180 files changed, 2763 insertions, 2256 deletions
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt
index 38bfea30a5f6..f6aca0df2151 100644
--- a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt
+++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt
@@ -59,12 +59,12 @@ parser context.
 The _tep_register_function()_ function registers a function name mapped to an
 address and (optional) module. This mapping is used in case the function tracer
-or events have "%pF" or "%pS" parameter in its format string. It is common to
+or events have "%pS" parameter in its format string. It is common to pass in
-pass in the kallsyms function names with their corresponding addresses with this
+the kallsyms function names with their corresponding addresses with this
 function. The _tep_ argument is the trace event parser context. The _name_ is
-the name of the function, the string is copied internally. The _addr_ is
+the name of the function, the string is copied internally. The _addr_ is the
-the start address of the function. The _mod_ is the kernel module
+start address of the function. The _mod_ is the kernel module the function may
-the function may be in (NULL for none).
+be in (NULL for none).
 The _tep_register_print_string()_ function  registers a string by the address
 it was stored in the kernel. Some strings internal to the kernel with static
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index bb22238debfe..6f842af4550b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4367,10 +4367,20 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
                                        switch (*ptr) {
                                        case 's':
                                        case 'S':
-                                        case 'f':
-                                        case 'F':
                                        case 'x':
                                                break;
+                                        case 'f':
+                                        case 'F':
+                                                /*
+                                                 * Pre-5.5 kernels use %pf and
+                                                 * %pF for printing symbols
+                                                 * while kernels since 5.5 use
+                                                 * %pfw for fwnodes. So check
+                                                 * %p[fF] isn't followed by 'w'.
+                                                 */
+                                                if (ptr[1] != 'w')
+                                                        break;
+                                                /* fall through */
                                        default:
                                                /*
                                                 * Older kernels do not process
@@ -4487,12 +4497,12 @@ get_bprint_format(void *data, int size __maybe_unused,
        printk = find_printk(tep, addr);
        if (!printk) {
-                if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
+                if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0)
                        return NULL;
                return format;
        }
-        if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0)
+        if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0)
                return NULL;
        return format;
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f9807d8c005b..2ccc12f3730b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -567,7 +567,7 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 # Create python binding output directory if not already present
 _dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) $(LIBPERF)
        $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
        CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
          $(PYTHON_WORD) util/setup.py \
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index c32db09baf0d..5d120b1e35ed 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -25,7 +25,7 @@
 #include "../../util/evsel.h"
 #include "../../util/pmu.h"
 #include "../../util/cs-etm.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/session.h"
 #include <errno.h>
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 4b364692da67..eebbf31f995c 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -16,7 +16,7 @@
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/auxtrace.h"
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index b047b882c5b1..917b97d7c5d3 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -11,7 +11,6 @@
 #include <dwarf-regs.h>
 #include <linux/ptrace.h> /* for struct user_pt_regs */
 #include <linux/stringify.h>
-#include "util.h"
 struct pt_regs_dwarfnum {
        const char *name;
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index e41defaaa2e6..a32e4b72a98f 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,5 +1,7 @@
 #include <stdio.h>
 #include <stdlib.h>
+#include <perf/cpumap.h>
+#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include "debug.h"
 #include "header.h"
@@ -29,7 +31,7 @@ char *get_cpuid_str(struct perf_pmu *pmu)
        /* read midr from list of cpus mapped to this pmu */
        cpus = perf_cpu_map__get(pmu->cpus);
-        for (cpu = 0; cpu < cpus->nr; cpu++) {
+        for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
                scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
                                sysfs, cpus->map[cpu]);
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 002520d4036b..1495a9523a23 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -5,8 +5,8 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
+#include "../../util/debug.h"
 int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 4952890b9428..0c4f4caf53ac 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -12,7 +12,6 @@
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
-#include "util.h"
 struct pt_regs_dwarfnum {
        const char *name;
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 0b242664f5ea..b6b7bc7e31a1 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -6,7 +6,6 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
-#include "util.h"
 #define mfspr(rn)       ({unsigned long rval; \
                         asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index f0dbf7b075c8..9cc1c4a9dec4 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -5,9 +5,11 @@
 #include "util/debug.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
+#include "util/pmu.h"
 #include "book3s_hv_exits.h"
 #include "book3s_hcalls.h"
+#include <subcmd/parse-options.h>
 #define NR_TPS 4
@@ -172,3 +174,46 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
        return ret;
 }
+/*
+ * Incase of powerpc architecture, pmu registers are programmable
+ * by guest kernel. So monitoring guest via host may not provide
+ * valid samples with default 'cycles' event. It is better to use
+ * 'trace_imc/trace_cycles' event for guest profiling, since it
+ * can track the guest instruction pointer in the trace-record.
+ *
+ * Function to parse the arguments and return appropriate values.
+ */
+int kvm_add_default_arch_event(int *argc, const char **argv)
+{
+        const char **tmp;
+        bool event = false;
+        int i, j = *argc;
+        const struct option event_options[] = {
+                OPT_BOOLEAN('e', "event", &event, NULL),
+                OPT_END()
+        };
+        tmp = calloc(j + 1, sizeof(char *));
+        if (!tmp)
+                return -EINVAL;
+        for (i = 0; i < j; i++)
+                tmp[i] = argv[i];
+        parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN);
+        if (!event) {
+                if (pmu_have_event("trace_imc", "trace_cycles")) {
+                        argv[j++] = strdup("-e");
+                        argv[j++] = strdup("trace_imc/trace_cycles/");
+                        *argc += 2;
+                } else {
+                        free(tmp);
+                        return -EINVAL;
+                }
+        }
+        free(tmp);
+        return 0;
+}
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index fc9c2f5fcd52..3018a054526a 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -13,6 +13,7 @@
 #include "util/callchain.h"
 #include "util/debug.h"
 #include "util/dso.h"
+#include "util/event.h" // struct ip_callchain
 #include "util/map.h"
 #include "util/symbol.h"
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 8a4b717e0a53..abb7a12d8f93 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -4,7 +4,6 @@
 * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
 */
-#include "debug.h"
 #include "dso.h"
 #include "symbol.h"
 #include "map.h"
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index c8c86a0c9b79..df099d6cc3f5 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -2,7 +2,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
-#include "util.h"
+#include "util.h" // page_size
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 3b5cc3373821..111c0ab2e7b5 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -5,7 +5,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "arch-tests.h"
-#include "util.h"
 #include <signal.h>
 #include <sys/mman.h>
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index eb3635941c2b..0a4570b340fa 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -15,7 +15,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "record.h"
 #include "tsc.h"
 #include "tests/tests.h"
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 6e67cee792b1..e7640fb047de 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -13,7 +13,7 @@
 #include "tests/tests.h"
 #include "cloexec.h"
 #include "event.h"
-#include "util.h"
+#include "util.h" // page_size
 #include "arch-tests.h"
 static u64 rdpmc(unsigned int counter)
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 9876c7a7ed7c..3e6791531ca5 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
+#include "event.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index a3a0b6884779..d357c625c09f 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -3,6 +3,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
+#include "../../util/event.h"
+#include "../../util/synthetic-events.h"
 #include "../../util/machine.h"
 #include "../../util/tool.h"
 #include "../../util/map.h"
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index d263430c045f..090d90e093df 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -22,7 +22,7 @@
 #include "../../util/tsc.h"
 #include "../../util/auxtrace.h"
 #include "../../util/intel-bts.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index cb7cf16af79c..3d041b89f018 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -26,7 +26,7 @@
 #include "../../util/record.h"
 #include "../../util/target.h"
 #include "../../util/tsc.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/intel-pt.h"
 #define KiB(x) ((x) * 1024)
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
index 1e9ec783b9a1..f0c289862f9f 100644
--- a/tools/perf/arch/x86/util/machine.c
+++ b/tools/perf/arch/x86/util/machine.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/string.h>
+#include <limits.h>
 #include <stdlib.h>
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/machine.h"
 #include "../../util/map.h"
 #include "../../util/symbol.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index c5197a15119b..2f55afb14e1f 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -8,6 +8,8 @@
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
 #include "../../../util/tsc.h"
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index d1caa4a0a12a..bb617e568841 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -21,12 +21,12 @@
 #include <sys/resource.h>
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 #include <err.h>
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index f6b4472847d2..7af694437f4e 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -76,12 +76,12 @@
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 #include <err.h>
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 80e138904c66..8ba0c3330a9a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -20,13 +20,13 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 #include <err.h>
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index c5d6d0abbaa9..d0cae8125423 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -14,10 +14,10 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 #include <err.h>
 #include <stdlib.h>
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 75d3418c1a88..a00a6891447a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 #include <err.h>
 #include <stdlib.h>
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 163fe16c275a..a053cf2b7039 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -29,7 +29,8 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
 #include <linux/time64.h>
 #include <errno.h>
 #include "futex.h"
-#include "cpumap.h"
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
 #include <err.h>
 #include <stdlib.h>
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 77dcdc13618a..df810096abfe 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 #include <err.h>
 #include <stdlib.h>
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 62b8ef4bcb1f..5797253b9700 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -9,7 +9,6 @@
 /* For the CLR_() macros */
 #include <pthread.h>
-#include "../builtin.h"
 #include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index c63eb9a46346..97e4a4fb3362 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -10,9 +10,7 @@
 *
 */
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
-#include "../builtin.h"
 #include "bench.h"
 /* Test groups of 20 processes spraying to 20 receivers */
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 35b07f197d48..3c88d1f201f1 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -9,9 +9,7 @@
 *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
 * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
 */
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
-#include "../builtin.h"
 #include "bench.h"
 #include <unistd.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4e4d2e76232e..553c651fa0a2 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -27,6 +27,7 @@
 #include "util/sort.h"
 #include "util/hist.h"
 #include "util/dso.h"
+#include "util/machine.h"
 #include "util/map.h"
 #include "util/session.h"
 #include "util/tool.h"
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index b09b12e0976b..61aaacc2aedd 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -20,6 +20,7 @@
 #include <sys/param.h>
 #include "debug.h"
 #include "builtin.h"
+#include <perf/cpumap.h>
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "map_symbol.h"
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 42d8157e047a..2603015f98be 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -9,7 +9,6 @@
 #include "util/cache.h"
 #include <subcmd/parse-options.h>
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/config.h"
 #include <linux/string.h>
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 238fa3876805..294494e60e48 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -5,8 +5,6 @@
 */
 #include "builtin.h"
-#include "util/util.h"
 #include <linux/list.h>
 #include "perf.h"
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c14f40b858bc..23a76cf3846f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -21,6 +21,7 @@
 #include "util/auxtrace.h"
 #include "util/jit.h"
 #include "util/symbol.h"
+#include "util/synthetic-events.h"
 #include "util/thread.h"
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0a4fcbe32bf6..6e3e36658900 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -17,9 +17,11 @@
 #include "util/debug.h"
 #include "util/tool.h"
 #include "util/stat.h"
+#include "util/synthetic-events.h"
 #include "util/top.h"
 #include "util/data.h"
 #include "util/ordered-events.h"
+#include "util/kvm-stat.h"
 #include "ui/ui.h"
 #include <sys/prctl.h>
@@ -58,7 +60,6 @@ static const char *get_filename_for_perf_kvm(void)
 }
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include "util/kvm-stat.h"
 void exit_event_get_key(struct evsel *evsel,
                        struct perf_sample *sample,
@@ -1513,11 +1514,21 @@ perf_stat:
 }
 #endif /* HAVE_KVM_STAT_SUPPORT */
+int __weak kvm_add_default_arch_event(int *argc __maybe_unused,
+                                        const char **argv __maybe_unused)
+{
+        return 0;
+}
 static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
-        int rec_argc, i = 0, j;
+        int rec_argc, i = 0, j, ret;
        const char **rec_argv;
+        ret = kvm_add_default_arch_event(&argc, argv);
+        if (ret)
+                return -EINVAL;
        rec_argc = argc + 2;
        rec_argv = calloc(rec_argc + 1, sizeof(char *));
        rec_argv[i++] = strdup("record");
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1447004eee8a..4bd11c918e73 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -38,6 +38,7 @@
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
 #include "util/cpu-set-sched.h"
+#include "util/synthetic-events.h"
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
@@ -1180,15 +1181,6 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 static void snapshot_sig_handler(int sig);
 static void alarm_sig_handler(int sig);
-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;
-}
 static const struct perf_event_mmap_page *
 perf_evlist__pick_pc(struct evlist *evlist)
 {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b18fab94d38d..3047e5169d9d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -48,7 +48,7 @@
 #include "util/auxtrace.h"
 #include "util/units.h"
 #include "util/branch.h"
-#include "util/util.h"
+#include "util/util.h" // perf_tip()
 #include "ui/ui.h"
 #include "ui/progress.h"
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index ec96d64aec69..f0b828c201cc 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3,6 +3,7 @@
 #include "perf.h"
 #include "perf-sys.h"
+#include "util/cpumap.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/symbol.h"
@@ -23,6 +24,7 @@
 #include "util/trace-event.h"
 #include "util/debug.h"
+#include "util/event.h"
 #include <linux/kernel.h>
 #include <linux/log2.h>
@@ -36,6 +38,7 @@
 #include <pthread.h>
 #include <math.h>
 #include <api/fs/fs.h>
+#include <perf/cpumap.h>
 #include <linux/time64.h>
 #include <linux/ctype.h>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7e17bf9f700a..60cdd383af81 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -61,6 +61,7 @@
 #include "util/tool.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
+#include "util/synthetic-events.h"
 #include "util/target.h"
 #include "util/time-utils.h"
 #include "util/top.h"
@@ -540,8 +541,8 @@ try_again:
                if (err < 0)
                        return err;
-                err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+                err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list,
-                                                  process_synthesized_event, is_pipe);
+                                                         process_synthesized_event, is_pipe);
                if (err < 0)
                        return err;
        }
@@ -822,18 +823,6 @@ static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
        return cpu_map__get_core(map, cpu, NULL);
 }
-static int cpu_map__get_max(struct perf_cpu_map *map)
-{
-        int i, max = -1;
-        for (i = 0; i < map->nr; i++) {
-                if (map->map[i] > max)
-                        max = map->map[i];
-        }
-        return max;
-}
 static int perf_stat__get_aggr(struct perf_stat_config *config,
                               aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
 {
@@ -928,7 +917,7 @@ static int perf_stat_init_aggr_mode(void)
         * taking the highest cpu number to be the size of
         * the aggregation translate cpumap.
         */
-        nr = cpu_map__get_max(evsel_list->core.cpus);
+        nr = perf_cpu_map__max(evsel_list->core.cpus);
        stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1);
        return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
@@ -1963,8 +1952,11 @@ int cmd_stat(int argc, const char **argv)
                        fprintf(output, "[ perf stat: executing run #%d ... ]\n",
                                run_idx + 1);
+                if (run_idx != 0)
+                        perf_evlist__reset_prev_raw_counts(evsel_list);
                status = run_perf_stat(argc, argv, run_idx);
-                if (forever && status != -1) {
+                if (forever && status != -1 && !interval) {
                        print_counters(NULL, argc, argv);
                        perf_stat__reset_stats();
                }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 726e3f2dd8c7..b052470f89b4 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -32,6 +32,7 @@
 #include "util/map.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/synthetic-events.h"
 #include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 0f633f0d6be8..f0f735093e21 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -28,6 +28,7 @@
 #include "util/dso.h"
 #include "util/env.h"
 #include "util/event.h"
+#include "util/synthetic-events.h"
 #include "util/evlist.h"
 #include "util/evswitch.h"
 #include <subcmd/pager.h>
diff --git a/tools/perf/jvmti/Build b/tools/perf/jvmti/Build
index eaeb8cb5379b..1e148bbdf820 100644
--- a/tools/perf/jvmti/Build
+++ b/tools/perf/jvmti/Build
@@ -1,8 +1,17 @@
 jvmti-y += libjvmti.o
 jvmti-y += jvmti_agent.o
+# For strlcpy
+jvmti-y += libstring.o
 CFLAGS_jvmti         = -fPIC -DPIC -I$(JDIR)/include -I$(JDIR)/include/linux
 CFLAGS_REMOVE_jvmti  = -Wmissing-declarations
 CFLAGS_REMOVE_jvmti += -Wstrict-prototypes
 CFLAGS_REMOVE_jvmti += -Wextra
 CFLAGS_REMOVE_jvmti += -Wwrite-strings
+CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+$(OUTPUT)jvmti/libstring.o: ../lib/string.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/lib/Makefile b/tools/perf/lib/Makefile
index a67efb8d9d39..e325c0503dc6 100644
--- a/tools/perf/lib/Makefile
+++ b/tools/perf/lib/Makefile
@@ -146,6 +146,7 @@ install_headers:
                $(call do_install,include/perf/threadmap.h,$(prefix)/include/perf,644); \
                $(call do_install,include/perf/evlist.h,$(prefix)/include/perf,644); \
                $(call do_install,include/perf/evsel.h,$(prefix)/include/perf,644);
+                $(call do_install,include/perf/event.h,$(prefix)/include/perf,644);
 install_pkgconfig: $(LIBPERF_PC)
        $(call QUIET_INSTALL, $(LIBPERF_PC)) \
diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index 1f0e6f334237..2ca1fafa620d 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -260,3 +260,15 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
        return -1;
 }
+int perf_cpu_map__max(struct perf_cpu_map *map)
+{
+        int i, max = -1;
+        for (i = 0; i < map->nr; i++) {
+                if (map->map[i] > max)
+                        max = map->map[i];
+        }
+        return max;
+}
diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h
index 8aa995c59498..ac9aa497f84a 100644
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/perf/lib/include/perf/cpumap.h
@@ -16,6 +16,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)              \
        for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);   \
diff --git a/tools/perf/lib/libperf.map b/tools/perf/lib/libperf.map
index dc4d66363bc4..cd0d17b996c8 100644
--- a/tools/perf/lib/libperf.map
+++ b/tools/perf/lib/libperf.map
@@ -9,6 +9,7 @@ LIBPERF_0.0.1 {
                perf_cpu_map__nr;
                perf_cpu_map__cpu;
                perf_cpu_map__empty;
+                perf_cpu_map__max;
                perf_thread_map__new_dummy;
                perf_thread_map__set_pid;
                perf_thread_map__comm;
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 1193b923e801..bb40a108b8f7 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -20,7 +20,7 @@
 #include "util/bpf-loader.h"
 #include "util/debug.h"
 #include "util/event.h"
-#include "util/util.h"
+#include "util/util.h" // page_size, usage()
 #include "ui/ui.h"
 #include "perf-sys.h"
 #include <api/fs/fs.h>
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json
new file mode 100644
index 000000000000..b5e5d055c70d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json
@@ -0,0 +1,14 @@
+[
+    {
+        "PublicDescription": "Mispredicted or not predicted branch speculatively executed. This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken.",
+        "EventCode": "0x10",
+        "EventName": "BR_MIS_PRED",
+        "BriefDescription": "Mispredicted or not predicted branch speculatively executed."
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed. This event counts all predictable branches.",
+        "EventCode": "0x12",
+        "EventName": "BR_PRED",
+        "BriefDescription": "Predictable branch speculatively executed."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json
new file mode 100644
index 000000000000..fce7309ae624
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json
@@ -0,0 +1,24 @@
+[
+    {
+        "EventCode": "0x11",
+        "EventName": "CPU_CYCLES",
+        "BriefDescription": "The number of core clock cycles."
+    },
+    {
+        "PublicDescription": "Bus access. This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.",
+        "EventCode": "0x19",
+        "EventName": "BUS_ACCESS",
+        "BriefDescription": "Bus access."
+    },
+    {
+        "EventCode": "0x1D",
+        "EventName": "BUS_CYCLES",
+        "BriefDescription": "Bus cycles. This event duplicates CPU_CYCLES."
+    },
+    {
+        "ArchStdEvent":  "BUS_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent":  "BUS_ACCESS_WR"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json
new file mode 100644
index 000000000000..24594081c199
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json
@@ -0,0 +1,207 @@
+[
+    {
+        "PublicDescription": "L1 instruction cache refill. This event counts any instruction fetch which misses in the cache.",
+        "EventCode": "0x01",
+        "EventName": "L1I_CACHE_REFILL",
+        "BriefDescription": "L1 instruction cache refill"
+    },
+    {
+        "PublicDescription": "L1 instruction TLB refill. This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.",
+        "EventCode": "0x02",
+        "EventName": "L1I_TLB_REFILL",
+        "BriefDescription": "L1 instruction TLB refill"
+    },
+    {
+        "PublicDescription": "L1 data cache refill. This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.",
+        "EventCode": "0x03",
+        "EventName": "L1D_CACHE_REFILL",
+        "BriefDescription": "L1 data cache refill"
+    },
+    {
+        "PublicDescription": "L1 data cache access. This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.",
+        "EventCode": "0x04",
+        "EventName": "L1D_CACHE",
+        "BriefDescription": "L1 data cache access"
+    },
+    {
+        "PublicDescription": "L1 data TLB refill. This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.",
+        "EventCode": "0x05",
+        "EventName": "L1D_TLB_REFILL",
+        "BriefDescription": "L1 data TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache access or Level 0 Macro-op cache access. This event counts any instruction fetch which accesses the L1 instruction cache or L0 Macro-op cache.",
+        "EventCode": "0x14",
+        "EventName": "L1I_CACHE",
+        "BriefDescription": "L1 instruction cache access"
+    },
+    {
+        "PublicDescription": "L1 data cache Write-Back. This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.",
+        "EventCode": "0x15",
+        "EventName": "L1D_CACHE_WB",
+        "BriefDescription": "L1 data cache Write-Back"
+    },
+    {
+        "PublicDescription": "L2 data cache access. This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.",
+        "EventCode": "0x16",
+        "EventName": "L2D_CACHE",
+        "BriefDescription": "L2 data cache access"
+    },
+    {
+        "PublicDescription": "L2 data cache refill. This event counts any cacheable transaction from L1 which causes data to be read from outside the core. L2 refills caused by stashes into L2 should not be counted",
+        "EventCode": "0x17",
+        "EventName": "L2D_CACHE_REFILL",
+        "BriefDescription": "L2 data cache refill"
+    },
+    {
+        "PublicDescription": "L2 data cache write-back. This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted",
+        "EventCode": "0x18",
+        "EventName": "L2D_CACHE_WB",
+        "BriefDescription": "L2 data cache write-back"
+    },
+    {
+        "PublicDescription": "L2 data cache allocation without refill. This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.",
+        "EventCode": "0x20",
+        "EventName": "L2D_CACHE_ALLOCATE",
+        "BriefDescription": "L2 data cache allocation without refill"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.",
+        "EventCode": "0x25",
+        "EventName": "L1D_TLB",
+        "BriefDescription": "Level 1 data TLB access."
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB.This event counts regardless of whether the MMU is enabled.",
+        "EventCode": "0x26",
+        "EventName": "L1I_TLB",
+        "BriefDescription": "Level 1 instruction TLB access"
+    },
+    {
+        "PublicDescription": "This event counts any full cache line write into the L3 cache which does not cause a linefill, including write-backs from L2 to L3 and full-line writes which do not allocate into L2",
+        "EventCode": "0x29",
+        "EventName": "L3D_CACHE_ALLOCATE",
+        "BriefDescription": "Allocation without refill"
+    },
+    {
+        "PublicDescription": "Attributable Level 3 unified cache refill. This event counts for any cacheable read transaction returning datafrom the SCU for which the data source was outside the cluster. Transactions such as ReadUnique are counted here as 'read' transactions, even though they can be generated by store instructions.",
+        "EventCode": "0x2A",
+        "EventName": "L3D_CACHE_REFILL",
+        "BriefDescription": "Attributable Level 3 unified cache refill."
+    },
+    {
+        "PublicDescription": "Attributable Level 3 unified cache access. This event counts for any cacheable read transaction returning datafrom the SCU, or for any cacheable write to the SCU.",
+        "EventCode": "0x2B",
+        "EventName": "L3D_CACHE",
+        "BriefDescription": "Attributable Level 3 unified cache access."
+    },
+    {
+        "PublicDescription": "Attributable L2 data or unified TLB refill. This event counts on anyrefill of the L2 TLB, caused by either an instruction or data access.This event does not count if the MMU is disabled.",
+        "EventCode": "0x2D",
+        "EventName": "L2D_TLB_REFILL",
+        "BriefDescription": "Attributable L2 data or unified TLB refill"
+    },
+    {
+        "PublicDescription": "Attributable L2 data or unified TLB access. This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.",
+        "EventCode": "0x2F",
+        "EventName": "L2D_TLB",
+        "BriefDescription": "Attributable L2 data or unified TLB access"
+    },
+    {
+        "PublicDescription": "Access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count.",
+        "EventCode": "0x34",
+        "EventName": "DTLB_WALK",
+        "BriefDescription": "Access to data TLB that caused a page table walk."
+    },
+    {
+        "PublicDescription": "Access to instruction TLB that caused a page table walk. This event counts on any instruction access which causes L2D_TLB_REFILL to count.",
+        "EventCode": "0x35",
+        "EventName": "ITLB_WALK",
+        "BriefDescription": "Access to instruction TLB that caused a page table walk."
+    },
+    {
+        "EventCode": "0x36",
+        "EventName": "LL_CACHE_RD",
+        "BriefDescription": "Last level cache access, read"
+    },
+    {
+        "EventCode": "0x37",
+        "EventName": "LL_CACHE_MISS_RD",
+        "BriefDescription": "Last level cache miss, read"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_RD"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json
new file mode 100644
index 000000000000..98d29c862320
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json
@@ -0,0 +1,52 @@
+[
+    {
+        "EventCode": "0x09",
+        "EventName": "EXC_TAKEN",
+        "BriefDescription": "Exception taken."
+    },
+    {
+        "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs",
+        "EventCode": "0x1A",
+        "EventName": "MEMORY_ERROR",
+        "BriefDescription": "Local memory error."
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_HVC"
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_SMC"
+    },
+    {
+        "ArchStdEvent": "EXC_SVC"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json
new file mode 100644
index 000000000000..c153ac706d8d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json
@@ -0,0 +1,108 @@
+[
+    {
+        "PublicDescription": "Software increment. Instruction architecturally executed (condition code check pass).",
+        "EventCode": "0x00",
+        "EventName": "SW_INCR",
+        "BriefDescription": "Software increment."
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed. This event counts all retired instructions, including those that fail their condition check.",
+        "EventCode": "0x08",
+        "EventName": "INST_RETIRED",
+        "BriefDescription": "Instruction architecturally executed."
+    },
+    {
+        "EventCode": "0x0A",
+        "EventName": "EXC_RETURN",
+        "BriefDescription": "Instruction architecturally executed, condition code check pass, exception return."
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR. This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.",
+        "EventCode": "0x0B",
+        "EventName": "CID_WRITE_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR."
+    },
+    {
+        "EventCode": "0x1B",
+        "EventName": "INST_SPEC",
+        "BriefDescription": "Operation speculatively executed"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition code check pass, write to TTBR. This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.",
+        "EventCode": "0x1C",
+        "EventName": "TTBR_WRITE_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, condition code check pass, write to TTBR"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.",
+        "EventCode": "0x21",
+        "EventName": "BR_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, branch."
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.",
+        "EventCode": "0x22",
+        "EventName": "BR_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted branch."
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC"
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC"
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DP_SPEC"
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC"
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC"
+    },
+    {
+        "ArchStdEvent": "LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json
new file mode 100644
index 000000000000..b86643253f19
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json
@@ -0,0 +1,23 @@
+[
+    {
+        "PublicDescription": "Data memory access. This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.",
+        "EventCode": "0x13",
+        "EventName": "MEM_ACCESS",
+        "BriefDescription": "Data memory access"
+    },
+    {
+         "ArchStdEvent": "MEM_ACCESS_RD"
+    },
+    {
+         "ArchStdEvent": "MEM_ACCESS_WR"
+    },
+    {
+         "ArchStdEvent": "UNALIGNED_LD_SPEC"
+    },
+    {
+         "ArchStdEvent": "UNALIGNED_ST_SPEC"
+    },
+    {
+         "ArchStdEvent": "UNALIGNED_LDST_SPEC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json
new file mode 100644
index 000000000000..8bde029a62d5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json
@@ -0,0 +1,7 @@
+[
+    {
+        "EventCode": "0x31",
+        "EventName": "REMOTE_ACCESS",
+        "BriefDescription": "Access to another socket in a multi-socket system"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json
new file mode 100644
index 000000000000..010a647f9d02
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json
@@ -0,0 +1,14 @@
+[
+    {
+        "PublicDescription": "No operation issued because of the frontend. The counter counts on any cycle when there are no fetched instructions available to dispatch.",
+        "EventCode": "0x23",
+        "EventName": "STALL_FRONTEND",
+        "BriefDescription": "No operation issued because of the frontend."
+    },
+    {
+        "PublicDescription": "No operation issued because of the backend. The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.",
+        "EventCode": "0x24",
+        "EventName": "STALL_BACKEND",
+        "BriefDescription": "No operation issued because of the backend."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 927fcddcb4aa..0d609149b82a 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -16,6 +16,8 @@
 0x00000000420f1000,v1,arm/cortex-a53,core
 0x00000000410fd070,v1,arm/cortex-a57-a72,core
 0x00000000410fd080,v1,arm/cortex-a57-a72,core
+0x00000000410fd0b0,v1,arm/cortex-a76-n1,core
+0x00000000410fd0c0,v1,arm/cortex-a76-n1,core
 0x00000000420f5160,v1,cavium/thunderx2,core
 0x00000000430f0af0,v1,cavium/thunderx2,core
 0x00000000480fd010,v1,hisilicon/hip08,core
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index db2aadff3708..96c137360918 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -2,8 +2,8 @@
 #include <linux/compiler.h>
 #include <linux/bitmap.h>
 #include <perf/cpumap.h>
+#include <internal/cpumap.h>
 #include "tests.h"
-#include "cpumap.h"
 #include "debug.h"
 #define NBITS 100
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
index f45fe11dcf50..2577d3ed1531 100644
--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "tests.h"
-#include "debug.h"
-#include "util.h"
 #include "c++/clang-c.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index c1c29e08e7fb..fd02c1f1d976 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -19,12 +19,12 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "machine.h"
 #include "map.h"
 #include "symbol.h"
 #include "event.h"
 #include "record.h"
+#include "util/synthetic-events.h"
 #include "thread.h"
 #include "tests.h"
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 39493de50117..8a0d236202b0 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -3,6 +3,7 @@
 #include <stdio.h>
 #include "cpumap.h"
 #include "event.h"
+#include "util/synthetic-events.h"
 #include <string.h>
 #include <linux/bitops.h>
 #include <perf/cpumap.h>
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index a4874d4ce7ef..627c1aaf1c9e 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -10,7 +10,6 @@
 #include <sys/resource.h>
 #include <api/fs/fs.h>
 #include "dso.h"
-#include "util.h"
 #include "machine.h"
 #include "symbol.h"
 #include "tests.h"
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 4125255ff637..4f4ecbcbe87e 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -15,6 +15,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include "callchain.h"
+#include "util/synthetic-events.h"
 #if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__)
 #include "arch-tests.h"
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index d824a726906c..0228ba435a2a 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -9,7 +9,6 @@
 #include "tests.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "util.h"
 #include "debug.h"
 #include "parse-events.h"
 #include "thread_map.h"
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index cac4290e233a..0497d900ced2 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -2,10 +2,12 @@
 #include <linux/compiler.h>
 #include <perf/cpumap.h>
 #include <string.h>
+#include "cpumap.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "header.h"
 #include "machine.h"
+#include "util/synthetic-events.h"
 #include "tool.h"
 #include "tests.h"
 #include "debug.h"
@@ -92,7 +94,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
        evsel = perf_evlist__first(evlist);
-        TEST_ASSERT_VAL("failed to allos ids",
+        TEST_ASSERT_VAL("failed to allocate ids",
                        !perf_evsel__alloc_id(evsel, 1, 1));
        perf_evlist__id_add(evlist, evsel, 0, 0, 123);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index de110d8f169b..6f34d08b84e5 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -2,6 +2,7 @@
 #include <inttypes.h>
 #include "util/debug.h"
 #include "util/dso.h"
+#include "util/event.h" // struct perf_sample
 #include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
@@ -10,6 +11,7 @@
 #include "util/thread.h"
 #include "tests/hists_common.h"
 #include <linux/kernel.h>
+#include <linux/perf_event.h>
 static struct {
        u32 pid;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 9f0762d987fa..df0fd5a44e04 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -12,7 +12,6 @@
 #include "evsel.h"
 #include "record.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "tests.h"
 #define CHECK__(x) {                            \
@@ -143,7 +142,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un
        found = find_comm(evlist, comm);
        if (found != 1) {
-                pr_debug("Seconf time, failed to find tracking event.\n");
+                pr_debug("Second time, failed to find tracking event.\n");
                goto out_err;
        }
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 022e4c9cf092..ae6cda81c209 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -7,7 +7,6 @@
 #include "llvm.h"
 #include "tests.h"
 #include "debug.h"
-#include "util.h"
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 70c48475896d..6b3afed5d910 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -327,6 +327,10 @@ make_kernelsrc_tools:
        (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
        test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
+make_libperf:
+        @echo "- make -C lib";
+        make -C lib clean >$@ 2>&1; make -C lib >>$@ 2>&1 && rm $@
 FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP
 FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC
@@ -365,5 +369,5 @@ $(foreach t,$(run),$(if $(findstring make_static,$(t)),\
                        $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE))))
 endif
-.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
+.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools make_libperf
 endif # ifndef MK
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index 7672ade70f20..a258bd51f1a4 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -4,7 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <perf/cpumap.h>
-#include "cpumap.h"
+#include <internal/cpumap.h>
 #include "debug.h"
 #include "env.h"
 #include "mem2node.h"
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 85e1d7337dc0..042757629e90 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -10,7 +10,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "tests.h"
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -53,7 +52,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
        cpus = perf_cpu_map__new(NULL);
        if (cpus == NULL) {
-                pr_debug("cpu_map__new\n");
+                pr_debug("perf_cpu_map__new\n");
                goto out_free_threads;
        }
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 360d70deb855..33b496d194f4 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -8,13 +8,15 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include "debug.h"
+#include "event.h"
 #include "tests.h"
 #include "machine.h"
 #include "thread_map.h"
 #include "map.h"
 #include "symbol.h"
+#include "util/synthetic-events.h"
 #include "thread.h"
-#include "util.h"
+#include "util.h" // page_size
 #define THREADS 4
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 9171f77cd9cd..93c176523e38 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -14,7 +14,8 @@
 #include "evsel.h"
 #include "tests.h"
 #include "thread_map.h"
-#include "cpumap.h"
+#include <perf/cpumap.h>
+#include <internal/cpumap.h>
 #include "debug.h"
 #include "stat.h"
 #include "util/counts.h"
@@ -37,7 +38,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int
        cpus = perf_cpu_map__new(NULL);
        if (cpus == NULL) {
-                pr_debug("cpu_map__new\n");
+                pr_debug("perf_cpu_map__new\n");
                goto out_thread_map_delete;
        }
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 02ba696fb87f..c25c8e7b41e5 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -6,7 +6,6 @@
 #include "tests.h"
 #include "debug.h"
 #include "pmu.h"
-#include "util.h"
 #include <dirent.h>
 #include <errno.h>
 #include <sys/types.h>
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 8284752a60c8..adf3c9c4a416 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -1,4 +1,3 @@
-// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <stddef.h>
@@ -8,7 +7,6 @@
 #include "event.h"
 #include "evlist.h"
 #include "header.h"
-#include "util.h"
 #include "debug.h"
 static int process_event(struct evlist **pevlist, union perf_event *event)
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index a693bcf017ea..dbc27199c65e 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -4,7 +4,6 @@
 #include "tests.h"
 #include "debug.h"
-#include "util.h"
 #include "perf-hooks.h"
 static void sigsegv_handler(int sig __maybe_unused)
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 14a78898d79e..74379ff1f7fa 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "parse-events.h"
 #include "pmu.h"
-#include "util.h"
 #include "tests.h"
 #include <errno.h>
 #include <stdio.h>
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 5fcc06817076..3a02426db9a6 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -9,10 +9,10 @@
 #include "map_symbol.h"
 #include "branch.h"
-#include "util.h"
 #include "event.h"
 #include "evsel.h"
 #include "debug.h"
+#include "util/synthetic-events.h"
 #include "tests.h"
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index cc10b4116c9f..c1911501c39c 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -5,6 +5,7 @@
 #include "stat.h"
 #include "counts.h"
 #include "debug.h"
+#include "util/synthetic-events.h"
 static bool has_term(struct perf_record_stat_config *config,
                     u64 tag, u64 val)
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 1a60fa1219f5..3fb1ff7b8a2f 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -14,7 +14,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "record.h"
 #include "tests.h"
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index f610e8c0a083..088c7708b03a 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -4,12 +4,12 @@
 #include "evsel.h"
 #include "target.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "tests.h"
 #include <errno.h>
 #include <signal.h>
 #include <linux/string.h>
+#include <perf/cpumap.h>
 #include <perf/evlist.h>
 static int exited;
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 39168c57943b..28f51c4bd373 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -8,6 +8,7 @@
 #include "thread_map.h"
 #include "debug.h"
 #include "event.h"
+#include "util/synthetic-events.h"
 #include <linux/zalloc.h>
 #include <perf/event.h>
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index a4f9f5182b47..7d845d913d7d 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -3,8 +3,8 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <perf/cpumap.h>
+#include "cpumap.h"
 #include "tests.h"
-#include "util.h"
 #include "session.h"
 #include "evlist.h"
 #include "debug.h"
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 01f434c067c6..7f28775875c2 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -7,7 +7,7 @@
 #include "dso.h"
 #include "map.h"
 #include "symbol.h"
-#include "util.h"
+#include "util.h" // page_size
 #include "tests.h"
 #include "debug.h"
 #include "machine.h"
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index f93d40b1c203..781afe42e90e 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../util/util.h"
 #include "../util/string2.h"
 #include "../util/config.h"
 #include "libslang.h"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ac74ed2c23a0..82207db8f97c 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -2,7 +2,6 @@
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
-#include "../util.h"
 #include "../../util/annotate.h"
 #include "../../util/debug.h"
 #include "../../util/dso.h"
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index 0f59a7001479..57e6e4332f74 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util/debug.h"
 #include "ui/browser.h"
 #include "ui/keysyms.h"
 #include "ui/ui.h"
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 893b065971f6..3d49b916c9e4 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -5,7 +5,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <linux/bitops.h>
-#include "../../util/util.h"
 #include "../../util/debug.h"
 #include "../../util/map.h"
 #include "../../util/dso.h"
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index f16a38fea45e..76d356a18790 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -7,7 +7,7 @@
 #include "config.h"
 #include "time-utils.h"
 #include "../util.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // perf_exe()
 #include "../../perf.h"
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 586a21acc13d..fc733a6354d4 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../builtin.h"
 #include "../../perf.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // perf_exe()
+#include "../util.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
 #include "../../util/symbol.h"
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
index e166da9ec767..e40a006aead8 100644
--- a/tools/perf/ui/gtk/helpline.c
+++ b/tools/perf/ui/gtk/helpline.c
@@ -6,7 +6,6 @@
 #include "gtk.h"
 #include "../ui.h"
 #include "../helpline.h"
-#include "../../util/debug.h"
 static void gtk_helpline_pop(void)
 {
diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c
index b6ad8857da78..eea6fcde518a 100644
--- a/tools/perf/ui/gtk/progress.c
+++ b/tools/perf/ui/gtk/progress.c
@@ -3,7 +3,6 @@
 #include "gtk.h"
 #include "../progress.h"
-#include "util.h"
 static GtkWidget *dialog;
 static GtkWidget *progress;
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 1a2616b97b5c..f5eee4d66873 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "gtk.h"
-#include "../../util/debug.h"
+#include <linux/compiler.h>
+#include "../util.h"
 extern struct perf_error_ops perf_gtk_eops;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index c2c558958b9c..c47f5c387838 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../util.h"
-#include "../../util/debug.h"
 #include "gtk.h"
 #include <stdlib.h>
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 54bcd08df87e..911182b3f5e6 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -3,10 +3,8 @@
 #include <stdlib.h>
 #include <string.h>
-#include "../util/debug.h"
 #include "helpline.h"
 #include "ui.h"
-#include "../util/util.h"
 char ui_helpline__current[512];
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 3e533de7d852..f73675500061 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -8,7 +8,6 @@
 #include "../util/callchain.h"
 #include "../util/debug.h"
 #include "../util/hist.h"
-#include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
 #include "../util/evlist.h"
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index c7a86b4be9f5..700335cde618 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <pthread.h>
 #include <dlfcn.h>
+#include <unistd.h>
 #include <subcmd/pager.h>
 #include "../util/debug.h"
 #include "../util/hist.h"
-#include "../util/util.h"
 #include "ui.h"
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 832ca6cfbe30..5365606e9dad 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -5,6 +5,7 @@
 #include "../../util/callchain.h"
 #include "../../util/debug.h"
+#include "../../util/event.h"
 #include "../../util/hist.h"
 #include "../../util/map.h"
 #include "../../util/map_groups.h"
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 5f188f678c55..298d6af82fdd 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -6,7 +6,6 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include "../../util/debug.h"
 #include "../helpline.h"
 #include "../ui.h"
 #include "../libslang.h"
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 56651a4f5aa0..e9bfe856a5de 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -2,13 +2,13 @@
 #include <signal.h>
 #include <stdbool.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <linux/kernel.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 #include "../../util/debug.h"
-#include "../../util/util.h"
 #include "../../perf.h"
 #include "../browser.h"
 #include "../helpline.h"
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index 087d9ab054c8..b98dd0e31dc1 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -5,7 +5,6 @@
 #include <stdlib.h>
 #include <sys/ttydefaults.h>
-#include "../../util/debug.h"
 #include "../browser.h"
 #include "../keysyms.h"
 #include "../helpline.h"
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;
+struct perf_tool;
-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_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;
+#endif // __PERF_TSC_H
-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
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