Merge tag 'perf-core-for-mingo-5.4-20190826' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

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

perf report:

  Andi Kleen:

  - Make --ns time sort key output column wide enough for nanoseconds.

perf script:

  Gustavo A. R. Silva:

  - Fix memory leaks in list_scripts()

perf tests:

  James Clark:

  - Fixes hang in zstd compression test by changing the source of random data.

perf trace:

  Arnaldo Carvalho de Melo:

  - augmented_raw_syscalls.c BPF helper improvements.

  Benjamin Peterson:

  - Fix off-by-one error in ioctl cmd->string table.

libperf:

  Jiri Olsa:

  - Move most PERF_RECORD_ structs to perf/event.h.

headers:

  Arnaldo Carvalho de Melo:

  - Move cacheline related routines to separate source files.

  - Move record_opts and other record declarations to separate files.

  - Explicitly add some more needed headers here and there.

  Souptick Joarder:

  - Remove some duplicate include directives.

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

69 files changed, 493 insertions, 427 deletions

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index c73da3245b67..a185dab2d903 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -15,7 +15,7 @@
 #include <linux/zalloc.h>
 
 #include "cs-etm.h"
-#include "../../perf.h"
+#include "../../util/record.h"
 #include "../../util/auxtrace.h"
 #include "../../util/cpumap.h"
 #include "../../util/evlist.h"
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 00915b8fd05b..cdd5c0c84183 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -19,6 +19,7 @@
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/auxtrace.h"
+#include "../../util/record.h"
 #include "../../util/arm-spe.h"
 
 #define KiB(x) ((x) * 1024)
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index cab46f517b83..f32d7a72d039 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -8,6 +8,7 @@
 #include "../../util/evlist.h"
 #include "../../util/auxtrace.h"
 #include "../../util/evsel.h"
+#include "../../util/record.h"
 
 #define PERF_EVENT_CPUM_SF              0xB0000 /* Event: Basic-sampling */
 #define PERF_EVENT_CPUM_SF_DIAG         0xBD000 /* Event: Combined-sampling */
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 582182d98a7f..02776109ba46 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <linux/types.h>
@@ -13,6 +14,7 @@
 #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/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 2d5d8a12dd1f..1f2cf612bc9c 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -17,6 +17,7 @@
 #include "../../util/session.h"
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
+#include "../../util/record.h"
 #include "../../util/tsc.h"
 #include "../../util/auxtrace.h"
 #include "../../util/intel-bts.h"
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index c72a77a82b39..44cfe72c1a4c 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -13,7 +13,6 @@
 #include <linux/zalloc.h>
 #include <cpuid.h>
 
-#include "../../perf.h"
 #include "../../util/session.h"
 #include "../../util/event.h"
 #include "../../util/evlist.h"
@@ -24,6 +23,8 @@
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/auxtrace.h"
+#include "../../util/record.h"
+#include "../../util/target.h"
 #include "../../util/tsc.h"
 #include "../../util/intel-pt.h"
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 211143720078..73782d99ee5a 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -26,6 +26,7 @@
 #include "hist.h"
 #include "sort.h"
 #include "tool.h"
+#include "cacheline.h"
 #include "data.h"
 #include "event.h"
 #include "evlist.h"
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index e91c0d798181..51c37e53b3d8 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -15,6 +15,7 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/sort.h"
+#include "util/srcline.h"
 #include "util/symbol.h"
 #include "util/data.h"
 #include "util/config.h"
@@ -22,6 +23,7 @@
 #include "util/annotate.h"
 #include "util/map.h"
 #include <linux/zalloc.h>
+#include <subcmd/parse-options.h>
 
 #include <errno.h>
 #include <inttypes.h>
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f71631f2bcb5..359bb8f33e57 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -8,8 +8,6 @@
  */
 #include "builtin.h"
 
-#include "perf.h"
-
 #include "util/build-id.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
@@ -22,9 +20,11 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/target.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"
+#include "util/record.h"
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 79dfb1139f94..318b0b95c14c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -28,6 +28,7 @@
 #include "util/evswitch.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/srcline.h"
 #include "util/tool.h"
 
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0d6b4c3b1a51..025151dcb651 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2643,7 +2643,7 @@ static int process_lost(struct perf_tool *tool __maybe_unused,
 
         timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
         printf("%15s ", tstr);
-        printf("lost %" PRIu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
+        printf("lost %" PRI_lu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
 
         return 0;
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9b93ddeaeafa..51e7e6d0eee6 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 
-#include "perf.h"
 #include "util/cache.h"
 #include "util/counts.h"
 #include "util/debug.h"
@@ -12,6 +11,7 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/map.h"
+#include "util/srcline.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
@@ -51,6 +51,7 @@
 #include <unistd.h>
 #include <subcmd/pager.h>
 #include <perf/evlist.h>
+#include "util/record.h"
 
 #include <linux/ctype.h>
 
@@ -2491,8 +2492,8 @@ static int __cmd_script(struct perf_script *script)
                 script->tool.finished_round = process_finished_round_event;
         }
         if (script->show_bpf_events) {
-                script->tool.ksymbol   = process_bpf_events;
-                script->tool.bpf_event = process_bpf_events;
+                script->tool.ksymbol = process_bpf_events;
+                script->tool.bpf     = process_bpf_events;
         }
 
         if (perf_script__setup_per_event_dump(script)) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8a4f1a7d0cba..6ab13f466827 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -40,7 +40,6 @@
  *   Jaswinder Singh Rajput <jaswinder@kernel.org>
  */
 
-#include "perf.h"
 #include "builtin.h"
 #include "util/cgroup.h"
 #include <subcmd/parse-options.h>
@@ -62,6 +61,7 @@
 #include "util/tool.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
+#include "util/target.h"
 #include "util/top.h"
 #include "asm/bug.h"
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index de126258ca10..8ea62fd2591d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -14,6 +14,7 @@
  * http://lwn.net/Articles/415728/ ("Announcing a new utility: 'trace'")
  */
 
+#include "util/record.h"
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include <bpf/bpf.h>
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 79787cf4fce9..b80437971d80 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -60,7 +60,7 @@ struct syscall_exit_args {
         long               ret;
 };
 
-struct augmented_filename {
+struct augmented_arg {
         unsigned int    size;
         int             err;
         char            value[PATH_MAX];
@@ -72,41 +72,52 @@ struct augmented_args_payload {
        struct syscall_enter_args args;
        union {
                 struct {
-                        struct augmented_filename filename,
-                                                  filename2;
+                        struct augmented_arg arg, arg2;
                 };
                 struct sockaddr_storage saddr;
         };
 };
 
+// We need more tmp space than the BPF stack can give us
 bpf_map(augmented_args_tmp, PERCPU_ARRAY, int, struct augmented_args_payload, 1);
 
+static inline struct augmented_args_payload *augmented_args_payload(void)
+{
+        int key = 0;
+        return bpf_map_lookup_elem(&augmented_args_tmp, &key);
+}
+
+static inline int augmented__output(void *ctx, struct augmented_args_payload *args, int len)
+{
+        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
+        return perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, args, len);
+}
+
 static inline
-unsigned int augmented_filename__read(struct augmented_filename *augmented_filename,
-                                      const void *filename_arg, unsigned int filename_len)
+unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
 {
-        unsigned int len = sizeof(*augmented_filename);
-        int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg);
+        unsigned int augmented_len = sizeof(*augmented_arg);
+        int string_len = probe_read_str(&augmented_arg->value, arg_len, arg);
 
-        augmented_filename->size = augmented_filename->err = 0;
+        augmented_arg->size = augmented_arg->err = 0;
         /*
          * probe_read_str may return < 0, e.g. -EFAULT
-         * So we leave that in the augmented_filename->size that userspace will
+         * So we leave that in the augmented_arg->size that userspace will
          */
-        if (size > 0) {
-                len -= sizeof(augmented_filename->value) - size;
-                len &= sizeof(augmented_filename->value) - 1;
-                augmented_filename->size = size;
+        if (string_len > 0) {
+                augmented_len -= sizeof(augmented_arg->value) - string_len;
+                augmented_len &= sizeof(augmented_arg->value) - 1;
+                augmented_arg->size = string_len;
         } else {
                 /*
                  * So that username notice the error while still being able
                  * to skip this augmented arg record
                  */
-                augmented_filename->err = size;
-                len = offsetof(struct augmented_filename, value);
+                augmented_arg->err = string_len;
+                augmented_len = offsetof(struct augmented_arg, value);
         }
 
-        return len;
+        return augmented_len;
 }
 
 SEC("!raw_syscalls:unaugmented")
@@ -124,8 +135,7 @@ int syscall_unaugmented(struct syscall_enter_args *args)
 SEC("!syscalls:sys_enter_connect")
 int sys_enter_connect(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *sockaddr_arg = (const void *)args->args[1];
         unsigned int socklen = args->args[2];
         unsigned int len = sizeof(augmented_args->args);
@@ -138,15 +148,13 @@ int sys_enter_connect(struct syscall_enter_args *args)
 
         probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len + socklen);
+        return augmented__output(args, augmented_args, len + socklen);
 }
 
 SEC("!syscalls:sys_enter_sendto")
 int sys_enter_sendto(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *sockaddr_arg = (const void *)args->args[4];
         unsigned int socklen = args->args[5];
         unsigned int len = sizeof(augmented_args->args);
@@ -159,49 +167,43 @@ int sys_enter_sendto(struct syscall_enter_args *args)
 
         probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len + socklen);
+        return augmented__output(args, augmented_args, len + socklen);
 }
 
 SEC("!syscalls:sys_enter_open")
 int sys_enter_open(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *filename_arg = (const void *)args->args[0];
         unsigned int len = sizeof(augmented_args->args);
 
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-        len += augmented_filename__read(&augmented_args->filename, filename_arg, sizeof(augmented_args->filename.value));
+        len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
+        return augmented__output(args, augmented_args, len);
 }
 
 SEC("!syscalls:sys_enter_openat")
 int sys_enter_openat(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *filename_arg = (const void *)args->args[1];
         unsigned int len = sizeof(augmented_args->args);
 
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-        len += augmented_filename__read(&augmented_args->filename, filename_arg, sizeof(augmented_args->filename.value));
+        len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
+        return augmented__output(args, augmented_args, len);
 }
 
 SEC("!syscalls:sys_enter_rename")
 int sys_enter_rename(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *oldpath_arg = (const void *)args->args[0],
                    *newpath_arg = (const void *)args->args[1];
         unsigned int len = sizeof(augmented_args->args), oldpath_len;
@@ -209,18 +211,16 @@ int sys_enter_rename(struct syscall_enter_args *args)
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-        oldpath_len = augmented_filename__read(&augmented_args->filename, oldpath_arg, sizeof(augmented_args->filename.value));
-        len += oldpath_len + augmented_filename__read((void *)(&augmented_args->filename) + oldpath_len, newpath_arg, sizeof(augmented_args->filename.value));
+        oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
+        len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
+        return augmented__output(args, augmented_args, len);
 }
 
 SEC("!syscalls:sys_enter_renameat")
 int sys_enter_renameat(struct syscall_enter_args *args)
 {
-        int key = 0;
-        struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
+        struct augmented_args_payload *augmented_args = augmented_args_payload();
         const void *oldpath_arg = (const void *)args->args[1],
                    *newpath_arg = (const void *)args->args[3];
         unsigned int len = sizeof(augmented_args->args), oldpath_len;
@@ -228,11 +228,10 @@ int sys_enter_renameat(struct syscall_enter_args *args)
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-        oldpath_len = augmented_filename__read(&augmented_args->filename, oldpath_arg, sizeof(augmented_args->filename.value));
-        len += oldpath_len + augmented_filename__read((void *)(&augmented_args->filename) + oldpath_len, newpath_arg, sizeof(augmented_args->filename.value));
+        oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
+        len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
 
-        /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-        return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
+        return augmented__output(args, augmented_args, len);
 }
 
 SEC("raw_syscalls:sys_enter")
@@ -250,15 +249,14 @@ int sys_enter(struct syscall_enter_args *args)
          */
         unsigned int len = sizeof(augmented_args->args);
         struct syscall *syscall;
-        int key = 0;
-
-        augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key);
-        if (augmented_args == NULL)
-                return 1;
 
         if (pid_filter__has(&pids_filtered, getpid()))
                 return 0;
 
+        augmented_args = augmented_args_payload();
+        if (augmented_args == NULL)
+                return 1;
+
         probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
 
         /*
diff --git a/tools/perf/lib/include/perf/event.h b/tools/perf/lib/include/perf/event.h
new file mode 100644
index 000000000000..36ad3a4a79e6
--- /dev/null
+++ b/tools/perf/lib/include/perf/event.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LIBPERF_EVENT_H
+#define __LIBPERF_EVENT_H
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/limits.h>
+#include <linux/bpf.h>
+
+struct perf_record_mmap {
+        struct perf_event_header header;
+        __u32                    pid, tid;
+        __u64                    start;
+        __u64                    len;
+        __u64                    pgoff;
+        char                     filename[PATH_MAX];
+};
+
+struct perf_record_mmap2 {
+        struct perf_event_header header;
+        __u32                    pid, tid;
+        __u64                    start;
+        __u64                    len;
+        __u64                    pgoff;
+        __u32                    maj;
+        __u32                    min;
+        __u64                    ino;
+        __u64                    ino_generation;
+        __u32                    prot;
+        __u32                    flags;
+        char                     filename[PATH_MAX];
+};
+
+struct perf_record_comm {
+        struct perf_event_header header;
+        __u32                    pid, tid;
+        char                     comm[16];
+};
+
+struct perf_record_namespaces {
+        struct perf_event_header header;
+        __u32                    pid, tid;
+        __u64                    nr_namespaces;
+        struct perf_ns_link_info link_info[];
+};
+
+struct perf_record_fork {
+        struct perf_event_header header;
+        __u32                    pid, ppid;
+        __u32                    tid, ptid;
+        __u64                    time;
+};
+
+struct perf_record_lost {
+        struct perf_event_header header;
+        __u64                    id;
+        __u64                    lost;
+};
+
+struct perf_record_lost_samples {
+        struct perf_event_header header;
+        __u64                    lost;
+};
+
+/*
+ * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ */
+struct perf_record_read {
+        struct perf_event_header header;
+        __u32                    pid, tid;
+        __u64                    value;
+        __u64                    time_enabled;
+        __u64                    time_running;
+        __u64                    id;
+};
+
+struct perf_record_throttle {
+        struct perf_event_header header;
+        __u64                    time;
+        __u64                    id;
+        __u64                    stream_id;
+};
+
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+struct perf_record_ksymbol {
+        struct perf_event_header header;
+        __u64                    addr;
+        __u32                    len;
+        __u16                    ksym_type;
+        __u16                    flags;
+        char                     name[KSYM_NAME_LEN];
+};
+
+struct perf_record_bpf_event {
+        struct perf_event_header header;
+        __u16                    type;
+        __u16                    flags;
+        __u32                    id;
+
+        /* for bpf_prog types */
+        __u8                     tag[BPF_TAG_SIZE];  // prog tag
+};
+
+struct perf_record_sample {
+        struct perf_event_header header;
+        __u64                    array[];
+};
+
+#endif /* __LIBPERF_EVENT_H */
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index dc0a7a237887..d9e6b8b957b6 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -35,63 +35,6 @@ extern const char perf_version_string[];
 
 void pthread__unblock_sigwinch(void);
 
-#include "util/target.h"
-
-struct record_opts {
-        struct target target;
-        bool         group;
-        bool         inherit_stat;
-        bool         no_buffering;
-        bool         no_inherit;
-        bool         no_inherit_set;
-        bool         no_samples;
-        bool         raw_samples;
-        bool         sample_address;
-        bool         sample_phys_addr;
-        bool         sample_weight;
-        bool         sample_time;
-        bool         sample_time_set;
-        bool         sample_cpu;
-        bool         period;
-        bool         period_set;
-        bool         running_time;
-        bool         full_auxtrace;
-        bool         auxtrace_snapshot_mode;
-        bool         auxtrace_snapshot_on_exit;
-        bool         record_namespaces;
-        bool         record_switch_events;
-        bool         all_kernel;
-        bool         all_user;
-        bool         kernel_callchains;
-        bool         user_callchains;
-        bool         tail_synthesize;
-        bool         overwrite;
-        bool         ignore_missing_thread;
-        bool         strict_freq;
-        bool         sample_id;
-        bool         no_bpf_event;
-        unsigned int freq;
-        unsigned int mmap_pages;
-        unsigned int auxtrace_mmap_pages;
-        unsigned int user_freq;
-        u64          branch_stack;
-        u64          sample_intr_regs;
-        u64          sample_user_regs;
-        u64          default_interval;
-        u64          user_interval;
-        size_t       auxtrace_snapshot_size;
-        const char   *auxtrace_snapshot_opts;
-        bool         sample_transaction;
-        unsigned     initial_delay;
-        bool         use_clockid;
-        clockid_t    clockid;
-        u64          clockid_res_ns;
-        int          nr_cblocks;
-        int          affinity;
-        int          mmap_flush;
-        unsigned int comp_level;
-};
-
 enum perf_affinity {
         PERF_AFFINITY_SYS = 0,
         PERF_AFFINITY_NODE,
@@ -99,10 +42,5 @@ enum perf_affinity {
         PERF_AFFINITY_MAX
 };
 
-struct option;
-extern const char * const *record_usage;
-extern struct option *record_options;
 extern int version_verbose;
-
-int record__parse_freq(const struct option *opt, const char *str, int unset);
 #endif
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 9bdf66139099..b6f27ef9fb02 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -4,9 +4,9 @@
  * beginning
  */
 
-#include <perf.h>
 #include <evlist.h>
 #include <sys/prctl.h>
+#include "record.h"
 #include "tests.h"
 #include "debug.h"
 #include <errno.h>
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index e16f927f38b6..98642961fc63 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -5,6 +5,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <util/record.h>
 #include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index e45df0736261..fe671b860086 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -20,6 +20,7 @@
 #include "map.h"
 #include "symbol.h"
 #include "event.h"
+#include "record.h"
 #include "thread.h"
 
 #include "tests.h"
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 0ce5ce33bac4..2af6faf1bbd6 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -8,6 +8,7 @@
 #include "parse-events.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "record.h"
 #include "thread_map.h"
 #include "cpumap.h"
 #include "tests.h"
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 9c06130d37be..62492106fb5e 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -1,12 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
 #include <linux/err.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include "perf.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
+#include "record.h"
 #include "tests.h"
 #include "debug.h"
 #include <errno.h>
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 396e40d68922..8284752a60c8 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -87,10 +87,10 @@ int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest _
                 },
                 .id = 2,
         };
-        struct mmap_event event3 = {
+        struct perf_record_mmap event3 = {
                 .header = {
                         .type = PERF_RECORD_MMAP,
-                        .size = sizeof(struct mmap_event),
+                        .size = sizeof(struct perf_record_mmap),
                 },
         };
         union perf_event *events[] = {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 67b388e92cba..3a205f6f9363 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -7,8 +7,8 @@
 #include <sched.h>
 #include "evlist.h"
 #include "evsel.h"
-#include "perf.h"
 #include "debug.h"
+#include "record.h"
 #include "tests.h"
 
 static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
index 899604d17b85..63a91ec473bb 100755
--- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -13,7 +13,7 @@ skip_if_no_z_record() {
 collect_z_record() {
         echo "Collecting compressed record file:"
         $perf_tool record -o $trace_file -g -z -F 5000 -- \
-                dd count=500 if=/dev/random of=/dev/null
+                dd count=500 if=/dev/urandom of=/dev/null
 }
 
 check_compressed_stats() {
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index e3cee69f6ea2..b63f02768724 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -13,6 +13,7 @@
 #include "evsel.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "record.h"
 #include "tests.h"
 
 static int spin_sleep(void)
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 4ca38fd0379a..d79a22e2d8be 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "evlist.h"
 #include "evsel.h"
+#include "target.h"
 #include "thread_map.h"
 #include "cpumap.h"
 #include "tests.h"
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 52242fa4072b..e19eb6ea361d 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -21,7 +21,7 @@
 static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 {
         static const char *ioctl_tty_cmd[] = {
-        "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+        [_IOC_NR(TCGETS)] = "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
         "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY",
         "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ",
         "TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR",
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index 08897bd5eb0f..41a9d8923ec4 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -6,6 +6,8 @@
 #include "sort.h"
 #include "config.h"
 #include "time-utils.h"
+#include "../util.h"
+#include "../../util/util.h"
 #include <linux/time64.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 04f9aff5621e..50e0c03171f2 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "../../builtin.h"
 #include "../../util/sort.h"
+#include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
 #include "../../util/symbol.h"
@@ -131,8 +133,10 @@ static int list_scripts(char *script_name, bool *custom,
                 int key = ui_browser__input_window("perf script command",
                                 "Enter perf script command line (without perf script prefix)",
                                 script_args, "", 0);
-                if (key != K_ENTER)
-                        return -1;
+                if (key != K_ENTER) {
+                        ret = -1;
+                        goto out;
+                }
                 sprintf(script_name, "%s script %s", perf, script_args);
         } else if (choice < num + max_std) {
                 strcpy(script_name, paths[choice]);
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index ee7ea6deed21..51ed67548b83 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -3,6 +3,7 @@
 #include <linux/string.h>
 
 #include "../../util/callchain.h"
+#include "../../util/debug.h"
 #include "../../util/hist.h"
 #include "../../util/map.h"
 #include "../../util/map_groups.h"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index b922c8c297ca..2e3856471e61 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,6 +1,7 @@
 perf-y += annotate.o
 perf-y += block-range.o
 perf-y += build-id.o
+perf-y += cacheline.o
 perf-y += config.o
 perf-y += ctype.o
 perf-y += db-export.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e0518dc4c4d2..3bd1691f0be7 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -22,6 +22,7 @@
 #include "cache.h"
 #include "map.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
@@ -37,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <bpf/libbpf.h>
+#include <subcmd/parse-options.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 094e6ceb3cf2..12e9b7acbb2c 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -26,7 +26,6 @@
 #include <linux/list.h>
 #include <linux/zalloc.h>
 
-#include "../perf.h"
 #include "evlist.h"
 #include "dso.h"
 #include "map.h"
@@ -41,6 +40,7 @@
 #include <linux/hash.h>
 
 #include "event.h"
+#include "record.h"
 #include "session.h"
 #include "debug.h"
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 5a5dcc6d8f85..2d6d500c9af7 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -14,6 +14,7 @@
 #include "session.h"
 #include "map.h"
 #include "evlist.h"
+#include "record.h"
 
 #define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
 
@@ -34,7 +35,7 @@ static int machine__process_bpf_event_load(struct machine *machine,
         struct bpf_prog_info_linear *info_linear;
         struct bpf_prog_info_node *info_node;
         struct perf_env *env = machine->env;
-        int id = event->bpf_event.id;
+        int id = event->bpf.id;
         unsigned int i;
 
         /* perf-record, no need to handle bpf-event */
@@ -63,14 +64,13 @@ static int machine__process_bpf_event_load(struct machine *machine,
         return 0;
 }
 
-int machine__process_bpf_event(struct machine *machine __maybe_unused,
-                               union perf_event *event,
-                               struct perf_sample *sample __maybe_unused)
+int machine__process_bpf(struct machine *machine, union perf_event *event,
+                         struct perf_sample *sample)
 {
         if (dump_trace)
-                perf_event__fprintf_bpf_event(event, stdout);
+                perf_event__fprintf_bpf(event, stdout);
 
-        switch (event->bpf_event.type) {
+        switch (event->bpf.type) {
         case PERF_BPF_EVENT_PROG_LOAD:
                 return machine__process_bpf_event_load(machine, event, sample);
 
@@ -82,8 +82,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
                  */
                 break;
         default:
-                pr_debug("unexpected bpf_event type of %d\n",
-                         event->bpf_event.type);
+                pr_debug("unexpected bpf event type of %d\n", event->bpf.type);
                 break;
         }
         return 0;
@@ -160,8 +159,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
                                                union perf_event *event,
                                                struct record_opts *opts)
 {
-        struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
-        struct bpf_event *bpf_event = &event->bpf_event;
+        struct perf_record_ksymbol *ksymbol_event = &event->ksymbol;
+        struct perf_record_bpf_event *bpf_event = &event->bpf;
         struct bpf_prog_info_linear *info_linear;
         struct perf_tool *tool = session->tool;
         struct bpf_prog_info_node *info_node;
@@ -229,10 +228,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
                 __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
                 int name_len;
 
-                *ksymbol_event = (struct ksymbol_event){
+                *ksymbol_event = (struct perf_record_ksymbol) {
                         .header = {
                                 .type = PERF_RECORD_KSYMBOL,
-                                .size = offsetof(struct ksymbol_event, name),
+                                .size = offsetof(struct perf_record_ksymbol, name),
                         },
                         .addr = prog_addrs[i],
                         .len = prog_lens[i],
@@ -253,10 +252,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 
         if (!opts->no_bpf_event) {
                 /* Synthesize PERF_RECORD_BPF_EVENT */
-                *bpf_event = (struct bpf_event){
+                *bpf_event = (struct perf_record_bpf_event) {
                         .header = {
                                 .type = PERF_RECORD_BPF_EVENT,
-                                .size = sizeof(struct bpf_event),
+                                .size = sizeof(struct perf_record_bpf_event),
                         },
                         .type = PERF_BPF_EVENT_PROG_LOAD,
                         .flags = 0,
@@ -301,7 +300,7 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
         int err;
         int fd;
 
-        event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN + machine->id_hdr_size);
+        event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
         if (!event)
                 return -1;
         while (true) {
@@ -398,9 +397,9 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
         if (event->header.type != PERF_RECORD_BPF_EVENT)
                 return -1;
 
-        switch (event->bpf_event.type) {
+        switch (event->bpf.type) {
         case PERF_BPF_EVENT_PROG_LOAD:
-                perf_env__add_bpf_info(env, event->bpf_event.id);
+                perf_env__add_bpf_info(env, event->bpf.id);
 
         case PERF_BPF_EVENT_PROG_UNLOAD:
                 /*
@@ -410,8 +409,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
                  */
                 break;
         default:
-                pr_debug("unexpected bpf_event type of %d\n",
-                         event->bpf_event.type);
+                pr_debug("unexpected bpf event type of %d\n", event->bpf.type);
                 break;
         }
 
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 26ab9239f986..417b78835ea0 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -30,8 +30,8 @@ struct btf_node {
 };
 
 #ifdef HAVE_LIBBPF_SUPPORT
-int machine__process_bpf_event(struct machine *machine, union perf_event *event,
-                               struct perf_sample *sample);
+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,
@@ -43,9 +43,9 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
                                     struct perf_env *env,
                                     FILE *fp);
 #else
-static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
-                                             union perf_event *event __maybe_unused,
-                                             struct perf_sample *sample __maybe_unused)
+static inline int machine__process_bpf(struct machine *machine __maybe_unused,
+                                       union perf_event *event __maybe_unused,
+                                       struct perf_sample *sample __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/cacheline.c b/tools/perf/util/cacheline.c
new file mode 100644
index 000000000000..9361d3f61f75
--- /dev/null
+++ b/tools/perf/util/cacheline.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "cacheline.h"
+#include "../perf.h"
+#include <unistd.h>
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+#include <api/fs/fs.h>
+#include "debug.h"
+static void cache_line_size(int *cacheline_sizep)
+{
+        if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+                pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+        static int size;
+
+        if (!size)
+                cache_line_size(&size);
+
+        return size;
+}
diff --git a/tools/perf/util/cacheline.h b/tools/perf/util/cacheline.h
new file mode 100644
index 000000000000..dec8c0fb1f4a
--- /dev/null
+++ b/tools/perf/util/cacheline.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CACHELINE_H
+#define PERF_CACHELINE_H
+
+#include <linux/compiler.h>
+
+int __pure cacheline_size(void);
+
+static inline u64 cl_address(u64 address)
+{
+        /* return the cacheline of the address */
+        return (address & ~(cacheline_size() - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+        /* return the cacheline of the address */
+        return (address & (cacheline_size() - 1));
+}
+
+#endif // PERF_CACHELINE_H
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index d077704f9afa..dd6e01000385 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -20,6 +20,7 @@
 
 #include "asm/bug.h"
 
+#include "debug.h"
 #include "hist.h"
 #include "sort.h"
 #include "machine.h"
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index d0c5bbfd91af..c2519e7ea958 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -7,8 +7,6 @@
 #include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
-#include "perf.h"
-
 struct cpu_map_data;
 
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 1d1b97a92c3f..74aafe0df506 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -9,7 +9,6 @@
 #include <unistd.h>
 #include <string.h>
 #include <asm/bug.h>
-#include <sys/types.h>
 #include <dirent.h>
 
 #include "data.h"
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 332edef8d394..33616ea62a47 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -387,7 +387,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 strcpy(execname, "");
 
                 /* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
+                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,
@@ -1343,17 +1343,17 @@ int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
         return machine__process_ksymbol(machine, event, sample);
 }
 
-int perf_event__process_bpf_event(struct perf_tool *tool __maybe_unused,
-                                  union perf_event *event,
-                                  struct perf_sample *sample __maybe_unused,
-                                  struct machine *machine)
+int perf_event__process_bpf(struct perf_tool *tool __maybe_unused,
+                            union perf_event *event,
+                            struct perf_sample *sample,
+                            struct machine *machine)
 {
-        return machine__process_bpf_event(machine, event, sample);
+        return machine__process_bpf(machine, event, sample);
 }
 
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
-        return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
+        return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 "]: %c %s\n",
                        event->mmap.pid, event->mmap.tid, event->mmap.start,
                        event->mmap.len, event->mmap.pgoff,
                        (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
@@ -1362,8 +1362,8 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
-        return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-                           " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
+        return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64
+                           " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n",
                        event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
                        event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
                        event->mmap2.min, event->mmap2.ino,
@@ -1480,22 +1480,21 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
 
 static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
 {
-        return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
+        return fprintf(fp, " lost %" PRI_lu64 "\n", event->lost.lost);
 }
 
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
 {
-        return fprintf(fp, " addr %" PRIx64 " len %u type %u flags 0x%x name %s\n",
-                       event->ksymbol_event.addr, event->ksymbol_event.len,
-                       event->ksymbol_event.ksym_type,
-                       event->ksymbol_event.flags, event->ksymbol_event.name);
+        return fprintf(fp, " addr %" PRI_lx64 " len %u type %u flags 0x%x name %s\n",
+                       event->ksymbol.addr, event->ksymbol.len,
+                       event->ksymbol.ksym_type,
+                       event->ksymbol.flags, event->ksymbol.name);
 }
 
-size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp)
 {
         return fprintf(fp, " type %u, flags %u, id %u\n",
-                       event->bpf_event.type, event->bpf_event.flags,
-                       event->bpf_event.id);
+                       event->bpf.type, event->bpf.flags, event->bpf.id);
 }
 
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
@@ -1537,7 +1536,7 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
                 ret += perf_event__fprintf_ksymbol(event, fp);
                 break;
         case PERF_RECORD_BPF_EVENT:
-                ret += perf_event__fprintf_bpf_event(event, fp);
+                ret += perf_event__fprintf_bpf(event, fp);
                 break;
         default:
                 ret += fprintf(fp, "\n");
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0e164e8ae28d..429a3fe52d6c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,108 +7,26 @@
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/perf_event.h>
+#include <perf/event.h>
 
 #include "../perf.h"
 #include "build-id.h"
 #include "perf_regs.h"
 
-struct mmap_event {
-        struct perf_event_header header;
-        u32 pid, tid;
-        u64 start;
-        u64 len;
-        u64 pgoff;
-        char filename[PATH_MAX];
-};
-
-struct mmap2_event {
-        struct perf_event_header header;
-        u32 pid, tid;
-        u64 start;
-        u64 len;
-        u64 pgoff;
-        u32 maj;
-        u32 min;
-        u64 ino;
-        u64 ino_generation;
-        u32 prot;
-        u32 flags;
-        char filename[PATH_MAX];
-};
-
-struct comm_event {
-        struct perf_event_header header;
-        u32 pid, tid;
-        char comm[16];
-};
-
-struct namespaces_event {
-        struct perf_event_header header;
-        u32 pid, tid;
-        u64 nr_namespaces;
-        struct perf_ns_link_info link_info[];
-};
-
-struct fork_event {
-        struct perf_event_header header;
-        u32 pid, ppid;
-        u32 tid, ptid;
-        u64 time;
-};
-
-struct lost_event {
-        struct perf_event_header header;
-        u64 id;
-        u64 lost;
-};
-
-struct lost_samples_event {
-        struct perf_event_header header;
-        u64 lost;
-};
-
+#ifdef __LP64__
 /*
- * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ * /usr/include/inttypes.h uses just 'lu' for PRIu64, but we end up defining
+ * __u64 as long long unsigned int, and then -Werror=format= kicks in and
+ * complains of the mismatched types, so use these two special extra PRI
+ * macros to overcome that.
  */
-struct read_event {
-        struct perf_event_header header;
-        u32 pid, tid;
-        u64 value;
-        u64 time_enabled;
-        u64 time_running;
-        u64 id;
-};
-
-struct throttle_event {
-        struct perf_event_header header;
-        u64 time;
-        u64 id;
-        u64 stream_id;
-};
-
-#ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
+#define PRI_lu64 "l" PRIu64
+#define PRI_lx64 "l" PRIx64
+#else
+#define PRI_lu64 PRIu64
+#define PRI_lx64 PRIx64
 #endif
 
-struct ksymbol_event {
-        struct perf_event_header header;
-        u64 addr;
-        u32 len;
-        u16 ksym_type;
-        u16 flags;
-        char name[KSYM_NAME_LEN];
-};
-
-struct bpf_event {
-        struct perf_event_header header;
-        u16 type;
-        u16 flags;
-        u32 id;
-
-        /* for bpf_prog types */
-        u8 tag[BPF_TAG_SIZE];  // prog tag
-};
-
 #define PERF_SAMPLE_MASK                                \
         (PERF_SAMPLE_IP | PERF_SAMPLE_TID |             \
          PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
@@ -119,11 +37,6 @@ struct bpf_event {
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
-struct sample_event {
-        struct perf_event_header        header;
-        u64 array[];
-};
-
 struct regs_dump {
         u64 abi;
         u64 mask;
@@ -392,18 +305,18 @@ static inline void *perf_synth__raw_data(void *p)
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
  * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
  * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
- * the sum of all struct lost_event.lost fields reported.
+ * the sum of all struct perf_record_lost.lost fields reported.
  *
  * The kernel discards mixed up samples and sends the number in a
  * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
  * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
  * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
- * all struct lost_samples_event.lost fields reported.
+ * all struct perf_record_lost_samples.lost fields reported.
  *
  * The total_period is needed because by default auto-freq is used, so
  * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
  * the total number of low level events, it is necessary to to sum all struct
- * sample_event.period and stash the result in total_period.
+ * perf_record_sample.period and stash the result in total_period.
  */
 struct events_stats {
         u64 total_period;
@@ -637,16 +550,18 @@ struct compressed_event {
 
 union perf_event {
         struct perf_event_header        header;
-        struct mmap_event               mmap;
-        struct mmap2_event              mmap2;
-        struct comm_event               comm;
-        struct namespaces_event         namespaces;
-        struct fork_event               fork;
-        struct lost_event               lost;
-        struct lost_samples_event       lost_samples;
-        struct read_event               read;
-        struct throttle_event           throttle;
-        struct sample_event             sample;
+        struct perf_record_mmap         mmap;
+        struct perf_record_mmap2        mmap2;
+        struct perf_record_comm         comm;
+        struct perf_record_namespaces   namespaces;
+        struct perf_record_fork         fork;
+        struct perf_record_lost         lost;
+        struct perf_record_lost_samples lost_samples;
+        struct perf_record_read         read;
+        struct perf_record_throttle     throttle;
+        struct perf_record_sample       sample;
+        struct perf_record_bpf_event    bpf;
+        struct perf_record_ksymbol      ksymbol;
         struct attr_event               attr;
         struct event_update_event       event_update;
         struct event_type_event         event_type;
@@ -666,8 +581,6 @@ union perf_event {
         struct stat_round_event         stat_round;
         struct time_conv_event          time_conv;
         struct feature_event            feat;
-        struct ksymbol_event            ksymbol_event;
-        struct bpf_event                bpf_event;
         struct compressed_event         pack;
 };
 
@@ -770,10 +683,10 @@ int perf_event__process_ksymbol(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_sample *sample,
                                 struct machine *machine);
-int perf_event__process_bpf_event(struct perf_tool *tool,
-                                  union perf_event *event,
-                                  struct perf_sample *sample,
-                                  struct machine *machine);
+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,
@@ -838,7 +751,7 @@ size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ff415680fe0a..47bc54111f57 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -587,7 +587,7 @@ struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
 static int perf_evlist__event2id(struct evlist *evlist,
                                  union perf_event *event, u64 *id)
 {
-        const u64 *array = event->sample.array;
+        const __u64 *array = event->sample.array;
         ssize_t n;
 
         n = (event->header.size - sizeof(event->header)) >> 3;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e983e721beca..fa676355559e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -34,6 +34,7 @@
 #include "thread_map.h"
 #include "target.h"
 #include "perf_regs.h"
+#include "record.h"
 #include "debug.h"
 #include "trace-event.h"
 #include "stat.h"
@@ -116,7 +117,7 @@ int __perf_evsel__sample_size(u64 sample_type)
  *
  * This function returns the position of the event id (PERF_SAMPLE_ID or
  * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
- * sample_event.
+ * perf_record_sample.
  */
 static int __perf_evsel__calc_id_pos(u64 sample_type)
 {
@@ -1071,8 +1072,7 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
         attr->mmap2 = track && !perf_missing_features.mmap2;
         attr->comm  = track;
         attr->ksymbol = track && !perf_missing_features.ksymbol;
-        attr->bpf_event = track && !opts->no_bpf_event &&
-                !perf_missing_features.bpf_event;
+        attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf;
 
         if (opts->record_namespaces)
                 attr->namespaces  = track;
@@ -1802,7 +1802,7 @@ fallback_missing_features:
                 evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
         if (perf_missing_features.ksymbol)
                 evsel->core.attr.ksymbol = 0;
-        if (perf_missing_features.bpf_event)
+        if (perf_missing_features.bpf)
                 evsel->core.attr.bpf_event = 0;
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
@@ -1919,8 +1919,8 @@ try_fallback:
                 perf_missing_features.aux_output = true;
                 pr_debug2("Kernel has no attr.aux_output support, bailing out\n");
                 goto out_close;
-        } else if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) {
-                perf_missing_features.bpf_event = true;
+        } else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) {
+                perf_missing_features.bpf = true;
                 pr_debug2("switching off bpf_event\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) {
@@ -2008,7 +2008,7 @@ static int perf_evsel__parse_id_sample(const struct evsel *evsel,
                                        struct perf_sample *sample)
 {
         u64 type = evsel->core.attr.sample_type;
-        const u64 *array = event->sample.array;
+        const __u64 *array = event->sample.array;
         bool swapped = evsel->needs_swap;
         union u64_swap u;
 
@@ -2098,7 +2098,7 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 {
         u64 type = evsel->core.attr.sample_type;
         bool swapped = evsel->needs_swap;
-        const u64 *array;
+        const __u64 *array;
         u16 max_size = event->header.size;
         const void *endp = (void *)event + max_size;
         u64 sz;
@@ -2377,7 +2377,7 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
                                        u64 *timestamp)
 {
         u64 type = evsel->core.attr.sample_type;
-        const u64 *array;
+        const __u64 *array;
 
         if (!(type & PERF_SAMPLE_TIME))
                 return -1;
@@ -2419,7 +2419,7 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                                      u64 read_format)
 {
-        size_t sz, result = sizeof(struct sample_event);
+        size_t sz, result = sizeof(struct perf_record_sample);
 
         if (type & PERF_SAMPLE_IDENTIFIER)
                 result += sizeof(u64);
@@ -2528,7 +2528,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                                   u64 read_format,
                                   const struct perf_sample *sample)
 {
-        u64 *array;
+        __u64 *array;
         size_t sz;
         /*
          * used for cross-endian analysis. See git commit 65014ab3
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5a351cae66df..fd60caced4fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -107,7 +107,7 @@ struct xyarray;
  *         show the name used, not some alias.
  * @id_pos: the position of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
- *          struct sample_event
+ *          struct perf_record_sample
  * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
  *          is used there is an id sample appended to non-sample events
@@ -194,7 +194,7 @@ struct perf_missing_features {
         bool write_backward;
         bool group_read;
         bool ksymbol;
-        bool bpf_event;
+        bool bpf;
         bool aux_output;
 };
 
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
index 01f32f26552d..b205d929245f 100644
--- a/tools/perf/util/get_current_dir_name.c
+++ b/tools/perf/util/get_current_dir_name.c
@@ -5,7 +5,6 @@
 #include "get_current_dir_name.h"
 #include <unistd.h>
 #include <stdlib.h>
-#include <stdlib.h>
 
 /* Android's 'bionic' library, for one, doesn't have this */
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8efbf58dc3d0..33702675073c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -193,7 +193,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
         hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
         hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
         hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
-        hists__new_col_len(hists, HISTC_TIME, 12);
+        if (symbol_conf.nanosecs)
+                hists__new_col_len(hists, HISTC_TIME, 16);
+        else
+                hists__new_col_len(hists, HISTC_TIME, 12);
 
         if (h->srcline) {
                 len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7eb9e6dc27dd..8dc6408206b9 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -818,7 +818,7 @@ static int intel_bts_synth_events(struct intel_bts *bts,
                  * We only use sample types from PERF_SAMPLE_MASK so we can use
                  * __perf_evsel__sample_size() here.
                  */
-                bts->branches_event_size = sizeof(struct sample_event) +
+                bts->branches_event_size = sizeof(struct perf_record_sample) +
                                 __perf_evsel__sample_size(attr.sample_type);
         }
 
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index a09c495f866b..46913637085b 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -2,9 +2,9 @@
 #ifndef __PERF_KVM_STAT_H
 #define __PERF_KVM_STAT_H
 
-#include "../perf.h"
 #include "tool.h"
 #include "stat.h"
+#include "record.h"
 
 struct evsel;
 struct evlist;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5734460fc89e..93483f1764d3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -10,10 +10,13 @@
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "srcline.h"
 #include "symbol.h"
 #include "sort.h"
 #include "strlist.h"
+#include "target.h"
 #include "thread.h"
+#include "util.h"
 #include "vdso.h"
 #include <stdbool.h>
 #include <sys/types.h>
@@ -642,7 +645,7 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,
 int machine__process_lost_event(struct machine *machine __maybe_unused,
                                 union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
-        dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+        dump_printf(": id:%" PRI_lu64 ": lost:%" PRI_lu64 "\n",
                     event->lost.id, event->lost.lost);
         return 0;
 }
@@ -650,7 +653,7 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
                                         union perf_event *event, struct perf_sample *sample)
 {
-        dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+        dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n",
                     sample->id, event->lost_samples.lost);
         return 0;
 }
@@ -710,20 +713,20 @@ static int machine__process_ksymbol_register(struct machine *machine,
         struct symbol *sym;
         struct map *map;
 
-        map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+        map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
         if (!map) {
-                map = dso__new_map(event->ksymbol_event.name);
+                map = dso__new_map(event->ksymbol.name);
                 if (!map)
                         return -ENOMEM;
 
-                map->start = event->ksymbol_event.addr;
-                map->end = map->start + event->ksymbol_event.len;
+                map->start = event->ksymbol.addr;
+                map->end = map->start + event->ksymbol.len;
                 map_groups__insert(&machine->kmaps, map);
         }
 
         sym = symbol__new(map->map_ip(map, map->start),
-                          event->ksymbol_event.len,
-                          0, 0, event->ksymbol_event.name);
+                          event->ksymbol.len,
+                          0, 0, event->ksymbol.name);
         if (!sym)
                 return -ENOMEM;
         dso__insert_symbol(map->dso, sym);
@@ -736,7 +739,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 {
         struct map *map;
 
-        map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+        map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
         if (map)
                 map_groups__remove(&machine->kmaps, map);
 
@@ -750,7 +753,7 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
         if (dump_trace)
                 perf_event__fprintf_ksymbol(event, stdout);
 
-        if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
+        if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
                 return machine__process_ksymbol_unregister(machine, event,
                                                            sample);
         return machine__process_ksymbol_register(machine, event, sample);
@@ -1919,7 +1922,7 @@ int machine__process_event(struct machine *machine, union perf_event *event,
         case PERF_RECORD_KSYMBOL:
                 ret = machine__process_ksymbol(machine, event, sample); break;
         case PERF_RECORD_BPF_EVENT:
-                ret = machine__process_bpf_event(machine, event, sample); break;
+                ret = machine__process_bpf(machine, event, sample); break;
         default:
                 ret = -1;
                 break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 8b9d7157276d..7d69119d0b5d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -14,6 +14,7 @@ struct branch_stack;
 struct evsel;
 struct perf_sample;
 struct symbol;
+struct target;
 struct thread;
 union perf_event;
 
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 46d3a7754897..99be15dd2b6b 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -19,7 +19,7 @@
 #include <asm/bug.h>
 #include <linux/zalloc.h>
 
-struct namespaces *namespaces__new(struct namespaces_event *event)
+struct namespaces *namespaces__new(struct perf_record_namespaces *event)
 {
         struct namespaces *namespaces;
         u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 004430c0de93..40edef56cb52 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -17,7 +17,7 @@
 int setns(int fd, int nstype);
 #endif
 
-struct namespaces_event;
+struct perf_record_namespaces;
 
 struct namespaces {
         struct list_head list;
@@ -25,7 +25,7 @@ struct namespaces {
         struct perf_ns_link_info link_info[];
 };
 
-struct namespaces *namespaces__new(struct namespaces_event *event);
+struct namespaces *namespaces__new(struct perf_record_namespaces *event);
 void namespaces__free(struct namespaces *namespaces);
 
 struct nsinfo {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 75ecc32a4427..59974e901232 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -116,12 +116,12 @@ static PyMemberDef pyrf_mmap_event__members[] = {
         sample_members
         member_def(perf_event_header, type, T_UINT, "event type"),
         member_def(perf_event_header, misc, T_UINT, "event misc"),
-        member_def(mmap_event, pid, T_UINT, "event pid"),
-        member_def(mmap_event, tid, T_UINT, "event tid"),
-        member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
-        member_def(mmap_event, len, T_ULONGLONG, "map length"),
-        member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
-        member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+        member_def(perf_record_mmap, pid, T_UINT, "event pid"),
+        member_def(perf_record_mmap, tid, T_UINT, "event tid"),
+        member_def(perf_record_mmap, start, T_ULONGLONG, "start of the map"),
+        member_def(perf_record_mmap, len, T_ULONGLONG, "map length"),
+        member_def(perf_record_mmap, pgoff, T_ULONGLONG, "page offset"),
+        member_def(perf_record_mmap, filename, T_STRING_INPLACE, "backing store"),
         { .name = NULL, },
 };
 
@@ -130,8 +130,8 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
         PyObject *ret;
         char *s;
 
-        if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
-                         "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+        if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRI_lx64 ", "
+                         "length: %#" PRI_lx64 ", offset: %#" PRI_lx64 ", "
                          "filename: %s }",
                      pevent->event.mmap.pid, pevent->event.mmap.tid,
                      pevent->event.mmap.start, pevent->event.mmap.len,
@@ -159,18 +159,18 @@ static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event obje
 static PyMemberDef pyrf_task_event__members[] = {
         sample_members
         member_def(perf_event_header, type, T_UINT, "event type"),
-        member_def(fork_event, pid, T_UINT, "event pid"),
-        member_def(fork_event, ppid, T_UINT, "event ppid"),
-        member_def(fork_event, tid, T_UINT, "event tid"),
-        member_def(fork_event, ptid, T_UINT, "event ptid"),
-        member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+        member_def(perf_record_fork, pid, T_UINT, "event pid"),
+        member_def(perf_record_fork, ppid, T_UINT, "event ppid"),
+        member_def(perf_record_fork, tid, T_UINT, "event tid"),
+        member_def(perf_record_fork, ptid, T_UINT, "event ptid"),
+        member_def(perf_record_fork, time, T_ULONGLONG, "timestamp"),
         { .name = NULL, },
 };
 
 static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
 {
         return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
-                                   "ptid: %u, time: %" PRIu64 "}",
+                                   "ptid: %u, time: %" PRI_lu64 "}",
                                    pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
                                    pevent->event.fork.pid,
                                    pevent->event.fork.ppid,
@@ -194,9 +194,9 @@ static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");
 static PyMemberDef pyrf_comm_event__members[] = {
         sample_members
         member_def(perf_event_header, type, T_UINT, "event type"),
-        member_def(comm_event, pid, T_UINT, "event pid"),
-        member_def(comm_event, tid, T_UINT, "event tid"),
-        member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+        member_def(perf_record_comm, pid, T_UINT, "event pid"),
+        member_def(perf_record_comm, tid, T_UINT, "event tid"),
+        member_def(perf_record_comm, comm, T_STRING_INPLACE, "process name"),
         { .name = NULL, },
 };
 
@@ -223,18 +223,18 @@ static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."
 static PyMemberDef pyrf_throttle_event__members[] = {
         sample_members
         member_def(perf_event_header, type, T_UINT, "event type"),
-        member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
-        member_def(throttle_event, id, T_ULONGLONG, "event id"),
-        member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+        member_def(perf_record_throttle, time, T_ULONGLONG, "timestamp"),
+        member_def(perf_record_throttle, id, T_ULONGLONG, "event id"),
+        member_def(perf_record_throttle, stream_id, T_ULONGLONG, "event stream id"),
         { .name = NULL, },
 };
 
 static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
 {
-        struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+        struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1);
 
-        return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
-                                   ", stream_id: %" PRIu64 " }",
+        return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64
+                                   ", stream_id: %" PRI_lu64 " }",
                                    pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
                                    te->time, te->id, te->stream_id);
 }
@@ -253,8 +253,8 @@ static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object.");
 
 static PyMemberDef pyrf_lost_event__members[] = {
         sample_members
-        member_def(lost_event, id, T_ULONGLONG, "event id"),
-        member_def(lost_event, lost, T_ULONGLONG, "number of lost events"),
+        member_def(perf_record_lost, id, T_ULONGLONG, "event id"),
+        member_def(perf_record_lost, lost, T_ULONGLONG, "number of lost events"),
         { .name = NULL, },
 };
 
@@ -263,8 +263,8 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
         PyObject *ret;
         char *s;
 
-        if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", "
-                         "lost: %#" PRIx64 " }",
+        if (asprintf(&s, "{ type: lost, id: %#" PRI_lx64 ", "
+                         "lost: %#" PRI_lx64 " }",
                      pevent->event.lost.id, pevent->event.lost.lost) < 0) {
                 ret = PyErr_NoMemory();
         } else {
@@ -288,8 +288,8 @@ static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object.");
 
 static PyMemberDef pyrf_read_event__members[] = {
         sample_members
-        member_def(read_event, pid, T_UINT, "event pid"),
-        member_def(read_event, tid, T_UINT, "event tid"),
+        member_def(perf_record_read, pid, T_UINT, "event pid"),
+        member_def(perf_record_read, tid, T_UINT, "event tid"),
         { .name = NULL, },
 };
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 51bbd0714e6d..574507d46c98 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -9,6 +9,7 @@
 #include <perf/cpumap.h>
 #include "util.h"
 #include "cloexec.h"
+#include "record.h"
 
 typedef void (*setup_probe_fn_t)(struct evsel *evsel);
 
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
new file mode 100644
index 000000000000..00275afc524d
--- /dev/null
+++ b/tools/perf/util/record.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_RECORD_H
+#define _PERF_RECORD_H
+
+#include <time.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include "util/target.h"
+
+struct option;
+
+struct record_opts {
+        struct target target;
+        bool          group;
+        bool          inherit_stat;
+        bool          no_buffering;
+        bool          no_inherit;
+        bool          no_inherit_set;
+        bool          no_samples;
+        bool          raw_samples;
+        bool          sample_address;
+        bool          sample_phys_addr;
+        bool          sample_weight;
+        bool          sample_time;
+        bool          sample_time_set;
+        bool          sample_cpu;
+        bool          period;
+        bool          period_set;
+        bool          running_time;
+        bool          full_auxtrace;
+        bool          auxtrace_snapshot_mode;
+        bool          auxtrace_snapshot_on_exit;
+        bool          record_namespaces;
+        bool          record_switch_events;
+        bool          all_kernel;
+        bool          all_user;
+        bool          kernel_callchains;
+        bool          user_callchains;
+        bool          tail_synthesize;
+        bool          overwrite;
+        bool          ignore_missing_thread;
+        bool          strict_freq;
+        bool          sample_id;
+        bool          no_bpf_event;
+        unsigned int  freq;
+        unsigned int  mmap_pages;
+        unsigned int  auxtrace_mmap_pages;
+        unsigned int  user_freq;
+        u64           branch_stack;
+        u64           sample_intr_regs;
+        u64           sample_user_regs;
+        u64           default_interval;
+        u64           user_interval;
+        size_t        auxtrace_snapshot_size;
+        const char    *auxtrace_snapshot_opts;
+        bool          sample_transaction;
+        unsigned      initial_delay;
+        bool          use_clockid;
+        clockid_t     clockid;
+        u64           clockid_res_ns;
+        int           nr_cblocks;
+        int           affinity;
+        int           mmap_flush;
+        unsigned int  comp_level;
+};
+
+extern const char * const *record_usage;
+extern struct option *record_options;
+
+int record__parse_freq(const struct option *opt, const char *str, int unset);
+
+#endif // _PERF_RECORD_H
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 82e0438a9160..5786e9c807c5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -473,8 +473,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->context_switch = perf_event__process_switch;
         if (tool->ksymbol == NULL)
                 tool->ksymbol = perf_event__process_ksymbol;
-        if (tool->bpf_event == NULL)
-                tool->bpf_event = perf_event__process_bpf_event;
+        if (tool->bpf == NULL)
+                tool->bpf = perf_event__process_bpf;
         if (tool->read == NULL)
                 tool->read = process_event_sample_stub;
         if (tool->throttle == NULL)
@@ -1254,13 +1254,13 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 
 static void dump_read(struct evsel *evsel, union perf_event *event)
 {
-        struct read_event *read_event = &event->read;
+        struct perf_record_read *read_event = &event->read;
         u64 read_format;
 
         if (!dump_trace)
                 return;
 
-        printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+        printf(": %d %d %s %" PRI_lu64 "\n", event->read.pid, event->read.tid,
                perf_evsel__name(evsel),
                event->read.value);
 
@@ -1270,13 +1270,13 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
         read_format = evsel->core.attr.read_format;
 
         if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-                printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled);
+                printf("... time enabled : %" PRI_lu64 "\n", read_event->time_enabled);
 
         if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-                printf("... time running : %" PRIu64 "\n", read_event->time_running);
+                printf("... time running : %" PRI_lu64 "\n", read_event->time_running);
 
         if (read_format & PERF_FORMAT_ID)
-                printf("... id           : %" PRIu64 "\n", read_event->id);
+                printf("... id           : %" PRI_lu64 "\n", read_event->id);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1452,7 +1452,7 @@ static int machines__deliver_event(struct machines *machines,
         case PERF_RECORD_KSYMBOL:
                 return tool->ksymbol(tool, event, sample, machine);
         case PERF_RECORD_BPF_EVENT:
-                return tool->bpf_event(tool, event, sample, machine);
+                return tool->bpf(tool, event, sample, machine);
         default:
                 ++evlist->stats.nr_unknown_events;
                 return -1;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f9a38a1dd4d1..83eb3fa6f941 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,12 +6,14 @@
 #include <linux/time64.h>
 #include "sort.h"
 #include "hist.h"
+#include "cacheline.h"
 #include "comm.h"
 #include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "srcline.h"
 #include "strlist.h"
 #include "strbuf.h"
 #include <traceevent/event-parse.h>
@@ -668,17 +670,11 @@ sort__time_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__time_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        unsigned long secs;
-        unsigned long long nsecs;
         char he_time[32];
 
-        nsecs = he->time;
-        secs = nsecs / NSEC_PER_SEC;
-        nsecs -= secs * NSEC_PER_SEC;
-
         if (symbol_conf.nanosecs)
-                snprintf(he_time, sizeof he_time, "%5lu.%09llu: ",
-                         secs, nsecs);
+                timestamp__scnprintf_nsec(he->time, he_time,
+                                          sizeof(he_time));
         else
                 timestamp__scnprintf_usec(he->time, he_time,
                                           sizeof(he_time));
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5e34676a98e8..3d7cef73924c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -1,29 +1,18 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SORT_H
 #define __PERF_SORT_H
-#include "../builtin.h"
-
 #include <regex.h>
-
-#include "color.h"
+#include <stdbool.h>
 #include <linux/list.h>
-#include "cache.h"
 #include <linux/rbtree.h>
 #include "map_symbol.h"
 #include "symbol_conf.h"
-#include "string.h"
 #include "callchain.h"
 #include "values.h"
 
-#include "../perf.h"
-#include "debug.h"
-#include "header.h"
-
-#include <subcmd/parse-options.h>
-#include "parse-events.h"
 #include "hist.h"
-#include "srcline.h"
 
+struct option;
 struct thread;
 
 extern regex_t parent_regex;
@@ -204,18 +193,6 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
         return period * 100.0 / total_period;
 }
 
-static inline u64 cl_address(u64 address)
-{
-        /* return the cacheline of the address */
-        return (address & ~(cacheline_size() - 1));
-}
-
-static inline u64 cl_offset(u64 address)
-{
-        /* return the cacheline of the address */
-        return (address & (cacheline_size() - 1));
-}
-
 enum sort_mode {
         SORT_MODE__NORMAL,
         SORT_MODE__BRANCH,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 51d6781aa90d..1461dac2322d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -14,7 +14,6 @@
 #include "string2.h"
 #include <linux/ctype.h>
 #include "cgroup.h"
-#include <math.h>
 #include <api/fs/fs.h>
 
 #define CNTR_NOT_SUPPORTED      "<not supported>"
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 0cbfd1eca1dd..f985336b3a22 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -4,6 +4,7 @@
 #include <math.h>
 #include "counts.h"
 #include "stat.h"
+#include "target.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index bcb376e1b3a7..14fe3e548229 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -5,13 +5,12 @@
 #include <linux/types.h>
 #include <stdio.h>
 #include <sys/types.h>
-#include <sys/time.h>
 #include <sys/resource.h>
-#include <sys/wait.h>
 #include "rblist.h"
-#include "perf.h"
 #include "event.h"
 
+struct timespec;
+
 struct stats {
         double n, mean, M2;
         u64 max, min;
@@ -199,6 +198,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 struct perf_tool;
 union perf_event;
 struct perf_session;
+struct target;
+
 int perf_event__process_stat_event(struct perf_session *session,
                                    union perf_event *event);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index bbf7816cba31..dbcb9cfb0f2f 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -169,7 +169,7 @@ struct namespaces *thread__namespaces(struct thread *thread)
 }
 
 static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
-                                    struct namespaces_event *event)
+                                    struct perf_record_namespaces *event)
 {
         struct namespaces *new, *curr = __thread__namespaces(thread);
 
@@ -193,7 +193,7 @@ static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
 }
 
 int thread__set_namespaces(struct thread *thread, u64 timestamp,
-                           struct namespaces_event *event)
+                           struct perf_record_namespaces *event)
 {
         int ret;
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index bf06113be4f3..51bdb9a7af7f 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -16,7 +16,7 @@
 
 struct addr_location;
 struct map;
-struct namespaces_event;
+struct perf_record_namespaces;
 struct thread_stack;
 struct unwind_libunwind_ops;
 
@@ -74,7 +74,7 @@ static inline void thread__exited(struct thread *thread)
 
 struct namespaces *thread__namespaces(struct thread *thread);
 int thread__set_namespaces(struct thread *thread, u64 timestamp,
-                           struct namespaces_event *event);
+                           struct perf_record_namespaces *event);
 
 int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
                        bool exec);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 7f95dd1d6883..2abbf668b8de 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -56,7 +56,7 @@ struct perf_tool {
                         throttle,
                         unthrottle,
                         ksymbol,
-                        bpf_event;
+                        bpf;
 
         event_attr_op   attr;
         event_attr_op   event_update;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index dc4bb6e52a83..7367433e767a 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -5,6 +5,7 @@
 #include "tool.h"
 #include "evswitch.h"
 #include "annotate.h"
+#include "record.h"
 #include <linux/types.h>
 #include <stddef.h>
 #include <stdbool.h>
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 6fd130a5d8f2..44211e483fbf 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -43,26 +43,6 @@ void perf_set_multithreaded(void)
 
 unsigned int page_size;
 
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
-        if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-                pr_debug("cannot determine cache line size");
-}
-#endif
-
-int cacheline_size(void)
-{
-        static int size;
-
-        if (!size)
-                cache_line_size(&size);
-
-        return size;
-}
-
 int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0dab140c6517..45a5c6f20197 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -34,7 +34,6 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
 size_t hex_width(u64 v);
 
 extern unsigned int page_size;
-int __pure cacheline_size(void);
 
 int sysctl__max_stack(void);