1#!/usr/bin/env perl
2#
3#	namespace.pl.  Mon Aug 30 2004
4#
5#	Perform a name space analysis on the linux kernel.
6#
7#	Copyright Keith Owens <kaos@ocs.com.au>.  GPL.
8#
9#	Invoke by changing directory to the top of the kernel object
10#	tree then namespace.pl, no parameters.
11#
12#	Tuned for 2.1.x kernels with the new module handling, it will
13#	work with 2.0 kernels as well.
14#
15#	Last change 2.6.9-rc1, adding support for separate source and object
16#	trees.
17#
18#	The source must be compiled/assembled first, the object files
19#	are the primary input to this script.  Incomplete or missing
20#	objects will result in a flawed analysis.  Compile both vmlinux
21#	and modules.
22#
23#	Even with complete objects, treat the result of the analysis
24#	with caution.  Some external references are only used by
25#	certain architectures, others with certain combinations of
26#	configuration parameters.  Ideally the source should include
27#	something like
28#
29#	#ifndef CONFIG_...
30#	static
31#	#endif
32#	symbol_definition;
33#
34#	so the symbols are defined as static unless a particular
35#	CONFIG_... requires it to be external.
36#
37#	A symbol that is suffixed with '(export only)' has these properties
38#
39#	* It is global.
40#	* It is marked EXPORT_SYMBOL or EXPORT_SYMBOL_GPL, either in the same
41#	  source file or a different source file.
42#	* Given the current .config, nothing uses the symbol.
43#
44#	The symbol is a candidate for conversion to static, plus removal of the
45#	export.  But be careful that a different .config might use the symbol.
46#
47#
48#	Name space analysis and cleanup is an iterative process.  You cannot
49#	expect to find all the problems in a single pass.
50#
51#	* Identify possibly unnecessary global declarations, verify that they
52#	  really are unnecessary and change them to static.
53#	* Compile and fix up gcc warnings about static, removing dead symbols
54#	  as necessary.
55#	* make clean and rebuild with different configs (especially
56#	  CONFIG_MODULES=n) to see which symbols are being defined when the
57#	  config does not require them.  These symbols bloat the kernel object
58#	  for no good reason, which is frustrating for embedded systems.
59#	* Wrap config sensitive symbols in #ifdef CONFIG_foo, as long as the
60#	  code does not get too ugly.
61#	* Repeat the name space analysis until you can live with with the
62#	  result.
63#
64
65use warnings;
66use strict;
67use File::Find;
68use File::Spec;
69
70my $nm = ($ENV{'NM'} || "nm") . " -p";
71my $objdump = ($ENV{'OBJDUMP'} || "objdump") . " -s -j .comment";
72my $srctree = File::Spec->curdir();
73my $objtree = File::Spec->curdir();
74$srctree = File::Spec->rel2abs($ENV{'srctree'}) if (exists($ENV{'srctree'}));
75$objtree = File::Spec->rel2abs($ENV{'objtree'}) if (exists($ENV{'objtree'}));
76
77if ($#ARGV != -1) {
78	print STDERR "usage: $0 takes no parameters\n";
79	die("giving up\n");
80}
81
82my %nmdata = ();	# nm data for each object
83my %def = ();		# all definitions for each name
84my %ksymtab = ();	# names that appear in __ksymtab_
85my %ref = ();		# $ref{$name} exists if there is a true external reference to $name
86my %export = ();	# $export{$name} exists if there is an EXPORT_... of $name
87
88my %nmexception = (
89    'fs/ext3/bitmap'			=> 1,
90    'fs/ext4/bitmap'			=> 1,
91    'arch/x86/lib/thunk_32'		=> 1,
92    'arch/x86/lib/cmpxchg'		=> 1,
93    'arch/x86/vdso/vdso32/note'		=> 1,
94    'lib/irq_regs'			=> 1,
95    'usr/initramfs_data'		=> 1,
96    'drivers/scsi/aic94xx/aic94xx_dump'	=> 1,
97    'drivers/scsi/libsas/sas_dump'	=> 1,
98    'lib/dec_and_lock'			=> 1,
99    'drivers/ide/ide-probe-mini'	=> 1,
100    'usr/initramfs_data'		=> 1,
101    'drivers/acpi/acpia/exdump'		=> 1,
102    'drivers/acpi/acpia/rsdump'		=> 1,
103    'drivers/acpi/acpia/nsdumpdv'	=> 1,
104    'drivers/acpi/acpia/nsdump'		=> 1,
105    'arch/ia64/sn/kernel/sn2/io'	=> 1,
106    'arch/ia64/kernel/gate-data'	=> 1,
107    'security/capability'		=> 1,
108    'fs/ntfs/sysctl'			=> 1,
109    'fs/jfs/jfs_debug'			=> 1,
110);
111
112my %nameexception = (
113    'mod_use_count_'	 => 1,
114    '__initramfs_end'	=> 1,
115    '__initramfs_start'	=> 1,
116    '_einittext'	=> 1,
117    '_sinittext'	=> 1,
118    'kallsyms_names'	=> 1,
119    'kallsyms_num_syms'	=> 1,
120    'kallsyms_addresses'=> 1,
121    'kallsyms_offsets'	=> 1,
122    'kallsyms_relative_base'=> 1,
123    '__this_module'	=> 1,
124    '_etext'		=> 1,
125    '_edata'		=> 1,
126    '_end'		=> 1,
127    '__bss_start'	=> 1,
128    '_text'		=> 1,
129    '_stext'		=> 1,
130    '__gp'		=> 1,
131    'ia64_unw_start'	=> 1,
132    'ia64_unw_end'	=> 1,
133    '__init_begin'	=> 1,
134    '__init_end'	=> 1,
135    '__bss_stop'	=> 1,
136    '__nosave_begin'	=> 1,
137    '__nosave_end'	=> 1,
138    'pg0'		=> 1,
139    'vdso_enabled'	=> 1,
140    '__stack_chk_fail'  => 1,
141    'VDSO32_PRELINK'	=> 1,
142    'VDSO32_vsyscall'	=> 1,
143    'VDSO32_rt_sigreturn'=>1,
144    'VDSO32_sigreturn'	=> 1,
145);
146
147
148&find(\&linux_objects, '.');	# find the objects and do_nm on them
149&list_multiply_defined();
150&resolve_external_references();
151&list_extra_externals();
152
153exit(0);
154
155sub linux_objects
156{
157	# Select objects, ignoring objects which are only created by
158	# merging other objects.  Also ignore all of modules, scripts
159	# and compressed.  Most conglomerate objects are handled by do_nm,
160	# this list only contains the special cases.  These include objects
161	# that are linked from just one other object and objects for which
162	# there is really no permanent source file.
163	my $basename = $_;
164	$_ = $File::Find::name;
165	s:^\./::;
166	if (/.*\.o$/ &&
167		! (
168		m:/built-in.a$:
169		|| m:arch/x86/vdso/:
170		|| m:arch/x86/boot/:
171		|| m:arch/ia64/ia32/ia32.o$:
172		|| m:arch/ia64/kernel/gate-syms.o$:
173		|| m:arch/ia64/lib/__divdi3.o$:
174		|| m:arch/ia64/lib/__divsi3.o$:
175		|| m:arch/ia64/lib/__moddi3.o$:
176		|| m:arch/ia64/lib/__modsi3.o$:
177		|| m:arch/ia64/lib/__udivdi3.o$:
178		|| m:arch/ia64/lib/__udivsi3.o$:
179		|| m:arch/ia64/lib/__umoddi3.o$:
180		|| m:arch/ia64/lib/__umodsi3.o$:
181		|| m:arch/ia64/scripts/check_gas_for_hint.o$:
182		|| m:arch/ia64/sn/kernel/xp.o$:
183		|| m:boot/bbootsect.o$:
184		|| m:boot/bsetup.o$:
185		|| m:/bootsect.o$:
186		|| m:/boot/setup.o$:
187		|| m:/compressed/:
188		|| m:drivers/cdrom/driver.o$:
189		|| m:drivers/char/drm/tdfx_drv.o$:
190		|| m:drivers/ide/ide-detect.o$:
191		|| m:drivers/ide/pci/idedriver-pci.o$:
192		|| m:drivers/media/media.o$:
193		|| m:drivers/scsi/sd_mod.o$:
194		|| m:drivers/video/video.o$:
195		|| m:fs/devpts/devpts.o$:
196		|| m:fs/exportfs/exportfs.o$:
197		|| m:fs/hugetlbfs/hugetlbfs.o$:
198		|| m:fs/msdos/msdos.o$:
199		|| m:fs/nls/nls.o$:
200		|| m:fs/ramfs/ramfs.o$:
201		|| m:fs/romfs/romfs.o$:
202		|| m:fs/vfat/vfat.o$:
203		|| m:init/mounts.o$:
204		|| m:^modules/:
205		|| m:net/netlink/netlink.o$:
206		|| m:net/sched/sched.o$:
207		|| m:/piggy.o$:
208		|| m:^scripts/:
209		|| m:sound/.*/snd-:
210		|| m:^.*/\.tmp_:
211		|| m:^\.tmp_:
212		|| m:/vmlinux-obj.o$:
213		|| m:^tools/:
214		)
215	) {
216		do_nm($basename, $_);
217	}
218	$_ = $basename;		# File::Find expects $_ untouched (undocumented)
219}
220
221sub do_nm
222{
223	my ($basename, $fullname) = @_;
224	my ($source, $type, $name);
225	if (! -e $basename) {
226		printf STDERR "$basename does not exist\n";
227		return;
228	}
229	if ($fullname !~ /\.o$/) {
230		printf STDERR "$fullname is not an object file\n";
231		return;
232	}
233	($source = $basename) =~ s/\.o$//;
234	if (-e "$source.c" || -e "$source.S") {
235		$source = File::Spec->catfile($objtree, $File::Find::dir, $source)
236	} else {
237		$source = File::Spec->catfile($srctree, $File::Find::dir, $source)
238	}
239	if (! -e "$source.c" && ! -e "$source.S") {
240		# No obvious source, exclude the object if it is conglomerate
241	        open(my $objdumpdata, "$objdump $basename|")
242		    or die "$objdump $fullname failed $!\n";
243
244		my $comment;
245		while (<$objdumpdata>) {
246			chomp();
247			if (/^In archive/) {
248				# Archives are always conglomerate
249				$comment = "GCC:GCC:";
250				last;
251			}
252			next if (! /^[ 0-9a-f]{5,} /);
253			$comment .= substr($_, 43);
254		}
255		close($objdumpdata);
256
257		if (!defined($comment) || $comment !~ /GCC\:.*GCC\:/m) {
258			printf STDERR "No source file found for $fullname\n";
259		}
260		return;
261	}
262	open (my $nmdata, "$nm $basename|")
263	    or die "$nm $fullname failed $!\n";
264
265	my @nmdata;
266	while (<$nmdata>) {
267		chop;
268		($type, $name) = (split(/ +/, $_, 3))[1..2];
269		# Expected types
270		# A absolute symbol
271		# B weak external reference to data that has been resolved
272		# C global variable, uninitialised
273		# D global variable, initialised
274		# G global variable, initialised, small data section
275		# R global array, initialised
276		# S global variable, uninitialised, small bss
277		# T global label/procedure
278		# U external reference
279		# W weak external reference to text that has been resolved
280		# V similar to W, but the value of the weak symbol becomes zero with no error.
281		# a assembler equate
282		# b static variable, uninitialised
283		# d static variable, initialised
284		# g static variable, initialised, small data section
285		# r static array, initialised
286		# s static variable, uninitialised, small bss
287		# t static label/procedures
288		# w weak external reference to text that has not been resolved
289		# v similar to w
290		# ? undefined type, used a lot by modules
291		if ($type !~ /^[ABCDGRSTUWVabdgrstwv?]$/) {
292			printf STDERR "nm output for $fullname contains unknown type '$_'\n";
293		}
294		elsif ($name =~ /\./) {
295			# name with '.' is local static
296		}
297		else {
298			$type = 'R' if ($type eq '?');	# binutils replaced ? with R at one point
299			# binutils keeps changing the type for exported symbols, force it to R
300			$type = 'R' if ($name =~ /^__ksymtab/ || $name =~ /^__kstrtab/);
301			$name =~ s/_R[a-f0-9]{8}$//;	# module versions adds this
302			if ($type =~ /[ABCDGRSTWV]/ &&
303				$name ne 'init_module' &&
304				$name ne 'cleanup_module' &&
305				$name ne 'Using_Versions' &&
306				$name !~ /^Version_[0-9]+$/ &&
307				$name !~ /^__parm_/ &&
308				$name !~ /^__kstrtab/ &&
309				$name !~ /^__ksymtab/ &&
310				$name !~ /^__kcrctab_/ &&
311				$name !~ /^__exitcall_/ &&
312				$name !~ /^__initcall_/ &&
313				$name !~ /^__kdb_initcall_/ &&
314				$name !~ /^__kdb_exitcall_/ &&
315				$name !~ /^__module_/ &&
316				$name !~ /^__mod_/ &&
317				$name !~ /^__crc_/ &&
318				$name ne '__this_module' &&
319				$name ne 'kernel_version') {
320				if (!exists($def{$name})) {
321					$def{$name} = [];
322				}
323				push(@{$def{$name}}, $fullname);
324			}
325			push(@nmdata, "$type $name");
326			if ($name =~ /^__ksymtab_/) {
327				$name = substr($name, 10);
328				if (!exists($ksymtab{$name})) {
329					$ksymtab{$name} = [];
330				}
331				push(@{$ksymtab{$name}}, $fullname);
332			}
333		}
334	}
335	close($nmdata);
336
337	if ($#nmdata < 0) {
338	    printf "No nm data for $fullname\n"
339		unless $nmexception{$fullname};
340	    return;
341	}
342	$nmdata{$fullname} = \@nmdata;
343}
344
345sub drop_def
346{
347	my ($object, $name) = @_;
348	my $nmdata = $nmdata{$object};
349	my ($i, $j);
350	for ($i = 0; $i <= $#{$nmdata}; ++$i) {
351		if ($name eq (split(' ', $nmdata->[$i], 2))[1]) {
352			splice(@{$nmdata{$object}}, $i, 1);
353			my $def = $def{$name};
354			for ($j = 0; $j < $#{$def{$name}}; ++$j) {
355				if ($def{$name}[$j] eq $object) {
356					splice(@{$def{$name}}, $j, 1);
357				}
358			}
359			last;
360		}
361	}
362}
363
364sub list_multiply_defined
365{
366	foreach my $name (keys(%def)) {
367		if ($#{$def{$name}} > 0) {
368			# Special case for cond_syscall
369			if ($#{$def{$name}} == 1 &&
370			   ($name =~ /^sys_/ || $name =~ /^compat_sys_/ ||
371			    $name =~ /^sys32_/)) {
372				if($def{$name}[0] eq "kernel/sys_ni.o" ||
373				   $def{$name}[1] eq "kernel/sys_ni.o") {
374					&drop_def("kernel/sys_ni.o", $name);
375					next;
376				}
377			}
378
379			printf "$name is multiply defined in :-\n";
380			foreach my $module (@{$def{$name}}) {
381				printf "\t$module\n";
382			}
383		}
384	}
385}
386
387sub resolve_external_references
388{
389	my ($kstrtab, $ksymtab, $export);
390
391	printf "\n";
392	foreach my $object (keys(%nmdata)) {
393		my $nmdata = $nmdata{$object};
394		for (my $i = 0; $i <= $#{$nmdata}; ++$i) {
395			my ($type, $name) = split(' ', $nmdata->[$i], 2);
396			if ($type eq "U" || $type eq "w") {
397				if (exists($def{$name}) || exists($ksymtab{$name})) {
398					# add the owning object to the nmdata
399					$nmdata->[$i] = "$type $name $object";
400					# only count as a reference if it is not EXPORT_...
401					$kstrtab = "R __kstrtab_$name";
402					$ksymtab = "R __ksymtab_$name";
403					$export = 0;
404					for (my $j = 0; $j <= $#{$nmdata}; ++$j) {
405						if ($nmdata->[$j] eq $kstrtab ||
406						    $nmdata->[$j] eq $ksymtab) {
407							$export = 1;
408							last;
409						}
410					}
411					if ($export) {
412						$export{$name} = "";
413					}
414					else {
415						$ref{$name} = ""
416					}
417				}
418				elsif ( ! $nameexception{$name}
419					&& $name !~ /^__sched_text_/
420					&& $name !~ /^__start_/
421					&& $name !~ /^__end_/
422					&& $name !~ /^__stop_/
423					&& $name !~ /^__scheduling_functions_.*_here/
424					&& $name !~ /^__.*initcall_/
425					&& $name !~ /^__.*per_cpu_start/
426					&& $name !~ /^__.*per_cpu_end/
427					&& $name !~ /^__alt_instructions/
428					&& $name !~ /^__setup_/
429					&& $name !~ /^__mod_timer/
430					&& $name !~ /^__mod_page_state/
431					&& $name !~ /^init_module/
432					&& $name !~ /^cleanup_module/
433				) {
434					printf "Cannot resolve ";
435					printf "weak " if ($type eq "w");
436					printf "reference to $name from $object\n";
437				}
438			}
439		}
440	}
441}
442
443sub list_extra_externals
444{
445	my %noref = ();
446
447	foreach my $name (keys(%def)) {
448		if (! exists($ref{$name})) {
449			my @module = @{$def{$name}};
450			foreach my $module (@module) {
451				if (! exists($noref{$module})) {
452					$noref{$module} = [];
453				}
454				push(@{$noref{$module}}, $name);
455			}
456		}
457	}
458	if (%noref) {
459		printf "\nExternally defined symbols with no external references\n";
460		foreach my $module (sort(keys(%noref))) {
461			printf "  $module\n";
462			foreach (sort(@{$noref{$module}})) {
463			    my $export;
464			    if (exists($export{$_})) {
465				$export = " (export only)";
466			    } else {
467				$export = "";
468			    }
469			    printf "    $_$export\n";
470			}
471		}
472	}
473}
474