Merge tag 'perf-core-for-mingo-4.20-20180905' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

perf trace:

- Augment the payload of syscall entry/exit tracepoints with the contents
  of pointer arguments, such as the "filename" argument to the "open"
  syscall or the 'struct sockaddr *' argument to the 'connect' syscall.

  This is done using a BPF program that gets compiled and attached to
  various syscalls:sys_enter_NAME tracepoints, copying via a BPF map and
  "bpf-output" perf event the raw_syscalls:sys_enter tracepoint payload +
  the contents of pointer arguments using the "probe_read", "probe_read_str"
  and "perf_event_output" BPF functions.

  The 'perf trace' codebase now just processes these augmented tracepoints
  using the existing beautifiers that now check if there is more in the
  perf_sample->raw_data than what is expected for a normal syscall enter
  tracepoint (the common preamble, syscall id, up to six parameters),
  using that with hand crafted struct beautifiers.

  This is just to show how to augment the existing tracepoints, work will
  be done to use DWARF or BTF info to do the pretty-printing and to create
  the collectors.

  For now this is done using an example restricted C BPF program, but the
  end goal is to have this all autogenerated and done transparently.

  Its still useful to have this example as one can use it as an skeleton and
  write more involved filters, see the etcsnoop.c BPF example, for instance.

  E.g.:

  # cd tools/perf/examples/bpf/
  # perf trace -e augmented_syscalls.c ping -c 1 ::1
     0.000 ( 0.008 ms): openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.020 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
     0.051 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
     0.076 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
     0.106 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
     0.136 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
     0.194 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.224 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
     0.252 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
     0.275 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
     0.730 ( 0.007 ms): open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
  PING ::1(::1) 56 data bytes
     0.834 ( 0.008 ms): connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.032 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.032/0.032/0.032/0.000 ms
     0.914 ( 0.036 ms): sendto(fd: 4<socket:[843044]>, buff: 0x55b5e52e9720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
  #

  Use 'perf trace -e augmented_syscalls.c,close ping -c 1 ::1' to see the
  'close' calls as well, as it is not one of the syscalls augmented in that .c
  file.

  (Arnaldo Carvalho de Melo)

- Alias 'umount' to 'umount2' (Benjamin Peterson)

perf stat: (Jiri Olsa)

- Make many builtin-stat.c functions generic, moving display functions
  to a separate file, prep work for adding the ability to store/display
  stat data in perf record/top.

perf annotate: (Kim Phillips)

- Handle arm64 move instructions

perf report: (Thomas Richter):

- Create auxiliary trace data files for s390

libtraceevent: (Tzvetomir Stoyanov (VMware)):

- Split trace-seq related APIs in a separate header file.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

39 files changed, 2464 insertions, 1514 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index b3d1b12a5081..92514fb3689f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -777,14 +777,14 @@ 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'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
+	$(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)'
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index f013b115dc86..dbef716a1913 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/arm64/include/generated/asm
 header := $(out)/syscalls.c
-sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
 sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
 systbl := $(sysprf)/mksyscalltbl
 
@@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, arm64) $(RM) $(header)
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 6688977e4ac7..76c6345a57d5 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -8,6 +8,63 @@ struct arm64_annotate {
 		jump_insn;
 };
 
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+			    struct ins_operands *ops,
+			    struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	*s = ' ';
+	ops->target.name = strdup(s);
+	*s = '<';
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops arm64_mov_ops = {
+	.parse	   = arm64_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
 {
 	struct arm64_annotate *arm = arch->priv;
@@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
 	else if (!strcmp(name, "ret"))
 		ops = &ret_ops;
 	else
-		return NULL;
+		ops = &arm64_mov_ops;
 
 	arch__associate_ins_ops(arch, name, ops);
 	return ops;
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 52e197317d3e..2dbb8cade048 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -11,7 +11,8 @@
 
 gcc=$1
 hostcc=$2
-input=$3
+incpath=$3
+input=$4
 
 if ! test -r $input; then
 	echo "Could not read input file" >&2
@@ -28,7 +29,6 @@ create_table_from_c()
 
 	cat <<-_EoHEADER
 		#include <stdio.h>
-		#define __ARCH_WANT_RENAMEAT
 		#include "$input"
 		int main(int argc, char *argv[])
 		{
@@ -42,7 +42,7 @@ create_table_from_c()
 	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
 	printf "}\n"
 
-	} | $hostcc -o $create_table_exe -x c -
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
 
 	$create_table_exe
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 20e7d74d86cd..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)
 {
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index cee4e2f7c057..de0dd66dbb48 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -100,8 +100,6 @@ out_free_source:
 	return -1;
 }
 
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops);
 
 static struct ins_ops s390_mov_ops = {
 	.parse	   = s390_mov__parse,
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/builtin-record.c b/tools/perf/builtin-record.c
index 22ebeb92ac51..9853552bcf16 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -758,7 +758,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		 * We need to synthesize events first, because some
 		 * features works on top of them (on report side).
 		 */
-		err = perf_event__synthesize_attrs(tool, session,
+		err = perf_event__synthesize_attrs(tool, rec->evlist,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ba481d73f910..6176bae177c2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1544,7 +1544,8 @@ struct metric_ctx {
 	FILE 			*fp;
 };
 
-static void script_print_metric(void *ctx, const char *color,
+static void script_print_metric(struct perf_stat_config *config __maybe_unused,
+				void *ctx, const char *color,
 			        const char *fmt,
 			        const char *unit, double val)
 {
@@ -1562,7 +1563,8 @@ static void script_print_metric(void *ctx, const char *color,
 	fprintf(mctx->fp, " %s\n", unit);
 }
 
-static void script_new_line(void *ctx)
+static void script_new_line(struct perf_stat_config *config __maybe_unused,
+			    void *ctx)
 {
 	struct metric_ctx *mctx = ctx;
 
@@ -1608,7 +1610,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	evsel_script(evsel)->val = val;
 	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
 		for_each_group_member (ev2, evsel->leader) {
-			perf_stat__print_shadow_stats(ev2,
+			perf_stat__print_shadow_stats(&stat_config, ev2,
 						      evsel_script(ev2)->val,
 						      sample->cpu,
 						      &ctx,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d097b5b47eb8..0b0e3961d511 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -88,8 +88,6 @@
 #include "sane_ctype.h"
 
 #define DEFAULT_SEPARATOR	" "
-#define CNTR_NOT_SUPPORTED	"<not supported>"
-#define CNTR_NOT_COUNTED	"<not counted>"
 #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
@@ -137,54 +135,30 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
-static struct rblist		 metric_events;
-
 static struct target target = {
 	.uid	= UINT_MAX,
 };
 
-typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
-
 #define METRIC_ONLY_LEN 20
 
-static int			run_count			=  1;
-static bool			no_inherit			= false;
 static volatile pid_t		child_pid			= -1;
-static bool			null_run			=  false;
 static int			detailed_run			=  0;
 static bool			transaction_run;
 static bool			topdown_run			= false;
 static bool			smi_cost			= false;
 static bool			smi_reset			= false;
-static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
-static const char		*csv_sep			= NULL;
-static bool			csv_output			= false;
 static bool			group				= false;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
-static unsigned int		initial_delay			= 0;
-static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
-static bool			metric_only			= false;
 static bool			force_metric_only		= false;
-static bool			no_merge			= false;
-static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
-static struct cpu_map		*aggr_map;
-static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
-static bool			interval_clear;
 static const char		*output_name;
 static int			output_fd;
-static int			print_free_counters_hint;
-static int			print_mixed_hw_group_error;
-static u64			*walltime_run;
-static bool			ru_display			= false;
-static struct rusage		ru_data;
-static unsigned int		metric_only_len			= METRIC_ONLY_LEN;
 
 struct perf_stat {
 	bool			 record;
@@ -204,15 +178,15 @@ static struct perf_stat		perf_stat;
 static volatile int done = 0;
 
 static struct perf_stat_config stat_config = {
-	.aggr_mode	= AGGR_GLOBAL,
-	.scale		= true,
+	.aggr_mode		= AGGR_GLOBAL,
+	.scale			= true,
+	.unit_width		= 4, /* strlen("unit") */
+	.run_count		= 1,
+	.metric_only_len	= METRIC_ONLY_LEN,
+	.walltime_nsecs_stats	= &walltime_nsecs_stats,
+	.big_num		= true,
 };
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -236,66 +210,6 @@ static void perf_stat__reset_stats(void)
 		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
-static int create_perf_stat_counter(struct perf_evsel *evsel)
-{
-	struct perf_event_attr *attr = &evsel->attr;
-	struct perf_evsel *leader = evsel->leader;
-
-	if (stat_config.scale) {
-		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-				    PERF_FORMAT_TOTAL_TIME_RUNNING;
-	}
-
-	/*
-	 * The event is part of non trivial group, let's enable
-	 * the group read (for leader) and ID retrieval for all
-	 * members.
-	 */
-	if (leader->nr_members > 1)
-		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
-
-	attr->inherit = !no_inherit;
-
-	/*
-	 * Some events get initialized with sample_(period/type) set,
-	 * like tracepoints. Clear it up for counting.
-	 */
-	attr->sample_period = 0;
-
-	/*
-	 * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
-	 * while avoiding that older tools show confusing messages.
-	 *
-	 * However for pipe sessions we need to keep it zero,
-	 * because script's perf_evsel__check_attr is triggered
-	 * by attr->sample_type != 0, and we can't run it on
-	 * stat sessions.
-	 */
-	if (!(STAT_RECORD && perf_stat.data.is_pipe))
-		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
-
-	/*
-	 * Disabling all counters initially, they will be enabled
-	 * either manually by us or by kernel via enable_on_exec
-	 * set later.
-	 */
-	if (perf_evsel__is_group_leader(evsel)) {
-		attr->disabled = 1;
-
-		/*
-		 * In case of initial_delay we enable tracee
-		 * events manually.
-		 */
-		if (target__none(&target) && !initial_delay)
-			attr->enable_on_exec = 1;
-	}
-
-	if (target__has_cpu(&target) && !target__has_per_thread(&target))
-		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
-
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -428,15 +342,15 @@ static void process_interval(void)
 
 static void enable_counters(void)
 {
-	if (initial_delay)
-		usleep(initial_delay * USEC_PER_MSEC);
+	if (stat_config.initial_delay)
+		usleep(stat_config.initial_delay * USEC_PER_MSEC);
 
 	/*
 	 * We need to enable counters only if:
 	 * - we don't have tracee (attaching to task or cpu)
 	 * - we have initial delay configured
 	 */
-	if (!target__none(&target) || initial_delay)
+	if (!target__none(&target) || stat_config.initial_delay)
 		perf_evlist__enable(evsel_list);
 }
 
@@ -464,80 +378,6 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(bool is_pipe)
-{
-	int err;
-
-	if (is_pipe) {
-		err = perf_event__synthesize_attrs(NULL, perf_stat.session,
-						   process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			return err;
-		}
-	}
-
-	err = perf_event__synthesize_extra_attr(NULL,
-						evsel_list,
-						process_synthesized_event,
-						is_pipe);
-
-	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
-						process_synthesized_event,
-						NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
-					     process_synthesized_event, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_stat_config(NULL, &stat_config,
-						 process_synthesized_event, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize config.\n");
-		return err;
-	}
-
-	return 0;
-}
-
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
-static int __store_counter_ids(struct perf_evsel *counter)
-{
-	int cpu, thread;
-
-	for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(counter->fd);
-		     thread++) {
-			int fd = FD(counter, cpu, thread);
-
-			if (perf_evlist__id_add_fd(evsel_list, counter,
-						   cpu, thread, fd) < 0)
-				return -1;
-		}
-	}
-
-	return 0;
-}
-
-static int store_counter_ids(struct perf_evsel *counter)
-{
-	struct cpu_map *cpus = counter->cpus;
-	struct thread_map *threads = counter->threads;
-
-	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
-		return -ENOMEM;
-
-	return __store_counter_ids(counter);
-}
-
 static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 {
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
@@ -609,7 +449,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
-		if (create_perf_stat_counter(counter) < 0) {
+		if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
 
 			/* Weak group failed. Reset the group. */
 			if ((errno == EINVAL || errno == EBADF) &&
@@ -664,11 +504,11 @@ try_again:
 		counter->supported = true;
 
 		l = strlen(counter->unit);
-		if (l > unit_width)
-			unit_width = l;
+		if (l > stat_config.unit_width)
+			stat_config.unit_width = l;
 
 		if (perf_evsel__should_store_id(counter) &&
-		    store_counter_ids(counter))
+		    perf_evsel__store_ids(counter, evsel_list))
 			return -1;
 	}
 
@@ -699,7 +539,8 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(is_pipe);
+		err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+						  process_synthesized_event, is_pipe);
 		if (err < 0)
 			return err;
 	}
@@ -724,7 +565,7 @@ try_again:
 					break;
 			}
 		}
-		wait4(child_pid, &status, 0, &ru_data);
+		wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -752,8 +593,8 @@ try_again:
 
 	t1 = rdclock();
 
-	if (walltime_run_table)
-		walltime_run[run_idx] = t1 - t0;
+	if (stat_config.walltime_run_table)
+		stat_config.walltime_run[run_idx] = t1 - t0;
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
@@ -795,1105 +636,14 @@ static int run_perf_stat(int argc, const char **argv, int run_idx)
 	return ret;
 }
 
-static void print_running(u64 run, u64 ena)
-{
-	if (csv_output) {
-		fprintf(stat_config.output, "%s%" PRIu64 "%s%.2f",
-					csv_sep,
-					run,
-					csv_sep,
-					ena ? 100.0 * run / ena : 100.0);
-	} else if (run != ena) {
-		fprintf(stat_config.output, "  (%.2f%%)", 100.0 * run / ena);
-	}
-}
-
-static void print_noise_pct(double total, double avg)
-{
-	double pct = rel_stddev_stats(total, avg);
-
-	if (csv_output)
-		fprintf(stat_config.output, "%s%.2f%%", csv_sep, pct);
-	else if (pct)
-		fprintf(stat_config.output, "  ( +-%6.2f%% )", pct);
-}
-
-static void print_noise(struct perf_evsel *evsel, double avg)
-{
-	struct perf_stat_evsel *ps;
-
-	if (run_count == 1)
-		return;
-
-	ps = evsel->stats;
-	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
-}
-
-static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
-{
-	switch (stat_config.aggr_mode) {
-	case AGGR_CORE:
-		fprintf(stat_config.output, "S%d-C%*d%s%*d%s",
-			cpu_map__id_to_socket(id),
-			csv_output ? 0 : -8,
-			cpu_map__id_to_cpu(id),
-			csv_sep,
-			csv_output ? 0 : 4,
-			nr,
-			csv_sep);
-		break;
-	case AGGR_SOCKET:
-		fprintf(stat_config.output, "S%*d%s%*d%s",
-			csv_output ? 0 : -5,
-			id,
-			csv_sep,
-			csv_output ? 0 : 4,
-			nr,
-			csv_sep);
-			break;
-	case AGGR_NONE:
-		fprintf(stat_config.output, "CPU%*d%s",
-			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[id], csv_sep);
-		break;
-	case AGGR_THREAD:
-		fprintf(stat_config.output, "%*s-%*d%s",
-			csv_output ? 0 : 16,
-			thread_map__comm(evsel->threads, id),
-			csv_output ? 0 : -8,
-			thread_map__pid(evsel->threads, id),
-			csv_sep);
-		break;
-	case AGGR_GLOBAL:
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-}
-
-struct outstate {
-	FILE *fh;
-	bool newline;
-	const char *prefix;
-	int  nfields;
-	int  id, nr;
-	struct perf_evsel *evsel;
-};
-
-#define METRIC_LEN  35
-
-static void new_line_std(void *ctx)
-{
-	struct outstate *os = ctx;
-
-	os->newline = true;
-}
-
-static void do_new_line_std(struct outstate *os)
-{
-	fputc('\n', os->fh);
-	fputs(os->prefix, os->fh);
-	aggr_printout(os->evsel, os->id, os->nr);
-	if (stat_config.aggr_mode == AGGR_NONE)
-		fprintf(os->fh, "        ");
-	fprintf(os->fh, "                                                 ");
-}
-
-static void print_metric_std(void *ctx, const char *color, const char *fmt,
-			     const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	int n;
-	bool newline = os->newline;
-
-	os->newline = false;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%-*s", METRIC_LEN, "");
-		return;
-	}
-
-	if (newline)
-		do_new_line_std(os);
-
-	n = fprintf(out, " # ");
-	if (color)
-		n += color_fprintf(out, color, fmt, val);
-	else
-		n += fprintf(out, fmt, val);
-	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
-}
-
-static void new_line_csv(void *ctx)
-{
-	struct outstate *os = ctx;
-	int i;
-
-	fputc('\n', os->fh);
-	if (os->prefix)
-		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
-	aggr_printout(os->evsel, os->id, os->nr);
-	for (i = 0; i < os->nfields; i++)
-		fputs(csv_sep, os->fh);
-}
-
-static void print_metric_csv(void *ctx,
-			     const char *color __maybe_unused,
-			     const char *fmt, const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%s%s", csv_sep, csv_sep);
-		return;
-	}
-	snprintf(buf, sizeof(buf), fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	while (isspace(*unit))
-		unit++;
-	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
-}
-
-/* Filter out some columns that don't work well in metrics only mode */
-
-static bool valid_only_metric(const char *unit)
-{
-	if (!unit)
-		return false;
-	if (strstr(unit, "/sec") ||
-	    strstr(unit, "hz") ||
-	    strstr(unit, "Hz") ||
-	    strstr(unit, "CPUs utilized"))
-		return false;
-	return true;
-}
-
-static const char *fixunit(char *buf, struct perf_evsel *evsel,
-			   const char *unit)
-{
-	if (!strncmp(unit, "of all", 6)) {
-		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
-			 unit);
-		return buf;
-	}
-	return unit;
-}
-
-static void print_metric_only(void *ctx, const char *color, const char *fmt,
-			      const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[1024], str[1024];
-	unsigned mlen = metric_only_len;
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(buf, os->evsel, unit);
-	if (mlen < strlen(unit))
-		mlen = strlen(unit) + 1;
-
-	if (color)
-		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
-
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
-	fprintf(out, "%*s ", mlen, str);
-}
-
-static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
-				  const char *fmt,
-				  const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof buf, fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	fprintf(out, "%s%s", vals, csv_sep);
-}
-
-static void new_line_metric(void *ctx __maybe_unused)
-{
-}
-
-static void print_metric_header(void *ctx, const char *color __maybe_unused,
-				const char *fmt __maybe_unused,
-				const char *unit, double val __maybe_unused)
-{
-	struct outstate *os = ctx;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	if (csv_output)
-		fprintf(os->fh, "%s%s", unit, csv_sep);
-	else
-		fprintf(os->fh, "%*s ", metric_only_len, unit);
-}
-
-static int first_shadow_cpu(struct perf_evsel *evsel, int id)
-{
-	int i;
-
-	if (!aggr_get_id)
-		return 0;
-
-	if (stat_config.aggr_mode == AGGR_NONE)
-		return id;
-
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		return 0;
-
-	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
-		int cpu2 = perf_evsel__cpus(evsel)->map[i];
-
-		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
-			return cpu2;
-	}
-	return 0;
-}
-
-static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double sc =  evsel->scale;
-	const char *fmt;
-
-	if (csv_output) {
-		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
-	} else {
-		if (big_num)
-			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
-		else
-			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
-	}
-
-	aggr_printout(evsel, id, nr);
-
-	fprintf(output, fmt, avg, csv_sep);
-
-	if (evsel->unit)
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			evsel->unit, csv_sep);
-
-	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
-static bool is_mixed_hw_group(struct perf_evsel *counter)
-{
-	struct perf_evlist *evlist = counter->evlist;
-	u32 pmu_type = counter->attr.type;
-	struct perf_evsel *pos;
-
-	if (counter->nr_members < 2)
-		return false;
-
-	evlist__for_each_entry(evlist, pos) {
-		/* software events can be part of any hardware group */
-		if (pos->attr.type == PERF_TYPE_SOFTWARE)
-			continue;
-		if (pmu_type == PERF_TYPE_SOFTWARE) {
-			pmu_type = pos->attr.type;
-			continue;
-		}
-		if (pmu_type != pos->attr.type)
-			return true;
-	}
-
-	return false;
-}
-
-static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-		     char *prefix, u64 run, u64 ena, double noise,
-		     struct runtime_stat *st)
-{
-	struct perf_stat_output_ctx out;
-	struct outstate os = {
-		.fh = stat_config.output,
-		.prefix = prefix ? prefix : "",
-		.id = id,
-		.nr = nr,
-		.evsel = counter,
-	};
-	print_metric_t pm = print_metric_std;
-	void (*nl)(void *);
-
-	if (metric_only) {
-		nl = new_line_metric;
-		if (csv_output)
-			pm = print_metric_only_csv;
-		else
-			pm = print_metric_only;
-	} else
-		nl = new_line_std;
-
-	if (csv_output && !metric_only) {
-		static int aggr_fields[] = {
-			[AGGR_GLOBAL] = 0,
-			[AGGR_THREAD] = 1,
-			[AGGR_NONE] = 1,
-			[AGGR_SOCKET] = 2,
-			[AGGR_CORE] = 2,
-		};
-
-		pm = print_metric_csv;
-		nl = new_line_csv;
-		os.nfields = 3;
-		os.nfields += aggr_fields[stat_config.aggr_mode];
-		if (counter->cgrp)
-			os.nfields++;
-	}
-	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
-		if (metric_only) {
-			pm(&os, NULL, "", "", 0);
-			return;
-		}
-		aggr_printout(counter, id, nr);
-
-		fprintf(stat_config.output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-
-		if (counter->supported) {
-			print_free_counters_hint = 1;
-			if (is_mixed_hw_group(counter))
-				print_mixed_hw_group_error = 1;
-		}
-
-		fprintf(stat_config.output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-
-		fprintf(stat_config.output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(stat_config.output, "%s%s",
-				csv_sep, counter->cgrp->name);
-
-		if (!csv_output)
-			pm(&os, NULL, NULL, "", 0);
-		print_noise(counter, noise);
-		print_running(run, ena);
-		if (csv_output)
-			pm(&os, NULL, NULL, "", 0);
-		return;
-	}
-
-	if (!metric_only)
-		abs_printout(id, nr, counter, uval);
-
-	out.print_metric = pm;
-	out.new_line = nl;
-	out.ctx = &os;
-	out.force_header = false;
-
-	if (csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
-	}
-
-	perf_stat__print_shadow_stats(counter, uval,
-				first_shadow_cpu(counter, id),
-				&out, &metric_events, st);
-	if (!csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
-	}
-}
-
-static void aggr_update_shadow(void)
-{
-	int cpu, s2, id, s;
-	u64 val;
-	struct perf_evsel *counter;
-
-	for (s = 0; s < aggr_map->nr; s++) {
-		id = aggr_map->map[s];
-		evlist__for_each_entry(evsel_list, counter) {
-			val = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = aggr_get_id(evsel_list->cpus, cpu);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-			}
-			perf_stat__update_shadow_stats(counter, val,
-					first_shadow_cpu(counter, id),
-					&rt_stat);
-		}
-	}
-}
-
-static void uniquify_event_name(struct perf_evsel *counter)
-{
-	char *new_name;
-	char *config;
-
-	if (counter->uniquified_name ||
-	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
-					   strlen(counter->pmu_name)))
-		return;
-
-	config = strchr(counter->name, '/');
-	if (config) {
-		if (asprintf(&new_name,
-			     "%s%s", counter->pmu_name, config) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	} else {
-		if (asprintf(&new_name,
-			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	}
-
-	counter->uniquified_name = true;
-}
-
-static void collect_all_aliases(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	struct perf_evsel *alias;
-
-	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
-	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
-		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
-		    alias->scale != counter->scale ||
-		    alias->cgrp != counter->cgrp ||
-		    strcmp(alias->unit, counter->unit) ||
-		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
-			break;
-		alias->merged_stat = true;
-		cb(alias, data, false);
-	}
-}
-
-static bool collect_data(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	if (counter->merged_stat)
-		return false;
-	cb(counter, data, true);
-	if (no_merge)
-		uniquify_event_name(counter);
-	else if (counter->auto_merge_stats)
-		collect_all_aliases(counter, cb, data);
-	return true;
-}
-
-struct aggr_data {
-	u64 ena, run, val;
-	int id;
-	int nr;
-	int cpu;
-};
-
-static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
-{
-	struct aggr_data *ad = data;
-	int cpu, s2;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct perf_counts_values *counts;
-
-		s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
-		if (s2 != ad->id)
-			continue;
-		if (first)
-			ad->nr++;
-		counts = perf_counts(counter->counts, cpu, 0);
-		/*
-		 * When any result is bad, make them all to give
-		 * consistent output in interval mode.
-		 */
-		if (counts->ena == 0 || counts->run == 0 ||
-		    counter->counts->scaled == -1) {
-			ad->ena = 0;
-			ad->run = 0;
-			break;
-		}
-		ad->val += counts->val;
-		ad->ena += counts->ena;
-		ad->run += counts->run;
-	}
-}
-
-static void print_aggr(char *prefix)
-{
-	FILE *output = stat_config.output;
-	struct perf_evsel *counter;
-	int s, id, nr;
-	double uval;
-	u64 ena, run, val;
-	bool first;
-
-	if (!(aggr_map || aggr_get_id))
-		return;
-
-	aggr_update_shadow();
-
-	/*
-	 * With metric_only everything is on a single line.
-	 * Without each counter has its own line.
-	 */
-	for (s = 0; s < aggr_map->nr; s++) {
-		struct aggr_data ad;
-		if (prefix && metric_only)
-			fprintf(output, "%s", prefix);
-
-		ad.id = id = aggr_map->map[s];
-		first = true;
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-
-			ad.val = ad.ena = ad.run = 0;
-			ad.nr = 0;
-			if (!collect_data(counter, aggr_cb, &ad))
-				continue;
-			nr = ad.nr;
-			ena = ad.ena;
-			run = ad.run;
-			val = ad.val;
-			if (first && metric_only) {
-				first = false;
-				aggr_printout(counter, id, nr);
-			}
-			if (prefix && !metric_only)
-				fprintf(output, "%s", prefix);
-
-			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
-			if (!metric_only)
-				fputc('\n', output);
-		}
-		if (metric_only)
-			fputc('\n', output);
-	}
-}
-
-static int cmp_val(const void *a, const void *b)
-{
-	return ((struct perf_aggr_thread_value *)b)->val -
-		((struct perf_aggr_thread_value *)a)->val;
-}
-
-static struct perf_aggr_thread_value *sort_aggr_thread(
-					struct perf_evsel *counter,
-					int nthreads, int ncpus,
-					int *ret)
-{
-	int cpu, thread, i = 0;
-	double uval;
-	struct perf_aggr_thread_value *buf;
-
-	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
-	if (!buf)
-		return NULL;
-
-	for (thread = 0; thread < nthreads; thread++) {
-		u64 ena = 0, run = 0, val = 0;
-
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			val += perf_counts(counter->counts, cpu, thread)->val;
-			ena += perf_counts(counter->counts, cpu, thread)->ena;
-			run += perf_counts(counter->counts, cpu, thread)->run;
-		}
-
-		uval = val * counter->scale;
-
-		/*
-		 * Skip value 0 when enabling --per-thread globally,
-		 * otherwise too many 0 output.
-		 */
-		if (uval == 0.0 && target__has_per_thread(&target))
-			continue;
-
-		buf[i].counter = counter;
-		buf[i].id = thread;
-		buf[i].uval = uval;
-		buf[i].val = val;
-		buf[i].run = run;
-		buf[i].ena = ena;
-		i++;
-	}
-
-	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
-
-	if (ret)
-		*ret = i;
-
-	return buf;
-}
-
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	int nthreads = thread_map__nr(counter->threads);
-	int ncpus = cpu_map__nr(counter->cpus);
-	int thread, sorted_threads, id;
-	struct perf_aggr_thread_value *buf;
-
-	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
-	if (!buf) {
-		perror("cannot sort aggr thread");
-		return;
-	}
-
-	for (thread = 0; thread < sorted_threads; thread++) {
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		id = buf[thread].id;
-		if (stat_config.stats)
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &stat_config.stats[id]);
-		else
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &rt_stat);
-		fputc('\n', output);
-	}
-
-	free(buf);
-}
-
-struct caggr_data {
-	double avg, avg_enabled, avg_running;
-};
-
-static void counter_aggr_cb(struct perf_evsel *counter, void *data,
-			    bool first __maybe_unused)
-{
-	struct caggr_data *cd = data;
-	struct perf_stat_evsel *ps = counter->stats;
-
-	cd->avg += avg_stats(&ps->res_stats[0]);
-	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
-	cd->avg_running += avg_stats(&ps->res_stats[2]);
-}
-
-/*
- * Print out the results of a single counter:
- * aggregated counts in system-wide mode
- */
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	double uval;
-	struct caggr_data cd = { .avg = 0.0 };
-
-	if (!collect_data(counter, counter_aggr_cb, &cd))
-		return;
-
-	if (prefix && !metric_only)
-		fprintf(output, "%s", prefix);
-
-	uval = cd.avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
-		 cd.avg, &rt_stat);
-	if (!metric_only)
-		fprintf(output, "\n");
-}
-
-static void counter_cb(struct perf_evsel *counter, void *data,
-		       bool first __maybe_unused)
-{
-	struct aggr_data *ad = data;
-
-	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
-	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
-	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
-}
-
-/*
- * Print out the results of a single counter:
- * does not use aggregated count in system-wide
- */
-static void print_counter(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	u64 ena, run, val;
-	double uval;
-	int cpu;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct aggr_data ad = { .cpu = cpu };
-
-		if (!collect_data(counter, counter_cb, &ad))
-			return;
-		val = ad.val;
-		ena = ad.ena;
-		run = ad.run;
-
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
-			 &rt_stat);
-
-		fputc('\n', output);
-	}
-}
-
-static void print_no_aggr_metric(char *prefix)
-{
-	int cpu;
-	int nrcpus = 0;
-	struct perf_evsel *counter;
-	u64 ena, run, val;
-	double uval;
-
-	nrcpus = evsel_list->cpus->nr;
-	for (cpu = 0; cpu < nrcpus; cpu++) {
-		bool first = true;
-
-		if (prefix)
-			fputs(prefix, stat_config.output);
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			if (first) {
-				aggr_printout(counter, cpu, 0);
-				first = false;
-			}
-			val = perf_counts(counter->counts, cpu, 0)->val;
-			ena = perf_counts(counter->counts, cpu, 0)->ena;
-			run = perf_counts(counter->counts, cpu, 0)->run;
-
-			uval = val * counter->scale;
-			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
-		}
-		fputc('\n', stat_config.output);
-	}
-}
-
-static int aggr_header_lens[] = {
-	[AGGR_CORE] = 18,
-	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 6,
-	[AGGR_THREAD] = 24,
-	[AGGR_GLOBAL] = 0,
-};
-
-static const char *aggr_header_csv[] = {
-	[AGGR_CORE] 	= 	"core,cpus,",
-	[AGGR_SOCKET] 	= 	"socket,cpus",
-	[AGGR_NONE] 	= 	"cpu,",
-	[AGGR_THREAD] 	= 	"comm-pid,",
-	[AGGR_GLOBAL] 	=	""
-};
-
-static void print_metric_headers(const char *prefix, bool no_indent)
-{
-	struct perf_stat_output_ctx out;
-	struct perf_evsel *counter;
-	struct outstate os = {
-		.fh = stat_config.output
-	};
-
-	if (prefix)
-		fprintf(stat_config.output, "%s", prefix);
-
-	if (!csv_output && !no_indent)
-		fprintf(stat_config.output, "%*s",
-			aggr_header_lens[stat_config.aggr_mode], "");
-	if (csv_output) {
-		if (stat_config.interval)
-			fputs("time,", stat_config.output);
-		fputs(aggr_header_csv[stat_config.aggr_mode],
-			stat_config.output);
-	}
-
-	/* Print metrics headers only */
-	evlist__for_each_entry(evsel_list, counter) {
-		if (is_duration_time(counter))
-			continue;
-		os.evsel = counter;
-		out.ctx = &os;
-		out.print_metric = print_metric_header;
-		out.new_line = new_line_metric;
-		out.force_header = true;
-		os.evsel = counter;
-		perf_stat__print_shadow_stats(counter, 0,
-					      0,
-					      &out,
-					      &metric_events,
-					      &rt_stat);
-	}
-	fputc('\n', stat_config.output);
-}
-
-static void print_interval(char *prefix, struct timespec *ts)
-{
-	FILE *output = stat_config.output;
-	static int num_print_interval;
-
-	if (interval_clear)
-		puts(CONSOLE_CLEAR);
-
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
-
-	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
-		switch (stat_config.aggr_mode) {
-		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			fprintf(output, "#           time CPU    ");
-			if (!metric_only)
-				fprintf(output, "                counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_THREAD:
-			fprintf(output, "#           time             comm-pid");
-			if (!metric_only)
-				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-		case AGGR_UNSET:
-			break;
-		}
-	}
-
-	if ((num_print_interval == 0 || interval_clear) && metric_only)
-		print_metric_headers(" ", true);
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
-}
-
-static void print_header(int argc, const char **argv)
-{
-	FILE *output = stat_config.output;
-	int i;
-
-	fflush(stdout);
-
-	if (!csv_output) {
-		fprintf(output, "\n");
-		fprintf(output, " Performance counter stats for ");
-		if (target.system_wide)
-			fprintf(output, "\'system wide");
-		else if (target.cpu_list)
-			fprintf(output, "\'CPU(s) %s", target.cpu_list);
-		else if (!target__has_task(&target)) {
-			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
-			for (i = 1; argv && (i < argc); i++)
-				fprintf(output, " %s", argv[i]);
-		} else if (target.pid)
-			fprintf(output, "process id \'%s", target.pid);
-		else
-			fprintf(output, "thread id \'%s", target.tid);
-
-		fprintf(output, "\'");
-		if (run_count > 1)
-			fprintf(output, " (%d runs)", run_count);
-		fprintf(output, ":\n\n");
-	}
-}
-
-static int get_precision(double num)
-{
-	if (num > 1)
-		return 0;
-
-	return lround(ceil(-log10(num)));
-}
-
-static void print_table(FILE *output, int precision, double avg)
-{
-	char tmp[64];
-	int idx, indent = 0;
-
-	scnprintf(tmp, 64, " %17.*f", precision, avg);
-	while (tmp[indent] == ' ')
-		indent++;
-
-	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
-
-	for (idx = 0; idx < run_count; idx++) {
-		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
-		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
-
-		fprintf(output, " %17.*f (%+.*f) ",
-			precision, run, precision, run - avg);
-
-		for (h = 0; h < n; h++)
-			fprintf(output, "#");
-
-		fprintf(output, "\n");
-	}
-
-	fprintf(output, "\n%*s# Final result:\n", indent, "");
-}
-
-static double timeval2double(struct timeval *t)
-{
-	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
-}
-
-static void print_footer(void)
-{
-	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
-	FILE *output = stat_config.output;
-	int n;
-
-	if (!null_run)
-		fprintf(output, "\n");
-
-	if (run_count == 1) {
-		fprintf(output, " %17.9f seconds time elapsed", avg);
-
-		if (ru_display) {
-			double ru_utime = timeval2double(&ru_data.ru_utime);
-			double ru_stime = timeval2double(&ru_data.ru_stime);
-
-			fprintf(output, "\n\n");
-			fprintf(output, " %17.9f seconds user\n", ru_utime);
-			fprintf(output, " %17.9f seconds sys\n", ru_stime);
-		}
-	} else {
-		double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
-		/*
-		 * Display at most 2 more significant
-		 * digits than the stddev inaccuracy.
-		 */
-		int precision = get_precision(sd) + 2;
-
-		if (walltime_run_table)
-			print_table(output, precision, avg);
-
-		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
-			precision, avg, precision, sd);
-
-		print_noise_pct(sd, avg);
-	}
-	fprintf(output, "\n\n");
-
-	if (print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
-		fprintf(output,
-"Some events weren't counted. Try disabling the NMI watchdog:\n"
-"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
-"	perf stat ...\n"
-"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
-
-	if (print_mixed_hw_group_error)
-		fprintf(output,
-			"The events in group usually have to be from "
-			"the same PMU. Try reorganizing the group.\n");
-}
-
 static void print_counters(struct timespec *ts, int argc, const char **argv)
 {
-	int interval = stat_config.interval;
-	struct perf_evsel *counter;
-	char buf[64], *prefix = NULL;
-
 	/* Do not print anything if we record to the pipe. */
 	if (STAT_RECORD && perf_stat.data.is_pipe)
 		return;
 
-	if (interval)
-		print_interval(prefix = buf, ts);
-	else
-		print_header(argc, argv);
-
-	if (metric_only) {
-		static int num_print_iv;
-
-		if (num_print_iv == 0 && !interval)
-			print_metric_headers(prefix, false);
-		if (num_print_iv++ == 25)
-			num_print_iv = 0;
-		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
-			fprintf(stat_config.output, "%s", prefix);
-	}
-
-	switch (stat_config.aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(prefix);
-		break;
-	case AGGR_THREAD:
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_aggr_thread(counter, prefix);
-		}
-		break;
-	case AGGR_GLOBAL:
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_counter_aggr(counter, prefix);
-		}
-		if (metric_only)
-			fputc('\n', stat_config.output);
-		break;
-	case AGGR_NONE:
-		if (metric_only)
-			print_no_aggr_metric(prefix);
-		else {
-			evlist__for_each_entry(evsel_list, counter) {
-				if (is_duration_time(counter))
-					continue;
-				print_counter(counter, prefix);
-			}
-		}
-		break;
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-
-	if (!interval && !csv_output)
-		print_footer();
-
-	fflush(stat_config.output);
+	perf_evlist__print_counters(evsel_list, &stat_config, &target,
+				    ts, argc, argv);
 }
 
 static volatile int signr = -1;
@@ -1950,7 +700,7 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
 			      const char *s __maybe_unused, int unset)
 {
 	force_metric_only = true;
-	metric_only = !unset;
+	stat_config.metric_only = !unset;
 	return 0;
 }
 
@@ -1958,7 +708,7 @@ static int parse_metric_groups(const struct option *opt,
 			       const char *str,
 			       int unset __maybe_unused)
 {
-	return metricgroup__parse_groups(opt, str, &metric_events);
+	return metricgroup__parse_groups(opt, str, &stat_config.metric_events);
 }
 
 static const struct option stat_options[] = {
@@ -1969,7 +719,7 @@ static const struct option stat_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+	OPT_BOOLEAN('i', "no-inherit", &stat_config.no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_STRING('p', "pid", &target.pid, "pid",
 		   "stat events on existing process id"),
@@ -1982,11 +732,11 @@ static const struct option stat_options[] = {
 	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
+	OPT_INTEGER('r', "repeat", &stat_config.run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN(0, "table", &walltime_run_table,
+	OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table,
 		    "display details about each run (only with -r option)"),
-	OPT_BOOLEAN('n', "null", &null_run,
+	OPT_BOOLEAN('n', "null", &stat_config.null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
 		    "detailed run - start a lot of events"),
@@ -1999,8 +749,8 @@ static const struct option stat_options[] = {
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
+	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
 		     "monitor event in cgroup name only", parse_cgroups),
@@ -2017,7 +767,7 @@ static const struct option stat_options[] = {
 		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
-	OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+	OPT_BOOLEAN(0, "interval-clear", &stat_config.interval_clear,
 		    "clear screen in between new interval"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
 		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
@@ -2027,9 +777,9 @@ static const struct option stat_options[] = {
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
 		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
+	OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
 		     "ms to wait before starting measurement after program start"),
-	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure topdown level 1 statistics"),
@@ -2041,12 +791,14 @@ static const struct option stat_options[] = {
 	OPT_END()
 };
 
-static int perf_stat__get_socket(struct cpu_map *map, int cpu)
+static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
+				 struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
 }
 
-static int perf_stat__get_core(struct cpu_map *map, int cpu)
+static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
+			       struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_core(map, cpu, NULL);
 }
@@ -2063,9 +815,8 @@ static int cpu_map__get_max(struct cpu_map *map)
 	return max;
 }
 
-static struct cpu_map *cpus_aggr_map;
-
-static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+static int perf_stat__get_aggr(struct perf_stat_config *config,
+			       aggr_get_id_t get_id, struct cpu_map *map, int idx)
 {
 	int cpu;
 
@@ -2074,20 +825,22 @@ static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int id
 
 	cpu = map->map[idx];
 
-	if (cpus_aggr_map->map[cpu] == -1)
-		cpus_aggr_map->map[cpu] = get_id(map, idx);
+	if (config->cpus_aggr_map->map[cpu] == -1)
+		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
 
-	return cpus_aggr_map->map[cpu];
+	return config->cpus_aggr_map->map[cpu];
 }
 
-static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_cached(struct perf_stat_config *config,
+					struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
 }
 
-static int perf_stat__get_core_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_core_cached(struct perf_stat_config *config,
+				      struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_core, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
 }
 
 static int perf_stat_init_aggr_mode(void)
@@ -2096,18 +849,18 @@ static int perf_stat_init_aggr_mode(void)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_socket_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_cached;
+		stat_config.aggr_get_id = perf_stat__get_socket_cached;
 		break;
 	case AGGR_CORE:
-		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_cached;
+		stat_config.aggr_get_id = perf_stat__get_core_cached;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -2123,16 +876,16 @@ static int perf_stat_init_aggr_mode(void)
 	 * the aggregation translate cpumap.
 	 */
 	nr = cpu_map__get_max(evsel_list->cpus);
-	cpus_aggr_map = cpu_map__empty_new(nr + 1);
-	return cpus_aggr_map ? 0 : -ENOMEM;
+	stat_config.cpus_aggr_map = cpu_map__empty_new(nr + 1);
+	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
 
 static void perf_stat__exit_aggr_mode(void)
 {
-	cpu_map__put(aggr_map);
-	cpu_map__put(cpus_aggr_map);
-	aggr_map = NULL;
-	cpus_aggr_map = NULL;
+	cpu_map__put(stat_config.aggr_map);
+	cpu_map__put(stat_config.cpus_aggr_map);
+	stat_config.aggr_map = NULL;
+	stat_config.cpus_aggr_map = NULL;
 }
 
 static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
@@ -2190,12 +943,14 @@ static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
 	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
 }
 
-static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
+				      struct cpu_map *map, int idx)
 {
 	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
 }
 
-static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
+				    struct cpu_map *map, int idx)
 {
 	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
 }
@@ -2206,18 +961,18 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_socket_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_file;
+		stat_config.aggr_get_id = perf_stat__get_socket_file;
 		break;
 	case AGGR_CORE:
-		if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_file;
+		stat_config.aggr_get_id = perf_stat__get_core_file;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -2401,7 +1156,7 @@ static int add_default_attributes(void)
 	struct parse_events_error errinfo;
 
 	/* Set attrs if no event is selected and !null_run: */
-	if (null_run)
+	if (stat_config.null_run)
 		return 0;
 
 	if (transaction_run) {
@@ -2414,7 +1169,7 @@ static int add_default_attributes(void)
 			struct option opt = { .value = &evsel_list };
 
 			return metricgroup__parse_groups(&opt, "transaction",
-							 &metric_events);
+							 &stat_config.metric_events);
 		}
 
 		if (pmu_have_event("cpu", "cycles-ct") &&
@@ -2452,7 +1207,7 @@ static int add_default_attributes(void)
 		if (pmu_have_event("msr", "aperf") &&
 		    pmu_have_event("msr", "smi")) {
 			if (!force_metric_only)
-				metric_only = true;
+				stat_config.metric_only = true;
 			err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
 		} else {
 			fprintf(stderr, "To measure SMI cost, it needs "
@@ -2483,7 +1238,7 @@ static int add_default_attributes(void)
 		}
 
 		if (!force_metric_only)
-			metric_only = true;
+			stat_config.metric_only = true;
 		if (topdown_filter_events(topdown_attrs, &str,
 				arch_topdown_check_group(&warn)) < 0) {
 			pr_err("Out of memory\n");
@@ -2580,7 +1335,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (output_name)
 		data->file.path = output_name;
 
-	if (run_count != 1 || forever) {
+	if (stat_config.run_count != 1 || forever) {
 		pr_err("Cannot use -r option with perf stat record.\n");
 		return -1;
 	}
@@ -2853,12 +1608,12 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__collect_metric_expr(evsel_list);
 	perf_stat__init_shadow_stats();
 
-	if (csv_sep) {
-		csv_output = true;
-		if (!strcmp(csv_sep, "\\t"))
-			csv_sep = "\t";
+	if (stat_config.csv_sep) {
+		stat_config.csv_output = true;
+		if (!strcmp(stat_config.csv_sep, "\\t"))
+			stat_config.csv_sep = "\t";
 	} else
-		csv_sep = DEFAULT_SEPARATOR;
+		stat_config.csv_sep = DEFAULT_SEPARATOR;
 
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = __cmd_record(argc, argv);
@@ -2883,17 +1638,17 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+	if (stat_config.metric_only && stat_config.aggr_mode == AGGR_THREAD) {
 		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
 		goto out;
 	}
 
-	if (metric_only && run_count > 1) {
+	if (stat_config.metric_only && stat_config.run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
 	}
 
-	if (walltime_run_table && run_count <= 1) {
+	if (stat_config.walltime_run_table && stat_config.run_count <= 1) {
 		fprintf(stderr, "--table is only supported with -r\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		parse_options_usage(NULL, stat_options, "table", 0);
@@ -2931,7 +1686,7 @@ int cmd_stat(int argc, const char **argv)
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
-	if (csv_output) {
+	if (stat_config.csv_output) {
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
@@ -2939,9 +1694,9 @@ int cmd_stat(int argc, const char **argv)
 			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
-			big_num = false;
+			stat_config.big_num = false;
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
-		big_num = false;
+		stat_config.big_num = false;
 
 	setup_system_wide(argc);
 
@@ -2949,21 +1704,21 @@ int cmd_stat(int argc, const char **argv)
 	 * Display user/system times only for single
 	 * run and when there's specified tracee.
 	 */
-	if ((run_count == 1) && target__none(&target))
-		ru_display = true;
+	if ((stat_config.run_count == 1) && target__none(&target))
+		stat_config.ru_display = true;
 
-	if (run_count < 0) {
+	if (stat_config.run_count < 0) {
 		pr_err("Run count must be a positive number\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
-	} else if (run_count == 0) {
+	} else if (stat_config.run_count == 0) {
 		forever = true;
-		run_count = 1;
+		stat_config.run_count = 1;
 	}
 
-	if (walltime_run_table) {
-		walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
-		if (!walltime_run) {
+	if (stat_config.walltime_run_table) {
+		stat_config.walltime_run = zalloc(stat_config.run_count * sizeof(stat_config.walltime_run[0]));
+		if (!stat_config.walltime_run) {
 			pr_err("failed to setup -r option");
 			goto out;
 		}
@@ -3066,6 +1821,17 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 
 	/*
+	 * Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+	 * while avoiding that older tools show confusing messages.
+	 *
+	 * However for pipe sessions we need to keep it zero,
+	 * because script's perf_evsel__check_attr is triggered
+	 * by attr->sample_type != 0, and we can't run it on
+	 * stat sessions.
+	 */
+	stat_config.identifier = !(STAT_RECORD && perf_stat.data.is_pipe);
+
+	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
 	 * What we want is for Ctrl-C to work in the exec()-ed
@@ -3079,8 +1845,8 @@ int cmd_stat(int argc, const char **argv)
 	signal(SIGABRT, skip_signal);
 
 	status = 0;
-	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-		if (run_count != 1 && verbose > 0)
+	for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
+		if (stat_config.run_count != 1 && verbose > 0)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
@@ -3132,7 +1898,7 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
-	free(walltime_run);
+	free(stat_config.walltime_run);
 
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 22ab8e67c760..7ce277d22a91 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -288,6 +288,13 @@ static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
 	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
 }
 
+static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv;
+
+	return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
+}
+
 static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
 {
 	evsel->priv = malloc(sizeof(struct syscall_tp));
@@ -498,16 +505,6 @@ static const char *clockid[] = {
 };
 static DEFINE_STRARRAY(clockid);
 
-static const char *socket_families[] = {
-	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
-	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
-	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
-	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
-	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
-	"ALG", "NFC", "VSOCK",
-};
-static DEFINE_STRARRAY(socket_families);
-
 static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
 						 struct syscall_arg *arg)
 {
@@ -631,6 +628,8 @@ static struct syscall_fmt {
 } syscall_fmts[] = {
 	{ .name	    = "access",
 	  .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
+	{ .name	    = "bind",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
 	{ .name	    = "bpf",
 	  .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
 	{ .name	    = "brk",	    .hexret = true,
@@ -645,6 +644,8 @@ static struct syscall_fmt {
 		   [4] = { .name = "tls",	    .scnprintf = SCA_HEX, }, }, },
 	{ .name	    = "close",
 	  .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+	{ .name	    = "connect",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
 	{ .name	    = "epoll_ctl",
 	  .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
 	{ .name	    = "eventfd2",
@@ -801,7 +802,8 @@ static struct syscall_fmt {
 	{ .name	    = "sendmsg",
 	  .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
 	{ .name	    = "sendto",
-	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
+		   [4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
 	  .arg = { [0] = STRARRAY(which, itimers), }, },
@@ -830,6 +832,7 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+	{ .name     = "umount2", .alias = "umount", },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@@ -856,10 +859,12 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 /*
  * 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.
+ * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
 	struct event_format *tp_format;
 	int		    nr_args;
+	int		    args_size;
 	bool		    is_exit;
 	bool		    is_open;
 	struct format_field *args;
@@ -1095,11 +1100,21 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf,
 	ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
 }
 
+static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct augmented_arg *augmented_arg = arg->augmented.args;
+
+	return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
+}
+
 static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
 					      struct syscall_arg *arg)
 {
 	unsigned long ptr = arg->val;
 
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_string(arg, bf, size);
+
 	if (!arg->trace->vfs_getname)
 		return scnprintf(bf, size, "%#x", ptr);
 
@@ -1142,11 +1157,9 @@ static void sig_handler(int sig)
 	interrupted = sig == SIGINT;
 }
 
-static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
 {
-	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
-	printed += fprintf_duration(duration, duration_calculated, fp);
+	size_t printed = 0;
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
@@ -1157,6 +1170,14 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	return printed;
 }
 
+static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
+					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+{
+	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
+	printed += fprintf_duration(duration, duration_calculated, fp);
+	return printed + trace__fprintf_comm_tid(trace, thread, fp);
+}
+
 static int trace__process_event(struct trace *trace, struct machine *machine,
 				union perf_event *event, struct perf_sample *sample)
 {
@@ -1258,10 +1279,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	struct format_field *field;
+	struct format_field *field, *last_field = NULL;
 	int idx = 0, len;
 
 	for (field = sc->args; field; field = field->next, ++idx) {
+		last_field = field;
+
 		if (sc->fmt && sc->fmt->arg[idx].scnprintf)
 			continue;
 
@@ -1292,6 +1315,9 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 		}
 	}
 
+	if (last_field)
+		sc->args_size = last_field->offset + last_field->size;
+
 	return 0;
 }
 
@@ -1472,14 +1498,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 }
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
-				      unsigned char *args, struct trace *trace,
-				      struct thread *thread)
+				      unsigned char *args, void *augmented_args, int augmented_args_size,
+				      struct trace *trace, struct thread *thread)
 {
 	size_t printed = 0;
 	unsigned long val;
 	u8 bit = 1;
 	struct syscall_arg arg = {
 		.args	= args,
+		.augmented = {
+			.size = augmented_args_size,
+			.args = augmented_args,
+		},
 		.idx	= 0,
 		.mask	= 0,
 		.trace  = trace,
@@ -1654,6 +1684,17 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+{
+	void *augmented_args = NULL;
+
+	*augmented_args_size = sample->raw_size - sc->args_size;
+	if (*augmented_args_size > 0)
+		augmented_args = sample->raw_data + sc->args_size;
+
+	return augmented_args;
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
@@ -1663,6 +1704,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	size_t printed = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+	int augmented_args_size = 0;
+	void *augmented_args = NULL;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1686,13 +1729,24 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
 		trace__printf_interrupted_entry(trace);
-
+	/*
+	 * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
+	 * arguments, even if the syscall being handled, say "openat", uses only 4 arguments
+	 * this breaks syscall__augmented_args() check for augmented args, as we calculate
+	 * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
+	 * so when handling, say the openat syscall, we end up getting 6 args for the
+	 * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
+	 * thinking that the extra 2 u64 args are the augmented filename, so just check
+	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
+	 */
+	if (evsel != trace->syscalls.events.sys_enter)
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
 
 	printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
-					   args, trace, thread);
+					   args, augmented_args, augmented_args_size, trace, thread);
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
@@ -1723,7 +1777,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 	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;
+	void *args, *augmented_args = NULL;
+	int augmented_args_size;
 
 	if (sc == NULL)
 		return -1;
@@ -1738,7 +1793,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
 out_put:
@@ -2022,6 +2078,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
+	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	int callchain_ret = 0;
 
 	if (sample->callchain) {
@@ -2039,13 +2096,31 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->trace_syscalls)
 		fprintf(trace->output, "(         ): ");
 
+	if (thread)
+		trace__fprintf_comm_tid(trace, thread, trace->output);
+
+	if (evsel == trace->syscalls.events.augmented) {
+		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+		struct syscall *sc = trace__syscall_info(trace, evsel, id);
+
+		if (sc) {
+			fprintf(trace->output, "%s(", sc->name);
+			trace__fprintf_sys_enter(trace, evsel, sample);
+			fputc(')', trace->output);
+			goto newline;
+		}
+
+		/*
+		 * XXX: Not having the associated syscall info or not finding/adding
+		 * 	the thread should never happen, but if it does...
+		 * 	fall thru and print it as a bpf_output event.
+		 */
+	}
+
 	fprintf(trace->output, "%s:", evsel->name);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		if (evsel == trace->syscalls.events.augmented)
-			trace__fprintf_sys_enter(trace, evsel, sample);
-		else
-			bpf_output__fprintf(trace, sample);
+		bpf_output__fprintf(trace, sample);
 	} else if (evsel->tp_format) {
 		if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
 		    trace__fprintf_sys_enter(trace, evsel, sample)) {
@@ -2055,12 +2130,14 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
+newline:
 	fprintf(trace->output, "\n");
 
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+	thread__put(thread);
 out:
 	return 0;
 }
@@ -3276,12 +3353,8 @@ int cmd_trace(int argc, const char **argv)
 		goto out;
 	}
 
-	if (evsel) {
-		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
-		    perf_evsel__init_augmented_syscall_tp_args(evsel))
-			goto out;
+	if (evsel)
 		trace.syscalls.events.augmented = evsel;
-	}
 
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
@@ -3326,6 +3399,34 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
+	/*
+	 * If we are augmenting syscalls, then combine what we put in the
+	 * __augmented_syscalls__ BPF map with what is in the
+	 * syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
+	 * combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
+	 *
+	 * We'll switch to look at two BPF maps, one for sys_enter and the
+	 * other for sys_exit when we start augmenting the sys_exit paths with
+	 * buffers that are being copied from kernel to userspace, think 'read'
+	 * syscall.
+	 */
+	if (trace.syscalls.events.augmented) {
+		evsel = trace.syscalls.events.augmented;
+
+		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+		    perf_evsel__init_augmented_syscall_tp_args(evsel))
+			goto out;
+		evsel->handler = trace__sys_enter;
+
+		evlist__for_each_entry(trace.evlist, evsel) {
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+				perf_evsel__init_augmented_syscall_tp(evsel);
+				perf_evsel__init_augmented_syscall_tp_ret(evsel);
+				evsel->handler = trace__sys_exit;
+			}
+		}
+	}
+
 	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
 		return trace__record(&trace, argc-1, &argv[1]);
 
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 69a31386d8cd..2ae44813ef2d 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Augment the openat syscall with the contents of the filename pointer argument.
+ * Augment syscalls with the contents of the pointer arguments.
  *
  * Test it with:
  *
@@ -10,15 +10,14 @@
  * 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.
+ * expected by the 'perf trace' beautifiers, and can be used by them, that will
+ * check if perf_sample->raw_data is more than what is expected for each
+ * syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
+ * contents of pointer arguments.
  */
 
 #include <stdio.h>
+#include <linux/socket.h>
 
 struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
@@ -27,6 +26,44 @@ struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .max_entries = __NR_CPUS__,
 };
 
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define augmented_filename_syscall(syscall)							\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	unsigned int len = sizeof(augmented_args);						\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {		\
+		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\
+		len &= sizeof(augmented_args.filename.value) - 1;				\
+	}											\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, len);						\
+	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
+}
+
 struct syscall_enter_openat_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
@@ -36,20 +73,101 @@ struct syscall_enter_openat_args {
 	long		   mode;
 };
 
-struct augmented_enter_openat_args {
-	struct syscall_enter_openat_args args;
-	char				 filename[64];
+augmented_filename_syscall(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall(open);
+
+struct syscall_enter_inotify_add_watch_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	char		   *filename_ptr;
+	long		   mask;
+};
+
+augmented_filename_syscall(inotify_add_watch);
+
+struct statbuf;
+
+struct syscall_enter_newstat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	struct stat	   *statbuf;
 };
 
-int syscall_enter(openat)(struct syscall_enter_openat_args *args)
-{
-	struct augmented_enter_openat_args augmented_args;
+augmented_filename_syscall(newstat);
+
+#ifndef _K_SS_MAXSIZE
+#define _K_SS_MAXSIZE 128
+#endif
 
-	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;
+#define augmented_sockaddr_syscall(syscall)						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct sockaddr_storage			addr;						\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args;				 	\
+	unsigned long addrlen = sizeof(augmented_args.addr);					\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */		\
+/*	if (addrlen > augmented_args.args.addrlen)				     */		\
+/*		addrlen = augmented_args.args.addrlen;				     */		\
+/*										     */		\
+	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 				\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);	\
+	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
 }
 
+struct sockaddr;
+
+struct syscall_enter_bind_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+augmented_sockaddr_syscall(bind);
+
+struct syscall_enter_connect_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+augmented_sockaddr_syscall(connect);
+
+struct syscall_enter_sendto_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	void		   *buff;
+	long		   len;
+	unsigned long	   flags;
+	struct sockaddr	   *addr_ptr;
+	long		   addr_len;
+};
+
+augmented_sockaddr_syscall(sendto);
+
 license(GPL);
diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c
new file mode 100644
index 000000000000..b59e8812ee8c
--- /dev/null
+++ b/tools/perf/examples/bpf/etcsnoop.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the filename syscalls with the contents of the filename pointer argument
+ * filtering only those that do not start with /etc/.
+ *
+ * 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 augmented_filename {
+	int	size;
+	int	reserved;
+	char	value[64];
+};
+
+#define augmented_filename_syscall_enter(syscall) 						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	char etc[6] = "/etc/";									\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0)			\
+		return 0;									\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
+			   augmented_args.filename.size));					\
+	return 0;										\
+}
+
+struct syscall_enter_openat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(open);
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index 47897d65e799..52b6d87fe822 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -26,6 +26,9 @@ struct bpf_map {
 #define syscall_enter(name) \
 	SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
 
+#define syscall_exit(name) \
+	SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
+
 #define license(name) \
 char _license[] SEC("license") = #name; \
 int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/include/bpf/linux/socket.h b/tools/perf/include/bpf/linux/socket.h
new file mode 100644
index 000000000000..7f844568dab8
--- /dev/null
+++ b/tools/perf/include/bpf/linux/socket.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SOCKET_H
+#define _UAPI_LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE	128	/* Implementation specific max size */
+#define _K_SS_ALIGNSIZE	(__alignof__ (struct sockaddr *))
+				/* Implementation specific desired alignment */
+
+typedef unsigned short __kernel_sa_family_t;
+
+struct __kernel_sockaddr_storage {
+	__kernel_sa_family_t	ss_family;		/* address family */
+	/* Following field(s) are implementation specific */
+	char		__data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+				/* space to achieve desired size, */
+				/* _SS_MAXSIZE value minus size of ss_family */
+} __attribute__ ((aligned(_K_SS_ALIGNSIZE)));	/* force desired alignment */
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+#endif /* _UAPI_LINUX_SOCKET_H */
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 3013ac8f83d0..cab7b0aea6ea 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -48,7 +48,7 @@ trace_libc_inet_pton_backtrace() {
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
-		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index f528ba35e140..c3b0afd67760 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,5 +7,6 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += sockaddr.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 9615af5d412b..2570152d3909 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -30,9 +30,36 @@ struct thread;
 
 size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
 
+extern struct strarray strarray__socket_families;
+
+/**
+ * augmented_arg: extra payload for syscall pointer arguments
+ 
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
+ * then its the arguments contents, so that we can show more than just a
+ * pointer. This will be done initially with eBPF, the start of that is at the
+ * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
+ * will eventually be done automagically caching the running kernel tracefs
+ * events data into an eBPF C script, that then gets compiled and its .o file
+ * cached for subsequent use. For char pointers like the ones for 'open' like
+ * syscalls its easy, for the rest we should use DWARF or better, BTF, much
+ * more compact.
+ *
+ * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
+ * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
+ * @value: u64 aligned, for structs, pathnames
+ */
+struct augmented_arg {
+	int  size;
+	int  int_arg;
+	u64  value[];
+};
+
 /**
  * @val: value of syscall argument being formatted
  * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
+ * @augmented_args_size: augmented_args total payload size
  * @thread: tid state (maps, pid, tid, etc)
  * @trace: 'perf trace' internals: all threads, etc
  * @parm: private area, may be an strarray, for instance
@@ -43,6 +70,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
 struct syscall_arg {
 	unsigned long val;
 	unsigned char *args;
+	struct {
+		struct augmented_arg *args;
+		int		     size;
+	} augmented;
 	struct thread *thread;
 	struct trace  *trace;
 	void	      *parm;
@@ -106,6 +137,9 @@ 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_sockaddr(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr
+
 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
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
new file mode 100644
index 000000000000..71a79f72d9d9
--- /dev/null
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "trace/beauty/beauty.h"
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <arpa/inet.h>
+
+static const char *socket_families[] = {
+	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+	"ALG", "NFC", "VSOCK",
+};
+DEFINE_STRARRAY(socket_families);
+
+static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sa;
+	char tmp[16];
+	return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port),
+			 inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
+}
+
+static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
+	u32 flowinfo = ntohl(sin6->sin6_flowinfo);
+	char tmp[512];
+	size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
+				   inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
+	if (flowinfo != 0)
+		printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
+	if (sin6->sin6_scope_id != 0)
+		printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
+
+	return printed;
+}
+
+static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_un *sun = (struct sockaddr_un *)sa;
+	return scnprintf(bf, size, ", path: %s", sun->sun_path);
+}
+
+static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = {
+	[AF_LOCAL] = af_local__scnprintf,
+	[AF_INET]  = af_inet__scnprintf,
+	[AF_INET6] = af_inet6__scnprintf,
+};
+
+static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct sockaddr *sa = (struct sockaddr *)arg->augmented.args;
+	char family[32];
+	size_t printed;
+
+	strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family);
+	printed = scnprintf(bf, size, "{ .family: %s", family);
+
+	if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family])
+		printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed);
+
+	return printed + scnprintf(bf + printed, size - printed, " }");
+}
+
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg)
+{
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
+
+	return scnprintf(bf, size, "%#x", arg->val);
+}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7efe15b9618d..ecd9f9ceda77 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -73,6 +73,7 @@ libperf-y += vdso.o
 libperf-y += counts.o
 libperf-y += stat.o
 libperf-y += stat-shadow.o
+libperf-y += stat-display.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 20061cf42288..28cd6a17491b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -246,8 +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;
 }
 
@@ -276,7 +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;
@@ -285,6 +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:
@@ -304,6 +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);
 		}
@@ -361,9 +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;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 005a5fe8a8c6..5399ba2321bb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -22,6 +22,7 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
+	char	*raw_comment;
 	struct {
 		char	*raw;
 		char	*name;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c980bbff6353..4ec909d57e9c 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 |
@@ -2939,3 +2940,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 		return evsel->evlist->env;
 	return NULL;
 }
+
+static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd);
+		     thread++) {
+			int fd = FD(evsel, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evlist, evsel,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	struct cpu_map *cpus = evsel->cpus;
+	struct thread_map *threads = evsel->threads;
+
+	if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return store_evsel_ids(evsel, evlist);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c960614d3..4f8430a85531 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -481,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3cadc252dd89..91e6d9cfd906 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3637,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 }
 
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				   struct perf_session *session,
-				   perf_event__handler_t process)
+				 struct perf_evlist *evlist,
+				 perf_event__handler_t process)
 {
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each_entry(session->evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6d7fe44aadc0..ff2a1263fb9b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -124,7 +124,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct perf_session *session,
+				 struct perf_evlist *evlist,
 				 perf_event__handler_t process);
 int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
 					     struct perf_evsel *evsel,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 19262f98cd4e..5b0b60f00275 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -19,7 +19,7 @@
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 36d0763311ef..3f07a587c8e6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -320,12 +320,11 @@ int map__load(struct map *map)
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
 					  sbuild_id);
-			pr_warning("%s with build id %s not found",
-				   name, sbuild_id);
+			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
-			pr_warning("Failed to open %s", name);
+			pr_debug("Failed to open %s", name);
 
-		pr_warning(", continuing without symbols\n");
+		pr_debug(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
 #ifdef HAVE_LIBELF_SUPPORT
@@ -334,12 +333,11 @@ int map__load(struct map *map)
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated (is prelink enabled?). "
+			pr_debug("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
-			pr_warning("no symbols found in %s, maybe install "
-				   "a debug package?\n", name);
+			pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
 		}
 #endif
 		return -1;
@@ -701,8 +699,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 		if (verbose >= 2) {
 
 			if (use_browser) {
-				pr_warning("overlapping maps in %s "
-					   "(disable tui for more info)\n",
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
 					   map->dso->name);
 			} else {
 				fputs("overlapping maps:\n", fp);
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d2c78ffd9fee..a2eeebbfb25f 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -147,6 +147,9 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 
+#include <sys/stat.h>
+#include <sys/types.h>
+
 #include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
@@ -159,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "config.h"
 
 struct s390_cpumsf {
 	struct auxtrace		auxtrace;
@@ -170,6 +174,8 @@ struct s390_cpumsf {
 	u32			pmu_type;
 	u16			machine_type;
 	bool			data_queued;
+	bool			use_logfile;
+	char			*logdir;
 };
 
 struct s390_cpumsf_queue {
@@ -177,6 +183,7 @@ struct s390_cpumsf_queue {
 	unsigned int		queue_nr;
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
+	FILE			*logfile;
 };
 
 /* Display s390 CPU measurement facility basic-sampling data entry */
@@ -595,6 +602,12 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			buffer->use_size = buffer->size;
 			buffer->use_data = buffer->data;
 		}
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	} else
 		buffer = sfq->buffer;
 
@@ -606,6 +619,13 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			return -ENOMEM;
 		buffer->use_size = buffer->size;
 		buffer->use_data = buffer->data;
+
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	}
 	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
 		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@@ -640,6 +660,23 @@ s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
 	sfq->sf = sf;
 	sfq->queue_nr = queue_nr;
 	sfq->cpu = -1;
+	if (sf->use_logfile) {
+		char *name;
+		int rc;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.smp.%02x",
+				 sf->logdir, queue_nr)
+			: asprintf(&name, "aux.smp.%02x", queue_nr);
+		if (rc > 0)
+			sfq->logfile = fopen(name, "w");
+		if (sfq->logfile == NULL) {
+			pr_err("Failed to open auxiliary log file %s,"
+			       "continue...\n", name);
+			sf->use_logfile = false;
+		}
+		free(name);
+	}
 	return sfq;
 }
 
@@ -850,8 +887,16 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 	struct auxtrace_queues *queues = &sf->queues;
 	unsigned int i;
 
-	for (i = 0; i < queues->nr_queues; i++)
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+						queues->queue_array[i].priv;
+
+		if (sfq != NULL && sfq->logfile) {
+			fclose(sfq->logfile);
+			sfq->logfile = NULL;
+		}
 		zfree(&queues->queue_array[i].priv);
+	}
 	auxtrace_queues__free(queues);
 }
 
@@ -864,6 +909,7 @@ static void s390_cpumsf_free(struct perf_session *session)
 	auxtrace_heap__free(&sf->heap);
 	s390_cpumsf_free_queues(session);
 	session->auxtrace = NULL;
+	free(sf->logdir);
 	free(sf);
 }
 
@@ -877,17 +923,55 @@ static int s390_cpumsf_get_type(const char *cpuid)
 
 /* Check itrace options set on perf report command.
  * Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
  * Return false otherwise.
  */
 static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 {
+	bool ison = false;
+
 	if (!itops || !itops->set)
 		return true;
-	pr_err("No --itrace options supported\n");
+	ison = itops->inject || itops->instructions || itops->branches ||
+		itops->transactions || itops->ptwrites ||
+		itops->pwr_events || itops->errors ||
+		itops->dont_decode || itops->calls || itops->returns ||
+		itops->callchain || itops->thread_stack ||
+		itops->last_branch;
+	if (!ison)
+		return true;
+	pr_err("Unsupported --itrace options specified\n");
 	return false;
 }
 
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+	struct s390_cpumsf *sf = cb;
+	struct stat stbuf;
+	int rc;
+
+	if (strcmp(var, "auxtrace.dumpdir"))
+		return 0;
+	sf->logdir = strdup(value);
+	if (sf->logdir == NULL) {
+		pr_err("Failed to find auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		return 1;
+	}
+	rc = stat(sf->logdir, &stbuf);
+	if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+		pr_err("Missing auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		free(sf->logdir);
+		sf->logdir = NULL;
+	}
+	return 1;
+}
+
 int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 				      struct perf_session *session)
 {
@@ -906,6 +990,9 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 		err = -EINVAL;
 		goto err_free;
 	}
+	sf->use_logfile = session->itrace_synth_opts->log;
+	if (sf->use_logfile)
+		perf_config(s390_cpumsf__config, sf);
 
 	err = auxtrace_queues__init(&sf->queues);
 	if (err)
@@ -940,6 +1027,7 @@ err_free_queues:
 	auxtrace_queues__free(&sf->queues);
 	session->auxtrace = NULL;
 err_free:
+	free(sf->logdir);
 	free(sf);
 	return err;
 }
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
new file mode 100644
index 000000000000..e7b4c44ebb62
--- /dev/null
+++ b/tools/perf/util/stat-display.c
@@ -0,0 +1,1166 @@
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include "sane_ctype.h"
+#include "cgroup.h"
+#include <math.h>
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
+{
+	if (config->csv_output) {
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+					config->csv_sep,
+					run,
+					config->csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+	else if (pct)
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+			struct perf_evsel *evsel, double avg)
+{
+	struct perf_stat_evsel *ps;
+
+	if (config->run_count == 1)
+		return;
+
+	ps = evsel->stats;
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void aggr_printout(struct perf_stat_config *config,
+			  struct perf_evsel *evsel, int id, int nr)
+{
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+		fprintf(config->output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(config->output, "S%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(config->output, "CPU%*d%s",
+			config->csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
+		break;
+	case AGGR_THREAD:
+		fprintf(config->output, "%*s-%*d%s",
+			config->csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			config->csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			config->csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+}
+
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(config, os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
+}
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(struct perf_stat_config *config,
+			      void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[1024], str[1024];
+	unsigned mlen = config->metric_only_len;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
+}
+
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+				void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
+	else
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct perf_evsel *evsel, int id)
+{
+	struct perf_evlist *evlist = evsel->evlist;
+	int i;
+
+	if (!config->aggr_get_id)
+		return 0;
+
+	if (config->aggr_mode == AGGR_NONE)
+		return id;
+
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct perf_evsel *evsel, double avg)
+{
+	FILE *output = config->output;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (config->csv_output) {
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (config->big_num)
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(config, evsel, id, nr);
+
+	fprintf(output, fmt, avg, config->csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			evsel->unit, config->csv_sep);
+
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
+}
+
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->attr.type;
+	struct perf_evsel *pos;
+
+	if (counter->nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->attr.type;
+			continue;
+		}
+		if (pmu_type != pos->attr.type)
+			return true;
+	}
+
+	return false;
+}
+
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
+{
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = config->output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	new_line_t nl;
+
+	if (config->metric_only) {
+		nl = new_line_metric;
+		if (config->csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (config->csv_output && !config->metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[config->aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (config->metric_only) {
+			pm(config, &os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(config, counter, id, nr);
+
+		fprintf(config->output, "%*s%s",
+			config->csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			config->csv_sep);
+
+		if (counter->supported) {
+			config->print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				config->print_mixed_hw_group_error = 1;
+		}
+
+		fprintf(config->output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			counter->unit, config->csv_sep);
+
+		fprintf(config->output, "%*s",
+			config->csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(config->output, "%s%s",
+				config->csv_sep, counter->cgrp->name);
+
+		if (!config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+		if (config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (!config->metric_only)
+		abs_printout(config, id, nr, counter, uval);
+
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+	out.force_header = false;
+
+	if (config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+
+	perf_stat__print_shadow_stats(config, counter, uval,
+				first_shadow_cpu(config, counter, id),
+				&out, &config->metric_events, st);
+	if (!config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct perf_evlist *evlist)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
+		evlist__for_each_entry(evlist, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			perf_stat__update_shadow_stats(counter, val,
+					first_shadow_cpu(config, counter, id),
+					&rt_stat);
+		}
+	}
+}
+
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+
+	counter->uniquified_name = true;
+}
+
+static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evlist->entries), node);
+	list_for_each_entry_continue (alias, &evlist->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
+			break;
+		alias->merged_stat = true;
+		cb(config, alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(config, counter, data, true);
+	if (config->no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
+		collect_all_aliases(config, counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+		    struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
+static void print_aggr(struct perf_stat_config *config,
+		       struct perf_evlist *evlist,
+		       char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	struct perf_evsel *counter;
+	int s, id, nr;
+	double uval;
+	u64 ena, run, val;
+	bool first;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	aggr_update_shadow(config, evlist);
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		struct aggr_data ad;
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		ad.id = id = config->aggr_map->map[s];
+		first = true;
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(config, counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(config, counter, id, nr);
+			}
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
+
+			uval = val * counter->scale;
+			printout(config, id, nr, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
+			if (!metric_only)
+				fputc('\n', output);
+		}
+		if (metric_only)
+			fputc('\n', output);
+	}
+}
+
+static int cmp_val(const void *a, const void *b)
+{
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret,
+					struct target *_target)
+{
+	int cpu, thread, i = 0;
+	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(_target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
+			      struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		id = buf[thread].id;
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &config->stats[id]);
+		else
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
+		fputc('\n', output);
+	}
+
+	free(buf);
+}
+
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->stats;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
+/*
+ * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
+ */
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct perf_evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	double uval;
+	struct caggr_data cd = { .avg = 0.0 };
+
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
+		return;
+
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = cd.avg * counter->scale;
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
+	if (!metric_only)
+		fprintf(output, "\n");
+}
+
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_stat_config *config,
+			  struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(config, counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
+
+		fputc('\n', output);
+	}
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evlist->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, config->output);
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			if (first) {
+				aggr_printout(config, counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
+		}
+		fputc('\n', config->output);
+	}
+}
+
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static const char *aggr_header_csv[] = {
+	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_SOCKET] 	= 	"socket,cpus",
+	[AGGR_NONE] 	= 	"cpu,",
+	[AGGR_THREAD] 	= 	"comm-pid,",
+	[AGGR_GLOBAL] 	=	""
+};
+
+static void print_metric_headers(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 const char *prefix, bool no_indent)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = config->output
+	};
+
+	if (prefix)
+		fprintf(config->output, "%s", prefix);
+
+	if (!config->csv_output && !no_indent)
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
+	if (config->csv_output) {
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
+	}
+
+	/* Print metrics headers only */
+	evlist__for_each_entry(evlist, counter) {
+		if (is_duration_time(counter))
+			continue;
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		out.force_header = true;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(config, counter, 0,
+					      0,
+					      &out,
+					      &config->metric_events,
+					      &rt_stat);
+	}
+	fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+			   struct perf_evlist *evlist,
+			   char *prefix, struct timespec *ts)
+{
+	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
+	FILE *output = config->output;
+	static int num_print_interval;
+
+	if (config->interval_clear)
+		puts(CONSOLE_CLEAR);
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+		switch (config->aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU    ");
+			if (!metric_only)
+				fprintf(output, "                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+		case AGGR_UNSET:
+			break;
+		}
+	}
+
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
+		print_metric_headers(config, evlist, " ", true);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
+			 int argc, const char **argv)
+{
+	FILE *output = config->output;
+	int i;
+
+	fflush(stdout);
+
+	if (!config->csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (_target->system_wide)
+			fprintf(output, "\'system wide");
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
+		else
+			fprintf(output, "thread id \'%s", _target->tid);
+
+		fprintf(output, "\'");
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
+		fprintf(output, ":\n\n");
+	}
+}
+
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < config->run_count; idx++) {
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
+static double timeval2double(struct timeval *t)
+{
+	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
+}
+
+static void print_footer(struct perf_stat_config *config)
+{
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+	FILE *output = config->output;
+	int n;
+
+	if (!config->null_run)
+		fprintf(output, "\n");
+
+	if (config->run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
+
+			fprintf(output, "\n\n");
+			fprintf(output, " %17.9f seconds user\n", ru_utime);
+			fprintf(output, " %17.9f seconds sys\n", ru_stime);
+		}
+	} else {
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (config->walltime_run_table)
+			print_table(config, output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(config, sd, avg);
+	}
+	fprintf(output, "\n\n");
+
+	if (config->print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (config->print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
+}
+
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv)
+{
+	bool metric_only = config->metric_only;
+	int interval = config->interval;
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(config, evlist, prefix = buf, ts);
+	else
+		print_header(config, _target, argc, argv);
+
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(config, evlist, prefix, false);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
+	}
+
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(config, evlist, prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_aggr_thread(config, _target, counter, prefix);
+		}
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_counter_aggr(config, counter, prefix);
+		}
+		if (metric_only)
+			fputc('\n', config->output);
+		break;
+	case AGGR_NONE:
+		if (metric_only)
+			print_no_aggr_metric(config, evlist, prefix);
+		else {
+			evlist__for_each_entry(evlist, counter) {
+				if (is_duration_time(counter))
+					continue;
+				print_counter(config, counter, prefix);
+			}
+		}
+		break;
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	if (!interval && !config->csv_output)
+		print_footer(config);
+
+	fflush(config->output);
+}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5f2512..8ad32763cfff 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st,
 	return v->stats.n;
 }
 
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+					  int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st)
@@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu,
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
 	if (ratio)
-		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
 				  ratio);
 	else
-		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+					 int cpu,
 					 struct perf_evsel *evsel, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st)
@@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(int cpu,
+static void print_branch_misses(struct perf_stat_config *config,
+				int cpu,
 				struct perf_evsel *evsel,
 				double avg,
 				struct perf_stat_output_ctx *out,
@@ -469,10 +472,11 @@ static void print_branch_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+				  int cpu,
 				  struct perf_evsel *evsel,
 				  double avg,
 				  struct perf_stat_output_ctx *out,
@@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
 /*
@@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 	return sanitize_val(1.0 - sum);
 }
 
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+			   int cpu, struct perf_evsel *evsel,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 
 	if (cost > 10)
 		color = PERF_COLOR_RED;
-	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
-	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
-static void generic_metric(const char *metric_expr,
+static void generic_metric(struct perf_stat_config *config,
+			   const char *metric_expr,
 			   struct perf_evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
@@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr,
 		const char *p = metric_expr;
 
 		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(ctxp, NULL, "%8.1f",
+			print_metric(config, ctxp, NULL, "%8.1f",
 				metric_name ?
 				metric_name :
 				out->force_header ?  name : "",
 				ratio);
 		else
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 	} else
-		print_metric(ctxp, NULL, NULL, "", 0);
+		print_metric(config, ctxp, NULL, NULL, "", 0);
 }
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"insn per cycle", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
 		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 						    ctx, cpu));
 
 		if (total && avg) {
-			out->new_line(ctxp);
+			out->new_line(config, ctxp);
 			ratio = total / avg;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(cpu, evsel, avg, out, st);
+			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all branches", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
@@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(cpu, evsel, avg, out, st);
+			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(cpu, evsel, avg, out, st);
+			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(cpu, evsel, avg, out, st);
+			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(cpu, evsel, avg, out, st);
+			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
@@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = avg * 100 / total;
 
 		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.3f %%",
+			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "Ghz", 0);
+			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total)
-			print_metric(ctxp, NULL,
+			print_metric(config, ctxp, NULL,
 					"%7.2f%%", "transactional cycles",
 					100.0 * (avg / total));
 		else
-			print_metric(ctxp, NULL, NULL, "transactional cycles",
+			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
 		else
-			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
 					 ctx, cpu);
@@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.0f",
+			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@@ -912,33 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (avg)
 			ratio = total / avg;
 
-		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
 		else
-			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
 		double fe_bound = td_fe_bound(ctx, cpu, st);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
 		double retiring = td_retiring(ctx, cpu, st);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
 		double bad_spec = td_bad_spec(ctx, cpu, st);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
 		double be_bound = td_be_bound(ctx, cpu, st);
@@ -955,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		if (td_total_slots(ctx, cpu, st) > 0)
-			print_metric(ctxp, color, "%8.1f%%", name,
+			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
-			print_metric(ctxp, NULL, NULL, name, 0);
+			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
 				evsel->metric_name, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
@@ -975,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			unit = 'K';
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(cpu, evsel, out, st);
+		print_smi_cost(config, cpu, evsel, out, st);
 	} else {
 		num = 0;
 	}
@@ -987,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		list_for_each_entry (mexp, &me->head, nd) {
 			if (num++ > 0)
-				out->new_line(ctxp);
-			generic_metric(mexp->metric_expr, mexp->metric_events,
+				out->new_line(config, ctxp);
+			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
 					avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0b0fad..5d3172bcc4ae 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -435,3 +435,98 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 
 	return ret;
 }
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_evsel *leader = evsel->leader;
+
+	if (config->scale) {
+		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+				    PERF_FORMAT_TOTAL_TIME_RUNNING;
+	}
+
+	/*
+	 * The event is part of non trivial group, let's enable
+	 * the group read (for leader) and ID retrieval for all
+	 * members.
+	 */
+	if (leader->nr_members > 1)
+		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+	attr->inherit = !config->no_inherit;
+
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+
+	if (config->identifier)
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(target) && !config->initial_delay)
+			attr->enable_on_exec = 1;
+	}
+
+	if (target__has_cpu(target) && !target__has_per_thread(target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
+	return perf_evsel__open_per_thread(evsel, evsel->threads);
+}
+
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs)
+{
+	int err;
+
+	if (attrs) {
+		err = perf_event__synthesize_attrs(tool, evlist, process);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	err = perf_event__synthesize_extra_attr(tool, evlist, process,
+						attrs);
+
+	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
+						 process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
+					     process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb986f7fc..3a13a6dc5a62 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -4,8 +4,14 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
 #include "xyarray.h"
 #include "rblist.h"
+#include "perf.h"
+#include "event.h"
 
 struct stats {
 	double n, mean, M2;
@@ -84,15 +90,42 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+			     struct cpu_map *m, int cpu);
+
 struct perf_stat_config {
-	enum aggr_mode	aggr_mode;
-	bool		scale;
-	FILE		*output;
-	unsigned int	interval;
-	unsigned int	timeout;
-	int		times;
-	struct runtime_stat *stats;
-	int		stats_num;
+	enum aggr_mode		 aggr_mode;
+	bool			 scale;
+	bool			 no_inherit;
+	bool			 identifier;
+	bool			 csv_output;
+	bool			 interval_clear;
+	bool			 metric_only;
+	bool			 null_run;
+	bool			 ru_display;
+	bool			 big_num;
+	bool			 no_merge;
+	bool			 walltime_run_table;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 initial_delay;
+	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
+	int			 times;
+	int			 run_count;
+	int			 print_free_counters_hint;
+	int			 print_mixed_hw_group_error;
+	struct runtime_stat	*stats;
+	int			 stats_num;
+	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
+	struct cpu_map		*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct cpu_map		*cpus_aggr_map;
+	u64			*walltime_run;
+	struct rblist		 metric_events;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -130,9 +163,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
@@ -148,7 +182,8 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -171,4 +206,19 @@ int perf_event__process_stat_event(struct perf_tool *tool,
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target);
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs);
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv);
 #endif
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 920b1d58a068..e76214f8d596 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *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);
-		tep_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);
 	}
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 40204ec3a7a2..c69d77d7cf55 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 #define _PERF_UTIL_TRACE_EVENT_H
 
 #include <traceevent/event-parse.h>
+#include <traceevent/trace-seq.h>
 #include "parse-events.h"
 
 struct machine;