Merge tag 'perf-core-for-mingo-5.4-20190901' 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:

objtool:

  Josh Poimboeuf:

  - Move x86 insn decoder to a common location.

  Arnaldo Carvalho de Melo:

  - Ignore intentional differences for the x86 insn decoder.

build:

  Arnaldo Carvalho de Melo:

  - Ignore intentional differences for the x86 insn decoder.

Intel PT:

  Josh Poimboeuf:

  - Use shared x86 insn decoder.

metric groups:

  Jin Yao:

  - Scale the metric result.

  - Support multiple events.

perf c2c:

  Jiri Olsa:

  - Display proper cpu count in nodes column.

Miscellaneous:

  Kyle Meyer:

  - Replace MAX_NR_CPUS with perf_env::nr_cpus_online, i.e. with
    the number of online CPUs as detected at tool start and/or
    recorded in the perf.data file.

libtraceevent:

  Tzvetomir Stoyanov:

  - Simplify the tep_print_event_* APIs.

  - Remove tep_register_trace_clock().

  - Change users plugin directory.

Cleanups:

  Arnaldo Carvalho de Melo:

  - Continue taming the includes hell: remove needless include directives, fix
    the fallout, rinse, repeat.

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

267 files changed, 1319 insertions, 3578 deletions

diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/arch/x86/include/asm/inat.h
index 877827b7c2c3..877827b7c2c3 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/arch/x86/include/asm/inat.h
diff --git a/tools/objtool/arch/x86/include/asm/inat_types.h b/tools/arch/x86/include/asm/inat_types.h
index b047efa9ddc2..b047efa9ddc2 100644
--- a/tools/objtool/arch/x86/include/asm/inat_types.h
+++ b/tools/arch/x86/include/asm/inat_types.h
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/arch/x86/include/asm/insn.h
index 37a4c390750b..37a4c390750b 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index 6e060907c163..6e060907c163 100644
--- a/tools/objtool/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
diff --git a/tools/objtool/arch/x86/lib/inat.c b/tools/arch/x86/lib/inat.c
index 12539fca75c4..4f5ed49e1b4e 100644
--- a/tools/objtool/arch/x86/lib/inat.c
+++ b/tools/arch/x86/lib/inat.c
@@ -4,7 +4,7 @@
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  */
-#include <asm/insn.h>
+#include "../include/asm/insn.h"
 
 /* Attribute tables are generated from opcode map */
 #include "inat-tables.c"
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/arch/x86/lib/insn.c
index 82783bf43b74..79e048f1d902 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -10,8 +10,8 @@
 #else
 #include <string.h>
 #endif
-#include "inat.h"
-#include "insn.h"
+#include "../include/asm/inat.h"
+#include "../include/asm/insn.h"
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
diff --git a/tools/objtool/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index e0b85930dd77..e0b85930dd77 100644
--- a/tools/objtool/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk
index b02a36b2c14f..b02a36b2c14f 100644
--- a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 8352d53dcb5a..a39cdd0d890d 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -62,15 +62,15 @@ set_plugin_dir := 1
 
 # Set plugin_dir to preffered global plugin location
 # If we install under $HOME directory we go under
-# $(HOME)/.traceevent/plugins
+# $(HOME)/.local/lib/traceevent/plugins
 #
 # We dont set PLUGIN_DIR in case we install under $HOME
 # directory, because by default the code looks under:
-# $(HOME)/.traceevent/plugins by default.
+# $(HOME)/.local/lib/traceevent/plugins by default.
 #
 ifeq ($(plugin_dir),)
 ifeq ($(prefix),$(HOME))
-override plugin_dir = $(HOME)/.traceevent/plugins
+override plugin_dir = $(HOME)/.local/lib/traceevent/plugins
 set_plugin_dir := 0
 else
 override plugin_dir = $(libdir)/traceevent/plugins
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index 988587840c80..4faf52a65791 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -303,33 +303,6 @@ void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
 }
 
 /**
- * tep_is_latency_format - get if the latency output format is configured
- * @tep: a handle to the tep_handle
- *
- * This returns true if the latency output format is configured
- * If @tep is NULL, false is returned.
- */
-bool tep_is_latency_format(struct tep_handle *tep)
-{
-	if (tep)
-		return (tep->latency_format);
-	return false;
-}
-
-/**
- * tep_set_latency_format - set the latency output format
- * @tep: a handle to the tep_handle
- * @lat: non zero for latency output format
- *
- * This sets the latency output format
-  */
-void tep_set_latency_format(struct tep_handle *tep, int lat)
-{
-	if (tep)
-		tep->latency_format = lat;
-}
-
-/**
  * tep_is_old_format - get if an old kernel is used
  * @tep: a handle to the tep_handle
  *
@@ -345,19 +318,6 @@ bool tep_is_old_format(struct tep_handle *tep)
 }
 
 /**
- * tep_set_print_raw - set a flag to force print in raw format
- * @tep: a handle to the tep_handle
- * @print_raw: the new value of the print_raw flag
- *
- * This sets a flag to force print in raw format
- */
-void tep_set_print_raw(struct tep_handle *tep, int print_raw)
-{
-	if (tep)
-		tep->print_raw = print_raw;
-}
-
-/**
  * tep_set_test_filters - set a flag to test a filter string
  * @tep: a handle to the tep_handle
  * @test_filters: the new value of the test_filters flag
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 09aa142f7fdd..cee469803a34 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -28,8 +28,6 @@ struct tep_handle {
 	enum tep_endian file_bigendian;
 	enum tep_endian host_bigendian;
 
-	int latency_format;
-
 	int old_format;
 
 	int cpus;
@@ -70,8 +68,6 @@ struct tep_handle {
 	int ld_offset;
 	int ld_size;
 
-	int print_raw;
-
 	int test_filters;
 
 	int flags;
@@ -85,8 +81,6 @@ struct tep_handle {
 
 	/* cache */
 	struct tep_event *last_event;
-
-	char *trace_clock;
 };
 
 void tep_free_event(struct tep_event *event);
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3e83636076b2..bb22238debfe 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -393,16 +393,6 @@ int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
 	return _tep_register_comm(tep, comm, pid, true);
 }
 
-int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock)
-{
-	tep->trace_clock = strdup(trace_clock);
-	if (!tep->trace_clock) {
-		errno = ENOMEM;
-		return -1;
-	}
-	return 0;
-}
-
 struct func_map {
 	unsigned long long		addr;
 	char				*func;
@@ -5212,24 +5202,20 @@ out_failed:
 	}
 }
 
-/**
- * tep_data_latency_format - parse the data for the latency format
- * @tep: a handle to the trace event parser context
- * @s: the trace_seq to write to
- * @record: the record to read from
- *
+/*
  * This parses out the Latency format (interrupts disabled,
  * need rescheduling, in hard/soft interrupt, preempt count
  * and lock depth) and places it into the trace_seq.
  */
-void tep_data_latency_format(struct tep_handle *tep,
-			     struct trace_seq *s, struct tep_record *record)
+static void data_latency_format(struct tep_handle *tep, struct trace_seq *s,
+				char *format, struct tep_record *record)
 {
 	static int check_lock_depth = 1;
 	static int check_migrate_disable = 1;
 	static int lock_depth_exists;
 	static int migrate_disable_exists;
 	unsigned int lat_flags;
+	struct trace_seq sq;
 	unsigned int pc;
 	int lock_depth = 0;
 	int migrate_disable = 0;
@@ -5237,6 +5223,7 @@ void tep_data_latency_format(struct tep_handle *tep,
 	int softirq;
 	void *data = record->data;
 
+	trace_seq_init(&sq);
 	lat_flags = parse_common_flags(tep, data);
 	pc = parse_common_pc(tep, data);
 	/* lock_depth may not always exist */
@@ -5264,7 +5251,7 @@ void tep_data_latency_format(struct tep_handle *tep,
 	hardirq = lat_flags & TRACE_FLAG_HARDIRQ;
 	softirq = lat_flags & TRACE_FLAG_SOFTIRQ;
 
-	trace_seq_printf(s, "%c%c%c",
+	trace_seq_printf(&sq, "%c%c%c",
 	       (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
 	       (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
 	       'X' : '.',
@@ -5274,24 +5261,32 @@ void tep_data_latency_format(struct tep_handle *tep,
 	       hardirq ? 'h' : softirq ? 's' : '.');
 
 	if (pc)
-		trace_seq_printf(s, "%x", pc);
+		trace_seq_printf(&sq, "%x", pc);
 	else
-		trace_seq_putc(s, '.');
+		trace_seq_printf(&sq, ".");
 
 	if (migrate_disable_exists) {
 		if (migrate_disable < 0)
-			trace_seq_putc(s, '.');
+			trace_seq_printf(&sq, ".");
 		else
-			trace_seq_printf(s, "%d", migrate_disable);
+			trace_seq_printf(&sq, "%d", migrate_disable);
 	}
 
 	if (lock_depth_exists) {
 		if (lock_depth < 0)
-			trace_seq_putc(s, '.');
+			trace_seq_printf(&sq, ".");
 		else
-			trace_seq_printf(s, "%d", lock_depth);
+			trace_seq_printf(&sq, "%d", lock_depth);
+	}
+
+	if (sq.state == TRACE_SEQ__MEM_ALLOC_FAILED) {
+		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
+		return;
 	}
 
+	trace_seq_terminate(&sq);
+	trace_seq_puts(s, sq.buffer);
+	trace_seq_destroy(&sq);
 	trace_seq_terminate(s);
 }
 
@@ -5452,21 +5447,16 @@ int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
 	return cmdline->pid;
 }
 
-/**
- * tep_event_info - parse the data into the print format
- * @s: the trace_seq to write to
- * @event: the handle to the event
- * @record: the record to read from
- *
+/*
  * This parses the raw @data using the given @event information and
  * writes the print format into the trace_seq.
  */
-void tep_event_info(struct trace_seq *s, struct tep_event *event,
-		    struct tep_record *record)
+static void print_event_info(struct trace_seq *s, char *format, bool raw,
+			     struct tep_event *event, struct tep_record *record)
 {
 	int print_pretty = 1;
 
-	if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
+	if (raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
 		tep_print_fields(s, record->data, record->size, event);
 	else {
 
@@ -5481,20 +5471,6 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event,
 	trace_seq_terminate(s);
 }
 
-static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
-{
-	if (!trace_clock || !use_trace_clock)
-		return true;
-
-	if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
-	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")
-	    || !strncmp(trace_clock, "mono", 4))
-		return true;
-
-	/* trace_clock is setting in tsc or counter mode */
-	return false;
-}
-
 /**
  * tep_find_event_by_record - return the event from a given record
  * @tep: a handle to the trace event parser context
@@ -5518,129 +5494,195 @@ tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
 	return tep_find_event(tep, type);
 }
 
-/**
- * tep_print_event_task - Write the event task comm, pid and CPU
- * @tep: a handle to the trace event parser context
- * @s: the trace_seq to write to
- * @event: the handle to the record's event
- * @record: The record to get the event from
- *
- * Writes the tasks comm, pid and CPU to @s.
+/*
+ * Writes the timestamp of the record into @s. Time divisor and precision can be
+ * specified as part of printf @format string. Example:
+ *	"%3.1000d" - divide the time by 1000 and print the first 3 digits
+ *	before the dot. Thus, the timestamp "123456000" will be printed as
+ *	"123.456"
  */
-void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record)
+static void print_event_time(struct tep_handle *tep, struct trace_seq *s,
+				 char *format, struct tep_event *event,
+				 struct tep_record *record)
+{
+	unsigned long long time;
+	char *divstr;
+	int prec = 0, pr;
+	int div = 0;
+	int p10 = 1;
+
+	if (isdigit(*(format + 1)))
+		prec = atoi(format + 1);
+	divstr = strchr(format, '.');
+	if (divstr && isdigit(*(divstr + 1)))
+		div = atoi(divstr + 1);
+	time = record->ts;
+	if (div)
+		time /= div;
+	pr = prec;
+	while (pr--)
+		p10 *= 10;
+
+	if (p10 > 1 && p10 < time)
+		trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10);
+	else
+		trace_seq_printf(s, "%12llu\n", time);
+}
+
+struct print_event_type {
+	enum {
+		EVENT_TYPE_INT = 1,
+		EVENT_TYPE_STRING,
+		EVENT_TYPE_UNKNOWN,
+	} type;
+	char format[32];
+};
+
+static void print_string(struct tep_handle *tep, struct trace_seq *s,
+			 struct tep_record *record, struct tep_event *event,
+			 const char *arg, struct print_event_type *type)
 {
-	void *data = record->data;
 	const char *comm;
 	int pid;
 
-	pid = parse_common_pid(tep, data);
-	comm = find_cmdline(tep, pid);
+	if (strncmp(arg, TEP_PRINT_LATENCY, strlen(TEP_PRINT_LATENCY)) == 0) {
+		data_latency_format(tep, s, type->format, record);
+	} else if (strncmp(arg, TEP_PRINT_COMM, strlen(TEP_PRINT_COMM)) == 0) {
+		pid = parse_common_pid(tep, record->data);
+		comm = find_cmdline(tep, pid);
+		trace_seq_printf(s, type->format, comm);
+	} else if (strncmp(arg, TEP_PRINT_INFO_RAW, strlen(TEP_PRINT_INFO_RAW)) == 0) {
+		print_event_info(s, type->format, true, event, record);
+	} else if (strncmp(arg, TEP_PRINT_INFO, strlen(TEP_PRINT_INFO)) == 0) {
+		print_event_info(s, type->format, false, event, record);
+	} else if  (strncmp(arg, TEP_PRINT_NAME, strlen(TEP_PRINT_NAME)) == 0) {
+		trace_seq_printf(s, type->format, event->name);
+	} else {
+		trace_seq_printf(s, "[UNKNOWN TEP TYPE %s]", arg);
+	}
 
-	if (tep->latency_format)
-		trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu);
-	else
-		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
 }
 
-/**
- * tep_print_event_time - Write the event timestamp
- * @tep: a handle to the trace event parser context
- * @s: the trace_seq to write to
- * @event: the handle to the record's event
- * @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @tep->trace_clock
- *
- * Writes the timestamp of the record into @s.
- */
-void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record,
-			  bool use_trace_clock)
+static void print_int(struct tep_handle *tep, struct trace_seq *s,
+		      struct tep_record *record, struct tep_event *event,
+		      int arg, struct print_event_type *type)
 {
-	unsigned long secs;
-	unsigned long usecs;
-	unsigned long nsecs;
-	int p;
-	bool use_usec_format;
+	int param;
 
-	use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock);
-	if (use_usec_format) {
-		secs = record->ts / NSEC_PER_SEC;
-		nsecs = record->ts - secs * NSEC_PER_SEC;
+	switch (arg) {
+	case TEP_PRINT_CPU:
+		param = record->cpu;
+		break;
+	case TEP_PRINT_PID:
+		param = parse_common_pid(tep, record->data);
+		break;
+	case TEP_PRINT_TIME:
+		return print_event_time(tep, s, type->format, event, record);
+	default:
+		return;
 	}
+	trace_seq_printf(s, type->format, param);
+}
 
-	if (tep->latency_format) {
-		tep_data_latency_format(tep, s, record);
-	}
+static int tep_print_event_param_type(char *format,
+				      struct print_event_type *type)
+{
+	char *str = format + 1;
+	int i = 1;
 
-	if (use_usec_format) {
-		if (tep->flags & TEP_NSEC_OUTPUT) {
-			usecs = nsecs;
-			p = 9;
-		} else {
-			usecs = (nsecs + 500) / NSEC_PER_USEC;
-			/* To avoid usecs larger than 1 sec */
-			if (usecs >= USEC_PER_SEC) {
-				usecs -= USEC_PER_SEC;
-				secs++;
-			}
-			p = 6;
+	type->type = EVENT_TYPE_UNKNOWN;
+	while (*str) {
+		switch (*str) {
+		case 'd':
+		case 'u':
+		case 'i':
+		case 'x':
+		case 'X':
+		case 'o':
+			type->type = EVENT_TYPE_INT;
+			break;
+		case 's':
+			type->type = EVENT_TYPE_STRING;
+			break;
 		}
-
-		trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs);
-	} else
-		trace_seq_printf(s, " %12llu:", record->ts);
+		str++;
+		i++;
+		if (type->type != EVENT_TYPE_UNKNOWN)
+			break;
+	}
+	memset(type->format, 0, 32);
+	memcpy(type->format, format, i < 32 ? i : 31);
+	return i;
 }
 
 /**
- * tep_print_event_data - Write the event data section
+ * tep_print_event - Write various event information
  * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
- * @event: the handle to the record's event
  * @record: The record to get the event from
- *
- * Writes the parsing of the record's data to @s.
+ * @format: a printf format string. Supported event fileds:
+ *	TEP_PRINT_PID, "%d" - event PID
+ *	TEP_PRINT_CPU, "%d" - event CPU
+ *	TEP_PRINT_COMM, "%s" - event command string
+ *	TEP_PRINT_NAME, "%s" - event name
+ *	TEP_PRINT_LATENCY, "%s" - event latency
+ *	TEP_PRINT_TIME, %d - event time stamp. A divisor and precision
+ *			can be specified as part of this format string:
+ *			"%precision.divisord". Example:
+ *			"%3.1000d" - divide the time by 1000 and print the first
+ *			3 digits before the dot. Thus, the time stamp
+ *			"123456000" will be printed as "123.456"
+ *	TEP_PRINT_INFO, "%s" - event information. If any width is specified in
+ *			the format string, the event information will be printed
+ *			in raw format.
+ * Writes the specified event information into @s.
  */
-void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record)
-{
-	static const char *spaces = "                    "; /* 20 spaces */
-	int len;
-
-	trace_seq_printf(s, " %s: ", event->name);
-
-	/* Space out the event names evenly. */
-	len = strlen(event->name);
-	if (len < 20)
-		trace_seq_printf(s, "%.*s", 20 - len, spaces);
-
-	tep_event_info(s, event, record);
-}
-
 void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
-		     struct tep_record *record, bool use_trace_clock)
-{
+		     struct tep_record *record, const char *fmt, ...)
+{
+	struct print_event_type type;
+	char *format = strdup(fmt);
+	char *current = format;
+	char *str = format;
+	int offset;
+	va_list args;
 	struct tep_event *event;
 
-	event = tep_find_event_by_record(tep, record);
-	if (!event) {
-		int i;
-		int type = trace_parse_common_type(tep, record->data);
-
-		do_warning("ug! no event found for type %d", type);
-		trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
-		for (i = 0; i < record->size; i++)
-			trace_seq_printf(s, " %02x",
-					 ((unsigned char *)record->data)[i]);
+	if (!format)
 		return;
-	}
 
-	tep_print_event_task(tep, s, event, record);
-	tep_print_event_time(tep, s, event, record, use_trace_clock);
-	tep_print_event_data(tep, s, event, record);
+	event = tep_find_event_by_record(tep, record);
+	va_start(args, fmt);
+	while (*current) {
+		current = strchr(str, '%');
+		if (!current) {
+			trace_seq_puts(s, str);
+			break;
+		}
+		memset(&type, 0, sizeof(type));
+		offset = tep_print_event_param_type(current, &type);
+		*current = '\0';
+		trace_seq_puts(s, str);
+		current += offset;
+		switch (type.type) {
+		case EVENT_TYPE_STRING:
+			print_string(tep, s, record, event,
+				     va_arg(args, char*), &type);
+			break;
+		case EVENT_TYPE_INT:
+			print_int(tep, s, record, event,
+				  va_arg(args, int), &type);
+			break;
+		case EVENT_TYPE_UNKNOWN:
+		default:
+			trace_seq_printf(s, "[UNKNOWN TYPE]");
+			break;
+		}
+		str = current;
+
+	}
+	va_end(args);
+	free(format);
 }
 
 static int events_id_cmp(const void *a, const void *b)
@@ -7005,7 +7047,6 @@ void tep_free(struct tep_handle *tep)
 		free_handler(handle);
 	}
 
-	free(tep->trace_clock);
 	free(tep->events);
 	free(tep->sort_events);
 	free(tep->func_resolver);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 642f68ab5fb2..d438ee44289f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -435,25 +435,24 @@ int tep_set_function_resolver(struct tep_handle *tep,
 void tep_reset_function_resolver(struct tep_handle *tep);
 int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
 int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock);
 int tep_register_function(struct tep_handle *tep, char *name,
 			  unsigned long long addr, char *mod);
 int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr);
 bool tep_is_pid_registered(struct tep_handle *tep, int pid);
 
-void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record);
-void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record,
-			  bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
-			  struct tep_event *event,
-			  struct tep_record *record);
+#define TEP_PRINT_INFO		"INFO"
+#define TEP_PRINT_INFO_RAW	"INFO_RAW"
+#define TEP_PRINT_COMM		"COMM"
+#define TEP_PRINT_LATENCY	"LATENCY"
+#define TEP_PRINT_NAME		"NAME"
+#define TEP_PRINT_PID		1U
+#define TEP_PRINT_TIME		2U
+#define TEP_PRINT_CPU		3U
+
 void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
-		     struct tep_record *record, bool use_trace_clock);
+		     struct tep_record *record, const char *fmt, ...)
+	__attribute__ ((format (printf, 4, 5)));
 
 int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
 			  int long_size);
@@ -525,8 +524,6 @@ tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name
 struct tep_event *
 tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
 
-void tep_data_latency_format(struct tep_handle *tep,
-			     struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
 int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
@@ -541,8 +538,6 @@ void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
 void tep_print_fields(struct trace_seq *s, void *data,
 		      int size __maybe_unused, struct tep_event *event);
-void tep_event_info(struct trace_seq *s, struct tep_event *event,
-		    struct tep_record *record);
 int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
 		 char *buf, size_t buflen);
 
@@ -566,12 +561,9 @@ bool tep_is_file_bigendian(struct tep_handle *tep);
 void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
 bool tep_is_local_bigendian(struct tep_handle *tep);
 void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
-bool tep_is_latency_format(struct tep_handle *tep);
-void tep_set_latency_format(struct tep_handle *tep, int lat);
 int tep_get_header_page_size(struct tep_handle *tep);
 int tep_get_header_timestamp_size(struct tep_handle *tep);
 bool tep_is_old_format(struct tep_handle *tep);
-void tep_set_print_raw(struct tep_handle *tep, int print_raw);
 void tep_set_test_filters(struct tep_handle *tep, int test_filters);
 
 struct tep_handle *tep_alloc(void);
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 8ca28de9337a..e1f7ddd5a6cf 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -18,7 +18,7 @@
 #include "event-utils.h"
 #include "trace-seq.h"
 
-#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+#define LOCAL_PLUGIN_DIR ".local/lib/traceevent/plugins/"
 
 static struct registered_plugin_options {
 	struct registered_plugin_options	*next;
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 88158239622b..8c9b9adc67ef 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -33,7 +33,7 @@ all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
+	    -I$(srctree)/tools/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
 CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
 LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
@@ -60,7 +60,7 @@ $(LIBSUBCMD): fixdep FORCE
 clean:
 	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
 	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
+	$(Q)$(RM) $(OUTPUT)arch/x86/inat-tables.c $(OUTPUT)fixdep
 
 FORCE:
 
diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
index b998412c017d..7c5004008e97 100644
--- a/tools/objtool/arch/x86/Build
+++ b/tools/objtool/arch/x86/Build
@@ -1,7 +1,7 @@
 objtool-y += decode.o
 
-inat_tables_script = arch/x86/tools/gen-insn-attr-x86.awk
-inat_tables_maps = arch/x86/lib/x86-opcode-map.txt
+inat_tables_script = ../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../arch/x86/lib/x86-opcode-map.txt
 
 $(OUTPUT)arch/x86/lib/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
 	$(call rule_mkdir)
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0567c47a91b1..a62e032863a8 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -8,8 +8,8 @@
 
 #define unlikely(cond) (cond)
 #include <asm/insn.h>
-#include "lib/inat.c"
-#include "lib/insn.c"
+#include "../../../arch/x86/lib/inat.c"
+#include "../../../arch/x86/lib/insn.c"
 
 #include "../../elf.h"
 #include "../../arch.h"
diff --git a/tools/objtool/arch/x86/include/asm/inat.h b/tools/objtool/arch/x86/include/asm/inat.h
deleted file mode 100644
index 4cf2ad521f65..000000000000
--- a/tools/objtool/arch/x86/include/asm/inat.h
+++ /dev/null
@@ -1,230 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_X86_INAT_H
-#define _ASM_X86_INAT_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- */
-#include <asm/inat_types.h>
-
-/*
- * Internal bits. Don't use bitmasks directly, because these bits are
- * unstable. You should use checking functions.
- */
-
-#define INAT_OPCODE_TABLE_SIZE 256
-#define INAT_GROUP_TABLE_SIZE 8
-
-/* Legacy last prefixes */
-#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
-#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
-#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
-/* Other Legacy prefixes */
-#define INAT_PFX_LOCK	4	/* 0xF0 */
-#define INAT_PFX_CS	5	/* 0x2E */
-#define INAT_PFX_DS	6	/* 0x3E */
-#define INAT_PFX_ES	7	/* 0x26 */
-#define INAT_PFX_FS	8	/* 0x64 */
-#define INAT_PFX_GS	9	/* 0x65 */
-#define INAT_PFX_SS	10	/* 0x36 */
-#define INAT_PFX_ADDRSZ	11	/* 0x67 */
-/* x86-64 REX prefix */
-#define INAT_PFX_REX	12	/* 0x4X */
-/* AVX VEX prefixes */
-#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
-#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
-#define INAT_PFX_EVEX	15	/* EVEX prefix */
-
-#define INAT_LSTPFX_MAX	3
-#define INAT_LGCPFX_MAX	11
-
-/* Immediate size */
-#define INAT_IMM_BYTE		1
-#define INAT_IMM_WORD		2
-#define INAT_IMM_DWORD		3
-#define INAT_IMM_QWORD		4
-#define INAT_IMM_PTR		5
-#define INAT_IMM_VWORD32	6
-#define INAT_IMM_VWORD		7
-
-/* Legacy prefix */
-#define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
-#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
-#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
-/* Escape opcodes */
-#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
-#define INAT_ESC_BITS	2
-#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
-#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
-/* Group opcodes (1-16) */
-#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
-#define INAT_GRP_BITS	5
-#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
-#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
-/* Immediates */
-#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
-#define INAT_IMM_BITS	3
-#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
-/* Flags */
-#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
-#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
-#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
-#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
-#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
-#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
-#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
-#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
-#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
-/* Attribute making macros for attribute tables */
-#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
-#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
-#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
-#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
-
-/* Identifiers for segment registers */
-#define INAT_SEG_REG_IGNORE	0
-#define INAT_SEG_REG_DEFAULT	1
-#define INAT_SEG_REG_CS		2
-#define INAT_SEG_REG_SS		3
-#define INAT_SEG_REG_DS		4
-#define INAT_SEG_REG_ES		5
-#define INAT_SEG_REG_FS		6
-#define INAT_SEG_REG_GS		7
-
-/* Attribute search APIs */
-extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
-extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
-extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     int lpfx_id,
-					     insn_attr_t esc_attr);
-extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    int lpfx_id,
-					    insn_attr_t esc_attr);
-extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
-					  insn_byte_t vex_m,
-					  insn_byte_t vex_pp);
-
-/* Attribute checking functions */
-static inline int inat_is_legacy_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr && attr <= INAT_LGCPFX_MAX;
-}
-
-static inline int inat_is_address_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
-}
-
-static inline int inat_is_operand_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
-}
-
-static inline int inat_is_rex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
-}
-
-static inline int inat_last_prefix_id(insn_attr_t attr)
-{
-	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
-		return 0;
-	else
-		return attr & INAT_PFX_MASK;
-}
-
-static inline int inat_is_vex_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
-	       attr == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_evex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_vex3_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
-}
-
-static inline int inat_is_escape(insn_attr_t attr)
-{
-	return attr & INAT_ESC_MASK;
-}
-
-static inline int inat_escape_id(insn_attr_t attr)
-{
-	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
-}
-
-static inline int inat_is_group(insn_attr_t attr)
-{
-	return attr & INAT_GRP_MASK;
-}
-
-static inline int inat_group_id(insn_attr_t attr)
-{
-	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
-}
-
-static inline int inat_group_common_attribute(insn_attr_t attr)
-{
-	return attr & ~INAT_GRP_MASK;
-}
-
-static inline int inat_has_immediate(insn_attr_t attr)
-{
-	return attr & INAT_IMM_MASK;
-}
-
-static inline int inat_immediate_size(insn_attr_t attr)
-{
-	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
-}
-
-static inline int inat_has_modrm(insn_attr_t attr)
-{
-	return attr & INAT_MODRM;
-}
-
-static inline int inat_is_force64(insn_attr_t attr)
-{
-	return attr & INAT_FORCE64;
-}
-
-static inline int inat_has_second_immediate(insn_attr_t attr)
-{
-	return attr & INAT_SCNDIMM;
-}
-
-static inline int inat_has_moffset(insn_attr_t attr)
-{
-	return attr & INAT_MOFFSET;
-}
-
-static inline int inat_has_variant(insn_attr_t attr)
-{
-	return attr & INAT_VARIANT;
-}
-
-static inline int inat_accept_vex(insn_attr_t attr)
-{
-	return attr & INAT_VEXOK;
-}
-
-static inline int inat_must_vex(insn_attr_t attr)
-{
-	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
-}
-
-static inline int inat_must_evex(insn_attr_t attr)
-{
-	return attr & INAT_EVEXONLY;
-}
-#endif
diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
deleted file mode 100644
index 154f27be8bfc..000000000000
--- a/tools/objtool/arch/x86/include/asm/insn.h
+++ /dev/null
@@ -1,216 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_X86_INSN_H
-#define _ASM_X86_INSN_H
-/*
- * x86 instruction analysis
- *
- * Copyright (C) IBM Corporation, 2009
- */
-
-/* insn_attr_t is defined in inat.h */
-#include <asm/inat.h>
-
-struct insn_field {
-	union {
-		insn_value_t value;
-		insn_byte_t bytes[4];
-	};
-	/* !0 if we've run insn_get_xxx() for this field */
-	unsigned char got;
-	unsigned char nbytes;
-};
-
-struct insn {
-	struct insn_field prefixes;	/*
-					 * Prefixes
-					 * prefixes.bytes[3]: last prefix
-					 */
-	struct insn_field rex_prefix;	/* REX prefix */
-	struct insn_field vex_prefix;	/* VEX prefix */
-	struct insn_field opcode;	/*
-					 * opcode.bytes[0]: opcode1
-					 * opcode.bytes[1]: opcode2
-					 * opcode.bytes[2]: opcode3
-					 */
-	struct insn_field modrm;
-	struct insn_field sib;
-	struct insn_field displacement;
-	union {
-		struct insn_field immediate;
-		struct insn_field moffset1;	/* for 64bit MOV */
-		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
-	};
-	union {
-		struct insn_field moffset2;	/* for 64bit MOV */
-		struct insn_field immediate2;	/* for 64bit imm or seg16 */
-	};
-
-	insn_attr_t attr;
-	unsigned char opnd_bytes;
-	unsigned char addr_bytes;
-	unsigned char length;
-	unsigned char x86_64;
-
-	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
-	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
-	const insn_byte_t *next_byte;
-};
-
-#define MAX_INSN_SIZE	15
-
-#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
-#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
-#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
-
-#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
-#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
-#define X86_SIB_BASE(sib) ((sib) & 0x07)
-
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
-
-/* VEX bit flags  */
-#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
-#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
-#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
-#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
-#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
-/* VEX bit fields */
-#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
-#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
-#define X86_VEX2_M	1			/* VEX2.M always 1 */
-#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
-
-extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
-
-/* Attribute will be determined after getting ModRM (for opcode groups) */
-static inline void insn_get_attribute(struct insn *insn)
-{
-	insn_get_modrm(insn);
-}
-
-/* Instruction uses RIP-relative addressing */
-extern int insn_rip_relative(struct insn *insn);
-
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
-				    const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
-static inline int insn_is_avx(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.value != 0);
-}
-
-static inline int insn_is_evex(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.nbytes == 4);
-}
-
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
-	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
-		insn->displacement.got && insn->immediate.got;
-}
-
-static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX2_M;
-	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
-		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
-	else					/* EVEX */
-		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
-}
-
-static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX_P(insn->vex_prefix.bytes[1]);
-	else
-		return X86_VEX_P(insn->vex_prefix.bytes[2]);
-}
-
-/* Get the last prefix id from last prefix or VEX prefix */
-static inline int insn_last_prefix_id(struct insn *insn)
-{
-	if (insn_is_avx(insn))
-		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
-
-	if (insn->prefixes.bytes[3])
-		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
-
-	return 0;
-}
-
-/* Offset of each field from kaddr */
-static inline int insn_offset_rex_prefix(struct insn *insn)
-{
-	return insn->prefixes.nbytes;
-}
-static inline int insn_offset_vex_prefix(struct insn *insn)
-{
-	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
-}
-static inline int insn_offset_opcode(struct insn *insn)
-{
-	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
-}
-static inline int insn_offset_modrm(struct insn *insn)
-{
-	return insn_offset_opcode(insn) + insn->opcode.nbytes;
-}
-static inline int insn_offset_sib(struct insn *insn)
-{
-	return insn_offset_modrm(insn) + insn->modrm.nbytes;
-}
-static inline int insn_offset_displacement(struct insn *insn)
-{
-	return insn_offset_sib(insn) + insn->sib.nbytes;
-}
-static inline int insn_offset_immediate(struct insn *insn)
-{
-	return insn_offset_displacement(insn) + insn->displacement.nbytes;
-}
-
-#define POP_SS_OPCODE 0x1f
-#define MOV_SREG_OPCODE 0x8e
-
-/*
- * Intel SDM Vol.3A 6.8.3 states;
- * "Any single-step trap that would be delivered following the MOV to SS
- * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
- * suppressed."
- * This function returns true if @insn is MOV SS or POP SS. On these
- * instructions, single stepping is suppressed.
- */
-static inline int insn_masking_exception(struct insn *insn)
-{
-	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
-		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
-		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
-}
-
-#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/arch/x86/lib/insn.c b/tools/objtool/arch/x86/lib/insn.c
deleted file mode 100644
index 0b5862ba6a75..000000000000
--- a/tools/objtool/arch/x86/lib/insn.c
+++ /dev/null
@@ -1,593 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * x86 instruction analysis
- *
- * Copyright (C) IBM Corporation, 2002, 2004, 2009
- */
-
-#ifdef __KERNEL__
-#include <linux/string.h>
-#else
-#include <string.h>
-#endif
-#include <asm/inat.h>
-#include <asm/insn.h>
-
-/* Verify next sizeof(t) bytes can be on the same instruction */
-#define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
-
-#define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
-
-#define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); r; })
-
-#define get_next(t, insn)	\
-	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
-
-#define peek_nbyte_next(t, insn, n)	\
-	({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
-
-#define peek_next(t, insn)	peek_nbyte_next(t, insn, 0)
-
-/**
- * insn_init() - initialize struct insn
- * @insn:	&struct insn to be initialized
- * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
- * @x86_64:	!0 for 64-bit kernel or 64-bit app
- */
-void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
-{
-	/*
-	 * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
-	 * even if the input buffer is long enough to hold them.
-	 */
-	if (buf_len > MAX_INSN_SIZE)
-		buf_len = MAX_INSN_SIZE;
-
-	memset(insn, 0, sizeof(*insn));
-	insn->kaddr = kaddr;
-	insn->end_kaddr = kaddr + buf_len;
-	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
-	insn->opnd_bytes = 4;
-	if (x86_64)
-		insn->addr_bytes = 8;
-	else
-		insn->addr_bytes = 4;
-}
-
-/**
- * insn_get_prefixes - scan x86 instruction prefix bytes
- * @insn:	&struct insn containing instruction
- *
- * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
- * to point to the (first) opcode.  No effect if @insn->prefixes.got
- * is already set.
- */
-void insn_get_prefixes(struct insn *insn)
-{
-	struct insn_field *prefixes = &insn->prefixes;
-	insn_attr_t attr;
-	insn_byte_t b, lb;
-	int i, nb;
-
-	if (prefixes->got)
-		return;
-
-	nb = 0;
-	lb = 0;
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	while (inat_is_legacy_prefix(attr)) {
-		/* Skip if same prefix */
-		for (i = 0; i < nb; i++)
-			if (prefixes->bytes[i] == b)
-				goto found;
-		if (nb == 4)
-			/* Invalid instruction */
-			break;
-		prefixes->bytes[nb++] = b;
-		if (inat_is_address_size_prefix(attr)) {
-			/* address size switches 2/4 or 4/8 */
-			if (insn->x86_64)
-				insn->addr_bytes ^= 12;
-			else
-				insn->addr_bytes ^= 6;
-		} else if (inat_is_operand_size_prefix(attr)) {
-			/* oprand size switches 2/4 */
-			insn->opnd_bytes ^= 6;
-		}
-found:
-		prefixes->nbytes++;
-		insn->next_byte++;
-		lb = b;
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-	}
-	/* Set the last prefix */
-	if (lb && lb != insn->prefixes.bytes[3]) {
-		if (unlikely(insn->prefixes.bytes[3])) {
-			/* Swap the last prefix */
-			b = insn->prefixes.bytes[3];
-			for (i = 0; i < nb; i++)
-				if (prefixes->bytes[i] == lb)
-					prefixes->bytes[i] = b;
-		}
-		insn->prefixes.bytes[3] = lb;
-	}
-
-	/* Decode REX prefix */
-	if (insn->x86_64) {
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-		if (inat_is_rex_prefix(attr)) {
-			insn->rex_prefix.value = b;
-			insn->rex_prefix.nbytes = 1;
-			insn->next_byte++;
-			if (X86_REX_W(b))
-				/* REX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		}
-	}
-	insn->rex_prefix.got = 1;
-
-	/* Decode VEX prefix */
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	if (inat_is_vex_prefix(attr)) {
-		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
-		if (!insn->x86_64) {
-			/*
-			 * In 32-bits mode, if the [7:6] bits (mod bits of
-			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES or BOUND.
-			 */
-			if (X86_MODRM_MOD(b2) != 3)
-				goto vex_end;
-		}
-		insn->vex_prefix.bytes[0] = b;
-		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_evex_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
-			insn->vex_prefix.bytes[3] = b2;
-			insn->vex_prefix.nbytes = 4;
-			insn->next_byte += 4;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else if (inat_is_vex3_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			insn->vex_prefix.nbytes = 3;
-			insn->next_byte += 3;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else {
-			/*
-			 * For VEX2, fake VEX3-like byte#2.
-			 * Makes it easier to decode vex.W, vex.vvvv,
-			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
-			 */
-			insn->vex_prefix.bytes[2] = b2 & 0x7f;
-			insn->vex_prefix.nbytes = 2;
-			insn->next_byte += 2;
-		}
-	}
-vex_end:
-	insn->vex_prefix.got = 1;
-
-	prefixes->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_opcode - collect opcode(s)
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->opcode, updates @insn->next_byte to point past the
- * opcode byte(s), and set @insn->attr (except for groups).
- * If necessary, first collects any preceding (prefix) bytes.
- * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
- * is already 1.
- */
-void insn_get_opcode(struct insn *insn)
-{
-	struct insn_field *opcode = &insn->opcode;
-	insn_byte_t op;
-	int pfx_id;
-	if (opcode->got)
-		return;
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-
-	/* Get first opcode */
-	op = get_next(insn_byte_t, insn);
-	opcode->bytes[0] = op;
-	opcode->nbytes = 1;
-
-	/* Check if there is VEX prefix or not */
-	if (insn_is_avx(insn)) {
-		insn_byte_t m, p;
-		m = insn_vex_m_bits(insn);
-		p = insn_vex_p_bits(insn);
-		insn->attr = inat_get_avx_attribute(op, m, p);
-		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
-		    (!inat_accept_vex(insn->attr) &&
-		     !inat_is_group(insn->attr)))
-			insn->attr = 0;	/* This instruction is bad */
-		goto end;	/* VEX has only 1 byte for opcode */
-	}
-
-	insn->attr = inat_get_opcode_attribute(op);
-	while (inat_is_escape(insn->attr)) {
-		/* Get escaped opcode */
-		op = get_next(insn_byte_t, insn);
-		opcode->bytes[opcode->nbytes++] = op;
-		pfx_id = insn_last_prefix_id(insn);
-		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
-	}
-	if (inat_must_vex(insn->attr))
-		insn->attr = 0;	/* This instruction is bad */
-end:
-	opcode->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_modrm - collect ModRM byte, if any
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->modrm and updates @insn->next_byte to point past the
- * ModRM byte, if any.  If necessary, first collects the preceding bytes
- * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
- */
-void insn_get_modrm(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-	insn_byte_t pfx_id, mod;
-	if (modrm->got)
-		return;
-	if (!insn->opcode.got)
-		insn_get_opcode(insn);
-
-	if (inat_has_modrm(insn->attr)) {
-		mod = get_next(insn_byte_t, insn);
-		modrm->value = mod;
-		modrm->nbytes = 1;
-		if (inat_is_group(insn->attr)) {
-			pfx_id = insn_last_prefix_id(insn);
-			insn->attr = inat_get_group_attribute(mod, pfx_id,
-							      insn->attr);
-			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
-				insn->attr = 0;	/* This is bad */
-		}
-	}
-
-	if (insn->x86_64 && inat_is_force64(insn->attr))
-		insn->opnd_bytes = 8;
-	modrm->got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.  No effect if @insn->x86_64 is 0.
- */
-int insn_rip_relative(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-
-	if (!insn->x86_64)
-		return 0;
-	if (!modrm->got)
-		insn_get_modrm(insn);
-	/*
-	 * For rip-relative instructions, the mod field (top 2 bits)
-	 * is zero and the r/m field (bottom 3 bits) is 0x5.
-	 */
-	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
-}
-
-/**
- * insn_get_sib() - Get the SIB byte of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.
- */
-void insn_get_sib(struct insn *insn)
-{
-	insn_byte_t modrm;
-
-	if (insn->sib.got)
-		return;
-	if (!insn->modrm.got)
-		insn_get_modrm(insn);
-	if (insn->modrm.nbytes) {
-		modrm = (insn_byte_t)insn->modrm.value;
-		if (insn->addr_bytes != 2 &&
-		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
-			insn->sib.value = get_next(insn_byte_t, insn);
-			insn->sib.nbytes = 1;
-		}
-	}
-	insn->sib.got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_get_displacement() - Get the displacement of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * SIB byte.
- * Displacement value is sign-expanded.
- */
-void insn_get_displacement(struct insn *insn)
-{
-	insn_byte_t mod, rm, base;
-
-	if (insn->displacement.got)
-		return;
-	if (!insn->sib.got)
-		insn_get_sib(insn);
-	if (insn->modrm.nbytes) {
-		/*
-		 * Interpreting the modrm byte:
-		 * mod = 00 - no displacement fields (exceptions below)
-		 * mod = 01 - 1-byte displacement field
-		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
-		 * 	address size = 2 (0x67 prefix in 32-bit mode)
-		 * mod = 11 - no memory operand
-		 *
-		 * If address size = 2...
-		 * mod = 00, r/m = 110 - displacement field is 2 bytes
-		 *
-		 * If address size != 2...
-		 * mod != 11, r/m = 100 - SIB byte exists
-		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
-		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
-		 * 	field is 4 bytes
-		 */
-		mod = X86_MODRM_MOD(insn->modrm.value);
-		rm = X86_MODRM_RM(insn->modrm.value);
-		base = X86_SIB_BASE(insn->sib.value);
-		if (mod == 3)
-			goto out;
-		if (mod == 1) {
-			insn->displacement.value = get_next(signed char, insn);
-			insn->displacement.nbytes = 1;
-		} else if (insn->addr_bytes == 2) {
-			if ((mod == 0 && rm == 6) || mod == 2) {
-				insn->displacement.value =
-					 get_next(short, insn);
-				insn->displacement.nbytes = 2;
-			}
-		} else {
-			if ((mod == 0 && rm == 5) || mod == 2 ||
-			    (mod == 0 && base == 5)) {
-				insn->displacement.value = get_next(int, insn);
-				insn->displacement.nbytes = 4;
-			}
-		}
-	}
-out:
-	insn->displacement.got = 1;
-
-err_out:
-	return;
-}
-
-/* Decode moffset16/32/64. Return 0 if failed */
-static int __get_moffset(struct insn *insn)
-{
-	switch (insn->addr_bytes) {
-	case 2:
-		insn->moffset1.value = get_next(short, insn);
-		insn->moffset1.nbytes = 2;
-		break;
-	case 4:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		break;
-	case 8:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		insn->moffset2.value = get_next(int, insn);
-		insn->moffset2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->moffset1.got = insn->moffset2.got = 1;
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v32(Iz). Return 0 if failed */
-static int __get_immv32(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case 4:
-	case 8:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v64(Iv/Ov), Return 0 if failed */
-static int __get_immv(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/* Decode ptr16:16/32(Ap) */
-static int __get_immptr(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		/* ptr16:64 is not exist (no segment) */
-		return 0;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate2.value = get_next(unsigned short, insn);
-	insn->immediate2.nbytes = 2;
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/**
- * insn_get_immediate() - Get the immediates of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * displacement bytes.
- * Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
- */
-void insn_get_immediate(struct insn *insn)
-{
-	if (insn->immediate.got)
-		return;
-	if (!insn->displacement.got)
-		insn_get_displacement(insn);
-
-	if (inat_has_moffset(insn->attr)) {
-		if (!__get_moffset(insn))
-			goto err_out;
-		goto done;
-	}
-
-	if (!inat_has_immediate(insn->attr))
-		/* no immediates */
-		goto done;
-
-	switch (inat_immediate_size(insn->attr)) {
-	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(signed char, insn);
-		insn->immediate.nbytes = 1;
-		break;
-	case INAT_IMM_WORD:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case INAT_IMM_DWORD:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	case INAT_IMM_QWORD:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	case INAT_IMM_PTR:
-		if (!__get_immptr(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD32:
-		if (!__get_immv32(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD:
-		if (!__get_immv(insn))
-			goto err_out;
-		break;
-	default:
-		/* Here, insn must have an immediate, but failed */
-		goto err_out;
-	}
-	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(signed char, insn);
-		insn->immediate2.nbytes = 1;
-	}
-done:
-	insn->immediate.got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_length() - Get the length of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * immediates bytes.
- */
-void insn_get_length(struct insn *insn)
-{
-	if (insn->length)
-		return;
-	if (!insn->immediate.got)
-		insn_get_immediate(insn);
-	insn->length = (unsigned char)((unsigned long)insn->next_byte
-				     - (unsigned long)insn->kaddr);
-}
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
index 1470e74e9d66..0a832e265a50 100755
--- a/tools/objtool/sync-check.sh
+++ b/tools/objtool/sync-check.sh
@@ -2,28 +2,50 @@
 # SPDX-License-Identifier: GPL-2.0
 
 FILES='
-arch/x86/lib/insn.c
-arch/x86/lib/inat.c
-arch/x86/lib/x86-opcode-map.txt
-arch/x86/tools/gen-insn-attr-x86.awk
-arch/x86/include/asm/insn.h
-arch/x86/include/asm/inat.h
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
+arch/x86/lib/x86-opcode-map.txt
+arch/x86/tools/gen-insn-attr-x86.awk
 '
 
-check()
-{
-	local file=$1
+check_2 () {
+  file1=$1
+  file2=$2
 
-	diff $file ../../$file > /dev/null ||
-		echo "Warning: synced file at 'tools/objtool/$file' differs from latest kernel version at '$file'"
+  shift
+  shift
+
+  cmd="diff $* $file1 $file2 > /dev/null"
+
+  test -f $file2 && {
+    eval $cmd || {
+      echo "Warning: Kernel ABI header at '$file1' differs from latest version at '$file2'" >&2
+      echo diff -u $file1 $file2
+    }
+  }
+}
+
+check () {
+  file=$1
+
+  shift
+
+  check_2 tools/$file $file $*
 }
 
 if [ ! -d ../../kernel ] || [ ! -d ../../tools ] || [ ! -d ../objtool ]; then
 	exit 0
 fi
 
+cd ../..
+
 for i in $FILES; do
   check $i
 done
+
+check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
+check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
+check arch/x86/lib/inat.c             '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
+check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]"'
+
+cd -
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 3e5135dded16..bf1252dc2cb0 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -34,3 +34,6 @@ arch/*/include/generated/
 trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
+feature/
+fixdep
+libtraceevent-dynamic-list
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index c7d1a69b894f..e1d4b484cc4b 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -3,6 +3,7 @@
 #include <linux/zalloc.h>
 #include <sys/types.h>
 #include <regex.h>
+#include <stdlib.h>
 
 struct arm_annotate {
 	regex_t call_insn,
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 41b78f74599f..0a6e75b8777a 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -9,6 +9,7 @@
 #include <linux/zalloc.h>
 
 #include "../../util/auxtrace.h"
+#include "../../util/debug.h"
 #include "../../util/evlist.h"
 #include "../../util/pmu.h"
 #include "cs-etm.h"
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 9644e2d405f7..c32db09baf0d 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -11,10 +11,12 @@
 #include <linux/coresight-pmu.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
+#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/zalloc.h>
 
 #include "cs-etm.h"
+#include "../../util/debug.h"
 #include "../../util/record.h"
 #include "../../util/auxtrace.h"
 #include "../../util/cpumap.h"
@@ -22,9 +24,9 @@
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
 #include "../../util/pmu.h"
-#include "../../util/thread_map.h"
 #include "../../util/cs-etm.h"
 #include "../../util/util.h"
+#include "../../util/session.h"
 
 #include <errno.h>
 #include <stdlib.h>
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 8f70a1b282df..43aa93ed8414 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -2,6 +2,7 @@
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
+#include <stdlib.h>
 
 struct arm64_annotate {
 	regex_t call_insn,
diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c
index 27fcf24d6850..5df788985130 100644
--- a/tools/perf/arch/arm64/util/sym-handling.c
+++ b/tools/perf/arch/arm64/util/sym-handling.c
@@ -4,11 +4,9 @@
  * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
  */
 
-#include "debug.h"
-#include "symbol.h"
-#include "map.h"
-#include "probe-event.h"
-#include "probe-file.h"
+#include "symbol.h" // for the elf__needs_adjust_symbols() prototype
+#include <stdbool.h>
+#include <gelf.h>
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 1a9e22f78c22..59dd875fd5e4 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
 #include "common.h"
 #include "../util/env.h"
 #include "../util/debug.h"
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index c298a446d1f6..e965ed8bb328 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -2,7 +2,9 @@
 #ifndef ARCH_PERF_COMMON_H
 #define ARCH_PERF_COMMON_H
 
-#include "../util/env.h"
+#include <stdbool.h>
+
+struct perf_env;
 
 int perf_env__lookup_objdump(struct perf_env *env, const char **path);
 bool perf_env__single_address_space(struct perf_env *env);
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
index d08311f04e95..07fb5e049488 100644
--- a/tools/perf/arch/powerpc/util/mem-events.c
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "map_symbol.h"
 #include "mem-events.h"
 
 /* PowerPC does not support 'ldlat' parameter. */
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index f14102b85509..e9c436eeffc9 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -4,7 +4,6 @@
 #include <regex.h>
 #include <linux/zalloc.h>
 
-#include "../../perf.h"
 #include "../../util/perf_regs.h"
 #include "../../util/debug.h"
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index b0a67eaf2ce8..8a4b717e0a53 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -5,6 +5,7 @@
  */
 
 #include "debug.h"
+#include "dso.h"
 #include "symbol.h"
 #include "map.h"
 #include "probe-event.h"
diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c
index 7a1f05ef2fc0..abf2dbc7f829 100644
--- a/tools/perf/arch/powerpc/util/unwind-libdw.c
+++ b/tools/perf/arch/powerpc/util/unwind-libdw.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
+#include <linux/kernel.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
 #include "../../util/event.h"
diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c
index f53e4406709f..adcacf1b6609 100644
--- a/tools/perf/arch/x86/tests/bp-modify.c
+++ b/tools/perf/arch/x86/tests/bp-modify.c
@@ -7,6 +7,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <sys/ptrace.h>
 #include <asm/ptrace.h>
 #include <errno.h>
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index c3e5f4ab0d3e..745f29adb14b 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
+#include "../../../../arch/x86/include/asm/insn.h"
+#include <string.h>
 
 #include "debug.h"
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-#include "intel-pt-decoder/insn.h"
 #include "intel-pt-decoder/intel-pt-insn-decoder.h"
 
 struct test_data {
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 2a105e3b2ad1..3b5cc3373821 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "tests/tests.h"
-#include "perf.h"
 #include "cloexec.h"
 #include "debug.h"
 #include "evlist.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 02776109ba46..eb3635941c2b 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 <limits.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <unistd.h>
@@ -9,6 +10,7 @@
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
 
+#include "debug.h"
 #include "parse-events.h"
 #include "evlist.h"
 #include "evsel.h"
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 7a11f02d6c6c..6e67cee792b1 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -6,11 +6,13 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/wait.h>
+#include <linux/string.h>
 #include <linux/types.h>
-#include "perf.h"
+#include "perf-sys.h"
 #include "debug.h"
 #include "tests/tests.h"
 #include "cloexec.h"
+#include "event.h"
 #include "util.h"
 #include "arch-tests.h"
 
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 4237bb2e7fa2..9876c7a7ed7c 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
+#include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
-#include "util/intel-pt-decoder/insn.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 0d7b77ff0ae6..c218b83e063b 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -2,11 +2,13 @@
 #include <errno.h>
 #include <string.h>
 #include <regex.h>
+#include <linux/kernel.h>
 #include <linux/zalloc.h>
 
-#include "../../perf.h"
+#include "../../perf-sys.h"
 #include "../../util/perf_regs.h"
 #include "../../util/debug.h"
+#include "../../util/event.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 81720e27f8a3..c5197a15119b 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -5,8 +5,8 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 
-#include "../../../perf.h"
 #include <linux/types.h>
+#include <asm/barrier.h>
 #include "../../../util/debug.h"
 #include "../../../util/tsc.h"
 
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 84658d45f349..d1caa4a0a12a 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -14,6 +14,7 @@
 #include <inttypes.h>
 #include <signal.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <sys/time.h>
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index c27a65639cfb..f6b4472847d2 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -63,6 +63,7 @@
 /* For the CLR_() macros */
 #include <string.h>
 #include <pthread.h>
+#include <unistd.h>
 
 #include <errno.h>
 #include <inttypes.h>
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 64dc994c72ea..9235b76501be 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -8,7 +8,7 @@
  */
 
 #include "debug.h"
-#include "../perf.h"
+#include "../perf-sys.h"
 #include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "../util/cloexec.h"
@@ -20,6 +20,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
 #include <sys/time.h>
 #include <errno.h>
 #include <linux/time64.h>
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 513cb2f2fa32..62b8ef4bcb1f 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 "../perf.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 f9d7641ae833..c63eb9a46346 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -10,7 +10,6 @@
  *
  */
 
-#include "../perf.h"
 #include "../util/util.h"
 #include <subcmd/parse-options.h>
 #include "../builtin.h"
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 0591be008f2a..35b07f197d48 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -9,7 +9,6 @@
  *  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 "../perf.h"
 #include "../util/util.h"
 #include <subcmd/parse-options.h>
 #include "../builtin.h"
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 9bb637165bf9..4e4d2e76232e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -24,15 +24,17 @@
 #include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
-#include "util/thread.h"
 #include "util/sort.h"
 #include "util/hist.h"
+#include "util/dso.h"
 #include "util/map.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/data.h"
 #include "arch/common.h"
 #include "util/block-range.h"
+#include "util/map_symbol.h"
+#include "util/branch.h"
 
 #include <dlfcn.h>
 #include <errno.h>
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b8e7c38ef221..c06fe21c8613 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -16,7 +16,6 @@
  *  futex ... Futex performance
  *  epoll ... Event poll performance
  */
-#include "perf.h"
 #include <subcmd/parse-options.h>
 #include "builtin.h"
 #include "bench/bench.h"
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 7dde3ef0398f..1a69eb565dc0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -14,19 +14,20 @@
 #include <errno.h>
 #include <unistd.h>
 #include "builtin.h"
-#include "perf.h"
 #include "namespaces.h"
-#include "util/cache.h"
 #include "util/debug.h"
 #include "util/header.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/strlist.h"
 #include "util/build-id.h"
 #include "util/session.h"
+#include "util/dso.h"
 #include "util/symbol.h"
 #include "util/time-utils.h"
 #include "util/util.h"
 #include "util/probe-file.h"
+#include <linux/string.h>
 
 static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 {
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index f403e19488b5..5a0d8b378cb5 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,4 +1,3 @@
-// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-buildid-list.c
  *
@@ -11,8 +10,9 @@
 #include "builtin.h"
 #include "perf.h"
 #include "util/build-id.h"
-#include "util/cache.h"
 #include "util/debug.h"
+#include "util/dso.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/symbol.h"
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 73782d99ee5a..b09b12e0976b 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -20,7 +20,9 @@
 #include <sys/param.h>
 #include "debug.h"
 #include "builtin.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
+#include "map_symbol.h"
 #include "mem-events.h"
 #include "session.h"
 #include "hist.h"
@@ -35,6 +37,9 @@
 #include "thread.h"
 #include "mem2node.h"
 #include "symbol.h"
+#include "ui/ui.h"
+#include "ui/progress.h"
+#include "../perf.h"
 
 struct c2c_hists {
 	struct hists		hists;
@@ -1107,7 +1112,7 @@ node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 			break;
 		case 1:
 		{
-			int num = bitmap_weight(c2c_he->cpuset, c2c.cpus_cnt);
+			int num = bitmap_weight(set, c2c.cpus_cnt);
 			struct c2c_stats *stats = &c2c_he->node_stats[node];
 
 			ret = scnprintf(hpp->buf, hpp->size, "%2d{%2d ", node, num);
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 6c1284c87aaa..42d8157e047a 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -7,14 +7,13 @@
  */
 #include "builtin.h"
 
-#include "perf.h"
-
 #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>
+#include <stdio.h>
 #include <stdlib.h>
 
 static bool use_system_config, use_user_config;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index dde25d4ca56d..ca2fb44874e4 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
+#include <stdio.h>
+#include <string.h>
 #include "builtin.h"
 #include "perf.h"
 #include "debug.h"
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 51c37e53b3d8..827e4800d862 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -6,6 +6,7 @@
  * DSOs and symbol information, sort them and produce a diff.
  */
 #include "builtin.h"
+#include "perf.h"
 
 #include "util/debug.h"
 #include "util/event.h"
@@ -23,6 +24,7 @@
 #include "util/annotate.h"
 #include "util/map.h"
 #include <linux/zalloc.h>
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 
 #include <errno.h>
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 565db782c1b9..d5adc417a4ca 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -6,16 +6,18 @@
  */
 
 #include "builtin.h"
-#include "perf.h"
 
 #include <errno.h>
 #include <unistd.h>
 #include <signal.h>
+#include <stdlib.h>
 #include <fcntl.h>
 #include <poll.h>
 #include <linux/capability.h>
+#include <linux/string.h>
 
 #include "debug.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include <api/fs/tracing_path.h>
 #include "evlist.h"
@@ -25,7 +27,6 @@
 #include "util/cap.h"
 #include "util/config.h"
 
-
 #define DEFAULT_TRACER  "function_graph"
 
 struct perf_ftrace {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index a83af92fb0d1..3976aebe3677 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -4,8 +4,9 @@
  *
  * Builtin help command
  */
-#include "perf.h"
+#include "util/cache.h"
 #include "util/config.h"
+#include "util/strbuf.h"
 #include "builtin.h"
 #include <subcmd/exec-cmd.h>
 #include "common-cmds.h"
@@ -14,10 +15,12 @@
 #include <subcmd/help.h>
 #include "util/debug.h"
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 040142581d20..c14f40b858bc 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -8,8 +8,8 @@
  */
 #include "builtin.h"
 
-#include "perf.h"
 #include "util/color.h"
+#include "util/dso.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/map.h"
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index c1a44671b0b5..c08ee81529e8 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <subcmd/parse-options.h>
 #include "debug.h"
+#include "dso.h"
 #include "machine.h"
 #include "map.h"
 #include "symbol.h"
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 46f828936120..b5682beaad72 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -2,6 +2,7 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/dso.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/config.h"
@@ -14,6 +15,7 @@
 #include "util/callchain.h"
 #include "util/time-utils.h"
 
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/data.h"
@@ -749,7 +751,8 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample,
 	}
 
 	trace_seq_init(&seq);
-	tep_event_info(&seq, evsel->tp_format, &record);
+	tep_print_event(evsel->tp_format->tep,
+			&seq, &record, "%s", TEP_PRINT_INFO);
 
 	str = strtok_r(seq.buffer, " ", &pos);
 	while (str) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 69d16ac852c3..0a4fcbe32bf6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -2,15 +2,16 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/build-id.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
 #include "util/term.h"
-#include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
 #include "util/intlist.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/debug.h"
@@ -19,6 +20,7 @@
 #include "util/top.h"
 #include "util/data.h"
 #include "util/ordered-events.h"
+#include "ui/ui.h"
 
 #include <sys/prctl.h>
 #ifdef HAVE_TIMERFD_SUPPORT
@@ -30,6 +32,7 @@
 #include <fcntl.h>
 
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
 #include <errno.h>
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index e0312a1c4792..e290f6b348d8 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -10,14 +10,13 @@
  */
 #include "builtin.h"
 
-#include "perf.h"
-
 #include "util/parse-events.h"
-#include "util/cache.h"
 #include "util/pmu.h"
 #include "util/debug.h"
 #include "util/metricgroup.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
+#include <stdio.h>
 
 static bool desc_flag = true;
 static bool details_flag;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 38500bff4423..4c2b7f437cdf 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -4,13 +4,13 @@
 #include "builtin.h"
 #include "perf.h"
 
-#include "util/evlist.h"
+#include "util/evlist.h" // for struct evsel_str_handler
 #include "util/evsel.h"
-#include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 9e60eda9297d..27d2bde943a8 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -11,8 +11,10 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/map_symbol.h"
 #include "util/mem-events.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include "util/map.h"
 #include "util/symbol.h"
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 3d0ffd41fb55..26bc5923e6b5 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -16,17 +16,18 @@
 #include <stdlib.h>
 #include <string.h>
 
-#include "perf.h"
 #include "builtin.h"
 #include "namespaces.h"
+#include "util/build-id.h"
 #include "util/strlist.h"
 #include "util/strfilter.h"
-#include "util/symbol.h"
+#include "util/symbol_conf.h"
 #include "util/debug.h"
 #include <subcmd/parse-options.h>
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 #include "util/probe-file.h"
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bd2a0cc6eb52..1447004eee8a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -42,6 +42,7 @@
 #include "util/units.h"
 #include "util/bpf-event.h"
 #include "asm/bug.h"
+#include "perf.h"
 
 #include <errno.h>
 #include <inttypes.h>
@@ -52,6 +53,7 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
+#include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 33c20e26b290..b18fab94d38d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -12,12 +12,16 @@
 
 #include "util/annotate.h"
 #include "util/color.h"
+#include "util/dso.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/err.h>
 #include <linux/zalloc.h>
 #include "util/map.h"
 #include "util/symbol.h"
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
+#include "util/branch.h"
 #include "util/callchain.h"
 #include "util/values.h"
 
@@ -45,6 +49,8 @@
 #include "util/units.h"
 #include "util/branch.h"
 #include "util/util.h"
+#include "ui/ui.h"
+#include "ui/progress.h"
 
 #include <dlfcn.h>
 #include <errno.h>
@@ -53,6 +59,7 @@
 #include <linux/ctype.h>
 #include <signal.h>
 #include <linux/bitmap.h>
+#include <linux/string.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
 #include <sys/types.h>
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 025151dcb651..ec96d64aec69 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
+#include "perf-sys.h"
 
 #include "util/evlist.h"
-#include "util/cache.h"
 #include "util/evsel.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -18,6 +18,7 @@
 #include "util/callchain.h"
 #include "util/time-utils.h"
 
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 37297b67905d..e079b34201f2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 
-#include "util/cache.h"
 #include "util/counts.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include <subcmd/exec-cmd.h>
 #include "util/header.h"
 #include <subcmd/parse-options.h>
@@ -29,6 +29,7 @@
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
 #include "util/path.h"
+#include "ui/ui.h"
 #include "print_binary.h"
 #include "archinsn.h"
 #include <linux/bitmap.h>
@@ -53,6 +54,7 @@
 #include <perf/evlist.h>
 #include "util/record.h"
 #include "util/util.h"
+#include "perf.h"
 
 #include <linux/ctype.h>
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a7e8c26635db..7e17bf9f700a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -41,6 +41,7 @@
  */
 
 #include "builtin.h"
+#include "perf.h"
 #include "util/cgroup.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
@@ -53,7 +54,6 @@
 #include "util/stat.h"
 #include "util/header.h"
 #include "util/cpumap.h"
-#include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
 #include "util/group.h"
@@ -62,6 +62,7 @@
 #include "util/string2.h"
 #include "util/metricgroup.h"
 #include "util/target.h"
+#include "util/time-utils.h"
 #include "util/top.h"
 #include "asm/bug.h"
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 7d6a6ecf4e02..e0e822695a29 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -10,13 +10,11 @@
 
 #include <errno.h>
 #include <inttypes.h>
-#include <traceevent/event-parse.h>
 
 #include "builtin.h"
 #include "util/color.h"
 #include <linux/list.h>
-#include "util/cache.h"
-#include "util/evlist.h"
+#include "util/evlist.h" // for struct evsel_str_handler
 #include "util/evsel.h"
 #include <linux/kernel.h>
 #include <linux/rbtree.h>
@@ -28,6 +26,7 @@
 
 #include "perf.h"
 #include "util/header.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/event.h"
@@ -1518,10 +1517,7 @@ static int process_header(struct perf_file_section *section __maybe_unused,
 		if (!tchart->topology)
 			break;
 
-		if (svg_build_topology_map(ph->env.sibling_cores,
-					   ph->env.nr_sibling_cores,
-					   ph->env.sibling_threads,
-					   ph->env.nr_sibling_threads))
+		if (svg_build_topology_map(&ph->env))
 			fprintf(stderr, "problem building topology\n");
 		break;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c3f95440e99c..726e3f2dd8c7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -24,6 +24,7 @@
 #include "util/bpf-event.h"
 #include "util/config.h"
 #include "util/color.h"
+#include "util/dso.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/event.h"
@@ -31,13 +32,12 @@
 #include "util/map.h"
 #include "util/session.h"
 #include "util/symbol.h"
-#include "util/thread.h"
-#include "util/thread_map.h"
 #include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
+#include "util/callchain.h"
 #include "util/cpumap.h"
 #include "util/sort.h"
 #include "util/string2.h"
@@ -45,6 +45,7 @@
 #include "util/intlist.h"
 #include "util/parse-branch-options.h"
 #include "arch/common.h"
+#include "ui/ui.h"
 
 #include "util/debug.h"
 #include "util/ordered-events.h"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6d9805a8791b..0f633f0d6be8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -25,10 +25,12 @@
 #include "util/color.h"
 #include "util/config.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include "util/env.h"
 #include "util/event.h"
 #include "util/evlist.h"
 #include "util/evswitch.h"
+#include <subcmd/pager.h>
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
 #include "util/map.h"
@@ -41,6 +43,7 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/tool.h"
 #include "util/util.h"
 #include "trace/beauty/beauty.h"
 #include "trace-event.h"
@@ -51,6 +54,7 @@
 #include "string2.h"
 #include "syscalltbl.h"
 #include "rb_resort.h"
+#include "../perf.h"
 
 #include <errno.h>
 #include <inttypes.h>
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index bf114ca9ca87..05cf2af9e2c2 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -2,8 +2,8 @@
 #include "builtin.h"
 #include "perf.h"
 #include "color.h"
-#include <linux/compiler.h>
 #include <tools/config.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <string.h>
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 5308b3836278..e2e0f06c97d0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-HEADERS='
+FILES='
 include/uapi/linux/const.h
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
@@ -26,7 +26,10 @@ include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
 arch/x86/include/asm/required-features.h
 arch/x86/include/asm/cpufeatures.h
+arch/x86/include/asm/inat_types.h
 arch/x86/include/uapi/asm/prctl.h
+arch/x86/lib/x86-opcode-map.txt
+arch/x86/tools/gen-insn-attr-x86.awk
 arch/arm/include/uapi/asm/perf_regs.h
 arch/arm64/include/uapi/asm/perf_regs.h
 arch/powerpc/include/uapi/asm/perf_regs.h
@@ -98,7 +101,7 @@ test -d ../../include || exit 0
 cd ../..
 
 # simple diff check
-for i in $HEADERS; do
+for i in $FILES; do
   check $i -B
 done
 
@@ -109,6 +112,10 @@ check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
+check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
+check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
+check arch/x86/lib/inat.c	      '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
+check arch/x86/lib/insn.c	      '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]"'
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index 2834753576b2..1f0e6f334237 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -100,6 +100,9 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 		if (prev >= 0) {
 			int new_max = nr_cpus + cpu - prev - 1;
 
+			WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. "
+							  "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);
+
 			if (new_max >= max_entries) {
 				max_entries = new_max + MAX_NR_CPUS / 2;
 				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
@@ -192,6 +195,9 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 			end_cpu = start_cpu;
 		}
 
+		WARN_ONCE(end_cpu >= MAX_NR_CPUS, "Perf can support %d CPUs. "
+						  "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);
+
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 3eb7a39169f6..63e4349a772a 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -5,54 +5,17 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/syscall.h>
-#include <linux/types.h>
 #include <linux/compiler.h>
-#include <linux/perf_event.h>
-#include <asm/barrier.h>
 
-#ifdef __powerpc__
-#define CPUINFO_PROC	{"cpu"}
-#endif
-
-#ifdef __s390__
-#define CPUINFO_PROC	{"vendor_id"}
-#endif
-
-#ifdef __sh__
-#define CPUINFO_PROC	{"cpu type"}
-#endif
+struct perf_event_attr;
 
-#ifdef __hppa__
-#define CPUINFO_PROC	{"cpu"}
-#endif
-
-#ifdef __sparc__
-#define CPUINFO_PROC	{"cpu"}
-#endif
-
-#ifdef __alpha__
-#define CPUINFO_PROC	{"cpu model"}
-#endif
+extern bool test_attr__enabled;
+void test_attr__ready(void);
+void test_attr__init(void);
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+		     int fd, int group_fd, unsigned long flags);
 
-#ifdef __arm__
-#define CPUINFO_PROC	{"model name", "Processor"}
-#endif
-
-#ifdef __mips__
-#define CPUINFO_PROC	{"cpu model"}
-#endif
-
-#ifdef __arc__
-#define CPUINFO_PROC	{"Processor"}
-#endif
-
-#ifdef __xtensa__
-#define CPUINFO_PROC	{"core ID"}
-#endif
-
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC	{ "model name", }
-#endif
+#define HAVE_ATTR_TEST
 
 static inline int
 sys_perf_event_open(struct perf_event_attr *attr,
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 34763a9b873d..1193b923e801 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -1,4 +1,3 @@
-// SPDX-License-Identifier: GPL-2.0
 /*
  * perf.c
  *
@@ -8,7 +7,10 @@
  * perf top, perf record, perf report, etc.) are started.
  */
 #include "builtin.h"
+#include "perf.h"
 
+#include "util/build-id.h"
+#include "util/cache.h"
 #include "util/env.h"
 #include <subcmd/exec-cmd.h>
 #include "util/config.h"
@@ -19,6 +21,8 @@
 #include "util/debug.h"
 #include "util/event.h"
 #include "util/util.h"
+#include "ui/ui.h"
+#include "perf-sys.h"
 #include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 #include <errno.h>
@@ -30,6 +34,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
 const char perf_usage_string[] =
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d9e6b8b957b6..74014033df60 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -2,28 +2,7 @@
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
-#include <time.h>
 #include <stdbool.h>
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <linux/perf_event.h>
-
-extern bool test_attr__enabled;
-void test_attr__ready(void);
-void test_attr__init(void);
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
-		     int fd, int group_fd, unsigned long flags);
-
-#define HAVE_ATTR_TEST
-#include "perf-sys.h"
-
-static inline unsigned long long rdclock(void)
-{
-	struct timespec ts;
-
-	clock_gettime(CLOCK_MONOTONIC, &ts);
-	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
-}
 
 #ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			2048
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index ead521dd8d79..25c47d23a130 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -19,7 +19,6 @@
 #include "EXTERN.h"
 #include "perl.h"
 #include "XSUB.h"
-#include "../../../perf.h"
 #include "../../../util/trace-event.h"
 
 #ifndef PERL_UNUSED_VAR
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 217568bc29ce..0b7096847991 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -6,7 +6,6 @@
  */
 
 #include <Python.h>
-#include "../../../perf.h"
 #include "../../../util/trace-event.h"
 
 #if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index d8426547219b..a9599ab8c471 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -30,8 +30,9 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
-#include "../perf.h"
+#include "../perf-sys.h"
 #include <subcmd/exec-cmd.h>
+#include "event.h"
 #include "tests.h"
 
 #define ENV "PERF_TEST_ATTR"
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index b6f27ef9fb02..a637a4a90760 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -9,7 +9,9 @@
 #include "record.h"
 #include "tests.h"
 #include "debug.h"
+#include "parse-events.h"
 #include <errno.h>
+#include <linux/string.h>
 
 #define NR_ITERS 111
 
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index 153624e2d0f5..016bba2c142d 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -19,7 +19,8 @@
 
 #include "tests.h"
 #include "debug.h"
-#include "perf.h"
+#include "event.h"
+#include "../perf-sys.h"
 #include "cloexec.h"
 
 volatile long the_var;
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 910e25e64188..c1c2c13de254 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -25,7 +25,8 @@
 
 #include "tests.h"
 #include "debug.h"
-#include "perf.h"
+#include "event.h"
+#include "perf-sys.h"
 #include "cloexec.h"
 
 static int fd1;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index ca962559e845..eb4dbbddf4ff 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -24,7 +24,8 @@
 
 #include "tests.h"
 #include "debug.h"
-#include "perf.h"
+#include "event.h"
+#include "../perf-sys.h"
 #include "cloexec.h"
 
 static int overflows;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 98642961fc63..fc102e4f403e 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -12,11 +12,13 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <api/fs/fs.h>
 #include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
+#include "parse-events.h"
 #define NR_ITERS       111
 #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index c3bec9d2c201..55774baffc2a 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <stdlib.h>
 #include <sys/types.h>
 #include <dirent.h>
 #include <sys/wait.h>
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index fe671b860086..c1c29e08e7fb 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -11,7 +11,11 @@
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
 
+#include "debug.h"
+#include "dso.h"
+#include "env.h"
 #include "parse-events.h"
+#include "trace-event.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
@@ -494,6 +498,10 @@ static void fs_something(void)
 	}
 }
 
+#ifdef __s390x__
+#include "header.h" // for get_cpuid()
+#endif
+
 static const char *do_determine_event(bool excl_kernel)
 {
 	const char *event = excl_kernel ? "cycles:u" : "cycles";
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 946ab4b63acd..a4874d4ce7ef 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -9,6 +9,7 @@
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <api/fs/fs.h>
+#include "dso.h"
 #include "util.h"
 #include "machine.h"
 #include "symbol.h"
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index f33709a79335..4125255ff637 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include <linux/types.h>
 #include <linux/zalloc.h>
 #include <inttypes.h>
+#include <limits.h>
 #include <unistd.h>
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 714e3611352c..d824a726906c 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <string.h>
@@ -10,6 +11,7 @@
 #include "evsel.h"
 #include "util.h"
 #include "debug.h"
+#include "parse-events.h"
 #include "thread_map.h"
 #include "target.h"
 
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index 1411155597b8..cac4290e233a 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <perf/cpumap.h>
+#include <string.h>
 #include "evlist.h"
 #include "evsel.h"
+#include "header.h"
 #include "machine.h"
+#include "tool.h"
 #include "tests.h"
 #include "debug.h"
 
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index ee1d88650e69..87843af4c118 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -3,6 +3,7 @@
 #include "util/expr.h"
 #include "tests.h"
 #include <stdlib.h>
+#include <string.h>
 #include <linux/zalloc.h>
 
 static int test(struct parse_ctx *ctx, const char *e, double val2)
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index 469958cd7fe0..de110d8f169b 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -1,12 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
-#include "perf.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
 #include "util/evsel.h"
-#include "util/evlist.h"
 #include "util/machine.h"
 #include "util/thread.h"
 #include "tests/hists_common.h"
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 1f3de85ae18b..fa55b7bad3af 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include "util/event.h"
 #include "util/map.h"
 #include "util/symbol.h"
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index a274716fc438..618b51ffcc01 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
 #include "util/debug.h"
 #include "util/map.h"
 #include "util/symbol.h"
@@ -8,7 +7,6 @@
 #include "util/event.h"
 #include "util/evlist.h"
 #include "util/machine.h"
-#include "util/thread.h"
 #include "util/parse-events.h"
 #include "tests/tests.h"
 #include "tests/hists_common.h"
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index b25383aa2e6e..8be4d0b61e3a 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
 #include "tests.h"
 #include "debug.h"
 #include "symbol.h"
@@ -7,7 +6,6 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
-#include "thread.h"
 #include "parse-events.h"
 #include "hists_common.h"
 #include <errno.h>
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 009888adf4b3..3f6dfa212260 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
 #include "util/debug.h"
+#include "util/dso.h"
 #include "util/event.h"
 #include "util/map.h"
 #include "util/symbol.h"
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 2af6faf1bbd6..9f0762d987fa 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
+#include <limits.h>
 #include <unistd.h>
 #include <sys/prctl.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
 
+#include "debug.h"
 #include "parse-events.h"
 #include "evlist.h"
 #include "evsel.h"
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 0579a70bbbff..e483210b176b 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <stdlib.h>
+#include <string.h>
 #include "tests.h"
 #include "dso.h"
 #include "debug.h"
+#include "event.h"
 
 static int test(const char *path, bool alloc_name, bool kmod,
 		int comp, const char *name)
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index ca5a5f94ce79..022e4c9cf092 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <bpf/libbpf.h>
 #include <util/llvm-utils.h>
-#include <util/cache.h>
 #include "llvm.h"
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c
index efe3397824d2..673a11a6cd1b 100644
--- a/tools/perf/tests/mem.c
+++ b/tools/perf/tests/mem.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "util/map_symbol.h"
 #include "util/mem-events.h"
 #include "util/symbol.h"
 #include "linux/perf_event.h"
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index 73b2855acaf4..7672ade70f20 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/bitmap.h>
+#include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <perf/cpumap.h>
 #include "cpumap.h"
 #include "debug.h"
+#include "env.h"
 #include "mem2node.h"
 #include "tests.h"
 
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 7327694fbde0..85e1d7337dc0 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -3,8 +3,10 @@
 #include <inttypes.h>
 /* For the CLR_() macros */
 #include <pthread.h>
+#include <stdlib.h>
 #include <perf/cpumap.h>
 
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
@@ -12,6 +14,7 @@
 #include "tests.h"
 #include <linux/err.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <perf/evlist.h>
 
 /*
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 4ae4dea07466..9171f77cd9cd 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <api/fs/fs.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <api/fs/tracing_path.h>
 #include "evsel.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 62492106fb5e..b71167b43dda 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 58df4bda5e12..5ebffae18605 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -3,6 +3,7 @@
 #include <inttypes.h>
 #include <api/fs/tracing_path.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 49f52e4de41b..02ba696fb87f 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -5,6 +5,7 @@
 #include <api/fs/fs.h>
 #include "tests.h"
 #include "debug.h"
+#include "pmu.h"
 #include "util.h"
 #include <dirent.h>
 #include <errno.h>
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 3a205f6f9363..e1b42292cf7f 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
+#include <linux/string.h>
 /* For the CLR_() macros */
 #include <pthread.h>
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index a8ca29fe172b..5fcc06817076 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -2,10 +2,12 @@
 #include <stdbool.h>
 #include <inttypes.h>
 #include <stdlib.h>
+#include <string.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 
+#include "map_symbol.h"
 #include "branch.h"
 #include "util.h"
 #include "event.h"
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index dbc35a8912ed..cf1bd57d3023 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
+#include <limits.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/epoll.h>
-#include <util/evlist.h>
 #include <util/symbol.h>
 #include <linux/filter.h>
 #include "tests.h"
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index c5f1a9f83380..97694a040986 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -5,8 +5,10 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
+#include <linux/string.h>
 
 #include "tests.h"
+#include "util/debug.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
 #include "util/cpumap.h"
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index b63f02768724..1a60fa1219f5 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -2,12 +2,14 @@
 #include <sys/time.h>
 #include <sys/prctl.h>
 #include <errno.h>
+#include <limits.h>
 #include <time.h>
 #include <stdlib.h>
 #include <linux/zalloc.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
 
+#include "debug.h"
 #include "parse-events.h"
 #include "evlist.h"
 #include "evsel.h"
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index d79a22e2d8be..f610e8c0a083 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "target.h"
@@ -8,6 +9,7 @@
 
 #include <errno.h>
 #include <signal.h>
+#include <linux/string.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 c19ec8849e77..39168c57943b 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,12 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
+#include <string.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/prctl.h>
 #include "tests.h"
 #include "thread_map.h"
 #include "debug.h"
+#include "event.h"
 #include <linux/zalloc.h>
+#include <perf/event.h>
+
+struct perf_sample;
+struct perf_tool;
+struct machine;
 
 #define NAME	(const char *) "perf"
 #define NAMEUL	(unsigned long) NAME
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index b1d1bbafe7ae..cbac71716dec 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -2,7 +2,6 @@
 #include "tests.h"
 #include "machine.h"
 #include "thread.h"
-#include "map.h"
 #include "debug.h"
 
 int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
index 2bb8cb0039c1..3721757435da 100644
--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -2,6 +2,7 @@
 #include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <string.h>
 #include "tests.h"
 #include "units.h"
 #include "debug.h"
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 5e8834fc7dec..01f434c067c6 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -4,6 +4,7 @@
 #include <inttypes.h>
 #include <string.h>
 #include <stdlib.h>
+#include "dso.h"
 #include "map.h"
 #include "symbol.h"
 #include "util.h"
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index f89e6806557b..d262d6639829 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -1,10 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
 #include <sys/ioctl.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/kernel.h>
 #include "tests.h"
 #include "debug.h"
+#include "event.h"
 #include "cloexec.h"
+#include "../perf-sys.h"
 
 #define WP_TEST_ASSERT_VAL(fd, text, val)       \
 do {                                            \
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index c797a853d3a0..f93d40b1c203 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -2,7 +2,6 @@
 #include "../util/util.h"
 #include "../util/string2.h"
 #include "../util/config.h"
-#include "../perf.h"
 #include "libslang.h"
 #include "ui.h"
 #include "util.h"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e633eb42550d..ac74ed2c23a0 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -4,6 +4,8 @@
 #include "../ui.h"
 #include "../util.h"
 #include "../../util/annotate.h"
+#include "../../util/debug.h"
+#include "../../util/dso.h"
 #include "../../util/hist.h"
 #include "../../util/sort.h"
 #include "../../util/map.h"
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index 5aeb663dd184..0f59a7001479 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/cache.h"
 #include "util/debug.h"
 #include "ui/browser.h"
 #include "ui/keysyms.h"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 30547fdb0787..589168ca9f62 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -11,17 +11,23 @@
 #include <linux/time64.h>
 #include <linux/zalloc.h>
 
+#include "../../util/debug.h"
+#include "../../util/dso.h"
 #include "../../util/callchain.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
+#include "../../util/header.h"
 #include "../../util/hist.h"
 #include "../../util/map.h"
 #include "../../util/symbol.h"
+#include "../../util/map_symbol.h"
+#include "../../util/branch.h"
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/top.h"
 #include "../../util/thread.h"
 #include "../../arch/common.h"
+#include "../../perf.h"
 
 #include "../browsers/hists.h"
 #include "../helpline.h"
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 4c545b92e20d..893b065971f6 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -8,6 +8,7 @@
 #include "../../util/util.h"
 #include "../../util/debug.h"
 #include "../../util/map.h"
+#include "../../util/dso.h"
 #include "../../util/symbol.h"
 #include "../browser.h"
 #include "../helpline.h"
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index 41a9d8923ec4..f16a38fea45e 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -8,6 +8,9 @@
 #include "time-utils.h"
 #include "../util.h"
 #include "../../util/util.h"
+#include "../../perf.h"
+#include <stdlib.h>
+#include <string.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 50e0c03171f2..586a21acc13d 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../builtin.h"
-#include "../../util/sort.h"
+#include "../../perf.h"
 #include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
@@ -8,7 +8,9 @@
 #include "../browser.h"
 #include "../libslang.h"
 #include "config.h"
+#include <linux/string.h>
 #include <linux/zalloc.h>
+#include <stdlib.h>
 
 #define SCRIPT_NAMELEN	128
 #define SCRIPT_MAX_NO	64
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index d7f984436dec..8e744af24f7c 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -5,6 +5,7 @@
 #include "util/annotate.h"
 #include "util/evsel.h"
 #include "util/map.h"
+#include "util/dso.h"
 #include "util/symbol.h"
 #include "ui/helpline.h"
 #include <inttypes.h>
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 4820e25ac68d..8f3e43d148a8 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../evlist.h"
-#include "../cache.h"
 #include "../evsel.h"
 #include "../sort.h"
 #include "../hist.h"
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
index fbf1ea9ce9a2..e166da9ec767 100644
--- a/tools/perf/ui/gtk/helpline.c
+++ b/tools/perf/ui/gtk/helpline.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <string.h>
+#include <linux/kernel.h>
 
 #include "gtk.h"
 #include "../ui.h"
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 0efdb226d1a7..6c2efc10bf5c 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../evlist.h"
-#include "../cache.h"
 #include "../callchain.h"
 #include "../evsel.h"
 #include "../sort.h"
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 506e73b3834c..1a2616b97b5c 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "gtk.h"
-#include "../../util/cache.h"
 #include "../../util/debug.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 c28bdb7517ac..c2c558958b9c 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -3,6 +3,7 @@
 #include "../../util/debug.h"
 #include "gtk.h"
 
+#include <stdlib.h>
 #include <string.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index 8f775a053ca3..2165a098dee8 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -5,8 +5,6 @@
 #include <stdio.h>
 #include <stdarg.h>
 
-#include "../util/cache.h"
-
 struct ui_helpline {
 	void (*pop)(void);
 	void (*push)(const char *msg);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index e5fb64347b2c..3e533de7d852 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -1,14 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <math.h>
+#include <stdlib.h>
+#include <string.h>
 #include <linux/compiler.h>
 
 #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"
+#include "../perf.h"
 
 /* hist period print (hpp) functions */
 
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index 8cd3b64c6893..99d60223c74b 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "../util/cache.h"
 #include "progress.h"
 
 static void null_progress__update(struct ui_progress *p __maybe_unused)
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 3bc7c9a6fae9..c7a86b4be9f5 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -2,10 +2,11 @@
 #include <pthread.h>
 #include <dlfcn.h>
 
-#include "../util/cache.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;
 void *perf_gtk_handle;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 51ed67548b83..832ca6cfbe30 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include <stdlib.h>
 #include <linux/string.h>
 
 #include "../../util/callchain.h"
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 93d6b7240285..5f188f678c55 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -3,6 +3,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <pthread.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
 
 #include "../../util/debug.h"
 #include "../helpline.h"
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index 5a24dd3ce4db..3d74af5a7ece 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "../../util/cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 3ad0d3363ac6..56651a4f5aa0 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,4 +1,3 @@
-// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
@@ -8,9 +7,9 @@
 #include <execinfo.h>
 #endif
 
-#include "../../util/cache.h"
 #include "../../util/debug.h"
 #include "../../util/util.h"
+#include "../../perf.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index 1163df8b6f06..087d9ab054c8 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/cache.h"
 #include "../../util/debug.h"
 #include "../browser.h"
 #include "../keysyms.h"
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index 9ed76e88a3e4..689b27c34246 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "../util/debug.h"
-
+#include <stdio.h>
 
 /*
  * Default error logging functions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2e3856471e61..0b4d8e0d474c 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -36,6 +36,7 @@ perf-y += strfilter.o
 perf-y += top.o
 perf-y += usage.o
 perf-y += dso.o
+perf-y += dsos.o
 perf-y += symbol.o
 perf-y += symbol_fprintf.o
 perf-y += color.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3bd1691f0be7..1748f528b6e9 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -9,6 +9,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <libgen.h>
+#include <stdlib.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
@@ -19,8 +20,10 @@
 #include "build-id.h"
 #include "color.h"
 #include "config.h"
-#include "cache.h"
+#include "dso.h"
+#include "env.h"
 #include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
 #include "srcline.h"
 #include "units.h"
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d7c3fbb3694f..8a7340f6a2a2 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -8,6 +8,8 @@
 #include <errno.h>
 #include <byteswap.h>
 #include <inttypes.h>
+#include <unistd.h>
+#include <stdlib.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
@@ -17,10 +19,8 @@
 #include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
-#include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "thread.h"
 #include "debug.h"
 #include "auxtrace.h"
 #include "arm-spe.h"
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 10c707724035..6f25224a3def 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -2196,3 +2196,36 @@ int auxtrace_parse_filters(struct evlist *evlist)
 
 	return 0;
 }
+
+int auxtrace__process_event(struct perf_session *session, union perf_event *event,
+			    struct perf_sample *sample, struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->flush_events(session, tool);
+}
+
+void auxtrace__free_events(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free_events(session);
+}
+
+void auxtrace__free(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free(session);
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b213e6431d88..37e70dc01436 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -15,11 +15,9 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include <asm/bitsperlong.h>
+#include <asm/barrier.h>
 
-#include "../perf.h"
 #include "event.h"
-#include "session.h"
-#include "debug.h"
 
 union perf_event;
 struct perf_session;
@@ -31,6 +29,11 @@ struct record_opts;
 struct perf_record_auxtrace_info;
 struct events_stats;
 
+enum auxtrace_error_type {
+       PERF_AUXTRACE_ERROR_ITRACE  = 1,
+       PERF_AUXTRACE_ERROR_MAX
+};
+
 /* Auxtrace records must have the same alignment as perf event records */
 #define PERF_AUXTRACE_RECORD_ALIGNMENT 8
 
@@ -376,6 +379,8 @@ struct addr_filters {
 	int			cnt;
 };
 
+struct auxtrace_cache;
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 /*
@@ -545,41 +550,11 @@ int addr_filters__parse_bare_filter(struct addr_filters *filts,
 				    const char *filter);
 int auxtrace_parse_filters(struct evlist *evlist);
 
-static inline int auxtrace__process_event(struct perf_session *session,
-					  union perf_event *event,
-					  struct perf_sample *sample,
-					  struct perf_tool *tool)
-{
-	if (!session->auxtrace)
-		return 0;
-
-	return session->auxtrace->process_event(session, event, sample, tool);
-}
-
-static inline int auxtrace__flush_events(struct perf_session *session,
-					 struct perf_tool *tool)
-{
-	if (!session->auxtrace)
-		return 0;
-
-	return session->auxtrace->flush_events(session, tool);
-}
-
-static inline void auxtrace__free_events(struct perf_session *session)
-{
-	if (!session->auxtrace)
-		return;
-
-	return session->auxtrace->free_events(session);
-}
-
-static inline void auxtrace__free(struct perf_session *session)
-{
-	if (!session->auxtrace)
-		return;
-
-	return session->auxtrace->free(session);
-}
+int auxtrace__process_event(struct perf_session *session, union perf_event *event,
+			    struct perf_sample *sample, struct perf_tool *tool);
+int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool);
+void auxtrace__free_events(struct perf_session *session);
+void auxtrace__free(struct perf_session *session);
 
 #define ITRACE_HELP \
 "				i:	    		synthesize instructions events\n"		\
@@ -614,6 +589,7 @@ void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts)
 }
 
 #else
+#include "debug.h"
 
 static inline struct auxtrace_record *
 auxtrace_record__init(struct evlist *evlist __maybe_unused,
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 2d6d500c9af7..7a3d4b125323 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -8,6 +8,7 @@
 #include <linux/err.h>
 #include "bpf-event.h"
 #include "debug.h"
+#include "dso.h"
 #include "symbol.h"
 #include "machine.h"
 #include "env.h"
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 417b78835ea0..a01c2fd68c03 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -13,6 +13,7 @@ struct machine;
 union perf_event;
 struct perf_env;
 struct perf_sample;
+struct perf_session;
 struct record_opts;
 struct evlist;
 struct target;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 80a828e75cf6..37283e865352 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -14,7 +14,7 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <errno.h>
-#include "perf.h"
+#include <stdlib.h>
 #include "debug.h"
 #include "evlist.h"
 #include "bpf-loader.h"
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 77e4891e17b0..b020a8678eb9 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -8,12 +8,12 @@
  */
 
 #include <bpf/libbpf.h>
-#include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-finder.h"
 #include <errno.h>
+#include <stdlib.h>
 #include <dwarf-regs.h>
 #include <linux/filter.h>
 
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index a4fce2729e50..9d1e090084a2 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -1,7 +1,8 @@
-#include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
+#include "util/map_symbol.h"
 #include "util/branch.h"
+#include <linux/kernel.h>
 
 static bool cross_area(u64 addr1, u64 addr2, int size)
 {
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 64f96b79f1d7..06f66dad0b79 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -16,6 +16,14 @@ struct branch_flags {
 	u64 reserved:40;
 };
 
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags    flags;
+	char		       *srcline_from;
+	char		       *srcline_to;
+};
+
 struct branch_entry {
 	u64			from;
 	u64			to;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 4c96a33b09ff..e5fb77755d9e 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -13,6 +13,7 @@
 #include <stdio.h>
 #include <sys/stat.h>
 #include <sys/types.h>
+#include "dso.h"
 #include "build-id.h"
 #include "event.h"
 #include "namespaces.h"
diff --git a/tools/perf/util/cacheline.c b/tools/perf/util/cacheline.c
index 9361d3f61f75..e98b5250a517 100644
--- a/tools/perf/util/cacheline.c
+++ b/tools/perf/util/cacheline.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "cacheline.h"
-#include "../perf.h"
 #include <unistd.h>
 
 #ifdef _SC_LEVEL1_DCACHE_LINESIZE
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index dd6e01000385..c14646c1f2eb 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -16,11 +16,13 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <math.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
 #include "asm/bug.h"
 
 #include "debug.h"
+#include "dso.h"
 #include "hist.h"
 #include "sort.h"
 #include "machine.h"
@@ -28,6 +30,7 @@
 #include "callchain.h"
 #include "branch.h"
 #include "symbol.h"
+#include "../perf.h"
 
 #define CALLCHAIN_PARAM_DEFAULT			\
 	.mode		= CHAIN_GRAPH_ABS,	\
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 45b9ed49e2b1..b042ceef4114 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -8,6 +8,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 
+struct evsel;
 struct map;
 
 #define HELP_PAD "\t\t\t\t"
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index f73599f271ff..4881d4af3381 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../perf.h"
 #include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
@@ -9,6 +8,8 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
 
 int nr_cgroups;
 
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 06f48312c5ed..4e904fcb2783 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -2,12 +2,14 @@
 #include <errno.h>
 #include <sched.h>
 #include "util.h"
-#include "../perf.h"
+#include "../perf-sys.h"
 #include "cloexec.h"
+#include "event.h"
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <linux/string.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 39b8c4ec4e2e..bffbdd216a6a 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "cache.h"
+#include <subcmd/pager.h>
 #include <stdlib.h>
 #include <stdio.h>
+#include <string.h>
 #include "color.h"
 #include <math.h>
 #include <unistd.h>
diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c
index 817dc56e7e95..dc09ba7cb31e 100644
--- a/tools/perf/util/color_config.c
+++ b/tools/perf/util/color_config.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "cache.h"
+#include <subcmd/pager.h>
+#include <string.h>
 #include "config.h"
 #include <stdlib.h>
 #include <stdio.h>
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 042ffbc8c53f..0bc9c4d7fdc5 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -17,9 +17,13 @@
 #include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
+#include "build-id.h"
+#include "debug.h"
 #include "config.h"
+#include "debug.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index b9301e7e9c76..a22c1114e880 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <api/fs/fs.h>
-#include "../perf.h"
 #include "cpumap.h"
 #include "debug.h"
 #include "event.h"
diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h
index bae2f1d41856..7bf6b811f715 100644
--- a/tools/perf/util/cputopo.h
+++ b/tools/perf/util/cputopo.h
@@ -3,7 +3,6 @@
 #define __PERF_CPUTOPO_H
 
 #include <linux/types.h>
-#include "env.h"
 
 struct cpu_topology {
 	u32	  core_sib;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index d6de3834865e..707afdbd9529 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -21,14 +21,18 @@
 #include "cs-etm.h"
 #include "cs-etm-decoder/cs-etm-decoder.h"
 #include "debug.h"
+#include "dso.h"
 #include "evlist.h"
 #include "intlist.h"
 #include "machine.h"
 #include "map.h"
 #include "perf.h"
+#include "session.h"
+#include "map_symbol.h"
+#include "branch.h"
 #include "symbol.h"
+#include "tool.h"
 #include "thread.h"
-#include "thread_map.h"
 #include "thread-stack.h"
 #include <tools/libc_compat.h>
 #include "util.h"
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index bc848fd095f4..650ecc2a6349 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -8,9 +8,10 @@
 #define INCLUDE__UTIL_PERF_CS_ETM_H__
 
 #include "util/event.h"
-#include "util/session.h"
 #include <linux/bits.h>
 
+struct perf_session;
+
 /* Versionning header in case things need tro change in the future.  That way
  * decoding of old snapshot is still possible.
  */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 74aafe0df506..e75c3a279fe8 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 701e9f814313..752227b265e7 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <stdlib.h>
 
+#include "dso.h"
 #include "evsel.h"
 #include "machine.h"
 #include "thread.h"
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 3780fe42453b..a1b59bd35519 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* For general debugging purposes */
 
-#include "../perf.h"
-
 #include <inttypes.h>
 #include <string.h>
 #include <stdarg.h>
@@ -10,17 +8,19 @@
 #include <stdlib.h>
 #include <sys/wait.h>
 #include <api/debug.h>
+#include <linux/kernel.h>
 #include <linux/time64.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
-#include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
 #include "print_binary.h"
 #include "util.h"
 #include "target.h"
+#include "ui/helpline.h"
+#include "ui/ui.h"
 
 #include <linux/ctype.h>
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 77445dfc5c7d..b2deee987ffa 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -4,11 +4,7 @@
 #define __PERF_DEBUG_H
 
 #include <stdbool.h>
-#include <string.h>
 #include <linux/compiler.h>
-#include "event.h"
-#include "../ui/helpline.h"
-#include "../ui/progress.h"
 #include "../ui/util.h"
 
 extern int verbose;
@@ -42,6 +38,8 @@ extern int debug_data_convert;
 
 #define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
+union perf_event;
+
 int dump_printf(const char *fmt, ...) __printf(1, 2);
 void trace_event(union perf_event *event);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index ebc9d46c15a7..e11ddf86f2b3 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -10,16 +10,18 @@
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
-#include <libgen.h>
+#include <stdlib.h>
 #include <bpf/libbpf.h>
 #include "bpf-event.h"
 #include "compress.h"
+#include "env.h"
 #include "namespaces.h"
 #include "path.h"
 #include "map.h"
 #include "symbol.h"
 #include "srcline.h"
 #include "dso.h"
+#include "dsos.h"
 #include "machine.h"
 #include "auxtrace.h"
 #include "util.h" /* O_CLOEXEC for older systems */
@@ -1094,66 +1096,6 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
 	return dso;
 }
 
-/*
- * Find a matching entry and/or link current entry to RB tree.
- * Either one of the dso or name parameter must be non-NULL or the
- * function will not work.
- */
-static struct dso *__dso__findlink_by_longname(struct rb_root *root,
-					       struct dso *dso, const char *name)
-{
-	struct rb_node **p = &root->rb_node;
-	struct rb_node  *parent = NULL;
-
-	if (!name)
-		name = dso->long_name;
-	/*
-	 * Find node with the matching name
-	 */
-	while (*p) {
-		struct dso *this = rb_entry(*p, struct dso, rb_node);
-		int rc = strcmp(name, this->long_name);
-
-		parent = *p;
-		if (rc == 0) {
-			/*
-			 * In case the new DSO is a duplicate of an existing
-			 * one, print a one-time warning & put the new entry
-			 * at the end of the list of duplicates.
-			 */
-			if (!dso || (dso == this))
-				return this;	/* Find matching dso */
-			/*
-			 * The core kernel DSOs may have duplicated long name.
-			 * In this case, the short name should be different.
-			 * Comparing the short names to differentiate the DSOs.
-			 */
-			rc = strcmp(dso->short_name, this->short_name);
-			if (rc == 0) {
-				pr_err("Duplicated dso name: %s\n", name);
-				return NULL;
-			}
-		}
-		if (rc < 0)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
-	}
-	if (dso) {
-		/* Add new node and rebalance tree */
-		rb_link_node(&dso->rb_node, parent, p);
-		rb_insert_color(&dso->rb_node, root);
-		dso->root = root;
-	}
-	return NULL;
-}
-
-static inline struct dso *__dso__find_by_longname(struct rb_root *root,
-						  const char *name)
-{
-	return __dso__findlink_by_longname(root, NULL, name);
-}
-
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	struct rb_root *root = dso->root;
@@ -1167,7 +1109,7 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 	if (root) {
 		rb_erase(&dso->rb_node, root);
 		/*
-		 * __dso__findlink_by_longname() isn't guaranteed to add it
+		 * __dsos__findnew_link_by_longname() isn't guaranteed to add it
 		 * back, so a clean removal is required here.
 		 */
 		RB_CLEAR_NODE(&dso->rb_node);
@@ -1179,7 +1121,7 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 	dso->long_name_allocated = name_allocated;
 
 	if (root)
-		__dso__findlink_by_longname(root, dso, NULL);
+		__dsos__findnew_link_by_longname(root, dso, NULL);
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
@@ -1195,38 +1137,6 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 	dso->short_name_allocated = name_allocated;
 }
 
-static void dso__set_basename(struct dso *dso)
-{
-	char *base, *lname;
-	int tid;
-
-	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
-		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
-			return;
-	} else {
-	      /*
-	       * basename() may modify path buffer, so we must pass
-               * a copy.
-               */
-		lname = strdup(dso->long_name);
-		if (!lname)
-			return;
-
-		/*
-		 * basename() may return a pointer to internal
-		 * storage which is reused in subsequent calls
-		 * so copy the result.
-		 */
-		base = strdup(basename(lname));
-
-		free(lname);
-
-		if (!base)
-			return;
-	}
-	dso__set_short_name(dso, base, true);
-}
-
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -1377,143 +1287,6 @@ int dso__kernel_module_get_build_id(struct dso *dso,
 	return 0;
 }
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
-{
-	bool have_build_id = false;
-	struct dso *pos;
-	struct nscookie nsc;
-
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit && !dso__is_vdso(pos))
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		nsinfo__mountns_enter(pos->nsinfo, &nsc);
-		if (filename__read_build_id(pos->long_name, pos->build_id,
-					    sizeof(pos->build_id)) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		}
-		nsinfo__mountns_exit(&nsc);
-	}
-
-	return have_build_id;
-}
-
-void __dsos__add(struct dsos *dsos, struct dso *dso)
-{
-	list_add_tail(&dso->node, &dsos->head);
-	__dso__findlink_by_longname(&dsos->root, dso, NULL);
-	/*
-	 * It is now in the linked list, grab a reference, then garbage collect
-	 * this when needing memory, by looking at LRU dso instances in the
-	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
-	 * anywhere besides the one for the list, do, under a lock for the
-	 * list: remove it from the list, then a dso__put(), that probably will
-	 * be the last and will then call dso__delete(), end of life.
-	 *
-	 * That, or at the end of the 'struct machine' lifetime, when all
-	 * 'struct dso' instances will be removed from the list, in
-	 * dsos__exit(), if they have no other reference from some other data
-	 * structure.
-	 *
-	 * E.g.: after processing a 'perf.data' file and storing references
-	 * to objects instantiated while processing events, we will have
-	 * references to the 'thread', 'map', 'dso' structs all from 'struct
-	 * hist_entry' instances, but we may not need anything not referenced,
-	 * so we might as well call machines__exit()/machines__delete() and
-	 * garbage collect it.
-	 */
-	dso__get(dso);
-}
-
-void dsos__add(struct dsos *dsos, struct dso *dso)
-{
-	down_write(&dsos->lock);
-	__dsos__add(dsos, dso);
-	up_write(&dsos->lock);
-}
-
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
-{
-	struct dso *pos;
-
-	if (cmp_short) {
-		list_for_each_entry(pos, &dsos->head, node)
-			if (strcmp(pos->short_name, name) == 0)
-				return pos;
-		return NULL;
-	}
-	return __dso__find_by_longname(&dsos->root, name);
-}
-
-struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
-{
-	struct dso *dso;
-	down_read(&dsos->lock);
-	dso = __dsos__find(dsos, name, cmp_short);
-	up_read(&dsos->lock);
-	return dso;
-}
-
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso = dso__new(name);
-
-	if (dso != NULL) {
-		__dsos__add(dsos, dso);
-		dso__set_basename(dso);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
-	}
-	return dso;
-}
-
-struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso = __dsos__find(dsos, name, false);
-
-	return dso ? dso : __dsos__addnew(dsos, name);
-}
-
-struct dso *dsos__findnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso;
-	down_write(&dsos->lock);
-	dso = dso__get(__dsos__findnew(dsos, name));
-	up_write(&dsos->lock);
-	return dso;
-}
-
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		if (skip && skip(pos, parm))
-			continue;
-		ret += dso__fprintf_buildid(pos, fp);
-		ret += fprintf(fp, " %s\n", pos->long_name);
-	}
-	return ret;
-}
-
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		ret += dso__fprintf(pos, fp);
-	}
-
-	return ret;
-}
-
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 6e3f63781e51..e4dddb76770d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -2,13 +2,13 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <pthread.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
 #include <stdio.h>
-#include "rwsem.h"
 #include <linux/bitops.h>
 #include "build-id.h"
 
@@ -16,6 +16,9 @@ struct machine;
 struct map;
 struct perf_env;
 
+#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
+#define DSO__NAME_KCORE		"[kernel.kcore]"
+
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
 	DSO_BINARY_TYPE__GUEST_KALLSYMS,
@@ -126,16 +129,6 @@ struct dso_cache {
 	char data[0];
 };
 
-/*
- * DSOs are put into both a list for fast iteration and rbtree for fast
- * long name lookup.
- */
-struct dsos {
-	struct list_head head;
-	struct rb_root	 root;	/* rbtree root sorted by long name */
-	struct rw_semaphore lock;
-};
-
 struct auxtrace_cache;
 
 struct dso {
@@ -344,21 +337,8 @@ struct map *dso__new_map(const char *name);
 struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
 				    const char *short_name, int dso_type);
 
-void __dsos__add(struct dsos *dsos, struct dso *dso);
-void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
-struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
-struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
-struct dso *dsos__findnew(struct dsos *dsos, const char *name);
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-
 void dso__reset_find_symbol_cache(struct dso *dso);
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm);
-size_t __dsos__fprintf(struct list_head *head, FILE *fp);
-
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
 size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
 size_t dso__fprintf(struct dso *dso, FILE *fp);
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
new file mode 100644
index 000000000000..3ea80d203587
--- /dev/null
+++ b/tools/perf/util/dsos.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
+#include "dsos.h"
+#include "dso.h"
+#include "vdso.h"
+#include "namespaces.h"
+#include <libgen.h>
+#include <stdlib.h>
+#include <string.h>
+#include <symbol.h> // filename__read_build_id
+
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+{
+	bool have_build_id = false;
+	struct dso *pos;
+	struct nscookie nsc;
+
+	list_for_each_entry(pos, head, node) {
+		if (with_hits && !pos->hit && !dso__is_vdso(pos))
+			continue;
+		if (pos->has_build_id) {
+			have_build_id = true;
+			continue;
+		}
+		nsinfo__mountns_enter(pos->nsinfo, &nsc);
+		if (filename__read_build_id(pos->long_name, pos->build_id,
+					    sizeof(pos->build_id)) > 0) {
+			have_build_id	  = true;
+			pos->has_build_id = true;
+		}
+		nsinfo__mountns_exit(&nsc);
+	}
+
+	return have_build_id;
+}
+
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node  *parent = NULL;
+
+	if (!name)
+		name = dso->long_name;
+	/*
+	 * Find node with the matching name
+	 */
+	while (*p) {
+		struct dso *this = rb_entry(*p, struct dso, rb_node);
+		int rc = strcmp(name, this->long_name);
+
+		parent = *p;
+		if (rc == 0) {
+			/*
+			 * In case the new DSO is a duplicate of an existing
+			 * one, print a one-time warning & put the new entry
+			 * at the end of the list of duplicates.
+			 */
+			if (!dso || (dso == this))
+				return this;	/* Find matching dso */
+			/*
+			 * The core kernel DSOs may have duplicated long name.
+			 * In this case, the short name should be different.
+			 * Comparing the short names to differentiate the DSOs.
+			 */
+			rc = strcmp(dso->short_name, this->short_name);
+			if (rc == 0) {
+				pr_err("Duplicated dso name: %s\n", name);
+				return NULL;
+			}
+		}
+		if (rc < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	if (dso) {
+		/* Add new node and rebalance tree */
+		rb_link_node(&dso->rb_node, parent, p);
+		rb_insert_color(&dso->rb_node, root);
+		dso->root = root;
+	}
+	return NULL;
+}
+
+void __dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	list_add_tail(&dso->node, &dsos->head);
+	__dsos__findnew_link_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	down_write(&dsos->lock);
+	__dsos__add(dsos, dso);
+	up_write(&dsos->lock);
+}
+
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *pos;
+
+	if (cmp_short) {
+		list_for_each_entry(pos, &dsos->head, node)
+			if (strcmp(pos->short_name, name) == 0)
+				return pos;
+		return NULL;
+	}
+	return __dsos__findnew_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *dso;
+	down_read(&dsos->lock);
+	dso = __dsos__find(dsos, name, cmp_short);
+	up_read(&dsos->lock);
+	return dso;
+}
+
+static void dso__set_basename(struct dso *dso)
+{
+	char *base, *lname;
+	int tid;
+
+	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
+		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
+			return;
+	} else {
+	      /*
+	       * basename() may modify path buffer, so we must pass
+               * a copy.
+               */
+		lname = strdup(dso->long_name);
+		if (!lname)
+			return;
+
+		/*
+		 * basename() may return a pointer to internal
+		 * storage which is reused in subsequent calls
+		 * so copy the result.
+		 */
+		base = strdup(basename(lname));
+
+		free(lname);
+
+		if (!base)
+			return;
+	}
+	dso__set_short_name(dso, base, true);
+}
+
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso = dso__new(name);
+
+	if (dso != NULL) {
+		__dsos__add(dsos, dso);
+		dso__set_basename(dso);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
+	}
+	return dso;
+}
+
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso = __dsos__find(dsos, name, false);
+
+	return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso;
+	down_write(&dsos->lock);
+	dso = dso__get(__dsos__findnew(dsos, name));
+	up_write(&dsos->lock);
+	return dso;
+}
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		if (skip && skip(pos, parm))
+			continue;
+		ret += dso__fprintf_buildid(pos, fp);
+		ret += fprintf(fp, " %s\n", pos->long_name);
+	}
+	return ret;
+}
+
+size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		ret += dso__fprintf(pos, fp);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h
new file mode 100644
index 000000000000..32f1fbee0feb
--- /dev/null
+++ b/tools/perf/util/dsos.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_DSOS
+#define __PERF_DSOS
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include "rwsem.h"
+
+struct dso;
+
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+	struct list_head    head;
+	struct rb_root	    root;	/* rbtree root sorted by long name */
+	struct rw_semaphore lock;
+};
+
+void __dsos__add(struct dsos *dsos, struct dso *dso);
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
+
+struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name);
+
+static inline struct dso *__dsos__findnew_by_longname(struct rb_root *root, const char *name)
+{
+	return __dsos__findnew_link_by_longname(root, NULL, name);
+}
+
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm);
+size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+
+#endif /* __PERF_DSOS */
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 03b2de1f5a35..df6cee5c071f 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "strbuf.h"
 #include "string2.h"
 
 /**
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 0489b0cf8e2c..f204e5892403 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -10,6 +10,8 @@
 #include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
 
+struct strbuf;
+
 /* Find the realpath of the target file */
 const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
 
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 571efb4f0351..3baca06786fb 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -9,6 +9,7 @@
 #include <sys/utsname.h>
 #include <bpf/libbpf.h>
 #include <stdlib.h>
+#include <string.h>
 
 struct perf_env perf_env;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index c9d1f83c747a..f4afbb858ebb 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,3 @@
-// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -12,6 +11,7 @@
 #include <api/fs/fs.h>
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
+#include "dso.h"
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -21,6 +21,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "time-utils.h"
 #include <linux/ctype.h>
 #include "map.h"
 #include "symbol.h"
@@ -29,6 +30,8 @@
 #include "stat.h"
 #include "session.h"
 #include "bpf-event.h"
+#include "tool.h"
+#include "../perf.h"
 
 #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 4c0c5232bd41..47ad81d47b1a 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -1,18 +1,23 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_RECORD_H
 #define __PERF_RECORD_H
-
-#include <limits.h>
+/*
+ * 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 <linux/kernel.h>
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include <linux/stddef.h>
 #include <perf/event.h>
+#include <linux/types.h>
 
-#include "../perf.h"
-#include "build-id.h"
 #include "perf_regs.h"
 
+struct dso;
+struct machine;
+struct perf_event_attr;
+
 #ifdef __LP64__
 /*
  * /usr/include/inttypes.h uses just 'lu' for PRIu64, but we end up defining
@@ -146,11 +151,6 @@ struct perf_sample {
 	 PERF_MEM_S(LOCK, NA) |\
 	 PERF_MEM_S(TLB, NA))
 
-enum auxtrace_error_type {
-	PERF_AUXTRACE_ERROR_ITRACE  = 1,
-	PERF_AUXTRACE_ERROR_MAX
-};
-
 /* Attribute type for custom synthesized events */
 #define PERF_TYPE_SYNTH		(INT_MAX + 1U)
 
@@ -272,43 +272,6 @@ static inline void *perf_synth__raw_data(void *p)
 
 #define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4)
 
-/*
- * The kernel collects the number of events it couldn't send in a stretch and
- * 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 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 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
- * perf_record_sample.period and stash the result in total_period.
- */
-struct events_stats {
-	u64 total_period;
-	u64 total_non_filtered_period;
-	u64 total_lost;
-	u64 total_lost_samples;
-	u64 total_aux_lost;
-	u64 total_aux_partial;
-	u64 total_invalid_chains;
-	u32 nr_events[PERF_RECORD_HEADER_MAX];
-	u32 nr_non_filtered_samples;
-	u32 nr_lost_warned;
-	u32 nr_unknown_events;
-	u32 nr_invalid_chains;
-	u32 nr_unknown_id;
-	u32 nr_unprocessable_samples;
-	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
-	u32 nr_proc_map_timeout;
-};
-
 enum {
 	PERF_STAT_ROUND_TYPE__INTERVAL	= 0,
 	PERF_STAT_ROUND_TYPE__FINAL	= 1,
diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h
new file mode 100644
index 000000000000..859cb34fcff2
--- /dev/null
+++ b/tools/perf/util/events_stats.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_EVENTS_STATS_
+#define __PERF_EVENTS_STATS_
+
+#include <stdio.h>
+#include <perf/event.h>
+#include <linux/types.h>
+#include "auxtrace.h"
+
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * 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 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 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
+ * perf_record_sample.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_non_filtered_period;
+	u64 total_lost;
+	u64 total_lost_samples;
+	u64 total_aux_lost;
+	u64 total_aux_partial;
+	u64 total_invalid_chains;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_non_filtered_samples;
+	u32 nr_lost_warned;
+	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
+	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
+};
+
+void events_stats__inc(struct events_stats *stats, u32 type);
+
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
+
+#endif /* __PERF_EVENTS_STATS_ */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 253dd8dd0e12..095924aa186b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -17,11 +17,13 @@
 #include "debug.h"
 #include "units.h"
 #include "util.h"
+#include "../perf.h"
 #include "asm/bug.h"
 #include "bpf-event.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
+#include <stdlib.h>
 
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
@@ -34,6 +36,7 @@
 #include <linux/hash.h>
 #include <linux/log2.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <perf/evlist.h>
 #include <perf/evsel.h>
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 16796de7af3f..a55f0f2546e5 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -9,8 +9,7 @@
 #include <api/fd/array.h>
 #include <stdio.h>
 #include <internal/evlist.h>
-#include "../perf.h"
-#include "event.h"
+#include "events_stats.h"
 #include "evsel.h"
 #include "mmap.h"
 #include <signal.h>
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbc04e1053a9..85825384f9e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -22,6 +22,7 @@
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <dirent.h>
+#include <stdlib.h>
 #include <perf/evsel.h>
 #include "asm/bug.h"
 #include "callchain.h"
@@ -41,6 +42,7 @@
 #include "string2.h"
 #include "memswap.h"
 #include "util.h"
+#include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index fd60caced4fc..68321d10eb2d 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -168,6 +168,7 @@ struct evsel {
 	const char *		metric_expr;
 	const char *		metric_name;
 	struct evsel		**metric_events;
+	struct evsel		*metric_leader;
 	bool			collect_stat;
 	bool			weak_group;
 	bool			percore;
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 432b8560cf51..f9a20a39b64a 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -2,9 +2,11 @@
 %{
 #include "util.h"
 #include "util/debug.h"
+#include <stdlib.h> // strtod()
 #define IN_EXPR_Y 1
 #include "expr.h"
 #include "smt.h"
+#include <assert.h>
 #include <string.h>
 
 #define MAXIDLEN 256
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index 7001247ebbd6..f9f18b8b1df9 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -14,6 +14,7 @@
 #include <libelf.h>
 #include <string.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <inttypes.h>
 #include <limits.h>
 #include <fcntl.h>
@@ -22,9 +23,9 @@
 #include <dwarf.h>
 #endif
 
-#include "perf.h"
 #include "genelf.h"
 #include "../util/jitdump.h"
+#include <linux/compiler.h>
 
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
index 995e490c17fa..30e9f618f6cd 100644
--- a/tools/perf/util/genelf_debug.c
+++ b/tools/perf/util/genelf_debug.c
@@ -24,7 +24,6 @@
 #include <err.h>
 #include <dwarf.h>
 
-#include "perf.h"
 #include "genelf.h"
 #include "../util/jitdump.h"
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0a842d9eff22..b0c34dda30a0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -22,11 +22,11 @@
 #include <bpf/libbpf.h>
 #include <perf/cpumap.h>
 
+#include "dso.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "header.h"
 #include "memswap.h"
-#include "../perf.h"
 #include "trace-event.h"
 #include "session.h"
 #include "symbol.h"
@@ -436,7 +436,25 @@ done:
 static int write_cpudesc(struct feat_fd *ff,
 		       struct evlist *evlist __maybe_unused)
 {
+#if defined(__powerpc__) || defined(__hppa__) || defined(__sparc__)
+#define CPUINFO_PROC	{ "cpu", }
+#elif defined(__s390__)
+#define CPUINFO_PROC	{ "vendor_id", }
+#elif defined(__sh__)
+#define CPUINFO_PROC	{ "cpu type", }
+#elif defined(__alpha__) || defined(__mips__)
+#define CPUINFO_PROC	{ "cpu model", }
+#elif defined(__arm__)
+#define CPUINFO_PROC	{ "model name", "Processor", }
+#elif defined(__arc__)
+#define CPUINFO_PROC	{ "Processor", }
+#elif defined(__xtensa__)
+#define CPUINFO_PROC	{ "core ID", }
+#else
+#define CPUINFO_PROC	{ "model name", }
+#endif
 	const char *cpuinfo_procs[] = CPUINFO_PROC;
+#undef CPUINFO_PROC
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
@@ -1122,16 +1140,17 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 	return 0;
 }
 
-#define MAX_CACHES (MAX_NR_CPUS * 4)
+#define MAX_CACHE_LVL 4
 
 static int write_cache(struct feat_fd *ff,
 		       struct evlist *evlist __maybe_unused)
 {
-	struct cpu_cache_level caches[MAX_CACHES];
+	u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL;
+	struct cpu_cache_level caches[max_caches];
 	u32 cnt = 0, i, version = 1;
 	int ret;
 
-	ret = build_caches(caches, MAX_CACHES, &cnt);
+	ret = build_caches(caches, max_caches, &cnt);
 	if (ret)
 		goto out;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e0b149673a88..679a1d75090c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,8 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "callchain.h"
+#include "debug.h"
+#include "dso.h"
 #include "build-id.h"
 #include "hist.h"
 #include "map.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "mem-events.h"
 #include "session.h"
 #include "namespaces.h"
 #include "sort.h"
@@ -18,6 +23,8 @@
 #include <math.h>
 #include <inttypes.h>
 #include <sys/param.h>
+#include <linux/rbtree.h>
+#include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7b9267ebebeb..34803e33dc80 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -6,9 +6,8 @@
 #include <linux/types.h>
 #include <pthread.h>
 #include "evsel.h"
-#include "header.h"
 #include "color.h"
-#include "ui/progress.h"
+#include "events_stats.h"
 
 struct hist_entry;
 struct hist_entry_ops;
@@ -18,6 +17,7 @@ struct mem_info;
 struct branch_info;
 struct block_info;
 struct symbol;
+struct ui_progress;
 
 enum hist_filter {
 	HIST_FILTER__DSO,
@@ -190,8 +190,6 @@ void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
 void hists__inc_nr_samples(struct hists *hists, bool filtered);
-void events_stats__inc(struct events_stats *stats, u32 type);
-size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 99dddb63dac1..aacffa2b0362 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -19,9 +19,9 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
-#include "map.h"
 #include "symbol.h"
 #include "session.h"
+#include "tool.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "debug.h"
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 23bf788f84b9..bc629359826f 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,7 +1,7 @@
 perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
 
-inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
-inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
+inat_tables_script = $(srctree)/tools/arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = $(srctree)/tools/arch/x86/lib/x86-opcode-map.txt
 
 $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
 	$(call rule_mkdir)
@@ -9,23 +9,7 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 
 # Busybox's diff doesn't have -I, avoid warning in the case
 
-$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
-	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
-	test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
-	((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
-	((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
deleted file mode 100644
index ddd5c4c21129..000000000000
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ /dev/null
@@ -1,392 +0,0 @@
-#!/bin/awk -f
-# SPDX-License-Identifier: GPL-2.0
-# gen-insn-attr-x86.awk: Instruction attribute table generator
-# Written by Masami Hiramatsu <mhiramat@redhat.com>
-#
-# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
-
-# Awk implementation sanity check
-function check_awk_implement() {
-	if (sprintf("%x", 0) != "0")
-		return "Your awk has a printf-format problem."
-	return ""
-}
-
-# Clear working vars
-function clear_vars() {
-	delete table
-	delete lptable2
-	delete lptable1
-	delete lptable3
-	eid = -1 # escape id
-	gid = -1 # group id
-	aid = -1 # AVX id
-	tname = ""
-}
-
-BEGIN {
-	# Implementation error checking
-	awkchecked = check_awk_implement()
-	if (awkchecked != "") {
-		print "Error: " awkchecked > "/dev/stderr"
-		print "Please try to use gawk." > "/dev/stderr"
-		exit 1
-	}
-
-	# Setup generating tables
-	print "/* x86 opcode map generated from x86-opcode-map.txt */"
-	print "/* Do not change this code. */\n"
-	ggid = 1
-	geid = 1
-	gaid = 0
-	delete etable
-	delete gtable
-	delete atable
-
-	opnd_expr = "^[A-Za-z/]"
-	ext_expr = "^\\("
-	sep_expr = "^\\|$"
-	group_expr = "^Grp[0-9A-Za-z]+"
-
-	imm_expr = "^[IJAOL][a-z]"
-	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
-	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
-	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
-	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
-	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
-	imm_flag["Ob"] = "INAT_MOFFSET"
-	imm_flag["Ov"] = "INAT_MOFFSET"
-	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-
-	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
-	force64_expr = "\\([df]64\\)"
-	rex_expr = "^REX(\\.[XRWB]+)*"
-	fpu_expr = "^ESC" # TODO
-
-	lprefix1_expr = "\\((66|!F3)\\)"
-	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
-	lprefix_expr = "\\((66|F2|F3)\\)"
-	max_lprefix = 4
-
-	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
-	# accepts VEX prefix
-	vexok_opcode_expr = "^[vk].*"
-	vexok_expr = "\\(v1\\)"
-	# All opcodes with (v) superscript supports *only* VEX prefix
-	vexonly_expr = "\\(v\\)"
-	# All opcodes with (ev) superscript supports *only* EVEX prefix
-	evexonly_expr = "\\(ev\\)"
-
-	prefix_expr = "\\(Prefix\\)"
-	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
-	prefix_num["REPNE"] = "INAT_PFX_REPNE"
-	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
-	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
-	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
-	prefix_num["LOCK"] = "INAT_PFX_LOCK"
-	prefix_num["SEG=CS"] = "INAT_PFX_CS"
-	prefix_num["SEG=DS"] = "INAT_PFX_DS"
-	prefix_num["SEG=ES"] = "INAT_PFX_ES"
-	prefix_num["SEG=FS"] = "INAT_PFX_FS"
-	prefix_num["SEG=GS"] = "INAT_PFX_GS"
-	prefix_num["SEG=SS"] = "INAT_PFX_SS"
-	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
-	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
-	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
-	prefix_num["EVEX"] = "INAT_PFX_EVEX"
-
-	clear_vars()
-}
-
-function semantic_error(msg) {
-	print "Semantic error at " NR ": " msg > "/dev/stderr"
-	exit 1
-}
-
-function debug(msg) {
-	print "DEBUG: " msg
-}
-
-function array_size(arr,   i,c) {
-	c = 0
-	for (i in arr)
-		c++
-	return c
-}
-
-/^Table:/ {
-	print "/* " $0 " */"
-	if (tname != "")
-		semantic_error("Hit Table: before EndTable:.");
-}
-
-/^Referrer:/ {
-	if (NF != 1) {
-		# escape opcode table
-		ref = ""
-		for (i = 2; i <= NF; i++)
-			ref = ref $i
-		eid = escape[ref]
-		tname = sprintf("inat_escape_table_%d", eid)
-	}
-}
-
-/^AVXcode:/ {
-	if (NF != 1) {
-		# AVX/escape opcode table
-		aid = $2
-		if (gaid <= aid)
-			gaid = aid + 1
-		if (tname == "")	# AVX only opcode table
-			tname = sprintf("inat_avx_table_%d", $2)
-	}
-	if (aid == -1 && eid == -1)	# primary opcode table
-		tname = "inat_primary_table"
-}
-
-/^GrpTable:/ {
-	print "/* " $0 " */"
-	if (!($2 in group))
-		semantic_error("No group: " $2 )
-	gid = group[$2]
-	tname = "inat_group_table_" gid
-}
-
-function print_table(tbl,name,fmt,n)
-{
-	print "const insn_attr_t " name " = {"
-	for (i = 0; i < n; i++) {
-		id = sprintf(fmt, i)
-		if (tbl[id])
-			print "	[" id "] = " tbl[id] ","
-	}
-	print "};"
-}
-
-/^EndTable/ {
-	if (gid != -1) {
-		# print group tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,3] = tname "_3"
-		}
-	} else {
-		# print primary/escaped tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,0] = tname
-			if (aid >= 0)
-				atable[aid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,1] = tname "_1"
-			if (aid >= 0)
-				atable[aid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,2] = tname "_2"
-			if (aid >= 0)
-				atable[aid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,3] = tname "_3"
-			if (aid >= 0)
-				atable[aid,3] = tname "_3"
-		}
-	}
-	print ""
-	clear_vars()
-}
-
-function add_flags(old,new) {
-	if (old && new)
-		return old " | " new
-	else if (old)
-		return old
-	else
-		return new
-}
-
-# convert operands to flags.
-function convert_operands(count,opnd,       i,j,imm,mod)
-{
-	imm = null
-	mod = null
-	for (j = 1; j <= count; j++) {
-		i = opnd[j]
-		if (match(i, imm_expr) == 1) {
-			if (!imm_flag[i])
-				semantic_error("Unknown imm opnd: " i)
-			if (imm) {
-				if (i != "Ib")
-					semantic_error("Second IMM error")
-				imm = add_flags(imm, "INAT_SCNDIMM")
-			} else
-				imm = imm_flag[i]
-		} else if (match(i, modrm_expr))
-			mod = "INAT_MODRM"
-	}
-	return add_flags(imm, mod)
-}
-
-/^[0-9a-f]+\:/ {
-	if (NR == 1)
-		next
-	# get index
-	idx = "0x" substr($1, 1, index($1,":") - 1)
-	if (idx in table)
-		semantic_error("Redefine " idx " in " tname)
-
-	# check if escaped opcode
-	if ("escape" == $2) {
-		if ($3 != "#")
-			semantic_error("No escaped name")
-		ref = ""
-		for (i = 4; i <= NF; i++)
-			ref = ref $i
-		if (ref in escape)
-			semantic_error("Redefine escape (" ref ")")
-		escape[ref] = geid
-		geid++
-		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
-		next
-	}
-
-	variant = null
-	# converts
-	i = 2
-	while (i <= NF) {
-		opcode = $(i++)
-		delete opnds
-		ext = null
-		flags = null
-		opnd = null
-		# parse one opcode
-		if (match($i, opnd_expr)) {
-			opnd = $i
-			count = split($(i++), opnds, ",")
-			flags = convert_operands(count, opnds)
-		}
-		if (match($i, ext_expr))
-			ext = $(i++)
-		if (match($i, sep_expr))
-			i++
-		else if (i < NF)
-			semantic_error($i " is not a separator")
-
-		# check if group opcode
-		if (match(opcode, group_expr)) {
-			if (!(opcode in group)) {
-				group[opcode] = ggid
-				ggid++
-			}
-			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
-		}
-		# check force(or default) 64bit
-		if (match(ext, force64_expr))
-			flags = add_flags(flags, "INAT_FORCE64")
-
-		# check REX prefix
-		if (match(opcode, rex_expr))
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
-
-		# check coprocessor escape : TODO
-		if (match(opcode, fpu_expr))
-			flags = add_flags(flags, "INAT_MODRM")
-
-		# check VEX codes
-		if (match(ext, evexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
-		else if (match(ext, vexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
-		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
-			flags = add_flags(flags, "INAT_VEXOK")
-
-		# check prefixes
-		if (match(ext, prefix_expr)) {
-			if (!prefix_num[opcode])
-				semantic_error("Unknown prefix: " opcode)
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
-		}
-		if (length(flags) == 0)
-			continue
-		# check if last prefix
-		if (match(ext, lprefix1_expr)) {
-			lptable1[idx] = add_flags(lptable1[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix2_expr)) {
-			lptable2[idx] = add_flags(lptable2[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix3_expr)) {
-			lptable3[idx] = add_flags(lptable3[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (!match(ext, lprefix_expr)){
-			table[idx] = add_flags(table[idx],flags)
-		}
-	}
-	if (variant)
-		table[idx] = add_flags(table[idx],variant)
-}
-
-END {
-	if (awkchecked != "")
-		exit 1
-	# print escape opcode map's array
-	print "/* Escape opcode map array */"
-	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < geid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (etable[i,j])
-				print "	["i"]["j"] = "etable[i,j]","
-	print "};\n"
-	# print group opcode map's array
-	print "/* Group opcode map array */"
-	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < ggid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (gtable[i,j])
-				print "	["i"]["j"] = "gtable[i,j]","
-	print "};\n"
-	# print AVX opcode map's array
-	print "/* AVX opcode map array */"
-	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < gaid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (atable[i,j])
-				print "	["i"]["j"] = "atable[i,j]","
-	print "};"
-}
diff --git a/tools/perf/util/intel-pt-decoder/inat.c b/tools/perf/util/intel-pt-decoder/inat.c
deleted file mode 100644
index 446c0413a27c..000000000000
--- a/tools/perf/util/intel-pt-decoder/inat.c
+++ /dev/null
@@ -1,82 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * x86 instruction attribute tables
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- */
-#include "insn.h"
-
-/* Attribute tables are generated from opcode map */
-#include "inat-tables.c"
-
-/* Attribute search APIs */
-insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
-{
-	return inat_primary_table[opcode];
-}
-
-int inat_get_last_prefix_id(insn_byte_t last_pfx)
-{
-	insn_attr_t lpfx_attr;
-
-	lpfx_attr = inat_get_opcode_attribute(last_pfx);
-	return inat_last_prefix_id(lpfx_attr);
-}
-
-insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
-				      insn_attr_t esc_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_escape_id(esc_attr);
-
-	table = inat_escape_tables[n][0];
-	if (!table)
-		return 0;
-	if (inat_has_variant(table[opcode]) && lpfx_id) {
-		table = inat_escape_tables[n][lpfx_id];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
-
-insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
-				     insn_attr_t grp_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_group_id(grp_attr);
-
-	table = inat_group_tables[n][0];
-	if (!table)
-		return inat_group_common_attribute(grp_attr);
-	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
-		table = inat_group_tables[n][lpfx_id];
-		if (!table)
-			return inat_group_common_attribute(grp_attr);
-	}
-	return table[X86_MODRM_REG(modrm)] |
-	       inat_group_common_attribute(grp_attr);
-}
-
-insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
-				   insn_byte_t vex_p)
-{
-	const insn_attr_t *table;
-	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
-		return 0;
-	/* At first, this checks the master table */
-	table = inat_avx_tables[vex_m][0];
-	if (!table)
-		return 0;
-	if (!inat_is_group(table[opcode]) && vex_p) {
-		/* If this is not a group, get attribute directly */
-		table = inat_avx_tables[vex_m][vex_p];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
diff --git a/tools/perf/util/intel-pt-decoder/inat_types.h b/tools/perf/util/intel-pt-decoder/inat_types.h
deleted file mode 100644
index b047efa9ddc2..000000000000
--- a/tools/perf/util/intel-pt-decoder/inat_types.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_X86_INAT_TYPES_H
-#define _ASM_X86_INAT_TYPES_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- */
-
-/* Instruction attributes */
-typedef unsigned int insn_attr_t;
-typedef unsigned char insn_byte_t;
-typedef signed int insn_value_t;
-
-#endif
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 3bfdf2b7a96a..f8ccfd6be0ee 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -14,9 +14,9 @@
 #include <stdint.h>
 #include <inttypes.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
-#include "../cache.h"
 #include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 598f56be9f17..fb8a3558d3d5 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -4,17 +4,17 @@
  * Copyright (c) 2013-2014, Intel Corporation.
  */
 
+#include <linux/kernel.h>
 #include <stdio.h>
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include "../../../arch/x86/include/asm/insn.h"
 
-#include "event.h"
-
-#include "insn.h"
+#include "../../../arch/x86/lib/inat.c"
+#include "../../../arch/x86/lib/insn.c"
 
-#include "inat.c"
-#include "insn.c"
+#include "event.h"
 
 #include "intel-pt-insn-decoder.h"
 #include "dump-insn.h"
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
deleted file mode 100644
index e0b85930dd77..000000000000
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ /dev/null
@@ -1,1072 +0,0 @@
-# x86 Opcode Maps
-#
-# This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
-#   (#326018-047US, June 2013)
-#
-#<Opcode maps>
-# Table: table-name
-# Referrer: escaped-name
-# AVXcode: avx-code
-# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# (or)
-# opcode: escape # escaped-name
-# EndTable
-#
-# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
-# mnemonics that begin with lowercase 'k' accept a VEX prefix
-#
-#<group maps>
-# GrpTable: GrpXXX
-# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# EndTable
-#
-# AVX Superscripts
-#  (ev): this opcode requires EVEX prefix.
-#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
-#  (v): this opcode requires VEX prefix.
-#  (v1): this opcode only supports 128bit VEX.
-#
-# Last Prefix Superscripts
-#  - (66): the last prefix is 0x66
-#  - (F3): the last prefix is 0xF3
-#  - (F2): the last prefix is 0xF2
-#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
-#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
-
-Table: one byte opcode
-Referrer:
-AVXcode:
-# 0x00 - 0x0f
-00: ADD Eb,Gb
-01: ADD Ev,Gv
-02: ADD Gb,Eb
-03: ADD Gv,Ev
-04: ADD AL,Ib
-05: ADD rAX,Iz
-06: PUSH ES (i64)
-07: POP ES (i64)
-08: OR Eb,Gb
-09: OR Ev,Gv
-0a: OR Gb,Eb
-0b: OR Gv,Ev
-0c: OR AL,Ib
-0d: OR rAX,Iz
-0e: PUSH CS (i64)
-0f: escape # 2-byte escape
-# 0x10 - 0x1f
-10: ADC Eb,Gb
-11: ADC Ev,Gv
-12: ADC Gb,Eb
-13: ADC Gv,Ev
-14: ADC AL,Ib
-15: ADC rAX,Iz
-16: PUSH SS (i64)
-17: POP SS (i64)
-18: SBB Eb,Gb
-19: SBB Ev,Gv
-1a: SBB Gb,Eb
-1b: SBB Gv,Ev
-1c: SBB AL,Ib
-1d: SBB rAX,Iz
-1e: PUSH DS (i64)
-1f: POP DS (i64)
-# 0x20 - 0x2f
-20: AND Eb,Gb
-21: AND Ev,Gv
-22: AND Gb,Eb
-23: AND Gv,Ev
-24: AND AL,Ib
-25: AND rAx,Iz
-26: SEG=ES (Prefix)
-27: DAA (i64)
-28: SUB Eb,Gb
-29: SUB Ev,Gv
-2a: SUB Gb,Eb
-2b: SUB Gv,Ev
-2c: SUB AL,Ib
-2d: SUB rAX,Iz
-2e: SEG=CS (Prefix)
-2f: DAS (i64)
-# 0x30 - 0x3f
-30: XOR Eb,Gb
-31: XOR Ev,Gv
-32: XOR Gb,Eb
-33: XOR Gv,Ev
-34: XOR AL,Ib
-35: XOR rAX,Iz
-36: SEG=SS (Prefix)
-37: AAA (i64)
-38: CMP Eb,Gb
-39: CMP Ev,Gv
-3a: CMP Gb,Eb
-3b: CMP Gv,Ev
-3c: CMP AL,Ib
-3d: CMP rAX,Iz
-3e: SEG=DS (Prefix)
-3f: AAS (i64)
-# 0x40 - 0x4f
-40: INC eAX (i64) | REX (o64)
-41: INC eCX (i64) | REX.B (o64)
-42: INC eDX (i64) | REX.X (o64)
-43: INC eBX (i64) | REX.XB (o64)
-44: INC eSP (i64) | REX.R (o64)
-45: INC eBP (i64) | REX.RB (o64)
-46: INC eSI (i64) | REX.RX (o64)
-47: INC eDI (i64) | REX.RXB (o64)
-48: DEC eAX (i64) | REX.W (o64)
-49: DEC eCX (i64) | REX.WB (o64)
-4a: DEC eDX (i64) | REX.WX (o64)
-4b: DEC eBX (i64) | REX.WXB (o64)
-4c: DEC eSP (i64) | REX.WR (o64)
-4d: DEC eBP (i64) | REX.WRB (o64)
-4e: DEC eSI (i64) | REX.WRX (o64)
-4f: DEC eDI (i64) | REX.WRXB (o64)
-# 0x50 - 0x5f
-50: PUSH rAX/r8 (d64)
-51: PUSH rCX/r9 (d64)
-52: PUSH rDX/r10 (d64)
-53: PUSH rBX/r11 (d64)
-54: PUSH rSP/r12 (d64)
-55: PUSH rBP/r13 (d64)
-56: PUSH rSI/r14 (d64)
-57: PUSH rDI/r15 (d64)
-58: POP rAX/r8 (d64)
-59: POP rCX/r9 (d64)
-5a: POP rDX/r10 (d64)
-5b: POP rBX/r11 (d64)
-5c: POP rSP/r12 (d64)
-5d: POP rBP/r13 (d64)
-5e: POP rSI/r14 (d64)
-5f: POP rDI/r15 (d64)
-# 0x60 - 0x6f
-60: PUSHA/PUSHAD (i64)
-61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
-63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
-64: SEG=FS (Prefix)
-65: SEG=GS (Prefix)
-66: Operand-Size (Prefix)
-67: Address-Size (Prefix)
-68: PUSH Iz (d64)
-69: IMUL Gv,Ev,Iz
-6a: PUSH Ib (d64)
-6b: IMUL Gv,Ev,Ib
-6c: INS/INSB Yb,DX
-6d: INS/INSW/INSD Yz,DX
-6e: OUTS/OUTSB DX,Xb
-6f: OUTS/OUTSW/OUTSD DX,Xz
-# 0x70 - 0x7f
-70: JO Jb
-71: JNO Jb
-72: JB/JNAE/JC Jb
-73: JNB/JAE/JNC Jb
-74: JZ/JE Jb
-75: JNZ/JNE Jb
-76: JBE/JNA Jb
-77: JNBE/JA Jb
-78: JS Jb
-79: JNS Jb
-7a: JP/JPE Jb
-7b: JNP/JPO Jb
-7c: JL/JNGE Jb
-7d: JNL/JGE Jb
-7e: JLE/JNG Jb
-7f: JNLE/JG Jb
-# 0x80 - 0x8f
-80: Grp1 Eb,Ib (1A)
-81: Grp1 Ev,Iz (1A)
-82: Grp1 Eb,Ib (1A),(i64)
-83: Grp1 Ev,Ib (1A)
-84: TEST Eb,Gb
-85: TEST Ev,Gv
-86: XCHG Eb,Gb
-87: XCHG Ev,Gv
-88: MOV Eb,Gb
-89: MOV Ev,Gv
-8a: MOV Gb,Eb
-8b: MOV Gv,Ev
-8c: MOV Ev,Sw
-8d: LEA Gv,M
-8e: MOV Sw,Ew
-8f: Grp1A (1A) | POP Ev (d64)
-# 0x90 - 0x9f
-90: NOP | PAUSE (F3) | XCHG r8,rAX
-91: XCHG rCX/r9,rAX
-92: XCHG rDX/r10,rAX
-93: XCHG rBX/r11,rAX
-94: XCHG rSP/r12,rAX
-95: XCHG rBP/r13,rAX
-96: XCHG rSI/r14,rAX
-97: XCHG rDI/r15,rAX
-98: CBW/CWDE/CDQE
-99: CWD/CDQ/CQO
-9a: CALLF Ap (i64)
-9b: FWAIT/WAIT
-9c: PUSHF/D/Q Fv (d64)
-9d: POPF/D/Q Fv (d64)
-9e: SAHF
-9f: LAHF
-# 0xa0 - 0xaf
-a0: MOV AL,Ob
-a1: MOV rAX,Ov
-a2: MOV Ob,AL
-a3: MOV Ov,rAX
-a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Yv,Xv
-a6: CMPS/B Xb,Yb
-a7: CMPS/W/D Xv,Yv
-a8: TEST AL,Ib
-a9: TEST rAX,Iz
-aa: STOS/B Yb,AL
-ab: STOS/W/D/Q Yv,rAX
-ac: LODS/B AL,Xb
-ad: LODS/W/D/Q rAX,Xv
-ae: SCAS/B AL,Yb
-# Note: The May 2011 Intel manual shows Xv for the second parameter of the
-# next instruction but Yv is correct
-af: SCAS/W/D/Q rAX,Yv
-# 0xb0 - 0xbf
-b0: MOV AL/R8L,Ib
-b1: MOV CL/R9L,Ib
-b2: MOV DL/R10L,Ib
-b3: MOV BL/R11L,Ib
-b4: MOV AH/R12L,Ib
-b5: MOV CH/R13L,Ib
-b6: MOV DH/R14L,Ib
-b7: MOV BH/R15L,Ib
-b8: MOV rAX/r8,Iv
-b9: MOV rCX/r9,Iv
-ba: MOV rDX/r10,Iv
-bb: MOV rBX/r11,Iv
-bc: MOV rSP/r12,Iv
-bd: MOV rBP/r13,Iv
-be: MOV rSI/r14,Iv
-bf: MOV rDI/r15,Iv
-# 0xc0 - 0xcf
-c0: Grp2 Eb,Ib (1A)
-c1: Grp2 Ev,Ib (1A)
-c2: RETN Iw (f64)
-c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11A Eb,Ib (1A)
-c7: Grp11B Ev,Iz (1A)
-c8: ENTER Iw,Ib
-c9: LEAVE (d64)
-ca: RETF Iw
-cb: RETF
-cc: INT3
-cd: INT Ib
-ce: INTO (i64)
-cf: IRET/D/Q
-# 0xd0 - 0xdf
-d0: Grp2 Eb,1 (1A)
-d1: Grp2 Ev,1 (1A)
-d2: Grp2 Eb,CL (1A)
-d3: Grp2 Ev,CL (1A)
-d4: AAM Ib (i64)
-d5: AAD Ib (i64)
-d6:
-d7: XLAT/XLATB
-d8: ESC
-d9: ESC
-da: ESC
-db: ESC
-dc: ESC
-dd: ESC
-de: ESC
-df: ESC
-# 0xe0 - 0xef
-# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
-# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
-# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-e1: LOOPE/LOOPZ Jb (f64)
-e2: LOOP Jb (f64)
-e3: JrCXZ Jb (f64)
-e4: IN AL,Ib
-e5: IN eAX,Ib
-e6: OUT Ib,AL
-e7: OUT Ib,eAX
-# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
-# in "near" jumps and calls is 16-bit. For CALL,
-# push of return address is 16-bit wide, RSP is decremented by 2
-# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64)
-e9: JMP-near Jz (f64)
-ea: JMP-far Ap (i64)
-eb: JMP-short Jb (f64)
-ec: IN AL,DX
-ed: IN eAX,DX
-ee: OUT DX,AL
-ef: OUT DX,eAX
-# 0xf0 - 0xff
-f0: LOCK (Prefix)
-f1:
-f2: REPNE (Prefix) | XACQUIRE (Prefix)
-f3: REP/REPE (Prefix) | XRELEASE (Prefix)
-f4: HLT
-f5: CMC
-f6: Grp3_1 Eb (1A)
-f7: Grp3_2 Ev (1A)
-f8: CLC
-f9: STC
-fa: CLI
-fb: STI
-fc: CLD
-fd: STD
-fe: Grp4 (1A)
-ff: Grp5 (1A)
-EndTable
-
-Table: 2-byte opcode (0x0f)
-Referrer: 2-byte escape
-AVXcode: 1
-# 0x0f 0x00-0x0f
-00: Grp6 (1A)
-01: Grp7 (1A)
-02: LAR Gv,Ew
-03: LSL Gv,Ew
-04:
-05: SYSCALL (o64)
-06: CLTS
-07: SYSRET (o64)
-08: INVD
-09: WBINVD
-0a:
-0b: UD2 (1B)
-0c:
-# AMD's prefetch group. Intel supports prefetchw(/1) only.
-0d: GrpP
-0e: FEMMS
-# 3DNow! uses the last imm byte as opcode extension.
-0f: 3DNow! Pq,Qq,Ib
-# 0x0f 0x10-0x1f
-# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
-# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
-# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
-# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
-# Reference A.1
-10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
-11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
-12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
-13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
-14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
-15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
-16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
-17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
-18: Grp16 (1A)
-19:
-# Intel SDM opcode map does not list MPX instructions. For now using Gv for
-# bnd registers and Ev for everything else is OK because the instruction
-# decoder does not use the information except as an indication that there is
-# a ModR/M byte.
-1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
-1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
-1d:
-1e:
-1f: NOP Ev
-# 0x0f 0x20-0x2f
-20: MOV Rd,Cd
-21: MOV Rd,Dd
-22: MOV Cd,Rd
-23: MOV Dd,Rd
-24:
-25:
-26:
-27:
-28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
-29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
-2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
-2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
-2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
-2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
-2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
-2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
-# 0x0f 0x30-0x3f
-30: WRMSR
-31: RDTSC
-32: RDMSR
-33: RDPMC
-34: SYSENTER
-35: SYSEXIT
-36:
-37: GETSEC
-38: escape # 3-byte escape 1
-39:
-3a: escape # 3-byte escape 2
-3b:
-3c:
-3d:
-3e:
-3f:
-# 0x0f 0x40-0x4f
-40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
-42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
-43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
-45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
-46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
-47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
-48: CMOVS Gv,Ev
-49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
-4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
-4c: CMOVL/NGE Gv,Ev
-4d: CMOVNL/GE Gv,Ev
-4e: CMOVLE/NG Gv,Ev
-4f: CMOVNLE/G Gv,Ev
-# 0x0f 0x50-0x5f
-50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
-51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
-52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
-53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
-54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
-55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
-56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
-57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
-58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
-59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
-5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
-5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
-5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
-5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
-5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
-# 0x0f 0x60-0x6f
-60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
-61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
-62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
-63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
-64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
-65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
-66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
-67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
-68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
-69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
-6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
-6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
-6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
-6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
-6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
-# 0x0f 0x70-0x7f
-70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
-71: Grp12 (1A)
-72: Grp13 (1A)
-73: Grp14 (1A)
-74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
-75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
-76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
-# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
-77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
-79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
-7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
-7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
-7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
-7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
-7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
-# 0x0f 0x80-0x8f
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-81: JNO Jz (f64)
-82: JB/JC/JNAE Jz (f64)
-83: JAE/JNB/JNC Jz (f64)
-84: JE/JZ Jz (f64)
-85: JNE/JNZ Jz (f64)
-86: JBE/JNA Jz (f64)
-87: JA/JNBE Jz (f64)
-88: JS Jz (f64)
-89: JNS Jz (f64)
-8a: JP/JPE Jz (f64)
-8b: JNP/JPO Jz (f64)
-8c: JL/JNGE Jz (f64)
-8d: JNL/JGE Jz (f64)
-8e: JLE/JNG Jz (f64)
-8f: JNLE/JG Jz (f64)
-# 0x0f 0x90-0x9f
-90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
-91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
-92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
-93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
-94: SETE/Z Eb
-95: SETNE/NZ Eb
-96: SETBE/NA Eb
-97: SETA/NBE Eb
-98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
-99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
-9a: SETP/PE Eb
-9b: SETNP/PO Eb
-9c: SETL/NGE Eb
-9d: SETNL/GE Eb
-9e: SETLE/NG Eb
-9f: SETNLE/G Eb
-# 0x0f 0xa0-0xaf
-a0: PUSH FS (d64)
-a1: POP FS (d64)
-a2: CPUID
-a3: BT Ev,Gv
-a4: SHLD Ev,Gv,Ib
-a5: SHLD Ev,Gv,CL
-a6: GrpPDLK
-a7: GrpRNG
-a8: PUSH GS (d64)
-a9: POP GS (d64)
-aa: RSM
-ab: BTS Ev,Gv
-ac: SHRD Ev,Gv,Ib
-ad: SHRD Ev,Gv,CL
-ae: Grp15 (1A),(1C)
-af: IMUL Gv,Ev
-# 0x0f 0xb0-0xbf
-b0: CMPXCHG Eb,Gb
-b1: CMPXCHG Ev,Gv
-b2: LSS Gv,Mp
-b3: BTR Ev,Gv
-b4: LFS Gv,Mp
-b5: LGS Gv,Mp
-b6: MOVZX Gv,Eb
-b7: MOVZX Gv,Ew
-b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
-b9: Grp10 (1A)
-ba: Grp8 Ev,Ib (1A)
-bb: BTC Ev,Gv
-bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
-be: MOVSX Gv,Eb
-bf: MOVSX Gv,Ew
-# 0x0f 0xc0-0xcf
-c0: XADD Eb,Gb
-c1: XADD Ev,Gv
-c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
-c3: movnti My,Gy
-c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
-c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
-c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
-c7: Grp9 (1A)
-c8: BSWAP RAX/EAX/R8/R8D
-c9: BSWAP RCX/ECX/R9/R9D
-ca: BSWAP RDX/EDX/R10/R10D
-cb: BSWAP RBX/EBX/R11/R11D
-cc: BSWAP RSP/ESP/R12/R12D
-cd: BSWAP RBP/EBP/R13/R13D
-ce: BSWAP RSI/ESI/R14/R14D
-cf: BSWAP RDI/EDI/R15/R15D
-# 0x0f 0xd0-0xdf
-d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
-d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
-d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
-d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
-d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
-d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
-d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
-d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
-d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
-da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
-dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
-dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
-de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
-e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
-e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
-e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
-e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
-e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
-e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
-e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
-e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
-ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
-ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
-ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
-ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xf0-0xff
-f0: vlddqu Vx,Mx (F2)
-f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
-f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
-f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
-f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
-f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
-f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
-f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
-f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
-f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
-fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
-fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
-fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
-fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
-fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff: UD0
-EndTable
-
-Table: 3-byte opcode 1 (0x0f 0x38)
-Referrer: 3-byte escape 1
-AVXcode: 2
-# 0x0f 0x38 0x00-0x0f
-00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
-01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
-02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
-03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
-04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
-05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
-06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
-07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
-08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
-09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
-0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
-0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
-0c: vpermilps Vx,Hx,Wx (66),(v)
-0d: vpermilpd Vx,Hx,Wx (66),(v)
-0e: vtestps Vx,Wx (66),(v)
-0f: vtestpd Vx,Wx (66),(v)
-# 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
-11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
-12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
-13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
-14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
-15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
-16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
-17: vptest Vx,Wx (66)
-18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
-1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
-1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
-1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
-1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
-1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f: vpabsq Vx,Wx (66),(ev)
-# 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
-21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
-24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
-26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
-27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
-28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
-2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
-2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
-2e: vmaskmovps Mx,Hx,Vx (66),(v)
-2f: vmaskmovpd Mx,Hx,Vx (66),(v)
-# 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
-31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
-34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
-36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
-37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
-39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
-3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
-3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
-3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
-3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
-41: vphminposuw Vdq,Wdq (66),(v1)
-42: vgetexpps/d Vx,Wx (66),(ev)
-43: vgetexpss/d Vx,Hx,Wx (66),(ev)
-44: vplzcntd/q Vx,Wx (66),(ev)
-45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
-47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
-4c: vrcp14ps/d Vpd,Wpd (66),(ev)
-4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
-4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
-4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-# Skip 0x50-0x57
-58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
-5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
-5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x63
-64: vpblendmd/q Vx,Hx,Wx (66),(ev)
-65: vblendmps/d Vx,Hx,Wx (66),(ev)
-66: vpblendmb/w Vx,Hx,Wx (66),(ev)
-# Skip 0x67-0x74
-75: vpermi2b/w Vx,Hx,Wx (66),(ev)
-76: vpermi2d/q Vx,Hx,Wx (66),(ev)
-77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
-78: vpbroadcastb Vx,Wx (66),(v)
-79: vpbroadcastw Vx,Wx (66),(v)
-7a: vpbroadcastb Vx,Rv (66),(ev)
-7b: vpbroadcastw Vx,Rv (66),(ev)
-7c: vpbroadcastd/q Vx,Rv (66),(ev)
-7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
-7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
-7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
-80: INVEPT Gy,Mdq (66)
-81: INVVPID Gy,Mdq (66)
-82: INVPCID Gy,Mdq (66)
-83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
-88: vexpandps/d Vpd,Wpd (66),(ev)
-89: vpexpandd/q Vx,Wx (66),(ev)
-8a: vcompressps/d Wx,Vx (66),(ev)
-8b: vpcompressd/q Wx,Vx (66),(ev)
-8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
-8d: vpermb/w Vx,Hx,Wx (66),(ev)
-8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
-# 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
-91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
-92: vgatherdps/d Vx,Hx,Wx (66),(v)
-93: vgatherqps/d Vx,Hx,Wx (66),(v)
-94:
-95:
-96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
-97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
-98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
-99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
-9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
-9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-a0: vpscatterdd/q Wx,Vx (66),(ev)
-a1: vpscatterqd/q Wx,Vx (66),(ev)
-a2: vscatterdps/d Wx,Vx (66),(ev)
-a3: vscatterqps/d Wx,Vx (66),(ev)
-a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
-a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
-a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
-a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
-ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
-af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
-b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
-b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
-b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
-b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
-b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
-bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
-bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
-bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-# 0x0f 0x38 0xc0-0xff
-c4: vpconflictd/q Vx,Wx (66),(ev)
-c6: Grp18 (1A)
-c7: Grp19 (1A)
-c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
-c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
-cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
-cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
-cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
-db: VAESIMC Vdq,Wdq (66),(v1)
-dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
-f2: ANDN Gy,By,Ey (v)
-f3: Grp17 (1A)
-f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
-f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
-EndTable
-
-Table: 3-byte opcode 2 (0x0f 0x3a)
-Referrer: 3-byte escape 2
-AVXcode: 3
-# 0x0f 0x3a 0x00-0xff
-00: vpermq Vqq,Wqq,Ib (66),(v)
-01: vpermpd Vqq,Wqq,Ib (66),(v)
-02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
-04: vpermilps Vx,Wx,Ib (66),(v)
-05: vpermilpd Vx,Wx,Ib (66),(v)
-06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
-07:
-08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
-09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
-0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
-0c: vblendps Vx,Hx,Wx,Ib (66)
-0d: vblendpd Vx,Hx,Wx,Ib (66)
-0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
-0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
-14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
-15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
-16: vpextrd/q Ey,Vdq,Ib (66),(v1)
-17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-1d: vcvtps2ph Wx,Vx,Ib (66),(v)
-1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
-1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
-20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
-21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
-22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
-26: vgetmantps/d Vx,Wx,Ib (66),(ev)
-27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
-30: kshiftrb/w Vk,Uk,Ib (66),(v)
-31: kshiftrd/q Vk,Uk,Ib (66),(v)
-32: kshiftlb/w Vk,Uk,Ib (66),(v)
-33: kshiftld/q Vk,Uk,Ib (66),(v)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
-3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
-40: vdpps Vx,Hx,Wx,Ib (66)
-41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
-43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
-46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
-4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
-4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
-4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
-50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
-51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
-54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
-55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
-56: vreduceps/d Vx,Wx,Ib (66),(ev)
-57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
-60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
-61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
-62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
-63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
-66: vfpclassps/d Vk,Wx,Ib (66),(ev)
-67: vfpclassss/d Vk,Wx,Ib (66),(ev)
-cc: sha1rnds4 Vdq,Wdq,Ib
-df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
-f0: RORX Gy,Ey,Ib (F2),(v)
-EndTable
-
-GrpTable: Grp1
-0: ADD
-1: OR
-2: ADC
-3: SBB
-4: AND
-5: SUB
-6: XOR
-7: CMP
-EndTable
-
-GrpTable: Grp1A
-0: POP
-EndTable
-
-GrpTable: Grp2
-0: ROL
-1: ROR
-2: RCL
-3: RCR
-4: SHL/SAL
-5: SHR
-6:
-7: SAR
-EndTable
-
-GrpTable: Grp3_1
-0: TEST Eb,Ib
-1: TEST Eb,Ib
-2: NOT Eb
-3: NEG Eb
-4: MUL AL,Eb
-5: IMUL AL,Eb
-6: DIV AL,Eb
-7: IDIV AL,Eb
-EndTable
-
-GrpTable: Grp3_2
-0: TEST Ev,Iz
-1:
-2: NOT Ev
-3: NEG Ev
-4: MUL rAX,Ev
-5: IMUL rAX,Ev
-6: DIV rAX,Ev
-7: IDIV rAX,Ev
-EndTable
-
-GrpTable: Grp4
-0: INC Eb
-1: DEC Eb
-EndTable
-
-GrpTable: Grp5
-0: INC Ev
-1: DEC Ev
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-2: CALLN Ev (f64)
-3: CALLF Ep
-4: JMPN Ev (f64)
-5: JMPF Mp
-6: PUSH Ev (d64)
-7:
-EndTable
-
-GrpTable: Grp6
-0: SLDT Rv/Mw
-1: STR Rv/Mw
-2: LLDT Ew
-3: LTR Ew
-4: VERR Ew
-5: VERW Ew
-EndTable
-
-GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
-3: LIDT Ms
-4: SMSW Mw/Rv
-5: rdpkru (110),(11B) | wrpkru (111),(11B)
-6: LMSW Ew
-7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
-EndTable
-
-GrpTable: Grp8
-4: BT
-5: BTS
-6: BTR
-7: BTC
-EndTable
-
-GrpTable: Grp9
-1: CMPXCHG8B/16B Mq/Mdq
-3: xrstors
-4: xsavec
-5: xsaves
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
-EndTable
-
-GrpTable: Grp10
-# all are UD1
-0: UD1
-1: UD1
-2: UD1
-3: UD1
-4: UD1
-5: UD1
-6: UD1
-7: UD1
-EndTable
-
-# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
-GrpTable: Grp11A
-0: MOV Eb,Ib
-7: XABORT Ib (000),(11B)
-EndTable
-
-GrpTable: Grp11B
-0: MOV Eb,Iz
-7: XBEGIN Jz (000),(11B)
-EndTable
-
-GrpTable: Grp12
-2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
-4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
-6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp13
-0: vprord/q Hx,Wx,Ib (66),(ev)
-1: vprold/q Hx,Wx,Ib (66),(ev)
-2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
-6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp14
-2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
-3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
-6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
-7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp15
-0: fxsave | RDFSBASE Ry (F3),(11B)
-1: fxstor | RDGSBASE Ry (F3),(11B)
-2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
-3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
-4: XSAVE | ptwrite Ey (F3),(11B)
-5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
-7: clflush | clflushopt (66) | sfence (11B)
-EndTable
-
-GrpTable: Grp16
-0: prefetch NTA
-1: prefetch T0
-2: prefetch T1
-3: prefetch T2
-EndTable
-
-GrpTable: Grp17
-1: BLSR By,Ey (v)
-2: BLSMSK By,Ey (v)
-3: BLSI By,Ey (v)
-EndTable
-
-GrpTable: Grp18
-1: vgatherpf0dps/d Wx (66),(ev)
-2: vgatherpf1dps/d Wx (66),(ev)
-5: vscatterpf0dps/d Wx (66),(ev)
-6: vscatterpf1dps/d Wx (66),(ev)
-EndTable
-
-GrpTable: Grp19
-1: vgatherpf0qps/d Wx (66),(ev)
-2: vgatherpf1qps/d Wx (66),(ev)
-5: vscatterpf0qps/d Wx (66),(ev)
-6: vscatterpf1qps/d Wx (66),(ev)
-EndTable
-
-# AMD's Prefetch Group
-GrpTable: GrpP
-0: PREFETCH
-1: PREFETCHW
-EndTable
-
-GrpTable: GrpPDLK
-0: MONTMUL
-1: XSHA1
-2: XSHA2
-EndTable
-
-GrpTable: GrpRNG
-0: xstore-rng
-1: xcrypt-ecb
-2: xcrypt-cbc
-4: xcrypt-cfb
-5: xcrypt-ofb
-EndTable
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 825a6a3b03a1..9b56fb74bedf 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -9,10 +9,10 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/zalloc.h>
 
-#include "../perf.h"
 #include "session.h"
 #include "machine.h"
 #include "memswap.h"
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index bbeac4f66402..b80f29bfc7bb 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -14,6 +14,7 @@
 #include <sys/mman.h>
 #include <linux/stringify.h>
 
+#include "build-id.h"
 #include "util.h"
 #include "event.h"
 #include "debug.h"
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 9f0470ecbca9..55fb4b3b1157 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -9,6 +9,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include "debug.h"
 #include "llvm-utils.h"
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index bf3f3f4c4fe2..7878a0e3fa98 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -6,7 +6,7 @@
 #ifndef __LLVM_UTILS_H
 #define __LLVM_UTILS_H
 
-#include "debug.h"
+#include <stdbool.h>
 
 struct llvm_param {
 	/* Path of clang executable */
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index b1dd29a9d915..397447066033 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -9,6 +9,7 @@
 #include "compress.h"
 #include "util.h"
 #include "debug.h"
+#include <string.h>
 #include <unistd.h>
 
 #define BUFSIZE 8192
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 93483f1764d3..b4749d3eed08 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -3,13 +3,19 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include <stdlib.h>
 #include "callchain.h"
 #include "debug.h"
+#include "dso.h"
+#include "env.h"
 #include "event.h"
 #include "evsel.h"
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "mem-events.h"
 #include "srcline.h"
 #include "symbol.h"
 #include "sort.h"
@@ -30,6 +36,7 @@
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
 #include <linux/mman.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
@@ -2619,7 +2626,9 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+
+	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
 		return -1;
 
 	return machine->current_tid[cpu];
@@ -2629,6 +2638,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid)
 {
 	struct thread *thread;
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
 
 	if (cpu < 0)
 		return -EINVAL;
@@ -2636,14 +2646,14 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	if (!machine->current_tid) {
 		int i;
 
-		machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+		machine->current_tid = calloc(nr_cpus, sizeof(pid_t));
 		if (!machine->current_tid)
 			return -ENOMEM;
-		for (i = 0; i < MAX_NR_CPUS; i++)
+		for (i = 0; i < nr_cpus; i++)
 			machine->current_tid[i] = -1;
 	}
 
-	if (cpu >= MAX_NR_CPUS) {
+	if (cpu >= nr_cpus) {
 		pr_err("Requested CPU %d too large. ", cpu);
 		pr_err("Consider raising MAX_NR_CPUS\n");
 		return -EINVAL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 7d69119d0b5d..ffd391a925a6 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -5,12 +5,13 @@
 #include <sys/types.h>
 #include <linux/rbtree.h>
 #include "map_groups.h"
-#include "dso.h"
+#include "dsos.h"
 #include "event.h"
 #include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
+struct dso;
 struct evsel;
 struct perf_sample;
 struct symbol;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 27b7b102e4a2..5b83ed1ebbd6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -8,7 +8,9 @@
 #include <stdio.h>
 #include <unistd.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include "dso.h"
 #include "map.h"
+#include "map_symbol.h"
 #include "thread.h"
 #include "vdso.h"
 #include "build-id.h"
@@ -20,6 +22,7 @@
 #include "namespaces.h"
 #include "unwind.h"
 #include "srccode.h"
+#include "ui/ui.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
 static void __maps__insert_name(struct maps *maps, struct map *map);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 42c3e5a229d2..3d391583f2ae 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -8,10 +8,10 @@
 #include <unistd.h>
 #include <api/fs/fs.h>
 #include <linux/kernel.h>
+#include "map_symbol.h"
 #include "mem-events.h"
 #include "debug.h"
 #include "symbol.h"
-#include "sort.h"
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index a889ec2fa9f5..f1389bdae7bf 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -6,6 +6,8 @@
 #include <stdint.h>
 #include <stdio.h>
 #include <linux/types.h>
+#include <linux/refcount.h>
+#include <linux/perf_event.h>
 #include "stat.h"
 
 struct perf_mem_event {
@@ -16,6 +18,13 @@ struct perf_mem_event {
 	const char	*sysfs_name;
 };
 
+struct mem_info {
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
+};
+
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index 14fb9e72aeeb..797d86a1ab09 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -1,8 +1,10 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitmap.h>
+#include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include "debug.h"
+#include "env.h"
 #include "mem2node.h"
 
 struct phys_entry {
diff --git a/tools/perf/util/mem2node.h b/tools/perf/util/mem2node.h
index 59c4752a2181..8dfa2b58d0cd 100644
--- a/tools/perf/util/mem2node.h
+++ b/tools/perf/util/mem2node.h
@@ -2,8 +2,9 @@
 #define __MEM2NODE_H
 
 #include <linux/rbtree.h>
-#include "env.h"
+#include <linux/types.h>
 
+struct perf_env;
 struct phys_entry;
 
 struct mem2node {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index aaf55444f81b..a7c0424dbda3 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -6,6 +6,7 @@
 /* Manage metrics and groups of metrics from JSON files */
 
 #include "metricgroup.h"
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "strbuf.h"
@@ -18,6 +19,7 @@
 #include "strlist.h"
 #include <assert.h>
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
 
@@ -85,59 +87,64 @@ struct egroup {
 	const char **ids;
 	const char *metric_name;
 	const char *metric_expr;
+	const char *metric_unit;
 };
 
-static bool record_evsel(int *ind, struct evsel **start,
-			 int idnum,
-			 struct evsel **metric_events,
-			 struct evsel *ev)
-{
-	metric_events[*ind] = ev;
-	if (*ind == 0)
-		*start = ev;
-	if (++*ind == idnum) {
-		metric_events[*ind] = NULL;
-		return true;
-	}
-	return false;
-}
-
 static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 				      const char **ids,
 				      int idnum,
 				      struct evsel **metric_events)
 {
-	struct evsel *ev, *start = NULL;
-	int ind = 0;
+	struct evsel *ev;
+	int i = 0;
+	bool leader_found;
 
 	evlist__for_each_entry (perf_evlist, ev) {
-		if (ev->collect_stat)
-			continue;
-		if (!strcmp(ev->name, ids[ind])) {
-			if (record_evsel(&ind, &start, idnum,
-					 metric_events, ev))
-				return start;
+		if (!strcmp(ev->name, ids[i])) {
+			if (!metric_events[i])
+				metric_events[i] = ev;
 		} else {
-			/*
-			 * We saw some other event that is not
-			 * in our list of events. Discard
-			 * the whole match and start again.
-			 */
-			ind = 0;
-			start = NULL;
-			if (!strcmp(ev->name, ids[ind])) {
-				if (record_evsel(&ind, &start, idnum,
-						 metric_events, ev))
-					return start;
+			if (++i == idnum) {
+				/* Discard the whole match and start again */
+				i = 0;
+				memset(metric_events, 0,
+				       sizeof(struct evsel *) * idnum);
+				continue;
+			}
+
+			if (!strcmp(ev->name, ids[i]))
+				metric_events[i] = ev;
+			else {
+				/* Discard the whole match and start again */
+				i = 0;
+				memset(metric_events, 0,
+				       sizeof(struct evsel *) * idnum);
+				continue;
 			}
 		}
 	}
-	/*
-	 * This can happen when an alias expands to multiple
-	 * events, like for uncore events.
-	 * We don't support this case for now.
-	 */
-	return NULL;
+
+	if (i != idnum - 1) {
+		/* Not whole match */
+		return NULL;
+	}
+
+	metric_events[idnum] = NULL;
+
+	for (i = 0; i < idnum; i++) {
+		leader_found = false;
+		evlist__for_each_entry(perf_evlist, ev) {
+			if (!leader_found && (ev == metric_events[i]))
+				leader_found = true;
+
+			if (leader_found &&
+			    !strcmp(ev->name, metric_events[i]->name)) {
+				ev->metric_leader = metric_events[i];
+			}
+		}
+	}
+
+	return metric_events[0];
 }
 
 static int metricgroup__setup_events(struct list_head *groups,
@@ -180,6 +187,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 		}
 		expr->metric_expr = eg->metric_expr;
 		expr->metric_name = eg->metric_name;
+		expr->metric_unit = eg->metric_unit;
 		expr->metric_events = metric_events;
 		list_add(&expr->nd, &me->head);
 	}
@@ -451,6 +459,7 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			eg->idnum = idnum;
 			eg->metric_name = pe->metric_name;
 			eg->metric_expr = pe->metric_expr;
+			eg->metric_unit = pe->unit;
 			list_add_tail(&eg->nd, group_list);
 			ret = 0;
 		}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index e5092f6404ae..475c7f912864 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -20,6 +20,7 @@ struct metric_expr {
 	struct list_head nd;
 	const char *metric_expr;
 	const char *metric_name;
+	const char *metric_unit;
 	struct evsel **metric_events;
 };
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 5f3532e51ec9..33c5b5495482 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,12 +10,16 @@
 #include <inttypes.h>
 #include <asm/bug.h>
 #include <linux/zalloc.h>
+#include <stdlib.h>
+#include <string.h>
 #ifdef HAVE_LIBNUMA_SUPPORT
 #include <numaif.h>
 #endif
+#include "cpumap.h"
 #include "debug.h"
 #include "event.h"
 #include "mmap.h"
+#include "../perf.h"
 #include "util.h" /* page_size */
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 274ce389cd84..3857a49e8f96 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/ring_buffer.h>
 #include <stdbool.h>
+#include <pthread.h> // for cpu_set_t
 #ifdef HAVE_AIO_SUPPORT
 #include <aio.h>
 #endif
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bb5f34b7ab44..359db2b1fcef 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -8,6 +8,7 @@
 #include "session.h"
 #include "asm/bug.h"
 #include "debug.h"
+#include "ui/progress.h"
 
 #define pr_N(n, fmt, ...) \
 	eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 4ed20c833d44..bb4aa88c50a8 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
 #include "util/debug.h"
+#include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
 #include <stdlib.h>
+#include <string.h>
 
 #define BRANCH_OPT(n, m) \
 	{ .name = n, .mode = (m) }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9101568946d2..5ec21d21113c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,16 +10,16 @@
 #include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
-#include "../perf.h"
+#include "build-id.h"
 #include "evlist.h"
 #include "evsel.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include <subcmd/exec-cmd.h>
 #include "string2.h"
 #include "strlist.h"
 #include "symbol.h"
-#include "cache.h"
 #include "header.h"
 #include "bpf-loader.h"
 #include "debug.h"
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index ca56ba2dd3da..caed0336429f 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,11 +11,12 @@
  *
  * which is what it's designed for.
  */
-#include "cache.h"
 #include "path.h"
+#include "cache.h"
 #include <linux/kernel.h>
 #include <limits.h>
 #include <stdio.h>
+#include <string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <dirent.h>
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
index f014f905df50..083429b7efa3 100644
--- a/tools/perf/util/path.h
+++ b/tools/perf/util/path.h
@@ -2,6 +2,9 @@
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
+#include <stddef.h>
+#include <stdbool.h>
+
 struct dirent;
 
 int path__join(char *bf, size_t size, const char *path1, const char *path2);
diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c
index 4f3aa8d99ef4..e635c594f773 100644
--- a/tools/perf/util/perf-hooks.c
+++ b/tools/perf/util/perf-hooks.c
@@ -8,6 +8,7 @@
 
 #include <errno.h>
 #include <stdlib.h>
+#include <string.h>
 #include <setjmp.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9807be6f09bb..fb597fa94234 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <linux/compiler.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
+#include <subcmd/pager.h>
 #include <sys/types.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -22,8 +23,8 @@
 #include "cpumap.h"
 #include "header.h"
 #include "pmu-events/pmu-events.h"
-#include "cache.h"
 #include "string2.h"
+#include "strbuf.h"
 
 struct perf_pmu_format {
 	char *name;
@@ -101,7 +102,7 @@ static int pmu_format(const char *name, struct list_head *format)
 	return 0;
 }
 
-static int convert_scale(const char *scale, char **end, double *sval)
+int perf_pmu__convert_scale(const char *scale, char **end, double *sval)
 {
 	char *lc;
 	int ret = 0;
@@ -164,7 +165,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	else
 		scale[sret] = '\0';
 
-	ret = convert_scale(scale, NULL, &alias->scale);
+	ret = perf_pmu__convert_scale(scale, NULL, &alias->scale);
 error:
 	close(fd);
 	return ret;
@@ -372,7 +373,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				desc ? strdup(desc) : NULL;
 	alias->topic = topic ? strdup(topic) : NULL;
 	if (unit) {
-		if (convert_scale(unit, &unit, &alias->scale) < 0)
+		if (perf_pmu__convert_scale(unit, &unit, &alias->scale) < 0)
 			return -1;
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 3f8b79b1dd85..f36ade6df76d 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -96,4 +96,6 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 
+int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 8394d48f8b32..b8e0967c5c21 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -19,17 +19,17 @@
 #include <limits.h>
 #include <elf.h>
 
+#include "build-id.h"
 #include "event.h"
 #include "namespaces.h"
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
-#include "cache.h"
+#include "dso.h"
 #include "color.h"
 #include "map.h"
 #include "map_groups.h"
 #include "symbol.h"
-#include "thread.h"
 #include <api/fs/fs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
@@ -37,7 +37,9 @@
 #include "probe-file.h"
 #include "session.h"
 #include "string2.h"
+#include "strbuf.h"
 
+#include <subcmd/pager.h>
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5b4d49382932..d13db55a2feb 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -16,10 +16,10 @@
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
-#include "cache.h"
+#include "dso.h"
 #include "color.h"
 #include "symbol.h"
-#include "thread.h"
+#include "strbuf.h"
 #include <api/fs/tracing_path.h>
 #include "probe-event.h"
 #include "probe-file.h"
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 025fc4491993..505905fc21c5 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -24,6 +24,7 @@
 #include "dso.h"
 #include "debug.h"
 #include "intlist.h"
+#include "strbuf.h"
 #include "strlist.h"
 #include "symbol.h"
 #include "probe-finder.h"
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index 28de8a4c2ce8..80ff41fc45be 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <stdlib.h>
+#include <string.h>
 
 struct pstack {
 	unsigned short	top;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 11479a7ad1c7..07ca4535e6f7 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -5,6 +5,8 @@
 #include <poll.h>
 #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"
@@ -12,8 +14,10 @@
 #include "cpumap.h"
 #include "print_binary.h"
 #include "thread_map.h"
+#include "trace-event.h"
 #include "mmap.h"
 #include "util.h"
+#include "../perf-sys.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 574507d46c98..286fe816c0f3 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -1,15 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "cpumap.h"
 #include "parse-events.h"
 #include <errno.h>
+#include <limits.h>
+#include <stdlib.h>
 #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"
 
 typedef void (*setup_probe_fn_t)(struct evsel *evsel);
 
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 4f6c1465998f..24a99909d8b3 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -157,7 +157,7 @@
 #include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "thread.h"
+#include "tool.h"
 #include "debug.h"
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index d311c81464e5..4d9593e331ea 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -23,10 +23,8 @@
 
 #include "debug.h"
 #include "util.h"
-#include "auxtrace.h"
 #include "session.h"
 #include "evlist.h"
-#include "config.h"
 #include "color.h"
 #include "sample-raw.h"
 #include "s390-cpumcf-kernel.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 01ebf10b8bf4..15961854ba67 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,8 +34,8 @@
 #include <EXTERN.h>
 #include <perl.h>
 
-#include "../../perf.h"
 #include "../callchain.h"
+#include "../dso.h"
 #include "../machine.h"
 #include "../map.h"
 #include "../symbol.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 78c8bc9380bd..666a56e88d8e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -31,9 +31,10 @@
 #include <linux/compiler.h>
 #include <linux/time64.h>
 
-#include "../../perf.h"
+#include "../build-id.h"
 #include "../counts.h"
 #include "../debug.h"
+#include "../dso.h"
 #include "../callchain.h"
 #include "../evsel.h"
 #include "../util.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7350b0dfbc1e..e9e4a04f15db 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -4,7 +4,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
-#include <traceevent/event-parse.h>
 #include <api/fs/fs.h>
 
 #include <byteswap.h>
@@ -13,6 +12,9 @@
 #include <sys/mman.h>
 #include <perf/cpumap.h>
 
+#include "map_symbol.h"
+#include "branch.h"
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "memswap.h"
@@ -20,7 +22,6 @@
 #include "symbol.h"
 #include "session.h"
 #include "tool.h"
-#include "sort.h"
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
@@ -30,6 +31,8 @@
 #include "sample-raw.h"
 #include "stat.h"
 #include "util.h"
+#include "ui/progress.h"
+#include "../perf.h"
 #include "arch/common.h"
 
 #ifdef HAVE_ZSTD_SUPPORT
@@ -2292,6 +2295,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 {
 	int i, err = -1;
 	struct perf_cpu_map *map;
+	int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2316,7 +2320,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	for (i = 0; i < map->nr; i++) {
 		int cpu = map->map[i];
 
-		if (cpu >= MAX_NR_CPUS) {
+		if (cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu);
 			goto out_delete_map;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 83eb3fa6f941..a2308eb77681 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,14 +2,19 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include <stdlib.h>
 #include <linux/mman.h>
 #include <linux/time64.h>
+#include "debug.h"
+#include "dso.h"
 #include "sort.h"
 #include "hist.h"
 #include "cacheline.h"
 #include "comm.h"
 #include "map.h"
 #include "symbol.h"
+#include "map_symbol.h"
+#include "branch.h"
 #include "thread.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -21,6 +26,7 @@
 #include "annotate.h"
 #include "time-utils.h"
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -707,7 +713,8 @@ static char *get_trace_output(struct hist_entry *he)
 		tep_print_fields(&seq, he->raw_data, he->raw_size,
 				 evsel->tp_format);
 	} else {
-		tep_event_info(&seq, evsel->tp_format, &rec);
+		tep_print_event(evsel->tp_format->tep,
+				&seq, &rec, "%s", TEP_PRINT_INFO);
 	}
 	/*
 	 * Trim the buffer, it starts at 4KB and we're not going to
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3d7cef73924c..7b93f34ac1f4 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -9,7 +9,6 @@
 #include "symbol_conf.h"
 #include "callchain.h"
 #include "values.h"
-
 #include "hist.h"
 
 struct option;
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 1461dac2322d..ed3b0ac2f785 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -1,3 +1,4 @@
+#include <stdlib.h>
 #include <stdio.h>
 #include <inttypes.h>
 #include <linux/string.h>
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2ed5e0066c70..70c87fdb2a43 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -31,6 +31,8 @@ struct saved_value {
 	int cpu;
 	struct runtime_stat *stat;
 	struct stats stats;
+	u64 metric_total;
+	int metric_other;
 };
 
 static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
@@ -212,6 +214,7 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 {
 	int ctx = evsel_context(counter);
 	u64 count_ns = count;
+	struct saved_value *v;
 
 	count *= counter->scale;
 
@@ -266,9 +269,15 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 		update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
 
 	if (counter->collect_stat) {
-		struct saved_value *v = saved_value_lookup(counter, cpu, true,
-							   STAT_NONE, 0, st);
+		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
 		update_stats(&v->stats, count);
+		if (counter->metric_leader)
+			v->metric_total += count;
+	} else if (counter->metric_leader) {
+		v = saved_value_lookup(counter->metric_leader,
+				       cpu, true, STAT_NONE, 0, st);
+		v->metric_total += count;
+		v->metric_other++;
 	}
 }
 
@@ -715,6 +724,7 @@ static void generic_metric(struct perf_stat_config *config,
 			   struct evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
+			   const char *metric_unit,
 			   double avg,
 			   int cpu,
 			   struct perf_stat_output_ctx *out,
@@ -722,17 +732,16 @@ static void generic_metric(struct perf_stat_config *config,
 {
 	print_metric_t print_metric = out->print_metric;
 	struct parse_ctx pctx;
-	double ratio;
+	double ratio, scale;
 	int i;
 	void *ctxp = out->ctx;
 	char *n, *pn;
 
 	expr__ctx_init(&pctx);
-	expr__add_id(&pctx, name, avg);
 	for (i = 0; metric_events[i]; i++) {
 		struct saved_value *v;
 		struct stats *stats;
-		double scale;
+		u64 metric_total = 0;
 
 		if (!strcmp(metric_events[i]->name, "duration_time")) {
 			stats = &walltime_nsecs_stats;
@@ -744,6 +753,9 @@ static void generic_metric(struct perf_stat_config *config,
 				break;
 			stats = &v->stats;
 			scale = 1.0;
+
+			if (v->metric_other)
+				metric_total = v->metric_total;
 		}
 
 		n = strdup(metric_events[i]->name);
@@ -757,21 +769,44 @@ static void generic_metric(struct perf_stat_config *config,
 		pn = strchr(n, ' ');
 		if (pn)
 			*pn = 0;
-		expr__add_id(&pctx, n, avg_stats(stats)*scale);
+
+		if (metric_total)
+			expr__add_id(&pctx, n, metric_total);
+		else
+			expr__add_id(&pctx, n, avg_stats(stats)*scale);
 	}
+
+	expr__add_id(&pctx, name, avg);
+
 	if (!metric_events[i]) {
 		const char *p = metric_expr;
 
-		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(config, ctxp, NULL, "%8.1f",
-				metric_name ?
-				metric_name :
-				out->force_header ?  name : "",
-				ratio);
-		else
+		if (expr__parse(&ratio, &pctx, &p) == 0) {
+			char *unit;
+			char metric_bf[64];
+
+			if (metric_unit && metric_name) {
+				if (perf_pmu__convert_scale(metric_unit,
+					&unit, &scale) >= 0) {
+					ratio *= scale;
+				}
+
+				scnprintf(metric_bf, sizeof(metric_bf),
+					  "%s  %s", unit, metric_name);
+				print_metric(config, ctxp, NULL, "%8.1f",
+					     metric_bf, ratio);
+			} else {
+				print_metric(config, ctxp, NULL, "%8.1f",
+					metric_name ?
+					metric_name :
+					out->force_header ?  name : "",
+					ratio);
+			}
+		} else {
 			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
+		}
 	} else
 		print_metric(config, ctxp, NULL, NULL, "", 0);
 
@@ -992,7 +1027,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
-				evsel->metric_name, avg, cpu, out, st);
+				evsel->metric_name, NULL, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
 		char unit_buf[10];
@@ -1021,7 +1056,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				out->new_line(config, ctxp);
 			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
-					avg, cpu, out, st);
+					mexp->metric_unit, avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 66f8808e57d3..8f1ea27f976f 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -2,8 +2,12 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <math.h>
+#include <string.h>
 #include "counts.h"
+#include "debug.h"
+#include "header.h"
 #include "stat.h"
+#include "session.h"
 #include "target.h"
 #include "evlist.h"
 #include "evsel.h"
@@ -210,7 +214,7 @@ void perf_evlist__reset_stats(struct evlist *evlist)
 static void zero_per_pkg(struct evsel *counter)
 {
 	if (counter->per_pkg_mask)
-		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+		memset(counter->per_pkg_mask, 0, cpu__max_cpu());
 }
 
 static int check_per_pkg(struct evsel *counter,
@@ -229,7 +233,7 @@ static int check_per_pkg(struct evsel *counter,
 		return 0;
 
 	if (!mask) {
-		mask = zalloc(MAX_NR_CPUS);
+		mask = zalloc(cpu__max_cpu());
 		if (!mask)
 			return -ENOMEM;
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 2ce0dc887364..a64a37628f12 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,9 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "cache.h"
 #include "debug.h"
+#include "strbuf.h"
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <errno.h>
+#include <stdio.h>
 #include <stdlib.h>
+#include <unistd.h>
 
 /*
  * Used as the default ->buf value, so that people can always assume
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index bbdd87163285..582f4a69cd48 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -19,7 +19,7 @@
 #include <linux/zalloc.h>
 #include <perf/cpumap.h>
 
-#include "perf.h"
+#include "env.h"
 #include "svghelper.h"
 #include "cpumap.h"
 
@@ -696,7 +696,8 @@ struct topology {
 	int sib_thr_nr;
 };
 
-static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+static void scan_thread_topology(int *map, struct topology *t, int cpu,
+				 int *pos, int nr_cpus)
 {
 	int i;
 	int thr;
@@ -705,28 +706,24 @@ static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos
 		if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
 			continue;
 
-		for_each_set_bit(thr,
-				 cpumask_bits(&t->sib_thr[i]),
-				 MAX_NR_CPUS)
+		for_each_set_bit(thr, cpumask_bits(&t->sib_thr[i]), nr_cpus)
 			if (map[thr] == -1)
 				map[thr] = (*pos)++;
 	}
 }
 
-static void scan_core_topology(int *map, struct topology *t)
+static void scan_core_topology(int *map, struct topology *t, int nr_cpus)
 {
 	int pos = 0;
 	int i;
 	int cpu;
 
 	for (i = 0; i < t->sib_core_nr; i++)
-		for_each_set_bit(cpu,
-				 cpumask_bits(&t->sib_core[i]),
-				 MAX_NR_CPUS)
-			scan_thread_topology(map, t, cpu, &pos);
+		for_each_set_bit(cpu, cpumask_bits(&t->sib_core[i]), nr_cpus)
+			scan_thread_topology(map, t, cpu, &pos, nr_cpus);
 }
 
-static int str_to_bitmap(char *s, cpumask_t *b)
+static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 {
 	int i;
 	int ret = 0;
@@ -739,7 +736,7 @@ static int str_to_bitmap(char *s, cpumask_t *b)
 
 	for (i = 0; i < m->nr; i++) {
 		c = m->map[i];
-		if (c >= MAX_NR_CPUS) {
+		if (c >= nr_cpus) {
 			ret = -1;
 			break;
 		}
@@ -752,24 +749,29 @@ static int str_to_bitmap(char *s, cpumask_t *b)
 	return ret;
 }
 
-int svg_build_topology_map(char *sib_core, int sib_core_nr,
-			   char *sib_thr, int sib_thr_nr)
+int svg_build_topology_map(struct perf_env *env)
 {
-	int i;
+	int i, nr_cpus;
 	struct topology t;
+	char *sib_core, *sib_thr;
+
+	nr_cpus = min(env->nr_cpus_online, MAX_NR_CPUS);
+
+	t.sib_core_nr = env->nr_sibling_cores;
+	t.sib_thr_nr = env->nr_sibling_threads;
+	t.sib_core = calloc(env->nr_sibling_cores, sizeof(cpumask_t));
+	t.sib_thr = calloc(env->nr_sibling_threads, sizeof(cpumask_t));
 
-	t.sib_core_nr = sib_core_nr;
-	t.sib_thr_nr = sib_thr_nr;
-	t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
-	t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+	sib_core = env->sibling_cores;
+	sib_thr = env->sibling_threads;
 
 	if (!t.sib_core || !t.sib_thr) {
 		fprintf(stderr, "topology: no memory\n");
 		goto exit;
 	}
 
-	for (i = 0; i < sib_core_nr; i++) {
-		if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+	for (i = 0; i < env->nr_sibling_cores; i++) {
+		if (str_to_bitmap(sib_core, &t.sib_core[i], nr_cpus)) {
 			fprintf(stderr, "topology: can't parse siblings map\n");
 			goto exit;
 		}
@@ -777,8 +779,8 @@ int svg_build_topology_map(char *sib_core, int sib_core_nr,
 		sib_core += strlen(sib_core) + 1;
 	}
 
-	for (i = 0; i < sib_thr_nr; i++) {
-		if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+	for (i = 0; i < env->nr_sibling_threads; i++) {
+		if (str_to_bitmap(sib_thr, &t.sib_thr[i], nr_cpus)) {
 			fprintf(stderr, "topology: can't parse siblings map\n");
 			goto exit;
 		}
@@ -786,16 +788,16 @@ int svg_build_topology_map(char *sib_core, int sib_core_nr,
 		sib_thr += strlen(sib_thr) + 1;
 	}
 
-	topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+	topology_map = malloc(sizeof(int) * nr_cpus);
 	if (!topology_map) {
 		fprintf(stderr, "topology: no memory\n");
 		goto exit;
 	}
 
-	for (i = 0; i < MAX_NR_CPUS; i++)
+	for (i = 0; i < nr_cpus; i++)
 		topology_map[i] = -1;
 
-	scan_core_topology(topology_map, &t);
+	scan_core_topology(topology_map, &t, nr_cpus);
 
 	return 0;
 
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e55338d5c3bd..81823e8bae3e 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -4,6 +4,8 @@
 
 #include <linux/types.h>
 
+struct perf_env;
+
 void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
 void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
@@ -28,7 +30,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 void svg_interrupt(u64 start, int row, const char *backtrace);
 void svg_text(int Yslot, u64 start, const char *text);
 void svg_close(void);
-int svg_build_topology_map(char *sib_core, int sib_core_nr, char *sib_thr, int sib_thr_nr);
+int svg_build_topology_map(struct perf_env *env);
 
 extern int svg_page_width;
 extern u64 svg_highlight;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 7d504dc22108..9428639872a6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -10,6 +10,7 @@
 #include "map.h"
 #include "map_groups.h"
 #include "symbol.h"
+#include "symsrc.h"
 #include "demangle-java.h"
 #include "demangle-rust.h"
 #include "machine.h"
@@ -40,6 +41,12 @@
 
 typedef Elf64_Nhdr GElf_Nhdr;
 
+#ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS     0              /* For readability... */
+#define DMGL_PARAMS      (1 << 0)       /* Include function args */
+#define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
+#endif
+
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 3bc8b7e3300e..7e2813ec9498 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "dso.h"
 #include "symbol.h"
+#include "symsrc.h"
 #include "util.h"
 
 #include <errno.h>
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 035f2e75728c..765c75df2904 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -7,6 +7,7 @@
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/mman.h>
+#include <linux/string.h>
 #include <linux/time64.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -17,12 +18,16 @@
 #include "annotate.h"
 #include "build-id.h"
 #include "cap.h"
+#include "dso.h"
 #include "util.h"
 #include "debug.h"
 #include "event.h"
 #include "machine.h"
 #include "map.h"
 #include "symbol.h"
+#include "map_symbol.h"
+#include "mem-events.h"
+#include "symsrc.h"
 #include "strlist.h"
 #include "intlist.h"
 #include "namespaces.h"
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 183f630cb5f1..0b0c6b5b1899 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -3,13 +3,12 @@
 #define __PERF_SYMBOL 1
 
 #include <linux/types.h>
+#include <linux/refcount.h>
 #include <stdbool.h>
 #include <stdint.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
-#include "map_symbol.h"
-#include "branch.h"
 #include "path.h"
 #include "symbol_conf.h"
 
@@ -19,8 +18,7 @@
 #endif
 #include <elf.h>
 
-#include "dso.h"
-
+struct dso;
 struct map;
 struct map_groups;
 struct option;
@@ -40,15 +38,6 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 			     GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
-#ifndef DMGL_PARAMS
-#define DMGL_NO_OPTS     0              /* For readability... */
-#define DMGL_PARAMS      (1 << 0)       /* Include function args */
-#define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
-#endif
-
-#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
-#define DSO__NAME_KCORE		"[kernel.kcore]"
-
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)
@@ -116,21 +105,6 @@ struct ref_reloc_sym {
 	u64		unrelocated_addr;
 };
 
-struct branch_info {
-	struct addr_map_symbol from;
-	struct addr_map_symbol to;
-	struct branch_flags flags;
-	char			*srcline_from;
-	char			*srcline_to;
-};
-
-struct mem_info {
-	struct addr_map_symbol	iaddr;
-	struct addr_map_symbol	daddr;
-	union perf_mem_data_src	data_src;
-	refcount_t		refcnt;
-};
-
 struct block_info {
 	struct symbol		*sym;
 	u64			start;
@@ -156,37 +130,6 @@ struct addr_location {
 	s32	      socket;
 };
 
-struct symsrc {
-	char *name;
-	int fd;
-	enum dso_binary_type type;
-
-#ifdef HAVE_LIBELF_SUPPORT
-	Elf *elf;
-	GElf_Ehdr ehdr;
-
-	Elf_Scn *opdsec;
-	size_t opdidx;
-	GElf_Shdr opdshdr;
-
-	Elf_Scn *symtab;
-	GElf_Shdr symshdr;
-
-	Elf_Scn *dynsym;
-	size_t dynsym_idx;
-	GElf_Shdr dynshdr;
-
-	bool adjust_symbols;
-	bool is_64_bit;
-#endif
-};
-
-void symsrc__destroy(struct symsrc *ss);
-int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
-		 enum dso_binary_type type);
-bool symsrc__has_symtab(struct symsrc *ss);
-bool symsrc__possibly_runtime(struct symsrc *ss);
-
 int dso__load(struct dso *dso, struct map *map);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated);
@@ -240,6 +183,8 @@ bool symbol__restricted_filename(const char *filename,
 int symbol__config_symfs(const struct option *opt __maybe_unused,
 			 const char *dir, int unset __maybe_unused);
 
+struct symsrc;
+
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule);
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 02e89b02c2ce..35c936ce33ef 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -3,6 +3,7 @@
 #include <inttypes.h>
 #include <stdio.h>
 
+#include "dso.h"
 #include "map.h"
 #include "symbol.h"
 
diff --git a/tools/perf/util/symsrc.h b/tools/perf/util/symsrc.h
new file mode 100644
index 000000000000..2665b4bde751
--- /dev/null
+++ b/tools/perf/util/symsrc.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYMSRC_
+#define __PERF_SYMSRC_ 1
+
+#include <stdbool.h>
+#include <stddef.h>
+#include "dso.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+#include <libelf.h>
+#include <gelf.h>
+#endif
+#include <elf.h>
+
+struct symsrc {
+	char		     *name;
+	int		     fd;
+	enum dso_binary_type type;
+
+#ifdef HAVE_LIBELF_SUPPORT
+	Elf		     *elf;
+	GElf_Ehdr	     ehdr;
+
+	Elf_Scn		     *opdsec;
+	size_t		     opdidx;
+	GElf_Shdr	     opdshdr;
+
+	Elf_Scn		     *symtab;
+	GElf_Shdr	     symshdr;
+
+	Elf_Scn		     *dynsym;
+	size_t		     dynsym_idx;
+	GElf_Shdr	     dynshdr;
+
+	bool		     adjust_symbols;
+	bool		     is_64_bit;
+#endif
+};
+
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type);
+void symsrc__destroy(struct symsrc *ss);
+
+bool symsrc__has_symtab(struct symsrc *ss);
+bool symsrc__possibly_runtime(struct symsrc *ss);
+
+#endif /* __PERF_SYMSRC_ */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3adc65480349..565f7aef7e6c 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -10,8 +10,11 @@
 #include "debug.h"
 
 #include <pwd.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
 
 enum target_errno target__validate(struct target *target)
 {
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 15134ac9b8f1..cd8a948d03ec 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -10,6 +10,7 @@
 #include <linux/zalloc.h>
 #include <errno.h>
 #include <stdlib.h>
+#include <string.h>
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index dbcb9cfb0f2f..b64e9e049636 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../perf.h"
 #include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
+#include "dso.h"
 #include "session.h"
 #include "thread.h"
 #include "thread-stack.h"
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index c2abc259b51d..9796a2e43f67 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -10,7 +10,6 @@
 #include <math.h>
 #include <linux/ctype.h>
 
-#include "perf.h"
 #include "debug.h"
 #include "time-utils.h"
 #include "session.h"
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 72a42ea1d513..4f42988eb2f7 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -3,6 +3,7 @@
 #define _TIME_UTILS_H_
 
 #include <stddef.h>
+#include <time.h>
 #include <linux/types.h>
 
 struct perf_time_interval {
@@ -34,4 +35,12 @@ int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz);
 
 int fetch_current_timestamp(char *buf, size_t sz);
 
+static inline unsigned long long rdclock(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
+}
+
 #endif
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index e5b690cf2898..51fb574998bb 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -12,6 +12,7 @@
 #include "parse-events.h"
 #include "symbol.h"
 #include "top.h"
+#include "../perf.h"
 #include <inttypes.h>
 
 #define SNPRINTF(buf, size, fmt, args...) \
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 7367433e767a..f117d4f4821e 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 "ordered-events.h"
 #include "record.h"
 #include <linux/types.h>
 #include <stddef.h>
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 2f8a0601a546..d63d542b2cde 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
-#include "../perf.h"
 #include "trace-event.h"
 #include <api/fs/tracing_path.h>
 #include "evsel.h"
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index b3982e1bb4c5..5d6bfc70b210 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -7,7 +7,6 @@
 #include <string.h>
 #include <errno.h>
 
-#include "../perf.h"
 #include "debug.h"
 #include "trace-event.h"
 
@@ -110,7 +109,7 @@ void event_format__fprintf(struct tep_event *event,
 	record.data = data;
 
 	trace_seq_init(&s);
-	tep_event_info(&s, event, &record);
+	tep_print_event(event->tep, &s, &record, "%s", TEP_PRINT_INFO);
 	trace_seq_do_fprintf(&s, fp);
 	trace_seq_destroy(&s);
 }
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 13c1cf60d1bc..b6c0db068be0 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 "../perf.h"
 #include "util.h"
 #include "trace-event.h"
 #include "debug.h"
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index dfd2640c763a..714581b0de65 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -10,7 +10,6 @@
 #include <string.h>
 #include <errno.h>
 
-#include "../perf.h"
 #include "debug.h"
 #include "trace-event.h"
 #include <linux/zalloc.h>
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 258d79071d81..2e158387b3d7 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,7 +3,6 @@
 #define _PERF_UTIL_TRACE_EVENT_H
 
 #include <traceevent/event-parse.h>
-#include <traceevent/trace-seq.h>
 #include "parse-events.h"
 
 struct machine;
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
index 88223bc7c82b..33e997f9ccc8 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -2,7 +2,6 @@
 #ifndef __TRIGGER_H_
 #define __TRIGGER_H_ 1
 
-#include "util/debug.h"
 #include "asm/bug.h"
 
 /*
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 28f71ca6ce1c..9ece188ae48a 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -5,6 +5,7 @@
 #include <inttypes.h>
 #include <errno.h>
 #include "debug.h"
+#include "dso.h"
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 6499b22b158b..a24fb57c9b2c 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "unwind.h"
+#include "dso.h"
 #include "map.h"
 #include "thread.h"
 #include "session.h"
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 44211e483fbf..32322a20a68b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../perf.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 #include "namespaces.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index c59154e2d124..b9823f414f10 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -2,6 +2,7 @@
 #include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <errno.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 7f427bab6c12..e5e6599603f4 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 
 #include "vdso.h"
+#include "dso.h"
 #include "util.h"
 #include "map.h"
 #include "symbol.h"
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 512ad7c09b13..59d456f716e9 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <fcntl.h>
 #include <stdio.h>
+#include <string.h>
 #include <unistd.h>
 #include <sys/stat.h>
 #include <sys/mman.h>