[PATCH v3] scripts: leaking_addresses: add support for 32-bit kernel addresses

[kaiwan . billimoria]

Currently, leaking_addresses.pl only supports scanning 64 bit
architectures. This is due to how the regular expressions are formed. We
can do better than this. 32 architectures can be supported if we take
into consideration the kernel virtual address split (via the PAGE_OFFSET
kernel configurable).

Add support for ix86 32 bit architectures.
 - Add command line option for page offset.
 - Add command line option for kernel configuration file.
 - Parse kernel config file for page offset (CONFIG_PAGE_OFFSET).
 - Use page offset when checking for kernel virtual addresses.


Signed-off-by: Kaiwan N Billimoria <kaiwan.billimoria@xxxxxxxxx>
---

Note- This patch represents co development by Tobin and Kaiwan (plus suggestions from 
Alexander Kapshuk). Applies on Tobin's tree 'leaks' branch on top of commit 680db1ef560f
(leaking_addresses: fix typo function not called).


 scripts/leaking_addresses.pl | 169 +++++++++++++++++++++++++++++++++++++------
 1 file changed, 148 insertions(+), 21 deletions(-)

diff --git a/scripts/leaking_addresses.pl b/scripts/leaking_addresses.pl
index 2d5336b3e1ea..6b015980d117 100755
--- a/scripts/leaking_addresses.pl
+++ b/scripts/leaking_addresses.pl
@@ -24,6 +24,7 @@ use Cwd 'abs_path';
 use Term::ANSIColor qw(:constants);
 use Getopt::Long qw(:config no_auto_abbrev);
 use Config;
+use feature 'state';
 
 my $P = $0;
 my $V = '0.01';
@@ -37,18 +38,20 @@ my $TIMEOUT = 10;
 # Script can only grep for kernel addresses on the following architectures. If
 # your architecture is not listed here and has a grep'able kernel address please
 # consider submitting a patch.
-my @SUPPORTED_ARCHITECTURES = ('x86_64', 'ppc64');
+my @SUPPORTED_ARCHITECTURES = ('x86_64', 'ppc64',  'i[3456]86');
 
 # 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 $raw = 0;                   # Show raw output.
+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 $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 $page_offset_32bit = 0;     # 32-bit: value of CONFIG_PAGE_OFFSET
+my $kernel_config_file = "";   # Kernel configuration file.
 
 # Do not parse these files (absolute path).
 my @skip_parse_files_abs = ('/proc/kmsg',
@@ -97,14 +100,16 @@ Version: $V
 
 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.
-	-d, --debug              Display debugging output.
-	-h, --help, --version    Display this help and exit.
+	-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.
+	--page-offset-32bit=<hex>       PAGE_OFFSET value (for 32-bit kernels).
+	--kernel-config-file=<file>     Kernel configuration file (e.g /boot/config)
+	-d, --debug                     Display debugging output.
+	-h, --help, --version           Display this help and exit.
 
 Examples:
 
@@ -117,7 +122,10 @@ Examples:
 	# View summary report.
 	$0 --input-raw scan.out --squash-by-filename
 
-Scans the running (64 bit) kernel for potential leaking addresses.
+	# Scan kernel on a 32-bit system with a 2GB:2GB virtual address split.
+	$0 --page-offset-32bit=0x80000000
+
+Scans the running kernel for potential leaking addresses.
 
 EOM
 	exit($exitcode);
@@ -133,6 +141,8 @@ GetOptions(
 	'squash-by-path'        => \$squash_by_path,
 	'squash-by-filename'    => \$squash_by_filename,
 	'raw'                   => \$raw,
+	'page-offset-32bit=o'   => \$page_offset_32bit,
+	'kernel-config-file=s'  => \$kernel_config_file,
 ) or help(1);
 
 help(0) if ($help);
@@ -148,6 +158,7 @@ if (!$input_raw and ($squash_by_path or $squash_by_filename)) {
 	exit(128);
 }
 
+show_detected_architecture() if $debug;
 if (!is_supported_architecture()) {
 	printf "\nScript does not support your architecture, sorry.\n";
 	printf "\nCurrently we support: \n\n";
@@ -179,7 +190,7 @@ sub dprint
 
 sub is_supported_architecture
 {
-	return (is_x86_64() or is_ppc64());
+	return (is_x86_64() or is_ppc64() or is_ix86_32());
 }
 
 sub is_x86_64
@@ -202,10 +213,40 @@ sub is_ppc64
 	return 0;
 }
 
+sub is_ix86_32
+{
+	my $archname = $Config{archname};
+
+	if ($archname =~ m/i[3456]86-linux/) {
+		return 1;
+	}
+	return 0;
+}
+
+sub show_detected_architecture
+{
+	printf "Detected architecture: ";
+	if (is_ix86_32()) {
+		printf "32 bit x86\n";
+	} elsif (is_x86_64()) {
+		printf "x86_64\n";
+	} elsif (is_ppc64()) {
+		printf "ppc64\n";
+	} else {
+		printf "failed to detect architecture\n"
+	}
+}
+
 sub is_false_positive
 {
 	my ($match) = @_;
 
+	if (is_ix86_32()) {
+		return is_false_positive_ix86_32($match);
+	}
+
+	# 64 bit architectures
+
 	if ($match =~ '\b(0x)?(f|F){16}\b' or
 	    $match =~ '\b(0x)?0{16}\b') {
 		return 1;
@@ -222,6 +263,89 @@ sub is_false_positive
 	return 0;
 }
 
+sub is_false_positive_ix86_32
+{
+	my ($match) = @_;
+	state $page_offset = get_page_offset(); # only gets called once
+	if ($match =~ '\b(0x)?(f|F){8}\b') {
+		return 1;
+	}
+
+	my $addr32 = eval hex($match);
+	if ($addr32 < $page_offset) {
+		return 1;
+	}
+
+	return 0;
+}
+
+sub get_page_offset
+{
+	my $page_offset;
+	my $default_offset = hex("0xc0000000");
+	my @config_files;
+
+	# Allow --page-offset-32bit to override.
+	if ($page_offset_32bit != 0) {
+		return $page_offset_32bit;
+	}
+
+	# Allow --kernel-config-file to override.
+	if ($kernel_config_file ne "") {
+		@config_files = ($kernel_config_file);
+	} else {
+		my $config_file = '/boot/config-' . `uname -r`;
+		@config_files = ($config_file, '/boot/config');
+	}
+
+	if (-R "/proc/config.gz") {
+		my $tmp_file = "/tmp/tmpkconf";
+		if (system("gunzip < /proc/config.gz > $tmp_file")) {
+			dprint " parse_kernel_config: system(gunzip...) failed\n";
+		} else {
+			$page_offset = parse_kernel_config_file($tmp_file);
+			if ($page_offset ne "") {
+				return hex($page_offset);
+			}
+		}
+		system("rm -f $tmp_file");
+	}
+
+	foreach my $config_file (@config_files) {
+		chomp $config_file;
+		$page_offset = parse_kernel_config_file($config_file);
+		if ($page_offset ne "") {
+			return hex($page_offset);
+		}
+	}
+
+	printf STDERR "\nFailed to parse kernel config files\n";
+	printf STDERR "*** NOTE ***\n";
+	printf STDERR "Falling back to PAGE_OFFSET = %#x\n\n", $default_offset;
+
+	return $default_offset;
+}
+
+sub parse_kernel_config_file
+{
+	my ($file) = @_;
+	my $config = 'CONFIG_PAGE_OFFSET';
+	my $str = "";
+	my $val = "";
+
+	open(my $fh, "<", $file) or return "";
+	while (my $line = <$fh> ) {
+		if ($line =~ /^$config/) {
+			($str, $val) = split /=/, $line;
+			chomp($val);
+			last;
+		}
+	}
+
+	close $fh;
+	return $val;
+}
+
 # True if argument potentially contains a kernel address.
 sub may_leak_address
 {
@@ -235,9 +359,11 @@ sub may_leak_address
 		return 0;
 	}
 
-	if ($line =~ '\bKEY=[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b' or
-	    $line =~ '\b[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b') {
-		return 0;
+	if (is_x86_64() or is_ppc64()) {
+		if ($line =~ '\bKEY=[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b' or
+		    $line =~ '\b[[:xdigit:]]{14} [[:xdigit:]]{16} [[:xdigit:]]{16}\b') {
+			return 0;
+		}
 	}
 
 	# One of these is guaranteed to be true.
@@ -245,6 +371,8 @@ sub may_leak_address
 		$address_re = '\b(0x)?ffff[[:xdigit:]]{12}\b';
 	} elsif (is_ppc64()) {
 		$address_re = '\b(0x)?[89abcdef]00[[:xdigit:]]{13}\b';
+	} elsif (is_ix86_32()) {
+		$address_re = '\b(0x)?[[:xdigit:]]{8}\b';
 	}
 
 	while (/($address_re)/g) {
@@ -330,7 +458,6 @@ sub parse_file
 	close $fh;
 }
 
-
 # True if we should skip walking this directory.
 sub skip_walk
 {
-- 
2.14.3