leaking_addresses.pl 12.9 KB
Newer Older
1 2 3 4 5
#!/usr/bin/env perl
#
# (c) 2017 Tobin C. Harding <me@tobin.cc>
# Licensed under the terms of the GNU GPL License version 2
#
6
# leaking_addresses.pl: Scan the kernel for potential leaking addresses.
7 8 9 10 11 12 13 14 15 16 17 18 19 20
#  - 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.

use warnings;
use strict;
use POSIX;
use File::Basename;
use File::Spec;
use Cwd 'abs_path';
use Term::ANSIColor qw(:constants);
use Getopt::Long qw(:config no_auto_abbrev);
21
use Config;
22
use bigint qw/hex/;
23
use feature 'state';
24 25 26 27 28 29 30

my $P = $0;
my $V = '0.01';

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

31 32 33
# Timer for parsing each file, in seconds.
my $TIMEOUT = 10;

34 35 36
# 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');
37

38 39 40
# Command line options.
my $help = 0;
my $debug = 0;
41 42 43 44 45 46
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.
47
my $kernel_config_file = "";	# Kernel configuration file.
48 49
my $opt_32bit = 0;		# Scan 32-bit kernel.
my $page_offset_32bit = 0;	# Page offset for 32-bit kernel.
50 51 52 53 54 55

# Do not parse these files (absolute path).
my @skip_parse_files_abs = ('/proc/kmsg',
			    '/proc/kcore',
			    '/proc/fs/ext4/sdb1/mb_groups',
			    '/proc/1/fd/3',
56 57
			    '/sys/firmware/devicetree',
			    '/proc/device-tree',
58 59 60
			    '/sys/kernel/debug/tracing/trace_pipe',
			    '/sys/kernel/security/apparmor/revision');

61
# Do not parse these files under any subdirectory.
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
my @skip_parse_files_any = ('0',
			    '1',
			    '2',
			    'pagemap',
			    'events',
			    'access',
			    'registers',
			    'snapshot_raw',
			    'trace_pipe_raw',
			    'ptmx',
			    'trace_pipe');

# Do not walk these directories (absolute path).
my @skip_walk_dirs_abs = ();

# Do not walk these directories under any subdirectory.
my @skip_walk_dirs_any = ('self',
			  'thread-self',
			  'cwd',
			  'fd',
82
			  'usbmon',
83 84 85 86 87 88 89 90 91
			  'stderr',
			  'stdin',
			  'stdout');

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

	print << "EOM";
92

93 94 95 96 97
Usage: $P [OPTIONS]
Version: $V

Options:

98 99 100 101 102 103
	-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.
104
	--kernel-config-file=<file>     Kernel configuration file (e.g /boot/config)
105 106
	--32-bit			Scan 32-bit kernel.
	--page-offset-32-bit=o		Page offset (for 32-bit kernel 0xABCD1234).
107 108
	-d, --debug			Display debugging output.
	-h, --help, --version		Display this help and exit.
109

110
Scans the running kernel for potential leaking addresses.
111 112 113 114 115 116 117 118

EOM
	exit($exitcode);
}

GetOptions(
	'd|debug'		=> \$debug,
	'h|help'		=> \$help,
119 120 121 122 123 124 125
	'version'		=> \$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,
126
	'kernel-config-file=s'	=> \$kernel_config_file,
127 128
	'32-bit'		=> \$opt_32bit,
	'page-offset-32-bit=o'	=> \$page_offset_32bit,
129 130 131 132
) or help(1);

help(0) if ($help);

133 134 135 136 137 138 139 140 141 142 143
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);
}

144
if (!(is_supported_architecture() or $opt_32bit or $page_offset_32bit)) {
145 146 147 148 149
	printf "\nScript does not support your architecture, sorry.\n";
	printf "\nCurrently we support: \n\n";
	foreach(@SUPPORTED_ARCHITECTURES) {
		printf "\t%s\n", $_;
	}
150
	printf("\n");
151

152 153 154
	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");

155 156
	my $archname = `uname -m`;
	printf("Machine hardware name (`uname -m`): %s\n", $archname);
157 158 159 160

	exit(129);
}

161 162 163 164 165
if ($output_raw) {
	open my $fh, '>', $output_raw or die "$0: $output_raw: $!\n";
	select $fh;
}

166 167 168 169 170 171 172 173 174 175
parse_dmesg();
walk(@DIRS);

exit 0;

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

176 177
sub is_supported_architecture
{
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
	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
{
       my $arch = `uname -m`;

       chomp $arch;
       if ($arch =~ m/i[3456]86/) {
               return 1;
       }
       return 0;
200 201
}

202
sub is_arch
203
{
204 205 206 207 208 209 210 211 212
       my ($desc) = @_;
       my $arch = `uname -m`;

       chomp $arch;
       if ($arch eq $desc) {
               return 1;
       }
       return 0;
}
213

214 215 216
sub is_x86_64
{
	return is_arch('x86_64');
217 218 219 220
}

sub is_ppc64
{
221
	return is_arch('ppc64');
222 223
}

224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
# 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_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") {
		my $tmp_file = "/tmp/tmpkconf";

		if (system("gunzip < /proc/config.gz > $tmp_file")) {
			dprint "$0: system(gunzip < /proc/config.gz) failed\n";
			return "";
		} else {
			@config_files = ($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: %s\n", $file);
		$value = option_from_file($option, $file);
		if ($value ne "") {
			last;
		}
	}

	if ($tmp_file ne "") {
		system("rm -f $tmp_file");
	}

	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;
}

286 287
sub is_false_positive
{
288 289
	my ($match) = @_;

290 291 292 293 294 295
	if (is_32bit()) {
		return is_false_positive_32bit($match);
	}

	# 64 bit false positives.

296 297 298 299
	if ($match =~ '\b(0x)?(f|F){16}\b' or
	    $match =~ '\b(0x)?0{16}\b') {
		return 1;
	}
300

301 302
	if (is_x86_64() and is_in_vsyscall_memory_region($match)) {
		return 1;
303
	}
304

305
	return 0;
306 307
}

308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
sub is_false_positive_32bit
{
       my ($match) = @_;
       state $page_offset = get_page_offset();

       if ($match =~ '\b(0x)?(f|F){8}\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;
}

342 343 344 345 346 347 348 349 350 351 352
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);
}

353 354 355
# True if argument potentially contains a kernel address.
sub may_leak_address
{
356
	my ($line) = @_;
357
	my $address_re;
358

359 360
	# Signal masks.
	if ($line =~ '^SigBlk:' or
361
	    $line =~ '^SigIgn:' or
362 363 364
	    $line =~ '^SigCgt:') {
		return 0;
	}
365

366 367
	if ($line =~ '\bKEY=[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b' or
	    $line =~ '\b[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b') {
368
		return 0;
369
	}
370

371
	$address_re = get_address_re();
372
	while (/($address_re)/g) {
373 374 375 376
		if (!is_false_positive($1)) {
			return 1;
		}
	}
377

378
	return 0;
379 380
}

381 382
sub get_address_re
{
383
	if (is_ppc64()) {
384
		return '\b(0x)?[89abcdef]00[[:xdigit:]]{13}\b';
385 386
	} elsif (is_32bit()) {
		return '\b(0x)?[[:xdigit:]]{8}\b';
387
	}
388 389

	return get_x86_64_re();
390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
}

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';
}

406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
sub parse_dmesg
{
	open my $cmd, '-|', 'dmesg';
	while (<$cmd>) {
		if (may_leak_address($_)) {
			print 'dmesg: ' . $_;
		}
	}
	close $cmd;
}

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

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

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

	return 0;
}

sub skip_parse
{
	my ($path) = @_;
	return skip($path, \@skip_parse_files_abs, \@skip_parse_files_any);
}

440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
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;
	}
}

457 458 459 460 461 462 463 464
sub parse_file
{
	my ($file) = @_;

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

465 466 467 468
	if (! -T $file) {
		return;
	}

469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
	if (skip_parse($file)) {
		dprint "skipping file: $file\n";
		return;
	}
	dprint "parsing: $file\n";

	open my $fh, "<", $file or return;
	while ( <$fh> ) {
		if (may_leak_address($_)) {
			print $file . ': ' . $_;
		}
	}
	close $fh;
}


# True if we should skip walking this directory.
sub skip_walk
{
	my ($path) = @_;
	return skip($path, \@skip_walk_dirs_abs, \@skip_walk_dirs_any)
}

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

	while (my $pwd = shift @dirs) {
		next if (skip_walk($pwd));
		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);

			if (-d $path) {
				push @dirs, $path;
			} else {
512
				timed_parse_file($path);
513 514 515 516
			}
		}
	}
}
517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654

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;
}