56 files changed, 722 insertions, 287 deletions

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2811fcf684cb..974ceb12c7f3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
         srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
-        brstackoff, callindent, insn, insnlen, synth, phys_addr.
+	brstackoff, callindent, insn, insnlen, synth, phys_addr, metric.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -217,6 +217,14 @@ OPTIONS
 
 	The brstackoff field will print an offset into a specific dso/binary.
 
+	With the metric option perf script can compute metrics for
+	sampling periods, similar to perf stat. This requires
+	specifying a group with multiple metrics with the :S option
+	for perf record. perf will sample on the first event, and
+	compute metrics for all the events in the group. Please note
+	that the metric computed is averaged over the whole sampling
+	period, not just for the sample point.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index db0ca3063eae..849599f39c5e 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -32,3 +32,5 @@ Order by the overhead of source file name and line number: perf report -s srclin
 System-wide collection from all CPUs: perf record -a
 Show current config key-value pairs: perf config --list
 Show user configuration overrides: perf config --user --list
+To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
+To report cacheline events from previous recording: perf c2c report
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f6786fa2419f..808066c823f7 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -41,6 +41,7 @@ ifeq ($(SRCARCH),x86)
     LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
   endif
   NO_PERF_REGS := 0
+  CFLAGS += -fPIC
 endif
 
 ifeq ($(SRCARCH),arm)
@@ -184,9 +185,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  ifeq ($(CC_NO_CLANG), 1)
-    PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
-  endif
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
@@ -263,6 +262,10 @@ ifeq ($(feature-pthread-attr-setaffinity-np), 1)
   CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP
 endif
 
+ifeq ($(feature-pthread-barrier), 1)
+  CFLAGS += -DHAVE_PTHREAD_BARRIER
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)
@@ -572,7 +575,6 @@ ifndef NO_GTK2
   endif
 endif
 
-
 ifdef NO_LIBPERL
   CFLAGS += -DNO_LIBPERL
 else
@@ -580,6 +582,8 @@ else
   PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
+  PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
   ifneq ($(feature-libperl), 1)
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index cef6fb38d17e..b1ab72d2a42e 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,3 +1,4 @@
+libperf-y += header.o
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
new file mode 100644
index 000000000000..534cd2507d83
--- /dev/null
+++ b/tools/perf/arch/arm64/util/header.c
@@ -0,0 +1,65 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <api/fs/fs.h>
+#include "header.h"
+
+#define MIDR "/regs/identification/midr_el1"
+#define MIDR_SIZE 19
+#define MIDR_REVISION_MASK      0xf
+#define MIDR_VARIANT_SHIFT      20
+#define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+	char *buf = NULL;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+	int cpu;
+	u64 midr = 0;
+	struct cpu_map *cpus;
+	FILE *file;
+
+	if (!sysfs || !pmu || !pmu->cpus)
+		return NULL;
+
+	buf = malloc(MIDR_SIZE);
+	if (!buf)
+		return NULL;
+
+	/* read midr from list of cpus mapped to this pmu */
+	cpus = cpu_map__get(pmu->cpus);
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
+				sysfs, cpus->map[cpu]);
+
+		file = fopen(path, "r");
+		if (!file) {
+			pr_debug("fopen failed for file %s\n", path);
+			continue;
+		}
+
+		if (!fgets(buf, MIDR_SIZE, file)) {
+			fclose(file);
+			continue;
+		}
+		fclose(file);
+
+		/* Ignore/clear Variant[23:20] and
+		 * Revision[3:0] of MIDR
+		 */
+		midr = strtoul(buf, NULL, 16);
+		midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK));
+		scnprintf(buf, MIDR_SIZE, "0x%016lx", midr);
+		/* got midr break loop */
+		break;
+	}
+
+	if (!midr) {
+		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+		free(buf);
+		buf = NULL;
+	}
+
+	cpu_map__put(cpus);
+	return buf;
+}
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 7a4cf80c207a..0b242664f5ea 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -35,7 +35,7 @@ get_cpuid(char *buffer, size_t sz)
 }
 
 char *
-get_cpuid_str(void)
+get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *bufp;
 
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index e0e466c650df..8c72b44444cb 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -18,7 +18,8 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	if (!strcmp(name, "br"))
 		ops = &ret_ops;
 
-	arch__associate_ins_ops(arch, name, ops);
+	if (ops)
+		arch__associate_ins_ops(arch, name, ops);
 	return ops;
 }
 
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e8c1e2..06abe8108b33 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	CHECK__(perf_evlist__open(evlist));
 
-	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
 	pc = evlist->mmap[0].base;
 	ret = perf_read_tsc_conversion(pc, &tc);
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 33027c5e6f92..b626d2bad9f1 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -66,7 +66,7 @@ get_cpuid(char *buffer, size_t sz)
 }
 
 char *
-get_cpuid_str(void)
+get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 58ae6ed8f38b..2defb6df7fd0 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -24,6 +24,7 @@
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <sys/time.h>
@@ -118,11 +119,12 @@ static void print_summary(void)
 int bench_futex_hash(int argc, const char **argv)
 {
 	int ret = 0;
-	cpu_set_t cpu;
+	cpu_set_t cpuset;
 	struct sigaction act;
-	unsigned int i, ncpus;
+	unsigned int i;
 	pthread_attr_t thread_attr;
 	struct worker *worker = NULL;
+	struct cpu_map *cpu;
 
 	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
 	if (argc) {
@@ -130,14 +132,16 @@ int bench_futex_hash(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		goto errmem;
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
 	if (!nthreads) /* default to the number of CPUs */
-		nthreads = ncpus;
+		nthreads = cpu->nr;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
@@ -163,10 +167,10 @@ int bench_futex_hash(int argc, const char **argv)
 		if (!worker[i].futex)
 			goto errmem;
 
-		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
 		if (ret)
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
@@ -217,6 +221,7 @@ int bench_futex_hash(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	free(cpu);
 	return ret;
 errmem:
 	err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 08653ae8a8c4..8e9c4753e304 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -32,7 +33,7 @@ static struct worker *worker;
 static unsigned int nsecs = 10;
 static bool silent = false, multi = false;
 static bool done = false, fshared = false;
-static unsigned int ncpus, nthreads = 0;
+static unsigned int nthreads = 0;
 static int futex_flag = 0;
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -113,9 +114,10 @@ static void *workerfn(void *arg)
 	return NULL;
 }
 
-static void create_threads(struct worker *w, pthread_attr_t thread_attr)
+static void create_threads(struct worker *w, pthread_attr_t thread_attr,
+			   struct cpu_map *cpu)
 {
-	cpu_set_t cpu;
+	cpu_set_t cpuset;
 	unsigned int i;
 
 	threads_starting = nthreads;
@@ -130,10 +132,10 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
 		} else
 			worker[i].futex = &global_futex;
 
-		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
 		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
@@ -147,19 +149,22 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	unsigned int i;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	struct cpu_map *cpu;
 
 	argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
 	if (argc)
 		goto err;
 
-	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		err(EXIT_FAILURE, "calloc");
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
 	if (!nthreads)
-		nthreads = ncpus;
+		nthreads = cpu->nr;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
@@ -180,7 +185,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&start, NULL);
 
-	create_threads(worker, thread_attr);
+	create_threads(worker, thread_attr, cpu);
 	pthread_attr_destroy(&thread_attr);
 
 	pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 1058c194608a..fc692efa0c05 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -40,7 +41,7 @@ static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
-static unsigned int ncpus, threads_starting, nthreads = 0;
+static unsigned int threads_starting, nthreads = 0;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -83,19 +84,19 @@ static void *workerfn(void *arg __maybe_unused)
 }
 
 static void block_threads(pthread_t *w,
-			  pthread_attr_t thread_attr)
+			  pthread_attr_t thread_attr, struct cpu_map *cpu)
 {
-	cpu_set_t cpu;
+	cpu_set_t cpuset;
 	unsigned int i;
 
 	threads_starting = nthreads;
 
 	/* create and block all threads */
 	for (i = 0; i < nthreads; i++) {
-		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
 		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -116,19 +117,22 @@ int bench_futex_requeue(int argc, const char **argv)
 	unsigned int i, j;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	struct cpu_map *cpu;
 
 	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
 	if (argc)
 		goto err;
 
-	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		err(EXIT_FAILURE, "cpu_map__new");
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
 	if (!nthreads)
-		nthreads = ncpus;
+		nthreads = cpu->nr;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
@@ -156,7 +160,7 @@ int bench_futex_requeue(int argc, const char **argv)
 		struct timeval start, end, runtime;
 
 		/* create, launch & block all threads */
-		block_threads(worker, thread_attr);
+		block_threads(worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index b4732dad9f89..69d8fdc87315 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,7 +7,17 @@
  * for each individual thread to service its share of work. Ultimately
  * it can be used to measure futex_wake() changes.
  */
+#include "bench.h"
+#include <linux/compiler.h>
+#include "../util/debug.h"
 
+#ifndef HAVE_PTHREAD_BARRIER
+int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+	pr_err("%s: pthread_barrier_t unavailable, disabling this test...\n", __func__);
+	return 0;
+}
+#else /* HAVE_PTHREAD_BARRIER */
 /* For the CLR_() macros */
 #include <string.h>
 #include <pthread.h>
@@ -15,12 +25,11 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
-#include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -42,8 +51,9 @@ static bool done = false, silent = false, fshared = false;
 static unsigned int nblocked_threads = 0, nwaking_threads = 0;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
+static pthread_barrier_t barrier;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting;
+static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -64,6 +74,8 @@ static void *waking_workerfn(void *arg)
 	struct thread_data *waker = (struct thread_data *) arg;
 	struct timeval start, end;
 
+	pthread_barrier_wait(&barrier);
+
 	gettimeofday(&start, NULL);
 
 	waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
@@ -84,6 +96,8 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 	pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
 
+	pthread_barrier_init(&barrier, NULL, nwaking_threads + 1);
+
 	/* create and block all threads */
 	for (i = 0; i < nwaking_threads; i++) {
 		/*
@@ -96,9 +110,13 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 			err(EXIT_FAILURE, "pthread_create");
 	}
 
+	pthread_barrier_wait(&barrier);
+
 	for (i = 0; i < nwaking_threads; i++)
 		if (pthread_join(td[i].worker, NULL))
 			err(EXIT_FAILURE, "pthread_join");
+
+	pthread_barrier_destroy(&barrier);
 }
 
 static void *blocked_workerfn(void *arg __maybe_unused)
@@ -119,19 +137,20 @@ static void *blocked_workerfn(void *arg __maybe_unused)
 	return NULL;
 }
 
-static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
+			  struct cpu_map *cpu)
 {
-	cpu_set_t cpu;
+	cpu_set_t cpuset;
 	unsigned int i;
 
 	threads_starting = nblocked_threads;
 
 	/* create and block all threads */
 	for (i = 0; i < nblocked_threads; i++) {
-		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
 		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
@@ -205,6 +224,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	struct sigaction act;
 	pthread_attr_t thread_attr;
 	struct thread_data *waking_worker;
+	struct cpu_map *cpu;
 
 	argc = parse_options(argc, argv, options,
 			     bench_futex_wake_parallel_usage, 0);
@@ -217,9 +237,12 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		err(EXIT_FAILURE, "calloc");
+
 	if (!nblocked_threads)
-		nblocked_threads = ncpus;
+		nblocked_threads = cpu->nr;
 
 	/* some sanity checks */
 	if (nwaking_threads > nblocked_threads || !nwaking_threads)
@@ -259,7 +282,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 			err(EXIT_FAILURE, "calloc");
 
 		/* create, launch & block all threads */
-		block_threads(blocked_worker, thread_attr);
+		block_threads(blocked_worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
@@ -297,3 +320,4 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	free(blocked_worker);
 	return ret;
 }
+#endif /* HAVE_PTHREAD_BARRIER */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 8c5c0b6b5c97..e8181ad7d088 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -89,19 +90,19 @@ static void print_summary(void)
 }
 
 static void block_threads(pthread_t *w,
-			  pthread_attr_t thread_attr)
+			  pthread_attr_t thread_attr, struct cpu_map *cpu)
 {
-	cpu_set_t cpu;
+	cpu_set_t cpuset;
 	unsigned int i;
 
 	threads_starting = nthreads;
 
 	/* create and block all threads */
 	for (i = 0; i < nthreads; i++) {
-		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
 		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -122,6 +123,7 @@ int bench_futex_wake(int argc, const char **argv)
 	unsigned int i, j;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	struct cpu_map *cpu;
 
 	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
 	if (argc) {
@@ -129,7 +131,9 @@ int bench_futex_wake(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		err(EXIT_FAILURE, "calloc");
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -161,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv)
 		struct timeval start, end, runtime;
 
 		/* create, launch & block all threads */
-		block_threads(worker, thread_attr);
+		block_threads(worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 597c7de9bec9..98853162eae9 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,7 +1044,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
-	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
 		ui__error("Failed to mmap the events: %s\n",
 			  str_error_r(errno, sbuf, sizeof(sbuf)));
 		perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 003255910c05..0a5749ef8b94 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -301,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
 	struct record_opts *opts = &rec->opts;
 	char msg[512];
 
-	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode) < 0) {
 		if (errno == EPERM) {
@@ -372,6 +372,8 @@ try_again:
 			ui__error("%s\n", msg);
 			goto out;
 		}
+
+		pos->supported = true;
 	}
 
 	if (perf_evlist__apply_filters(evlist, &pos)) {
@@ -477,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-				    bool backward)
+				    bool overwrite)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
@@ -487,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (!evlist)
 		return 0;
 
-	maps = backward ? evlist->backward_mmap : evlist->mmap;
+	maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
 	if (!maps)
 		return 0;
 
-	if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+	if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], evlist->overwrite, backward, rec, record__pushfn) != 0) {
+			if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -518,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
-	if (backward)
+	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
 	return rc;
@@ -690,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
 	if (evlist) {
 		if (evlist->mmap && evlist->mmap[0].base)
 			return evlist->mmap[0].base;
-		if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-			return evlist->backward_mmap[0].base;
+		if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+			return evlist->overwrite_mmap[0].base;
 	}
 	return NULL;
 }
@@ -784,6 +786,28 @@ static int record__synthesize(struct record *rec, bool tail)
 					 perf_event__synthesize_guest_os, tool);
 	}
 
+	err = perf_event__synthesize_extra_attr(&rec->tool,
+						rec->evlist,
+						process_synthesized_event,
+						data->is_pipe);
+	if (err)
+		goto out;
+
+	err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->threads,
+						 process_synthesized_event,
+						NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->cpus,
+					     process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize cpu map.\n");
+		return err;
+	}
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address,
 					    opts->proc_map_timeout, 1);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index af5dd038195e..eb9ce6327e71 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -921,13 +921,6 @@ int cmd_report(int argc, const char **argv)
 		return -EINVAL;
 	}
 
-	if (report.use_stdio)
-		use_browser = 0;
-	else if (report.use_tui)
-		use_browser = 1;
-	else if (report.use_gtk)
-		use_browser = 2;
-
 	if (report.inverted_callchain)
 		callchain_param.order = ORDER_CALLER;
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
@@ -1014,6 +1007,13 @@ repeat:
 		perf_hpp_list.need_collapse = true;
 	}
 
+	if (report.use_stdio)
+		use_browser = 0;
+	else if (report.use_tui)
+		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
+
 	/* Force tty output for header output and per-thread stat. */
 	if (report.header || report.header_only || report.show_threads)
 		use_browser = 0;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ee7c7aaaae72..39d8b55f0db3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,6 +22,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/color.h"
 #include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
@@ -90,6 +91,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SYNTH           = 1U << 25,
 	PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
 	PERF_OUTPUT_UREGS	    = 1U << 27,
+	PERF_OUTPUT_METRIC	    = 1U << 28,
 };
 
 struct output_option {
@@ -124,6 +126,7 @@ struct output_option {
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 	{.str = "synth", .field = PERF_OUTPUT_SYNTH},
 	{.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
+	{.str = "metric", .field = PERF_OUTPUT_METRIC},
 };
 
 enum {
@@ -215,12 +218,20 @@ struct perf_evsel_script {
        char *filename;
        FILE *fp;
        u64  samples;
+       /* For metric output */
+       u64  val;
+       int  gnum;
 };
 
+static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel)
+{
+	return (struct perf_evsel_script *)evsel->priv;
+}
+
 static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
 							struct perf_data *data)
 {
-	struct perf_evsel_script *es = malloc(sizeof(*es));
+	struct perf_evsel_script *es = zalloc(sizeof(*es));
 
 	if (es != NULL) {
 		if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
@@ -228,7 +239,6 @@ static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel
 		es->fp = fopen(es->filename, "w");
 		if (es->fp == NULL)
 			goto out_free_filename;
-		es->samples = 0;
 	}
 
 	return es;
@@ -1472,6 +1482,86 @@ static int data_src__fprintf(u64 data_src, FILE *fp)
 	return fprintf(fp, "%-*s", maxlen, out);
 }
 
+struct metric_ctx {
+	struct perf_sample	*sample;
+	struct thread		*thread;
+	struct perf_evsel	*evsel;
+	FILE 			*fp;
+};
+
+static void script_print_metric(void *ctx, const char *color,
+			        const char *fmt,
+			        const char *unit, double val)
+{
+	struct metric_ctx *mctx = ctx;
+
+	if (!fmt)
+		return;
+	perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+				   mctx->fp);
+	fputs("\tmetric: ", mctx->fp);
+	if (color)
+		color_fprintf(mctx->fp, color, fmt, val);
+	else
+		printf(fmt, val);
+	fprintf(mctx->fp, " %s\n", unit);
+}
+
+static void script_new_line(void *ctx)
+{
+	struct metric_ctx *mctx = ctx;
+
+	perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+				   mctx->fp);
+	fputs("\tmetric: ", mctx->fp);
+}
+
+static void perf_sample__fprint_metric(struct perf_script *script,
+				       struct thread *thread,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       FILE *fp)
+{
+	struct perf_stat_output_ctx ctx = {
+		.print_metric = script_print_metric,
+		.new_line = script_new_line,
+		.ctx = &(struct metric_ctx) {
+				.sample = sample,
+				.thread = thread,
+				.evsel  = evsel,
+				.fp     = fp,
+			 },
+		.force_header = false,
+	};
+	struct perf_evsel *ev2;
+	static bool init;
+	u64 val;
+
+	if (!init) {
+		perf_stat__init_shadow_stats();
+		init = true;
+	}
+	if (!evsel->stats)
+		perf_evlist__alloc_stats(script->session->evlist, false);
+	if (evsel_script(evsel->leader)->gnum++ == 0)
+		perf_stat__reset_shadow_stats();
+	val = sample->period * evsel->scale;
+	perf_stat__update_shadow_stats(evsel,
+				       val,
+				       sample->cpu);
+	evsel_script(evsel)->val = val;
+	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
+		for_each_group_member (ev2, evsel->leader) {
+			perf_stat__print_shadow_stats(ev2,
+						      evsel_script(ev2)->val,
+						      sample->cpu,
+						      &ctx,
+						      NULL);
+		}
+		evsel_script(evsel->leader)->gnum = 0;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1559,6 +1649,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
 	fprintf(fp, "\n");
+
+	if (PRINT_FIELD(METRIC))
+		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
 }
 
 static struct scripting_ops	*scripting_ops;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 59af5a8419e2..a027b4712e48 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -458,19 +458,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static bool has_unit(struct perf_evsel *counter)
-{
-	return counter->unit && *counter->unit;
-}
-
-static bool has_scale(struct perf_evsel *counter)
-{
-	return counter->scale != 1;
-}
-
 static int perf_stat_synthesize_config(bool is_pipe)
 {
-	struct perf_evsel *counter;
 	int err;
 
 	if (is_pipe) {
@@ -482,53 +471,10 @@ static int perf_stat_synthesize_config(bool is_pipe)
 		}
 	}
 
-	/*
-	 * Synthesize other events stuff not carried within
-	 * attr event - unit, scale, name
-	 */
-	evlist__for_each_entry(evsel_list, counter) {
-		if (!counter->supported)
-			continue;
-
-		/*
-		 * Synthesize unit and scale only if it's defined.
-		 */
-		if (has_unit(counter)) {
-			err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel unit.\n");
-				return err;
-			}
-		}
-
-		if (has_scale(counter)) {
-			err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel scale.\n");
-				return err;
-			}
-		}
-
-		if (counter->own_cpus) {
-			err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel scale.\n");
-				return err;
-			}
-		}
-
-		/*
-		 * Name is needed only for pipe output,
-		 * perf.data carries event names.
-		 */
-		if (is_pipe) {
-			err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel name.\n");
-				return err;
-			}
-		}
-	}
+	err = perf_event__synthesize_extra_attr(NULL,
+						evsel_list,
+						process_synthesized_event,
+						is_pipe);
 
 	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
 						process_synthesized_event,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0077724fb24f..540461f5e345 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ try_again:
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+	if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
 			    errno, str_error_r(errno, msg, sizeof(msg)));
 		goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 84debdbad327..7c57898095ea 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_apply_filters;
 
-	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
 	if (err < 0)
 		goto out_error_mmap;
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 77406d25e521..e66a8a7bcced 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -45,7 +45,6 @@ include/uapi/asm-generic/mman-common.h
 
 check () {
   file=$1
-  opts="--ignore-blank-lines --ignore-space-change"
 
   shift
   while [ -n "$*" ]; do
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
new file mode 100644
index 000000000000..2db45c40ebc7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
@@ -0,0 +1,62 @@
+[
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, read",
+        "EventCode": "0x40",
+        "EventName": "l1d_cache_rd",
+        "BriefDescription": "L1D cache read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, write ",
+        "EventCode": "0x41",
+        "EventName": "l1d_cache_wr",
+        "BriefDescription": "L1D cache write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, read",
+        "EventCode": "0x42",
+        "EventName": "l1d_cache_refill_rd",
+        "BriefDescription": "L1D cache refill read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, write",
+        "EventCode": "0x43",
+        "EventName": "l1d_cache_refill_wr",
+        "BriefDescription": "L1D refill write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, read",
+        "EventCode": "0x4C",
+        "EventName": "l1d_tlb_refill_rd",
+        "BriefDescription": "L1D tlb refill read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, write",
+        "EventCode": "0x4D",
+        "EventName": "l1d_tlb_refill_wr",
+        "BriefDescription": "L1D tlb refill write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, read",
+        "EventCode": "0x4E",
+        "EventName": "l1d_tlb_rd",
+        "BriefDescription": "L1D tlb read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, write",
+        "EventCode": "0x4F",
+        "EventName": "l1d_tlb_wr",
+        "BriefDescription": "L1D tlb write",
+    },
+    {
+        "PublicDescription": "Bus access read",
+        "EventCode": "0x60",
+        "EventName": "bus_access_rd",
+        "BriefDescription": "Bus access read",
+   },
+   {
+        "PublicDescription": "Bus access write",
+        "EventCode": "0x61",
+        "EventName": "bus_access_wr",
+        "BriefDescription": "Bus access write",
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
new file mode 100644
index 000000000000..219d6756134e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -0,0 +1,15 @@
+# Format:
+#	MIDR,Version,JSON/file/pathname,Type
+#
+# where
+#	MIDR	Processor version
+#		Variant[23:20] and Revision [3:0] should be zero.
+#	Version could be used to track version of of JSON file
+#		but currently unused.
+#	JSON/file/pathname is the path to JSON file, relative
+#		to tools/perf/pmu-events/arch/arm64/.
+#	Type is core, uncore etc
+#
+#
+#Family-model,Version,Filename,EventType
+0x00000000420f5160,v1,cavium,core
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index a0f3a11ca19f..229150e7ab7d 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -13,13 +13,5 @@
 #
 
 # Power8 entries
-004b0000,1,power8,core
-004b0201,1,power8,core
-004c0000,1,power8,core
-004d0000,1,power8,core
-004d0100,1,power8,core
-004d0200,1,power8,core
-004c0100,1,power8,core
-004e0100,1,power9,core
-004e0200,1,power9,core
-004e1200,1,power9,core
+004[bcd][[:xdigit:]]{4},1,power8,core
+004e[[:xdigit:]]{4},1,power9,core
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index fe1a2c47cabf..93656f2fd53a 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -23,10 +23,7 @@ GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
 GenuineIntel-6-2E,v2,nehalemex,core
-GenuineIntel-6-4E,v24,skylake,core
-GenuineIntel-6-5E,v24,skylake,core
-GenuineIntel-6-8E,v24,skylake,core
-GenuineIntel-6-9E,v24,skylake,core
+GenuineIntel-6-[4589]E,v24,skylake,core
 GenuineIntel-6-37,v13,silvermont,core
 GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 9eb7047bafe4..b578aa26e375 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -116,6 +116,43 @@ static void fixdesc(char *s)
 		*e = 0;
 }
 
+/* Add escapes for '\' so they are proper C strings. */
+static char *fixregex(char *s)
+{
+	int len = 0;
+	int esc_count = 0;
+	char *fixed = NULL;
+	char *p, *q;
+
+	/* Count the number of '\' in string */
+	for (p = s; *p; p++) {
+		++len;
+		if (*p == '\\')
+			++esc_count;
+	}
+
+	if (esc_count == 0)
+		return s;
+
+	/* allocate space for a new string */
+	fixed = (char *) malloc(len + 1);
+	if (!fixed)
+		return NULL;
+
+	/* copy over the characters */
+	q = fixed;
+	for (p = s; *p; p++) {
+		if (*p == '\\') {
+			*q = '\\';
+			++q;
+		}
+		*q = *p;
+		++q;
+	}
+	*q = '\0';
+	return fixed;
+}
+
 static struct msrmap {
 	const char *num;
 	const char *pname;
@@ -648,7 +685,7 @@ static int process_mapfile(FILE *outfp, char *fpath)
 		}
 		line[strlen(line)-1] = '\0';
 
-		cpuid = strtok_r(p, ",", &save);
+		cpuid = fixregex(strtok_r(p, ",", &save));
 		version = strtok_r(NULL, ",", &save);
 		fname = strtok_r(NULL, ",", &save);
 		type = strtok_r(NULL, ",", &save);
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 43a8c6ac4070..4035d43523c3 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 
-		perf_mmap__read_catchup(&evlist->backward_mmap[i]);
-		while ((event = perf_mmap__read_backward(&evlist->backward_mmap[i])) != NULL) {
+		perf_mmap__read_catchup(&evlist->overwrite_mmap[i]);
+		while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 	int err;
 	char sbuf[STRERR_BUFSIZE];
 
-	err = perf_evlist__mmap(evlist, mmap_pages, false);
+	err = perf_evlist__mmap(evlist, mmap_pages);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 335b695f4970..a467615c5a0e 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -296,7 +296,7 @@ bool test__bp_signal_is_supported(void)
  * instruction breakpoint using the perf event interface.
  * Once it's there we can release this.
  */
-#ifdef __powerpc__
+#if defined(__powerpc__) || defined(__s390x__)
 	return false;
 #else
 	return true;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cdf4d5d..c433dd30975a 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -167,7 +167,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		goto out_delete_evlist;
 	}
 
-	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	err = perf_evlist__mmap(evlist, opts.mmap_pages);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index fcc8984bc329..3bf7b145b826 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -639,7 +639,7 @@ static int do_test_code_reading(bool try_kcore)
 		break;
 	}
 
-	ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+	ret = perf_evlist__mmap(evlist, UINT_MAX);
 	if (ret < 0) {
 		pr_debug("perf_evlist__mmap failed\n");
 		goto out_put;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 842d33637a18..c46530918938 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -95,7 +95,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un
 		goto out_err;
 	}
 
-	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
 	/*
 	 * First, test that a 'comm' event can be found when the event is
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 91f10d6d9ae2..c0e971da965c 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		expected_nr_events[i] = 1 + rand() % 127;
 	}
 
-	if (perf_evlist__mmap(evlist, 128, false) < 0) {
+	if (perf_evlist__mmap(evlist, 128) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index d9619d265314..97c9407d02a0 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -64,7 +64,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 		goto out_delete_evlist;
 	}
 
-	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	err = perf_evlist__mmap(evlist, UINT_MAX);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index c34904d37705..0afafab85238 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -141,7 +141,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	 * fds in the same CPU to be injected in the same mmap ring buffer
 	 * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
 	 */
-	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	err = perf_evlist__mmap(evlist, opts.mmap_pages);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index c6937ed12e6b..f6c72f915d48 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		goto out_delete_evlist;
 	}
 
-	err = perf_evlist__mmap(evlist, 128, false);
+	err = perf_evlist__mmap(evlist, 128);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 7d3f4bf9534f..33e00295a972 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -449,7 +449,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 		goto out;
 	}
 
-	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	err = perf_evlist__mmap(evlist, UINT_MAX);
 	if (err) {
 		pr_debug("perf_evlist__mmap failed!\n");
 		goto out_err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5d06ac81f7f1..01b62b81751b 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -101,7 +101,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		goto out_delete_evlist;
 	}
 
-	if (perf_evlist__mmap(evlist, 128, false) < 0) {
+	if (perf_evlist__mmap(evlist, 128) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 22ea7936d92f..facad1e279a8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -322,6 +322,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 		return 0;
 
 	*addrp = strtoull(comment, &endptr, 16);
+	if (endptr == comment)
+		return 0;
 	name = strchr(endptr, '<');
 	if (name == NULL)
 		return -1;
@@ -435,8 +437,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 		return 0;
 
 	comment = ltrim(comment);
-	comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
-	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
 	return 0;
 
@@ -480,7 +482,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 		return 0;
 
 	comment = ltrim(comment);
-	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
 	return 0;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 199bb82efbcd..3570355bcf39 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
-	zfree(&evlist->backward_mmap);
+	zfree(&evlist->overwrite_mmap);
 	fdarray__exit(&evlist->pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
 	int i;
 
-	if (!evlist->backward_mmap)
+	if (!evlist->overwrite_mmap)
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->backward_mmap[i].fd;
+		int fd = evlist->overwrite_mmap[i].fd;
 		int err;
 
 		if (fd < 0)
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
 	 * No need for read-write ring buffer: kernel stop outputting when
 	 * it hit md->prev (perf_mmap__consume()).
 	 */
-	return perf_mmap__read_forward(md, evlist->overwrite);
+	return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
+	perf_mmap__consume(&evlist->mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 		for (i = 0; i < evlist->nr_mmaps; i++)
 			perf_mmap__munmap(&evlist->mmap[i]);
 
-	if (evlist->backward_mmap)
+	if (evlist->overwrite_mmap)
 		for (i = 0; i < evlist->nr_mmaps; i++)
-			perf_mmap__munmap(&evlist->backward_mmap[i]);
+			perf_mmap__munmap(&evlist->overwrite_mmap[i]);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	perf_evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
-	zfree(&evlist->backward_mmap);
+	zfree(&evlist->overwrite_mmap);
 }
 
 static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
@@ -800,7 +800,7 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu_idx,
-				       int thread, int *_output, int *_output_backward)
+				       int thread, int *_output, int *_output_overwrite)
 {
 	struct perf_evsel *evsel;
 	int revent;
@@ -812,18 +812,20 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		int fd;
 		int cpu;
 
+		mp->prot = PROT_READ | PROT_WRITE;
 		if (evsel->attr.write_backward) {
-			output = _output_backward;
-			maps = evlist->backward_mmap;
+			output = _output_overwrite;
+			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
 				maps = perf_evlist__alloc_mmap(evlist);
 				if (!maps)
 					return -1;
-				evlist->backward_mmap = maps;
+				evlist->overwrite_mmap = maps;
 				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
 					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
 			}
+			mp->prot &= ~PROT_WRITE;
 		}
 
 		if (evsel->system_wide && thread)
@@ -884,14 +886,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
-		int output_backward = -1;
+		int output_overwrite = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output, &output_backward))
+							thread, &output, &output_overwrite))
 				goto out_unmap;
 		}
 	}
@@ -912,13 +914,13 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
-		int output_backward = -1;
+		int output_overwrite = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output, &output_backward))
+						&output, &output_overwrite))
 			goto out_unmap;
 	}
 
@@ -1052,15 +1054,18 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-			 bool overwrite, unsigned int auxtrace_pages,
+			 unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	struct mmap_params mp = {
-		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
-	};
+	/*
+	 * Delay setting mp.prot: set it before calling perf_mmap__mmap.
+	 * Its value is decided by evsel's write_backward.
+	 * So &mp should not be passed through const pointer.
+	 */
+	struct mmap_params mp;
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist);
@@ -1070,7 +1075,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	evlist->overwrite = overwrite;
 	evlist->mmap_len = perf_evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mp.mask = evlist->mmap_len - page_size - 1;
@@ -1091,10 +1095,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite)
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1750,7 +1753,7 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 		RESUME,
 	} action = NONE;
 
-	if (!evlist->backward_mmap)
+	if (!evlist->overwrite_mmap)
 		return;
 
 	switch (old_state) {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4e8131dacbd7..75160666d305 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
-	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
 	size_t		 mmap_len;
@@ -45,7 +44,7 @@ struct perf_evlist {
 	} workload;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
-	struct perf_mmap *backward_mmap;
+	struct perf_mmap *overwrite_mmap;
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
@@ -169,10 +168,9 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-			 bool overwrite, unsigned int auxtrace_pages,
+			 unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite);
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite);
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 size_t perf_evlist__mmap_size(unsigned long pages);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 7c0e9d587bfa..5890e08e0754 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3258,6 +3258,74 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	return err;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+	return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+	return counter->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+				      struct perf_evlist *evsel_list,
+				      perf_event__handler_t process,
+				      bool is_pipe)
+{
+	struct perf_evsel *counter;
+	int err;
+
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each_entry(evsel_list, counter) {
+		if (!counter->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(counter)) {
+			err = perf_event__synthesize_event_update_unit(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(counter)) {
+			err = perf_event__synthesize_event_update_scale(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel counter.\n");
+				return err;
+			}
+		}
+
+		if (counter->own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel cpus.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
 int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 29ccbfdf8724..317fb901e47f 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "env.h"
+#include "pmu.h"
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
@@ -107,6 +108,11 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 				    struct perf_evlist *evlist,
 				    perf_event__handler_t process);
 
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+				      struct perf_evlist *evsel_list,
+				      perf_event__handler_t process,
+				      bool is_pipe);
+
 int perf_event__process_feature(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_session *session);
@@ -166,5 +172,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
  */
 int get_cpuid(char *buffer, size_t sz);
 
-char *get_cpuid_str(void);
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 10e0814bb8d2..1b704fbea9de 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -11,15 +11,21 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
-	test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
-	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-	diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-	|| echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+	test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
+	((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
+	((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 0ddd9c199227..e48410c99b39 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -38,6 +38,10 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 	struct metric_event me = {
 		.evsel = evsel
 	};
+
+	if (!metric_events)
+		return NULL;
+
 	nd = rblist__find(metric_events, &me);
 	if (nd)
 		return container_of(nd, struct metric_event, nd);
@@ -270,7 +274,7 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
 void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 			bool raw)
 {
-	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
 	int i;
 	struct rblist groups;
@@ -368,7 +372,7 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
-	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
 	int ret = -EINVAL;
 	int i, j;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c7d577..05076e683938 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 					 u64 start, u64 end, u64 *prev)
 {
 	unsigned char *data = map->base + page_size;
 	union perf_event *event = NULL;
 	int diff = end - start;
 
-	if (check_messup) {
-		/*
-		 * If we're further behind than half the buffer, there's a chance
-		 * the writer will bite our tail and mess up the samples under us.
-		 *
-		 * If we somehow ended up ahead of the 'end', we got messed up.
-		 *
-		 * In either case, truncate and restart at 'end'.
-		 */
-		if (diff > map->mask / 2 || diff < 0) {
-			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-			/*
-			 * 'end' points to a known good entry, start there.
-			 */
-			start = end;
-			diff = 0;
-		}
-	}
-
 	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
@@ -89,7 +69,7 @@ broken_event:
 	return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
 	u64 head;
 	u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_mess
 
 	head = perf_mmap__read_head(map);
 
-	return perf_mmap__read(map, check_messup, old, head, &map->prev);
+	return perf_mmap__read(map, old, head, &map->prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
 	else
 		end = head + map->mask + 1;
 
-	return perf_mmap__read(map, false, start, end, &map->prev);
+	return perf_mmap__read(map, start, end, &map->prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
@@ -254,18 +234,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
 	return 0;
 }
 
-static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 {
 	struct perf_event_header *pheader;
 	u64 evt_head = head;
 	int size = mask + 1;
 
-	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+	pr_debug2("overwrite_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
 	pheader = (struct perf_event_header *)(buf + (head & mask));
 	*start = head;
 	while (true) {
 		if (evt_head - head >= (unsigned int)size) {
-			pr_debug("Finished reading backward ring buffer: rewind\n");
+			pr_debug("Finished reading overwrite ring buffer: rewind\n");
 			if (evt_head - head > (unsigned int)size)
 				evt_head -= pheader->size;
 			*end = evt_head;
@@ -275,7 +255,7 @@ static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64
 		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
 
 		if (pheader->size == 0) {
-			pr_debug("Finished reading backward ring buffer: get start\n");
+			pr_debug("Finished reading overwrite ring buffer: get start\n");
 			*end = evt_head;
 			return 0;
 		}
@@ -287,19 +267,7 @@ static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64
 	return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-			 u64 *start, u64 *end, bool backward)
-{
-	if (!backward) {
-		*start = old;
-		*end = head;
-		return 0;
-	}
-
-	return backward_rb_find_range(data, mask, head, start, end);
-}
-
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 		    void *to, int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
@@ -310,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
 	void *buf;
 	int rc = 0;
 
-	if (rb_find_range(data, md->mask, head, old, &start, &end, backward))
-		return -1;
+	start = overwrite ? head : old;
+	end = overwrite ? old : head;
 
 	if (start == end)
 		return 0;
 
 	size = end - start;
 	if (size > (unsigned long)(md->mask) + 1) {
-		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+		if (!overwrite) {
+			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
-		md->prev = head;
-		perf_mmap__consume(md, overwrite || backward);
-		return 0;
+			md->prev = head;
+			perf_mmap__consume(md, overwrite);
+			return 0;
+		}
+
+		/*
+		 * Backward ring buffer is full. We still have a chance to read
+		 * most of data from it.
+		 */
+		if (overwrite_rb_find_range(data, md->mask, head, &start, &end))
+			return -1;
 	}
 
 	if ((start & md->mask) + size != (end & md->mask)) {
@@ -346,7 +323,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, overwrite || backward);
+	perf_mmap__consume(md, overwrite);
 out:
 	return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b827b05..d640273b7762 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,10 +86,10 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 	pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
 		    void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 80fb1593913a..57e38fdf0b34 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -12,6 +12,7 @@
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
+#include <regex.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
@@ -537,17 +538,45 @@ static bool pmu_is_uncore(const char *name)
 }
 
 /*
+ *  PMU CORE devices have different name other than cpu in sysfs on some
+ *  platforms. looking for possible sysfs files to identify as core device.
+ */
+static int is_pmu_core(const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return 0;
+
+	/* Look for cpu sysfs (x86 and others) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
+	if ((stat(path, &st) == 0) &&
+			(strncmp(name, "cpu", strlen("cpu")) == 0))
+		return 1;
+
+	/* Look for cpu sysfs (specific to arm) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
+				sysfs, name);
+	if (stat(path, &st) == 0)
+		return 1;
+
+	return 0;
+}
+
+/*
  * Return the CPU id as a raw string.
  *
  * Each architecture should provide a more precise id string that
  * can be use to match the architecture's "mapfile".
  */
-char * __weak get_cpuid_str(void)
+char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;
 }
 
-static char *perf_pmu__getcpuid(void)
+static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;
 	static bool printed;
@@ -556,7 +585,7 @@ static char *perf_pmu__getcpuid(void)
 	if (cpuid)
 		cpuid = strdup(cpuid);
 	if (!cpuid)
-		cpuid = get_cpuid_str();
+		cpuid = get_cpuid_str(pmu);
 	if (!cpuid)
 		return NULL;
 
@@ -567,22 +596,45 @@ static char *perf_pmu__getcpuid(void)
 	return cpuid;
 }
 
-struct pmu_events_map *perf_pmu__find_map(void)
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 {
 	struct pmu_events_map *map;
-	char *cpuid = perf_pmu__getcpuid();
+	char *cpuid = perf_pmu__getcpuid(pmu);
 	int i;
 
+	/* on some platforms which uses cpus map, cpuid can be NULL for
+	 * PMUs other than CORE PMUs.
+	 */
+	if (!cpuid)
+		return NULL;
+
 	i = 0;
 	for (;;) {
+		regex_t re;
+		regmatch_t pmatch[1];
+		int match;
+
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (!strcmp(map->cpuid, cpuid))
+		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
+			/* Warn unable to generate match particular string. */
+			pr_info("Invalid regular expression %s\n", map->cpuid);
 			break;
+		}
+
+		match = !regexec(&re, cpuid, 1, pmatch, 0);
+		regfree(&re);
+		if (match) {
+			size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+			/* Verify the entire string matched. */
+			if (match_len == strlen(cpuid))
+				break;
+		}
 	}
 	free(cpuid);
 	return map;
@@ -593,13 +645,14 @@ struct pmu_events_map *perf_pmu__find_map(void)
  * to the current running CPU. Then, add all PMU events from that table
  * as aliases.
  */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 {
 	int i;
 	struct pmu_events_map *map;
 	struct pmu_event *pe;
+	const char *name = pmu->name;
 
-	map = perf_pmu__find_map();
+	map = perf_pmu__find_map(pmu);
 	if (!map)
 		return;
 
@@ -608,7 +661,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	 */
 	i = 0;
 	while (1) {
-		const char *pname;
 
 		pe = &map->table[i++];
 		if (!pe->name) {
@@ -617,9 +669,13 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 			break;
 		}
 
-		pname = pe->pmu ? pe->pmu : "cpu";
-		if (strncmp(pname, name, strlen(pname)))
-			continue;
+		if (!is_pmu_core(name)) {
+			/* check for uncore devices */
+			if (pe->pmu == NULL)
+				continue;
+			if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+				continue;
+		}
 
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
@@ -661,21 +717,20 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_aliases(name, &aliases))
 		return NULL;
 
-	pmu_add_cpu_aliases(&aliases, name);
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
 
 	pmu->cpus = pmu_cpumask(name);
-
+	pmu->name = strdup(name);
+	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(name);
+	pmu_add_cpu_aliases(&aliases, pmu);
 
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
 	list_splice(&aliases, &pmu->aliases);
-	pmu->name = strdup(name);
-	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
 
 	pmu->default_config = perf_pmu__get_default_config(pmu);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 27c75e635866..76fecec7b3f9 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -92,6 +92,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
-struct pmu_events_map *perf_pmu__find_map(void);
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 8e49d9cafcfc..b1e999bd21ef 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -864,7 +864,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
 					 &pages, &overwrite))
 		return NULL;
 
-	if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+	if (perf_evlist__mmap(evlist, pages) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index 0dfe27d99458..0efc3258c648 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -101,16 +101,21 @@ void rblist__init(struct rblist *rblist)
 	return;
 }
 
+void rblist__exit(struct rblist *rblist)
+{
+	struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+	while (next) {
+		pos = next;
+		next = rb_next(pos);
+		rblist__remove_node(rblist, pos);
+	}
+}
+
 void rblist__delete(struct rblist *rblist)
 {
 	if (rblist != NULL) {
-		struct rb_node *pos, *next = rb_first(&rblist->entries);
-
-		while (next) {
-			pos = next;
-			next = rb_next(pos);
-			rblist__remove_node(rblist, pos);
-		}
+		rblist__exit(rblist);
 		free(rblist);
 	}
 }
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 4c8638a22571..76df15c27f5f 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -29,6 +29,7 @@ struct rblist {
 };
 
 void rblist__init(struct rblist *rblist);
+void rblist__exit(struct rblist *rblist);
 void rblist__delete(struct rblist *rblist);
 int rblist__add_node(struct rblist *rblist, const void *new_entry);
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index df2857137908..54e30f1bcbd7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1348,10 +1348,11 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
+	struct perf_sample sample = { .time = 0, };
 	int fd = perf_data__fd(session->data);
 	int err;
 
-	dump_event(session->evlist, event, file_offset, NULL);
+	dump_event(session->evlist, event, file_offset, &sample);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 855e35cbb1dc..57ec22513971 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -87,6 +87,16 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 	return &nd->rb_node;
 }
 
+static void saved_value_delete(struct rblist *rblist __maybe_unused,
+			       struct rb_node *rb_node)
+{
+	struct saved_value *v;
+
+	BUG_ON(!rb_node);
+	v = container_of(rb_node, struct saved_value, rb_node);
+	free(v);
+}
+
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
 					      int cpu,
 					      bool create)
@@ -114,7 +124,7 @@ void perf_stat__init_shadow_stats(void)
 	rblist__init(&runtime_saved_values);
 	runtime_saved_values.node_cmp = saved_value_cmp;
 	runtime_saved_values.node_new = saved_value_new;
-	/* No delete for now */
+	runtime_saved_values.node_delete = saved_value_delete;
 }
 
 static int evsel_context(struct perf_evsel *evsel)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index be0d5a736dea..2b653853eec2 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -92,7 +92,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	return threads;
 }
 
-struct thread_map *thread_map__new_by_uid(uid_t uid)
+static struct thread_map *__thread_map__new_all_cpus(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
@@ -113,7 +113,6 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
-		struct stat st;
 		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
@@ -121,11 +120,12 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 
 		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
-		if (stat(path, &st) != 0)
-			continue;
+		if (uid != UINT_MAX) {
+			struct stat st;
 
-		if (st.st_uid != uid)
-			continue;
+			if (stat(path, &st) != 0 || st.st_uid != uid)
+				continue;
+		}
 
 		snprintf(path, sizeof(path), "/proc/%d/task", pid);
 		items = scandir(path, &namelist, filter, NULL);
@@ -178,6 +178,16 @@ out_free_closedir:
 	goto out_closedir;
 }
 
+struct thread_map *thread_map__new_all_cpus(void)
+{
+	return __thread_map__new_all_cpus(UINT_MAX);
+}
+
+struct thread_map *thread_map__new_by_uid(uid_t uid)
+{
+	return __thread_map__new_all_cpus(uid);
+}
+
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
 {
 	if (pid != -1)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index f15803985435..07a765fb22bb 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -23,6 +23,7 @@ struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
+struct thread_map *thread_map__new_all_cpus(void);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 struct thread_map *thread_map__new_event(struct thread_map_event *event);