[thirdparty/kernel/linux.git] / scripts / leaking_addresses.pl

#!/usr/bin/env perl
# SPDX-License-Identifier: GPL-2.0-only
#
# (c) 2017 Tobin C. Harding <me@tobin.cc>
#
# leaking_addresses.pl: Scan the kernel for potential leaking addresses.
#  - Scans dmesg output.
#  - Walks directory tree and parses each file (for each directory in @DIRS).
#
# Use --debug to output path before parsing, this is useful to find files that
# cause the script to choke.

#
# When the system is idle it is likely that most files under /proc/PID will be
# identical for various processes.  Scanning _all_ the PIDs under /proc is
# unnecessary and implies that we are thoroughly scanning /proc.  This is _not_
# the case because there may be ways userspace can trigger creation of /proc
# files that leak addresses but were not present during a scan.  For these two
# reasons we exclude all PID directories under /proc except '1/'

use warnings;
use strict;
use POSIX;
use File::Basename;
use File::Spec;
use File::Temp qw/tempfile/;
use Cwd 'abs_path';
use Term::ANSIColor qw(:constants);
use Getopt::Long qw(:config no_auto_abbrev);
use Config;
use bigint qw/hex/;
use feature 'state';

my $P = $0;

# Directories to scan.
my @DIRS = ('/proc', '/sys');

# Timer for parsing each file, in seconds.
my $TIMEOUT = 10;

# Kernel addresses vary by architecture.  We can only auto-detect the following
# architectures (using `uname -m`).  (flag --32-bit overrides auto-detection.)
my @SUPPORTED_ARCHITECTURES = ('x86_64', 'ppc64', 'x86');

# Command line options.
my $help = 0;
my $debug = 0;
my $raw = 0;
my $output_raw = "";	# Write raw results to file.
my $input_raw = "";	# Read raw results from file instead of scanning.
my $suppress_dmesg = 0;		# Don't show dmesg in output.
my $squash_by_path = 0;		# Summary report grouped by absolute path.
my $squash_by_filename = 0;	# Summary report grouped by filename.
my $kallsyms_file = "";		# Kernel symbols file.
my $kernel_config_file = "";	# Kernel configuration file.
my $opt_32bit = 0;		# Scan 32-bit kernel.
my $page_offset_32bit = 0;	# Page offset for 32-bit kernel.

my @kallsyms = ();

# Skip these absolute paths.
my @skip_abs = (
	'/proc/kmsg',
	'/proc/device-tree',
	'/proc/1/syscall',
	'/sys/firmware/devicetree',
	'/sys/kernel/tracing/trace_pipe',
	'/sys/kernel/debug/tracing/trace_pipe',
	'/sys/kernel/security/apparmor/revision');

# Skip these under any subdirectory.
my @skip_any = (
	'pagemap',
	'events',
	'access',
	'registers',
	'snapshot_raw',
	'trace_pipe_raw',
	'ptmx',
	'trace_pipe',
	'fd',
	'usbmon');

sub help
{
	my ($exitcode) = @_;

	print << "EOM";

Usage: $P [OPTIONS]

Options:

	-o, --output-raw=<file>		Save results for future processing.
	-i, --input-raw=<file>		Read results from file instead of scanning.
	      --raw			Show raw results (default).
	      --suppress-dmesg		Do not show dmesg results.
	      --squash-by-path		Show one result per unique path.
	      --squash-by-filename	Show one result per unique filename.
	--kernel-config-file=<file>     Kernel configuration file (e.g /boot/config)
	--kallsyms=<file>		Read kernel symbol addresses from file (for
						scanning binary files).
	--32-bit			Scan 32-bit kernel.
	--page-offset-32-bit=o		Page offset (for 32-bit kernel 0xABCD1234).
	-d, --debug			Display debugging output.
	-h, --help			Display this help and exit.

Scans the running kernel for potential leaking addresses.

EOM
	exit($exitcode);
}

GetOptions(
	'd|debug'		=> \$debug,
	'h|help'		=> \$help,
	'o|output-raw=s'        => \$output_raw,
	'i|input-raw=s'         => \$input_raw,
	'suppress-dmesg'        => \$suppress_dmesg,
	'squash-by-path'        => \$squash_by_path,
	'squash-by-filename'    => \$squash_by_filename,
	'raw'                   => \$raw,
	'kallsyms=s'            => \$kallsyms_file,
	'kernel-config-file=s'	=> \$kernel_config_file,
	'32-bit'		=> \$opt_32bit,
	'page-offset-32-bit=o'	=> \$page_offset_32bit,
) or help(1);

help(0) if ($help);

if ($input_raw) {
	format_output($input_raw);
	exit(0);
}

if (!$input_raw and ($squash_by_path or $squash_by_filename)) {
	printf "\nSummary reporting only available with --input-raw=<file>\n";
	printf "(First run scan with --output-raw=<file>.)\n";
	exit(128);
}

if (!(is_supported_architecture() or $opt_32bit or $page_offset_32bit)) {
	printf "\nScript does not support your architecture, sorry.\n";
	printf "\nCurrently we support: \n\n";
	foreach(@SUPPORTED_ARCHITECTURES) {
		printf "\t%s\n", $_;
	}
	printf("\n");

	printf("If you are running a 32-bit architecture you may use:\n");
	printf("\n\t--32-bit or --page-offset-32-bit=<page offset>\n\n");

	my $archname = `uname -m`;
	printf("Machine hardware name (`uname -m`): %s\n", $archname);

	exit(129);
}

if ($output_raw) {
	open my $fh, '>', $output_raw or die "$0: $output_raw: $!\n";
	select $fh;
}

if ($kallsyms_file) {
	open my $fh, '<', $kallsyms_file or die "$0: $kallsyms_file: $!\n";
	while (<$fh>) {
		chomp;
		my @entry = split / /, $_;
		my $addr_text = $entry[0];
		if ($addr_text !~ /^0/) {
			# TODO: Why is hex() so impossibly slow?
			my $addr = hex($addr_text);
			my $symbol = $entry[2];
			# Only keep kernel text addresses.
			my $long = pack("J", $addr);
			my $entry = [$long, $symbol];
			push @kallsyms, $entry;
		}
	}
	close $fh;
}

parse_dmesg();
walk(@DIRS);

exit 0;

sub dprint
{
	printf(STDERR @_) if $debug;
}

sub is_supported_architecture
{
	return (is_x86_64() or is_ppc64() or is_ix86_32());
}

sub is_32bit
{
	# Allow --32-bit or --page-offset-32-bit to override
	if ($opt_32bit or $page_offset_32bit) {
		return 1;
	}

	return is_ix86_32();
}

sub is_ix86_32
{
       state $arch = `uname -m`;

       chomp $arch;
       if ($arch =~ m/i[3456]86/) {
               return 1;
       }
       return 0;
}

sub is_arch
{
       my ($desc) = @_;
       my $arch = `uname -m`;

       chomp $arch;
       if ($arch eq $desc) {
               return 1;
       }
       return 0;
}

sub is_x86_64
{
	state $is = is_arch('x86_64');
	return $is;
}

sub is_ppc64
{
	state $is = is_arch('ppc64');
	return $is;
}

# Gets config option value from kernel config file.
# Returns "" on error or if config option not found.
sub get_kernel_config_option
{
	my ($option) = @_;
	my $value = "";
	my $tmp_fh;
	my $tmp_file = "";
	my @config_files;

	# Allow --kernel-config-file to override.
	if ($kernel_config_file ne "") {
		@config_files = ($kernel_config_file);
	} elsif (-R "/proc/config.gz") {
		($tmp_fh, $tmp_file) = tempfile("config.gz-XXXXXX",
						UNLINK => 1);

		if (system("gunzip < /proc/config.gz > $tmp_file")) {
			dprint("system(gunzip < /proc/config.gz) failed\n");
			return "";
		} else {
			@config_files = ($tmp_file);
		}
	} else {
		my $file = '/boot/config-' . `uname -r`;
		chomp $file;
		@config_files = ($file, '/boot/config');
	}

	foreach my $file (@config_files) {
		dprint("parsing config file: $file\n");
		$value = option_from_file($option, $file);
		if ($value ne "") {
			last;
		}
	}

	return $value;
}

# Parses $file and returns kernel configuration option value.
sub option_from_file
{
	my ($option, $file) = @_;
	my $str = "";
	my $val = "";

	open(my $fh, "<", $file) or return "";
	while (my $line = <$fh> ) {
		if ($line =~ /^$option/) {
			($str, $val) = split /=/, $line;
			chomp $val;
			last;
		}
	}

	close $fh;
	return $val;
}

sub is_false_positive
{
	my ($match) = @_;

	if (is_32bit()) {
		return is_false_positive_32bit($match);
	}

	# Ignore 64 bit false positives:
	# 0xfffffffffffffff[0-f]
	# 0x0000000000000000
	if ($match =~ '\b(0x)?(f|F){15}[0-9a-f]\b' or
	    $match =~ '\b(0x)?0{16}\b') {
		return 1;
	}

	if (is_x86_64() and is_in_vsyscall_memory_region($match)) {
		return 1;
	}

	return 0;
}

sub is_false_positive_32bit
{
       my ($match) = @_;
       state $page_offset = get_page_offset();

       if ($match =~ '\b(0x)?(f|F){7}[0-9a-f]\b') {
               return 1;
       }

       if (hex($match) < $page_offset) {
               return 1;
       }

       return 0;
}

# returns integer value
sub get_page_offset
{
       my $page_offset;
       my $default_offset = 0xc0000000;

       # Allow --page-offset-32bit to override.
       if ($page_offset_32bit != 0) {
               return $page_offset_32bit;
       }

       $page_offset = get_kernel_config_option('CONFIG_PAGE_OFFSET');
       if (!$page_offset) {
	       return $default_offset;
       }
       return $page_offset;
}

sub is_in_vsyscall_memory_region
{
	my ($match) = @_;

	my $hex = hex($match);
	my $region_min = hex("0xffffffffff600000");
	my $region_max = hex("0xffffffffff601000");

	return ($hex >= $region_min and $hex <= $region_max);
}

# True if argument potentially contains a kernel address.
sub may_leak_address
{
	my ($path, $line) = @_;
	my $address_re;

	# Ignore Signal masks.
	if ($line =~ '^SigBlk:' or
	    $line =~ '^SigIgn:' or
	    $line =~ '^SigCgt:') {
		return 0;
	}

	# Ignore input device reporting.
	# /proc/bus/input/devices: B: KEY=402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	# /sys/devices/platform/i8042/serio0/input/input1/uevent: KEY=402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	# /sys/devices/platform/i8042/serio0/input/input1/capabilities/key: 402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	if ($line =~ '\bKEY=[[:xdigit:]]{9,14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b' or
            ($path =~ '\bkey$' and
             $line =~ '\b[[:xdigit:]]{9,14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b')) {
		return 0;
	}

	$address_re = get_address_re();
	while ($line =~ /($address_re)/g) {
		if (!is_false_positive($1)) {
			return 1;
		}
	}

	return 0;
}

sub get_address_re
{
	if (is_ppc64()) {
		return '\b(0x)?[89abcdef]00[[:xdigit:]]{13}\b';
	} elsif (is_32bit()) {
		return '\b(0x)?[[:xdigit:]]{8}\b';
	}

	return get_x86_64_re();
}

sub get_x86_64_re
{
	# We handle page table levels but only if explicitly configured using
	# CONFIG_PGTABLE_LEVELS.  If config file parsing fails or config option
	# is not found we default to using address regular expression suitable
	# for 4 page table levels.
	state $ptl = get_kernel_config_option('CONFIG_PGTABLE_LEVELS');

	if ($ptl == 5) {
		return '\b(0x)?ff[[:xdigit:]]{14}\b';
	}
	return '\b(0x)?ffff[[:xdigit:]]{12}\b';
}

sub parse_dmesg
{
	open my $cmd, '-|', 'dmesg';
	while (<$cmd>) {
		if (may_leak_address("dmesg", $_)) {
			print 'dmesg: ' . $_;
		}
	}
	close $cmd;
}

# True if we should skip this path.
sub skip
{
	my ($path) = @_;

	foreach (@skip_abs) {
		return 1 if (/^$path$/);
	}

	my($filename, $dirs, $suffix) = fileparse($path);
	foreach (@skip_any) {
		return 1 if (/^$filename$/);
	}

	return 0;
}

sub timed_parse_file
{
	my ($file) = @_;

	eval {
		local $SIG{ALRM} = sub { die "alarm\n" }; # NB: \n required.
		alarm $TIMEOUT;
		parse_file($file);
		alarm 0;
	};

	if ($@) {
		die unless $@ eq "alarm\n";	# Propagate unexpected errors.
		printf STDERR "timed out parsing: %s\n", $file;
	}
}

sub parse_binary
{
	my ($file) = @_;

	open my $fh, "<:raw", $file or return;
	local $/ = undef;
	my $bytes = <$fh>;
	close $fh;

	foreach my $entry (@kallsyms) {
		my $addr = $entry->[0];
		my $symbol = $entry->[1];
		my $offset = index($bytes, $addr);
		if ($offset != -1) {
			printf("$file: $symbol @ $offset\n");
		}
	}
}

sub parse_file
{
	my ($file) = @_;

	if (! -R $file) {
		return;
	}

	if (! -T $file) {
		if ($file =~ m|^/sys/kernel/btf/| or
		    $file =~ m|^/sys/devices/pci| or
		    $file =~ m|^/sys/firmware/efi/efivars/| or
		    $file =~ m|^/proc/bus/pci/|) {
			return;
		}
		if (scalar @kallsyms > 0) {
			parse_binary($file);
		}
		return;
	}

	open my $fh, "<", $file or return;
	while ( <$fh> ) {
		chomp;
		if (may_leak_address($file, $_)) {
			printf("$file: $_\n");
		}
	}
	close $fh;
}

# Checks if the actual path name is leaking a kernel address.
sub check_path_for_leaks
{
	my ($path) = @_;

	if (may_leak_address($path, $path)) {
		printf("Path name may contain address: $path\n");
	}
}

# Recursively walk directory tree.
sub walk
{
	my @dirs = @_;

	while (my $pwd = shift @dirs) {
		next if (!opendir(DIR, $pwd));
		my @files = readdir(DIR);
		closedir(DIR);

		foreach my $file (@files) {
			next if ($file eq '.' or $file eq '..');

			my $path = "$pwd/$file";
			next if (-l $path);

			# skip /proc/PID except /proc/1
			next if (($path =~ /^\/proc\/[0-9]+$/) &&
				 ($path !~ /^\/proc\/1$/));

			next if (skip($path));

			check_path_for_leaks($path);

			if (-d $path) {
				push @dirs, $path;
				next;
			}

			dprint("parsing: $path\n");
			timed_parse_file($path);
		}
	}
}

sub format_output
{
	my ($file) = @_;

	# Default is to show raw results.
	if ($raw or (!$squash_by_path and !$squash_by_filename)) {
		dump_raw_output($file);
		return;
	}

	my ($total, $dmesg, $paths, $files) = parse_raw_file($file);

	printf "\nTotal number of results from scan (incl dmesg): %d\n", $total;

	if (!$suppress_dmesg) {
		print_dmesg($dmesg);
	}

	if ($squash_by_filename) {
		squash_by($files, 'filename');
	}

	if ($squash_by_path) {
		squash_by($paths, 'path');
	}
}

sub dump_raw_output
{
	my ($file) = @_;

	open (my $fh, '<', $file) or die "$0: $file: $!\n";
	while (<$fh>) {
		if ($suppress_dmesg) {
			if ("dmesg:" eq substr($_, 0, 6)) {
				next;
			}
		}
		print $_;
	}
	close $fh;
}

sub parse_raw_file
{
	my ($file) = @_;

	my $total = 0;          # Total number of lines parsed.
	my @dmesg;              # dmesg output.
	my %files;              # Unique filenames containing leaks.
	my %paths;              # Unique paths containing leaks.

	open (my $fh, '<', $file) or die "$0: $file: $!\n";
	while (my $line = <$fh>) {
		$total++;

		if ("dmesg:" eq substr($line, 0, 6)) {
			push @dmesg, $line;
			next;
		}

		cache_path(\%paths, $line);
		cache_filename(\%files, $line);
	}

	return $total, \@dmesg, \%paths, \%files;
}

sub print_dmesg
{
	my ($dmesg) = @_;

	print "\ndmesg output:\n";

	if (@$dmesg == 0) {
		print "<no results>\n";
		return;
	}

	foreach(@$dmesg) {
		my $index = index($_, ': ');
		$index += 2;    # skid ': '
		print substr($_, $index);
	}
}

sub squash_by
{
	my ($ref, $desc) = @_;

	print "\nResults squashed by $desc (excl dmesg). ";
	print "Displaying [<number of results> <$desc>], <example result>\n";

	if (keys %$ref == 0) {
		print "<no results>\n";
		return;
	}

	foreach(keys %$ref) {
		my $lines = $ref->{$_};
		my $length = @$lines;
		printf "[%d %s] %s", $length, $_, @$lines[0];
	}
}

sub cache_path
{
	my ($paths, $line) = @_;

	my $index = index($line, ': ');
	my $path = substr($line, 0, $index);

	$index += 2;            # skip ': '
	add_to_cache($paths, $path, substr($line, $index));
}

sub cache_filename
{
	my ($files, $line) = @_;

	my $index = index($line, ': ');
	my $path = substr($line, 0, $index);
	my $filename = basename($path);

	$index += 2;            # skip ': '
	add_to_cache($files, $filename, substr($line, $index));
}

sub add_to_cache
{
	my ($cache, $key, $value) = @_;

	if (!$cache->{$key}) {
		$cache->{$key} = ();
	}
	push @{$cache->{$key}}, $value;
}
Commit	Line	Data
136fc5c4	1	#!/usr/bin/env perl
4f19048f	2	# SPDX-License-Identifier: GPL-2.0-only
136fc5c4 TH	3	#
136fc5c4 TH	4	# (c) 2017 Tobin C. Harding <me@tobin.cc>
136fc5c4	5	#
1410fe4e	6	# leaking_addresses.pl: Scan the kernel for potential leaking addresses.
136fc5c4 TH	7	# - Scans dmesg output.
	8	# - Walks directory tree and parses each file (for each directory in @DIRS).
	9	#
136fc5c4 TH	10	# Use --debug to output path before parsing, this is useful to find files that
136fc5c4 TH	11	# cause the script to choke.
136fc5c4	12
472c9e10 TH	13	#
	14	# When the system is idle it is likely that most files under /proc/PID will be
	15	# identical for various processes. Scanning _all_ the PIDs under /proc is
	16	# unnecessary and implies that we are thoroughly scanning /proc. This is _not_
	17	# the case because there may be ways userspace can trigger creation of /proc
	18	# files that leak addresses but were not present during a scan. For these two
	19	# reasons we exclude all PID directories under /proc except '1/'
	20
136fc5c4 TH	21	use warnings;
	22	use strict;
	23	use POSIX;
	24	use File::Basename;
	25	use File::Spec;
1b1bcbf4	26	use File::Temp qw/tempfile/;
136fc5c4 TH	27	use Cwd 'abs_path';
	28	use Term::ANSIColor qw(:constants);
	29	use Getopt::Long qw(:config no_auto_abbrev);
62139c12	30	use Config;
87e37588	31	use bigint qw/hex/;
2f042c93	32	use feature 'state';
136fc5c4 TH	33
136fc5c4 TH	34	my $P = $0;
136fc5c4 TH	35
	36	# Directories to scan.
	37	my @DIRS = ('/proc', '/sys');
	38
dd98c252 TH	39	# Timer for parsing each file, in seconds.
	40	my $TIMEOUT = 10;
	41
1410fe4e TH	42	# Kernel addresses vary by architecture. We can only auto-detect the following
	43	# architectures (using `uname -m`). (flag --32-bit overrides auto-detection.)
	44	my @SUPPORTED_ARCHITECTURES = ('x86_64', 'ppc64', 'x86');
62139c12	45
136fc5c4 TH	46	# Command line options.
	47	my $help = 0;
	48	my $debug = 0;
d09bd8da TH	49	my $raw = 0;
	50	my $output_raw = ""; # Write raw results to file.
	51	my $input_raw = ""; # Read raw results from file instead of scanning.
d09bd8da TH	52	my $suppress_dmesg = 0; # Don't show dmesg in output.
	53	my $squash_by_path = 0; # Summary report grouped by absolute path.
	54	my $squash_by_filename = 0; # Summary report grouped by filename.
67bbd2f0	55	my $kallsyms_file = ""; # Kernel symbols file.
f9d2a42d	56	my $kernel_config_file = ""; # Kernel configuration file.
1410fe4e TH	57	my $opt_32bit = 0; # Scan 32-bit kernel.
1410fe4e TH	58	my $page_offset_32bit = 0; # Page offset for 32-bit kernel.
136fc5c4	59
67bbd2f0 KC	60	my @kallsyms = ();
67bbd2f0 KC	61
b401f56f TH	62	# Skip these absolute paths.
	63	my @skip_abs = (
	64	'/proc/kmsg',
	65	'/proc/device-tree',
2ad74293	66	'/proc/1/syscall',
b401f56f	67	'/sys/firmware/devicetree',
d1c27c55	68	'/sys/kernel/tracing/trace_pipe',
b401f56f TH	69	'/sys/kernel/debug/tracing/trace_pipe',
	70	'/sys/kernel/security/apparmor/revision');
	71
	72	# Skip these under any subdirectory.
	73	my @skip_any = (
	74	'pagemap',
	75	'events',
	76	'access',
	77	'registers',
	78	'snapshot_raw',
	79	'trace_pipe_raw',
	80	'ptmx',
	81	'trace_pipe',
	82	'fd',
	83	'usbmon');
136fc5c4 TH	84
	85	sub help
	86	{
	87	my ($exitcode) = @_;
	88
	89	print << "EOM";
d09bd8da	90
136fc5c4	91	Usage: $P [OPTIONS]
136fc5c4 TH	92
	93	Options:
	94
15d60a35 TH	95	-o, --output-raw=<file> Save results for future processing.
	96	-i, --input-raw=<file> Read results from file instead of scanning.
	97	--raw Show raw results (default).
	98	--suppress-dmesg Do not show dmesg results.
	99	--squash-by-path Show one result per unique path.
	100	--squash-by-filename Show one result per unique filename.
f9d2a42d	101	--kernel-config-file=<file> Kernel configuration file (e.g /boot/config)
67bbd2f0 KC	102	--kallsyms=<file> Read kernel symbol addresses from file (for
67bbd2f0 KC	103	scanning binary files).
1410fe4e TH	104	--32-bit Scan 32-bit kernel.
1410fe4e TH	105	--page-offset-32-bit=o Page offset (for 32-bit kernel 0xABCD1234).
15d60a35	106	-d, --debug Display debugging output.
9ac060a7	107	-h, --help Display this help and exit.
d09bd8da	108
1410fe4e	109	Scans the running kernel for potential leaking addresses.
136fc5c4 TH	110
	111	EOM
	112	exit($exitcode);
	113	}
	114
	115	GetOptions(
136fc5c4 TH	116	'd\|debug' => \$debug,
136fc5c4 TH	117	'h\|help' => \$help,
d09bd8da TH	118	'o\|output-raw=s' => \$output_raw,
	119	'i\|input-raw=s' => \$input_raw,
	120	'suppress-dmesg' => \$suppress_dmesg,
	121	'squash-by-path' => \$squash_by_path,
	122	'squash-by-filename' => \$squash_by_filename,
	123	'raw' => \$raw,
67bbd2f0	124	'kallsyms=s' => \$kallsyms_file,
f9d2a42d	125	'kernel-config-file=s' => \$kernel_config_file,
1410fe4e TH	126	'32-bit' => \$opt_32bit,
1410fe4e TH	127	'page-offset-32-bit=o' => \$page_offset_32bit,
136fc5c4 TH	128	) or help(1);
	129
	130	help(0) if ($help);
	131
d09bd8da TH	132	if ($input_raw) {
	133	format_output($input_raw);
	134	exit(0);
	135	}
	136
	137	if (!$input_raw and ($squash_by_path or $squash_by_filename)) {
	138	printf "\nSummary reporting only available with --input-raw=<file>\n";
	139	printf "(First run scan with --output-raw=<file>.)\n";
	140	exit(128);
	141	}
	142
1410fe4e	143	if (!(is_supported_architecture() or $opt_32bit or $page_offset_32bit)) {
62139c12 TH	144	printf "\nScript does not support your architecture, sorry.\n";
	145	printf "\nCurrently we support: \n\n";
	146	foreach(@SUPPORTED_ARCHITECTURES) {
	147	printf "\t%s\n", $_;
	148	}
6efb7458	149	printf("\n");
62139c12	150
1410fe4e TH	151	printf("If you are running a 32-bit architecture you may use:\n");
	152	printf("\n\t--32-bit or --page-offset-32-bit=<page offset>\n\n");
	153
6efb7458 TH	154	my $archname = `uname -m`;
6efb7458 TH	155	printf("Machine hardware name (`uname -m`): %s\n", $archname);
62139c12 TH	156
	157	exit(129);
	158	}
	159
d09bd8da TH	160	if ($output_raw) {
	161	open my $fh, '>', $output_raw or die "$0: $output_raw: $!\n";
	162	select $fh;
	163	}
	164
67bbd2f0 KC	165	if ($kallsyms_file) {
	166	open my $fh, '<', $kallsyms_file or die "$0: $kallsyms_file: $!\n";
	167	while (<$fh>) {
	168	chomp;
	169	my @entry = split / /, $_;
	170	my $addr_text = $entry[0];
	171	if ($addr_text !~ /^0/) {
	172	# TODO: Why is hex() so impossibly slow?
	173	my $addr = hex($addr_text);
	174	my $symbol = $entry[2];
	175	# Only keep kernel text addresses.
	176	my $long = pack("J", $addr);
	177	my $entry = [$long, $symbol];
	178	push @kallsyms, $entry;
	179	}
	180	}
	181	close $fh;
	182	}
	183
136fc5c4 TH	184	parse_dmesg();
	185	walk(@DIRS);
	186
	187	exit 0;
	188
136fc5c4 TH	189	sub dprint
	190	{
	191	printf(STDERR @_) if $debug;
	192	}
	193
62139c12 TH	194	sub is_supported_architecture
62139c12 TH	195	{
1410fe4e TH	196	return (is_x86_64() or is_ppc64() or is_ix86_32());
	197	}
	198
	199	sub is_32bit
	200	{
	201	# Allow --32-bit or --page-offset-32-bit to override
	202	if ($opt_32bit or $page_offset_32bit) {
	203	return 1;
	204	}
	205
	206	return is_ix86_32();
	207	}
	208
	209	sub is_ix86_32
	210	{
5e4bac34	211	state $arch = `uname -m`;
1410fe4e TH	212
	213	chomp $arch;
	214	if ($arch =~ m/i[3456]86/) {
	215	return 1;
	216	}
	217	return 0;
62139c12 TH	218	}
62139c12 TH	219
5eb0da05	220	sub is_arch
62139c12	221	{
5eb0da05 TH	222	my ($desc) = @_;
	223	my $arch = `uname -m`;
	224
	225	chomp $arch;
	226	if ($arch eq $desc) {
	227	return 1;
	228	}
	229	return 0;
	230	}
62139c12	231
5eb0da05 TH	232	sub is_x86_64
5eb0da05 TH	233	{
5e4bac34 TH	234	state $is = is_arch('x86_64');
5e4bac34 TH	235	return $is;
62139c12 TH	236	}
	237
	238	sub is_ppc64
	239	{
5e4bac34 TH	240	state $is = is_arch('ppc64');
5e4bac34 TH	241	return $is;
62139c12 TH	242	}
62139c12 TH	243
f9d2a42d TH	244	# Gets config option value from kernel config file.
	245	# Returns "" on error or if config option not found.
	246	sub get_kernel_config_option
	247	{
	248	my ($option) = @_;
	249	my $value = "";
1b1bcbf4	250	my $tmp_fh;
f9d2a42d TH	251	my $tmp_file = "";
	252	my @config_files;
	253
	254	# Allow --kernel-config-file to override.
	255	if ($kernel_config_file ne "") {
	256	@config_files = ($kernel_config_file);
	257	} elsif (-R "/proc/config.gz") {
1b1bcbf4 KC	258	($tmp_fh, $tmp_file) = tempfile("config.gz-XXXXXX",
1b1bcbf4 KC	259	UNLINK => 1);
f9d2a42d TH	260
f9d2a42d TH	261	if (system("gunzip < /proc/config.gz > $tmp_file")) {
0f299433	262	dprint("system(gunzip < /proc/config.gz) failed\n");
f9d2a42d TH	263	return "";
	264	} else {
	265	@config_files = ($tmp_file);
	266	}
	267	} else {
	268	my $file = '/boot/config-' . `uname -r`;
	269	chomp $file;
	270	@config_files = ($file, '/boot/config');
	271	}
	272
	273	foreach my $file (@config_files) {
0f299433	274	dprint("parsing config file: $file\n");
f9d2a42d TH	275	$value = option_from_file($option, $file);
	276	if ($value ne "") {
	277	last;
	278	}
	279	}
	280
f9d2a42d TH	281	return $value;
	282	}
	283
	284	# Parses $file and returns kernel configuration option value.
	285	sub option_from_file
	286	{
	287	my ($option, $file) = @_;
	288	my $str = "";
	289	my $val = "";
	290
	291	open(my $fh, "<", $file) or return "";
	292	while (my $line = <$fh> ) {
	293	if ($line =~ /^$option/) {
	294	($str, $val) = split /=/, $line;
	295	chomp $val;
	296	last;
	297	}
	298	}
	299
	300	close $fh;
	301	return $val;
	302	}
	303
136fc5c4 TH	304	sub is_false_positive
136fc5c4 TH	305	{
7e5758f7 TH	306	my ($match) = @_;
7e5758f7 TH	307
1410fe4e TH	308	if (is_32bit()) {
	309	return is_false_positive_32bit($match);
	310	}
	311
3e389d45 KC	312	# Ignore 64 bit false positives:
	313	# 0xfffffffffffffff[0-f]
	314	# 0x0000000000000000
	315	if ($match =~ '\b(0x)?(f\|F){15}[0-9a-f]\b' or
7e5758f7 TH	316	$match =~ '\b(0x)?0{16}\b') {
	317	return 1;
	318	}
136fc5c4	319
87e37588 TH	320	if (is_x86_64() and is_in_vsyscall_memory_region($match)) {
87e37588 TH	321	return 1;
7e5758f7	322	}
136fc5c4	323
7e5758f7	324	return 0;
136fc5c4 TH	325	}
136fc5c4 TH	326
1410fe4e TH	327	sub is_false_positive_32bit
	328	{
	329	my ($match) = @_;
	330	state $page_offset = get_page_offset();
	331
3e389d45	332	if ($match =~ '\b(0x)?(f\|F){7}[0-9a-f]\b') {
1410fe4e TH	333	return 1;
	334	}
	335
	336	if (hex($match) < $page_offset) {
	337	return 1;
	338	}
	339
	340	return 0;
	341	}
	342
	343	# returns integer value
	344	sub get_page_offset
	345	{
	346	my $page_offset;
	347	my $default_offset = 0xc0000000;
	348
	349	# Allow --page-offset-32bit to override.
	350	if ($page_offset_32bit != 0) {
	351	return $page_offset_32bit;
	352	}
	353
	354	$page_offset = get_kernel_config_option('CONFIG_PAGE_OFFSET');
	355	if (!$page_offset) {
	356	return $default_offset;
	357	}
	358	return $page_offset;
	359	}
	360
87e37588 TH	361	sub is_in_vsyscall_memory_region
	362	{
	363	my ($match) = @_;
	364
	365	my $hex = hex($match);
	366	my $region_min = hex("0xffffffffff600000");
	367	my $region_max = hex("0xffffffffff601000");
	368
	369	return ($hex >= $region_min and $hex <= $region_max);
	370	}
	371
136fc5c4 TH	372	# True if argument potentially contains a kernel address.
	373	sub may_leak_address
	374	{
3e389d45	375	my ($path, $line) = @_;
62139c12	376	my $address_re;
136fc5c4	377
3e389d45	378	# Ignore Signal masks.
7e5758f7	379	if ($line =~ '^SigBlk:' or
a11949ec	380	$line =~ '^SigIgn:' or
7e5758f7 TH	381	$line =~ '^SigCgt:') {
	382	return 0;
	383	}
136fc5c4	384
3e389d45 KC	385	# Ignore input device reporting.
	386	# /proc/bus/input/devices: B: KEY=402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	387	# /sys/devices/platform/i8042/serio0/input/input1/uevent: KEY=402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	388	# /sys/devices/platform/i8042/serio0/input/input1/capabilities/key: 402000000 3803078f800d001 feffffdfffefffff fffffffffffffffe
	389	if ($line =~ '\bKEY=[[:xdigit:]]{9,14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b' or
	390	($path =~ '\bkey$' and
	391	$line =~ '\b[[:xdigit:]]{9,14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b')) {
136fc5c4	392	return 0;
7e5758f7	393	}
136fc5c4	394
2f042c93	395	$address_re = get_address_re();
2306a677	396	while ($line =~ /($address_re)/g) {
7e5758f7 TH	397	if (!is_false_positive($1)) {
	398	return 1;
	399	}
	400	}
136fc5c4	401
7e5758f7	402	return 0;
136fc5c4 TH	403	}
136fc5c4 TH	404
2f042c93 TH	405	sub get_address_re
2f042c93 TH	406	{
1410fe4e	407	if (is_ppc64()) {
2f042c93	408	return '\b(0x)?[89abcdef]00[[:xdigit:]]{13}\b';
1410fe4e TH	409	} elsif (is_32bit()) {
1410fe4e TH	410	return '\b(0x)?[[:xdigit:]]{8}\b';
2f042c93	411	}
1410fe4e TH	412
1410fe4e TH	413	return get_x86_64_re();
2f042c93 TH	414	}
	415
	416	sub get_x86_64_re
	417	{
	418	# We handle page table levels but only if explicitly configured using
	419	# CONFIG_PGTABLE_LEVELS. If config file parsing fails or config option
	420	# is not found we default to using address regular expression suitable
	421	# for 4 page table levels.
	422	state $ptl = get_kernel_config_option('CONFIG_PGTABLE_LEVELS');
	423
	424	if ($ptl == 5) {
	425	return '\b(0x)?ff[[:xdigit:]]{14}\b';
	426	}
	427	return '\b(0x)?ffff[[:xdigit:]]{12}\b';
	428	}
	429
136fc5c4 TH	430	sub parse_dmesg
	431	{
	432	open my $cmd, '-\|', 'dmesg';
	433	while (<$cmd>) {
3e389d45	434	if (may_leak_address("dmesg", $_)) {
136fc5c4 TH	435	print 'dmesg: ' . $_;
	436	}
	437	}
	438	close $cmd;
	439	}
	440
	441	# True if we should skip this path.
	442	sub skip
	443	{
b401f56f	444	my ($path) = @_;
136fc5c4	445
b401f56f	446	foreach (@skip_abs) {
136fc5c4 TH	447	return 1 if (/^$path$/);
	448	}
	449
	450	my($filename, $dirs, $suffix) = fileparse($path);
b401f56f	451	foreach (@skip_any) {
136fc5c4 TH	452	return 1 if (/^$filename$/);
	453	}
	454
	455	return 0;
	456	}
	457
dd98c252 TH	458	sub timed_parse_file
	459	{
	460	my ($file) = @_;
	461
	462	eval {
	463	local $SIG{ALRM} = sub { die "alarm\n" }; # NB: \n required.
	464	alarm $TIMEOUT;
	465	parse_file($file);
	466	alarm 0;
	467	};
	468
	469	if ($@) {
	470	die unless $@ eq "alarm\n"; # Propagate unexpected errors.
	471	printf STDERR "timed out parsing: %s\n", $file;
	472	}
	473	}
	474
67bbd2f0 KC	475	sub parse_binary
	476	{
	477	my ($file) = @_;
	478
	479	open my $fh, "<:raw", $file or return;
	480	local $/ = undef;
	481	my $bytes = <$fh>;
	482	close $fh;
	483
	484	foreach my $entry (@kallsyms) {
	485	my $addr = $entry->[0];
	486	my $symbol = $entry->[1];
	487	my $offset = index($bytes, $addr);
	488	if ($offset != -1) {
	489	printf("$file: $symbol @ $offset\n");
	490	}
	491	}
	492	}
	493
136fc5c4 TH	494	sub parse_file
	495	{
	496	my ($file) = @_;
	497
	498	if (! -R $file) {
	499	return;
	500	}
	501
e2858cad	502	if (! -T $file) {
67bbd2f0 KC	503	if ($file =~ m\|^/sys/kernel/btf/\| or
	504	$file =~ m\|^/sys/devices/pci\| or
	505	$file =~ m\|^/sys/firmware/efi/efivars/\| or
	506	$file =~ m\|^/proc/bus/pci/\|) {
	507	return;
	508	}
	509	if (scalar @kallsyms > 0) {
	510	parse_binary($file);
	511	}
e2858cad TH	512	return;
	513	}
	514
136fc5c4 TH	515	open my $fh, "<", $file or return;
136fc5c4 TH	516	while ( <$fh> ) {
cf2a85ef	517	chomp;
3e389d45	518	if (may_leak_address($file, $_)) {
cf2a85ef	519	printf("$file: $_\n");
136fc5c4 TH	520	}
	521	}
	522	close $fh;
	523	}
	524
c73dff59 TH	525	# Checks if the actual path name is leaking a kernel address.
	526	sub check_path_for_leaks
	527	{
	528	my ($path) = @_;
	529
3e389d45	530	if (may_leak_address($path, $path)) {
c73dff59 TH	531	printf("Path name may contain address: $path\n");
	532	}
	533	}
	534
136fc5c4 TH	535	# Recursively walk directory tree.
	536	sub walk
	537	{
	538	my @dirs = @_;
136fc5c4 TH	539
136fc5c4 TH	540	while (my $pwd = shift @dirs) {
136fc5c4 TH	541	next if (!opendir(DIR, $pwd));
	542	my @files = readdir(DIR);
	543	closedir(DIR);
	544
	545	foreach my $file (@files) {
	546	next if ($file eq '.' or $file eq '..');
	547
	548	my $path = "$pwd/$file";
	549	next if (-l $path);
	550
472c9e10 TH	551	# skip /proc/PID except /proc/1
	552	next if (($path =~ /^\/proc\/[0-9]+$/) &&
	553	($path !~ /^\/proc\/1$/));
	554
b401f56f TH	555	next if (skip($path));
b401f56f TH	556
c73dff59 TH	557	check_path_for_leaks($path);
c73dff59 TH	558
136fc5c4 TH	559	if (-d $path) {
136fc5c4 TH	560	push @dirs, $path;
b401f56f	561	next;
136fc5c4	562	}
b401f56f	563
0f299433	564	dprint("parsing: $path\n");
b401f56f	565	timed_parse_file($path);
136fc5c4 TH	566	}
	567	}
	568	}
d09bd8da TH	569
	570	sub format_output
	571	{
	572	my ($file) = @_;
	573
	574	# Default is to show raw results.
	575	if ($raw or (!$squash_by_path and !$squash_by_filename)) {
	576	dump_raw_output($file);
	577	return;
	578	}
	579
	580	my ($total, $dmesg, $paths, $files) = parse_raw_file($file);
	581
	582	printf "\nTotal number of results from scan (incl dmesg): %d\n", $total;
	583
	584	if (!$suppress_dmesg) {
	585	print_dmesg($dmesg);
	586	}
	587
	588	if ($squash_by_filename) {
	589	squash_by($files, 'filename');
	590	}
	591
	592	if ($squash_by_path) {
	593	squash_by($paths, 'path');
	594	}
	595	}
	596
	597	sub dump_raw_output
	598	{
	599	my ($file) = @_;
	600
	601	open (my $fh, '<', $file) or die "$0: $file: $!\n";
	602	while (<$fh>) {
	603	if ($suppress_dmesg) {
	604	if ("dmesg:" eq substr($_, 0, 6)) {
	605	next;
	606	}
	607	}
	608	print $_;
	609	}
	610	close $fh;
	611	}
	612
	613	sub parse_raw_file
	614	{
	615	my ($file) = @_;
	616
	617	my $total = 0; # Total number of lines parsed.
	618	my @dmesg; # dmesg output.
	619	my %files; # Unique filenames containing leaks.
	620	my %paths; # Unique paths containing leaks.
	621
	622	open (my $fh, '<', $file) or die "$0: $file: $!\n";
	623	while (my $line = <$fh>) {
	624	$total++;
	625
	626	if ("dmesg:" eq substr($line, 0, 6)) {
	627	push @dmesg, $line;
	628	next;
	629	}
	630
	631	cache_path(\%paths, $line);
	632	cache_filename(\%files, $line);
633	}
634
635	return $total, \@dmesg, \%paths, \%files;
636	}
637
638	sub print_dmesg
639	{
640	my ($dmesg) = @_;
641
642	print "\ndmesg output:\n";
643
644	if (@$dmesg == 0) {
645	print "<no results>\n";
646	return;
647	}
648
649	foreach(@$dmesg) {
650	my $index = index($_, ': ');
651	$index += 2; # skid ': '
652	print substr($_, $index);
653	}
654	}
655
656	sub squash_by
657	{
658	my ($ref, $desc) = @_;
659
660	print "\nResults squashed by $desc (excl dmesg). ";
661	print "Displaying [<number of results> <$desc>], <example result>\n";
662
663	if (keys %$ref == 0) {
664	print "<no results>\n";
665	return;
666	}
667
668	foreach(keys %$ref) {
669	my $lines = $ref->{$_};
670	my $length = @$lines;
671	printf "[%d %s] %s", $length, $_, @$lines[0];
672	}
673	}
674
675	sub cache_path
676	{
677	my ($paths, $line) = @_;
678
679	my $index = index($line, ': ');
680	my $path = substr($line, 0, $index);
681
682	$index += 2; # skip ': '
683	add_to_cache($paths, $path, substr($line, $index));
684	}
685
686	sub cache_filename
687	{
688	my ($files, $line) = @_;
689
690	my $index = index($line, ': ');
691	my $path = substr($line, 0, $index);
692	my $filename = basename($path);
693
694	$index += 2; # skip ': '
695	add_to_cache($files, $filename, substr($line, $index));
696	}
697
698	sub add_to_cache
699	{
700	my ($cache, $key, $value) = @_;
701
702	if (!$cache->{$key}) {
703	$cache->{$key} = ();
704	}
705	push @{$cache->{$key}}, $value;
706	}