Commit | Line | Data |
6badd1a5 |
1 | package Opcode; |
2 | |
3 | require 5.002; |
4 | |
5 | use vars qw($VERSION @ISA @EXPORT_OK); |
6 | |
7 | $VERSION = "1.01"; |
8 | |
9 | use strict; |
10 | use Carp; |
11 | use Exporter (); |
12 | use DynaLoader (); |
13 | @ISA = qw(Exporter DynaLoader); |
14 | |
15 | BEGIN { |
16 | @EXPORT_OK = qw( |
17 | opset ops_to_opset |
18 | opset_to_ops opset_to_hex invert_opset |
19 | empty_opset full_opset |
20 | opdesc opcodes opmask define_optag |
21 | opmask_add verify_opset opdump |
22 | ); |
23 | } |
24 | |
25 | use subs @EXPORT_OK; |
26 | |
27 | bootstrap Opcode $VERSION; |
28 | |
29 | _init_optags(); |
30 | |
31 | |
32 | *ops_to_opset = \&opset; # alias for old name |
33 | |
34 | |
35 | sub opset_to_hex ($) { |
36 | return "(invalid opset)" unless verify_opset($_[0]); |
37 | unpack("h*",$_[0]); |
38 | } |
39 | |
40 | sub opdump (;$) { |
41 | my $pat = shift; |
42 | # handy utility: perl -MOpcode=opdump -e 'opdump File' |
43 | foreach(opset_to_ops(full_opset)) { |
44 | my $op = sprintf " %12s %s\n", $_, opdesc($_); |
45 | next if defined $pat and $op !~ m/$pat/i; |
46 | print $op; |
47 | } |
48 | } |
49 | |
50 | |
51 | |
52 | sub _init_optags { |
53 | my(%all, %seen); |
54 | @all{opset_to_ops(full_opset)} = (); # keys only |
55 | |
56 | local($/) = "\n=cut"; # skip to optags definition section |
57 | <DATA>; |
58 | $/ = "\n="; # now read in 'pod section' chunks |
59 | while(<DATA>) { |
60 | next unless m/^item\s+(:\w+)/; |
61 | my $tag = $1; |
62 | |
63 | # Split into lines, keep only indented lines |
64 | my @lines = grep { m/^\s/ } split(/\n/); |
65 | foreach (@lines) { s/--.*// } # delete comments |
66 | my @ops = map { split ' ' } @lines; # get op words |
67 | |
68 | foreach(@ops) { |
69 | warn "$tag - $_ already tagged in $seen{$_}\n" if $seen{$_}; |
70 | $seen{$_} = $tag; |
71 | delete $all{$_}; |
72 | } |
73 | # opset will croak on invalid names |
74 | define_optag($tag, opset(@ops)); |
75 | } |
76 | close(DATA); |
77 | warn "Untagged opnames: ".join(' ',keys %all)."\n" if %all; |
78 | } |
79 | |
80 | |
81 | 1; |
82 | |
83 | __DATA__ |
84 | |
85 | =head1 NAME |
86 | |
87 | Opcode - Disable named opcodes when compiling perl code |
88 | |
89 | =head1 SYNOPSIS |
90 | |
91 | use Opcode; |
92 | |
93 | |
94 | =head1 DESCRIPTION |
95 | |
96 | Perl code is always compiled into an internal format before execution. |
97 | |
98 | Evaluating perl code (e.g. via "eval" or "do 'file'") causes |
99 | the code to be compiled into an internal format and then, |
100 | provided there was no error in the compilation, executed. |
101 | The internal format is based on many distinct I<opcodes>. |
102 | |
103 | By default no opmask is in effect and any code can be compiled. |
104 | |
105 | The Opcode module allow you to define an I<operator mask> to be in |
106 | effect when perl I<next> compiles any code. Attempting to compile code |
107 | which contains a masked opcode will cause the compilation to fail |
108 | with an error. The code will not be executed. |
109 | |
110 | =head1 NOTE |
111 | |
112 | The Opcode module is not usually used directly. See the ops pragma and |
113 | Safe modules for more typical uses. |
114 | |
115 | =head1 WARNING |
116 | |
117 | The authors make B<no warranty>, implied or otherwise, about the |
118 | suitability of this software for safety or security purposes. |
119 | |
120 | The authors shall not in any case be liable for special, incidental, |
121 | consequential, indirect or other similar damages arising from the use |
122 | of this software. |
123 | |
124 | Your mileage will vary. If in any doubt B<do not use it>. |
125 | |
126 | |
127 | =head1 Operator Names and Operator Lists |
128 | |
129 | The canonical list of operator names is the contents of the array |
130 | op_name defined and initialised in file F<opcode.h> of the Perl |
131 | source distribution (and installed into the perl library). |
132 | |
133 | Each operator has both a terse name (its opname) and a more verbose or |
134 | recognisable descriptive name. The opdesc function can be used to |
135 | return a list of descriptions for a list of operators. |
136 | |
137 | Many of the functions and methods listed below take a list of |
138 | operators as parameters. Most operator lists can be made up of several |
139 | types of element. Each element can be one of |
140 | |
141 | =over 8 |
142 | |
143 | =item an operator name (opname) |
144 | |
145 | Operator names are typically small lowercase words like enterloop, |
146 | leaveloop, last, next, redo etc. Sometimes they are rather cryptic |
147 | like gv2cv, i_ncmp and ftsvtx. |
148 | |
149 | =item an operator tag name (optag) |
150 | |
151 | Operator tags can be used to refer to groups (or sets) of operators. |
152 | Tag names always being with a colon. The Opcode module defines several |
153 | optags and the user can define others using the define_optag function. |
154 | |
155 | =item a negated opname or optag |
156 | |
157 | An opname or optag can be prefixed with an exclamation mark, e.g., !mkdir. |
158 | Negating an opname or optag means remove the corresponding ops from the |
159 | accumulated set of ops at that point. |
160 | |
161 | =item an operator set (opset) |
162 | |
163 | An I<opset> as a binary string of approximately 43 bytes which holds a |
164 | set or zero or more operators. |
165 | |
166 | The opset and opset_to_ops functions can be used to convert from |
167 | a list of operators to an opset and I<vice versa>. |
168 | |
169 | Wherever a list of operators can be given you can use one or more opsets. |
170 | See also Manipulating Opsets below. |
171 | |
172 | =back |
173 | |
174 | |
175 | =head1 Opcode Functions |
176 | |
177 | The Opcode package contains functions for manipulating operator names |
178 | tags and sets. All are available for export by the package. |
179 | |
180 | =over 8 |
181 | |
182 | =item opcodes |
183 | |
184 | In a scalar context opcodes returns the number of opcodes in this |
185 | version of perl (around 340 for perl5.002). |
186 | |
187 | In a list context it returns a list of all the operator names. |
188 | (Not yet implemented, use @names = opset_to_ops(full_opset).) |
189 | |
190 | =item opset (OP, ...) |
191 | |
192 | Returns an opset containing the listed operators. |
193 | |
194 | =item opset_to_ops (OPSET) |
195 | |
196 | Returns a list of operator names corresponding to those operators in |
197 | the set. |
198 | |
199 | =item opset_to_hex (OPSET) |
200 | |
201 | Returns a string representation of an opset. Can be handy for debugging. |
202 | |
203 | =item full_opset |
204 | |
205 | Returns an opset which includes all operators. |
206 | |
207 | =item empty_opset |
208 | |
209 | Returns an opset which contains no operators. |
210 | |
211 | =item invert_opset (OPSET) |
212 | |
213 | Returns an opset which is the inverse set of the one supplied. |
214 | |
215 | =item verify_opset (OPSET, ...) |
216 | |
217 | Returns true if the supplied opset looks like a valid opset (is the |
218 | right length etc) otherwise it returns false. If an optional second |
219 | parameter is true then verify_opset will croak on an invalid opset |
220 | instead of returning false. |
221 | |
222 | Most of the other Opcode functions call verify_opset automatically |
223 | and will croak if given an invalid opset. |
224 | |
225 | =item define_optag (OPTAG, OPSET) |
226 | |
227 | Define OPTAG as a symbolic name for OPSET. Optag names always start |
228 | with a colon C<:>. |
229 | |
230 | The optag name used must not be defined already (define_optag will |
231 | croak if it is already defined). Optag names are global to the perl |
232 | process and optag definitions cannot be altered or deleted once |
233 | defined. |
234 | |
235 | It is strongly recommended that applications using Opcode should use a |
236 | leading capital letter on their tag names since lowercase names are |
237 | reserved for use by the Opcode module. If using Opcode within a module |
238 | you should prefix your tags names with the name of your module to |
239 | ensure uniqueness and thus avoid clashes with other modules. |
240 | |
241 | =item opmask_add (OPSET) |
242 | |
243 | Adds the supplied opset to the current opmask. Note that there is |
244 | currently I<no> mechanism for unmasking ops once they have been masked. |
245 | This is intentional. |
246 | |
247 | =item opmask |
248 | |
249 | Returns an opset corresponding to the current opmask. |
250 | |
251 | =item opdesc (OP, ...) |
252 | |
253 | This takes a list of operator names and returns the corresponding list |
254 | of operator descriptions. |
255 | |
256 | =item opdump (PAT) |
257 | |
258 | Dumps to STDOUT a two column list of op names and op descriptions. |
259 | If an optional pattern is given then only lines which match the |
260 | (case insensitive) pattern will be output. |
261 | |
262 | It's designed to be used as a handy command line utility: |
263 | |
264 | perl -MOpcode=opdump -e opdump |
265 | perl -MOpcode=opdump -e 'opdump Eval' |
266 | |
267 | =back |
268 | |
269 | =head1 Manipulating Opsets |
270 | |
271 | Opsets may be manipulated using the perl bit vector operators & (and), | (or), |
272 | ^ (xor) and ~ (negate/invert). |
273 | |
274 | However you should never rely on the numerical position of any opcode |
275 | within the opset. In other words both sides of a bit vector operator |
276 | should be opsets returned from Opcode functions. |
277 | |
278 | Also, since the number of opcodes in your current version of perl might |
279 | not be an exact multiple of eight, there may be unused bits in the last |
280 | byte of an upset. This should not cause any problems (Opcode functions |
281 | ignore those extra bits) but it does mean that using the ~ operator |
282 | will typically not produce the same 'physical' opset 'string' as the |
283 | invert_opset function. |
284 | |
285 | |
286 | =head1 TO DO (maybe) |
287 | |
288 | $bool = opset_eq($opset1, $opset2) true if opsets are logically eqiv |
289 | |
290 | $yes = opset_can($opset, @ops) true if $opset has all @ops set |
291 | |
292 | @diff = opset_diff($opset1, $opset2) => ('foo', '!bar', ...) |
293 | |
294 | =cut |
295 | |
296 | # the =cut above is used by _init_optags() to get here quickly |
297 | |
298 | =head1 Predefined Opcode Tags |
299 | |
300 | =over 5 |
301 | |
302 | =item :base_core |
303 | |
304 | null stub scalar pushmark wantarray const defined undef |
305 | |
306 | rv2sv sassign |
307 | |
308 | rv2av aassign aelem aelemfast aslice av2arylen |
309 | |
310 | rv2hv helem hslice each values keys exists delete |
311 | |
312 | preinc i_preinc predec i_predec postinc i_postinc postdec i_postdec |
313 | int hex oct abs pow multiply i_multiply divide i_divide |
314 | modulo i_modulo add i_add subtract i_subtract |
315 | |
316 | left_shift right_shift bit_and bit_xor bit_or negate i_negate |
317 | not complement |
318 | |
319 | lt i_lt gt i_gt le i_le ge i_ge eq i_eq ne i_ne ncmp i_ncmp |
320 | slt sgt sle sge seq sne scmp |
321 | |
322 | substr vec stringify study pos length index rindex ord chr |
323 | |
324 | ucfirst lcfirst uc lc quotemeta trans chop schop chomp schomp |
325 | |
326 | match split |
327 | |
328 | list lslice splice push pop shift unshift reverse |
329 | |
330 | cond_expr flip flop andassign orassign and or xor |
331 | |
332 | warn die lineseq nextstate unstack scope enter leave |
333 | |
334 | rv2cv anoncode prototype |
335 | |
336 | entersub leavesub return method -- XXX loops via recursion? |
337 | |
338 | leaveeval -- needed for Safe to operate, is safe without entereval |
339 | |
340 | =item :base_mem |
341 | |
342 | These memory related ops are not included in :base_core because they |
343 | can easily be used to implement a resource attack (e.g., consume all |
344 | available memory). |
345 | |
346 | concat repeat join range |
347 | |
348 | anonlist anonhash |
349 | |
350 | Note that despite the existance of this optag a memory resource attack |
351 | may still be possible using only :base_core ops. |
352 | |
353 | Disabling these ops is a I<very> heavy handed way to attempt to prevent |
354 | a memory resource attack. It's probable that a specific memory limit |
355 | mechanism will be added to perl in the near future. |
356 | |
357 | =item :base_loop |
358 | |
359 | These loop ops are not included in :base_core because they can easily be |
360 | used to implement a resource attack (e.g., consume all available CPU time). |
361 | |
362 | grepstart grepwhile |
363 | mapstart mapwhile |
364 | enteriter iter |
365 | enterloop leaveloop |
366 | last next redo |
367 | goto |
368 | |
369 | =item :base_io |
370 | |
371 | These ops enable I<filehandle> (rather than filename) based input and |
372 | output. These are safe on the assumption that only pre-existing |
373 | filehandles are available for use. To create new filehandles other ops |
374 | such as open would need to be enabled. |
375 | |
376 | readline rcatline getc read |
377 | |
378 | formline enterwrite leavewrite |
379 | |
380 | print sysread syswrite send recv eof tell seek |
381 | |
382 | readdir telldir seekdir rewinddir |
383 | |
384 | =item :base_orig |
385 | |
386 | These are a hotchpotch of opcodes still waiting to be considered |
387 | |
388 | gvsv gv gelem |
389 | |
390 | padsv padav padhv padany |
391 | |
392 | rv2gv refgen srefgen ref |
393 | |
394 | bless -- could be used to change ownership of objects (reblessing) |
395 | |
396 | glob |
397 | |
398 | pushre regcmaybe regcomp subst substcont |
399 | |
400 | sprintf prtf -- can core dump |
401 | |
402 | crypt |
403 | |
404 | tie untie |
405 | |
406 | dbmopen dbmclose |
407 | sselect select |
408 | pipe_op sockpair |
409 | |
410 | getppid getpgrp setpgrp getpriority setpriority localtime gmtime |
411 | |
412 | entertry leavetry -- can be used to 'hide' fatal errors |
413 | |
414 | =item :base_math |
415 | |
416 | These ops are not included in :base_core because of the risk of them being |
417 | used to generate floating point exceptions (which would have to be caught |
418 | using a $SIG{FPE} handler). |
419 | |
420 | atan2 sin cos exp log sqrt |
421 | |
422 | These ops are not included in :base_core because they have an effect |
423 | beyond the scope of the compartment. |
424 | |
425 | rand srand |
426 | |
427 | =item :default |
428 | |
429 | A handy tag name for a I<reasonable> default set of ops. (The current ops |
430 | allowed are unstable while development continues. It will change.) |
431 | |
432 | :base_core :base_mem :base_loop :base_io :base_orig |
433 | |
434 | If safety matters to you (and why else would you be using the Opcode module?) |
435 | then you should not rely on the definition of this, or indeed any other, optag! |
436 | |
437 | |
438 | =item :filesys_read |
439 | |
440 | stat lstat readlink |
441 | |
442 | ftatime ftblk ftchr ftctime ftdir fteexec fteowned fteread |
443 | ftewrite ftfile ftis ftlink ftmtime ftpipe ftrexec ftrowned |
444 | ftrread ftsgid ftsize ftsock ftsuid fttty ftzero ftrwrite ftsvtx |
445 | |
446 | fttext ftbinary |
447 | |
448 | fileno |
449 | |
450 | =item :sys_db |
451 | |
452 | ghbyname ghbyaddr ghostent shostent ehostent -- hosts |
453 | gnbyname gnbyaddr gnetent snetent enetent -- networks |
454 | gpbyname gpbynumber gprotoent sprotoent eprotoent -- protocols |
455 | gsbyname gsbyport gservent sservent eservent -- services |
456 | |
457 | gpwnam gpwuid gpwent spwent epwent getlogin -- users |
458 | ggrnam ggrgid ggrent sgrent egrent -- groups |
459 | |
460 | =item :browse |
461 | |
462 | A handy tag name for a I<reasonable> default set of ops beyond the |
463 | :default optag. Like :default (and indeed all the other optags) its |
464 | current definition is unstable while development continues. It will change. |
465 | |
466 | The :browse tag represents the next step beyond :default. It it a |
467 | superset of the :default ops and adds :filesys_read the :sys_db. |
468 | The intent being that scripts can access more (possibly sensitive) |
469 | information about your system but not be able to change it. |
470 | |
471 | :default :filesys_read :sys_db |
472 | |
473 | =item :filesys_open |
474 | |
475 | sysopen open close |
476 | umask binmode |
477 | |
478 | open_dir closedir -- other dir ops are in :base_io |
479 | |
480 | =item :filesys_write |
481 | |
482 | link unlink rename symlink truncate |
483 | |
484 | mkdir rmdir |
485 | |
486 | utime chmod chown |
487 | |
488 | fcntl -- not strictly filesys related, but possibly as dangerous? |
489 | |
490 | =item :subprocess |
491 | |
492 | backtick system |
493 | |
494 | fork |
495 | |
496 | wait waitpid |
497 | |
498 | =item :ownprocess |
499 | |
500 | exec exit kill |
501 | |
502 | time tms -- could be used for timing attacks (paranoid?) |
503 | |
504 | =item :others |
505 | |
506 | This tag holds groups of assorted specialist opcodes that don't warrant |
507 | having optags defined for them. |
508 | |
509 | SystemV Interprocess Communications: |
510 | |
511 | msgctl msgget msgrcv msgsnd |
512 | |
513 | semctl semget semop |
514 | |
515 | shmctl shmget shmread shmwrite |
516 | |
517 | =item :still_to_be_decided |
518 | |
519 | chdir |
520 | flock ioctl |
521 | |
522 | socket getpeername ssockopt |
523 | bind connect listen accept shutdown gsockopt getsockname |
524 | |
525 | sleep alarm -- changes global timer state and signal handling |
526 | sort -- assorted problems including core dumps |
527 | tied -- can be used to access object implementing a tie |
528 | pack unpack -- can be used to create/use memory pointers |
529 | |
530 | entereval -- can be used to hide code from initial compile |
531 | require dofile |
532 | |
533 | caller -- get info about calling environment and args |
534 | |
535 | reset |
536 | |
537 | dbstate -- perl -d version of nextstate(ment) opcode |
538 | |
539 | =item :dangerous |
540 | |
541 | This tag is simply a bucket for opcodes that are unlikely to be used via |
542 | a tag name but need to be tagged for completness and documentation. |
543 | |
544 | syscall dump chroot |
545 | |
546 | |
547 | =back |
548 | |
549 | =head1 SEE ALSO |
550 | |
551 | ops(3) -- perl pragma interface to Opcode module. |
552 | |
553 | Safe(3) -- Opcode and namespace limited execution compartments |
554 | |
555 | =head1 AUTHORS |
556 | |
557 | Originally designed and implemented by Malcolm Beattie, |
558 | mbeattie@sable.ox.ac.uk as part of Safe version 1. |
559 | |
560 | Split out from Safe module version 1, named opcode tags and other |
561 | changes added by Tim Bunce <Tim.Bunce@ig.co.uk>. |
562 | |
563 | =cut |
564 | |