Merge tag 'v5.15' into next

Sync up with the mainline to get the latest APIs and DT bindings.

8 files changed, 592 insertions, 173 deletions

diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 0b7096847991..895f5fc23965 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -5,68 +5,178 @@
  * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
  */
 
+/*
+ * Use Py_ssize_t for '#' formats to avoid DeprecationWarning: PY_SSIZE_T_CLEAN
+ * will be required for '#' formats.
+ */
+#define PY_SSIZE_T_CLEAN
+
 #include <Python.h>
 #include "../../../util/trace-event.h"
+#include "../../../util/event.h"
+#include "../../../util/symbol.h"
+#include "../../../util/thread.h"
+#include "../../../util/map.h"
+#include "../../../util/maps.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/session.h"
+#include "../../../util/srcline.h"
+#include "../../../util/srccode.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyCapsule_GetPointer(arg1, arg2) \
   PyCObject_AsVoidPtr(arg1)
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+  PyString_FromStringAndSize((arg1), (arg2))
+#define _PyUnicode_AsUTF8(arg) \
+  PyString_AsString(arg)
 
 PyMODINIT_FUNC initperf_trace_context(void);
 #else
 #define _PyCapsule_GetPointer(arg1, arg2) \
   PyCapsule_GetPointer((arg1), (arg2))
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+  PyBytes_FromStringAndSize((arg1), (arg2))
+#define _PyUnicode_AsUTF8(arg) \
+  PyUnicode_AsUTF8(arg)
 
 PyMODINIT_FUNC PyInit_perf_trace_context(void);
 #endif
 
-static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args)
+static struct scripting_context *get_args(PyObject *args, const char *name, PyObject **arg2)
 {
-	static struct scripting_context *scripting_context;
+	int cnt = 1 + !!arg2;
 	PyObject *context;
-	int retval;
 
-	if (!PyArg_ParseTuple(args, "O", &context))
+	if (!PyArg_UnpackTuple(args, name, 1, cnt, &context, arg2))
 		return NULL;
 
-	scripting_context = _PyCapsule_GetPointer(context, NULL);
-	retval = common_pc(scripting_context);
+	return _PyCapsule_GetPointer(context, NULL);
+}
 
-	return Py_BuildValue("i", retval);
+static struct scripting_context *get_scripting_context(PyObject *args)
+{
+	return get_args(args, "context", NULL);
+}
+
+static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args)
+{
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
+
+	return Py_BuildValue("i", common_pc(c));
 }
 
 static PyObject *perf_trace_context_common_flags(PyObject *obj,
 						 PyObject *args)
 {
-	static struct scripting_context *scripting_context;
-	PyObject *context;
-	int retval;
+	struct scripting_context *c = get_scripting_context(args);
 
-	if (!PyArg_ParseTuple(args, "O", &context))
+	if (!c)
 		return NULL;
 
-	scripting_context = _PyCapsule_GetPointer(context, NULL);
-	retval = common_flags(scripting_context);
-
-	return Py_BuildValue("i", retval);
+	return Py_BuildValue("i", common_flags(c));
 }
 
 static PyObject *perf_trace_context_common_lock_depth(PyObject *obj,
 						      PyObject *args)
 {
-	static struct scripting_context *scripting_context;
-	PyObject *context;
-	int retval;
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
+
+	return Py_BuildValue("i", common_lock_depth(c));
+}
+
+static PyObject *perf_sample_insn(PyObject *obj, PyObject *args)
+{
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
 
-	if (!PyArg_ParseTuple(args, "O", &context))
+	if (c->sample->ip && !c->sample->insn_len &&
+	    c->al->thread->maps && c->al->thread->maps->machine)
+		script_fetch_insn(c->sample, c->al->thread, c->al->thread->maps->machine);
+
+	if (!c->sample->insn_len)
+		Py_RETURN_NONE; /* N.B. This is a return statement */
+
+	return _PyBytes_FromStringAndSize(c->sample->insn, c->sample->insn_len);
+}
+
+static PyObject *perf_set_itrace_options(PyObject *obj, PyObject *args)
+{
+	struct scripting_context *c;
+	const char *itrace_options;
+	int retval = -1;
+	PyObject *str;
+
+	c = get_args(args, "itrace_options", &str);
+	if (!c)
 		return NULL;
 
-	scripting_context = _PyCapsule_GetPointer(context, NULL);
-	retval = common_lock_depth(scripting_context);
+	if (!c->session || !c->session->itrace_synth_opts)
+		goto out;
+
+	if (c->session->itrace_synth_opts->set) {
+		retval = 1;
+		goto out;
+	}
 
+	itrace_options = _PyUnicode_AsUTF8(str);
+
+	retval = itrace_do_parse_synth_opts(c->session->itrace_synth_opts, itrace_options, 0);
+out:
 	return Py_BuildValue("i", retval);
 }
 
+static PyObject *perf_sample_src(PyObject *obj, PyObject *args, bool get_srccode)
+{
+	struct scripting_context *c = get_scripting_context(args);
+	unsigned int line = 0;
+	char *srcfile = NULL;
+	char *srccode = NULL;
+	PyObject *result;
+	struct map *map;
+	int len = 0;
+	u64 addr;
+
+	if (!c)
+		return NULL;
+
+	map = c->al->map;
+	addr = c->al->addr;
+
+	if (map && map->dso)
+		srcfile = get_srcline_split(map->dso, map__rip_2objdump(map, addr), &line);
+
+	if (get_srccode) {
+		if (srcfile)
+			srccode = find_sourceline(srcfile, line, &len);
+		result = Py_BuildValue("(sIs#)", srcfile, line, srccode, (Py_ssize_t)len);
+	} else {
+		result = Py_BuildValue("(sI)", srcfile, line);
+	}
+
+	free(srcfile);
+
+	return result;
+}
+
+static PyObject *perf_sample_srcline(PyObject *obj, PyObject *args)
+{
+	return perf_sample_src(obj, args, false);
+}
+
+static PyObject *perf_sample_srccode(PyObject *obj, PyObject *args)
+{
+	return perf_sample_src(obj, args, true);
+}
+
 static PyMethodDef ContextMethods[] = {
 	{ "common_pc", perf_trace_context_common_pc, METH_VARARGS,
 	  "Get the common preempt count event field value."},
@@ -74,6 +184,14 @@ static PyMethodDef ContextMethods[] = {
 	  "Get the common flags event field value."},
 	{ "common_lock_depth", perf_trace_context_common_lock_depth,
 	  METH_VARARGS,	"Get the common lock depth event field value."},
+	{ "perf_sample_insn", perf_sample_insn,
+	  METH_VARARGS,	"Get the machine code instruction."},
+	{ "perf_set_itrace_options", perf_set_itrace_options,
+	  METH_VARARGS,	"Set --itrace options."},
+	{ "perf_sample_srcline", perf_sample_srcline,
+	  METH_VARARGS,	"Get source file name and line number."},
+	{ "perf_sample_srccode", perf_sample_srccode,
+	  METH_VARARGS,	"Get source file name, line number and line."},
 	{ NULL, NULL, 0, NULL}
 };
 
@@ -96,6 +214,12 @@ PyMODINIT_FUNC PyInit_perf_trace_context(void)
 		NULL,			/* m_clear */
 		NULL,			/* m_free */
 	};
-	return PyModule_Create(&moduledef);
+	PyObject *mod;
+
+	mod = PyModule_Create(&moduledef);
+	/* Add perf_script_context to the module so it can be imported */
+	PyObject_SetAttrString(mod, "perf_script_context", Py_None);
+
+	return mod;
 }
 #endif
diff --git a/tools/perf/scripts/python/bin/intel-pt-events-record b/tools/perf/scripts/python/bin/intel-pt-events-record
index 10fe2b6977d4..6b9877cfe23e 100644
--- a/tools/perf/scripts/python/bin/intel-pt-events-record
+++ b/tools/perf/scripts/python/bin/intel-pt-events-record
@@ -1,8 +1,8 @@
 #!/bin/bash
 
 #
-# print Intel PT Power Events and PTWRITE. The intel_pt PMU event needs
-# to be specified with appropriate config terms.
+# print Intel PT Events including Power Events and PTWRITE. The intel_pt PMU
+# event needs to be specified with appropriate config terms.
 #
 if ! echo "$@" | grep -q intel_pt ; then
 	echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/"
diff --git a/tools/perf/scripts/python/bin/intel-pt-events-report b/tools/perf/scripts/python/bin/intel-pt-events-report
index 9a9c92fcd026..beeac3fde9db 100644
--- a/tools/perf/scripts/python/bin/intel-pt-events-report
+++ b/tools/perf/scripts/python/bin/intel-pt-events-report
@@ -1,3 +1,3 @@
 #!/bin/bash
-# description: print Intel PT Power Events and PTWRITE
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
\ No newline at end of file
+# description: print Intel PT Events including Power Events and PTWRITE
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
diff --git a/tools/perf/scripts/python/bin/stackcollapse-report b/tools/perf/scripts/python/bin/stackcollapse-report
index 356b9656393d..21a356bd27f6 100755
--- a/tools/perf/scripts/python/bin/stackcollapse-report
+++ b/tools/perf/scripts/python/bin/stackcollapse-report
@@ -1,3 +1,3 @@
 #!/bin/sh
 # description: produce callgraphs in short form for scripting use
-perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py -- "$@"
+perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py "$@"
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 711d4f9f5645..13f2d8a81610 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -113,6 +113,7 @@ import os
 import random
 import copy
 import math
+from libxed import LibXED
 
 pyside_version_1 = True
 if not "--pyside-version-1" in sys.argv:
@@ -4747,94 +4748,6 @@ class MainWindow(QMainWindow):
 		dialog = AboutDialog(self.glb, self)
 		dialog.exec_()
 
-# XED Disassembler
-
-class xed_state_t(Structure):
-
-	_fields_ = [
-		("mode", c_int),
-		("width", c_int)
-	]
-
-class XEDInstruction():
-
-	def __init__(self, libxed):
-		# Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
-		xedd_t = c_byte * 512
-		self.xedd = xedd_t()
-		self.xedp = addressof(self.xedd)
-		libxed.xed_decoded_inst_zero(self.xedp)
-		self.state = xed_state_t()
-		self.statep = addressof(self.state)
-		# Buffer for disassembled instruction text
-		self.buffer = create_string_buffer(256)
-		self.bufferp = addressof(self.buffer)
-
-class LibXED():
-
-	def __init__(self):
-		try:
-			self.libxed = CDLL("libxed.so")
-		except:
-			self.libxed = None
-		if not self.libxed:
-			self.libxed = CDLL("/usr/local/lib/libxed.so")
-
-		self.xed_tables_init = self.libxed.xed_tables_init
-		self.xed_tables_init.restype = None
-		self.xed_tables_init.argtypes = []
-
-		self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
-		self.xed_decoded_inst_zero.restype = None
-		self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
-
-		self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
-		self.xed_operand_values_set_mode.restype = None
-		self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
-
-		self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
-		self.xed_decoded_inst_zero_keep_mode.restype = None
-		self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
-
-		self.xed_decode = self.libxed.xed_decode
-		self.xed_decode.restype = c_int
-		self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
-
-		self.xed_format_context = self.libxed.xed_format_context
-		self.xed_format_context.restype = c_uint
-		self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
-
-		self.xed_tables_init()
-
-	def Instruction(self):
-		return XEDInstruction(self)
-
-	def SetMode(self, inst, mode):
-		if mode:
-			inst.state.mode = 4 # 32-bit
-			inst.state.width = 4 # 4 bytes
-		else:
-			inst.state.mode = 1 # 64-bit
-			inst.state.width = 8 # 8 bytes
-		self.xed_operand_values_set_mode(inst.xedp, inst.statep)
-
-	def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
-		self.xed_decoded_inst_zero_keep_mode(inst.xedp)
-		err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
-		if err:
-			return 0, ""
-		# Use AT&T mode (2), alternative is Intel (3)
-		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
-		if not ok:
-			return 0, ""
-		if sys.version_info[0] == 2:
-			result = inst.buffer.value
-		else:
-			result = inst.buffer.value.decode()
-		# Return instruction length and the disassembled instruction text
-		# For now, assume the length is in byte 166
-		return inst.xedd[166], result
-
 def TryOpen(file_name):
 	try:
 		return open(file_name, "rb")
diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py
index 65780013f745..b6af1dd5f816 100755
--- a/tools/perf/scripts/python/flamegraph.py
+++ b/tools/perf/scripts/python/flamegraph.py
@@ -13,6 +13,10 @@
 # Written by Andreas Gerstmayr <agerstmayr@redhat.com>
 # Flame Graphs invented by Brendan Gregg <bgregg@netflix.com>
 # Works in tandem with d3-flame-graph by Martin Spier <mspier@netflix.com>
+#
+# pylint: disable=missing-module-docstring
+# pylint: disable=missing-class-docstring
+# pylint: disable=missing-function-docstring
 
 from __future__ import print_function
 import sys
@@ -20,16 +24,19 @@ import os
 import io
 import argparse
 import json
+import subprocess
 
-
+# pylint: disable=too-few-public-methods
 class Node:
-    def __init__(self, name, libtype=""):
+    def __init__(self, name, libtype):
         self.name = name
+        # "root" | "kernel" | ""
+        # "" indicates user space
         self.libtype = libtype
         self.value = 0
         self.children = []
 
-    def toJSON(self):
+    def to_json(self):
         return {
             "n": self.name,
             "l": self.libtype,
@@ -41,7 +48,7 @@ class Node:
 class FlameGraphCLI:
     def __init__(self, args):
         self.args = args
-        self.stack = Node("root")
+        self.stack = Node("all", "root")
 
         if self.args.format == "html" and \
                 not os.path.isfile(self.args.template):
@@ -53,13 +60,21 @@ class FlameGraphCLI:
                   file=sys.stderr)
             sys.exit(1)
 
-    def find_or_create_node(self, node, name, dso):
-        libtype = "kernel" if dso == "[kernel.kallsyms]" else ""
-        if name is None:
-            name = "[unknown]"
+    @staticmethod
+    def get_libtype_from_dso(dso):
+        """
+        when kernel-debuginfo is installed,
+        dso points to /usr/lib/debug/lib/modules/*/vmlinux
+        """
+        if dso and (dso == "[kernel.kallsyms]" or dso.endswith("/vmlinux")):
+            return "kernel"
 
+        return ""
+
+    @staticmethod
+    def find_or_create_node(node, name, libtype):
         for child in node.children:
-            if child.name == name and child.libtype == libtype:
+            if child.name == name:
                 return child
 
         child = Node(name, libtype)
@@ -67,30 +82,65 @@ class FlameGraphCLI:
         return child
 
     def process_event(self, event):
-        node = self.find_or_create_node(self.stack, event["comm"], None)
+        pid = event.get("sample", {}).get("pid", 0)
+        # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
+        # for user-space processes; let's use pid for kernel or user-space distinction
+        if pid == 0:
+            comm = event["comm"]
+            libtype = "kernel"
+        else:
+            comm = "{} ({})".format(event["comm"], pid)
+            libtype = ""
+        node = self.find_or_create_node(self.stack, comm, libtype)
+
         if "callchain" in event:
-            for entry in reversed(event['callchain']):
-                node = self.find_or_create_node(
-                    node, entry.get("sym", {}).get("name"), event.get("dso"))
+            for entry in reversed(event["callchain"]):
+                name = entry.get("sym", {}).get("name", "[unknown]")
+                libtype = self.get_libtype_from_dso(entry.get("dso"))
+                node = self.find_or_create_node(node, name, libtype)
         else:
-            node = self.find_or_create_node(
-                node, entry.get("symbol"), event.get("dso"))
+            name = event.get("symbol", "[unknown]")
+            libtype = self.get_libtype_from_dso(event.get("dso"))
+            node = self.find_or_create_node(node, name, libtype)
         node.value += 1
 
+    def get_report_header(self):
+        if self.args.input == "-":
+            # when this script is invoked with "perf script flamegraph",
+            # no perf.data is created and we cannot read the header of it
+            return ""
+
+        try:
+            output = subprocess.check_output(["perf", "report", "--header-only"])
+            return output.decode("utf-8")
+        except Exception as err:  # pylint: disable=broad-except
+            print("Error reading report header: {}".format(err), file=sys.stderr)
+            return ""
+
     def trace_end(self):
-        json_str = json.dumps(self.stack, default=lambda x: x.toJSON())
+        stacks_json = json.dumps(self.stack, default=lambda x: x.to_json())
 
         if self.args.format == "html":
+            report_header = self.get_report_header()
+            options = {
+                "colorscheme": self.args.colorscheme,
+                "context": report_header
+            }
+            options_json = json.dumps(options)
+
             try:
-                with io.open(self.args.template, encoding="utf-8") as f:
-                    output_str = f.read().replace("/** @flamegraph_json **/",
-                                                  json_str)
-            except IOError as e:
-                print("Error reading template file: {}".format(e), file=sys.stderr)
+                with io.open(self.args.template, encoding="utf-8") as template:
+                    output_str = (
+                        template.read()
+                        .replace("/** @options_json **/", options_json)
+                        .replace("/** @flamegraph_json **/", stacks_json)
+                    )
+            except IOError as err:
+                print("Error reading template file: {}".format(err), file=sys.stderr)
                 sys.exit(1)
             output_fn = self.args.output or "flamegraph.html"
         else:
-            output_str = json_str
+            output_str = stacks_json
             output_fn = self.args.output or "stacks.json"
 
         if output_fn == "-":
@@ -101,8 +151,8 @@ class FlameGraphCLI:
             try:
                 with io.open(output_fn, "w", encoding="utf-8") as out:
                     out.write(output_str)
-            except IOError as e:
-                print("Error writing output file: {}".format(e), file=sys.stderr)
+            except IOError as err:
+                print("Error writing output file: {}".format(err), file=sys.stderr)
                 sys.exit(1)
 
 
@@ -115,12 +165,16 @@ if __name__ == "__main__":
                         help="output file name")
     parser.add_argument("--template",
                         default="/usr/share/d3-flame-graph/d3-flamegraph-base.html",
-                        help="path to flamegraph HTML template")
+                        help="path to flame graph HTML template")
+    parser.add_argument("--colorscheme",
+                        default="blue-green",
+                        help="flame graph color scheme",
+                        choices=["blue-green", "orange"])
     parser.add_argument("-i", "--input",
                         help=argparse.SUPPRESS)
 
-    args = parser.parse_args()
-    cli = FlameGraphCLI(args)
+    cli_args = parser.parse_args()
+    cli = FlameGraphCLI(cli_args)
 
     process_event = cli.process_event
     trace_end = cli.trace_end
diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py
index a73847c8f548..1d3a189a9a54 100644
--- a/tools/perf/scripts/python/intel-pt-events.py
+++ b/tools/perf/scripts/python/intel-pt-events.py
@@ -1,5 +1,6 @@
-# intel-pt-events.py: Print Intel PT Power Events and PTWRITE
-# Copyright (c) 2017, Intel Corporation.
+# SPDX-License-Identifier: GPL-2.0
+# intel-pt-events.py: Print Intel PT Events including Power Events and PTWRITE
+# Copyright (c) 2017-2021, Intel Corporation.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms and conditions of the GNU General Public License,
@@ -15,16 +16,82 @@ from __future__ import print_function
 import os
 import sys
 import struct
+import argparse
+
+from libxed import LibXED
+from ctypes import create_string_buffer, addressof
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
 
-# These perf imports are not used at present
-#from perf_trace_context import *
-#from Core import *
+from perf_trace_context import perf_set_itrace_options, \
+	perf_sample_insn, perf_sample_srccode
+
+try:
+	broken_pipe_exception = BrokenPipeError
+except:
+	broken_pipe_exception = IOError
+
+glb_switch_str		= None
+glb_switch_printed	= True
+glb_insn		= False
+glb_disassembler	= None
+glb_src			= False
+glb_source_file_name	= None
+glb_line_number		= None
+glb_dso			= None
+
+def get_optional_null(perf_dict, field):
+	if field in perf_dict:
+		return perf_dict[field]
+	return ""
+
+def get_optional_zero(perf_dict, field):
+	if field in perf_dict:
+		return perf_dict[field]
+	return 0
+
+def get_optional_bytes(perf_dict, field):
+	if field in perf_dict:
+		return perf_dict[field]
+	return bytes()
+
+def get_optional(perf_dict, field):
+	if field in perf_dict:
+		return perf_dict[field]
+	return "[unknown]"
+
+def get_offset(perf_dict, field):
+	if field in perf_dict:
+		return "+%#x" % perf_dict[field]
+	return ""
 
 def trace_begin():
-	print("Intel PT Power Events and PTWRITE")
+	ap = argparse.ArgumentParser(usage = "", add_help = False)
+	ap.add_argument("--insn-trace", action='store_true')
+	ap.add_argument("--src-trace", action='store_true')
+	global glb_args
+	global glb_insn
+	global glb_src
+	glb_args = ap.parse_args()
+	if glb_args.insn_trace:
+		print("Intel PT Instruction Trace")
+		itrace = "i0nsepwx"
+		glb_insn = True
+	elif glb_args.src_trace:
+		print("Intel PT Source Trace")
+		itrace = "i0nsepwx"
+		glb_insn = True
+		glb_src = True
+	else:
+		print("Intel PT Branch Trace, Power Events and PTWRITE")
+		itrace = "bepwx"
+	global glb_disassembler
+	try:
+		glb_disassembler = LibXED()
+	except:
+		glb_disassembler = None
+	perf_set_itrace_options(perf_script_context, itrace)
 
 def trace_end():
 	print("End")
@@ -77,58 +144,212 @@ def print_pwrx(raw_buf):
 	print("deepest cstate: %u last cstate: %u wake reason: %#x" %
 		(deepest_cstate, last_cstate, wake_reason), end=' ')
 
-def print_common_start(comm, sample, name):
+def print_psb(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	offset = data[1]
+	print("offset: %#x" % (offset), end=' ')
+
+def common_start_str(comm, sample):
 	ts = sample["time"]
 	cpu = sample["cpu"]
 	pid = sample["pid"]
 	tid = sample["tid"]
-	print("%16s %5u/%-5u [%03u] %9u.%09u %7s:" %
-		(comm, pid, tid, cpu, ts / 1000000000, ts %1000000000, name),
-		end=' ')
+	return "%16s %5u/%-5u [%03u] %9u.%09u  " % (comm, pid, tid, cpu, ts / 1000000000, ts %1000000000)
+
+def print_common_start(comm, sample, name):
+	flags_disp = get_optional_null(sample, "flags_disp")
+	# Unused fields:
+	# period      = sample["period"]
+	# phys_addr   = sample["phys_addr"]
+	# weight      = sample["weight"]
+	# transaction = sample["transaction"]
+	# cpumode     = get_optional_zero(sample, "cpumode")
+	print(common_start_str(comm, sample) + "%7s  %19s" % (name, flags_disp), end=' ')
+
+def print_instructions_start(comm, sample):
+	if "x" in get_optional_null(sample, "flags"):
+		print(common_start_str(comm, sample) + "x", end=' ')
+	else:
+		print(common_start_str(comm, sample), end='  ')
+
+def disassem(insn, ip):
+	inst = glb_disassembler.Instruction()
+	glb_disassembler.SetMode(inst, 0) # Assume 64-bit
+	buf = create_string_buffer(64)
+	buf.value = insn
+	return glb_disassembler.DisassembleOne(inst, addressof(buf), len(insn), ip)
+
+def print_common_ip(param_dict, sample, symbol, dso):
+	ip   = sample["ip"]
+	offs = get_offset(param_dict, "symoff")
+	if "cyc_cnt" in sample:
+		cyc_cnt = sample["cyc_cnt"]
+		insn_cnt = get_optional_zero(sample, "insn_cnt")
+		ipc_str = "  IPC: %#.2f (%u/%u)" % (insn_cnt / cyc_cnt, insn_cnt, cyc_cnt)
+	else:
+		ipc_str = ""
+	if glb_insn and glb_disassembler is not None:
+		insn = perf_sample_insn(perf_script_context)
+		if insn and len(insn):
+			cnt, text = disassem(insn, ip)
+			byte_str = ("%x" % ip).rjust(16)
+			if sys.version_info.major >= 3:
+				for k in range(cnt):
+					byte_str += " %02x" % insn[k]
+			else:
+				for k in xrange(cnt):
+					byte_str += " %02x" % ord(insn[k])
+			print("%-40s  %-30s" % (byte_str, text), end=' ')
+		print("%s%s (%s)" % (symbol, offs, dso), end=' ')
+	else:
+		print("%16x %s%s (%s)" % (ip, symbol, offs, dso), end=' ')
+	if "addr_correlates_sym" in sample:
+		addr   = sample["addr"]
+		dso    = get_optional(sample, "addr_dso")
+		symbol = get_optional(sample, "addr_symbol")
+		offs   = get_offset(sample, "addr_symoff")
+		print("=> %x %s%s (%s)%s" % (addr, symbol, offs, dso, ipc_str))
+	else:
+		print(ipc_str)
 
-def print_common_ip(sample, symbol, dso):
+def print_srccode(comm, param_dict, sample, symbol, dso, with_insn):
 	ip = sample["ip"]
-	print("%16x %s (%s)" % (ip, symbol, dso))
+	if symbol == "[unknown]":
+		start_str = common_start_str(comm, sample) + ("%x" % ip).rjust(16).ljust(40)
+	else:
+		offs = get_offset(param_dict, "symoff")
+		start_str = common_start_str(comm, sample) + (symbol + offs).ljust(40)
 
-def process_event(param_dict):
+	if with_insn and glb_insn and glb_disassembler is not None:
+		insn = perf_sample_insn(perf_script_context)
+		if insn and len(insn):
+			cnt, text = disassem(insn, ip)
+		start_str += text.ljust(30)
+
+	global glb_source_file_name
+	global glb_line_number
+	global glb_dso
+
+	source_file_name, line_number, source_line = perf_sample_srccode(perf_script_context)
+	if source_file_name:
+		if glb_line_number == line_number and glb_source_file_name == source_file_name:
+			src_str = ""
+		else:
+			if len(source_file_name) > 40:
+				src_file = ("..." + source_file_name[-37:]) + " "
+			else:
+				src_file = source_file_name.ljust(41)
+			if source_line is None:
+				src_str = src_file + str(line_number).rjust(4) + " <source not found>"
+			else:
+				src_str = src_file + str(line_number).rjust(4) + " " + source_line
+		glb_dso = None
+	elif dso == glb_dso:
+		src_str = ""
+	else:
+		src_str = dso
+		glb_dso = dso
+
+	glb_line_number = line_number
+	glb_source_file_name = source_file_name
+
+	print(start_str, src_str)
+
+def do_process_event(param_dict):
+	global glb_switch_printed
+	if not glb_switch_printed:
+		print(glb_switch_str)
+		glb_switch_printed = True
 	event_attr = param_dict["attr"]
-	sample	 = param_dict["sample"]
-	raw_buf	= param_dict["raw_buf"]
+	sample	   = param_dict["sample"]
+	raw_buf	   = param_dict["raw_buf"]
 	comm	   = param_dict["comm"]
 	name	   = param_dict["ev_name"]
+	# Unused fields:
+	# callchain  = param_dict["callchain"]
+	# brstack    = param_dict["brstack"]
+	# brstacksym = param_dict["brstacksym"]
 
 	# Symbol and dso info are not always resolved
-	if "dso" in param_dict:
-		dso = param_dict["dso"]
-	else:
-		dso = "[unknown]"
-
-	if "symbol" in param_dict:
-		symbol = param_dict["symbol"]
-	else:
-		symbol = "[unknown]"
+	dso    = get_optional(param_dict, "dso")
+	symbol = get_optional(param_dict, "symbol")
 
-	if name == "ptwrite":
+	if name[0:12] == "instructions":
+		if glb_src:
+			print_srccode(comm, param_dict, sample, symbol, dso, True)
+		else:
+			print_instructions_start(comm, sample)
+			print_common_ip(param_dict, sample, symbol, dso)
+	elif name[0:8] == "branches":
+		if glb_src:
+			print_srccode(comm, param_dict, sample, symbol, dso, False)
+		else:
+			print_common_start(comm, sample, name)
+			print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "ptwrite":
 		print_common_start(comm, sample, name)
 		print_ptwrite(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
 	elif name == "cbr":
 		print_common_start(comm, sample, name)
 		print_cbr(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
 	elif name == "mwait":
 		print_common_start(comm, sample, name)
 		print_mwait(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
 	elif name == "pwre":
 		print_common_start(comm, sample, name)
 		print_pwre(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
 	elif name == "exstop":
 		print_common_start(comm, sample, name)
 		print_exstop(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
 	elif name == "pwrx":
 		print_common_start(comm, sample, name)
 		print_pwrx(raw_buf)
-		print_common_ip(sample, symbol, dso)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "psb":
+		print_common_start(comm, sample, name)
+		print_psb(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	else:
+		print_common_start(comm, sample, name)
+		print_common_ip(param_dict, sample, symbol, dso)
+
+def process_event(param_dict):
+	try:
+		do_process_event(param_dict)
+	except broken_pipe_exception:
+		# Stop python printing broken pipe errors and traceback
+		sys.stdout = open(os.devnull, 'w')
+		sys.exit(1)
+
+def auxtrace_error(typ, code, cpu, pid, tid, ip, ts, msg, cpumode, *x):
+	try:
+		print("%16s %5u/%-5u [%03u] %9u.%09u  error type %u code %u: %s ip 0x%16x" %
+			("Trace error", pid, tid, cpu, ts / 1000000000, ts %1000000000, typ, code, msg, ip))
+	except broken_pipe_exception:
+		# Stop python printing broken pipe errors and traceback
+		sys.stdout = open(os.devnull, 'w')
+		sys.exit(1)
+
+def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_preempt, *x):
+	global glb_switch_printed
+	global glb_switch_str
+	if out:
+		out_str = "Switch out "
+	else:
+		out_str = "Switch In  "
+	if out_preempt:
+		preempt_str = "preempt"
+	else:
+		preempt_str = ""
+	if machine_pid == -1:
+		machine_str = ""
+	else:
+		machine_str = "machine PID %d" % machine_pid
+	glb_switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \
+		(out_str, pid, tid, cpu, ts / 1000000000, ts %1000000000, np_pid, np_tid, machine_str, preempt_str)
+	glb_switch_printed = False
diff --git a/tools/perf/scripts/python/libxed.py b/tools/perf/scripts/python/libxed.py
new file mode 100644
index 000000000000..2c70a5a7eb9c
--- /dev/null
+++ b/tools/perf/scripts/python/libxed.py
@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
+# libxed.py: Python wrapper for libxed.so
+# Copyright (c) 2014-2021, Intel Corporation.
+
+# To use Intel XED, libxed.so must be present. To build and install
+# libxed.so:
+#            git clone https://github.com/intelxed/mbuild.git mbuild
+#            git clone https://github.com/intelxed/xed
+#            cd xed
+#            ./mfile.py --share
+#            sudo ./mfile.py --prefix=/usr/local install
+#            sudo ldconfig
+#
+
+import sys
+
+from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \
+		   c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong
+
+# XED Disassembler
+
+class xed_state_t(Structure):
+
+	_fields_ = [
+		("mode", c_int),
+		("width", c_int)
+	]
+
+class XEDInstruction():
+
+	def __init__(self, libxed):
+		# Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
+		xedd_t = c_byte * 512
+		self.xedd = xedd_t()
+		self.xedp = addressof(self.xedd)
+		libxed.xed_decoded_inst_zero(self.xedp)
+		self.state = xed_state_t()
+		self.statep = addressof(self.state)
+		# Buffer for disassembled instruction text
+		self.buffer = create_string_buffer(256)
+		self.bufferp = addressof(self.buffer)
+
+class LibXED():
+
+	def __init__(self):
+		try:
+			self.libxed = CDLL("libxed.so")
+		except:
+			self.libxed = None
+		if not self.libxed:
+			self.libxed = CDLL("/usr/local/lib/libxed.so")
+
+		self.xed_tables_init = self.libxed.xed_tables_init
+		self.xed_tables_init.restype = None
+		self.xed_tables_init.argtypes = []
+
+		self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
+		self.xed_decoded_inst_zero.restype = None
+		self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
+
+		self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
+		self.xed_operand_values_set_mode.restype = None
+		self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
+
+		self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
+		self.xed_decoded_inst_zero_keep_mode.restype = None
+		self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
+
+		self.xed_decode = self.libxed.xed_decode
+		self.xed_decode.restype = c_int
+		self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
+
+		self.xed_format_context = self.libxed.xed_format_context
+		self.xed_format_context.restype = c_uint
+		self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
+
+		self.xed_tables_init()
+
+	def Instruction(self):
+		return XEDInstruction(self)
+
+	def SetMode(self, inst, mode):
+		if mode:
+			inst.state.mode = 4 # 32-bit
+			inst.state.width = 4 # 4 bytes
+		else:
+			inst.state.mode = 1 # 64-bit
+			inst.state.width = 8 # 8 bytes
+		self.xed_operand_values_set_mode(inst.xedp, inst.statep)
+
+	def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
+		self.xed_decoded_inst_zero_keep_mode(inst.xedp)
+		err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
+		if err:
+			return 0, ""
+		# Use AT&T mode (2), alternative is Intel (3)
+		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
+		if not ok:
+			return 0, ""
+		if sys.version_info[0] == 2:
+			result = inst.buffer.value
+		else:
+			result = inst.buffer.value.decode()
+		# Return instruction length and the disassembled instruction text
+		# For now, assume the length is in byte 166
+		return inst.xedd[166], result