Merge tag 'v4.19-rc5' of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into fbdev-for-next

Sync with upstream (which now contains fbdev-v4.19 changes) to prepare a base for fbdev-v4.20 changes.
author: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> 2018-09-26 15:54:31 +0200
committer: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> 2018-09-26 15:54:31 +0200
commit: aaccf3c97418f169afdbb5855e9cbcbda34e90fd (patch)
tree: 5d4207e67958bdbc23288cf30178692f5534e1a0 /tools/perf
parent: f39684524b391c5a7ed0ac44db4fec3357af1c5d (diff)
parent: 6bf4ca7fbc85d80446ac01c0d1d77db4d91a6d84 (diff)
156 files changed, 3636 insertions, 772 deletions
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 42261a9b280e..ac841bc5c35b 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt
 	mv $@+ $@
 
 ifdef USE_ASCIIDOCTOR
-$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b manpage -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 749cc6055dac..e8c972f89357 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -118,6 +118,15 @@ OPTIONS
 --group::
 	Show event group information together
 
+--percent-type::
+	Set annotation percent type from following choices:
+	  global-period, local-period, global-hits, local-hits
+
+	The local/global keywords set if the percentage is computed
+	in the scope of the function (local) or the whole data (global).
+	The period/hits keywords set the base the percentage is computed
+	on - the samples period or the number of samples (hits).
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
 	selects either tracepoint event(s) or a hardware trace PMU
 	(e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
-	a event selector (-e) which selects tracepoint event(s). It adds a
+	an event selector (-e) which selects tracepoint event(s). It adds a
 	filter expression 'common_pid != $PERFPID' to filters. If other
 	'--filter' exists, the new filter expression will be combined with
 	them by '&&'.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 917e36fde6d8..474a4941f65d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -477,6 +477,15 @@ include::itrace.txt[]
 	Display monitored tasks stored in perf data. Displaying pid/tid/ppid
 	plus the command string aligned to distinguish parent and child tasks.
 
+--percent-type::
+	Set annotation percent type from following choices:
+	  global-period, local-period, global-hits, local-hits
+
+	The local/global keywords set if the percentage is computed
+	in the scope of the function (local) or the whole data (global).
+	The period/hits keywords set the base the percentage is computed
+	on - the samples period or the number of samples (hits).
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 225454416ed5..7902a5681fc8 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -84,10 +84,10 @@ endif # has_clean
 endif # MAKECMDGOALS
 
 #
-# The clean target is not really parallel, don't print the jobs info:
+# Explicitly disable parallelism for the clean target.
 #
 clean:
-	$(make)
+	$(make) -j1
 
 #
 # The build-test target is not really parallel, don't print the jobs info,
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
@@ -207,8 +209,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   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)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
@@ -906,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..5224ade3d5af 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -768,14 +777,12 @@ endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBBPF
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, include/bpf) \
-		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, examples/bpf) \
-		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-headers) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-examples) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
+		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -860,6 +867,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..dbef716a1913 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,25 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..2dbb8cade048
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+incpath=$3
+input=$4
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 1120e39c1b00..5ccfce87e693 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -194,6 +194,7 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	sper->itr.read_finish = arm_spe_read_finish;
 	sper->itr.alignment = 0;
 
+	*err = 0;
 	return &sper->itr;
 }
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
 	}
 
 	/*
-	 * Check if return address is on the stack.
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
 	 */
-	if (nops != 0 || ops != NULL)
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
 		return 0;
 
 	/*
@@ -243,10 +247,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
-	ip = chain->ips[2];
+	ip = chain->ips[1];
 
 	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 53d83d7e6a09..10a44e946f77 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 
 #endif
 
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
 int arch__choose_best_symbol(struct symbol *syma,
 			     struct symbol *symb __maybe_unused)
 {
 	char *sym = syma->name;
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 	/* Skip over any initial dot */
 	if (*sym == '.')
 		sym++;
+#endif
 
 	/* Avoid "SyS" kernel syscall aliases */
 	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
@@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma,
 	return SYMBOL_A;
 }
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 /* Allow matching against dot variants */
 int arch__compare_symbol_names(const char *namea, const char *nameb)
 {
@@ -141,8 +143,10 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 	for (i = 0; i < ntevs; i++) {
 		tev = &pev->tevs[i];
 		map__for_each_symbol(map, sym, tmp) {
-			if (map->unmap_ip(map, sym->start) == tev->point.address)
+			if (map->unmap_ip(map, sym->start) == tev->point.address) {
 				arch__fix_tev_from_maps(pev, tev, map, sym);
+				break;
+			}
 		}
 	}
 }
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index 3afe8256eff2..44c857388897 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -30,6 +30,7 @@ cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused,
 		 struct auxtrace_info_event *auxtrace_info __maybe_unused,
 		 size_t priv_size __maybe_unused)
 {
+	auxtrace_info->type = PERF_AUXTRACE_S390_CPUMSF;
 	return 0;
 }
 
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-	if (strstr(cpuid, "IBM/S390")) {
+	if (strstr(cpuid, "IBM")) {
 		kvm->exit_reasons = sie_exit_reasons;
 		kvm->exit_reasons_isa = "SIE";
 	} else
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 1a38e78117ce..8cc6642fce7a 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -19,9 +19,6 @@ systbl := $(sys)/syscalltbl.sh
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sys)/syscall_64.tbl $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-        (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
-        || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c1bd979b957b..613709cfbbd0 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -9,6 +9,7 @@ struct test;
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__bp_modify(struct test *test, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 8e2c5a38c3b9..586849ff83a0 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -5,3 +5,4 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
+libperf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index cc1802ff5410..d47d3f8e3c8e 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -24,6 +24,12 @@ struct test arch_tests[] = {
 		.func = test__insn_x86,
 	},
 #endif
+#if defined(__x86_64__)
+	{
+		.desc = "x86 bp modify",
+		.func = test__bp_modify,
+	},
+#endif
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c
new file mode 100644
index 000000000000..f53e4406709f
--- /dev/null
+++ b/tools/perf/arch/x86/tests/bp-modify.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <asm/ptrace.h>
+#include <errno.h>
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static noinline int bp_1(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static noinline int bp_2(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static int spawn_child(void)
+{
+	int child = fork();
+
+	if (child == 0) {
+		/*
+		 * The child sets itself for as tracee and
+		 * waits in signal for parent to trace it,
+		 * then it calls bp_1 and quits.
+		 */
+		int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL);
+
+		if (err) {
+			pr_debug("failed to PTRACE_TRACEME\n");
+			exit(1);
+		}
+
+		raise(SIGCONT);
+		bp_1();
+		exit(0);
+	}
+
+	return child;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it and checks it was properly changed.
+ */
+static int bp_modify1(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_2 function
+	 *  - changes that breakponit to bp_1 function
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_2)) {
+		pr_debug("failed to set breakpoint, 1st time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint, 2nd time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it to bogus value and checks the original
+ * breakpoint is hit.
+ */
+static int bp_modify2(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_1 function
+	 *  - tries to change that breakpoint to (-1) address
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (!ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) {
+		pr_debug("failed, breakpoint set to bogus address\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+int test__bp_modify(struct test *test __maybe_unused,
+		    int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
+	TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2());
+
+	return 0;
+}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 63a74c32ddc5..e33ef5bc31c5 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 06bae7023a51..950539f9a4f7 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -2,6 +2,7 @@
 #include <stdbool.h>
 #include <errno.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..eafce1a130a1 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index b43f8d2a34ec..9ad015a1e202 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,6 +6,7 @@
 #define altinstr_replacement text
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
 
 #include "../../arch/x86/lib/memcpy_64.S"
 /*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
new file mode 100644
index 000000000000..4130734dde84
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c
@@ -0,0 +1,24 @@
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..830481b8db26 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ out_put:
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -533,6 +542,10 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
 			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
 			     stdio__config_color, "always"),
+	OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period",
+		     "Set percent type local/global-period/hits",
+		     annotate_parse_percent_type),
+
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
 	fprintf(out, "%s\n", bf);
 	fprintf(out, "  -------------------------------------------------------------\n");
 
-	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 	fprintf(out, "#\n");
 
-	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
 	fprintf(out, "\n");
 	fprintf(out, "=================================================\n");
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
 	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-		       symbol_conf.use_callchain);
+		       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 54d3f21b0e62..b63bca4b0c2a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -729,7 +729,7 @@ static char *compact_gfp_string(unsigned long gfp_flags)
 static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
 			   unsigned int gfp_flags)
 {
-	struct pevent_record record = {
+	struct tep_record record = {
 		.cpu = sample->cpu,
 		.data = sample->raw_data,
 		.size = sample->raw_size,
@@ -747,7 +747,7 @@ static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
 	}
 
 	trace_seq_init(&seq);
-	pevent_event_info(&seq, evsel->tp_format, &record);
+	tep_event_info(&seq, evsel->tp_format, &record);
 
 	str = strtok_r(seq.buffer, " ", &pos);
 	while (str) {
@@ -1974,7 +1974,7 @@ int cmd_kmem(int argc, const char **argv)
 			goto out_delete;
 		}
 
-		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+		kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
 		symbol_conf.use_callchain = true;
 	}
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..76e12bcd1765 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
@@ -477,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-			       symbol_conf.use_callchain ||
-			       symbol_conf.show_branchflag_count);
+			       !(symbol_conf.use_callchain ||
+			         symbol_conf.show_branchflag_count));
 		fprintf(stdout, "\n\n");
 	}
 
@@ -1123,6 +1124,9 @@ int cmd_report(int argc, const char **argv)
 		   "Time span of interest (start,stop)"),
 	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
 		    "Show inline function"),
+	OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period",
+		     "Set percent type local/global-period/hits",
+		     annotate_parse_percent_type),
 	OPT_END()
 	};
 	struct perf_data data = {
@@ -1365,9 +1369,9 @@ repeat:
 	}
 
 	if (session->tevent.pevent &&
-	    pevent_set_function_resolver(session->tevent.pevent,
-					 machine__resolve_kernel_addr,
-					 &session->machines.host) < 0) {
+	    tep_set_function_resolver(session->tevent.pevent,
+				      machine__resolve_kernel_addr,
+				      &session->machines.host) < 0) {
 		pr_err("%s: failed to set libtraceevent function resolver\n",
 		       __func__);
 		return -1;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a31d7082188e..ba481d73f910 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3030,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3074,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3125,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
@@ -3405,9 +3429,9 @@ int cmd_script(int argc, const char **argv)
 		symbol_conf.use_callchain = false;
 
 	if (session->tevent.pevent &&
-	    pevent_set_function_resolver(session->tevent.pevent,
-					 machine__resolve_kernel_addr,
-					 &session->machines.host) < 0) {
+	    tep_set_function_resolver(session->tevent.pevent,
+				      machine__resolve_kernel_addr,
+				      &session->machines.host) < 0) {
 		pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
 		err = -1;
 		goto out_delete;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 22547a490e1f..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		return 1;
-
-	return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double msecs = avg / NSEC_PER_MSEC;
-	const char *fmt_v, *fmt_n;
-	char name[25];
-
-	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-	fmt_n = csv_output ? "%s" : "%-25s";
-
-	aggr_printout(evsel, id, nr);
-
-	scnprintf(name, sizeof(name), "%s%s",
-		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-	fprintf(output, fmt_v, msecs, csv_sep);
-
-	if (csv_output)
-		fprintf(output, "%s%s", evsel->unit, csv_sep);
-	else
-		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-	fprintf(output, fmt_n, name);
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
 	int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (metric_only)
-		/* nothing */;
-	else if (nsec_counter(counter))
-		nsec_printout(id, nr, counter, uval);
-	else
+	if (!metric_only)
 		abs_printout(id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    nsec_counter(alias) != nsec_counter(counter))
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
 		cb(alias, data, false);
@@ -1742,7 +1698,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if ((num_print_interval == 0 && metric_only) || interval_clear)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
@@ -2449,6 +2405,18 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		/* Handle -T as -M transaction. Once platform specific metrics
+		 * support has been added to the json files, all archictures
+		 * will use this approach. To determine transaction support
+		 * on an architecture test for such a metric name.
+		 */
+		if (metricgroup__has_metric("transaction")) {
+			struct option opt = { .value = &evsel_list };
+
+			return metricgroup__parse_groups(&opt, "transaction",
+							 &metric_events);
+		}
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout, symbol_conf.use_callchain);
+		       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..22ab8e67c760 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -77,7 +77,8 @@ struct trace {
 		struct syscall  *table;
 		struct {
 			struct perf_evsel *sys_enter,
-					  *sys_exit;
+					  *sys_exit,
+					  *augmented;
 		}		events;
 	} syscalls;
 	struct record_opts	opts;
@@ -121,7 +122,6 @@ struct trace {
 	bool			force;
 	bool			vfs_getname;
 	int			trace_pgfaults;
-	int			open_id;
 };
 
 struct tp_field {
@@ -157,13 +157,11 @@ TP_UINT_FIELD__SWAPPED(16);
 TP_UINT_FIELD__SWAPPED(32);
 TP_UINT_FIELD__SWAPPED(64);
 
-static int tp_field__init_uint(struct tp_field *field,
-			       struct format_field *format_field,
-			       bool needs_swap)
+static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap)
 {
-	field->offset = format_field->offset;
+	field->offset = offset;
 
-	switch (format_field->size) {
+	switch (size) {
 	case 1:
 		field->integer = tp_field__u8;
 		break;
@@ -183,18 +181,28 @@ static int tp_field__init_uint(struct tp_field *field,
 	return 0;
 }
 
+static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap)
+{
+	return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
+}
+
 static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
 {
 	return sample->raw_data + field->offset;
 }
 
-static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+static int __tp_field__init_ptr(struct tp_field *field, int offset)
 {
-	field->offset = format_field->offset;
+	field->offset = offset;
 	field->pointer = tp_field__ptr;
 	return 0;
 }
 
+static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+{
+	return __tp_field__init_ptr(field, format_field->offset);
+}
+
 struct syscall_tp {
 	struct tp_field id;
 	union {
@@ -240,7 +248,47 @@ static void perf_evsel__delete_priv(struct perf_evsel *evsel)
 	perf_evsel__delete(evsel);
 }
 
-static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
+static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+
+	if (evsel->priv != NULL) {
+		if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr"))
+			goto out_delete;
+		return 0;
+	}
+
+	return -ENOMEM;
+out_delete:
+	zfree(&evsel->priv);
+	return -ENOENT;
+}
+
+static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+
+	if (evsel->priv != NULL) {       /* field, sizeof_field, offsetof_field */
+		if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap))
+			goto out_delete;
+
+		return 0;
+	}
+
+	return -ENOMEM;
+out_delete:
+	zfree(&evsel->priv);
+	return -EINVAL;
+}
+
+static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv;
+
+	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
+}
+
+static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
 {
 	evsel->priv = malloc(sizeof(struct syscall_tp));
 	if (evsel->priv != NULL) {
@@ -258,7 +306,7 @@ out_delete:
 	return -ENOENT;
 }
 
-static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
+static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler)
 {
 	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
@@ -269,7 +317,7 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void
 	if (IS_ERR(evsel))
 		return NULL;
 
-	if (perf_evsel__init_syscall_tp(evsel, handler))
+	if (perf_evsel__init_raw_syscall_tp(evsel, handler))
 		goto out_delete;
 
 	return evsel;
@@ -291,7 +339,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +809,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
@@ -803,12 +853,17 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+/*
+ * is_exit: is this "exit" or "exit_group"?
+ * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ */
 struct syscall {
 	struct event_format *tp_format;
 	int		    nr_args;
+	bool		    is_exit;
+	bool		    is_open;
 	struct format_field *args;
 	const char	    *name;
-	bool		    is_exit;
 	struct syscall_fmt  *fmt;
 	struct syscall_arg_fmt *arg_fmt;
 };
@@ -1297,6 +1352,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	}
 
 	sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+	sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat");
 
 	return syscall__set_arg_fmts(sc);
 }
@@ -1659,6 +1715,37 @@ out_put:
 	return err;
 }
 
+static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel,
+				    struct perf_sample *sample)
+{
+	struct thread_trace *ttrace;
+	struct thread *thread;
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+	struct syscall *sc = trace__syscall_info(trace, evsel, id);
+	char msg[1024];
+	void *args;
+
+	if (sc == NULL)
+		return -1;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	/*
+	 * We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
+	 * and the rest of the beautifiers accessing it via struct syscall_arg touches it.
+	 */
+	if (ttrace == NULL)
+		goto out_put;
+
+	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
+	syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+	fprintf(trace->output, "%s", msg);
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
+}
+
 static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel,
 				    struct perf_sample *sample,
 				    struct callchain_cursor *cursor)
@@ -1720,7 +1807,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
 	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
-	if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
+	if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) {
 		trace__set_fd_pathname(thread, ret, ttrace->filename.name);
 		ttrace->filename.pending_open = false;
 		++trace->stats.vfs_getname;
@@ -1955,11 +2042,17 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	fprintf(trace->output, "%s:", evsel->name);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		bpf_output__fprintf(trace, sample);
+		if (evsel == trace->syscalls.events.augmented)
+			trace__fprintf_sys_enter(trace, evsel, sample);
+		else
+			bpf_output__fprintf(trace, sample);
 	} else if (evsel->tp_format) {
-		event_format__fprintf(evsel->tp_format, sample->cpu,
-				      sample->raw_data, sample->raw_size,
-				      trace->output);
+		if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
+		    trace__fprintf_sys_enter(trace, evsel, sample)) {
+			event_format__fprintf(evsel->tp_format, sample->cpu,
+					      sample->raw_data, sample->raw_size,
+					      trace->output);
+		}
 	}
 
 	fprintf(trace->output, "\n");
@@ -2240,14 +2333,14 @@ static int trace__add_syscall_newtp(struct trace *trace)
 	struct perf_evlist *evlist = trace->evlist;
 	struct perf_evsel *sys_enter, *sys_exit;
 
-	sys_enter = perf_evsel__syscall_newtp("sys_enter", trace__sys_enter);
+	sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter);
 	if (sys_enter == NULL)
 		goto out;
 
 	if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
 		goto out_delete_sys_enter;
 
-	sys_exit = perf_evsel__syscall_newtp("sys_exit", trace__sys_exit);
+	sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit);
 	if (sys_exit == NULL)
 		goto out_delete_sys_enter;
 
@@ -2669,7 +2762,7 @@ static int trace__replay(struct trace *trace)
 							     "syscalls:sys_enter");
 
 	if (evsel &&
-	    (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+	    (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
 	    perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
 		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
 		goto out;
@@ -2681,7 +2774,7 @@ static int trace__replay(struct trace *trace)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_exit");
 	if (evsel &&
-	    (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+	    (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
 	    perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
 		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
 		goto out;
@@ -2921,6 +3014,36 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 		evsel->handler = handler;
 }
 
+static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->priv || !evsel->tp_format)
+			continue;
+
+		if (strcmp(evsel->tp_format->system, "syscalls"))
+			continue;
+
+		if (perf_evsel__init_syscall_tp(evsel))
+			return -1;
+
+		if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
+			struct syscall_tp *sc = evsel->priv;
+
+			if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)))
+				return -1;
+		} else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) {
+			struct syscall_tp *sc = evsel->priv;
+
+			if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * XXX: Hackish, just splitting the combined -e+--event (syscalls
  * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
@@ -2990,6 +3113,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3045,7 +3169,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3120,8 +3244,9 @@ int cmd_trace(int argc, const char **argv)
 	};
 	bool __maybe_unused max_stack_user_set = true;
 	bool mmap_pages_user_set = true;
+	struct perf_evsel *evsel;
 	const char * const trace_subcommands[] = { "record", NULL };
-	int err;
+	int err = -1;
 	char bf[BUFSIZ];
 
 	signal(SIGSEGV, sighandler_dump_stack);
@@ -3144,6 +3269,20 @@ int cmd_trace(int argc, const char **argv)
 				       "cgroup monitoring only available in system-wide mode");
 	}
 
+	evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
+	if (IS_ERR(evsel)) {
+		bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
+		pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
+		goto out;
+	}
+
+	if (evsel) {
+		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+		    perf_evsel__init_augmented_syscall_tp_args(evsel))
+			goto out;
+		trace.syscalls.events.augmented = evsel;
+	}
+
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
@@ -3179,8 +3318,13 @@ int cmd_trace(int argc, const char **argv)
 		symbol_conf.use_callchain = true;
 	}
 
-	if (trace.evlist->nr_entries > 0)
+	if (trace.evlist->nr_entries > 0) {
 		evlist__set_evsel_handler(trace.evlist, trace__event_handler);
+		if (evlist__set_syscall_tp_fields(trace.evlist)) {
+			perror("failed to set syscalls:* tracepoint fields");
+			goto out;
+		}
+	}
 
 	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
 		return trace__record(&trace, argc-1, &argv[1]);
@@ -3191,13 +3335,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
@@ -3208,8 +3346,6 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
-	trace.open_id = syscalltbl__id(trace.sctbl, "open");
-
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..466540ee8ea7 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
@@ -64,8 +67,12 @@ check_2 () {
 
   cmd="diff $* $file1 $file2 > /dev/null"
 
-  test -f $file2 &&
-  eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
+  test -f $file2 && {
+    eval $cmd || {
+      echo "Warning: Kernel ABI header at '$file1' differs from latest version at '$file2'" >&2
+      echo diff -u $file1 $file2
+    }
+  }
 }
 
 check () {
@@ -73,7 +80,7 @@ check () {
 
   shift
 
-  check_2 ../$file ../../$file $*
+  check_2 tools/$file $file $*
 }
 
 # Check if we have the kernel headers (tools/perf/../../include), else
@@ -81,6 +88,8 @@ check () {
 # differences.
 test -d ../../include || exit 0
 
+cd ../..
+
 # simple diff check
 for i in $HEADERS; do
   check $i -B
@@ -91,3 +100,8 @@ check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
+
+# diff non-symmetric files
+check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
+
+cd tools/perf
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
new file mode 100644
index 000000000000..69a31386d8cd
--- /dev/null
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the openat syscall with the contents of the filename pointer argument.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#include <stdio.h>
+
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+struct syscall_enter_openat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+struct augmented_enter_openat_args {
+	struct syscall_enter_openat_args args;
+	char				 filename[64];
+};
+
+int syscall_enter(openat)(struct syscall_enter_openat_args *args)
+{
+	struct augmented_enter_openat_args augmented_args;
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
+			  &augmented_args, sizeof(augmented_args));
+	return 1;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/hello.c b/tools/perf/examples/bpf/hello.c
new file mode 100644
index 000000000000..cf3c2fdc7f79
--- /dev/null
+++ b/tools/perf/examples/bpf/hello.c
@@ -0,0 +1,9 @@
+#include <stdio.h>
+
+int syscall_enter(openat)(void *args)
+{
+	puts("Hello, world\n");
+	return 0;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c
new file mode 100644
index 000000000000..9cd124b09392
--- /dev/null
+++ b/tools/perf/examples/bpf/sys_enter_openat.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hook into 'openat' syscall entry tracepoint
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * The syscall_enter_openat_args can be used to get the syscall fields
+ * and use them for filtering calls, i.e. use in expressions for
+ * the return value.
+ */
+
+#include <bpf.h>
+
+struct syscall_enter_openat_args {
+	unsigned long long unused;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+int syscall_enter(openat)(struct syscall_enter_openat_args *args)
+{
+	return 1;
+}
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..47897d65e799 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,13 +1,36 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
+/*
+ * A helper structure used by eBPF C program to describe map attributes to
+ * elf_bpf loader, taken from tools/testing/selftests/bpf/bpf_helpers.h:
+ */
+struct bpf_map {
+        unsigned int type;
+        unsigned int key_size;
+        unsigned int value_size;
+        unsigned int max_entries;
+        unsigned int map_flags;
+        unsigned int inner_map_idx;
+        unsigned int numa_node;
+};
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
 	SEC(#function "=" #function " " #vars) function
 
+#define syscall_enter(name) \
+	SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
+
 #define license(name) \
 char _license[] SEC("license") = #name; \
 int _version SEC("version") = LINUX_VERSION_CODE;
 
+static int (*probe_read)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read;
+static int (*probe_read_str)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read_str;
+
 #endif /* _PERF_BPF_H */
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
new file mode 100644
index 000000000000..2899cb7bfed8
--- /dev/null
+++ b/tools/perf/include/bpf/stdio.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <bpf.h>
+
+struct bpf_map SEC("maps") __bpf_stdout__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+static int (*perf_event_output)(void *, struct bpf_map *, int, void *, unsigned long) =
+	(void *)BPF_FUNC_perf_event_output;
+
+#define puts(from) \
+	({ const int __len = sizeof(from); \
+	   char __from[__len] = from; \
+	   perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \
+			  &__from, __len & (sizeof(from) - 1)); })
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a1a97956136f..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,6 +5,7 @@
 #include <time.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
@@ -24,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 17783913d330..215ba30b8534 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -1,7 +1,7 @@
 hostprogs := jevents
 
 jevents-y	+= json.o jsmn.o jevents.o
-CHOSTFLAGS_jevents.o	= -I$(srctree)/tools/include
+HOSTCFLAGS_jevents.o	= -I$(srctree)/tools/include
 pmu-events-y	+= pmu-events.o
 JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
new file mode 100644
index 000000000000..bc03c06c3918
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
@@ -0,0 +1,32 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+   },
+   {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index f03e26ecb658..59cd8604b0bd 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -16,3 +16,4 @@
 0x00000000420f5160,v1,cavium/thunderx2,core
 0x00000000430f0af0,v1,cavium/thunderx2,core
 0x00000000480fd010,v1,hisilicon/hip08,core
+0x00000000500f0000,v1,ampere/emag,core
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1I_L3_LOCAL_WRITES",
 		"BriefDescription": "L1I L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1D_L3_LOCAL_WRITES",
 		"BriefDescription": "L1D L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1I_L3_REMOTE_WRITES",
 		"BriefDescription": "L1I L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L3_REMOTE_WRITES",
 		"BriefDescription": "L1D L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_CACHELINE_INVALIDATES",
 		"BriefDescription": "L1I Cacheline Invalidates",
 		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
 		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB1_MISSES",
 		"BriefDescription": "L1C TLB1 Misses",
 		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "176",
 		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "218",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "219",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "220",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB2_WRITES",
 		"BriefDescription": "DTLB2 Writes",
 		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB2_MISSES",
 		"BriefDescription": "DTLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB2_GPAGE_WRITES",
 		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
 		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB2_WRITES",
 		"BriefDescription": "ITLB2 Writes",
 		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB2_MISSES",
 		"BriefDescription": "ITLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_ENGINES_BUSY",
 		"BriefDescription": "TLB2 Engines Busy",
 		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB2_MISSES",
 		"BriefDescription": "L1C TLB2 Misses",
 		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "224",
 		"EventName": "BCD_DFP_EXECUTION_SLOTS",
 		"BriefDescription": "BCD DFP Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "225",
 		"EventName": "VX_BCD_EXECUTION_SLOTS",
 		"BriefDescription": "VX BCD Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "226",
 		"EventName": "DECIMAL_INSTRUCTIONS",
 		"BriefDescription": "Decimal Instructions",
 		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "232",
 		"EventName": "LAST_HOST_TRANSLATIONS",
 		"BriefDescription": "Last host translation done",
 		"PublicDescription": "Last Host Translation done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "243",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "244",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "245",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
 		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1D_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1D L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
 	{ "iMPH-U", "uncore_arb" },
+	{ "CPU-M-CF", "cpum_cf" },
+	{ "CPU-M-SF", "cpum_sf" },
 	{}
 };
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value):
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value):
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ def trace_flag_str(value):
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ class PerfEvent(object):
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ def nsecs_str(nsecs):
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ class TimeSliceList(UserList):
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ class SchedEventProxy:
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 47bedf25ba69..96e7fc1ad3f9 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -16,8 +16,6 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 	bm = bitmap_alloc(nbits);
 
 	if (map && bm) {
-		bitmap_zero(bm, nbits);
-
 		for (i = 0; i < map->nr; i++)
 			set_bit(map->map[i], bm);
 	}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 4892bd2dc33e..6b049f3f5cf4 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -232,6 +232,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	u64 objdump_addr;
 	const char *objdump_name;
 	char decomp_name[KMOD_DECOMP_LEN];
+	bool decomp = false;
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -305,6 +306,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 			return -1;
 		}
 
+		decomp = true;
 		objdump_name = decomp_name;
 	}
 
@@ -312,7 +314,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
 	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
 
-	if (dso__needs_decompress(al.map->dso))
+	if (decomp)
 		unlink(objdump_name);
 
 	if (ret > 0) {
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 148dd31cc201..0579a70bbbff 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -5,34 +5,28 @@
 #include "dso.h"
 #include "debug.h"
 
-static int test(const char *path, bool alloc_name, bool alloc_ext,
-		bool kmod, bool comp, const char *name, const char *ext)
+static int test(const char *path, bool alloc_name, bool kmod,
+		int comp, const char *name)
 {
 	struct kmod_path m;
 
 	memset(&m, 0x0, sizeof(m));
 
 	TEST_ASSERT_VAL("kmod_path__parse",
-			!__kmod_path__parse(&m, path, alloc_name, alloc_ext));
+			!__kmod_path__parse(&m, path, alloc_name));
 
-	pr_debug("%s - alloc name %d, alloc ext %d, kmod %d, comp %d, name '%s', ext '%s'\n",
-		 path, alloc_name, alloc_ext, m.kmod, m.comp, m.name, m.ext);
+	pr_debug("%s - alloc name %d, kmod %d, comp %d, name '%s'\n",
+		 path, alloc_name, m.kmod, m.comp, m.name);
 
 	TEST_ASSERT_VAL("wrong kmod", m.kmod == kmod);
 	TEST_ASSERT_VAL("wrong comp", m.comp == comp);
 
-	if (ext)
-		TEST_ASSERT_VAL("wrong ext", m.ext && !strcmp(ext, m.ext));
-	else
-		TEST_ASSERT_VAL("wrong ext", !m.ext);
-
 	if (name)
 		TEST_ASSERT_VAL("wrong name", m.name && !strcmp(name, m.name));
 	else
 		TEST_ASSERT_VAL("wrong name", !m.name);
 
 	free(m.name);
-	free(m.ext);
 	return 0;
 }
 
@@ -45,118 +39,118 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 	return 0;
 }
 
-#define T(path, an, ae, k, c, n, e) \
-	TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e))
+#define T(path, an, k, c, n) \
+	TEST_ASSERT_VAL("failed", !test(path, an, k, c, n))
 
 #define M(path, c, e) \
 	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
 int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
-	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
-	T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
-	T("/xxxx/xxxx/x-x.ko", false     , true      , true, false, NULL   , NULL);
-	T("/xxxx/xxxx/x-x.ko", true      , false     , true, false, "[x_x]", NULL);
-	T("/xxxx/xxxx/x-x.ko", false     , false     , true, false, NULL   , NULL);
+	/* path                alloc_name  kmod  comp   name   */
+	T("/xxxx/xxxx/x-x.ko", true      , true, 0    , "[x_x]");
+	T("/xxxx/xxxx/x-x.ko", false     , true, 0    , NULL   );
+	T("/xxxx/xxxx/x-x.ko", true      , true, 0    , "[x_x]");
+	T("/xxxx/xxxx/x-x.ko", false     , true, 0    , NULL   );
 	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
 	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true);
 	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false);
 
 #ifdef HAVE_ZLIB_SUPPORT
-	/* path                alloc_name  alloc_ext   kmod  comp  name   ext */
-	T("/xxxx/xxxx/x.ko.gz", true     , true      , true, true, "[x]", "gz");
-	T("/xxxx/xxxx/x.ko.gz", false    , true      , true, true, NULL , "gz");
-	T("/xxxx/xxxx/x.ko.gz", true     , false     , true, true, "[x]", NULL);
-	T("/xxxx/xxxx/x.ko.gz", false    , false     , true, true, NULL , NULL);
+	/* path                alloc_name   kmod  comp  name  */
+	T("/xxxx/xxxx/x.ko.gz", true     , true, 1   , "[x]");
+	T("/xxxx/xxxx/x.ko.gz", false    , true, 1   , NULL );
+	T("/xxxx/xxxx/x.ko.gz", true     , true, 1   , "[x]");
+	T("/xxxx/xxxx/x.ko.gz", false    , true, 1   , NULL );
 	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
 	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
 	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false);
 
-	/* path              alloc_name  alloc_ext  kmod   comp  name    ext */
-	T("/xxxx/xxxx/x.gz", true      , true     , false, true, "x.gz" ,"gz");
-	T("/xxxx/xxxx/x.gz", false     , true     , false, true, NULL   ,"gz");
-	T("/xxxx/xxxx/x.gz", true      , false    , false, true, "x.gz" , NULL);
-	T("/xxxx/xxxx/x.gz", false     , false    , false, true, NULL   , NULL);
+	/* path              alloc_name  kmod   comp  name  */
+	T("/xxxx/xxxx/x.gz", true      , false, 1   , "x.gz");
+	T("/xxxx/xxxx/x.gz", false     , false, 1   , NULL  );
+	T("/xxxx/xxxx/x.gz", true      , false, 1   , "x.gz");
+	T("/xxxx/xxxx/x.gz", false     , false, 1   , NULL  );
 	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false);
 	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false);
 
-	/* path   alloc_name  alloc_ext  kmod   comp  name     ext */
-	T("x.gz", true      , true     , false, true, "x.gz", "gz");
-	T("x.gz", false     , true     , false, true, NULL  , "gz");
-	T("x.gz", true      , false    , false, true, "x.gz", NULL);
-	T("x.gz", false     , false    , false, true, NULL  , NULL);
+	/* path   alloc_name  kmod   comp  name   */
+	T("x.gz", true      , false, 1   , "x.gz");
+	T("x.gz", false     , false, 1   , NULL  );
+	T("x.gz", true      , false, 1   , "x.gz");
+	T("x.gz", false     , false, 1   , NULL  );
 	M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("x.gz", PERF_RECORD_MISC_KERNEL, false);
 	M("x.gz", PERF_RECORD_MISC_USER, false);
 
-	/* path      alloc_name  alloc_ext  kmod  comp  name  ext */
-	T("x.ko.gz", true      , true     , true, true, "[x]", "gz");
-	T("x.ko.gz", false     , true     , true, true, NULL , "gz");
-	T("x.ko.gz", true      , false    , true, true, "[x]", NULL);
-	T("x.ko.gz", false     , false    , true, true, NULL , NULL);
+	/* path      alloc_name  kmod  comp  name  */
+	T("x.ko.gz", true      , true, 1   , "[x]");
+	T("x.ko.gz", false     , true, 1   , NULL );
+	T("x.ko.gz", true      , true, 1   , "[x]");
+	T("x.ko.gz", false     , true, 1   , NULL );
 	M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
 	M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
 	M("x.ko.gz", PERF_RECORD_MISC_USER, false);
 #endif
 
-	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
-	T("[test_module]", true      , true     , true, false, "[test_module]", NULL);
-	T("[test_module]", false     , true     , true, false, NULL           , NULL);
-	T("[test_module]", true      , false    , true, false, "[test_module]", NULL);
-	T("[test_module]", false     , false    , true, false, NULL           , NULL);
+	/* path            alloc_name  kmod  comp   name           */
+	T("[test_module]", true      , true, false, "[test_module]");
+	T("[test_module]", false     , true, false, NULL           );
+	T("[test_module]", true      , true, false, "[test_module]");
+	T("[test_module]", false     , true, false, NULL           );
 	M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
 	M("[test_module]", PERF_RECORD_MISC_KERNEL, true);
 	M("[test_module]", PERF_RECORD_MISC_USER, false);
 
-	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
-	T("[test.module]", true      , true     , true, false, "[test.module]", NULL);
-	T("[test.module]", false     , true     , true, false, NULL           , NULL);
-	T("[test.module]", true      , false    , true, false, "[test.module]", NULL);
-	T("[test.module]", false     , false    , true, false, NULL           , NULL);
+	/* path            alloc_name  kmod  comp   name           */
+	T("[test.module]", true      , true, false, "[test.module]");
+	T("[test.module]", false     , true, false, NULL           );
+	T("[test.module]", true      , true, false, "[test.module]");
+	T("[test.module]", false     , true, false, NULL           );
 	M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
 	M("[test.module]", PERF_RECORD_MISC_KERNEL, true);
 	M("[test.module]", PERF_RECORD_MISC_USER, false);
 
-	/* path     alloc_name  alloc_ext  kmod   comp   name      ext */
-	T("[vdso]", true      , true     , false, false, "[vdso]", NULL);
-	T("[vdso]", false     , true     , false, false, NULL    , NULL);
-	T("[vdso]", true      , false    , false, false, "[vdso]", NULL);
-	T("[vdso]", false     , false    , false, false, NULL    , NULL);
+	/* path     alloc_name  kmod   comp   name    */
+	T("[vdso]", true      , false, false, "[vdso]");
+	T("[vdso]", false     , false, false, NULL    );
+	T("[vdso]", true      , false, false, "[vdso]");
+	T("[vdso]", false     , false, false, NULL    );
 	M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("[vdso]", PERF_RECORD_MISC_KERNEL, false);
 	M("[vdso]", PERF_RECORD_MISC_USER, false);
 
-	T("[vdso32]", true      , true     , false, false, "[vdso32]", NULL);
-	T("[vdso32]", false     , true     , false, false, NULL    , NULL);
-	T("[vdso32]", true      , false    , false, false, "[vdso32]", NULL);
-	T("[vdso32]", false     , false    , false, false, NULL    , NULL);
+	T("[vdso32]", true      , false, false, "[vdso32]");
+	T("[vdso32]", false     , false, false, NULL      );
+	T("[vdso32]", true      , false, false, "[vdso32]");
+	T("[vdso32]", false     , false, false, NULL      );
 	M("[vdso32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("[vdso32]", PERF_RECORD_MISC_KERNEL, false);
 	M("[vdso32]", PERF_RECORD_MISC_USER, false);
 
-	T("[vdsox32]", true      , true     , false, false, "[vdsox32]", NULL);
-	T("[vdsox32]", false     , true     , false, false, NULL    , NULL);
-	T("[vdsox32]", true      , false    , false, false, "[vdsox32]", NULL);
-	T("[vdsox32]", false     , false    , false, false, NULL    , NULL);
+	T("[vdsox32]", true      , false, false, "[vdsox32]");
+	T("[vdsox32]", false     , false, false, NULL       );
+	T("[vdsox32]", true      , false, false, "[vdsox32]");
+	T("[vdsox32]", false     , false, false, NULL       );
 	M("[vdsox32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("[vdsox32]", PERF_RECORD_MISC_KERNEL, false);
 	M("[vdsox32]", PERF_RECORD_MISC_USER, false);
 
-	/* path         alloc_name  alloc_ext  kmod   comp   name          ext */
-	T("[vsyscall]", true      , true     , false, false, "[vsyscall]", NULL);
-	T("[vsyscall]", false     , true     , false, false, NULL        , NULL);
-	T("[vsyscall]", true      , false    , false, false, "[vsyscall]", NULL);
-	T("[vsyscall]", false     , false    , false, false, NULL        , NULL);
+	/* path         alloc_name  kmod   comp   name        */
+	T("[vsyscall]", true      , false, false, "[vsyscall]");
+	T("[vsyscall]", false     , false, false, NULL        );
+	T("[vsyscall]", true      , false, false, "[vsyscall]");
+	T("[vsyscall]", false     , false, false, NULL        );
 	M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false);
 	M("[vsyscall]", PERF_RECORD_MISC_USER, false);
 
-	/* path                alloc_name  alloc_ext  kmod   comp   name      ext */
-	T("[kernel.kallsyms]", true      , true     , false, false, "[kernel.kallsyms]", NULL);
-	T("[kernel.kallsyms]", false     , true     , false, false, NULL               , NULL);
-	T("[kernel.kallsyms]", true      , false    , false, false, "[kernel.kallsyms]", NULL);
-	T("[kernel.kallsyms]", false     , false    , false, false, NULL               , NULL);
+	/* path                alloc_name  kmod   comp   name      */
+	T("[kernel.kallsyms]", true      , false, false, "[kernel.kallsyms]");
+	T("[kernel.kallsyms]", false     , false, false, NULL               );
+	T("[kernel.kallsyms]", true      , false, false, "[kernel.kallsyms]");
+	T("[kernel.kallsyms]", false     , false, false, NULL               );
 	M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
 	M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false);
 	M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false);
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index 0c3c87f86e03..9e9e4d37cc77 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -24,8 +24,6 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 	bm = bitmap_alloc(nbits);
 
 	if (map && bm) {
-		bitmap_zero(bm, nbits);
-
 		for (i = 0; i < map->nr; i++) {
 			set_bit(map->map[i], bm);
 		}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1317,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1375,6 +1388,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,9 +1662,15 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
+	{
+		.name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+		.check = test__checkevent_complex_name,
+		.id    = 53
+	}
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1669,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
 		.check = test__checkevent_pmu_partial_time_callgraph,
 		.id    = 2,
 	},
+	{
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+		.check = test__checkevent_complex_name,
+		.id    = 3,
+	}
 };
 
 struct terms_test {
@@ -1686,17 +1711,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1746,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1832,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,36 +13,60 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
-			exit 1
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
+			return 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -51,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
 	# even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
-perf probe -q -d probe_libc:inet_pton
+rm -f ${perf_data} ${perf_script} ${expected}
+delete_libc_inet_pton_event
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 3b4f1c10ff57..1d00e5ec7906 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <sys/ttydefaults.h>
+#include <asm/bug.h>
 
 struct disasm_line_samples {
 	double		      percent;
@@ -115,7 +116,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	if (!browser->navkeypressed)
 		ops.width += 1;
 
-	annotation_line__write(al, notes, &ops);
+	annotation_line__write(al, notes, &ops, ab->opts);
 
 	if (ops.current_entry)
 		ab->selection = al;
@@ -227,10 +228,10 @@ static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
 {
 	int i;
 
-	for (i = 0; i < a->samples_nr; i++) {
-		if (a->samples[i].percent == b->samples[i].percent)
+	for (i = 0; i < a->data_nr; i++) {
+		if (a->data[i].percent == b->data[i].percent)
 			continue;
-		return a->samples[i].percent < b->samples[i].percent;
+		return a->data[i].percent < b->data[i].percent;
 	}
 	return 0;
 }
@@ -314,11 +315,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 			continue;
 		}
 
-		for (i = 0; i < pos->al.samples_nr; i++) {
-			struct annotation_data *sample = &pos->al.samples[i];
+		for (i = 0; i < pos->al.data_nr; i++) {
+			double percent;
 
-			if (max_percent < sample->percent)
-				max_percent = sample->percent;
+			percent = annotation_data__percent(&pos->al.data[i],
+							   browser->opts->percent_type);
+
+			if (max_percent < percent)
+				max_percent = percent;
 		}
 
 		if (max_percent < 0.01 && pos->al.ipc == 0) {
@@ -380,9 +384,10 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser)
 #define SYM_TITLE_MAX_SIZE (PATH_MAX + 64)
 
 static int sym_title(struct symbol *sym, struct map *map, char *title,
-		     size_t sz)
+		     size_t sz, int percent_type)
 {
-	return snprintf(title, sz, "%s  %s", sym->name, map->dso->long_name);
+	return snprintf(title, sz, "%s  %s [Percent: %s]", sym->name, map->dso->long_name,
+			percent_type_str(percent_type));
 }
 
 /*
@@ -420,7 +425,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 
 	pthread_mutex_unlock(&notes->lock);
 	symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt, browser->opts);
-	sym_title(ms->sym, ms->map, title, sizeof(title));
+	sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type);
 	ui_browser__show_title(&browser->b, title);
 	return true;
 }
@@ -595,6 +600,7 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
 
 static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help)
 {
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	struct map_symbol *ms = browser->priv;
 	struct symbol *sym = ms->sym;
 	char symbol_dso[SYM_TITLE_MAX_SIZE];
@@ -602,7 +608,7 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const
 	if (ui_browser__show(browser, title, help) < 0)
 		return -1;
 
-	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso));
+	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type);
 
 	ui_browser__gotorc_title(browser, 0, 0);
 	ui_browser__set_color(browser, HE_COLORSET_ROOT);
@@ -610,6 +616,39 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const
 	return 0;
 }
 
+static void
+switch_percent_type(struct annotation_options *opts, bool base)
+{
+	switch (opts->percent_type) {
+	case PERCENT_HITS_LOCAL:
+		if (base)
+			opts->percent_type = PERCENT_PERIOD_LOCAL;
+		else
+			opts->percent_type = PERCENT_HITS_GLOBAL;
+		break;
+	case PERCENT_HITS_GLOBAL:
+		if (base)
+			opts->percent_type = PERCENT_PERIOD_GLOBAL;
+		else
+			opts->percent_type = PERCENT_HITS_LOCAL;
+		break;
+	case PERCENT_PERIOD_LOCAL:
+		if (base)
+			opts->percent_type = PERCENT_HITS_LOCAL;
+		else
+			opts->percent_type = PERCENT_PERIOD_GLOBAL;
+		break;
+	case PERCENT_PERIOD_GLOBAL:
+		if (base)
+			opts->percent_type = PERCENT_HITS_GLOBAL;
+		else
+			opts->percent_type = PERCENT_PERIOD_LOCAL;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
 static int annotate_browser__run(struct annotate_browser *browser,
 				 struct perf_evsel *evsel,
 				 struct hist_browser_timer *hbt)
@@ -624,8 +663,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 	char title[256];
 	int key;
 
-	annotation__scnprintf_samples_period(notes, title, sizeof(title), evsel);
-
+	hists__scnprintf_title(hists, title, sizeof(title));
 	if (annotate_browser__show(&browser->b, title, help) < 0)
 		return -1;
 
@@ -701,6 +739,8 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"k             Toggle line numbers\n"
 		"P             Print to [symbol_name].annotation file.\n"
 		"r             Run available scripts\n"
+		"p             Toggle percent type [local/global]\n"
+		"b             Toggle percent base [period/hits]\n"
 		"?             Search string backwards\n");
 			continue;
 		case 'r':
@@ -781,7 +821,7 @@ show_sup_ins:
 			continue;
 		}
 		case 'P':
-			map_symbol__annotation_dump(ms, evsel);
+			map_symbol__annotation_dump(ms, evsel, browser->opts);
 			continue;
 		case 't':
 			if (notes->options->show_total_period) {
@@ -800,6 +840,12 @@ show_sup_ins:
 				notes->options->show_minmax_cycle = true;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'p':
+		case 'b':
+			switch_percent_type(browser->opts, key == 'b');
+			hists__scnprintf_title(hists, title, sizeof(title));
+			annotate_browser__show(&browser->b, title, help);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
-			       bool use_callchain)
+			       bool ignore_callchains)
 {
 	int ret;
 	int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (hist_entry__has_callchains(he) && use_callchain)
+	if (hist_entry__has_callchains(he) && !ignore_callchains)
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain)
+		      bool ignore_callchains)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index b604ef334dc9..7efe15b9618d 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -87,6 +87,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-$(CONFIG_AUXTRACE) += arm-spe.o
 libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
 
 ifdef CONFIG_LIBOPENCSD
 libperf-$(CONFIG_AUXTRACE) += cs-etm.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index f91775b4bc3c..28cd6a17491b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -49,6 +49,7 @@ struct annotation_options annotation__default_options = {
 	.jump_arrows    = true,
 	.annotate_src	= true,
 	.offset_level	= ANNOTATION__OFFSET_JUMP_TARGETS,
+	.percent_type	= PERCENT_PERIOD_LOCAL,
 };
 
 static regex_t	 file_lineno;
@@ -245,8 +246,14 @@ find_target:
 
 indirect_call:
 	tok = strchr(endptr, '*');
-	if (tok != NULL)
-		ops->target.addr = strtoull(tok + 1, NULL, 16);
+	if (tok != NULL) {
+		endptr++;
+
+		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
+		 * Do not parse such instruction.  */
+		if (strstr(endptr, "(%r") == NULL)
+			ops->target.addr = strtoull(endptr, NULL, 16);
+	}
 	goto find_target;
 }
 
@@ -275,7 +282,19 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops || ins->ops == &s390_call_ops;
 }
 
-static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms)
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+	if (ops->raw_comment && c > ops->raw_comment)
+		return NULL;
+
+	return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -284,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	};
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
+
+	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	c = validate_comma(c, ops);
+
 	/*
 	 * Examples of lines to parse for the _cpp_lex_token@@Base
 	 * function:
@@ -303,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 		ops->target.addr = strtoull(c, NULL, 16);
 		if (!ops->target.addr) {
 			c = strchr(c, ',');
+			c = validate_comma(c, ops);
 			if (c++ != NULL)
 				ops->target.addr = strtoull(c, NULL, 16);
 		}
@@ -360,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
 
 	c = strchr(ops->raw, ',');
+	c = validate_comma(c, ops);
+
 	if (c != NULL) {
 		const char *c2 = strchr(c + 1, ',');
 
+		c2 = validate_comma(c2, ops);
 		/* check for 3-op insn */
 		if (c2 != NULL)
 			c = c2;
@@ -1108,7 +1135,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize)
 	if (perf_evsel__is_group_event(evsel))
 		nr = evsel->nr_members;
 
-	size += sizeof(al->samples[0]) * nr;
+	size += sizeof(al->data[0]) * nr;
 
 	al = zalloc(size);
 	if (al) {
@@ -1117,7 +1144,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize)
 		al->offset     = args->offset;
 		al->line       = strdup(args->line);
 		al->line_nr    = args->line_nr;
-		al->samples_nr = nr;
+		al->data_nr    = nr;
 	}
 
 	return al;
@@ -1297,7 +1324,8 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi
 static int
 annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start,
 		       struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
-		       int max_lines, struct annotation_line *queue, int addr_fmt_width)
+		       int max_lines, struct annotation_line *queue, int addr_fmt_width,
+		       int percent_type)
 {
 	struct disasm_line *dl = container_of(al, struct disasm_line, al);
 	static const char *prev_line;
@@ -1309,15 +1337,18 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
 
-		for (i = 0; i < al->samples_nr; i++) {
-			struct annotation_data *sample = &al->samples[i];
+		for (i = 0; i < al->data_nr; i++) {
+			double percent;
 
-			if (sample->percent > max_percent)
-				max_percent = sample->percent;
+			percent = annotation_data__percent(&al->data[i],
+							   percent_type);
+
+			if (percent > max_percent)
+				max_percent = percent;
 		}
 
-		if (al->samples_nr > nr_percent)
-			nr_percent = al->samples_nr;
+		if (al->data_nr > nr_percent)
+			nr_percent = al->data_nr;
 
 		if (max_percent < min_pcnt)
 			return -1;
@@ -1330,7 +1361,8 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 				if (queue == al)
 					break;
 				annotation_line__print(queue, sym, start, evsel, len,
-						       0, 0, 1, NULL, addr_fmt_width);
+						       0, 0, 1, NULL, addr_fmt_width,
+						       percent_type);
 			}
 		}
 
@@ -1351,18 +1383,20 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 		}
 
 		for (i = 0; i < nr_percent; i++) {
-			struct annotation_data *sample = &al->samples[i];
+			struct annotation_data *data = &al->data[i];
+			double percent;
 
-			color = get_percent_color(sample->percent);
+			percent = annotation_data__percent(data, percent_type);
+			color = get_percent_color(percent);
 
 			if (symbol_conf.show_total_period)
 				color_fprintf(stdout, color, " %11" PRIu64,
-					      sample->he.period);
+					      data->he.period);
 			else if (symbol_conf.show_nr_samples)
 				color_fprintf(stdout, color, " %7" PRIu64,
-					      sample->he.nr_samples);
+					      data->he.nr_samples);
 			else
-				color_fprintf(stdout, color, " %7.2f", sample->percent);
+				color_fprintf(stdout, color, " %7.2f", percent);
 		}
 
 		printf(" : ");
@@ -1621,6 +1655,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	char symfs_filename[PATH_MAX];
 	struct kcore_extract kce;
 	bool delete_extract = false;
+	bool decomp = false;
 	int stdout_fd[2];
 	int lineno = 0;
 	int nline;
@@ -1654,6 +1689,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 						 tmp, sizeof(tmp)) < 0)
 			goto out;
 
+		decomp = true;
 		strcpy(symfs_filename, tmp);
 	}
 
@@ -1740,7 +1776,7 @@ out_free_command:
 out_remove_tmp:
 	close(stdout_fd[0]);
 
-	if (dso__needs_decompress(dso))
+	if (decomp)
 		unlink(symfs_filename);
 
 	if (delete_extract)
@@ -1753,34 +1789,45 @@ out_close_stdout:
 	goto out_free_command;
 }
 
-static void calc_percent(struct sym_hist *hist,
-			 struct annotation_data *sample,
+static void calc_percent(struct sym_hist *sym_hist,
+			 struct hists *hists,
+			 struct annotation_data *data,
 			 s64 offset, s64 end)
 {
 	unsigned int hits = 0;
 	u64 period = 0;
 
 	while (offset < end) {
-		hits   += hist->addr[offset].nr_samples;
-		period += hist->addr[offset].period;
+		hits   += sym_hist->addr[offset].nr_samples;
+		period += sym_hist->addr[offset].period;
 		++offset;
 	}
 
-	if (hist->nr_samples) {
-		sample->he.period     = period;
-		sample->he.nr_samples = hits;
-		sample->percent = 100.0 * hits / hist->nr_samples;
+	if (sym_hist->nr_samples) {
+		data->he.period     = period;
+		data->he.nr_samples = hits;
+		data->percent[PERCENT_HITS_LOCAL] = 100.0 * hits / sym_hist->nr_samples;
 	}
+
+	if (hists->stats.nr_non_filtered_samples)
+		data->percent[PERCENT_HITS_GLOBAL] = 100.0 * hits / hists->stats.nr_non_filtered_samples;
+
+	if (sym_hist->period)
+		data->percent[PERCENT_PERIOD_LOCAL] = 100.0 * period / sym_hist->period;
+
+	if (hists->stats.total_period)
+		data->percent[PERCENT_PERIOD_GLOBAL] = 100.0 * period / hists->stats.total_period;
 }
 
 static void annotation__calc_percent(struct annotation *notes,
-				     struct perf_evsel *evsel, s64 len)
+				     struct perf_evsel *leader, s64 len)
 {
 	struct annotation_line *al, *next;
+	struct perf_evsel *evsel;
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		s64 end;
-		int i;
+		int i = 0;
 
 		if (al->offset == -1)
 			continue;
@@ -1788,14 +1835,17 @@ static void annotation__calc_percent(struct annotation *notes,
 		next = annotation_line__next(al, &notes->src->source);
 		end  = next ? next->offset : len;
 
-		for (i = 0; i < al->samples_nr; i++) {
-			struct annotation_data *sample;
-			struct sym_hist *hist;
+		for_each_group_evsel(evsel, leader) {
+			struct hists *hists = evsel__hists(evsel);
+			struct annotation_data *data;
+			struct sym_hist *sym_hist;
 
-			hist   = annotation__histogram(notes, evsel->idx + i);
-			sample = &al->samples[i];
+			BUG_ON(i >= al->data_nr);
 
-			calc_percent(hist, sample, al->offset, end);
+			sym_hist = annotation__histogram(notes, evsel->idx);
+			data = &al->data[i++];
+
+			calc_percent(sym_hist, hists, data, al->offset, end);
 		}
 	}
 }
@@ -1846,7 +1896,8 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 	return symbol__disassemble(sym, &args);
 }
 
-static void insert_source_line(struct rb_root *root, struct annotation_line *al)
+static void insert_source_line(struct rb_root *root, struct annotation_line *al,
+			       struct annotation_options *opts)
 {
 	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
@@ -1859,8 +1910,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 
 		ret = strcmp(iter->path, al->path);
 		if (ret == 0) {
-			for (i = 0; i < al->samples_nr; i++)
-				iter->samples[i].percent_sum += al->samples[i].percent;
+			for (i = 0; i < al->data_nr; i++) {
+				iter->data[i].percent_sum += annotation_data__percent(&al->data[i],
+										      opts->percent_type);
+			}
 			return;
 		}
 
@@ -1870,8 +1923,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 			p = &(*p)->rb_right;
 	}
 
-	for (i = 0; i < al->samples_nr; i++)
-		al->samples[i].percent_sum = al->samples[i].percent;
+	for (i = 0; i < al->data_nr; i++) {
+		al->data[i].percent_sum = annotation_data__percent(&al->data[i],
+								   opts->percent_type);
+	}
 
 	rb_link_node(&al->rb_node, parent, p);
 	rb_insert_color(&al->rb_node, root);
@@ -1881,10 +1936,10 @@ static int cmp_source_line(struct annotation_line *a, struct annotation_line *b)
 {
 	int i;
 
-	for (i = 0; i < a->samples_nr; i++) {
-		if (a->samples[i].percent_sum == b->samples[i].percent_sum)
+	for (i = 0; i < a->data_nr; i++) {
+		if (a->data[i].percent_sum == b->data[i].percent_sum)
 			continue;
-		return a->samples[i].percent_sum > b->samples[i].percent_sum;
+		return a->data[i].percent_sum > b->data[i].percent_sum;
 	}
 
 	return 0;
@@ -1949,8 +2004,8 @@ static void print_summary(struct rb_root *root, const char *filename)
 		int i;
 
 		al = rb_entry(node, struct annotation_line, rb_node);
-		for (i = 0; i < al->samples_nr; i++) {
-			percent = al->samples[i].percent_sum;
+		for (i = 0; i < al->data_nr; i++) {
+			percent = al->data[i].percent_sum;
 			color = get_percent_color(percent);
 			color_fprintf(stdout, color, " %7.2f", percent);
 
@@ -2029,10 +2084,12 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 		evsel_name = buf;
 	}
 
-	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
+	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples, "
+				  "percent: %s)\n",
 				  width, width, symbol_conf.show_total_period ? "Period" :
 				  symbol_conf.show_nr_samples ? "Samples" : "Percent",
-				  d_filename, evsel_name, h->nr_samples);
+				  d_filename, evsel_name, h->nr_samples,
+				  percent_type_str(opts->percent_type));
 
 	printf("%-*.*s----\n",
 	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
@@ -2052,7 +2109,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 		err = annotation_line__print(pos, sym, start, evsel, len,
 					     opts->min_pcnt, printed, opts->max_lines,
-					     queue, addr_fmt_width);
+					     queue, addr_fmt_width, opts->percent_type);
 
 		switch (err) {
 		case 0:
@@ -2129,10 +2186,11 @@ static void FILE__write_graph(void *fp, int graph)
 	fputs(s, fp);
 }
 
-int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
+static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
+				     struct annotation_options *opts)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct annotation_write_ops ops = {
+	struct annotation_write_ops wops = {
 		.first_line		 = true,
 		.obj			 = fp,
 		.set_color		 = FILE__set_color,
@@ -2146,15 +2204,16 @@ int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
 	list_for_each_entry(al, &notes->src->source, node) {
 		if (annotation_line__filter(al, notes))
 			continue;
-		annotation_line__write(al, notes, &ops);
+		annotation_line__write(al, notes, &wops, opts);
 		fputc('\n', fp);
-		ops.first_line = false;
+		wops.first_line = false;
 	}
 
 	return 0;
 }
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel)
+int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel,
+				struct annotation_options *opts)
 {
 	const char *ev_name = perf_evsel__name(evsel);
 	char buf[1024];
@@ -2176,7 +2235,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel)
 
 	fprintf(fp, "%s() %s\nEvent: %s\n\n",
 		ms->sym->name, ms->map->dso->long_name, ev_name);
-	symbol__annotate_fprintf2(ms->sym, fp);
+	symbol__annotate_fprintf2(ms->sym, fp, opts);
 
 	fclose(fp);
 	err = 0;
@@ -2346,7 +2405,8 @@ void annotation__update_column_widths(struct annotation *notes)
 }
 
 static void annotation__calc_lines(struct annotation *notes, struct map *map,
-				  struct rb_root *root)
+				   struct rb_root *root,
+				   struct annotation_options *opts)
 {
 	struct annotation_line *al;
 	struct rb_root tmp_root = RB_ROOT;
@@ -2355,13 +2415,14 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 		double percent_max = 0.0;
 		int i;
 
-		for (i = 0; i < al->samples_nr; i++) {
-			struct annotation_data *sample;
+		for (i = 0; i < al->data_nr; i++) {
+			double percent;
 
-			sample = &al->samples[i];
+			percent = annotation_data__percent(&al->data[i],
+							   opts->percent_type);
 
-			if (sample->percent > percent_max)
-				percent_max = sample->percent;
+			if (percent > percent_max)
+				percent_max = percent;
 		}
 
 		if (percent_max <= 0.5)
@@ -2369,18 +2430,19 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 		al->path = get_srcline(map->dso, notes->start + al->offset, NULL,
 				       false, true, notes->start + al->offset);
-		insert_source_line(&tmp_root, al);
+		insert_source_line(&tmp_root, al, opts);
 	}
 
 	resort_source_line(root, &tmp_root);
 }
 
 static void symbol__calc_lines(struct symbol *sym, struct map *map,
-			      struct rb_root *root)
+			       struct rb_root *root,
+			       struct annotation_options *opts)
 {
 	struct annotation *notes = symbol__annotation(sym);
 
-	annotation__calc_lines(notes, map, root);
+	annotation__calc_lines(notes, map, root, opts);
 }
 
 int symbol__tty_annotate2(struct symbol *sym, struct map *map,
@@ -2389,7 +2451,7 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map,
 {
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
-	struct annotation *notes = symbol__annotation(sym);
+	struct hists *hists = evsel__hists(evsel);
 	char buf[1024];
 
 	if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0)
@@ -2397,13 +2459,14 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map,
 
 	if (opts->print_lines) {
 		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(sym, map, &source_line);
+		symbol__calc_lines(sym, map, &source_line, opts);
 		print_summary(&source_line, dso->long_name);
 	}
 
-	annotation__scnprintf_samples_period(notes, buf, sizeof(buf), evsel);
-	fprintf(stdout, "%s\n%s() %s\n", buf, sym->name, dso->long_name);
-	symbol__annotate_fprintf2(sym, stdout);
+	hists__scnprintf_title(hists, buf, sizeof(buf));
+	fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
+		buf, percent_type_str(opts->percent_type), sym->name, dso->long_name);
+	symbol__annotate_fprintf2(sym, stdout, opts);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
@@ -2424,7 +2487,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 
 	if (opts->print_lines) {
 		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(sym, map, &source_line);
+		symbol__calc_lines(sym, map, &source_line, opts);
 		print_summary(&source_line, dso->long_name);
 	}
 
@@ -2441,14 +2504,21 @@ bool ui__has_annotation(void)
 }
 
 
-double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes)
+static double annotation_line__max_percent(struct annotation_line *al,
+					   struct annotation *notes,
+					   unsigned int percent_type)
 {
 	double percent_max = 0.0;
 	int i;
 
 	for (i = 0; i < notes->nr_events; i++) {
-		if (al->samples[i].percent > percent_max)
-			percent_max = al->samples[i].percent;
+		double percent;
+
+		percent = annotation_data__percent(&al->data[i],
+						   percent_type);
+
+		if (percent > percent_max)
+			percent_max = percent;
 	}
 
 	return percent_max;
@@ -2487,7 +2557,7 @@ call_like:
 
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
 				     bool first_line, bool current_entry, bool change_color, int width,
-				     void *obj,
+				     void *obj, unsigned int percent_type,
 				     int  (*obj__set_color)(void *obj, int color),
 				     void (*obj__set_percent_color)(void *obj, double percent, bool current),
 				     int  (*obj__set_jumps_percent_color)(void *obj, int nr, bool current),
@@ -2495,7 +2565,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				     void (*obj__write_graph)(void *obj, int graph))
 
 {
-	double percent_max = annotation_line__max_percent(al, notes);
+	double percent_max = annotation_line__max_percent(al, notes, percent_type);
 	int pcnt_width = annotation__pcnt_width(notes),
 	    cycles_width = annotation__cycles_width(notes);
 	bool show_title = false;
@@ -2514,15 +2584,18 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		int i;
 
 		for (i = 0; i < notes->nr_events; i++) {
-			obj__set_percent_color(obj, al->samples[i].percent, current_entry);
+			double percent;
+
+			percent = annotation_data__percent(&al->data[i], percent_type);
+
+			obj__set_percent_color(obj, percent, current_entry);
 			if (notes->options->show_total_period) {
-				obj__printf(obj, "%11" PRIu64 " ", al->samples[i].he.period);
+				obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
 			} else if (notes->options->show_nr_samples) {
 				obj__printf(obj, "%6" PRIu64 " ",
-						   al->samples[i].he.nr_samples);
+						   al->data[i].he.nr_samples);
 			} else {
-				obj__printf(obj, "%6.2f ",
-						   al->samples[i].percent);
+				obj__printf(obj, "%6.2f ", percent);
 			}
 		}
 	} else {
@@ -2640,13 +2713,15 @@ print_addr:
 }
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *ops)
+			    struct annotation_write_ops *wops,
+			    struct annotation_options *opts)
 {
-	__annotation_line__write(al, notes, ops->first_line, ops->current_entry,
-				 ops->change_color, ops->width, ops->obj,
-				 ops->set_color, ops->set_percent_color,
-				 ops->set_jumps_percent_color, ops->printf,
-				 ops->write_graph);
+	__annotation_line__write(al, notes, wops->first_line, wops->current_entry,
+				 wops->change_color, wops->width, wops->obj,
+				 opts->percent_type,
+				 wops->set_color, wops->set_percent_color,
+				 wops->set_jumps_percent_color, wops->printf,
+				 wops->write_graph);
 }
 
 int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel,
@@ -2688,46 +2763,6 @@ out_free_offsets:
 	return -1;
 }
 
-int __annotation__scnprintf_samples_period(struct annotation *notes,
-					   char *bf, size_t size,
-					   struct perf_evsel *evsel,
-					   bool show_freq)
-{
-	const char *ev_name = perf_evsel__name(evsel);
-	char buf[1024], ref[30] = " show reference callgraph, ";
-	char sample_freq_str[64] = "";
-	unsigned long nr_samples = 0;
-	int nr_members = 1;
-	bool enable_ref = false;
-	u64 nr_events = 0;
-	char unit;
-	int i;
-
-	if (perf_evsel__is_group_event(evsel)) {
-		perf_evsel__group_desc(evsel, buf, sizeof(buf));
-		ev_name = buf;
-                nr_members = evsel->nr_members;
-	}
-
-	for (i = 0; i < nr_members; i++) {
-		struct sym_hist *ah = annotation__histogram(notes, evsel->idx + i);
-
-		nr_samples += ah->nr_samples;
-		nr_events  += ah->period;
-	}
-
-	if (symbol_conf.show_ref_callgraph && strstr(ev_name, "call-graph=no"))
-		enable_ref = true;
-
-	if (show_freq)
-		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq);
-
-	nr_samples = convert_unit(nr_samples, &unit);
-	return scnprintf(bf, size, "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
-			 nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
-			 ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
-}
-
 #define ANNOTATION__CFG(n) \
 	{ .name = #n, .value = &annotation__default_options.n, }
 
@@ -2792,3 +2827,55 @@ void annotation_config__init(void)
 	annotation__default_options.show_total_period = symbol_conf.show_total_period;
 	annotation__default_options.show_nr_samples   = symbol_conf.show_nr_samples;
 }
+
+static unsigned int parse_percent_type(char *str1, char *str2)
+{
+	unsigned int type = (unsigned int) -1;
+
+	if (!strcmp("period", str1)) {
+		if (!strcmp("local", str2))
+			type = PERCENT_PERIOD_LOCAL;
+		else if (!strcmp("global", str2))
+			type = PERCENT_PERIOD_GLOBAL;
+	}
+
+	if (!strcmp("hits", str1)) {
+		if (!strcmp("local", str2))
+			type = PERCENT_HITS_LOCAL;
+		else if (!strcmp("global", str2))
+			type = PERCENT_HITS_GLOBAL;
+	}
+
+	return type;
+}
+
+int annotate_parse_percent_type(const struct option *opt, const char *_str,
+				int unset __maybe_unused)
+{
+	struct annotation_options *opts = opt->value;
+	unsigned int type;
+	char *str1, *str2;
+	int err = -1;
+
+	str1 = strdup(_str);
+	if (!str1)
+		return -ENOMEM;
+
+	str2 = strchr(str1, '-');
+	if (!str2)
+		goto out;
+
+	*str2++ = 0;
+
+	type = parse_percent_type(str1, str2);
+	if (type == (unsigned int) -1)
+		type = parse_percent_type(str2, str1);
+	if (type != (unsigned int) -1) {
+		opts->percent_type = type;
+		err = 0;
+	}
+
+out:
+	free(str1);
+	return err;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index a4c0d91907e6..5399ba2321bb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <pthread.h>
+#include <asm/bug.h>
 
 struct ins_ops;
 
@@ -21,6 +22,7 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
+	char	*raw_comment;
 	struct {
 		char	*raw;
 		char	*name;
@@ -82,6 +84,7 @@ struct annotation_options {
 	int  context;
 	const char *objdump_path;
 	const char *disassembler_style;
+	unsigned int percent_type;
 };
 
 enum {
@@ -101,8 +104,16 @@ struct sym_hist_entry {
 	u64		period;
 };
 
+enum {
+	PERCENT_HITS_LOCAL,
+	PERCENT_HITS_GLOBAL,
+	PERCENT_PERIOD_LOCAL,
+	PERCENT_PERIOD_GLOBAL,
+	PERCENT_MAX,
+};
+
 struct annotation_data {
-	double			 percent;
+	double			 percent[PERCENT_MAX];
 	double			 percent_sum;
 	struct sym_hist_entry	 he;
 };
@@ -122,8 +133,8 @@ struct annotation_line {
 	char			*path;
 	u32			 idx;
 	int			 idx_asm;
-	int			 samples_nr;
-	struct annotation_data	 samples[0];
+	int			 data_nr;
+	struct annotation_data	 data[0];
 };
 
 struct disasm_line {
@@ -134,6 +145,27 @@ struct disasm_line {
 	struct annotation_line	 al;
 };
 
+static inline double annotation_data__percent(struct annotation_data *data,
+					      unsigned int which)
+{
+	return which < PERCENT_MAX ? data->percent[which] : -1;
+}
+
+static inline const char *percent_type_str(unsigned int type)
+{
+	static const char *str[PERCENT_MAX] = {
+		"local hits",
+		"global hits",
+		"local period",
+		"global period",
+	};
+
+	if (WARN_ON(type >= PERCENT_MAX))
+		return "N/A";
+
+	return str[type];
+}
+
 static inline struct disasm_line *disasm_line(struct annotation_line *al)
 {
 	return al ? container_of(al, struct disasm_line, al) : NULL;
@@ -169,22 +201,15 @@ struct annotation_write_ops {
 	void (*write_graph)(void *obj, int graph);
 };
 
-double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes);
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *ops);
+			    struct annotation_write_ops *ops,
+			    struct annotation_options *opts);
 
 int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   char *bf, size_t size,
 					   struct perf_evsel *evsel,
 					   bool show_freq);
 
-static inline int annotation__scnprintf_samples_period(struct annotation *notes,
-						       char *bf, size_t size,
-						       struct perf_evsel *evsel)
-{
-	return __annotation__scnprintf_samples_period(notes, bf, size, evsel, true);
-}
-
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
@@ -340,12 +365,12 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel,
 			    struct annotation_options *options);
-int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel);
+int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel,
+				struct annotation_options *opts);
 
 bool ui__has_annotation(void);
 
@@ -373,4 +398,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
 
 void annotation_config__init(void);
 
+int annotate_parse_percent_type(const struct option *opt, const char *_str,
+				int unset);
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index d056447520a2..db1511359c5e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -56,6 +56,7 @@
 #include "intel-pt.h"
 #include "intel-bts.h"
 #include "arm-spe.h"
+#include "s390-cpumsf.h"
 
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
@@ -202,6 +203,9 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues,
 	for (i = 0; i < queues->nr_queues; i++) {
 		list_splice_tail(&queues->queue_array[i].head,
 				 &queue_array[i].head);
+		queue_array[i].tid = queues->queue_array[i].tid;
+		queue_array[i].cpu = queues->queue_array[i].cpu;
+		queue_array[i].set = queues->queue_array[i].set;
 		queue_array[i].priv = queues->queue_array[i].priv;
 	}
 
@@ -920,6 +924,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 		return arm_spe_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_CS_ETM:
 		return cs_etm__process_auxtrace_info(event, session);
+	case PERF_AUXTRACE_S390_CPUMSF:
+		return s390_cpumsf_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index e731f55da072..71fc3bd74299 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -44,6 +44,7 @@ enum auxtrace_type {
 	PERF_AUXTRACE_INTEL_BTS,
 	PERF_AUXTRACE_CS_ETM,
 	PERF_AUXTRACE_ARM_SPE,
+	PERF_AUXTRACE_S390_CPUMSF,
 };
 
 enum itrace_period_type {
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..47aac41349a2 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
@@ -1527,13 +1529,13 @@ int bpf__apply_obj_config(void)
 	bpf_object__for_each_safe(obj, objtmp)	\
 		bpf_map__for_each(pos, obj)
 
-#define bpf__for_each_stdout_map(pos, obj, objtmp)	\
+#define bpf__for_each_map_named(pos, obj, objtmp, name)	\
 	bpf__for_each_map(pos, obj, objtmp) 		\
 		if (bpf_map__name(pos) && 		\
-			(strcmp("__bpf_stdout__", 	\
+			(strcmp(name, 			\
 				bpf_map__name(pos)) == 0))
 
-int bpf__setup_stdout(struct perf_evlist *evlist)
+struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
 	struct bpf_object *obj, *tmp;
@@ -1542,11 +1544,11 @@ int bpf__setup_stdout(struct perf_evlist *evlist)
 	int err;
 	bool need_init = false;
 
-	bpf__for_each_stdout_map(map, obj, tmp) {
+	bpf__for_each_map_named(map, obj, tmp, name) {
 		struct bpf_map_priv *priv = bpf_map__priv(map);
 
 		if (IS_ERR(priv))
-			return -BPF_LOADER_ERRNO__INTERNAL;
+			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
 
 		/*
 		 * No need to check map type: type should have been
@@ -1559,49 +1561,61 @@ int bpf__setup_stdout(struct perf_evlist *evlist)
 	}
 
 	if (!need_init)
-		return 0;
+		return NULL;
 
 	if (!tmpl_priv) {
-		err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/",
-				   NULL);
+		char *event_definition = NULL;
+
+		if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0)
+			return ERR_PTR(-ENOMEM);
+
+		err = parse_events(evlist, event_definition, NULL);
+		free(event_definition);
+
 		if (err) {
-			pr_debug("ERROR: failed to create bpf-output event\n");
-			return -err;
+			pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name);
+			return ERR_PTR(-err);
 		}
 
 		evsel = perf_evlist__last(evlist);
 	}
 
-	bpf__for_each_stdout_map(map, obj, tmp) {
+	bpf__for_each_map_named(map, obj, tmp, name) {
 		struct bpf_map_priv *priv = bpf_map__priv(map);
 
 		if (IS_ERR(priv))
-			return -BPF_LOADER_ERRNO__INTERNAL;
+			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
 		if (priv)
 			continue;
 
 		if (tmpl_priv) {
 			priv = bpf_map_priv__clone(tmpl_priv);
 			if (!priv)
-				return -ENOMEM;
+				return ERR_PTR(-ENOMEM);
 
 			err = bpf_map__set_priv(map, priv, bpf_map_priv__clear);
 			if (err) {
 				bpf_map_priv__clear(map, priv);
-				return err;
+				return ERR_PTR(err);
 			}
 		} else if (evsel) {
 			struct bpf_map_op *op;
 
 			op = bpf_map__add_newop(map, NULL);
 			if (IS_ERR(op))
-				return PTR_ERR(op);
+				return ERR_PTR(PTR_ERR(op));
 			op->op_type = BPF_MAP_OP_SET_EVSEL;
 			op->v.evsel = evsel;
 		}
 	}
 
-	return 0;
+	return evsel;
+}
+
+int bpf__setup_stdout(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
+	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
@@ -1778,8 +1792,8 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
 	return 0;
 }
 
-int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused,
-			       int err, char *buf, size_t size)
+int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused,
+				     int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
 	bpf__strerror_end(buf, size);
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 5d3aefd6fae7..62d245a90e1d 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -43,6 +43,7 @@ enum bpf_loader_errno {
 	__BPF_LOADER_ERRNO__END,
 };
 
+struct perf_evsel;
 struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
@@ -82,9 +83,8 @@ int bpf__apply_obj_config(void);
 int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 
 int bpf__setup_stdout(struct perf_evlist *evlist);
-int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err,
-			       char *buf, size_t size);
-
+struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name);
+int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size);
 #else
 #include <errno.h>
 
@@ -138,6 +138,12 @@ bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 	return 0;
 }
 
+static inline struct perf_evsel *
+bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused)
+{
+	return NULL;
+}
+
 static inline int
 __bpf_strerror(char *buf, size_t size)
 {
@@ -193,11 +199,16 @@ bpf__strerror_apply_obj_config(int err __maybe_unused,
 }
 
 static inline int
-bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused,
-			   int err __maybe_unused, char *buf,
-			   size_t size)
+bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused,
+				 int err __maybe_unused, char *buf, size_t size)
 {
 	return __bpf_strerror(buf, size);
 }
+
 #endif
+
+static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size)
+{
+	return bpf__strerror_setup_output_event(evlist, err, buf, size);
+}
 #endif
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs)
-		refcount_inc(&cs->refcnt);
-	return cs;
+	if (cs && refcount_inc_not_zero(&cs->refcnt))
+		return cs;
+
+	return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 		parent = *p;
 		iter = rb_entry(parent, struct comm_str, rb_node);
 
+		/*
+		 * If we race with comm_str__put, iter->refcnt is 0
+		 * and it will be removed within comm_str__put call
+		 * shortly, ignore it in this search.
+		 */
 		cmp = strcmp(str, iter->str);
-		if (!cmp)
-			return comm_str__get(iter);
+		if (!cmp && comm_str__get(iter))
+			return iter;
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index ecca688a25fb..892e92e7e7fc 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -4,10 +4,12 @@
 
 #ifdef HAVE_ZLIB_SUPPORT
 int gzip_decompress_to_file(const char *input, int output_fd);
+bool gzip_is_compressed(const char *input);
 #endif
 
 #ifdef HAVE_LZMA_SUPPORT
 int lzma_decompress_to_file(const char *input, int output_fd);
+bool lzma_is_compressed(const char *input);
 #endif
 
 #endif /* PERF_COMPRESS_H */
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 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->tail = 0;
 	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].start_addr = CS_ETM_INVAL_ADDR;
+		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].exc = false;
 		decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
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 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		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 && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	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
@@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 		err = cs_etm__synth_instruction_sample(
 			etmq, addr,
 			etmq->period_instructions);
+		if (err)
+			return err;
+
 		etmq->period_instructions = 0;
 
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 5744c12641a5..abd38abf1d91 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -310,8 +310,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	if (flags & FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
-		tmp_val = pevent_read_number(fmtf->event->pevent,
-				data + offset, len);
+		tmp_val = tep_read_number(fmtf->event->pevent,
+					  data + offset, len);
 		offset = tmp_val;
 		len = offset >> 16;
 		offset &= 0xffff;
@@ -353,7 +353,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		else {
 			unsigned long long value_int;
 
-			value_int = pevent_read_number(
+			value_int = tep_read_number(
 					fmtf->event->pevent,
 					data + offset + i * len, len);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 51cf82cf1882..bbed90e5d9bb 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -189,28 +189,34 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
+enum {
+	COMP_ID__NONE = 0,
+};
+
 static const struct {
 	const char *fmt;
 	int (*decompress)(const char *input, int output);
+	bool (*is_compressed)(const char *input);
 } compressions[] = {
+	[COMP_ID__NONE] = { .fmt = NULL, },
 #ifdef HAVE_ZLIB_SUPPORT
-	{ "gz", gzip_decompress_to_file },
+	{ "gz", gzip_decompress_to_file, gzip_is_compressed },
 #endif
 #ifdef HAVE_LZMA_SUPPORT
-	{ "xz", lzma_decompress_to_file },
+	{ "xz", lzma_decompress_to_file, lzma_is_compressed },
 #endif
-	{ NULL, NULL },
+	{ NULL, NULL, NULL },
 };
 
-bool is_supported_compression(const char *ext)
+static int is_supported_compression(const char *ext)
 {
 	unsigned i;
 
-	for (i = 0; compressions[i].fmt; i++) {
+	for (i = 1; compressions[i].fmt; i++) {
 		if (!strcmp(ext, compressions[i].fmt))
-			return true;
+			return i;
 	}
-	return false;
+	return COMP_ID__NONE;
 }
 
 bool is_kernel_module(const char *pathname, int cpumode)
@@ -239,80 +245,73 @@ bool is_kernel_module(const char *pathname, int cpumode)
 	return m.kmod;
 }
 
-bool decompress_to_file(const char *ext, const char *filename, int output_fd)
-{
-	unsigned i;
-
-	for (i = 0; compressions[i].fmt; i++) {
-		if (!strcmp(ext, compressions[i].fmt))
-			return !compressions[i].decompress(filename,
-							   output_fd);
-	}
-	return false;
-}
-
 bool dso__needs_decompress(struct dso *dso)
 {
 	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+static int decompress_kmodule(struct dso *dso, const char *name,
+			      char *pathname, size_t len)
 {
+	char tmpbuf[] = KMOD_DECOMP_NAME;
 	int fd = -1;
-	struct kmod_path m;
 
 	if (!dso__needs_decompress(dso))
 		return -1;
 
-	if (kmod_path__parse_ext(&m, dso->long_name))
+	if (dso->comp == COMP_ID__NONE)
 		return -1;
 
-	if (!m.comp)
-		goto out;
+	/*
+	 * We have proper compression id for DSO and yet the file
+	 * behind the 'name' can still be plain uncompressed object.
+	 *
+	 * The reason is behind the logic we open the DSO object files,
+	 * when we try all possible 'debug' objects until we find the
+	 * data. So even if the DSO is represented by 'krava.xz' module,
+	 * we can end up here opening ~/.debug/....23432432/debug' file
+	 * which is not compressed.
+	 *
+	 * To keep this transparent, we detect this and return the file
+	 * descriptor to the uncompressed file.
+	 */
+	if (!compressions[dso->comp].is_compressed(name))
+		return open(name, O_RDONLY);
 
 	fd = mkstemp(tmpbuf);
 	if (fd < 0) {
 		dso->load_errno = errno;
-		goto out;
+		return -1;
 	}
 
-	if (!decompress_to_file(m.ext, name, fd)) {
+	if (compressions[dso->comp].decompress(name, fd)) {
 		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
 		close(fd);
 		fd = -1;
 	}
 
-out:
-	free(m.ext);
+	if (!pathname || (fd < 0))
+		unlink(tmpbuf);
+
+	if (pathname && (fd >= 0))
+		strncpy(pathname, tmpbuf, len);
+
 	return fd;
 }
 
 int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
 {
-	char tmpbuf[] = KMOD_DECOMP_NAME;
-	int fd;
-
-	fd = decompress_kmodule(dso, name, tmpbuf);
-	unlink(tmpbuf);
-	return fd;
+	return decompress_kmodule(dso, name, NULL, 0);
 }
 
 int dso__decompress_kmodule_path(struct dso *dso, const char *name,
 				 char *pathname, size_t len)
 {
-	char tmpbuf[] = KMOD_DECOMP_NAME;
-	int fd;
+	int fd = decompress_kmodule(dso, name, pathname, len);
 
-	fd = decompress_kmodule(dso, name, tmpbuf);
-	if (fd < 0) {
-		unlink(tmpbuf);
-		return -1;
-	}
-
-	strncpy(pathname, tmpbuf, len);
 	close(fd);
-	return 0;
+	return fd >= 0 ? 0 : -1;
 }
 
 /*
@@ -332,7 +331,7 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name,
  * Returns 0 if there's no strdup error, -ENOMEM otherwise.
  */
 int __kmod_path__parse(struct kmod_path *m, const char *path,
-		       bool alloc_name, bool alloc_ext)
+		       bool alloc_name)
 {
 	const char *name = strrchr(path, '/');
 	const char *ext  = strrchr(path, '.');
@@ -372,10 +371,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 		return 0;
 	}
 
-	if (is_supported_compression(ext + 1)) {
-		m->comp = true;
+	m->comp = is_supported_compression(ext + 1);
+	if (m->comp > COMP_ID__NONE)
 		ext -= 3;
-	}
 
 	/* Check .ko extension only if there's enough name left. */
 	if (ext > name)
@@ -393,14 +391,6 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 		strxfrchar(m->name, '-', '_');
 	}
 
-	if (alloc_ext && m->comp) {
-		m->ext = strdup(ext + 4);
-		if (!m->ext) {
-			free((void *) m->name);
-			return -ENOMEM;
-		}
-	}
-
 	return 0;
 }
 
@@ -413,8 +403,10 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m,
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
 
 	/* _KMODULE_COMP should be next to _KMODULE */
-	if (m->kmod && m->comp)
+	if (m->kmod && m->comp) {
 		dso->symtab_type++;
+		dso->comp = m->comp;
+	}
 
 	dso__set_short_name(dso, strdup(m->name), true);
 }
@@ -468,6 +460,7 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 	int fd = -EINVAL;
 	char *root_dir = (char *)"";
 	char *name = malloc(PATH_MAX);
+	bool decomp = false;
 
 	if (!name)
 		return -ENOMEM;
@@ -491,12 +484,13 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 			goto out;
 		}
 
+		decomp = true;
 		strcpy(name, newpath);
 	}
 
 	fd = do_open(name);
 
-	if (dso__needs_decompress(dso))
+	if (decomp)
 		unlink(name);
 
 out:
@@ -1218,6 +1212,7 @@ struct dso *dso__new(const char *name)
 		dso->a2l_fails = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
+		dso->comp = COMP_ID__NONE;
 		RB_CLEAR_NODE(&dso->rb_node);
 		dso->root = NULL;
 		INIT_LIST_HEAD(&dso->node);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ef69de2e69ea..c5380500bed4 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -175,6 +175,7 @@ struct dso {
 	u16		 short_name_len;
 	void		*dwfl;			/* DWARF debug info */
 	struct auxtrace_cache *auxtrace_cache;
+	int		 comp;
 
 	/* dso data file */
 	struct {
@@ -250,9 +251,7 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
-bool is_supported_compression(const char *ext);
 bool is_kernel_module(const char *pathname, int cpumode);
-bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
 int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
 int dso__decompress_kmodule_path(struct dso *dso, const char *name,
@@ -263,17 +262,15 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name,
 
 struct kmod_path {
 	char *name;
-	char *ext;
-	bool  comp;
+	int   comp;
 	bool  kmod;
 };
 
 int __kmod_path__parse(struct kmod_path *m, const char *path,
-		     bool alloc_name, bool alloc_ext);
+		     bool alloc_name);
 
-#define kmod_path__parse(__m, __p)      __kmod_path__parse(__m, __p, false, false)
-#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
-#define kmod_path__parse_ext(__m, __p)  __kmod_path__parse(__m, __p, false, true)
+#define kmod_path__parse(__m, __p)      __kmod_path__parse(__m, __p, false)
+#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true)
 
 void dso__set_module_info(struct dso *dso, struct kmod_path *m,
 			  struct machine *machine);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0c8ecf0c78a4..0cd42150f712 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -541,10 +541,17 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 						      tgid, process, machine) < 0)
 			return -1;
 
+		/*
+		 * send mmap only for thread group leader
+		 * see thread__init_map_groups
+		 */
+		if (pid == tgid &&
+		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						       process, machine, mmap_data,
+						       proc_map_timeout))
+			return -1;
 
-		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-							  process, machine, mmap_data,
-							  proc_map_timeout);
+		return 0;
 	}
 
 	if (machine__is_default_guest(machine))
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e7a4b31a84fb..be440df29615 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -803,7 +803,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		if (*output == -1) {
 			*output = fd;
 
-			if (perf_mmap__mmap(&maps[idx], mp, *output)  < 0)
+			if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..1a61628a1c12 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
-	if (evsel != NULL)
-		perf_evsel__init(evsel, attr, idx);
+	if (!evsel)
+		return NULL;
+	perf_evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
 		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
@@ -260,6 +261,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		evsel->attr.sample_period = 1;
 	}
 
+	if (perf_evsel__is_clock(evsel)) {
+		/*
+		 * The evsel->unit points to static alias->unit
+		 * so it's ok to use static string in here.
+		 */
+		static const char *unit = "msec";
+
+		evsel->unit = unit;
+		evsel->scale = 1e-6;
+	}
+
 	return evsel;
 }
 
@@ -848,6 +860,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1086,6 +1104,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -2658,7 +2684,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
 {
-	return pevent_find_field(evsel->tp_format, name);
+	return tep_find_field(evsel->tp_format, name);
 }
 
 void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..163c960614d3 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
 
-	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-		(attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
 struct perf_attr_details {
@@ -449,11 +452,18 @@ static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
 	return evsel->idx - evsel->leader->idx;
 }
 
+/* Iterates group WITHOUT the leader. */
 #define for_each_group_member(_evsel, _leader) 					\
 for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
      (_evsel) && (_evsel)->leader == (_leader);					\
      (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
 
+/* Iterates group WITH the leader. */
+#define for_each_group_evsel(_evsel, _leader) 					\
+for ((_evsel) = _leader; 							\
+     (_evsel) && (_evsel)->leader == (_leader);					\
+     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+
 static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel)
 {
 	return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..3cadc252dd89 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -279,8 +279,6 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
 	if (!set)
 		return -ENOMEM;
 
-	bitmap_zero(set, size);
-
 	p = (u64 *) set;
 
 	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
@@ -1285,7 +1283,6 @@ static int memory_node__read(struct memory_node *n, unsigned long idx)
 		return -ENOMEM;
 	}
 
-	bitmap_zero(n->set, size);
 	n->node = idx;
 	n->size = size;
 
@@ -2129,6 +2126,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2181,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2197,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -2579,7 +2584,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(NUMA_TOPOLOGY,	numa_topology,	true),
 	FEAT_OPN(BRANCH_STACK,	branch_stack,	false),
 	FEAT_OPR(PMU_MAPPINGS,	pmu_mappings,	false),
-	FEAT_OPN(GROUP_DESC,	group_desc,	false),
+	FEAT_OPR(GROUP_DESC,	group_desc,	false),
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
@@ -3199,7 +3204,7 @@ static int read_attr(int fd, struct perf_header *ph,
 }
 
 static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
-						struct pevent *pevent)
+						struct tep_handle *pevent)
 {
 	struct event_format *event;
 	char bf[128];
@@ -3213,7 +3218,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 		return -1;
 	}
 
-	event = pevent_find_event(pevent, evsel->attr.config);
+	event = tep_find_event(pevent, evsel->attr.config);
 	if (event == NULL) {
 		pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
 		return -1;
@@ -3231,7 +3236,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 }
 
 static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
-						  struct pevent *pevent)
+						  struct tep_handle *pevent)
 {
 	struct perf_evsel *pos;
 
@@ -3456,7 +3461,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 90d4577a92dc..6d7fe44aadc0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain);
+		      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..19262f98cd4e 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -22,12 +22,14 @@
 		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
+		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
+	.llc_path = "llc",
 	.clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE,
 	.clang_opt = NULL,
+	.opts = NULL,
 	.kbuild_dir = NULL,
 	.kbuild_opts = NULL,
 	.user_set_param = false,
@@ -51,6 +53,8 @@ int perf_llvm_config(const char *var, const char *value)
 		llvm_param.kbuild_opts = strdup(value);
 	else if (!strcmp(var, "dump-obj"))
 		llvm_param.dump_obj = !!perf_config_bool(var, value);
+	else if (!strcmp(var, "opts"))
+		llvm_param.opts = strdup(value);
 	else {
 		pr_debug("Invalid LLVM config option: %s\n", value);
 		return -1;
@@ -266,16 +270,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
@@ -430,11 +434,13 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	unsigned int kernel_version;
 	char linux_version_code_str[64];
 	const char *clang_opt = llvm_param.clang_opt;
-	char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
+	char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
 	char serr[STRERR_BUFSIZE];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
 	     *perf_bpf_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
+	char *pipe_template = NULL;
+	const char *opts = llvm_param.opts;
 	char *command_echo = NULL, *command_out;
 	char *perf_include_dir = system_path(PERF_INCLUDE_DIR);
 
@@ -484,6 +490,26 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
 	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
 
+	if (opts) {
+		err = search_program(llvm_param.llc_path, "llc", llc_path);
+		if (err) {
+			pr_err("ERROR:\tunable to find llc.\n"
+			       "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n"
+			       "     \tand 'llc-path' option in [llvm] section of ~/.perfconfig.\n");
+			version_notice();
+			goto errout;
+		}
+
+		if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -",
+			      template, llc_path, opts) < 0) {
+			pr_err("ERROR:\tnot enough memory to setup command line\n");
+			goto errout;
+		}
+
+		template = pipe_template;
+
+	}
+
 	/*
 	 * Since we may reset clang's working dir, path of source file
 	 * should be transferred into absolute path, except we want
@@ -535,6 +561,7 @@ errout:
 	free(obj_buf);
 	free(perf_bpf_include_opts);
 	free(perf_include_dir);
+	free(pipe_template);
 	if (p_obj_buf)
 		*p_obj_buf = NULL;
 	if (p_obj_buf_sz)
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index d3ad8deb5db4..bf3f3f4c4fe2 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -11,6 +11,8 @@
 struct llvm_param {
 	/* Path of clang executable */
 	const char *clang_path;
+	/* Path of llc executable */
+	const char *llc_path;
 	/*
 	 * Template of clang bpf compiling. 5 env variables
 	 * can be used:
@@ -23,6 +25,13 @@ struct llvm_param {
 	const char *clang_bpf_cmd_template;
 	/* Will be filled in $CLANG_OPTIONS */
 	const char *clang_opt;
+	/*
+	 * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe
+	 * the clang output to llc, useful for new llvm options not
+	 * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris
+	 * in clang 6.0/llvm 7
+	 */
+	const char *opts;
 	/* Where to find kbuild system */
 	const char *kbuild_dir;
 	/*
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 07498eaddc08..b1dd29a9d915 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -3,9 +3,13 @@
 #include <lzma.h>
 #include <stdio.h>
 #include <linux/compiler.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include "compress.h"
 #include "util.h"
 #include "debug.h"
+#include <unistd.h>
 
 #define BUFSIZE 8192
 
@@ -99,3 +103,19 @@ err_fclose:
 	fclose(infile);
 	return err;
 }
+
+bool lzma_is_compressed(const char *input)
+{
+	int fd = open(input, O_RDONLY);
+	const uint8_t magic[6] = { 0xFD, '7', 'z', 'X', 'Z', 0x00 };
+	char buf[6] = { 0 };
+	ssize_t rc;
+
+	if (fd < 0)
+		return -1;
+
+	rc = read(fd, buf, sizeof(buf));
+	close(fd);
+	return rc == sizeof(buf) ?
+	       memcmp(buf, magic, sizeof(buf)) == 0 : false;
+}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..c4acd2001db0 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+			  int pid, int tid)
 {
-	struct rb_node **p = &threads->entries.rb_node;
-	struct rb_node *parent = NULL;
 	struct thread *th;
 
-	/*
-	 * Front-end cache - TID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
 	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
@@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		threads->last_match = NULL;
 	}
 
+	return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
+{
+	struct thread *th = NULL;
+
+	if (perf_singlethreaded)
+		th = __threads__get_last_match(threads, machine, pid, tid);
+
+	return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	if (perf_singlethreaded)
+		__threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
+						  pid_t pid, pid_t tid,
+						  bool create)
+{
+	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	th = threads__get_last_match(threads, machine, pid, tid);
+	if (th)
+		return th;
+
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			threads->last_match = th;
+			threads__set_last_match(threads, th);
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		threads->last_match = th;
+		threads__set_last_match(threads, th);
 		++threads->nr;
 	}
 
@@ -1174,8 +1212,10 @@ static int map_groups__set_module_path(struct map_groups *mg, const char *path,
 	 * Full name could reveal us kmod compression, so
 	 * we need to update the symtab_type if needed.
 	 */
-	if (m->comp && is_kmod_dso(map->dso))
+	if (m->comp && is_kmod_dso(map->dso)) {
 		map->dso->symtab_type++;
+		map->dso->comp = m->comp;
+	}
 
 	return 0;
 }
@@ -1635,7 +1675,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	struct threads *threads = machine__threads(machine, th->tid);
 
 	if (threads->last_match == th)
-		threads->last_match = NULL;
+		threads__set_last_match(threads, NULL);
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
@@ -2272,6 +2312,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
+	u64 addr;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2279,7 +2320,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
 		return 0;
 
-	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+	/*
+	 * Convert entry->ip from a virtual address to an offset in
+	 * its corresponding binary.
+	 */
+	addr = map__map_ip(entry->map, entry->ip);
+
+	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
 				       false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 1de7660d93e9..d856b85862e2 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -265,7 +265,7 @@ pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
 /*
- * For use with libtraceevent's pevent_set_function_resolver()
+ * For use with libtraceevent's tep_set_function_resolver()
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 89ac5b5dc218..6a6929f208b4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -381,20 +381,6 @@ struct map *map__clone(struct map *from)
 	return map;
 }
 
-int map__overlap(struct map *l, struct map *r)
-{
-	if (l->start > r->start) {
-		struct map *t = l;
-		l = r;
-		r = t;
-	}
-
-	if (l->end > r->start)
-		return 1;
-
-	return 0;
-}
-
 size_t map__fprintf(struct map *map, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
@@ -590,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 	return NULL;
 }
 
+static bool map__contains_symbol(struct map *map, struct symbol *sym)
+{
+	u64 ip = map->unmap_ip(map, sym->start);
+
+	return ip >= map->start && ip < map->end;
+}
+
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 					 struct map **mapp)
 {
@@ -605,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
 		if (sym == NULL)
 			continue;
+		if (!map__contains_symbol(pos, sym)) {
+			sym = NULL;
+			continue;
+		}
 		if (mapp != NULL)
 			*mapp = pos;
 		goto out;
@@ -675,20 +672,42 @@ static void __map_groups__insert(struct map_groups *mg, struct map *map)
 static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
 	struct rb_root *root;
-	struct rb_node *next;
+	struct rb_node *next, *first;
 	int err = 0;
 
 	down_write(&maps->lock);
 
 	root = &maps->entries;
-	next = rb_first(root);
 
+	/*
+	 * Find first map where end > map->start.
+	 * Same as find_vma() in kernel.
+	 */
+	next = root->rb_node;
+	first = NULL;
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+
+		if (pos->end > map->start) {
+			first = next;
+			if (pos->start <= map->start)
+				break;
+			next = next->rb_left;
+		} else
+			next = next->rb_right;
+	}
+
+	next = first;
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 		next = rb_next(&pos->rb_node);
 
-		if (!map__overlap(pos, map))
-			continue;
+		/*
+		 * Stop if current map starts after map->end.
+		 * Maps are ordered by start: next will not overlap for sure.
+		 */
+		if (pos->start >= map->end)
+			break;
 
 		if (verbose >= 2) {
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 4cb90f242bed..e0f327b51e66 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -166,7 +166,6 @@ static inline void __map__zput(struct map **map)
 
 #define map__zput(map) __map__zput(&map)
 
-int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}
 
@@ -490,3 +490,25 @@ out:
 	metricgroup__free_egroups(&group_list);
 	return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
+	struct pmu_event *pe;
+	int i;
+
+	if (!map)
+		return false;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_name, metric))
+			return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
 			struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index fc832676a798..215f69f41672 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -164,7 +164,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
 	/*
 	 * The last one will be done at perf_mmap__consume(), so that we
@@ -191,6 +191,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
 		return -1;
 	}
 	map->fd = fd;
+	map->cpu = cpu;
 
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index d82294db1295..05a6d47c7956 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -18,6 +18,7 @@ struct perf_mmap {
 	void		 *base;
 	int		 mask;
 	int		 fd;
+	int		 cpu;
 	refcount_t	 refcnt;
 	u64		 prev;
 	u64		 start;
@@ -60,7 +61,7 @@ struct mmap_params {
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu);
 void perf_mmap__munmap(struct perf_mmap *map);
 
 void perf_mmap__get(struct perf_mmap *map);
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 5be021701f34..cf8bd123cf73 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -139,6 +139,9 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
 {
 	struct nsinfo *nnsi;
 
+	if (nsi == NULL)
+		return NULL;
+
 	nnsi = calloc(1, sizeof(*nnsi));
 	if (nnsi != NULL) {
 		nnsi->pid = nsi->pid;
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 760558dcfd18..cae1a9a39722 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -10,6 +10,7 @@
 #define __PERF_NAMESPACES_H
 
 #include <sys/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 15eec49e71a1..f8cd3e7c9186 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1991,8 +1991,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg)
 	int nr_addr_filters = 0;
 	struct perf_pmu *pmu = NULL;
 
-	if (evsel == NULL)
-		goto err;
+	if (evsel == NULL) {
+		fprintf(stderr,
+			"--filter option should follow a -e tracepoint or HW tracer option\n");
+		return -1;
+	}
 
 	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
 		if (perf_evsel__append_tp_filter(evsel, str) < 0) {
@@ -2014,8 +2017,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg)
 		perf_pmu__scan_file(pmu, "nr_addr_filters",
 				    "%d", &nr_addr_filters);
 
-	if (!nr_addr_filters)
-		goto err;
+	if (!nr_addr_filters) {
+		fprintf(stderr,
+			"This CPU does not support address filtering\n");
+		return -1;
+	}
 
 	if (perf_evsel__append_addr_filter(evsel, str) < 0) {
 		fprintf(stderr,
@@ -2024,12 +2030,6 @@ static int set_filter(struct perf_evsel *evsel, const void *arg)
 	}
 
 	return 0;
-
-err:
-	fprintf(stderr,
-		"--filter option should follow a -e tracepoint or HW tracer option\n");
-
-	return -1;
 }
 
 int parse_filter(const struct option *opt, const char *str,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+				char **new_str)
+{
+	if (!*old_str)
+		goto set_new;
+
+	if (*new_str) {	/* Have new string, check with old */
+		if (strcasecmp(*old_str, *new_str))
+			pr_debug("alias %s differs in field '%s'\n",
+				 name, field);
+		zfree(old_str);
+	} else		/* Nothing new --> keep old string */
+		return;
+set_new:
+	*old_str = *new_str;
+	*new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+				  struct perf_pmu_alias *newalias)
+{
+	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+			    &newalias->long_desc);
+	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+	perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+			    &newalias->metric_expr);
+	perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+			    &newalias->metric_name);
+	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+	old->scale = newalias->scale;
+	old->per_pkg = newalias->per_pkg;
+	old->snapshot = newalias->snapshot;
+	memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+	zfree(&newalias->name);
+	zfree(&newalias->desc);
+	zfree(&newalias->long_desc);
+	zfree(&newalias->topic);
+	zfree(&newalias->str);
+	zfree(&newalias->metric_expr);
+	zfree(&newalias->metric_name);
+	parse_events_terms__purge(&newalias->terms);
+	free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+				 struct list_head *alist)
+{
+	struct perf_pmu_alias *a;
+
+	list_for_each_entry(a, alist, list) {
+		if (!strcasecmp(newalias->name, a->name)) {
+			perf_pmu_update_alias(a, newalias);
+			perf_pmu_free_alias(newalias);
+			return true;
+		}
+	}
+	return false;
+}
+
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
@@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *metric_expr,
 				 char *metric_name)
 {
+	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
 	int num;
+	char newval[256];
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		return ret;
 	}
 
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	memset(newval, 0, sizeof(newval));
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
+
 	alias->name = strdup(name);
 	if (dir) {
 		/*
@@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
-	alias->str = strdup(val);
+	alias->str = strdup(newval);
 
-	list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(alias, list))
+		list_add_tail(&alias->list, list);
 
 	return 0;
 }
@@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
+	/* Remove trailing newline from sysfs file */
+	rtrim(buf);
+
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
 }
@@ -557,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
-	/* Look for cpu sysfs (specific to s390) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-		  sysfs, name);
-	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-		return 1;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 863b61478edd..ce501ba14b08 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -11,6 +11,7 @@
 #include "cpumap.h"
 #include "print_binary.h"
 #include "thread_map.h"
+#include "mmap.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
@@ -341,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 static PyObject*
 tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 {
-	struct pevent *pevent = field->event->pevent;
+	struct tep_handle *pevent = field->event->pevent;
 	void *data = pe->sample.raw_data;
 	PyObject *ret = NULL;
 	unsigned long long val;
@@ -351,7 +352,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 		offset = field->offset;
 		len    = field->size;
 		if (field->flags & FIELD_IS_DYNAMIC) {
-			val     = pevent_read_number(pevent, data + offset, len);
+			val     = tep_read_number(pevent, data + offset, len);
 			offset  = val;
 			len     = offset >> 16;
 			offset &= 0xffff;
@@ -364,8 +365,8 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 			field->flags &= ~FIELD_IS_STRING;
 		}
 	} else {
-		val = pevent_read_number(pevent, data + field->offset,
-					 field->size);
+		val = tep_read_number(pevent, data + field->offset,
+				      field->size);
 		if (field->flags & FIELD_IS_POINTER)
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
 		else if (field->flags & FIELD_IS_SIGNED)
@@ -394,7 +395,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 		evsel->tp_format = tp_format;
 	}
 
-	field = pevent_find_any_field(evsel->tp_format, str);
+	field = tep_find_any_field(evsel->tp_format, str);
 	if (!field)
 		return NULL;
 
@@ -976,6 +977,20 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
 	return Py_BuildValue("i", evlist->nr_entries);
 }
 
+static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu)
+{
+	int i;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *md = &evlist->mmap[i];
+
+		if (md->cpu == cpu)
+			return md;
+	}
+
+	return NULL;
+}
+
 static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					  PyObject *args, PyObject *kwargs)
 {
@@ -990,7 +1005,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	md = &evlist->mmap[cpu];
+	md = get_md(evlist, cpu);
+	if (!md)
+		return NULL;
+
 	if (perf_mmap__read_init(md) < 0)
 		goto end;
 
diff --git a/tools/perf/util/s390-cpumsf-kernel.h b/tools/perf/util/s390-cpumsf-kernel.h
new file mode 100644
index 000000000000..de8c7ad0eca8
--- /dev/null
+++ b/tools/perf/util/s390-cpumsf-kernel.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Auxtrace support for s390 CPU measurement sampling facility
+ *
+ *  Copyright IBM Corp. 2018
+ *  Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ *	       Thomas Richter <tmricht@linux.ibm.com>
+ */
+#ifndef S390_CPUMSF_KERNEL_H
+#define S390_CPUMSF_KERNEL_H
+
+#define	S390_CPUMSF_PAGESZ	4096	/* Size of sample block units */
+#define	S390_CPUMSF_DIAG_DEF_FIRST	0x8001	/* Diagnostic entry lowest id */
+
+struct hws_basic_entry {
+	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
+	unsigned int R:4;	    /* 16-19 reserved			 */
+	unsigned int U:4;	    /* 20-23 Number of unique instruct.  */
+	unsigned int z:2;	    /* zeros				 */
+	unsigned int T:1;	    /* 26 PSW DAT mode			 */
+	unsigned int W:1;	    /* 27 PSW wait state		 */
+	unsigned int P:1;	    /* 28 PSW Problem state		 */
+	unsigned int AS:2;	    /* 29-30 PSW address-space control	 */
+	unsigned int I:1;	    /* 31 entry valid or invalid	 */
+	unsigned int CL:2;	    /* 32-33 Configuration Level	 */
+	unsigned int:14;
+	unsigned int prim_asn:16;   /* primary ASN			 */
+	unsigned long long ia;	    /* Instruction Address		 */
+	unsigned long long gpp;     /* Guest Program Parameter		 */
+	unsigned long long hpp;     /* Host Program Parameter		 */
+};
+
+struct hws_diag_entry {
+	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
+	unsigned int R:15;	    /* 16-19 and 20-30 reserved		 */
+	unsigned int I:1;	    /* 31 entry valid or invalid	 */
+	u8	     data[];	    /* Machine-dependent sample data	 */
+};
+
+struct hws_combined_entry {
+	struct hws_basic_entry	basic;	/* Basic-sampling data entry */
+	struct hws_diag_entry	diag;	/* Diagnostic-sampling data entry */
+};
+
+struct hws_trailer_entry {
+	union {
+		struct {
+			unsigned int f:1;	/* 0 - Block Full Indicator   */
+			unsigned int a:1;	/* 1 - Alert request control  */
+			unsigned int t:1;	/* 2 - Timestamp format	      */
+			unsigned int:29;	/* 3 - 31: Reserved	      */
+			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
+		};
+		unsigned long long flags;	/* 0 - 64: All indicators     */
+	};
+	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
+	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
+	unsigned long long reserved1;	 /* 32 -Reserved		      */
+	unsigned long long reserved2;	 /*				      */
+	union {				 /* 48 - reserved for programming use */
+		struct {
+			unsigned long long clock_base:1; /* in progusage2 */
+			unsigned long long progusage1:63;
+			unsigned long long progusage2;
+		};
+		unsigned long long progusage[2];
+	};
+};
+
+#endif
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
new file mode 100644
index 000000000000..d2c78ffd9fee
--- /dev/null
+++ b/tools/perf/util/s390-cpumsf.c
@@ -0,0 +1,945 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2018
+ * Auxtrace support for s390 CPU-Measurement Sampling Facility
+ *
+ * Author(s):  Thomas Richter <tmricht@linux.ibm.com>
+ *
+ * Auxiliary traces are collected during 'perf record' using rbd000 event.
+ * Several PERF_RECORD_XXX are generated during recording:
+ *
+ * PERF_RECORD_AUX:
+ *	Records that new data landed in the AUX buffer part.
+ * PERF_RECORD_AUXTRACE:
+ *	Defines auxtrace data. Followed by the actual data. The contents of
+ *	the auxtrace data is dependent on the event and the CPU.
+ *	This record is generated by perf record command. For details
+ *	see Documentation/perf.data-file-format.txt.
+ * PERF_RECORD_AUXTRACE_INFO:
+ *	Defines a table of contains for PERF_RECORD_AUXTRACE records. This
+ *	record is generated during 'perf record' command. Each record contains up
+ *	to 256 entries describing offset and size of the AUXTRACE data in the
+ *	perf.data file.
+ * PERF_RECORD_AUXTRACE_ERROR:
+ *	Indicates an error during AUXTRACE collection such as buffer overflow.
+ * PERF_RECORD_FINISHED_ROUND:
+ *	Perf events are not necessarily in time stamp order, as they can be
+ *	collected in parallel on different CPUs. If the events should be
+ *	processed in time order they need to be sorted first.
+ *	Perf report guarantees that there is no reordering over a
+ *	PERF_RECORD_FINISHED_ROUND boundary event. All perf records with a
+ *	time stamp lower than this record are processed (and displayed) before
+ *	the succeeding perf record are processed.
+ *
+ * These records are evaluated during perf report command.
+ *
+ * 1. PERF_RECORD_AUXTRACE_INFO is used to set up the infrastructure for
+ * auxiliary trace data processing. See s390_cpumsf_process_auxtrace_info()
+ * below.
+ * Auxiliary trace data is collected per CPU. To merge the data into the report
+ * an auxtrace_queue is created for each CPU. It is assumed that the auxtrace
+ * data is in ascending order.
+ *
+ * Each queue has a double linked list of auxtrace_buffers. This list contains
+ * the offset and size of a CPU's auxtrace data. During auxtrace processing
+ * the data portion is mmap()'ed.
+ *
+ * To sort the queues in chronological order, all queue access is controlled
+ * by the auxtrace_heap. This is basicly a stack, each stack element has two
+ * entries, the queue number and a time stamp. However the stack is sorted by
+ * the time stamps. The highest time stamp is at the bottom the lowest
+ * (nearest) time stamp is at the top. That sort order is maintained at all
+ * times!
+ *
+ * After the auxtrace infrastructure has been setup, the auxtrace queues are
+ * filled with data (offset/size pairs) and the auxtrace_heap is populated.
+ *
+ * 2. PERF_RECORD_XXX processing triggers access to the auxtrace_queues.
+ * Each record is handled by s390_cpumsf_process_event(). The time stamp of
+ * the perf record is compared with the time stamp located on the auxtrace_heap
+ * top element. If that time stamp is lower than the time stamp from the
+ * record sample, the auxtrace queues will be processed. As auxtrace queues
+ * control many auxtrace_buffers and each buffer can be quite large, the
+ * auxtrace buffer might be processed only partially. In this case the
+ * position in the auxtrace_buffer of that queue is remembered and the time
+ * stamp of the last processed entry of the auxtrace_buffer replaces the
+ * current auxtrace_heap top.
+ *
+ * 3. Auxtrace_queues might run of out data and are feeded by the
+ * PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event().
+ *
+ * Event Generation
+ * Each sampling-data entry in the auxilary trace data generates a perf sample.
+ * This sample is filled
+ * with data from the auxtrace such as PID/TID, instruction address, CPU state,
+ * etc. This sample is processed with perf_session__deliver_synth_event() to
+ * be included into the GUI.
+ *
+ * 4. PERF_RECORD_FINISHED_ROUND event is used to process all the remaining
+ * auxiliary traces entries until the time stamp of this record is reached
+ * auxtrace_heap top. This is triggered by ordered_event->deliver().
+ *
+ *
+ * Perf event processing.
+ * Event processing of PERF_RECORD_XXX entries relies on time stamp entries.
+ * This is the function call sequence:
+ *
+ * __cmd_report()
+ * |
+ * perf_session__process_events()
+ * |
+ * __perf_session__process_events()
+ * |
+ * perf_session__process_event()
+ * |  This functions splits the PERF_RECORD_XXX records.
+ * |  - Those generated by perf record command (type number equal or higher
+ * |    than PERF_RECORD_USER_TYPE_START) are handled by
+ * |    perf_session__process_user_event(see below)
+ * |  - Those generated by the kernel are handled by
+ * |    perf_evlist__parse_sample_timestamp()
+ * |
+ * perf_evlist__parse_sample_timestamp()
+ * |  Extract time stamp from sample data.
+ * |
+ * perf_session__queue_event()
+ * |  If timestamp is positive the sample is entered into an ordered_event
+ * |  list, sort order is the timestamp. The event processing is deferred until
+ * |  later (see perf_session__process_user_event()).
+ * |  Other timestamps (0 or -1) are handled immediately by
+ * |  perf_session__deliver_event(). These are events generated at start up
+ * |  of command perf record. They create PERF_RECORD_COMM and PERF_RECORD_MMAP*
+ * |  records. They are needed to create a list of running processes and its
+ * |  memory mappings and layout. They are needed at the beginning to enable
+ * |  command perf report to create process trees and memory mappings.
+ * |
+ * perf_session__deliver_event()
+ * |  Delivers a PERF_RECORD_XXX entry for handling.
+ * |
+ * auxtrace__process_event()
+ * |  The timestamp of the PERF_RECORD_XXX entry is taken to correlate with
+ * |  time stamps from the auxiliary trace buffers. This enables
+ * |  synchronization between auxiliary trace data and the events on the
+ * |  perf.data file.
+ * |
+ * machine__deliver_event()
+ * |  Handles the PERF_RECORD_XXX event. This depends on the record type.
+ *    It might update the process tree, update a process memory map or enter
+ *    a sample with IP and call back chain data into GUI data pool.
+ *
+ *
+ * Deferred processing determined by perf_session__process_user_event() is
+ * finally processed when a PERF_RECORD_FINISHED_ROUND is encountered. These
+ * are generated during command perf record.
+ * The timestamp of PERF_RECORD_FINISHED_ROUND event is taken to process all
+ * PERF_RECORD_XXX entries stored in the ordered_event list. This list was
+ * built up while reading the perf.data file.
+ * Each event is now processed by calling perf_session__deliver_event().
+ * This enables time synchronization between the data in the perf.data file and
+ * the data in the auxiliary trace buffers.
+ */
+
+#include <endian.h>
+#include <errno.h>
+#include <byteswap.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "cpumap.h"
+#include "color.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "session.h"
+#include "util.h"
+#include "thread.h"
+#include "debug.h"
+#include "auxtrace.h"
+#include "s390-cpumsf.h"
+#include "s390-cpumsf-kernel.h"
+
+struct s390_cpumsf {
+	struct auxtrace		auxtrace;
+	struct auxtrace_queues	queues;
+	struct auxtrace_heap	heap;
+	struct perf_session	*session;
+	struct machine		*machine;
+	u32			auxtrace_type;
+	u32			pmu_type;
+	u16			machine_type;
+	bool			data_queued;
+};
+
+struct s390_cpumsf_queue {
+	struct s390_cpumsf	*sf;
+	unsigned int		queue_nr;
+	struct auxtrace_buffer	*buffer;
+	int			cpu;
+};
+
+/* Display s390 CPU measurement facility basic-sampling data entry */
+static bool s390_cpumsf_basic_show(const char *color, size_t pos,
+				   struct hws_basic_entry *basic)
+{
+	if (basic->def != 1) {
+		pr_err("Invalid AUX trace basic entry [%#08zx]\n", pos);
+		return false;
+	}
+	color_fprintf(stdout, color, "    [%#08zx] Basic   Def:%04x Inst:%#04x"
+		      " %c%c%c%c AS:%d ASN:%#04x IA:%#018llx\n"
+		      "\t\tCL:%d HPP:%#018llx GPP:%#018llx\n",
+		      pos, basic->def, basic->U,
+		      basic->T ? 'T' : ' ',
+		      basic->W ? 'W' : ' ',
+		      basic->P ? 'P' : ' ',
+		      basic->I ? 'I' : ' ',
+		      basic->AS, basic->prim_asn, basic->ia, basic->CL,
+		      basic->hpp, basic->gpp);
+	return true;
+}
+
+/* Display s390 CPU measurement facility diagnostic-sampling data entry */
+static bool s390_cpumsf_diag_show(const char *color, size_t pos,
+				  struct hws_diag_entry *diag)
+{
+	if (diag->def < S390_CPUMSF_DIAG_DEF_FIRST) {
+		pr_err("Invalid AUX trace diagnostic entry [%#08zx]\n", pos);
+		return false;
+	}
+	color_fprintf(stdout, color, "    [%#08zx] Diag    Def:%04x %c\n",
+		      pos, diag->def, diag->I ? 'I' : ' ');
+	return true;
+}
+
+/* Return TOD timestamp contained in an trailer entry */
+static unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
+{
+	/* te->t set: TOD in STCKE format, bytes 8-15
+	 * to->t not set: TOD in STCK format, bytes 0-7
+	 */
+	unsigned long long ts;
+
+	memcpy(&ts, &te->timestamp[te->t], sizeof(ts));
+	return ts;
+}
+
+/* Display s390 CPU measurement facility trailer entry */
+static bool s390_cpumsf_trailer_show(const char *color, size_t pos,
+				     struct hws_trailer_entry *te)
+{
+	if (te->bsdes != sizeof(struct hws_basic_entry)) {
+		pr_err("Invalid AUX trace trailer entry [%#08zx]\n", pos);
+		return false;
+	}
+	color_fprintf(stdout, color, "    [%#08zx] Trailer %c%c%c bsdes:%d"
+		      " dsdes:%d Overflow:%lld Time:%#llx\n"
+		      "\t\tC:%d TOD:%#lx 1:%#llx 2:%#llx\n",
+		      pos,
+		      te->f ? 'F' : ' ',
+		      te->a ? 'A' : ' ',
+		      te->t ? 'T' : ' ',
+		      te->bsdes, te->dsdes, te->overflow,
+		      trailer_timestamp(te), te->clock_base, te->progusage2,
+		      te->progusage[0], te->progusage[1]);
+	return true;
+}
+
+/* Test a sample data block. It must be 4KB or a multiple thereof in size and
+ * 4KB page aligned. Each sample data page has a trailer entry at the
+ * end which contains the sample entry data sizes.
+ *
+ * Return true if the sample data block passes the checks and set the
+ * basic set entry size and diagnostic set entry size.
+ *
+ * Return false on failure.
+ *
+ * Note: Old hardware does not set the basic or diagnostic entry sizes
+ * in the trailer entry. Use the type number instead.
+ */
+static bool s390_cpumsf_validate(int machine_type,
+				 unsigned char *buf, size_t len,
+				 unsigned short *bsdes,
+				 unsigned short *dsdes)
+{
+	struct hws_basic_entry *basic = (struct hws_basic_entry *)buf;
+	struct hws_trailer_entry *te;
+
+	*dsdes = *bsdes = 0;
+	if (len & (S390_CPUMSF_PAGESZ - 1))	/* Illegal size */
+		return false;
+	if (basic->def != 1)		/* No basic set entry, must be first */
+		return false;
+	/* Check for trailer entry at end of SDB */
+	te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
+					      - sizeof(*te));
+	*bsdes = te->bsdes;
+	*dsdes = te->dsdes;
+	if (!te->bsdes && !te->dsdes) {
+		/* Very old hardware, use CPUID */
+		switch (machine_type) {
+		case 2097:
+		case 2098:
+			*dsdes = 64;
+			*bsdes = 32;
+			break;
+		case 2817:
+		case 2818:
+			*dsdes = 74;
+			*bsdes = 32;
+			break;
+		case 2827:
+		case 2828:
+			*dsdes = 85;
+			*bsdes = 32;
+			break;
+		default:
+			/* Illegal trailer entry */
+			return false;
+		}
+	}
+	return true;
+}
+
+/* Return true if there is room for another entry */
+static bool s390_cpumsf_reached_trailer(size_t entry_sz, size_t pos)
+{
+	size_t payload = S390_CPUMSF_PAGESZ - sizeof(struct hws_trailer_entry);
+
+	if (payload - (pos & (S390_CPUMSF_PAGESZ - 1)) < entry_sz)
+		return false;
+	return true;
+}
+
+/* Dump an auxiliary buffer. These buffers are multiple of
+ * 4KB SDB pages.
+ */
+static void s390_cpumsf_dump(struct s390_cpumsf *sf,
+			     unsigned char *buf, size_t len)
+{
+	const char *color = PERF_COLOR_BLUE;
+	struct hws_basic_entry *basic;
+	struct hws_diag_entry *diag;
+	unsigned short bsdes, dsdes;
+	size_t pos = 0;
+
+	color_fprintf(stdout, color,
+		      ". ... s390 AUX data: size %zu bytes\n",
+		      len);
+
+	if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes,
+				  &dsdes)) {
+		pr_err("Invalid AUX trace data block size:%zu"
+		       " (type:%d bsdes:%hd dsdes:%hd)\n",
+		       len, sf->machine_type, bsdes, dsdes);
+		return;
+	}
+
+	/* s390 kernel always returns 4KB blocks fully occupied,
+	 * no partially filled SDBs.
+	 */
+	while (pos < len) {
+		/* Handle Basic entry */
+		basic = (struct hws_basic_entry *)(buf + pos);
+		if (s390_cpumsf_basic_show(color, pos, basic))
+			pos += bsdes;
+		else
+			return;
+
+		/* Handle Diagnostic entry */
+		diag = (struct hws_diag_entry *)(buf + pos);
+		if (s390_cpumsf_diag_show(color, pos, diag))
+			pos += dsdes;
+		else
+			return;
+
+		/* Check for trailer entry */
+		if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) {
+			/* Show trailer entry */
+			struct hws_trailer_entry te;
+
+			pos = (pos + S390_CPUMSF_PAGESZ)
+			       & ~(S390_CPUMSF_PAGESZ - 1);
+			pos -= sizeof(te);
+			memcpy(&te, buf + pos, sizeof(te));
+			/* Set descriptor sizes in case of old hardware
+			 * where these values are not set.
+			 */
+			te.bsdes = bsdes;
+			te.dsdes = dsdes;
+			if (s390_cpumsf_trailer_show(color, pos, &te))
+				pos += sizeof(te);
+			else
+				return;
+		}
+	}
+}
+
+static void s390_cpumsf_dump_event(struct s390_cpumsf *sf, unsigned char *buf,
+				   size_t len)
+{
+	printf(".\n");
+	s390_cpumsf_dump(sf, buf, len);
+}
+
+#define	S390_LPP_PID_MASK	0xffffffff
+
+static bool s390_cpumsf_make_event(size_t pos,
+				   struct hws_basic_entry *basic,
+				   struct s390_cpumsf_queue *sfq)
+{
+	struct perf_sample sample = {
+				.ip = basic->ia,
+				.pid = basic->hpp & S390_LPP_PID_MASK,
+				.tid = basic->hpp & S390_LPP_PID_MASK,
+				.cpumode = PERF_RECORD_MISC_CPUMODE_UNKNOWN,
+				.cpu = sfq->cpu,
+				.period = 1
+			    };
+	union perf_event event;
+
+	memset(&event, 0, sizeof(event));
+	if (basic->CL == 1)	/* Native LPAR mode */
+		sample.cpumode = basic->P ? PERF_RECORD_MISC_USER
+					  : PERF_RECORD_MISC_KERNEL;
+	else if (basic->CL == 2)	/* Guest kernel/user space */
+		sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER
+					  : PERF_RECORD_MISC_GUEST_KERNEL;
+	else if (basic->gpp || basic->prim_asn != 0xffff)
+		/* Use heuristics on old hardware */
+		sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER
+					  : PERF_RECORD_MISC_GUEST_KERNEL;
+	else
+		sample.cpumode = basic->P ? PERF_RECORD_MISC_USER
+					  : PERF_RECORD_MISC_KERNEL;
+
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = sample.cpumode;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
+	pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n",
+		 __func__, pos, sample.ip, basic->P, basic->CL, sample.pid,
+		 sample.tid, sample.cpumode, sample.cpu);
+	if (perf_session__deliver_synth_event(sfq->sf->session, &event,
+					      &sample)) {
+		pr_err("s390 Auxiliary Trace: failed to deliver event\n");
+		return false;
+	}
+	return true;
+}
+
+static unsigned long long get_trailer_time(const unsigned char *buf)
+{
+	struct hws_trailer_entry *te;
+	unsigned long long aux_time;
+
+	te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
+					      - sizeof(*te));
+
+	if (!te->clock_base)	/* TOD_CLOCK_BASE value missing */
+		return 0;
+
+	/* Correct calculation to convert time stamp in trailer entry to
+	 * nano seconds (taken from arch/s390 function tod_to_ns()).
+	 * TOD_CLOCK_BASE is stored in trailer entry member progusage2.
+	 */
+	aux_time = trailer_timestamp(te) - te->progusage2;
+	aux_time = (aux_time >> 9) * 125 + (((aux_time & 0x1ff) * 125) >> 9);
+	return aux_time;
+}
+
+/* Process the data samples of a single queue. The first parameter is a
+ * pointer to the queue, the second parameter is the time stamp. This
+ * is the time stamp:
+ * - of the event that triggered this processing.
+ * - or the time stamp when the last proccesing of this queue stopped.
+ *   In this case it stopped at a 4KB page boundary and record the
+ *   position on where to continue processing on the next invocation
+ *   (see buffer->use_data and buffer->use_size).
+ *
+ * When this function returns the second parameter is updated to
+ * reflect the time stamp of the last processed auxiliary data entry
+ * (taken from the trailer entry of that page). The caller uses this
+ * returned time stamp to record the last processed entry in this
+ * queue.
+ *
+ * The function returns:
+ * 0:  Processing successful. The second parameter returns the
+ *     time stamp from the trailer entry until which position
+ *     processing took place. Subsequent calls resume from this
+ *     position.
+ * <0: An error occurred during processing. The second parameter
+ *     returns the maximum time stamp.
+ * >0: Done on this queue. The second parameter returns the
+ *     maximum time stamp.
+ */
+static int s390_cpumsf_samples(struct s390_cpumsf_queue *sfq, u64 *ts)
+{
+	struct s390_cpumsf *sf = sfq->sf;
+	unsigned char *buf = sfq->buffer->use_data;
+	size_t len = sfq->buffer->use_size;
+	struct hws_basic_entry *basic;
+	unsigned short bsdes, dsdes;
+	size_t pos = 0;
+	int err = 1;
+	u64 aux_ts;
+
+	if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes,
+				  &dsdes)) {
+		*ts = ~0ULL;
+		return -1;
+	}
+
+	/* Get trailer entry time stamp and check if entries in
+	 * this auxiliary page are ready for processing. If the
+	 * time stamp of the first entry is too high, whole buffer
+	 * can be skipped. In this case return time stamp.
+	 */
+	aux_ts = get_trailer_time(buf);
+	if (!aux_ts) {
+		pr_err("[%#08" PRIx64 "] Invalid AUX trailer entry TOD clock base\n",
+		       sfq->buffer->data_offset);
+		aux_ts = ~0ULL;
+		goto out;
+	}
+	if (aux_ts > *ts) {
+		*ts = aux_ts;
+		return 0;
+	}
+
+	while (pos < len) {
+		/* Handle Basic entry */
+		basic = (struct hws_basic_entry *)(buf + pos);
+		if (s390_cpumsf_make_event(pos, basic, sfq))
+			pos += bsdes;
+		else {
+			err = -EBADF;
+			goto out;
+		}
+
+		pos += dsdes;	/* Skip diagnositic entry */
+
+		/* Check for trailer entry */
+		if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) {
+			pos = (pos + S390_CPUMSF_PAGESZ)
+			       & ~(S390_CPUMSF_PAGESZ - 1);
+			/* Check existence of next page */
+			if (pos >= len)
+				break;
+			aux_ts = get_trailer_time(buf + pos);
+			if (!aux_ts) {
+				aux_ts = ~0ULL;
+				goto out;
+			}
+			if (aux_ts > *ts) {
+				*ts = aux_ts;
+				sfq->buffer->use_data += pos;
+				sfq->buffer->use_size -= pos;
+				return 0;
+			}
+		}
+	}
+out:
+	*ts = aux_ts;
+	sfq->buffer->use_size = 0;
+	sfq->buffer->use_data = NULL;
+	return err;	/* Buffer completely scanned or error */
+}
+
+/* Run the s390 auxiliary trace decoder.
+ * Select the queue buffer to operate on, the caller already selected
+ * the proper queue, depending on second parameter 'ts'.
+ * This is the time stamp until which the auxiliary entries should
+ * be processed. This value is updated by called functions and
+ * returned to the caller.
+ *
+ * Resume processing in the current buffer. If there is no buffer
+ * get a new buffer from the queue and setup start position for
+ * processing.
+ * When a buffer is completely processed remove it from the queue
+ * before returning.
+ *
+ * This function returns
+ * 1: When the queue is empty. Second parameter will be set to
+ *    maximum time stamp.
+ * 0: Normal processing done.
+ * <0: Error during queue buffer setup. This causes the caller
+ *     to stop processing completely.
+ */
+static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
+				   u64 *ts)
+{
+
+	struct auxtrace_buffer *buffer;
+	struct auxtrace_queue *queue;
+	int err;
+
+	queue = &sfq->sf->queues.queue_array[sfq->queue_nr];
+
+	/* Get buffer and last position in buffer to resume
+	 * decoding the auxiliary entries. One buffer might be large
+	 * and decoding might stop in between. This depends on the time
+	 * stamp of the trailer entry in each page of the auxiliary
+	 * data and the time stamp of the event triggering the decoding.
+	 */
+	if (sfq->buffer == NULL) {
+		sfq->buffer = buffer = auxtrace_buffer__next(queue,
+							     sfq->buffer);
+		if (!buffer) {
+			*ts = ~0ULL;
+			return 1;	/* Processing done on this queue */
+		}
+		/* Start with a new buffer on this queue */
+		if (buffer->data) {
+			buffer->use_size = buffer->size;
+			buffer->use_data = buffer->data;
+		}
+	} else
+		buffer = sfq->buffer;
+
+	if (!buffer->data) {
+		int fd = perf_data__fd(sfq->sf->session->data);
+
+		buffer->data = auxtrace_buffer__get_data(buffer, fd);
+		if (!buffer->data)
+			return -ENOMEM;
+		buffer->use_size = buffer->size;
+		buffer->use_data = buffer->data;
+	}
+	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
+		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
+		  buffer->size, buffer->use_size);
+	err = s390_cpumsf_samples(sfq, ts);
+
+	/* If non-zero, there is either an error (err < 0) or the buffer is
+	 * completely done (err > 0). The error is unrecoverable, usually
+	 * some descriptors could not be read successfully, so continue with
+	 * the next buffer.
+	 * In both cases the parameter 'ts' has been updated.
+	 */
+	if (err) {
+		sfq->buffer = NULL;
+		list_del(&buffer->list);
+		auxtrace_buffer__free(buffer);
+		if (err > 0)		/* Buffer done, no error */
+			err = 0;
+	}
+	return err;
+}
+
+static struct s390_cpumsf_queue *
+s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
+{
+	struct s390_cpumsf_queue *sfq;
+
+	sfq = zalloc(sizeof(struct s390_cpumsf_queue));
+	if (sfq == NULL)
+		return NULL;
+
+	sfq->sf = sf;
+	sfq->queue_nr = queue_nr;
+	sfq->cpu = -1;
+	return sfq;
+}
+
+static int s390_cpumsf_setup_queue(struct s390_cpumsf *sf,
+				   struct auxtrace_queue *queue,
+				   unsigned int queue_nr, u64 ts)
+{
+	struct s390_cpumsf_queue *sfq = queue->priv;
+
+	if (list_empty(&queue->head))
+		return 0;
+
+	if (sfq == NULL) {
+		sfq = s390_cpumsf_alloc_queue(sf, queue_nr);
+		if (!sfq)
+			return -ENOMEM;
+		queue->priv = sfq;
+
+		if (queue->cpu != -1)
+			sfq->cpu = queue->cpu;
+	}
+	return auxtrace_heap__add(&sf->heap, queue_nr, ts);
+}
+
+static int s390_cpumsf_setup_queues(struct s390_cpumsf *sf, u64 ts)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < sf->queues.nr_queues; i++) {
+		ret = s390_cpumsf_setup_queue(sf, &sf->queues.queue_array[i],
+					      i, ts);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+static int s390_cpumsf_update_queues(struct s390_cpumsf *sf, u64 ts)
+{
+	if (!sf->queues.new_data)
+		return 0;
+
+	sf->queues.new_data = false;
+	return s390_cpumsf_setup_queues(sf, ts);
+}
+
+static int s390_cpumsf_process_queues(struct s390_cpumsf *sf, u64 timestamp)
+{
+	unsigned int queue_nr;
+	u64 ts;
+	int ret;
+
+	while (1) {
+		struct auxtrace_queue *queue;
+		struct s390_cpumsf_queue *sfq;
+
+		if (!sf->heap.heap_cnt)
+			return 0;
+
+		if (sf->heap.heap_array[0].ordinal >= timestamp)
+			return 0;
+
+		queue_nr = sf->heap.heap_array[0].queue_nr;
+		queue = &sf->queues.queue_array[queue_nr];
+		sfq = queue->priv;
+
+		auxtrace_heap__pop(&sf->heap);
+		if (sf->heap.heap_cnt) {
+			ts = sf->heap.heap_array[0].ordinal + 1;
+			if (ts > timestamp)
+				ts = timestamp;
+		} else {
+			ts = timestamp;
+		}
+
+		ret = s390_cpumsf_run_decoder(sfq, &ts);
+		if (ret < 0) {
+			auxtrace_heap__add(&sf->heap, queue_nr, ts);
+			return ret;
+		}
+		if (!ret) {
+			ret = auxtrace_heap__add(&sf->heap, queue_nr, ts);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
+				   pid_t pid, pid_t tid, u64 ip)
+{
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+	union perf_event event;
+	int err;
+
+	strncpy(msg, "Lost Auxiliary Trace Buffer", sizeof(msg) - 1);
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     code, cpu, pid, tid, ip, msg);
+
+	err = perf_session__deliver_synth_event(sf->session, &event, NULL);
+	if (err)
+		pr_err("s390 Auxiliary Trace: failed to deliver error event,"
+			"error %d\n", err);
+	return err;
+}
+
+static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample)
+{
+	return s390_cpumsf_synth_error(sf, 1, sample->cpu,
+				       sample->pid, sample->tid, 0);
+}
+
+static int
+s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
+			  union perf_event *event,
+			  struct perf_sample *sample,
+			  struct perf_tool *tool)
+{
+	struct s390_cpumsf *sf = container_of(session->auxtrace,
+					      struct s390_cpumsf,
+					      auxtrace);
+	u64 timestamp = sample->time;
+	int err = 0;
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events) {
+		pr_err("s390 Auxiliary Trace requires ordered events\n");
+		return -EINVAL;
+	}
+
+	if (event->header.type == PERF_RECORD_AUX &&
+	    event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+		return s390_cpumsf_lost(sf, sample);
+
+	if (timestamp) {
+		err = s390_cpumsf_update_queues(sf, timestamp);
+		if (!err)
+			err = s390_cpumsf_process_queues(sf, timestamp);
+	}
+	return err;
+}
+
+struct s390_cpumsf_synth {
+	struct perf_tool cpumsf_tool;
+	struct perf_session *session;
+};
+
+static int
+s390_cpumsf_process_auxtrace_event(struct perf_session *session,
+				   union perf_event *event __maybe_unused,
+				   struct perf_tool *tool __maybe_unused)
+{
+	struct s390_cpumsf *sf = container_of(session->auxtrace,
+					      struct s390_cpumsf,
+					      auxtrace);
+
+	int fd = perf_data__fd(session->data);
+	struct auxtrace_buffer *buffer;
+	off_t data_offset;
+	int err;
+
+	if (sf->data_queued)
+		return 0;
+
+	if (perf_data__is_pipe(session->data)) {
+		data_offset = 0;
+	} else {
+		data_offset = lseek(fd, 0, SEEK_CUR);
+		if (data_offset == -1)
+			return -errno;
+	}
+
+	err = auxtrace_queues__add_event(&sf->queues, session, event,
+					 data_offset, &buffer);
+	if (err)
+		return err;
+
+	/* Dump here after copying piped trace out of the pipe */
+	if (dump_trace) {
+		if (auxtrace_buffer__get_data(buffer, fd)) {
+			s390_cpumsf_dump_event(sf, buffer->data,
+					       buffer->size);
+			auxtrace_buffer__put_data(buffer);
+		}
+	}
+	return 0;
+}
+
+static void s390_cpumsf_free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static int s390_cpumsf_flush(struct perf_session *session __maybe_unused,
+			     struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static void s390_cpumsf_free_queues(struct perf_session *session)
+{
+	struct s390_cpumsf *sf = container_of(session->auxtrace,
+					      struct s390_cpumsf,
+					      auxtrace);
+	struct auxtrace_queues *queues = &sf->queues;
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++)
+		zfree(&queues->queue_array[i].priv);
+	auxtrace_queues__free(queues);
+}
+
+static void s390_cpumsf_free(struct perf_session *session)
+{
+	struct s390_cpumsf *sf = container_of(session->auxtrace,
+					      struct s390_cpumsf,
+					      auxtrace);
+
+	auxtrace_heap__free(&sf->heap);
+	s390_cpumsf_free_queues(session);
+	session->auxtrace = NULL;
+	free(sf);
+}
+
+static int s390_cpumsf_get_type(const char *cpuid)
+{
+	int ret, family = 0;
+
+	ret = sscanf(cpuid, "%*[^,],%u", &family);
+	return (ret == 1) ? family : 0;
+}
+
+/* Check itrace options set on perf report command.
+ * Return true, if none are set or all options specified can be
+ * handled on s390.
+ * Return false otherwise.
+ */
+static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
+{
+	if (!itops || !itops->set)
+		return true;
+	pr_err("No --itrace options supported\n");
+	return false;
+}
+
+int s390_cpumsf_process_auxtrace_info(union perf_event *event,
+				      struct perf_session *session)
+{
+	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct s390_cpumsf *sf;
+	int err;
+
+	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event))
+		return -EINVAL;
+
+	sf = zalloc(sizeof(struct s390_cpumsf));
+	if (sf == NULL)
+		return -ENOMEM;
+
+	if (!check_auxtrace_itrace(session->itrace_synth_opts)) {
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	err = auxtrace_queues__init(&sf->queues);
+	if (err)
+		goto err_free;
+
+	sf->session = session;
+	sf->machine = &session->machines.host; /* No kvm support */
+	sf->auxtrace_type = auxtrace_info->type;
+	sf->pmu_type = PERF_TYPE_RAW;
+	sf->machine_type = s390_cpumsf_get_type(session->evlist->env->cpuid);
+
+	sf->auxtrace.process_event = s390_cpumsf_process_event;
+	sf->auxtrace.process_auxtrace_event = s390_cpumsf_process_auxtrace_event;
+	sf->auxtrace.flush_events = s390_cpumsf_flush;
+	sf->auxtrace.free_events = s390_cpumsf_free_events;
+	sf->auxtrace.free = s390_cpumsf_free;
+	session->auxtrace = &sf->auxtrace;
+
+	if (dump_trace)
+		return 0;
+
+	err = auxtrace_queues__process_index(&sf->queues, session);
+	if (err)
+		goto err_free_queues;
+
+	if (sf->queues.populated)
+		sf->data_queued = true;
+
+	return 0;
+
+err_free_queues:
+	auxtrace_queues__free(&sf->queues);
+	session->auxtrace = NULL;
+err_free:
+	free(sf);
+	return err;
+}
diff --git a/tools/perf/util/s390-cpumsf.h b/tools/perf/util/s390-cpumsf.h
new file mode 100644
index 000000000000..fb64d100555c
--- /dev/null
+++ b/tools/perf/util/s390-cpumsf.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 2018
+ * Auxtrace support for s390 CPU-Measurement Sampling Facility
+ *
+ * Author(s):  Thomas Richter <tmricht@linux.ibm.com>
+ */
+
+#ifndef INCLUDE__PERF_S390_CPUMSF_H
+#define INCLUDE__PERF_S390_CPUMSF_H
+
+union perf_event;
+struct perf_session;
+struct perf_pmu;
+
+struct auxtrace_record *
+s390_cpumsf_recording_init(int *err, struct perf_pmu *s390_cpumsf_pmu);
+
+int s390_cpumsf_process_auxtrace_info(union perf_event *event,
+				      struct perf_session *session);
+#endif
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 7b79c413486b..45484f0f7292 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -535,7 +535,7 @@ static int perl_stop_script(void)
 	return 0;
 }
 
-static int perl_generate_script(struct pevent *pevent, const char *outfile)
+static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
 	struct event_format *event = NULL;
 	struct format_field *f;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..dfc6093f118c 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -871,8 +871,8 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			offset = field->offset;
 			len    = field->size;
 			if (field->flags & FIELD_IS_DYNAMIC) {
-				val     = pevent_read_number(scripting_context->pevent,
-							     data + offset, len);
+				val     = tep_read_number(scripting_context->pevent,
+							  data + offset, len);
 				offset  = val;
 				len     = offset >> 16;
 				offset &= 0xffff;
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1592,7 +1588,7 @@ static int python_stop_script(void)
 	return 0;
 }
 
-static int python_generate_script(struct pevent *pevent, const char *outfile)
+static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
 	struct event_format *event = NULL;
 	struct format_field *f;
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 001be4f9d3b9..97efbcad076e 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,12 +1,20 @@
 #!/usr/bin/python
 
 from os import getenv
+from subprocess import Popen, PIPE
+from re import sub
+
+def clang_has_option(option):
+    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ]
 
 cc = getenv("CC")
 if cc == "clang":
     from _sysconfigdata import build_time_vars
-    from re import sub
     build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
+    if not clang_has_option("-mcet"):
+        build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"])
+    if not clang_has_option("-fcf-protection"):
+        build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index fed2952ab45a..b284276ec963 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -601,7 +601,7 @@ static char *get_trace_output(struct hist_entry *he)
 {
 	struct trace_seq seq;
 	struct perf_evsel *evsel;
-	struct pevent_record rec = {
+	struct tep_record rec = {
 		.data = he->raw_data,
 		.size = he->raw_size,
 	};
@@ -610,10 +610,10 @@ static char *get_trace_output(struct hist_entry *he)
 
 	trace_seq_init(&seq);
 	if (symbol_conf.raw_trace) {
-		pevent_print_fields(&seq, he->raw_data, he->raw_size,
-				    evsel->tp_format);
+		tep_print_fields(&seq, he->raw_data, he->raw_size,
+				 evsel->tp_format);
 	} else {
-		pevent_event_info(&seq, evsel->tp_format, &rec);
+		tep_event_info(&seq, evsel->tp_format, &rec);
 	}
 	/*
 	 * Trim the buffer, it starts at 4KB and we're not going to
@@ -2047,7 +2047,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		struct trace_seq seq;
 raw_field:
 		trace_seq_init(&seq);
-		pevent_print_field(&seq, he->raw_data, hde->field);
+		tep_print_field(&seq, he->raw_data, hde->field);
 		str = seq.buffer;
 	}
 
@@ -2074,7 +2074,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	if (field->flags & FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
 
-		pevent_read_number_field(field, a->raw_data, &dyn);
+		tep_read_number_field(field, a->raw_data, &dyn);
 		offset = dyn & 0xffff;
 		size = (dyn >> 16) & 0xffff;
 
@@ -2311,7 +2311,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		field = pevent_find_any_field(evsel->tp_format, field_name);
+		field = tep_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL)
 			continue;
 
@@ -2378,7 +2378,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
 	if (!strcmp(field_name, "*")) {
 		ret = add_evsel_fields(evsel, raw_trace, level);
 	} else {
-		field = pevent_find_any_field(evsel->tp_format, field_name);
+		field = tep_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL) {
 			pr_debug("Cannot find event field for %s.%s\n",
 				 event_name, field_name);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 8bf302cafcec..a97cf8e6be86 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -276,7 +276,7 @@ extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
 struct perf_evlist;
-struct pevent;
+struct tep_handle;
 int setup_sorting(struct perf_evlist *evlist);
 int setup_output_field(void);
 void reset_output_field(void);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-				     avg / ratio);
+				     avg / (ratio * evsel->scale));
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c85d0d1a65ed..7b0ca7cbb7de 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -377,7 +377,7 @@ out:
 
 static int record_saved_cmdline(void)
 {
-	unsigned int size;
+	unsigned long long size;
 	char *path;
 	struct stat st;
 	int ret, err = 0;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e0a6e9a6a053..e76214f8d596 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -32,7 +32,7 @@
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
-	struct pevent *pevent = context->pevent;
+	struct tep_handle *pevent = context->pevent;
 	struct event_format *event;
 	struct format_field *field;
 
@@ -41,14 +41,14 @@ static int get_common_field(struct scripting_context *context,
 			return 0;
 
 		event = pevent->events[0];
-		field = pevent_find_common_field(event, type);
+		field = tep_find_common_field(event, type);
 		if (!field)
 			return 0;
 		*offset = field->offset;
 		*size = field->size;
 	}
 
-	return pevent_read_number(pevent, context->event_data + *offset, *size);
+	return tep_read_number(pevent, context->event_data + *offset, *size);
 }
 
 int common_lock_depth(struct scripting_context *context)
@@ -99,24 +99,24 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	struct format_field *field;
 	unsigned long long val;
 
-	field = pevent_find_any_field(event, name);
+	field = tep_find_any_field(event, name);
 	if (!field)
 		return 0ULL;
 
-	pevent_read_number_field(field, data, &val);
+	tep_read_number_field(field, data, &val);
 
 	return val;
 }
 
 unsigned long long read_size(struct event_format *event, void *ptr, int size)
 {
-	return pevent_read_number(event->pevent, ptr, size);
+	return tep_read_number(event->pevent, ptr, size);
 }
 
 void event_format__fprintf(struct event_format *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
-	struct pevent_record record;
+	struct tep_record record;
 	struct trace_seq s;
 
 	memset(&record, 0, sizeof(record));
@@ -125,7 +125,7 @@ void event_format__fprintf(struct event_format *event,
 	record.data = data;
 
 	trace_seq_init(&s);
-	pevent_event_info(&s, event, &record);
+	tep_event_info(&s, event, &record);
 	trace_seq_do_fprintf(&s, fp);
 	trace_seq_destroy(&s);
 }
@@ -136,7 +136,7 @@ void event_format__print(struct event_format *event,
 	return event_format__fprintf(event, cpu, data, size, stdout);
 }
 
-void parse_ftrace_printk(struct pevent *pevent,
+void parse_ftrace_printk(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
 	unsigned long long addr;
@@ -157,39 +157,38 @@ void parse_ftrace_printk(struct pevent *pevent,
 		/* fmt still has a space, skip it */
 		printk = strdup(fmt+1);
 		line = strtok_r(NULL, "\n", &next);
-		pevent_register_print_string(pevent, printk, addr);
+		tep_register_print_string(pevent, printk, addr);
 	}
 }
 
-void parse_saved_cmdline(struct pevent *pevent,
+void parse_saved_cmdline(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
-	char *comm;
+	char comm[17]; /* Max comm length in the kernel is 16. */
 	char *line;
 	char *next = NULL;
 	int pid;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
-		sscanf(line, "%d %ms", &pid, &comm);
-		pevent_register_comm(pevent, comm, pid);
-		free(comm);
+		if (sscanf(line, "%d %16s", &pid, comm) == 2)
+			tep_register_comm(pevent, comm, pid);
 		line = strtok_r(NULL, "\n", &next);
 	}
 }
 
-int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
+int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size)
 {
-	return pevent_parse_event(pevent, buf, size, "ftrace");
+	return tep_parse_event(pevent, buf, size, "ftrace");
 }
 
-int parse_event_file(struct pevent *pevent,
+int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys)
 {
-	return pevent_parse_event(pevent, buf, size, sys);
+	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct pevent *pevent,
+struct event_format *trace_find_next_event(struct tep_handle *pevent,
 					   struct event_format *event)
 {
 	static int idx;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 40b425949aa3..3dfc1db6b25b 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -96,7 +96,7 @@ static void skip(int size)
 	};
 }
 
-static unsigned int read4(struct pevent *pevent)
+static unsigned int read4(struct tep_handle *pevent)
 {
 	unsigned int data;
 
@@ -105,7 +105,7 @@ static unsigned int read4(struct pevent *pevent)
 	return __data2host4(pevent, data);
 }
 
-static unsigned long long read8(struct pevent *pevent)
+static unsigned long long read8(struct tep_handle *pevent)
 {
 	unsigned long long data;
 
@@ -158,7 +158,7 @@ out:
 	return str;
 }
 
-static int read_proc_kallsyms(struct pevent *pevent)
+static int read_proc_kallsyms(struct tep_handle *pevent)
 {
 	unsigned int size;
 
@@ -181,7 +181,7 @@ static int read_proc_kallsyms(struct pevent *pevent)
 	return 0;
 }
 
-static int read_ftrace_printk(struct pevent *pevent)
+static int read_ftrace_printk(struct tep_handle *pevent)
 {
 	unsigned int size;
 	char *buf;
@@ -208,7 +208,7 @@ static int read_ftrace_printk(struct pevent *pevent)
 	return 0;
 }
 
-static int read_header_files(struct pevent *pevent)
+static int read_header_files(struct tep_handle *pevent)
 {
 	unsigned long long size;
 	char *header_page;
@@ -235,13 +235,13 @@ static int read_header_files(struct pevent *pevent)
 		return -1;
 	}
 
-	if (!pevent_parse_header_page(pevent, header_page, size,
-				      pevent_get_long_size(pevent))) {
+	if (!tep_parse_header_page(pevent, header_page, size,
+				   tep_get_long_size(pevent))) {
 		/*
 		 * The commit field in the page is of type long,
 		 * use that instead, since it represents the kernel.
 		 */
-		pevent_set_long_size(pevent, pevent->header_page_size_size);
+		tep_set_long_size(pevent, pevent->header_page_size_size);
 	}
 	free(header_page);
 
@@ -259,7 +259,7 @@ static int read_header_files(struct pevent *pevent)
 	return ret;
 }
 
-static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
+static int read_ftrace_file(struct tep_handle *pevent, unsigned long long size)
 {
 	int ret;
 	char *buf;
@@ -284,8 +284,8 @@ out:
 	return ret;
 }
 
-static int read_event_file(struct pevent *pevent, char *sys,
-			    unsigned long long size)
+static int read_event_file(struct tep_handle *pevent, char *sys,
+			   unsigned long long size)
 {
 	int ret;
 	char *buf;
@@ -310,7 +310,7 @@ out:
 	return ret;
 }
 
-static int read_ftrace_files(struct pevent *pevent)
+static int read_ftrace_files(struct tep_handle *pevent)
 {
 	unsigned long long size;
 	int count;
@@ -328,7 +328,7 @@ static int read_ftrace_files(struct pevent *pevent)
 	return 0;
 }
 
-static int read_event_files(struct pevent *pevent)
+static int read_event_files(struct tep_handle *pevent)
 {
 	unsigned long long size;
 	char *sys;
@@ -356,7 +356,7 @@ static int read_event_files(struct pevent *pevent)
 	return 0;
 }
 
-static int read_saved_cmdline(struct pevent *pevent)
+static int read_saved_cmdline(struct tep_handle *pevent)
 {
 	unsigned long long size;
 	char *buf;
@@ -399,7 +399,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 	int host_bigendian;
 	int file_long_size;
 	int file_page_size;
-	struct pevent *pevent = NULL;
+	struct tep_handle *pevent = NULL;
 	int err;
 
 	repipe = __repipe;
@@ -439,9 +439,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 
 	pevent = tevent->pevent;
 
-	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-	pevent_set_file_bigendian(pevent, file_bigendian);
-	pevent_set_host_bigendian(pevent, host_bigendian);
+	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
+	tep_set_file_bigendian(pevent, file_bigendian);
+	tep_set_host_bigendian(pevent, host_bigendian);
 
 	if (do_read(buf, 1) < 0)
 		goto out;
@@ -451,8 +451,8 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 	if (!file_page_size)
 		goto out;
 
-	pevent_set_long_size(pevent, file_long_size);
-	pevent_set_page_size(pevent, file_page_size);
+	tep_set_long_size(pevent, file_long_size);
+	tep_set_page_size(pevent, file_page_size);
 
 	err = read_header_files(pevent);
 	if (err)
@@ -479,9 +479,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 	repipe = false;
 
 	if (show_funcs) {
-		pevent_print_funcs(pevent);
+		tep_print_funcs(pevent);
 	} else if (show_printk) {
-		pevent_print_printk(pevent);
+		tep_print_printk(pevent);
 	}
 
 	pevent = NULL;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index b1e5c3a2b8e3..b749f812ac70 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -66,7 +66,7 @@ static int python_start_script_unsupported(const char *script __maybe_unused,
 	return -1;
 }
 
-static int python_generate_script_unsupported(struct pevent *pevent
+static int python_generate_script_unsupported(struct tep_handle *pevent
 					      __maybe_unused,
 					      const char *outfile
 					      __maybe_unused)
@@ -130,7 +130,7 @@ static int perl_start_script_unsupported(const char *script __maybe_unused,
 	return -1;
 }
 
-static int perl_generate_script_unsupported(struct pevent *pevent
+static int perl_generate_script_unsupported(struct tep_handle *pevent
 					    __maybe_unused,
 					    const char *outfile __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 1aa368603268..58bb72f266f3 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -28,10 +28,10 @@ static bool tevent_initialized;
 
 int trace_event__init(struct trace_event *t)
 {
-	struct pevent *pevent = pevent_alloc();
+	struct tep_handle *pevent = tep_alloc();
 
 	if (pevent) {
-		t->plugin_list = traceevent_load_plugins(pevent);
+		t->plugin_list = tep_load_plugins(pevent);
 		t->pevent  = pevent;
 	}
 
@@ -40,33 +40,33 @@ int trace_event__init(struct trace_event *t)
 
 static int trace_event__init2(void)
 {
-	int be = traceevent_host_bigendian();
-	struct pevent *pevent;
+	int be = tep_host_bigendian();
+	struct tep_handle *pevent;
 
 	if (trace_event__init(&tevent))
 		return -1;
 
 	pevent = tevent.pevent;
-	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-	pevent_set_file_bigendian(pevent, be);
-	pevent_set_host_bigendian(pevent, be);
+	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
+	tep_set_file_bigendian(pevent, be);
+	tep_set_host_bigendian(pevent, be);
 	tevent_initialized = true;
 	return 0;
 }
 
 int trace_event__register_resolver(struct machine *machine,
-				   pevent_func_resolver_t *func)
+				   tep_func_resolver_t *func)
 {
 	if (!tevent_initialized && trace_event__init2())
 		return -1;
 
-	return pevent_set_function_resolver(tevent.pevent, func, machine);
+	return tep_set_function_resolver(tevent.pevent, func, machine);
 }
 
 void trace_event__cleanup(struct trace_event *t)
 {
-	traceevent_unload_plugins(t->plugin_list, t->pevent);
-	pevent_free(t->pevent);
+	tep_unload_plugins(t->plugin_list, t->pevent);
+	tep_free(t->pevent);
 }
 
 /*
@@ -76,7 +76,7 @@ static struct event_format*
 tp_format(const char *sys, const char *name)
 {
 	char *tp_dir = get_events_file(sys);
-	struct pevent *pevent = tevent.pevent;
+	struct tep_handle *pevent = tevent.pevent;
 	struct event_format *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
@@ -93,7 +93,7 @@ tp_format(const char *sys, const char *name)
 	if (err)
 		return ERR_PTR(err);
 
-	pevent_parse_format(pevent, &event, data, size, sys);
+	tep_parse_format(pevent, &event, data, size, sys);
 
 	free(data);
 	return event;
@@ -116,5 +116,5 @@ struct event_format *trace_event__tp_format_id(int id)
 	if (!tevent_initialized && trace_event__init2())
 		return ERR_PTR(-ENOMEM);
 
-	return pevent_find_event(tevent.pevent, id);
+	return tep_find_event(tevent.pevent, id);
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index dcbdb53dc702..40204ec3a7a2 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -13,14 +13,14 @@ struct thread;
 struct plugin_list;
 
 struct trace_event {
-	struct pevent		*pevent;
+	struct tep_handle	*pevent;
 	struct plugin_list	*plugin_list;
 };
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
 int trace_event__register_resolver(struct machine *machine,
-				   pevent_func_resolver_t *func);
+				   tep_func_resolver_t *func);
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
@@ -34,20 +34,20 @@ void event_format__fprintf(struct event_format *event,
 void event_format__print(struct event_format *event,
 			 int cpu, void *data, int size);
 
-int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
-int parse_event_file(struct pevent *pevent,
+int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
+int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);
 
 unsigned long long
 raw_field_value(struct event_format *event, const char *name, void *data);
 
-void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
-void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
-void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
+void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
+void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size);
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct event_format *trace_find_next_event(struct pevent *pevent,
+struct event_format *trace_find_next_event(struct tep_handle *pevent,
 					   struct event_format *event);
 unsigned long long read_size(struct event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
@@ -83,7 +83,7 @@ struct scripting_ops {
 	void (*process_stat)(struct perf_stat_config *config,
 			     struct perf_evsel *evsel, u64 tstamp);
 	void (*process_stat_interval)(u64 tstamp);
-	int (*generate_script) (struct pevent *pevent, const char *outfile);
+	int (*generate_script) (struct tep_handle *pevent, const char *outfile);
 };
 
 extern unsigned int scripting_max_stack;
@@ -94,7 +94,7 @@ void setup_perl_scripting(void);
 void setup_python_scripting(void);
 
 struct scripting_context {
-	struct pevent *pevent;
+	struct tep_handle *pevent;
 	void *event_data;
 };
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e->ip  = al.addr;
+	e->ip  = ip;
 	e->map = al.map;
 	e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
 	struct addr_location al;
 
 	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-	e.ip = al.addr;
+	e.ip  = ip;
 	e.map = al.map;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index a725b958cf31..902ce6384f57 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -5,6 +5,8 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <zlib.h>
+#include <linux/compiler.h>
+#include <unistd.h>
 
 #include "util/compress.h"
 #include "util/util.h"
@@ -79,3 +81,19 @@ out_close:
 
 	return ret == Z_STREAM_END ? 0 : -1;
 }
+
+bool gzip_is_compressed(const char *input)
+{
+	int fd = open(input, O_RDONLY);
+	const uint8_t magic[2] = { 0x1f, 0x8b };
+	char buf[2] = { 0 };
+	ssize_t rc;
+
+	if (fd < 0)
+		return -1;
+
+	rc = read(fd, buf, sizeof(buf));
+	close(fd);
+	return rc == sizeof(buf) ?
+	       memcmp(buf, magic, sizeof(buf)) == 0 : false;
+}
author	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>	2018-09-26 15:54:31 +0200
committer	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>	2018-09-26 15:54:31 +0200
commit	aaccf3c97418f169afdbb5855e9cbcbda34e90fd (patch)
tree	5d4207e67958bdbc23288cf30178692f5534e1a0 /tools/perf
parent	f39684524b391c5a7ed0ac44db4fec3357af1c5d (diff)
parent	6bf4ca7fbc85d80446ac01c0d1d77db4d91a6d84 (diff)