Merge tag 'perf-core-for-mingo-4.17-20180216' 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:

- Fix wrong jump arrow in systems with branch records with cycles,
  i.e. Intel's >= Skylake (Jin Yao)

- Fix 'perf record --per-thread' problem introduced when
  implementing 'perf stat --per-thread (Jin Yao)

- Use arch__compare_symbol_names() to fix 'perf test vmlinux',
  that was using strcmp(symbol names) while the dso routines
  doing symbol lookups used the arch overridable one, making
  this test fail in architectures that overrided that function
  with something other than strcmp() (Jiri Olsa)

- Add 'perf script --show-round-event' to display
  PERF_RECORD_FINISHED_ROUND entries (Jiri Olsa)

- Fix dwarf unwind for stripped binaries in 'perf test' (Jiri Olsa)

- Use ordered_events for 'perf report --tasks', otherwise we may get
  artifacts when PERF_RECORD_FORK gets processed before PERF_RECORD_COMM
  (when they got recorded in different CPUs) (Jiri Olsa)

- Add support to display group output for non group events, i.e.
  now when one uses 'perf report --group' on a perf.data file
  recorded without explicitly grouping events with {} (e.g.
  "perf record -e '{cycles,instructions}'" get the same output
  that would produce, i.e. see all those non-grouped events in
  multiple columns, at the same time (Jiri Olsa)

- Skip non-address kallsyms entries, e.g. '(null)' for !root (Jiri Olsa)

- Kernel maps fixes wrt perf.data(report) versus live system (top)
  (Jiri Olsa)

- Fix memory corruption when using 'perf record -j call -g -a <application>'
  followed by 'perf report --branch-history' (Jiri Olsa)

- ARM CoreSight fixes (Mathieu Poirier)

- Add inject capability for CoreSight Traces (Robert Waker)

- Update documentation for use of 'perf' + ARM CoreSight (Robert Walker)

- Man pages fixes (Sangwon Hong, Jaecheol Shin)

- Fix some 'perf test' cases on s/390 and x86_64 (some backtraces
  changed with a glibc update) (Thomas Richter)

- Add detailed CPUID info in the 'perf.data' headers for s/390 to
  then use it in 'perf annotate' (Thomas Richter)

- Add '--interval-count N' to 'perf stat', to use with -I, i.e.
  'perf stat -I 1000 --interval-count 2' will show stats every
   1000ms, two times (yuzhoujian)

- Add 'perf stat --timeout Nms', that will run for that many
  milliseconds and then stop, printing the counters (yuzhoujian)

- Fix description for 'perf report --mem-modex (Andi Kleen)

- Use a wildcard to remove the vfs_getname probe in the
  'perf test' shell based test cases (Arnaldo Carvalho de Melo)

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

42 files changed, 1083 insertions, 264 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index c635eab6af54..292809c3c0ca 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -21,7 +21,7 @@ If there is no debug info in the object, then annotated assembly is displayed.
 OPTIONS
 -------
 -i::
---input=::
+--input=<file>::
         Input file name. (default: perf.data unless stdin is a fifo)
 
 -d::
@@ -69,7 +69,7 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
---stdio-color::
+--stdio-color=<mode>::
 	'always', 'never' or 'auto', allowing configuring color output
 	via the command line, in addition to via "color.ui" .perfconfig.
 	Use '--stdio-color always' to generate color even when redirecting
@@ -84,7 +84,7 @@ OPTIONS
 --gtk:: Use the GTK interface.
 
 -C::
---cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+--cpu=<cpu>:: Only report samples for the list of CPUs provided. Multiple CPUs can
 	be provided as a comma-separated list with no space: 0,1. Ranges of
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 479fc3261a50..85b8ac695c87 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -25,6 +25,10 @@ OPTIONS
 --input=<file>::
 	Select the input file (default: perf.data unless stdin is a fifo)
 
+-f::
+--force::
+	Don't do ownership validation
+
 -v::
 --verbose::
         Be more verbose. (show symbol address, etc)
@@ -61,7 +65,7 @@ OPTIONS
 	default, but this option shows live (currently allocated) pages
 	instead.  (This option works with --page option only)
 
---time::
+--time=<start>,<stop>::
 	Only analyze samples within given time window: <start>,<stop>. Times
 	have the format seconds.microseconds. If start is not given (i.e., time
 	string is ',x.y') then analysis starts at the beginning of the file. If
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 4be08a1e3f8d..b0211410969b 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,6 +28,10 @@ OPTIONS
 <command>...::
 	Any command you can specify in a shell.
 
+-f::
+--force::
+	Don't do ownership validation
+
 -t::
 --type=::
 	Select the memory operation type: load or store (default: load,store)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 907e505b6309..cba16d8a970e 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -354,7 +354,8 @@ OPTIONS
         Path to objdump binary.
 
 --group::
-	Show event group information together.
+	Show event group information together. It forces group output also
+	if there are no groups defined in data file.
 
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
@@ -367,7 +368,7 @@ OPTIONS
 	Use the data addresses of samples in addition to instruction addresses
 	to build the histograms.  To generate meaningful output, the perf.data
 	file must have been obtained using perf record -d -W and using a
-	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	special event -e cpu/mem-loads/p or -e cpu/mem-stores/p. See
 	'perf mem' for simpler access.
 
 --percent-limit::
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 7730c1d2b5d3..36ec0257f8d3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -303,6 +303,9 @@ OPTIONS
 --show-lost-events
 	Display lost events i.e. events of type PERF_RECORD_LOST.
 
+--show-round-events
+	Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 823fce7674bb..2bbe79a50d3c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -146,6 +146,16 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--interval-count times::
+Print count deltas for fixed number of times.
+This option should be used together with "-I" option.
+	example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
+
+--timeout msecs::
+Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
+This option is not supported with the "-I" option.
+	example: 'perf stat --time 2000 -e cycles -a'
+
 --metric-only::
 Only print computed metrics. Print them in a single line.
 Don't show any raw values. Not supported with --per-thread.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0dfdaa9fa81e..577a5d2988fe 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -27,6 +27,8 @@ NO_SYSCALL_TABLE := 1
 # Additional ARCH settings for ppc
 ifeq ($(SRCARCH),powerpc)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/powerpc/include/generated
   LIBUNWIND_LIBS := -lunwind -lunwind-ppc64
 endif
 
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 2323581b157d..fa639e3e52ac 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -68,7 +68,7 @@ struct auxtrace_record
 	bool found_spe = false;
 	static struct perf_pmu **arm_spe_pmus = NULL;
 	static int nr_spes = 0;
-	int i;
+	int i = 0;
 
 	if (!evlist)
 		return NULL;
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fbfc055d3f4d..5c655ad4621e 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -298,12 +298,17 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 {
 	int i;
 	int etmv3 = 0, etmv4 = 0;
-	const struct cpu_map *cpus = evlist->cpus;
+	struct cpu_map *event_cpus = evlist->cpus;
+	struct cpu_map *online_cpus = cpu_map__new(NULL);
 
 	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!cpu_map__empty(cpus)) {
-		for (i = 0; i < cpu_map__nr(cpus); i++) {
-			if (cs_etm_is_etmv4(itr, cpus->map[i]))
+	if (!cpu_map__empty(event_cpus)) {
+		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(event_cpus, i) ||
+			    !cpu_map__has(online_cpus, i))
+				continue;
+
+			if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
 				etmv3++;
@@ -311,6 +316,9 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	} else {
 		/* get configuration for all CPUs in the system */
 		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(online_cpus, i))
+				continue;
+
 			if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
@@ -318,6 +326,8 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		}
 	}
 
+	cpu_map__put(online_cpus);
+
 	return (CS_ETM_HEADER_SIZE +
 	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
 	       (etmv3 * CS_ETMV3_PRIV_SIZE));
@@ -447,7 +457,9 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	int i;
 	u32 offset;
 	u64 nr_cpu, type;
-	const struct cpu_map *cpus = session->evlist->cpus;
+	struct cpu_map *cpu_map;
+	struct cpu_map *event_cpus = session->evlist->cpus;
+	struct cpu_map *online_cpus = cpu_map__new(NULL);
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
@@ -458,8 +470,21 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	if (!session->evlist->nr_mmaps)
 		return -EINVAL;
 
-	/* If the cpu_map is empty all CPUs are involved */
-	nr_cpu = cpu_map__empty(cpus) ? cpu__max_cpu() : cpu_map__nr(cpus);
+	/* If the cpu_map is empty all online CPUs are involved */
+	if (cpu_map__empty(event_cpus)) {
+		cpu_map = online_cpus;
+	} else {
+		/* Make sure all specified CPUs are online */
+		for (i = 0; i < cpu_map__nr(event_cpus); i++) {
+			if (cpu_map__has(event_cpus, i) &&
+			    !cpu_map__has(online_cpus, i))
+				return -EINVAL;
+		}
+
+		cpu_map = event_cpus;
+	}
+
+	nr_cpu = cpu_map__nr(cpu_map);
 	/* Get PMU type as dynamically assigned by the core */
 	type = cs_etm_pmu->type;
 
@@ -472,15 +497,11 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 
 	offset = CS_ETM_SNAPSHOT + 1;
 
-	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!cpu_map__empty(cpus)) {
-		for (i = 0; i < cpu_map__nr(cpus) && offset < priv_size; i++)
-			cs_etm_get_metadata(cpus->map[i], &offset, itr, info);
-	} else {
-		/* get configuration for all CPUs in the system */
-		for (i = 0; i < cpu__max_cpu(); i++)
+	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
+		if (cpu_map__has(cpu_map, i))
 			cs_etm_get_metadata(i, &offset, itr, info);
-	}
+
+	cpu_map__put(online_cpus);
 
 	return 0;
 }
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 42dab7c8f508..a111239df182 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -6,3 +6,28 @@ endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/powerpc/include/generated/asm
+header32 := $(out)/syscalls_32.c
+header64 := $(out)/syscalls_64.c
+sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header64): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@
+
+$(header32): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64)
+
+archheaders: $(header32) $(header64)
diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..ef52e1dd694b
--- /dev/null
+++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
@@ -0,0 +1,37 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# s390 script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+
+wordsize=$1
+gcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table()
+{
+	local wordsize=$1
+	local max_nr
+
+	echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
+	while read sc nr; do
+		printf '\t[%d] = "%s",\n' $nr $sc
+		max_nr=$nr
+	done
+	echo '};'
+	echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr"
+}
+
+$gcc -m${wordsize} -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table ${wordsize}
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 8c72b44444cb..01df9d8303e1 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -23,12 +23,37 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	return ops;
 }
 
+static int s390__cpuid_parse(struct arch *arch, char *cpuid)
+{
+	unsigned int family;
+	char model[16], model_c[16], cpumf_v[16], cpumf_a[16];
+	int ret;
+
+	/*
+	 * cpuid string format:
+	 * "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]"
+	 */
+	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c,
+		     model, cpumf_v, cpumf_a);
+	if (ret >= 2) {
+		arch->family = family;
+		arch->model = 0;
+		return 0;
+	}
+
+	return -1;
+}
+
 static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
+	int err = 0;
+
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = s390__associate_ins_ops;
+		if (cpuid)
+			err = s390__cpuid_parse(arch, cpuid);
 	}
 
-	return 0;
+	return err;
 }
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 9fa6c3e5782c..231294b80dc4 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -1,8 +1,9 @@
 /*
  * Implementation of get_cpuid().
  *
- * Copyright 2014 IBM Corp.
+ * Copyright IBM Corp. 2014, 2018
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *	      Thomas Richter <tmricht@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -13,16 +14,153 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
+#include <ctype.h>
 
 #include "../../util/header.h"
+#include "../../util/util.h"
+
+#define SYSINFO_MANU	"Manufacturer:"
+#define SYSINFO_TYPE	"Type:"
+#define SYSINFO_MODEL	"Model:"
+#define SRVLVL_CPUMF	"CPU-MF:"
+#define SRVLVL_VERSION	"version="
+#define SRVLVL_AUTHORIZATION	"authorization="
+#define SYSINFO		"/proc/sysinfo"
+#define SRVLVL		"/proc/service_levels"
 
 int get_cpuid(char *buffer, size_t sz)
 {
-	const char *cpuid = "IBM/S390";
+	char *cp, *line = NULL, *line2;
+	char type[8], model[33], version[8], manufacturer[32], authorization[8];
+	int tpsize = 0, mdsize = 0, vssize = 0, mfsize = 0, atsize = 0;
+	int read;
+	unsigned long line_sz;
+	size_t nbytes;
+	FILE *sysinfo;
+
+	/*
+	 * Scan /proc/sysinfo line by line and read out values for
+	 * Manufacturer:, Type: and Model:, for example:
+	 * Manufacturer:    IBM
+	 * Type:            2964
+	 * Model:           702              N96
+	 * The first word is the Model Capacity and the second word is
+	 * Model (can be omitted). Both words have a maximum size of 16
+	 * bytes.
+	 */
+	memset(manufacturer, 0, sizeof(manufacturer));
+	memset(type, 0, sizeof(type));
+	memset(model, 0, sizeof(model));
+	memset(version, 0, sizeof(version));
+	memset(authorization, 0, sizeof(authorization));
+
+	sysinfo = fopen(SYSINFO, "r");
+	if (sysinfo == NULL)
+		return -1;
+
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
+			line2 = line + strlen(SYSINFO_MANU);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mfsize += scnprintf(manufacturer + mfsize,
+						    sizeof(manufacturer) - mfsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_TYPE, strlen(SYSINFO_TYPE))) {
+			line2 = line + strlen(SYSINFO_TYPE);
 
-	if (strlen(cpuid) + 1 > sz)
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				tpsize += scnprintf(type + tpsize,
+						    sizeof(type) - tpsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_MODEL, strlen(SYSINFO_MODEL))) {
+			line2 = line + strlen(SYSINFO_MODEL);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mdsize += scnprintf(model + mdsize, sizeof(type) - mdsize,
+						    "%s%s", model[0] ? "," : "", cp);
+			}
+			break;
+		}
+	}
+	fclose(sysinfo);
+
+	/* Missing manufacturer, type or model information should not happen */
+	if (!manufacturer[0] || !type[0] || !model[0])
 		return -1;
 
-	strcpy(buffer, cpuid);
-	return 0;
+	/*
+	 * Scan /proc/service_levels and return the CPU-MF counter facility
+	 * version number and authorization level.
+	 * Optional, does not exist on z/VM guests.
+	 */
+	sysinfo = fopen(SRVLVL, "r");
+	if (sysinfo == NULL)
+		goto skip_sysinfo;
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (strncmp(line, SRVLVL_CPUMF, strlen(SRVLVL_CPUMF)))
+			continue;
+
+		line2 = line + strlen(SRVLVL_CPUMF);
+		while ((cp = strtok_r(line2, "\n ", &line2))) {
+			if (!strncmp(cp, SRVLVL_VERSION,
+				     strlen(SRVLVL_VERSION))) {
+				char *sep = strchr(cp, '=');
+
+				vssize += scnprintf(version + vssize,
+						    sizeof(version) - vssize, "%s", sep + 1);
+			}
+			if (!strncmp(cp, SRVLVL_AUTHORIZATION,
+				     strlen(SRVLVL_AUTHORIZATION))) {
+				char *sep = strchr(cp, '=');
+
+				atsize += scnprintf(authorization + atsize,
+						    sizeof(authorization) - atsize, "%s", sep + 1);
+			}
+		}
+	}
+	fclose(sysinfo);
+
+skip_sysinfo:
+	free(line);
+
+	if (version[0] && authorization[0] )
+		nbytes = snprintf(buffer, sz, "%s,%s,%s,%s,%s",
+				  manufacturer, type, model, version,
+				  authorization);
+	else
+		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
+				  model);
+	return (nbytes >= sz) ? -1 : 0;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	char *buf = malloc(128);
+
+	if (buf && get_cpuid(buf, 128) < 0)
+		zfree(&buf);
+	return buf;
+}
+
+/*
+ * Compare the cpuid string returned by get_cpuid() function
+ * with the name generated by the jevents file read from
+ * pmu-events/arch/s390/mapfile.csv.
+ *
+ * Parameter mapcpuid is the cpuid as stored in the
+ * pmu-events/arch/s390/mapfile.csv. This is just the type number.
+ * Parameter cpuid is the cpuid returned by function get_cpuid().
+ */
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	char *cp = strchr(cpuid, ',');
+
+	if (cp == NULL)
+		return -1;
+	return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bf4ca749d1ac..907267206973 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1803,7 +1803,7 @@ int cmd_record(int argc, const char **argv)
 	err = target__validate(&rec->opts.target);
 	if (err) {
 		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
-		ui__warning("%s", errbuf);
+		ui__warning("%s\n", errbuf);
 	}
 
 	err = target__parse_uid(&rec->opts.target);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4ad5dc649716..1eedb1815c4c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -614,6 +614,7 @@ static int stats_print(struct report *rep)
 static void tasks_setup(struct report *rep)
 {
 	memset(&rep->tool, 0, sizeof(rep->tool));
+	rep->tool.ordered_events = true;
 	if (rep->mmaps_mode) {
 		rep->tool.mmap = perf_event__process_mmap;
 		rep->tool.mmap2 = perf_event__process_mmap2;
@@ -937,6 +938,7 @@ int cmd_report(int argc, const char **argv)
 		"perf report [<options>]",
 		NULL
 	};
+	bool group_set = false;
 	struct report report = {
 		.tool = {
 			.sample		 = process_sample_event,
@@ -1056,7 +1058,7 @@ int cmd_report(int argc, const char **argv)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
-	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &group_set,
 		    "Show event group information together"),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
 		    "use branch records for per branch histogram filling",
@@ -1173,6 +1175,9 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
+	if (group_set && !session->evlist->nr_groups)
+		perf_evlist__set_leader(session->evlist);
+
 	if (itrace_synth_opts.last_branch)
 		has_br_stack = true;
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ab19a6ee4093..cce926aeb0c0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1489,6 +1489,7 @@ struct perf_script {
 	bool			show_switch_events;
 	bool			show_namespace_events;
 	bool			show_lost_events;
+	bool			show_round_events;
 	bool			allocated;
 	bool			per_event_dump;
 	struct cpu_map		*cpus;
@@ -2104,6 +2105,16 @@ process_lost_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int
+process_finished_round_event(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct ordered_events *oe __maybe_unused)
+
+{
+	perf_event__fprintf(event, stdout);
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -2200,6 +2211,10 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.namespaces = process_namespaces_event;
 	if (script->show_lost_events)
 		script->tool.lost = process_lost_event;
+	if (script->show_round_events) {
+		script->tool.ordered_events = false;
+		script->tool.finished_round = process_finished_round_event;
+	}
 
 	if (perf_script__setup_per_event_dump(script)) {
 		pr_err("Couldn't create the per event dump files\n");
@@ -3139,6 +3154,8 @@ int cmd_script(int argc, const char **argv)
 		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events,
 		    "Show lost events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,
+		    "Show round events (if recorded)"),
 	OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
 		    "Dump trace output to files named by the monitored events"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d32f222..2d49eccf98f2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -168,6 +168,7 @@ static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
+static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
@@ -571,6 +572,8 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
+	int times = stat_config.times;
+	int timeout = stat_config.timeout;
 	char msg[BUFSIZ];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
@@ -584,6 +587,9 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (interval) {
 		ts.tv_sec  = interval / USEC_PER_MSEC;
 		ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
+	} else if (timeout) {
+		ts.tv_sec  = timeout / USEC_PER_MSEC;
+		ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC;
 	} else {
 		ts.tv_sec  = 1;
 		ts.tv_nsec = 0;
@@ -696,10 +702,14 @@ try_again:
 		perf_evlist__start_workload(evsel_list);
 		enable_counters();
 
-		if (interval) {
+		if (interval || timeout) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
+				if (timeout)
+					break;
 				process_interval();
+				if (interval_count && !(--times))
+					break;
 			}
 		}
 		waitpid(child_pid, &status, 0);
@@ -716,8 +726,13 @@ try_again:
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
-			if (interval)
+			if (timeout)
+				break;
+			if (interval) {
 				process_interval();
+				if (interval_count && !(--times))
+					break;
+			}
 		}
 	}
 
@@ -1891,6 +1906,10 @@ static const struct option stat_options[] = {
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
 		    "print counts at regular interval in ms (>= 10)"),
+	OPT_INTEGER(0, "interval-count", &stat_config.times,
+		    "print counts for fixed number of times"),
+	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
+		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
 	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
@@ -2688,7 +2707,7 @@ int cmd_stat(int argc, const char **argv)
 	int status = -EINVAL, run_idx;
 	const char *mode;
 	FILE *output = stderr;
-	unsigned int interval;
+	unsigned int interval, timeout;
 	const char * const stat_subcommands[] = { "record", "report" };
 
 	setlocale(LC_ALL, "");
@@ -2719,6 +2738,7 @@ int cmd_stat(int argc, const char **argv)
 		return __cmd_report(argc, argv);
 
 	interval = stat_config.interval;
+	timeout = stat_config.timeout;
 
 	/*
 	 * For record command the -o is already taken care of.
@@ -2871,6 +2891,33 @@ int cmd_stat(int argc, const char **argv)
 				   "Please proceed with caution.\n");
 	}
 
+	if (stat_config.times && interval)
+		interval_count = true;
+	else if (stat_config.times && !interval) {
+		pr_err("interval-count option should be used together with "
+				"interval-print.\n");
+		parse_options_usage(stat_usage, stat_options, "interval-count", 0);
+		parse_options_usage(stat_usage, stat_options, "I", 1);
+		goto out;
+	}
+
+	if (timeout && timeout < 100) {
+		if (timeout < 10) {
+			pr_err("timeout must be >= 10ms.\n");
+			parse_options_usage(stat_usage, stat_options, "timeout", 0);
+			goto out;
+		} else
+			pr_warning("timeout < 100ms. "
+				   "The overhead percentage could be high in some cases. "
+				   "Please proceed with caution.\n");
+	}
+	if (timeout && interval) {
+		pr_err("timeout option is not supported with interval-print.\n");
+		parse_options_usage(stat_usage, stat_options, "timeout", 0);
+		parse_options_usage(stat_usage, stat_options, "I", 1);
+		goto out;
+	}
+
 	if (perf_evlist__alloc_stats(evsel_list, interval))
 		goto out;
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 790ec25919a0..bf206ffe5c45 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -42,6 +42,7 @@ arch/parisc/include/uapi/asm/errno.h
 arch/powerpc/include/uapi/asm/errno.h
 arch/sparc/include/uapi/asm/errno.h
 arch/x86/include/uapi/asm/errno.h
+arch/powerpc/include/uapi/asm/unistd.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 3bf7b145b826..c7115d369511 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -482,6 +482,34 @@ static void fs_something(void)
 	}
 }
 
+static const char *do_determine_event(bool excl_kernel)
+{
+	const char *event = excl_kernel ? "cycles:u" : "cycles";
+
+#ifdef __s390x__
+	char cpuid[128], model[16], model_c[16], cpum_cf_v[16];
+	unsigned int family;
+	int ret, cpum_cf_a;
+
+	if (get_cpuid(cpuid, sizeof(cpuid)))
+		goto out_clocks;
+	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c,
+		     model, cpum_cf_v, &cpum_cf_a);
+	if (ret != 5)		 /* Not available */
+		goto out_clocks;
+	if (excl_kernel && (cpum_cf_a & 4))
+		return event;
+	if (!excl_kernel && (cpum_cf_a & 2))
+		return event;
+
+	/* Fall through: missing authorization */
+out_clocks:
+	event = excl_kernel ? "cpu-clock:u" : "cpu-clock";
+
+#endif
+	return event;
+}
+
 static void do_something(void)
 {
 	fs_something();
@@ -592,10 +620,7 @@ static int do_test_code_reading(bool try_kcore)
 
 		perf_evlist__set_maps(evlist, cpus, threads);
 
-		if (excl_kernel)
-			str = "cycles:u";
-		else
-			str = "cycles";
+		str = do_determine_event(excl_kernel);
 		pr_debug("Parsing event '%s'\n", str);
 		ret = parse_events(evlist, str, NULL);
 		if (ret < 0) {
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 260418969120..2f008067d989 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -37,6 +37,19 @@ static int init_live_machine(struct machine *machine)
 						  mmap_handler, machine, true, 500);
 }
 
+/*
+ * We need to keep these functions global, despite the
+ * fact that they are used only locally in this object,
+ * in order to keep them around even if the binary is
+ * stripped. If they are gone, the unwind check for
+ * symbol fails.
+ */
+int test_dwarf_unwind__thread(struct thread *thread);
+int test_dwarf_unwind__compare(void *p1, void *p2);
+int test_dwarf_unwind__krava_3(struct thread *thread);
+int test_dwarf_unwind__krava_2(struct thread *thread);
+int test_dwarf_unwind__krava_1(struct thread *thread);
+
 #define MAX_STACK 8
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
@@ -45,12 +58,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	char *symbol = entry->sym ? entry->sym->name : NULL;
 	static const char *funcs[MAX_STACK] = {
 		"test__arch_unwind_sample",
-		"unwind_thread",
-		"compare",
+		"test_dwarf_unwind__thread",
+		"test_dwarf_unwind__compare",
 		"bsearch",
-		"krava_3",
-		"krava_2",
-		"krava_1",
+		"test_dwarf_unwind__krava_3",
+		"test_dwarf_unwind__krava_2",
+		"test_dwarf_unwind__krava_1",
 		"test__dwarf_unwind"
 	};
 	/*
@@ -77,7 +90,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-static noinline int unwind_thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -108,7 +121,7 @@ static noinline int unwind_thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-static noinline int compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -117,17 +130,17 @@ static noinline int compare(void *p1, void *p2)
 		/* Call unwinder twice for both callchain orders. */
 		callchain_param.order = ORDER_CALLER;
 
-		global_unwind_retval = unwind_thread(thread);
+		global_unwind_retval = test_dwarf_unwind__thread(thread);
 		if (!global_unwind_retval) {
 			callchain_param.order = ORDER_CALLEE;
-			global_unwind_retval = unwind_thread(thread);
+			global_unwind_retval = test_dwarf_unwind__thread(thread);
 		}
 	}
 
 	return p1 - p2;
 }
 
-static noinline int krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -141,18 +154,19 @@ static noinline int krava_3(struct thread *thread)
 			size_t, int (*)(void *, void *));
 
 	_bsearch = fp;
-	_bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+	_bsearch(array, &thread, 2, sizeof(struct thread **),
+		 test_dwarf_unwind__compare);
 	return global_unwind_retval;
 }
 
-static noinline int krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
-	return krava_3(thread);
+	return test_dwarf_unwind__krava_3(thread);
 }
 
-static noinline int krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
-	return krava_2(thread);
+	return test_dwarf_unwind__krava_2(thread);
 }
 
 int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
@@ -189,7 +203,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
 		goto out;
 	}
 
-	err = krava_1(thread);
+	err = test_dwarf_unwind__krava_1(thread);
 	thread__put(thread);
 
  out:
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 30a950c9d407..1c16e56cd93e 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -5,7 +5,7 @@ had_vfs_getname=$?
 
 cleanup_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
-		perf probe -q -d probe:vfs_getname
+		perf probe -q -d probe:vfs_getname*
 	fi
 }
 
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index c446c894b297..8c4ab0b390c0 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -21,12 +21,12 @@ trace_libc_inet_pton_backtrace() {
 	expected[3]=".*packets transmitted.*"
 	expected[4]="rtt min.*"
 	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
-	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[6]=".*inet_pton[[:space:]]\($libc|inlined\)$"
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf'
-		expected[7]="gaih_inet[[:space:]]\(inlined\)$"
-		expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$"
+		expected[7]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
+		expected[8]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
 		expected[9]="main[[:space:]]\(.*/bin/ping.*\)$"
 		expected[10]="__libc_start_main[[:space:]]\($libc\)$"
 		expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$"
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f6789fb029d6..1e5adb65632a 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -56,7 +56,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true) <= 0) {
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -125,7 +125,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 
 		if (pair && UM(pair->start) == mem_start) {
 next_pair:
-			if (strcmp(sym->name, pair->name) == 0) {
+			if (arch__compare_symbol_names(sym->name, pair->name) == 0) {
 				/*
 				 * kallsyms don't have the symbol end, so we
 				 * set that by using the next symbol start - 1,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 286427975112..e2f666391ac4 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -319,6 +319,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	struct map_symbol *ms = ab->b.priv;
 	struct symbol *sym = ms->sym;
 	u8 pcnt_width = annotate_browser__pcnt_width(ab);
+	int width = 0;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
@@ -340,13 +341,17 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
+	if (ab->have_cycles)
+		width = IPC_WIDTH + CYCLES_WIDTH;
+
 	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
-	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
+	__ui_browser__line_arrow(browser,
+				 pcnt_width + 2 + ab->addr_width + width,
 				 from, to);
 
 	if (is_fused(ab, cursor)) {
 		ui_browser__mark_fused(browser,
-				       pcnt_width + 3 + ab->addr_width,
+				       pcnt_width + 3 + ab->addr_width + width,
 				       from - 1,
 				       to > from ? true : false);
 	}
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 7f8553630c4d..537eadd81914 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -316,7 +316,6 @@ static int machine__write_buildid_table(struct machine *machine,
 					struct feat_fd *fd)
 {
 	int err = 0;
-	char nm[PATH_MAX];
 	struct dso *pos;
 	u16 kmisc = PERF_RECORD_MISC_KERNEL,
 	    umisc = PERF_RECORD_MISC_USER;
@@ -338,9 +337,8 @@ static int machine__write_buildid_table(struct machine *machine,
 			name = pos->short_name;
 			name_len = pos->short_name_len;
 		} else if (dso__is_kcore(pos)) {
-			machine__mmap_name(machine, nm, sizeof(nm));
-			name = nm;
-			name_len = strlen(nm);
+			name = machine->mmap_name;
+			name_len = strlen(name);
 		} else {
 			name = pos->long_name;
 			name_len = pos->long_name_len;
@@ -813,12 +811,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
 	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
-	char nm[PATH_MAX];
 
 	if (dso__is_kcore(dso)) {
 		is_kallsyms = true;
-		machine__mmap_name(machine, nm, sizeof(nm));
-		name = nm;
+		name = machine->mmap_name;
 	}
 	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
 				     dso->nsinfo, is_kallsyms, is_vdso);
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 1fb01849f1c7..640af88331b4 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -78,6 +78,8 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
 {
 	ocsd_datapath_resp_t dp_ret;
 
+	decoder->prev_return = OCSD_RESP_CONT;
+
 	dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
 				      0, 0, NULL, NULL);
 	if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
@@ -253,16 +255,16 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
 		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr   = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].exc	     = false;
-		decoder->packet_buffer[i].exc_ret    = false;
-		decoder->packet_buffer[i].cpu	     = INT_MIN;
+		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].last_instr_taken_branch = false;
+		decoder->packet_buffer[i].exc = false;
+		decoder->packet_buffer[i].exc_ret = false;
+		decoder->packet_buffer[i].cpu = INT_MIN;
 	}
 }
 
 static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
-			      const ocsd_generic_trace_elem *elem,
 			      const u8 trace_chan_id,
 			      enum cs_etm_sample_type sample_type)
 {
@@ -278,18 +280,16 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 		return OCSD_RESP_FATAL_SYS_ERR;
 
 	et = decoder->tail;
+	et = (et + 1) & (MAX_BUFFER - 1);
+	decoder->tail = et;
+	decoder->packet_count++;
+
 	decoder->packet_buffer[et].sample_type = sample_type;
-	decoder->packet_buffer[et].start_addr = elem->st_addr;
-	decoder->packet_buffer[et].end_addr = elem->en_addr;
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-
-	/* Wrap around if need be */
-	et = (et + 1) & (MAX_BUFFER - 1);
-
-	decoder->tail = et;
-	decoder->packet_count++;
+	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -297,6 +297,47 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	return OCSD_RESP_CONT;
 }
 
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
+			     const ocsd_generic_trace_elem *elem,
+			     const uint8_t trace_chan_id)
+{
+	int ret = 0;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_RANGE);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+
+	packet->start_addr = elem->st_addr;
+	packet->end_addr = elem->en_addr;
+	switch (elem->last_i_type) {
+	case OCSD_INSTR_BR:
+	case OCSD_INSTR_BR_INDIRECT:
+		packet->last_instr_taken_branch = elem->last_instr_exec;
+		break;
+	case OCSD_INSTR_ISB:
+	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_OTHER:
+	default:
+		packet->last_instr_taken_branch = false;
+		break;
+	}
+
+	return ret;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
+				const uint8_t trace_chan_id)
+{
+	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					     CS_ETM_TRACE_ON);
+}
+
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 				const void *context,
 				const ocsd_trc_index_t indx __maybe_unused,
@@ -313,12 +354,13 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 		decoder->trace_on = false;
 		break;
 	case OCSD_GEN_TRC_ELEM_TRACE_ON:
+		resp = cs_etm_decoder__buffer_trace_on(decoder,
+						       trace_chan_id);
 		decoder->trace_on = true;
 		break;
 	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
-		resp = cs_etm_decoder__buffer_packet(decoder, elem,
-						     trace_chan_id,
-						     CS_ETM_RANGE);
+		resp = cs_etm_decoder__buffer_range(decoder, elem,
+						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
 		decoder->packet_buffer[decoder->tail].exc = true;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 3d2e6205d186..743f5f444304 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -24,12 +24,14 @@ struct cs_etm_buffer {
 
 enum cs_etm_sample_type {
 	CS_ETM_RANGE = 1 << 0,
+	CS_ETM_TRACE_ON = 1 << 1,
 };
 
 struct cs_etm_packet {
 	enum cs_etm_sample_type sample_type;
 	u64 start_addr;
 	u64 end_addr;
+	u8 last_instr_taken_branch;
 	u8 exc;
 	u8 exc_ret;
 	int cpu;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index b9f0a53dfa65..1b0d422373be 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -32,6 +32,14 @@
 
 #define MAX_TIMESTAMP (~0ULL)
 
+/*
+ * A64 instructions are always 4 bytes
+ *
+ * Only A64 is supported, so can use this constant for converting between
+ * addresses and instruction counts, calculting offsets etc
+ */
+#define A64_INSTR_SIZE 4
+
 struct cs_etm_auxtrace {
 	struct auxtrace auxtrace;
 	struct auxtrace_queues queues;
@@ -45,11 +53,15 @@ struct cs_etm_auxtrace {
 	u8 snapshot_mode;
 	u8 data_queued;
 	u8 sample_branches;
+	u8 sample_instructions;
 
 	int num_cpu;
 	u32 auxtrace_type;
 	u64 branches_sample_type;
 	u64 branches_id;
+	u64 instructions_sample_type;
+	u64 instructions_sample_period;
+	u64 instructions_id;
 	u64 **metadata;
 	u64 kernel_start;
 	unsigned int pmu_type;
@@ -68,6 +80,12 @@ struct cs_etm_queue {
 	u64 time;
 	u64 timestamp;
 	u64 offset;
+	u64 period_instructions;
+	struct branch_stack *last_branch;
+	struct branch_stack *last_branch_rb;
+	size_t last_branch_pos;
+	struct cs_etm_packet *prev_packet;
+	struct cs_etm_packet *packet;
 };
 
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
@@ -174,6 +192,16 @@ static void cs_etm__free_queue(void *priv)
 {
 	struct cs_etm_queue *etmq = priv;
 
+	if (!etmq)
+		return;
+
+	thread__zput(etmq->thread);
+	cs_etm_decoder__free(etmq->decoder);
+	zfree(&etmq->event_buf);
+	zfree(&etmq->last_branch);
+	zfree(&etmq->last_branch_rb);
+	zfree(&etmq->prev_packet);
+	zfree(&etmq->packet);
 	free(etmq);
 }
 
@@ -270,11 +298,35 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params  *t_params;
 	struct cs_etm_queue *etmq;
+	size_t szp = sizeof(struct cs_etm_packet);
 
 	etmq = zalloc(sizeof(*etmq));
 	if (!etmq)
 		return NULL;
 
+	etmq->packet = zalloc(szp);
+	if (!etmq->packet)
+		goto out_free;
+
+	if (etm->synth_opts.last_branch || etm->sample_branches) {
+		etmq->prev_packet = zalloc(szp);
+		if (!etmq->prev_packet)
+			goto out_free;
+	}
+
+	if (etm->synth_opts.last_branch) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += etm->synth_opts.last_branch_sz *
+		      sizeof(struct branch_entry);
+		etmq->last_branch = zalloc(sz);
+		if (!etmq->last_branch)
+			goto out_free;
+		etmq->last_branch_rb = zalloc(sz);
+		if (!etmq->last_branch_rb)
+			goto out_free;
+	}
+
 	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
 	if (!etmq->event_buf)
 		goto out_free;
@@ -329,6 +381,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 		goto out_free_decoder;
 
 	etmq->offset = 0;
+	etmq->period_instructions = 0;
 
 	return etmq;
 
@@ -336,6 +389,10 @@ out_free_decoder:
 	cs_etm_decoder__free(etmq->decoder);
 out_free:
 	zfree(&etmq->event_buf);
+	zfree(&etmq->last_branch);
+	zfree(&etmq->last_branch_rb);
+	zfree(&etmq->prev_packet);
+	zfree(&etmq->packet);
 	free(etmq);
 
 	return NULL;
@@ -389,6 +446,129 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
 	return 0;
 }
 
+static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	struct branch_stack *bs_src = etmq->last_branch_rb;
+	struct branch_stack *bs_dst = etmq->last_branch;
+	size_t nr = 0;
+
+	/*
+	 * Set the number of records before early exit: ->nr is used to
+	 * determine how many branches to copy from ->entries.
+	 */
+	bs_dst->nr = bs_src->nr;
+
+	/*
+	 * Early exit when there is nothing to copy.
+	 */
+	if (!bs_src->nr)
+		return;
+
+	/*
+	 * As bs_src->entries is a circular buffer, we need to copy from it in
+	 * two steps.  First, copy the branches from the most recently inserted
+	 * branch ->last_branch_pos until the end of bs_src->entries buffer.
+	 */
+	nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos;
+	memcpy(&bs_dst->entries[0],
+	       &bs_src->entries[etmq->last_branch_pos],
+	       sizeof(struct branch_entry) * nr);
+
+	/*
+	 * If we wrapped around at least once, the branches from the beginning
+	 * of the bs_src->entries buffer and until the ->last_branch_pos element
+	 * are older valid branches: copy them over.  The total number of
+	 * branches copied over will be equal to the number of branches asked by
+	 * the user in last_branch_sz.
+	 */
+	if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
+		memcpy(&bs_dst->entries[nr],
+		       &bs_src->entries[0],
+		       sizeof(struct branch_entry) * etmq->last_branch_pos);
+	}
+}
+
+static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	etmq->last_branch_pos = 0;
+	etmq->last_branch_rb->nr = 0;
+}
+
+static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
+{
+	/*
+	 * The packet records the execution range with an exclusive end address
+	 *
+	 * A64 instructions are constant size, so the last executed
+	 * instruction is A64_INSTR_SIZE before the end address
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return packet->end_addr - A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
+{
+	/*
+	 * Only A64 instructions are currently supported, so can get
+	 * instruction count by dividing.
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet,
+				     u64 offset)
+{
+	/*
+	 * Only A64 instructions are currently supported, so can get
+	 * instruction address by muliplying.
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return packet->start_addr + offset * A64_INSTR_SIZE;
+}
+
+static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	struct branch_stack *bs = etmq->last_branch_rb;
+	struct branch_entry *be;
+
+	/*
+	 * The branches are recorded in a circular buffer in reverse
+	 * chronological order: we start recording from the last element of the
+	 * buffer down.  After writing the first element of the stack, move the
+	 * insert position back to the end of the buffer.
+	 */
+	if (!etmq->last_branch_pos)
+		etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
+
+	etmq->last_branch_pos -= 1;
+
+	be       = &bs->entries[etmq->last_branch_pos];
+	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
+	be->to	 = etmq->packet->start_addr;
+	/* No support for mispredict */
+	be->flags.mispred = 0;
+	be->flags.predicted = 1;
+
+	/*
+	 * Increment bs->nr until reaching the number of last branches asked by
+	 * the user on the command line.
+	 */
+	if (bs->nr < etmq->etm->synth_opts.last_branch_sz)
+		bs->nr += 1;
+}
+
+static int cs_etm__inject_event(union perf_event *event,
+			       struct perf_sample *sample, u64 type)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
+
 static int
 cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 {
@@ -453,35 +633,105 @@ static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
 	}
 }
 
+static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
+					    u64 addr, u64 period)
+{
+	int ret = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	union perf_event *event = etmq->event_buf;
+	struct perf_sample sample = {.ip = 0,};
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	sample.ip = addr;
+	sample.pid = etmq->pid;
+	sample.tid = etmq->tid;
+	sample.id = etmq->etm->instructions_id;
+	sample.stream_id = etmq->etm->instructions_id;
+	sample.period = period;
+	sample.cpu = etmq->packet->cpu;
+	sample.flags = 0;
+	sample.insn_len = 1;
+	sample.cpumode = event->header.misc;
+
+	if (etm->synth_opts.last_branch) {
+		cs_etm__copy_last_branch_rb(etmq);
+		sample.branch_stack = etmq->last_branch;
+	}
+
+	if (etm->synth_opts.inject) {
+		ret = cs_etm__inject_event(event, &sample,
+					   etm->instructions_sample_type);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+	if (ret)
+		pr_err(
+			"CS ETM Trace: failed to deliver instruction event, error %d\n",
+			ret);
+
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(etmq);
+
+	return ret;
+}
+
 /*
  * The cs etm packet encodes an instruction range between a branch target
  * and the next taken branch. Generate sample accordingly.
  */
-static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
-				       struct cs_etm_packet *packet)
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 {
 	int ret = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct perf_sample sample = {.ip = 0,};
 	union perf_event *event = etmq->event_buf;
-	u64 start_addr = packet->start_addr;
-	u64 end_addr = packet->end_addr;
+	struct dummy_branch_stack {
+		u64			nr;
+		struct branch_entry	entries;
+	} dummy_bs;
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = start_addr;
+	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = end_addr;
+	sample.addr = etmq->packet->start_addr;
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
-	sample.cpu = packet->cpu;
+	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.cpumode = PERF_RECORD_MISC_USER;
 
+	/*
+	 * perf report cannot handle events without a branch stack
+	 */
+	if (etm->synth_opts.last_branch) {
+		dummy_bs = (struct dummy_branch_stack){
+			.nr = 1,
+			.entries = {
+				.from = sample.ip,
+				.to = sample.addr,
+			},
+		};
+		sample.branch_stack = (struct branch_stack *)&dummy_bs;
+	}
+
+	if (etm->synth_opts.inject) {
+		ret = cs_etm__inject_event(event, &sample,
+					   etm->branches_sample_type);
+		if (ret)
+			return ret;
+	}
+
 	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
 
 	if (ret)
@@ -578,6 +828,24 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		etm->sample_branches = true;
 		etm->branches_sample_type = attr.sample_type;
 		etm->branches_id = id;
+		id += 1;
+		attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
+	}
+
+	if (etm->synth_opts.last_branch)
+		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+
+	if (etm->synth_opts.instructions) {
+		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+		attr.sample_period = etm->synth_opts.period;
+		etm->instructions_sample_period = attr.sample_period;
+		err = cs_etm__synth_event(session, &attr, id);
+		if (err)
+			return err;
+		etm->sample_instructions = true;
+		etm->instructions_sample_type = attr.sample_type;
+		etm->instructions_id = id;
+		id += 1;
 	}
 
 	return 0;
@@ -585,25 +853,108 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 
 static int cs_etm__sample(struct cs_etm_queue *etmq)
 {
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_packet *tmp;
 	int ret;
-	struct cs_etm_packet packet;
+	u64 instrs_executed;
 
-	while (1) {
-		ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
-		if (ret <= 0)
+	instrs_executed = cs_etm__instr_count(etmq->packet);
+	etmq->period_instructions += instrs_executed;
+
+	/*
+	 * Record a branch when the last instruction in
+	 * PREV_PACKET is a branch.
+	 */
+	if (etm->synth_opts.last_branch &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+	    etmq->prev_packet->last_instr_taken_branch)
+		cs_etm__update_last_branch_rb(etmq);
+
+	if (etm->sample_instructions &&
+	    etmq->period_instructions >= etm->instructions_sample_period) {
+		/*
+		 * Emit instruction sample periodically
+		 * TODO: allow period to be defined in cycles and clock time
+		 */
+
+		/* Get number of instructions executed after the sample point */
+		u64 instrs_over = etmq->period_instructions -
+			etm->instructions_sample_period;
+
+		/*
+		 * Calculate the address of the sampled instruction (-1 as
+		 * sample is reported as though instruction has just been
+		 * executed, but PC has not advanced to next instruction)
+		 */
+		u64 offset = (instrs_executed - instrs_over - 1);
+		u64 addr = cs_etm__instr_addr(etmq->packet, offset);
+
+		ret = cs_etm__synth_instruction_sample(
+			etmq, addr, etm->instructions_sample_period);
+		if (ret)
+			return ret;
+
+		/* Carry remaining instructions into next sample period */
+		etmq->period_instructions = instrs_over;
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+	    etmq->prev_packet->last_instr_taken_branch) {
+		ret = cs_etm__synth_branch_sample(etmq);
+		if (ret)
 			return ret;
+	}
 
+	if (etm->sample_branches || etm->synth_opts.last_branch) {
 		/*
-		 * If the packet contains an instruction range, generate an
-		 * instruction sequence event.
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
 		 */
-		if (packet.sample_type & CS_ETM_RANGE)
-			cs_etm__synth_branch_sample(etmq, &packet);
+		tmp = etmq->packet;
+		etmq->packet = etmq->prev_packet;
+		etmq->prev_packet = tmp;
 	}
 
 	return 0;
 }
 
+static int cs_etm__flush(struct cs_etm_queue *etmq)
+{
+	int err = 0;
+	struct cs_etm_packet *tmp;
+
+	if (etmq->etm->synth_opts.last_branch &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		/*
+		 * Generate a last branch event for the branches left in the
+		 * circular buffer at the end of the trace.
+		 *
+		 * Use the address of the end of the last reported execution
+		 * range
+		 */
+		u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+
+		err = cs_etm__synth_instruction_sample(
+			etmq, addr,
+			etmq->period_instructions);
+		etmq->period_instructions = 0;
+
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = etmq->packet;
+		etmq->packet = etmq->prev_packet;
+		etmq->prev_packet = tmp;
+	}
+
+	return err;
+}
+
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
@@ -615,45 +966,72 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 		etm->kernel_start = machine__kernel_start(etm->machine);
 
 	/* Go through each buffer in the queue and decode them one by one */
-more:
-	buffer_used = 0;
-	memset(&buffer, 0, sizeof(buffer));
-	err = cs_etm__get_trace(&buffer, etmq);
-	if (err <= 0)
-		return err;
-	/*
-	 * We cannot assume consecutive blocks in the data file are contiguous,
-	 * reset the decoder to force re-sync.
-	 */
-	err = cs_etm_decoder__reset(etmq->decoder);
-	if (err != 0)
-		return err;
-
-	/* Run trace decoder until buffer consumed or end of trace */
-	do {
-		processed = 0;
-
-		err = cs_etm_decoder__process_data_block(
-						etmq->decoder,
-						etmq->offset,
-						&buffer.buf[buffer_used],
-						buffer.len - buffer_used,
-						&processed);
-
-		if (err)
+	while (1) {
+		buffer_used = 0;
+		memset(&buffer, 0, sizeof(buffer));
+		err = cs_etm__get_trace(&buffer, etmq);
+		if (err <= 0)
 			return err;
-
-		etmq->offset += processed;
-		buffer_used += processed;
-
 		/*
-		 * Nothing to do with an error condition, let's hope the next
-		 * chunk will be better.
+		 * We cannot assume consecutive blocks in the data file are
+		 * contiguous, reset the decoder to force re-sync.
 		 */
-		err = cs_etm__sample(etmq);
-	} while (buffer.len > buffer_used);
+		err = cs_etm_decoder__reset(etmq->decoder);
+		if (err != 0)
+			return err;
+
+		/* Run trace decoder until buffer consumed or end of trace */
+		do {
+			processed = 0;
+			err = cs_etm_decoder__process_data_block(
+				etmq->decoder,
+				etmq->offset,
+				&buffer.buf[buffer_used],
+				buffer.len - buffer_used,
+				&processed);
+			if (err)
+				return err;
+
+			etmq->offset += processed;
+			buffer_used += processed;
+
+			/* Process each packet in this chunk */
+			while (1) {
+				err = cs_etm_decoder__get_packet(etmq->decoder,
+								 etmq->packet);
+				if (err <= 0)
+					/*
+					 * Stop processing this chunk on
+					 * end of data or error
+					 */
+					break;
+
+				switch (etmq->packet->sample_type) {
+				case CS_ETM_RANGE:
+					/*
+					 * If the packet contains an instruction
+					 * range, generate instruction sequence
+					 * events.
+					 */
+					cs_etm__sample(etmq);
+					break;
+				case CS_ETM_TRACE_ON:
+					/*
+					 * Discontinuity in trace, flush
+					 * previous branch stack
+					 */
+					cs_etm__flush(etmq);
+					break;
+				default:
+					break;
+				}
+			}
+		} while (buffer.len > buffer_used);
 
-goto more;
+		if (err == 0)
+			/* Flush any remaining branch stack entries */
+			err = cs_etm__flush(etmq);
+	}
 
 	return err;
 }
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 44e603c27944..f0a6cbd033cc 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -894,8 +894,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	size_t size;
-	const char *mmap_name;
-	char name_buff[PATH_MAX];
 	struct map *map = machine__kernel_map(machine);
 	struct kmap *kmap;
 	int err;
@@ -918,7 +916,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		return -1;
 	}
 
-	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
 	if (machine__is_host(machine)) {
 		/*
 		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
@@ -931,7 +928,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 
 	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
+			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
@@ -1591,17 +1588,6 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 		return -1;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
-	/*
-	 * Have we already created the kernel maps for this machine?
-	 *
-	 * This should have happened earlier, when we processed the kernel MMAP
-	 * events, but for older perf.data files there was no such thing, so do
-	 * it now.
-	 */
-	if (sample->cpumode == PERF_RECORD_MISC_KERNEL &&
-	    machine__kernel_map(machine) == NULL)
-		machine__create_kernel_maps(machine);
-
 	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e5fc14e53c05..7b7d535396f7 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1086,11 +1086,30 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
+	bool all_threads = (target->per_thread && target->system_wide);
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 
+	/*
+	 * If specify '-a' and '--per-thread' to perf record, perf record
+	 * will override '--per-thread'. target->per_thread = false and
+	 * target->system_wide = true.
+	 *
+	 * If specify '--per-thread' only to perf record,
+	 * target->per_thread = true and target->system_wide = false.
+	 *
+	 * So target->per_thread && target->system_wide is false.
+	 * For perf record, thread_map__new_str doesn't call
+	 * thread_map__new_all_cpus. That will keep perf record's
+	 * current behavior.
+	 *
+	 * For perf stat, it allows the case that target->per_thread and
+	 * target->system_wide are all true. It means to collect system-wide
+	 * per-thread data. thread_map__new_str will call
+	 * thread_map__new_all_cpus to enumerate all threads.
+	 */
 	threads = thread_map__new_str(target->pid, target->tid, target->uid,
-				      target->per_thread);
+				      all_threads);
 
 	if (!threads)
 		return -1;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index f28aaaa3a440..942bdec6d70d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -174,4 +174,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
 int get_cpuid(char *buffer, size_t sz);
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
+int strcmp_cpuid_str(const char *s1, const char *s2);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b6140950301e..44a8456cea10 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -879,7 +879,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 	 * cumulated only one time to prevent entries more than 100%
 	 * overhead.
 	 */
-	he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
+	he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1));
 	if (he_cache == NULL)
 		return -ENOMEM;
 
@@ -1045,8 +1045,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (err)
 		return err;
 
-	iter->max_stack = max_stack_depth;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 02721b579746..e869cad4d89f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -107,7 +107,6 @@ struct hist_entry_iter {
 	int curr;
 
 	bool hide_unresolved;
-	int max_stack;
 
 	struct perf_evsel *evsel;
 	struct perf_sample *sample;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b05a67464c03..fe27ef55cbb9 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -48,8 +48,31 @@ static void machine__threads_init(struct machine *machine)
 	}
 }
 
+static int machine__set_mmap_name(struct machine *machine)
+{
+	if (machine__is_host(machine)) {
+		if (symbol_conf.vmlinux_name)
+			machine->mmap_name = strdup(symbol_conf.vmlinux_name);
+		else
+			machine->mmap_name = strdup("[kernel.kallsyms]");
+	} else if (machine__is_default_guest(machine)) {
+		if (symbol_conf.default_guest_vmlinux_name)
+			machine->mmap_name = strdup(symbol_conf.default_guest_vmlinux_name);
+		else
+			machine->mmap_name = strdup("[guest.kernel.kallsyms]");
+	} else {
+		if (asprintf(&machine->mmap_name, "[guest.kernel.kallsyms.%d]",
+			 machine->pid) < 0)
+			machine->mmap_name = NULL;
+	}
+
+	return machine->mmap_name ? 0 : -ENOMEM;
+}
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
+	int err = -ENOMEM;
+
 	memset(machine, 0, sizeof(*machine));
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
@@ -73,13 +96,16 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	if (machine->root_dir == NULL)
 		return -ENOMEM;
 
+	if (machine__set_mmap_name(machine))
+		goto out;
+
 	if (pid != HOST_KERNEL_ID) {
 		struct thread *thread = machine__findnew_thread(machine, -1,
 								pid);
 		char comm[64];
 
 		if (thread == NULL)
-			return -ENOMEM;
+			goto out;
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
 		thread__set_comm(thread, comm, 0);
@@ -87,7 +113,13 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	}
 
 	machine->current_tid = NULL;
+	err = 0;
 
+out:
+	if (err) {
+		zfree(&machine->root_dir);
+		zfree(&machine->mmap_name);
+	}
 	return 0;
 }
 
@@ -119,7 +151,7 @@ struct machine *machine__new_kallsyms(void)
 	 *    ask for not using the kcore parsing code, once this one is fixed
 	 *    to create a map per module.
 	 */
-	if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
 		machine__delete(machine);
 		machine = NULL;
 	}
@@ -180,6 +212,7 @@ void machine__exit(struct machine *machine)
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
+	zfree(&machine->mmap_name);
 	zfree(&machine->current_tid);
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
@@ -322,20 +355,6 @@ void machines__process_guests(struct machines *machines,
 	}
 }
 
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size)
-{
-	if (machine__is_host(machine))
-		snprintf(bf, size, "[%s]", "kernel.kallsyms");
-	else if (machine__is_default_guest(machine))
-		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
-	else {
-		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms",
-			 machine->pid);
-	}
-
-	return bf;
-}
-
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 {
 	struct rb_node *node;
@@ -771,25 +790,13 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 
 static struct dso *machine__get_kernel(struct machine *machine)
 {
-	const char *vmlinux_name = NULL;
+	const char *vmlinux_name = machine->mmap_name;
 	struct dso *kernel;
 
 	if (machine__is_host(machine)) {
-		vmlinux_name = symbol_conf.vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = DSO__NAME_KALLSYMS;
-
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[kernel]", DSO_TYPE_KERNEL);
 	} else {
-		char bf[PATH_MAX];
-
-		if (machine__is_default_guest(machine))
-			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = machine__mmap_name(machine, bf,
-							  sizeof(bf));
-
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[guest.kernel]",
 						 DSO_TYPE_GUEST_KERNEL);
@@ -849,13 +856,10 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+static int
+__machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	int type;
-	u64 start = 0;
-
-	if (machine__get_running_kernel_start(machine, NULL, &start))
-		return -1;
 
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
@@ -864,7 +868,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		struct kmap *kmap;
 		struct map *map;
 
-		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		machine->vmlinux_maps[type] = map__new2(0, kernel, type);
 		if (machine->vmlinux_maps[type] == NULL)
 			return -1;
 
@@ -987,11 +991,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 	return machine__create_kernel_maps(machine);
 }
 
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore)
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			     enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore);
+	int ret = __dso__load_kallsyms(map->dso, filename, map, true);
 
 	if (ret > 0) {
 		dso__set_loaded(map->dso, type);
@@ -1006,12 +1010,6 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename,
 	return ret;
 }
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type)
-{
-	return __machine__load_kallsyms(machine, filename, type, false);
-}
-
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
@@ -1215,6 +1213,24 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
+static void machine__set_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	int i;
+
+	for (i = 0; i < MAP__NR_TYPES; i++) {
+		machine->vmlinux_maps[i]->start = start;
+		machine->vmlinux_maps[i]->end   = end;
+
+		/*
+		 * Be a bit paranoid here, some perf.data file came with
+		 * a zero sized synthesized MMAP event for the kernel.
+		 */
+		if (machine->vmlinux_maps[i]->end == 0)
+			machine->vmlinux_maps[i]->end = ~0ULL;
+	}
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1239,40 +1255,22 @@ int machine__create_kernel_maps(struct machine *machine)
 				 "continuing anyway...\n", machine->pid);
 	}
 
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
-
 	if (!machine__get_running_kernel_start(machine, &name, &addr)) {
 		if (name &&
 		    maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 			machine__destroy_kernel_maps(machine);
 			return -1;
 		}
+		machine__set_kernel_mmap(machine, addr, 0);
 	}
 
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&machine->kmaps);
 	return 0;
 }
 
-static void machine__set_kernel_mmap_len(struct machine *machine,
-					 union perf_event *event)
-{
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; i++) {
-		machine->vmlinux_maps[i]->start = event->mmap.start;
-		machine->vmlinux_maps[i]->end   = (event->mmap.start +
-						   event->mmap.len);
-		/*
-		 * Be a bit paranoid here, some perf.data file came with
-		 * a zero sized synthesized MMAP event for the kernel.
-		 */
-		if (machine->vmlinux_maps[i]->end == 0)
-			machine->vmlinux_maps[i]->end = ~0ULL;
-	}
-}
-
 static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
@@ -1289,7 +1287,6 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 					      union perf_event *event)
 {
 	struct map *map;
-	char kmmap_prefix[PATH_MAX];
 	enum dso_kernel_type kernel_type;
 	bool is_kernel_mmap;
 
@@ -1297,15 +1294,14 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 	if (machine__uses_kcore(machine))
 		return 0;
 
-	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
 	if (machine__is_host(machine))
 		kernel_type = DSO_TYPE_KERNEL;
 	else
 		kernel_type = DSO_TYPE_GUEST_KERNEL;
 
 	is_kernel_mmap = memcmp(event->mmap.filename,
-				kmmap_prefix,
-				strlen(kmmap_prefix) - 1) == 0;
+				machine->mmap_name,
+				strlen(machine->mmap_name) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
 		map = machine__findnew_module_map(machine, event->mmap.start,
@@ -1316,7 +1312,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
 		const char *symbol_name = (event->mmap.filename +
-				strlen(kmmap_prefix));
+				strlen(machine->mmap_name));
 		/*
 		 * Should be there already, from the build-id table in
 		 * the header.
@@ -1357,7 +1353,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		up_read(&machine->dsos.lock);
 
 		if (kernel == NULL)
-			kernel = machine__findnew_dso(machine, kmmap_prefix);
+			kernel = machine__findnew_dso(machine, machine->mmap_name);
 		if (kernel == NULL)
 			goto out_problem;
 
@@ -1370,7 +1366,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap_len(machine, event);
+		machine__set_kernel_mmap(machine, event->mmap.start,
+					 event->mmap.start + event->mmap.len);
 
 		/*
 		 * Avoid using a zero address (kptr_restrict) for the ref reloc
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5ce860b64c74..66cc200ef86f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -43,6 +43,7 @@ struct machine {
 	bool		  comm_exec;
 	bool		  kptr_restrict_warned;
 	char		  *root_dir;
+	char		  *mmap_name;
 	struct threads    threads[THREADS__TABLE_SIZE];
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
@@ -142,8 +143,6 @@ struct machine *machines__find(struct machines *machines, pid_t pid);
 struct machine *machines__findnew(struct machines *machines, pid_t pid);
 
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
-
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
@@ -226,8 +225,6 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
 int arch__fix_module_text_start(u64 *start, const char *name);
 
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore);
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type);
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
@@ -239,7 +236,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);
 
 void machine__destroy_kernel_maps(struct machine *machine);
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
 int machine__create_kernel_maps(struct machine *machine);
 
 int machines__create_kernel_maps(struct machines *machines, pid_t pid);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 57e38fdf0b34..1111d5bf15ca 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -576,6 +576,34 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 	return NULL;
 }
 
+/* Return zero when the cpuid from the mapfile.csv matches the
+ * cpuid string generated on this platform.
+ * Otherwise return non-zero.
+ */
+int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	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))
+			return 0;
+	}
+	return 1;
+}
+
 static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;
@@ -610,31 +638,14 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 
 	i = 0;
 	for (;;) {
-		regex_t re;
-		regmatch_t pmatch[1];
-		int match;
-
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
-			/* Warn unable to generate match particular string. */
-			pr_info("Invalid regular expression %s\n", map->cpuid);
+		if (!strcmp_cpuid_str(map->cpuid, 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;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2da4d0456a03..e8514f651865 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -111,17 +111,20 @@ struct sort_entry sort_thread = {
 
 /* --sort comm */
 
+/*
+ * We can't use pointer comparison in functions below,
+ * because it gives different results based on pointer
+ * values, which could break some sorting assumptions.
+ */
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	/* Compare the addr that should be unique among comm */
 	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
-	/* Compare the addr that should be unique among comm */
 	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index dbc6f7134f61..2f44e386a0e8 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,6 +90,8 @@ struct perf_stat_config {
 	bool		scale;
 	FILE		*output;
 	unsigned int	interval;
+	unsigned int	timeout;
+	int		times;
 	struct runtime_stat *stats;
 	int		stats_num;
 };
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cc065d4bfafc..a1a312d99f30 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1582,7 +1582,7 @@ int dso__load(struct dso *dso, struct map *map)
 		bool next_slot = false;
 		bool is_reg;
 		bool nsexit;
-		int sirc;
+		int sirc = -1;
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
@@ -1600,16 +1600,14 @@ int dso__load(struct dso *dso, struct map *map)
 			nsinfo__mountns_exit(&nsc);
 
 		is_reg = is_regular_file(name);
-		sirc = symsrc__init(ss, dso, name, symtab_type);
+		if (is_reg)
+			sirc = symsrc__init(ss, dso, name, symtab_type);
 
 		if (nsexit)
 			nsinfo__mountns_enter(dso->nsinfo, &nsc);
 
-		if (!is_reg || sirc < 0) {
-			if (sirc >= 0)
-				symsrc__destroy(ss);
+		if (!is_reg || sirc < 0)
 			continue;
-		}
 
 		if (!syms_ss && symsrc__has_symtab(ss)) {
 			syms_ss = ss;
@@ -1960,8 +1958,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
 		dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
-		machine__mmap_name(machine, path, sizeof(path));
-		dso__set_long_name(dso, strdup(path), true);
+		dso__set_long_name(dso, machine->mmap_name, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 303bdb84ab5a..895122d638dd 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -30,6 +30,14 @@ static const char **syscalltbl_native = syscalltbl_x86_64;
 #include <asm/syscalls_64.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_s390_64;
+#elif defined(__powerpc64__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_64;
+#elif defined(__powerpc__)
+#include <asm/syscalls_32.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_32;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 3e1038f6491c..729dad8f412d 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -323,7 +323,7 @@ out_free_threads:
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-				       uid_t uid, bool per_thread)
+				       uid_t uid, bool all_threads)
 {
 	if (pid)
 		return thread_map__new_by_pid_str(pid);
@@ -331,7 +331,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	if (!tid && uid != UINT_MAX)
 		return thread_map__new_by_uid(uid);
 
-	if (per_thread)
+	if (all_threads)
 		return thread_map__new_all_cpus();
 
 	return thread_map__new_by_tid_str(tid);
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0a806b99e73c..5ec91cfd1869 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -31,7 +31,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-		const char *tid, uid_t uid, bool per_thread);
+		const char *tid, uid_t uid, bool all_threads);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);