This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
Add :base_thread to :default in Opcode.pm
[perl5.git] / ext / Opcode / Opcode.pm
CommitLineData
6badd1a5
PP
1package Opcode;
2
3require 5.002;
4
137443ea 5use vars qw($VERSION $XS_VERSION @ISA @EXPORT_OK);
6badd1a5 6
8903cb82 7$VERSION = "1.04";
e858de61 8$XS_VERSION = "1.03";
6badd1a5
PP
9
10use strict;
11use Carp;
12use Exporter ();
13use DynaLoader ();
14@ISA = qw(Exporter DynaLoader);
15
16BEGIN {
17 @EXPORT_OK = qw(
18 opset ops_to_opset
19 opset_to_ops opset_to_hex invert_opset
20 empty_opset full_opset
21 opdesc opcodes opmask define_optag
22 opmask_add verify_opset opdump
23 );
24}
25
68dc0745
PP
26sub opset (;@);
27sub opset_to_hex ($);
28sub opdump (;$);
6badd1a5
PP
29use subs @EXPORT_OK;
30
137443ea 31bootstrap Opcode $XS_VERSION;
6badd1a5
PP
32
33_init_optags();
34
68dc0745 35sub ops_to_opset { opset @_ } # alias for old name
6badd1a5
PP
36
37sub opset_to_hex ($) {
38 return "(invalid opset)" unless verify_opset($_[0]);
39 unpack("h*",$_[0]);
40}
41
42sub opdump (;$) {
43 my $pat = shift;
44 # handy utility: perl -MOpcode=opdump -e 'opdump File'
45 foreach(opset_to_ops(full_opset)) {
46 my $op = sprintf " %12s %s\n", $_, opdesc($_);
47 next if defined $pat and $op !~ m/$pat/i;
48 print $op;
49 }
50}
51
52
53
54sub _init_optags {
55 my(%all, %seen);
56 @all{opset_to_ops(full_opset)} = (); # keys only
57
7a57407b 58 local($_);
6badd1a5
PP
59 local($/) = "\n=cut"; # skip to optags definition section
60 <DATA>;
61 $/ = "\n="; # now read in 'pod section' chunks
62 while(<DATA>) {
63 next unless m/^item\s+(:\w+)/;
64 my $tag = $1;
65
66 # Split into lines, keep only indented lines
67 my @lines = grep { m/^\s/ } split(/\n/);
68 foreach (@lines) { s/--.*// } # delete comments
69 my @ops = map { split ' ' } @lines; # get op words
70
71 foreach(@ops) {
72 warn "$tag - $_ already tagged in $seen{$_}\n" if $seen{$_};
73 $seen{$_} = $tag;
74 delete $all{$_};
75 }
76 # opset will croak on invalid names
77 define_optag($tag, opset(@ops));
78 }
79 close(DATA);
80 warn "Untagged opnames: ".join(' ',keys %all)."\n" if %all;
81}
82
83
841;
85
86__DATA__
87
88=head1 NAME
89
90Opcode - Disable named opcodes when compiling perl code
91
92=head1 SYNOPSIS
93
94 use Opcode;
95
96
97=head1 DESCRIPTION
98
99Perl code is always compiled into an internal format before execution.
100
101Evaluating perl code (e.g. via "eval" or "do 'file'") causes
102the code to be compiled into an internal format and then,
103provided there was no error in the compilation, executed.
104The internal format is based on many distinct I<opcodes>.
105
106By default no opmask is in effect and any code can be compiled.
107
108The Opcode module allow you to define an I<operator mask> to be in
109effect when perl I<next> compiles any code. Attempting to compile code
110which contains a masked opcode will cause the compilation to fail
111with an error. The code will not be executed.
112
113=head1 NOTE
114
115The Opcode module is not usually used directly. See the ops pragma and
116Safe modules for more typical uses.
117
118=head1 WARNING
119
120The authors make B<no warranty>, implied or otherwise, about the
121suitability of this software for safety or security purposes.
122
123The authors shall not in any case be liable for special, incidental,
124consequential, indirect or other similar damages arising from the use
125of this software.
126
127Your mileage will vary. If in any doubt B<do not use it>.
128
129
130=head1 Operator Names and Operator Lists
131
132The canonical list of operator names is the contents of the array
133op_name defined and initialised in file F<opcode.h> of the Perl
134source distribution (and installed into the perl library).
135
136Each operator has both a terse name (its opname) and a more verbose or
137recognisable descriptive name. The opdesc function can be used to
138return a list of descriptions for a list of operators.
139
140Many of the functions and methods listed below take a list of
141operators as parameters. Most operator lists can be made up of several
142types of element. Each element can be one of
143
144=over 8
145
146=item an operator name (opname)
147
148Operator names are typically small lowercase words like enterloop,
149leaveloop, last, next, redo etc. Sometimes they are rather cryptic
150like gv2cv, i_ncmp and ftsvtx.
151
152=item an operator tag name (optag)
153
154Operator tags can be used to refer to groups (or sets) of operators.
155Tag names always being with a colon. The Opcode module defines several
156optags and the user can define others using the define_optag function.
157
158=item a negated opname or optag
159
160An opname or optag can be prefixed with an exclamation mark, e.g., !mkdir.
161Negating an opname or optag means remove the corresponding ops from the
162accumulated set of ops at that point.
163
164=item an operator set (opset)
165
166An I<opset> as a binary string of approximately 43 bytes which holds a
167set or zero or more operators.
168
169The opset and opset_to_ops functions can be used to convert from
170a list of operators to an opset and I<vice versa>.
171
172Wherever a list of operators can be given you can use one or more opsets.
173See also Manipulating Opsets below.
174
175=back
176
177
178=head1 Opcode Functions
179
180The Opcode package contains functions for manipulating operator names
181tags and sets. All are available for export by the package.
182
183=over 8
184
185=item opcodes
186
187In a scalar context opcodes returns the number of opcodes in this
188version of perl (around 340 for perl5.002).
189
190In a list context it returns a list of all the operator names.
191(Not yet implemented, use @names = opset_to_ops(full_opset).)
192
193=item opset (OP, ...)
194
195Returns an opset containing the listed operators.
196
197=item opset_to_ops (OPSET)
198
199Returns a list of operator names corresponding to those operators in
200the set.
201
202=item opset_to_hex (OPSET)
203
204Returns a string representation of an opset. Can be handy for debugging.
205
206=item full_opset
207
208Returns an opset which includes all operators.
209
210=item empty_opset
211
212Returns an opset which contains no operators.
213
214=item invert_opset (OPSET)
215
216Returns an opset which is the inverse set of the one supplied.
217
218=item verify_opset (OPSET, ...)
219
220Returns true if the supplied opset looks like a valid opset (is the
221right length etc) otherwise it returns false. If an optional second
222parameter is true then verify_opset will croak on an invalid opset
223instead of returning false.
224
225Most of the other Opcode functions call verify_opset automatically
226and will croak if given an invalid opset.
227
228=item define_optag (OPTAG, OPSET)
229
230Define OPTAG as a symbolic name for OPSET. Optag names always start
231with a colon C<:>.
232
233The optag name used must not be defined already (define_optag will
234croak if it is already defined). Optag names are global to the perl
235process and optag definitions cannot be altered or deleted once
236defined.
237
238It is strongly recommended that applications using Opcode should use a
239leading capital letter on their tag names since lowercase names are
240reserved for use by the Opcode module. If using Opcode within a module
241you should prefix your tags names with the name of your module to
242ensure uniqueness and thus avoid clashes with other modules.
243
244=item opmask_add (OPSET)
245
246Adds the supplied opset to the current opmask. Note that there is
247currently I<no> mechanism for unmasking ops once they have been masked.
248This is intentional.
249
250=item opmask
251
252Returns an opset corresponding to the current opmask.
253
254=item opdesc (OP, ...)
255
256This takes a list of operator names and returns the corresponding list
257of operator descriptions.
258
259=item opdump (PAT)
260
261Dumps to STDOUT a two column list of op names and op descriptions.
262If an optional pattern is given then only lines which match the
263(case insensitive) pattern will be output.
264
265It's designed to be used as a handy command line utility:
266
267 perl -MOpcode=opdump -e opdump
268 perl -MOpcode=opdump -e 'opdump Eval'
269
270=back
271
272=head1 Manipulating Opsets
273
274Opsets may be manipulated using the perl bit vector operators & (and), | (or),
275^ (xor) and ~ (negate/invert).
276
277However you should never rely on the numerical position of any opcode
278within the opset. In other words both sides of a bit vector operator
279should be opsets returned from Opcode functions.
280
281Also, since the number of opcodes in your current version of perl might
282not be an exact multiple of eight, there may be unused bits in the last
283byte of an upset. This should not cause any problems (Opcode functions
284ignore those extra bits) but it does mean that using the ~ operator
285will typically not produce the same 'physical' opset 'string' as the
286invert_opset function.
287
288
289=head1 TO DO (maybe)
290
291 $bool = opset_eq($opset1, $opset2) true if opsets are logically eqiv
292
293 $yes = opset_can($opset, @ops) true if $opset has all @ops set
294
295 @diff = opset_diff($opset1, $opset2) => ('foo', '!bar', ...)
296
297=cut
298
299# the =cut above is used by _init_optags() to get here quickly
300
301=head1 Predefined Opcode Tags
302
303=over 5
304
305=item :base_core
306
307 null stub scalar pushmark wantarray const defined undef
308
309 rv2sv sassign
310
311 rv2av aassign aelem aelemfast aslice av2arylen
312
313 rv2hv helem hslice each values keys exists delete
314
315 preinc i_preinc predec i_predec postinc i_postinc postdec i_postdec
316 int hex oct abs pow multiply i_multiply divide i_divide
317 modulo i_modulo add i_add subtract i_subtract
318
319 left_shift right_shift bit_and bit_xor bit_or negate i_negate
320 not complement
321
322 lt i_lt gt i_gt le i_le ge i_ge eq i_eq ne i_ne ncmp i_ncmp
323 slt sgt sle sge seq sne scmp
324
325 substr vec stringify study pos length index rindex ord chr
326
327 ucfirst lcfirst uc lc quotemeta trans chop schop chomp schomp
328
329 match split
330
331 list lslice splice push pop shift unshift reverse
332
333 cond_expr flip flop andassign orassign and or xor
334
335 warn die lineseq nextstate unstack scope enter leave
336
337 rv2cv anoncode prototype
338
339 entersub leavesub return method -- XXX loops via recursion?
340
341 leaveeval -- needed for Safe to operate, is safe without entereval
342
343=item :base_mem
344
345These memory related ops are not included in :base_core because they
346can easily be used to implement a resource attack (e.g., consume all
347available memory).
348
349 concat repeat join range
350
351 anonlist anonhash
352
353Note that despite the existance of this optag a memory resource attack
354may still be possible using only :base_core ops.
355
356Disabling these ops is a I<very> heavy handed way to attempt to prevent
357a memory resource attack. It's probable that a specific memory limit
358mechanism will be added to perl in the near future.
359
360=item :base_loop
361
362These loop ops are not included in :base_core because they can easily be
363used to implement a resource attack (e.g., consume all available CPU time).
364
365 grepstart grepwhile
366 mapstart mapwhile
367 enteriter iter
368 enterloop leaveloop
369 last next redo
370 goto
371
372=item :base_io
373
374These ops enable I<filehandle> (rather than filename) based input and
375output. These are safe on the assumption that only pre-existing
376filehandles are available for use. To create new filehandles other ops
377such as open would need to be enabled.
378
379 readline rcatline getc read
380
381 formline enterwrite leavewrite
382
96e4d5b1
PP
383 print sysread syswrite send recv
384
8903cb82 385 eof tell seek sysseek
6badd1a5
PP
386
387 readdir telldir seekdir rewinddir
388
389=item :base_orig
390
391These are a hotchpotch of opcodes still waiting to be considered
392
393 gvsv gv gelem
394
395 padsv padav padhv padany
396
397 rv2gv refgen srefgen ref
398
399 bless -- could be used to change ownership of objects (reblessing)
400
6badd1a5
PP
401 pushre regcmaybe regcomp subst substcont
402
403 sprintf prtf -- can core dump
404
405 crypt
406
407 tie untie
408
409 dbmopen dbmclose
410 sselect select
411 pipe_op sockpair
412
413 getppid getpgrp setpgrp getpriority setpriority localtime gmtime
414
415 entertry leavetry -- can be used to 'hide' fatal errors
416
417=item :base_math
418
419These ops are not included in :base_core because of the risk of them being
420used to generate floating point exceptions (which would have to be caught
421using a $SIG{FPE} handler).
422
423 atan2 sin cos exp log sqrt
424
425These ops are not included in :base_core because they have an effect
426beyond the scope of the compartment.
427
428 rand srand
429
1f5895a1
MB
430=item :base_thread
431
554b3eca 432These ops are related to multi-threading.
1f5895a1 433
554b3eca 434 lock specific
1f5895a1 435
6badd1a5
PP
436=item :default
437
438A handy tag name for a I<reasonable> default set of ops. (The current ops
439allowed are unstable while development continues. It will change.)
440
5ddb6eab 441 :base_core :base_mem :base_loop :base_io :base_orig :base_thread
6badd1a5
PP
442
443If safety matters to you (and why else would you be using the Opcode module?)
444then you should not rely on the definition of this, or indeed any other, optag!
445
446
447=item :filesys_read
448
449 stat lstat readlink
450
451 ftatime ftblk ftchr ftctime ftdir fteexec fteowned fteread
452 ftewrite ftfile ftis ftlink ftmtime ftpipe ftrexec ftrowned
453 ftrread ftsgid ftsize ftsock ftsuid fttty ftzero ftrwrite ftsvtx
454
455 fttext ftbinary
456
457 fileno
458
459=item :sys_db
460
461 ghbyname ghbyaddr ghostent shostent ehostent -- hosts
462 gnbyname gnbyaddr gnetent snetent enetent -- networks
463 gpbyname gpbynumber gprotoent sprotoent eprotoent -- protocols
464 gsbyname gsbyport gservent sservent eservent -- services
465
466 gpwnam gpwuid gpwent spwent epwent getlogin -- users
467 ggrnam ggrgid ggrent sgrent egrent -- groups
468
469=item :browse
470
471A handy tag name for a I<reasonable> default set of ops beyond the
472:default optag. Like :default (and indeed all the other optags) its
473current definition is unstable while development continues. It will change.
474
475The :browse tag represents the next step beyond :default. It it a
476superset of the :default ops and adds :filesys_read the :sys_db.
477The intent being that scripts can access more (possibly sensitive)
478information about your system but not be able to change it.
479
480 :default :filesys_read :sys_db
481
482=item :filesys_open
483
484 sysopen open close
485 umask binmode
486
487 open_dir closedir -- other dir ops are in :base_io
488
489=item :filesys_write
490
491 link unlink rename symlink truncate
492
493 mkdir rmdir
494
495 utime chmod chown
496
497 fcntl -- not strictly filesys related, but possibly as dangerous?
498
499=item :subprocess
500
501 backtick system
502
503 fork
504
505 wait waitpid
506
f812a825
PP
507 glob -- access to Cshell via <`rm *`>
508
6badd1a5
PP
509=item :ownprocess
510
511 exec exit kill
512
513 time tms -- could be used for timing attacks (paranoid?)
514
515=item :others
516
517This tag holds groups of assorted specialist opcodes that don't warrant
518having optags defined for them.
519
520SystemV Interprocess Communications:
521
522 msgctl msgget msgrcv msgsnd
523
524 semctl semget semop
525
526 shmctl shmget shmread shmwrite
527
528=item :still_to_be_decided
529
530 chdir
531 flock ioctl
532
533 socket getpeername ssockopt
534 bind connect listen accept shutdown gsockopt getsockname
535
536 sleep alarm -- changes global timer state and signal handling
537 sort -- assorted problems including core dumps
538 tied -- can be used to access object implementing a tie
539 pack unpack -- can be used to create/use memory pointers
540
541 entereval -- can be used to hide code from initial compile
542 require dofile
543
544 caller -- get info about calling environment and args
545
546 reset
547
548 dbstate -- perl -d version of nextstate(ment) opcode
549
550=item :dangerous
551
552This tag is simply a bucket for opcodes that are unlikely to be used via
553a tag name but need to be tagged for completness and documentation.
554
555 syscall dump chroot
556
557
558=back
559
560=head1 SEE ALSO
561
562ops(3) -- perl pragma interface to Opcode module.
563
564Safe(3) -- Opcode and namespace limited execution compartments
565
566=head1 AUTHORS
567
568Originally designed and implemented by Malcolm Beattie,
569mbeattie@sable.ox.ac.uk as part of Safe version 1.
570
571Split out from Safe module version 1, named opcode tags and other
7a57407b 572changes added by Tim Bunce E<lt>F<Tim.Bunce@ig.co.uk>E<gt>.
6badd1a5
PP
573
574=cut
575