Resguardo inicial

linux-7.2.3/tools/perf/scripts/Build

@@ -0,0 +1,30 @@
+ifeq ($(CONFIG_LIBTRACEEVENT),y)
+  perf-util-$(CONFIG_LIBPERL)   += perl/Perf-Trace-Util/
+endif
+perf-util-$(CONFIG_LIBPYTHON) += python/Perf-Trace-Util/
+
+ifdef MYPY
+  PY_TESTS := $(shell find python -type f -name '*.py')
+  MYPY_TEST_LOGS := $(PY_TESTS:python/%=python/%.mypy_log)
+else
+  MYPY_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.mypy_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(MYPY_TEST_LOGS)
+
+ifdef PYLINT
+  PY_TESTS := $(shell find python -type f -name '*.py')
+  PYLINT_TEST_LOGS := $(PY_TESTS:python/%=python/%.pylint_log)
+else
+  PYLINT_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.pylint_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(PYLINT_TEST_LOGS)

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/Build

@@ -0,0 +1,9 @@
+perf-util-y += Context.o
+
+CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
+CFLAGS_Context.o += -Wno-unused-parameter -Wno-nested-externs -Wno-undef
+CFLAGS_Context.o += -Wno-switch-default -Wno-shadow -Wno-thread-safety-analysis
+
+ifeq ($(CC_NO_CLANG), 1)
+  CFLAGS_Context.o += -Wno-unused-command-line-argument
+endif

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/Context.c

@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file was generated automatically by ExtUtils::ParseXS version 2.18_02 from the
+ * contents of Context.xs. Do not edit this file, edit Context.xs instead.
+ *
+ *	ANY CHANGES MADE HERE WILL BE LOST! 
+ */
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
+#line 1 "Context.xs"
+/*
+ * Context.xs.  XS interfaces for perf script.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ */
+
+#include "EXTERN.h"
+#include "perl.h"
+#include "XSUB.h"
+#include "../../../util/trace-event.h"
+
+#ifndef PERL_UNUSED_VAR
+#  define PERL_UNUSED_VAR(var) if (0) var = var
+#endif
+
+#line 42 "Context.c"
+
+XS(XS_Perf__Trace__Context_common_pc); /* prototype to pass -Wmissing-prototypes */
+XS(XS_Perf__Trace__Context_common_pc)
+{
+#ifdef dVAR
+    dVAR; dXSARGS;
+#else
+    dXSARGS;
+#endif
+    if (items != 1)
+       Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_pc", "context");
+    PERL_UNUSED_VAR(cv); /* -W */
+    {
+	struct scripting_context *	context = INT2PTR(struct scripting_context *,SvIV(ST(0)));
+	int	RETVAL;
+	dXSTARG;
+
+	RETVAL = common_pc(context);
+	XSprePUSH; PUSHi((IV)RETVAL);
+    }
+    XSRETURN(1);
+}
+
+
+XS(XS_Perf__Trace__Context_common_flags); /* prototype to pass -Wmissing-prototypes */
+XS(XS_Perf__Trace__Context_common_flags)
+{
+#ifdef dVAR
+    dVAR; dXSARGS;
+#else
+    dXSARGS;
+#endif
+    if (items != 1)
+       Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_flags", "context");
+    PERL_UNUSED_VAR(cv); /* -W */
+    {
+	struct scripting_context *	context = INT2PTR(struct scripting_context *,SvIV(ST(0)));
+	int	RETVAL;
+	dXSTARG;
+
+	RETVAL = common_flags(context);
+	XSprePUSH; PUSHi((IV)RETVAL);
+    }
+    XSRETURN(1);
+}
+
+
+XS(XS_Perf__Trace__Context_common_lock_depth); /* prototype to pass -Wmissing-prototypes */
+XS(XS_Perf__Trace__Context_common_lock_depth)
+{
+#ifdef dVAR
+    dVAR; dXSARGS;
+#else
+    dXSARGS;
+#endif
+    if (items != 1)
+       Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_lock_depth", "context");
+    PERL_UNUSED_VAR(cv); /* -W */
+    {
+	struct scripting_context *	context = INT2PTR(struct scripting_context *,SvIV(ST(0)));
+	int	RETVAL;
+	dXSTARG;
+
+	RETVAL = common_lock_depth(context);
+	XSprePUSH; PUSHi((IV)RETVAL);
+    }
+    XSRETURN(1);
+}
+
+#ifdef __cplusplus
+extern "C"
+#endif
+XS(boot_Perf__Trace__Context); /* prototype to pass -Wmissing-prototypes */
+XS(boot_Perf__Trace__Context)
+{
+#ifdef dVAR
+    dVAR; dXSARGS;
+#else
+    dXSARGS;
+#endif
+    const char* file = __FILE__;
+
+    PERL_UNUSED_VAR(cv); /* -W */
+    PERL_UNUSED_VAR(items); /* -W */
+    XS_VERSION_BOOTCHECK ;
+
+        newXSproto("Perf::Trace::Context::common_pc", XS_Perf__Trace__Context_common_pc, file, "$");
+        newXSproto("Perf::Trace::Context::common_flags", XS_Perf__Trace__Context_common_flags, file, "$");
+        newXSproto("Perf::Trace::Context::common_lock_depth", XS_Perf__Trace__Context_common_lock_depth, file, "$");
+    if (PL_unitcheckav)
+         call_list(PL_scopestack_ix, PL_unitcheckav);
+    XSRETURN_YES;
+}
+

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs

@@ -0,0 +1,42 @@
+/*
+ * Context.xs.  XS interfaces for perf script.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include "EXTERN.h"
+#include "perl.h"
+#include "XSUB.h"
+#include "../../../perf.h"
+#include "../../../util/trace-event.h"
+
+MODULE = Perf::Trace::Context		PACKAGE = Perf::Trace::Context
+PROTOTYPES: ENABLE
+
+int
+common_pc(context)
+	struct scripting_context * context
+
+int
+common_flags(context)
+	struct scripting_context * context
+
+int
+common_lock_depth(context)
+	struct scripting_context * context
+

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL

@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+use 5.010000;
+use ExtUtils::MakeMaker;
+# See lib/ExtUtils/MakeMaker.pm for details of how to influence
+# the contents of the Makefile that is written.
+WriteMakefile(
+    NAME              => 'Perf::Trace::Context',
+    VERSION_FROM      => 'lib/Perf/Trace/Context.pm', # finds $VERSION
+    PREREQ_PM         => {}, # e.g., Module::Name => 1.1
+    ($] >= 5.005 ?     ## Add these new keywords supported since 5.005
+      (ABSTRACT_FROM  => 'lib/Perf/Trace/Context.pm', # retrieve abstract from module
+       AUTHOR         => 'Tom Zanussi <tzanussi@gmail.com>') : ()),
+    LIBS              => [''], # e.g., '-lm'
+    DEFINE            => '-I ../..', # e.g., '-DHAVE_SOMETHING'
+    INC               => '-I.', # e.g., '-I. -I/usr/include/other'
+	# Un-comment this if you add C files to link with later:
+    OBJECT            => 'Context.o', # link all the C files too
+);

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/README

@@ -0,0 +1,59 @@
+Perf-Trace-Util version 0.01
+============================
+
+This module contains utility functions for use with perf script.
+
+Core.pm and Util.pm are pure Perl modules; Core.pm contains routines
+that the core perf support for Perl calls on and should always be
+'used', while Util.pm contains useful but optional utility functions
+that scripts may want to use.  Context.pm contains the Perl->C
+interface that allows scripts to access data in the embedding perf
+executable; scripts wishing to do that should 'use Context.pm'.
+
+The Perl->C perf interface is completely driven by Context.xs.  If you
+want to add new Perl functions that end up accessing C data in the
+perf executable, you add desciptions of the new functions here.
+scripting_context is a pointer to the perf data in the perf executable
+that you want to access - it's passed as the second parameter,
+$context, to all handler functions.
+
+After you do that:
+
+  perl Makefile.PL   # to create a Makefile for the next step
+  make               # to create Context.c
+
+  edit Context.c to add const to the char* file = __FILE__ line in
+  XS(boot_Perf__Trace__Context) to silence a warning/error.
+
+  You can delete the Makefile, object files and anything else that was
+  generated e.g. blib and shared library, etc, except for of course
+  Context.c
+
+  You should then be able to run the normal perf make as usual.
+
+INSTALLATION
+
+Building perf with perf script Perl scripting should install this
+module in the right place.
+
+You should make sure libperl and ExtUtils/Embed.pm are installed first
+e.g. apt-get install libperl-dev or yum install perl-ExtUtils-Embed.
+
+DEPENDENCIES
+
+This module requires these other modules and libraries:
+
+  None
+
+COPYRIGHT AND LICENCE
+
+Copyright (C) 2009 by Tom Zanussi <tzanussi@gmail.com>
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself, either Perl version 5.10.0 or,
+at your option, any later version of Perl 5 you may have available.
+
+Alternatively, this software may be distributed under the terms of the
+GNU General Public License ("GPL") version 2 as published by the Free
+Software Foundation.
+

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm

@@ -0,0 +1,55 @@
+package Perf::Trace::Context;
+
+use 5.010000;
+use strict;
+use warnings;
+
+require Exporter;
+
+our @ISA = qw(Exporter);
+
+our %EXPORT_TAGS = ( 'all' => [ qw(
+) ] );
+
+our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );
+
+our @EXPORT = qw(
+	common_pc common_flags common_lock_depth
+);
+
+our $VERSION = '0.01';
+
+require XSLoader;
+XSLoader::load('Perf::Trace::Context', $VERSION);
+
+1;
+__END__
+=head1 NAME
+
+Perf::Trace::Context - Perl extension for accessing functions in perf.
+
+=head1 SYNOPSIS
+
+  use Perf::Trace::Context;
+
+=head1 SEE ALSO
+
+Perf (script) documentation
+
+=head1 AUTHOR
+
+Tom Zanussi, E<lt>tzanussi@gmail.com<gt>
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2009 by Tom Zanussi
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself, either Perl version 5.10.0 or,
+at your option, any later version of Perl 5 you may have available.
+
+Alternatively, this software may be distributed under the terms of the
+GNU General Public License ("GPL") version 2 as published by the Free
+Software Foundation.
+
+=cut

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm

@@ -0,0 +1,192 @@
+package Perf::Trace::Core;
+
+use 5.010000;
+use strict;
+use warnings;
+
+require Exporter;
+
+our @ISA = qw(Exporter);
+
+our %EXPORT_TAGS = ( 'all' => [ qw(
+) ] );
+
+our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );
+
+our @EXPORT = qw(
+define_flag_field define_flag_value flag_str dump_flag_fields
+define_symbolic_field define_symbolic_value symbol_str dump_symbolic_fields
+trace_flag_str
+);
+
+our $VERSION = '0.01';
+
+my %trace_flags = (0x00 => "NONE",
+		   0x01 => "IRQS_OFF",
+		   0x02 => "IRQS_NOSUPPORT",
+		   0x04 => "NEED_RESCHED",
+		   0x08 => "HARDIRQ",
+		   0x10 => "SOFTIRQ");
+
+sub trace_flag_str
+{
+    my ($value) = @_;
+
+    my $string;
+
+    my $print_delim = 0;
+
+    foreach my $idx (sort {$a <=> $b} keys %trace_flags) {
+	if (!$value && !$idx) {
+	    $string .= "NONE";
+	    last;
+	}
+
+	if ($idx && ($value & $idx) == $idx) {
+	    if ($print_delim) {
+		$string .= " | ";
+	    }
+	    $string .= "$trace_flags{$idx}";
+	    $print_delim = 1;
+	    $value &= ~$idx;
+	}
+    }
+
+    return $string;
+}
+
+my %flag_fields;
+my %symbolic_fields;
+
+sub flag_str
+{
+    my ($event_name, $field_name, $value) = @_;
+
+    my $string;
+
+    if ($flag_fields{$event_name}{$field_name}) {
+	my $print_delim = 0;
+	foreach my $idx (sort {$a <=> $b} keys %{$flag_fields{$event_name}{$field_name}{"values"}}) {
+	    if (!$value && !$idx) {
+		$string .= "$flag_fields{$event_name}{$field_name}{'values'}{$idx}";
+		last;
+	    }
+	    if ($idx && ($value & $idx) == $idx) {
+		if ($print_delim && $flag_fields{$event_name}{$field_name}{'delim'}) {
+		    $string .= " $flag_fields{$event_name}{$field_name}{'delim'} ";
+		}
+		$string .= "$flag_fields{$event_name}{$field_name}{'values'}{$idx}";
+		$print_delim = 1;
+		$value &= ~$idx;
+	    }
+	}
+    }
+
+    return $string;
+}
+
+sub define_flag_field
+{
+    my ($event_name, $field_name, $delim) = @_;
+
+    $flag_fields{$event_name}{$field_name}{"delim"} = $delim;
+}
+
+sub define_flag_value
+{
+    my ($event_name, $field_name, $value, $field_str) = @_;
+
+    $flag_fields{$event_name}{$field_name}{"values"}{$value} = $field_str;
+}
+
+sub dump_flag_fields
+{
+    for my $event (keys %flag_fields) {
+	print "event $event:\n";
+	for my $field (keys %{$flag_fields{$event}}) {
+	    print "    field: $field:\n";
+	    print "        delim: $flag_fields{$event}{$field}{'delim'}\n";
+	    foreach my $idx (sort {$a <=> $b} keys %{$flag_fields{$event}{$field}{"values"}}) {
+		print "        value $idx: $flag_fields{$event}{$field}{'values'}{$idx}\n";
+	    }
+	}
+    }
+}
+
+sub symbol_str
+{
+    my ($event_name, $field_name, $value) = @_;
+
+    if ($symbolic_fields{$event_name}{$field_name}) {
+	foreach my $idx (sort {$a <=> $b} keys %{$symbolic_fields{$event_name}{$field_name}{"values"}}) {
+	    if (!$value && !$idx) {
+		return "$symbolic_fields{$event_name}{$field_name}{'values'}{$idx}";
+		last;
+	    }
+	    if ($value == $idx) {
+		return "$symbolic_fields{$event_name}{$field_name}{'values'}{$idx}";
+	    }
+	}
+    }
+
+    return undef;
+}
+
+sub define_symbolic_field
+{
+    my ($event_name, $field_name) = @_;
+
+    # nothing to do, really
+}
+
+sub define_symbolic_value
+{
+    my ($event_name, $field_name, $value, $field_str) = @_;
+
+    $symbolic_fields{$event_name}{$field_name}{"values"}{$value} = $field_str;
+}
+
+sub dump_symbolic_fields
+{
+    for my $event (keys %symbolic_fields) {
+	print "event $event:\n";
+	for my $field (keys %{$symbolic_fields{$event}}) {
+	    print "    field: $field:\n";
+	    foreach my $idx (sort {$a <=> $b} keys %{$symbolic_fields{$event}{$field}{"values"}}) {
+		print "        value $idx: $symbolic_fields{$event}{$field}{'values'}{$idx}\n";
+	    }
+	}
+    }
+}
+
+1;
+__END__
+=head1 NAME
+
+Perf::Trace::Core - Perl extension for perf script
+
+=head1 SYNOPSIS
+
+  use Perf::Trace::Core
+
+=head1 SEE ALSO
+
+Perf (script) documentation
+
+=head1 AUTHOR
+
+Tom Zanussi, E<lt>tzanussi@gmail.com<gt>
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2009 by Tom Zanussi
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself, either Perl version 5.10.0 or,
+at your option, any later version of Perl 5 you may have available.
+
+Alternatively, this software may be distributed under the terms of the
+GNU General Public License ("GPL") version 2 as published by the Free
+Software Foundation.
+
+=cut

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm

@@ -0,0 +1,94 @@
+package Perf::Trace::Util;
+
+use 5.010000;
+use strict;
+use warnings;
+
+require Exporter;
+
+our @ISA = qw(Exporter);
+
+our %EXPORT_TAGS = ( 'all' => [ qw(
+) ] );
+
+our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );
+
+our @EXPORT = qw(
+avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs
+clear_term
+);
+
+our $VERSION = '0.01';
+
+sub avg
+{
+    my ($total, $n) = @_;
+
+    return $total / $n;
+}
+
+my $NSECS_PER_SEC    = 1000000000;
+
+sub nsecs
+{
+    my ($secs, $nsecs) = @_;
+
+    return $secs * $NSECS_PER_SEC + $nsecs;
+}
+
+sub nsecs_secs {
+    my ($nsecs) = @_;
+
+    return $nsecs / $NSECS_PER_SEC;
+}
+
+sub nsecs_nsecs {
+    my ($nsecs) = @_;
+
+    return $nsecs % $NSECS_PER_SEC;
+}
+
+sub nsecs_str {
+    my ($nsecs) = @_;
+
+    my $str = sprintf("%5u.%09u", nsecs_secs($nsecs), nsecs_nsecs($nsecs));
+
+    return $str;
+}
+
+sub clear_term
+{
+    print "\x1b[H\x1b[2J";
+}
+
+1;
+__END__
+=head1 NAME
+
+Perf::Trace::Util - Perl extension for perf script
+
+=head1 SYNOPSIS
+
+  use Perf::Trace::Util;
+
+=head1 SEE ALSO
+
+Perf (script) documentation
+
+=head1 AUTHOR
+
+Tom Zanussi, E<lt>tzanussi@gmail.com<gt>
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2009 by Tom Zanussi
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself, either Perl version 5.10.0 or,
+at your option, any later version of Perl 5 you may have available.
+
+Alternatively, this software may be distributed under the terms of the
+GNU General Public License ("GPL") version 2 as published by the Free
+Software Foundation.
+
+=cut

linux-7.2.3/tools/perf/scripts/perl/Perf-Trace-Util/typemap

@@ -0,0 +1 @@
+struct scripting_context * T_PTR

linux-7.2.3/tools/perf/scripts/perl/bin/check-perf-trace-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -a -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree

linux-7.2.3/tools/perf/scripts/perl/bin/failed-syscalls-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null

linux-7.2.3/tools/perf/scripts/perl/bin/failed-syscalls-report

@@ -0,0 +1,10 @@
+#!/bin/bash
+# description: system-wide failed syscalls
+# args: [comm]
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/failed-syscalls.pl $comm

linux-7.2.3/tools/perf/scripts/perl/bin/rw-by-file-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+

linux-7.2.3/tools/perf/scripts/perl/bin/rw-by-file-report

@@ -0,0 +1,10 @@
+#!/bin/bash
+# description: r/w activity for a program, by file
+# args: <comm>
+if [ $# -lt 1 ] ; then
+    echo "usage: rw-by-file <comm>"
+    exit
+fi
+comm=$1
+shift
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-file.pl $comm

linux-7.2.3/tools/perf/scripts/perl/bin/rw-by-pid-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

linux-7.2.3/tools/perf/scripts/perl/bin/rw-by-pid-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: system-wide r/w activity
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-pid.pl

linux-7.2.3/tools/perf/scripts/perl/bin/rwtop-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

linux-7.2.3/tools/perf/scripts/perl/bin/rwtop-report

@@ -0,0 +1,20 @@
+#!/bin/bash
+# description: system-wide r/w top
+# args: [interval]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 1 ] ; then
+    echo "usage: rwtop-report [interval]"
+    exit
+fi
+if [ "$n_args" -gt 0 ] ; then
+    interval=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rwtop.pl $interval

linux-7.2.3/tools/perf/scripts/perl/bin/wakeup-latency-record

@@ -0,0 +1,6 @@
+#!/bin/bash
+perf record -e sched:sched_switch -e sched:sched_wakeup $@
+
+
+
+

linux-7.2.3/tools/perf/scripts/perl/bin/wakeup-latency-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: system-wide min/max/avg wakeup latency
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/wakeup-latency.pl

linux-7.2.3/tools/perf/scripts/perl/check-perf-trace.pl

@@ -0,0 +1,106 @@
+# perf script event handlers, generated by perf script -g perl
+# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+
+# This script tests basic functionality such as flag and symbol
+# strings, common_xxx() calls back into perf, begin, end, unhandled
+# events, etc.  Basically, if this script runs successfully and
+# displays expected results, perl scripting support should be ok.
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Context;
+use Perf::Trace::Util;
+
+sub trace_begin
+{
+    print "trace_begin\n";
+}
+
+sub trace_end
+{
+    print "trace_end\n";
+
+    print_unhandled();
+}
+
+sub irq::softirq_entry
+{
+	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	    $common_pid, $common_comm, $common_callchain,
+	    $vec) = @_;
+
+	print_header($event_name, $common_cpu, $common_secs, $common_nsecs,
+		     $common_pid, $common_comm);
+
+	print_uncommon($context);
+
+	printf("vec=%s\n",
+	       symbol_str("irq::softirq_entry", "vec", $vec));
+}
+
+sub kmem::kmalloc
+{
+	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	    $common_pid, $common_comm, $common_callchain,
+	    $call_site, $ptr, $bytes_req, $bytes_alloc,
+	    $gfp_flags) = @_;
+
+	print_header($event_name, $common_cpu, $common_secs, $common_nsecs,
+		     $common_pid, $common_comm);
+
+	print_uncommon($context);
+
+	printf("call_site=%p, ptr=%p, bytes_req=%u, bytes_alloc=%u, ".
+	       "gfp_flags=%s\n",
+	       $call_site, $ptr, $bytes_req, $bytes_alloc,
+
+	       flag_str("kmem::kmalloc", "gfp_flags", $gfp_flags));
+}
+
+# print trace fields not included in handler args
+sub print_uncommon
+{
+    my ($context) = @_;
+
+    printf("common_preempt_count=%d, common_flags=%s, common_lock_depth=%d, ",
+	   common_pc($context), trace_flag_str(common_flags($context)),
+	   common_lock_depth($context));
+
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain) = @_;
+
+    $unhandled{$event_name}++;
+}
+
+sub print_header
+{
+	my ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;
+
+	printf("%-20s %5u %05u.%09u %8u %-20s ",
+	       $event_name, $cpu, $secs, $nsecs, $pid, $comm);
+}

linux-7.2.3/tools/perf/scripts/perl/failed-syscalls.pl

@@ -0,0 +1,47 @@
+# failed system call counts
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide failed system call totals
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Context;
+use Perf::Trace::Util;
+
+my $for_comm = shift;
+
+my %failed_syscalls;
+
+sub raw_syscalls::sys_exit
+{
+	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	    $common_pid, $common_comm, $common_callchain,
+	    $id, $ret) = @_;
+
+	if ($ret < 0) {
+	    $failed_syscalls{$common_comm}++;
+	}
+}
+
+sub syscalls::sys_exit
+{
+	raw_syscalls::sys_exit(@_)
+}
+
+sub trace_end
+{
+    printf("\nfailed syscalls by comm:\n\n");
+
+    printf("%-20s  %10s\n", "comm", "# errors");
+    printf("%-20s  %6s  %10s\n", "--------------------", "----------");
+
+    foreach my $comm (sort {$failed_syscalls{$b} <=> $failed_syscalls{$a}}
+		      keys %failed_syscalls) {
+	next if ($for_comm && $comm ne $for_comm);
+
+	printf("%-20s  %10s\n", $comm, $failed_syscalls{$comm});
+    }
+}

linux-7.2.3/tools/perf/scripts/perl/rw-by-file.pl

@@ -0,0 +1,106 @@
+#!/usr/bin/perl -w
+# SPDX-License-Identifier: GPL-2.0-only
+# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
+
+# Display r/w activity for files read/written to for a given program
+
+# The common_* event handler fields are the most useful fields common to
+# all events.  They don't necessarily correspond to the 'common_*' fields
+# in the status files.  Those fields not available as handler params can
+# be retrieved via script functions of the form get_common_*().
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my $usage = "perf script -s rw-by-file.pl <comm>\n";
+
+my $for_comm = shift or die $usage;
+
+my %reads;
+my %writes;
+
+sub syscalls::sys_enter_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
+
+    if ($common_comm eq $for_comm) {
+	$reads{$fd}{bytes_requested} += $count;
+	$reads{$fd}{total_reads}++;
+    }
+}
+
+sub syscalls::sys_enter_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
+
+    if ($common_comm eq $for_comm) {
+	$writes{$fd}{bytes_written} += $count;
+	$writes{$fd}{total_writes}++;
+    }
+}
+
+sub trace_end
+{
+    printf("file read counts for $for_comm:\n\n");
+
+    printf("%6s  %10s  %10s\n", "fd", "# reads", "bytes_requested");
+    printf("%6s  %10s  %10s\n", "------", "----------", "-----------");
+
+    foreach my $fd (sort {$reads{$b}{bytes_requested} <=>
+			      $reads{$a}{bytes_requested}} keys %reads) {
+	my $total_reads = $reads{$fd}{total_reads};
+	my $bytes_requested = $reads{$fd}{bytes_requested};
+	printf("%6u  %10u  %10u\n", $fd, $total_reads, $bytes_requested);
+    }
+
+    printf("\nfile write counts for $for_comm:\n\n");
+
+    printf("%6s  %10s  %10s\n", "fd", "# writes", "bytes_written");
+    printf("%6s  %10s  %10s\n", "------", "----------", "-----------");
+
+    foreach my $fd (sort {$writes{$b}{bytes_written} <=>
+			      $writes{$a}{bytes_written}} keys %writes) {
+	my $total_writes = $writes{$fd}{total_writes};
+	my $bytes_written = $writes{$fd}{bytes_written};
+	printf("%6u  %10u  %10u\n", $fd, $total_writes, $bytes_written);
+    }
+
+    print_unhandled();
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain) = @_;
+
+    $unhandled{$event_name}++;
+}
+
+

linux-7.2.3/tools/perf/scripts/perl/rw-by-pid.pl

@@ -0,0 +1,184 @@
+#!/usr/bin/perl -w
+# SPDX-License-Identifier: GPL-2.0-only
+# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
+
+# Display r/w activity for all processes
+
+# The common_* event handler fields are the most useful fields common to
+# all events.  They don't necessarily correspond to the 'common_*' fields
+# in the status files.  Those fields not available as handler params can
+# be retrieved via script functions of the form get_common_*().
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my %reads;
+my %writes;
+
+sub syscalls::sys_exit_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $ret) = @_;
+
+    if ($ret > 0) {
+	$reads{$common_pid}{bytes_read} += $ret;
+    } else {
+	if (!defined ($reads{$common_pid}{bytes_read})) {
+	    $reads{$common_pid}{bytes_read} = 0;
+	}
+	$reads{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $fd, $buf, $count) = @_;
+
+    $reads{$common_pid}{bytes_requested} += $count;
+    $reads{$common_pid}{total_reads}++;
+    $reads{$common_pid}{comm} = $common_comm;
+}
+
+sub syscalls::sys_exit_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $ret) = @_;
+
+    if ($ret <= 0) {
+	$writes{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $fd, $buf, $count) = @_;
+
+    $writes{$common_pid}{bytes_written} += $count;
+    $writes{$common_pid}{total_writes}++;
+    $writes{$common_pid}{comm} = $common_comm;
+}
+
+sub trace_end
+{
+    printf("read counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %10s  %10s\n", "pid", "comm",
+	   "# reads", "bytes_requested", "bytes_read");
+    printf("%6s  %-20s  %10s  %10s  %10s\n", "------", "--------------------",
+	   "-----------", "----------", "----------");
+
+    foreach my $pid (sort { ($reads{$b}{bytes_read} || 0) <=>
+				($reads{$a}{bytes_read} || 0) } keys %reads) {
+	my $comm = $reads{$pid}{comm} || "";
+	my $total_reads = $reads{$pid}{total_reads} || 0;
+	my $bytes_requested = $reads{$pid}{bytes_requested} || 0;
+	my $bytes_read = $reads{$pid}{bytes_read} || 0;
+
+	printf("%6s  %-20s  %10s  %10s  %10s\n", $pid, $comm,
+	       $total_reads, $bytes_requested, $bytes_read);
+    }
+
+    printf("\nfailed reads by pid:\n\n");
+
+    printf("%6s  %20s  %6s  %10s\n", "pid", "comm", "error #", "# errors");
+    printf("%6s  %20s  %6s  %10s\n", "------", "--------------------",
+	   "------", "----------");
+
+    my @errcounts = ();
+
+    foreach my $pid (keys %reads) {
+	foreach my $error (keys %{$reads{$pid}{errors}}) {
+	    my $comm = $reads{$pid}{comm} || "";
+	    my $errcount = $reads{$pid}{errors}{$error} || 0;
+	    push @errcounts, [$pid, $comm, $error, $errcount];
+	}
+    }
+
+    @errcounts = sort { $b->[3] <=> $a->[3] } @errcounts;
+
+    for my $i (0 .. $#errcounts) {
+	printf("%6d  %-20s  %6d  %10s\n", $errcounts[$i][0],
+	       $errcounts[$i][1], $errcounts[$i][2], $errcounts[$i][3]);
+    }
+
+    printf("\nwrite counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %10s\n", "pid", "comm",
+	   "# writes", "bytes_written");
+    printf("%6s  %-20s  %10s  %10s\n", "------", "--------------------",
+	   "-----------", "----------");
+
+    foreach my $pid (sort { ($writes{$b}{bytes_written} || 0) <=>
+			($writes{$a}{bytes_written} || 0)} keys %writes) {
+	my $comm = $writes{$pid}{comm} || "";
+	my $total_writes = $writes{$pid}{total_writes} || 0;
+	my $bytes_written = $writes{$pid}{bytes_written} || 0;
+
+	printf("%6s  %-20s  %10s  %10s\n", $pid, $comm,
+	       $total_writes, $bytes_written);
+    }
+
+    printf("\nfailed writes by pid:\n\n");
+
+    printf("%6s  %20s  %6s  %10s\n", "pid", "comm", "error #", "# errors");
+    printf("%6s  %20s  %6s  %10s\n", "------", "--------------------",
+	   "------", "----------");
+
+    @errcounts = ();
+
+    foreach my $pid (keys %writes) {
+	foreach my $error (keys %{$writes{$pid}{errors}}) {
+	    my $comm = $writes{$pid}{comm} || "";
+	    my $errcount = $writes{$pid}{errors}{$error} || 0;
+	    push @errcounts, [$pid, $comm, $error, $errcount];
+	}
+    }
+
+    @errcounts = sort { $b->[3] <=> $a->[3] } @errcounts;
+
+    for my $i (0 .. $#errcounts) {
+	printf("%6d  %-20s  %6d  %10s\n", $errcounts[$i][0],
+	       $errcounts[$i][1], $errcounts[$i][2], $errcounts[$i][3]);
+    }
+
+    print_unhandled();
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain) = @_;
+
+    $unhandled{$event_name}++;
+}

linux-7.2.3/tools/perf/scripts/perl/rwtop.pl

@@ -0,0 +1,203 @@
+#!/usr/bin/perl -w
+# SPDX-License-Identifier: GPL-2.0-only
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+
+# read/write top
+#
+# Periodically displays system-wide r/w call activity, broken down by
+# pid.  If an [interval] arg is specified, the display will be
+# refreshed every [interval] seconds.  The default interval is 3
+# seconds.
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+use POSIX qw/SIGALRM SA_RESTART/;
+
+my $default_interval = 3;
+my $nlines = 20;
+my $print_thread;
+my $print_pending = 0;
+
+my %reads;
+my %writes;
+
+my $interval = shift;
+if (!$interval) {
+    $interval = $default_interval;
+}
+
+sub syscalls::sys_exit_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $ret) = @_;
+
+    print_check();
+
+    if ($ret > 0) {
+	$reads{$common_pid}{bytes_read} += $ret;
+    } else {
+	if (!defined ($reads{$common_pid}{bytes_read})) {
+	    $reads{$common_pid}{bytes_read} = 0;
+	}
+	$reads{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $fd, $buf, $count) = @_;
+
+    print_check();
+
+    $reads{$common_pid}{bytes_requested} += $count;
+    $reads{$common_pid}{total_reads}++;
+    $reads{$common_pid}{comm} = $common_comm;
+}
+
+sub syscalls::sys_exit_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $ret) = @_;
+
+    print_check();
+
+    if ($ret <= 0) {
+	$writes{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$nr, $fd, $buf, $count) = @_;
+
+    print_check();
+
+    $writes{$common_pid}{bytes_written} += $count;
+    $writes{$common_pid}{total_writes}++;
+    $writes{$common_pid}{comm} = $common_comm;
+}
+
+sub trace_begin
+{
+    my $sa = POSIX::SigAction->new(\&set_print_pending);
+    $sa->flags(SA_RESTART);
+    $sa->safe(1);
+    POSIX::sigaction(SIGALRM, $sa) or die "Can't set SIGALRM handler: $!\n";
+    alarm 1;
+}
+
+sub trace_end
+{
+    print_unhandled();
+    print_totals();
+}
+
+sub print_check()
+{
+    if ($print_pending == 1) {
+	$print_pending = 0;
+	print_totals();
+    }
+}
+
+sub set_print_pending()
+{
+    $print_pending = 1;
+    alarm $interval;
+}
+
+sub print_totals
+{
+    my $count;
+
+    $count = 0;
+
+    clear_term();
+
+    printf("\nread counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %10s  %10s\n", "pid", "comm",
+	   "# reads", "bytes_req", "bytes_read");
+    printf("%6s  %-20s  %10s  %10s  %10s\n", "------", "--------------------",
+	   "----------", "----------", "----------");
+
+    foreach my $pid (sort { ($reads{$b}{bytes_read} || 0) <=>
+			       ($reads{$a}{bytes_read} || 0) } keys %reads) {
+	my $comm = $reads{$pid}{comm} || "";
+	my $total_reads = $reads{$pid}{total_reads} || 0;
+	my $bytes_requested = $reads{$pid}{bytes_requested} || 0;
+	my $bytes_read = $reads{$pid}{bytes_read} || 0;
+
+	printf("%6s  %-20s  %10s  %10s  %10s\n", $pid, $comm,
+	       $total_reads, $bytes_requested, $bytes_read);
+
+	if (++$count == $nlines) {
+	    last;
+	}
+    }
+
+    $count = 0;
+
+    printf("\nwrite counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %13s\n", "pid", "comm",
+	   "# writes", "bytes_written");
+    printf("%6s  %-20s  %10s  %13s\n", "------", "--------------------",
+	   "----------", "-------------");
+
+    foreach my $pid (sort { ($writes{$b}{bytes_written} || 0) <=>
+			($writes{$a}{bytes_written} || 0)} keys %writes) {
+	my $comm = $writes{$pid}{comm} || "";
+	my $total_writes = $writes{$pid}{total_writes} || 0;
+	my $bytes_written = $writes{$pid}{bytes_written} || 0;
+
+	printf("%6s  %-20s  %10s  %13s\n", $pid, $comm,
+	       $total_writes, $bytes_written);
+
+	if (++$count == $nlines) {
+	    last;
+	}
+    }
+
+    %reads = ();
+    %writes = ();
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain) = @_;
+
+    $unhandled{$event_name}++;
+}

linux-7.2.3/tools/perf/scripts/perl/wakeup-latency.pl

@@ -0,0 +1,107 @@
+#!/usr/bin/perl -w
+# SPDX-License-Identifier: GPL-2.0-only
+# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
+
+# Display avg/min/max wakeup latency
+
+# The common_* event handler fields are the most useful fields common to
+# all events.  They don't necessarily correspond to the 'common_*' fields
+# in the status files.  Those fields not available as handler params can
+# be retrieved via script functions of the form get_common_*().
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my %last_wakeup;
+
+my $max_wakeup_latency;
+my $min_wakeup_latency;
+my $total_wakeup_latency = 0;
+my $total_wakeups = 0;
+
+sub sched::sched_switch
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$prev_comm, $prev_pid, $prev_prio, $prev_state, $next_comm, $next_pid,
+	$next_prio) = @_;
+
+    my $wakeup_ts = $last_wakeup{$common_cpu}{ts};
+    if ($wakeup_ts) {
+	my $switch_ts = nsecs($common_secs, $common_nsecs);
+	my $wakeup_latency = $switch_ts - $wakeup_ts;
+	if ($wakeup_latency > $max_wakeup_latency) {
+	    $max_wakeup_latency = $wakeup_latency;
+	}
+	if ($wakeup_latency < $min_wakeup_latency) {
+	    $min_wakeup_latency = $wakeup_latency;
+	}
+	$total_wakeup_latency += $wakeup_latency;
+	$total_wakeups++;
+    }
+    $last_wakeup{$common_cpu}{ts} = 0;
+}
+
+sub sched::sched_wakeup
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain,
+	$comm, $pid, $prio, $success, $target_cpu) = @_;
+
+    $last_wakeup{$target_cpu}{ts} = nsecs($common_secs, $common_nsecs);
+}
+
+sub trace_begin
+{
+    $min_wakeup_latency = 1000000000;
+    $max_wakeup_latency = 0;
+}
+
+sub trace_end
+{
+    printf("wakeup_latency stats:\n\n");
+    print "total_wakeups: $total_wakeups\n";
+    if ($total_wakeups) {
+	printf("avg_wakeup_latency (ns): %u\n",
+	       avg($total_wakeup_latency, $total_wakeups));
+    } else {
+	printf("avg_wakeup_latency (ns): N/A\n");
+    }
+    printf("min_wakeup_latency (ns): %u\n", $min_wakeup_latency);
+    printf("max_wakeup_latency (ns): %u\n", $max_wakeup_latency);
+
+    print_unhandled();
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm, $common_callchain) = @_;
+
+    $unhandled{$event_name}++;
+}

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/Build

@@ -0,0 +1,4 @@
+perf-util-y += Context.o
+
+# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance)
+CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-declaration-after-statement

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/Context.c

@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Context.c.  Python interfaces for perf script.
+ *
+ * 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/config.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"
+
+#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);
+
+static struct scripting_context *get_args(PyObject *args, const char *name, PyObject **arg2)
+{
+	int cnt = 1 + !!arg2;
+	PyObject *context;
+
+	if (!PyArg_UnpackTuple(args, name, 1, cnt, &context, arg2))
+		return NULL;
+
+	return _PyCapsule_GetPointer(context, NULL);
+}
+
+static struct scripting_context *get_scripting_context(PyObject *args)
+{
+	return get_args(args, "context", NULL);
+}
+
+#ifdef HAVE_LIBTRACEEVENT
+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)
+{
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
+
+	return Py_BuildValue("i", common_flags(c));
+}
+
+static PyObject *perf_trace_context_common_lock_depth(PyObject *obj,
+						      PyObject *args)
+{
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
+
+	return Py_BuildValue("i", common_lock_depth(c));
+}
+#endif
+
+static PyObject *perf_sample_insn(PyObject *obj, PyObject *args)
+{
+	struct scripting_context *c = get_scripting_context(args);
+
+	if (!c)
+		return NULL;
+
+	if (c->sample->ip && !c->sample->insn_len && thread__maps(c->al->thread)) {
+		struct machine *machine =  maps__machine(thread__maps(c->al->thread));
+
+		perf_sample__fetch_insn(c->sample, c->al->thread, 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;
+
+	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;
+	struct dso *dso;
+	int len = 0;
+	u64 addr;
+
+	if (!c)
+		return NULL;
+
+	map = c->al->map;
+	addr = c->al->addr;
+	dso = map ? map__dso(map) : NULL;
+
+	if (dso)
+		srcfile = get_srcline_split(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 PyObject *__perf_config_get(PyObject *obj, PyObject *args)
+{
+	const char *config_name;
+
+	if (!PyArg_ParseTuple(args, "s", &config_name))
+		return NULL;
+	return Py_BuildValue("s", perf_config_get(config_name));
+}
+
+static PyMethodDef ContextMethods[] = {
+#ifdef HAVE_LIBTRACEEVENT
+	{ "common_pc", perf_trace_context_common_pc, METH_VARARGS,
+	  "Get the common preempt count event field value."},
+	{ "common_flags", perf_trace_context_common_flags, METH_VARARGS,
+	  "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."},
+#endif
+	{ "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."},
+	{ "perf_config_get", __perf_config_get, METH_VARARGS, "Get perf config entry"},
+	{ NULL, NULL, 0, NULL}
+};
+
+PyMODINIT_FUNC PyInit_perf_trace_context(void)
+{
+	static struct PyModuleDef moduledef = {
+		PyModuleDef_HEAD_INIT,
+		"perf_trace_context",	/* m_name */
+		"",			/* m_doc */
+		-1,			/* m_size */
+		ContextMethods,		/* m_methods */
+		NULL,			/* m_reload */
+		NULL,			/* m_traverse */
+		NULL,			/* m_clear */
+		NULL,			/* m_free */
+	};
+	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;
+}

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py

@@ -0,0 +1,116 @@
+# Core.py - Python extension for perf script, core functions
+#
+# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
+#
+# This software may be distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+from collections import defaultdict
+
+def autodict():
+    return defaultdict(autodict)
+
+flag_fields = autodict()
+symbolic_fields = autodict()
+
+def define_flag_field(event_name, field_name, delim):
+    flag_fields[event_name][field_name]['delim'] = delim
+
+def define_flag_value(event_name, field_name, value, field_str):
+    flag_fields[event_name][field_name]['values'][value] = field_str
+
+def define_symbolic_field(event_name, field_name):
+    # nothing to do, really
+    pass
+
+def define_symbolic_value(event_name, field_name, value, field_str):
+    symbolic_fields[event_name][field_name]['values'][value] = field_str
+
+def flag_str(event_name, field_name, value):
+    string = ""
+
+    if flag_fields[event_name][field_name]:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
+            if not value and not idx:
+                string += flag_fields[event_name][field_name]['values'][idx]
+                break
+            if idx and (value & idx) == idx:
+                if print_delim and flag_fields[event_name][field_name]['delim']:
+                    string += " " + flag_fields[event_name][field_name]['delim'] + " "
+                string += flag_fields[event_name][field_name]['values'][idx]
+                print_delim = 1
+                value &= ~idx
+
+    return string
+
+def symbol_str(event_name, field_name, value):
+    string = ""
+
+    if symbolic_fields[event_name][field_name]:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
+            if not value and not idx:
+                string = symbolic_fields[event_name][field_name]['values'][idx]
+                break
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
+                break
+
+    return string
+
+trace_flags = { 0x00: "NONE", \
+                    0x01: "IRQS_OFF", \
+                    0x02: "IRQS_NOSUPPORT", \
+                    0x04: "NEED_RESCHED", \
+                    0x08: "HARDIRQ", \
+                    0x10: "SOFTIRQ" }
+
+def trace_flag_str(value):
+    string = ""
+    print_delim = 0
+
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
+
+    return string
+
+
+def taskState(state):
+	states = {
+		0 : "R",
+		1 : "S",
+		2 : "D",
+		64: "DEAD"
+	}
+
+	if state not in states:
+		return "Unknown"
+
+	return states[state]
+
+
+class EventHeaders:
+	def __init__(self, common_cpu, common_secs, common_nsecs,
+		     common_pid, common_comm, common_callchain):
+		self.cpu = common_cpu
+		self.secs = common_secs
+		self.nsecs = common_nsecs
+		self.pid = common_pid
+		self.comm = common_comm
+		self.callchain = common_callchain
+
+	def ts(self):
+		return (self.secs * (10 ** 9)) + self.nsecs
+
+	def ts_format(self):
+		return "%d.%d" % (self.secs, int(self.nsecs / 1000))

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py

@@ -0,0 +1,97 @@
+# EventClass.py
+# SPDX-License-Identifier: GPL-2.0
+#
+# This is a library defining some events types classes, which could
+# be used by other scripts to analyzing the perf samples.
+#
+# Currently there are just a few classes defined for examples,
+# PerfEvent is the base class for all perf event sample, PebsEvent
+# is a HW base Intel x86 PEBS event, and user could add more SW/HW
+# event classes based on requirements.
+from __future__ import print_function
+
+import struct
+
+# Event types, user could add more here
+EVTYPE_GENERIC  = 0
+EVTYPE_PEBS     = 1     # Basic PEBS event
+EVTYPE_PEBS_LL  = 2     # PEBS event with load latency info
+EVTYPE_IBS      = 3
+
+#
+# Currently we don't have good way to tell the event type, but by
+# the size of raw buffer, raw PEBS event with load latency data's
+# size is 176 bytes, while the pure PEBS event's size is 144 bytes.
+#
+def create_event(name, comm, dso, symbol, raw_buf):
+        if (len(raw_buf) == 144):
+                event = PebsEvent(name, comm, dso, symbol, raw_buf)
+        elif (len(raw_buf) == 176):
+                event = PebsNHM(name, comm, dso, symbol, raw_buf)
+        else:
+                event = PerfEvent(name, comm, dso, symbol, raw_buf)
+
+        return event
+
+class PerfEvent(object):
+        event_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_GENERIC):
+                self.name       = name
+                self.comm       = comm
+                self.dso        = dso
+                self.symbol     = symbol
+                self.raw_buf    = raw_buf
+                self.ev_type    = ev_type
+                PerfEvent.event_num += 1
+
+        def show(self):
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
+
+#
+# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
+# contains the context info when that event happened: the EFLAGS and
+# linear IP info, as well as all the registers.
+#
+class PebsEvent(PerfEvent):
+        pebs_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS):
+                tmp_buf=raw_buf[0:80]
+                flags, ip, ax, bx, cx, dx, si, di, bp, sp = struct.unpack('QQQQQQQQQQ', tmp_buf)
+                self.flags = flags
+                self.ip    = ip
+                self.ax    = ax
+                self.bx    = bx
+                self.cx    = cx
+                self.dx    = dx
+                self.si    = si
+                self.di    = di
+                self.bp    = bp
+                self.sp    = sp
+
+                PerfEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+                PebsEvent.pebs_num += 1
+                del tmp_buf
+
+#
+# Intel Nehalem and Westmere support PEBS plus Load Latency info which lie
+# in the four 64 bit words write after the PEBS data:
+#       Status: records the IA32_PERF_GLOBAL_STATUS register value
+#       DLA:    Data Linear Address (EIP)
+#       DSE:    Data Source Encoding, where the latency happens, hit or miss
+#               in L1/L2/L3 or IO operations
+#       LAT:    the actual latency in cycles
+#
+class PebsNHM(PebsEvent):
+        pebs_nhm_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS_LL):
+                tmp_buf=raw_buf[144:176]
+                status, dla, dse, lat = struct.unpack('QQQQ', tmp_buf)
+                self.status = status
+                self.dla = dla
+                self.dse = dse
+                self.lat = lat
+
+                PebsEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+                PebsNHM.pebs_nhm_num += 1
+                del tmp_buf

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py

@@ -0,0 +1,184 @@
+# SchedGui.py - Python extension for perf script, basic GUI code for
+#		traces drawing and overview.
+#
+# Copyright (C) 2010 by Frederic Weisbecker <fweisbec@gmail.com>
+#
+# This software is distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+
+try:
+	import wx
+except ImportError:
+	raise ImportError("You need to install the wxpython lib for this script")
+
+
+class RootFrame(wx.Frame):
+	Y_OFFSET = 100
+	RECT_HEIGHT = 100
+	RECT_SPACE = 50
+	EVENT_MARKING_WIDTH = 5
+
+	def __init__(self, sched_tracer, title, parent = None, id = -1):
+		wx.Frame.__init__(self, parent, id, title)
+
+		(self.screen_width, self.screen_height) = wx.GetDisplaySize()
+		self.screen_width -= 10
+		self.screen_height -= 10
+		self.zoom = 0.5
+		self.scroll_scale = 20
+		self.sched_tracer = sched_tracer
+		self.sched_tracer.set_root_win(self)
+		(self.ts_start, self.ts_end) = sched_tracer.interval()
+		self.update_width_virtual()
+		self.nr_rects = sched_tracer.nr_rectangles() + 1
+		self.height_virtual = RootFrame.Y_OFFSET + (self.nr_rects * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE))
+
+		# whole window panel
+		self.panel = wx.Panel(self, size=(self.screen_width, self.screen_height))
+
+		# scrollable container
+		self.scroll = wx.ScrolledWindow(self.panel)
+		self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale)
+		self.scroll.EnableScrolling(True, True)
+		self.scroll.SetFocus()
+
+		# scrollable drawing area
+		self.scroll_panel = wx.Panel(self.scroll, size=(self.screen_width - 15, self.screen_height / 2))
+		self.scroll_panel.Bind(wx.EVT_PAINT, self.on_paint)
+		self.scroll_panel.Bind(wx.EVT_KEY_DOWN, self.on_key_press)
+		self.scroll_panel.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down)
+		self.scroll.Bind(wx.EVT_PAINT, self.on_paint)
+		self.scroll.Bind(wx.EVT_KEY_DOWN, self.on_key_press)
+		self.scroll.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down)
+
+		self.scroll.Fit()
+		self.Fit()
+
+		self.scroll_panel.SetDimensions(-1, -1, self.width_virtual, self.height_virtual, wx.SIZE_USE_EXISTING)
+
+		self.txt = None
+
+		self.Show(True)
+
+	def us_to_px(self, val):
+		return val / (10 ** 3) * self.zoom
+
+	def px_to_us(self, val):
+		return (val / self.zoom) * (10 ** 3)
+
+	def scroll_start(self):
+		(x, y) = self.scroll.GetViewStart()
+		return (x * self.scroll_scale, y * self.scroll_scale)
+
+	def scroll_start_us(self):
+		(x, y) = self.scroll_start()
+		return self.px_to_us(x)
+
+	def paint_rectangle_zone(self, nr, color, top_color, start, end):
+		offset_px = self.us_to_px(start - self.ts_start)
+		width_px = self.us_to_px(end - self.ts_start)
+
+		offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE))
+		width_py = RootFrame.RECT_HEIGHT
+
+		dc = self.dc
+
+		if top_color is not None:
+			(r, g, b) = top_color
+			top_color = wx.Colour(r, g, b)
+			brush = wx.Brush(top_color, wx.SOLID)
+			dc.SetBrush(brush)
+			dc.DrawRectangle(offset_px, offset_py, width_px, RootFrame.EVENT_MARKING_WIDTH)
+			width_py -= RootFrame.EVENT_MARKING_WIDTH
+			offset_py += RootFrame.EVENT_MARKING_WIDTH
+
+		(r ,g, b) = color
+		color = wx.Colour(r, g, b)
+		brush = wx.Brush(color, wx.SOLID)
+		dc.SetBrush(brush)
+		dc.DrawRectangle(offset_px, offset_py, width_px, width_py)
+
+	def update_rectangles(self, dc, start, end):
+		start += self.ts_start
+		end += self.ts_start
+		self.sched_tracer.fill_zone(start, end)
+
+	def on_paint(self, event):
+		dc = wx.PaintDC(self.scroll_panel)
+		self.dc = dc
+
+		width = min(self.width_virtual, self.screen_width)
+		(x, y) = self.scroll_start()
+		start = self.px_to_us(x)
+		end = self.px_to_us(x + width)
+		self.update_rectangles(dc, start, end)
+
+	def rect_from_ypixel(self, y):
+		y -= RootFrame.Y_OFFSET
+		rect = y / (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)
+		height = y % (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)
+
+		if rect < 0 or rect > self.nr_rects - 1 or height > RootFrame.RECT_HEIGHT:
+			return -1
+
+		return rect
+
+	def update_summary(self, txt):
+		if self.txt:
+			self.txt.Destroy()
+		self.txt = wx.StaticText(self.panel, -1, txt, (0, (self.screen_height / 2) + 50))
+
+
+	def on_mouse_down(self, event):
+		(x, y) = event.GetPositionTuple()
+		rect = self.rect_from_ypixel(y)
+		if rect == -1:
+			return
+
+		t = self.px_to_us(x) + self.ts_start
+
+		self.sched_tracer.mouse_down(rect, t)
+
+
+	def update_width_virtual(self):
+		self.width_virtual = self.us_to_px(self.ts_end - self.ts_start)
+
+	def __zoom(self, x):
+		self.update_width_virtual()
+		(xpos, ypos) = self.scroll.GetViewStart()
+		xpos = self.us_to_px(x) / self.scroll_scale
+		self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale, xpos, ypos)
+		self.Refresh()
+
+	def zoom_in(self):
+		x = self.scroll_start_us()
+		self.zoom *= 2
+		self.__zoom(x)
+
+	def zoom_out(self):
+		x = self.scroll_start_us()
+		self.zoom /= 2
+		self.__zoom(x)
+
+
+	def on_key_press(self, event):
+		key = event.GetRawKeyCode()
+		if key == ord("+"):
+			self.zoom_in()
+			return
+		if key == ord("-"):
+			self.zoom_out()
+			return
+
+		key = event.GetKeyCode()
+		(x, y) = self.scroll.GetViewStart()
+		if key == wx.WXK_RIGHT:
+			self.scroll.Scroll(x + 1, y)
+		elif key == wx.WXK_LEFT:
+			self.scroll.Scroll(x - 1, y)
+		elif key == wx.WXK_DOWN:
+			self.scroll.Scroll(x, y + 1)
+		elif key == wx.WXK_UP:
+			self.scroll.Scroll(x, y - 1)

linux-7.2.3/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py

@@ -0,0 +1,92 @@
+# Util.py - Python extension for perf script, miscellaneous utility code
+#
+# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
+#
+# This software may be distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+from __future__ import print_function
+
+import errno, os
+
+FUTEX_WAIT = 0
+FUTEX_WAKE = 1
+FUTEX_PRIVATE_FLAG = 128
+FUTEX_CLOCK_REALTIME = 256
+FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
+
+NSECS_PER_SEC    = 1000000000
+
+def avg(total, n):
+    return total / n
+
+def nsecs(secs, nsecs):
+    return secs * NSECS_PER_SEC + nsecs
+
+def nsecs_secs(nsecs):
+    return nsecs / NSECS_PER_SEC
+
+def nsecs_nsecs(nsecs):
+    return nsecs % NSECS_PER_SEC
+
+def nsecs_str(nsecs):
+    str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
+    return str
+
+def add_stats(dict, key, value):
+	if key not in dict:
+		dict[key] = (value, value, value, 1)
+	else:
+		min, max, avg, count = dict[key]
+		if value < min:
+			min = value
+		if value > max:
+			max = value
+		avg = (avg + value) / 2
+		dict[key] = (min, max, avg, count + 1)
+
+def clear_term():
+    print("\x1b[H\x1b[2J")
+
+audit_package_warned = False
+
+try:
+	import audit
+	machine_to_id = {
+		'x86_64': audit.MACH_86_64,
+		'aarch64': audit.MACH_AARCH64,
+		'alpha'	: audit.MACH_ALPHA,
+		'ia64'	: audit.MACH_IA64,
+		'ppc'	: audit.MACH_PPC,
+		'ppc64'	: audit.MACH_PPC64,
+		'ppc64le' : audit.MACH_PPC64LE,
+		's390'	: audit.MACH_S390,
+		's390x'	: audit.MACH_S390X,
+		'i386'	: audit.MACH_X86,
+		'i586'	: audit.MACH_X86,
+		'i686'	: audit.MACH_X86,
+	}
+	try:
+		machine_to_id['armeb'] = audit.MACH_ARMEB
+	except:
+		pass
+	machine_id = machine_to_id[os.uname()[4]]
+except:
+	if not audit_package_warned:
+		audit_package_warned = True
+		print("Install the python-audit package to get syscall names.\n"
+                    "For example:\n  # apt-get install python3-audit (Ubuntu)"
+                    "\n  # yum install python3-audit (Fedora)"
+                    "\n  etc.\n")
+
+def syscall_name(id):
+	try:
+		return audit.audit_syscall_to_name(id, machine_id)
+	except:
+		return str(id)
+
+def strerror(nr):
+	try:
+		return errno.errorcode[abs(nr)]
+	except:
+		return "Unknown %d errno" % nr

linux-7.2.3/tools/perf/scripts/python/arm-cs-trace-disasm.py

@@ -0,0 +1,355 @@
+# SPDX-License-Identifier: GPL-2.0
+# arm-cs-trace-disasm.py: ARM CoreSight Trace Dump With Disassember
+#
+# Author: Tor Jeremiassen <tor@ti.com>
+#         Mathieu Poirier <mathieu.poirier@linaro.org>
+#         Leo Yan <leo.yan@linaro.org>
+#         Al Grant <Al.Grant@arm.com>
+
+from __future__ import print_function
+import os
+from os import path
+import re
+from subprocess import *
+import argparse
+import platform
+
+from perf_trace_context import perf_sample_srccode, perf_config_get
+
+# Below are some example commands for using this script.
+# Note a --kcore recording is required for accurate decode
+# due to the alternatives patching mechanism. In addition to this,
+# source line info comes from Perf, and when using kcore there is
+# no debug info. The following lists the supported features in each mode:
+#
+# +-----------+-----------------+------------------+------------------+
+# | Recording | Accurate decode | Source line dump | Disassembly dump |
+# +-----------+-----------------+------------------+------------------+
+# | --kcore   | yes             | no               | yes              |
+# | normal    | no              | yes (inaccurate) | yes (inaccurate) |
+# +-----------+-----------------+------------------+------------------+
+#
+# Output disassembly with objdump and auto detect vmlinux
+# (when running on same machine.):
+#  perf script -s scripts/python/arm-cs-trace-disasm.py -d
+#
+# Output disassembly with llvm-objdump:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#		-- -d llvm-objdump-11 -k path/to/vmlinux
+#
+# Output accurate disassembly by passing kcore to script:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#		-- -d -k perf.data/kcore_dir/kcore
+#
+# Output only source line and symbols:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py
+
+def default_objdump():
+	config = perf_config_get("annotate.objdump")
+	return config if config else "objdump"
+
+# Command line parsing.
+def int_arg(v):
+	v = int(v)
+	if v < 0:
+		raise argparse.ArgumentTypeError("Argument must be a positive integer")
+	return v
+
+args = argparse.ArgumentParser()
+args.add_argument("-k", "--vmlinux",
+		  help="Set path to vmlinux or kcore file. Omit to autodetect if running on same machine")
+args.add_argument("-d", "--objdump", nargs="?", const=default_objdump(),
+		  help="Show disassembly. Can also be used to change the objdump path"),
+args.add_argument("-v", "--verbose", action="store_true", help="Enable debugging log")
+args.add_argument("--start-time", type=int_arg, help="Monotonic clock time of sample to start from. "
+		  "See 'time' field on samples in -v mode.")
+args.add_argument("--stop-time", type=int_arg, help="Monotonic clock time of sample to stop at. "
+		  "See 'time' field on samples in -v mode.")
+args.add_argument("--start-sample", type=int_arg, help="Index of sample to start from. "
+		  "See 'index' field on samples in -v mode.")
+args.add_argument("--stop-sample", type=int_arg, help="Index of sample to stop at. "
+		  "See 'index' field on samples in -v mode.")
+
+options = args.parse_args()
+if (options.start_time and options.stop_time and
+    options.start_time >= options.stop_time):
+	print("--start-time must less than --stop-time")
+	exit(2)
+if (options.start_sample and options.stop_sample and
+    options.start_sample >= options.stop_sample):
+	print("--start-sample must less than --stop-sample")
+	exit(2)
+
+# Initialize global dicts and regular expression
+disasm_cache = dict()
+cpu_data = dict()
+disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):")
+disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:")
+cache_size = 64*1024
+sample_idx = -1
+
+glb_source_file_name	= None
+glb_line_number		= None
+glb_dso			= None
+
+kver = platform.release()
+vmlinux_paths = [
+	f"/usr/lib/debug/boot/vmlinux-{kver}.debug",
+	f"/usr/lib/debug/lib/modules/{kver}/vmlinux",
+	f"/lib/modules/{kver}/build/vmlinux",
+	f"/usr/lib/debug/boot/vmlinux-{kver}",
+	f"/boot/vmlinux-{kver}",
+	f"/boot/vmlinux",
+	f"vmlinux"
+]
+
+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 find_vmlinux():
+	if hasattr(find_vmlinux, "path"):
+		return find_vmlinux.path
+
+	for v in vmlinux_paths:
+		if os.access(v, os.R_OK):
+			find_vmlinux.path = v
+			break
+	else:
+		find_vmlinux.path = None
+
+	return find_vmlinux.path
+
+def get_dso_file_path(dso_name, dso_build_id):
+	if (dso_name == "[kernel.kallsyms]" or dso_name == "vmlinux"):
+		if (options.vmlinux):
+			return options.vmlinux;
+		else:
+			return find_vmlinux() if find_vmlinux() else dso_name
+
+	if (dso_name == "[vdso]") :
+		append = "/vdso"
+	else:
+		append = "/elf"
+
+	dso_path = os.environ['PERF_BUILDID_DIR'] + "/" + dso_name + "/" + dso_build_id + append;
+	# Replace duplicate slash chars to single slash char
+	dso_path = dso_path.replace('//', '/', 1)
+	return dso_path
+
+def read_disam(dso_fname, dso_start, start_addr, stop_addr):
+	addr_range = str(start_addr) + ":" + str(stop_addr) + ":" + dso_fname
+
+	# Don't let the cache get too big, clear it when it hits max size
+	if (len(disasm_cache) > cache_size):
+		disasm_cache.clear();
+
+	if addr_range in disasm_cache:
+		disasm_output = disasm_cache[addr_range];
+	else:
+		start_addr = start_addr - dso_start;
+		stop_addr = stop_addr - dso_start;
+		disasm = [ options.objdump, "-d", "-z",
+			   "--start-address="+format(start_addr,"#x"),
+			   "--stop-address="+format(stop_addr,"#x") ]
+		disasm += [ dso_fname ]
+		disasm_output = check_output(disasm).decode('utf-8').split('\n')
+		disasm_cache[addr_range] = disasm_output
+
+	return disasm_output
+
+def print_disam(dso_fname, dso_start, start_addr, stop_addr):
+	for line in read_disam(dso_fname, dso_start, start_addr, stop_addr):
+		m = disasm_func_re.search(line)
+		if m is None:
+			m = disasm_re.search(line)
+			if m is None:
+				continue
+		print("\t" + line)
+
+def print_sample(sample):
+	print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \
+	      "pid: %d tid: %d period: %d time: %d index: %d}" % \
+	      (sample['cpu'], sample['addr'], sample['phys_addr'], \
+	       sample['ip'], sample['pid'], sample['tid'], \
+	       sample['period'], sample['time'], sample_idx))
+
+def trace_begin():
+	print('ARM CoreSight Trace Data Assembler Dump')
+
+def trace_end():
+	print('End')
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	print(' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]))
+
+def common_start_str(comm, sample):
+	sec = int(sample["time"] / 1000000000)
+	ns = sample["time"] % 1000000000
+	cpu = sample["cpu"]
+	pid = sample["pid"]
+	tid = sample["tid"]
+	return "%16s %5u/%-5u [%04u] %9u.%09u  " % (comm, pid, tid, cpu, sec, ns)
+
+# This code is copied from intel-pt-events.py for printing source code
+# line and symbols.
+def print_srccode(comm, param_dict, sample, symbol, dso):
+	ip = sample["ip"]
+	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)
+
+	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 process_event(param_dict):
+	global cache_size
+	global options
+	global sample_idx
+
+	sample = param_dict["sample"]
+	comm = param_dict["comm"]
+
+	name = param_dict["ev_name"]
+	dso = get_optional(param_dict, "dso")
+	dso_bid = get_optional(param_dict, "dso_bid")
+	dso_start = get_optional(param_dict, "dso_map_start")
+	dso_end = get_optional(param_dict, "dso_map_end")
+	symbol = get_optional(param_dict, "symbol")
+	map_pgoff = get_optional(param_dict, "map_pgoff")
+	# check for valid map offset
+	if (str(map_pgoff) == '[unknown]'):
+		map_pgoff = 0
+
+	cpu = sample["cpu"]
+	ip = sample["ip"]
+	addr = sample["addr"]
+
+	sample_idx += 1
+
+	if (options.start_time and sample["time"] < options.start_time):
+		return
+	if (options.stop_time and sample["time"] > options.stop_time):
+		exit(0)
+	if (options.start_sample and sample_idx < options.start_sample):
+		return
+	if (options.stop_sample and sample_idx > options.stop_sample):
+		exit(0)
+
+	if (options.verbose == True):
+		print("Event type: %s" % name)
+		print_sample(sample)
+
+	# Initialize CPU data if it's empty, and directly return back
+	# if this is the first tracing event for this CPU.
+	if (cpu_data.get(str(cpu) + 'addr') == None):
+		cpu_data[str(cpu) + 'addr'] = addr
+		return
+
+	# If cannot find dso so cannot dump assembler, bail out
+	if (dso == '[unknown]'):
+		return
+
+	# Validate dso start and end addresses
+	if ((dso_start == '[unknown]') or (dso_end == '[unknown]')):
+		print("Failed to find valid dso map for dso %s" % dso)
+		return
+
+	if (name[0:12] == "instructions"):
+		print_srccode(comm, param_dict, sample, symbol, dso)
+		return
+
+	# Don't proceed if this event is not a branch sample, .
+	if (name[0:8] != "branches"):
+		return
+
+	# The format for packet is:
+	#
+	#		  +------------+------------+------------+
+	#  sample_prev:   |    addr    |    ip	    |	 cpu	 |
+	#		  +------------+------------+------------+
+	#  sample_next:   |    addr    |    ip	    |	 cpu	 |
+	#		  +------------+------------+------------+
+	#
+	# We need to combine the two continuous packets to get the instruction
+	# range for sample_prev::cpu:
+	#
+	#     [ sample_prev::addr .. sample_next::ip ]
+	#
+	# For this purose, sample_prev::addr is stored into cpu_data structure
+	# and read back for 'start_addr' when the new packet comes, and we need
+	# to use sample_next::ip to calculate 'stop_addr', plusing extra 4 for
+	# 'stop_addr' is for the sake of objdump so the final assembler dump can
+	# include last instruction for sample_next::ip.
+	start_addr = cpu_data[str(cpu) + 'addr']
+	stop_addr  = ip + 4
+
+	# Record for previous sample packet
+	cpu_data[str(cpu) + 'addr'] = addr
+
+	# Filter out zero start_address. Optionally identify CS_ETM_TRACE_ON packet
+	if (start_addr == 0):
+		if ((stop_addr == 4) and (options.verbose == True)):
+			print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
+		return
+
+	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
+		print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
+		return
+
+	if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
+		print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
+		return
+
+	if (options.objdump != None):
+		# It doesn't need to decrease virtual memory offset for disassembly
+		# for kernel dso and executable file dso, so in this case we set
+		# vm_start to zero.
+		if (dso == "[kernel.kallsyms]" or dso_start == 0x400000):
+			dso_vm_start = 0
+			map_pgoff = 0
+		else:
+			dso_vm_start = int(dso_start)
+
+		dso_fname = get_dso_file_path(dso, dso_bid)
+		if path.exists(dso_fname):
+			print_disam(dso_fname, dso_vm_start, start_addr + map_pgoff, stop_addr + map_pgoff)
+		else:
+			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr + map_pgoff, stop_addr + map_pgoff))
+
+	print_srccode(comm, param_dict, sample, symbol, dso)

linux-7.2.3/tools/perf/scripts/python/bin/compaction-times-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e compaction:mm_compaction_begin -e compaction:mm_compaction_end -e compaction:mm_compaction_migratepages -e compaction:mm_compaction_isolate_migratepages -e compaction:mm_compaction_isolate_freepages $@

linux-7.2.3/tools/perf/scripts/python/bin/compaction-times-report

@@ -0,0 +1,4 @@
+#!/bin/bash
+#description: display time taken by mm compaction
+#args: [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex]
+perf script -s "$PERF_EXEC_PATH"/scripts/python/compaction-times.py $@

linux-7.2.3/tools/perf/scripts/python/bin/event_analyzing_sample-record

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# event_analyzing_sample.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record $@

linux-7.2.3/tools/perf/scripts/python/bin/event_analyzing_sample-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: analyze all perf samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py

linux-7.2.3/tools/perf/scripts/python/bin/export-to-postgresql-record

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a postgresql database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@

linux-7.2.3/tools/perf/scripts/python/bin/export-to-postgresql-report

@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a postgresql database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls

linux-7.2.3/tools/perf/scripts/python/bin/export-to-sqlite-record

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a sqlite3 database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@

linux-7.2.3/tools/perf/scripts/python/bin/export-to-sqlite-report

@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a sqlite3 database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-sqlite-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls

linux-7.2.3/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null

linux-7.2.3/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report

@@ -0,0 +1,10 @@
+#!/bin/bash
+# description: system-wide failed syscalls, by pid
+# args: [comm]
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/failed-syscalls-by-pid.py $comm

linux-7.2.3/tools/perf/scripts/python/bin/flamegraph-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -g "$@"

linux-7.2.3/tools/perf/scripts/python/bin/flamegraph-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: create flame graphs
+perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py "$@"

linux-7.2.3/tools/perf/scripts/python/bin/futex-contention-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@

linux-7.2.3/tools/perf/scripts/python/bin/futex-contention-report

@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: futext contention measurement
+
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py

linux-7.2.3/tools/perf/scripts/python/bin/gecko-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -F 99 -g "$@"

linux-7.2.3/tools/perf/scripts/python/bin/gecko-report

@@ -0,0 +1,7 @@
+#!/bin/bash
+# description: create firefox gecko profile json format from perf.data
+if [ "$*" = "-i -" ]; then
+perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py
+else
+perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py -- "$@"
+fi

linux-7.2.3/tools/perf/scripts/python/bin/intel-pt-events-record

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+#
+# 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/"
+	echo "and for power events it probably needs to be system wide i.e. -a option"
+	echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1"
+	exit 1
+fi
+perf record $@

linux-7.2.3/tools/perf/scripts/python/bin/intel-pt-events-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: print Intel PT Events including Power Events and PTWRITE
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py

linux-7.2.3/tools/perf/scripts/python/bin/mem-phys-addr-record

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+#
+# Profiling physical memory by all retired load instructions/uops event
+# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS
+#
+
+load=`perf list | grep mem_inst_retired.all_loads`
+if [ -z "$load" ]; then
+	load=`perf list | grep mem_uops_retired.all_loads`
+fi
+if [ -z "$load" ]; then
+	echo "There is no event to count all retired load instructions/uops."
+	exit 1
+fi
+
+arg=$(echo $load | tr -d ' ')
+arg="$arg:P"
+perf record --phys-data -e $arg $@

linux-7.2.3/tools/perf/scripts/python/bin/mem-phys-addr-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: resolve physical address samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py

linux-7.2.3/tools/perf/scripts/python/bin/net_dropmonitor-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e skb:kfree_skb $@

linux-7.2.3/tools/perf/scripts/python/bin/net_dropmonitor-report

@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: display a table of dropped frames
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@

linux-7.2.3/tools/perf/scripts/python/bin/netdev-times-record

@@ -0,0 +1,8 @@
+#!/bin/bash
+perf record -e net:net_dev_xmit -e net:net_dev_queue		\
+		-e net:netif_receive_skb -e net:netif_rx		\
+		-e skb:consume_skb -e skb:kfree_skb			\
+		-e skb:skb_copy_datagram_iovec -e napi:napi_poll	\
+		-e irq:irq_handler_entry -e irq:irq_handler_exit	\
+		-e irq:softirq_entry -e irq:softirq_exit		\
+		-e irq:softirq_raise $@

linux-7.2.3/tools/perf/scripts/python/bin/netdev-times-report

@@ -0,0 +1,5 @@
+#!/bin/bash
+# description: display a process of packet and processing time
+# args: [tx] [rx] [dev=] [debug]
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@

linux-7.2.3/tools/perf/scripts/python/bin/powerpc-hcalls-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e "{powerpc:hcall_entry,powerpc:hcall_exit}" $@

linux-7.2.3/tools/perf/scripts/python/bin/powerpc-hcalls-report

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/powerpc-hcalls.py

linux-7.2.3/tools/perf/scripts/python/bin/sched-migration-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@

linux-7.2.3/tools/perf/scripts/python/bin/sched-migration-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: sched migration overview
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py

linux-7.2.3/tools/perf/scripts/python/bin/sctop-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null

linux-7.2.3/tools/perf/scripts/python/bin/sctop-report

@@ -0,0 +1,24 @@
+#!/bin/bash
+# description: syscall top
+# args: [comm] [interval]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 2 ] ; then
+    echo "usage: sctop-report [comm] [interval]"
+    exit
+fi
+if [ "$n_args" -gt 1 ] ; then
+    comm=$1
+    interval=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    interval=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sctop.py $comm $interval

linux-7.2.3/tools/perf/scripts/python/bin/stackcollapse-record

@@ -0,0 +1,8 @@
+#!/bin/sh
+
+#
+# stackcollapse.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record "$@"

linux-7.2.3/tools/perf/scripts/python/bin/stackcollapse-report

@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: produce callgraphs in short form for scripting use
+perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py "$@"

linux-7.2.3/tools/perf/scripts/python/bin/syscall-counts-by-pid-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null

linux-7.2.3/tools/perf/scripts/python/bin/syscall-counts-by-pid-report

@@ -0,0 +1,10 @@
+#!/bin/bash
+# description: system-wide syscall counts, by pid
+# args: [comm]
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts-by-pid.py $comm

linux-7.2.3/tools/perf/scripts/python/bin/syscall-counts-record

@@ -0,0 +1,3 @@
+#!/bin/bash
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null

linux-7.2.3/tools/perf/scripts/python/bin/syscall-counts-report

@@ -0,0 +1,10 @@
+#!/bin/bash
+# description: system-wide syscall counts
+# args: [comm]
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts.py $comm

linux-7.2.3/tools/perf/scripts/python/bin/task-analyzer-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e sched:sched_switch -e sched:sched_migrate_task "$@"

linux-7.2.3/tools/perf/scripts/python/bin/task-analyzer-report

@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: analyze timings of tasks
+perf script -s "$PERF_EXEC_PATH"/scripts/python/task-analyzer.py -- "$@"

linux-7.2.3/tools/perf/scripts/python/check-perf-trace.py

@@ -0,0 +1,84 @@
+# perf script event handlers, generated by perf script -g python
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# This script tests basic functionality such as flag and symbol
+# strings, common_xxx() calls back into perf, begin, end, unhandled
+# events, etc.  Basically, if this script runs successfully and
+# displays expected results, Python scripting support should be ok.
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from Core import *
+from perf_trace_context import *
+
+unhandled = autodict()
+
+def trace_begin():
+	print("trace_begin")
+	pass
+
+def trace_end():
+	print_unhandled()
+
+def irq__softirq_entry(event_name, context, common_cpu,
+		       common_secs, common_nsecs, common_pid, common_comm,
+		       common_callchain, vec):
+	print_header(event_name, common_cpu, common_secs, common_nsecs,
+		common_pid, common_comm)
+
+	print_uncommon(context)
+
+	print("vec=%s" % (symbol_str("irq__softirq_entry", "vec", vec)))
+
+def kmem__kmalloc(event_name, context, common_cpu,
+		  common_secs, common_nsecs, common_pid, common_comm,
+		  common_callchain, call_site, ptr, bytes_req, bytes_alloc,
+		  gfp_flags):
+	print_header(event_name, common_cpu, common_secs, common_nsecs,
+		common_pid, common_comm)
+
+	print_uncommon(context)
+
+	print("call_site=%u, ptr=%u, bytes_req=%u, "
+		"bytes_alloc=%u, gfp_flags=%s" %
+		(call_site, ptr, bytes_req, bytes_alloc,
+		flag_str("kmem__kmalloc", "gfp_flags", gfp_flags)))
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	try:
+		unhandled[event_name] += 1
+	except TypeError:
+		unhandled[event_name] = 1
+
+def print_header(event_name, cpu, secs, nsecs, pid, comm):
+	print("%-20s %5u %05u.%09u %8u %-20s " %
+		(event_name, cpu, secs, nsecs, pid, comm),
+		end=' ')
+
+# print trace fields not included in handler args
+def print_uncommon(context):
+	print("common_preempt_count=%d, common_flags=%s, "
+		"common_lock_depth=%d, " %
+		(common_pc(context), trace_flag_str(common_flags(context)),
+		common_lock_depth(context)))
+
+def print_unhandled():
+	keys = unhandled.keys()
+	if not keys:
+		return
+
+	print("\nunhandled events:\n")
+
+	print("%-40s  %10s" % ("event", "count"))
+	print("%-40s  %10s" % ("----------------------------------------",
+				"-----------"))
+
+	for event_name in keys:
+		print("%-40s  %10d\n" % (event_name, unhandled[event_name]))

linux-7.2.3/tools/perf/scripts/python/compaction-times.py

@@ -0,0 +1,311 @@
+# report time spent in compaction
+# Licensed under the terms of the GNU GPL License version 2
+
+# testing:
+# 'echo 1 > /proc/sys/vm/compact_memory' to force compaction of all zones
+
+import os
+import sys
+import re
+
+import signal
+signal.signal(signal.SIGPIPE, signal.SIG_DFL)
+
+usage = "usage: perf script report compaction-times.py -- [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex]\n"
+
+class popt:
+	DISP_DFL = 0
+	DISP_PROC = 1
+	DISP_PROC_VERBOSE=2
+
+class topt:
+	DISP_TIME = 0
+	DISP_MIG = 1
+	DISP_ISOLFREE = 2
+	DISP_ISOLMIG = 4
+	DISP_ALL = 7
+
+class comm_filter:
+	def __init__(self, re):
+		self.re = re
+
+	def filter(self, pid, comm):
+		m = self.re.search(comm)
+		return m == None or m.group() == ""
+
+class pid_filter:
+	def __init__(self, low, high):
+		self.low = (0 if low == "" else int(low))
+		self.high = (0 if high == "" else int(high))
+
+	def filter(self, pid, comm):
+		return not (pid >= self.low and (self.high == 0 or pid <= self.high))
+
+def set_type(t):
+	global opt_disp
+	opt_disp = (t if opt_disp == topt.DISP_ALL else opt_disp|t)
+
+def ns(sec, nsec):
+	return (sec * 1000000000) + nsec
+
+def time(ns):
+	return "%dns" % ns if opt_ns else "%dus" % (round(ns, -3) / 1000)
+
+class pair:
+	def __init__(self, aval, bval, alabel = None, blabel = None):
+		self.alabel = alabel
+		self.blabel = blabel
+		self.aval = aval
+		self.bval = bval
+
+	def __add__(self, rhs):
+		self.aval += rhs.aval
+		self.bval += rhs.bval
+		return self
+
+	def __str__(self):
+		return "%s=%d %s=%d" % (self.alabel, self.aval, self.blabel, self.bval)
+
+class cnode:
+	def __init__(self, ns):
+		self.ns = ns
+		self.migrated = pair(0, 0, "moved", "failed")
+		self.fscan = pair(0,0, "scanned", "isolated")
+		self.mscan = pair(0,0, "scanned", "isolated")
+
+	def __add__(self, rhs):
+		self.ns += rhs.ns
+		self.migrated += rhs.migrated
+		self.fscan += rhs.fscan
+		self.mscan += rhs.mscan
+		return self
+
+	def __str__(self):
+		prev = 0
+		s = "%s " % time(self.ns)
+		if (opt_disp & topt.DISP_MIG):
+			s += "migration: %s" % self.migrated
+			prev = 1
+		if (opt_disp & topt.DISP_ISOLFREE):
+			s += "%sfree_scanner: %s" % (" " if prev else "", self.fscan)
+			prev = 1
+		if (opt_disp & topt.DISP_ISOLMIG):
+			s += "%smigration_scanner: %s" % (" " if prev else "", self.mscan)
+		return s
+
+	def complete(self, secs, nsecs):
+		self.ns = ns(secs, nsecs) - self.ns
+
+	def increment(self, migrated, fscan, mscan):
+		if (migrated != None):
+			self.migrated += migrated
+		if (fscan != None):
+			self.fscan += fscan
+		if (mscan != None):
+			self.mscan += mscan
+
+
+class chead:
+	heads = {}
+	val = cnode(0);
+	fobj = None
+
+	@classmethod
+	def add_filter(cls, filter):
+		cls.fobj = filter
+
+	@classmethod
+	def create_pending(cls, pid, comm, start_secs, start_nsecs):
+		filtered = 0
+		try:
+			head = cls.heads[pid]
+			filtered = head.is_filtered()
+		except KeyError:
+			if cls.fobj != None:
+				filtered = cls.fobj.filter(pid, comm)
+			head = cls.heads[pid] = chead(comm, pid, filtered)
+
+		if not filtered:
+			head.mark_pending(start_secs, start_nsecs)
+
+	@classmethod
+	def increment_pending(cls, pid, migrated, fscan, mscan):
+		head = cls.heads[pid]
+		if not head.is_filtered():
+			if head.is_pending():
+				head.do_increment(migrated, fscan, mscan)
+			else:
+				sys.stderr.write("missing start compaction event for pid %d\n" % pid)
+
+	@classmethod
+	def complete_pending(cls, pid, secs, nsecs):
+		head = cls.heads[pid]
+		if not head.is_filtered():
+			if head.is_pending():
+				head.make_complete(secs, nsecs)
+			else:
+				sys.stderr.write("missing start compaction event for pid %d\n" % pid)
+
+	@classmethod
+	def gen(cls):
+		if opt_proc != popt.DISP_DFL:
+			for i in cls.heads:
+				yield cls.heads[i]
+
+	@classmethod
+	def str(cls):
+		return cls.val
+
+	def __init__(self, comm, pid, filtered):
+		self.comm = comm
+		self.pid = pid
+		self.val = cnode(0)
+		self.pending = None
+		self.filtered = filtered
+		self.list = []
+
+	def __add__(self, rhs):
+		self.ns += rhs.ns
+		self.val += rhs.val
+		return self
+
+	def mark_pending(self, secs, nsecs):
+		self.pending = cnode(ns(secs, nsecs))
+
+	def do_increment(self, migrated, fscan, mscan):
+		self.pending.increment(migrated, fscan, mscan)
+
+	def make_complete(self, secs, nsecs):
+		self.pending.complete(secs, nsecs)
+		chead.val += self.pending
+
+		if opt_proc != popt.DISP_DFL:
+			self.val += self.pending
+
+			if opt_proc == popt.DISP_PROC_VERBOSE:
+				self.list.append(self.pending)
+		self.pending = None
+
+	def enumerate(self):
+		if opt_proc == popt.DISP_PROC_VERBOSE and not self.is_filtered():
+			for i, pelem in enumerate(self.list):
+				sys.stdout.write("%d[%s].%d: %s\n" % (self.pid, self.comm, i+1, pelem))
+
+	def is_pending(self):
+		return self.pending != None
+
+	def is_filtered(self):
+		return self.filtered
+
+	def display(self):
+		if not self.is_filtered():
+			sys.stdout.write("%d[%s]: %s\n" % (self.pid, self.comm, self.val))
+
+
+def trace_end():
+	sys.stdout.write("total: %s\n" % chead.str())
+	for i in chead.gen():
+		i.display(),
+		i.enumerate()
+
+def compaction__mm_compaction_migratepages(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, nr_migrated, nr_failed):
+
+	chead.increment_pending(common_pid,
+		pair(nr_migrated, nr_failed), None, None)
+
+def compaction__mm_compaction_isolate_freepages(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, start_pfn, end_pfn, nr_scanned, nr_taken):
+
+	chead.increment_pending(common_pid,
+		None, pair(nr_scanned, nr_taken), None)
+
+def compaction__mm_compaction_isolate_migratepages(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, start_pfn, end_pfn, nr_scanned, nr_taken):
+
+	chead.increment_pending(common_pid,
+		None, None, pair(nr_scanned, nr_taken))
+
+def compaction__mm_compaction_end(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, zone_start, migrate_start, free_start, zone_end,
+	sync, status):
+
+	chead.complete_pending(common_pid, common_secs, common_nsecs)
+
+def compaction__mm_compaction_begin(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, zone_start, migrate_start, free_start, zone_end,
+	sync):
+
+	chead.create_pending(common_pid, common_comm, common_secs, common_nsecs)
+
+def pr_help():
+	global usage
+
+	sys.stdout.write(usage)
+	sys.stdout.write("\n")
+	sys.stdout.write("-h	display this help\n")
+	sys.stdout.write("-p	display by process\n")
+	sys.stdout.write("-pv	display by process (verbose)\n")
+	sys.stdout.write("-t	display stall times only\n")
+	sys.stdout.write("-m	display stats for migration\n")
+	sys.stdout.write("-fs	display stats for free scanner\n")
+	sys.stdout.write("-ms	display stats for migration scanner\n")
+	sys.stdout.write("-u	display results in microseconds (default nanoseconds)\n")
+
+
+comm_re = None
+pid_re = None
+pid_regex = r"^(\d*)-(\d*)$|^(\d*)$"
+
+opt_proc = popt.DISP_DFL
+opt_disp = topt.DISP_ALL
+
+opt_ns = True
+
+argc = len(sys.argv) - 1
+if argc >= 1:
+	pid_re = re.compile(pid_regex)
+
+	for i, opt in enumerate(sys.argv[1:]):
+		if opt[0] == "-":
+			if opt == "-h":
+				pr_help()
+				exit(0);
+			elif opt == "-p":
+				opt_proc = popt.DISP_PROC
+			elif opt == "-pv":
+				opt_proc = popt.DISP_PROC_VERBOSE
+			elif opt == '-u':
+				opt_ns = False
+			elif opt == "-t":
+				set_type(topt.DISP_TIME)
+			elif opt == "-m":
+				set_type(topt.DISP_MIG)
+			elif opt == "-fs":
+				set_type(topt.DISP_ISOLFREE)
+			elif opt == "-ms":
+				set_type(topt.DISP_ISOLMIG)
+			else:
+				sys.exit(usage)
+
+		elif i == argc - 1:
+			m = pid_re.search(opt)
+			if m != None and m.group() != "":
+				if m.group(3) != None:
+					f = pid_filter(m.group(3), m.group(3))
+				else:
+					f = pid_filter(m.group(1), m.group(2))
+			else:
+				try:
+					comm_re=re.compile(opt)
+				except:
+					sys.stderr.write("invalid regex '%s'" % opt)
+					sys.exit(usage)
+				f = comm_filter(comm_re)
+
+			chead.add_filter(f)

linux-7.2.3/tools/perf/scripts/python/event_analyzing_sample.py

@@ -0,0 +1,192 @@
+# event_analyzing_sample.py: general event handler in python
+# SPDX-License-Identifier: GPL-2.0
+#
+# Current perf report is already very powerful with the annotation integrated,
+# and this script is not trying to be as powerful as perf report, but
+# providing end user/developer a flexible way to analyze the events other
+# than trace points.
+#
+# The 2 database related functions in this script just show how to gather
+# the basic information, and users can modify and write their own functions
+# according to their specific requirement.
+#
+# The first function "show_general_events" just does a basic grouping for all
+# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is
+# for a x86 HW PMU event: PEBS with load latency data.
+#
+
+from __future__ import print_function
+
+import os
+import sys
+import math
+import struct
+import sqlite3
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from EventClass import *
+
+#
+# If the perf.data has a big number of samples, then the insert operation
+# will be very time consuming (about 10+ minutes for 10000 samples) if the
+# .db database is on disk. Move the .db file to RAM based FS to speedup
+# the handling, which will cut the time down to several seconds.
+#
+con = sqlite3.connect("/dev/shm/perf.db")
+con.isolation_level = None
+
+def trace_begin():
+        print("In trace_begin:\n")
+
+        #
+        # Will create several tables at the start, pebs_ll is for PEBS data with
+        # load latency info, while gen_events is for general event.
+        #
+        con.execute("""
+                create table if not exists gen_events (
+                        name text,
+                        symbol text,
+                        comm text,
+                        dso text
+                );""")
+        con.execute("""
+                create table if not exists pebs_ll (
+                        name text,
+                        symbol text,
+                        comm text,
+                        dso text,
+                        flags integer,
+                        ip integer,
+                        status integer,
+                        dse integer,
+                        dla integer,
+                        lat integer
+                );""")
+
+#
+# Create and insert event object to a database so that user could
+# do more analysis with simple database commands.
+#
+def process_event(param_dict):
+        event_attr = param_dict["attr"]
+        sample     = param_dict["sample"]
+        raw_buf    = param_dict["raw_buf"]
+        comm       = param_dict["comm"]
+        name       = param_dict["ev_name"]
+
+        # Symbol and dso info are not always resolved
+        if ("dso" in param_dict):
+                dso = param_dict["dso"]
+        else:
+                dso = "Unknown_dso"
+
+        if ("symbol" in param_dict):
+                symbol = param_dict["symbol"]
+        else:
+                symbol = "Unknown_symbol"
+
+        # Create the event object and insert it to the right table in database
+        event = create_event(name, comm, dso, symbol, raw_buf)
+        insert_db(event)
+
+def insert_db(event):
+        if event.ev_type == EVTYPE_GENERIC:
+                con.execute("insert into gen_events values(?, ?, ?, ?)",
+                                (event.name, event.symbol, event.comm, event.dso))
+        elif event.ev_type == EVTYPE_PEBS_LL:
+                event.ip &= 0x7fffffffffffffff
+                event.dla &= 0x7fffffffffffffff
+                con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+                        (event.name, event.symbol, event.comm, event.dso, event.flags,
+                                event.ip, event.status, event.dse, event.dla, event.lat))
+
+def trace_end():
+        print("In trace_end:\n")
+        # We show the basic info for the 2 type of event classes
+        show_general_events()
+        show_pebs_ll()
+        con.close()
+
+#
+# As the event number may be very big, so we can't use linear way
+# to show the histogram in real number, but use a log2 algorithm.
+#
+
+def num2sym(num):
+        # Each number will have at least one '#'
+        snum = '#' * (int)(math.log(num, 2) + 1)
+        return snum
+
+def show_general_events():
+
+        # Check the total record number in the table
+        count = con.execute("select count(*) from gen_events")
+        for t in count:
+                print("There is %d records in gen_events table" % t[0])
+                if t[0] == 0:
+                        return
+
+        print("Statistics about the general events grouped by thread/symbol/dso: \n")
+
+         # Group by thread
+        commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)")
+        print("\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42))
+        for row in commq:
+             print("%16s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+        # Group by symbol
+        print("\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58))
+        symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)")
+        for row in symbolq:
+             print("%32s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+        # Group by dso
+        print("\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74))
+        dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)")
+        for row in dsoq:
+             print("%40s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+#
+# This function just shows the basic info, and we could do more with the
+# data in the tables, like checking the function parameters when some
+# big latency events happen.
+#
+def show_pebs_ll():
+
+        count = con.execute("select count(*) from pebs_ll")
+        for t in count:
+                print("There is %d records in pebs_ll table" % t[0])
+                if t[0] == 0:
+                        return
+
+        print("Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n")
+
+        # Group by thread
+        commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)")
+        print("\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42))
+        for row in commq:
+             print("%16s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+        # Group by symbol
+        print("\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58))
+        symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)")
+        for row in symbolq:
+             print("%32s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+        # Group by dse
+        dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)")
+        print("\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58))
+        for row in dseq:
+             print("%32s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+        # Group by latency
+        latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat")
+        print("\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58))
+        for row in latq:
+             print("%32s %8d     %s" % (row[0], row[1], num2sym(row[1])))
+
+def trace_unhandled(event_name, context, event_fields_dict):
+        print (' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]))

linux-7.2.3/tools/perf/scripts/python/export-to-sqlite.py

@@ -0,0 +1,799 @@
+# export-to-sqlite.py: export perf data to a sqlite3 database
+# Copyright (c) 2017, 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,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+from __future__ import print_function
+
+import os
+import sys
+import struct
+import datetime
+
+# To use this script you will need to have installed package python-pyside which
+# provides LGPL-licensed Python bindings for Qt.  You will also need the package
+# libqt4-sql-sqlite for Qt sqlite3 support.
+#
+# Examples of installing pyside:
+#
+# ubuntu:
+#
+#	$ sudo apt-get install python-pyside.qtsql libqt4-sql-psql
+#
+#	Alternately, to use Python3 and/or pyside 2, one of the following:
+#
+#		$ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql
+#		$ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql
+#		$ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql
+# fedora:
+#
+#	$ sudo yum install python-pyside
+#
+#	Alternately, to use Python3 and/or pyside 2, one of the following:
+#		$ sudo yum install python3-pyside
+#		$ pip install --user PySide2
+#		$ pip3 install --user PySide2
+#
+# An example of using this script with Intel PT:
+#
+#	$ perf record -e intel_pt//u ls
+#	$ perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
+#	2017-07-31 14:26:07.326913 Creating database...
+#	2017-07-31 14:26:07.538097 Writing records...
+#	2017-07-31 14:26:09.889292 Adding indexes
+#	2017-07-31 14:26:09.958746 Done
+#
+# To browse the database, sqlite3 can be used e.g.
+#
+#	$ sqlite3 pt_example
+#	sqlite> .header on
+#	sqlite> select * from samples_view where id < 10;
+#	sqlite> .mode column
+#	sqlite> select * from samples_view where id < 10;
+#	sqlite> .tables
+#	sqlite> .schema samples_view
+#	sqlite> .quit
+#
+# An example of using the database is provided by the script
+# exported-sql-viewer.py.  Refer to that script for details.
+#
+# The database structure is practically the same as created by the script
+# export-to-postgresql.py. Refer to that script for details.  A notable
+# difference is  the 'transaction' column of the 'samples' table which is
+# renamed 'transaction_' in sqlite because 'transaction' is a reserved word.
+
+pyside_version_1 = True
+if not "pyside-version-1" in sys.argv:
+	try:
+		from PySide2.QtSql import *
+		pyside_version_1 = False
+	except:
+		pass
+
+if pyside_version_1:
+	from PySide.QtSql import *
+
+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 *
+
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = False
+
+def printerr(*args, **keyword_args):
+	print(*args, file=sys.stderr, **keyword_args)
+
+def printdate(*args, **kw_args):
+        print(datetime.datetime.today(), *args, sep=' ', **kw_args)
+
+def usage():
+	printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]");
+	printerr("where:  columns            'all' or 'branches'");
+	printerr("        calls              'calls' => create calls and call_paths table");
+	printerr("        callchains         'callchains' => create call_paths table");
+	printerr("        pyside-version-1   'pyside-version-1' => use pyside version 1");
+	raise Exception("Too few or bad arguments")
+
+if (len(sys.argv) < 2):
+	usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+	columns = sys.argv[2]
+else:
+	columns = "all"
+
+if columns not in ("all", "branches"):
+	usage()
+
+branches = (columns == "branches")
+
+for i in range(3,len(sys.argv)):
+	if (sys.argv[i] == "calls"):
+		perf_db_export_calls = True
+	elif (sys.argv[i] == "callchains"):
+		perf_db_export_callchains = True
+	elif (sys.argv[i] == "pyside-version-1"):
+		pass
+	else:
+		usage()
+
+def do_query(q, s):
+	if (q.exec_(s)):
+		return
+	raise Exception("Query failed: " + q.lastError().text())
+
+def do_query_(q):
+	if (q.exec_()):
+		return
+	raise Exception("Query failed: " + q.lastError().text())
+
+printdate("Creating database ...")
+
+db_exists = False
+try:
+	f = open(dbname)
+	f.close()
+	db_exists = True
+except:
+	pass
+
+if db_exists:
+	raise Exception(dbname + " already exists")
+
+db = QSqlDatabase.addDatabase('QSQLITE')
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+
+do_query(query, 'PRAGMA journal_mode = OFF')
+do_query(query, 'BEGIN TRANSACTION')
+
+do_query(query, 'CREATE TABLE selected_events ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'name		varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'pid		integer,'
+		'root_dir 	varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'machine_id	bigint,'
+		'process_id	bigint,'
+		'pid		integer,'
+		'tid		integer)')
+do_query(query, 'CREATE TABLE comms ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'comm		varchar(16),'
+		'c_thread_id	bigint,'
+		'c_time		bigint,'
+		'exec_flag	boolean)')
+do_query(query, 'CREATE TABLE comm_threads ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'comm_id	bigint,'
+		'thread_id	bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'machine_id	bigint,'
+		'short_name	varchar(256),'
+		'long_name	varchar(4096),'
+		'build_id	varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'dso_id		bigint,'
+		'sym_start	bigint,'
+		'sym_end	bigint,'
+		'binding	integer,'
+		'name		varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'name		varchar(80))')
+
+if branches:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean,'
+		'call_path_id	bigint,'
+		'insn_count	bigint,'
+		'cyc_count	bigint,'
+		'flags		integer)')
+else:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint,'
+		'period		bigint,'
+		'weight		bigint,'
+		'transaction_	bigint,'
+		'data_src	bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean,'
+		'call_path_id	bigint,'
+		'insn_count	bigint,'
+		'cyc_count	bigint,'
+		'flags		integer)')
+
+if perf_db_export_calls or perf_db_export_callchains:
+	do_query(query, 'CREATE TABLE call_paths ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'parent_id	bigint,'
+		'symbol_id	bigint,'
+		'ip		bigint)')
+if perf_db_export_calls:
+	do_query(query, 'CREATE TABLE calls ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'call_path_id	bigint,'
+		'call_time	bigint,'
+		'return_time	bigint,'
+		'branch_count	bigint,'
+		'call_id	bigint,'
+		'return_id	bigint,'
+		'parent_call_path_id	bigint,'
+		'flags		integer,'
+		'parent_id	bigint,'
+		'insn_count	bigint,'
+		'cyc_count	bigint)')
+
+do_query(query, 'CREATE TABLE ptwrite ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'payload	bigint,'
+		'exact_ip	integer)')
+
+do_query(query, 'CREATE TABLE cbr ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'cbr		integer,'
+		'mhz		integer,'
+		'percent	integer)')
+
+do_query(query, 'CREATE TABLE mwait ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'hints		integer,'
+		'extensions	integer)')
+
+do_query(query, 'CREATE TABLE pwre ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'cstate		integer,'
+		'subcstate	integer,'
+		'hw		integer)')
+
+do_query(query, 'CREATE TABLE exstop ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'exact_ip	integer)')
+
+do_query(query, 'CREATE TABLE pwrx ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'deepest_cstate	integer,'
+		'last_cstate	integer,'
+		'wake_reason	integer)')
+
+do_query(query, 'CREATE TABLE context_switches ('
+		'id		integer		NOT NULL	PRIMARY KEY,'
+		'machine_id	bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'thread_out_id	bigint,'
+		'comm_out_id	bigint,'
+		'thread_in_id	bigint,'
+		'comm_in_id	bigint,'
+		'flags		integer)')
+
+# printf was added to sqlite in version 3.8.3
+sqlite_has_printf = False
+try:
+	do_query(query, 'SELECT printf("") FROM machines')
+	sqlite_has_printf = True
+except:
+	pass
+
+def emit_to_hex(x):
+	if sqlite_has_printf:
+		return 'printf("%x", ' + x + ')'
+	else:
+		return x
+
+do_query(query, 'CREATE VIEW machines_view AS '
+	'SELECT '
+		'id,'
+		'pid,'
+		'root_dir,'
+		'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest'
+	' FROM machines')
+
+do_query(query, 'CREATE VIEW dsos_view AS '
+	'SELECT '
+		'id,'
+		'machine_id,'
+		'(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+		'short_name,'
+		'long_name,'
+		'build_id'
+	' FROM dsos')
+
+do_query(query, 'CREATE VIEW symbols_view AS '
+	'SELECT '
+		'id,'
+		'name,'
+		'(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,'
+		'dso_id,'
+		'sym_start,'
+		'sym_end,'
+		'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding'
+	' FROM symbols')
+
+do_query(query, 'CREATE VIEW threads_view AS '
+	'SELECT '
+		'id,'
+		'machine_id,'
+		'(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+		'process_id,'
+		'pid,'
+		'tid'
+	' FROM threads')
+
+do_query(query, 'CREATE VIEW comm_threads_view AS '
+	'SELECT '
+		'comm_id,'
+		'(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+		'thread_id,'
+		'(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+		'(SELECT tid FROM threads WHERE id = thread_id) AS tid'
+	' FROM comm_threads')
+
+if perf_db_export_calls or perf_db_export_callchains:
+	do_query(query, 'CREATE VIEW call_paths_view AS '
+		'SELECT '
+			'c.id,'
+			+ emit_to_hex('c.ip') + ' AS ip,'
+			'c.symbol_id,'
+			'(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,'
+			'(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,'
+			'(SELECT dso FROM symbols_view  WHERE id = c.symbol_id) AS dso_short_name,'
+			'c.parent_id,'
+			+ emit_to_hex('p.ip') + ' AS parent_ip,'
+			'p.symbol_id AS parent_symbol_id,'
+			'(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,'
+			'(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,'
+			'(SELECT dso FROM symbols_view  WHERE id = p.symbol_id) AS parent_dso_short_name'
+		' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id')
+if perf_db_export_calls:
+	do_query(query, 'CREATE VIEW calls_view AS '
+		'SELECT '
+			'calls.id,'
+			'thread_id,'
+			'(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+			'(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+			'(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+			'call_path_id,'
+			+ emit_to_hex('ip') + ' AS ip,'
+			'symbol_id,'
+			'(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+			'call_time,'
+			'return_time,'
+			'return_time - call_time AS elapsed_time,'
+			'branch_count,'
+			'insn_count,'
+			'cyc_count,'
+			'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,'
+			'call_id,'
+			'return_id,'
+			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
+			'parent_call_path_id,'
+			'calls.parent_id'
+		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+	'SELECT '
+		'id,'
+		'time,'
+		'cpu,'
+		'(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+		'(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+		'(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+		'(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+		+ emit_to_hex('ip') + ' AS ip_hex,'
+		'(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+		'sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+		+ emit_to_hex('to_ip') + ' AS to_ip_hex,'
+		'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+		'to_sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+		'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+		'in_tx,'
+		'insn_count,'
+		'cyc_count,'
+		'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,'
+		'flags'
+	' FROM samples')
+
+do_query(query, 'CREATE VIEW ptwrite_view AS '
+	'SELECT '
+		'ptwrite.id,'
+		'time,'
+		'cpu,'
+		+ emit_to_hex('payload') + ' AS payload_hex,'
+		'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
+	' FROM ptwrite'
+	' INNER JOIN samples ON samples.id = ptwrite.id')
+
+do_query(query, 'CREATE VIEW cbr_view AS '
+	'SELECT '
+		'cbr.id,'
+		'time,'
+		'cpu,'
+		'cbr,'
+		'mhz,'
+		'percent'
+	' FROM cbr'
+	' INNER JOIN samples ON samples.id = cbr.id')
+
+do_query(query, 'CREATE VIEW mwait_view AS '
+	'SELECT '
+		'mwait.id,'
+		'time,'
+		'cpu,'
+		+ emit_to_hex('hints') + ' AS hints_hex,'
+		+ emit_to_hex('extensions') + ' AS extensions_hex'
+	' FROM mwait'
+	' INNER JOIN samples ON samples.id = mwait.id')
+
+do_query(query, 'CREATE VIEW pwre_view AS '
+	'SELECT '
+		'pwre.id,'
+		'time,'
+		'cpu,'
+		'cstate,'
+		'subcstate,'
+		'CASE WHEN hw=0 THEN \'False\' ELSE \'True\' END AS hw'
+	' FROM pwre'
+	' INNER JOIN samples ON samples.id = pwre.id')
+
+do_query(query, 'CREATE VIEW exstop_view AS '
+	'SELECT '
+		'exstop.id,'
+		'time,'
+		'cpu,'
+		'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
+	' FROM exstop'
+	' INNER JOIN samples ON samples.id = exstop.id')
+
+do_query(query, 'CREATE VIEW pwrx_view AS '
+	'SELECT '
+		'pwrx.id,'
+		'time,'
+		'cpu,'
+		'deepest_cstate,'
+		'last_cstate,'
+		'CASE     WHEN wake_reason=1 THEN \'Interrupt\''
+			' WHEN wake_reason=2 THEN \'Timer Deadline\''
+			' WHEN wake_reason=4 THEN \'Monitored Address\''
+			' WHEN wake_reason=8 THEN \'HW\''
+			' ELSE wake_reason '
+		'END AS wake_reason'
+	' FROM pwrx'
+	' INNER JOIN samples ON samples.id = pwrx.id')
+
+do_query(query, 'CREATE VIEW power_events_view AS '
+	'SELECT '
+		'samples.id,'
+		'time,'
+		'cpu,'
+		'selected_events.name AS event,'
+		'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT cbr FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS cbr,'
+		'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT mhz FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS mhz,'
+		'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT percent FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS percent,'
+		'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('hints') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS hints_hex,'
+		'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('extensions') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS extensions_hex,'
+		'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT cstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS cstate,'
+		'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT subcstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS subcstate,'
+		'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT hw FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS hw,'
+		'CASE WHEN selected_events.name=\'exstop\' THEN (SELECT exact_ip FROM exstop WHERE exstop.id = samples.id) ELSE "" END AS exact_ip,'
+		'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT deepest_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS deepest_cstate,'
+		'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT last_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS last_cstate,'
+		'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT '
+			'CASE     WHEN wake_reason=1 THEN \'Interrupt\''
+				' WHEN wake_reason=2 THEN \'Timer Deadline\''
+				' WHEN wake_reason=4 THEN \'Monitored Address\''
+				' WHEN wake_reason=8 THEN \'HW\''
+				' ELSE wake_reason '
+			'END'
+		' FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS wake_reason'
+	' FROM samples'
+	' INNER JOIN selected_events ON selected_events.id = evsel_id'
+	' WHERE selected_events.name IN (\'cbr\',\'mwait\',\'exstop\',\'pwre\',\'pwrx\')')
+
+do_query(query, 'CREATE VIEW context_switches_view AS '
+	'SELECT '
+		'context_switches.id,'
+		'context_switches.machine_id,'
+		'context_switches.time,'
+		'context_switches.cpu,'
+		'th_out.pid AS pid_out,'
+		'th_out.tid AS tid_out,'
+		'comm_out.comm AS comm_out,'
+		'th_in.pid AS pid_in,'
+		'th_in.tid AS tid_in,'
+		'comm_in.comm AS comm_in,'
+		'CASE	  WHEN context_switches.flags = 0 THEN \'in\''
+			' WHEN context_switches.flags = 1 THEN \'out\''
+			' WHEN context_switches.flags = 3 THEN \'out preempt\''
+			' ELSE context_switches.flags '
+		'END AS flags'
+	' FROM context_switches'
+	' INNER JOIN threads AS th_out ON th_out.id   = context_switches.thread_out_id'
+	' INNER JOIN threads AS th_in  ON th_in.id    = context_switches.thread_in_id'
+	' INNER JOIN comms AS comm_out ON comm_out.id = context_switches.comm_out_id'
+	' INNER JOIN comms AS comm_in  ON comm_in.id  = context_switches.comm_in_id')
+
+do_query(query, 'END TRANSACTION')
+
+evsel_query = QSqlQuery(db)
+evsel_query.prepare("INSERT INTO selected_events VALUES (?, ?)")
+machine_query = QSqlQuery(db)
+machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)")
+thread_query = QSqlQuery(db)
+thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)")
+comm_query = QSqlQuery(db)
+comm_query.prepare("INSERT INTO comms VALUES (?, ?, ?, ?, ?)")
+comm_thread_query = QSqlQuery(db)
+comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)")
+dso_query = QSqlQuery(db)
+dso_query.prepare("INSERT INTO dsos VALUES (?, ?, ?, ?, ?)")
+symbol_query = QSqlQuery(db)
+symbol_query.prepare("INSERT INTO symbols VALUES (?, ?, ?, ?, ?, ?)")
+branch_type_query = QSqlQuery(db)
+branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)")
+sample_query = QSqlQuery(db)
+if branches:
+	sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+else:
+	sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+if perf_db_export_calls or perf_db_export_callchains:
+	call_path_query = QSqlQuery(db)
+	call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)")
+if perf_db_export_calls:
+	call_query = QSqlQuery(db)
+	call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+ptwrite_query = QSqlQuery(db)
+ptwrite_query.prepare("INSERT INTO ptwrite VALUES (?, ?, ?)")
+cbr_query = QSqlQuery(db)
+cbr_query.prepare("INSERT INTO cbr VALUES (?, ?, ?, ?)")
+mwait_query = QSqlQuery(db)
+mwait_query.prepare("INSERT INTO mwait VALUES (?, ?, ?)")
+pwre_query = QSqlQuery(db)
+pwre_query.prepare("INSERT INTO pwre VALUES (?, ?, ?, ?)")
+exstop_query = QSqlQuery(db)
+exstop_query.prepare("INSERT INTO exstop VALUES (?, ?)")
+pwrx_query = QSqlQuery(db)
+pwrx_query.prepare("INSERT INTO pwrx VALUES (?, ?, ?, ?)")
+context_switch_query = QSqlQuery(db)
+context_switch_query.prepare("INSERT INTO context_switches VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)")
+
+def trace_begin():
+	printdate("Writing records...")
+	do_query(query, 'BEGIN TRANSACTION')
+	# id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+	evsel_table(0, "unknown")
+	machine_table(0, 0, "unknown")
+	thread_table(0, 0, 0, -1, -1)
+	comm_table(0, "unknown", 0, 0, 0)
+	dso_table(0, 0, "unknown", "unknown", "")
+	symbol_table(0, 0, 0, 0, 0, "unknown")
+	sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+	if perf_db_export_calls or perf_db_export_callchains:
+		call_path_table(0, 0, 0, 0)
+		call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+
+unhandled_count = 0
+
+def is_table_empty(table_name):
+	do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1');
+	if query.next():
+		return False
+	return True
+
+def drop(table_name):
+	do_query(query, 'DROP VIEW ' + table_name + '_view');
+	do_query(query, 'DROP TABLE ' + table_name);
+
+def trace_end():
+	do_query(query, 'END TRANSACTION')
+
+	printdate("Adding indexes")
+	if perf_db_export_calls:
+		do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
+		do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
+		do_query(query, 'ALTER TABLE comms ADD has_calls boolean')
+		do_query(query, 'UPDATE comms SET has_calls = 1 WHERE comms.id IN (SELECT DISTINCT comm_id FROM calls)')
+
+	printdate("Dropping unused tables")
+	if is_table_empty("ptwrite"):
+		drop("ptwrite")
+	if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
+		do_query(query, 'DROP VIEW power_events_view');
+		drop("mwait")
+		drop("pwre")
+		drop("exstop")
+		drop("pwrx")
+		if is_table_empty("cbr"):
+			drop("cbr")
+	if is_table_empty("context_switches"):
+		drop("context_switches")
+
+	if (unhandled_count):
+		printdate("Warning: ", unhandled_count, " unhandled events")
+	printdate("Done")
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	global unhandled_count
+	unhandled_count += 1
+
+def sched__sched_switch(*x):
+	pass
+
+def bind_exec(q, n, x):
+	for xx in x[0:n]:
+		q.addBindValue(str(xx))
+	do_query_(q)
+
+def evsel_table(*x):
+	bind_exec(evsel_query, 2, x)
+
+def machine_table(*x):
+	bind_exec(machine_query, 3, x)
+
+def thread_table(*x):
+	bind_exec(thread_query, 5, x)
+
+def comm_table(*x):
+	bind_exec(comm_query, 5, x)
+
+def comm_thread_table(*x):
+	bind_exec(comm_thread_query, 3, x)
+
+def dso_table(*x):
+	bind_exec(dso_query, 5, x)
+
+def symbol_table(*x):
+	bind_exec(symbol_query, 6, x)
+
+def branch_type_table(*x):
+	bind_exec(branch_type_query, 2, x)
+
+def sample_table(*x):
+	if branches:
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:25]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
+	else:
+		bind_exec(sample_query, 25, x)
+
+def call_path_table(*x):
+	bind_exec(call_path_query, 4, x)
+
+def call_return_table(*x):
+	bind_exec(call_query, 14, x)
+
+def ptwrite(id, raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	flags = data[0]
+	payload = data[1]
+	exact_ip = flags & 1
+	ptwrite_query.addBindValue(str(id))
+	ptwrite_query.addBindValue(str(payload))
+	ptwrite_query.addBindValue(str(exact_ip))
+	do_query_(ptwrite_query)
+
+def cbr(id, raw_buf):
+	data = struct.unpack_from("<BBBBII", raw_buf)
+	cbr = data[0]
+	MHz = (data[4] + 500) / 1000
+	percent = ((cbr * 1000 / data[2]) + 5) / 10
+	cbr_query.addBindValue(str(id))
+	cbr_query.addBindValue(str(cbr))
+	cbr_query.addBindValue(str(MHz))
+	cbr_query.addBindValue(str(percent))
+	do_query_(cbr_query)
+
+def mwait(id, raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	hints = payload & 0xff
+	extensions = (payload >> 32) & 0x3
+	mwait_query.addBindValue(str(id))
+	mwait_query.addBindValue(str(hints))
+	mwait_query.addBindValue(str(extensions))
+	do_query_(mwait_query)
+
+def pwre(id, raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	hw = (payload >> 7) & 1
+	cstate = (payload >> 12) & 0xf
+	subcstate = (payload >> 8) & 0xf
+	pwre_query.addBindValue(str(id))
+	pwre_query.addBindValue(str(cstate))
+	pwre_query.addBindValue(str(subcstate))
+	pwre_query.addBindValue(str(hw))
+	do_query_(pwre_query)
+
+def exstop(id, raw_buf):
+	data = struct.unpack_from("<I", raw_buf)
+	flags = data[0]
+	exact_ip = flags & 1
+	exstop_query.addBindValue(str(id))
+	exstop_query.addBindValue(str(exact_ip))
+	do_query_(exstop_query)
+
+def pwrx(id, raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	deepest_cstate = payload & 0xf
+	last_cstate = (payload >> 4) & 0xf
+	wake_reason = (payload >> 8) & 0xf
+	pwrx_query.addBindValue(str(id))
+	pwrx_query.addBindValue(str(deepest_cstate))
+	pwrx_query.addBindValue(str(last_cstate))
+	pwrx_query.addBindValue(str(wake_reason))
+	do_query_(pwrx_query)
+
+def synth_data(id, config, raw_buf, *x):
+	if config == 0:
+		ptwrite(id, raw_buf)
+	elif config == 1:
+		mwait(id, raw_buf)
+	elif config == 2:
+		pwre(id, raw_buf)
+	elif config == 3:
+		exstop(id, raw_buf)
+	elif config == 4:
+		pwrx(id, raw_buf)
+	elif config == 5:
+		cbr(id, raw_buf)
+
+def context_switch_table(*x):
+	bind_exec(context_switch_query, 9, x)

linux-7.2.3/tools/perf/scripts/python/failed-syscalls-by-pid.py

@@ -0,0 +1,79 @@
+# failed system call counts, by pid
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide failed system call totals, broken down by pid.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+usage = "perf script -s syscall-counts-by-pid.py [comm|pid]\n";
+
+for_comm = None
+for_pid = None
+
+if len(sys.argv) > 2:
+	sys.exit(usage)
+
+if len(sys.argv) > 1:
+	try:
+		for_pid = int(sys.argv[1])
+	except:
+		for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+	print("Press control+C to stop and show the summary")
+
+def trace_end():
+	print_error_totals()
+
+def raw_syscalls__sys_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, id, ret):
+	if (for_comm and common_comm != for_comm) or \
+	   (for_pid  and common_pid  != for_pid ):
+		return
+
+	if ret < 0:
+		try:
+			syscalls[common_comm][common_pid][id][ret] += 1
+		except TypeError:
+			syscalls[common_comm][common_pid][id][ret] = 1
+
+def syscalls__sys_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, ret):
+	raw_syscalls__sys_exit(**locals())
+
+def print_error_totals():
+	if for_comm is not None:
+		print("\nsyscall errors for %s:\n" % (for_comm))
+	else:
+		print("\nsyscall errors:\n")
+
+	print("%-30s  %10s" % ("comm [pid]", "count"))
+	print("%-30s  %10s" % ("------------------------------", "----------"))
+
+	comm_keys = syscalls.keys()
+	for comm in comm_keys:
+		pid_keys = syscalls[comm].keys()
+		for pid in pid_keys:
+			print("\n%s [%d]" % (comm, pid))
+			id_keys = syscalls[comm][pid].keys()
+			for id in id_keys:
+				print("  syscall: %-16s" % syscall_name(id))
+				ret_keys = syscalls[comm][pid][id].keys()
+				for ret, val in sorted(syscalls[comm][pid][id].items(), key = lambda kv: (kv[1], kv[0]), reverse = True):
+					print("    err = %-20s  %10d" % (strerror(ret), val))

linux-7.2.3/tools/perf/scripts/python/flamegraph.py

@@ -0,0 +1,267 @@
+# flamegraph.py - create flame graphs from perf samples
+# SPDX-License-Identifier: GPL-2.0
+#
+# Usage:
+#
+#     perf record -a -g -F 99 sleep 60
+#     perf script report flamegraph
+#
+# Combined:
+#
+#     perf script flamegraph -a -F 99 sleep 60
+#
+# 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
+
+import argparse
+import hashlib
+import io
+import json
+import os
+import subprocess
+import sys
+from typing import Dict, Optional, Union
+import urllib.request
+
+MINIMAL_HTML = """<head>
+  <link rel="stylesheet" type="text/css" href="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.css">
+</head>
+<body>
+  <div id="chart"></div>
+  <script type="text/javascript" src="https://d3js.org/d3.v7.js"></script>
+  <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.min.js"></script>
+  <script type="text/javascript">
+  const stacks = [/** @flamegraph_json **/];
+  // Note, options is unused.
+  const options = [/** @options_json **/];
+
+  var chart = flamegraph();
+  d3.select("#chart")
+        .datum(stacks[0])
+        .call(chart);
+  </script>
+</body>
+"""
+
+# pylint: disable=too-few-public-methods
+class Node:
+    def __init__(self, name: str, libtype: str):
+        self.name = name
+        # "root" | "kernel" | ""
+        # "" indicates user space
+        self.libtype = libtype
+        self.value: int = 0
+        self.children: list[Node] = []
+
+    def to_json(self) -> Dict[str, Union[str, int, list[Dict]]]:
+        return {
+            "n": self.name,
+            "l": self.libtype,
+            "v": self.value,
+            "c": [x.to_json() for x in self.children]
+        }
+
+
+class FlameGraphCLI:
+    def __init__(self, args):
+        self.args = args
+        self.stack = Node("all", "root")
+
+    @staticmethod
+    def get_libtype_from_dso(dso: Optional[str]) -> str:
+        """
+        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: Node, name: str, libtype: str) -> Node:
+        for child in node.children:
+            if child.name == name:
+                return child
+
+        child = Node(name, libtype)
+        node.children.append(child)
+        return child
+
+    def process_event(self, event) -> None:
+        # ignore events where the event name does not match
+        # the one specified by the user
+        if self.args.event_name and event.get("ev_name") != self.args.event_name:
+            return
+
+        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 = f"{event['comm']} ({pid})"
+            libtype = ""
+        node = self.find_or_create_node(self.stack, comm, libtype)
+
+        if "callchain" in event:
+            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:
+            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) -> str:
+        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:
+            # if the file name other than perf.data is given,
+            # we read the header of that file
+            if self.args.input:
+                output = subprocess.check_output(["perf", "report", "--header-only",
+                                                  "-i", self.args.input])
+            else:
+                output = subprocess.check_output(["perf", "report", "--header-only"])
+
+            result = output.decode("utf-8")
+            if self.args.event_name:
+                result += "\nFocused event: " + self.args.event_name
+            return result
+        except Exception as err:  # pylint: disable=broad-except
+            print(f"Error reading report header: {err}", file=sys.stderr)
+            return ""
+
+    def trace_end(self) -> None:
+        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)
+
+            template_md5sum = None
+            if self.args.format == "html":
+                if os.path.isfile(self.args.template):
+                    template = f"file://{self.args.template}"
+                else:
+                    if not self.args.allow_download:
+                        print(f"""Warning: Flame Graph template '{self.args.template}'
+does not exist. To avoid this please install a package such as the
+js-d3-flame-graph or libjs-d3-flame-graph, specify an existing flame
+graph template (--template PATH) or use another output format (--format
+FORMAT).""",
+                              file=sys.stderr)
+                        if self.args.input == "-":
+                            print(
+"""Not attempting to download Flame Graph template as script command line
+input is disabled due to using live mode. If you want to download the
+template retry without live mode. For example, use 'perf record -a -g
+-F 99 sleep 60' and 'perf script report flamegraph'. Alternatively,
+download the template from:
+https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/d3-flamegraph-base.html
+and place it at:
+/usr/share/d3-flame-graph/d3-flamegraph-base.html""",
+                                  file=sys.stderr)
+                            sys.exit(1)
+                        s = None
+                        while s not in ["y", "n"]:
+                            s = input("Do you wish to download a template from cdn.jsdelivr.net?" +
+                                      "(this warning can be suppressed with --allow-download) [yn] "
+                                      ).lower()
+                        if s == "n":
+                            sys.exit(1)
+                    template = ("https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/"
+                                "d3-flamegraph-base.html")
+                    template_md5sum = "143e0d06ba69b8370b9848dcd6ae3f36"
+
+            try:
+                with urllib.request.urlopen(template) as url_template:
+                    output_str = "".join([
+                        l.decode("utf-8") for l in url_template.readlines()
+                    ])
+            except Exception as err:
+                print(f"Error reading template {template}: {err}\n"
+                      "a minimal flame graph will be generated", file=sys.stderr)
+                output_str = MINIMAL_HTML
+                template_md5sum = None
+
+            if template_md5sum:
+                download_md5sum = hashlib.md5(output_str.encode("utf-8")).hexdigest()
+                if download_md5sum != template_md5sum:
+                    s = None
+                    while s not in ["y", "n"]:
+                        s = input(f"""Unexpected template md5sum.
+{download_md5sum} != {template_md5sum}, for:
+{output_str}
+continue?[yn] """).lower()
+                    if s == "n":
+                        sys.exit(1)
+
+            output_str = output_str.replace("/** @options_json **/", options_json)
+            output_str = output_str.replace("/** @flamegraph_json **/", stacks_json)
+
+            output_fn = self.args.output or "flamegraph.html"
+        else:
+            output_str = stacks_json
+            output_fn = self.args.output or "stacks.json"
+
+        if output_fn == "-":
+            with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out:
+                out.write(output_str)
+        else:
+            print(f"dumping data to {output_fn}")
+            try:
+                with io.open(output_fn, "w", encoding="utf-8") as out:
+                    out.write(output_str)
+            except IOError as err:
+                print(f"Error writing output file: {err}", file=sys.stderr)
+                sys.exit(1)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Create flame graphs.")
+    parser.add_argument("-f", "--format",
+                        default="html", choices=["json", "html"],
+                        help="output file format")
+    parser.add_argument("-o", "--output",
+                        help="output file name")
+    parser.add_argument("--template",
+                        default="/usr/share/d3-flame-graph/d3-flamegraph-base.html",
+                        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)
+    parser.add_argument("--allow-download",
+                        default=False,
+                        action="store_true",
+                        help="allow unprompted downloading of HTML template")
+    parser.add_argument("-e", "--event",
+                        default="",
+                        dest="event_name",
+                        type=str,
+                        help="specify the event to generate flamegraph for")
+
+    cli_args = parser.parse_args()
+    cli = FlameGraphCLI(cli_args)
+
+    process_event = cli.process_event
+    trace_end = cli.trace_end

linux-7.2.3/tools/perf/scripts/python/futex-contention.py

@@ -0,0 +1,57 @@
+# futex contention
+# (c) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Translation of:
+#
+# http://sourceware.org/systemtap/wiki/WSFutexContention
+#
+# to perf python scripting.
+#
+# Measures futex contention
+
+from __future__ import print_function
+
+import os
+import sys
+sys.path.append(os.environ['PERF_EXEC_PATH'] +
+                '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+from Util import *
+
+process_names = {}
+thread_thislock = {}
+thread_blocktime = {}
+
+lock_waits = {}  # long-lived stats on (tid,lock) blockage elapsed time
+process_names = {}  # long-lived pid-to-execname mapping
+
+
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
+                              nr, uaddr, op, val, utime, uaddr2, val3):
+    cmd = op & FUTEX_CMD_MASK
+    if cmd != FUTEX_WAIT:
+        return  # we don't care about originators of WAKE events
+
+    process_names[tid] = comm
+    thread_thislock[tid] = uaddr
+    thread_blocktime[tid] = nsecs(s, ns)
+
+
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
+                             nr, ret):
+    if tid in thread_blocktime:
+        elapsed = nsecs(s, ns) - thread_blocktime[tid]
+        add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed)
+        del thread_blocktime[tid]
+        del thread_thislock[tid]
+
+
+def trace_begin():
+    print("Press control+C to stop and show the summary")
+
+
+def trace_end():
+    for (tid, lock) in lock_waits:
+        min, max, avg, count = lock_waits[tid, lock]
+        print("%s[%d] lock %x contended %d times, %d avg ns [max: %d ns, min %d ns]" %
+              (process_names[tid], tid, lock, count, avg, max, min))

linux-7.2.3/tools/perf/scripts/python/gecko.py

@@ -0,0 +1,395 @@
+# gecko.py - Convert perf record output to Firefox's gecko profile format
+# SPDX-License-Identifier: GPL-2.0
+#
+# The script converts perf.data to Gecko Profile Format,
+# which can be read by https://profiler.firefox.com/.
+#
+# Usage:
+#
+#     perf record -a -g -F 99 sleep 60
+#     perf script report gecko
+#
+# Combined:
+#
+#     perf script gecko -F 99 -a sleep 60
+
+import os
+import sys
+import time
+import json
+import string
+import random
+import argparse
+import threading
+import webbrowser
+import urllib.parse
+from os import system
+from functools import reduce
+from dataclasses import dataclass, field
+from http.server import HTTPServer, SimpleHTTPRequestHandler, test
+from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
+
+# Add the Perf-Trace-Util library to the Python path
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+StringID = int
+StackID = int
+FrameID = int
+CategoryID = int
+Milliseconds = float
+
+# start_time is intialiazed only once for the all event traces.
+start_time = None
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/profile.js#L425
+# Follow Brendan Gregg's Flamegraph convention: orange for kernel and yellow for user space by default.
+CATEGORIES = None
+
+# The product name is used by the profiler UI to show the Operating system and Processor.
+PRODUCT = os.popen('uname -op').read().strip()
+
+# store the output file
+output_file = None
+
+# Here key = tid, value = Thread
+tid_to_thread = dict()
+
+# The HTTP server is used to serve the profile to the profiler UI.
+http_server_thread = None
+
+# The category index is used by the profiler UI to show the color of the flame graph.
+USER_CATEGORY_INDEX = 0
+KERNEL_CATEGORY_INDEX = 1
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
+class Frame(NamedTuple):
+	string_id: StringID
+	relevantForJS: bool
+	innerWindowID: int
+	implementation: None
+	optimizations: None
+	line: None
+	column: None
+	category: CategoryID
+	subcategory: int
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216
+class Stack(NamedTuple):
+	prefix_id: Optional[StackID]
+	frame_id: FrameID
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90
+class Sample(NamedTuple):
+	stack_id: Optional[StackID]
+	time_ms: Milliseconds
+	responsiveness: int
+
+@dataclass
+class Thread:
+	"""A builder for a profile of the thread.
+
+	Attributes:
+		comm: Thread command-line (name).
+		pid: process ID of containing process.
+		tid: thread ID.
+		samples: Timeline of profile samples.
+		frameTable: interned stack frame ID -> stack frame.
+		stringTable: interned string ID -> string.
+		stringMap: interned string -> string ID.
+		stackTable: interned stack ID -> stack.
+		stackMap: (stack prefix ID, leaf stack frame ID) -> interned Stack ID.
+		frameMap: Stack Frame string -> interned Frame ID.
+		comm: str
+		pid: int
+		tid: int
+		samples: List[Sample] = field(default_factory=list)
+		frameTable: List[Frame] = field(default_factory=list)
+		stringTable: List[str] = field(default_factory=list)
+		stringMap: Dict[str, int] = field(default_factory=dict)
+		stackTable: List[Stack] = field(default_factory=list)
+		stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
+		frameMap: Dict[str, int] = field(default_factory=dict)
+	"""
+	comm: str
+	pid: int
+	tid: int
+	samples: List[Sample] = field(default_factory=list)
+	frameTable: List[Frame] = field(default_factory=list)
+	stringTable: List[str] = field(default_factory=list)
+	stringMap: Dict[str, int] = field(default_factory=dict)
+	stackTable: List[Stack] = field(default_factory=list)
+	stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
+	frameMap: Dict[str, int] = field(default_factory=dict)
+
+	def _intern_stack(self, frame_id: int, prefix_id: Optional[int]) -> int:
+		"""Gets a matching stack, or saves the new stack. Returns a Stack ID."""
+		key = f"{frame_id}" if prefix_id is None else f"{frame_id},{prefix_id}"
+		# key = (prefix_id, frame_id)
+		stack_id = self.stackMap.get(key)
+		if stack_id is None:
+			# return stack_id
+			stack_id = len(self.stackTable)
+			self.stackTable.append(Stack(prefix_id=prefix_id, frame_id=frame_id))
+			self.stackMap[key] = stack_id
+		return stack_id
+
+	def _intern_string(self, string: str) -> int:
+		"""Gets a matching string, or saves the new string. Returns a String ID."""
+		string_id = self.stringMap.get(string)
+		if string_id is not None:
+			return string_id
+		string_id = len(self.stringTable)
+		self.stringTable.append(string)
+		self.stringMap[string] = string_id
+		return string_id
+
+	def _intern_frame(self, frame_str: str) -> int:
+		"""Gets a matching stack frame, or saves the new frame. Returns a Frame ID."""
+		frame_id = self.frameMap.get(frame_str)
+		if frame_id is not None:
+			return frame_id
+		frame_id = len(self.frameTable)
+		self.frameMap[frame_str] = frame_id
+		string_id = self._intern_string(frame_str)
+
+		symbol_name_to_category = KERNEL_CATEGORY_INDEX if frame_str.find('kallsyms') != -1 \
+		or frame_str.find('/vmlinux') != -1 \
+		or frame_str.endswith('.ko)') \
+		else USER_CATEGORY_INDEX
+
+		self.frameTable.append(Frame(
+			string_id=string_id,
+			relevantForJS=False,
+			innerWindowID=0,
+			implementation=None,
+			optimizations=None,
+			line=None,
+			column=None,
+			category=symbol_name_to_category,
+			subcategory=None,
+		))
+		return frame_id
+
+	def _add_sample(self, comm: str, stack: List[str], time_ms: Milliseconds) -> None:
+		"""Add a timestamped stack trace sample to the thread builder.
+		Args:
+			comm: command-line (name) of the thread at this sample
+			stack: sampled stack frames. Root first, leaf last.
+			time_ms: timestamp of sample in milliseconds.
+		"""
+		# Ihreads may not set their names right after they are created.
+		# Instead, they might do it later. In such situations, to use the latest name they have set.
+		if self.comm != comm:
+			self.comm = comm
+
+		prefix_stack_id = reduce(lambda prefix_id, frame: self._intern_stack
+						(self._intern_frame(frame), prefix_id), stack, None)
+		if prefix_stack_id is not None:
+			self.samples.append(Sample(stack_id=prefix_stack_id,
+									time_ms=time_ms,
+									responsiveness=0))
+
+	def _to_json_dict(self) -> Dict:
+		"""Converts current Thread to GeckoThread JSON format."""
+		# Gecko profile format is row-oriented data as List[List],
+		# And a schema for interpreting each index.
+		# Schema:
+		# https://github.com/firefox-devtools/profiler/blob/main/docs-developer/gecko-profile-format.md
+		# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L230
+		return {
+			"tid": self.tid,
+			"pid": self.pid,
+			"name": self.comm,
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L51
+			"markers": {
+				"schema": {
+					"name": 0,
+					"startTime": 1,
+					"endTime": 2,
+					"phase": 3,
+					"category": 4,
+					"data": 5,
+				},
+				"data": [],
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90
+			"samples": {
+				"schema": {
+					"stack": 0,
+					"time": 1,
+					"responsiveness": 2,
+				},
+				"data": self.samples
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
+			"frameTable": {
+				"schema": {
+					"location": 0,
+					"relevantForJS": 1,
+					"innerWindowID": 2,
+					"implementation": 3,
+					"optimizations": 4,
+					"line": 5,
+					"column": 6,
+					"category": 7,
+					"subcategory": 8,
+				},
+				"data": self.frameTable,
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216
+			"stackTable": {
+				"schema": {
+					"prefix": 0,
+					"frame": 1,
+				},
+				"data": self.stackTable,
+			},
+			"stringTable": self.stringTable,
+			"registerTime": 0,
+			"unregisterTime": None,
+			"processType": "default",
+		}
+
+# Uses perf script python interface to parse each
+# event and store the data in the thread builder.
+def process_event(param_dict: Dict) -> None:
+	global start_time
+	global tid_to_thread
+	time_stamp = (param_dict['sample']['time'] // 1000) / 1000
+	pid = param_dict['sample']['pid']
+	tid = param_dict['sample']['tid']
+	comm = param_dict['comm']
+
+	# Start time is the time of the first sample
+	if not start_time:
+		start_time = time_stamp
+
+	# Parse and append the callchain of the current sample into a stack.
+	stack = []
+	if param_dict['callchain']:
+		for call in param_dict['callchain']:
+			if 'sym' not in call:
+				continue
+			stack.append(f'{call["sym"]["name"]} (in {call["dso"]})')
+		if len(stack) != 0:
+			# Reverse the stack, as root come first and the leaf at the end.
+			stack = stack[::-1]
+
+	# During perf record if -g is not used, the callchain is not available.
+	# In that case, the symbol and dso are available in the event parameters.
+	else:
+		func = param_dict['symbol'] if 'symbol' in param_dict else '[unknown]'
+		dso = param_dict['dso'] if 'dso' in param_dict else '[unknown]'
+		stack.append(f'{func} (in {dso})')
+
+	# Add sample to the specific thread.
+	thread = tid_to_thread.get(tid)
+	if thread is None:
+		thread = Thread(comm=comm, pid=pid, tid=tid)
+		tid_to_thread[tid] = thread
+	thread._add_sample(comm=comm, stack=stack, time_ms=time_stamp)
+
+def trace_begin() -> None:
+	global output_file
+	if (output_file is None):
+		print("Staring Firefox Profiler on your default browser...")
+		global http_server_thread
+		http_server_thread = threading.Thread(target=test, args=(CORSRequestHandler, HTTPServer,))
+		http_server_thread.daemon = True
+		http_server_thread.start()
+
+# Trace_end runs at the end and will be used to aggregate
+# the data into the final json object and print it out to stdout.
+def trace_end() -> None:
+	global output_file
+	threads = [thread._to_json_dict() for thread in tid_to_thread.values()]
+
+	# Schema: https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L305
+	gecko_profile_with_meta = {
+		"meta": {
+			"interval": 1,
+			"processType": 0,
+			"product": PRODUCT,
+			"stackwalk": 1,
+			"debug": 0,
+			"gcpoison": 0,
+			"asyncstack": 1,
+			"startTime": start_time,
+			"shutdownTime": None,
+			"version": 24,
+			"presymbolicated": True,
+			"categories": CATEGORIES,
+			"markerSchema": [],
+			},
+		"libs": [],
+		"threads": threads,
+		"processes": [],
+		"pausedRanges": [],
+	}
+	# launch the profiler on local host if not specified --save-only args, otherwise print to file
+	if (output_file is None):
+		output_file = 'gecko_profile.json'
+		with open(output_file, 'w') as f:
+			json.dump(gecko_profile_with_meta, f, indent=2)
+		launchFirefox(output_file)
+		time.sleep(1)
+		print(f'[ perf gecko: Captured and wrote into {output_file} ]')
+	else:
+		print(f'[ perf gecko: Captured and wrote into {output_file} ]')
+		with open(output_file, 'w') as f:
+			json.dump(gecko_profile_with_meta, f, indent=2)
+
+# Used to enable Cross-Origin Resource Sharing (CORS) for requests coming from 'https://profiler.firefox.com', allowing it to access resources from this server.
+class CORSRequestHandler(SimpleHTTPRequestHandler):
+	def end_headers (self):
+		self.send_header('Access-Control-Allow-Origin', 'https://profiler.firefox.com')
+		SimpleHTTPRequestHandler.end_headers(self)
+
+# start a local server to serve the gecko_profile.json file to the profiler.firefox.com
+def launchFirefox(file):
+	safe_string = urllib.parse.quote_plus(f'http://localhost:8000/{file}')
+	url = 'https://profiler.firefox.com/from-url/' + safe_string
+	webbrowser.open(f'{url}')
+
+def main() -> None:
+	global output_file
+	global CATEGORIES
+	parser = argparse.ArgumentParser(description="Convert perf.data to Firefox\'s Gecko Profile format which can be uploaded to profiler.firefox.com for visualization")
+
+	# Add the command-line options
+	# Colors must be defined according to this:
+	# https://github.com/firefox-devtools/profiler/blob/50124adbfa488adba6e2674a8f2618cf34b59cd2/res/css/categories.css
+	parser.add_argument('--user-color', default='yellow', help='Color for the User category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta'])
+	parser.add_argument('--kernel-color', default='orange', help='Color for the Kernel category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta'])
+	# If --save-only is specified, the output will be saved to a file instead of opening Firefox's profiler directly.
+	parser.add_argument('--save-only', help='Save the output to a file instead of opening Firefox\'s profiler')
+
+	# Parse the command-line arguments
+	args = parser.parse_args()
+	# Access the values provided by the user
+	user_color = args.user_color
+	kernel_color = args.kernel_color
+	output_file = args.save_only
+
+	CATEGORIES = [
+		{
+			"name": 'User',
+			"color": user_color,
+			"subcategories": ['Other']
+		},
+		{
+			"name": 'Kernel',
+			"color": kernel_color,
+			"subcategories": ['Other']
+		},
+	]
+
+if __name__ == '__main__':
+	main()

linux-7.2.3/tools/perf/scripts/python/intel-pt-events.py

@@ -0,0 +1,494 @@
+# 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,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+from __future__ import division, print_function
+
+import io
+import os
+import sys
+import struct
+import argparse
+import contextlib
+
+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')
+
+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		= {}
+glb_insn		= False
+glb_disassembler	= None
+glb_src			= False
+glb_source_file_name	= None
+glb_line_number		= None
+glb_dso			= None
+glb_stash_dict		= {}
+glb_output		= None
+glb_output_pos		= 0
+glb_cpu			= -1
+glb_time		= 0
+
+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():
+	ap = argparse.ArgumentParser(usage = "", add_help = False)
+	ap.add_argument("--insn-trace", action='store_true')
+	ap.add_argument("--src-trace", action='store_true')
+	ap.add_argument("--all-switch-events", action='store_true')
+	ap.add_argument("--interleave", type=int, nargs='?', const=4, default=0)
+	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 = "i0nsepwxI"
+		glb_insn = True
+	elif glb_args.src_trace:
+		print("Intel PT Source Trace")
+		itrace = "i0nsepwxI"
+		glb_insn = True
+		glb_src = True
+	else:
+		print("Intel PT Branch Trace, Power Events, Event Trace and PTWRITE")
+		itrace = "bepwxI"
+	global glb_disassembler
+	try:
+		glb_disassembler = LibXED()
+	except:
+		glb_disassembler = None
+	perf_set_itrace_options(perf_script_context, itrace)
+
+def trace_end():
+	if glb_args.interleave:
+		flush_stashed_output()
+	print("End")
+
+def trace_unhandled(event_name, context, event_fields_dict):
+		print(' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]))
+
+def stash_output():
+	global glb_stash_dict
+	global glb_output_pos
+	output_str = glb_output.getvalue()[glb_output_pos:]
+	n = len(output_str)
+	if n:
+		glb_output_pos += n
+		if glb_cpu not in glb_stash_dict:
+			glb_stash_dict[glb_cpu] = []
+		glb_stash_dict[glb_cpu].append(output_str)
+
+def flush_stashed_output():
+	global glb_stash_dict
+	while glb_stash_dict:
+		cpus = list(glb_stash_dict.keys())
+		# Output at most glb_args.interleave output strings per cpu
+		for cpu in cpus:
+			items = glb_stash_dict[cpu]
+			countdown = glb_args.interleave
+			while len(items) and countdown:
+				sys.stdout.write(items[0])
+				del items[0]
+				countdown -= 1
+			if not items:
+				del glb_stash_dict[cpu]
+
+def print_ptwrite(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	flags = data[0]
+	payload = data[1]
+	exact_ip = flags & 1
+	try:
+		s = payload.to_bytes(8, "little").decode("ascii").rstrip("\x00")
+		if not s.isprintable():
+			s = ""
+	except:
+		s = ""
+	print("IP: %u payload: %#x" % (exact_ip, payload), s, end=' ')
+
+def print_cbr(raw_buf):
+	data = struct.unpack_from("<BBBBII", raw_buf)
+	cbr = data[0]
+	f = (data[4] + 500) / 1000
+	p = ((cbr * 1000 / data[2]) + 5) / 10
+	print("%3u  freq: %4u MHz  (%3u%%)" % (cbr, f, p), end=' ')
+
+def print_mwait(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	hints = payload & 0xff
+	extensions = (payload >> 32) & 0x3
+	print("hints: %#x extensions: %#x" % (hints, extensions), end=' ')
+
+def print_pwre(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	hw = (payload >> 7) & 1
+	cstate = (payload >> 12) & 0xf
+	subcstate = (payload >> 8) & 0xf
+	print("hw: %u cstate: %u sub-cstate: %u" % (hw, cstate, subcstate),
+		end=' ')
+
+def print_exstop(raw_buf):
+	data = struct.unpack_from("<I", raw_buf)
+	flags = data[0]
+	exact_ip = flags & 1
+	print("IP: %u" % (exact_ip), end=' ')
+
+def print_pwrx(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	payload = data[1]
+	deepest_cstate = payload & 0xf
+	last_cstate = (payload >> 4) & 0xf
+	wake_reason = (payload >> 8) & 0xf
+	print("deepest cstate: %u last cstate: %u wake reason: %#x" %
+		(deepest_cstate, last_cstate, wake_reason), end=' ')
+
+def print_psb(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	offset = data[1]
+	print("offset: %#x" % (offset), end=' ')
+
+glb_cfe = ["", "INTR", "IRET", "SMI", "RSM", "SIPI", "INIT", "VMENTRY", "VMEXIT",
+		"VMEXIT_INTR", "SHUTDOWN", "", "UINT", "UIRET"] + [""] * 18
+glb_evd = ["", "PFA", "VMXQ", "VMXR"] + [""] * 60
+
+def print_evt(raw_buf):
+	data = struct.unpack_from("<BBH", raw_buf)
+	typ = data[0] & 0x1f
+	ip_flag = (data[0] & 0x80) >> 7
+	vector = data[1]
+	evd_cnt = data[2]
+	s = glb_cfe[typ]
+	if s:
+		print(" cfe: %s IP: %u vector: %u" % (s, ip_flag, vector), end=' ')
+	else:
+		print(" cfe: %u IP: %u vector: %u" % (typ, ip_flag, vector), end=' ')
+	pos = 4
+	for i in range(evd_cnt):
+		data = struct.unpack_from("<QQ", raw_buf)
+		et = data[0] & 0x3f
+		s = glb_evd[et]
+		if s:
+			print("%s: %#x" % (s, data[1]), end=' ')
+		else:
+			print("EVD_%u: %#x" % (et, data[1]), end=' ')
+
+def print_iflag(raw_buf):
+	data = struct.unpack_from("<IQ", raw_buf)
+	iflag = data[0] & 1
+	old_iflag = iflag ^ 1
+	via_branch = data[0] & 2
+	branch_ip = data[1]
+	if via_branch:
+		s = "via"
+	else:
+		s = "non"
+	print("IFLAG: %u->%u %s branch" % (old_iflag, iflag, s), end=' ')
+
+def common_start_str(comm, sample):
+	ts = sample["time"]
+	cpu = sample["cpu"]
+	pid = sample["pid"]
+	tid = sample["tid"]
+	if "machine_pid" in sample:
+		machine_pid = sample["machine_pid"]
+		vcpu = sample["vcpu"]
+		return "VM:%5d VCPU:%03d %16s %5u/%-5u [%03u] %9u.%09u  " % (machine_pid, vcpu, comm, pid, tid, cpu, ts / 1000000000, ts %1000000000)
+	else:
+		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) + "%8s  %21s" % (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_srccode(comm, param_dict, sample, symbol, dso, with_insn):
+	ip = sample["ip"]
+	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)
+
+	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):
+	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"]
+	# event_attr = param_dict["attr"]
+
+	# Symbol and dso info are not always resolved
+	dso    = get_optional(param_dict, "dso")
+	symbol = get_optional(param_dict, "symbol")
+
+	cpu = sample["cpu"]
+	if cpu in glb_switch_str:
+		print(glb_switch_str[cpu])
+		del glb_switch_str[cpu]
+
+	if name.startswith("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.startswith("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(param_dict, sample, symbol, dso)
+	elif name == "cbr":
+		print_common_start(comm, sample, name)
+		print_cbr(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "mwait":
+		print_common_start(comm, sample, name)
+		print_mwait(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "pwre":
+		print_common_start(comm, sample, name)
+		print_pwre(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "exstop":
+		print_common_start(comm, sample, name)
+		print_exstop(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "pwrx":
+		print_common_start(comm, sample, name)
+		print_pwrx(raw_buf)
+		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)
+	elif name == "evt":
+		print_common_start(comm, sample, name)
+		print_evt(raw_buf)
+		print_common_ip(param_dict, sample, symbol, dso)
+	elif name == "iflag":
+		print_common_start(comm, sample, name)
+		print_iflag(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 interleave_events(param_dict):
+	global glb_cpu
+	global glb_time
+	global glb_output
+	global glb_output_pos
+
+	sample  = param_dict["sample"]
+	glb_cpu = sample["cpu"]
+	ts      = sample["time"]
+
+	if glb_time != ts:
+		glb_time = ts
+		flush_stashed_output()
+
+	glb_output_pos = 0
+	with contextlib.redirect_stdout(io.StringIO()) as glb_output:
+		do_process_event(param_dict)
+
+	stash_output()
+
+def process_event(param_dict):
+	try:
+		if glb_args.interleave:
+			interleave_events(param_dict)
+		else:
+			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):
+	if glb_args.interleave:
+		flush_stashed_output()
+	if len(x) >= 2 and x[0]:
+		machine_pid = x[0]
+		vcpu = x[1]
+	else:
+		machine_pid = 0
+		vcpu = -1
+	try:
+		if machine_pid:
+			print("VM:%5d VCPU:%03d %16s %5u/%-5u [%03u] %9u.%09u  error type %u code %u: %s ip 0x%16x" %
+				(machine_pid, vcpu, "Trace error", pid, tid, cpu, ts / 1000000000, ts %1000000000, typ, code, msg, ip))
+		else:
+			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):
+	if glb_args.interleave:
+		flush_stashed_output()
+	if out:
+		out_str = "Switch out "
+	else:
+		out_str = "Switch In  "
+	if out_preempt:
+		preempt_str = "preempt"
+	else:
+		preempt_str = ""
+	if len(x) >= 2 and x[0]:
+		machine_pid = x[0]
+		vcpu = x[1]
+	else:
+		vcpu = None;
+	if machine_pid == -1:
+		machine_str = ""
+	elif vcpu is None:
+		machine_str = "machine PID %d" % machine_pid
+	else:
+		machine_str = "machine PID %d VCPU %d" % (machine_pid, vcpu)
+	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)
+	if glb_args.all_switch_events:
+		print(switch_str)
+	else:
+		global glb_switch_str
+		glb_switch_str[cpu] = switch_str

linux-7.2.3/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

linux-7.2.3/tools/perf/scripts/python/mem-phys-addr.py

@@ -0,0 +1,127 @@
+# mem-phys-addr.py: Resolve physical address samples
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018, Intel Corporation.
+
+import os
+import sys
+import re
+import bisect
+import collections
+from dataclasses import dataclass
+from typing import (Dict, Optional)
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+    '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+@dataclass(frozen=True)
+class IomemEntry:
+    """Read from a line in /proc/iomem"""
+    begin: int
+    end: int
+    indent: int
+    label: str
+
+# Physical memory layout from /proc/iomem. Key is the indent and then
+# a list of ranges.
+iomem: Dict[int, list[IomemEntry]] = collections.defaultdict(list)
+# Child nodes from the iomem parent.
+children: Dict[IomemEntry, set[IomemEntry]] = collections.defaultdict(set)
+# Maximum indent seen before an entry in the iomem file.
+max_indent: int = 0
+# Count for each range of memory.
+load_mem_type_cnt: Dict[IomemEntry, int] = collections.Counter()
+# Perf event name set from the first sample in the data.
+event_name: Optional[str] = None
+
+def parse_iomem():
+    """Populate iomem from /proc/iomem file"""
+    global iomem
+    global max_indent
+    global children
+    with open('/proc/iomem', 'r', encoding='ascii') as f:
+        for line in f:
+            indent = 0
+            while line[indent] == ' ':
+                indent += 1
+            if indent > max_indent:
+                max_indent = indent
+            m = re.split('-|:', line, 2)
+            begin = int(m[0], 16)
+            end = int(m[1], 16)
+            label = m[2].strip()
+            entry = IomemEntry(begin, end, indent, label)
+            # Before adding entry, search for a parent node using its begin.
+            if indent > 0:
+                parent = find_memory_type(begin)
+                assert parent, f"Given indent expected a parent for {label}"
+                children[parent].add(entry)
+            iomem[indent].append(entry)
+
+def find_memory_type(phys_addr) -> Optional[IomemEntry]:
+    """Search iomem for the range containing phys_addr with the maximum indent"""
+    for i in range(max_indent, -1, -1):
+        if i not in iomem:
+            continue
+        position = bisect.bisect_right(iomem[i], phys_addr,
+                                       key=lambda entry: entry.begin)
+        if position is None:
+            continue
+        iomem_entry = iomem[i][position-1]
+        if  iomem_entry.begin <= phys_addr <= iomem_entry.end:
+            return iomem_entry
+    print(f"Didn't find {phys_addr}")
+    return None
+
+def print_memory_type():
+    print(f"Event: {event_name}")
+    print(f"{'Memory type':<40}  {'count':>10}  {'percentage':>10}")
+    print(f"{'-' * 40:<40}  {'-' * 10:>10}  {'-' * 10:>10}")
+    total = sum(load_mem_type_cnt.values())
+    # Add count from children into the parent.
+    for i in range(max_indent, -1, -1):
+        if i not in iomem:
+            continue
+        for entry in iomem[i]:
+            global children
+            for child in children[entry]:
+                if load_mem_type_cnt[child] > 0:
+                    load_mem_type_cnt[entry] += load_mem_type_cnt[child]
+
+    def print_entries(entries):
+        """Print counts from parents down to their children"""
+        global children
+        for entry in sorted(entries,
+                            key = lambda entry: load_mem_type_cnt[entry],
+                            reverse = True):
+            count = load_mem_type_cnt[entry]
+            if count > 0:
+                mem_type = ' ' * entry.indent + f"{entry.begin:x}-{entry.end:x} : {entry.label}"
+                percent = 100 * count / total
+                print(f"{mem_type:<40}  {count:>10}  {percent:>10.1f}")
+                print_entries(children[entry])
+
+    print_entries(iomem[0])
+
+def trace_begin():
+    parse_iomem()
+
+def trace_end():
+    print_memory_type()
+
+def process_event(param_dict):
+    if "sample" not in param_dict:
+        return
+
+    sample = param_dict["sample"]
+    if "phys_addr" not in sample:
+        return
+
+    phys_addr  = sample["phys_addr"]
+    entry = find_memory_type(phys_addr)
+    if entry:
+        load_mem_type_cnt[entry] += 1
+
+    global event_name
+    if event_name is None:
+        event_name  = param_dict["ev_name"]

linux-7.2.3/tools/perf/scripts/python/net_dropmonitor.py

@@ -0,0 +1,78 @@
+# Monitor the system for dropped packets and proudce a report of drop locations and counts
+# SPDX-License-Identifier: GPL-2.0
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+drop_log = {}
+kallsyms = []
+
+def get_kallsyms_table():
+	global kallsyms
+
+	try:
+		f = open("/proc/kallsyms", "r")
+	except:
+		return
+
+	for line in f:
+		loc = int(line.split()[0], 16)
+		name = line.split()[2]
+		kallsyms.append((loc, name))
+	kallsyms.sort()
+
+def get_sym(sloc):
+	loc = int(sloc)
+
+	# Invariant: kallsyms[i][0] <= loc for all 0 <= i <= start
+	#            kallsyms[i][0] > loc for all end <= i < len(kallsyms)
+	start, end = -1, len(kallsyms)
+	while end != start + 1:
+		pivot = (start + end) // 2
+		if loc < kallsyms[pivot][0]:
+			end = pivot
+		else:
+			start = pivot
+
+	# Now (start == -1 or kallsyms[start][0] <= loc)
+	# and (start == len(kallsyms) - 1 or loc < kallsyms[start + 1][0])
+	if start >= 0:
+		symloc, name = kallsyms[start]
+		return (name, loc - symloc)
+	else:
+		return (None, 0)
+
+def print_drop_table():
+	print("%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT"))
+	for i in drop_log.keys():
+		(sym, off) = get_sym(i)
+		if sym == None:
+			sym = i
+		print("%25s %25s %25s" % (sym, off, drop_log[i]))
+
+
+def trace_begin():
+	print("Starting trace (Ctrl-C to dump results)")
+
+def trace_end():
+	print("Gathering kallsyms data")
+	get_kallsyms_table()
+	print_drop_table()
+
+# called from perf, when it finds a corresponding event
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
+		   skbaddr, location, protocol, reason):
+	slocation = str(location)
+	try:
+		drop_log[slocation] = drop_log[slocation] + 1
+	except:
+		drop_log[slocation] = 1

linux-7.2.3/tools/perf/scripts/python/netdev-times.py

@@ -0,0 +1,473 @@
+# Display a process of packets and processed time.
+# SPDX-License-Identifier: GPL-2.0
+# It helps us to investigate networking or network device.
+#
+# options
+# tx: show only tx chart
+# rx: show only rx chart
+# dev=: show only thing related to specified device
+# debug: work with debug mode. It shows buffer status.
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+from functools import cmp_to_key
+
+all_event_list = []; # insert all tracepoint event related with this script
+irq_dic = {}; # key is cpu and value is a list which stacks irqs
+              # which raise NET_RX softirq
+net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry
+		 # and a list which stacks receive
+receive_hunk_list = []; # a list which include a sequence of receive events
+rx_skb_list = []; # received packet list for matching
+		       # skb_copy_datagram_iovec
+
+buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and
+		       # tx_xmit_list
+of_count_rx_skb_list = 0; # overflow count
+
+tx_queue_list = []; # list of packets which pass through dev_queue_xmit
+of_count_tx_queue_list = 0; # overflow count
+
+tx_xmit_list = [];  # list of packets which pass through dev_hard_start_xmit
+of_count_tx_xmit_list = 0; # overflow count
+
+tx_free_list = [];  # list of packets which is freed
+
+# options
+show_tx = 0;
+show_rx = 0;
+dev = 0; # store a name of device specified by option "dev="
+debug = 0;
+
+# indices of event_info tuple
+EINFO_IDX_NAME=   0
+EINFO_IDX_CONTEXT=1
+EINFO_IDX_CPU=    2
+EINFO_IDX_TIME=   3
+EINFO_IDX_PID=    4
+EINFO_IDX_COMM=   5
+
+# Calculate a time interval(msec) from src(nsec) to dst(nsec)
+def diff_msec(src, dst):
+	return (dst - src) / 1000000.0
+
+# Display a process of transmitting a packet
+def print_transmit(hunk):
+	if dev != 0 and hunk['dev'].find(dev) < 0:
+		return
+	print("%7s %5d %6d.%06dsec %12.3fmsec      %12.3fmsec" %
+		(hunk['dev'], hunk['len'],
+		nsecs_secs(hunk['queue_t']),
+		nsecs_nsecs(hunk['queue_t'])/1000,
+		diff_msec(hunk['queue_t'], hunk['xmit_t']),
+		diff_msec(hunk['xmit_t'], hunk['free_t'])))
+
+# Format for displaying rx packet processing
+PF_IRQ_ENTRY= "  irq_entry(+%.3fmsec irq=%d:%s)"
+PF_SOFT_ENTRY="  softirq_entry(+%.3fmsec)"
+PF_NAPI_POLL= "  napi_poll_exit(+%.3fmsec %s)"
+PF_JOINT=     "         |"
+PF_WJOINT=    "         |            |"
+PF_NET_RECV=  "         |---netif_receive_skb(+%.3fmsec skb=%x len=%d)"
+PF_NET_RX=    "         |---netif_rx(+%.3fmsec skb=%x)"
+PF_CPY_DGRAM= "         |      skb_copy_datagram_iovec(+%.3fmsec %d:%s)"
+PF_KFREE_SKB= "         |      kfree_skb(+%.3fmsec location=%x)"
+PF_CONS_SKB=  "         |      consume_skb(+%.3fmsec)"
+
+# Display a process of received packets and interrputs associated with
+# a NET_RX softirq
+def print_receive(hunk):
+	show_hunk = 0
+	irq_list = hunk['irq_list']
+	cpu = irq_list[0]['cpu']
+	base_t = irq_list[0]['irq_ent_t']
+	# check if this hunk should be showed
+	if dev != 0:
+		for i in range(len(irq_list)):
+			if irq_list[i]['name'].find(dev) >= 0:
+				show_hunk = 1
+				break
+	else:
+		show_hunk = 1
+	if show_hunk == 0:
+		return
+
+	print("%d.%06dsec cpu=%d" %
+		(nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu))
+	for i in range(len(irq_list)):
+		print(PF_IRQ_ENTRY %
+			(diff_msec(base_t, irq_list[i]['irq_ent_t']),
+			irq_list[i]['irq'], irq_list[i]['name']))
+		print(PF_JOINT)
+		irq_event_list = irq_list[i]['event_list']
+		for j in range(len(irq_event_list)):
+			irq_event = irq_event_list[j]
+			if irq_event['event'] == 'netif_rx':
+				print(PF_NET_RX %
+					(diff_msec(base_t, irq_event['time']),
+					irq_event['skbaddr']))
+				print(PF_JOINT)
+	print(PF_SOFT_ENTRY %
+		diff_msec(base_t, hunk['sirq_ent_t']))
+	print(PF_JOINT)
+	event_list = hunk['event_list']
+	for i in range(len(event_list)):
+		event = event_list[i]
+		if event['event_name'] == 'napi_poll':
+			print(PF_NAPI_POLL %
+				(diff_msec(base_t, event['event_t']),
+				event['dev']))
+			if i == len(event_list) - 1:
+				print("")
+			else:
+				print(PF_JOINT)
+		else:
+			print(PF_NET_RECV %
+				(diff_msec(base_t, event['event_t']),
+				event['skbaddr'],
+				event['len']))
+			if 'comm' in event.keys():
+				print(PF_WJOINT)
+				print(PF_CPY_DGRAM %
+					(diff_msec(base_t, event['comm_t']),
+					event['pid'], event['comm']))
+			elif 'handle' in event.keys():
+				print(PF_WJOINT)
+				if event['handle'] == "kfree_skb":
+					print(PF_KFREE_SKB %
+						(diff_msec(base_t,
+						event['comm_t']),
+						event['location']))
+				elif event['handle'] == "consume_skb":
+					print(PF_CONS_SKB %
+						diff_msec(base_t,
+							event['comm_t']))
+			print(PF_JOINT)
+
+def trace_begin():
+	global show_tx
+	global show_rx
+	global dev
+	global debug
+
+	for i in range(len(sys.argv)):
+		if i == 0:
+			continue
+		arg = sys.argv[i]
+		if arg == 'tx':
+			show_tx = 1
+		elif arg =='rx':
+			show_rx = 1
+		elif arg.find('dev=',0, 4) >= 0:
+			dev = arg[4:]
+		elif arg == 'debug':
+			debug = 1
+	if show_tx == 0  and show_rx == 0:
+		show_tx = 1
+		show_rx = 1
+
+def trace_end():
+	# order all events in time
+	all_event_list.sort(key=cmp_to_key(lambda a,b :a[EINFO_IDX_TIME] < b[EINFO_IDX_TIME]))
+	# process all events
+	for i in range(len(all_event_list)):
+		event_info = all_event_list[i]
+		name = event_info[EINFO_IDX_NAME]
+		if name == 'irq__softirq_exit':
+			handle_irq_softirq_exit(event_info)
+		elif name == 'irq__softirq_entry':
+			handle_irq_softirq_entry(event_info)
+		elif name == 'irq__softirq_raise':
+			handle_irq_softirq_raise(event_info)
+		elif name == 'irq__irq_handler_entry':
+			handle_irq_handler_entry(event_info)
+		elif name == 'irq__irq_handler_exit':
+			handle_irq_handler_exit(event_info)
+		elif name == 'napi__napi_poll':
+			handle_napi_poll(event_info)
+		elif name == 'net__netif_receive_skb':
+			handle_netif_receive_skb(event_info)
+		elif name == 'net__netif_rx':
+			handle_netif_rx(event_info)
+		elif name == 'skb__skb_copy_datagram_iovec':
+			handle_skb_copy_datagram_iovec(event_info)
+		elif name == 'net__net_dev_queue':
+			handle_net_dev_queue(event_info)
+		elif name == 'net__net_dev_xmit':
+			handle_net_dev_xmit(event_info)
+		elif name == 'skb__kfree_skb':
+			handle_kfree_skb(event_info)
+		elif name == 'skb__consume_skb':
+			handle_consume_skb(event_info)
+	# display receive hunks
+	if show_rx:
+		for i in range(len(receive_hunk_list)):
+			print_receive(receive_hunk_list[i])
+	# display transmit hunks
+	if show_tx:
+		print("   dev    len      Qdisc        "
+			"       netdevice             free")
+		for i in range(len(tx_free_list)):
+			print_transmit(tx_free_list[i])
+	if debug:
+		print("debug buffer status")
+		print("----------------------------")
+		print("xmit Qdisc:remain:%d overflow:%d" %
+			(len(tx_queue_list), of_count_tx_queue_list))
+		print("xmit netdevice:remain:%d overflow:%d" %
+			(len(tx_xmit_list), of_count_tx_xmit_list))
+		print("receive:remain:%d overflow:%d" %
+			(len(rx_skb_list), of_count_rx_skb_list))
+
+# called from perf, when it finds a correspoinding event
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
+			callchain, irq, irq_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			irq, irq_name)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
+	all_event_list.append(event_info)
+
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi,
+		dev_name, work=None, budget=None):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			napi, dev_name, work, budget)
+	all_event_list.append(event_info)
+
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain,
+			skbaddr, skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain,
+			skbaddr, skblen, rc, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, rc ,dev_name)
+	all_event_list.append(event_info)
+
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
+			skbaddr, location, protocol, reason):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, location, protocol, reason)
+	all_event_list.append(event_info)
+
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
+			skbaddr, location):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr)
+	all_event_list.append(event_info)
+
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain,
+	skbaddr, skblen):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen)
+	all_event_list.append(event_info)
+
+def handle_irq_handler_entry(event_info):
+	(name, context, cpu, time, pid, comm, irq, irq_name) = event_info
+	if cpu not in irq_dic.keys():
+		irq_dic[cpu] = []
+	irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time}
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_handler_exit(event_info):
+	(name, context, cpu, time, pid, comm, irq, ret) = event_info
+	if cpu not in irq_dic.keys():
+		return
+	irq_record = irq_dic[cpu].pop()
+	if irq != irq_record['irq']:
+		return
+	irq_record.update({'irq_ext_t':time})
+	# if an irq doesn't include NET_RX softirq, drop.
+	if 'event_list' in irq_record.keys():
+		irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_raise(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'sirq_raise'})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_entry(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]}
+
+def handle_irq_softirq_exit(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	irq_list = []
+	event_list = 0
+	if cpu in irq_dic.keys():
+		irq_list = irq_dic[cpu]
+		del irq_dic[cpu]
+	if cpu in net_rx_dic.keys():
+		sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t']
+		event_list = net_rx_dic[cpu]['event_list']
+		del net_rx_dic[cpu]
+	if irq_list == [] or event_list == 0:
+		return
+	rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time,
+			'irq_list':irq_list, 'event_list':event_list}
+	# merge information related to a NET_RX softirq
+	receive_hunk_list.append(rec_data)
+
+def handle_napi_poll(event_info):
+	(name, context, cpu, time, pid, comm, napi, dev_name,
+		work, budget) = event_info
+	if cpu in net_rx_dic.keys():
+		event_list = net_rx_dic[cpu]['event_list']
+		rec_data = {'event_name':'napi_poll',
+				'dev':dev_name, 'event_t':time,
+				'work':work, 'budget':budget}
+		event_list.append(rec_data)
+
+def handle_netif_rx(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'netif_rx',
+		'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_netif_receive_skb(event_info):
+	global of_count_rx_skb_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		rec_data = {'event_name':'netif_receive_skb',
+				'event_t':time, 'skbaddr':skbaddr, 'len':skblen}
+		event_list = net_rx_dic[cpu]['event_list']
+		event_list.append(rec_data)
+		rx_skb_list.insert(0, rec_data)
+		if len(rx_skb_list) > buffer_budget:
+			rx_skb_list.pop()
+			of_count_rx_skb_list += 1
+
+def handle_net_dev_queue(event_info):
+	global of_count_tx_queue_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time}
+	tx_queue_list.insert(0, skb)
+	if len(tx_queue_list) > buffer_budget:
+		tx_queue_list.pop()
+		of_count_tx_queue_list += 1
+
+def handle_net_dev_xmit(event_info):
+	global of_count_tx_xmit_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, rc, dev_name) = event_info
+	if rc == 0: # NETDEV_TX_OK
+		for i in range(len(tx_queue_list)):
+			skb = tx_queue_list[i]
+			if skb['skbaddr'] == skbaddr:
+				skb['xmit_t'] = time
+				tx_xmit_list.insert(0, skb)
+				del tx_queue_list[i]
+				if len(tx_xmit_list) > buffer_budget:
+					tx_xmit_list.pop()
+					of_count_tx_xmit_list += 1
+				return
+
+def handle_kfree_skb(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, location, protocol, reason) = event_info
+	for i in range(len(tx_queue_list)):
+		skb = tx_queue_list[i]
+		if skb['skbaddr'] == skbaddr:
+			del tx_queue_list[i]
+			return
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if rec_data['skbaddr'] == skbaddr:
+			rec_data.update({'handle':"kfree_skb",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
+
+def handle_consume_skb(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr) = event_info
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+
+def handle_skb_copy_datagram_iovec(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if skbaddr == rec_data['skbaddr']:
+			rec_data.update({'handle':"skb_copy_datagram_iovec",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return

linux-7.2.3/tools/perf/scripts/python/parallel-perf.py

@@ -0,0 +1,989 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a perf script command multiple times in parallel, using perf script
+# options --cpu and --time so that each job processes a different chunk
+# of the data.
+#
+# Copyright (c) 2024, Intel Corporation.
+
+import subprocess
+import argparse
+import pathlib
+import shlex
+import time
+import copy
+import sys
+import os
+import re
+
+glb_prog_name = "parallel-perf.py"
+glb_min_interval = 10.0
+glb_min_samples = 64
+
+class Verbosity():
+
+	def __init__(self, quiet=False, verbose=False, debug=False):
+		self.normal    = True
+		self.verbose   = verbose
+		self.debug     = debug
+		self.self_test = True
+		if self.debug:
+			self.verbose = True
+		if self.verbose:
+			quiet = False
+		if quiet:
+			self.normal = False
+
+# Manage work (Start/Wait/Kill), as represented by a subprocess.Popen command
+class Work():
+
+	def __init__(self, cmd, pipe_to, output_dir="."):
+		self.popen = None
+		self.consumer = None
+		self.cmd = cmd
+		self.pipe_to = pipe_to
+		self.output_dir = output_dir
+		self.cmdout_name = f"{output_dir}/cmd.txt"
+		self.stdout_name = f"{output_dir}/out.txt"
+		self.stderr_name = f"{output_dir}/err.txt"
+
+	def Command(self):
+		sh_cmd = [ shlex.quote(x) for x in self.cmd ]
+		return " ".join(self.cmd)
+
+	def Stdout(self):
+		return open(self.stdout_name, "w")
+
+	def Stderr(self):
+		return open(self.stderr_name, "w")
+
+	def CreateOutputDir(self):
+		pathlib.Path(self.output_dir).mkdir(parents=True, exist_ok=True)
+
+	def Start(self):
+		if self.popen:
+			return
+		self.CreateOutputDir()
+		with open(self.cmdout_name, "w") as f:
+			f.write(self.Command())
+			f.write("\n")
+		stdout = self.Stdout()
+		stderr = self.Stderr()
+		if self.pipe_to:
+			self.popen = subprocess.Popen(self.cmd, stdout=subprocess.PIPE, stderr=stderr)
+			args = shlex.split(self.pipe_to)
+			self.consumer = subprocess.Popen(args, stdin=self.popen.stdout, stdout=stdout, stderr=stderr)
+		else:
+			self.popen = subprocess.Popen(self.cmd, stdout=stdout, stderr=stderr)
+
+	def RemoveEmptyErrFile(self):
+		if os.path.exists(self.stderr_name):
+			if os.path.getsize(self.stderr_name) == 0:
+				os.unlink(self.stderr_name)
+
+	def Errors(self):
+		if os.path.exists(self.stderr_name):
+			if os.path.getsize(self.stderr_name) != 0:
+				return [ f"Non-empty error file {self.stderr_name}" ]
+		return []
+
+	def TidyUp(self):
+		self.RemoveEmptyErrFile()
+
+	def RawPollWait(self, p, wait):
+		if wait:
+			return p.wait()
+		return p.poll()
+
+	def Poll(self, wait=False):
+		if not self.popen:
+			return None
+		result = self.RawPollWait(self.popen, wait)
+		if self.consumer:
+			res = result
+			result = self.RawPollWait(self.consumer, wait)
+			if result != None and res == None:
+				self.popen.kill()
+				result = None
+			elif result == 0 and res != None and res != 0:
+				result = res
+		if result != None:
+			self.TidyUp()
+		return result
+
+	def Wait(self):
+		return self.Poll(wait=True)
+
+	def Kill(self):
+		if not self.popen:
+			return
+		self.popen.kill()
+		if self.consumer:
+			self.consumer.kill()
+
+def KillWork(worklist, verbosity):
+	for w in worklist:
+		w.Kill()
+	for w in worklist:
+		w.Wait()
+
+def NumberOfCPUs():
+	return os.sysconf("SC_NPROCESSORS_ONLN")
+
+def NanoSecsToSecsStr(x):
+	if x == None:
+		return ""
+	x = str(x)
+	if len(x) < 10:
+		x = "0" * (10 - len(x)) + x
+	return x[:len(x) - 9] + "." + x[-9:]
+
+def InsertOptionAfter(cmd, option, after):
+	try:
+		pos = cmd.index(after)
+		cmd.insert(pos + 1, option)
+	except:
+		cmd.append(option)
+
+def CreateWorkList(cmd, pipe_to, output_dir, cpus, time_ranges_by_cpu):
+	max_len = len(str(cpus[-1]))
+	cpu_dir_fmt = f"cpu-%.{max_len}u"
+	worklist = []
+	pos = 0
+	for cpu in cpus:
+		if cpu >= 0:
+			cpu_dir = os.path.join(output_dir, cpu_dir_fmt % cpu)
+			cpu_option = f"--cpu={cpu}"
+		else:
+			cpu_dir = output_dir
+			cpu_option = None
+
+		tr_dir_fmt = "time-range"
+
+		if len(time_ranges_by_cpu) > 1:
+			time_ranges = time_ranges_by_cpu[pos]
+			tr_dir_fmt += f"-{pos}"
+			pos += 1
+		else:
+			time_ranges = time_ranges_by_cpu[0]
+
+		max_len = len(str(len(time_ranges)))
+		tr_dir_fmt += f"-%.{max_len}u"
+
+		i = 0
+		for r in time_ranges:
+			if r == [None, None]:
+				time_option = None
+				work_output_dir = cpu_dir
+			else:
+				time_option = "--time=" + NanoSecsToSecsStr(r[0]) + "," + NanoSecsToSecsStr(r[1])
+				work_output_dir = os.path.join(cpu_dir, tr_dir_fmt % i)
+				i += 1
+			work_cmd = list(cmd)
+			if time_option != None:
+				InsertOptionAfter(work_cmd, time_option, "script")
+			if cpu_option != None:
+				InsertOptionAfter(work_cmd, cpu_option, "script")
+			w = Work(work_cmd, pipe_to, work_output_dir)
+			worklist.append(w)
+	return worklist
+
+def DoRunWork(worklist, nr_jobs, verbosity):
+	nr_to_do = len(worklist)
+	not_started = list(worklist)
+	running = []
+	done = []
+	chg = False
+	while True:
+		nr_done = len(done)
+		if chg and verbosity.normal:
+			nr_run = len(running)
+			print(f"\rThere are {nr_to_do} jobs: {nr_done} completed, {nr_run} running", flush=True, end=" ")
+			if verbosity.verbose:
+				print()
+			chg = False
+		if nr_done == nr_to_do:
+			break
+		while len(running) < nr_jobs and len(not_started):
+			w = not_started.pop(0)
+			running.append(w)
+			if verbosity.verbose:
+				print("Starting:", w.Command())
+			w.Start()
+			chg = True
+		if len(running):
+			time.sleep(0.1)
+		finished = []
+		not_finished = []
+		while len(running):
+			w = running.pop(0)
+			r = w.Poll()
+			if r == None:
+				not_finished.append(w)
+				continue
+			if r == 0:
+				if verbosity.verbose:
+					print("Finished:", w.Command())
+				finished.append(w)
+				chg = True
+				continue
+			if verbosity.normal and not verbosity.verbose:
+				print()
+			print("Job failed!\n    return code:", r, "\n    command:    ", w.Command())
+			if w.pipe_to:
+				print("    piped to:   ", w.pipe_to)
+			print("Killing outstanding jobs")
+			KillWork(not_finished, verbosity)
+			KillWork(running, verbosity)
+			return False
+		running = not_finished
+		done += finished
+	errorlist = []
+	for w in worklist:
+		errorlist += w.Errors()
+	if len(errorlist):
+		print("Errors:")
+		for e in errorlist:
+			print(e)
+	elif verbosity.normal:
+		print("\r"," "*50, "\rAll jobs finished successfully", flush=True)
+	return True
+
+def RunWork(worklist, nr_jobs=NumberOfCPUs(), verbosity=Verbosity()):
+	try:
+		return DoRunWork(worklist, nr_jobs, verbosity)
+	except:
+		for w in worklist:
+			w.Kill()
+		raise
+	return True
+
+def ReadHeader(perf, file_name):
+	return subprocess.Popen([perf, "script", "--header-only", "--input", file_name], stdout=subprocess.PIPE).stdout.read().decode("utf-8")
+
+def ParseHeader(hdr):
+	result = {}
+	lines = hdr.split("\n")
+	for line in lines:
+		if ":" in line and line[0] == "#":
+			pos = line.index(":")
+			name = line[1:pos-1].strip()
+			value = line[pos+1:].strip()
+			if name in result:
+				orig_name = name
+				nr = 2
+				while True:
+					name = f"{orig_name} {nr}"
+					if name not in result:
+						break
+					nr += 1
+			result[name] = value
+	return result
+
+def HeaderField(hdr_dict, hdr_fld):
+	if hdr_fld not in hdr_dict:
+		raise Exception(f"'{hdr_fld}' missing from header information")
+	return hdr_dict[hdr_fld]
+
+# Represent the position of an option within a command string
+# and provide the option value and/or remove the option
+class OptPos():
+
+	def Init(self, opt_element=-1, value_element=-1, opt_pos=-1, value_pos=-1, error=None):
+		self.opt_element = opt_element		# list element that contains option
+		self.value_element = value_element	# list element that contains option value
+		self.opt_pos = opt_pos			# string position of option
+		self.value_pos = value_pos		# string position of value
+		self.error = error			# error message string
+
+	def __init__(self, args, short_name, long_name, default=None):
+		self.args = list(args)
+		self.default = default
+		n = 2 + len(long_name)
+		m = len(short_name)
+		pos = -1
+		for opt in args:
+			pos += 1
+			if m and opt[:2] == f"-{short_name}":
+				if len(opt) == 2:
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, 0, 0)
+					else:
+						self.Init(error = f"-{short_name} option missing value")
+				else:
+					self.Init(pos, pos, 0, 2)
+				return
+			if opt[:n] == f"--{long_name}":
+				if len(opt) == n:
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, 0, 0)
+					else:
+						self.Init(error = f"--{long_name} option missing value")
+				elif opt[n] == "=":
+					self.Init(pos, pos, 0, n + 1)
+				else:
+					self.Init(error = f"--{long_name} option expected '='")
+				return
+			if m and opt[:1] == "-" and opt[:2] != "--" and short_name in opt:
+				ipos = opt.index(short_name)
+				if "-" in opt[1:]:
+					hpos = opt[1:].index("-")
+					if hpos < ipos:
+						continue
+				if ipos + 1 == len(opt):
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, ipos, 0)
+					else:
+						self.Init(error = f"-{short_name} option missing value")
+				else:
+					self.Init(pos, pos, ipos, ipos + 1)
+				return
+		self.Init()
+
+	def Value(self):
+		if self.opt_element >= 0:
+			if self.opt_element != self.value_element:
+				return self.args[self.value_element]
+			else:
+				return self.args[self.value_element][self.value_pos:]
+		return self.default
+
+	def Remove(self, args):
+		if self.opt_element == -1:
+			return
+		if self.opt_element != self.value_element:
+			del args[self.value_element]
+		if self.opt_pos:
+			args[self.opt_element] = args[self.opt_element][:self.opt_pos]
+		else:
+			del args[self.opt_element]
+
+def DetermineInputFileName(cmd):
+	p = OptPos(cmd, "i", "input", "perf.data")
+	if p.error:
+		raise Exception(f"perf command {p.error}")
+	file_name = p.Value()
+	if not os.path.exists(file_name):
+		raise Exception(f"perf command input file '{file_name}' not found")
+	return file_name
+
+def ReadOption(args, short_name, long_name, err_prefix, remove=False):
+	p = OptPos(args, short_name, long_name)
+	if p.error:
+		raise Exception(f"{err_prefix}{p.error}")
+	value = p.Value()
+	if remove:
+		p.Remove(args)
+	return value
+
+def ExtractOption(args, short_name, long_name, err_prefix):
+	return ReadOption(args, short_name, long_name, err_prefix, True)
+
+def ReadPerfOption(args, short_name, long_name):
+	return ReadOption(args, short_name, long_name, "perf command ")
+
+def ExtractPerfOption(args, short_name, long_name):
+	return ExtractOption(args, short_name, long_name, "perf command ")
+
+def PerfDoubleQuickCommands(cmd, file_name):
+	cpu_str = ReadPerfOption(cmd, "C", "cpu")
+	time_str = ReadPerfOption(cmd, "", "time")
+	# Use double-quick sampling to determine trace data density
+	times_cmd = ["perf", "script", "--ns", "--input", file_name, "--itrace=qqi"]
+	if cpu_str != None and cpu_str != "":
+		times_cmd.append(f"--cpu={cpu_str}")
+	if time_str != None and time_str != "":
+		times_cmd.append(f"--time={time_str}")
+	cnts_cmd = list(times_cmd)
+	cnts_cmd.append("-Fcpu")
+	times_cmd.append("-Fcpu,time")
+	return cnts_cmd, times_cmd
+
+class CPUTimeRange():
+	def __init__(self, cpu):
+		self.cpu = cpu
+		self.sample_cnt = 0
+		self.time_ranges = None
+		self.interval = 0
+		self.interval_remaining = 0
+		self.remaining = 0
+		self.tr_pos = 0
+
+def CalcTimeRangesByCPU(line, cpu, cpu_time_ranges, max_time):
+	cpu_time_range = cpu_time_ranges[cpu]
+	cpu_time_range.remaining -= 1
+	cpu_time_range.interval_remaining -= 1
+	if cpu_time_range.remaining == 0:
+		cpu_time_range.time_ranges[cpu_time_range.tr_pos][1] = max_time
+		return
+	if cpu_time_range.interval_remaining == 0:
+		time = TimeVal(line[1][:-1], 0)
+		time_ranges = cpu_time_range.time_ranges
+		time_ranges[cpu_time_range.tr_pos][1] = time - 1
+		time_ranges.append([time, max_time])
+		cpu_time_range.tr_pos += 1
+		cpu_time_range.interval_remaining = cpu_time_range.interval
+
+def CountSamplesByCPU(line, cpu, cpu_time_ranges):
+	try:
+		cpu_time_ranges[cpu].sample_cnt += 1
+	except:
+		print("exception")
+		print("cpu", cpu)
+		print("len(cpu_time_ranges)", len(cpu_time_ranges))
+		raise
+
+def ProcessCommandOutputLines(cmd, per_cpu, fn, *x):
+	# Assume CPU number is at beginning of line and enclosed by []
+	pat = re.compile(r"\s*\[[0-9]+\]")
+	p = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+	while True:
+		line = p.stdout.readline()
+		if line:
+			line = line.decode("utf-8")
+			if pat.match(line):
+				line = line.split()
+				if per_cpu:
+					# Assumes CPU number is enclosed by []
+					cpu = int(line[0][1:-1])
+				else:
+					cpu = 0
+				fn(line, cpu, *x)
+		else:
+			break
+	p.wait()
+
+def IntersectTimeRanges(new_time_ranges, time_ranges):
+	pos = 0
+	new_pos = 0
+	# Can assume len(time_ranges) != 0 and len(new_time_ranges) != 0
+	# Note also, there *must* be at least one intersection.
+	while pos < len(time_ranges) and new_pos < len(new_time_ranges):
+		# new end < old start => no intersection, remove new
+		if new_time_ranges[new_pos][1] < time_ranges[pos][0]:
+			del new_time_ranges[new_pos]
+			continue
+		# new start > old end => no intersection, check next
+		if new_time_ranges[new_pos][0] > time_ranges[pos][1]:
+			pos += 1
+			if pos < len(time_ranges):
+				continue
+			# no next, so remove remaining
+			while new_pos < len(new_time_ranges):
+				del new_time_ranges[new_pos]
+			return
+		# Found an intersection
+		# new start < old start => adjust new start = old start
+		if new_time_ranges[new_pos][0] < time_ranges[pos][0]:
+			new_time_ranges[new_pos][0] = time_ranges[pos][0]
+		# new end > old end => keep the overlap, insert the remainder
+		if new_time_ranges[new_pos][1] > time_ranges[pos][1]:
+			r = [ time_ranges[pos][1] + 1, new_time_ranges[new_pos][1] ]
+			new_time_ranges[new_pos][1] = time_ranges[pos][1]
+			new_pos += 1
+			new_time_ranges.insert(new_pos, r)
+			continue
+		# new [start, end] is within old [start, end]
+		new_pos += 1
+
+def SplitTimeRangesByTraceDataDensity(time_ranges, cpus, nr, cmd, file_name, per_cpu, min_size, min_interval, verbosity):
+	if verbosity.normal:
+		print("\rAnalyzing...", flush=True, end=" ")
+		if verbosity.verbose:
+			print()
+	cnts_cmd, times_cmd = PerfDoubleQuickCommands(cmd, file_name)
+
+	nr_cpus = cpus[-1] + 1 if per_cpu else 1
+	if per_cpu:
+		nr_cpus = cpus[-1] + 1
+		cpu_time_ranges = [ CPUTimeRange(cpu) for cpu in range(nr_cpus) ]
+	else:
+		nr_cpus = 1
+		cpu_time_ranges = [ CPUTimeRange(-1) ]
+
+	if verbosity.debug:
+		print("nr_cpus", nr_cpus)
+		print("cnts_cmd", cnts_cmd)
+		print("times_cmd", times_cmd)
+
+	# Count the number of "double quick" samples per CPU
+	ProcessCommandOutputLines(cnts_cmd, per_cpu, CountSamplesByCPU, cpu_time_ranges)
+
+	tot = 0
+	mx = 0
+	for cpu_time_range in cpu_time_ranges:
+		cnt = cpu_time_range.sample_cnt
+		tot += cnt
+		if cnt > mx:
+			mx = cnt
+		if verbosity.debug:
+			print("cpu:", cpu_time_range.cpu, "sample_cnt", cnt)
+
+	if min_size < 1:
+		min_size = 1
+
+	if mx < min_size:
+		# Too little data to be worth splitting
+		if verbosity.debug:
+			print("Too little data to split by time")
+		if nr == 0:
+			nr = 1
+		return [ SplitTimeRangesIntoN(time_ranges, nr, min_interval) ]
+
+	if nr:
+		divisor = nr
+		min_size = 1
+	else:
+		divisor = NumberOfCPUs()
+
+	interval = int(round(tot / divisor, 0))
+	if interval < min_size:
+		interval = min_size
+
+	if verbosity.debug:
+		print("divisor", divisor)
+		print("min_size", min_size)
+		print("interval", interval)
+
+	min_time = time_ranges[0][0]
+	max_time = time_ranges[-1][1]
+
+	for cpu_time_range in cpu_time_ranges:
+		cnt = cpu_time_range.sample_cnt
+		if cnt == 0:
+			cpu_time_range.time_ranges = copy.deepcopy(time_ranges)
+			continue
+		# Adjust target interval for CPU to give approximately equal interval sizes
+		# Determine number of intervals, rounding to nearest integer
+		n = int(round(cnt / interval, 0))
+		if n < 1:
+			n = 1
+		# Determine interval size, rounding up
+		d, m = divmod(cnt, n)
+		if m:
+			d += 1
+		cpu_time_range.interval = d
+		cpu_time_range.interval_remaining = d
+		cpu_time_range.remaining = cnt
+		# Init. time ranges for each CPU with the start time
+		cpu_time_range.time_ranges = [ [min_time, max_time] ]
+
+	# Set time ranges so that the same number of "double quick" samples
+	# will fall into each time range.
+	ProcessCommandOutputLines(times_cmd, per_cpu, CalcTimeRangesByCPU, cpu_time_ranges, max_time)
+
+	for cpu_time_range in cpu_time_ranges:
+		if cpu_time_range.sample_cnt:
+			IntersectTimeRanges(cpu_time_range.time_ranges, time_ranges)
+
+	return [cpu_time_ranges[cpu].time_ranges for cpu in cpus]
+
+def SplitSingleTimeRangeIntoN(time_range, n):
+	if n <= 1:
+		return [time_range]
+	start = time_range[0]
+	end   = time_range[1]
+	duration = int((end - start + 1) / n)
+	if duration < 1:
+		return [time_range]
+	time_ranges = []
+	for i in range(n):
+		time_ranges.append([start, start + duration - 1])
+		start += duration
+	time_ranges[-1][1] = end
+	return time_ranges
+
+def TimeRangeDuration(r):
+	return r[1] - r[0] + 1
+
+def TotalDuration(time_ranges):
+	duration = 0
+	for r in time_ranges:
+		duration += TimeRangeDuration(r)
+	return duration
+
+def SplitTimeRangesByInterval(time_ranges, interval):
+	new_ranges = []
+	for r in time_ranges:
+		duration = TimeRangeDuration(r)
+		n = duration / interval
+		n = int(round(n, 0))
+		new_ranges += SplitSingleTimeRangeIntoN(r, n)
+	return new_ranges
+
+def SplitTimeRangesIntoN(time_ranges, n, min_interval):
+	if n <= len(time_ranges):
+		return time_ranges
+	duration = TotalDuration(time_ranges)
+	interval = duration / n
+	if interval < min_interval:
+		interval = min_interval
+	return SplitTimeRangesByInterval(time_ranges, interval)
+
+def RecombineTimeRanges(tr):
+	new_tr = copy.deepcopy(tr)
+	n = len(new_tr)
+	i = 1
+	while i < len(new_tr):
+		# if prev end + 1 == cur start, combine them
+		if new_tr[i - 1][1] + 1 == new_tr[i][0]:
+			new_tr[i][0] = new_tr[i - 1][0]
+			del new_tr[i - 1]
+		else:
+			i += 1
+	return new_tr
+
+def OpenTimeRangeEnds(time_ranges, min_time, max_time):
+	if time_ranges[0][0] <= min_time:
+		time_ranges[0][0] = None
+	if time_ranges[-1][1] >= max_time:
+		time_ranges[-1][1] = None
+
+def BadTimeStr(time_str):
+	raise Exception(f"perf command bad time option: '{time_str}'\nCheck also 'time of first sample' and 'time of last sample' in perf script --header-only")
+
+def ValidateTimeRanges(time_ranges, time_str):
+	n = len(time_ranges)
+	for i in range(n):
+		start = time_ranges[i][0]
+		end   = time_ranges[i][1]
+		if i != 0 and start <= time_ranges[i - 1][1]:
+			BadTimeStr(time_str)
+		if start > end:
+			BadTimeStr(time_str)
+
+def TimeVal(s, dflt):
+	s = s.strip()
+	if s == "":
+		return dflt
+	a = s.split(".")
+	if len(a) > 2:
+		raise Exception(f"Bad time value'{s}'")
+	x = int(a[0])
+	if x < 0:
+		raise Exception("Negative time not allowed")
+	x *= 1000000000
+	if len(a) > 1:
+		x += int((a[1] + "000000000")[:9])
+	return x
+
+def BadCPUStr(cpu_str):
+	raise Exception(f"perf command bad cpu option: '{cpu_str}'\nCheck also 'nrcpus avail' in perf script --header-only")
+
+def ParseTimeStr(time_str, min_time, max_time):
+	if time_str == None or time_str == "":
+		return [[min_time, max_time]]
+	time_ranges = []
+	for r in time_str.split():
+		a = r.split(",")
+		if len(a) != 2:
+			BadTimeStr(time_str)
+		try:
+			start = TimeVal(a[0], min_time)
+			end   = TimeVal(a[1], max_time)
+		except:
+			BadTimeStr(time_str)
+		time_ranges.append([start, end])
+	ValidateTimeRanges(time_ranges, time_str)
+	return time_ranges
+
+def ParseCPUStr(cpu_str, nr_cpus):
+	if cpu_str == None or cpu_str == "":
+		return [-1]
+	cpus = []
+	for r in cpu_str.split(","):
+		a = r.split("-")
+		if len(a) < 1 or len(a) > 2:
+			BadCPUStr(cpu_str)
+		try:
+			start = int(a[0].strip())
+			if len(a) > 1:
+				end = int(a[1].strip())
+			else:
+				end = start
+		except:
+			BadCPUStr(cpu_str)
+		if start < 0 or end < 0 or end < start or end >= nr_cpus:
+			BadCPUStr(cpu_str)
+		cpus.extend(range(start, end + 1))
+	cpus = list(set(cpus)) # Remove duplicates
+	cpus.sort()
+	return cpus
+
+class ParallelPerf():
+
+	def __init__(self, a):
+		for arg_name in vars(a):
+			setattr(self, arg_name, getattr(a, arg_name))
+		self.orig_nr = self.nr
+		self.orig_cmd = list(self.cmd)
+		self.perf = self.cmd[0]
+		if os.path.exists(self.output_dir):
+			raise Exception(f"Output '{self.output_dir}' already exists")
+		if self.jobs < 0 or self.nr < 0 or self.interval < 0:
+			raise Exception("Bad options (negative values): try -h option for help")
+		if self.nr != 0 and self.interval != 0:
+			raise Exception("Cannot specify number of time subdivisions and time interval")
+		if self.jobs == 0:
+			self.jobs = NumberOfCPUs()
+		if self.nr == 0 and self.interval == 0:
+			if self.per_cpu:
+				self.nr = 1
+			else:
+				self.nr = self.jobs
+
+	def Init(self):
+		if self.verbosity.debug:
+			print("cmd", self.cmd)
+		self.file_name = DetermineInputFileName(self.cmd)
+		self.hdr = ReadHeader(self.perf, self.file_name)
+		self.hdr_dict = ParseHeader(self.hdr)
+		self.cmd_line = HeaderField(self.hdr_dict, "cmdline")
+
+	def ExtractTimeInfo(self):
+		self.min_time = TimeVal(HeaderField(self.hdr_dict, "time of first sample"), 0)
+		self.max_time = TimeVal(HeaderField(self.hdr_dict, "time of last sample"), 0)
+		self.time_str = ExtractPerfOption(self.cmd, "", "time")
+		self.time_ranges = ParseTimeStr(self.time_str, self.min_time, self.max_time)
+		if self.verbosity.debug:
+			print("time_ranges", self.time_ranges)
+
+	def ExtractCPUInfo(self):
+		if self.per_cpu:
+			nr_cpus = int(HeaderField(self.hdr_dict, "nrcpus avail"))
+			self.cpu_str = ExtractPerfOption(self.cmd, "C", "cpu")
+			if self.cpu_str == None or self.cpu_str == "":
+				self.cpus = [ x for x in range(nr_cpus) ]
+			else:
+				self.cpus = ParseCPUStr(self.cpu_str, nr_cpus)
+		else:
+			self.cpu_str = None
+			self.cpus = [-1]
+		if self.verbosity.debug:
+			print("cpus", self.cpus)
+
+	def IsIntelPT(self):
+		return self.cmd_line.find("intel_pt") >= 0
+
+	def SplitTimeRanges(self):
+		if self.IsIntelPT() and self.interval == 0:
+			self.split_time_ranges_for_each_cpu = \
+				SplitTimeRangesByTraceDataDensity(self.time_ranges, self.cpus, self.orig_nr,
+								  self.orig_cmd, self.file_name, self.per_cpu,
+								  self.min_size, self.min_interval, self.verbosity)
+		elif self.nr:
+			self.split_time_ranges_for_each_cpu = [ SplitTimeRangesIntoN(self.time_ranges, self.nr, self.min_interval) ]
+		else:
+			self.split_time_ranges_for_each_cpu = [ SplitTimeRangesByInterval(self.time_ranges, self.interval) ]
+
+	def CheckTimeRanges(self):
+		for tr in self.split_time_ranges_for_each_cpu:
+			# Re-combined time ranges should be the same
+			new_tr = RecombineTimeRanges(tr)
+			if new_tr != self.time_ranges:
+				if self.verbosity.debug:
+					print("tr", tr)
+					print("new_tr", new_tr)
+				raise Exception("Self test failed!")
+
+	def OpenTimeRangeEnds(self):
+		for time_ranges in self.split_time_ranges_for_each_cpu:
+			OpenTimeRangeEnds(time_ranges, self.min_time, self.max_time)
+
+	def CreateWorkList(self):
+		self.worklist = CreateWorkList(self.cmd, self.pipe_to, self.output_dir, self.cpus, self.split_time_ranges_for_each_cpu)
+
+	def PerfDataRecordedPerCPU(self):
+		if "--per-thread" in self.cmd_line.split():
+			return False
+		return True
+
+	def DefaultToPerCPU(self):
+		# --no-per-cpu option takes precedence
+		if self.no_per_cpu:
+			return False
+		if not self.PerfDataRecordedPerCPU():
+			return False
+		# Default to per-cpu for Intel PT data that was recorded per-cpu,
+		# because decoding can be done for each CPU separately.
+		if self.IsIntelPT():
+			return True
+		return False
+
+	def Config(self):
+		self.Init()
+		self.ExtractTimeInfo()
+		if not self.per_cpu:
+			self.per_cpu = self.DefaultToPerCPU()
+		if self.verbosity.debug:
+			print("per_cpu", self.per_cpu)
+		self.ExtractCPUInfo()
+		self.SplitTimeRanges()
+		if self.verbosity.self_test:
+			self.CheckTimeRanges()
+		# Prefer open-ended time range to starting / ending with min_time / max_time resp.
+		self.OpenTimeRangeEnds()
+		self.CreateWorkList()
+
+	def Run(self):
+		if self.dry_run:
+			print(len(self.worklist),"jobs:")
+			for w in self.worklist:
+				print(w.Command())
+			return True
+		result = RunWork(self.worklist, self.jobs, verbosity=self.verbosity)
+		if self.verbosity.verbose:
+			print(glb_prog_name, "done")
+		return result
+
+def RunParallelPerf(a):
+	pp = ParallelPerf(a)
+	pp.Config()
+	return pp.Run()
+
+def Main(args):
+	ap = argparse.ArgumentParser(
+		prog=glb_prog_name, formatter_class = argparse.RawDescriptionHelpFormatter,
+		description =
+"""
+Run a perf script command multiple times in parallel, using perf script options
+--cpu and --time so that each job processes a different chunk of the data.
+""",
+		epilog =
+"""
+Follow the options by '--' and then the perf script command e.g.
+
+	$ perf record -a -- sleep 10
+	$ parallel-perf.py --nr=4 -- perf script --ns
+	All jobs finished successfully
+	$ tree parallel-perf-output/
+	parallel-perf-output/
+	├── time-range-0
+	│   ├── cmd.txt
+	│   └── out.txt
+	├── time-range-1
+	│   ├── cmd.txt
+	│   └── out.txt
+	├── time-range-2
+	│   ├── cmd.txt
+	│   └── out.txt
+	└── time-range-3
+	    ├── cmd.txt
+	    └── out.txt
+	$ find parallel-perf-output -name cmd.txt | sort | xargs grep -H .
+	parallel-perf-output/time-range-0/cmd.txt:perf script --time=,9466.504461499 --ns
+	parallel-perf-output/time-range-1/cmd.txt:perf script --time=9466.504461500,9469.005396999 --ns
+	parallel-perf-output/time-range-2/cmd.txt:perf script --time=9469.005397000,9471.506332499 --ns
+	parallel-perf-output/time-range-3/cmd.txt:perf script --time=9471.506332500, --ns
+
+Any perf script command can be used, including the use of perf script options
+--dlfilter and --script, so that the benefit of running parallel jobs
+naturally extends to them also.
+
+If option --pipe-to is used, standard output is first piped through that
+command. Beware, if the command fails (e.g. grep with no matches), it will be
+considered a fatal error.
+
+Final standard output is redirected to files named out.txt in separate
+subdirectories under the output directory. Similarly, standard error is
+written to files named err.txt. In addition, files named cmd.txt contain the
+corresponding perf script command. After processing, err.txt files are removed
+if they are empty.
+
+If any job exits with a non-zero exit code, then all jobs are killed and no
+more are started. A message is printed if any job results in a non-empty
+err.txt file.
+
+There is a separate output subdirectory for each time range. If the --per-cpu
+option is used, these are further grouped under cpu-n subdirectories, e.g.
+
+	$ parallel-perf.py --per-cpu --nr=2 -- perf script --ns --cpu=0,1
+	All jobs finished successfully
+	$ tree parallel-perf-output
+	parallel-perf-output/
+	├── cpu-0
+	│   ├── time-range-0
+	│   │   ├── cmd.txt
+	│   │   └── out.txt
+	│   └── time-range-1
+	│       ├── cmd.txt
+	│       └── out.txt
+	└── cpu-1
+	    ├── time-range-0
+	    │   ├── cmd.txt
+	    │   └── out.txt
+	    └── time-range-1
+	        ├── cmd.txt
+	        └── out.txt
+	$ find parallel-perf-output -name cmd.txt | sort | xargs grep -H .
+	parallel-perf-output/cpu-0/time-range-0/cmd.txt:perf script --cpu=0 --time=,9469.005396999 --ns
+	parallel-perf-output/cpu-0/time-range-1/cmd.txt:perf script --cpu=0 --time=9469.005397000, --ns
+	parallel-perf-output/cpu-1/time-range-0/cmd.txt:perf script --cpu=1 --time=,9469.005396999 --ns
+	parallel-perf-output/cpu-1/time-range-1/cmd.txt:perf script --cpu=1 --time=9469.005397000, --ns
+
+Subdivisions of time range, and cpus if the --per-cpu option is used, are
+expressed by the --time and --cpu perf script options respectively. If the
+supplied perf script command has a --time option, then that time range is
+subdivided, otherwise the time range given by 'time of first sample' to
+'time of last sample' is used (refer perf script --header-only). Similarly, the
+supplied perf script command may provide a --cpu option, and only those CPUs
+will be processed.
+
+To prevent time intervals becoming too small, the --min-interval option can
+be used.
+
+Note there is special handling for processing Intel PT traces. If an interval is
+not specified and the perf record command contained the intel_pt event, then the
+time range will be subdivided in order to produce subdivisions that contain
+approximately the same amount of trace data. That is accomplished by counting
+double-quick (--itrace=qqi) samples, and choosing time ranges that encompass
+approximately the same number of samples. In that case, time ranges may not be
+the same for each CPU processed. For Intel PT, --per-cpu is the default, but
+that can be overridden by --no-per-cpu. Note, for Intel PT, double-quick
+decoding produces 1 sample for each PSB synchronization packet, which in turn
+come after a certain number of bytes output, determined by psb_period (refer
+perf Intel PT documentation). The minimum number of double-quick samples that
+will define a time range can be set by the --min_size option, which defaults to
+64.
+""")
+	ap.add_argument("-o", "--output-dir", default="parallel-perf-output", help="output directory (default 'parallel-perf-output')")
+	ap.add_argument("-j", "--jobs", type=int, default=0, help="maximum number of jobs to run in parallel at one time (default is the number of CPUs)")
+	ap.add_argument("-n", "--nr", type=int, default=0, help="number of time subdivisions (default is the number of jobs)")
+	ap.add_argument("-i", "--interval", type=float, default=0, help="subdivide the time range using this time interval (in seconds e.g. 0.1 for a tenth of a second)")
+	ap.add_argument("-c", "--per-cpu", action="store_true", help="process data for each CPU in parallel")
+	ap.add_argument("-m", "--min-interval", type=float, default=glb_min_interval, help=f"minimum interval (default {glb_min_interval} seconds)")
+	ap.add_argument("-p", "--pipe-to", help="command to pipe output to (optional)")
+	ap.add_argument("-N", "--no-per-cpu", action="store_true", help="do not process data for each CPU in parallel")
+	ap.add_argument("-b", "--min_size", type=int, default=glb_min_samples, help="minimum data size (for Intel PT in PSBs)")
+	ap.add_argument("-D", "--dry-run", action="store_true", help="do not run any jobs, just show the perf script commands")
+	ap.add_argument("-q", "--quiet", action="store_true", help="do not print any messages except errors")
+	ap.add_argument("-v", "--verbose", action="store_true", help="print more messages")
+	ap.add_argument("-d", "--debug", action="store_true", help="print debugging messages")
+	cmd_line = list(args)
+	try:
+		split_pos = cmd_line.index("--")
+		cmd = cmd_line[split_pos + 1:]
+		args = cmd_line[:split_pos]
+	except:
+		cmd = None
+		args = cmd_line
+	a = ap.parse_args(args=args[1:])
+	a.cmd = cmd
+	a.verbosity = Verbosity(a.quiet, a.verbose, a.debug)
+	try:
+		if a.cmd == None:
+			if len(args) <= 1:
+				ap.print_help()
+				return True
+			raise Exception("Command line must contain '--' before perf command")
+		return RunParallelPerf(a)
+	except Exception as e:
+		print("Fatal error: ", str(e))
+		if a.debug:
+			raise
+		return False
+
+if __name__ == "__main__":
+	if not Main(sys.argv):
+		sys.exit(1)

linux-7.2.3/tools/perf/scripts/python/powerpc-hcalls.py

@@ -0,0 +1,202 @@
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Copyright (C) 2018 Ravi Bangoria, IBM Corporation
+#
+# Hypervisor call statisics
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+# output: {
+#	opcode: {
+#		'min': minimum time nsec
+#		'max': maximum time nsec
+#		'time': average time nsec
+#		'cnt': counter
+#	} ...
+# }
+output = {}
+
+# d_enter: {
+#	cpu: {
+#		opcode: nsec
+#	} ...
+# }
+d_enter = {}
+
+hcall_table = {
+	4: 'H_REMOVE',
+	8: 'H_ENTER',
+	12: 'H_READ',
+	16: 'H_CLEAR_MOD',
+	20: 'H_CLEAR_REF',
+	24: 'H_PROTECT',
+	28: 'H_GET_TCE',
+	32: 'H_PUT_TCE',
+	36: 'H_SET_SPRG0',
+	40: 'H_SET_DABR',
+	44: 'H_PAGE_INIT',
+	48: 'H_SET_ASR',
+	52: 'H_ASR_ON',
+	56: 'H_ASR_OFF',
+	60: 'H_LOGICAL_CI_LOAD',
+	64: 'H_LOGICAL_CI_STORE',
+	68: 'H_LOGICAL_CACHE_LOAD',
+	72: 'H_LOGICAL_CACHE_STORE',
+	76: 'H_LOGICAL_ICBI',
+	80: 'H_LOGICAL_DCBF',
+	84: 'H_GET_TERM_CHAR',
+	88: 'H_PUT_TERM_CHAR',
+	92: 'H_REAL_TO_LOGICAL',
+	96: 'H_HYPERVISOR_DATA',
+	100: 'H_EOI',
+	104: 'H_CPPR',
+	108: 'H_IPI',
+	112: 'H_IPOLL',
+	116: 'H_XIRR',
+	120: 'H_MIGRATE_DMA',
+	124: 'H_PERFMON',
+	220: 'H_REGISTER_VPA',
+	224: 'H_CEDE',
+	228: 'H_CONFER',
+	232: 'H_PROD',
+	236: 'H_GET_PPP',
+	240: 'H_SET_PPP',
+	244: 'H_PURR',
+	248: 'H_PIC',
+	252: 'H_REG_CRQ',
+	256: 'H_FREE_CRQ',
+	260: 'H_VIO_SIGNAL',
+	264: 'H_SEND_CRQ',
+	272: 'H_COPY_RDMA',
+	276: 'H_REGISTER_LOGICAL_LAN',
+	280: 'H_FREE_LOGICAL_LAN',
+	284: 'H_ADD_LOGICAL_LAN_BUFFER',
+	288: 'H_SEND_LOGICAL_LAN',
+	292: 'H_BULK_REMOVE',
+	304: 'H_MULTICAST_CTRL',
+	308: 'H_SET_XDABR',
+	312: 'H_STUFF_TCE',
+	316: 'H_PUT_TCE_INDIRECT',
+	332: 'H_CHANGE_LOGICAL_LAN_MAC',
+	336: 'H_VTERM_PARTNER_INFO',
+	340: 'H_REGISTER_VTERM',
+	344: 'H_FREE_VTERM',
+	348: 'H_RESET_EVENTS',
+	352: 'H_ALLOC_RESOURCE',
+	356: 'H_FREE_RESOURCE',
+	360: 'H_MODIFY_QP',
+	364: 'H_QUERY_QP',
+	368: 'H_REREGISTER_PMR',
+	372: 'H_REGISTER_SMR',
+	376: 'H_QUERY_MR',
+	380: 'H_QUERY_MW',
+	384: 'H_QUERY_HCA',
+	388: 'H_QUERY_PORT',
+	392: 'H_MODIFY_PORT',
+	396: 'H_DEFINE_AQP1',
+	400: 'H_GET_TRACE_BUFFER',
+	404: 'H_DEFINE_AQP0',
+	408: 'H_RESIZE_MR',
+	412: 'H_ATTACH_MCQP',
+	416: 'H_DETACH_MCQP',
+	420: 'H_CREATE_RPT',
+	424: 'H_REMOVE_RPT',
+	428: 'H_REGISTER_RPAGES',
+	432: 'H_DISABLE_AND_GETC',
+	436: 'H_ERROR_DATA',
+	440: 'H_GET_HCA_INFO',
+	444: 'H_GET_PERF_COUNT',
+	448: 'H_MANAGE_TRACE',
+	468: 'H_FREE_LOGICAL_LAN_BUFFER',
+	472: 'H_POLL_PENDING',
+	484: 'H_QUERY_INT_STATE',
+	580: 'H_ILLAN_ATTRIBUTES',
+	592: 'H_MODIFY_HEA_QP',
+	596: 'H_QUERY_HEA_QP',
+	600: 'H_QUERY_HEA',
+	604: 'H_QUERY_HEA_PORT',
+	608: 'H_MODIFY_HEA_PORT',
+	612: 'H_REG_BCMC',
+	616: 'H_DEREG_BCMC',
+	620: 'H_REGISTER_HEA_RPAGES',
+	624: 'H_DISABLE_AND_GET_HEA',
+	628: 'H_GET_HEA_INFO',
+	632: 'H_ALLOC_HEA_RESOURCE',
+	644: 'H_ADD_CONN',
+	648: 'H_DEL_CONN',
+	664: 'H_JOIN',
+	676: 'H_VASI_STATE',
+	688: 'H_ENABLE_CRQ',
+	696: 'H_GET_EM_PARMS',
+	720: 'H_SET_MPP',
+	724: 'H_GET_MPP',
+	748: 'H_HOME_NODE_ASSOCIATIVITY',
+	756: 'H_BEST_ENERGY',
+	764: 'H_XIRR_X',
+	768: 'H_RANDOM',
+	772: 'H_COP',
+	788: 'H_GET_MPP_X',
+	796: 'H_SET_MODE',
+	61440: 'H_RTAS',
+}
+
+def hcall_table_lookup(opcode):
+	if (opcode in hcall_table):
+		return hcall_table[opcode]
+	else:
+		return opcode
+
+print_ptrn = '%-28s%10s%10s%10s%10s'
+
+def trace_end():
+	print(print_ptrn % ('hcall', 'count', 'min(ns)', 'max(ns)', 'avg(ns)'))
+	print('-' * 68)
+	for opcode in output:
+		h_name = hcall_table_lookup(opcode)
+		time = output[opcode]['time']
+		cnt = output[opcode]['cnt']
+		min_t = output[opcode]['min']
+		max_t = output[opcode]['max']
+
+		print(print_ptrn % (h_name, cnt, min_t, max_t, time//cnt))
+
+def powerpc__hcall_exit(name, context, cpu, sec, nsec, pid, comm, callchain,
+			opcode, retval):
+	if (cpu in d_enter and opcode in d_enter[cpu]):
+		diff = nsecs(sec, nsec) - d_enter[cpu][opcode]
+
+		if (opcode in output):
+			output[opcode]['time'] += diff
+			output[opcode]['cnt'] += 1
+			if (output[opcode]['min'] > diff):
+				output[opcode]['min'] = diff
+			if (output[opcode]['max'] < diff):
+				output[opcode]['max'] = diff
+		else:
+			output[opcode] = {
+				'time': diff,
+				'cnt': 1,
+				'min': diff,
+				'max': diff,
+			}
+
+		del d_enter[cpu][opcode]
+#	else:
+#		print("Can't find matching hcall_enter event. Ignoring sample")
+
+def powerpc__hcall_entry(event_name, context, cpu, sec, nsec, pid, comm,
+			 callchain, opcode):
+		if (cpu in d_enter):
+			d_enter[cpu][opcode] = nsecs(sec, nsec)
+		else:
+			d_enter[cpu] = {opcode: nsecs(sec, nsec)}

linux-7.2.3/tools/perf/scripts/python/sched-migration.py

@@ -0,0 +1,462 @@
+# Cpu task migration overview toy
+#
+# Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com>
+#
+# perf script event handlers have been generated by perf script -g python
+#
+# This software is distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+from __future__ import print_function
+
+import os
+import sys
+
+from collections import defaultdict
+try:
+	from UserList import UserList
+except ImportError:
+	# Python 3: UserList moved to the collections package
+	from collections import UserList
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+sys.path.append('scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from SchedGui import *
+
+
+threads = { 0 : "idle"}
+
+def thread_name(pid):
+	return "%s:%d" % (threads[pid], pid)
+
+class RunqueueEventUnknown:
+	@staticmethod
+	def color():
+		return None
+
+	def __repr__(self):
+		return "unknown"
+
+class RunqueueEventSleep:
+	@staticmethod
+	def color():
+		return (0, 0, 0xff)
+
+	def __init__(self, sleeper):
+		self.sleeper = sleeper
+
+	def __repr__(self):
+		return "%s gone to sleep" % thread_name(self.sleeper)
+
+class RunqueueEventWakeup:
+	@staticmethod
+	def color():
+		return (0xff, 0xff, 0)
+
+	def __init__(self, wakee):
+		self.wakee = wakee
+
+	def __repr__(self):
+		return "%s woke up" % thread_name(self.wakee)
+
+class RunqueueEventFork:
+	@staticmethod
+	def color():
+		return (0, 0xff, 0)
+
+	def __init__(self, child):
+		self.child = child
+
+	def __repr__(self):
+		return "new forked task %s" % thread_name(self.child)
+
+class RunqueueMigrateIn:
+	@staticmethod
+	def color():
+		return (0, 0xf0, 0xff)
+
+	def __init__(self, new):
+		self.new = new
+
+	def __repr__(self):
+		return "task migrated in %s" % thread_name(self.new)
+
+class RunqueueMigrateOut:
+	@staticmethod
+	def color():
+		return (0xff, 0, 0xff)
+
+	def __init__(self, old):
+		self.old = old
+
+	def __repr__(self):
+		return "task migrated out %s" % thread_name(self.old)
+
+class RunqueueSnapshot:
+	def __init__(self, tasks = [0], event = RunqueueEventUnknown()):
+		self.tasks = tuple(tasks)
+		self.event = event
+
+	def sched_switch(self, prev, prev_state, next):
+		event = RunqueueEventUnknown()
+
+		if taskState(prev_state) == "R" and next in self.tasks \
+			and prev in self.tasks:
+			return self
+
+		if taskState(prev_state) != "R":
+			event = RunqueueEventSleep(prev)
+
+		next_tasks = list(self.tasks[:])
+		if prev in self.tasks:
+			if taskState(prev_state) != "R":
+				next_tasks.remove(prev)
+		elif taskState(prev_state) == "R":
+			next_tasks.append(prev)
+
+		if next not in next_tasks:
+			next_tasks.append(next)
+
+		return RunqueueSnapshot(next_tasks, event)
+
+	def migrate_out(self, old):
+		if old not in self.tasks:
+			return self
+		next_tasks = [task for task in self.tasks if task != old]
+
+		return RunqueueSnapshot(next_tasks, RunqueueMigrateOut(old))
+
+	def __migrate_in(self, new, event):
+		if new in self.tasks:
+			self.event = event
+			return self
+		next_tasks = self.tasks[:] + tuple([new])
+
+		return RunqueueSnapshot(next_tasks, event)
+
+	def migrate_in(self, new):
+		return self.__migrate_in(new, RunqueueMigrateIn(new))
+
+	def wake_up(self, new):
+		return self.__migrate_in(new, RunqueueEventWakeup(new))
+
+	def wake_up_new(self, new):
+		return self.__migrate_in(new, RunqueueEventFork(new))
+
+	def load(self):
+		""" Provide the number of tasks on the runqueue.
+		    Don't count idle"""
+		return len(self.tasks) - 1
+
+	def __repr__(self):
+		ret = self.tasks.__repr__()
+		ret += self.origin_tostring()
+
+		return ret
+
+class TimeSlice:
+	def __init__(self, start, prev):
+		self.start = start
+		self.prev = prev
+		self.end = start
+		# cpus that triggered the event
+		self.event_cpus = []
+		if prev is not None:
+			self.total_load = prev.total_load
+			self.rqs = prev.rqs.copy()
+		else:
+			self.rqs = defaultdict(RunqueueSnapshot)
+			self.total_load = 0
+
+	def __update_total_load(self, old_rq, new_rq):
+		diff = new_rq.load() - old_rq.load()
+		self.total_load += diff
+
+	def sched_switch(self, ts_list, prev, prev_state, next, cpu):
+		old_rq = self.prev.rqs[cpu]
+		new_rq = old_rq.sched_switch(prev, prev_state, next)
+
+		if old_rq is new_rq:
+			return
+
+		self.rqs[cpu] = new_rq
+		self.__update_total_load(old_rq, new_rq)
+		ts_list.append(self)
+		self.event_cpus = [cpu]
+
+	def migrate(self, ts_list, new, old_cpu, new_cpu):
+		if old_cpu == new_cpu:
+			return
+		old_rq = self.prev.rqs[old_cpu]
+		out_rq = old_rq.migrate_out(new)
+		self.rqs[old_cpu] = out_rq
+		self.__update_total_load(old_rq, out_rq)
+
+		new_rq = self.prev.rqs[new_cpu]
+		in_rq = new_rq.migrate_in(new)
+		self.rqs[new_cpu] = in_rq
+		self.__update_total_load(new_rq, in_rq)
+
+		ts_list.append(self)
+
+		if old_rq is not out_rq:
+			self.event_cpus.append(old_cpu)
+		self.event_cpus.append(new_cpu)
+
+	def wake_up(self, ts_list, pid, cpu, fork):
+		old_rq = self.prev.rqs[cpu]
+		if fork:
+			new_rq = old_rq.wake_up_new(pid)
+		else:
+			new_rq = old_rq.wake_up(pid)
+
+		if new_rq is old_rq:
+			return
+		self.rqs[cpu] = new_rq
+		self.__update_total_load(old_rq, new_rq)
+		ts_list.append(self)
+		self.event_cpus = [cpu]
+
+	def next(self, t):
+		self.end = t
+		return TimeSlice(t, self)
+
+class TimeSliceList(UserList):
+	def __init__(self, arg = []):
+		self.data = arg
+
+	def get_time_slice(self, ts):
+		if len(self.data) == 0:
+			slice = TimeSlice(ts, TimeSlice(-1, None))
+		else:
+			slice = self.data[-1].next(ts)
+		return slice
+
+	def find_time_slice(self, ts):
+		start = 0
+		end = len(self.data)
+		found = -1
+		searching = True
+		while searching:
+			if start == end or start == end - 1:
+				searching = False
+
+			i = (end + start) / 2
+			if self.data[i].start <= ts and self.data[i].end >= ts:
+				found = i
+				end = i
+				continue
+
+			if self.data[i].end < ts:
+				start = i
+
+			elif self.data[i].start > ts:
+				end = i
+
+		return found
+
+	def set_root_win(self, win):
+		self.root_win = win
+
+	def mouse_down(self, cpu, t):
+		idx = self.find_time_slice(t)
+		if idx == -1:
+			return
+
+		ts = self[idx]
+		rq = ts.rqs[cpu]
+		raw = "CPU: %d\n" % cpu
+		raw += "Last event : %s\n" % rq.event.__repr__()
+		raw += "Timestamp : %d.%06d\n" % (ts.start / (10 ** 9), (ts.start % (10 ** 9)) / 1000)
+		raw += "Duration : %6d us\n" % ((ts.end - ts.start) / (10 ** 6))
+		raw += "Load = %d\n" % rq.load()
+		for t in rq.tasks:
+			raw += "%s \n" % thread_name(t)
+
+		self.root_win.update_summary(raw)
+
+	def update_rectangle_cpu(self, slice, cpu):
+		rq = slice.rqs[cpu]
+
+		if slice.total_load != 0:
+			load_rate = rq.load() / float(slice.total_load)
+		else:
+			load_rate = 0
+
+		red_power = int(0xff - (0xff * load_rate))
+		color = (0xff, red_power, red_power)
+
+		top_color = None
+
+		if cpu in slice.event_cpus:
+			top_color = rq.event.color()
+
+		self.root_win.paint_rectangle_zone(cpu, color, top_color, slice.start, slice.end)
+
+	def fill_zone(self, start, end):
+		i = self.find_time_slice(start)
+		if i == -1:
+			return
+
+		for i in range(i, len(self.data)):
+			timeslice = self.data[i]
+			if timeslice.start > end:
+				return
+
+			for cpu in timeslice.rqs:
+				self.update_rectangle_cpu(timeslice, cpu)
+
+	def interval(self):
+		if len(self.data) == 0:
+			return (0, 0)
+
+		return (self.data[0].start, self.data[-1].end)
+
+	def nr_rectangles(self):
+		last_ts = self.data[-1]
+		max_cpu = 0
+		for cpu in last_ts.rqs:
+			if cpu > max_cpu:
+				max_cpu = cpu
+		return max_cpu
+
+
+class SchedEventProxy:
+	def __init__(self):
+		self.current_tsk = defaultdict(lambda : -1)
+		self.timeslices = TimeSliceList()
+
+	def sched_switch(self, headers, prev_comm, prev_pid, prev_prio, prev_state,
+			 next_comm, next_pid, next_prio):
+		""" Ensure the task we sched out this cpu is really the one
+		    we logged. Otherwise we may have missed traces """
+
+		on_cpu_task = self.current_tsk[headers.cpu]
+
+		if on_cpu_task != -1 and on_cpu_task != prev_pid:
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+
+		threads[prev_pid] = prev_comm
+		threads[next_pid] = next_comm
+		self.current_tsk[headers.cpu] = next_pid
+
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.sched_switch(self.timeslices, prev_pid, prev_state, next_pid, headers.cpu)
+
+	def migrate(self, headers, pid, prio, orig_cpu, dest_cpu):
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.migrate(self.timeslices, pid, orig_cpu, dest_cpu)
+
+	def wake_up(self, headers, comm, pid, success, target_cpu, fork):
+		if success == 0:
+			return
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.wake_up(self.timeslices, pid, target_cpu, fork)
+
+
+def trace_begin():
+	global parser
+	parser = SchedEventProxy()
+
+def trace_end():
+	app = wx.App(False)
+	timeslices = parser.timeslices
+	frame = RootFrame(timeslices, "Migration")
+	app.MainLoop()
+
+def sched__sched_stat_runtime(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, runtime, vruntime):
+	pass
+
+def sched__sched_stat_iowait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, delay):
+	pass
+
+def sched__sched_stat_sleep(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, delay):
+	pass
+
+def sched__sched_stat_wait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, delay):
+	pass
+
+def sched__sched_process_fork(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, parent_comm, parent_pid, child_comm, child_pid):
+	pass
+
+def sched__sched_process_wait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio):
+	pass
+
+def sched__sched_process_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio):
+	pass
+
+def sched__sched_process_free(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio):
+	pass
+
+def sched__sched_migrate_task(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio, orig_cpu,
+	dest_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm, common_callchain)
+	parser.migrate(headers, pid, prio, orig_cpu, dest_cpu)
+
+def sched__sched_switch(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm, common_callchain,
+	prev_comm, prev_pid, prev_prio, prev_state,
+	next_comm, next_pid, next_prio):
+
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm, common_callchain)
+	parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state,
+			 next_comm, next_pid, next_prio)
+
+def sched__sched_wakeup_new(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio, success,
+	target_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm, common_callchain)
+	parser.wake_up(headers, comm, pid, success, target_cpu, 1)
+
+def sched__sched_wakeup(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio, success,
+	target_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm, common_callchain)
+	parser.wake_up(headers, comm, pid, success, target_cpu, 0)
+
+def sched__sched_wait_task(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid, prio):
+	pass
+
+def sched__sched_kthread_stop_ret(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, ret):
+	pass
+
+def sched__sched_kthread_stop(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, comm, pid):
+	pass
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	pass

linux-7.2.3/tools/perf/scripts/python/sctop.py

@@ -0,0 +1,89 @@
+# system call top
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Periodically displays system-wide system call totals, broken down by
+# syscall.  If a [comm] arg is specified, only syscalls called by
+# [comm] are displayed. If an [interval] arg is specified, the display
+# will be refreshed every [interval] seconds.  The default interval is
+# 3 seconds.
+
+from __future__ import print_function
+
+import os, sys, time
+
+try:
+	import thread
+except ImportError:
+	import _thread as thread
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+usage = "perf script -s sctop.py [comm] [interval]\n";
+
+for_comm = None
+default_interval = 3
+interval = default_interval
+
+if len(sys.argv) > 3:
+	sys.exit(usage)
+
+if len(sys.argv) > 2:
+	for_comm = sys.argv[1]
+	interval = int(sys.argv[2])
+elif len(sys.argv) > 1:
+	try:
+		interval = int(sys.argv[1])
+	except ValueError:
+		for_comm = sys.argv[1]
+		interval = default_interval
+
+syscalls = autodict()
+
+def trace_begin():
+	thread.start_new_thread(print_syscall_totals, (interval,))
+	pass
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	common_callchain, id, args):
+	if for_comm is not None:
+		if common_comm != for_comm:
+			return
+	try:
+		syscalls[id] += 1
+	except TypeError:
+		syscalls[id] = 1
+
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
+def print_syscall_totals(interval):
+	while 1:
+		clear_term()
+		if for_comm is not None:
+			print("\nsyscall events for %s:\n" % (for_comm))
+		else:
+			print("\nsyscall events:\n")
+
+		print("%-40s  %10s" % ("event", "count"))
+		print("%-40s  %10s" %
+			("----------------------------------------",
+			"----------"))
+
+		for id, val in sorted(syscalls.items(),
+				key = lambda kv: (kv[1], kv[0]),
+				reverse = True):
+			try:
+				print("%-40s  %10d" % (syscall_name(id), val))
+			except TypeError:
+				pass
+		syscalls.clear()
+		time.sleep(interval)

linux-7.2.3/tools/perf/scripts/python/stackcollapse.py

@@ -0,0 +1,127 @@
+# stackcollapse.py - format perf samples with one line per distinct call stack
+# SPDX-License-Identifier: GPL-2.0
+#
+# This script's output has two space-separated fields.  The first is a semicolon
+# separated stack including the program name (from the "comm" field) and the
+# function names from the call stack.  The second is a count:
+#
+#  swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2
+#
+# The file is sorted according to the first field.
+#
+# Input may be created and processed using:
+#
+#  perf record -a -g -F 99 sleep 60
+#  perf script report stackcollapse > out.stacks-folded
+#
+# (perf script record stackcollapse works too).
+#
+# Written by Paolo Bonzini <pbonzini@redhat.com>
+# Based on Brendan Gregg's stackcollapse-perf.pl script.
+
+from __future__ import print_function
+
+import os
+import sys
+from collections import defaultdict
+from optparse import OptionParser, make_option
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+    '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from EventClass import *
+
+# command line parsing
+
+option_list = [
+    # formatting options for the bottom entry of the stack
+    make_option("--include-tid", dest="include_tid",
+                 action="store_true", default=False,
+                 help="include thread id in stack"),
+    make_option("--include-pid", dest="include_pid",
+                 action="store_true", default=False,
+                 help="include process id in stack"),
+    make_option("--no-comm", dest="include_comm",
+                 action="store_false", default=True,
+                 help="do not separate stacks according to comm"),
+    make_option("--tidy-java", dest="tidy_java",
+                 action="store_true", default=False,
+                 help="beautify Java signatures"),
+    make_option("--kernel", dest="annotate_kernel",
+                 action="store_true", default=False,
+                 help="annotate kernel functions with _[k]")
+]
+
+parser = OptionParser(option_list=option_list)
+(opts, args) = parser.parse_args()
+
+if len(args) != 0:
+    parser.error("unexpected command line argument")
+if opts.include_tid and not opts.include_comm:
+    parser.error("requesting tid but not comm is invalid")
+if opts.include_pid and not opts.include_comm:
+    parser.error("requesting pid but not comm is invalid")
+
+# event handlers
+
+lines = defaultdict(lambda: 0)
+
+def process_event(param_dict):
+    def tidy_function_name(sym, dso):
+        if sym is None:
+            sym = '[unknown]'
+
+        sym = sym.replace(';', ':')
+        if opts.tidy_java:
+            # the original stackcollapse-perf.pl script gives the
+            # example of converting this:
+            #    Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V
+            # to this:
+            #    org/mozilla/javascript/MemberBox:.init
+            sym = sym.replace('<', '')
+            sym = sym.replace('>', '')
+            if sym[0] == 'L' and sym.find('/'):
+                sym = sym[1:]
+            try:
+                sym = sym[:sym.index('(')]
+            except ValueError:
+                pass
+
+        if opts.annotate_kernel and dso == '[kernel.kallsyms]':
+            return sym + '_[k]'
+        else:
+            return sym
+
+    stack = list()
+    if 'callchain' in param_dict:
+        for entry in param_dict['callchain']:
+            entry.setdefault('sym', dict())
+            entry['sym'].setdefault('name', None)
+            entry.setdefault('dso', None)
+            stack.append(tidy_function_name(entry['sym']['name'],
+                                            entry['dso']))
+    else:
+        param_dict.setdefault('symbol', None)
+        param_dict.setdefault('dso', None)
+        stack.append(tidy_function_name(param_dict['symbol'],
+                                        param_dict['dso']))
+
+    if opts.include_comm:
+        comm = param_dict["comm"].replace(' ', '_')
+        sep = "-"
+        if opts.include_pid:
+            comm = comm + sep + str(param_dict['sample']['pid'])
+            sep = "/"
+        if opts.include_tid:
+            comm = comm + sep + str(param_dict['sample']['tid'])
+        stack.append(comm)
+
+    stack_string = ';'.join(reversed(stack))
+    lines[stack_string] = lines[stack_string] + 1
+
+def trace_end():
+    list = sorted(lines)
+    for stack in list:
+        print("%s %d" % (stack, lines[stack]))

linux-7.2.3/tools/perf/scripts/python/stat-cpi.py

@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from __future__ import print_function
+
+data    = {}
+times   = []
+threads = []
+cpus    = []
+
+def get_key(time, event, cpu, thread):
+    return "%d-%s-%d-%d" % (time, event, cpu, thread)
+
+def store_key(time, cpu, thread):
+    if (time not in times):
+        times.append(time)
+
+    if (cpu not in cpus):
+        cpus.append(cpu)
+
+    if (thread not in threads):
+        threads.append(thread)
+
+def store(time, event, cpu, thread, val, ena, run):
+    #print("event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" %
+    #      (event, cpu, thread, time, val, ena, run))
+
+    store_key(time, cpu, thread)
+    key = get_key(time, event, cpu, thread)
+    data[key] = [ val, ena, run]
+
+def get(time, event, cpu, thread):
+    key = get_key(time, event, cpu, thread)
+    return data[key][0]
+
+def stat__cycles_k(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_k(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles_u(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_u(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__interval(time):
+    for cpu in cpus:
+        for thread in threads:
+            cyc = get(time, "cycles", cpu, thread)
+            ins = get(time, "instructions", cpu, thread)
+            cpi = 0
+
+            if ins != 0:
+                cpi = cyc/float(ins)
+
+            print("%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins))
+
+def trace_end():
+    pass
+# XXX trace_end callback could be used as an alternative place
+#     to compute same values as in the script above:
+#
+#    for time in times:
+#        for cpu in cpus:
+#            for thread in threads:
+#                cyc = get(time, "cycles", cpu, thread)
+#                ins = get(time, "instructions", cpu, thread)
+#
+#                if ins != 0:
+#                    cpi = cyc/float(ins)
+#
+#                print("time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi))

linux-7.2.3/tools/perf/scripts/python/syscall-counts-by-pid.py

@@ -0,0 +1,75 @@
+# system call counts, by pid
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide system call totals, broken down by syscall.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+from __future__ import print_function
+
+import os, sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import syscall_name
+
+usage = "perf script -s syscall-counts-by-pid.py [comm]\n";
+
+for_comm = None
+for_pid = None
+
+if len(sys.argv) > 2:
+	sys.exit(usage)
+
+if len(sys.argv) > 1:
+	try:
+		for_pid = int(sys.argv[1])
+	except:
+		for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+	print("Press control+C to stop and show the summary")
+
+def trace_end():
+	print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+		common_secs, common_nsecs, common_pid, common_comm,
+		common_callchain, id, args):
+	if (for_comm and common_comm != for_comm) or \
+		(for_pid and common_pid != for_pid ):
+		return
+	try:
+		syscalls[common_comm][common_pid][id] += 1
+	except TypeError:
+		syscalls[common_comm][common_pid][id] = 1
+
+def syscalls__sys_enter(event_name, context, common_cpu,
+		common_secs, common_nsecs, common_pid, common_comm,
+		id, args):
+	raw_syscalls__sys_enter(**locals())
+
+def print_syscall_totals():
+	if for_comm is not None:
+		print("\nsyscall events for %s:\n" % (for_comm))
+	else:
+		print("\nsyscall events by comm/pid:\n")
+
+	print("%-40s  %10s" % ("comm [pid]/syscalls", "count"))
+	print("%-40s  %10s" % ("----------------------------------------",
+				"----------"))
+
+	comm_keys = syscalls.keys()
+	for comm in comm_keys:
+		pid_keys = syscalls[comm].keys()
+		for pid in pid_keys:
+			print("\n%s [%d]" % (comm, pid))
+			id_keys = syscalls[comm][pid].keys()
+			for id, val in sorted(syscalls[comm][pid].items(),
+				key = lambda kv: (kv[1], kv[0]), reverse = True):
+				print("  %-38s  %10d" % (syscall_name(id), val))

linux-7.2.3/tools/perf/scripts/python/syscall-counts.py

@@ -0,0 +1,65 @@
+# system call counts
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide system call totals, broken down by syscall.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+from __future__ import print_function
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import syscall_name
+
+usage = "perf script -s syscall-counts.py [comm]\n";
+
+for_comm = None
+
+if len(sys.argv) > 2:
+	sys.exit(usage)
+
+if len(sys.argv) > 1:
+	for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+	print("Press control+C to stop and show the summary")
+
+def trace_end():
+	print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+		common_secs, common_nsecs, common_pid, common_comm,
+		common_callchain, id, args):
+	if for_comm is not None:
+		if common_comm != for_comm:
+			return
+	try:
+		syscalls[id] += 1
+	except TypeError:
+		syscalls[id] = 1
+
+def syscalls__sys_enter(event_name, context, common_cpu,
+		common_secs, common_nsecs, common_pid, common_comm, id, args):
+	raw_syscalls__sys_enter(**locals())
+
+def print_syscall_totals():
+	if for_comm is not None:
+		print("\nsyscall events for %s:\n" % (for_comm))
+	else:
+		print("\nsyscall events:\n")
+
+	print("%-40s  %10s" % ("event", "count"))
+	print("%-40s  %10s" % ("----------------------------------------",
+				"-----------"))
+
+	for id, val in sorted(syscalls.items(),
+			key = lambda kv: (kv[1], kv[0]), reverse = True):
+		print("%-40s  %10d" % (syscall_name(id), val))

linux-7.2.3/tools/perf/scripts/python/task-analyzer.py

@@ -0,0 +1,934 @@
+# task-analyzer.py - comprehensive perf tasks analysis
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2022, Hagen Paul Pfeifer <hagen@jauu.net>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Usage:
+#
+#     perf record -e sched:sched_switch -a -- sleep 10
+#     perf script report task-analyzer
+#
+
+from __future__ import print_function
+import sys
+import os
+import string
+import argparse
+import decimal
+
+
+sys.path.append(
+    os.environ["PERF_EXEC_PATH"] + "/scripts/python/Perf-Trace-Util/lib/Perf/Trace"
+)
+from perf_trace_context import *
+from Core import *
+
+# Definition of possible ASCII color codes
+_COLORS = {
+    "grey": "\033[90m",
+    "red": "\033[91m",
+    "green": "\033[92m",
+    "yellow": "\033[93m",
+    "blue": "\033[94m",
+    "violet": "\033[95m",
+    "reset": "\033[0m",
+}
+
+# Columns will have a static size to align everything properly
+# Support of 116 days of active update with nano precision
+LEN_SWITCHED_IN = len("9999999.999999999")  # 17
+LEN_SWITCHED_OUT = len("9999999.999999999")  # 17
+LEN_CPU = len("000")
+LEN_PID = len("maxvalue")  # 8
+LEN_TID = len("maxvalue")  # 8
+LEN_COMM = len("max-comms-length")  # 16
+LEN_RUNTIME = len("999999.999")  # 10
+# Support of 3.45 hours of timespans
+LEN_OUT_IN = len("99999999999.999")  # 15
+LEN_OUT_OUT = len("99999999999.999")  # 15
+LEN_IN_IN = len("99999999999.999")  # 15
+LEN_IN_OUT = len("99999999999.999")  # 15
+
+
+# py2/py3 compatibility layer, see PEP469
+try:
+    dict.iteritems
+except AttributeError:
+    # py3
+    def itervalues(d):
+        return iter(d.values())
+
+    def iteritems(d):
+        return iter(d.items())
+
+else:
+    # py2
+    def itervalues(d):
+        return d.itervalues()
+
+    def iteritems(d):
+        return d.iteritems()
+
+
+def _check_color():
+    global _COLORS
+    """user enforced no-color or if stdout is no tty we disable colors"""
+    if sys.stdout.isatty() and args.stdio_color != "never":
+        return
+    _COLORS = {
+        "grey": "",
+        "red": "",
+        "green": "",
+        "yellow": "",
+        "blue": "",
+        "violet": "",
+        "reset": "",
+    }
+
+
+def _parse_args():
+    global args
+    parser = argparse.ArgumentParser(description="Analyze tasks behavior")
+    parser.add_argument(
+        "--time-limit",
+        default=[],
+        help=
+            "print tasks only in time[s] window e.g"
+        " --time-limit 123.111:789.222(print all between 123.111 and 789.222)"
+        " --time-limit 123: (print all from 123)"
+        " --time-limit :456 (print all until incl. 456)",
+    )
+    parser.add_argument(
+        "--summary", action="store_true", help="print addtional runtime information"
+    )
+    parser.add_argument(
+        "--summary-only", action="store_true", help="print only summary without traces"
+    )
+    parser.add_argument(
+        "--summary-extended",
+        action="store_true",
+        help="print the summary with additional information of max inter task times"
+            " relative to the prev task",
+    )
+    parser.add_argument(
+        "--ns", action="store_true", help="show timestamps in nanoseconds"
+    )
+    parser.add_argument(
+        "--ms", action="store_true", help="show timestamps in milliseconds"
+    )
+    parser.add_argument(
+        "--extended-times",
+        action="store_true",
+        help="Show the elapsed times between schedule in/schedule out"
+            " of this task and the schedule in/schedule out of previous occurrence"
+            " of the same task",
+    )
+    parser.add_argument(
+        "--filter-tasks",
+        default=[],
+        help="filter out unneeded tasks by tid, pid or processname."
+        " E.g --filter-task 1337,/sbin/init ",
+    )
+    parser.add_argument(
+        "--limit-to-tasks",
+        default=[],
+        help="limit output to selected task by tid, pid, processname."
+        " E.g --limit-to-tasks 1337,/sbin/init",
+    )
+    parser.add_argument(
+        "--highlight-tasks",
+        default="",
+        help="colorize special tasks by their pid/tid/comm."
+        " E.g. --highlight-tasks 1:red,mutt:yellow"
+        " Colors available: red,grey,yellow,blue,violet,green",
+    )
+    parser.add_argument(
+        "--rename-comms-by-tids",
+        default="",
+        help="rename task names by using tid (<tid>:<newname>,<tid>:<newname>)"
+            " This option is handy for inexpressive processnames like python interpreted"
+            " process. E.g --rename 1337:my-python-app",
+    )
+    parser.add_argument(
+        "--stdio-color",
+        default="auto",
+        choices=["always", "never", "auto"],
+        help="always, never or auto, allowing configuring color output"
+            " via the command line",
+    )
+    parser.add_argument(
+        "--csv",
+        default="",
+        help="Write trace to file selected by user. Options, like --ns or --extended"
+            "-times are used.",
+    )
+    parser.add_argument(
+        "--csv-summary",
+        default="",
+        help="Write summary to file selected by user. Options, like --ns or"
+            " --summary-extended are used.",
+    )
+    args = parser.parse_args()
+    args.tid_renames = dict()
+
+    _argument_filter_sanity_check()
+    _argument_prepare_check()
+
+
+def time_uniter(unit):
+    picker = {
+        "s": 1,
+        "ms": 1e3,
+        "us": 1e6,
+        "ns": 1e9,
+    }
+    return picker[unit]
+
+
+def _init_db():
+    global db
+    db = dict()
+    db["running"] = dict()
+    db["cpu"] = dict()
+    db["tid"] = dict()
+    db["global"] = []
+    if args.summary or args.summary_extended or args.summary_only:
+        db["task_info"] = dict()
+        db["runtime_info"] = dict()
+        # min values for summary depending on the header
+        db["task_info"]["pid"] = len("PID")
+        db["task_info"]["tid"] = len("TID")
+        db["task_info"]["comm"] = len("Comm")
+        db["runtime_info"]["runs"] = len("Runs")
+        db["runtime_info"]["acc"] = len("Accumulated")
+        db["runtime_info"]["max"] = len("Max")
+        db["runtime_info"]["max_at"] = len("Max At")
+        db["runtime_info"]["min"] = len("Min")
+        db["runtime_info"]["mean"] = len("Mean")
+        db["runtime_info"]["median"] = len("Median")
+        if args.summary_extended:
+            db["inter_times"] = dict()
+            db["inter_times"]["out_in"] = len("Out-In")
+            db["inter_times"]["inter_at"] = len("At")
+            db["inter_times"]["out_out"] = len("Out-Out")
+            db["inter_times"]["in_in"] = len("In-In")
+            db["inter_times"]["in_out"] = len("In-Out")
+
+
+def _median(numbers):
+    """phython3 hat statistics module - we have nothing"""
+    n = len(numbers)
+    index = n // 2
+    if n % 2:
+        return sorted(numbers)[index]
+    return sum(sorted(numbers)[index - 1 : index + 1]) / 2
+
+
+def _mean(numbers):
+    return sum(numbers) / len(numbers)
+
+
+class Timespans(object):
+    """
+    The elapsed time between two occurrences of the same task is being tracked with the
+    help of this class. There are 4 of those Timespans Out-Out, In-Out, Out-In and
+    In-In.
+    The first half of the name signals the first time point of the
+    first task. The second half of the name represents the second
+    timepoint of the second task.
+    """
+
+    def __init__(self):
+        self._last_start = None
+        self._last_finish = None
+        self.out_out = -1
+        self.in_out = -1
+        self.out_in = -1
+        self.in_in = -1
+        if args.summary_extended:
+            self._time_in = -1
+            self.max_out_in = -1
+            self.max_at = -1
+            self.max_in_out = -1
+            self.max_in_in = -1
+            self.max_out_out = -1
+
+    def feed(self, task):
+        """
+        Called for every recorded trace event to find process pair and calculate the
+        task timespans. Chronological ordering, feed does not do reordering
+        """
+        if not self._last_finish:
+            self._last_start = task.time_in(time_unit)
+            self._last_finish = task.time_out(time_unit)
+            return
+        self._time_in = task.time_in()
+        time_in = task.time_in(time_unit)
+        time_out = task.time_out(time_unit)
+        self.in_in = time_in - self._last_start
+        self.out_in = time_in - self._last_finish
+        self.in_out = time_out - self._last_start
+        self.out_out = time_out - self._last_finish
+        if args.summary_extended:
+            self._update_max_entries()
+        self._last_finish = task.time_out(time_unit)
+        self._last_start = task.time_in(time_unit)
+
+    def _update_max_entries(self):
+        if self.in_in > self.max_in_in:
+            self.max_in_in = self.in_in
+        if self.out_out > self.max_out_out:
+            self.max_out_out = self.out_out
+        if self.in_out > self.max_in_out:
+            self.max_in_out = self.in_out
+        if self.out_in > self.max_out_in:
+            self.max_out_in = self.out_in
+            self.max_at = self._time_in
+
+
+
+class Summary(object):
+    """
+    Primary instance for calculating the summary output. Processes the whole trace to
+    find and memorize relevant data such as mean, max et cetera. This instance handles
+    dynamic alignment aspects for summary output.
+    """
+
+    def __init__(self):
+        self._body = []
+
+    class AlignmentHelper:
+        """
+        Used to calculated the alignment for the output of the summary.
+        """
+        def __init__(self, pid, tid, comm, runs, acc, mean,
+                    median, min, max, max_at):
+            self.pid = pid
+            self.tid = tid
+            self.comm = comm
+            self.runs = runs
+            self.acc = acc
+            self.mean = mean
+            self.median = median
+            self.min = min
+            self.max = max
+            self.max_at = max_at
+            if args.summary_extended:
+                self.out_in = None
+                self.inter_at = None
+                self.out_out = None
+                self.in_in = None
+                self.in_out = None
+
+    def _print_header(self):
+        '''
+        Output is trimmed in _format_stats thus additional adjustment in the header
+        is needed, depending on the choice of timeunit. The adjustment corresponds
+        to the amount of column titles being adjusted in _column_titles.
+        '''
+        decimal_precision = 6 if not args.ns else 9
+        fmt = " {{:^{}}}".format(sum(db["task_info"].values()))
+        fmt += " {{:^{}}}".format(
+            sum(db["runtime_info"].values()) - 2 * decimal_precision
+            )
+        _header = ("Task Information", "Runtime Information")
+
+        if args.summary_extended:
+            fmt += " {{:^{}}}".format(
+                sum(db["inter_times"].values()) - 4 * decimal_precision
+                )
+            _header += ("Max Inter Task Times",)
+        fd_sum.write(fmt.format(*_header) +  "\n")
+
+    def _column_titles(self):
+        """
+        Cells are being processed and displayed in different way so an alignment adjust
+        is implemented depeding on the choice of the timeunit. The positions of the max
+        values are being displayed in grey. Thus in their format two additional {},
+        are placed for color set and reset.
+        """
+        separator, fix_csv_align = _prepare_fmt_sep()
+        decimal_precision, time_precision = _prepare_fmt_precision()
+        fmt = "{{:>{}}}".format(db["task_info"]["pid"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, db["task_info"]["tid"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, db["task_info"]["comm"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, db["runtime_info"]["runs"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, db["runtime_info"]["acc"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, db["runtime_info"]["mean"] * fix_csv_align)
+        fmt += "{}{{:>{}}}".format(
+            separator, db["runtime_info"]["median"] * fix_csv_align
+        )
+        fmt += "{}{{:>{}}}".format(
+            separator, (db["runtime_info"]["min"] - decimal_precision) * fix_csv_align
+        )
+        fmt += "{}{{:>{}}}".format(
+            separator, (db["runtime_info"]["max"] - decimal_precision) * fix_csv_align
+        )
+        fmt += "{}{{}}{{:>{}}}{{}}".format(
+            separator, (db["runtime_info"]["max_at"] - time_precision) * fix_csv_align
+        )
+
+        column_titles = ("PID", "TID", "Comm")
+        column_titles += ("Runs", "Accumulated", "Mean", "Median", "Min", "Max")
+        column_titles += (_COLORS["grey"], "Max At", _COLORS["reset"])
+
+        if args.summary_extended:
+            fmt += "{}{{:>{}}}".format(
+                separator,
+                (db["inter_times"]["out_in"] - decimal_precision) * fix_csv_align
+            )
+            fmt += "{}{{}}{{:>{}}}{{}}".format(
+                separator,
+                (db["inter_times"]["inter_at"] - time_precision) * fix_csv_align
+            )
+            fmt += "{}{{:>{}}}".format(
+                separator,
+                (db["inter_times"]["out_out"] - decimal_precision) * fix_csv_align
+            )
+            fmt += "{}{{:>{}}}".format(
+                separator,
+                (db["inter_times"]["in_in"] - decimal_precision) * fix_csv_align
+            )
+            fmt += "{}{{:>{}}}".format(
+                separator,
+                (db["inter_times"]["in_out"] - decimal_precision) * fix_csv_align
+            )
+
+            column_titles += ("Out-In", _COLORS["grey"], "Max At", _COLORS["reset"],
+                        "Out-Out", "In-In", "In-Out")
+
+        fd_sum.write(fmt.format(*column_titles) + "\n")
+
+
+    def _task_stats(self):
+        """calculates the stats of every task and constructs the printable summary"""
+        for tid in sorted(db["tid"]):
+            color_one_sample = _COLORS["grey"]
+            color_reset = _COLORS["reset"]
+            no_executed = 0
+            runtimes = []
+            time_in = []
+            timespans = Timespans()
+            for task in db["tid"][tid]:
+                pid = task.pid
+                comm = task.comm
+                no_executed += 1
+                runtimes.append(task.runtime(time_unit))
+                time_in.append(task.time_in())
+                timespans.feed(task)
+            if len(runtimes) > 1:
+                color_one_sample = ""
+                color_reset = ""
+            time_max = max(runtimes)
+            time_min = min(runtimes)
+            max_at = time_in[runtimes.index(max(runtimes))]
+
+            # The size of the decimal after sum,mean and median varies, thus we cut
+            # the decimal number, by rounding it. It has no impact on the output,
+            # because we have a precision of the decimal points at the output.
+            time_sum = round(sum(runtimes), 3)
+            time_mean = round(_mean(runtimes), 3)
+            time_median = round(_median(runtimes), 3)
+
+            align_helper = self.AlignmentHelper(pid, tid, comm, no_executed, time_sum,
+                                    time_mean, time_median, time_min, time_max, max_at)
+            self._body.append([pid, tid, comm, no_executed, time_sum, color_one_sample,
+                                time_mean, time_median, time_min, time_max,
+                                _COLORS["grey"], max_at, _COLORS["reset"], color_reset])
+            if args.summary_extended:
+                self._body[-1].extend([timespans.max_out_in,
+                                _COLORS["grey"], timespans.max_at,
+                                _COLORS["reset"], timespans.max_out_out,
+                                timespans.max_in_in,
+                                timespans.max_in_out])
+                align_helper.out_in = timespans.max_out_in
+                align_helper.inter_at = timespans.max_at
+                align_helper.out_out = timespans.max_out_out
+                align_helper.in_in = timespans.max_in_in
+                align_helper.in_out = timespans.max_in_out
+            self._calc_alignments_summary(align_helper)
+
+    def _format_stats(self):
+        separator, fix_csv_align = _prepare_fmt_sep()
+        decimal_precision, time_precision = _prepare_fmt_precision()
+        len_pid = db["task_info"]["pid"] * fix_csv_align
+        len_tid = db["task_info"]["tid"] * fix_csv_align
+        len_comm = db["task_info"]["comm"] * fix_csv_align
+        len_runs = db["runtime_info"]["runs"] * fix_csv_align
+        len_acc = db["runtime_info"]["acc"] * fix_csv_align
+        len_mean = db["runtime_info"]["mean"] * fix_csv_align
+        len_median = db["runtime_info"]["median"] * fix_csv_align
+        len_min = (db["runtime_info"]["min"] - decimal_precision) * fix_csv_align
+        len_max = (db["runtime_info"]["max"] - decimal_precision) * fix_csv_align
+        len_max_at = (db["runtime_info"]["max_at"] - time_precision) * fix_csv_align
+        if args.summary_extended:
+            len_out_in = (
+                db["inter_times"]["out_in"] - decimal_precision
+            ) * fix_csv_align
+            len_inter_at = (
+                db["inter_times"]["inter_at"] - time_precision
+            ) * fix_csv_align
+            len_out_out = (
+                db["inter_times"]["out_out"] - decimal_precision
+            ) * fix_csv_align
+            len_in_in = (db["inter_times"]["in_in"] - decimal_precision) * fix_csv_align
+            len_in_out = (
+                db["inter_times"]["in_out"] - decimal_precision
+            ) * fix_csv_align
+
+        fmt = "{{:{}d}}".format(len_pid)
+        fmt += "{}{{:{}d}}".format(separator, len_tid)
+        fmt += "{}{{:>{}}}".format(separator, len_comm)
+        fmt += "{}{{:{}d}}".format(separator, len_runs)
+        fmt += "{}{{:{}.{}f}}".format(separator, len_acc, time_precision)
+        fmt += "{}{{}}{{:{}.{}f}}".format(separator, len_mean, time_precision)
+        fmt += "{}{{:{}.{}f}}".format(separator, len_median, time_precision)
+        fmt += "{}{{:{}.{}f}}".format(separator, len_min, time_precision)
+        fmt += "{}{{:{}.{}f}}".format(separator, len_max, time_precision)
+        fmt += "{}{{}}{{:{}.{}f}}{{}}{{}}".format(
+            separator, len_max_at, decimal_precision
+        )
+        if args.summary_extended:
+            fmt += "{}{{:{}.{}f}}".format(separator, len_out_in, time_precision)
+            fmt += "{}{{}}{{:{}.{}f}}{{}}".format(
+                separator, len_inter_at, decimal_precision
+            )
+            fmt += "{}{{:{}.{}f}}".format(separator, len_out_out, time_precision)
+            fmt += "{}{{:{}.{}f}}".format(separator, len_in_in, time_precision)
+            fmt += "{}{{:{}.{}f}}".format(separator, len_in_out, time_precision)
+        return fmt
+
+
+    def _calc_alignments_summary(self, align_helper):
+        # Length is being cut in 3 groups so that further addition is easier to handle.
+        # The length of every argument from the alignment helper is being checked if it
+        # is longer than the longest until now. In that case the length is being saved.
+        for key in db["task_info"]:
+            if len(str(getattr(align_helper, key))) > db["task_info"][key]:
+                db["task_info"][key] = len(str(getattr(align_helper, key)))
+        for key in db["runtime_info"]:
+            if len(str(getattr(align_helper, key))) > db["runtime_info"][key]:
+                db["runtime_info"][key] = len(str(getattr(align_helper, key)))
+        if args.summary_extended:
+            for key in db["inter_times"]:
+                if len(str(getattr(align_helper, key))) > db["inter_times"][key]:
+                    db["inter_times"][key] = len(str(getattr(align_helper, key)))
+
+
+    def print(self):
+        self._task_stats()
+        fmt = self._format_stats()
+
+        if not args.csv_summary:
+            print("\nSummary")
+            self._print_header()
+        self._column_titles()
+        for i in range(len(self._body)):
+            fd_sum.write(fmt.format(*tuple(self._body[i])) + "\n")
+
+
+
+class Task(object):
+    """ The class is used to handle the information of a given task."""
+
+    def __init__(self, id, tid, cpu, comm):
+        self.id = id
+        self.tid = tid
+        self.cpu = cpu
+        self.comm = comm
+        self.pid = None
+        self._time_in = None
+        self._time_out = None
+
+    def schedule_in_at(self, time):
+        """set the time where the task was scheduled in"""
+        self._time_in = time
+
+    def schedule_out_at(self, time):
+        """set the time where the task was scheduled out"""
+        self._time_out = time
+
+    def time_out(self, unit="s"):
+        """return time where a given task was scheduled out"""
+        factor = time_uniter(unit)
+        return self._time_out * decimal.Decimal(factor)
+
+    def time_in(self, unit="s"):
+        """return time where a given task was scheduled in"""
+        factor = time_uniter(unit)
+        return self._time_in * decimal.Decimal(factor)
+
+    def runtime(self, unit="us"):
+        factor = time_uniter(unit)
+        return (self._time_out - self._time_in) * decimal.Decimal(factor)
+
+    def update_pid(self, pid):
+        self.pid = pid
+
+
+def _task_id(pid, cpu):
+    """returns a "unique-enough" identifier, please do not change"""
+    return "{}-{}".format(pid, cpu)
+
+
+def _filter_non_printable(unfiltered):
+    """comm names may contain loony chars like '\x00000'"""
+    filtered = ""
+    for char in unfiltered:
+        if char not in string.printable:
+            continue
+        filtered += char
+    return filtered
+
+
+def _fmt_header():
+    separator, fix_csv_align = _prepare_fmt_sep()
+    fmt = "{{:>{}}}".format(LEN_SWITCHED_IN*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_SWITCHED_OUT*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_CPU*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_PID*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_TID*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_COMM*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_RUNTIME*fix_csv_align)
+    fmt += "{}{{:>{}}}".format(separator, LEN_OUT_IN*fix_csv_align)
+    if args.extended_times:
+        fmt += "{}{{:>{}}}".format(separator, LEN_OUT_OUT*fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, LEN_IN_IN*fix_csv_align)
+        fmt += "{}{{:>{}}}".format(separator, LEN_IN_OUT*fix_csv_align)
+    return fmt
+
+
+def _fmt_body():
+    separator, fix_csv_align = _prepare_fmt_sep()
+    decimal_precision, time_precision = _prepare_fmt_precision()
+    fmt = "{{}}{{:{}.{}f}}".format(LEN_SWITCHED_IN*fix_csv_align, decimal_precision)
+    fmt += "{}{{:{}.{}f}}".format(
+        separator, LEN_SWITCHED_OUT*fix_csv_align, decimal_precision
+    )
+    fmt += "{}{{:{}d}}".format(separator, LEN_CPU*fix_csv_align)
+    fmt += "{}{{:{}d}}".format(separator, LEN_PID*fix_csv_align)
+    fmt += "{}{{}}{{:{}d}}{{}}".format(separator, LEN_TID*fix_csv_align)
+    fmt += "{}{{}}{{:>{}}}".format(separator, LEN_COMM*fix_csv_align)
+    fmt += "{}{{:{}.{}f}}".format(separator, LEN_RUNTIME*fix_csv_align, time_precision)
+    if args.extended_times:
+        fmt += "{}{{:{}.{}f}}".format(separator, LEN_OUT_IN*fix_csv_align, time_precision)
+        fmt += "{}{{:{}.{}f}}".format(separator, LEN_OUT_OUT*fix_csv_align, time_precision)
+        fmt += "{}{{:{}.{}f}}".format(separator, LEN_IN_IN*fix_csv_align, time_precision)
+        fmt += "{}{{:{}.{}f}}{{}}".format(
+            separator, LEN_IN_OUT*fix_csv_align, time_precision
+        )
+    else:
+        fmt += "{}{{:{}.{}f}}{{}}".format(
+            separator, LEN_OUT_IN*fix_csv_align, time_precision
+        )
+    return fmt
+
+
+def _print_header():
+    fmt = _fmt_header()
+    header = ("Switched-In", "Switched-Out", "CPU", "PID", "TID", "Comm", "Runtime",
+            "Time Out-In")
+    if args.extended_times:
+        header += ("Time Out-Out", "Time In-In", "Time In-Out")
+    fd_task.write(fmt.format(*header) + "\n")
+
+
+
+def _print_task_finish(task):
+    """calculating every entry of a row and printing it immediately"""
+    c_row_set = ""
+    c_row_reset = ""
+    out_in = -1
+    out_out = -1
+    in_in = -1
+    in_out = -1
+    fmt = _fmt_body()
+    # depending on user provided highlight option we change the color
+    # for particular tasks
+    if str(task.tid) in args.highlight_tasks_map:
+        c_row_set = _COLORS[args.highlight_tasks_map[str(task.tid)]]
+        c_row_reset = _COLORS["reset"]
+    if task.comm in args.highlight_tasks_map:
+        c_row_set = _COLORS[args.highlight_tasks_map[task.comm]]
+        c_row_reset = _COLORS["reset"]
+    # grey-out entries if PID == TID, they
+    # are identical, no threaded model so the
+    # thread id (tid) do not matter
+    c_tid_set = ""
+    c_tid_reset = ""
+    if task.pid == task.tid:
+        c_tid_set = _COLORS["grey"]
+        c_tid_reset = _COLORS["reset"]
+    if task.tid in db["tid"]:
+        # get last task of tid
+        last_tid_task = db["tid"][task.tid][-1]
+        # feed the timespan calculate, last in tid db
+        # and second the current one
+        timespan_gap_tid = Timespans()
+        timespan_gap_tid.feed(last_tid_task)
+        timespan_gap_tid.feed(task)
+        out_in = timespan_gap_tid.out_in
+        out_out = timespan_gap_tid.out_out
+        in_in = timespan_gap_tid.in_in
+        in_out = timespan_gap_tid.in_out
+
+
+    if args.extended_times:
+        line_out = fmt.format(c_row_set, task.time_in(), task.time_out(), task.cpu,
+                        task.pid, c_tid_set, task.tid, c_tid_reset, c_row_set, task.comm,
+                        task.runtime(time_unit), out_in, out_out, in_in, in_out,
+                        c_row_reset) + "\n"
+    else:
+        line_out = fmt.format(c_row_set, task.time_in(), task.time_out(), task.cpu,
+                        task.pid, c_tid_set, task.tid, c_tid_reset, c_row_set, task.comm,
+                        task.runtime(time_unit), out_in, c_row_reset) + "\n"
+    try:
+        fd_task.write(line_out)
+    except(IOError):
+        # don't mangle the output if user SIGINT this script
+        sys.exit()
+
+def _record_cleanup(_list):
+    """
+    no need to store more then one element if --summarize
+    is not enabled
+    """
+    if not args.summary and len(_list) > 1:
+        _list = _list[len(_list) - 1 :]
+
+
+def _record_by_tid(task):
+    tid = task.tid
+    if tid not in db["tid"]:
+        db["tid"][tid] = []
+    db["tid"][tid].append(task)
+    _record_cleanup(db["tid"][tid])
+
+
+def _record_by_cpu(task):
+    cpu = task.cpu
+    if cpu not in db["cpu"]:
+        db["cpu"][cpu] = []
+    db["cpu"][cpu].append(task)
+    _record_cleanup(db["cpu"][cpu])
+
+
+def _record_global(task):
+    """record all executed task, ordered by finish chronological"""
+    db["global"].append(task)
+    _record_cleanup(db["global"])
+
+
+def _handle_task_finish(tid, cpu, time, perf_sample_dict):
+    if tid == 0:
+        return
+    _id = _task_id(tid, cpu)
+    if _id not in db["running"]:
+        # may happen, if we missed the switch to
+        # event. Seen in combination with --exclude-perf
+        # where the start is filtered out, but not the
+        # switched in. Probably a bug in exclude-perf
+        # option.
+        return
+    task = db["running"][_id]
+    task.schedule_out_at(time)
+
+    # record tid, during schedule in the tid
+    # is not available, update now
+    pid = int(perf_sample_dict["sample"]["pid"])
+
+    task.update_pid(pid)
+    del db["running"][_id]
+
+    # print only tasks which are not being filtered and no print of trace
+    # for summary only, but record every task.
+    if not _limit_filtered(tid, pid, task.comm) and not args.summary_only:
+        _print_task_finish(task)
+    _record_by_tid(task)
+    _record_by_cpu(task)
+    _record_global(task)
+
+
+def _handle_task_start(tid, cpu, comm, time):
+    if tid == 0:
+        return
+    if tid in args.tid_renames:
+        comm = args.tid_renames[tid]
+    _id = _task_id(tid, cpu)
+    if _id in db["running"]:
+        # handle corner cases where already running tasks
+        # are switched-to again - saw this via --exclude-perf
+        # recorded traces. We simple ignore this "second start"
+        # event.
+        return
+    assert _id not in db["running"]
+    task = Task(_id, tid, cpu, comm)
+    task.schedule_in_at(time)
+    db["running"][_id] = task
+
+
+def _time_to_internal(time_ns):
+    """
+    To prevent float rounding errors we use Decimal internally
+    """
+    return decimal.Decimal(time_ns) / decimal.Decimal(1e9)
+
+
+def _limit_filtered(tid, pid, comm):
+    if args.filter_tasks:
+        if str(tid) in args.filter_tasks or comm in args.filter_tasks:
+            return True
+        else:
+            return False
+    if args.limit_to_tasks:
+        if str(tid) in args.limit_to_tasks or comm in args.limit_to_tasks:
+            return False
+        else:
+            return True
+
+
+def _argument_filter_sanity_check():
+    if args.limit_to_tasks and args.filter_tasks:
+        sys.exit("Error: Filter and Limit at the same time active.")
+    if args.extended_times and args.summary_only:
+        sys.exit("Error: Summary only and extended times active.")
+    if args.time_limit and ":" not in args.time_limit:
+        sys.exit(
+            "Error: No bound set for time limit. Please set bound by ':' e.g :123."
+        )
+    if args.time_limit and (args.summary or args.summary_only or args.summary_extended):
+        sys.exit("Error: Cannot set time limit and print summary")
+    if args.csv_summary:
+        args.summary = True
+        if args.csv == args.csv_summary:
+            sys.exit("Error: Chosen files for csv and csv summary are the same")
+    if args.csv and (args.summary_extended or args.summary) and not args.csv_summary:
+        sys.exit("Error: No file chosen to write summary to. Choose with --csv-summary "
+        "<file>")
+    if args.csv and args.summary_only:
+        sys.exit("Error: --csv chosen and --summary-only. Standard task would not be"
+            "written to csv file.")
+
+def _argument_prepare_check():
+    global time_unit, fd_task, fd_sum
+    if args.filter_tasks:
+        args.filter_tasks = args.filter_tasks.split(",")
+    if args.limit_to_tasks:
+        args.limit_to_tasks = args.limit_to_tasks.split(",")
+    if args.time_limit:
+        args.time_limit = args.time_limit.split(":")
+    for rename_tuple in args.rename_comms_by_tids.split(","):
+        tid_name = rename_tuple.split(":")
+        if len(tid_name) != 2:
+            continue
+        args.tid_renames[int(tid_name[0])] = tid_name[1]
+    args.highlight_tasks_map = dict()
+    for highlight_tasks_tuple in args.highlight_tasks.split(","):
+        tasks_color_map = highlight_tasks_tuple.split(":")
+        # default highlight color to red if no color set by user
+        if len(tasks_color_map) == 1:
+            tasks_color_map.append("red")
+        if args.highlight_tasks and tasks_color_map[1].lower() not in _COLORS:
+            sys.exit(
+                "Error: Color not defined, please choose from grey,red,green,yellow,blue,"
+                "violet"
+            )
+        if len(tasks_color_map) != 2:
+            continue
+        args.highlight_tasks_map[tasks_color_map[0]] = tasks_color_map[1]
+    time_unit = "us"
+    if args.ns:
+        time_unit = "ns"
+    elif args.ms:
+        time_unit = "ms"
+
+
+    fd_task = sys.stdout
+    if args.csv:
+        args.stdio_color = "never"
+        fd_task = open(args.csv, "w")
+        print("generating csv at",args.csv,)
+
+    fd_sum = sys.stdout
+    if args.csv_summary:
+        args.stdio_color = "never"
+        fd_sum = open(args.csv_summary, "w")
+        print("generating csv summary at",args.csv_summary)
+        if not args.csv:
+            args.summary_only = True
+
+
+def _is_within_timelimit(time):
+    """
+    Check if a time limit was given by parameter, if so ignore the rest. If not,
+    process the recorded trace in its entirety.
+    """
+    if not args.time_limit:
+        return True
+    lower_time_limit = args.time_limit[0]
+    upper_time_limit = args.time_limit[1]
+    # check for upper limit
+    if upper_time_limit == "":
+        if time >= decimal.Decimal(lower_time_limit):
+            return True
+    # check for lower limit
+    if lower_time_limit == "":
+        if time <= decimal.Decimal(upper_time_limit):
+            return True
+        # quit if time exceeds upper limit. Good for big datasets
+        else:
+            quit()
+    if lower_time_limit != "" and upper_time_limit != "":
+        if (time >= decimal.Decimal(lower_time_limit) and
+            time <= decimal.Decimal(upper_time_limit)):
+            return True
+        # quit if time exceeds upper limit. Good for big datasets
+        elif time > decimal.Decimal(upper_time_limit):
+            quit()
+
+def _prepare_fmt_precision():
+    decimal_precision = 6
+    time_precision = 3
+    if args.ns:
+     decimal_precision = 9
+     time_precision = 0
+    return decimal_precision, time_precision
+
+def _prepare_fmt_sep():
+    separator = " "
+    fix_csv_align = 1
+    if args.csv or args.csv_summary:
+        separator = ";"
+        fix_csv_align = 0
+    return separator, fix_csv_align
+
+def trace_unhandled(event_name, context, event_fields_dict, perf_sample_dict):
+    pass
+
+
+def trace_begin():
+    _parse_args()
+    _check_color()
+    _init_db()
+    if not args.summary_only:
+        _print_header()
+
+def trace_end():
+    if args.summary or args.summary_extended or args.summary_only:
+        Summary().print()
+
+def sched__sched_switch(event_name, context, common_cpu, common_secs, common_nsecs,
+                        common_pid, common_comm, common_callchain, prev_comm,
+                        prev_pid, prev_prio, prev_state, next_comm, next_pid,
+                        next_prio, perf_sample_dict):
+    # ignore common_secs & common_nsecs cause we need
+    # high res timestamp anyway, using the raw value is
+    # faster
+    time = _time_to_internal(perf_sample_dict["sample"]["time"])
+    if not _is_within_timelimit(time):
+        # user specific --time-limit a:b set
+        return
+
+    next_comm = _filter_non_printable(next_comm)
+    _handle_task_finish(prev_pid, common_cpu, time, perf_sample_dict)
+    _handle_task_start(next_pid, common_cpu, next_comm, time)