From 67bbd2f00735d7f5ad6c3d08eff6c5403c3a9c33 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 22 Feb 2024 14:00:51 -0800
Subject: [PATCH] leaking_addresses: Provide mechanism to scan binary files

Introduce --kallsyms argument for scanning binary files for known symbol
addresses. This would have found the exposure in /sys/kernel/notes:

$ scripts/leaking_addresses.pl --kallsyms=<(sudo cat /proc/kallsyms)
/sys/kernel/notes: hypercall_page @ 156
/sys/kernel/notes: xen_hypercall_set_trap_table @ 156
/sys/kernel/notes: startup_xen @ 132

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Tycho Andersen <tandersen@netflix.com>
Link: https://lore.kernel.org/r/20240222220053.1475824-4-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 scripts/leaking_addresses.pl | 53 ++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/scripts/leaking_addresses.pl b/scripts/leaking_addresses.pl
index 73cfcc5c8854..8e992b18bcd9 100755
--- a/scripts/leaking_addresses.pl
+++ b/scripts/leaking_addresses.pl
@@ -52,10 +52,13 @@ 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',
@@ -96,6 +99,8 @@ Options:
 	      --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.
@@ -116,6 +121,7 @@ GetOptions(
 	'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,
@@ -156,6 +162,25 @@ if ($output_raw) {
 	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);
 
@@ -447,6 +472,25 @@ sub timed_parse_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) = @_;
@@ -456,6 +500,15 @@ sub parse_file
 	}
 
 	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;
 	}