Merge tag 'perf-core-for-mingo-5.4-20190920-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

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

perf stat:

  Srikar Dronamraju:

  - Fix a segmentation fault when using repeat forever.

  - Reset previous counts on repeat with interval.

aarch64:

  James Clark:

  - Add PMU event JSON files for Cortex-A76 and Neoverse N1.

PowerPC:

  Anju T Sudhakar:

  - Make 'trace_cycles' the default event for 'perf kvm record' in PowerPC.

S/390:

  - Link libjvmti to tools/lib/string.o to have a weak strlcpy()
    implementation, providing previously unresolved symbol on s/390.

perf test:

  Jiri Olsa:

  - Add libperf automated tests to 'make -C tools/perf build-test'.

  Colin Ian King:

  - Fix spelling mistake.

Tree wide:

  Arnaldo Carvalho de Melo:

  - Some more header file sanitization.

libperf:

  Jiri Olsa:

  - Add dependency on libperf for python.so binding.

libtraceevent:

  Sakari Ailus:

  - Convert remaining %p[fF] users to %p[sS].

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

76 files changed, 2128 insertions, 2143 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 0b4d8e0d474c..fd89d6a8cd65 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -86,6 +86,7 @@ perf-y += stat-display.o
 perf-y += record.o
 perf-y += srcline.o
 perf-y += srccode.o
+perf-y += synthetic-events.o
 perf-y += data.o
 perf-y += tsc.o
 perf-y += cloexec.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1748f528b6e9..d441cca6a517 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -14,7 +14,7 @@
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
 #include <linux/btf.h>
-#include "util.h"
+#include "util.h" // hex_width()
 #include "ui/ui.h"
 #include "sort.h"
 #include "build-id.h"
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 8a7340f6a2a2..53be12b23ff4 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -16,7 +16,6 @@
 #include <linux/log2.h>
 #include <linux/zalloc.h>
 
-#include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
 #include "machine.h"
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 6f25224a3def..0e8c89cf7cad 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -31,8 +31,8 @@
 #include "map.h"
 #include "pmu.h"
 #include "evsel.h"
-#include "cpumap.h"
 #include "symbol.h"
+#include "util/synthetic-events.h"
 #include "thread_map.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
@@ -50,10 +50,12 @@
 #include "intel-bts.h"
 #include "arm-spe.h"
 #include "s390-cpumsf.h"
-#include "util.h"
+#include "util.h" // page_size
 
 #include <linux/ctype.h>
+#include <linux/kernel.h>
 #include "symbol/kallsyms.h"
+#include <internal/lib.h>
 
 static bool auxtrace__dont_decode(struct perf_session *session)
 {
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 37e70dc01436..b110aec1da4d 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -11,21 +11,22 @@
 #include <errno.h>
 #include <stdbool.h>
 #include <stddef.h>
+#include <stdio.h> // FILE
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include <asm/bitsperlong.h>
 #include <asm/barrier.h>
 
-#include "event.h"
-
 union perf_event;
 struct perf_session;
 struct evlist;
 struct perf_tool;
 struct perf_mmap;
+struct perf_sample;
 struct option;
 struct record_opts;
+struct perf_record_auxtrace_error;
 struct perf_record_auxtrace_info;
 struct events_stats;
 
@@ -524,10 +525,6 @@ void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
 			  const char *msg, u64 timestamp);
 
-int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
-					 struct perf_tool *tool,
-					 struct perf_session *session,
-					 perf_event__handler_t process);
 int perf_event__process_auxtrace_info(struct perf_session *session,
 				      union perf_event *event);
 s64 perf_event__process_auxtrace(struct perf_session *session,
@@ -604,15 +601,6 @@ void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
 {
 }
 
-static inline int
-perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
-				     struct perf_tool *tool __maybe_unused,
-				     struct perf_session *session __maybe_unused,
-				     perf_event__handler_t process __maybe_unused)
-{
-	return -EINVAL;
-}
-
 static inline
 int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
 			     struct evlist *evlist __maybe_unused,
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 7a3d4b125323..f7ed5d122e22 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -16,6 +16,7 @@
 #include "map.h"
 #include "evlist.h"
 #include "record.h"
+#include "util/synthetic-events.h"
 
 #define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
 
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index a01c2fd68c03..81fdc88e6c1a 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -6,9 +6,9 @@
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <api/fd/array.h>
-#include "event.h"
 #include <stdio.h>
 
+struct bpf_prog_info;
 struct machine;
 union perf_event;
 struct perf_env;
@@ -33,11 +33,6 @@ struct btf_node {
 #ifdef HAVE_LIBBPF_SUPPORT
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
-
-int perf_event__synthesize_bpf_events(struct perf_session *session,
-				      perf_event__handler_t process,
-				      struct machine *machine,
-				      struct record_opts *opts);
 int bpf_event__add_sb_event(struct evlist **evlist,
 				 struct perf_env *env);
 void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
@@ -51,14 +46,6 @@ static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused,
-						    perf_event__handler_t process __maybe_unused,
-						    struct machine *machine __maybe_unused,
-						    struct record_opts *opts __maybe_unused)
-{
-	return 0;
-}
-
 static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused,
 					  struct perf_env *env __maybe_unused)
 {
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 9d1e090084a2..2285b1eb3128 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -1,5 +1,3 @@
-#include "util/util.h"
-#include "util/debug.h"
 #include "util/map_symbol.h"
 #include "util/branch.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 06f66dad0b79..88e00d268f6f 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -1,8 +1,15 @@
 #ifndef _PERF_BRANCH_H
 #define _PERF_BRANCH_H 1
-
+/*
+ * The linux/stddef.h isn't need here, but is needed for __always_inline used
+ * in files included from uapi/linux/perf_event.h such as
+ * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h,
+ * detected in at least musl libc, used in Alpine Linux. -acme
+ */
 #include <stdio.h>
 #include <stdint.h>
+#include <linux/compiler.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e5fb77755d9e..7928c398a063 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -7,7 +7,7 @@
  * Copyright (C) 2009, 2010 Red Hat Inc.
  * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
  */
-#include "util.h"
+#include "util.h" // copyfile_ns(), lsdir(), mkdir_p(), rm_rf()
 #include <dirent.h>
 #include <errno.h>
 #include <stdio.h>
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index c14646c1f2eb..9a9b56ed3f0a 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -23,6 +23,7 @@
 
 #include "debug.h"
 #include "dso.h"
+#include "event.h"
 #include "hist.h"
 #include "sort.h"
 #include "machine.h"
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b042ceef4114..83398e5bbe4b 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -4,12 +4,15 @@
 
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include "event.h"
 #include "map_symbol.h"
 #include "branch.h"
 
+struct addr_location;
 struct evsel;
+struct ip_callchain;
 struct map;
+struct perf_sample;
+struct thread;
 
 #define HELP_PAD "\t\t\t\t"
 
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 4e904fcb2783..a12872f2856a 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <sched.h>
-#include "util.h"
+#include "util.h" // for sched_getcpu()
 #include "../perf-sys.h"
 #include "cloexec.h"
 #include "event.h"
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 37d7c492b155..cd92a99eb89d 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -17,7 +17,6 @@
 #include "cs-etm.h"
 #include "cs-etm-decoder.h"
 #include "intlist.h"
-#include "util.h"
 
 /* use raw logging */
 #ifdef CS_DEBUG_RAW
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 707afdbd9529..6021974577d5 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -35,7 +35,7 @@
 #include "thread.h"
 #include "thread-stack.h"
 #include <tools/libc_compat.h>
-#include "util.h"
+#include "util/synthetic-events.h"
 
 #define MAX_TIMESTAMP (~0ULL)
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e75c3a279fe8..88fba2ba549f 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -13,9 +13,10 @@
 #include <dirent.h>
 
 #include "data.h"
-#include "util.h"
+#include "util.h" // rm_rf_perf_data()
 #include "debug.h"
 #include "header.h"
+#include <internal/lib.h>
 
 static void close_dir(struct perf_data_file *files, int nr)
 {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index a1b59bd35519..e55114f0336f 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -17,7 +17,6 @@
 #include "event.h"
 #include "debug.h"
 #include "print_binary.h"
-#include "util.h"
 #include "target.h"
 #include "ui/helpline.h"
 #include "ui/ui.h"
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index b2deee987ffa..d25ae1c4cee9 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,9 +3,9 @@
 #ifndef __PERF_DEBUG_H
 #define __PERF_DEBUG_H
 
+#include <stdarg.h>
 #include <stdbool.h>
 #include <linux/compiler.h>
-#include "../ui/util.h"
 
 extern int verbose;
 extern bool quiet, dump_trace;
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
index 763328c151e9..6fb7f34c0814 100644
--- a/tools/perf/util/demangle-java.c
+++ b/tools/perf/util/demangle-java.c
@@ -3,7 +3,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include "debug.h"
 #include "symbol.h"
 
 #include "demangle-java.h"
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
index 423afbbd386b..a659fc69f73a 100644
--- a/tools/perf/util/demangle-rust.c
+++ b/tools/perf/util/demangle-rust.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
-#include "util.h"
 #include "debug.h"
 
 #include "demangle-rust.h"
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index db55eddce8cd..1b49ecee5aff 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -5,7 +5,6 @@
  * Written by: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
-#include <util.h>
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index d8e083d42610..db40906e2937 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -4,9 +4,10 @@
 
 #include <linux/types.h>
 #include <linux/rbtree.h>
-#include "cpumap.h"
 #include "rwsem.h"
 
+struct perf_cpu_map;
+
 struct cpu_topology_map {
 	int	socket_id;
 	int	die_id;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f4afbb858ebb..fc1e5a991008 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,16 +1,16 @@
-#include <dirent.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <perf/cpumap.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
-#include <api/fs/fs.h>
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
+#include "cpumap.h"
 #include "dso.h"
 #include "event.h"
 #include "debug.h"
@@ -24,6 +24,7 @@
 #include "time-utils.h"
 #include <linux/ctype.h>
 #include "map.h"
+#include "util/namespaces.h"
 #include "symbol.h"
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
@@ -33,8 +34,6 @@
 #include "tool.h"
 #include "../perf.h"
 
-#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
-
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
 	[PERF_RECORD_MMAP]			= "MMAP",
@@ -75,18 +74,6 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
 };
 
-static const char *perf_ns__names[] = {
-	[NET_NS_INDEX]		= "net",
-	[UTS_NS_INDEX]		= "uts",
-	[IPC_NS_INDEX]		= "ipc",
-	[PID_NS_INDEX]		= "pid",
-	[USER_NS_INDEX]		= "user",
-	[MNT_NS_INDEX]		= "mnt",
-	[CGROUP_NS_INDEX]	= "cgroup",
-};
-
-unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT;
-
 const char *perf_event__name(unsigned int id)
 {
 	if (id >= ARRAY_SIZE(perf_event__names))
@@ -96,775 +83,6 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-static const char *perf_ns__name(unsigned int id)
-{
-	if (id >= ARRAY_SIZE(perf_ns__names))
-		return "UNKNOWN";
-	return perf_ns__names[id];
-}
-
-int perf_tool__process_synth_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct machine *machine,
-				   perf_event__handler_t process)
-{
-	struct perf_sample synth_sample = {
-	.pid	   = -1,
-	.tid	   = -1,
-	.time	   = -1,
-	.stream_id = -1,
-	.cpu	   = -1,
-	.period	   = 1,
-	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
-	};
-
-	return process(tool, event, &synth_sample, machine);
-};
-
-/*
- * Assumes that the first 4095 bytes of /proc/pid/stat contains
- * the comm, tgid and ppid.
- */
-static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
-				    pid_t *tgid, pid_t *ppid)
-{
-	char filename[PATH_MAX];
-	char bf[4096];
-	int fd;
-	size_t size = 0;
-	ssize_t n;
-	char *name, *tgids, *ppids;
-
-	*tgid = -1;
-	*ppid = -1;
-
-	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0) {
-		pr_debug("couldn't open %s\n", filename);
-		return -1;
-	}
-
-	n = read(fd, bf, sizeof(bf) - 1);
-	close(fd);
-	if (n <= 0) {
-		pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
-			   pid);
-		return -1;
-	}
-	bf[n] = '\0';
-
-	name = strstr(bf, "Name:");
-	tgids = strstr(bf, "Tgid:");
-	ppids = strstr(bf, "PPid:");
-
-	if (name) {
-		char *nl;
-
-		name = skip_spaces(name + 5);  /* strlen("Name:") */
-		nl = strchr(name, '\n');
-		if (nl)
-			*nl = '\0';
-
-		size = strlen(name);
-		if (size >= len)
-			size = len - 1;
-		memcpy(comm, name, size);
-		comm[size] = '\0';
-	} else {
-		pr_debug("Name: string not found for pid %d\n", pid);
-	}
-
-	if (tgids) {
-		tgids += 5;  /* strlen("Tgid:") */
-		*tgid = atoi(tgids);
-	} else {
-		pr_debug("Tgid: string not found for pid %d\n", pid);
-	}
-
-	if (ppids) {
-		ppids += 5;  /* strlen("PPid:") */
-		*ppid = atoi(ppids);
-	} else {
-		pr_debug("PPid: string not found for pid %d\n", pid);
-	}
-
-	return 0;
-}
-
-static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
-				    struct machine *machine,
-				    pid_t *tgid, pid_t *ppid)
-{
-	size_t size;
-
-	*ppid = -1;
-
-	memset(&event->comm, 0, sizeof(event->comm));
-
-	if (machine__is_host(machine)) {
-		if (perf_event__get_comm_ids(pid, event->comm.comm,
-					     sizeof(event->comm.comm),
-					     tgid, ppid) != 0) {
-			return -1;
-		}
-	} else {
-		*tgid = machine->pid;
-	}
-
-	if (*tgid < 0)
-		return -1;
-
-	event->comm.pid = *tgid;
-	event->comm.header.type = PERF_RECORD_COMM;
-
-	size = strlen(event->comm.comm) + 1;
-	size = PERF_ALIGN(size, sizeof(u64));
-	memset(event->comm.comm + size, 0, machine->id_hdr_size);
-	event->comm.header.size = (sizeof(event->comm) -
-				(sizeof(event->comm.comm) - size) +
-				machine->id_hdr_size);
-	event->comm.tid = pid;
-
-	return 0;
-}
-
-pid_t perf_event__synthesize_comm(struct perf_tool *tool,
-					 union perf_event *event, pid_t pid,
-					 perf_event__handler_t process,
-					 struct machine *machine)
-{
-	pid_t tgid, ppid;
-
-	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
-		return -1;
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return tgid;
-}
-
-static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
-					 struct perf_ns_link_info *ns_link_info)
-{
-	struct stat64 st;
-	char proc_ns[128];
-
-	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
-	if (stat64(proc_ns, &st) == 0) {
-		ns_link_info->dev = st.st_dev;
-		ns_link_info->ino = st.st_ino;
-	}
-}
-
-int perf_event__synthesize_namespaces(struct perf_tool *tool,
-				      union perf_event *event,
-				      pid_t pid, pid_t tgid,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	u32 idx;
-	struct perf_ns_link_info *ns_link_info;
-
-	if (!tool || !tool->namespace_events)
-		return 0;
-
-	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
-	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-	       machine->id_hdr_size));
-
-	event->namespaces.pid = tgid;
-	event->namespaces.tid = pid;
-
-	event->namespaces.nr_namespaces = NR_NAMESPACES;
-
-	ns_link_info = event->namespaces.link_info;
-
-	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
-		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
-					     &ns_link_info[idx]);
-
-	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
-
-	event->namespaces.header.size = (sizeof(event->namespaces) +
-			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-			machine->id_hdr_size);
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return 0;
-}
-
-static int perf_event__synthesize_fork(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid, pid_t ppid,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
-
-	/*
-	 * for main thread set parent to ppid from status file. For other
-	 * threads set parent pid to main thread. ie., assume main thread
-	 * spawns all threads in a process
-	*/
-	if (tgid == pid) {
-		event->fork.ppid = ppid;
-		event->fork.ptid = ppid;
-	} else {
-		event->fork.ppid = tgid;
-		event->fork.ptid = tgid;
-	}
-	event->fork.pid  = tgid;
-	event->fork.tid  = pid;
-	event->fork.header.type = PERF_RECORD_FORK;
-	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
-
-	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return 0;
-}
-
-int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid,
-				       perf_event__handler_t process,
-				       struct machine *machine,
-				       bool mmap_data)
-{
-	char filename[PATH_MAX];
-	FILE *fp;
-	unsigned long long t;
-	bool truncation = false;
-	unsigned long long timeout = proc_map_timeout * 1000000ULL;
-	int rc = 0;
-	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
-	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
-		 machine->root_dir, pid, pid);
-
-	fp = fopen(filename, "r");
-	if (fp == NULL) {
-		/*
-		 * We raced with a task exiting - just return:
-		 */
-		pr_debug("couldn't open %s\n", filename);
-		return -1;
-	}
-
-	event->header.type = PERF_RECORD_MMAP2;
-	t = rdclock();
-
-	while (1) {
-		char bf[BUFSIZ];
-		char prot[5];
-		char execname[PATH_MAX];
-		char anonstr[] = "//anon";
-		unsigned int ino;
-		size_t size;
-		ssize_t n;
-
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			break;
-
-		if ((rdclock() - t) > timeout) {
-			pr_warning("Reading %s time out. "
-				   "You may want to increase "
-				   "the time limit by --proc-map-timeout\n",
-				   filename);
-			truncation = true;
-			goto out;
-		}
-
-		/* ensure null termination since stack will be reused. */
-		strcpy(execname, "");
-
-		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
-		       &event->mmap2.start, &event->mmap2.len, prot,
-		       &event->mmap2.pgoff, &event->mmap2.maj,
-		       &event->mmap2.min,
-		       &ino, execname);
-
-		/*
- 		 * Anon maps don't have the execname.
- 		 */
-		if (n < 7)
-			continue;
-
-		event->mmap2.ino = (u64)ino;
-
-		/*
-		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
-		 */
-		if (machine__is_host(machine))
-			event->header.misc = PERF_RECORD_MISC_USER;
-		else
-			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
-
-		/* map protection and flags bits */
-		event->mmap2.prot = 0;
-		event->mmap2.flags = 0;
-		if (prot[0] == 'r')
-			event->mmap2.prot |= PROT_READ;
-		if (prot[1] == 'w')
-			event->mmap2.prot |= PROT_WRITE;
-		if (prot[2] == 'x')
-			event->mmap2.prot |= PROT_EXEC;
-
-		if (prot[3] == 's')
-			event->mmap2.flags |= MAP_SHARED;
-		else
-			event->mmap2.flags |= MAP_PRIVATE;
-
-		if (prot[2] != 'x') {
-			if (!mmap_data || prot[0] != 'r')
-				continue;
-
-			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
-		}
-
-out:
-		if (truncation)
-			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
-
-		if (!strcmp(execname, ""))
-			strcpy(execname, anonstr);
-
-		if (hugetlbfs_mnt_len &&
-		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
-			strcpy(execname, anonstr);
-			event->mmap2.flags |= MAP_HUGETLB;
-		}
-
-		size = strlen(execname) + 1;
-		memcpy(event->mmap2.filename, execname, size);
-		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap2.len -= event->mmap.start;
-		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-		event->mmap2.header.size += machine->id_hdr_size;
-		event->mmap2.pid = tgid;
-		event->mmap2.tid = pid;
-
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-
-		if (truncation)
-			break;
-	}
-
-	fclose(fp);
-	return rc;
-}
-
-int perf_event__synthesize_modules(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine)
-{
-	int rc = 0;
-	struct map *pos;
-	struct maps *maps = machine__kernel_maps(machine);
-	union perf_event *event = zalloc((sizeof(event->mmap) +
-					  machine->id_hdr_size));
-	if (event == NULL) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for kernel modules\n");
-		return -1;
-	}
-
-	event->header.type = PERF_RECORD_MMAP;
-
-	/*
-	 * kernel uses 0 for user space maps, see kernel/perf_event.c
-	 * __perf_event_mmap
-	 */
-	if (machine__is_host(machine))
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
-	else
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-
-	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
-		size_t size;
-
-		if (!__map__is_kmodule(pos))
-			continue;
-
-		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-		event->mmap.header.type = PERF_RECORD_MMAP;
-		event->mmap.header.size = (sizeof(event->mmap) -
-				        (sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.start = pos->start;
-		event->mmap.len   = pos->end - pos->start;
-		event->mmap.pid   = machine->pid;
-
-		memcpy(event->mmap.filename, pos->dso->long_name,
-		       pos->dso->long_name_len + 1);
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-	}
-
-	free(event);
-	return rc;
-}
-
-static int __event__synthesize_thread(union perf_event *comm_event,
-				      union perf_event *mmap_event,
-				      union perf_event *fork_event,
-				      union perf_event *namespaces_event,
-				      pid_t pid, int full,
-				      perf_event__handler_t process,
-				      struct perf_tool *tool,
-				      struct machine *machine,
-				      bool mmap_data)
-{
-	char filename[PATH_MAX];
-	DIR *tasks;
-	struct dirent *dirent;
-	pid_t tgid, ppid;
-	int rc = 0;
-
-	/* special case: only send one comm event using passed in pid */
-	if (!full) {
-		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
-						   process, machine);
-
-		if (tgid == -1)
-			return -1;
-
-		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
-						      tgid, process, machine) < 0)
-			return -1;
-
-		/*
-		 * send mmap only for thread group leader
-		 * see thread__init_map_groups
-		 */
-		if (pid == tgid &&
-		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						       process, machine, mmap_data))
-			return -1;
-
-		return 0;
-	}
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
-		 machine->root_dir, pid);
-
-	tasks = opendir(filename);
-	if (tasks == NULL) {
-		pr_debug("couldn't open %s\n", filename);
-		return 0;
-	}
-
-	while ((dirent = readdir(tasks)) != NULL) {
-		char *end;
-		pid_t _pid;
-
-		_pid = strtol(dirent->d_name, &end, 10);
-		if (*end)
-			continue;
-
-		rc = -1;
-		if (perf_event__prepare_comm(comm_event, _pid, machine,
-					     &tgid, &ppid) != 0)
-			break;
-
-		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
-						ppid, process, machine) < 0)
-			break;
-
-		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
-						      tgid, process, machine) < 0)
-			break;
-
-		/*
-		 * Send the prepared comm event
-		 */
-		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
-			break;
-
-		rc = 0;
-		if (_pid == pid) {
-			/* process the parent's maps too */
-			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data);
-			if (rc)
-				break;
-		}
-	}
-
-	closedir(tasks);
-	return rc;
-}
-
-int perf_event__synthesize_thread_map(struct perf_tool *tool,
-				      struct perf_thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine,
-				      bool mmap_data)
-{
-	union perf_event *comm_event, *mmap_event, *fork_event;
-	union perf_event *namespaces_event;
-	int err = -1, thread, j;
-
-	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
-	if (comm_event == NULL)
-		goto out;
-
-	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
-	if (mmap_event == NULL)
-		goto out_free_comm;
-
-	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
-	if (fork_event == NULL)
-		goto out_free_mmap;
-
-	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
-				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-				  machine->id_hdr_size);
-	if (namespaces_event == NULL)
-		goto out_free_fork;
-
-	err = 0;
-	for (thread = 0; thread < threads->nr; ++thread) {
-		if (__event__synthesize_thread(comm_event, mmap_event,
-					       fork_event, namespaces_event,
-					       perf_thread_map__pid(threads, thread), 0,
-					       process, tool, machine,
-					       mmap_data)) {
-			err = -1;
-			break;
-		}
-
-		/*
-		 * comm.pid is set to thread group id by
-		 * perf_event__synthesize_comm
-		 */
-		if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) {
-			bool need_leader = true;
-
-			/* is thread group leader in thread_map? */
-			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) {
-					need_leader = false;
-					break;
-				}
-			}
-
-			/* if not, generate events for it */
-			if (need_leader &&
-			    __event__synthesize_thread(comm_event, mmap_event,
-						       fork_event, namespaces_event,
-						       comm_event->comm.pid, 0,
-						       process, tool, machine,
-						       mmap_data)) {
-				err = -1;
-				break;
-			}
-		}
-	}
-	free(namespaces_event);
-out_free_fork:
-	free(fork_event);
-out_free_mmap:
-	free(mmap_event);
-out_free_comm:
-	free(comm_event);
-out:
-	return err;
-}
-
-static int __perf_event__synthesize_threads(struct perf_tool *tool,
-					    perf_event__handler_t process,
-					    struct machine *machine,
-					    bool mmap_data,
-					    struct dirent **dirent,
-					    int start,
-					    int num)
-{
-	union perf_event *comm_event, *mmap_event, *fork_event;
-	union perf_event *namespaces_event;
-	int err = -1;
-	char *end;
-	pid_t pid;
-	int i;
-
-	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
-	if (comm_event == NULL)
-		goto out;
-
-	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
-	if (mmap_event == NULL)
-		goto out_free_comm;
-
-	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
-	if (fork_event == NULL)
-		goto out_free_mmap;
-
-	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
-				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-				  machine->id_hdr_size);
-	if (namespaces_event == NULL)
-		goto out_free_fork;
-
-	for (i = start; i < start + num; i++) {
-		if (!isdigit(dirent[i]->d_name[0]))
-			continue;
-
-		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
-		/* only interested in proper numerical dirents */
-		if (*end)
-			continue;
-		/*
-		 * We may race with exiting thread, so don't stop just because
-		 * one thread couldn't be synthesized.
-		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event,
-					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data);
-	}
-	err = 0;
-
-	free(namespaces_event);
-out_free_fork:
-	free(fork_event);
-out_free_mmap:
-	free(mmap_event);
-out_free_comm:
-	free(comm_event);
-out:
-	return err;
-}
-
-struct synthesize_threads_arg {
-	struct perf_tool *tool;
-	perf_event__handler_t process;
-	struct machine *machine;
-	bool mmap_data;
-	struct dirent **dirent;
-	int num;
-	int start;
-};
-
-static void *synthesize_threads_worker(void *arg)
-{
-	struct synthesize_threads_arg *args = arg;
-
-	__perf_event__synthesize_threads(args->tool, args->process,
-					 args->machine, args->mmap_data,
-					 args->dirent,
-					 args->start, args->num);
-	return NULL;
-}
-
-int perf_event__synthesize_threads(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine,
-				   bool mmap_data,
-				   unsigned int nr_threads_synthesize)
-{
-	struct synthesize_threads_arg *args = NULL;
-	pthread_t *synthesize_threads = NULL;
-	char proc_path[PATH_MAX];
-	struct dirent **dirent;
-	int num_per_thread;
-	int m, n, i, j;
-	int thread_nr;
-	int base = 0;
-	int err = -1;
-
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	n = scandir(proc_path, &dirent, 0, alphasort);
-	if (n < 0)
-		return err;
-
-	if (nr_threads_synthesize == UINT_MAX)
-		thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
-	else
-		thread_nr = nr_threads_synthesize;
-
-	if (thread_nr <= 1) {
-		err = __perf_event__synthesize_threads(tool, process,
-						       machine, mmap_data,
-						       dirent, base, n);
-		goto free_dirent;
-	}
-	if (thread_nr > n)
-		thread_nr = n;
-
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
-	if (synthesize_threads == NULL)
-		goto free_dirent;
-
-	args = calloc(sizeof(*args), thread_nr);
-	if (args == NULL)
-		goto free_threads;
-
-	num_per_thread = n / thread_nr;
-	m = n % thread_nr;
-	for (i = 0; i < thread_nr; i++) {
-		args[i].tool = tool;
-		args[i].process = process;
-		args[i].machine = machine;
-		args[i].mmap_data = mmap_data;
-		args[i].dirent = dirent;
-	}
-	for (i = 0; i < m; i++) {
-		args[i].num = num_per_thread + 1;
-		args[i].start = i * args[i].num;
-	}
-	if (i != 0)
-		base = args[i-1].start + args[i-1].num;
-	for (j = i; j < thread_nr; j++) {
-		args[j].num = num_per_thread;
-		args[j].start = base + (j - i) * args[i].num;
-	}
-
-	for (i = 0; i < thread_nr; i++) {
-		if (pthread_create(&synthesize_threads[i], NULL,
-				   synthesize_threads_worker, &args[i]))
-			goto out_join;
-	}
-	err = 0;
-out_join:
-	for (i = 0; i < thread_nr; i++)
-		pthread_join(synthesize_threads[i], NULL);
-	free(args);
-free_threads:
-	free(synthesize_threads);
-free_dirent:
-	for (i = 0; i < n; i++)
-		zfree(&dirent[i]);
-	free(dirent);
-
-	return err;
-}
-
 struct process_symbol_args {
 	const char *name;
 	u64	   start;
@@ -899,327 +117,6 @@ int kallsyms__get_function_start(const char *kallsyms_filename,
 	return 0;
 }
 
-int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
-					      perf_event__handler_t process __maybe_unused,
-					      struct machine *machine __maybe_unused)
-{
-	return 0;
-}
-
-static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-						perf_event__handler_t process,
-						struct machine *machine)
-{
-	size_t size;
-	struct map *map = machine__kernel_map(machine);
-	struct kmap *kmap;
-	int err;
-	union perf_event *event;
-
-	if (map == NULL)
-		return -1;
-
-	kmap = map__kmap(map);
-	if (!kmap->ref_reloc_sym)
-		return -1;
-
-	/*
-	 * We should get this from /sys/kernel/sections/.text, but till that is
-	 * available use this, and after it is use this as a fallback for older
-	 * kernels.
-	 */
-	event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
-	if (event == NULL) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for kernel modules\n");
-		return -1;
-	}
-
-	if (machine__is_host(machine)) {
-		/*
-		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
-		 * see kernel/perf_event.c __perf_event_mmap
-		 */
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
-	} else {
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-	}
-
-	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
-	size = PERF_ALIGN(size, sizeof(u64));
-	event->mmap.header.type = PERF_RECORD_MMAP;
-	event->mmap.header.size = (sizeof(event->mmap) -
-			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
-	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
-	event->mmap.start = map->start;
-	event->mmap.len   = map->end - event->mmap.start;
-	event->mmap.pid   = machine->pid;
-
-	err = perf_tool__process_synth_event(tool, event, machine, process);
-	free(event);
-
-	return err;
-}
-
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	int err;
-
-	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
-	if (err < 0)
-		return err;
-
-	return perf_event__synthesize_extra_kmaps(tool, process, machine);
-}
-
-int perf_event__synthesize_thread_map2(struct perf_tool *tool,
-				      struct perf_thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	union perf_event *event;
-	int i, err, size;
-
-	size  = sizeof(event->thread_map);
-	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
-
-	event = zalloc(size);
-	if (!event)
-		return -ENOMEM;
-
-	event->header.type = PERF_RECORD_THREAD_MAP;
-	event->header.size = size;
-	event->thread_map.nr = threads->nr;
-
-	for (i = 0; i < threads->nr; i++) {
-		struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i];
-		char *comm = perf_thread_map__comm(threads, i);
-
-		if (!comm)
-			comm = (char *) "";
-
-		entry->pid = perf_thread_map__pid(threads, i);
-		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
-	}
-
-	err = process(tool, event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-static void synthesize_cpus(struct cpu_map_entries *cpus,
-			    struct perf_cpu_map *map)
-{
-	int i;
-
-	cpus->nr = map->nr;
-
-	for (i = 0; i < map->nr; i++)
-		cpus->cpu[i] = map->map[i];
-}
-
-static void synthesize_mask(struct perf_record_record_cpu_map *mask,
-			    struct perf_cpu_map *map, int max)
-{
-	int i;
-
-	mask->nr = BITS_TO_LONGS(max);
-	mask->long_size = sizeof(long);
-
-	for (i = 0; i < map->nr; i++)
-		set_bit(map->map[i], mask->mask);
-}
-
-static size_t cpus_size(struct perf_cpu_map *map)
-{
-	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
-}
-
-static size_t mask_size(struct perf_cpu_map *map, int *max)
-{
-	int i;
-
-	*max = 0;
-
-	for (i = 0; i < map->nr; i++) {
-		/* bit possition of the cpu is + 1 */
-		int bit = map->map[i] + 1;
-
-		if (bit > *max)
-			*max = bit;
-	}
-
-	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
-}
-
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
-{
-	size_t size_cpus, size_mask;
-	bool is_dummy = perf_cpu_map__empty(map);
-
-	/*
-	 * Both array and mask data have variable size based
-	 * on the number of cpus and their actual values.
-	 * The size of the 'struct perf_record_cpu_map_data' is:
-	 *
-	 *   array = size of 'struct cpu_map_entries' +
-	 *           number of cpus * sizeof(u64)
-	 *
-	 *   mask  = size of 'struct perf_record_record_cpu_map' +
-	 *           maximum cpu bit converted to size of longs
-	 *
-	 * and finaly + the size of 'struct perf_record_cpu_map_data'.
-	 */
-	size_cpus = cpus_size(map);
-	size_mask = mask_size(map, max);
-
-	if (is_dummy || (size_cpus < size_mask)) {
-		*size += size_cpus;
-		*type  = PERF_CPU_MAP__CPUS;
-	} else {
-		*size += size_mask;
-		*type  = PERF_CPU_MAP__MASK;
-	}
-
-	*size += sizeof(struct perf_record_cpu_map_data);
-	*size = PERF_ALIGN(*size, sizeof(u64));
-	return zalloc(*size);
-}
-
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			      u16 type, int max)
-{
-	data->type = type;
-
-	switch (type) {
-	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus((struct cpu_map_entries *) data->data, map);
-		break;
-	case PERF_CPU_MAP__MASK:
-		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
-	default:
-		break;
-	};
-}
-
-static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
-{
-	size_t size = sizeof(struct perf_record_cpu_map);
-	struct perf_record_cpu_map *event;
-	int max;
-	u16 type;
-
-	event = cpu_map_data__alloc(map, &size, &type, &max);
-	if (!event)
-		return NULL;
-
-	event->header.type = PERF_RECORD_CPU_MAP;
-	event->header.size = size;
-	event->data.type   = type;
-
-	cpu_map_data__synthesize(&event->data, map, type, max);
-	return event;
-}
-
-int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct perf_cpu_map *map,
-				   perf_event__handler_t process,
-				   struct machine *machine)
-{
-	struct perf_record_cpu_map *event;
-	int err;
-
-	event = cpu_map_event__new(map);
-	if (!event)
-		return -ENOMEM;
-
-	err = process(tool, (union perf_event *) event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-int perf_event__synthesize_stat_config(struct perf_tool *tool,
-				       struct perf_stat_config *config,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	struct perf_record_stat_config *event;
-	int size, i = 0, err;
-
-	size  = sizeof(*event);
-	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
-
-	event = zalloc(size);
-	if (!event)
-		return -ENOMEM;
-
-	event->header.type = PERF_RECORD_STAT_CONFIG;
-	event->header.size = size;
-	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
-
-#define ADD(__term, __val)					\
-	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
-	event->data[i].val = __val;				\
-	i++;
-
-	ADD(AGGR_MODE,	config->aggr_mode)
-	ADD(INTERVAL,	config->interval)
-	ADD(SCALE,	config->scale)
-
-	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
-		  "stat config terms unbalanced\n");
-#undef ADD
-
-	err = process(tool, (union perf_event *) event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-int perf_event__synthesize_stat(struct perf_tool *tool,
-				u32 cpu, u32 thread, u64 id,
-				struct perf_counts_values *count,
-				perf_event__handler_t process,
-				struct machine *machine)
-{
-	struct perf_record_stat event;
-
-	event.header.type = PERF_RECORD_STAT;
-	event.header.size = sizeof(event);
-	event.header.misc = 0;
-
-	event.id        = id;
-	event.cpu       = cpu;
-	event.thread    = thread;
-	event.val       = count->val;
-	event.ena       = count->ena;
-	event.run       = count->run;
-
-	return process(tool, (union perf_event *) &event, NULL, machine);
-}
-
-int perf_event__synthesize_stat_round(struct perf_tool *tool,
-				      u64 evtime, u64 type,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	struct perf_record_stat_round event;
-
-	event.header.type = PERF_RECORD_STAT_ROUND;
-	event.header.size = sizeof(event);
-	event.header.misc = 0;
-
-	event.time = evtime;
-	event.type = type;
-
-	return process(tool, (union perf_event *) &event, NULL, machine);
-}
-
 void perf_event__read_stat_config(struct perf_stat_config *config,
 				  struct perf_record_stat_config *event)
 {
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 47ad81d47b1a..a0a0c91cde4a 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -279,54 +279,13 @@ enum {
 
 void perf_event__print_totals(void);
 
-struct perf_tool;
-struct perf_thread_map;
 struct perf_cpu_map;
+struct perf_record_stat_config;
 struct perf_stat_config;
-struct perf_counts_values;
-
-typedef int (*perf_event__handler_t)(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_sample *sample,
-				     struct machine *machine);
+struct perf_tool;
 
-int perf_event__synthesize_thread_map(struct perf_tool *tool,
-				      struct perf_thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data);
-int perf_event__synthesize_thread_map2(struct perf_tool *tool,
-				      struct perf_thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct perf_cpu_map *cpus,
-				   perf_event__handler_t process,
-				   struct machine *machine);
-int perf_event__synthesize_threads(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data,
-				   unsigned int nr_threads_synthesize);
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine);
-int perf_event__synthesize_stat_config(struct perf_tool *tool,
-				       struct perf_stat_config *config,
-				       perf_event__handler_t process,
-				       struct machine *machine);
 void perf_event__read_stat_config(struct perf_stat_config *config,
 				  struct perf_record_stat_config *event);
-int perf_event__synthesize_stat(struct perf_tool *tool,
-				u32 cpu, u32 thread, u64 id,
-				struct perf_counts_values *count,
-				perf_event__handler_t process,
-				struct machine *machine);
-int perf_event__synthesize_stat_round(struct perf_tool *tool,
-				      u64 time, u64 type,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-int perf_event__synthesize_modules(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine);
 
 int perf_event__process_comm(struct perf_tool *tool,
 			     union perf_event *event,
@@ -380,10 +339,6 @@ int perf_event__process_bpf(struct perf_tool *tool,
 			    union perf_event *event,
 			    struct perf_sample *sample,
 			    struct machine *machine);
-int perf_tool__process_synth_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct machine *machine,
-				   perf_event__handler_t process);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -405,34 +360,6 @@ void thread__resolve(struct thread *thread, struct addr_location *al,
 
 const char *perf_event__name(unsigned int id);
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 read_format);
-int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 read_format,
-				  const struct perf_sample *sample);
-
-pid_t perf_event__synthesize_comm(struct perf_tool *tool,
-				  union perf_event *event, pid_t pid,
-				  perf_event__handler_t process,
-				  struct machine *machine);
-
-int perf_event__synthesize_namespaces(struct perf_tool *tool,
-				      union perf_event *event,
-				      pid_t pid, pid_t tgid,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-
-int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid,
-				       perf_event__handler_t process,
-				       struct machine *machine,
-				       bool mmap_data);
-
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine);
-
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 095924aa186b..ea9517d506d8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -16,7 +16,7 @@
 #include "evsel.h"
 #include "debug.h"
 #include "units.h"
-#include "util.h"
+#include "util.h" // page_size
 #include "../perf.h"
 #include "asm/bug.h"
 #include "bpf-event.h"
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 85825384f9e8..8e335d168503 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -31,7 +31,7 @@
 #include "event.h"
 #include "evsel.h"
 #include "evlist.h"
-#include "cpumap.h"
+#include <perf/cpumap.h>
 #include "thread_map.h"
 #include "target.h"
 #include "perf_regs.h"
@@ -45,6 +45,7 @@
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
+#include <internal/lib.h>
 
 #include <linux/ctype.h>
 
@@ -2419,283 +2420,6 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
 	return 0;
 }
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 read_format)
-{
-	size_t sz, result = sizeof(struct perf_record_sample);
-
-	if (type & PERF_SAMPLE_IDENTIFIER)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_IP)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TIME)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_ADDR)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_ID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_STREAM_ID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_CPU)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_PERIOD)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_READ) {
-		result += sizeof(u64);
-		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-			result += sizeof(u64);
-		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-			result += sizeof(u64);
-		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
-		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		sz = (sample->callchain->nr + 1) * sizeof(u64);
-		result += sz;
-	}
-
-	if (type & PERF_SAMPLE_RAW) {
-		result += sizeof(u32);
-		result += sample->raw_size;
-	}
-
-	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
-		result += sz;
-	}
-
-	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
-			result += sizeof(u64);
-			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_STACK_USER) {
-		sz = sample->user_stack.size;
-		result += sizeof(u64);
-		if (sz) {
-			result += sz;
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_WEIGHT)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_DATA_SRC)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TRANSACTION)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
-			result += sizeof(u64);
-			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_PHYS_ADDR)
-		result += sizeof(u64);
-
-	return result;
-}
-
-int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 read_format,
-				  const struct perf_sample *sample)
-{
-	__u64 *array;
-	size_t sz;
-	/*
-	 * used for cross-endian analysis. See git commit 65014ab3
-	 * for why this goofiness is needed.
-	 */
-	union u64_swap u;
-
-	array = event->sample.array;
-
-	if (type & PERF_SAMPLE_IDENTIFIER) {
-		*array = sample->id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_IP) {
-		*array = sample->ip;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TID) {
-		u.val32[0] = sample->pid;
-		u.val32[1] = sample->tid;
-		*array = u.val64;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TIME) {
-		*array = sample->time;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ADDR) {
-		*array = sample->addr;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ID) {
-		*array = sample->id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_STREAM_ID) {
-		*array = sample->stream_id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_CPU) {
-		u.val32[0] = sample->cpu;
-		u.val32[1] = 0;
-		*array = u.val64;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_PERIOD) {
-		*array = sample->period;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_READ) {
-		if (read_format & PERF_FORMAT_GROUP)
-			*array = sample->read.group.nr;
-		else
-			*array = sample->read.one.value;
-		array++;
-
-		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-			*array = sample->read.time_enabled;
-			array++;
-		}
-
-		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-			*array = sample->read.time_running;
-			array++;
-		}
-
-		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
-		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			memcpy(array, sample->read.group.values, sz);
-			array = (void *)array + sz;
-		} else {
-			*array = sample->read.one.id;
-			array++;
-		}
-	}
-
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		sz = (sample->callchain->nr + 1) * sizeof(u64);
-		memcpy(array, sample->callchain, sz);
-		array = (void *)array + sz;
-	}
-
-	if (type & PERF_SAMPLE_RAW) {
-		u.val32[0] = sample->raw_size;
-		*array = u.val64;
-		array = (void *)array + sizeof(u32);
-
-		memcpy(array, sample->raw_data, sample->raw_size);
-		array = (void *)array + sample->raw_size;
-	}
-
-	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
-		memcpy(array, sample->branch_stack, sz);
-		array = (void *)array + sz;
-	}
-
-	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
-			*array++ = sample->user_regs.abi;
-			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
-			memcpy(array, sample->user_regs.regs, sz);
-			array = (void *)array + sz;
-		} else {
-			*array++ = 0;
-		}
-	}
-
-	if (type & PERF_SAMPLE_STACK_USER) {
-		sz = sample->user_stack.size;
-		*array++ = sz;
-		if (sz) {
-			memcpy(array, sample->user_stack.data, sz);
-			array = (void *)array + sz;
-			*array++ = sz;
-		}
-	}
-
-	if (type & PERF_SAMPLE_WEIGHT) {
-		*array = sample->weight;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_DATA_SRC) {
-		*array = sample->data_src;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TRANSACTION) {
-		*array = sample->transaction;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
-			*array++ = sample->intr_regs.abi;
-			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
-			memcpy(array, sample->intr_regs.regs, sz);
-			array = (void *)array + sz;
-		} else {
-			*array++ = 0;
-		}
-	}
-
-	if (type & PERF_SAMPLE_PHYS_ADDR) {
-		*array = sample->phys_addr;
-		array++;
-	}
-
-	return 0;
-}
-
 struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 68321d10eb2d..74df298acb31 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -179,11 +179,6 @@ struct evsel {
 	} side_band;
 };
 
-union u64_swap {
-	u64 val64;
-	u32 val32[2];
-};
-
 struct perf_missing_features {
 	bool sample_id_all;
 	bool exclude_guest;
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 496fec01f5d1..a8cbdf4c2753 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -4,6 +4,7 @@
 #include <stdbool.h>
 #include <traceevent/event-parse.h>
 #include "evsel.h"
+#include "util/event.h"
 #include "callchain.h"
 #include "map.h"
 #include "strlist.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b0c34dda30a0..5722ff717777 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -42,11 +42,12 @@
 #include "tool.h"
 #include "time-utils.h"
 #include "units.h"
-#include "util.h"
+#include "util.h" // page_size, perf_exe()
 #include "cputopo.h"
 #include "bpf-event.h"
 
 #include <linux/ctype.h>
+#include <internal/lib.h>
 
 /*
  * magic2 = "PERFILE2"
@@ -70,15 +71,6 @@ struct perf_file_attr {
 	struct perf_file_section	ids;
 };
 
-struct feat_fd {
-	struct perf_header	*ph;
-	int			fd;
-	void			*buf;	/* Either buf != NULL or fd >= 0 */
-	ssize_t			offset;
-	size_t			size;
-	struct evsel	*events;
-};
-
 void perf_header__set_feat(struct perf_header *header, int feat)
 {
 	set_bit(feat, header->adds_features);
@@ -2823,15 +2815,6 @@ static int process_compressed(struct feat_fd *ff,
 	return 0;
 }
 
-struct feature_ops {
-	int (*write)(struct feat_fd *ff, struct evlist *evlist);
-	void (*print)(struct feat_fd *ff, FILE *fp);
-	int (*process)(struct feat_fd *ff, void *data);
-	const char *name;
-	bool full_only;
-	bool synthesize;
-};
-
 #define FEAT_OPR(n, func, __full_only) \
 	[HEADER_##n] = {					\
 		.name	    = __stringify(n),			\
@@ -2858,8 +2841,10 @@ struct feature_ops {
 #define process_branch_stack	NULL
 #define process_stat		NULL
 
+// Only used in util/synthetic-events.c
+const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE];
 
-static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
+const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(TRACING_DATA,	tracing_data,	false),
 	FEAT_OPN(BUILD_ID,	build_id,	false),
 	FEAT_OPR(HOSTNAME,	hostname,	false),
@@ -3656,105 +3641,6 @@ out_delete_evlist:
 	return -ENOMEM;
 }
 
-int perf_event__synthesize_attr(struct perf_tool *tool,
-				struct perf_event_attr *attr, u32 ids, u64 *id,
-				perf_event__handler_t process)
-{
-	union perf_event *ev;
-	size_t size;
-	int err;
-
-	size = sizeof(struct perf_event_attr);
-	size = PERF_ALIGN(size, sizeof(u64));
-	size += sizeof(struct perf_event_header);
-	size += ids * sizeof(u64);
-
-	ev = zalloc(size);
-
-	if (ev == NULL)
-		return -ENOMEM;
-
-	ev->attr.attr = *attr;
-	memcpy(ev->attr.id, id, ids * sizeof(u64));
-
-	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
-	ev->attr.header.size = (u16)size;
-
-	if (ev->attr.header.size == size)
-		err = process(tool, ev, NULL, NULL);
-	else
-		err = -E2BIG;
-
-	free(ev);
-
-	return err;
-}
-
-int perf_event__synthesize_features(struct perf_tool *tool,
-				    struct perf_session *session,
-				    struct evlist *evlist,
-				    perf_event__handler_t process)
-{
-	struct perf_header *header = &session->header;
-	struct feat_fd ff;
-	struct perf_record_header_feature *fe;
-	size_t sz, sz_hdr;
-	int feat, ret;
-
-	sz_hdr = sizeof(fe->header);
-	sz = sizeof(union perf_event);
-	/* get a nice alignment */
-	sz = PERF_ALIGN(sz, page_size);
-
-	memset(&ff, 0, sizeof(ff));
-
-	ff.buf = malloc(sz);
-	if (!ff.buf)
-		return -ENOMEM;
-
-	ff.size = sz - sz_hdr;
-	ff.ph = &session->header;
-
-	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
-		if (!feat_ops[feat].synthesize) {
-			pr_debug("No record header feature for header :%d\n", feat);
-			continue;
-		}
-
-		ff.offset = sizeof(*fe);
-
-		ret = feat_ops[feat].write(&ff, evlist);
-		if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
-			pr_debug("Error writing feature\n");
-			continue;
-		}
-		/* ff.buf may have changed due to realloc in do_write() */
-		fe = ff.buf;
-		memset(fe, 0, sizeof(*fe));
-
-		fe->feat_id = feat;
-		fe->header.type = PERF_RECORD_HEADER_FEATURE;
-		fe->header.size = ff.offset;
-
-		ret = process(tool, ff.buf, NULL, NULL);
-		if (ret) {
-			free(ff.buf);
-			return ret;
-		}
-	}
-
-	/* Send HEADER_LAST_FEATURE mark. */
-	fe = ff.buf;
-	fe->feat_id     = HEADER_LAST_FEATURE;
-	fe->header.type = PERF_RECORD_HEADER_FEATURE;
-	fe->header.size = sizeof(*fe);
-
-	ret = process(tool, ff.buf, NULL, NULL);
-
-	free(ff.buf);
-	return ret;
-}
-
 int perf_event__process_feature(struct perf_session *session,
 				union perf_event *event)
 {
@@ -3797,113 +3683,6 @@ int perf_event__process_feature(struct perf_session *session,
 	return 0;
 }
 
-static struct perf_record_event_update *
-event_update_event__new(size_t size, u64 type, u64 id)
-{
-	struct perf_record_event_update *ev;
-
-	size += sizeof(*ev);
-	size  = PERF_ALIGN(size, sizeof(u64));
-
-	ev = zalloc(size);
-	if (ev) {
-		ev->header.type = PERF_RECORD_EVENT_UPDATE;
-		ev->header.size = (u16)size;
-		ev->type = type;
-		ev->id = id;
-	}
-	return ev;
-}
-
-int
-perf_event__synthesize_event_update_unit(struct perf_tool *tool,
-					 struct evsel *evsel,
-					 perf_event__handler_t process)
-{
-	struct perf_record_event_update *ev;
-	size_t size = strlen(evsel->unit);
-	int err;
-
-	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	strlcpy(ev->data, evsel->unit, size + 1);
-	err = process(tool, (union perf_event *)ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_scale(struct perf_tool *tool,
-					  struct evsel *evsel,
-					  perf_event__handler_t process)
-{
-	struct perf_record_event_update *ev;
-	struct perf_record_event_update_scale *ev_data;
-	int err;
-
-	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	ev_data = (struct perf_record_event_update_scale *)ev->data;
-	ev_data->scale = evsel->scale;
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_name(struct perf_tool *tool,
-					 struct evsel *evsel,
-					 perf_event__handler_t process)
-{
-	struct perf_record_event_update *ev;
-	size_t len = strlen(evsel->name);
-	int err;
-
-	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	strlcpy(ev->data, evsel->name, len + 1);
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
-					struct evsel *evsel,
-					perf_event__handler_t process)
-{
-	size_t size = sizeof(struct perf_record_event_update);
-	struct perf_record_event_update *ev;
-	int max, err;
-	u16 type;
-
-	if (!evsel->core.own_cpus)
-		return 0;
-
-	ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max);
-	if (!ev)
-		return -ENOMEM;
-
-	ev->header.type = PERF_RECORD_EVENT_UPDATE;
-	ev->header.size = (u16)size;
-	ev->type = PERF_EVENT_UPDATE__CPUS;
-	ev->id   = evsel->id[0];
-
-	cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data,
-				 evsel->core.own_cpus,
-				 type, max);
-
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 {
 	struct perf_record_event_update *ev = &event->event_update;
@@ -3943,93 +3722,6 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 	return ret;
 }
 
-int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct evlist *evlist,
-				 perf_event__handler_t process)
-{
-	struct evsel *evsel;
-	int err = 0;
-
-	evlist__for_each_entry(evlist, evsel) {
-		err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->ids,
-						  evsel->id, process);
-		if (err) {
-			pr_debug("failed to create perf header attribute\n");
-			return err;
-		}
-	}
-
-	return err;
-}
-
-static bool has_unit(struct evsel *counter)
-{
-	return counter->unit && *counter->unit;
-}
-
-static bool has_scale(struct evsel *counter)
-{
-	return counter->scale != 1;
-}
-
-int perf_event__synthesize_extra_attr(struct perf_tool *tool,
-				      struct evlist *evsel_list,
-				      perf_event__handler_t process,
-				      bool is_pipe)
-{
-	struct evsel *counter;
-	int err;
-
-	/*
-	 * Synthesize other events stuff not carried within
-	 * attr event - unit, scale, name
-	 */
-	evlist__for_each_entry(evsel_list, counter) {
-		if (!counter->supported)
-			continue;
-
-		/*
-		 * Synthesize unit and scale only if it's defined.
-		 */
-		if (has_unit(counter)) {
-			err = perf_event__synthesize_event_update_unit(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel unit.\n");
-				return err;
-			}
-		}
-
-		if (has_scale(counter)) {
-			err = perf_event__synthesize_event_update_scale(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel counter.\n");
-				return err;
-			}
-		}
-
-		if (counter->core.own_cpus) {
-			err = perf_event__synthesize_event_update_cpus(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel cpus.\n");
-				return err;
-			}
-		}
-
-		/*
-		 * Name is needed only for pipe output,
-		 * perf.data carries event names.
-		 */
-		if (is_pipe) {
-			err = perf_event__synthesize_event_update_name(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel name.\n");
-				return err;
-			}
-		}
-	}
-	return 0;
-}
-
 int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct evlist **pevlist)
@@ -4114,55 +3806,6 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
-					struct evlist *evlist,
-					perf_event__handler_t process)
-{
-	union perf_event ev;
-	struct tracing_data *tdata;
-	ssize_t size = 0, aligned_size = 0, padding;
-	struct feat_fd ff;
-	int err __maybe_unused = 0;
-
-	/*
-	 * We are going to store the size of the data followed
-	 * by the data contents. Since the fd descriptor is a pipe,
-	 * we cannot seek back to store the size of the data once
-	 * we know it. Instead we:
-	 *
-	 * - write the tracing data to the temp file
-	 * - get/write the data size to pipe
-	 * - write the tracing data from the temp file
-	 *   to the pipe
-	 */
-	tdata = tracing_data_get(&evlist->core.entries, fd, true);
-	if (!tdata)
-		return -1;
-
-	memset(&ev, 0, sizeof(ev));
-
-	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-	size = tdata->size;
-	aligned_size = PERF_ALIGN(size, sizeof(u64));
-	padding = aligned_size - size;
-	ev.tracing_data.header.size = sizeof(ev.tracing_data);
-	ev.tracing_data.size = aligned_size;
-
-	process(tool, &ev, NULL, NULL);
-
-	/*
-	 * The put function will copy all the tracing data
-	 * stored in temp file to the pipe.
-	 */
-	tracing_data_put(tdata);
-
-	ff = (struct feat_fd){ .fd = fd };
-	if (write_padded(&ff, NULL, 0, padding))
-		return -1;
-
-	return aligned_size;
-}
-
 int perf_event__process_tracing_data(struct perf_session *session,
 				     union perf_event *event)
 {
@@ -4202,34 +3845,6 @@ int perf_event__process_tracing_data(struct perf_session *session,
 	return size_read + padding;
 }
 
-int perf_event__synthesize_build_id(struct perf_tool *tool,
-				    struct dso *pos, u16 misc,
-				    perf_event__handler_t process,
-				    struct machine *machine)
-{
-	union perf_event ev;
-	size_t len;
-	int err = 0;
-
-	if (!pos->hit)
-		return err;
-
-	memset(&ev, 0, sizeof(ev));
-
-	len = pos->long_name_len + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
-	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
-	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
-	ev.build_id.header.misc = misc;
-	ev.build_id.pid = machine->pid;
-	ev.build_id.header.size = sizeof(ev.build_id) + len;
-	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
-
-	err = process(tool, &ev, NULL, machine);
-
-	return err;
-}
-
 int perf_event__process_build_id(struct perf_session *session,
 				 union perf_event *event)
 {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3e48ae3c49b1..ca53a929e9fd 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -5,10 +5,10 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
+#include <stdio.h> // FILE
 #include <stdbool.h>
 #include <linux/bitmap.h>
 #include <linux/types.h>
-#include "event.h"
 #include "env.h"
 #include "pmu.h"
 
@@ -92,8 +92,28 @@ struct perf_header {
 	struct perf_env 	env;
 };
 
+struct feat_fd {
+	struct perf_header *ph;
+	int		   fd;
+	void		   *buf;	/* Either buf != NULL or fd >= 0 */
+	ssize_t		   offset;
+	size_t		   size;
+	struct evsel	   *events;
+};
+
+struct perf_header_feature_ops {
+	int	   (*write)(struct feat_fd *ff, struct evlist *evlist);
+	void	   (*print)(struct feat_fd *ff, FILE *fp);
+	int	   (*process)(struct feat_fd *ff, void *data);
+	const char *name;
+	bool	   full_only;
+	bool	   synthesize;
+};
+
 struct evlist;
 struct perf_session;
+struct perf_tool;
+union perf_event;
 
 int perf_session__read_header(struct perf_session *session);
 int perf_session__write_header(struct perf_session *session,
@@ -115,54 +135,16 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int perf_event__synthesize_features(struct perf_tool *tool,
-				    struct perf_session *session,
-				    struct evlist *evlist,
-				    perf_event__handler_t process);
-
-int perf_event__synthesize_extra_attr(struct perf_tool *tool,
-				      struct evlist *evsel_list,
-				      perf_event__handler_t process,
-				      bool is_pipe);
-
 int perf_event__process_feature(struct perf_session *session,
 				union perf_event *event);
-
-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 evlist *evlist,
-				 perf_event__handler_t process);
-int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
-					     struct evsel *evsel,
-					     perf_event__handler_t process);
-int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
-					      struct evsel *evsel,
-					      perf_event__handler_t process);
-int perf_event__synthesize_event_update_name(struct perf_tool *tool,
-					     struct evsel *evsel,
-					     perf_event__handler_t process);
-int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
-					     struct evsel *evsel,
-					     perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
 			     struct evlist **pevlist);
 int perf_event__process_event_update(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct evlist **pevlist);
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
-
-int perf_event__synthesize_tracing_data(struct perf_tool *tool,
-					int fd, struct evlist *evlist,
-					perf_event__handler_t process);
 int perf_event__process_tracing_data(struct perf_session *session,
 				     union perf_event *event);
-
-int perf_event__synthesize_build_id(struct perf_tool *tool,
-				    struct dso *pos, u16 misc,
-				    perf_event__handler_t process,
-				    struct machine *machine);
 int perf_event__process_build_id(struct perf_session *session,
 				 union perf_event *event);
 bool is_perf_magic(u64 magic);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 34803e33dc80..6a186b668303 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -15,6 +15,7 @@ struct addr_location;
 struct map_symbol;
 struct mem_info;
 struct branch_info;
+struct branch_stack;
 struct block_info;
 struct symbol;
 struct ui_progress;
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index aacffa2b0362..3888d4cd3ed1 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -14,7 +14,6 @@
 #include <linux/log2.h>
 #include <linux/zalloc.h>
 
-#include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -29,6 +28,7 @@
 #include "auxtrace.h"
 #include "intel-pt-decoder/intel-pt-insn-decoder.h"
 #include "intel-bts.h"
+#include "util/synthetic-events.h"
 
 #define MAX_TIMESTAMP (~0ULL)
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 9b56fb74bedf..bcdc0359f7cf 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -33,6 +33,7 @@
 #include "tsc.h"
 #include "intel-pt.h"
 #include "config.h"
+#include "util/synthetic-events.h"
 #include "time-utils.h"
 
 #include "../arch/x86/include/uapi/asm/perf_regs.h"
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index b80f29bfc7bb..9f9c6c6a2fd3 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -15,7 +15,6 @@
 #include <linux/stringify.h>
 
 #include "build-id.h"
-#include "util.h"
 #include "event.h"
 #include "debug.h"
 #include "evlist.h"
@@ -27,7 +26,6 @@
 #include "jit.h"
 #include "jitdump.h"
 #include "genelf.h"
-#include "../builtin.h"
 
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 46913637085b..6f0fa05b62b6 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -2,6 +2,8 @@
 #ifndef __PERF_KVM_STAT_H
 #define __PERF_KVM_STAT_H
 
+#ifdef HAVE_KVM_STAT_SUPPORT
+
 #include "tool.h"
 #include "stat.h"
 #include "record.h"
@@ -144,5 +146,7 @@ extern const int decode_str_len;
 extern const char *kvm_exit_reason;
 extern const char *kvm_entry_trace;
 extern const char *kvm_exit_trace;
+#endif /* HAVE_KVM_STAT_SUPPORT */
 
+extern int kvm_add_default_arch_event(int *argc, const char **argv);
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 66756e6be111..6b4e5a0892f8 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -22,7 +22,6 @@
 #define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
 
 #include "unwind.h"
-#include "debug.h"
 #include "libunwind-aarch64.h"
 #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
 #include "../../arch/arm64/util/unwind-libunwind.c"
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index c5e568188e19..21c216c40a3b 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -22,7 +22,6 @@
 #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
 #include "unwind.h"
-#include "debug.h"
 #include "libunwind-x86.h"
 #include <../../../../arch/x86/include/uapi/asm/perf_regs.h>
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 55fb4b3b1157..8d04e3d070b1 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -8,6 +8,7 @@
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 397447066033..39062df02629 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -7,10 +7,10 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include "compress.h"
-#include "util.h"
 #include "debug.h"
 #include <string.h>
 #include <unistd.h>
+#include <internal/lib.h>
 
 #define BUFSIZE 8192
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b4749d3eed08..0535338f2d7a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2609,21 +2609,6 @@ int machines__for_each_thread(struct machines *machines,
 	return rc;
 }
 
-int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct target *target, struct perf_thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int nr_threads_synthesize)
-{
-	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
-	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process,
-						      machine, data_mmap,
-						      nr_threads_synthesize);
-	/* command specified */
-	return 0;
-}
-
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
 	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index ffd391a925a6..18e13c0ccd6a 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -6,7 +6,6 @@
 #include <linux/rbtree.h>
 #include "map_groups.h"
 #include "dsos.h"
-#include "event.h"
 #include "rwsem.h"
 
 struct addr_location;
@@ -252,20 +251,6 @@ int machines__for_each_thread(struct machines *machines,
 			      int (*fn)(struct thread *thread, void *p),
 			      void *priv);
 
-int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct target *target, struct perf_thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int nr_threads_synthesize);
-static inline
-int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct perf_thread_map *threads, bool data_mmap,
-				unsigned int nr_threads_synthesize)
-{
-	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap,
-					     nr_threads_synthesize);
-}
-
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h
index 1e29ff903ca9..2c38e8c2d548 100644
--- a/tools/perf/util/memswap.h
+++ b/tools/perf/util/memswap.h
@@ -2,6 +2,13 @@
 #ifndef PERF_MEMSWAP_H_
 #define PERF_MEMSWAP_H_
 
+#include <linux/types.h>
+
+union u64_swap {
+	u64 val64;
+	u32 val32[2];
+};
+
 void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 99be15dd2b6b..285d6f30d912 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -17,8 +17,26 @@
 #include <string.h>
 #include <unistd.h>
 #include <asm/bug.h>
+#include <linux/kernel.h>
 #include <linux/zalloc.h>
 
+static const char *perf_ns__names[] = {
+	[NET_NS_INDEX]		= "net",
+	[UTS_NS_INDEX]		= "uts",
+	[IPC_NS_INDEX]		= "ipc",
+	[PID_NS_INDEX]		= "pid",
+	[USER_NS_INDEX]		= "user",
+	[MNT_NS_INDEX]		= "mnt",
+	[CGROUP_NS_INDEX]	= "cgroup",
+};
+
+const char *perf_ns__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_ns__names))
+		return "UNKNOWN";
+	return perf_ns__names[id];
+}
+
 struct namespaces *namespaces__new(struct perf_record_namespaces *event)
 {
 	struct namespaces *namespaces;
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 40edef56cb52..4b33f684eddd 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -66,4 +66,6 @@ static inline void __nsinfo__zput(struct nsinfo **nsip)
 
 #define nsinfo__zput(nsi) __nsinfo__zput(&nsi)
 
+const char *perf_ns__name(unsigned int id);
+
 #endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5ec21d21113c..a33a1d5059a2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -30,7 +30,6 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c
index e635c594f773..7a0ab3507bd5 100644
--- a/tools/perf/util/perf-hooks.c
+++ b/tools/perf/util/perf-hooks.c
@@ -12,7 +12,6 @@
 #include <setjmp.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/perf-hooks.h"
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index fb597fa94234..5608da82ad23 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -20,7 +20,6 @@
 #include "debug.h"
 #include "pmu.h"
 #include "parse-events.h"
-#include "cpumap.h"
 #include "header.h"
 #include "pmu-events/pmu-events.h"
 #include "string2.h"
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index d13db55a2feb..b659466ea498 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -16,6 +16,7 @@
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
+#include "build-id.h"
 #include "dso.h"
 #include "color.h"
 #include "symbol.h"
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 07ca4535e6f7..0ba19dd75510 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -6,12 +6,10 @@
 #include <linux/err.h>
 #include <perf/cpumap.h>
 #include <traceevent/event-parse.h>
-#include "debug.h"
 #include "evlist.h"
 #include "callchain.h"
 #include "evsel.h"
 #include "event.h"
-#include "cpumap.h"
 #include "print_binary.h"
 #include "thread_map.h"
 #include "trace-event.h"
@@ -61,6 +59,8 @@ int parse_callchain_record(const char *arg __maybe_unused,
  */
 int verbose;
 
+int eprintf(int level, int var, const char *fmt, ...);
+
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 286fe816c0f3..8a015fc0aba0 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,7 +2,6 @@
 #include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "cpumap.h"
 #include "parse-events.h"
 #include <errno.h>
 #include <limits.h>
@@ -10,7 +9,6 @@
 #include <api/fs/fs.h>
 #include <subcmd/parse-options.h>
 #include <perf/cpumap.h>
-#include "util.h"
 #include "cloexec.h"
 #include "record.h"
 #include "../perf-sys.h"
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
index 5e52e7baa7b6..f3d29d8ddc99 100644
--- a/tools/perf/util/rwsem.c
+++ b/tools/perf/util/rwsem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "rwsem.h"
 
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 24a99909d8b3..6785cd87aa4d 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -151,7 +151,6 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 
-#include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
 #include "evlist.h"
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 4d9593e331ea..05b43ab4eeef 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -22,7 +22,6 @@
 #include <asm/byteorder.h>
 
 #include "debug.h"
-#include "util.h"
 #include "session.h"
 #include "evlist.h"
 #include "color.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 666a56e88d8e..5d341efc3237 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -37,7 +37,6 @@
 #include "../dso.h"
 #include "../callchain.h"
 #include "../evsel.h"
-#include "../util.h"
 #include "../event.h"
 #include "../thread.h"
 #include "../comm.h"
@@ -49,7 +48,6 @@
 #include "map.h"
 #include "symbol.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "print_binary.h"
 #include "stat.h"
 #include "mem-events.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index e9e4a04f15db..58b5bc34ba12 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -22,7 +22,6 @@
 #include "symbol.h"
 #include "session.h"
 #include "tool.h"
-#include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
@@ -34,6 +33,7 @@
 #include "ui/progress.h"
 #include "../perf.h"
 #include "arch/common.h"
+#include <internal/lib.h>
 
 #ifdef HAVE_ZSTD_SUPPORT
 static int perf_session__process_compressed_event(struct perf_session *session,
@@ -2412,73 +2412,3 @@ int perf_event__process_id_index(struct perf_session *session,
 	}
 	return 0;
 }
-
-int perf_event__synthesize_id_index(struct perf_tool *tool,
-				    perf_event__handler_t process,
-				    struct evlist *evlist,
-				    struct machine *machine)
-{
-	union perf_event *ev;
-	struct evsel *evsel;
-	size_t nr = 0, i = 0, sz, max_nr, n;
-	int err;
-
-	pr_debug2("Synthesizing id index\n");
-
-	max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) /
-		 sizeof(struct id_index_entry);
-
-	evlist__for_each_entry(evlist, evsel)
-		nr += evsel->ids;
-
-	n = nr > max_nr ? max_nr : nr;
-	sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry);
-	ev = zalloc(sz);
-	if (!ev)
-		return -ENOMEM;
-
-	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
-	ev->id_index.header.size = sz;
-	ev->id_index.nr = n;
-
-	evlist__for_each_entry(evlist, evsel) {
-		u32 j;
-
-		for (j = 0; j < evsel->ids; j++) {
-			struct id_index_entry *e;
-			struct perf_sample_id *sid;
-
-			if (i >= n) {
-				err = process(tool, ev, NULL, machine);
-				if (err)
-					goto out_err;
-				nr -= n;
-				i = 0;
-			}
-
-			e = &ev->id_index.entries[i++];
-
-			e->id = evsel->id[j];
-
-			sid = perf_evlist__id2sid(evlist, e->id);
-			if (!sid) {
-				free(ev);
-				return -ENOENT;
-			}
-
-			e->idx = sid->idx;
-			e->cpu = sid->cpu;
-			e->tid = sid->tid;
-		}
-	}
-
-	sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry);
-	ev->id_index.header.size = sz;
-	ev->id_index.nr = nr;
-
-	err = process(tool, ev, NULL, machine);
-out_err:
-	free(ev);
-
-	return err;
-}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b7aa076ab6fd..b4c9428c18f0 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -138,9 +138,4 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event);
 
-int perf_event__synthesize_id_index(struct perf_tool *tool,
-				    perf_event__handler_t process,
-				    struct evlist *evlist,
-				    struct machine *machine);
-
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c
index adfcf1ff464c..b402f9ca89ab 100644
--- a/tools/perf/util/srccode.c
+++ b/tools/perf/util/srccode.c
@@ -15,7 +15,7 @@
 #include <string.h>
 #include "srccode.h"
 #include "debug.h"
-#include "util.h"
+#include "util.h" // page_size
 
 #define MAXSRCCACHE (32*1024*1024)
 #define MAXSRCFILES     64
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 8f1ea27f976f..fcd54342c04c 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -4,6 +4,7 @@
 #include <math.h>
 #include <string.h>
 #include "counts.h"
+#include "cpumap.h"
 #include "debug.h"
 #include "header.h"
 #include "stat.h"
@@ -161,6 +162,15 @@ static void perf_evsel__free_prev_raw_counts(struct evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel)
+{
+	if (evsel->prev_raw_counts) {
+		evsel->prev_raw_counts->aggr.val = 0;
+		evsel->prev_raw_counts->aggr.ena = 0;
+		evsel->prev_raw_counts->aggr.run = 0;
+       }
+}
+
 static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
@@ -211,6 +221,14 @@ void perf_evlist__reset_stats(struct evlist *evlist)
 	}
 }
 
+void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__reset_prev_raw_counts(evsel);
+}
+
 static void zero_per_pkg(struct evsel *counter)
 {
 	if (counter->per_pkg_mask)
@@ -493,45 +511,3 @@ int create_perf_stat_counter(struct evsel *evsel,
 
 	return perf_evsel__open_per_thread(evsel, evsel->core.threads);
 }
-
-int perf_stat_synthesize_config(struct perf_stat_config *config,
-				struct perf_tool *tool,
-				struct 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->core.threads,
-						 process, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_cpu_map(tool, evlist->core.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 14fe3e548229..edbeb2f63e8d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -7,8 +7,9 @@
 #include <sys/types.h>
 #include <sys/resource.h>
 #include "rblist.h"
-#include "event.h"
 
+struct perf_cpu_map;
+struct perf_stat_config;
 struct timespec;
 
 struct stats {
@@ -192,6 +193,7 @@ void perf_stat__collect_metric_expr(struct evlist *);
 int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct evlist *evlist);
 void perf_evlist__reset_stats(struct evlist *evlist);
+void perf_evlist__reset_prev_raw_counts(struct evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct evsel *counter);
@@ -210,11 +212,6 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 int create_perf_stat_counter(struct 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 evlist *evlist,
-				perf_event__handler_t process,
-				bool attrs);
 void
 perf_evlist__print_counters(struct evlist *evlist,
 			    struct perf_stat_config *config,
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 582f4a69cd48..96f941e01681 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,11 +17,11 @@
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "env.h"
 #include "svghelper.h"
-#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 9428639872a6..6fbfdf8bf61f 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -7,6 +7,7 @@
 #include <unistd.h>
 #include <inttypes.h>
 
+#include "dso.h"
 #include "map.h"
 #include "map_groups.h"
 #include "symbol.h"
@@ -18,8 +19,10 @@
 #include "debug.h"
 #include "util.h"
 #include <linux/ctype.h>
+#include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <symbol/kallsyms.h>
+#include <internal/lib.h>
 
 #ifndef EM_AARCH64
 #define EM_AARCH64	183  /* ARM 64 bit */
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 7e2813ec9498..d6e99af263ec 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,8 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
 #include "dso.h"
 #include "symbol.h"
 #include "symsrc.h"
-#include "util.h"
 
 #include <errno.h>
 #include <unistd.h>
@@ -13,6 +11,7 @@
 #include <byteswap.h>
 #include <sys/stat.h>
 #include <linux/zalloc.h>
+#include <internal/lib.h>
 
 static bool check_need_swap(int file_endian)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 765c75df2904..a8f80e427674 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -19,7 +19,7 @@
 #include "build-id.h"
 #include "cap.h"
 #include "dso.h"
-#include "util.h"
+#include "util.h" // lsdir()
 #include "debug.h"
 #include "event.h"
 #include "machine.h"
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
new file mode 100644
index 000000000000..8322028a9a97
--- /dev/null
+++ b/tools/perf/util/synthetic-events.c
@@ -0,0 +1,1884 @@
+// SPDX-License-Identifier: GPL-2.0-only 
+
+#include "util/debug.h"
+#include "util/dso.h"
+#include "util/event.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/map.h"
+#include "util/map_symbol.h"
+#include "util/branch.h"
+#include "util/memswap.h"
+#include "util/namespaces.h"
+#include "util/session.h"
+#include "util/stat.h"
+#include "util/symbol.h"
+#include "util/synthetic-events.h"
+#include "util/target.h"
+#include "util/time-utils.h"
+#include "util/util.h"
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <linux/perf_event.h>
+#include <asm/bug.h>
+#include <perf/evsel.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
+#include <internal/threadmap.h>
+#include <perf/threadmap.h>
+#include <symbol/kallsyms.h>
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <string.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <api/fs/fs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
+
+unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT;
+
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
+		.pid	   = -1,
+		.tid	   = -1,
+		.time	   = -1,
+		.stream_id = -1,
+		.cpu	   = -1,
+		.period	   = 1,
+		.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
+};
+
+/*
+ * Assumes that the first 4095 bytes of /proc/pid/stat contains
+ * the comm, tgid and ppid.
+ */
+static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
+				    pid_t *tgid, pid_t *ppid)
+{
+	char filename[PATH_MAX];
+	char bf[4096];
+	int fd;
+	size_t size = 0;
+	ssize_t n;
+	char *name, *tgids, *ppids;
+
+	*tgid = -1;
+	*ppid = -1;
+
+	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0) {
+		pr_debug("couldn't open %s\n", filename);
+		return -1;
+	}
+
+	n = read(fd, bf, sizeof(bf) - 1);
+	close(fd);
+	if (n <= 0) {
+		pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
+			   pid);
+		return -1;
+	}
+	bf[n] = '\0';
+
+	name = strstr(bf, "Name:");
+	tgids = strstr(bf, "Tgid:");
+	ppids = strstr(bf, "PPid:");
+
+	if (name) {
+		char *nl;
+
+		name = skip_spaces(name + 5);  /* strlen("Name:") */
+		nl = strchr(name, '\n');
+		if (nl)
+			*nl = '\0';
+
+		size = strlen(name);
+		if (size >= len)
+			size = len - 1;
+		memcpy(comm, name, size);
+		comm[size] = '\0';
+	} else {
+		pr_debug("Name: string not found for pid %d\n", pid);
+	}
+
+	if (tgids) {
+		tgids += 5;  /* strlen("Tgid:") */
+		*tgid = atoi(tgids);
+	} else {
+		pr_debug("Tgid: string not found for pid %d\n", pid);
+	}
+
+	if (ppids) {
+		ppids += 5;  /* strlen("PPid:") */
+		*ppid = atoi(ppids);
+	} else {
+		pr_debug("PPid: string not found for pid %d\n", pid);
+	}
+
+	return 0;
+}
+
+static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
+				    struct machine *machine,
+				    pid_t *tgid, pid_t *ppid)
+{
+	size_t size;
+
+	*ppid = -1;
+
+	memset(&event->comm, 0, sizeof(event->comm));
+
+	if (machine__is_host(machine)) {
+		if (perf_event__get_comm_ids(pid, event->comm.comm,
+					     sizeof(event->comm.comm),
+					     tgid, ppid) != 0) {
+			return -1;
+		}
+	} else {
+		*tgid = machine->pid;
+	}
+
+	if (*tgid < 0)
+		return -1;
+
+	event->comm.pid = *tgid;
+	event->comm.header.type = PERF_RECORD_COMM;
+
+	size = strlen(event->comm.comm) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	memset(event->comm.comm + size, 0, machine->id_hdr_size);
+	event->comm.header.size = (sizeof(event->comm) -
+				(sizeof(event->comm.comm) - size) +
+				machine->id_hdr_size);
+	event->comm.tid = pid;
+
+	return 0;
+}
+
+pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+					 union perf_event *event, pid_t pid,
+					 perf_event__handler_t process,
+					 struct machine *machine)
+{
+	pid_t tgid, ppid;
+
+	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
+		return -1;
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return tgid;
+}
+
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+					 struct perf_ns_link_info *ns_link_info)
+{
+	struct stat64 st;
+	char proc_ns[128];
+
+	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+	if (stat64(proc_ns, &st) == 0) {
+		ns_link_info->dev = st.st_dev;
+		ns_link_info->ino = st.st_ino;
+	}
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	u32 idx;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!tool || !tool->namespace_events)
+		return 0;
+
+	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+	       machine->id_hdr_size));
+
+	event->namespaces.pid = tgid;
+	event->namespaces.tid = pid;
+
+	event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+	ns_link_info = event->namespaces.link_info;
+
+	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+					     &ns_link_info[idx]);
+
+	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+	event->namespaces.header.size = (sizeof(event->namespaces) +
+			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
+static int perf_event__synthesize_fork(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid, pid_t ppid,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
+
+	/*
+	 * for main thread set parent to ppid from status file. For other
+	 * threads set parent pid to main thread. ie., assume main thread
+	 * spawns all threads in a process
+	*/
+	if (tgid == pid) {
+		event->fork.ppid = ppid;
+		event->fork.ptid = ppid;
+	} else {
+		event->fork.ppid = tgid;
+		event->fork.ptid = tgid;
+	}
+	event->fork.pid  = tgid;
+	event->fork.tid  = pid;
+	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
+
+	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data)
+{
+	char filename[PATH_MAX];
+	FILE *fp;
+	unsigned long long t;
+	bool truncation = false;
+	unsigned long long timeout = proc_map_timeout * 1000000ULL;
+	int rc = 0;
+	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
+	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
+		 machine->root_dir, pid, pid);
+
+	fp = fopen(filename, "r");
+	if (fp == NULL) {
+		/*
+		 * We raced with a task exiting - just return:
+		 */
+		pr_debug("couldn't open %s\n", filename);
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
+
+	while (1) {
+		char bf[BUFSIZ];
+		char prot[5];
+		char execname[PATH_MAX];
+		char anonstr[] = "//anon";
+		unsigned int ino;
+		size_t size;
+		ssize_t n;
+
+		if (fgets(bf, sizeof(bf), fp) == NULL)
+			break;
+
+		if ((rdclock() - t) > timeout) {
+			pr_warning("Reading %s time out. "
+				   "You may want to increase "
+				   "the time limit by --proc-map-timeout\n",
+				   filename);
+			truncation = true;
+			goto out;
+		}
+
+		/* ensure null termination since stack will be reused. */
+		strcpy(execname, "");
+
+		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
+		n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
+		/*
+ 		 * Anon maps don't have the execname.
+ 		 */
+		if (n < 7)
+			continue;
+
+		event->mmap2.ino = (u64)ino;
+
+		/*
+		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_USER;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
+
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
+		if (prot[2] != 'x') {
+			if (!mmap_data || prot[0] != 'r')
+				continue;
+
+			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+		}
+
+out:
+		if (truncation)
+			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
+		if (!strcmp(execname, ""))
+			strcpy(execname, anonstr);
+
+		if (hugetlbfs_mnt_len &&
+		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
+			strcpy(execname, anonstr);
+			event->mmap2.flags |= MAP_HUGETLB;
+		}
+
+		size = strlen(execname) + 1;
+		memcpy(event->mmap2.filename, execname, size);
+		size = PERF_ALIGN(size, sizeof(u64));
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
+
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
+			rc = -1;
+			break;
+		}
+
+		if (truncation)
+			break;
+	}
+
+	fclose(fp);
+	return rc;
+}
+
+int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
+				   struct machine *machine)
+{
+	int rc = 0;
+	struct map *pos;
+	struct maps *maps = machine__kernel_maps(machine);
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP;
+
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		size_t size;
+
+		if (!__map__is_kmodule(pos))
+			continue;
+
+		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+				        (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+		event->mmap.header.size += machine->id_hdr_size;
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pid   = machine->pid;
+
+		memcpy(event->mmap.filename, pos->dso->long_name,
+		       pos->dso->long_name_len + 1);
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
+			rc = -1;
+			break;
+		}
+	}
+
+	free(event);
+	return rc;
+}
+
+static int __event__synthesize_thread(union perf_event *comm_event,
+				      union perf_event *mmap_event,
+				      union perf_event *fork_event,
+				      union perf_event *namespaces_event,
+				      pid_t pid, int full, perf_event__handler_t process,
+				      struct perf_tool *tool, struct machine *machine, bool mmap_data)
+{
+	char filename[PATH_MAX];
+	DIR *tasks;
+	struct dirent *dirent;
+	pid_t tgid, ppid;
+	int rc = 0;
+
+	/* special case: only send one comm event using passed in pid */
+	if (!full) {
+		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
+						   process, machine);
+
+		if (tgid == -1)
+			return -1;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+						      tgid, process, machine) < 0)
+			return -1;
+
+		/*
+		 * send mmap only for thread group leader
+		 * see thread__init_map_groups
+		 */
+		if (pid == tgid &&
+		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						       process, machine, mmap_data))
+			return -1;
+
+		return 0;
+	}
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
+
+	tasks = opendir(filename);
+	if (tasks == NULL) {
+		pr_debug("couldn't open %s\n", filename);
+		return 0;
+	}
+
+	while ((dirent = readdir(tasks)) != NULL) {
+		char *end;
+		pid_t _pid;
+
+		_pid = strtol(dirent->d_name, &end, 10);
+		if (*end)
+			continue;
+
+		rc = -1;
+		if (perf_event__prepare_comm(comm_event, _pid, machine,
+					     &tgid, &ppid) != 0)
+			break;
+
+		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
+						ppid, process, machine) < 0)
+			break;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+						      tgid, process, machine) < 0)
+			break;
+
+		/*
+		 * Send the prepared comm event
+		 */
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
+			break;
+
+		rc = 0;
+		if (_pid == pid) {
+			/* process the parent's maps too */
+			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						process, machine, mmap_data);
+			if (rc)
+				break;
+		}
+	}
+
+	closedir(tasks);
+	return rc;
+}
+
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+				      struct perf_thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      bool mmap_data)
+{
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
+	int err = -1, thread, j;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
+	err = 0;
+	for (thread = 0; thread < threads->nr; ++thread) {
+		if (__event__synthesize_thread(comm_event, mmap_event,
+					       fork_event, namespaces_event,
+					       perf_thread_map__pid(threads, thread), 0,
+					       process, tool, machine,
+					       mmap_data)) {
+			err = -1;
+			break;
+		}
+
+		/*
+		 * comm.pid is set to thread group id by
+		 * perf_event__synthesize_comm
+		 */
+		if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) {
+			bool need_leader = true;
+
+			/* is thread group leader in thread_map? */
+			for (j = 0; j < threads->nr; ++j) {
+				if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) {
+					need_leader = false;
+					break;
+				}
+			}
+
+			/* if not, generate events for it */
+			if (need_leader &&
+			    __event__synthesize_thread(comm_event, mmap_event,
+						       fork_event, namespaces_event,
+						       comm_event->comm.pid, 0,
+						       process, tool, machine,
+						       mmap_data)) {
+				err = -1;
+				break;
+			}
+		}
+	}
+	free(namespaces_event);
+out_free_fork:
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
+}
+
+static int __perf_event__synthesize_threads(struct perf_tool *tool,
+					    perf_event__handler_t process,
+					    struct machine *machine,
+					    bool mmap_data,
+					    struct dirent **dirent,
+					    int start,
+					    int num)
+{
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
+	int err = -1;
+	char *end;
+	pid_t pid;
+	int i;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
+	for (i = start; i < start + num; i++) {
+		if (!isdigit(dirent[i]->d_name[0]))
+			continue;
+
+		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+		/* only interested in proper numerical dirents */
+		if (*end)
+			continue;
+		/*
+		 * We may race with exiting thread, so don't stop just because
+		 * one thread couldn't be synthesized.
+		 */
+		__event__synthesize_thread(comm_event, mmap_event, fork_event,
+					   namespaces_event, pid, 1, process,
+					   tool, machine, mmap_data);
+	}
+	err = 0;
+
+	free(namespaces_event);
+out_free_fork:
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
+}
+
+struct synthesize_threads_arg {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	bool mmap_data;
+	struct dirent **dirent;
+	int num;
+	int start;
+};
+
+static void *synthesize_threads_worker(void *arg)
+{
+	struct synthesize_threads_arg *args = arg;
+
+	__perf_event__synthesize_threads(args->tool, args->process,
+					 args->machine, args->mmap_data,
+					 args->dirent,
+					 args->start, args->num);
+	return NULL;
+}
+
+int perf_event__synthesize_threads(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int nr_threads_synthesize)
+{
+	struct synthesize_threads_arg *args = NULL;
+	pthread_t *synthesize_threads = NULL;
+	char proc_path[PATH_MAX];
+	struct dirent **dirent;
+	int num_per_thread;
+	int m, n, i, j;
+	int thread_nr;
+	int base = 0;
+	int err = -1;
+
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+	n = scandir(proc_path, &dirent, 0, alphasort);
+	if (n < 0)
+		return err;
+
+	if (nr_threads_synthesize == UINT_MAX)
+		thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
+	else
+		thread_nr = nr_threads_synthesize;
+
+	if (thread_nr <= 1) {
+		err = __perf_event__synthesize_threads(tool, process,
+						       machine, mmap_data,
+						       dirent, base, n);
+		goto free_dirent;
+	}
+	if (thread_nr > n)
+		thread_nr = n;
+
+	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	if (synthesize_threads == NULL)
+		goto free_dirent;
+
+	args = calloc(sizeof(*args), thread_nr);
+	if (args == NULL)
+		goto free_threads;
+
+	num_per_thread = n / thread_nr;
+	m = n % thread_nr;
+	for (i = 0; i < thread_nr; i++) {
+		args[i].tool = tool;
+		args[i].process = process;
+		args[i].machine = machine;
+		args[i].mmap_data = mmap_data;
+		args[i].dirent = dirent;
+	}
+	for (i = 0; i < m; i++) {
+		args[i].num = num_per_thread + 1;
+		args[i].start = i * args[i].num;
+	}
+	if (i != 0)
+		base = args[i-1].start + args[i-1].num;
+	for (j = i; j < thread_nr; j++) {
+		args[j].num = num_per_thread;
+		args[j].start = base + (j - i) * args[i].num;
+	}
+
+	for (i = 0; i < thread_nr; i++) {
+		if (pthread_create(&synthesize_threads[i], NULL,
+				   synthesize_threads_worker, &args[i]))
+			goto out_join;
+	}
+	err = 0;
+out_join:
+	for (i = 0; i < thread_nr; i++)
+		pthread_join(synthesize_threads[i], NULL);
+	free(args);
+free_threads:
+	free(synthesize_threads);
+free_dirent:
+	for (i = 0; i < n; i++)
+		zfree(&dirent[i]);
+	free(dirent);
+
+	return err;
+}
+
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+					      perf_event__handler_t process __maybe_unused,
+					      struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+						perf_event__handler_t process,
+						struct machine *machine)
+{
+	size_t size;
+	struct map *map = machine__kernel_map(machine);
+	struct kmap *kmap;
+	int err;
+	union perf_event *event;
+
+	if (map == NULL)
+		return -1;
+
+	kmap = map__kmap(map);
+	if (!kmap->ref_reloc_sym)
+		return -1;
+
+	/*
+	 * We should get this from /sys/kernel/sections/.text, but till that is
+	 * available use this, and after it is use this as a fallback for older
+	 * kernels.
+	 */
+	event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	if (machine__is_host(machine)) {
+		/*
+		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
+		 * see kernel/perf_event.c __perf_event_mmap
+		 */
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	} else {
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+	}
+
+	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
+			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = (sizeof(event->mmap) -
+			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
+	event->mmap.start = map->start;
+	event->mmap.len   = map->end - event->mmap.start;
+	event->mmap.pid   = machine->pid;
+
+	err = perf_tool__process_synth_event(tool, event, machine, process);
+	free(event);
+
+	return err;
+}
+
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int err;
+
+	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+	if (err < 0)
+		return err;
+
+	return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct perf_thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	union perf_event *event;
+	int i, err, size;
+
+	size  = sizeof(event->thread_map);
+	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_THREAD_MAP;
+	event->header.size = size;
+	event->thread_map.nr = threads->nr;
+
+	for (i = 0; i < threads->nr; i++) {
+		struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i];
+		char *comm = perf_thread_map__comm(threads, i);
+
+		if (!comm)
+			comm = (char *) "";
+
+		entry->pid = perf_thread_map__pid(threads, i);
+		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+	}
+
+	err = process(tool, event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+			    struct perf_cpu_map *map)
+{
+	int i;
+
+	cpus->nr = map->nr;
+
+	for (i = 0; i < map->nr; i++)
+		cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct perf_record_record_cpu_map *mask,
+			    struct perf_cpu_map *map, int max)
+{
+	int i;
+
+	mask->nr = BITS_TO_LONGS(max);
+	mask->long_size = sizeof(long);
+
+	for (i = 0; i < map->nr; i++)
+		set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct perf_cpu_map *map)
+{
+	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct perf_cpu_map *map, int *max)
+{
+	int i;
+
+	*max = 0;
+
+	for (i = 0; i < map->nr; i++) {
+		/* bit possition of the cpu is + 1 */
+		int bit = map->map[i] + 1;
+
+		if (bit > *max)
+			*max = bit;
+	}
+
+	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+{
+	size_t size_cpus, size_mask;
+	bool is_dummy = perf_cpu_map__empty(map);
+
+	/*
+	 * Both array and mask data have variable size based
+	 * on the number of cpus and their actual values.
+	 * The size of the 'struct perf_record_cpu_map_data' is:
+	 *
+	 *   array = size of 'struct cpu_map_entries' +
+	 *           number of cpus * sizeof(u64)
+	 *
+	 *   mask  = size of 'struct perf_record_record_cpu_map' +
+	 *           maximum cpu bit converted to size of longs
+	 *
+	 * and finaly + the size of 'struct perf_record_cpu_map_data'.
+	 */
+	size_cpus = cpus_size(map);
+	size_mask = mask_size(map, max);
+
+	if (is_dummy || (size_cpus < size_mask)) {
+		*size += size_cpus;
+		*type  = PERF_CPU_MAP__CPUS;
+	} else {
+		*size += size_mask;
+		*type  = PERF_CPU_MAP__MASK;
+	}
+
+	*size += sizeof(struct perf_record_cpu_map_data);
+	*size = PERF_ALIGN(*size, sizeof(u64));
+	return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
+			      u16 type, int max)
+{
+	data->type = type;
+
+	switch (type) {
+	case PERF_CPU_MAP__CPUS:
+		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		break;
+	case PERF_CPU_MAP__MASK:
+		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+	default:
+		break;
+	};
+}
+
+static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+{
+	size_t size = sizeof(struct perf_record_cpu_map);
+	struct perf_record_cpu_map *event;
+	int max;
+	u16 type;
+
+	event = cpu_map_data__alloc(map, &size, &type, &max);
+	if (!event)
+		return NULL;
+
+	event->header.type = PERF_RECORD_CPU_MAP;
+	event->header.size = size;
+	event->data.type   = type;
+
+	cpu_map_data__synthesize(&event->data, map, type, max);
+	return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct perf_cpu_map *map,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	struct perf_record_cpu_map *event;
+	int err;
+
+	event = cpu_map_event__new(map);
+	if (!event)
+		return -ENOMEM;
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	struct perf_record_stat_config *event;
+	int size, i = 0, err;
+
+	size  = sizeof(*event);
+	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_STAT_CONFIG;
+	event->header.size = size;
+	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)					\
+	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
+	event->data[i].val = __val;				\
+	i++;
+
+	ADD(AGGR_MODE,	config->aggr_mode)
+	ADD(INTERVAL,	config->interval)
+	ADD(SCALE,	config->scale)
+
+	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+		  "stat config terms unbalanced\n");
+#undef ADD
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	struct perf_record_stat event;
+
+	event.header.type = PERF_RECORD_STAT;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.id        = id;
+	event.cpu       = cpu;
+	event.thread    = thread;
+	event.val       = count->val;
+	event.ena       = count->ena;
+	event.run       = count->run;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 evtime, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	struct perf_record_stat_round event;
+
+	event.header.type = PERF_RECORD_STAT_ROUND;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.time = evtime;
+	event.type = type;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format)
+{
+	size_t sz, result = sizeof(struct perf_record_sample);
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_IP)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TIME)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ADDR)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_CPU)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_READ) {
+		result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			result += sizeof(u64);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		result += sizeof(u32);
+		result += sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		result += sizeof(u64);
+		if (sz) {
+			result += sz;
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_PHYS_ADDR)
+		result += sizeof(u64);
+
+	return result;
+}
+
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
+				  const struct perf_sample *sample)
+{
+	__u64 *array;
+	size_t sz;
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union u64_swap u;
+
+	array = event->sample.array;
+
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_IP) {
+		*array = sample->ip;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val32[0] = sample->pid;
+		u.val32[1] = sample->tid;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		*array = sample->time;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ADDR) {
+		*array = sample->addr;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		*array = sample->stream_id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u.val32[0] = sample->cpu;
+		u.val32[1] = 0;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		*array = sample->period;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			*array = sample->read.group.nr;
+		else
+			*array = sample->read.one.value;
+		array++;
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			*array = sample->read.time_enabled;
+			array++;
+		}
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			*array = sample->read.time_running;
+			array++;
+		}
+
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			memcpy(array, sample->read.group.values, sz);
+			array = (void *)array + sz;
+		} else {
+			*array = sample->read.one.id;
+			array++;
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		memcpy(array, sample->callchain, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		u.val32[0] = sample->raw_size;
+		*array = u.val64;
+		array = (void *)array + sizeof(u32);
+
+		memcpy(array, sample->raw_data, sample->raw_size);
+		array = (void *)array + sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		memcpy(array, sample->branch_stack, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			*array++ = sample->user_regs.abi;
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
+			memcpy(array, sample->user_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		*array++ = sz;
+		if (sz) {
+			memcpy(array, sample->user_stack.data, sz);
+			array = (void *)array + sz;
+			*array++ = sz;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT) {
+		*array = sample->weight;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		*array = sample->data_src;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		*array = sample->transaction;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			*array++ = sample->intr_regs.abi;
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
+			memcpy(array, sample->intr_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_PHYS_ADDR) {
+		*array = sample->phys_addr;
+		array++;
+	}
+
+	return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
+				    struct evlist *evlist, struct machine *machine)
+{
+	union perf_event *ev;
+	struct evsel *evsel;
+	size_t nr = 0, i = 0, sz, max_nr, n;
+	int err;
+
+	pr_debug2("Synthesizing id index\n");
+
+	max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) /
+		 sizeof(struct id_index_entry);
+
+	evlist__for_each_entry(evlist, evsel)
+		nr += evsel->ids;
+
+	n = nr > max_nr ? max_nr : nr;
+	sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry);
+	ev = zalloc(sz);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = n;
+
+	evlist__for_each_entry(evlist, evsel) {
+		u32 j;
+
+		for (j = 0; j < evsel->ids; j++) {
+			struct id_index_entry *e;
+			struct perf_sample_id *sid;
+
+			if (i >= n) {
+				err = process(tool, ev, NULL, machine);
+				if (err)
+					goto out_err;
+				nr -= n;
+				i = 0;
+			}
+
+			e = &ev->id_index.entries[i++];
+
+			e->id = evsel->id[j];
+
+			sid = perf_evlist__id2sid(evlist, e->id);
+			if (!sid) {
+				free(ev);
+				return -ENOENT;
+			}
+
+			e->idx = sid->idx;
+			e->cpu = sid->cpu;
+			e->tid = sid->tid;
+		}
+	}
+
+	sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry);
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = nr;
+
+	err = process(tool, ev, NULL, machine);
+out_err:
+	free(ev);
+
+	return err;
+}
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct perf_thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int nr_threads_synthesize)
+{
+	if (target__has_task(target))
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+	else if (target__has_cpu(target))
+		return perf_event__synthesize_threads(tool, process,
+						      machine, data_mmap,
+						      nr_threads_synthesize);
+	/* command specified */
+	return 0;
+}
+
+int machine__synthesize_threads(struct machine *machine, struct target *target,
+				struct perf_thread_map *threads, bool data_mmap,
+				unsigned int nr_threads_synthesize)
+{
+	return __machine__synthesize_threads(machine, NULL, target, threads,
+					     perf_event__process, data_mmap,
+					     nr_threads_synthesize);
+}
+
+static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id)
+{
+	struct perf_record_event_update *ev;
+
+	size += sizeof(*ev);
+	size  = PERF_ALIGN(size, sizeof(u64));
+
+	ev = zalloc(size);
+	if (ev) {
+		ev->header.type = PERF_RECORD_EVENT_UPDATE;
+		ev->header.size = (u16)size;
+		ev->type	= type;
+		ev->id		= id;
+	}
+	return ev;
+}
+
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	size_t size = strlen(evsel->unit);
+	struct perf_record_event_update *ev;
+	int err;
+
+	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strlcpy(ev->data, evsel->unit, size + 1);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel,
+					      perf_event__handler_t process)
+{
+	struct perf_record_event_update *ev;
+	struct perf_record_event_update_scale *ev_data;
+	int err;
+
+	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev_data = (struct perf_record_event_update_scale *)ev->data;
+	ev_data->scale = evsel->scale;
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	struct perf_record_event_update *ev;
+	size_t len = strlen(evsel->name);
+	int err;
+
+	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strlcpy(ev->data, evsel->name, len + 1);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	size_t size = sizeof(struct perf_record_event_update);
+	struct perf_record_event_update *ev;
+	int max, err;
+	u16 type;
+
+	if (!evsel->core.own_cpus)
+		return 0;
+
+	ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->header.type = PERF_RECORD_EVENT_UPDATE;
+	ev->header.size = (u16)size;
+	ev->type	= PERF_EVENT_UPDATE__CPUS;
+	ev->id		= evsel->id[0];
+
+	cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data,
+				 evsel->core.own_cpus, type, max);
+
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist,
+				 perf_event__handler_t process)
+{
+	struct evsel *evsel;
+	int err = 0;
+
+	evlist__for_each_entry(evlist, evsel) {
+		err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->ids,
+						  evsel->id, process);
+		if (err) {
+			pr_debug("failed to create perf header attribute\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+static bool has_unit(struct evsel *evsel)
+{
+	return evsel->unit && *evsel->unit;
+}
+
+static bool has_scale(struct evsel *evsel)
+{
+	return evsel->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list,
+				      perf_event__handler_t process, bool is_pipe)
+{
+	struct evsel *evsel;
+	int err;
+
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each_entry(evsel_list, evsel) {
+		if (!evsel->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(evsel)) {
+			err = perf_event__synthesize_event_update_unit(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(evsel)) {
+			err = perf_event__synthesize_event_update_scale(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel evsel.\n");
+				return err;
+			}
+		}
+
+		if (evsel->core.own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel cpus.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr,
+				u32 ids, u64 *id, perf_event__handler_t process)
+{
+	union perf_event *ev;
+	size_t size;
+	int err;
+
+	size = sizeof(struct perf_event_attr);
+	size = PERF_ALIGN(size, sizeof(u64));
+	size += sizeof(struct perf_event_header);
+	size += ids * sizeof(u64);
+
+	ev = zalloc(size);
+
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev->attr.attr = *attr;
+	memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+	ev->attr.header.size = (u16)size;
+
+	if (ev->attr.header.size == size)
+		err = process(tool, ev, NULL, NULL);
+	else
+		err = -E2BIG;
+
+	free(ev);
+
+	return err;
+}
+
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist,
+					perf_event__handler_t process)
+{
+	union perf_event ev;
+	struct tracing_data *tdata;
+	ssize_t size = 0, aligned_size = 0, padding;
+	struct feat_fd ff;
+
+	/*
+	 * We are going to store the size of the data followed
+	 * by the data contents. Since the fd descriptor is a pipe,
+	 * we cannot seek back to store the size of the data once
+	 * we know it. Instead we:
+	 *
+	 * - write the tracing data to the temp file
+	 * - get/write the data size to pipe
+	 * - write the tracing data from the temp file
+	 *   to the pipe
+	 */
+	tdata = tracing_data_get(&evlist->core.entries, fd, true);
+	if (!tdata)
+		return -1;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+	size = tdata->size;
+	aligned_size = PERF_ALIGN(size, sizeof(u64));
+	padding = aligned_size - size;
+	ev.tracing_data.header.size = sizeof(ev.tracing_data);
+	ev.tracing_data.size = aligned_size;
+
+	process(tool, &ev, NULL, NULL);
+
+	/*
+	 * The put function will copy all the tracing data
+	 * stored in temp file to the pipe.
+	 */
+	tracing_data_put(tdata);
+
+	ff = (struct feat_fd){ .fd = fd };
+	if (write_padded(&ff, NULL, 0, padding))
+		return -1;
+
+	return aligned_size;
+}
+
+int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc,
+				    perf_event__handler_t process, struct machine *machine)
+{
+	union perf_event ev;
+	size_t len;
+
+	if (!pos->hit)
+		return 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	len = pos->long_name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+	ev.build_id.header.misc = misc;
+	ev.build_id.pid = machine->pid;
+	ev.build_id.header.size = sizeof(ev.build_id) + len;
+	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+	return process(tool, &ev, NULL, machine);
+}
+
+int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool,
+				       struct 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->core.threads, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->core.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;
+}
+
+int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
+				       struct perf_tool *tool __maybe_unused,
+				       perf_event__handler_t process __maybe_unused,
+				       struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE];
+
+int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session,
+				    struct evlist *evlist, perf_event__handler_t process)
+{
+	struct perf_header *header = &session->header;
+	struct perf_record_header_feature *fe;
+	struct feat_fd ff;
+	size_t sz, sz_hdr;
+	int feat, ret;
+
+	sz_hdr = sizeof(fe->header);
+	sz = sizeof(union perf_event);
+	/* get a nice alignment */
+	sz = PERF_ALIGN(sz, page_size);
+
+	memset(&ff, 0, sizeof(ff));
+
+	ff.buf = malloc(sz);
+	if (!ff.buf)
+		return -ENOMEM;
+
+	ff.size = sz - sz_hdr;
+	ff.ph = &session->header;
+
+	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+		if (!feat_ops[feat].synthesize) {
+			pr_debug("No record header feature for header :%d\n", feat);
+			continue;
+		}
+
+		ff.offset = sizeof(*fe);
+
+		ret = feat_ops[feat].write(&ff, evlist);
+		if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
+			pr_debug("Error writing feature\n");
+			continue;
+		}
+		/* ff.buf may have changed due to realloc in do_write() */
+		fe = ff.buf;
+		memset(fe, 0, sizeof(*fe));
+
+		fe->feat_id = feat;
+		fe->header.type = PERF_RECORD_HEADER_FEATURE;
+		fe->header.size = ff.offset;
+
+		ret = process(tool, ff.buf, NULL, NULL);
+		if (ret) {
+			free(ff.buf);
+			return ret;
+		}
+	}
+
+	/* Send HEADER_LAST_FEATURE mark. */
+	fe = ff.buf;
+	fe->feat_id     = HEADER_LAST_FEATURE;
+	fe->header.type = PERF_RECORD_HEADER_FEATURE;
+	fe->header.size = sizeof(*fe);
+
+	ret = process(tool, ff.buf, NULL, NULL);
+
+	free(ff.buf);
+	return ret;
+}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
new file mode 100644
index 000000000000..baead0cdc381
--- /dev/null
+++ b/tools/perf/util/synthetic-events.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYNTHETIC_EVENTS_H
+#define __PERF_SYNTHETIC_EVENTS_H
+
+#include <stdbool.h>
+#include <sys/types.h> // pid_t
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct auxtrace_record;
+struct dso;
+struct evlist;
+struct evsel;
+struct machine;
+struct perf_counts_values;
+struct perf_cpu_map;
+struct perf_event_attr;
+struct perf_event_mmap_page;
+struct perf_sample;
+struct perf_session;
+struct perf_stat_config;
+struct perf_thread_map;
+struct perf_tool;
+struct record_opts;
+struct target;
+
+union perf_event;
+
+typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event,
+				     struct perf_sample *sample, struct machine *machine);
+
+int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
+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_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe);
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process);
+int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine);
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);
+int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
+int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
+int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data);
+int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize);
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process);
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine);
+
+int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process);
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format);
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct perf_thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int nr_threads_synthesize);
+int machine__synthesize_threads(struct machine *machine, struct target *target,
+				struct perf_thread_map *threads, bool data_mmap,
+				unsigned int nr_threads_synthesize);
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, struct perf_tool *tool,
+					 struct perf_session *session, perf_event__handler_t process);
+
+#else // HAVE_AUXTRACE_SUPPORT
+
+#include <errno.h>
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+				     struct perf_tool *tool __maybe_unused,
+				     struct perf_session *session __maybe_unused,
+				     perf_event__handler_t process __maybe_unused)
+{
+	return -EINVAL;
+}
+#endif // HAVE_AUXTRACE_SUPPORT
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process,
+				      struct machine *machine, struct record_opts *opts);
+#else // HAVE_LIBBPF_SUPPORT
+static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused,
+						    perf_event__handler_t process __maybe_unused,
+						    struct machine *machine __maybe_unused,
+						    struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+#endif // __PERF_SYNTHETIC_EVENTS_H
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 565f7aef7e6c..a3db13dea937 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -6,8 +6,6 @@
  */
 
 #include "target.h"
-#include "util.h"
-#include "debug.h"
 
 #include <pwd.h>
 #include <stdio.h>
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 51fb574998bb..ef96e3dd6902 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -5,7 +5,6 @@
  * Refactored from builtin-top.c, see that files for further copyright notes.
  */
 
-#include "cpumap.h"
 #include "event.h"
 #include "evlist.h"
 #include "evsel.h"
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d63d542b2cde..fe07e7550930 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2008,2009, Steven Rostedt <srostedt@redhat.com>
  */
-#include "util.h"
+#include "util.h" // page_size
 #include <dirent.h>
 #include <mntent.h>
 #include <stdio.h>
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b6c0db068be0..8593d3c200c6 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -15,7 +15,6 @@
 #include <unistd.h>
 #include <errno.h>
 
-#include "util.h"
 #include "trace-event.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 01b9d89bf5bf..b3ee651e3d91 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -14,7 +14,6 @@
 #include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
-#include "util.h"
 
 /*
  * global trace_event object used by trace_event__tp_format
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index e0c3af34ac8d..3c5a632ee57c 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -4,13 +4,12 @@
 
 #include <linux/types.h>
 
-#include "event.h"
-
 struct perf_tsc_conversion {
 	u16 time_shift;
 	u32 time_mult;
 	u64 time_zero;
 };
+
 struct perf_event_mmap_page;
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
@@ -20,13 +19,4 @@ u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
 
-struct perf_event_mmap_page;
-struct perf_tool;
-struct machine;
-
-int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
-				struct perf_tool *tool,
-				perf_event__handler_t process,
-				struct machine *machine);
-
-#endif
+#endif // __PERF_TSC_H
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 9ece188ae48a..15f6e46d7124 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -17,7 +17,6 @@
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
-#include "util.h"
 
 static char *debuginfo_path;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index ebdbb056510c..1800887b2255 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -37,7 +37,6 @@
 #include "unwind.h"
 #include "map.h"
 #include "symbol.h"
-#include "util.h"
 #include "debug.h"
 #include "asm/bug.h"
 #include "dso.h"
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 3949a60b00ae..196438ee4c9d 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -8,7 +8,6 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "util.h"
-#include "debug.h"
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/compiler.h>
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index e5e6599603f4..ba4b4395f35d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,7 +11,7 @@
 
 #include "vdso.h"
 #include "dso.h"
-#include "util.h"
+#include <internal/lib.h>
 #include "map.h"
 #include "symbol.h"
 #include "machine.h"
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 59d456f716e9..78d2297c1b67 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -7,11 +7,9 @@
 #include <sys/mman.h>
 #include <zlib.h>
 #include <linux/compiler.h>
+#include <internal/lib.h>
 
 #include "util/compress.h"
-#include "util/util.h"
-#include "util/debug.h"
-
 
 #define CHUNK_SIZE  16384