/src/binutils-gdb/gas/config/tc-i386.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* tc-i386.c -- Assemble code for the Intel 80386 |
2 | | Copyright (C) 1989-2025 Free Software Foundation, Inc. |
3 | | |
4 | | This file is part of GAS, the GNU Assembler. |
5 | | |
6 | | GAS is free software; you can redistribute it and/or modify |
7 | | it under the terms of the GNU General Public License as published by |
8 | | the Free Software Foundation; either version 3, or (at your option) |
9 | | any later version. |
10 | | |
11 | | GAS is distributed in the hope that it will be useful, |
12 | | but WITHOUT ANY WARRANTY; without even the implied warranty of |
13 | | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
14 | | GNU General Public License for more details. |
15 | | |
16 | | You should have received a copy of the GNU General Public License |
17 | | along with GAS; see the file COPYING. If not, write to the Free |
18 | | Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA |
19 | | 02110-1301, USA. */ |
20 | | |
21 | | /* Intel 80386 machine specific gas. |
22 | | Written by Eliot Dresselhaus (eliot@mgm.mit.edu). |
23 | | x86_64 support by Jan Hubicka (jh@suse.cz) |
24 | | VIA PadLock support by Michal Ludvig (mludvig@suse.cz) |
25 | | Bugs & suggestions are completely welcome. This is free software. |
26 | | Please help us make it better. */ |
27 | | |
28 | | #include "as.h" |
29 | | #include "safe-ctype.h" |
30 | | #include "subsegs.h" |
31 | | #include "dwarf2dbg.h" |
32 | | #include "dw2gencfi.h" |
33 | | #include "scfi.h" |
34 | | #include "gen-sframe.h" |
35 | | #include "sframe.h" |
36 | | #include "elf/x86-64.h" |
37 | | #include "opcodes/i386-init.h" |
38 | | #include "opcodes/i386-mnem.h" |
39 | | #include <limits.h> |
40 | | |
41 | | #ifndef INFER_ADDR_PREFIX |
42 | | #define INFER_ADDR_PREFIX 1 |
43 | | #endif |
44 | | |
45 | | #ifndef DEFAULT_ARCH |
46 | | #define DEFAULT_ARCH "i386" |
47 | | #endif |
48 | | |
49 | | #ifndef INLINE |
50 | | #if __GNUC__ >= 2 |
51 | | #define INLINE __inline__ |
52 | | #else |
53 | | #define INLINE |
54 | | #endif |
55 | | #endif |
56 | | |
57 | | /* Prefixes will be emitted in the order defined below. |
58 | | WAIT_PREFIX must be the first prefix since FWAIT is really is an |
59 | | instruction, and so must come before any prefixes. |
60 | | The preferred prefix order is SEG_PREFIX, ADDR_PREFIX, DATA_PREFIX, |
61 | | REP_PREFIX/HLE_PREFIX, LOCK_PREFIX. */ |
62 | 10 | #define WAIT_PREFIX 0 |
63 | 3.49k | #define SEG_PREFIX 1 |
64 | 157k | #define ADDR_PREFIX 2 |
65 | 9.52k | #define DATA_PREFIX 3 |
66 | 596 | #define REP_PREFIX 4 |
67 | 0 | #define HLE_PREFIX REP_PREFIX |
68 | 581 | #define BND_PREFIX REP_PREFIX |
69 | 2.92k | #define LOCK_PREFIX 5 |
70 | 175k | #define REX_PREFIX 6 /* must come last. */ |
71 | | #define MAX_PREFIXES 7 /* max prefixes per opcode */ |
72 | | |
73 | | /* we define the syntax here (modulo base,index,scale syntax) */ |
74 | 298k | #define REGISTER_PREFIX '%' |
75 | 44.3k | #define IMMEDIATE_PREFIX '$' |
76 | 88.8k | #define ABSOLUTE_PREFIX '*' |
77 | | |
78 | | /* these are the instruction mnemonic suffixes in AT&T syntax or |
79 | | memory operand size in Intel syntax. */ |
80 | 4.77k | #define WORD_MNEM_SUFFIX 'w' |
81 | 9.20k | #define BYTE_MNEM_SUFFIX 'b' |
82 | 50.8k | #define SHORT_MNEM_SUFFIX 's' |
83 | 74.7k | #define LONG_MNEM_SUFFIX 'l' |
84 | 281k | #define QWORD_MNEM_SUFFIX 'q' |
85 | | |
86 | 2.73M | #define END_OF_INSN '\0' |
87 | | |
88 | | #define OPERAND_TYPE_NONE { .bitfield = { .class = ClassNone } } |
89 | | |
90 | | /* This matches the C -> StaticRounding alias in the opcode table. */ |
91 | 512 | #define commutative staticrounding |
92 | | |
93 | | /* |
94 | | 'templates' is for grouping together 'template' structures for opcodes |
95 | | of the same name. This is only used for storing the insns in the grand |
96 | | ole hash table of insns. |
97 | | The templates themselves start at START and range up to (but not including) |
98 | | END. |
99 | | */ |
100 | | typedef struct |
101 | | { |
102 | | const insn_template *start; |
103 | | const insn_template *end; |
104 | | } |
105 | | templates; |
106 | | |
107 | | /* 386 operand encoding bytes: see 386 book for details of this. */ |
108 | | typedef struct |
109 | | { |
110 | | unsigned int regmem; /* codes register or memory operand */ |
111 | | unsigned int reg; /* codes register operand (or extended opcode) */ |
112 | | unsigned int mode; /* how to interpret regmem & reg */ |
113 | | } |
114 | | modrm_byte; |
115 | | |
116 | | /* x86-64 extension prefix. */ |
117 | | typedef int rex_byte; |
118 | | |
119 | | /* 386 opcode byte to code indirect addressing. */ |
120 | | typedef struct |
121 | | { |
122 | | unsigned base; |
123 | | unsigned index; |
124 | | unsigned scale; |
125 | | } |
126 | | sib_byte; |
127 | | |
128 | | /* x86 arch names, types and features */ |
129 | | typedef struct |
130 | | { |
131 | | const char *name; /* arch name */ |
132 | | unsigned int len:8; /* arch string length */ |
133 | | bool skip:1; /* show_arch should skip this. */ |
134 | | enum processor_type type; /* arch type */ |
135 | | enum { vsz_none, vsz_set, vsz_reset } vsz; /* vector size control */ |
136 | | i386_cpu_flags enable; /* cpu feature enable flags */ |
137 | | i386_cpu_flags disable; /* cpu feature disable flags */ |
138 | | } |
139 | | arch_entry; |
140 | | |
141 | | /* Modes for parse_insn() to operate in. */ |
142 | | enum parse_mode { |
143 | | parse_all, |
144 | | parse_prefix, |
145 | | parse_pseudo_prefix, |
146 | | }; |
147 | | |
148 | | static void update_code_flag (int, int); |
149 | | static void s_insn (int); |
150 | | static void s_noopt (int); |
151 | | static void set_code_flag (int); |
152 | | static void set_16bit_gcc_code_flag (int); |
153 | | static void set_intel_syntax (int); |
154 | | static void set_intel_mnemonic (int); |
155 | | static void set_allow_index_reg (int); |
156 | | static void set_check (int); |
157 | | static void set_cpu_arch (int); |
158 | | #ifdef TE_PE |
159 | | static void pe_directive_secrel (int); |
160 | | static void pe_directive_secidx (int); |
161 | | #endif |
162 | | static void signed_cons (int); |
163 | | static char *output_invalid (int c); |
164 | | static int i386_finalize_immediate (segT, expressionS *, i386_operand_type, |
165 | | const char *); |
166 | | static int i386_finalize_displacement (segT, expressionS *, i386_operand_type, |
167 | | const char *); |
168 | | static int i386_att_operand (char *); |
169 | | static int i386_intel_operand (char *, int); |
170 | | static int i386_intel_simplify (expressionS *); |
171 | | static int i386_intel_parse_name (const char *, expressionS *, enum expr_mode); |
172 | | static const reg_entry *parse_register (const char *, char **); |
173 | | static const char *parse_insn (const char *, char *, enum parse_mode); |
174 | | static char *parse_operands (char *, const char *); |
175 | | static void copy_operand (unsigned int, unsigned int); |
176 | | static void swap_operands (void); |
177 | | static void swap_2_operands (unsigned int, unsigned int); |
178 | | static enum i386_flag_code i386_addressing_mode (void); |
179 | | static void optimize_imm (void); |
180 | | static bool optimize_disp (const insn_template *t); |
181 | | static const insn_template *match_template (char); |
182 | | static int check_string (void); |
183 | | static int process_suffix (const insn_template *); |
184 | | static int check_byte_reg (void); |
185 | | static int check_long_reg (void); |
186 | | static int check_qword_reg (void); |
187 | | static int check_word_reg (void); |
188 | | static int finalize_imm (void); |
189 | | static int process_operands (void); |
190 | | static const reg_entry *build_modrm_byte (void); |
191 | | static void output_insn (const struct last_insn *); |
192 | | static void output_imm (fragS *, offsetT); |
193 | | static void output_disp (fragS *, offsetT); |
194 | | #ifdef OBJ_AOUT |
195 | | static void s_bss (int); |
196 | | #endif |
197 | | #ifdef OBJ_ELF |
198 | | static void handle_large_common (int small ATTRIBUTE_UNUSED); |
199 | | |
200 | | /* GNU_PROPERTY_X86_ISA_1_USED. */ |
201 | | static unsigned int x86_isa_1_used; |
202 | | /* GNU_PROPERTY_X86_FEATURE_2_USED. */ |
203 | | static unsigned int x86_feature_2_used; |
204 | | /* Generate x86 used ISA and feature properties. */ |
205 | | static unsigned int x86_used_note = DEFAULT_X86_USED_NOTE; |
206 | | #endif |
207 | | |
208 | | static const char *default_arch = DEFAULT_ARCH; |
209 | | |
210 | | /* parse_register() returns this when a register alias cannot be used. */ |
211 | | static const reg_entry bad_reg = { "<bad>", OPERAND_TYPE_NONE, 0, 0, |
212 | | { Dw2Inval, Dw2Inval } }; |
213 | | |
214 | | static const reg_entry *reg_eax; |
215 | | static const reg_entry *reg_ds; |
216 | | static const reg_entry *reg_es; |
217 | | static const reg_entry *reg_ss; |
218 | | static const reg_entry *reg_st0; |
219 | | static const reg_entry *reg_k0; |
220 | | |
221 | | /* VEX prefix. */ |
222 | | typedef struct |
223 | | { |
224 | | /* VEX prefix is either 2 byte or 3 byte. EVEX is 4 byte. */ |
225 | | unsigned char bytes[4]; |
226 | | unsigned int length; |
227 | | /* Destination or source register specifier. */ |
228 | | const reg_entry *register_specifier; |
229 | | } vex_prefix; |
230 | | |
231 | | /* 'md_assemble ()' gathers together information and puts it into a |
232 | | i386_insn. */ |
233 | | |
234 | | union i386_op |
235 | | { |
236 | | expressionS *disps; |
237 | | expressionS *imms; |
238 | | const reg_entry *regs; |
239 | | }; |
240 | | |
241 | | enum i386_error |
242 | | { |
243 | | no_error, /* Must be first. */ |
244 | | operand_size_mismatch, |
245 | | operand_type_mismatch, |
246 | | register_type_mismatch, |
247 | | number_of_operands_mismatch, |
248 | | invalid_instruction_suffix, |
249 | | bad_imm4, |
250 | | unsupported_with_intel_mnemonic, |
251 | | unsupported_syntax, |
252 | | unsupported_EGPR_for_addressing, |
253 | | unsupported_nf, |
254 | | unsupported, |
255 | | unsupported_on_arch, |
256 | | unsupported_64bit, |
257 | | no_vex_encoding, |
258 | | no_evex_encoding, |
259 | | invalid_sib_address, |
260 | | invalid_vsib_address, |
261 | | invalid_vector_register_set, |
262 | | invalid_tmm_register_set, |
263 | | invalid_dest_and_src_register_set, |
264 | | invalid_dest_register_set, |
265 | | invalid_pseudo_prefix, |
266 | | unsupported_vector_index_register, |
267 | | unsupported_broadcast, |
268 | | broadcast_needed, |
269 | | unsupported_masking, |
270 | | mask_not_on_destination, |
271 | | no_default_mask, |
272 | | unsupported_rc_sae, |
273 | | unsupported_vector_size, |
274 | | unsupported_rsp_register, |
275 | | internal_error, |
276 | | }; |
277 | | |
278 | | #ifdef OBJ_ELF |
279 | | enum x86_tls_error_type |
280 | | { |
281 | | x86_tls_error_continue, |
282 | | x86_tls_error_none, |
283 | | x86_tls_error_insn, |
284 | | x86_tls_error_opcode, |
285 | | x86_tls_error_sib, |
286 | | x86_tls_error_no_base_reg, |
287 | | x86_tls_error_require_no_base_index_reg, |
288 | | x86_tls_error_base_reg, |
289 | | x86_tls_error_index_ebx, |
290 | | x86_tls_error_eax, |
291 | | x86_tls_error_RegA, |
292 | | x86_tls_error_ebx, |
293 | | x86_tls_error_rip, |
294 | | x86_tls_error_dest_eax, |
295 | | x86_tls_error_dest_rdi, |
296 | | x86_tls_error_scale_factor, |
297 | | x86_tls_error_base_reg_size, |
298 | | x86_tls_error_dest_32bit_reg_size, |
299 | | x86_tls_error_dest_64bit_reg_size, |
300 | | x86_tls_error_dest_32bit_or_64bit_reg_size |
301 | | }; |
302 | | #endif |
303 | | |
304 | | struct _i386_insn |
305 | | { |
306 | | /* TM holds the template for the insn were currently assembling. */ |
307 | | insn_template tm; |
308 | | |
309 | | /* SUFFIX holds the instruction size suffix for byte, word, dword |
310 | | or qword, if given. */ |
311 | | char suffix; |
312 | | |
313 | | /* OPCODE_LENGTH holds the number of base opcode bytes. */ |
314 | | unsigned char opcode_length; |
315 | | |
316 | | /* OPERANDS gives the number of given operands. */ |
317 | | unsigned int operands; |
318 | | |
319 | | /* REG_OPERANDS, DISP_OPERANDS, MEM_OPERANDS, IMM_OPERANDS give the number |
320 | | of given register, displacement, memory operands and immediate |
321 | | operands. */ |
322 | | unsigned int reg_operands, disp_operands, mem_operands, imm_operands; |
323 | | |
324 | | /* TYPES [i] is the type (see above #defines) which tells us how to |
325 | | use OP[i] for the corresponding operand. */ |
326 | | i386_operand_type types[MAX_OPERANDS]; |
327 | | |
328 | | /* Displacement expression, immediate expression, or register for each |
329 | | operand. */ |
330 | | union i386_op op[MAX_OPERANDS]; |
331 | | |
332 | | /* Flags for operands. */ |
333 | | unsigned int flags[MAX_OPERANDS]; |
334 | 282 | #define Operand_PCrel 1 |
335 | 50.0k | #define Operand_Mem 2 |
336 | 0 | #define Operand_Signed 4 /* .insn only */ |
337 | | |
338 | | /* Relocation type for operand */ |
339 | | enum bfd_reloc_code_real reloc[MAX_OPERANDS]; |
340 | | |
341 | | /* BASE_REG, INDEX_REG, and LOG2_SCALE_FACTOR are used to encode |
342 | | the base index byte below. */ |
343 | | const reg_entry *base_reg; |
344 | | const reg_entry *index_reg; |
345 | | unsigned int log2_scale_factor; |
346 | | |
347 | | /* SEG gives the seg_entries of this insn. They are zero unless |
348 | | explicit segment overrides are given. */ |
349 | | const reg_entry *seg[2]; |
350 | | |
351 | | /* PREFIX holds all the given prefix opcodes (usually null). |
352 | | PREFIXES is the number of prefix opcodes. */ |
353 | | unsigned int prefixes; |
354 | | unsigned char prefix[MAX_PREFIXES]; |
355 | | |
356 | | /* .insn allows for reserved opcode spaces. */ |
357 | | unsigned char insn_opcode_space; |
358 | | |
359 | | /* .insn also allows (requires) specifying immediate size. */ |
360 | | unsigned char imm_bits[MAX_OPERANDS]; |
361 | | |
362 | | /* Register is in low 3 bits of opcode. */ |
363 | | bool short_form; |
364 | | |
365 | | /* The operand to a branch insn indicates an absolute branch. */ |
366 | | bool jumpabsolute; |
367 | | |
368 | | /* The operand to a branch insn indicates a far branch. */ |
369 | | bool far_branch; |
370 | | |
371 | | /* There is a memory operand of (%dx) which should be only used |
372 | | with input/output instructions. */ |
373 | | bool input_output_operand; |
374 | | |
375 | | /* Extended states. */ |
376 | | enum |
377 | | { |
378 | | /* Use MMX state. */ |
379 | | xstate_mmx = 1 << 0, |
380 | | /* Use XMM state. */ |
381 | | xstate_xmm = 1 << 1, |
382 | | /* Use YMM state. */ |
383 | | xstate_ymm = 1 << 2 | xstate_xmm, |
384 | | /* Use ZMM state. */ |
385 | | xstate_zmm = 1 << 3 | xstate_ymm, |
386 | | /* Use TMM state. */ |
387 | | xstate_tmm = 1 << 4, |
388 | | /* Use MASK state. */ |
389 | | xstate_mask = 1 << 5 |
390 | | } xstate; |
391 | | |
392 | | /* Has GOTPC or TLS relocation. */ |
393 | | bool has_gotpc_tls_reloc; |
394 | | |
395 | | /* Has relocation entry from the gotrel array. */ |
396 | | bool has_gotrel; |
397 | | |
398 | | /* RM and SIB are the modrm byte and the sib byte where the |
399 | | addressing modes of this insn are encoded. */ |
400 | | modrm_byte rm; |
401 | | rex_byte rex; |
402 | | rex_byte vrex; |
403 | | rex_byte rex2; |
404 | | sib_byte sib; |
405 | | vex_prefix vex; |
406 | | |
407 | | /* Masking attributes. |
408 | | |
409 | | The struct describes masking, applied to OPERAND in the instruction. |
410 | | REG is a pointer to the corresponding mask register. ZEROING tells |
411 | | whether merging or zeroing mask is used. */ |
412 | | struct Mask_Operation |
413 | | { |
414 | | const reg_entry *reg; |
415 | | unsigned int zeroing; |
416 | | /* The operand where this operation is associated. */ |
417 | | unsigned int operand; |
418 | | } mask; |
419 | | |
420 | | /* Rounding control and SAE attributes. */ |
421 | | struct RC_Operation |
422 | | { |
423 | | enum rc_type |
424 | | { |
425 | | rc_none = -1, |
426 | | rne, |
427 | | rd, |
428 | | ru, |
429 | | rz, |
430 | | saeonly |
431 | | } type; |
432 | | /* In Intel syntax the operand modifier form is supposed to be used, but |
433 | | we continue to accept the immediate forms as well. */ |
434 | | bool modifier; |
435 | | } rounding; |
436 | | |
437 | | /* Broadcasting attributes. |
438 | | |
439 | | The struct describes broadcasting, applied to OPERAND. TYPE is |
440 | | expresses the broadcast factor. */ |
441 | | struct Broadcast_Operation |
442 | | { |
443 | | /* Type of broadcast: {1to2}, {1to4}, {1to8}, {1to16} or {1to32}. */ |
444 | | unsigned int type; |
445 | | |
446 | | /* Index of broadcasted operand. */ |
447 | | unsigned int operand; |
448 | | |
449 | | /* Number of bytes to broadcast. */ |
450 | | unsigned int bytes; |
451 | | } broadcast; |
452 | | |
453 | | /* Compressed disp8*N attribute. */ |
454 | | unsigned int memshift; |
455 | | |
456 | | /* SCC = EVEX.[SC3,SC2,SC1,SC0]. */ |
457 | | unsigned int scc; |
458 | | |
459 | | /* Store 4 bits of EVEX.[OF,SF,ZF,CF]. */ |
460 | 0 | #define OSZC_CF 1 |
461 | 0 | #define OSZC_ZF 2 |
462 | 0 | #define OSZC_SF 4 |
463 | 0 | #define OSZC_OF 8 |
464 | | unsigned int oszc_flags; |
465 | | |
466 | | /* Invert the condition encoded in a base opcode. */ |
467 | | bool invert_cond; |
468 | | |
469 | | /* REP prefix. */ |
470 | | const char *rep_prefix; |
471 | | |
472 | | /* HLE prefix. */ |
473 | | const char *hle_prefix; |
474 | | |
475 | | /* Have BND prefix. */ |
476 | | const char *bnd_prefix; |
477 | | |
478 | | /* Have NOTRACK prefix. */ |
479 | | const char *notrack_prefix; |
480 | | |
481 | | /* Error message. */ |
482 | | enum i386_error error; |
483 | | }; |
484 | | |
485 | | typedef struct _i386_insn i386_insn; |
486 | | |
487 | | /* Pseudo-prefix recording state, separate from i386_insn. */ |
488 | | static struct pseudo_prefixes { |
489 | | /* How to encode instructions. */ |
490 | | enum { |
491 | | encoding_default = 0, |
492 | | encoding_vex, |
493 | | encoding_vex3, |
494 | | encoding_egpr, /* REX2 or EVEX. */ |
495 | | encoding_evex, |
496 | | encoding_evex512, |
497 | | encoding_error |
498 | | } encoding; |
499 | | |
500 | | /* Prefer load or store in encoding. */ |
501 | | enum { |
502 | | dir_encoding_default = 0, |
503 | | dir_encoding_load, |
504 | | dir_encoding_store, |
505 | | dir_encoding_swap |
506 | | } dir_encoding; |
507 | | |
508 | | /* Prefer 8bit, 16bit, 32bit displacement in encoding. */ |
509 | | enum { |
510 | | disp_encoding_default = 0, |
511 | | disp_encoding_8bit, |
512 | | disp_encoding_16bit, |
513 | | disp_encoding_32bit |
514 | | } disp_encoding; |
515 | | |
516 | | /* Exclude sign-extended 8bit immediate in encoding. */ |
517 | | bool no_imm8s; |
518 | | |
519 | | /* Prefer the REX byte in encoding. */ |
520 | | bool rex_encoding; |
521 | | |
522 | | /* Prefer the REX2 prefix in encoding. */ |
523 | | bool rex2_encoding; |
524 | | |
525 | | /* No CSPAZO flags update. */ |
526 | | bool has_nf; |
527 | | |
528 | | /* Disable instruction size optimization. */ |
529 | | bool no_optimize; |
530 | | } pp; |
531 | | |
532 | | /* Link RC type with corresponding string, that'll be looked for in |
533 | | asm. */ |
534 | | struct RC_name |
535 | | { |
536 | | enum rc_type type; |
537 | | const char *name; |
538 | | unsigned int len; |
539 | | }; |
540 | | |
541 | | static const struct RC_name RC_NamesTable[] = |
542 | | { |
543 | | { rne, STRING_COMMA_LEN ("rn-sae") }, |
544 | | { rd, STRING_COMMA_LEN ("rd-sae") }, |
545 | | { ru, STRING_COMMA_LEN ("ru-sae") }, |
546 | | { rz, STRING_COMMA_LEN ("rz-sae") }, |
547 | | { saeonly, STRING_COMMA_LEN ("sae") }, |
548 | | }; |
549 | | |
550 | | /* To be indexed by segment register number. */ |
551 | | static const unsigned char i386_seg_prefixes[] = { |
552 | | ES_PREFIX_OPCODE, |
553 | | CS_PREFIX_OPCODE, |
554 | | SS_PREFIX_OPCODE, |
555 | | DS_PREFIX_OPCODE, |
556 | | FS_PREFIX_OPCODE, |
557 | | GS_PREFIX_OPCODE |
558 | | }; |
559 | | |
560 | | /* List of chars besides those in app.c:symbol_chars that can start an |
561 | | operand. Used to prevent the scrubber eating vital white-space. */ |
562 | | const char extra_symbol_chars[] = "*%-([" |
563 | | #ifdef LEX_AT |
564 | | "@" |
565 | | #endif |
566 | | #ifdef LEX_QM |
567 | | "?" |
568 | | #endif |
569 | | ; |
570 | | |
571 | | #if (defined (OBJ_ELF) \ |
572 | | && !defined (TE_GNU) \ |
573 | | && !defined (TE_LINUX) \ |
574 | | && !defined (TE_Haiku) \ |
575 | | && !defined (TE_FreeBSD) \ |
576 | | && !defined (TE_DragonFly) \ |
577 | | && !defined (TE_NetBSD)) |
578 | | /* This array holds the chars that always start a comment. If the |
579 | | pre-processor is disabled, these aren't very useful. The option |
580 | | --divide will remove '/' from this list. */ |
581 | | const char *i386_comment_chars = "#/"; |
582 | | #define SVR4_COMMENT_CHARS 1 |
583 | | #define PREFIX_SEPARATOR '\\' |
584 | | |
585 | | #else |
586 | | const char *i386_comment_chars = "#"; |
587 | 629k | #define PREFIX_SEPARATOR '/' |
588 | | #endif |
589 | | |
590 | | /* This array holds the chars that only start a comment at the beginning of |
591 | | a line. If the line seems to have the form '# 123 filename' |
592 | | .line and .file directives will appear in the pre-processed output. |
593 | | Note that input_file.c hand checks for '#' at the beginning of the |
594 | | first line of the input file. This is because the compiler outputs |
595 | | #NO_APP at the beginning of its output. |
596 | | Also note that comments started like this one will always work if |
597 | | '/' isn't otherwise defined. */ |
598 | | const char line_comment_chars[] = "#/"; |
599 | | |
600 | | const char line_separator_chars[] = ";"; |
601 | | |
602 | | /* Chars that can be used to separate mant from exp in floating point |
603 | | nums. */ |
604 | | const char EXP_CHARS[] = "eE"; |
605 | | |
606 | | /* Chars that mean this number is a floating point constant |
607 | | As in 0f12.456 |
608 | | or 0d1.2345e12. */ |
609 | | const char FLT_CHARS[] = "fFdDxXhHbB"; |
610 | | |
611 | | /* Tables for lexical analysis. */ |
612 | | static char mnemonic_chars[256]; |
613 | | static char register_chars[256]; |
614 | | static char operand_chars[256]; |
615 | | |
616 | | /* Lexical macros. */ |
617 | 2.17M | #define is_operand_char(x) (operand_chars[(unsigned char) x]) |
618 | | #define is_register_char(x) (register_chars[(unsigned char) x]) |
619 | | |
620 | | /* All non-digit non-letter characters that may occur in an operand and |
621 | | which aren't already in extra_symbol_chars[]. */ |
622 | | static const char operand_special_chars[] = "$+,)._~/<>|&^!=:@]{}"; |
623 | | |
624 | | /* md_assemble() always leaves the strings it's passed unaltered. To |
625 | | effect this we maintain a stack of saved characters that we've smashed |
626 | | with '\0's (indicating end of strings for various sub-fields of the |
627 | | assembler instruction). */ |
628 | | static char save_stack[32]; |
629 | | static char *save_stack_p; |
630 | | #define END_STRING_AND_SAVE(s) \ |
631 | 83.3k | do { *save_stack_p++ = *(s); *(s) = '\0'; } while (0) |
632 | | #define RESTORE_END_STRING(s) \ |
633 | 83.3k | do { *(s) = *--save_stack_p; } while (0) |
634 | | |
635 | | /* The instruction we're assembling. */ |
636 | | static i386_insn i; |
637 | | |
638 | | /* Possible templates for current insn. */ |
639 | | static templates current_templates; |
640 | | |
641 | | /* Per instruction expressionS buffers: max displacements & immediates. */ |
642 | | static expressionS disp_expressions[MAX_MEMORY_OPERANDS]; |
643 | | static expressionS im_expressions[MAX_IMMEDIATE_OPERANDS]; |
644 | | |
645 | | /* Current operand we are working on. */ |
646 | | static int this_operand = -1; |
647 | | |
648 | | /* Are we processing a .insn directive? */ |
649 | 11.1k | #define dot_insn() (i.tm.mnem_off == MN__insn) |
650 | | |
651 | | enum i386_flag_code i386_flag_code; |
652 | 596k | #define flag_code i386_flag_code /* Permit to continue using original name. */ |
653 | | static unsigned int object_64bit; |
654 | | static unsigned int disallow_64bit_reloc; |
655 | | static int use_rela_relocations = 0; |
656 | | /* __tls_get_addr/___tls_get_addr symbol for TLS. */ |
657 | | static const char *tls_get_addr; |
658 | | |
659 | | #ifdef OBJ_ELF |
660 | | |
661 | | /* The ELF ABI to use. */ |
662 | | enum x86_elf_abi |
663 | | { |
664 | | I386_ABI, |
665 | | X86_64_ABI, |
666 | | X86_64_X32_ABI |
667 | | }; |
668 | | |
669 | | static enum x86_elf_abi x86_elf_abi = I386_ABI; |
670 | | #endif |
671 | | |
672 | | #if defined (TE_PE) || defined (TE_PEP) |
673 | | /* Use big object file format. */ |
674 | | static int use_big_obj = 0; |
675 | | #endif |
676 | | |
677 | | #ifdef OBJ_ELF |
678 | | /* 1 if generating code for a shared library. */ |
679 | | static int shared = 0; |
680 | | |
681 | | const unsigned int x86_sframe_cfa_sp_reg = REG_SP; |
682 | | /* The other CFA base register for SFrame stack trace info. */ |
683 | | const unsigned int x86_sframe_cfa_fp_reg = REG_FP; |
684 | | /* The return address register for SFrame stack trace info. For AMD64, RA |
685 | | tracking is not needed, but some directives like .cfi_undefined may use |
686 | | RA to indicate the outermost frame. */ |
687 | | const unsigned int x86_sframe_cfa_ra_reg = REG_RA; |
688 | | |
689 | | static ginsnS *x86_ginsn_new (const symbolS *, enum ginsn_gen_mode); |
690 | | #endif |
691 | | |
692 | | /* 1 for intel syntax, |
693 | | 0 if att syntax. */ |
694 | | static int intel_syntax = 0; |
695 | | |
696 | | static enum x86_64_isa |
697 | | { |
698 | | amd64 = 1, /* AMD64 ISA. */ |
699 | | intel64 /* Intel64 ISA. */ |
700 | | } isa64; |
701 | | |
702 | | /* 1 for intel mnemonic, |
703 | | 0 if att mnemonic. */ |
704 | | static int intel_mnemonic = !SYSV386_COMPAT; |
705 | | |
706 | | /* 1 if pseudo registers are permitted. */ |
707 | | static int allow_pseudo_reg = 0; |
708 | | |
709 | | /* 1 if register prefix % not required. */ |
710 | | static int allow_naked_reg = 0; |
711 | | |
712 | | /* 1 if the assembler should add BND prefix for all control-transferring |
713 | | instructions supporting it, even if this prefix wasn't specified |
714 | | explicitly. */ |
715 | | static int add_bnd_prefix = 0; |
716 | | |
717 | | /* 1 if pseudo index register, eiz/riz, is allowed . */ |
718 | | static int allow_index_reg = 0; |
719 | | |
720 | | /* 1 if the assembler should ignore LOCK prefix, even if it was |
721 | | specified explicitly. */ |
722 | | static int omit_lock_prefix = 0; |
723 | | |
724 | | /* 1 if the assembler should encode lfence, mfence, and sfence as |
725 | | "lock addl $0, (%{re}sp)". */ |
726 | | static int avoid_fence = 0; |
727 | | |
728 | | /* 1 if lfence should be inserted after every load. */ |
729 | | static int lfence_after_load = 0; |
730 | | |
731 | | /* Non-zero if lfence should be inserted before indirect branch. */ |
732 | | static enum lfence_before_indirect_branch_kind |
733 | | { |
734 | | lfence_branch_none = 0, |
735 | | lfence_branch_register, |
736 | | lfence_branch_memory, |
737 | | lfence_branch_all |
738 | | } |
739 | | lfence_before_indirect_branch; |
740 | | |
741 | | /* Non-zero if lfence should be inserted before ret. */ |
742 | | static enum lfence_before_ret_kind |
743 | | { |
744 | | lfence_before_ret_none = 0, |
745 | | lfence_before_ret_not, |
746 | | lfence_before_ret_or, |
747 | | lfence_before_ret_shl |
748 | | } |
749 | | lfence_before_ret; |
750 | | |
751 | | /* 1 if the assembler should generate relax relocations. */ |
752 | | |
753 | | static int generate_relax_relocations |
754 | | = DEFAULT_GENERATE_X86_RELAX_RELOCATIONS; |
755 | | |
756 | | /* 1 if the assembler should check tls relocation. */ |
757 | | static bool tls_check = DEFAULT_X86_TLS_CHECK; |
758 | | |
759 | | static enum check_kind |
760 | | { |
761 | | check_none = 0, |
762 | | check_warning, |
763 | | check_error |
764 | | } |
765 | | sse_check, operand_check = check_warning; |
766 | | |
767 | | /* Non-zero if branches should be aligned within power of 2 boundary. */ |
768 | | static int align_branch_power = 0; |
769 | | |
770 | | /* Types of branches to align. */ |
771 | | enum align_branch_kind |
772 | | { |
773 | | align_branch_none = 0, |
774 | | align_branch_jcc = 1, |
775 | | align_branch_fused = 2, |
776 | | align_branch_jmp = 3, |
777 | | align_branch_call = 4, |
778 | | align_branch_indirect = 5, |
779 | | align_branch_ret = 6 |
780 | | }; |
781 | | |
782 | | /* Type bits of branches to align. */ |
783 | | enum align_branch_bit |
784 | | { |
785 | | align_branch_jcc_bit = 1 << align_branch_jcc, |
786 | | align_branch_fused_bit = 1 << align_branch_fused, |
787 | | align_branch_jmp_bit = 1 << align_branch_jmp, |
788 | | align_branch_call_bit = 1 << align_branch_call, |
789 | | align_branch_indirect_bit = 1 << align_branch_indirect, |
790 | | align_branch_ret_bit = 1 << align_branch_ret |
791 | | }; |
792 | | |
793 | | static unsigned int align_branch = (align_branch_jcc_bit |
794 | | | align_branch_fused_bit |
795 | | | align_branch_jmp_bit); |
796 | | |
797 | | /* Types of condition jump used by macro-fusion. */ |
798 | | enum mf_jcc_kind |
799 | | { |
800 | | mf_jcc_jo = 0, /* base opcode 0x70 */ |
801 | | mf_jcc_jc, /* base opcode 0x72 */ |
802 | | mf_jcc_je, /* base opcode 0x74 */ |
803 | | mf_jcc_jna, /* base opcode 0x76 */ |
804 | | mf_jcc_js, /* base opcode 0x78 */ |
805 | | mf_jcc_jp, /* base opcode 0x7a */ |
806 | | mf_jcc_jl, /* base opcode 0x7c */ |
807 | | mf_jcc_jle, /* base opcode 0x7e */ |
808 | | }; |
809 | | |
810 | | /* Types of compare flag-modifying insntructions used by macro-fusion. */ |
811 | | enum mf_cmp_kind |
812 | | { |
813 | | mf_cmp_test_and, /* test/cmp */ |
814 | | mf_cmp_alu_cmp, /* add/sub/cmp */ |
815 | | mf_cmp_incdec /* inc/dec */ |
816 | | }; |
817 | | |
818 | | /* The maximum padding size for fused jcc. CMP like instruction can |
819 | | be 9 bytes and jcc can be 6 bytes. Leave room just in case for |
820 | | prefixes. */ |
821 | 28 | #define MAX_FUSED_JCC_PADDING_SIZE 20 |
822 | | |
823 | | /* The maximum number of prefixes added for an instruction. */ |
824 | | static unsigned int align_branch_prefix_size = 5; |
825 | | |
826 | | /* Optimization: |
827 | | 1. Clear the REX_W bit with register operand if possible. |
828 | | 2. Above plus use 128bit vector instruction to clear the full vector |
829 | | register. |
830 | | */ |
831 | | static int optimize = 0; |
832 | | |
833 | | /* Optimization: |
834 | | 1. Clear the REX_W bit with register operand if possible. |
835 | | 2. Above plus use 128bit vector instruction to clear the full vector |
836 | | register. |
837 | | 3. Above plus optimize "test{q,l,w} $imm8,%r{64,32,16}" to |
838 | | "testb $imm7,%r8". |
839 | | */ |
840 | | static int optimize_for_space = 0; |
841 | | |
842 | | /* Register prefix used for error message. */ |
843 | | static const char *register_prefix = "%"; |
844 | | |
845 | | /* Used in 16 bit gcc mode to add an l suffix to call, ret, enter, |
846 | | leave, push, and pop instructions so that gcc has the same stack |
847 | | frame as in 32 bit mode. */ |
848 | | static char stackop_size = '\0'; |
849 | | |
850 | | /* Non-zero to optimize code alignment. */ |
851 | | int optimize_align_code = 1; |
852 | | |
853 | | /* Non-zero to quieten some warnings. */ |
854 | | static int quiet_warnings = 0; |
855 | | |
856 | | /* Guard to avoid repeated warnings about non-16-bit code on 16-bit CPUs. */ |
857 | | static bool pre_386_16bit_warned; |
858 | | |
859 | | /* CPU name. */ |
860 | | static const char *cpu_arch_name = NULL; |
861 | | static char *cpu_sub_arch_name = NULL; |
862 | | |
863 | | /* CPU feature flags. */ |
864 | | i386_cpu_flags cpu_arch_flags = CPU_UNKNOWN_FLAGS; |
865 | | |
866 | | /* ISA extensions available in 64-bit mode only. */ |
867 | | static const i386_cpu_flags cpu_64_flags = CPU_ANY_64_FLAGS; |
868 | | |
869 | | /* If we have selected a cpu we are generating instructions for. */ |
870 | | static int cpu_arch_tune_set = 0; |
871 | | |
872 | | /* Cpu we are generating instructions for. */ |
873 | | enum processor_type cpu_arch_tune = PROCESSOR_UNKNOWN; |
874 | | |
875 | | /* CPU instruction set architecture used. */ |
876 | | enum processor_type cpu_arch_isa = PROCESSOR_UNKNOWN; |
877 | | |
878 | | /* CPU feature flags of instruction set architecture used. */ |
879 | | i386_cpu_flags cpu_arch_isa_flags; |
880 | | |
881 | | /* If set, conditional jumps are not automatically promoted to handle |
882 | | larger than a byte offset. */ |
883 | | static bool no_cond_jump_promotion = false; |
884 | | |
885 | | /* This will be set from an expression parser hook if there's any |
886 | | applicable operator involved in an expression. */ |
887 | | static enum { |
888 | | expr_operator_none, |
889 | | expr_operator_present, |
890 | | expr_large_value, |
891 | | } expr_mode; |
892 | | |
893 | | /* Encode SSE instructions with VEX prefix. */ |
894 | | static unsigned int sse2avx; |
895 | | |
896 | | /* Encode aligned vector move as unaligned vector move. */ |
897 | | static unsigned int use_unaligned_vector_move; |
898 | | |
899 | | /* Maximum permitted vector size. */ |
900 | 0 | #define VSZ128 0 |
901 | 7.16k | #define VSZ256 1 |
902 | 5.90k | #define VSZ512 2 |
903 | 63 | #define VSZ_DEFAULT VSZ512 |
904 | | static unsigned int vector_size = VSZ_DEFAULT; |
905 | | |
906 | | /* Encode scalar AVX instructions with specific vector length. */ |
907 | | static enum |
908 | | { |
909 | | vex128 = 0, |
910 | | vex256 |
911 | | } avxscalar; |
912 | | |
913 | | /* Encode VEX WIG instructions with specific vex.w. */ |
914 | | static enum |
915 | | { |
916 | | vexw0 = 0, |
917 | | vexw1 |
918 | | } vexwig; |
919 | | |
920 | | /* Encode scalar EVEX LIG instructions with specific vector length. */ |
921 | | static enum |
922 | | { |
923 | | evexl128 = 0, |
924 | | evexl256, |
925 | | evexl512 |
926 | | } evexlig; |
927 | | |
928 | | /* Encode EVEX WIG instructions with specific evex.w. */ |
929 | | static enum |
930 | | { |
931 | | evexw0 = 0, |
932 | | evexw1 |
933 | | } evexwig; |
934 | | |
935 | | /* Value to encode in EVEX RC bits, for SAE-only instructions. */ |
936 | | static enum rc_type evexrcig = rne; |
937 | | |
938 | | /* Pre-defined "_GLOBAL_OFFSET_TABLE_". */ |
939 | | static symbolS *GOT_symbol; |
940 | | |
941 | | /* The dwarf2 return column, adjusted for 32 or 64 bit. */ |
942 | | unsigned int x86_dwarf2_return_column; |
943 | | |
944 | | /* The dwarf2 data alignment, adjusted for 32 or 64 bit. */ |
945 | | int x86_cie_data_alignment; |
946 | | |
947 | | /* Interface to relax_segment. |
948 | | There are 3 major relax states for 386 jump insns because the |
949 | | different types of jumps add different sizes to frags when we're |
950 | | figuring out what sort of jump to choose to reach a given label. |
951 | | |
952 | | BRANCH_PADDING, BRANCH_PREFIX and FUSED_JCC_PADDING are used to align |
953 | | branches which are handled by md_estimate_size_before_relax() and |
954 | | i386_generic_table_relax_frag(). */ |
955 | | |
956 | | /* Types. */ |
957 | 0 | #define UNCOND_JUMP 0 |
958 | 0 | #define COND_JUMP 1 |
959 | 0 | #define COND_JUMP86 2 |
960 | 0 | #define BRANCH_PADDING 3 |
961 | 0 | #define BRANCH_PREFIX 4 |
962 | 0 | #define FUSED_JCC_PADDING 5 |
963 | | |
964 | | /* Sizes. */ |
965 | 162 | #define CODE16 1 |
966 | 250 | #define SMALL 0 |
967 | | #define SMALL16 (SMALL | CODE16) |
968 | 0 | #define BIG 2 |
969 | 0 | #define BIG16 (BIG | CODE16) |
970 | | |
971 | | #ifndef INLINE |
972 | | #ifdef __GNUC__ |
973 | | #define INLINE __inline__ |
974 | | #else |
975 | | #define INLINE |
976 | | #endif |
977 | | #endif |
978 | | |
979 | | #define ENCODE_RELAX_STATE(type, size) \ |
980 | 125 | ((relax_substateT) (((type) << 2) | (size))) |
981 | | #define TYPE_FROM_RELAX_STATE(s) \ |
982 | 0 | ((s) >> 2) |
983 | | #define DISP_SIZE_FROM_RELAX_STATE(s) \ |
984 | 0 | ((((s) & 3) == BIG ? 4 : (((s) & 3) == BIG16 ? 2 : 1))) |
985 | | |
986 | | /* This table is used by relax_frag to promote short jumps to long |
987 | | ones where necessary. SMALL (short) jumps may be promoted to BIG |
988 | | (32 bit long) ones, and SMALL16 jumps to BIG16 (16 bit long). We |
989 | | don't allow a short jump in a 32 bit code segment to be promoted to |
990 | | a 16 bit offset jump because it's slower (requires data size |
991 | | prefix), and doesn't work, unless the destination is in the bottom |
992 | | 64k of the code segment (The top 16 bits of eip are zeroed). */ |
993 | | |
994 | | const relax_typeS md_relax_table[] = |
995 | | { |
996 | | /* The fields are: |
997 | | 1) most positive reach of this state, |
998 | | 2) most negative reach of this state, |
999 | | 3) how many bytes this mode will have in the variable part of the frag |
1000 | | 4) which index into the table to try if we can't fit into this one. */ |
1001 | | |
1002 | | /* UNCOND_JUMP states. */ |
1003 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (UNCOND_JUMP, BIG)}, |
1004 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (UNCOND_JUMP, BIG16)}, |
1005 | | /* dword jmp adds 4 bytes to frag: |
1006 | | 0 extra opcode bytes, 4 displacement bytes. */ |
1007 | | {0, 0, 4, 0}, |
1008 | | /* word jmp adds 2 byte2 to frag: |
1009 | | 0 extra opcode bytes, 2 displacement bytes. */ |
1010 | | {0, 0, 2, 0}, |
1011 | | |
1012 | | /* COND_JUMP states. */ |
1013 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (COND_JUMP, BIG)}, |
1014 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (COND_JUMP, BIG16)}, |
1015 | | /* dword conditionals adds 5 bytes to frag: |
1016 | | 1 extra opcode byte, 4 displacement bytes. */ |
1017 | | {0, 0, 5, 0}, |
1018 | | /* word conditionals add 3 bytes to frag: |
1019 | | 1 extra opcode byte, 2 displacement bytes. */ |
1020 | | {0, 0, 3, 0}, |
1021 | | |
1022 | | /* COND_JUMP86 states. */ |
1023 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (COND_JUMP86, BIG)}, |
1024 | | {127 + 1, -128 + 1, 1, ENCODE_RELAX_STATE (COND_JUMP86, BIG16)}, |
1025 | | /* dword conditionals adds 5 bytes to frag: |
1026 | | 1 extra opcode byte, 4 displacement bytes. */ |
1027 | | {0, 0, 5, 0}, |
1028 | | /* word conditionals add 4 bytes to frag: |
1029 | | 1 displacement byte and a 3 byte long branch insn. */ |
1030 | | {0, 0, 4, 0} |
1031 | | }; |
1032 | | |
1033 | | #define ARCH(n, t, f, s) \ |
1034 | | { STRING_COMMA_LEN (#n), s, PROCESSOR_ ## t, vsz_none, CPU_ ## f ## _FLAGS, \ |
1035 | | CPU_NONE_FLAGS } |
1036 | | #define SUBARCH(n, e, d, s) \ |
1037 | | { STRING_COMMA_LEN (#n), s, PROCESSOR_NONE, vsz_none, CPU_ ## e ## _FLAGS, \ |
1038 | | CPU_ ## d ## _FLAGS } |
1039 | | #define VECARCH(n, e, d, v) \ |
1040 | | { STRING_COMMA_LEN (#n), false, PROCESSOR_NONE, vsz_ ## v, \ |
1041 | | CPU_ ## e ## _FLAGS, CPU_ ## d ## _FLAGS } |
1042 | | |
1043 | | static const arch_entry cpu_arch[] = |
1044 | | { |
1045 | | /* Do not replace the first two entries - i386_target_format() and |
1046 | | set_cpu_arch() rely on them being there in this order. */ |
1047 | | ARCH (generic32, GENERIC32, GENERIC32, false), |
1048 | | ARCH (generic64, GENERIC64, GENERIC64, false), |
1049 | | ARCH (i8086, UNKNOWN, NONE, false), |
1050 | | ARCH (i186, UNKNOWN, 186, false), |
1051 | | ARCH (i286, UNKNOWN, 286, false), |
1052 | | ARCH (i386, I386, 386, false), |
1053 | | ARCH (i486, I486, 486, false), |
1054 | | ARCH (i586, PENTIUM, 586, false), |
1055 | | ARCH (pentium, PENTIUM, 586, false), |
1056 | | ARCH (i686, I686, 686, false), |
1057 | | ARCH (pentiumpro, PENTIUMPRO, PENTIUMPRO, false), |
1058 | | ARCH (pentiumii, PENTIUMPRO, P2, false), |
1059 | | ARCH (pentiumiii, PENTIUMPRO, P3, false), |
1060 | | ARCH (pentium4, PENTIUM4, P4, false), |
1061 | | ARCH (prescott, NOCONA, CORE, false), |
1062 | | ARCH (nocona, NOCONA, NOCONA, false), |
1063 | | ARCH (yonah, CORE, CORE, true), |
1064 | | ARCH (core, CORE, CORE, false), |
1065 | | ARCH (merom, CORE2, CORE2, true), |
1066 | | ARCH (core2, CORE2, CORE2, false), |
1067 | | ARCH (corei7, COREI7, COREI7, false), |
1068 | | ARCH (iamcu, IAMCU, IAMCU, false), |
1069 | | ARCH (k6, K6, K6, false), |
1070 | | ARCH (k6_2, K6, K6_2, false), |
1071 | | ARCH (athlon, ATHLON, ATHLON, false), |
1072 | | ARCH (sledgehammer, K8, K8, true), |
1073 | | ARCH (opteron, K8, K8, false), |
1074 | | ARCH (k8, K8, K8, false), |
1075 | | ARCH (amdfam10, AMDFAM10, AMDFAM10, false), |
1076 | | ARCH (bdver1, BD, BDVER1, false), |
1077 | | ARCH (bdver2, BD, BDVER2, false), |
1078 | | ARCH (bdver3, BD, BDVER3, false), |
1079 | | ARCH (bdver4, BD, BDVER4, false), |
1080 | | ARCH (znver1, ZNVER, ZNVER1, false), |
1081 | | ARCH (znver2, ZNVER, ZNVER2, false), |
1082 | | ARCH (znver3, ZNVER, ZNVER3, false), |
1083 | | ARCH (znver4, ZNVER, ZNVER4, false), |
1084 | | ARCH (znver5, ZNVER, ZNVER5, false), |
1085 | | ARCH (btver1, BT, BTVER1, false), |
1086 | | ARCH (btver2, BT, BTVER2, false), |
1087 | | |
1088 | | SUBARCH (8087, 8087, ANY_8087, false), |
1089 | | SUBARCH (87, NONE, ANY_8087, false), /* Disable only! */ |
1090 | | SUBARCH (287, 287, ANY_287, false), |
1091 | | SUBARCH (387, 387, ANY_387, false), |
1092 | | SUBARCH (687, 687, ANY_687, false), |
1093 | | SUBARCH (cmov, CMOV, CMOV, false), |
1094 | | SUBARCH (fxsr, FXSR, ANY_FXSR, false), |
1095 | | SUBARCH (mmx, MMX, ANY_MMX, false), |
1096 | | SUBARCH (sse, SSE, ANY_SSE, false), |
1097 | | SUBARCH (sse2, SSE2, ANY_SSE2, false), |
1098 | | SUBARCH (sse3, SSE3, ANY_SSE3, false), |
1099 | | SUBARCH (sse4a, SSE4A, ANY_SSE4A, false), |
1100 | | SUBARCH (ssse3, SSSE3, ANY_SSSE3, false), |
1101 | | SUBARCH (sse4.1, SSE4_1, ANY_SSE4_1, false), |
1102 | | SUBARCH (sse4.2, SSE4_2, ANY_SSE4_2, false), |
1103 | | SUBARCH (sse4, SSE4_2, ANY_SSE4_1, false), |
1104 | | VECARCH (avx, AVX, ANY_AVX, reset), |
1105 | | VECARCH (avx2, AVX2, ANY_AVX2, reset), |
1106 | | VECARCH (avx512f, AVX512F, ANY_AVX512F, reset), |
1107 | | VECARCH (avx512cd, AVX512CD, ANY_AVX512CD, reset), |
1108 | | VECARCH (avx512er, AVX512ER, ANY_AVX512ER, reset), |
1109 | | VECARCH (avx512pf, AVX512PF, ANY_AVX512PF, reset), |
1110 | | VECARCH (avx512dq, AVX512DQ, ANY_AVX512DQ, reset), |
1111 | | VECARCH (avx512bw, AVX512BW, ANY_AVX512BW, reset), |
1112 | | VECARCH (avx512vl, AVX512VL, ANY_AVX512VL, reset), |
1113 | | SUBARCH (monitor, MONITOR, MONITOR, false), |
1114 | | SUBARCH (vmx, VMX, ANY_VMX, false), |
1115 | | SUBARCH (vmfunc, VMFUNC, ANY_VMFUNC, false), |
1116 | | SUBARCH (smx, SMX, SMX, false), |
1117 | | SUBARCH (xsave, XSAVE, ANY_XSAVE, false), |
1118 | | SUBARCH (xsaveopt, XSAVEOPT, ANY_XSAVEOPT, false), |
1119 | | SUBARCH (xsavec, XSAVEC, ANY_XSAVEC, false), |
1120 | | SUBARCH (xsaves, XSAVES, ANY_XSAVES, false), |
1121 | | SUBARCH (aes, AES, ANY_AES, false), |
1122 | | SUBARCH (pclmul, PCLMULQDQ, ANY_PCLMULQDQ, false), |
1123 | | SUBARCH (clmul, PCLMULQDQ, ANY_PCLMULQDQ, true), |
1124 | | SUBARCH (fsgsbase, FSGSBASE, FSGSBASE, false), |
1125 | | SUBARCH (rdrnd, RDRND, RDRND, false), |
1126 | | SUBARCH (f16c, F16C, ANY_F16C, false), |
1127 | | SUBARCH (bmi2, BMI2, BMI2, false), |
1128 | | SUBARCH (fma, FMA, ANY_FMA, false), |
1129 | | SUBARCH (fma4, FMA4, ANY_FMA4, false), |
1130 | | SUBARCH (xop, XOP, ANY_XOP, false), |
1131 | | SUBARCH (lwp, LWP, ANY_LWP, false), |
1132 | | SUBARCH (movbe, MOVBE, MOVBE, false), |
1133 | | SUBARCH (cx16, CX16, CX16, false), |
1134 | | SUBARCH (lahf_sahf, LAHF_SAHF, LAHF_SAHF, false), |
1135 | | SUBARCH (ept, EPT, ANY_EPT, false), |
1136 | | SUBARCH (lzcnt, LZCNT, LZCNT, false), |
1137 | | SUBARCH (popcnt, POPCNT, POPCNT, false), |
1138 | | SUBARCH (hle, HLE, HLE, false), |
1139 | | SUBARCH (rtm, RTM, ANY_RTM, false), |
1140 | | SUBARCH (tsx, TSX, TSX, false), |
1141 | | SUBARCH (invpcid, INVPCID, INVPCID, false), |
1142 | | SUBARCH (clflush, CLFLUSH, CLFLUSH, false), |
1143 | | SUBARCH (nop, NOP, NOP, false), |
1144 | | SUBARCH (syscall, SYSCALL, SYSCALL, false), |
1145 | | SUBARCH (rdtscp, RDTSCP, RDTSCP, false), |
1146 | | SUBARCH (3dnow, 3DNOW, ANY_3DNOW, false), |
1147 | | SUBARCH (3dnowa, 3DNOWA, ANY_3DNOWA, false), |
1148 | | SUBARCH (padlock, PADLOCK, PADLOCK, false), |
1149 | | SUBARCH (pacifica, SVME, ANY_SVME, true), |
1150 | | SUBARCH (svme, SVME, ANY_SVME, false), |
1151 | | SUBARCH (abm, ABM, ABM, false), |
1152 | | SUBARCH (bmi, BMI, BMI, false), |
1153 | | SUBARCH (tbm, TBM, TBM, false), |
1154 | | SUBARCH (adx, ADX, ADX, false), |
1155 | | SUBARCH (rdseed, RDSEED, RDSEED, false), |
1156 | | SUBARCH (prfchw, PRFCHW, PRFCHW, false), |
1157 | | SUBARCH (smap, SMAP, SMAP, false), |
1158 | | SUBARCH (mpx, MPX, ANY_MPX, false), |
1159 | | SUBARCH (sha, SHA, ANY_SHA, false), |
1160 | | SUBARCH (clflushopt, CLFLUSHOPT, CLFLUSHOPT, false), |
1161 | | SUBARCH (prefetchwt1, PREFETCHWT1, PREFETCHWT1, false), |
1162 | | SUBARCH (se1, SE1, SE1, false), |
1163 | | SUBARCH (clwb, CLWB, CLWB, false), |
1164 | | VECARCH (avx512ifma, AVX512IFMA, ANY_AVX512IFMA, reset), |
1165 | | VECARCH (avx512vbmi, AVX512VBMI, ANY_AVX512VBMI, reset), |
1166 | | VECARCH (avx512_4fmaps, AVX512_4FMAPS, ANY_AVX512_4FMAPS, reset), |
1167 | | VECARCH (avx512_4vnniw, AVX512_4VNNIW, ANY_AVX512_4VNNIW, reset), |
1168 | | VECARCH (avx512_vpopcntdq, AVX512_VPOPCNTDQ, ANY_AVX512_VPOPCNTDQ, reset), |
1169 | | VECARCH (avx512_vbmi2, AVX512_VBMI2, ANY_AVX512_VBMI2, reset), |
1170 | | VECARCH (avx512_vnni, AVX512_VNNI, ANY_AVX512_VNNI, reset), |
1171 | | VECARCH (avx512_bitalg, AVX512_BITALG, ANY_AVX512_BITALG, reset), |
1172 | | VECARCH (avx_vnni, AVX_VNNI, ANY_AVX_VNNI, reset), |
1173 | | SUBARCH (clzero, CLZERO, CLZERO, false), |
1174 | | SUBARCH (mwaitx, MWAITX, MWAITX, false), |
1175 | | SUBARCH (ospke, OSPKE, ANY_OSPKE, false), |
1176 | | SUBARCH (rdpid, RDPID, RDPID, false), |
1177 | | SUBARCH (ptwrite, PTWRITE, PTWRITE, false), |
1178 | | SUBARCH (ibt, IBT, IBT, false), |
1179 | | SUBARCH (shstk, SHSTK, SHSTK, false), |
1180 | | SUBARCH (gfni, GFNI, ANY_GFNI, false), |
1181 | | VECARCH (vaes, VAES, ANY_VAES, reset), |
1182 | | VECARCH (vpclmulqdq, VPCLMULQDQ, ANY_VPCLMULQDQ, reset), |
1183 | | SUBARCH (wbnoinvd, WBNOINVD, WBNOINVD, false), |
1184 | | SUBARCH (pconfig, PCONFIG, PCONFIG, false), |
1185 | | SUBARCH (waitpkg, WAITPKG, WAITPKG, false), |
1186 | | SUBARCH (cldemote, CLDEMOTE, CLDEMOTE, false), |
1187 | | SUBARCH (amx_int8, AMX_INT8, ANY_AMX_INT8, false), |
1188 | | SUBARCH (amx_bf16, AMX_BF16, ANY_AMX_BF16, false), |
1189 | | SUBARCH (amx_fp16, AMX_FP16, ANY_AMX_FP16, false), |
1190 | | SUBARCH (amx_complex, AMX_COMPLEX, ANY_AMX_COMPLEX, false), |
1191 | | SUBARCH (amx_transpose, AMX_TRANSPOSE, ANY_AMX_TRANSPOSE, false), |
1192 | | SUBARCH (amx_tf32, AMX_TF32, ANY_AMX_TF32, false), |
1193 | | SUBARCH (amx_fp8, AMX_FP8, ANY_AMX_FP8, false), |
1194 | | SUBARCH (amx_movrs, AMX_MOVRS, ANY_AMX_MOVRS, false), |
1195 | | SUBARCH (amx_avx512, AMX_AVX512, ANY_AMX_AVX512, false), |
1196 | | SUBARCH (amx_tile, AMX_TILE, ANY_AMX_TILE, false), |
1197 | | SUBARCH (movdiri, MOVDIRI, MOVDIRI, false), |
1198 | | SUBARCH (movdir64b, MOVDIR64B, MOVDIR64B, false), |
1199 | | VECARCH (avx512_bf16, AVX512_BF16, ANY_AVX512_BF16, reset), |
1200 | | VECARCH (avx512_vp2intersect, AVX512_VP2INTERSECT, |
1201 | | ANY_AVX512_VP2INTERSECT, reset), |
1202 | | SUBARCH (tdx, TDX, TDX, false), |
1203 | | SUBARCH (enqcmd, ENQCMD, ENQCMD, false), |
1204 | | SUBARCH (serialize, SERIALIZE, SERIALIZE, false), |
1205 | | SUBARCH (rdpru, RDPRU, RDPRU, false), |
1206 | | SUBARCH (mcommit, MCOMMIT, MCOMMIT, false), |
1207 | | SUBARCH (sev_es, SEV_ES, ANY_SEV_ES, false), |
1208 | | SUBARCH (tsxldtrk, TSXLDTRK, ANY_TSXLDTRK, false), |
1209 | | SUBARCH (kl, KL, ANY_KL, false), |
1210 | | SUBARCH (widekl, WIDEKL, ANY_WIDEKL, false), |
1211 | | SUBARCH (uintr, UINTR, UINTR, false), |
1212 | | SUBARCH (hreset, HRESET, HRESET, false), |
1213 | | VECARCH (avx512_fp16, AVX512_FP16, ANY_AVX512_FP16, reset), |
1214 | | SUBARCH (prefetchi, PREFETCHI, PREFETCHI, false), |
1215 | | VECARCH (avx_ifma, AVX_IFMA, ANY_AVX_IFMA, reset), |
1216 | | VECARCH (avx_vnni_int8, AVX_VNNI_INT8, ANY_AVX_VNNI_INT8, reset), |
1217 | | SUBARCH (cmpccxadd, CMPCCXADD, CMPCCXADD, false), |
1218 | | SUBARCH (wrmsrns, WRMSRNS, WRMSRNS, false), |
1219 | | SUBARCH (msrlist, MSRLIST, MSRLIST, false), |
1220 | | VECARCH (avx_ne_convert, AVX_NE_CONVERT, ANY_AVX_NE_CONVERT, reset), |
1221 | | SUBARCH (rao_int, RAO_INT, RAO_INT, false), |
1222 | | SUBARCH (rmpquery, RMPQUERY, ANY_RMPQUERY, false), |
1223 | | SUBARCH (rmpread, RMPREAD, ANY_RMPREAD, false), |
1224 | | SUBARCH (fred, FRED, ANY_FRED, false), |
1225 | | SUBARCH (lkgs, LKGS, ANY_LKGS, false), |
1226 | | VECARCH (avx_vnni_int16, AVX_VNNI_INT16, ANY_AVX_VNNI_INT16, reset), |
1227 | | VECARCH (sha512, SHA512, ANY_SHA512, reset), |
1228 | | VECARCH (sm3, SM3, ANY_SM3, reset), |
1229 | | VECARCH (sm4, SM4, ANY_SM4, reset), |
1230 | | SUBARCH (pbndkb, PBNDKB, PBNDKB, false), |
1231 | | VECARCH (avx10.1, AVX10_1, ANY_AVX512F, set), |
1232 | | SUBARCH (user_msr, USER_MSR, USER_MSR, false), |
1233 | | SUBARCH (apx_f, APX_F, APX_F, false), |
1234 | | VECARCH (avx10.2, AVX10_2, ANY_AVX10_2, set), |
1235 | | SUBARCH (gmism2, GMISM2, GMISM2, false), |
1236 | | SUBARCH (gmiccs, GMICCS, GMICCS, false), |
1237 | | SUBARCH (msr_imm, MSR_IMM, MSR_IMM, false), |
1238 | | SUBARCH (padlockrng2, PADLOCKRNG2, PADLOCKRNG2, false), |
1239 | | SUBARCH (padlockphe2, PADLOCKPHE2, PADLOCKPHE2, false), |
1240 | | SUBARCH (padlockxmodx, PADLOCKXMODX, PADLOCKXMODX, false), |
1241 | | SUBARCH (movrs, MOVRS, MOVRS, false), |
1242 | | }; |
1243 | | |
1244 | | #undef SUBARCH |
1245 | | #undef ARCH |
1246 | | |
1247 | | #ifdef I386COFF |
1248 | | /* Like s_lcomm_internal in gas/read.c but the alignment string |
1249 | | is allowed to be optional. */ |
1250 | | |
1251 | | static symbolS * |
1252 | | pe_lcomm_internal (int needs_align, symbolS *symbolP, addressT size) |
1253 | | { |
1254 | | addressT align = 0; |
1255 | | |
1256 | | SKIP_WHITESPACE (); |
1257 | | |
1258 | | if (needs_align |
1259 | | && *input_line_pointer == ',') |
1260 | | { |
1261 | | align = parse_align (needs_align - 1); |
1262 | | |
1263 | | if (align == (addressT) -1) |
1264 | | return NULL; |
1265 | | } |
1266 | | else |
1267 | | { |
1268 | | if (size >= 8) |
1269 | | align = 3; |
1270 | | else if (size >= 4) |
1271 | | align = 2; |
1272 | | else if (size >= 2) |
1273 | | align = 1; |
1274 | | else |
1275 | | align = 0; |
1276 | | } |
1277 | | |
1278 | | bss_alloc (symbolP, size, align); |
1279 | | return symbolP; |
1280 | | } |
1281 | | |
1282 | | static void |
1283 | | pe_lcomm (int needs_align) |
1284 | | { |
1285 | | s_comm_internal (needs_align * 2, pe_lcomm_internal); |
1286 | | } |
1287 | | #endif |
1288 | | |
1289 | | const pseudo_typeS md_pseudo_table[] = |
1290 | | { |
1291 | | #if !defined(OBJ_AOUT) && !defined(USE_ALIGN_PTWO) |
1292 | | {"align", s_align_bytes, 0}, |
1293 | | #else |
1294 | | {"align", s_align_ptwo, 0}, |
1295 | | #endif |
1296 | | {"arch", set_cpu_arch, 0}, |
1297 | | #ifdef OBJ_AOUT |
1298 | | {"bss", s_bss, 0}, |
1299 | | #endif |
1300 | | #ifdef I386COFF |
1301 | | {"lcomm", pe_lcomm, 1}, |
1302 | | #endif |
1303 | | {"ffloat", float_cons, 'f'}, |
1304 | | {"dfloat", float_cons, 'd'}, |
1305 | | {"tfloat", float_cons, 'x'}, |
1306 | | {"hfloat", float_cons, 'h'}, |
1307 | | {"bfloat16", float_cons, 'b'}, |
1308 | | {"value", cons, 2}, |
1309 | | {"slong", signed_cons, 4}, |
1310 | | {"insn", s_insn, 0}, |
1311 | | {"noopt", s_noopt, 0}, |
1312 | | {"optim", s_ignore, 0}, |
1313 | | {"code16gcc", set_16bit_gcc_code_flag, CODE_16BIT}, |
1314 | | {"code16", set_code_flag, CODE_16BIT}, |
1315 | | {"code32", set_code_flag, CODE_32BIT}, |
1316 | | #ifdef BFD64 |
1317 | | {"code64", set_code_flag, CODE_64BIT}, |
1318 | | #endif |
1319 | | {"intel_syntax", set_intel_syntax, 1}, |
1320 | | {"att_syntax", set_intel_syntax, 0}, |
1321 | | {"intel_mnemonic", set_intel_mnemonic, 1}, |
1322 | | {"att_mnemonic", set_intel_mnemonic, 0}, |
1323 | | {"allow_index_reg", set_allow_index_reg, 1}, |
1324 | | {"disallow_index_reg", set_allow_index_reg, 0}, |
1325 | | {"sse_check", set_check, 0}, |
1326 | | {"operand_check", set_check, 1}, |
1327 | | #ifdef OBJ_ELF |
1328 | | {"largecomm", handle_large_common, 0}, |
1329 | | #else |
1330 | | {"file", dwarf2_directive_file, 0}, |
1331 | | {"loc", dwarf2_directive_loc, 0}, |
1332 | | {"loc_mark_labels", dwarf2_directive_loc_mark_labels, 0}, |
1333 | | #endif |
1334 | | #ifdef TE_PE |
1335 | | {"secrel32", pe_directive_secrel, 0}, |
1336 | | {"secidx", pe_directive_secidx, 0}, |
1337 | | #endif |
1338 | | {0, 0, 0} |
1339 | | }; |
1340 | | |
1341 | | /* For interface with expression (). */ |
1342 | | extern char *input_line_pointer; |
1343 | | |
1344 | | /* Hash table for instruction mnemonic lookup. */ |
1345 | | static htab_t op_hash; |
1346 | | |
1347 | | /* Hash table for register lookup. */ |
1348 | | static htab_t reg_hash; |
1349 | | |
1350 | | #if (defined (OBJ_ELF) || defined (OBJ_MACH_O) || defined (TE_PE)) |
1351 | | static const struct |
1352 | | { |
1353 | | const char *str; |
1354 | | unsigned int len; |
1355 | | const enum bfd_reloc_code_real rel[2]; |
1356 | | const i386_operand_type types64; |
1357 | | bool need_GOT_symbol; |
1358 | | } |
1359 | | gotrel[] = |
1360 | | { |
1361 | | #define OPERAND_TYPE_IMM32_32S_DISP32 { .bitfield = \ |
1362 | | { .imm32 = 1, .imm32s = 1, .disp32 = 1 } } |
1363 | | #define OPERAND_TYPE_IMM32_32S_64_DISP32 { .bitfield = \ |
1364 | | { .imm32 = 1, .imm32s = 1, .imm64 = 1, .disp32 = 1 } } |
1365 | | #define OPERAND_TYPE_IMM32_32S_64_DISP32_64 { .bitfield = \ |
1366 | | { .imm32 = 1, .imm32s = 1, .imm64 = 1, .disp32 = 1, .disp64 = 1 } } |
1367 | | #define OPERAND_TYPE_IMM64_DISP64 { .bitfield = \ |
1368 | | { .imm64 = 1, .disp64 = 1 } } |
1369 | | |
1370 | | #ifndef TE_PE |
1371 | | #ifdef OBJ_ELF |
1372 | | { STRING_COMMA_LEN ("SIZE"), { BFD_RELOC_SIZE32, |
1373 | | BFD_RELOC_SIZE32 }, |
1374 | | { .bitfield = { .imm32 = 1, .imm64 = 1 } }, false }, |
1375 | | #endif |
1376 | | { STRING_COMMA_LEN ("PLTOFF"), { _dummy_first_bfd_reloc_code_real, |
1377 | | BFD_RELOC_X86_64_PLTOFF64 }, |
1378 | | { .bitfield = { .imm64 = 1 } }, true }, |
1379 | | { STRING_COMMA_LEN ("PLT"), { BFD_RELOC_386_PLT32, |
1380 | | BFD_RELOC_X86_64_PLT32 }, |
1381 | | OPERAND_TYPE_IMM32_32S_DISP32, false }, |
1382 | | { STRING_COMMA_LEN ("GOTPLT"), { _dummy_first_bfd_reloc_code_real, |
1383 | | BFD_RELOC_X86_64_GOTPLT64 }, |
1384 | | OPERAND_TYPE_IMM64_DISP64, true }, |
1385 | | { STRING_COMMA_LEN ("GOTOFF"), { BFD_RELOC_386_GOTOFF, |
1386 | | BFD_RELOC_X86_64_GOTOFF64 }, |
1387 | | OPERAND_TYPE_IMM64_DISP64, true }, |
1388 | | { STRING_COMMA_LEN ("GOTPCREL"), { _dummy_first_bfd_reloc_code_real, |
1389 | | BFD_RELOC_X86_64_GOTPCREL }, |
1390 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1391 | | { STRING_COMMA_LEN ("TLSGD"), { BFD_RELOC_386_TLS_GD, |
1392 | | BFD_RELOC_X86_64_TLSGD }, |
1393 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1394 | | { STRING_COMMA_LEN ("TLSLDM"), { BFD_RELOC_386_TLS_LDM, |
1395 | | _dummy_first_bfd_reloc_code_real }, |
1396 | | OPERAND_TYPE_NONE, true }, |
1397 | | { STRING_COMMA_LEN ("TLSLD"), { _dummy_first_bfd_reloc_code_real, |
1398 | | BFD_RELOC_X86_64_TLSLD }, |
1399 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1400 | | { STRING_COMMA_LEN ("GOTTPOFF"), { BFD_RELOC_386_TLS_IE_32, |
1401 | | BFD_RELOC_X86_64_GOTTPOFF }, |
1402 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1403 | | { STRING_COMMA_LEN ("TPOFF"), { BFD_RELOC_386_TLS_LE_32, |
1404 | | BFD_RELOC_X86_64_TPOFF32 }, |
1405 | | OPERAND_TYPE_IMM32_32S_64_DISP32_64, true }, |
1406 | | { STRING_COMMA_LEN ("NTPOFF"), { BFD_RELOC_386_TLS_LE, |
1407 | | _dummy_first_bfd_reloc_code_real }, |
1408 | | OPERAND_TYPE_NONE, true }, |
1409 | | { STRING_COMMA_LEN ("DTPOFF"), { BFD_RELOC_386_TLS_LDO_32, |
1410 | | BFD_RELOC_X86_64_DTPOFF32 }, |
1411 | | OPERAND_TYPE_IMM32_32S_64_DISP32_64, true }, |
1412 | | { STRING_COMMA_LEN ("GOTNTPOFF"),{ BFD_RELOC_386_TLS_GOTIE, |
1413 | | _dummy_first_bfd_reloc_code_real }, |
1414 | | OPERAND_TYPE_NONE, true }, |
1415 | | { STRING_COMMA_LEN ("INDNTPOFF"),{ BFD_RELOC_386_TLS_IE, |
1416 | | _dummy_first_bfd_reloc_code_real }, |
1417 | | OPERAND_TYPE_NONE, true }, |
1418 | | { STRING_COMMA_LEN ("GOT"), { BFD_RELOC_386_GOT32, |
1419 | | BFD_RELOC_X86_64_GOT32 }, |
1420 | | OPERAND_TYPE_IMM32_32S_64_DISP32, true }, |
1421 | | { STRING_COMMA_LEN ("TLSDESC"), { BFD_RELOC_386_TLS_GOTDESC, |
1422 | | BFD_RELOC_X86_64_GOTPC32_TLSDESC }, |
1423 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1424 | | { STRING_COMMA_LEN ("TLSCALL"), { BFD_RELOC_386_TLS_DESC_CALL, |
1425 | | BFD_RELOC_X86_64_TLSDESC_CALL }, |
1426 | | OPERAND_TYPE_IMM32_32S_DISP32, true }, |
1427 | | #else /* TE_PE */ |
1428 | | { STRING_COMMA_LEN ("SECREL32"), { BFD_RELOC_32_SECREL, |
1429 | | BFD_RELOC_32_SECREL }, |
1430 | | OPERAND_TYPE_IMM32_32S_DISP32, false }, |
1431 | | { STRING_COMMA_LEN ("SECIDX16"), { BFD_RELOC_16_SECIDX, |
1432 | | BFD_RELOC_16_SECIDX }, |
1433 | | { .bitfield = { .imm16 = 1, .disp16 = 1 } }, false }, |
1434 | | { STRING_COMMA_LEN ("RVA"), { BFD_RELOC_RVA, |
1435 | | BFD_RELOC_RVA }, |
1436 | | OPERAND_TYPE_IMM32_32S_DISP32, false }, |
1437 | | { STRING_COMMA_LEN ("IMGREL"), { BFD_RELOC_RVA, |
1438 | | BFD_RELOC_RVA }, |
1439 | | OPERAND_TYPE_IMM32_32S_DISP32, false }, |
1440 | | #endif |
1441 | | |
1442 | | #undef OPERAND_TYPE_IMM32_32S_DISP32 |
1443 | | #undef OPERAND_TYPE_IMM32_32S_64_DISP32 |
1444 | | #undef OPERAND_TYPE_IMM32_32S_64_DISP32_64 |
1445 | | #undef OPERAND_TYPE_IMM64_DISP64 |
1446 | | }; |
1447 | | #endif |
1448 | | |
1449 | | /* Various efficient no-op patterns for aligning code labels. |
1450 | | Note: Don't try to assemble the instructions in the comments. |
1451 | | 0L and 0w are not legal. */ |
1452 | | static const unsigned char f32_1[] = |
1453 | | {0x90}; /* nop */ |
1454 | | static const unsigned char f32_2[] = |
1455 | | {0x66,0x90}; /* xchg %ax,%ax */ |
1456 | | static const unsigned char f32_3[] = |
1457 | | {0x8d,0x76,0x00}; /* leal 0(%esi),%esi */ |
1458 | | #define f32_4 (f32_5 + 1) /* leal 0(%esi,%eiz),%esi */ |
1459 | | static const unsigned char f32_5[] = |
1460 | | {0x2e,0x8d,0x74,0x26,0x00}; /* leal %cs:0(%esi,%eiz),%esi */ |
1461 | | static const unsigned char f32_6[] = |
1462 | | {0x8d,0xb6,0x00,0x00,0x00,0x00}; /* leal 0L(%esi),%esi */ |
1463 | | #define f32_7 (f32_8 + 1) /* leal 0L(%esi,%eiz),%esi */ |
1464 | | static const unsigned char f32_8[] = |
1465 | | {0x2e,0x8d,0xb4,0x26,0x00,0x00,0x00,0x00}; /* leal %cs:0L(%esi,%eiz),%esi */ |
1466 | | static const unsigned char f64_3[] = |
1467 | | {0x48,0x89,0xf6}; /* mov %rsi,%rsi */ |
1468 | | static const unsigned char f64_4[] = |
1469 | | {0x48,0x8d,0x76,0x00}; /* lea 0(%rsi),%rsi */ |
1470 | | #define f64_5 (f64_6 + 1) /* lea 0(%rsi,%riz),%rsi */ |
1471 | | static const unsigned char f64_6[] = |
1472 | | {0x2e,0x48,0x8d,0x74,0x26,0x00}; /* lea %cs:0(%rsi,%riz),%rsi */ |
1473 | | static const unsigned char f64_7[] = |
1474 | | {0x48,0x8d,0xb6,0x00,0x00,0x00,0x00}; /* lea 0L(%rsi),%rsi */ |
1475 | | #define f64_8 (f64_9 + 1) /* lea 0L(%rsi,%riz),%rsi */ |
1476 | | static const unsigned char f64_9[] = |
1477 | | {0x2e,0x48,0x8d,0xb4,0x26,0x00,0x00,0x00,0x00}; /* lea %cs:0L(%rsi,%riz),%rsi */ |
1478 | | #define f16_2 (f64_3 + 1) /* mov %si,%si */ |
1479 | | static const unsigned char f16_3[] = |
1480 | | {0x8d,0x74,0x00}; /* lea 0(%si),%si */ |
1481 | | #define f16_4 (f16_5 + 1) /* lea 0W(%si),%si */ |
1482 | | static const unsigned char f16_5[] = |
1483 | | {0x2e,0x8d,0xb4,0x00,0x00}; /* lea %cs:0W(%si),%si */ |
1484 | | static const unsigned char jump_disp8[] = |
1485 | | {0xeb}; /* jmp disp8 */ |
1486 | | static const unsigned char jump32_disp32[] = |
1487 | | {0xe9}; /* jmp disp32 */ |
1488 | | static const unsigned char jump16_disp32[] = |
1489 | | {0x66,0xe9}; /* jmp disp32 */ |
1490 | | /* 32-bit NOPs patterns. */ |
1491 | | static const unsigned char *const f32_patt[] = { |
1492 | | f32_1, f32_2, f32_3, f32_4, f32_5, f32_6, f32_7, f32_8 |
1493 | | }; |
1494 | | /* 64-bit NOPs patterns. */ |
1495 | | static const unsigned char *const f64_patt[] = { |
1496 | | f32_1, f32_2, f64_3, f64_4, f64_5, f64_6, f64_7, f64_8, f64_9 |
1497 | | }; |
1498 | | /* 16-bit NOPs patterns. */ |
1499 | | static const unsigned char *const f16_patt[] = { |
1500 | | f32_1, f16_2, f16_3, f16_4, f16_5 |
1501 | | }; |
1502 | | /* nopl (%[re]ax) */ |
1503 | | static const unsigned char alt_3[] = |
1504 | | {0x0f,0x1f,0x00}; |
1505 | | /* nopl 0(%[re]ax) */ |
1506 | | static const unsigned char alt_4[] = |
1507 | | {0x0f,0x1f,0x40,0x00}; |
1508 | | /* nopl 0(%[re]ax,%[re]ax,1) */ |
1509 | | #define alt_5 (alt_6 + 1) |
1510 | | /* nopw 0(%[re]ax,%[re]ax,1) */ |
1511 | | static const unsigned char alt_6[] = |
1512 | | {0x66,0x0f,0x1f,0x44,0x00,0x00}; |
1513 | | /* nopl 0L(%[re]ax) */ |
1514 | | static const unsigned char alt_7[] = |
1515 | | {0x0f,0x1f,0x80,0x00,0x00,0x00,0x00}; |
1516 | | /* nopl 0L(%[re]ax,%[re]ax,1) */ |
1517 | | #define alt_8 (alt_9 + 1) |
1518 | | /* nopw 0L(%[re]ax,%[re]ax,1) */ |
1519 | | static const unsigned char alt_9[] = |
1520 | | {0x66,0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00}; |
1521 | | /* nopw %cs:0L(%[re]ax,%[re]ax,1) */ |
1522 | | #define alt_10 (alt_11 + 1) |
1523 | | /* data16 nopw %cs:0L(%eax,%eax,1) */ |
1524 | | static const unsigned char alt_11[] = |
1525 | | {0x66,0x66,0x2e,0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00}; |
1526 | | /* 32-bit and 64-bit NOPs patterns. */ |
1527 | | static const unsigned char *const alt_patt[] = { |
1528 | | f32_1, f32_2, alt_3, alt_4, alt_5, alt_6, alt_7, alt_8, |
1529 | | alt_9, alt_10, alt_11 |
1530 | | }; |
1531 | | #define alt64_9 (alt64_15 + 6) /* nopq 0L(%rax,%rax,1) */ |
1532 | | #define alt64_10 (alt64_15 + 5) /* cs nopq 0L(%rax,%rax,1) */ |
1533 | | /* data16 cs nopq 0L(%rax,%rax,1) */ |
1534 | | #define alt64_11 (alt64_15 + 4) |
1535 | | /* data16 data16 cs nopq 0L(%rax,%rax,1) */ |
1536 | | #define alt64_12 (alt64_15 + 3) |
1537 | | /* data16 data16 data16 cs nopq 0L(%rax,%rax,1) */ |
1538 | | #define alt64_13 (alt64_15 + 2) |
1539 | | /* data16 data16 data16 data16 cs nopq 0L(%rax,%rax,1) */ |
1540 | | #define alt64_14 (alt64_15 + 1) |
1541 | | /* data16 data16 data16 data16 data16 cs nopq 0L(%rax,%rax,1) */ |
1542 | | static const unsigned char alt64_15[] = |
1543 | | {0x66,0x66,0x66,0x66,0x66,0x2e,0x48, |
1544 | | 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00}; |
1545 | | /* Long 64-bit NOPs patterns. */ |
1546 | | static const unsigned char *const alt64_patt[] = { |
1547 | | f32_1, f32_2, alt_3, alt_4, alt_5, alt_6, alt_7, alt_8, |
1548 | | alt64_9, alt64_10, alt64_11,alt64_12, alt64_13, alt64_14, alt64_15 |
1549 | | }; |
1550 | | |
1551 | | static INLINE int |
1552 | | fits_in_imm7 (offsetT num) |
1553 | 0 | { |
1554 | 0 | return (num & 0x7f) == num; |
1555 | 0 | } |
1556 | | |
1557 | | static INLINE int |
1558 | | fits_in_imm31 (offsetT num) |
1559 | 0 | { |
1560 | 0 | return (num & 0x7fffffff) == num; |
1561 | 0 | } |
1562 | | |
1563 | | /* Genenerate COUNT bytes of NOPs to WHERE with the maximum size of a |
1564 | | single NOP instruction LIMIT. */ |
1565 | | |
1566 | | void |
1567 | | i386_generate_nops (fragS *fragP, char *where, offsetT count, int limit) |
1568 | 0 | { |
1569 | 0 | const unsigned char *const *patt = NULL; |
1570 | 0 | int max_single_nop_size; |
1571 | | /* Maximum number of NOPs before switching to jump over NOPs. */ |
1572 | 0 | int max_number_of_nops; |
1573 | |
|
1574 | 0 | switch (fragP->fr_type) |
1575 | 0 | { |
1576 | 0 | case rs_fill_nop: |
1577 | 0 | case rs_align_code: |
1578 | 0 | break; |
1579 | 0 | case rs_machine_dependent: |
1580 | | /* Allow NOP padding for jumps and calls. */ |
1581 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PADDING |
1582 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == FUSED_JCC_PADDING) |
1583 | 0 | break; |
1584 | | /* Fall through. */ |
1585 | 0 | default: |
1586 | 0 | return; |
1587 | 0 | } |
1588 | | |
1589 | | /* We need to decide which NOP sequence to use for 32bit and |
1590 | | 64bit. When -mtune= is used: |
1591 | | |
1592 | | 1. For PROCESSOR_I?86, PROCESSOR_PENTIUM, PROCESSOR_IAMCU, and |
1593 | | PROCESSOR_GENERIC32, f32_patt will be used. |
1594 | | 2. For the rest, alt_patt will be used. |
1595 | | |
1596 | | When -mtune= isn't used, alt_patt will be used if |
1597 | | cpu_arch_isa_flags has CpuNop. Otherwise, f32_patt/f64_patt will |
1598 | | be used. |
1599 | | |
1600 | | When -march= or .arch is used, we can't use anything beyond |
1601 | | cpu_arch_isa_flags. */ |
1602 | | |
1603 | 0 | if (fragP->tc_frag_data.code == CODE_16BIT) |
1604 | 0 | { |
1605 | 0 | patt = f16_patt; |
1606 | 0 | max_single_nop_size = sizeof (f16_patt) / sizeof (f16_patt[0]); |
1607 | | /* Limit number of NOPs to 2 in 16-bit mode. */ |
1608 | 0 | max_number_of_nops = 2; |
1609 | 0 | } |
1610 | 0 | else |
1611 | 0 | { |
1612 | 0 | patt = fragP->tc_frag_data.code == CODE_64BIT ? f64_patt : f32_patt; |
1613 | 0 | if (fragP->tc_frag_data.isa == PROCESSOR_UNKNOWN) |
1614 | 0 | { |
1615 | | /* PROCESSOR_UNKNOWN means that all ISAs may be used, unless |
1616 | | explicitly disabled. */ |
1617 | 0 | switch (fragP->tc_frag_data.tune) |
1618 | 0 | { |
1619 | 0 | case PROCESSOR_UNKNOWN: |
1620 | | /* We use cpu_arch_isa_flags to check if we SHOULD |
1621 | | optimize with nops. */ |
1622 | 0 | if (fragP->tc_frag_data.isanop) |
1623 | 0 | patt = alt_patt; |
1624 | 0 | break; |
1625 | | |
1626 | 0 | case PROCESSOR_CORE: |
1627 | 0 | case PROCESSOR_CORE2: |
1628 | 0 | case PROCESSOR_COREI7: |
1629 | 0 | if (fragP->tc_frag_data.cpunop) |
1630 | 0 | { |
1631 | 0 | if (fragP->tc_frag_data.code == CODE_64BIT) |
1632 | 0 | patt = alt64_patt; |
1633 | 0 | else |
1634 | 0 | patt = alt_patt; |
1635 | 0 | } |
1636 | 0 | break; |
1637 | | |
1638 | 0 | case PROCESSOR_PENTIUMPRO: |
1639 | 0 | case PROCESSOR_PENTIUM4: |
1640 | 0 | case PROCESSOR_NOCONA: |
1641 | 0 | case PROCESSOR_GENERIC64: |
1642 | 0 | case PROCESSOR_K6: |
1643 | 0 | case PROCESSOR_ATHLON: |
1644 | 0 | case PROCESSOR_K8: |
1645 | 0 | case PROCESSOR_AMDFAM10: |
1646 | 0 | case PROCESSOR_BD: |
1647 | 0 | case PROCESSOR_ZNVER: |
1648 | 0 | case PROCESSOR_BT: |
1649 | 0 | if (fragP->tc_frag_data.cpunop) |
1650 | 0 | patt = alt_patt; |
1651 | 0 | break; |
1652 | | |
1653 | 0 | case PROCESSOR_I386: |
1654 | 0 | case PROCESSOR_I486: |
1655 | 0 | case PROCESSOR_PENTIUM: |
1656 | 0 | case PROCESSOR_I686: |
1657 | 0 | case PROCESSOR_IAMCU: |
1658 | 0 | case PROCESSOR_GENERIC32: |
1659 | 0 | break; |
1660 | 0 | case PROCESSOR_NONE: |
1661 | 0 | abort (); |
1662 | 0 | } |
1663 | 0 | } |
1664 | 0 | else |
1665 | 0 | { |
1666 | 0 | switch (fragP->tc_frag_data.tune) |
1667 | 0 | { |
1668 | 0 | case PROCESSOR_UNKNOWN: |
1669 | | /* When cpu_arch_isa is set, cpu_arch_tune shouldn't be |
1670 | | PROCESSOR_UNKNOWN. */ |
1671 | 0 | abort (); |
1672 | 0 | break; |
1673 | | |
1674 | 0 | default: |
1675 | | /* We use cpu_arch_isa_flags to check if we CAN optimize |
1676 | | with nops. */ |
1677 | 0 | if (fragP->tc_frag_data.isanop) |
1678 | 0 | patt = alt_patt; |
1679 | 0 | break; |
1680 | | |
1681 | 0 | case PROCESSOR_NONE: |
1682 | 0 | abort (); |
1683 | 0 | } |
1684 | 0 | } |
1685 | | |
1686 | 0 | if (patt != alt_patt && patt != alt64_patt) |
1687 | 0 | { |
1688 | 0 | max_single_nop_size = patt == f32_patt ? ARRAY_SIZE (f32_patt) |
1689 | 0 | : ARRAY_SIZE (f64_patt); |
1690 | | /* Limit number of NOPs to 2 for older processors. */ |
1691 | 0 | max_number_of_nops = 2; |
1692 | 0 | } |
1693 | 0 | else |
1694 | 0 | { |
1695 | 0 | max_single_nop_size = patt == alt_patt |
1696 | 0 | ? ARRAY_SIZE (alt_patt) |
1697 | 0 | : ARRAY_SIZE (alt64_patt); |
1698 | | /* Limit number of NOPs to 7 for newer processors. */ |
1699 | 0 | max_number_of_nops = 7; |
1700 | 0 | } |
1701 | 0 | } |
1702 | | |
1703 | 0 | if (limit == 0) |
1704 | 0 | limit = max_single_nop_size; |
1705 | |
|
1706 | 0 | if (limit > max_single_nop_size || limit < 1) |
1707 | 0 | { |
1708 | 0 | as_bad_where (fragP->fr_file, fragP->fr_line, |
1709 | 0 | _("invalid single nop size: %d " |
1710 | 0 | "(expect within [0, %d])"), |
1711 | 0 | limit, max_single_nop_size); |
1712 | 0 | return; |
1713 | 0 | } |
1714 | | |
1715 | | /* Emit a plain NOP first when the last thing we saw may not have been |
1716 | | a proper instruction (e.g. a stand-alone prefix or .byte). */ |
1717 | 0 | if (!fragP->tc_frag_data.last_insn_normal) |
1718 | 0 | { |
1719 | 0 | *where++ = 0x90; |
1720 | 0 | --count; |
1721 | 0 | } |
1722 | |
|
1723 | 0 | if ((count / max_single_nop_size) > max_number_of_nops) |
1724 | 0 | { |
1725 | | /* Generate jump over NOPs. */ |
1726 | 0 | offsetT disp = count - 2; |
1727 | 0 | if (fits_in_imm7 (disp)) |
1728 | 0 | { |
1729 | | /* Use "jmp disp8" if possible. */ |
1730 | 0 | count = disp; |
1731 | 0 | where[0] = jump_disp8[0]; |
1732 | 0 | where[1] = count; |
1733 | 0 | where += 2; |
1734 | 0 | } |
1735 | 0 | else |
1736 | 0 | { |
1737 | 0 | unsigned int size_of_jump; |
1738 | |
|
1739 | 0 | if (flag_code == CODE_16BIT) |
1740 | 0 | { |
1741 | 0 | where[0] = jump16_disp32[0]; |
1742 | 0 | where[1] = jump16_disp32[1]; |
1743 | 0 | size_of_jump = 2; |
1744 | 0 | } |
1745 | 0 | else |
1746 | 0 | { |
1747 | 0 | where[0] = jump32_disp32[0]; |
1748 | 0 | size_of_jump = 1; |
1749 | 0 | } |
1750 | |
|
1751 | 0 | count -= size_of_jump + 4; |
1752 | 0 | if (!fits_in_imm31 (count)) |
1753 | 0 | { |
1754 | 0 | as_bad_where (fragP->fr_file, fragP->fr_line, |
1755 | 0 | _("jump over nop padding out of range")); |
1756 | 0 | return; |
1757 | 0 | } |
1758 | | |
1759 | 0 | md_number_to_chars (where + size_of_jump, count, 4); |
1760 | 0 | where += size_of_jump + 4; |
1761 | 0 | } |
1762 | 0 | } |
1763 | | |
1764 | 0 | int non_repeat = count % limit; |
1765 | 0 | if (non_repeat) |
1766 | 0 | { |
1767 | 0 | memcpy (where, patt[non_repeat - 1], non_repeat); |
1768 | 0 | where += non_repeat; |
1769 | 0 | count -= non_repeat; |
1770 | 0 | } |
1771 | |
|
1772 | 0 | if (fragP->fr_type != rs_machine_dependent) |
1773 | 0 | { |
1774 | | /* Set up the frag so that everything we have emitted so far is |
1775 | | included in fr_fix. The repeating larger nop only needs to |
1776 | | be written once to the frag memory. */ |
1777 | 0 | fragP->fr_fix = where - fragP->fr_literal; |
1778 | 0 | if (count != 0) |
1779 | 0 | { |
1780 | 0 | fragP->fr_var = limit; |
1781 | 0 | count = limit; |
1782 | 0 | } |
1783 | 0 | } |
1784 | |
|
1785 | 0 | const unsigned char *nops = patt[limit - 1]; |
1786 | 0 | while (count) |
1787 | 0 | { |
1788 | 0 | memcpy (where, nops, limit); |
1789 | 0 | where += limit; |
1790 | 0 | count -= limit; |
1791 | 0 | } |
1792 | 0 | } |
1793 | | |
1794 | | static INLINE int |
1795 | | operand_type_all_zero (const union i386_operand_type *x) |
1796 | 17.3k | { |
1797 | 17.3k | switch (ARRAY_SIZE(x->array)) |
1798 | 17.3k | { |
1799 | 0 | case 3: |
1800 | 0 | if (x->array[2]) |
1801 | 0 | return 0; |
1802 | | /* Fall through. */ |
1803 | 0 | case 2: |
1804 | 0 | if (x->array[1]) |
1805 | 0 | return 0; |
1806 | | /* Fall through. */ |
1807 | 17.3k | case 1: |
1808 | 17.3k | return !x->array[0]; |
1809 | 0 | default: |
1810 | 0 | abort (); |
1811 | 17.3k | } |
1812 | 17.3k | } |
1813 | | |
1814 | | static INLINE void |
1815 | | operand_type_set (union i386_operand_type *x, unsigned int v) |
1816 | 49.3k | { |
1817 | 49.3k | switch (ARRAY_SIZE(x->array)) |
1818 | 49.3k | { |
1819 | 0 | case 3: |
1820 | 0 | x->array[2] = v; |
1821 | | /* Fall through. */ |
1822 | 0 | case 2: |
1823 | 0 | x->array[1] = v; |
1824 | | /* Fall through. */ |
1825 | 49.3k | case 1: |
1826 | 49.3k | x->array[0] = v; |
1827 | | /* Fall through. */ |
1828 | 49.3k | break; |
1829 | 0 | default: |
1830 | 0 | abort (); |
1831 | 49.3k | } |
1832 | | |
1833 | 49.3k | x->bitfield.class = ClassNone; |
1834 | 49.3k | x->bitfield.instance = InstanceNone; |
1835 | 49.3k | } |
1836 | | |
1837 | | static INLINE int |
1838 | | operand_type_equal (const union i386_operand_type *x, |
1839 | | const union i386_operand_type *y) |
1840 | 0 | { |
1841 | 0 | switch (ARRAY_SIZE(x->array)) |
1842 | 0 | { |
1843 | 0 | case 3: |
1844 | 0 | if (x->array[2] != y->array[2]) |
1845 | 0 | return 0; |
1846 | | /* Fall through. */ |
1847 | 0 | case 2: |
1848 | 0 | if (x->array[1] != y->array[1]) |
1849 | 0 | return 0; |
1850 | | /* Fall through. */ |
1851 | 0 | case 1: |
1852 | 0 | return x->array[0] == y->array[0]; |
1853 | 0 | break; |
1854 | 0 | default: |
1855 | 0 | abort (); |
1856 | 0 | } |
1857 | 0 | } |
1858 | | |
1859 | | static INLINE bool |
1860 | | _is_cpu (const i386_cpu_attr *a, enum i386_cpu cpu) |
1861 | 69.9k | { |
1862 | 69.9k | switch (cpu) |
1863 | 69.9k | { |
1864 | 1.45k | case Cpu287: return a->bitfield.cpu287; |
1865 | 1.45k | case Cpu387: return a->bitfield.cpu387; |
1866 | 0 | case Cpu3dnow: return a->bitfield.cpu3dnow; |
1867 | 0 | case Cpu3dnowA: return a->bitfield.cpu3dnowa; |
1868 | 4.11k | case CpuAVX: return a->bitfield.cpuavx; |
1869 | 13 | case CpuHLE: return a->bitfield.cpuhle; |
1870 | 1.47k | case CpuAVX512F: return a->bitfield.cpuavx512f; |
1871 | 1.45k | case CpuAVX512VL: return a->bitfield.cpuavx512vl; |
1872 | 4.47k | case CpuAPX_F: return a->bitfield.cpuapx_f; |
1873 | 0 | case CpuAVX10_2: return a->bitfield.cpuavx10_2; |
1874 | 0 | case CpuAMX_TRANSPOSE: return a->bitfield.cpuamx_transpose; |
1875 | 0 | case Cpu64: return a->bitfield.cpu64; |
1876 | 0 | case CpuNo64: return a->bitfield.cpuno64; |
1877 | 55.5k | default: |
1878 | 55.5k | gas_assert (cpu < CpuAttrEnums); |
1879 | 69.9k | } |
1880 | 55.5k | return a->bitfield.isa == cpu + 1u; |
1881 | 69.9k | } |
1882 | | |
1883 | | static INLINE bool |
1884 | | is_cpu (const insn_template *t, enum i386_cpu cpu) |
1885 | 67.3k | { |
1886 | 67.3k | return _is_cpu(&t->cpu, cpu); |
1887 | 67.3k | } |
1888 | | |
1889 | | static INLINE bool |
1890 | | maybe_cpu (const insn_template *t, enum i386_cpu cpu) |
1891 | 2.62k | { |
1892 | 2.62k | return _is_cpu(&t->cpu_any, cpu); |
1893 | 2.62k | } |
1894 | | |
1895 | | static i386_cpu_flags cpu_flags_from_attr (i386_cpu_attr a) |
1896 | 376k | { |
1897 | 376k | const unsigned int bps = sizeof (a.array[0]) * CHAR_BIT; |
1898 | 376k | i386_cpu_flags f = { .array[0] = 0 }; |
1899 | | |
1900 | 376k | switch (ARRAY_SIZE (a.array)) |
1901 | 376k | { |
1902 | 376k | case 1: |
1903 | 376k | f.array[CpuAttrEnums / bps] |
1904 | 376k | #ifndef WORDS_BIGENDIAN |
1905 | 376k | |= (a.array[0] >> CpuIsaBits) << (CpuAttrEnums % bps); |
1906 | | #else |
1907 | | |= (a.array[0] << CpuIsaBits) >> (CpuAttrEnums % bps); |
1908 | | #endif |
1909 | 376k | if (CpuMax / bps > CpuAttrEnums / bps) |
1910 | 0 | f.array[CpuAttrEnums / bps + 1] |
1911 | 0 | #ifndef WORDS_BIGENDIAN |
1912 | 0 | = (a.array[0] >> CpuIsaBits) >> (bps - CpuAttrEnums % bps); |
1913 | | #else |
1914 | | = (a.array[0] << CpuIsaBits) << (bps - CpuAttrEnums % bps); |
1915 | | #endif |
1916 | 376k | break; |
1917 | | |
1918 | 0 | default: |
1919 | 0 | abort (); |
1920 | 376k | } |
1921 | | |
1922 | 376k | if (a.bitfield.isa) |
1923 | 6.32k | #ifndef WORDS_BIGENDIAN |
1924 | 6.32k | f.array[(a.bitfield.isa - 1) / bps] |= 1u << ((a.bitfield.isa - 1) % bps); |
1925 | | #else |
1926 | | f.array[(a.bitfield.isa - 1) / bps] |= 1u << (~(a.bitfield.isa - 1) % bps); |
1927 | | #endif |
1928 | | |
1929 | 376k | return f; |
1930 | 376k | } |
1931 | | |
1932 | | static INLINE int |
1933 | | cpu_flags_all_zero (const union i386_cpu_flags *x) |
1934 | 398k | { |
1935 | 398k | switch (ARRAY_SIZE(x->array)) |
1936 | 398k | { |
1937 | 398k | case 5: |
1938 | 398k | if (x->array[4]) |
1939 | 156k | return 0; |
1940 | | /* Fall through. */ |
1941 | 241k | case 4: |
1942 | 241k | if (x->array[3]) |
1943 | 16 | return 0; |
1944 | | /* Fall through. */ |
1945 | 241k | case 3: |
1946 | 241k | if (x->array[2]) |
1947 | 104 | return 0; |
1948 | | /* Fall through. */ |
1949 | 241k | case 2: |
1950 | 241k | if (x->array[1]) |
1951 | 322 | return 0; |
1952 | | /* Fall through. */ |
1953 | 241k | case 1: |
1954 | 241k | return !x->array[0]; |
1955 | 0 | default: |
1956 | 0 | abort (); |
1957 | 398k | } |
1958 | 398k | } |
1959 | | |
1960 | | static INLINE int |
1961 | | cpu_flags_equal (const union i386_cpu_flags *x, |
1962 | | const union i386_cpu_flags *y) |
1963 | 91.2k | { |
1964 | 91.2k | switch (ARRAY_SIZE(x->array)) |
1965 | 91.2k | { |
1966 | 91.2k | case 5: |
1967 | 91.2k | if (x->array[4] != y->array[4]) |
1968 | 49.0k | return 0; |
1969 | | /* Fall through. */ |
1970 | 42.2k | case 4: |
1971 | 42.2k | if (x->array[3] != y->array[3]) |
1972 | 15 | return 0; |
1973 | | /* Fall through. */ |
1974 | 42.2k | case 3: |
1975 | 42.2k | if (x->array[2] != y->array[2]) |
1976 | 92 | return 0; |
1977 | | /* Fall through. */ |
1978 | 42.1k | case 2: |
1979 | 42.1k | if (x->array[1] != y->array[1]) |
1980 | 202 | return 0; |
1981 | | /* Fall through. */ |
1982 | 41.9k | case 1: |
1983 | 41.9k | return x->array[0] == y->array[0]; |
1984 | 0 | break; |
1985 | 0 | default: |
1986 | 0 | abort (); |
1987 | 91.2k | } |
1988 | 91.2k | } |
1989 | | |
1990 | | static INLINE int |
1991 | | cpu_flags_check_cpu64 (const insn_template *t) |
1992 | 186k | { |
1993 | 186k | return flag_code == CODE_64BIT |
1994 | 186k | ? !t->cpu.bitfield.cpuno64 |
1995 | 186k | : !t->cpu.bitfield.cpu64; |
1996 | 186k | } |
1997 | | |
1998 | | static INLINE i386_cpu_flags |
1999 | | cpu_flags_and (i386_cpu_flags x, i386_cpu_flags y) |
2000 | 135k | { |
2001 | 135k | switch (ARRAY_SIZE (x.array)) |
2002 | 135k | { |
2003 | 135k | case 5: |
2004 | 135k | x.array [4] &= y.array [4]; |
2005 | | /* Fall through. */ |
2006 | 135k | case 4: |
2007 | 135k | x.array [3] &= y.array [3]; |
2008 | | /* Fall through. */ |
2009 | 135k | case 3: |
2010 | 135k | x.array [2] &= y.array [2]; |
2011 | | /* Fall through. */ |
2012 | 135k | case 2: |
2013 | 135k | x.array [1] &= y.array [1]; |
2014 | | /* Fall through. */ |
2015 | 135k | case 1: |
2016 | 135k | x.array [0] &= y.array [0]; |
2017 | 135k | break; |
2018 | 0 | default: |
2019 | 0 | abort (); |
2020 | 135k | } |
2021 | 135k | return x; |
2022 | 135k | } |
2023 | | |
2024 | | static INLINE i386_cpu_flags |
2025 | | cpu_flags_or (i386_cpu_flags x, i386_cpu_flags y) |
2026 | 0 | { |
2027 | 0 | switch (ARRAY_SIZE (x.array)) |
2028 | 0 | { |
2029 | 0 | case 5: |
2030 | 0 | x.array [4] |= y.array [4]; |
2031 | | /* Fall through. */ |
2032 | 0 | case 4: |
2033 | 0 | x.array [3] |= y.array [3]; |
2034 | | /* Fall through. */ |
2035 | 0 | case 3: |
2036 | 0 | x.array [2] |= y.array [2]; |
2037 | | /* Fall through. */ |
2038 | 0 | case 2: |
2039 | 0 | x.array [1] |= y.array [1]; |
2040 | | /* Fall through. */ |
2041 | 0 | case 1: |
2042 | 0 | x.array [0] |= y.array [0]; |
2043 | 0 | break; |
2044 | 0 | default: |
2045 | 0 | abort (); |
2046 | 0 | } |
2047 | 0 | return x; |
2048 | 0 | } |
2049 | | |
2050 | | static INLINE i386_cpu_flags |
2051 | | cpu_flags_and_not (i386_cpu_flags x, i386_cpu_flags y) |
2052 | 12.7k | { |
2053 | 12.7k | switch (ARRAY_SIZE (x.array)) |
2054 | 12.7k | { |
2055 | 12.7k | case 5: |
2056 | 12.7k | x.array [4] &= ~y.array [4]; |
2057 | | /* Fall through. */ |
2058 | 12.7k | case 4: |
2059 | 12.7k | x.array [3] &= ~y.array [3]; |
2060 | | /* Fall through. */ |
2061 | 12.7k | case 3: |
2062 | 12.7k | x.array [2] &= ~y.array [2]; |
2063 | | /* Fall through. */ |
2064 | 12.7k | case 2: |
2065 | 12.7k | x.array [1] &= ~y.array [1]; |
2066 | | /* Fall through. */ |
2067 | 12.7k | case 1: |
2068 | 12.7k | x.array [0] &= ~y.array [0]; |
2069 | 12.7k | break; |
2070 | 0 | default: |
2071 | 0 | abort (); |
2072 | 12.7k | } |
2073 | 12.7k | return x; |
2074 | 12.7k | } |
2075 | | |
2076 | | static const i386_cpu_flags avx512 = CPU_ANY_AVX512F_FLAGS; |
2077 | | |
2078 | | static INLINE bool need_evex_encoding (const insn_template *t) |
2079 | 35.7k | { |
2080 | 35.7k | return pp.encoding == encoding_evex |
2081 | 35.7k | || pp.encoding == encoding_evex512 |
2082 | 35.7k | || pp.has_nf |
2083 | 35.7k | || (t->opcode_modifier.vex && pp.encoding == encoding_egpr) |
2084 | 35.7k | || i.mask.reg; |
2085 | 35.7k | } |
2086 | | |
2087 | 320k | #define CPU_FLAGS_ARCH_MATCH 0x1 |
2088 | 395k | #define CPU_FLAGS_64BIT_MATCH 0x2 |
2089 | | |
2090 | | #define CPU_FLAGS_PERFECT_MATCH \ |
2091 | 184k | (CPU_FLAGS_ARCH_MATCH | CPU_FLAGS_64BIT_MATCH) |
2092 | | |
2093 | | static INLINE bool set_oszc_flags (unsigned int oszc_shift) |
2094 | 0 | { |
2095 | 0 | if (i.oszc_flags & oszc_shift) |
2096 | 0 | { |
2097 | 0 | as_bad (_("same oszc flag used twice")); |
2098 | 0 | return false; |
2099 | 0 | } |
2100 | 0 | i.oszc_flags |= oszc_shift; |
2101 | 0 | return true; |
2102 | 0 | } |
2103 | | |
2104 | | /* Handle SCC OSZC flags. */ |
2105 | | |
2106 | | static int |
2107 | | check_Scc_OszcOperations (const char *l) |
2108 | 26 | { |
2109 | 26 | const char *suffix_string = l; |
2110 | | |
2111 | 26 | while (is_whitespace (*suffix_string)) |
2112 | 0 | suffix_string++; |
2113 | | |
2114 | | /* If {oszc flags} is absent, just return. */ |
2115 | 26 | if (*suffix_string != '{') |
2116 | 26 | return 0; |
2117 | | |
2118 | | /* Skip '{'. */ |
2119 | 0 | suffix_string++; |
2120 | | |
2121 | | /* For .insn require 'scc=' as the first element. */ |
2122 | 0 | if (dot_insn ()) |
2123 | 0 | { |
2124 | 0 | char *copy; |
2125 | 0 | valueT val; |
2126 | |
|
2127 | 0 | while (is_whitespace (*suffix_string)) |
2128 | 0 | suffix_string++; |
2129 | |
|
2130 | 0 | if (strncasecmp (suffix_string, "scc", 3) == 0) |
2131 | 0 | suffix_string += 3; |
2132 | 0 | else |
2133 | 0 | { |
2134 | 0 | as_bad (_("unrecognized pseudo-suffix")); |
2135 | 0 | return -1; |
2136 | 0 | } |
2137 | | |
2138 | 0 | while (is_whitespace (*suffix_string)) |
2139 | 0 | suffix_string++; |
2140 | |
|
2141 | 0 | if (*suffix_string == '=') |
2142 | 0 | suffix_string++; |
2143 | 0 | else |
2144 | 0 | { |
2145 | 0 | as_bad (_("unrecognized pseudo-suffix")); |
2146 | 0 | return -1; |
2147 | 0 | } |
2148 | | |
2149 | 0 | copy = xstrdup (suffix_string); |
2150 | | /* No need to save/restore input_line_pointer; that's done in the |
2151 | | caller already. */ |
2152 | 0 | input_line_pointer = copy; |
2153 | 0 | val = get_absolute_expression (); |
2154 | 0 | suffix_string += input_line_pointer - copy; |
2155 | 0 | free (copy); |
2156 | |
|
2157 | 0 | if (val > 0xf) |
2158 | 0 | { |
2159 | 0 | as_bad (_("scc= value must be between 0 and 15 (decimal)")); |
2160 | 0 | return -1; |
2161 | 0 | } |
2162 | | |
2163 | 0 | i.scc = val; |
2164 | | |
2165 | | /* Permit dfv= to be absent (implying all flag values being zero). */ |
2166 | 0 | if (*suffix_string == '}') |
2167 | 0 | return suffix_string + 1 - l; |
2168 | | |
2169 | 0 | if (*suffix_string != ',') |
2170 | 0 | goto bad; |
2171 | 0 | suffix_string++; |
2172 | 0 | } |
2173 | | |
2174 | | /* Parse 'dfv='. */ |
2175 | 0 | while (is_whitespace (*suffix_string)) |
2176 | 0 | suffix_string++; |
2177 | |
|
2178 | 0 | if (strncasecmp (suffix_string, "dfv", 3) == 0) |
2179 | 0 | suffix_string += 3; |
2180 | 0 | else |
2181 | 0 | { |
2182 | 0 | as_bad (_("unrecognized pseudo-suffix")); |
2183 | 0 | return -1; |
2184 | 0 | } |
2185 | | |
2186 | 0 | while (is_whitespace (*suffix_string)) |
2187 | 0 | suffix_string++; |
2188 | |
|
2189 | 0 | if (*suffix_string == '=') |
2190 | 0 | suffix_string++; |
2191 | 0 | else |
2192 | 0 | { |
2193 | 0 | as_bad (_("unrecognized pseudo-suffix")); |
2194 | 0 | return -1; |
2195 | 0 | } |
2196 | | |
2197 | | /* Parse 'of, sf, zf, cf}'. */ |
2198 | 0 | while (*suffix_string) |
2199 | 0 | { |
2200 | 0 | while (is_whitespace (*suffix_string)) |
2201 | 0 | suffix_string++; |
2202 | | |
2203 | | /* Return for '{dfv=}'. */ |
2204 | 0 | if (*suffix_string == '}') |
2205 | 0 | return suffix_string + 1 - l; |
2206 | | |
2207 | 0 | if (strncasecmp (suffix_string, "of", 2) == 0) |
2208 | 0 | { |
2209 | 0 | if (!set_oszc_flags (OSZC_OF)) |
2210 | 0 | return -1; |
2211 | 0 | } |
2212 | 0 | else if (strncasecmp (suffix_string, "sf", 2) == 0) |
2213 | 0 | { |
2214 | 0 | if (!set_oszc_flags (OSZC_SF)) |
2215 | 0 | return -1; |
2216 | 0 | } |
2217 | 0 | else if (strncasecmp (suffix_string, "zf", 2) == 0) |
2218 | 0 | { |
2219 | 0 | if (!set_oszc_flags (OSZC_ZF)) |
2220 | 0 | return -1; |
2221 | 0 | } |
2222 | 0 | else if (strncasecmp (suffix_string, "cf", 2) == 0) |
2223 | 0 | { |
2224 | 0 | if (!set_oszc_flags (OSZC_CF)) |
2225 | 0 | return -1; |
2226 | 0 | } |
2227 | 0 | else |
2228 | 0 | { |
2229 | 0 | as_bad (_("unrecognized oszc flags or illegal `,' in pseudo-suffix")); |
2230 | 0 | return -1; |
2231 | 0 | } |
2232 | | |
2233 | 0 | suffix_string += 2; |
2234 | |
|
2235 | 0 | while (is_whitespace (*suffix_string)) |
2236 | 0 | suffix_string++; |
2237 | |
|
2238 | 0 | if (*suffix_string == '}') |
2239 | 0 | return ++suffix_string - l; |
2240 | | |
2241 | 0 | if (*suffix_string != ',') |
2242 | 0 | break; |
2243 | 0 | suffix_string ++; |
2244 | 0 | } |
2245 | | |
2246 | 0 | bad: |
2247 | 0 | as_bad (_("missing `}' or `,' in pseudo-suffix")); |
2248 | 0 | return -1; |
2249 | 0 | } |
2250 | | |
2251 | | /* Return CPU flags match bits. */ |
2252 | | |
2253 | | static int |
2254 | | cpu_flags_match (const insn_template *t) |
2255 | 186k | { |
2256 | 186k | i386_cpu_flags cpu, active, all = cpu_flags_from_attr (t->cpu); |
2257 | 186k | i386_cpu_flags any = cpu_flags_from_attr (t->cpu_any); |
2258 | 186k | int match = cpu_flags_check_cpu64 (t) ? CPU_FLAGS_64BIT_MATCH : 0; |
2259 | | |
2260 | 186k | all.bitfield.cpu64 = 0; |
2261 | 186k | all.bitfield.cpuno64 = 0; |
2262 | 186k | gas_assert (!any.bitfield.cpu64); |
2263 | 186k | gas_assert (!any.bitfield.cpuno64); |
2264 | | |
2265 | 186k | if (cpu_flags_all_zero (&all) && cpu_flags_all_zero (&any)) |
2266 | 95.6k | { |
2267 | | /* This instruction is available on all archs. */ |
2268 | 95.6k | return match | CPU_FLAGS_ARCH_MATCH; |
2269 | 95.6k | } |
2270 | | |
2271 | | /* This instruction is available only on some archs. */ |
2272 | | |
2273 | | /* Dual VEX/EVEX templates may need stripping of one of the flags. */ |
2274 | 91.0k | if (t->opcode_modifier.vex && t->opcode_modifier.evex) |
2275 | 35.7k | { |
2276 | | /* Dual AVX/AVX512 templates need to retain AVX512* only if we already |
2277 | | know that EVEX encoding will be needed. */ |
2278 | 35.7k | if ((any.bitfield.cpuavx || any.bitfield.cpuavx2 || any.bitfield.cpufma) |
2279 | 35.7k | && (any.bitfield.cpuavx512f || any.bitfield.cpuavx512vl)) |
2280 | 35.6k | { |
2281 | 35.6k | if (need_evex_encoding (t)) |
2282 | 0 | { |
2283 | 0 | any.bitfield.cpuavx = 0; |
2284 | 0 | any.bitfield.cpuavx2 = 0; |
2285 | 0 | any.bitfield.cpufma = 0; |
2286 | 0 | } |
2287 | | /* need_evex_encoding(t) isn't reliable before operands were |
2288 | | parsed. */ |
2289 | 35.6k | else if (i.operands) |
2290 | 0 | { |
2291 | 0 | any.bitfield.cpuavx512f = 0; |
2292 | 0 | any.bitfield.cpuavx512vl = 0; |
2293 | 0 | } |
2294 | 35.6k | } |
2295 | | |
2296 | | /* Dual non-APX/APX templates need massaging from what APX_F() in the |
2297 | | opcode table has produced. While the direct transformation of the |
2298 | | incoming cpuid&(cpuid|APX_F) would be to cpuid&(cpuid) / cpuid&(APX_F) |
2299 | | respectively, it's cheaper to move to just cpuid / cpuid&APX_F |
2300 | | instead. */ |
2301 | 35.7k | if (any.bitfield.cpuapx_f |
2302 | 35.7k | && (any.bitfield.cpubmi || any.bitfield.cpubmi2 |
2303 | 76 | || any.bitfield.cpuavx512f || any.bitfield.cpuavx512bw |
2304 | 76 | || any.bitfield.cpuavx512dq || any.bitfield.cpuamx_tile |
2305 | 76 | || any.bitfield.cpucmpccxadd || any.bitfield.cpuuser_msr |
2306 | 76 | || any.bitfield.cpumsr_imm || any.bitfield.cpuamx_transpose |
2307 | 76 | || any.bitfield.cpuamx_movrs)) |
2308 | 76 | { |
2309 | | /* These checks (verifying that APX_F() was properly used in the |
2310 | | opcode table entry) make sure there's no need for an "else" to |
2311 | | the "if()" below. */ |
2312 | 76 | gas_assert (!cpu_flags_all_zero (&all)); |
2313 | | |
2314 | 76 | cpu = cpu_flags_and (all, any); |
2315 | 76 | gas_assert (cpu_flags_equal (&cpu, &all)); |
2316 | | |
2317 | 76 | if (need_evex_encoding (t)) |
2318 | 0 | all = any; |
2319 | | |
2320 | 76 | memset (&any, 0, sizeof (any)); |
2321 | 76 | } |
2322 | 35.7k | } |
2323 | | |
2324 | 91.0k | if (flag_code != CODE_64BIT) |
2325 | 12.5k | active = cpu_flags_and_not (cpu_arch_flags, cpu_64_flags); |
2326 | 78.5k | else |
2327 | 78.5k | active = cpu_arch_flags; |
2328 | 91.0k | cpu = cpu_flags_and (all, active); |
2329 | 91.0k | if (cpu_flags_equal (&cpu, &all)) |
2330 | 41.5k | { |
2331 | | /* AVX and AVX2 present at the same time express an operand size |
2332 | | dependency - strip AVX2 for the purposes here. The operand size |
2333 | | dependent check occurs in check_vecOperands(). */ |
2334 | 41.5k | if (any.bitfield.cpuavx && any.bitfield.cpuavx2) |
2335 | 48 | any.bitfield.cpuavx2 = 0; |
2336 | | |
2337 | 41.5k | cpu = cpu_flags_and (any, active); |
2338 | 41.5k | if (cpu_flags_all_zero (&any) || !cpu_flags_all_zero (&cpu)) |
2339 | 41.3k | match |= CPU_FLAGS_ARCH_MATCH; |
2340 | 41.5k | } |
2341 | 91.0k | return match; |
2342 | 91.0k | } |
2343 | | |
2344 | | static INLINE i386_operand_type |
2345 | | operand_type_and (i386_operand_type x, i386_operand_type y) |
2346 | 100k | { |
2347 | 100k | if (x.bitfield.class != y.bitfield.class) |
2348 | 26.5k | x.bitfield.class = ClassNone; |
2349 | 100k | if (x.bitfield.instance != y.bitfield.instance) |
2350 | 3.52k | x.bitfield.instance = InstanceNone; |
2351 | | |
2352 | 100k | switch (ARRAY_SIZE (x.array)) |
2353 | 100k | { |
2354 | 0 | case 3: |
2355 | 0 | x.array [2] &= y.array [2]; |
2356 | | /* Fall through. */ |
2357 | 0 | case 2: |
2358 | 0 | x.array [1] &= y.array [1]; |
2359 | | /* Fall through. */ |
2360 | 100k | case 1: |
2361 | 100k | x.array [0] &= y.array [0]; |
2362 | 100k | break; |
2363 | 0 | default: |
2364 | 0 | abort (); |
2365 | 100k | } |
2366 | 100k | return x; |
2367 | 100k | } |
2368 | | |
2369 | | static INLINE i386_operand_type |
2370 | | operand_type_and_not (i386_operand_type x, i386_operand_type y) |
2371 | 41.2k | { |
2372 | 41.2k | gas_assert (y.bitfield.class == ClassNone); |
2373 | 41.2k | gas_assert (y.bitfield.instance == InstanceNone); |
2374 | | |
2375 | 41.2k | switch (ARRAY_SIZE (x.array)) |
2376 | 41.2k | { |
2377 | 0 | case 3: |
2378 | 0 | x.array [2] &= ~y.array [2]; |
2379 | | /* Fall through. */ |
2380 | 0 | case 2: |
2381 | 0 | x.array [1] &= ~y.array [1]; |
2382 | | /* Fall through. */ |
2383 | 41.2k | case 1: |
2384 | 41.2k | x.array [0] &= ~y.array [0]; |
2385 | 41.2k | break; |
2386 | 0 | default: |
2387 | 0 | abort (); |
2388 | 41.2k | } |
2389 | 41.2k | return x; |
2390 | 41.2k | } |
2391 | | |
2392 | | static INLINE i386_operand_type |
2393 | | operand_type_or (i386_operand_type x, i386_operand_type y) |
2394 | 100k | { |
2395 | 100k | gas_assert (x.bitfield.class == ClassNone || |
2396 | 100k | y.bitfield.class == ClassNone || |
2397 | 100k | x.bitfield.class == y.bitfield.class); |
2398 | 100k | gas_assert (x.bitfield.instance == InstanceNone || |
2399 | 100k | y.bitfield.instance == InstanceNone || |
2400 | 100k | x.bitfield.instance == y.bitfield.instance); |
2401 | | |
2402 | 100k | switch (ARRAY_SIZE (x.array)) |
2403 | 100k | { |
2404 | 0 | case 3: |
2405 | 0 | x.array [2] |= y.array [2]; |
2406 | | /* Fall through. */ |
2407 | 0 | case 2: |
2408 | 0 | x.array [1] |= y.array [1]; |
2409 | | /* Fall through. */ |
2410 | 100k | case 1: |
2411 | 100k | x.array [0] |= y.array [0]; |
2412 | 100k | break; |
2413 | 0 | default: |
2414 | 0 | abort (); |
2415 | 100k | } |
2416 | 100k | return x; |
2417 | 100k | } |
2418 | | |
2419 | | static INLINE i386_operand_type |
2420 | | operand_type_xor (i386_operand_type x, i386_operand_type y) |
2421 | 0 | { |
2422 | 0 | gas_assert (y.bitfield.class == ClassNone); |
2423 | 0 | gas_assert (y.bitfield.instance == InstanceNone); |
2424 | | |
2425 | 0 | switch (ARRAY_SIZE (x.array)) |
2426 | 0 | { |
2427 | 0 | case 3: |
2428 | 0 | x.array [2] ^= y.array [2]; |
2429 | | /* Fall through. */ |
2430 | 0 | case 2: |
2431 | 0 | x.array [1] ^= y.array [1]; |
2432 | | /* Fall through. */ |
2433 | 0 | case 1: |
2434 | 0 | x.array [0] ^= y.array [0]; |
2435 | 0 | break; |
2436 | 0 | default: |
2437 | 0 | abort (); |
2438 | 0 | } |
2439 | 0 | return x; |
2440 | 0 | } |
2441 | | |
2442 | | static const i386_operand_type anydisp = { |
2443 | | .bitfield = { .disp8 = 1, .disp16 = 1, .disp32 = 1, .disp64 = 1 } |
2444 | | }; |
2445 | | |
2446 | | enum operand_type |
2447 | | { |
2448 | | reg, |
2449 | | imm, |
2450 | | disp, |
2451 | | anymem |
2452 | | }; |
2453 | | |
2454 | | static INLINE int |
2455 | | operand_type_check (i386_operand_type t, enum operand_type c) |
2456 | 123k | { |
2457 | 123k | switch (c) |
2458 | 123k | { |
2459 | 0 | case reg: |
2460 | 0 | return t.bitfield.class == Reg; |
2461 | | |
2462 | 12.9k | case imm: |
2463 | 12.9k | return (t.bitfield.imm8 |
2464 | 12.9k | || t.bitfield.imm8s |
2465 | 12.9k | || t.bitfield.imm16 |
2466 | 12.9k | || t.bitfield.imm32 |
2467 | 12.9k | || t.bitfield.imm32s |
2468 | 12.9k | || t.bitfield.imm64); |
2469 | | |
2470 | 100k | case disp: |
2471 | 100k | return (t.bitfield.disp8 |
2472 | 100k | || t.bitfield.disp16 |
2473 | 100k | || t.bitfield.disp32 |
2474 | 100k | || t.bitfield.disp64); |
2475 | | |
2476 | 9.81k | case anymem: |
2477 | 9.81k | return (t.bitfield.disp8 |
2478 | 9.81k | || t.bitfield.disp16 |
2479 | 9.81k | || t.bitfield.disp32 |
2480 | 9.81k | || t.bitfield.disp64 |
2481 | 9.81k | || t.bitfield.baseindex); |
2482 | | |
2483 | 0 | default: |
2484 | 0 | abort (); |
2485 | 123k | } |
2486 | | |
2487 | 0 | return 0; |
2488 | 123k | } |
2489 | | |
2490 | | /* Return 1 if there is no conflict in 8bit/16bit/32bit/64bit size |
2491 | | between operand GIVEN and operand WANTED for instruction template T. */ |
2492 | | |
2493 | | static INLINE int |
2494 | | match_operand_size (const insn_template *t, unsigned int wanted, |
2495 | | unsigned int given) |
2496 | 6.35k | { |
2497 | 6.35k | return !((i.types[given].bitfield.byte |
2498 | 6.35k | && !t->operand_types[wanted].bitfield.byte) |
2499 | 6.35k | || (i.types[given].bitfield.word |
2500 | 6.35k | && !t->operand_types[wanted].bitfield.word) |
2501 | 6.35k | || (i.types[given].bitfield.dword |
2502 | 6.35k | && !t->operand_types[wanted].bitfield.dword) |
2503 | 6.35k | || (i.types[given].bitfield.qword |
2504 | 6.35k | && (!t->operand_types[wanted].bitfield.qword |
2505 | | /* Don't allow 64-bit (memory) operands outside of 64-bit |
2506 | | mode, when they're used where a 64-bit GPR could also |
2507 | | be used. Checking is needed for Intel Syntax only. */ |
2508 | 0 | || (intel_syntax |
2509 | 0 | && flag_code != CODE_64BIT |
2510 | 0 | && (t->operand_types[wanted].bitfield.class == Reg |
2511 | 0 | || t->opcode_modifier.isstring))))); |
2512 | 6.35k | } |
2513 | | |
2514 | | /* Return 1 if there is no conflict in 80bit size |
2515 | | between operand GIVEN and operand WANTED for instruction template T. */ |
2516 | | |
2517 | | static INLINE int |
2518 | | match_fp_size (const insn_template *t, unsigned int wanted, |
2519 | | unsigned int given) |
2520 | 0 | { |
2521 | 0 | return !i.types[given].bitfield.tbyte |
2522 | 0 | || t->operand_types[wanted].bitfield.tbyte; |
2523 | 0 | } |
2524 | | |
2525 | | /* Return 1 if there is no conflict in SIMD register between operand |
2526 | | GIVEN and operand WANTED for instruction template T. */ |
2527 | | |
2528 | | static INLINE int |
2529 | | match_simd_size (const insn_template *t, unsigned int wanted, |
2530 | | unsigned int given) |
2531 | 6.26k | { |
2532 | 6.26k | return !((i.types[given].bitfield.xmmword |
2533 | 6.26k | && !t->operand_types[wanted].bitfield.xmmword) |
2534 | 6.26k | || (i.types[given].bitfield.ymmword |
2535 | 6.26k | && !t->operand_types[wanted].bitfield.ymmword) |
2536 | 6.26k | || (i.types[given].bitfield.zmmword |
2537 | 6.26k | && !t->operand_types[wanted].bitfield.zmmword) |
2538 | 6.26k | || (i.types[given].bitfield.tmmword |
2539 | 6.26k | && !t->operand_types[wanted].bitfield.tmmword)); |
2540 | 6.26k | } |
2541 | | |
2542 | | /* Return 1 if there is no conflict in any size between operand GIVEN |
2543 | | and operand WANTED for instruction template T. */ |
2544 | | |
2545 | | static INLINE int |
2546 | | match_mem_size (const insn_template *t, unsigned int wanted, |
2547 | | unsigned int given) |
2548 | 6.35k | { |
2549 | 6.35k | return (match_operand_size (t, wanted, given) |
2550 | 6.35k | && (!i.types[given].bitfield.tbyte |
2551 | 6.35k | || t->operand_types[wanted].bitfield.tbyte) |
2552 | 6.35k | && !((i.types[given].bitfield.unspecified |
2553 | 6.35k | && !i.broadcast.type |
2554 | 6.35k | && !i.broadcast.bytes |
2555 | 6.35k | && !t->operand_types[wanted].bitfield.unspecified) |
2556 | 6.35k | || (i.types[given].bitfield.fword |
2557 | 6.35k | && !t->operand_types[wanted].bitfield.fword) |
2558 | | /* For scalar opcode templates to allow register and memory |
2559 | | operands at the same time, some special casing is needed |
2560 | | here. Also for v{,p}broadcast*, {,v}pmov{s,z}*, and |
2561 | | down-conversion vpmov*. */ |
2562 | 6.35k | || ((t->operand_types[wanted].bitfield.class == RegSIMD |
2563 | 6.35k | && t->operand_types[wanted].bitfield.byte |
2564 | 89 | + t->operand_types[wanted].bitfield.word |
2565 | 89 | + t->operand_types[wanted].bitfield.dword |
2566 | 89 | + t->operand_types[wanted].bitfield.qword |
2567 | 89 | > !!t->opcode_modifier.broadcast) |
2568 | 6.35k | ? (i.types[given].bitfield.xmmword |
2569 | 89 | || i.types[given].bitfield.ymmword |
2570 | 89 | || i.types[given].bitfield.zmmword) |
2571 | 6.35k | : !match_simd_size(t, wanted, given)))); |
2572 | 6.35k | } |
2573 | | |
2574 | | /* Return value has MATCH_STRAIGHT set if there is no size conflict on any |
2575 | | operands for instruction template T, and it has MATCH_REVERSE set if there |
2576 | | is no size conflict on any operands for the template with operands reversed |
2577 | | (and the template allows for reversing in the first place). */ |
2578 | | |
2579 | 16.6k | #define MATCH_STRAIGHT 1 |
2580 | 4.19k | #define MATCH_REVERSE 2 |
2581 | | |
2582 | | static INLINE unsigned int |
2583 | | operand_size_match (const insn_template *t) |
2584 | 9.05k | { |
2585 | 9.05k | unsigned int j, match = MATCH_STRAIGHT; |
2586 | | |
2587 | | /* Don't check non-absolute jump instructions. */ |
2588 | 9.05k | if (t->opcode_modifier.jump |
2589 | 9.05k | && t->opcode_modifier.jump != JUMP_ABSOLUTE) |
2590 | 500 | return match; |
2591 | | |
2592 | 15.1k | for (j = 0; j < i.imm_operands; j++) |
2593 | | /* Instruction templates with only sign-extended 8-bit immediate |
2594 | | operand also have a second template with full-operand-size |
2595 | | immediate operand under a different opcode. Don't match the |
2596 | | first template if sign-extended 8-bit immediate operand should |
2597 | | be excluded. */ |
2598 | 6.58k | if (pp.no_imm8s |
2599 | 6.58k | && !t->operand_types[j].bitfield.imm8 |
2600 | 6.58k | && t->operand_types[j].bitfield.imm8s) |
2601 | 0 | { |
2602 | 0 | gas_assert (!t->opcode_modifier.d); |
2603 | 0 | return 0; |
2604 | 0 | } |
2605 | | |
2606 | | /* Check memory and accumulator operand size. */ |
2607 | 17.8k | for (; j < i.operands; j++) |
2608 | 9.26k | { |
2609 | 9.26k | if (i.types[j].bitfield.class == Reg |
2610 | 9.26k | && (t->operand_types[j].bitfield.class == Reg |
2611 | 0 | || (t->operand_types[j].bitfield.instance == Accum |
2612 | 0 | && (t->operand_types[j].bitfield.byte |
2613 | 0 | || t->operand_types[j].bitfield.word |
2614 | 0 | || t->operand_types[j].bitfield.dword |
2615 | 0 | || t->operand_types[j].bitfield.qword))) |
2616 | 9.26k | && !match_operand_size (t, j, j)) |
2617 | 0 | { |
2618 | 0 | match = 0; |
2619 | 0 | break; |
2620 | 0 | } |
2621 | | |
2622 | 9.26k | if (i.types[j].bitfield.class == RegFP |
2623 | 9.26k | && (t->operand_types[j].bitfield.class == RegFP |
2624 | 0 | || (t->operand_types[j].bitfield.instance == Accum |
2625 | 0 | && t->operand_types[j].bitfield.tbyte)) |
2626 | 9.26k | && !match_fp_size (t, j, j)) |
2627 | 0 | { |
2628 | 0 | match = 0; |
2629 | 0 | break; |
2630 | 0 | } |
2631 | | |
2632 | 9.26k | if (i.types[j].bitfield.class == RegSIMD |
2633 | 9.26k | && (t->operand_types[j].bitfield.class == RegSIMD |
2634 | 0 | || (t->operand_types[j].bitfield.instance == Accum |
2635 | | /* Note: %ymm0, %zmm0, and %tmm0 aren't marked Accum. */ |
2636 | 0 | && t->operand_types[j].bitfield.xmmword)) |
2637 | 9.26k | && !match_simd_size (t, j, j)) |
2638 | 0 | { |
2639 | 0 | match = 0; |
2640 | 0 | break; |
2641 | 0 | } |
2642 | | |
2643 | 9.26k | if ((i.flags[j] & Operand_Mem) |
2644 | 9.26k | && operand_type_check (t->operand_types[j], anymem) |
2645 | 9.26k | && t->opcode_modifier.operandconstraint != ANY_SIZE |
2646 | 9.26k | && !match_mem_size (t, j, j)) |
2647 | 0 | { |
2648 | 0 | match = 0; |
2649 | 0 | break; |
2650 | 0 | } |
2651 | 9.26k | } |
2652 | | |
2653 | 8.55k | if (!t->opcode_modifier.d) |
2654 | 6.45k | return match; |
2655 | | |
2656 | | /* Check reverse. */ |
2657 | 2.09k | gas_assert (i.operands >= 2); |
2658 | | |
2659 | 4.47k | for (j = i.imm_operands; j < i.operands; j++) |
2660 | 2.37k | { |
2661 | 2.37k | unsigned int given = i.operands - j - 1; |
2662 | | |
2663 | | /* For FMA4 and XOP insns VEX.W controls just the first two |
2664 | | register operands. And APX_F insns just swap the two source operands, |
2665 | | with the 3rd one being the destination. */ |
2666 | 2.37k | if (is_cpu (t, CpuFMA4) || is_cpu (t, CpuXOP) |
2667 | 2.37k | || is_cpu (t, CpuAPX_F)) |
2668 | 8 | given = j < 2 ? 1 - j : j; |
2669 | | |
2670 | 2.37k | if (i.types[given].bitfield.class == Reg |
2671 | 2.37k | && (t->operand_types[j].bitfield.class == Reg |
2672 | 0 | || (t->operand_types[j].bitfield.instance == Accum |
2673 | 0 | && (t->operand_types[j].bitfield.byte |
2674 | 0 | || t->operand_types[j].bitfield.word |
2675 | 0 | || t->operand_types[j].bitfield.dword |
2676 | 0 | || t->operand_types[j].bitfield.qword |
2677 | 0 | || t->operand_types[j].bitfield.tbyte))) |
2678 | 2.37k | && !match_operand_size (t, j, given)) |
2679 | 0 | return match; |
2680 | | |
2681 | 2.37k | if (i.types[given].bitfield.class == RegFP |
2682 | 2.37k | && (t->operand_types[j].bitfield.class == RegFP |
2683 | 0 | || (t->operand_types[j].bitfield.instance == Accum |
2684 | 0 | && t->operand_types[j].bitfield.tbyte)) |
2685 | 2.37k | && !match_fp_size (t, j, given)) |
2686 | 0 | return match; |
2687 | | |
2688 | | /* No need to check for Accum here: There are no such templates with D |
2689 | | set. */ |
2690 | 2.37k | if (i.types[given].bitfield.class == RegSIMD |
2691 | 2.37k | && t->operand_types[j].bitfield.class == RegSIMD |
2692 | 2.37k | && !match_simd_size (t, j, given)) |
2693 | 0 | return match; |
2694 | | |
2695 | 2.37k | if ((i.flags[given] & Operand_Mem) |
2696 | 2.37k | && operand_type_check (t->operand_types[j], anymem) |
2697 | 2.37k | && !match_mem_size (t, j, given)) |
2698 | 0 | return match; |
2699 | 2.37k | } |
2700 | | |
2701 | 2.09k | return match | MATCH_REVERSE; |
2702 | 2.09k | } |
2703 | | |
2704 | | static INLINE int |
2705 | | operand_type_match (i386_operand_type overlap, |
2706 | | i386_operand_type given) |
2707 | 14.4k | { |
2708 | 14.4k | i386_operand_type temp = overlap; |
2709 | | |
2710 | 14.4k | temp.bitfield.unspecified = 0; |
2711 | 14.4k | temp.bitfield.byte = 0; |
2712 | 14.4k | temp.bitfield.word = 0; |
2713 | 14.4k | temp.bitfield.dword = 0; |
2714 | 14.4k | temp.bitfield.fword = 0; |
2715 | 14.4k | temp.bitfield.qword = 0; |
2716 | 14.4k | temp.bitfield.tbyte = 0; |
2717 | 14.4k | temp.bitfield.xmmword = 0; |
2718 | 14.4k | temp.bitfield.ymmword = 0; |
2719 | 14.4k | temp.bitfield.zmmword = 0; |
2720 | 14.4k | temp.bitfield.tmmword = 0; |
2721 | 14.4k | if (operand_type_all_zero (&temp)) |
2722 | 8.21k | goto mismatch; |
2723 | | |
2724 | | /* When a (register) instance is expected, operand size needs checking |
2725 | | to disambiguate. */ |
2726 | 6.26k | if (overlap.bitfield.instance != InstanceNone |
2727 | 6.26k | && !overlap.bitfield.byte |
2728 | 6.26k | && !overlap.bitfield.word |
2729 | 6.26k | && !overlap.bitfield.dword |
2730 | 6.26k | && !overlap.bitfield.qword |
2731 | 6.26k | && !overlap.bitfield.tbyte |
2732 | 6.26k | && !overlap.bitfield.xmmword |
2733 | 6.26k | && !overlap.bitfield.ymmword |
2734 | 6.26k | && !overlap.bitfield.zmmword |
2735 | 6.26k | && !overlap.bitfield.tmmword) |
2736 | 0 | { |
2737 | 0 | gas_assert (overlap.bitfield.class == ClassNone); |
2738 | 0 | goto mismatch; |
2739 | 0 | } |
2740 | | |
2741 | 6.26k | if (given.bitfield.baseindex == overlap.bitfield.baseindex) |
2742 | 6.26k | return 1; |
2743 | | |
2744 | 8.21k | mismatch: |
2745 | 8.21k | i.error = operand_type_mismatch; |
2746 | 8.21k | return 0; |
2747 | 6.26k | } |
2748 | | |
2749 | | /* If given types g0 and g1 are registers they must be of the same type |
2750 | | unless the expected operand type register overlap is null. |
2751 | | Intel syntax sized memory operands are also checked here. */ |
2752 | | |
2753 | | static INLINE int |
2754 | | operand_type_register_match (i386_operand_type g0, |
2755 | | i386_operand_type t0, |
2756 | | i386_operand_type g1, |
2757 | | i386_operand_type t1) |
2758 | 0 | { |
2759 | 0 | if (g0.bitfield.class != Reg |
2760 | 0 | && g0.bitfield.class != RegSIMD |
2761 | 0 | && (g0.bitfield.unspecified |
2762 | 0 | || !operand_type_check (g0, anymem))) |
2763 | 0 | return 1; |
2764 | | |
2765 | 0 | if (g1.bitfield.class != Reg |
2766 | 0 | && g1.bitfield.class != RegSIMD |
2767 | 0 | && (g1.bitfield.unspecified |
2768 | 0 | || !operand_type_check (g1, anymem))) |
2769 | 0 | return 1; |
2770 | | |
2771 | 0 | if (g0.bitfield.byte == g1.bitfield.byte |
2772 | 0 | && g0.bitfield.word == g1.bitfield.word |
2773 | 0 | && g0.bitfield.dword == g1.bitfield.dword |
2774 | 0 | && g0.bitfield.qword == g1.bitfield.qword |
2775 | 0 | && g0.bitfield.xmmword == g1.bitfield.xmmword |
2776 | 0 | && g0.bitfield.ymmword == g1.bitfield.ymmword |
2777 | 0 | && g0.bitfield.zmmword == g1.bitfield.zmmword) |
2778 | 0 | return 1; |
2779 | | |
2780 | | /* If expectations overlap in no more than a single size, all is fine. */ |
2781 | 0 | g0 = operand_type_and (t0, t1); |
2782 | 0 | if (g0.bitfield.byte |
2783 | 0 | + g0.bitfield.word |
2784 | 0 | + g0.bitfield.dword |
2785 | 0 | + g0.bitfield.qword |
2786 | 0 | + g0.bitfield.xmmword |
2787 | 0 | + g0.bitfield.ymmword |
2788 | 0 | + g0.bitfield.zmmword <= 1) |
2789 | 0 | return 1; |
2790 | | |
2791 | 0 | i.error = register_type_mismatch; |
2792 | |
|
2793 | 0 | return 0; |
2794 | 0 | } |
2795 | | |
2796 | | static INLINE unsigned int |
2797 | | register_number (const reg_entry *r) |
2798 | 0 | { |
2799 | 0 | unsigned int nr = r->reg_num; |
2800 | |
|
2801 | 0 | if (r->reg_flags & RegRex) |
2802 | 0 | nr += 8; |
2803 | |
|
2804 | 0 | if (r->reg_flags & (RegVRex | RegRex2)) |
2805 | 0 | nr += 16; |
2806 | |
|
2807 | 0 | return nr; |
2808 | 0 | } |
2809 | | |
2810 | | static INLINE unsigned int |
2811 | | mode_from_disp_size (i386_operand_type t) |
2812 | 0 | { |
2813 | 0 | if (t.bitfield.disp8) |
2814 | 0 | return 1; |
2815 | 0 | else if (t.bitfield.disp16 |
2816 | 0 | || t.bitfield.disp32) |
2817 | 0 | return 2; |
2818 | 0 | else |
2819 | 0 | return 0; |
2820 | 0 | } |
2821 | | |
2822 | | static INLINE int |
2823 | | fits_in_signed_byte (addressT num) |
2824 | 4.48k | { |
2825 | 4.48k | return num + 0x80 <= 0xff; |
2826 | 4.48k | } |
2827 | | |
2828 | | static INLINE int |
2829 | | fits_in_unsigned_byte (addressT num) |
2830 | 2.44k | { |
2831 | 2.44k | return num <= 0xff; |
2832 | 2.44k | } |
2833 | | |
2834 | | static INLINE int |
2835 | | fits_in_unsigned_word (addressT num) |
2836 | 1.90k | { |
2837 | 1.90k | return num <= 0xffff; |
2838 | 1.90k | } |
2839 | | |
2840 | | static INLINE int |
2841 | | fits_in_signed_word (addressT num) |
2842 | 1.53k | { |
2843 | 1.53k | return num + 0x8000 <= 0xffff; |
2844 | 1.53k | } |
2845 | | |
2846 | | static INLINE int |
2847 | | fits_in_signed_long (addressT num ATTRIBUTE_UNUSED) |
2848 | 1.24k | { |
2849 | | #ifndef BFD64 |
2850 | | return 1; |
2851 | | #else |
2852 | 1.24k | return num + 0x80000000 <= 0xffffffff; |
2853 | 1.24k | #endif |
2854 | 1.24k | } /* fits_in_signed_long() */ |
2855 | | |
2856 | | static INLINE int |
2857 | | fits_in_unsigned_long (addressT num ATTRIBUTE_UNUSED) |
2858 | 113k | { |
2859 | | #ifndef BFD64 |
2860 | | return 1; |
2861 | | #else |
2862 | 113k | return num <= 0xffffffff; |
2863 | 113k | #endif |
2864 | 113k | } /* fits_in_unsigned_long() */ |
2865 | | |
2866 | | static INLINE valueT extend_to_32bit_address (addressT num) |
2867 | 0 | { |
2868 | 0 | #ifdef BFD64 |
2869 | 0 | if (fits_in_unsigned_long(num)) |
2870 | 0 | return (num ^ ((addressT) 1 << 31)) - ((addressT) 1 << 31); |
2871 | | |
2872 | 0 | if (!fits_in_signed_long (num)) |
2873 | 0 | return num & 0xffffffff; |
2874 | 0 | #endif |
2875 | | |
2876 | 0 | return num; |
2877 | 0 | } |
2878 | | |
2879 | | static INLINE int |
2880 | | fits_in_disp8 (offsetT num) |
2881 | 2.04k | { |
2882 | 2.04k | int shift = i.memshift; |
2883 | 2.04k | unsigned int mask; |
2884 | | |
2885 | 2.04k | if (shift == -1) |
2886 | 0 | abort (); |
2887 | | |
2888 | 2.04k | mask = (1 << shift) - 1; |
2889 | | |
2890 | | /* Return 0 if NUM isn't properly aligned. */ |
2891 | 2.04k | if ((num & mask)) |
2892 | 0 | return 0; |
2893 | | |
2894 | | /* Check if NUM will fit in 8bit after shift. */ |
2895 | 2.04k | return fits_in_signed_byte (num >> shift); |
2896 | 2.04k | } |
2897 | | |
2898 | | static INLINE int |
2899 | | fits_in_imm4 (offsetT num) |
2900 | 0 | { |
2901 | | /* Despite the name, check for imm3 if we're dealing with EVEX. */ |
2902 | 0 | return (num & (pp.encoding != encoding_evex |
2903 | 0 | && pp.encoding != encoding_egpr ? 0xf : 7)) == num; |
2904 | 0 | } |
2905 | | |
2906 | | static i386_operand_type |
2907 | | smallest_imm_type (offsetT num) |
2908 | 2.45k | { |
2909 | 2.45k | i386_operand_type t; |
2910 | | |
2911 | 2.45k | operand_type_set (&t, 0); |
2912 | 2.45k | t.bitfield.imm64 = 1; |
2913 | | |
2914 | 2.45k | if (cpu_arch_tune != PROCESSOR_I486 && num == 1) |
2915 | 15 | { |
2916 | | /* This code is disabled on the 486 because all the Imm1 forms |
2917 | | in the opcode table are slower on the i486. They're the |
2918 | | versions with the implicitly specified single-position |
2919 | | displacement, which has another syntax if you really want to |
2920 | | use that form. */ |
2921 | 15 | t.bitfield.imm1 = 1; |
2922 | 15 | t.bitfield.imm8 = 1; |
2923 | 15 | t.bitfield.imm8s = 1; |
2924 | 15 | t.bitfield.imm16 = 1; |
2925 | 15 | t.bitfield.imm32 = 1; |
2926 | 15 | t.bitfield.imm32s = 1; |
2927 | 15 | } |
2928 | 2.44k | else if (fits_in_signed_byte (num)) |
2929 | 881 | { |
2930 | 881 | if (fits_in_unsigned_byte (num)) |
2931 | 595 | t.bitfield.imm8 = 1; |
2932 | 881 | t.bitfield.imm8s = 1; |
2933 | 881 | t.bitfield.imm16 = 1; |
2934 | 881 | if (flag_code != CODE_64BIT || fits_in_unsigned_long (num)) |
2935 | 868 | t.bitfield.imm32 = 1; |
2936 | 881 | t.bitfield.imm32s = 1; |
2937 | 881 | } |
2938 | 1.55k | else if (fits_in_unsigned_byte (num)) |
2939 | 20 | { |
2940 | 20 | t.bitfield.imm8 = 1; |
2941 | 20 | t.bitfield.imm16 = 1; |
2942 | 20 | t.bitfield.imm32 = 1; |
2943 | 20 | t.bitfield.imm32s = 1; |
2944 | 20 | } |
2945 | 1.53k | else if (fits_in_signed_word (num) || fits_in_unsigned_word (num)) |
2946 | 414 | { |
2947 | 414 | t.bitfield.imm16 = 1; |
2948 | 414 | if (flag_code != CODE_64BIT || fits_in_unsigned_long (num)) |
2949 | 414 | t.bitfield.imm32 = 1; |
2950 | 414 | t.bitfield.imm32s = 1; |
2951 | 414 | } |
2952 | 1.12k | else if (fits_in_signed_long (num)) |
2953 | 972 | { |
2954 | 972 | if (flag_code != CODE_64BIT || fits_in_unsigned_long (num)) |
2955 | 50 | t.bitfield.imm32 = 1; |
2956 | 972 | t.bitfield.imm32s = 1; |
2957 | 972 | } |
2958 | 153 | else if (fits_in_unsigned_long (num)) |
2959 | 0 | t.bitfield.imm32 = 1; |
2960 | | |
2961 | 2.45k | return t; |
2962 | 2.45k | } |
2963 | | |
2964 | | static offsetT |
2965 | | offset_in_range (offsetT val, int size) |
2966 | 851 | { |
2967 | 851 | addressT mask; |
2968 | | |
2969 | 851 | switch (size) |
2970 | 851 | { |
2971 | 191 | case 1: mask = ((addressT) 1 << 8) - 1; break; |
2972 | 84 | case 2: mask = ((addressT) 1 << 16) - 1; break; |
2973 | 0 | #ifdef BFD64 |
2974 | 576 | case 4: mask = ((addressT) 1 << 32) - 1; break; |
2975 | 0 | #endif |
2976 | 0 | case sizeof (val): return val; |
2977 | 0 | default: abort (); |
2978 | 851 | } |
2979 | | |
2980 | 851 | if ((val & ~mask) != 0 && (-(addressT) val & ~mask) != 0) |
2981 | 33 | as_warn (_("0x%" PRIx64 " shortened to 0x%" PRIx64), |
2982 | 33 | (uint64_t) val, (uint64_t) (val & mask)); |
2983 | | |
2984 | 851 | return val & mask; |
2985 | 851 | } |
2986 | | |
2987 | | static INLINE const char *insn_name (const insn_template *t) |
2988 | 153k | { |
2989 | 153k | return &i386_mnemonics[t->mnem_off]; |
2990 | 153k | } |
2991 | | |
2992 | | enum PREFIX_GROUP |
2993 | | { |
2994 | | PREFIX_EXIST = 0, |
2995 | | PREFIX_LOCK, |
2996 | | PREFIX_REP, |
2997 | | PREFIX_DS, |
2998 | | PREFIX_OTHER |
2999 | | }; |
3000 | | |
3001 | | /* Returns |
3002 | | a. PREFIX_EXIST if attempting to add a prefix where one from the |
3003 | | same class already exists. |
3004 | | b. PREFIX_LOCK if lock prefix is added. |
3005 | | c. PREFIX_REP if rep/repne prefix is added. |
3006 | | d. PREFIX_DS if ds prefix is added. |
3007 | | e. PREFIX_OTHER if other prefix is added. |
3008 | | */ |
3009 | | |
3010 | | static enum PREFIX_GROUP |
3011 | | add_prefix (unsigned int prefix) |
3012 | 35.5k | { |
3013 | 35.5k | enum PREFIX_GROUP ret = PREFIX_OTHER; |
3014 | 35.5k | unsigned int q; |
3015 | | |
3016 | 35.5k | if (prefix >= REX_OPCODE && prefix < REX_OPCODE + 16 |
3017 | 35.5k | && flag_code == CODE_64BIT) |
3018 | 33.4k | { |
3019 | 33.4k | if ((i.prefix[REX_PREFIX] & prefix & REX_W) |
3020 | 33.4k | || (i.prefix[REX_PREFIX] & prefix & REX_R) |
3021 | 33.4k | || (i.prefix[REX_PREFIX] & prefix & REX_X) |
3022 | 33.4k | || (i.prefix[REX_PREFIX] & prefix & REX_B)) |
3023 | 0 | ret = PREFIX_EXIST; |
3024 | 33.4k | q = REX_PREFIX; |
3025 | 33.4k | } |
3026 | 2.08k | else |
3027 | 2.08k | { |
3028 | 2.08k | switch (prefix) |
3029 | 2.08k | { |
3030 | 0 | default: |
3031 | 0 | abort (); |
3032 | | |
3033 | 0 | case DS_PREFIX_OPCODE: |
3034 | 0 | ret = PREFIX_DS; |
3035 | | /* Fall through. */ |
3036 | 38 | case CS_PREFIX_OPCODE: |
3037 | 38 | case ES_PREFIX_OPCODE: |
3038 | 39 | case FS_PREFIX_OPCODE: |
3039 | 39 | case GS_PREFIX_OPCODE: |
3040 | 362 | case SS_PREFIX_OPCODE: |
3041 | 362 | q = SEG_PREFIX; |
3042 | 362 | break; |
3043 | | |
3044 | 0 | case REPNE_PREFIX_OPCODE: |
3045 | 14 | case REPE_PREFIX_OPCODE: |
3046 | 14 | q = REP_PREFIX; |
3047 | 14 | ret = PREFIX_REP; |
3048 | 14 | break; |
3049 | | |
3050 | 5 | case LOCK_PREFIX_OPCODE: |
3051 | 5 | q = LOCK_PREFIX; |
3052 | 5 | ret = PREFIX_LOCK; |
3053 | 5 | break; |
3054 | | |
3055 | 10 | case FWAIT_OPCODE: |
3056 | 10 | q = WAIT_PREFIX; |
3057 | 10 | break; |
3058 | | |
3059 | 25 | case ADDR_PREFIX_OPCODE: |
3060 | 25 | q = ADDR_PREFIX; |
3061 | 25 | break; |
3062 | | |
3063 | 1.67k | case DATA_PREFIX_OPCODE: |
3064 | 1.67k | q = DATA_PREFIX; |
3065 | 1.67k | break; |
3066 | 2.08k | } |
3067 | 2.08k | if (i.prefix[q] != 0) |
3068 | 0 | ret = PREFIX_EXIST; |
3069 | 2.08k | } |
3070 | | |
3071 | 35.5k | if (ret) |
3072 | 35.5k | { |
3073 | 35.5k | if (!i.prefix[q]) |
3074 | 35.5k | ++i.prefixes; |
3075 | 35.5k | i.prefix[q] |= prefix; |
3076 | 35.5k | } |
3077 | 0 | else |
3078 | 0 | as_bad (_("same type of prefix used twice")); |
3079 | | |
3080 | 35.5k | return ret; |
3081 | 35.5k | } |
3082 | | |
3083 | | static void |
3084 | | update_code_flag (int value, int check) |
3085 | 570 | { |
3086 | 570 | PRINTF_LIKE ((*as_error)) = check ? as_fatal : as_bad; |
3087 | | |
3088 | 570 | if (value == CODE_64BIT && !cpu_arch_flags.bitfield.cpu64 ) |
3089 | 0 | { |
3090 | 0 | as_error (_("64bit mode not supported on `%s'."), |
3091 | 0 | cpu_arch_name ? cpu_arch_name : default_arch); |
3092 | 0 | return; |
3093 | 0 | } |
3094 | | |
3095 | 570 | if (value == CODE_32BIT && !cpu_arch_flags.bitfield.cpui386) |
3096 | 0 | { |
3097 | 0 | as_error (_("32bit mode not supported on `%s'."), |
3098 | 0 | cpu_arch_name ? cpu_arch_name : default_arch); |
3099 | 0 | return; |
3100 | 0 | } |
3101 | | |
3102 | 570 | flag_code = (enum flag_code) value; |
3103 | | |
3104 | 570 | stackop_size = '\0'; |
3105 | 570 | } |
3106 | | |
3107 | | static void |
3108 | | set_code_flag (int value) |
3109 | 542 | { |
3110 | 542 | update_code_flag (value, 0); |
3111 | 542 | } |
3112 | | |
3113 | | static void |
3114 | | set_16bit_gcc_code_flag (int new_code_flag) |
3115 | 0 | { |
3116 | 0 | flag_code = (enum flag_code) new_code_flag; |
3117 | 0 | if (flag_code != CODE_16BIT) |
3118 | 0 | abort (); |
3119 | 0 | stackop_size = LONG_MNEM_SUFFIX; |
3120 | 0 | } |
3121 | | |
3122 | | static void |
3123 | | _set_intel_syntax (int syntax_flag) |
3124 | 2 | { |
3125 | 2 | intel_syntax = syntax_flag; |
3126 | | |
3127 | 2 | expr_set_rank (O_full_ptr, syntax_flag ? 10 : 0); |
3128 | | |
3129 | 2 | register_prefix = allow_naked_reg ? "" : "%"; |
3130 | 2 | } |
3131 | | |
3132 | | static void |
3133 | | set_intel_syntax (int syntax_flag) |
3134 | 2 | { |
3135 | | /* Find out if register prefixing is specified. */ |
3136 | 2 | int ask_naked_reg = 0; |
3137 | | |
3138 | 2 | SKIP_WHITESPACE (); |
3139 | 2 | if (!is_end_of_stmt (*input_line_pointer)) |
3140 | 2 | { |
3141 | 2 | char *string; |
3142 | 2 | int e = get_symbol_name (&string); |
3143 | | |
3144 | 2 | if (strcmp (string, "prefix") == 0) |
3145 | 0 | ask_naked_reg = 1; |
3146 | 2 | else if (strcmp (string, "noprefix") == 0) |
3147 | 0 | ask_naked_reg = -1; |
3148 | 2 | else |
3149 | 2 | as_bad (_("bad argument to syntax directive.")); |
3150 | 2 | (void) restore_line_pointer (e); |
3151 | 2 | } |
3152 | 2 | demand_empty_rest_of_line (); |
3153 | | |
3154 | 2 | if (ask_naked_reg == 0) |
3155 | 2 | allow_naked_reg = (syntax_flag |
3156 | 2 | && (bfd_get_symbol_leading_char (stdoutput) != '\0')); |
3157 | 0 | else |
3158 | 0 | allow_naked_reg = (ask_naked_reg < 0); |
3159 | | |
3160 | 2 | _set_intel_syntax (syntax_flag); |
3161 | 2 | } |
3162 | | |
3163 | | static void |
3164 | | set_intel_mnemonic (int mnemonic_flag) |
3165 | 0 | { |
3166 | 0 | intel_mnemonic = mnemonic_flag; |
3167 | 0 | } |
3168 | | |
3169 | | static void |
3170 | | set_allow_index_reg (int flag) |
3171 | 0 | { |
3172 | 0 | allow_index_reg = flag; |
3173 | 0 | } |
3174 | | |
3175 | | static void |
3176 | | set_check (int what) |
3177 | 0 | { |
3178 | 0 | enum check_kind *kind; |
3179 | 0 | const char *str; |
3180 | |
|
3181 | 0 | if (what) |
3182 | 0 | { |
3183 | 0 | kind = &operand_check; |
3184 | 0 | str = "operand"; |
3185 | 0 | } |
3186 | 0 | else |
3187 | 0 | { |
3188 | 0 | kind = &sse_check; |
3189 | 0 | str = "sse"; |
3190 | 0 | } |
3191 | |
|
3192 | 0 | SKIP_WHITESPACE (); |
3193 | |
|
3194 | 0 | if (!is_end_of_stmt (*input_line_pointer)) |
3195 | 0 | { |
3196 | 0 | char *string; |
3197 | 0 | int e = get_symbol_name (&string); |
3198 | |
|
3199 | 0 | if (strcmp (string, "none") == 0) |
3200 | 0 | *kind = check_none; |
3201 | 0 | else if (strcmp (string, "warning") == 0) |
3202 | 0 | *kind = check_warning; |
3203 | 0 | else if (strcmp (string, "error") == 0) |
3204 | 0 | *kind = check_error; |
3205 | 0 | else |
3206 | 0 | as_bad (_("bad argument to %s_check directive."), str); |
3207 | 0 | (void) restore_line_pointer (e); |
3208 | 0 | } |
3209 | 0 | else |
3210 | 0 | as_bad (_("missing argument for %s_check directive"), str); |
3211 | |
|
3212 | 0 | demand_empty_rest_of_line (); |
3213 | 0 | } |
3214 | | |
3215 | | static void |
3216 | | check_cpu_arch_compatible (const char *name ATTRIBUTE_UNUSED, |
3217 | | i386_cpu_flags new_flag ATTRIBUTE_UNUSED) |
3218 | 63 | { |
3219 | | /* Intel MCU is only supported on ELF. */ |
3220 | 63 | #ifdef OBJ_ELF |
3221 | 63 | static const char *arch; |
3222 | | |
3223 | 63 | if (!arch) |
3224 | 1 | { |
3225 | | /* Use cpu_arch_name if it is set in md_parse_option. Otherwise |
3226 | | use default_arch. */ |
3227 | 1 | arch = cpu_arch_name; |
3228 | 1 | if (!arch) |
3229 | 1 | arch = default_arch; |
3230 | 1 | } |
3231 | | |
3232 | | /* If we are targeting Intel MCU, we must enable it. */ |
3233 | 63 | if ((get_elf_backend_data (stdoutput)->elf_machine_code == EM_IAMCU) |
3234 | 63 | == new_flag.bitfield.cpuiamcu) |
3235 | 63 | return; |
3236 | | |
3237 | 0 | as_bad (_("`%s' is not supported on `%s'"), name, arch); |
3238 | 0 | #endif |
3239 | 0 | } |
3240 | | |
3241 | | static void |
3242 | | extend_cpu_sub_arch_name (const char *pfx, const char *name) |
3243 | 3 | { |
3244 | 3 | if (cpu_sub_arch_name) |
3245 | 0 | cpu_sub_arch_name = reconcat (cpu_sub_arch_name, cpu_sub_arch_name, |
3246 | 0 | pfx, name, (const char *) NULL); |
3247 | 3 | else |
3248 | 3 | cpu_sub_arch_name = concat (pfx, name, (const char *) NULL); |
3249 | 3 | } |
3250 | | |
3251 | | static void isa_enable (unsigned int idx) |
3252 | 0 | { |
3253 | 0 | i386_cpu_flags flags = cpu_flags_or (cpu_arch_flags, cpu_arch[idx].enable); |
3254 | |
|
3255 | 0 | if (!cpu_flags_equal (&flags, &cpu_arch_flags)) |
3256 | 0 | { |
3257 | 0 | extend_cpu_sub_arch_name (".", cpu_arch[idx].name); |
3258 | 0 | cpu_arch_flags = flags; |
3259 | 0 | } |
3260 | |
|
3261 | 0 | cpu_arch_isa_flags = cpu_flags_or (cpu_arch_isa_flags, cpu_arch[idx].enable); |
3262 | 0 | } |
3263 | | |
3264 | | static void isa_disable (unsigned int idx) |
3265 | 110 | { |
3266 | 110 | i386_cpu_flags flags |
3267 | 110 | = cpu_flags_and_not (cpu_arch_flags, cpu_arch[idx].disable); |
3268 | | |
3269 | 110 | if (!cpu_flags_equal (&flags, &cpu_arch_flags)) |
3270 | 3 | { |
3271 | 3 | extend_cpu_sub_arch_name (".no", cpu_arch[idx].name); |
3272 | 3 | cpu_arch_flags = flags; |
3273 | 3 | } |
3274 | | |
3275 | 110 | cpu_arch_isa_flags |
3276 | 110 | = cpu_flags_and_not (cpu_arch_isa_flags, cpu_arch[idx].disable); |
3277 | 110 | } |
3278 | | |
3279 | | static void |
3280 | | set_cpu_arch (int dummy ATTRIBUTE_UNUSED) |
3281 | 1.85k | { |
3282 | 1.85k | typedef struct arch_stack_entry |
3283 | 1.85k | { |
3284 | 1.85k | const struct arch_stack_entry *prev; |
3285 | 1.85k | const char *name; |
3286 | 1.85k | char *sub_name; |
3287 | 1.85k | i386_cpu_flags flags; |
3288 | 1.85k | i386_cpu_flags isa_flags; |
3289 | 1.85k | enum processor_type isa; |
3290 | 1.85k | enum flag_code flag_code; |
3291 | 1.85k | unsigned int vector_size; |
3292 | 1.85k | char stackop_size; |
3293 | 1.85k | bool no_cond_jump_promotion; |
3294 | 1.85k | } arch_stack_entry; |
3295 | 1.85k | static const arch_stack_entry *arch_stack_top; |
3296 | 1.85k | char *s; |
3297 | 1.85k | int e; |
3298 | 1.85k | const char *string; |
3299 | 1.85k | unsigned int j = 0; |
3300 | | |
3301 | 1.85k | SKIP_WHITESPACE (); |
3302 | | |
3303 | 1.85k | if (is_end_of_stmt (*input_line_pointer)) |
3304 | 35 | { |
3305 | 35 | as_bad (_("missing cpu architecture")); |
3306 | 35 | input_line_pointer++; |
3307 | 35 | return; |
3308 | 35 | } |
3309 | | |
3310 | 1.81k | e = get_symbol_name (&s); |
3311 | 1.81k | string = s; |
3312 | | |
3313 | 1.81k | if (strcmp (string, "push") == 0) |
3314 | 0 | { |
3315 | 0 | arch_stack_entry *top = XNEW (arch_stack_entry); |
3316 | |
|
3317 | 0 | top->name = cpu_arch_name; |
3318 | 0 | if (cpu_sub_arch_name) |
3319 | 0 | top->sub_name = xstrdup (cpu_sub_arch_name); |
3320 | 0 | else |
3321 | 0 | top->sub_name = NULL; |
3322 | 0 | top->flags = cpu_arch_flags; |
3323 | 0 | top->isa = cpu_arch_isa; |
3324 | 0 | top->isa_flags = cpu_arch_isa_flags; |
3325 | 0 | top->flag_code = flag_code; |
3326 | 0 | top->vector_size = vector_size; |
3327 | 0 | top->stackop_size = stackop_size; |
3328 | 0 | top->no_cond_jump_promotion = no_cond_jump_promotion; |
3329 | |
|
3330 | 0 | top->prev = arch_stack_top; |
3331 | 0 | arch_stack_top = top; |
3332 | |
|
3333 | 0 | (void) restore_line_pointer (e); |
3334 | 0 | demand_empty_rest_of_line (); |
3335 | 0 | return; |
3336 | 0 | } |
3337 | | |
3338 | 1.81k | if (strcmp (string, "pop") == 0) |
3339 | 0 | { |
3340 | 0 | const arch_stack_entry *top = arch_stack_top; |
3341 | |
|
3342 | 0 | if (!top) |
3343 | 0 | { |
3344 | 0 | as_bad (_(".arch stack is empty")); |
3345 | 1.64k | restore_bad: |
3346 | 1.64k | (void) restore_line_pointer (e); |
3347 | 1.64k | ignore_rest_of_line (); |
3348 | 1.64k | return; |
3349 | 0 | } |
3350 | | |
3351 | 0 | if (top->flag_code != flag_code |
3352 | 0 | || top->stackop_size != stackop_size) |
3353 | 0 | { |
3354 | 0 | static const unsigned int bits[] = { |
3355 | 0 | [CODE_16BIT] = 16, |
3356 | 0 | [CODE_32BIT] = 32, |
3357 | 0 | [CODE_64BIT] = 64, |
3358 | 0 | }; |
3359 | |
|
3360 | 0 | as_bad (_("this `.arch pop' requires `.code%u%s' to be in effect"), |
3361 | 0 | bits[top->flag_code], |
3362 | 0 | top->stackop_size == LONG_MNEM_SUFFIX ? "gcc" : ""); |
3363 | 0 | goto restore_bad; |
3364 | 0 | } |
3365 | | |
3366 | 0 | arch_stack_top = top->prev; |
3367 | |
|
3368 | 0 | cpu_arch_name = top->name; |
3369 | 0 | free (cpu_sub_arch_name); |
3370 | 0 | cpu_sub_arch_name = top->sub_name; |
3371 | 0 | cpu_arch_flags = top->flags; |
3372 | 0 | cpu_arch_isa = top->isa; |
3373 | 0 | cpu_arch_isa_flags = top->isa_flags; |
3374 | 0 | vector_size = top->vector_size; |
3375 | 0 | no_cond_jump_promotion = top->no_cond_jump_promotion; |
3376 | |
|
3377 | 0 | XDELETE (top); |
3378 | |
|
3379 | 0 | (void) restore_line_pointer (e); |
3380 | 0 | demand_empty_rest_of_line (); |
3381 | 0 | return; |
3382 | 0 | } |
3383 | | |
3384 | 1.81k | if (strcmp (string, "default") == 0) |
3385 | 0 | { |
3386 | 0 | if (strcmp (default_arch, "iamcu") == 0) |
3387 | 0 | string = default_arch; |
3388 | 0 | else |
3389 | 0 | { |
3390 | 0 | static const i386_cpu_flags cpu_unknown_flags = CPU_UNKNOWN_FLAGS; |
3391 | |
|
3392 | 0 | cpu_arch_name = NULL; |
3393 | 0 | free (cpu_sub_arch_name); |
3394 | 0 | cpu_sub_arch_name = NULL; |
3395 | 0 | cpu_arch_flags = cpu_unknown_flags; |
3396 | 0 | cpu_arch_isa = PROCESSOR_UNKNOWN; |
3397 | 0 | cpu_arch_isa_flags = cpu_arch[flag_code == CODE_64BIT].enable; |
3398 | 0 | if (!cpu_arch_tune_set) |
3399 | 0 | cpu_arch_tune = PROCESSOR_UNKNOWN; |
3400 | |
|
3401 | 0 | vector_size = VSZ_DEFAULT; |
3402 | |
|
3403 | 0 | j = ARRAY_SIZE (cpu_arch) + 1; |
3404 | 0 | } |
3405 | 0 | } |
3406 | | |
3407 | 342k | for (; j < ARRAY_SIZE (cpu_arch); j++) |
3408 | 340k | { |
3409 | 340k | if (strcmp (string + (*string == '.'), cpu_arch[j].name) == 0 |
3410 | 340k | && (*string == '.') == (cpu_arch[j].type == PROCESSOR_NONE)) |
3411 | 63 | { |
3412 | 63 | if (*string != '.') |
3413 | 63 | { |
3414 | 63 | check_cpu_arch_compatible (string, cpu_arch[j].enable); |
3415 | | |
3416 | 63 | if (flag_code == CODE_64BIT && !cpu_arch[j].enable.bitfield.cpu64 ) |
3417 | 0 | { |
3418 | 0 | as_bad (_("64bit mode not supported on `%s'."), |
3419 | 0 | cpu_arch[j].name); |
3420 | 0 | goto restore_bad; |
3421 | 0 | } |
3422 | | |
3423 | 63 | if (flag_code == CODE_32BIT && !cpu_arch[j].enable.bitfield.cpui386) |
3424 | 0 | { |
3425 | 0 | as_bad (_("32bit mode not supported on `%s'."), |
3426 | 0 | cpu_arch[j].name); |
3427 | 0 | goto restore_bad; |
3428 | 0 | } |
3429 | | |
3430 | 63 | cpu_arch_name = cpu_arch[j].name; |
3431 | 63 | free (cpu_sub_arch_name); |
3432 | 63 | cpu_sub_arch_name = NULL; |
3433 | 63 | cpu_arch_flags = cpu_arch[j].enable; |
3434 | 63 | cpu_arch_isa = cpu_arch[j].type; |
3435 | 63 | cpu_arch_isa_flags = cpu_arch[j].enable; |
3436 | 63 | if (!cpu_arch_tune_set) |
3437 | 63 | cpu_arch_tune = cpu_arch_isa; |
3438 | | |
3439 | 63 | vector_size = VSZ_DEFAULT; |
3440 | | |
3441 | 63 | pre_386_16bit_warned = false; |
3442 | 63 | break; |
3443 | 63 | } |
3444 | | |
3445 | 0 | if (cpu_flags_all_zero (&cpu_arch[j].enable)) |
3446 | 0 | continue; |
3447 | | |
3448 | 0 | isa_enable (j); |
3449 | |
|
3450 | 0 | (void) restore_line_pointer (e); |
3451 | |
|
3452 | 0 | switch (cpu_arch[j].vsz) |
3453 | 0 | { |
3454 | 0 | default: |
3455 | 0 | break; |
3456 | | |
3457 | 0 | case vsz_set: |
3458 | | #ifdef SVR4_COMMENT_CHARS |
3459 | | if (*input_line_pointer == ':' || *input_line_pointer == '/') |
3460 | | #else |
3461 | 0 | if (*input_line_pointer == '/') |
3462 | 0 | #endif |
3463 | 0 | { |
3464 | 0 | ++input_line_pointer; |
3465 | 0 | switch (get_absolute_expression ()) |
3466 | 0 | { |
3467 | 0 | case 512: vector_size = VSZ512; break; |
3468 | 0 | case 256: vector_size = VSZ256; break; |
3469 | 0 | case 128: vector_size = VSZ128; break; |
3470 | 0 | default: |
3471 | 0 | as_bad (_("Unrecognized vector size specifier")); |
3472 | 0 | ignore_rest_of_line (); |
3473 | 0 | return; |
3474 | 0 | } |
3475 | 0 | break; |
3476 | 0 | } |
3477 | | /* Fall through. */ |
3478 | 0 | case vsz_reset: |
3479 | 0 | vector_size = VSZ_DEFAULT; |
3480 | 0 | break; |
3481 | 0 | } |
3482 | | |
3483 | 0 | demand_empty_rest_of_line (); |
3484 | 0 | return; |
3485 | 0 | } |
3486 | 340k | } |
3487 | | |
3488 | 1.81k | if (startswith (string, ".no") && j >= ARRAY_SIZE (cpu_arch)) |
3489 | 110 | { |
3490 | | /* Disable an ISA extension. */ |
3491 | 6.27k | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
3492 | 6.27k | if (cpu_arch[j].type == PROCESSOR_NONE |
3493 | 6.27k | && strcmp (string + 3, cpu_arch[j].name) == 0) |
3494 | 110 | { |
3495 | 110 | isa_disable (j); |
3496 | | |
3497 | 110 | if (cpu_arch[j].vsz == vsz_set) |
3498 | 0 | vector_size = VSZ_DEFAULT; |
3499 | | |
3500 | 110 | (void) restore_line_pointer (e); |
3501 | 110 | demand_empty_rest_of_line (); |
3502 | 110 | return; |
3503 | 110 | } |
3504 | 110 | } |
3505 | | |
3506 | 1.70k | if (j == ARRAY_SIZE (cpu_arch)) |
3507 | 1.64k | { |
3508 | 1.64k | as_bad (_("no such architecture: `%s'"), string); |
3509 | 1.64k | goto restore_bad; |
3510 | 1.64k | } |
3511 | | |
3512 | 63 | no_cond_jump_promotion = 0; |
3513 | 63 | if (restore_line_pointer (e) == ',' |
3514 | 63 | && !is_end_of_stmt (input_line_pointer[1])) |
3515 | 0 | { |
3516 | 0 | ++input_line_pointer; |
3517 | 0 | e = get_symbol_name (&s); |
3518 | 0 | string = s; |
3519 | |
|
3520 | 0 | if (strcmp (string, "nojumps") == 0) |
3521 | 0 | no_cond_jump_promotion = 1; |
3522 | 0 | else if (strcmp (string, "jumps") != 0) |
3523 | 0 | { |
3524 | 0 | as_bad (_("no such architecture modifier: `%s'"), string); |
3525 | 0 | goto restore_bad; |
3526 | 0 | } |
3527 | | |
3528 | 0 | (void) restore_line_pointer (e); |
3529 | 0 | } |
3530 | | |
3531 | 63 | demand_empty_rest_of_line (); |
3532 | 63 | } |
3533 | | |
3534 | | enum bfd_architecture |
3535 | | i386_arch (void) |
3536 | 28 | { |
3537 | 28 | if (cpu_arch_isa == PROCESSOR_IAMCU) |
3538 | 0 | { |
3539 | 0 | if (!IS_ELF || flag_code == CODE_64BIT) |
3540 | 0 | as_fatal (_("Intel MCU is 32bit ELF only")); |
3541 | 0 | return bfd_arch_iamcu; |
3542 | 0 | } |
3543 | 28 | else |
3544 | 28 | return bfd_arch_i386; |
3545 | 28 | } |
3546 | | |
3547 | | unsigned long |
3548 | | i386_mach (void) |
3549 | 28 | { |
3550 | 28 | if (startswith (default_arch, "x86_64")) |
3551 | 28 | { |
3552 | 28 | if (default_arch[6] == '\0') |
3553 | 28 | return bfd_mach_x86_64; |
3554 | 0 | else |
3555 | 0 | return bfd_mach_x64_32; |
3556 | 28 | } |
3557 | 0 | else if (!strcmp (default_arch, "i386") |
3558 | 0 | || !strcmp (default_arch, "iamcu")) |
3559 | 0 | { |
3560 | 0 | if (cpu_arch_isa == PROCESSOR_IAMCU) |
3561 | 0 | { |
3562 | 0 | if (!IS_ELF) |
3563 | 0 | as_fatal (_("Intel MCU is 32bit ELF only")); |
3564 | 0 | return bfd_mach_i386_iamcu; |
3565 | 0 | } |
3566 | 0 | else |
3567 | 0 | return bfd_mach_i386_i386; |
3568 | 0 | } |
3569 | 0 | else |
3570 | 0 | as_fatal (_("unknown architecture")); |
3571 | 28 | } |
3572 | | |
3573 | | #include "opcodes/i386-tbl.h" |
3574 | | |
3575 | | static void |
3576 | | op_lookup (const char *mnemonic) |
3577 | 309k | { |
3578 | 309k | i386_op_off_t *pos = str_hash_find (op_hash, mnemonic); |
3579 | | |
3580 | 309k | if (pos != NULL) |
3581 | 158k | { |
3582 | 158k | current_templates.start = &i386_optab[pos[0]]; |
3583 | 158k | current_templates.end = &i386_optab[pos[1]]; |
3584 | 158k | } |
3585 | 150k | else |
3586 | 150k | current_templates.end = current_templates.start = NULL; |
3587 | 309k | } |
3588 | | |
3589 | | void |
3590 | | md_begin (void) |
3591 | 28 | { |
3592 | | /* Make sure possible padding space is clear. */ |
3593 | 28 | memset (&pp, 0, sizeof (pp)); |
3594 | | |
3595 | | /* Initialize op_hash hash table. */ |
3596 | 28 | op_hash = str_htab_create (); |
3597 | | |
3598 | 28 | { |
3599 | 28 | const i386_op_off_t *cur = i386_op_sets; |
3600 | 28 | const i386_op_off_t *end = cur + ARRAY_SIZE (i386_op_sets) - 1; |
3601 | | |
3602 | 73.0k | for (; cur < end; ++cur) |
3603 | 73.0k | if (str_hash_insert (op_hash, insn_name (&i386_optab[*cur]), cur, 0)) |
3604 | 0 | as_fatal (_("duplicate %s"), insn_name (&i386_optab[*cur])); |
3605 | 28 | } |
3606 | | |
3607 | | /* Initialize reg_hash hash table. */ |
3608 | 28 | reg_hash = str_htab_create (); |
3609 | 28 | { |
3610 | 28 | const reg_entry *regtab; |
3611 | 28 | unsigned int regtab_size = i386_regtab_size; |
3612 | | |
3613 | 9.88k | for (regtab = i386_regtab; regtab_size--; regtab++) |
3614 | 9.85k | { |
3615 | 9.85k | switch (regtab->reg_type.bitfield.class) |
3616 | 9.85k | { |
3617 | 3.80k | case Reg: |
3618 | 3.80k | if (regtab->reg_type.bitfield.dword) |
3619 | 896 | { |
3620 | 896 | if (regtab->reg_type.bitfield.instance == Accum) |
3621 | 28 | reg_eax = regtab; |
3622 | 896 | } |
3623 | 3.80k | break; |
3624 | | |
3625 | 224 | case RegFP: |
3626 | | /* There's no point inserting st(<N>) in the hash table, as |
3627 | | parentheses aren't included in register_chars[] anyway. */ |
3628 | 224 | if (regtab->reg_type.bitfield.instance != Accum) |
3629 | 196 | continue; |
3630 | 28 | reg_st0 = regtab; |
3631 | 28 | break; |
3632 | | |
3633 | 196 | case SReg: |
3634 | 196 | switch (regtab->reg_num) |
3635 | 196 | { |
3636 | 28 | case 0: reg_es = regtab; break; |
3637 | 28 | case 2: reg_ss = regtab; break; |
3638 | 28 | case 3: reg_ds = regtab; break; |
3639 | 196 | } |
3640 | 196 | break; |
3641 | | |
3642 | 224 | case RegMask: |
3643 | 224 | if (!regtab->reg_num) |
3644 | 28 | reg_k0 = regtab; |
3645 | 224 | break; |
3646 | 9.85k | } |
3647 | | |
3648 | 9.66k | if (str_hash_insert (reg_hash, regtab->reg_name, regtab, 0) != NULL) |
3649 | 0 | as_fatal (_("duplicate %s"), regtab->reg_name); |
3650 | 9.66k | } |
3651 | 28 | } |
3652 | | |
3653 | | /* Fill in lexical tables: mnemonic_chars, operand_chars. */ |
3654 | 28 | { |
3655 | 28 | int c; |
3656 | 28 | const char *p; |
3657 | | |
3658 | 7.19k | for (c = 0; c < 256; c++) |
3659 | 7.16k | { |
3660 | 7.16k | if (ISDIGIT (c) || ISLOWER (c)) |
3661 | 1.00k | { |
3662 | 1.00k | mnemonic_chars[c] = c; |
3663 | 1.00k | register_chars[c] = c; |
3664 | 1.00k | operand_chars[c] = c; |
3665 | 1.00k | } |
3666 | 6.16k | else if (ISUPPER (c)) |
3667 | 728 | { |
3668 | 728 | mnemonic_chars[c] = TOLOWER (c); |
3669 | 728 | register_chars[c] = mnemonic_chars[c]; |
3670 | 728 | operand_chars[c] = c; |
3671 | 728 | } |
3672 | | #ifdef SVR4_COMMENT_CHARS |
3673 | | else if (c == '\\' && strchr (i386_comment_chars, '/')) |
3674 | | operand_chars[c] = c; |
3675 | | #endif |
3676 | | |
3677 | 7.16k | if (c >= 128) |
3678 | 3.58k | operand_chars[c] = c; |
3679 | 7.16k | } |
3680 | | |
3681 | 28 | mnemonic_chars['_'] = '_'; |
3682 | 28 | mnemonic_chars['-'] = '-'; |
3683 | 28 | mnemonic_chars['.'] = '.'; |
3684 | | |
3685 | 168 | for (p = extra_symbol_chars; *p != '\0'; p++) |
3686 | 140 | operand_chars[(unsigned char) *p] = *p; |
3687 | 588 | for (p = operand_special_chars; *p != '\0'; p++) |
3688 | 560 | operand_chars[(unsigned char) *p] = *p; |
3689 | 28 | } |
3690 | | |
3691 | 28 | if (object_64bit) |
3692 | 28 | { |
3693 | | #if defined (OBJ_COFF) && defined (TE_PE) |
3694 | | x86_dwarf2_return_column = 32; |
3695 | | #else |
3696 | 28 | x86_dwarf2_return_column = REG_RA; |
3697 | 28 | #endif |
3698 | 28 | x86_cie_data_alignment = -8; |
3699 | 28 | } |
3700 | 0 | else |
3701 | 0 | { |
3702 | 0 | x86_dwarf2_return_column = 8; |
3703 | 0 | x86_cie_data_alignment = -4; |
3704 | 0 | } |
3705 | | |
3706 | | /* NB: FUSED_JCC_PADDING frag must have sufficient room so that it |
3707 | | can be turned into BRANCH_PREFIX frag. */ |
3708 | 28 | if (align_branch_prefix_size > MAX_FUSED_JCC_PADDING_SIZE) |
3709 | 0 | abort (); |
3710 | 28 | } |
3711 | | |
3712 | | void |
3713 | | i386_print_statistics (FILE *file) |
3714 | 0 | { |
3715 | 0 | htab_print_statistics (file, "i386 opcode", op_hash); |
3716 | 0 | htab_print_statistics (file, "i386 register", reg_hash); |
3717 | 0 | } |
3718 | | |
3719 | | void |
3720 | | i386_md_end (void) |
3721 | 28 | { |
3722 | 28 | htab_delete (op_hash); |
3723 | 28 | htab_delete (reg_hash); |
3724 | 28 | GOT_symbol = NULL; |
3725 | 28 | } |
3726 | | |
3727 | | #ifdef DEBUG386 |
3728 | | |
3729 | | /* Debugging routines for md_assemble. */ |
3730 | | static void pte (insn_template *); |
3731 | | static void pt (i386_operand_type); |
3732 | | static void pe (expressionS *); |
3733 | | static void ps (symbolS *); |
3734 | | |
3735 | | static void |
3736 | | pi (const char *line, i386_insn *x) |
3737 | | { |
3738 | | unsigned int j; |
3739 | | |
3740 | | fprintf (stdout, "%s: template ", line); |
3741 | | pte (&x->tm); |
3742 | | fprintf (stdout, " address: base %s index %s scale %x\n", |
3743 | | x->base_reg ? x->base_reg->reg_name : "none", |
3744 | | x->index_reg ? x->index_reg->reg_name : "none", |
3745 | | x->log2_scale_factor); |
3746 | | fprintf (stdout, " modrm: mode %x reg %x reg/mem %x\n", |
3747 | | x->rm.mode, x->rm.reg, x->rm.regmem); |
3748 | | fprintf (stdout, " sib: base %x index %x scale %x\n", |
3749 | | x->sib.base, x->sib.index, x->sib.scale); |
3750 | | fprintf (stdout, " rex: 64bit %x extX %x extY %x extZ %x\n", |
3751 | | (x->rex & REX_W) != 0, |
3752 | | (x->rex & REX_R) != 0, |
3753 | | (x->rex & REX_X) != 0, |
3754 | | (x->rex & REX_B) != 0); |
3755 | | for (j = 0; j < x->operands; j++) |
3756 | | { |
3757 | | fprintf (stdout, " #%d: ", j + 1); |
3758 | | pt (x->types[j]); |
3759 | | fprintf (stdout, "\n"); |
3760 | | if (x->types[j].bitfield.class == Reg |
3761 | | || x->types[j].bitfield.class == RegFP |
3762 | | || x->types[j].bitfield.class == RegMMX |
3763 | | || x->types[j].bitfield.class == RegSIMD |
3764 | | || x->types[j].bitfield.class == RegMask |
3765 | | || x->types[j].bitfield.class == SReg |
3766 | | || x->types[j].bitfield.class == RegCR |
3767 | | || x->types[j].bitfield.class == RegDR |
3768 | | || x->types[j].bitfield.class == RegTR |
3769 | | || x->types[j].bitfield.class == RegBND) |
3770 | | fprintf (stdout, "%s\n", x->op[j].regs->reg_name); |
3771 | | if (operand_type_check (x->types[j], imm)) |
3772 | | pe (x->op[j].imms); |
3773 | | if (operand_type_check (x->types[j], disp)) |
3774 | | pe (x->op[j].disps); |
3775 | | } |
3776 | | } |
3777 | | |
3778 | | static void |
3779 | | pte (insn_template *t) |
3780 | | { |
3781 | | static const unsigned char opc_pfx[] = { 0, 0x66, 0xf3, 0xf2 }; |
3782 | | static const char *const opc_spc[] = { |
3783 | | NULL, "0f", "0f38", "0f3a", NULL, "evexmap5", "evexmap6", NULL, |
3784 | | "XOP08", "XOP09", "XOP0A", |
3785 | | }; |
3786 | | unsigned int j; |
3787 | | |
3788 | | fprintf (stdout, " %d operands ", t->operands); |
3789 | | if (opc_pfx[t->opcode_modifier.opcodeprefix]) |
3790 | | fprintf (stdout, "pfx %x ", opc_pfx[t->opcode_modifier.opcodeprefix]); |
3791 | | if (opc_spc[t->opcode_space]) |
3792 | | fprintf (stdout, "space %s ", opc_spc[t->opcode_space]); |
3793 | | fprintf (stdout, "opcode %x ", t->base_opcode); |
3794 | | if (t->extension_opcode != None) |
3795 | | fprintf (stdout, "ext %x ", t->extension_opcode); |
3796 | | if (t->opcode_modifier.d) |
3797 | | fprintf (stdout, "D"); |
3798 | | if (t->opcode_modifier.w) |
3799 | | fprintf (stdout, "W"); |
3800 | | fprintf (stdout, "\n"); |
3801 | | for (j = 0; j < t->operands; j++) |
3802 | | { |
3803 | | fprintf (stdout, " #%d type ", j + 1); |
3804 | | pt (t->operand_types[j]); |
3805 | | fprintf (stdout, "\n"); |
3806 | | } |
3807 | | } |
3808 | | |
3809 | | static void |
3810 | | pe (expressionS *e) |
3811 | | { |
3812 | | fprintf (stdout, " operation %d\n", e->X_op); |
3813 | | fprintf (stdout, " add_number %" PRId64 " (%" PRIx64 ")\n", |
3814 | | (int64_t) e->X_add_number, (uint64_t) (valueT) e->X_add_number); |
3815 | | if (e->X_add_symbol) |
3816 | | { |
3817 | | fprintf (stdout, " add_symbol "); |
3818 | | ps (e->X_add_symbol); |
3819 | | fprintf (stdout, "\n"); |
3820 | | } |
3821 | | if (e->X_op_symbol) |
3822 | | { |
3823 | | fprintf (stdout, " op_symbol "); |
3824 | | ps (e->X_op_symbol); |
3825 | | fprintf (stdout, "\n"); |
3826 | | } |
3827 | | } |
3828 | | |
3829 | | static void |
3830 | | ps (symbolS *s) |
3831 | | { |
3832 | | fprintf (stdout, "%s type %s%s", |
3833 | | S_GET_NAME (s), |
3834 | | S_IS_EXTERNAL (s) ? "EXTERNAL " : "", |
3835 | | segment_name (S_GET_SEGMENT (s))); |
3836 | | } |
3837 | | |
3838 | | static struct type_name |
3839 | | { |
3840 | | i386_operand_type mask; |
3841 | | const char *name; |
3842 | | } |
3843 | | const type_names[] = |
3844 | | { |
3845 | | { { .bitfield = { .class = Reg, .byte = 1 } }, "r8" }, |
3846 | | { { .bitfield = { .class = Reg, .word = 1 } }, "r16" }, |
3847 | | { { .bitfield = { .class = Reg, .dword = 1 } }, "r32" }, |
3848 | | { { .bitfield = { .class = Reg, .qword = 1 } }, "r64" }, |
3849 | | { { .bitfield = { .instance = Accum, .byte = 1 } }, "acc8" }, |
3850 | | { { .bitfield = { .instance = Accum, .word = 1 } }, "acc16" }, |
3851 | | { { .bitfield = { .instance = Accum, .dword = 1 } }, "acc32" }, |
3852 | | { { .bitfield = { .instance = Accum, .qword = 1 } }, "acc64" }, |
3853 | | { { .bitfield = { .imm8 = 1 } }, "i8" }, |
3854 | | { { .bitfield = { .imm8s = 1 } }, "i8s" }, |
3855 | | { { .bitfield = { .imm16 = 1 } }, "i16" }, |
3856 | | { { .bitfield = { .imm32 = 1 } }, "i32" }, |
3857 | | { { .bitfield = { .imm32s = 1 } }, "i32s" }, |
3858 | | { { .bitfield = { .imm64 = 1 } }, "i64" }, |
3859 | | { { .bitfield = { .imm1 = 1 } }, "i1" }, |
3860 | | { { .bitfield = { .baseindex = 1 } }, "BaseIndex" }, |
3861 | | { { .bitfield = { .disp8 = 1 } }, "d8" }, |
3862 | | { { .bitfield = { .disp16 = 1 } }, "d16" }, |
3863 | | { { .bitfield = { .disp32 = 1 } }, "d32" }, |
3864 | | { { .bitfield = { .disp64 = 1 } }, "d64" }, |
3865 | | { { .bitfield = { .instance = RegD, .word = 1 } }, "InOutPortReg" }, |
3866 | | { { .bitfield = { .instance = RegC, .byte = 1 } }, "ShiftCount" }, |
3867 | | { { .bitfield = { .class = RegCR } }, "control reg" }, |
3868 | | { { .bitfield = { .class = RegTR } }, "test reg" }, |
3869 | | { { .bitfield = { .class = RegDR } }, "debug reg" }, |
3870 | | { { .bitfield = { .class = RegFP, .tbyte = 1 } }, "FReg" }, |
3871 | | { { .bitfield = { .instance = Accum, .tbyte = 1 } }, "FAcc" }, |
3872 | | { { .bitfield = { .class = SReg } }, "SReg" }, |
3873 | | { { .bitfield = { .class = RegMMX } }, "rMMX" }, |
3874 | | { { .bitfield = { .class = RegSIMD, .xmmword = 1 } }, "rXMM" }, |
3875 | | { { .bitfield = { .class = RegSIMD, .ymmword = 1 } }, "rYMM" }, |
3876 | | { { .bitfield = { .class = RegSIMD, .zmmword = 1 } }, "rZMM" }, |
3877 | | { { .bitfield = { .class = RegSIMD, .tmmword = 1 } }, "rTMM" }, |
3878 | | { { .bitfield = { .class = RegMask } }, "Mask reg" }, |
3879 | | }; |
3880 | | |
3881 | | static void |
3882 | | pt (i386_operand_type t) |
3883 | | { |
3884 | | unsigned int j; |
3885 | | i386_operand_type a; |
3886 | | |
3887 | | for (j = 0; j < ARRAY_SIZE (type_names); j++) |
3888 | | { |
3889 | | a = operand_type_and (t, type_names[j].mask); |
3890 | | if (operand_type_equal (&a, &type_names[j].mask)) |
3891 | | fprintf (stdout, "%s, ", type_names[j].name); |
3892 | | } |
3893 | | fflush (stdout); |
3894 | | } |
3895 | | |
3896 | | #endif /* DEBUG386 */ |
3897 | | |
3898 | | static bfd_reloc_code_real_type |
3899 | | reloc (unsigned int size, |
3900 | | int pcrel, |
3901 | | int sign, |
3902 | | bfd_reloc_code_real_type other) |
3903 | 2.63k | { |
3904 | 2.63k | if (other != NO_RELOC) |
3905 | 623 | { |
3906 | 623 | reloc_howto_type *rel; |
3907 | | |
3908 | 623 | if (size == 8) |
3909 | 0 | switch (other) |
3910 | 0 | { |
3911 | 0 | case BFD_RELOC_X86_64_GOT32: |
3912 | 0 | return BFD_RELOC_X86_64_GOT64; |
3913 | 0 | break; |
3914 | 0 | case BFD_RELOC_X86_64_GOTPLT64: |
3915 | 0 | return BFD_RELOC_X86_64_GOTPLT64; |
3916 | 0 | break; |
3917 | 0 | case BFD_RELOC_X86_64_PLTOFF64: |
3918 | 0 | return BFD_RELOC_X86_64_PLTOFF64; |
3919 | 0 | break; |
3920 | 0 | case BFD_RELOC_X86_64_GOTPC32: |
3921 | 0 | other = BFD_RELOC_X86_64_GOTPC64; |
3922 | 0 | break; |
3923 | 0 | case BFD_RELOC_X86_64_GOTPCREL: |
3924 | 0 | other = BFD_RELOC_X86_64_GOTPCREL64; |
3925 | 0 | break; |
3926 | 0 | case BFD_RELOC_X86_64_TPOFF32: |
3927 | 0 | other = BFD_RELOC_X86_64_TPOFF64; |
3928 | 0 | break; |
3929 | 0 | case BFD_RELOC_X86_64_DTPOFF32: |
3930 | 0 | other = BFD_RELOC_X86_64_DTPOFF64; |
3931 | 0 | break; |
3932 | 0 | default: |
3933 | 0 | break; |
3934 | 0 | } |
3935 | | |
3936 | 623 | #ifdef OBJ_ELF |
3937 | 623 | if (other == BFD_RELOC_SIZE32) |
3938 | 0 | { |
3939 | 0 | if (size == 8) |
3940 | 0 | other = BFD_RELOC_SIZE64; |
3941 | 0 | if (pcrel) |
3942 | 0 | { |
3943 | 0 | as_bad (_("there are no pc-relative size relocations")); |
3944 | 0 | return NO_RELOC; |
3945 | 0 | } |
3946 | 0 | } |
3947 | 623 | #endif |
3948 | | |
3949 | | /* Sign-checking 4-byte relocations in 16-/32-bit code is pointless. */ |
3950 | 623 | if (size == 4 && (flag_code != CODE_64BIT || disallow_64bit_reloc)) |
3951 | 443 | sign = -1; |
3952 | | |
3953 | 623 | rel = bfd_reloc_type_lookup (stdoutput, other); |
3954 | 623 | if (!rel) |
3955 | 0 | as_bad (_("unknown relocation (%u)"), other); |
3956 | 623 | else if (size != bfd_get_reloc_size (rel)) |
3957 | 121 | as_bad (_("%u-byte relocation cannot be applied to %u-byte field"), |
3958 | 121 | bfd_get_reloc_size (rel), |
3959 | 121 | size); |
3960 | 502 | else if (pcrel && !rel->pc_relative) |
3961 | 0 | as_bad (_("non-pc-relative relocation for pc-relative field")); |
3962 | 502 | else if ((rel->complain_on_overflow == complain_overflow_signed |
3963 | 502 | && !sign) |
3964 | 502 | || (rel->complain_on_overflow == complain_overflow_unsigned |
3965 | 502 | && sign > 0)) |
3966 | 0 | as_bad (_("relocated field and relocation type differ in signedness")); |
3967 | 502 | else |
3968 | 502 | return other; |
3969 | 121 | return NO_RELOC; |
3970 | 623 | } |
3971 | | |
3972 | 2.00k | if (pcrel) |
3973 | 277 | { |
3974 | 277 | if (!sign) |
3975 | 0 | as_bad (_("there are no unsigned pc-relative relocations")); |
3976 | 277 | switch (size) |
3977 | 277 | { |
3978 | 1 | case 1: return BFD_RELOC_8_PCREL; |
3979 | 136 | case 2: return BFD_RELOC_16_PCREL; |
3980 | 140 | case 4: return BFD_RELOC_32_PCREL; |
3981 | 0 | case 8: return BFD_RELOC_64_PCREL; |
3982 | 277 | } |
3983 | 0 | as_bad (_("cannot do %u byte pc-relative relocation"), size); |
3984 | 0 | } |
3985 | 1.73k | else |
3986 | 1.73k | { |
3987 | 1.73k | if (sign > 0) |
3988 | 33 | switch (size) |
3989 | 33 | { |
3990 | 33 | case 4: return BFD_RELOC_X86_64_32S; |
3991 | 33 | } |
3992 | 1.69k | else |
3993 | 1.69k | switch (size) |
3994 | 1.69k | { |
3995 | 198 | case 1: return BFD_RELOC_8; |
3996 | 41 | case 2: return BFD_RELOC_16; |
3997 | 1.40k | case 4: return BFD_RELOC_32; |
3998 | 59 | case 8: return BFD_RELOC_64; |
3999 | 1.69k | } |
4000 | 0 | as_bad (_("cannot do %s %u byte relocation"), |
4001 | 0 | sign > 0 ? "signed" : "unsigned", size); |
4002 | 0 | } |
4003 | | |
4004 | 0 | return NO_RELOC; |
4005 | 2.00k | } |
4006 | | |
4007 | | #ifdef OBJ_ELF |
4008 | | /* Here we decide which fixups can be adjusted to make them relative to |
4009 | | the beginning of the section instead of the symbol. Basically we need |
4010 | | to make sure that the dynamic relocations are done correctly, so in |
4011 | | some cases we force the original symbol to be used. */ |
4012 | | |
4013 | | int |
4014 | | tc_i386_fix_adjustable (fixS *fixP) |
4015 | 0 | { |
4016 | | /* Don't adjust pc-relative references to merge sections in 64-bit |
4017 | | mode. */ |
4018 | 0 | if (use_rela_relocations |
4019 | 0 | && (S_GET_SEGMENT (fixP->fx_addsy)->flags & SEC_MERGE) != 0 |
4020 | 0 | && fixP->fx_pcrel) |
4021 | 0 | return 0; |
4022 | | |
4023 | | /* The x86_64 GOTPCREL are represented as 32bit PCrel relocations |
4024 | | and changed later by validate_fix. */ |
4025 | 0 | if (GOT_symbol && fixP->fx_subsy == GOT_symbol |
4026 | 0 | && fixP->fx_r_type == BFD_RELOC_32_PCREL) |
4027 | 0 | return 0; |
4028 | | |
4029 | | /* Adjust_reloc_syms doesn't know about the GOT. Need to keep symbol |
4030 | | for size relocations. */ |
4031 | 0 | if (fixP->fx_r_type == BFD_RELOC_SIZE32 |
4032 | 0 | || fixP->fx_r_type == BFD_RELOC_SIZE64 |
4033 | 0 | || fixP->fx_r_type == BFD_RELOC_386_GOTOFF |
4034 | 0 | || fixP->fx_r_type == BFD_RELOC_386_GOT32 |
4035 | 0 | || fixP->fx_r_type == BFD_RELOC_386_GOT32X |
4036 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_GD |
4037 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_LDM |
4038 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_LDO_32 |
4039 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_IE_32 |
4040 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_IE |
4041 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_GOTIE |
4042 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_LE_32 |
4043 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_LE |
4044 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_GOTDESC |
4045 | 0 | || fixP->fx_r_type == BFD_RELOC_386_TLS_DESC_CALL |
4046 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOT32 |
4047 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOTPCREL |
4048 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOTPCRELX |
4049 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_REX_GOTPCRELX |
4050 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_4_GOTPCRELX |
4051 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_5_GOTPCRELX |
4052 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_6_GOTPCRELX |
4053 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_TLSGD |
4054 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_TLSLD |
4055 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_DTPOFF32 |
4056 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_DTPOFF64 |
4057 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOTTPOFF |
4058 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_4_GOTTPOFF |
4059 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_5_GOTTPOFF |
4060 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_6_GOTTPOFF |
4061 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_TPOFF32 |
4062 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_TPOFF64 |
4063 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOTOFF64 |
4064 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOT64 |
4065 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_GOTPC32_TLSDESC |
4066 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC |
4067 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_5_GOTPC32_TLSDESC |
4068 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_CODE_6_GOTPC32_TLSDESC |
4069 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_TLSDESC_CALL |
4070 | 0 | || fixP->fx_r_type == BFD_RELOC_VTABLE_INHERIT |
4071 | 0 | || fixP->fx_r_type == BFD_RELOC_VTABLE_ENTRY) |
4072 | 0 | return 0; |
4073 | | /* Resolve PLT32 relocation against local symbol to section only for |
4074 | | PC-relative relocations. */ |
4075 | 0 | if (fixP->fx_r_type == BFD_RELOC_386_PLT32 |
4076 | 0 | || fixP->fx_r_type == BFD_RELOC_X86_64_PLT32) |
4077 | 0 | return fixP->fx_pcrel; |
4078 | 0 | return 1; |
4079 | 0 | } |
4080 | | #endif |
4081 | | |
4082 | | static INLINE bool |
4083 | | want_disp32 (const insn_template *t) |
4084 | 37.5k | { |
4085 | 37.5k | return flag_code != CODE_64BIT |
4086 | 37.5k | || i.prefix[ADDR_PREFIX] |
4087 | 37.5k | || ((t->mnem_off == MN_lea |
4088 | 34.3k | || (i.tm.base_opcode == 0x8d && i.tm.opcode_space == SPACE_BASE)) |
4089 | 34.3k | && (!i.types[1].bitfield.qword |
4090 | 0 | || t->opcode_modifier.size == SIZE32)); |
4091 | 37.5k | } |
4092 | | |
4093 | | static int |
4094 | | intel_float_operand (const char *mnemonic) |
4095 | 0 | { |
4096 | | /* Note that the value returned is meaningful only for opcodes with (memory) |
4097 | | operands, hence the code here is free to improperly handle opcodes that |
4098 | | have no operands (for better performance and smaller code). */ |
4099 | |
|
4100 | 0 | if (mnemonic[0] != 'f') |
4101 | 0 | return 0; /* non-math */ |
4102 | | |
4103 | 0 | switch (mnemonic[1]) |
4104 | 0 | { |
4105 | | /* fclex, fdecstp, fdisi, femms, feni, fincstp, finit, fsetpm, and |
4106 | | the fs segment override prefix not currently handled because no |
4107 | | call path can make opcodes without operands get here */ |
4108 | 0 | case 'i': |
4109 | 0 | return 2 /* integer op */; |
4110 | 0 | case 'l': |
4111 | 0 | if (mnemonic[2] == 'd' && (mnemonic[3] == 'c' || mnemonic[3] == 'e')) |
4112 | 0 | return 3; /* fldcw/fldenv */ |
4113 | 0 | break; |
4114 | 0 | case 'n': |
4115 | 0 | if (mnemonic[2] != 'o' /* fnop */) |
4116 | 0 | return 3; /* non-waiting control op */ |
4117 | 0 | break; |
4118 | 0 | case 'r': |
4119 | 0 | if (mnemonic[2] == 's') |
4120 | 0 | return 3; /* frstor/frstpm */ |
4121 | 0 | break; |
4122 | 0 | case 's': |
4123 | 0 | if (mnemonic[2] == 'a') |
4124 | 0 | return 3; /* fsave */ |
4125 | 0 | if (mnemonic[2] == 't') |
4126 | 0 | { |
4127 | 0 | switch (mnemonic[3]) |
4128 | 0 | { |
4129 | 0 | case 'c': /* fstcw */ |
4130 | 0 | case 'd': /* fstdw */ |
4131 | 0 | case 'e': /* fstenv */ |
4132 | 0 | case 's': /* fsts[gw] */ |
4133 | 0 | return 3; |
4134 | 0 | } |
4135 | 0 | } |
4136 | 0 | break; |
4137 | 0 | case 'x': |
4138 | 0 | if (mnemonic[2] == 'r' || mnemonic[2] == 's') |
4139 | 0 | return 0; /* fxsave/fxrstor are not really math ops */ |
4140 | 0 | break; |
4141 | 0 | } |
4142 | | |
4143 | 0 | return 1; |
4144 | 0 | } |
4145 | | |
4146 | | static INLINE void |
4147 | | install_template (const insn_template *t) |
4148 | 2.92k | { |
4149 | 2.92k | unsigned int l; |
4150 | | |
4151 | 2.92k | i.tm = *t; |
4152 | | |
4153 | | /* Dual VEX/EVEX templates need stripping one of the possible variants. */ |
4154 | 2.92k | if (t->opcode_modifier.vex && t->opcode_modifier.evex) |
4155 | 0 | { |
4156 | 0 | if ((maybe_cpu (t, CpuAVX) || maybe_cpu (t, CpuAVX2) |
4157 | 0 | || maybe_cpu (t, CpuFMA)) |
4158 | 0 | && (maybe_cpu (t, CpuAVX512F) || maybe_cpu (t, CpuAVX512VL))) |
4159 | 0 | { |
4160 | 0 | if (need_evex_encoding (t)) |
4161 | 0 | { |
4162 | 0 | i.tm.opcode_modifier.vex = 0; |
4163 | 0 | i.tm.cpu.bitfield.cpuavx512f = i.tm.cpu_any.bitfield.cpuavx512f; |
4164 | 0 | i.tm.cpu.bitfield.cpuavx512vl = i.tm.cpu_any.bitfield.cpuavx512vl; |
4165 | 0 | } |
4166 | 0 | else |
4167 | 0 | { |
4168 | 0 | i.tm.opcode_modifier.evex = 0; |
4169 | 0 | if (i.tm.cpu_any.bitfield.cpuavx) |
4170 | 0 | i.tm.cpu.bitfield.cpuavx = 1; |
4171 | 0 | else if (!i.tm.cpu.bitfield.isa) |
4172 | 0 | i.tm.cpu.bitfield.isa = i.tm.cpu_any.bitfield.isa; |
4173 | 0 | else |
4174 | 0 | gas_assert (i.tm.cpu.bitfield.isa == i.tm.cpu_any.bitfield.isa); |
4175 | 0 | } |
4176 | 0 | } |
4177 | | |
4178 | 0 | if ((maybe_cpu (t, CpuCMPCCXADD) || maybe_cpu (t, CpuAMX_TILE) |
4179 | 0 | || maybe_cpu (t, CpuAVX512F) || maybe_cpu (t, CpuAVX512DQ) |
4180 | 0 | || maybe_cpu (t, CpuAVX512BW) || maybe_cpu (t, CpuBMI) |
4181 | 0 | || maybe_cpu (t, CpuBMI2) || maybe_cpu (t, CpuUSER_MSR) |
4182 | 0 | || maybe_cpu (t, CpuMSR_IMM) || maybe_cpu (t, CpuAMX_TRANSPOSE) |
4183 | 0 | || maybe_cpu (t, CpuAMX_MOVRS)) |
4184 | 0 | && maybe_cpu (t, CpuAPX_F)) |
4185 | 0 | { |
4186 | 0 | if (need_evex_encoding (t)) |
4187 | 0 | i.tm.opcode_modifier.vex = 0; |
4188 | 0 | else |
4189 | 0 | i.tm.opcode_modifier.evex = 0; |
4190 | 0 | } |
4191 | 0 | } |
4192 | | |
4193 | | /* For CCMP and CTEST the template has EVEX.SCC in base_opcode. Move it out of |
4194 | | there, to then adjust base_opcode to obtain its normal meaning. */ |
4195 | 2.92k | if (i.tm.opcode_modifier.operandconstraint == SCC) |
4196 | 0 | { |
4197 | | /* Get EVEX.SCC value from the lower 4 bits of base_opcode. */ |
4198 | 0 | i.scc = i.tm.base_opcode & 0xf; |
4199 | 0 | i.tm.base_opcode >>= 8; |
4200 | 0 | } |
4201 | | |
4202 | | /* For CMOVcc having undergone NDD-to-legacy optimization with its source |
4203 | | operands being swapped, we need to invert the encoded condition. */ |
4204 | 2.92k | if (i.invert_cond) |
4205 | 0 | i.tm.base_opcode ^= 1; |
4206 | | |
4207 | | /* Note that for pseudo prefixes this produces a length of 1. But for them |
4208 | | the length isn't interesting at all. */ |
4209 | 2.94k | for (l = 1; l < 4; ++l) |
4210 | 2.94k | if (!(i.tm.base_opcode >> (8 * l))) |
4211 | 2.92k | break; |
4212 | | |
4213 | 2.92k | i.opcode_length = l; |
4214 | 2.92k | } |
4215 | | |
4216 | | /* Build the VEX prefix. */ |
4217 | | |
4218 | | static void |
4219 | | build_vex_prefix (const insn_template *t) |
4220 | 512 | { |
4221 | 512 | unsigned int register_specifier; |
4222 | 512 | unsigned int vector_length; |
4223 | 512 | bool w; |
4224 | | |
4225 | | /* Check register specifier. */ |
4226 | 512 | if (i.vex.register_specifier) |
4227 | 0 | { |
4228 | 0 | register_specifier = |
4229 | 0 | ~register_number (i.vex.register_specifier) & 0xf; |
4230 | 0 | gas_assert ((i.vex.register_specifier->reg_flags & RegVRex) == 0); |
4231 | 0 | } |
4232 | 512 | else |
4233 | 512 | register_specifier = 0xf; |
4234 | | |
4235 | | /* Use 2-byte VEX prefix by swapping destination and source operand |
4236 | | if there are more than 1 register operand. */ |
4237 | 512 | if (i.reg_operands > 1 |
4238 | 512 | && pp.encoding != encoding_vex3 |
4239 | 512 | && pp.dir_encoding == dir_encoding_default |
4240 | 512 | && i.operands == i.reg_operands |
4241 | 512 | && operand_type_equal (&i.types[0], &i.types[i.operands - 1]) |
4242 | 512 | && i.tm.opcode_space == SPACE_0F |
4243 | 512 | && (i.tm.opcode_modifier.load || i.tm.opcode_modifier.d) |
4244 | 512 | && i.rex == REX_B) |
4245 | 0 | { |
4246 | 0 | unsigned int xchg; |
4247 | |
|
4248 | 0 | swap_2_operands (0, i.operands - 1); |
4249 | |
|
4250 | 0 | gas_assert (i.rm.mode == 3); |
4251 | | |
4252 | 0 | i.rex = REX_R; |
4253 | 0 | xchg = i.rm.regmem; |
4254 | 0 | i.rm.regmem = i.rm.reg; |
4255 | 0 | i.rm.reg = xchg; |
4256 | |
|
4257 | 0 | if (i.tm.opcode_modifier.d) |
4258 | 0 | i.tm.base_opcode ^= (i.tm.base_opcode & 0xee) != 0x6e |
4259 | 0 | ? Opcode_ExtD : Opcode_SIMD_IntD; |
4260 | 0 | else /* Use the next insn. */ |
4261 | 0 | install_template (&t[1]); |
4262 | 0 | } |
4263 | | |
4264 | | /* Use 2-byte VEX prefix by swapping commutative source operands if there |
4265 | | are no memory operands and at least 3 register ones. */ |
4266 | 512 | if (i.reg_operands >= 3 |
4267 | 512 | && pp.encoding != encoding_vex3 |
4268 | 512 | && i.reg_operands == i.operands - i.imm_operands |
4269 | 512 | && i.tm.opcode_modifier.vex |
4270 | 512 | && i.tm.opcode_modifier.commutative |
4271 | | /* .commutative aliases .staticrounding; disambiguate. */ |
4272 | 512 | && !i.tm.opcode_modifier.sae |
4273 | 512 | && (i.tm.opcode_modifier.sse2avx |
4274 | 0 | || (optimize > 1 && !pp.no_optimize)) |
4275 | 512 | && i.rex == REX_B |
4276 | 512 | && i.vex.register_specifier |
4277 | 512 | && !(i.vex.register_specifier->reg_flags & RegRex)) |
4278 | 0 | { |
4279 | 0 | unsigned int xchg = i.operands - i.reg_operands; |
4280 | |
|
4281 | 0 | gas_assert (i.tm.opcode_space == SPACE_0F); |
4282 | 0 | gas_assert (!i.tm.opcode_modifier.sae); |
4283 | 0 | gas_assert (operand_type_equal (&i.types[i.operands - 2], |
4284 | 0 | &i.types[i.operands - 3])); |
4285 | 0 | gas_assert (i.rm.mode == 3); |
4286 | | |
4287 | 0 | swap_2_operands (xchg, xchg + 1); |
4288 | |
|
4289 | 0 | i.rex = 0; |
4290 | 0 | xchg = i.rm.regmem | 8; |
4291 | 0 | i.rm.regmem = ~register_specifier & 0xf; |
4292 | 0 | gas_assert (!(i.rm.regmem & 8)); |
4293 | 0 | i.vex.register_specifier += xchg - i.rm.regmem; |
4294 | 0 | register_specifier = ~xchg & 0xf; |
4295 | 0 | } |
4296 | | |
4297 | 512 | if (i.tm.opcode_modifier.vex == VEXScalar) |
4298 | 477 | vector_length = avxscalar; |
4299 | 35 | else if (i.tm.opcode_modifier.vex == VEX256) |
4300 | 0 | vector_length = 1; |
4301 | 35 | else if (dot_insn () && i.tm.opcode_modifier.vex == VEX128) |
4302 | 0 | vector_length = 0; |
4303 | 35 | else |
4304 | 35 | { |
4305 | 35 | unsigned int op; |
4306 | | |
4307 | | /* Determine vector length from the last multi-length vector |
4308 | | operand. */ |
4309 | 35 | vector_length = 0; |
4310 | 70 | for (op = t->operands; op--;) |
4311 | 35 | if (t->operand_types[op].bitfield.xmmword |
4312 | 35 | && t->operand_types[op].bitfield.ymmword |
4313 | 35 | && i.types[op].bitfield.ymmword) |
4314 | 0 | { |
4315 | 0 | vector_length = 1; |
4316 | 0 | break; |
4317 | 0 | } |
4318 | 35 | } |
4319 | | |
4320 | | /* Check the REX.W bit and VEXW. */ |
4321 | 512 | if (i.tm.opcode_modifier.vexw == VEXWIG) |
4322 | 35 | w = vexwig == vexw1 || (i.rex & REX_W); |
4323 | 477 | else if (i.tm.opcode_modifier.vexw && !(i.rex & REX_W)) |
4324 | 0 | w = i.tm.opcode_modifier.vexw == VEXW1; |
4325 | 477 | else |
4326 | 477 | w = flag_code == CODE_64BIT ? i.rex & REX_W : vexwig == vexw1; |
4327 | | |
4328 | | /* Use 2-byte VEX prefix if possible. */ |
4329 | 512 | if (w == 0 |
4330 | 512 | && pp.encoding != encoding_vex3 |
4331 | 512 | && i.tm.opcode_space == SPACE_0F |
4332 | 512 | && (i.rex & (REX_W | REX_X | REX_B)) == 0) |
4333 | 35 | { |
4334 | | /* 2-byte VEX prefix. */ |
4335 | 35 | bool r; |
4336 | | |
4337 | 35 | i.vex.length = 2; |
4338 | 35 | i.vex.bytes[0] = 0xc5; |
4339 | | |
4340 | | /* Check the REX.R bit. */ |
4341 | 35 | r = !(i.rex & REX_R); |
4342 | 35 | i.vex.bytes[1] = (r << 7 |
4343 | 35 | | register_specifier << 3 |
4344 | 35 | | vector_length << 2 |
4345 | 35 | | i.tm.opcode_modifier.opcodeprefix); |
4346 | 35 | } |
4347 | 477 | else |
4348 | 477 | { |
4349 | | /* 3-byte VEX prefix. */ |
4350 | 477 | i.vex.length = 3; |
4351 | | |
4352 | 477 | switch (i.tm.opcode_space) |
4353 | 477 | { |
4354 | 0 | case SPACE_0F: |
4355 | 477 | case SPACE_0F38: |
4356 | 477 | case SPACE_0F3A: |
4357 | 477 | case SPACE_MAP5: |
4358 | 477 | case SPACE_MAP7: |
4359 | 477 | i.vex.bytes[0] = 0xc4; |
4360 | 477 | break; |
4361 | 0 | case SPACE_XOP08: |
4362 | 0 | case SPACE_XOP09: |
4363 | 0 | case SPACE_XOP0A: |
4364 | 0 | i.vex.bytes[0] = 0x8f; |
4365 | 0 | break; |
4366 | 0 | default: |
4367 | 0 | abort (); |
4368 | 477 | } |
4369 | | |
4370 | | /* The high 3 bits of the second VEX byte are 1's compliment |
4371 | | of RXB bits from REX. */ |
4372 | 477 | i.vex.bytes[1] = ((~i.rex & 7) << 5) |
4373 | 477 | | (!dot_insn () ? i.tm.opcode_space |
4374 | 477 | : i.insn_opcode_space); |
4375 | | |
4376 | 477 | i.vex.bytes[2] = (w << 7 |
4377 | 477 | | register_specifier << 3 |
4378 | 477 | | vector_length << 2 |
4379 | 477 | | i.tm.opcode_modifier.opcodeprefix); |
4380 | 477 | } |
4381 | 512 | } |
4382 | | |
4383 | | static INLINE bool |
4384 | | is_any_vex_encoding (const insn_template *t) |
4385 | 10.6k | { |
4386 | 10.6k | return t->opcode_modifier.vex || t->opcode_modifier.evex; |
4387 | 10.6k | } |
4388 | | |
4389 | | /* We can use this function only when the current encoding is evex. */ |
4390 | | static INLINE bool |
4391 | | is_apx_evex_encoding (void) |
4392 | 512 | { |
4393 | 512 | return i.rex2 || i.tm.opcode_space == SPACE_MAP4 || pp.has_nf |
4394 | 512 | || (i.vex.register_specifier |
4395 | 512 | && (i.vex.register_specifier->reg_flags & RegRex2)); |
4396 | 512 | } |
4397 | | |
4398 | | static INLINE bool |
4399 | | is_apx_rex2_encoding (void) |
4400 | 5.34k | { |
4401 | 5.34k | return i.rex2 || pp.rex2_encoding |
4402 | 5.34k | || i.tm.opcode_modifier.rex2; |
4403 | 5.34k | } |
4404 | | |
4405 | | static unsigned int |
4406 | | get_broadcast_bytes (const insn_template *t, bool diag) |
4407 | 0 | { |
4408 | 0 | unsigned int op, bytes; |
4409 | 0 | const i386_operand_type *types; |
4410 | |
|
4411 | 0 | if (i.broadcast.type) |
4412 | 0 | return (1 << (t->opcode_modifier.broadcast - 1)) * i.broadcast.type; |
4413 | | |
4414 | 0 | gas_assert (intel_syntax); |
4415 | | |
4416 | 0 | for (op = 0; op < t->operands; ++op) |
4417 | 0 | if (t->operand_types[op].bitfield.baseindex) |
4418 | 0 | break; |
4419 | |
|
4420 | 0 | gas_assert (op < t->operands); |
4421 | | |
4422 | 0 | if (t->opcode_modifier.evex != EVEXDYN) |
4423 | 0 | switch (i.broadcast.bytes) |
4424 | 0 | { |
4425 | 0 | case 1: |
4426 | 0 | if (t->operand_types[op].bitfield.word) |
4427 | 0 | return 2; |
4428 | | /* Fall through. */ |
4429 | 0 | case 2: |
4430 | 0 | if (t->operand_types[op].bitfield.dword) |
4431 | 0 | return 4; |
4432 | | /* Fall through. */ |
4433 | 0 | case 4: |
4434 | 0 | if (t->operand_types[op].bitfield.qword) |
4435 | 0 | return 8; |
4436 | | /* Fall through. */ |
4437 | 0 | case 8: |
4438 | 0 | if (t->operand_types[op].bitfield.xmmword) |
4439 | 0 | return 16; |
4440 | 0 | if (t->operand_types[op].bitfield.ymmword) |
4441 | 0 | return 32; |
4442 | 0 | if (t->operand_types[op].bitfield.zmmword) |
4443 | 0 | return 64; |
4444 | | /* Fall through. */ |
4445 | 0 | default: |
4446 | 0 | abort (); |
4447 | 0 | } |
4448 | | |
4449 | 0 | gas_assert (op + 1 < t->operands); |
4450 | | |
4451 | 0 | if (t->operand_types[op + 1].bitfield.xmmword |
4452 | 0 | + t->operand_types[op + 1].bitfield.ymmword |
4453 | 0 | + t->operand_types[op + 1].bitfield.zmmword > 1) |
4454 | 0 | { |
4455 | 0 | types = &i.types[op + 1]; |
4456 | 0 | diag = false; |
4457 | 0 | } |
4458 | 0 | else /* Ambiguous - guess with a preference to non-AVX512VL forms. */ |
4459 | 0 | types = &t->operand_types[op]; |
4460 | |
|
4461 | 0 | if (types->bitfield.zmmword) |
4462 | 0 | bytes = 64; |
4463 | 0 | else if (types->bitfield.ymmword) |
4464 | 0 | bytes = 32; |
4465 | 0 | else |
4466 | 0 | bytes = 16; |
4467 | |
|
4468 | 0 | if (diag) |
4469 | 0 | as_warn (_("ambiguous broadcast for `%s', using %u-bit form"), |
4470 | 0 | insn_name (t), bytes * 8); |
4471 | |
|
4472 | 0 | return bytes; |
4473 | 0 | } |
4474 | | |
4475 | | /* Build the EVEX prefix. */ |
4476 | | |
4477 | | static void |
4478 | | build_evex_prefix (void) |
4479 | 0 | { |
4480 | 0 | unsigned int register_specifier; |
4481 | 0 | bool w; |
4482 | 0 | rex_byte vrex_used = 0; |
4483 | | |
4484 | | /* Check register specifier. */ |
4485 | 0 | if (i.vex.register_specifier) |
4486 | 0 | { |
4487 | 0 | gas_assert ((i.vrex & REX_X) == 0); |
4488 | | |
4489 | 0 | register_specifier = i.vex.register_specifier->reg_num; |
4490 | 0 | if ((i.vex.register_specifier->reg_flags & RegRex)) |
4491 | 0 | register_specifier += 8; |
4492 | | /* The upper 16 registers are encoded in the fourth byte of the |
4493 | | EVEX prefix. */ |
4494 | 0 | if (!(i.vex.register_specifier->reg_flags & RegVRex)) |
4495 | 0 | i.vex.bytes[3] = 0x8; |
4496 | 0 | register_specifier = ~register_specifier & 0xf; |
4497 | 0 | } |
4498 | 0 | else |
4499 | 0 | { |
4500 | 0 | register_specifier = 0xf; |
4501 | | |
4502 | | /* Encode upper 16 vector index register in the fourth byte of |
4503 | | the EVEX prefix. */ |
4504 | 0 | if (!(i.vrex & REX_X)) |
4505 | 0 | i.vex.bytes[3] = 0x8; |
4506 | 0 | else |
4507 | 0 | vrex_used |= REX_X; |
4508 | 0 | } |
4509 | | |
4510 | | /* 4 byte EVEX prefix. */ |
4511 | 0 | i.vex.length = 4; |
4512 | 0 | i.vex.bytes[0] = 0x62; |
4513 | | |
4514 | | /* The high 3 bits of the second EVEX byte are 1's compliment of RXB |
4515 | | bits from REX. */ |
4516 | 0 | gas_assert (i.tm.opcode_space >= SPACE_0F); |
4517 | 0 | gas_assert (i.tm.opcode_space <= SPACE_MAP7); |
4518 | 0 | i.vex.bytes[1] = ((~i.rex & 7) << 5) |
4519 | 0 | | (!dot_insn () ? i.tm.opcode_space |
4520 | 0 | : i.insn_opcode_space); |
4521 | | |
4522 | | /* The fifth bit of the second EVEX byte is 1's compliment of the |
4523 | | REX_R bit in VREX. */ |
4524 | 0 | if (!(i.vrex & REX_R)) |
4525 | 0 | i.vex.bytes[1] |= 0x10; |
4526 | 0 | else |
4527 | 0 | vrex_used |= REX_R; |
4528 | |
|
4529 | 0 | if ((i.reg_operands + i.imm_operands) == i.operands) |
4530 | 0 | { |
4531 | | /* When all operands are registers, the REX_X bit in REX is not |
4532 | | used. We reuse it to encode the upper 16 registers, which is |
4533 | | indicated by the REX_B bit in VREX. The REX_X bit is encoded |
4534 | | as 1's compliment. */ |
4535 | 0 | if ((i.vrex & REX_B)) |
4536 | 0 | { |
4537 | 0 | vrex_used |= REX_B; |
4538 | 0 | i.vex.bytes[1] &= ~0x40; |
4539 | 0 | } |
4540 | 0 | } |
4541 | | |
4542 | | /* EVEX instructions shouldn't need the REX prefix. */ |
4543 | 0 | i.vrex &= ~vrex_used; |
4544 | 0 | gas_assert (i.vrex == 0); |
4545 | | |
4546 | | /* Check the REX.W bit and VEXW. */ |
4547 | 0 | if (i.tm.opcode_modifier.vexw == VEXWIG) |
4548 | 0 | w = evexwig == evexw1 || (i.rex & REX_W); |
4549 | 0 | else if (i.tm.opcode_modifier.vexw && !(i.rex & REX_W)) |
4550 | 0 | w = i.tm.opcode_modifier.vexw == VEXW1; |
4551 | 0 | else |
4552 | 0 | w = flag_code == CODE_64BIT ? i.rex & REX_W : evexwig == evexw1; |
4553 | |
|
4554 | 0 | if (i.tm.opcode_modifier.evex == EVEXDYN) |
4555 | 0 | { |
4556 | 0 | unsigned int op; |
4557 | | |
4558 | | /* Determine vector length from the last multi-length vector operand. */ |
4559 | 0 | for (op = i.operands; op--;) |
4560 | 0 | if (i.tm.operand_types[op].bitfield.xmmword |
4561 | 0 | + i.tm.operand_types[op].bitfield.ymmword |
4562 | 0 | + i.tm.operand_types[op].bitfield.zmmword > 1) |
4563 | 0 | { |
4564 | 0 | if (i.types[op].bitfield.zmmword) |
4565 | 0 | { |
4566 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
4567 | 0 | break; |
4568 | 0 | } |
4569 | 0 | else if (i.types[op].bitfield.ymmword) |
4570 | 0 | { |
4571 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
4572 | 0 | break; |
4573 | 0 | } |
4574 | 0 | else if (i.types[op].bitfield.xmmword) |
4575 | 0 | { |
4576 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
4577 | 0 | break; |
4578 | 0 | } |
4579 | 0 | else if ((i.broadcast.type || i.broadcast.bytes) |
4580 | 0 | && op == i.broadcast.operand) |
4581 | 0 | { |
4582 | 0 | switch (get_broadcast_bytes (&i.tm, true)) |
4583 | 0 | { |
4584 | 0 | case 64: |
4585 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
4586 | 0 | break; |
4587 | 0 | case 32: |
4588 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
4589 | 0 | break; |
4590 | 0 | case 16: |
4591 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
4592 | 0 | break; |
4593 | 0 | default: |
4594 | 0 | abort (); |
4595 | 0 | } |
4596 | 0 | break; |
4597 | 0 | } |
4598 | 0 | } |
4599 | | |
4600 | 0 | if (op >= MAX_OPERANDS) |
4601 | 0 | abort (); |
4602 | 0 | } |
4603 | | |
4604 | | /* The third byte of the EVEX prefix. */ |
4605 | 0 | i.vex.bytes[2] = ((w << 7) |
4606 | 0 | | (register_specifier << 3) |
4607 | 0 | | 4 /* Encode the U bit. */ |
4608 | 0 | | i.tm.opcode_modifier.opcodeprefix); |
4609 | | |
4610 | | /* The fourth byte of the EVEX prefix. */ |
4611 | | /* The zeroing-masking bit. */ |
4612 | 0 | if (i.mask.reg && i.mask.zeroing) |
4613 | 0 | i.vex.bytes[3] |= 0x80; |
4614 | | |
4615 | | /* Don't always set the broadcast bit if there is no RC. */ |
4616 | 0 | if (i.rounding.type == rc_none) |
4617 | 0 | { |
4618 | | /* Encode the vector length. */ |
4619 | 0 | unsigned int vec_length; |
4620 | |
|
4621 | 0 | switch (i.tm.opcode_modifier.evex) |
4622 | 0 | { |
4623 | 0 | case EVEXLIG: /* LL' is ignored */ |
4624 | 0 | vec_length = evexlig << 5; |
4625 | 0 | break; |
4626 | 0 | case EVEX128: |
4627 | 0 | vec_length = 0 << 5; |
4628 | 0 | break; |
4629 | 0 | case EVEX256: |
4630 | 0 | vec_length = 1 << 5; |
4631 | 0 | break; |
4632 | 0 | case EVEX512: |
4633 | 0 | vec_length = 2 << 5; |
4634 | 0 | break; |
4635 | 0 | case EVEX_L3: |
4636 | 0 | if (dot_insn ()) |
4637 | 0 | { |
4638 | 0 | vec_length = 3 << 5; |
4639 | 0 | break; |
4640 | 0 | } |
4641 | | /* Fall through. */ |
4642 | 0 | default: |
4643 | 0 | abort (); |
4644 | 0 | break; |
4645 | 0 | } |
4646 | 0 | i.vex.bytes[3] |= vec_length; |
4647 | | /* Encode the broadcast bit. */ |
4648 | 0 | if (i.broadcast.type || i.broadcast.bytes) |
4649 | 0 | i.vex.bytes[3] |= 0x10; |
4650 | 0 | } |
4651 | 0 | else if (i.rounding.type != saeonly) |
4652 | 0 | i.vex.bytes[3] |= 0x10 | (i.rounding.type << 5); |
4653 | 0 | else |
4654 | 0 | i.vex.bytes[3] |= 0x10 | (evexrcig << 5); |
4655 | | |
4656 | 0 | if (i.mask.reg) |
4657 | 0 | i.vex.bytes[3] |= i.mask.reg->reg_num; |
4658 | 0 | } |
4659 | | |
4660 | | /* Build (2 bytes) rex2 prefix. |
4661 | | | D5h | |
4662 | | | m | R4 X4 B4 | W R X B | |
4663 | | |
4664 | | Rex2 reuses i.vex as they both encode i.tm.opcode_space in their prefixes. |
4665 | | */ |
4666 | | static void |
4667 | | build_rex2_prefix (void) |
4668 | 0 | { |
4669 | 0 | i.vex.length = 2; |
4670 | 0 | i.vex.bytes[0] = 0xd5; |
4671 | | /* For the W R X B bits, the variables of rex prefix will be reused. */ |
4672 | 0 | i.vex.bytes[1] = ((i.tm.opcode_space << 7) |
4673 | 0 | | (i.rex2 << 4) |
4674 | 0 | | ((i.rex | i.prefix[REX_PREFIX]) & 0xf)); |
4675 | 0 | } |
4676 | | |
4677 | | /* Build the EVEX prefix (4-byte) for evex insn |
4678 | | | 62h | |
4679 | | | `R`X`B`R' | B'mmm | |
4680 | | | W | v`v`v`v | `x' | pp | |
4681 | | | z| L'L | b | `v | aaa | |
4682 | | */ |
4683 | | static bool |
4684 | | build_apx_evex_prefix (bool force_nd) |
4685 | 0 | { |
4686 | | /* To mimic behavior for legacy insns, transform use of DATA16 and REX64 into |
4687 | | their embedded-prefix representations. */ |
4688 | 0 | if (i.tm.opcode_space == SPACE_MAP4) |
4689 | 0 | { |
4690 | 0 | if (i.prefix[DATA_PREFIX]) |
4691 | 0 | { |
4692 | 0 | if (i.tm.opcode_modifier.opcodeprefix) |
4693 | 0 | { |
4694 | 0 | as_bad (i.tm.opcode_modifier.opcodeprefix == PREFIX_0X66 |
4695 | 0 | ? _("same type of prefix used twice") |
4696 | 0 | : _("conflicting use of `data16' prefix")); |
4697 | 0 | return false; |
4698 | 0 | } |
4699 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0X66; |
4700 | 0 | i.prefix[DATA_PREFIX] = 0; |
4701 | 0 | } |
4702 | 0 | if (i.prefix[REX_PREFIX] & REX_W) |
4703 | 0 | { |
4704 | 0 | if (i.suffix == QWORD_MNEM_SUFFIX) |
4705 | 0 | { |
4706 | 0 | as_bad (_("same type of prefix used twice")); |
4707 | 0 | return false; |
4708 | 0 | } |
4709 | 0 | i.tm.opcode_modifier.vexw = VEXW1; |
4710 | 0 | i.prefix[REX_PREFIX] = 0; |
4711 | 0 | } |
4712 | 0 | } |
4713 | | |
4714 | 0 | build_evex_prefix (); |
4715 | 0 | if (i.rex2 & REX_R) |
4716 | 0 | i.vex.bytes[1] &= ~0x10; |
4717 | 0 | if (i.rex2 & REX_B) |
4718 | 0 | i.vex.bytes[1] |= 0x08; |
4719 | 0 | if (i.rex2 & REX_X) |
4720 | 0 | { |
4721 | 0 | gas_assert (i.rm.mode != 3); |
4722 | 0 | i.vex.bytes[2] &= ~0x04; |
4723 | 0 | } |
4724 | 0 | if (i.vex.register_specifier |
4725 | 0 | && i.vex.register_specifier->reg_flags & RegRex2) |
4726 | 0 | i.vex.bytes[3] &= ~0x08; |
4727 | | |
4728 | | /* Encode the NDD bit of the instruction promoted from the legacy |
4729 | | space. ZU shares the same bit with NDD. */ |
4730 | 0 | if ((i.vex.register_specifier && i.tm.opcode_space == SPACE_MAP4) |
4731 | 0 | || i.tm.opcode_modifier.operandconstraint == ZERO_UPPER |
4732 | 0 | || force_nd) |
4733 | 0 | i.vex.bytes[3] |= 0x10; |
4734 | | |
4735 | | /* Encode SCC and oszc flags bits. */ |
4736 | 0 | if (i.tm.opcode_modifier.operandconstraint == SCC) |
4737 | 0 | { |
4738 | | /* The default value of vvvv is 1111 and needs to be cleared. */ |
4739 | 0 | i.vex.bytes[2] &= ~0x78; |
4740 | 0 | i.vex.bytes[2] |= (i.oszc_flags << 3); |
4741 | | /* ND and aaa bits shold be 0. */ |
4742 | 0 | know (!(i.vex.bytes[3] & 0x17)); |
4743 | | /* The default value of V' is 1 and needs to be cleared. */ |
4744 | 0 | i.vex.bytes[3] = (i.vex.bytes[3] & ~0x08) | i.scc; |
4745 | 0 | } |
4746 | | |
4747 | | /* Encode the NF bit. */ |
4748 | 0 | if (pp.has_nf || i.tm.opcode_modifier.operandconstraint == EVEX_NF) |
4749 | 0 | i.vex.bytes[3] |= 0x04; |
4750 | |
|
4751 | 0 | return true; |
4752 | 0 | } |
4753 | | |
4754 | | static void establish_rex (void) |
4755 | 2.93k | { |
4756 | | /* Note that legacy encodings have at most 2 non-immediate operands. */ |
4757 | 2.93k | unsigned int first = i.imm_operands; |
4758 | 2.93k | unsigned int last = i.operands > first ? i.operands - first - 1 : first; |
4759 | | |
4760 | | /* Respect a user-specified REX prefix. */ |
4761 | 2.93k | i.rex |= i.prefix[REX_PREFIX] & REX_OPCODE; |
4762 | | |
4763 | | /* For 8 bit RegRex64 registers without a prefix, we need an empty rex prefix. */ |
4764 | 2.93k | if (((i.types[first].bitfield.class == Reg |
4765 | 2.93k | && (i.op[first].regs->reg_flags & RegRex64) != 0) |
4766 | 2.93k | || (i.types[last].bitfield.class == Reg |
4767 | 2.93k | && (i.op[last].regs->reg_flags & RegRex64) != 0)) |
4768 | 2.93k | && !is_apx_rex2_encoding () && !is_any_vex_encoding (&i.tm)) |
4769 | 0 | i.rex |= REX_OPCODE; |
4770 | | |
4771 | | /* For REX/REX2/EVEX prefix instructions, we need to convert old registers |
4772 | | (AL, CL, DL and BL) to new ones (AXL, CXL, DXL and BXL) and reject AH, |
4773 | | CH, DH and BH. */ |
4774 | 2.93k | if (i.rex || i.rex2 || i.tm.opcode_modifier.evex) |
4775 | 10 | { |
4776 | 19 | for (unsigned int x = first; x <= last; x++) |
4777 | 9 | { |
4778 | | /* Look for 8 bit operand that uses old registers. */ |
4779 | 9 | if (i.types[x].bitfield.class == Reg && i.types[x].bitfield.byte |
4780 | 9 | && !(i.op[x].regs->reg_flags & (RegRex | RegRex2 | RegRex64))) |
4781 | 0 | { |
4782 | | /* In case it is "hi" register, give up. */ |
4783 | 0 | if (i.op[x].regs->reg_num > 3) |
4784 | 0 | as_bad (_("can't encode register '%s%s' in an " |
4785 | 0 | "instruction requiring %s prefix"), |
4786 | 0 | register_prefix, i.op[x].regs->reg_name, |
4787 | 0 | i.tm.opcode_modifier.evex ? "EVEX" : "REX/REX2"); |
4788 | | |
4789 | | /* Otherwise it is equivalent to the extended register. |
4790 | | Since the encoding doesn't change this is merely |
4791 | | cosmetic cleanup for debug output. */ |
4792 | 0 | i.op[x].regs += 8; |
4793 | 0 | } |
4794 | 9 | } |
4795 | 10 | } |
4796 | | |
4797 | 2.93k | if (i.rex == 0 && i.rex2 == 0 && (pp.rex_encoding || pp.rex2_encoding)) |
4798 | 0 | { |
4799 | | /* Check if we can add a REX_OPCODE byte. Look for 8 bit operand |
4800 | | that uses legacy register. If it is "hi" register, don't add |
4801 | | rex and rex2 prefix. */ |
4802 | 0 | unsigned int x; |
4803 | |
|
4804 | 0 | for (x = first; x <= last; x++) |
4805 | 0 | if (i.types[x].bitfield.class == Reg |
4806 | 0 | && i.types[x].bitfield.byte |
4807 | 0 | && !(i.op[x].regs->reg_flags & (RegRex | RegRex2 | RegRex64)) |
4808 | 0 | && i.op[x].regs->reg_num > 3) |
4809 | 0 | { |
4810 | 0 | pp.rex_encoding = false; |
4811 | 0 | pp.rex2_encoding = false; |
4812 | 0 | break; |
4813 | 0 | } |
4814 | |
|
4815 | 0 | if (pp.rex_encoding) |
4816 | 0 | i.rex = REX_OPCODE; |
4817 | 0 | } |
4818 | | |
4819 | 2.93k | if (is_apx_rex2_encoding ()) |
4820 | 0 | { |
4821 | | /* Most prefixes are not permitted with JMPABS. */ |
4822 | 0 | if (i.tm.mnem_off == MN_jmpabs) |
4823 | 0 | { |
4824 | 0 | if (i.prefix[DATA_PREFIX] || (i.prefix[REX_PREFIX] & REX_W)) |
4825 | 0 | { |
4826 | 0 | as_bad (_("size override not allowed with `%s'"), |
4827 | 0 | insn_name (&i.tm)); |
4828 | 0 | i.prefix[DATA_PREFIX] = 0; |
4829 | 0 | i.prefix[REX_PREFIX] &= ~REX_W; |
4830 | 0 | } |
4831 | 0 | if (i.prefix[ADDR_PREFIX]) |
4832 | 0 | { |
4833 | 0 | as_bad (_("address override not allowed with `%s'"), |
4834 | 0 | insn_name (&i.tm)); |
4835 | 0 | i.prefix[ADDR_PREFIX] = 0; |
4836 | 0 | } |
4837 | 0 | } |
4838 | |
|
4839 | 0 | build_rex2_prefix (); |
4840 | | /* The individual REX.RXBW bits got consumed. */ |
4841 | 0 | i.rex &= REX_OPCODE; |
4842 | 0 | i.prefix[REX_PREFIX] = 0; |
4843 | 0 | } |
4844 | 2.93k | else if (i.rex != 0) |
4845 | 10 | add_prefix (REX_OPCODE | i.rex); |
4846 | 2.93k | } |
4847 | | |
4848 | | static void |
4849 | | process_immext (void) |
4850 | 0 | { |
4851 | 0 | expressionS *exp; |
4852 | | |
4853 | | /* These AMD 3DNow! and SSE2 instructions have an opcode suffix |
4854 | | which is coded in the same place as an 8-bit immediate field |
4855 | | would be. Here we fake an 8-bit immediate operand from the |
4856 | | opcode suffix stored in tm.extension_opcode. |
4857 | | |
4858 | | AVX instructions also use this encoding, for some of |
4859 | | 3 argument instructions. */ |
4860 | |
|
4861 | 0 | gas_assert (i.imm_operands <= 1 |
4862 | 0 | && (i.operands <= 2 |
4863 | 0 | || (is_any_vex_encoding (&i.tm) |
4864 | 0 | && i.operands <= 4))); |
4865 | | |
4866 | 0 | exp = &im_expressions[i.imm_operands++]; |
4867 | 0 | i.op[i.operands].imms = exp; |
4868 | 0 | i.types[i.operands].bitfield.imm8 = 1; |
4869 | 0 | i.operands++; |
4870 | 0 | exp->X_op = O_constant; |
4871 | 0 | exp->X_add_number = i.tm.extension_opcode; |
4872 | 0 | i.tm.extension_opcode = None; |
4873 | 0 | } |
4874 | | |
4875 | | |
4876 | | static int |
4877 | | check_hle (void) |
4878 | 0 | { |
4879 | 0 | switch (i.tm.opcode_modifier.prefixok) |
4880 | 0 | { |
4881 | 0 | default: |
4882 | 0 | abort (); |
4883 | 0 | case PrefixLock: |
4884 | 0 | case PrefixNone: |
4885 | 0 | case PrefixNoTrack: |
4886 | 0 | case PrefixRep: |
4887 | 0 | as_bad (_("invalid instruction `%s' after `%s'"), |
4888 | 0 | insn_name (&i.tm), i.hle_prefix); |
4889 | 0 | return 0; |
4890 | 0 | case PrefixHLELock: |
4891 | 0 | if (i.prefix[LOCK_PREFIX]) |
4892 | 0 | return 1; |
4893 | 0 | as_bad (_("missing `lock' with `%s'"), i.hle_prefix); |
4894 | 0 | return 0; |
4895 | 0 | case PrefixHLEAny: |
4896 | 0 | return 1; |
4897 | 0 | case PrefixHLERelease: |
4898 | 0 | if (i.prefix[HLE_PREFIX] != XRELEASE_PREFIX_OPCODE) |
4899 | 0 | { |
4900 | 0 | as_bad (_("instruction `%s' after `xacquire' not allowed"), |
4901 | 0 | insn_name (&i.tm)); |
4902 | 0 | return 0; |
4903 | 0 | } |
4904 | 0 | if (i.mem_operands == 0 || !(i.flags[i.operands - 1] & Operand_Mem)) |
4905 | 0 | { |
4906 | 0 | as_bad (_("memory destination needed for instruction `%s'" |
4907 | 0 | " after `xrelease'"), insn_name (&i.tm)); |
4908 | 0 | return 0; |
4909 | 0 | } |
4910 | 0 | return 1; |
4911 | 0 | } |
4912 | 0 | } |
4913 | | |
4914 | | /* Helper for optimization (running ahead of process_suffix()), to make sure we |
4915 | | convert only well-formed insns. @OP is the sized operand to cross check |
4916 | | against (typically a register). Checking against a single operand typically |
4917 | | suffices, as match_template() has already honored CheckOperandSize. */ |
4918 | | |
4919 | | static bool is_plausible_suffix (unsigned int op) |
4920 | 0 | { |
4921 | 0 | return !i.suffix |
4922 | 0 | || (i.suffix == BYTE_MNEM_SUFFIX && i.types[op].bitfield.byte) |
4923 | 0 | || (i.suffix == WORD_MNEM_SUFFIX && i.types[op].bitfield.word) |
4924 | 0 | || (i.suffix == LONG_MNEM_SUFFIX && i.types[op].bitfield.dword) |
4925 | 0 | || (i.suffix == QWORD_MNEM_SUFFIX && i.types[op].bitfield.qword); |
4926 | 0 | } |
4927 | | |
4928 | | /* Encode aligned vector move as unaligned vector move. */ |
4929 | | |
4930 | | static void |
4931 | | encode_with_unaligned_vector_move (void) |
4932 | 0 | { |
4933 | 0 | switch (i.tm.base_opcode) |
4934 | 0 | { |
4935 | 0 | case 0x28: /* Load instructions. */ |
4936 | 0 | case 0x29: /* Store instructions. */ |
4937 | | /* movaps/movapd/vmovaps/vmovapd. */ |
4938 | 0 | if (i.tm.opcode_space == SPACE_0F |
4939 | 0 | && i.tm.opcode_modifier.opcodeprefix <= PREFIX_0X66) |
4940 | 0 | i.tm.base_opcode = 0x10 | (i.tm.base_opcode & 1); |
4941 | 0 | break; |
4942 | 0 | case 0x6f: /* Load instructions. */ |
4943 | 0 | case 0x7f: /* Store instructions. */ |
4944 | | /* movdqa/vmovdqa/vmovdqa64/vmovdqa32. */ |
4945 | 0 | if (i.tm.opcode_space == SPACE_0F |
4946 | 0 | && i.tm.opcode_modifier.opcodeprefix == PREFIX_0X66) |
4947 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
4948 | 0 | break; |
4949 | 0 | default: |
4950 | 0 | break; |
4951 | 0 | } |
4952 | 0 | } |
4953 | | |
4954 | | /* Try the shortest encoding by shortening operand size. */ |
4955 | | |
4956 | | static void |
4957 | | optimize_encoding (void) |
4958 | 0 | { |
4959 | 0 | unsigned int j; |
4960 | |
|
4961 | 0 | if (i.tm.mnem_off == MN_lea) |
4962 | 0 | { |
4963 | | /* Optimize: -O: |
4964 | | lea symbol, %rN -> mov $symbol, %rN |
4965 | | lea (%rM), %rN -> mov %rM, %rN |
4966 | | lea (,%rM,1), %rN -> mov %rM, %rN |
4967 | | |
4968 | | and in 32-bit mode for 16-bit addressing |
4969 | | |
4970 | | lea (%rM), %rN -> movzx %rM, %rN |
4971 | | |
4972 | | and in 64-bit mode zap 32-bit addressing in favor of using a |
4973 | | 32-bit (or less) destination. |
4974 | | */ |
4975 | 0 | if (flag_code == CODE_64BIT && i.prefix[ADDR_PREFIX]) |
4976 | 0 | { |
4977 | 0 | if (!i.op[1].regs->reg_type.bitfield.word) |
4978 | 0 | i.tm.opcode_modifier.size = SIZE32; |
4979 | 0 | i.prefix[ADDR_PREFIX] = 0; |
4980 | 0 | } |
4981 | |
|
4982 | 0 | if (!i.index_reg && !i.base_reg) |
4983 | 0 | { |
4984 | | /* Handle: |
4985 | | lea symbol, %rN -> mov $symbol, %rN |
4986 | | */ |
4987 | 0 | if (flag_code == CODE_64BIT) |
4988 | 0 | { |
4989 | | /* Don't transform a relocation to a 16-bit one. */ |
4990 | 0 | if (i.op[0].disps |
4991 | 0 | && i.op[0].disps->X_op != O_constant |
4992 | 0 | && i.op[1].regs->reg_type.bitfield.word) |
4993 | 0 | return; |
4994 | | |
4995 | 0 | if (!i.op[1].regs->reg_type.bitfield.qword |
4996 | 0 | || i.tm.opcode_modifier.size == SIZE32) |
4997 | 0 | { |
4998 | 0 | i.tm.base_opcode = 0xb8; |
4999 | 0 | i.tm.opcode_modifier.modrm = 0; |
5000 | 0 | if (!i.op[1].regs->reg_type.bitfield.word) |
5001 | 0 | i.types[0].bitfield.imm32 = 1; |
5002 | 0 | else |
5003 | 0 | { |
5004 | 0 | i.tm.opcode_modifier.size = SIZE16; |
5005 | 0 | i.types[0].bitfield.imm16 = 1; |
5006 | 0 | } |
5007 | 0 | } |
5008 | 0 | else |
5009 | 0 | { |
5010 | | /* Subject to further optimization below. */ |
5011 | 0 | i.tm.base_opcode = 0xc7; |
5012 | 0 | i.tm.extension_opcode = 0; |
5013 | 0 | i.types[0].bitfield.imm32s = 1; |
5014 | 0 | i.types[0].bitfield.baseindex = 0; |
5015 | 0 | } |
5016 | 0 | } |
5017 | | /* Outside of 64-bit mode address and operand sizes have to match if |
5018 | | a relocation is involved, as otherwise we wouldn't (currently) or |
5019 | | even couldn't express the relocation correctly. */ |
5020 | 0 | else if (i.op[0].disps |
5021 | 0 | && i.op[0].disps->X_op != O_constant |
5022 | 0 | && ((!i.prefix[ADDR_PREFIX]) |
5023 | 0 | != (flag_code == CODE_32BIT |
5024 | 0 | ? i.op[1].regs->reg_type.bitfield.dword |
5025 | 0 | : i.op[1].regs->reg_type.bitfield.word))) |
5026 | 0 | return; |
5027 | | /* In 16-bit mode converting LEA with 16-bit addressing and a 32-bit |
5028 | | destination is going to grow encoding size. */ |
5029 | 0 | else if (flag_code == CODE_16BIT |
5030 | 0 | && (optimize <= 1 || optimize_for_space) |
5031 | 0 | && !i.prefix[ADDR_PREFIX] |
5032 | 0 | && i.op[1].regs->reg_type.bitfield.dword) |
5033 | 0 | return; |
5034 | 0 | else |
5035 | 0 | { |
5036 | 0 | i.tm.base_opcode = 0xb8; |
5037 | 0 | i.tm.opcode_modifier.modrm = 0; |
5038 | 0 | if (i.op[1].regs->reg_type.bitfield.dword) |
5039 | 0 | i.types[0].bitfield.imm32 = 1; |
5040 | 0 | else |
5041 | 0 | i.types[0].bitfield.imm16 = 1; |
5042 | |
|
5043 | 0 | if (i.op[0].disps |
5044 | 0 | && i.op[0].disps->X_op == O_constant |
5045 | 0 | && i.op[1].regs->reg_type.bitfield.dword |
5046 | | /* NB: Add () to !i.prefix[ADDR_PREFIX] to silence |
5047 | | GCC 5. */ |
5048 | 0 | && (!i.prefix[ADDR_PREFIX]) != (flag_code == CODE_32BIT)) |
5049 | 0 | i.op[0].disps->X_add_number &= 0xffff; |
5050 | 0 | } |
5051 | | |
5052 | 0 | i.tm.operand_types[0] = i.types[0]; |
5053 | 0 | i.imm_operands = 1; |
5054 | 0 | if (!i.op[0].imms) |
5055 | 0 | { |
5056 | 0 | i.op[0].imms = &im_expressions[0]; |
5057 | 0 | i.op[0].imms->X_op = O_absent; |
5058 | 0 | } |
5059 | 0 | } |
5060 | 0 | else if (i.op[0].disps |
5061 | 0 | && (i.op[0].disps->X_op != O_constant |
5062 | 0 | || i.op[0].disps->X_add_number)) |
5063 | 0 | return; |
5064 | 0 | else |
5065 | 0 | { |
5066 | | /* Handle: |
5067 | | lea (%rM), %rN -> mov %rM, %rN |
5068 | | lea (,%rM,1), %rN -> mov %rM, %rN |
5069 | | lea (%rM), %rN -> movzx %rM, %rN |
5070 | | */ |
5071 | 0 | const reg_entry *addr_reg; |
5072 | |
|
5073 | 0 | if (!i.index_reg && i.base_reg->reg_num != RegIP) |
5074 | 0 | addr_reg = i.base_reg; |
5075 | 0 | else if (!i.base_reg |
5076 | 0 | && i.index_reg->reg_num != RegIZ |
5077 | 0 | && !i.log2_scale_factor) |
5078 | 0 | addr_reg = i.index_reg; |
5079 | 0 | else |
5080 | 0 | return; |
5081 | | |
5082 | 0 | if (addr_reg->reg_type.bitfield.word |
5083 | 0 | && i.op[1].regs->reg_type.bitfield.dword) |
5084 | 0 | { |
5085 | 0 | if (flag_code != CODE_32BIT) |
5086 | 0 | return; |
5087 | 0 | i.tm.opcode_space = SPACE_0F; |
5088 | 0 | i.tm.base_opcode = 0xb7; |
5089 | 0 | } |
5090 | 0 | else |
5091 | 0 | i.tm.base_opcode = 0x8b; |
5092 | | |
5093 | 0 | if (addr_reg->reg_type.bitfield.dword |
5094 | 0 | && i.op[1].regs->reg_type.bitfield.qword) |
5095 | 0 | i.tm.opcode_modifier.size = SIZE32; |
5096 | |
|
5097 | 0 | i.op[0].regs = addr_reg; |
5098 | 0 | i.reg_operands = 2; |
5099 | 0 | } |
5100 | | |
5101 | 0 | i.mem_operands = 0; |
5102 | 0 | i.disp_operands = 0; |
5103 | 0 | i.prefix[ADDR_PREFIX] = 0; |
5104 | 0 | i.prefix[SEG_PREFIX] = 0; |
5105 | 0 | i.seg[0] = NULL; |
5106 | 0 | } |
5107 | | |
5108 | 0 | if (optimize_for_space |
5109 | 0 | && (i.tm.mnem_off == MN_test |
5110 | 0 | || (i.tm.base_opcode == 0xf6 |
5111 | 0 | && i.tm.opcode_space == SPACE_MAP4)) |
5112 | 0 | && i.reg_operands == 1 |
5113 | 0 | && i.imm_operands == 1 |
5114 | 0 | && !i.types[1].bitfield.byte |
5115 | 0 | && is_plausible_suffix (1) |
5116 | 0 | && i.op[0].imms->X_op == O_constant |
5117 | 0 | && fits_in_imm7 (i.op[0].imms->X_add_number)) |
5118 | 0 | { |
5119 | | /* Optimize: -Os: |
5120 | | test $imm7, %r64/%r32/%r16 -> test $imm7, %r8 |
5121 | | ctest<cc> $imm7, %r64/%r32/%r16 -> ctest<cc> $imm7, %r8 |
5122 | | */ |
5123 | 0 | unsigned int base_regnum = i.op[1].regs->reg_num; |
5124 | |
|
5125 | 0 | gas_assert (!i.tm.opcode_modifier.modrm || i.tm.extension_opcode == 0); |
5126 | | |
5127 | 0 | if (flag_code == CODE_64BIT || base_regnum < 4) |
5128 | 0 | { |
5129 | 0 | i.types[1].bitfield.byte = 1; |
5130 | | /* Squash the suffix. */ |
5131 | 0 | i.suffix = 0; |
5132 | | /* Convert to byte registers. 8-bit registers are special, |
5133 | | RegRex64 and non-RegRex* each have 8 registers. */ |
5134 | 0 | if (i.types[1].bitfield.word) |
5135 | | /* 32 (or 40) 8-bit registers. */ |
5136 | 0 | j = 32; |
5137 | 0 | else if (i.types[1].bitfield.dword) |
5138 | | /* 32 (or 40) 8-bit registers + 32 16-bit registers. */ |
5139 | 0 | j = 64; |
5140 | 0 | else |
5141 | | /* 32 (or 40) 8-bit registers + 32 16-bit registers |
5142 | | + 32 32-bit registers. */ |
5143 | 0 | j = 96; |
5144 | | |
5145 | | /* In 64-bit mode, the following byte registers cannot be accessed |
5146 | | if using the Rex and Rex2 prefix: AH, BH, CH, DH */ |
5147 | 0 | if (!(i.op[1].regs->reg_flags & (RegRex | RegRex2)) && base_regnum < 4) |
5148 | 0 | j += 8; |
5149 | 0 | i.op[1].regs -= j; |
5150 | 0 | } |
5151 | 0 | } |
5152 | 0 | else if (flag_code == CODE_64BIT |
5153 | 0 | && i.tm.opcode_space == SPACE_BASE |
5154 | 0 | && i.types[i.operands - 1].bitfield.qword |
5155 | 0 | && ((i.reg_operands == 1 |
5156 | 0 | && i.imm_operands == 1 |
5157 | 0 | && i.op[0].imms->X_op == O_constant |
5158 | 0 | && ((i.tm.base_opcode == 0xb8 |
5159 | 0 | && i.tm.extension_opcode == None |
5160 | 0 | && fits_in_unsigned_long (i.op[0].imms->X_add_number)) |
5161 | 0 | || (fits_in_imm31 (i.op[0].imms->X_add_number) |
5162 | 0 | && (i.tm.base_opcode == 0x24 |
5163 | 0 | || (((i.tm.base_opcode == 0x80 |
5164 | 0 | && i.tm.extension_opcode == 0x4) |
5165 | 0 | || i.tm.mnem_off == MN_test) |
5166 | 0 | && !(i.op[1].regs->reg_flags |
5167 | 0 | & (RegRex | RegRex2))) |
5168 | 0 | || ((i.tm.base_opcode | 1) == 0xc7 |
5169 | 0 | && i.tm.extension_opcode == 0x0))) |
5170 | 0 | || (fits_in_imm7 (i.op[0].imms->X_add_number) |
5171 | 0 | && i.tm.base_opcode == 0x83 |
5172 | 0 | && i.tm.extension_opcode == 0x4 |
5173 | 0 | && !(i.op[1].regs->reg_flags & (RegRex | RegRex2))))) |
5174 | 0 | || ((i.reg_operands == 2 |
5175 | 0 | && i.op[0].regs == i.op[1].regs |
5176 | 0 | && (i.tm.mnem_off == MN_xor |
5177 | 0 | || i.tm.mnem_off == MN_sub)) |
5178 | 0 | || i.tm.mnem_off == MN_clr))) |
5179 | 0 | { |
5180 | | /* Optimize: -O: |
5181 | | andq $imm31, %r64 -> andl $imm31, %r32 |
5182 | | andq $imm7, %r64 -> andl $imm7, %r32 |
5183 | | testq $imm31, %r64 -> testl $imm31, %r32 |
5184 | | xorq %r64, %r64 -> xorl %r32, %r32 |
5185 | | clrq %r64 -> clrl %r32 |
5186 | | subq %r64, %r64 -> subl %r32, %r32 |
5187 | | movq $imm31, %r64 -> movl $imm31, %r32 |
5188 | | movq $imm32, %r64 -> movl $imm32, %r32 |
5189 | | */ |
5190 | 0 | i.tm.opcode_modifier.size = SIZE32; |
5191 | 0 | if (i.imm_operands) |
5192 | 0 | { |
5193 | 0 | i.types[0].bitfield.imm32 = 1; |
5194 | 0 | i.types[0].bitfield.imm32s = 0; |
5195 | 0 | i.types[0].bitfield.imm64 = 0; |
5196 | 0 | } |
5197 | 0 | else |
5198 | 0 | { |
5199 | 0 | i.types[0].bitfield.dword = 1; |
5200 | 0 | i.types[0].bitfield.qword = 0; |
5201 | 0 | } |
5202 | 0 | i.types[1].bitfield.dword = 1; |
5203 | 0 | i.types[1].bitfield.qword = 0; |
5204 | 0 | if (i.tm.mnem_off == MN_mov || i.tm.mnem_off == MN_lea) |
5205 | 0 | { |
5206 | | /* Handle |
5207 | | movq $imm31, %r64 -> movl $imm31, %r32 |
5208 | | movq $imm32, %r64 -> movl $imm32, %r32 |
5209 | | */ |
5210 | 0 | i.tm.operand_types[0].bitfield.imm32 = 1; |
5211 | 0 | i.tm.operand_types[0].bitfield.imm32s = 0; |
5212 | 0 | i.tm.operand_types[0].bitfield.imm64 = 0; |
5213 | 0 | if ((i.tm.base_opcode | 1) == 0xc7) |
5214 | 0 | { |
5215 | | /* Handle |
5216 | | movq $imm31, %r64 -> movl $imm31, %r32 |
5217 | | */ |
5218 | 0 | i.tm.base_opcode = 0xb8; |
5219 | 0 | i.tm.extension_opcode = None; |
5220 | 0 | i.tm.opcode_modifier.w = 0; |
5221 | 0 | i.tm.opcode_modifier.modrm = 0; |
5222 | 0 | } |
5223 | 0 | } |
5224 | 0 | } |
5225 | 0 | else if (i.reg_operands == 3 |
5226 | 0 | && i.op[0].regs == i.op[1].regs |
5227 | 0 | && pp.encoding != encoding_evex |
5228 | 0 | && (i.tm.mnem_off == MN_xor |
5229 | 0 | || i.tm.mnem_off == MN_sub)) |
5230 | 0 | { |
5231 | | /* Optimize: -O: |
5232 | | xorb %rNb, %rNb, %rMb -> xorl %rMd, %rMd |
5233 | | xorw %rNw, %rNw, %rMw -> xorl %rMd, %rMd |
5234 | | xorl %rNd, %rNd, %rMd -> xorl %rMd, %rMd |
5235 | | xorq %rN, %rN, %rM -> xorl %rMd, %rMd |
5236 | | subb %rNb, %rNb, %rMb -> subl %rMd, %rMd |
5237 | | subw %rNw, %rNw, %rMw -> subl %rMd, %rMd |
5238 | | subl %rNd, %rNd, %rMd -> subl %rMd, %rMd |
5239 | | subq %rN, %rN, %rM -> subl %rMd, %rMd |
5240 | | */ |
5241 | 0 | i.tm.opcode_space = SPACE_BASE; |
5242 | 0 | i.tm.opcode_modifier.evex = 0; |
5243 | 0 | i.tm.opcode_modifier.size = SIZE32; |
5244 | 0 | i.types[0].bitfield.byte = 0; |
5245 | 0 | i.types[0].bitfield.word = 0; |
5246 | 0 | i.types[0].bitfield.dword = 1; |
5247 | 0 | i.types[0].bitfield.qword = 0; |
5248 | 0 | i.op[0].regs = i.op[2].regs; |
5249 | 0 | i.types[1] = i.types[0]; |
5250 | 0 | i.op[1].regs = i.op[2].regs; |
5251 | 0 | i.reg_operands = 2; |
5252 | 0 | } |
5253 | 0 | else if (optimize > 1 |
5254 | 0 | && !optimize_for_space |
5255 | 0 | && i.reg_operands == 2 |
5256 | 0 | && i.op[0].regs == i.op[1].regs |
5257 | 0 | && (i.tm.mnem_off == MN_and || i.tm.mnem_off == MN_or) |
5258 | 0 | && (flag_code != CODE_64BIT || !i.types[0].bitfield.dword)) |
5259 | 0 | { |
5260 | | /* Optimize: -O2: |
5261 | | andb %rN, %rN -> testb %rN, %rN |
5262 | | andw %rN, %rN -> testw %rN, %rN |
5263 | | andq %rN, %rN -> testq %rN, %rN |
5264 | | orb %rN, %rN -> testb %rN, %rN |
5265 | | orw %rN, %rN -> testw %rN, %rN |
5266 | | orq %rN, %rN -> testq %rN, %rN |
5267 | | |
5268 | | and outside of 64-bit mode |
5269 | | |
5270 | | andl %rN, %rN -> testl %rN, %rN |
5271 | | orl %rN, %rN -> testl %rN, %rN |
5272 | | */ |
5273 | 0 | i.tm.base_opcode = 0x84 | (i.tm.base_opcode & 1); |
5274 | 0 | } |
5275 | 0 | else if (!optimize_for_space |
5276 | 0 | && i.tm.base_opcode == 0xd0 |
5277 | 0 | && i.tm.extension_opcode == 4 |
5278 | 0 | && (i.tm.opcode_space == SPACE_BASE |
5279 | 0 | || i.tm.opcode_space == SPACE_MAP4) |
5280 | 0 | && !i.mem_operands) |
5281 | 0 | { |
5282 | | /* Optimize: -O: |
5283 | | shlb $1, %rN -> addb %rN, %rN |
5284 | | shlw $1, %rN -> addw %rN, %rN |
5285 | | shll $1, %rN -> addl %rN, %rN |
5286 | | shlq $1, %rN -> addq %rN, %rN |
5287 | | |
5288 | | shlb $1, %rN, %rM -> addb %rN, %rN, %rM |
5289 | | shlw $1, %rN, %rM -> addw %rN, %rN, %rM |
5290 | | shll $1, %rN, %rM -> addl %rN, %rN, %rM |
5291 | | shlq $1, %rN, %rM -> addq %rN, %rN, %rM |
5292 | | */ |
5293 | 0 | i.tm.base_opcode = 0x00; |
5294 | 0 | i.tm.extension_opcode = None; |
5295 | 0 | if (i.operands >= 2) |
5296 | 0 | copy_operand (0, 1); |
5297 | 0 | else |
5298 | 0 | { |
5299 | | /* Legacy form with omitted shift count operand. */ |
5300 | 0 | copy_operand (1, 0); |
5301 | 0 | i.operands = 2; |
5302 | 0 | } |
5303 | 0 | i.reg_operands++; |
5304 | 0 | i.imm_operands = 0; |
5305 | 0 | } |
5306 | 0 | else if (i.tm.base_opcode == 0xba |
5307 | 0 | && i.tm.opcode_space == SPACE_0F |
5308 | 0 | && i.reg_operands == 1 |
5309 | 0 | && i.op[0].imms->X_op == O_constant |
5310 | 0 | && i.op[0].imms->X_add_number >= 0) |
5311 | 0 | { |
5312 | | /* Optimize: -O: |
5313 | | btw $n, %rN -> btl $n, %rN (outside of 16-bit mode, n < 16) |
5314 | | btq $n, %rN -> btl $n, %rN (in 64-bit mode, n < 32, N < 8) |
5315 | | btl $n, %rN -> btw $n, %rN (in 16-bit mode, n < 16) |
5316 | | |
5317 | | With <BT> one of bts, btr, and bts also: |
5318 | | <BT>w $n, %rN -> btl $n, %rN (in 32-bit mode, n < 16) |
5319 | | <BT>l $n, %rN -> btw $n, %rN (in 16-bit mode, n < 16) |
5320 | | */ |
5321 | 0 | switch (flag_code) |
5322 | 0 | { |
5323 | 0 | case CODE_64BIT: |
5324 | 0 | if (i.tm.extension_opcode != 4) |
5325 | 0 | break; |
5326 | 0 | if (i.types[1].bitfield.qword |
5327 | 0 | && i.op[0].imms->X_add_number < 32 |
5328 | 0 | && !(i.op[1].regs->reg_flags & RegRex)) |
5329 | 0 | i.tm.opcode_modifier.size = SIZE32; |
5330 | | /* Fall through. */ |
5331 | 0 | case CODE_32BIT: |
5332 | 0 | if (i.types[1].bitfield.word |
5333 | 0 | && i.op[0].imms->X_add_number < 16) |
5334 | 0 | i.tm.opcode_modifier.size = SIZE32; |
5335 | 0 | break; |
5336 | 0 | case CODE_16BIT: |
5337 | 0 | if (i.op[0].imms->X_add_number < 16) |
5338 | 0 | i.tm.opcode_modifier.size = SIZE16; |
5339 | 0 | break; |
5340 | 0 | } |
5341 | 0 | } |
5342 | 0 | else if (optimize > 1 |
5343 | 0 | && (i.tm.base_opcode | 0xf) == 0x4f |
5344 | 0 | && i.tm.opcode_space == SPACE_MAP4 |
5345 | 0 | && i.reg_operands == 3 |
5346 | 0 | && i.tm.opcode_modifier.operandconstraint == EVEX_NF |
5347 | 0 | && !i.types[0].bitfield.word) |
5348 | 0 | { |
5349 | | /* Optimize: -O2: |
5350 | | cfcmov<cc> %rM, %rN, %rN -> cmov<cc> %rM, %rN |
5351 | | cfcmov<cc> %rM, %rN, %rM -> cmov<!cc> %rN, %rM |
5352 | | cfcmov<cc> %rN, %rN, %rN -> nop %rN |
5353 | | */ |
5354 | 0 | if (i.op[0].regs == i.op[2].regs) |
5355 | 0 | { |
5356 | 0 | i.tm.base_opcode ^= 1; |
5357 | 0 | i.op[0].regs = i.op[1].regs; |
5358 | 0 | i.op[1].regs = i.op[2].regs; |
5359 | 0 | } |
5360 | 0 | else if (i.op[1].regs != i.op[2].regs) |
5361 | 0 | return; |
5362 | | |
5363 | 0 | i.tm.opcode_space = SPACE_0F; |
5364 | 0 | i.tm.opcode_modifier.evex = 0; |
5365 | 0 | i.tm.opcode_modifier.vexvvvv = 0; |
5366 | 0 | i.tm.opcode_modifier.operandconstraint = 0; |
5367 | 0 | i.reg_operands = 2; |
5368 | | |
5369 | | /* While at it, convert to NOP if all three regs match. */ |
5370 | 0 | if (i.op[0].regs == i.op[1].regs) |
5371 | 0 | { |
5372 | 0 | i.tm.base_opcode = 0x1f; |
5373 | 0 | i.tm.extension_opcode = 0; |
5374 | 0 | i.reg_operands = 1; |
5375 | 0 | } |
5376 | 0 | } |
5377 | 0 | else if (i.reg_operands == 3 |
5378 | 0 | && i.op[0].regs == i.op[1].regs |
5379 | 0 | && !i.types[2].bitfield.xmmword |
5380 | 0 | && (i.tm.opcode_modifier.vex |
5381 | 0 | || ((!i.mask.reg || i.mask.zeroing) |
5382 | 0 | && i.tm.opcode_modifier.evex |
5383 | 0 | && (pp.encoding != encoding_evex |
5384 | 0 | || cpu_arch_isa_flags.bitfield.cpuavx512vl |
5385 | 0 | || is_cpu (&i.tm, CpuAVX512VL) |
5386 | 0 | || (i.tm.operand_types[2].bitfield.zmmword |
5387 | 0 | && i.types[2].bitfield.ymmword)))) |
5388 | 0 | && i.tm.opcode_space == SPACE_0F |
5389 | 0 | && ((i.tm.base_opcode | 2) == 0x57 |
5390 | 0 | || i.tm.base_opcode == 0xdf |
5391 | 0 | || i.tm.base_opcode == 0xef |
5392 | 0 | || (i.tm.base_opcode | 3) == 0xfb |
5393 | 0 | || i.tm.base_opcode == 0x42 |
5394 | 0 | || i.tm.base_opcode == 0x47)) |
5395 | 0 | { |
5396 | | /* Optimize: -O1: |
5397 | | VOP, one of vandnps, vandnpd, vxorps, vxorpd, vpsubb, vpsubd, |
5398 | | vpsubq and vpsubw: |
5399 | | EVEX VOP %zmmM, %zmmM, %zmmN |
5400 | | -> VEX VOP %xmmM, %xmmM, %xmmN (M and N < 16) |
5401 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5402 | | EVEX VOP %ymmM, %ymmM, %ymmN |
5403 | | -> VEX VOP %xmmM, %xmmM, %xmmN (M and N < 16) |
5404 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5405 | | VEX VOP %ymmM, %ymmM, %ymmN |
5406 | | -> VEX VOP %xmmM, %xmmM, %xmmN |
5407 | | VOP, one of vpandn and vpxor: |
5408 | | VEX VOP %ymmM, %ymmM, %ymmN |
5409 | | -> VEX VOP %xmmM, %xmmM, %xmmN |
5410 | | VOP, one of vpandnd and vpandnq: |
5411 | | EVEX VOP %zmmM, %zmmM, %zmmN |
5412 | | -> VEX vpandn %xmmM, %xmmM, %xmmN (M and N < 16) |
5413 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5414 | | EVEX VOP %ymmM, %ymmM, %ymmN |
5415 | | -> VEX vpandn %xmmM, %xmmM, %xmmN (M and N < 16) |
5416 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5417 | | VOP, one of vpxord and vpxorq: |
5418 | | EVEX VOP %zmmM, %zmmM, %zmmN |
5419 | | -> VEX vpxor %xmmM, %xmmM, %xmmN (M and N < 16) |
5420 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5421 | | EVEX VOP %ymmM, %ymmM, %ymmN |
5422 | | -> VEX vpxor %xmmM, %xmmM, %xmmN (M and N < 16) |
5423 | | -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2) |
5424 | | VOP, one of kxord and kxorq: |
5425 | | VEX VOP %kM, %kM, %kN |
5426 | | -> VEX kxorw %kM, %kM, %kN |
5427 | | VOP, one of kandnd and kandnq: |
5428 | | VEX VOP %kM, %kM, %kN |
5429 | | -> VEX kandnw %kM, %kM, %kN |
5430 | | */ |
5431 | 0 | if (i.tm.opcode_modifier.evex) |
5432 | 0 | { |
5433 | 0 | if (pp.encoding != encoding_evex) |
5434 | 0 | { |
5435 | 0 | i.tm.opcode_modifier.vex = VEX128; |
5436 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
5437 | 0 | i.tm.opcode_modifier.evex = 0; |
5438 | 0 | pp.encoding = encoding_vex; |
5439 | 0 | i.mask.reg = NULL; |
5440 | 0 | } |
5441 | 0 | else if (optimize > 1) |
5442 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
5443 | 0 | else |
5444 | 0 | return; |
5445 | 0 | } |
5446 | 0 | else if (i.tm.operand_types[0].bitfield.class == RegMask) |
5447 | 0 | { |
5448 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_NONE; |
5449 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
5450 | 0 | } |
5451 | 0 | else |
5452 | 0 | i.tm.opcode_modifier.vex = VEX128; |
5453 | | |
5454 | 0 | if (i.tm.opcode_modifier.vex) |
5455 | 0 | for (j = 0; j < 3; j++) |
5456 | 0 | { |
5457 | 0 | i.types[j].bitfield.xmmword = 1; |
5458 | 0 | i.types[j].bitfield.ymmword = 0; |
5459 | 0 | } |
5460 | 0 | } |
5461 | 0 | else if (pp.encoding != encoding_evex |
5462 | 0 | && pp.encoding != encoding_egpr |
5463 | 0 | && !i.types[0].bitfield.zmmword |
5464 | 0 | && !i.types[1].bitfield.zmmword |
5465 | 0 | && !i.mask.reg |
5466 | 0 | && !i.broadcast.type |
5467 | 0 | && !i.broadcast.bytes |
5468 | 0 | && i.tm.opcode_modifier.evex |
5469 | 0 | && ((i.tm.base_opcode & ~Opcode_SIMD_IntD) == 0x6f |
5470 | 0 | || (i.tm.base_opcode & ~4) == 0xdb |
5471 | 0 | || (i.tm.base_opcode & ~4) == 0xeb) |
5472 | 0 | && i.tm.extension_opcode == None) |
5473 | 0 | { |
5474 | | /* Optimize: -O1: |
5475 | | VOP, one of vmovdqa32, vmovdqa64, vmovdqu8, vmovdqu16, |
5476 | | vmovdqu32 and vmovdqu64: |
5477 | | EVEX VOP %xmmM, %xmmN |
5478 | | -> VEX vmovdqa|vmovdqu %xmmM, %xmmN (M and N < 16) |
5479 | | EVEX VOP %ymmM, %ymmN |
5480 | | -> VEX vmovdqa|vmovdqu %ymmM, %ymmN (M and N < 16) |
5481 | | EVEX VOP %xmmM, mem |
5482 | | -> VEX vmovdqa|vmovdqu %xmmM, mem (M < 16) |
5483 | | EVEX VOP %ymmM, mem |
5484 | | -> VEX vmovdqa|vmovdqu %ymmM, mem (M < 16) |
5485 | | EVEX VOP mem, %xmmN |
5486 | | -> VEX mvmovdqa|vmovdquem, %xmmN (N < 16) |
5487 | | EVEX VOP mem, %ymmN |
5488 | | -> VEX vmovdqa|vmovdqu mem, %ymmN (N < 16) |
5489 | | VOP, one of vpand, vpandn, vpor, vpxor: |
5490 | | EVEX VOP{d,q} %xmmL, %xmmM, %xmmN |
5491 | | -> VEX VOP %xmmL, %xmmM, %xmmN (L, M, and N < 16) |
5492 | | EVEX VOP{d,q} %ymmL, %ymmM, %ymmN |
5493 | | -> VEX VOP %ymmL, %ymmM, %ymmN (L, M, and N < 16) |
5494 | | EVEX VOP{d,q} mem, %xmmM, %xmmN |
5495 | | -> VEX VOP mem, %xmmM, %xmmN (M and N < 16) |
5496 | | EVEX VOP{d,q} mem, %ymmM, %ymmN |
5497 | | -> VEX VOP mem, %ymmM, %ymmN (M and N < 16) |
5498 | | */ |
5499 | 0 | for (j = 0; j < i.operands; j++) |
5500 | 0 | if (operand_type_check (i.types[j], disp) |
5501 | 0 | && i.op[j].disps->X_op == O_constant) |
5502 | 0 | { |
5503 | | /* Since the VEX prefix has 2 or 3 bytes, the EVEX prefix |
5504 | | has 4 bytes, EVEX Disp8 has 1 byte and VEX Disp32 has 4 |
5505 | | bytes, we choose EVEX Disp8 over VEX Disp32. */ |
5506 | 0 | int evex_disp8, vex_disp8; |
5507 | 0 | unsigned int memshift = i.memshift; |
5508 | 0 | offsetT n = i.op[j].disps->X_add_number; |
5509 | |
|
5510 | 0 | evex_disp8 = fits_in_disp8 (n); |
5511 | 0 | i.memshift = 0; |
5512 | 0 | vex_disp8 = fits_in_disp8 (n); |
5513 | 0 | if (evex_disp8 != vex_disp8) |
5514 | 0 | { |
5515 | 0 | i.memshift = memshift; |
5516 | 0 | return; |
5517 | 0 | } |
5518 | | |
5519 | 0 | i.types[j].bitfield.disp8 = vex_disp8; |
5520 | 0 | break; |
5521 | 0 | } |
5522 | 0 | if ((i.tm.base_opcode & ~Opcode_SIMD_IntD) == 0x6f |
5523 | 0 | && i.tm.opcode_modifier.opcodeprefix == PREFIX_0XF2) |
5524 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
5525 | 0 | i.tm.opcode_modifier.vex |
5526 | 0 | = i.types[0].bitfield.ymmword ? VEX256 : VEX128; |
5527 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
5528 | | /* VPAND, VPOR, and VPXOR are commutative. */ |
5529 | 0 | if (i.reg_operands == 3 && i.tm.base_opcode != 0xdf) |
5530 | 0 | i.tm.opcode_modifier.commutative = 1; |
5531 | 0 | i.tm.opcode_modifier.evex = 0; |
5532 | 0 | i.tm.opcode_modifier.masking = 0; |
5533 | 0 | i.tm.opcode_modifier.broadcast = 0; |
5534 | 0 | i.tm.opcode_modifier.disp8memshift = 0; |
5535 | 0 | i.memshift = 0; |
5536 | 0 | if (j < i.operands) |
5537 | 0 | i.types[j].bitfield.disp8 |
5538 | 0 | = fits_in_disp8 (i.op[j].disps->X_add_number); |
5539 | 0 | } |
5540 | 0 | else if (optimize_for_space |
5541 | 0 | && i.tm.base_opcode == 0x29 |
5542 | 0 | && i.tm.opcode_space == SPACE_0F38 |
5543 | 0 | && i.operands == i.reg_operands |
5544 | 0 | && i.op[0].regs == i.op[1].regs |
5545 | 0 | && (!i.tm.opcode_modifier.vex |
5546 | 0 | || !(i.op[0].regs->reg_flags & RegRex)) |
5547 | 0 | && !i.tm.opcode_modifier.evex) |
5548 | 0 | { |
5549 | | /* Optimize: -Os: |
5550 | | pcmpeqq %xmmN, %xmmN -> pcmpeqd %xmmN, %xmmN |
5551 | | vpcmpeqq %xmmN, %xmmN, %xmmM -> vpcmpeqd %xmmN, %xmmN, %xmmM (N < 8) |
5552 | | vpcmpeqq %ymmN, %ymmN, %ymmM -> vpcmpeqd %ymmN, %ymmN, %ymmM (N < 8) |
5553 | | */ |
5554 | 0 | i.tm.opcode_space = SPACE_0F; |
5555 | 0 | i.tm.base_opcode = 0x76; |
5556 | 0 | } |
5557 | 0 | else if (((i.tm.base_opcode >= 0x64 |
5558 | 0 | && i.tm.base_opcode <= 0x66 |
5559 | 0 | && i.tm.opcode_space == SPACE_0F) |
5560 | 0 | || (i.tm.base_opcode == 0x37 |
5561 | 0 | && i.tm.opcode_space == SPACE_0F38)) |
5562 | 0 | && i.operands == i.reg_operands |
5563 | 0 | && i.op[0].regs == i.op[1].regs |
5564 | 0 | && !i.tm.opcode_modifier.evex) |
5565 | 0 | { |
5566 | | /* Optimize: -O: |
5567 | | pcmpgt[bwd] %mmN, %mmN -> pxor %mmN, %mmN |
5568 | | pcmpgt[bwdq] %xmmN, %xmmN -> pxor %xmmN, %xmmN |
5569 | | vpcmpgt[bwdq] %xmmN, %xmmN, %xmmM -> vpxor %xmmN, %xmmN, %xmmM (N < 8) |
5570 | | vpcmpgt[bwdq] %xmmN, %xmmN, %xmmM -> vpxor %xmm0, %xmm0, %xmmM (N > 7) |
5571 | | vpcmpgt[bwdq] %ymmN, %ymmN, %ymmM -> vpxor %ymmN, %ymmN, %ymmM (N < 8) |
5572 | | vpcmpgt[bwdq] %ymmN, %ymmN, %ymmM -> vpxor %ymm0, %ymm0, %ymmM (N > 7) |
5573 | | */ |
5574 | 0 | i.tm.opcode_space = SPACE_0F; |
5575 | 0 | i.tm.base_opcode = 0xef; |
5576 | 0 | if (i.tm.opcode_modifier.vex && (i.op[0].regs->reg_flags & RegRex)) |
5577 | 0 | { |
5578 | 0 | if (i.operands == 2) |
5579 | 0 | { |
5580 | 0 | gas_assert (i.tm.opcode_modifier.sse2avx); |
5581 | | |
5582 | 0 | i.operands = 3; |
5583 | 0 | i.reg_operands = 3; |
5584 | 0 | i.tm.operands = 3; |
5585 | |
|
5586 | 0 | copy_operand (2, 0); |
5587 | |
|
5588 | 0 | i.tm.opcode_modifier.sse2avx = 0; |
5589 | 0 | } |
5590 | 0 | i.op[0].regs -= i.op[0].regs->reg_num + 8; |
5591 | 0 | i.op[1].regs = i.op[0].regs; |
5592 | 0 | } |
5593 | 0 | } |
5594 | 0 | else if (i.tm.extension_opcode == 6 |
5595 | 0 | && i.tm.base_opcode >= 0x71 |
5596 | 0 | && i.tm.base_opcode <= 0x73 |
5597 | 0 | && i.tm.opcode_space == SPACE_0F |
5598 | 0 | && i.op[0].imms->X_op == O_constant |
5599 | 0 | && i.op[0].imms->X_add_number == 1 |
5600 | 0 | && !i.mem_operands) |
5601 | 0 | { |
5602 | | /* Optimize: -O: |
5603 | | psllw $1, %mmxN -> paddw %mmxN, %mmxN |
5604 | | psllw $1, %xmmN -> paddw %xmmN, %xmmN |
5605 | | vpsllw $1, %xmmN, %xmmM -> vpaddw %xmmN, %xmmN, %xmmM |
5606 | | vpsllw $1, %ymmN, %ymmM -> vpaddw %ymmN, %ymmN, %ymmM |
5607 | | vpsllw $1, %zmmN, %zmmM -> vpaddw %zmmN, %zmmN, %zmmM |
5608 | | |
5609 | | pslld $1, %mmxN -> paddd %mmxN, %mmxN |
5610 | | pslld $1, %xmmN -> paddd %xmmN, %xmmN |
5611 | | vpslld $1, %xmmN, %xmmM -> vpaddd %xmmN, %xmmN, %xmmM |
5612 | | vpslld $1, %ymmN, %ymmM -> vpaddd %ymmN, %ymmN, %ymmM |
5613 | | vpslld $1, %zmmN, %zmmM -> vpaddd %zmmN, %zmmN, %zmmM |
5614 | | |
5615 | | psllq $1, %xmmN -> paddq %xmmN, %xmmN |
5616 | | vpsllq $1, %xmmN, %xmmM -> vpaddq %xmmN, %xmmN, %xmmM |
5617 | | vpsllq $1, %ymmN, %ymmM -> vpaddq %ymmN, %ymmN, %ymmM |
5618 | | vpsllq $1, %zmmN, %zmmM -> vpaddq %zmmN, %zmmN, %zmmM |
5619 | | */ |
5620 | 0 | if (i.tm.base_opcode != 0x73) |
5621 | 0 | i.tm.base_opcode |= 0xfc; /* {,v}padd{w,d} */ |
5622 | 0 | else |
5623 | 0 | { |
5624 | 0 | gas_assert (i.tm.operand_types[1].bitfield.class != RegMMX); |
5625 | 0 | i.tm.base_opcode = 0xd4; /* {,v}paddq */ |
5626 | 0 | } |
5627 | 0 | i.tm.extension_opcode = None; |
5628 | 0 | if (i.tm.opcode_modifier.vexvvvv) |
5629 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_SRC1; |
5630 | 0 | copy_operand (0, 1); |
5631 | 0 | i.reg_operands++; |
5632 | 0 | i.imm_operands = 0; |
5633 | 0 | } |
5634 | 0 | else if (optimize_for_space |
5635 | 0 | && i.tm.base_opcode == 0x59 |
5636 | 0 | && i.tm.opcode_space == SPACE_0F38 |
5637 | 0 | && i.operands == i.reg_operands |
5638 | 0 | && i.tm.opcode_modifier.vex |
5639 | 0 | && !(i.op[0].regs->reg_flags & RegRex) |
5640 | 0 | && i.op[0].regs->reg_type.bitfield.xmmword |
5641 | 0 | && pp.encoding != encoding_vex3) |
5642 | 0 | { |
5643 | | /* Optimize: -Os: |
5644 | | vpbroadcastq %xmmN, %xmmM -> vpunpcklqdq %xmmN, %xmmN, %xmmM (N < 8) |
5645 | | */ |
5646 | 0 | i.tm.opcode_space = SPACE_0F; |
5647 | 0 | i.tm.base_opcode = 0x6c; |
5648 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_SRC1; |
5649 | |
|
5650 | 0 | ++i.operands; |
5651 | 0 | ++i.reg_operands; |
5652 | 0 | ++i.tm.operands; |
5653 | |
|
5654 | 0 | copy_operand (2, 0); |
5655 | 0 | swap_2_operands (1, 2); |
5656 | 0 | } |
5657 | 0 | else if (i.tm.base_opcode == 0x16 |
5658 | 0 | && i.tm.opcode_space == SPACE_0F3A |
5659 | 0 | && i.op[0].imms->X_op == O_constant |
5660 | 0 | && i.op[0].imms->X_add_number == 0) |
5661 | 0 | { |
5662 | | /* Optimize: -O: |
5663 | | pextrd $0, %xmmN, ... -> movd %xmmN, ... |
5664 | | pextrq $0, %xmmN, ... -> movq %xmmN, ... |
5665 | | vpextrd $0, %xmmN, ... -> vmovd %xmmN, ... |
5666 | | vpextrq $0, %xmmN, ... -> vmovq %xmmN, ... |
5667 | | */ |
5668 | 0 | i.tm.opcode_space = SPACE_0F; |
5669 | 0 | if (!i.mem_operands |
5670 | 0 | || i.tm.opcode_modifier.evex |
5671 | 0 | || (i.tm.opcode_modifier.vexw != VEXW1 |
5672 | 0 | && i.tm.opcode_modifier.size != SIZE64)) |
5673 | 0 | i.tm.base_opcode = 0x7e; |
5674 | 0 | else |
5675 | 0 | { |
5676 | 0 | i.tm.base_opcode = 0xd6; |
5677 | 0 | i.tm.opcode_modifier.size = 0; |
5678 | 0 | i.tm.opcode_modifier.vexw |
5679 | 0 | = i.tm.opcode_modifier.sse2avx ? VEXW0 : VEXWIG; |
5680 | 0 | } |
5681 | |
|
5682 | 0 | copy_operand (0, 1); |
5683 | 0 | copy_operand (1, 2); |
5684 | |
|
5685 | 0 | i.operands = 2; |
5686 | 0 | i.imm_operands = 0; |
5687 | 0 | } |
5688 | 0 | else if (i.tm.base_opcode == 0x17 |
5689 | 0 | && i.tm.opcode_space == SPACE_0F3A |
5690 | 0 | && i.op[0].imms->X_op == O_constant |
5691 | 0 | && i.op[0].imms->X_add_number == 0) |
5692 | 0 | { |
5693 | | /* Optimize: -O: |
5694 | | extractps $0, %xmmN, %rM -> movd %xmmN, %rM |
5695 | | extractps $0, %xmmN, mem -> movss %xmmN, mem |
5696 | | vextractps $0, %xmmN, %rM -> vmovd %xmmN, %rM |
5697 | | vextractps $0, %xmmN, mem -> vmovss %xmmN, mem |
5698 | | */ |
5699 | 0 | i.tm.opcode_space = SPACE_0F; |
5700 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
5701 | |
|
5702 | 0 | if (!i.mem_operands) |
5703 | 0 | i.tm.base_opcode = 0x7e; |
5704 | 0 | else |
5705 | 0 | { |
5706 | 0 | i.tm.base_opcode = 0x11; |
5707 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
5708 | 0 | } |
5709 | |
|
5710 | 0 | copy_operand (0, 1); |
5711 | 0 | copy_operand (1, 2); |
5712 | |
|
5713 | 0 | i.operands = 2; |
5714 | 0 | i.imm_operands = 0; |
5715 | 0 | } |
5716 | 0 | else if ((i.tm.base_opcode | 0x22) == 0x3b |
5717 | 0 | && i.tm.opcode_space == SPACE_0F3A |
5718 | 0 | && i.op[0].imms->X_op == O_constant |
5719 | 0 | && i.op[0].imms->X_add_number == 0) |
5720 | 0 | { |
5721 | | /* Optimize: -O: |
5722 | | vextractf128 $0, %ymmN, %xmmM -> vmovaps %xmmN, %xmmM |
5723 | | vextractf128 $0, %ymmN, mem -> vmovups %xmmN, mem |
5724 | | vextractf32x4 $0, %[yz]mmN, %xmmM -> vmovaps %xmmN, %xmmM |
5725 | | vextractf32x4 $0, %[yz]mmN, mem -> vmovups %xmmN, mem |
5726 | | vextractf64x2 $0, %[yz]mmN, %xmmM -> vmovapd %xmmN, %xmmM |
5727 | | vextractf64x2 $0, %[yz]mmN, mem -> vmovupd %xmmN, mem |
5728 | | vextractf32x8 $0, %zmmN, %ymmM -> vmovaps %ymmN, %ymmM |
5729 | | vextractf32x8 $0, %zmmN, mem -> vmovups %ymmN, mem |
5730 | | vextractf64x4 $0, %zmmN, %ymmM -> vmovapd %ymmN, %ymmM |
5731 | | vextractf64x4 $0, %zmmN, mem -> vmovupd %ymmN, mem |
5732 | | vextracti128 $0, %ymmN, %xmmM -> vmovdqa %xmmN, %xmmM |
5733 | | vextracti128 $0, %ymmN, mem -> vmovdqu %xmmN, mem |
5734 | | vextracti32x4 $0, %[yz]mmN, %xmmM -> vmovdqa{,32} %xmmN, %xmmM |
5735 | | vextracti32x4 $0, %[yz]mmN, mem -> vmovdqu{,32} %xmmN, mem |
5736 | | vextracti64x2 $0, %[yz]mmN, %xmmM -> vmovdqa{,64} %xmmN, %xmmM |
5737 | | vextracti64x2 $0, %[yz]mmN, mem -> vmovdqu{,64} %xmmN, mem |
5738 | | vextracti32x8 $0, %zmmN, %ymmM -> vmovdqa{,32} %ymmN, %ymmM |
5739 | | vextracti32x8 $0, %zmmN, mem -> vmovdqu{,32} %ymmN, mem |
5740 | | vextracti64x4 $0, %zmmN, %ymmM -> vmovdqa{,64} %ymmN, %ymmM |
5741 | | vextracti64x4 $0, %zmmN, mem -> vmovdqu{,64} %ymmN, mem |
5742 | | */ |
5743 | 0 | i.tm.opcode_space = SPACE_0F; |
5744 | |
|
5745 | 0 | if (!i.mask.reg |
5746 | 0 | && (pp.encoding <= encoding_vex3 |
5747 | 0 | || (pp.encoding == encoding_evex512 |
5748 | 0 | && (!i.base_reg || !(i.base_reg->reg_flags & RegRex2)) |
5749 | 0 | && (!i.index_reg || !(i.index_reg->reg_flags & RegRex2))))) |
5750 | 0 | { |
5751 | 0 | i.tm.opcode_modifier.vex = i.tm.base_opcode & 2 ? VEX256 : VEX128; |
5752 | 0 | i.tm.opcode_modifier.evex = 0; |
5753 | 0 | } |
5754 | 0 | else |
5755 | 0 | i.tm.opcode_modifier.evex = i.tm.base_opcode & 2 ? EVEX256 : EVEX128; |
5756 | |
|
5757 | 0 | if (i.tm.base_opcode & 0x20) |
5758 | 0 | { |
5759 | 0 | i.tm.base_opcode = 0x7f; |
5760 | 0 | if (i.reg_operands != 2) |
5761 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
5762 | 0 | } |
5763 | 0 | else |
5764 | 0 | { |
5765 | 0 | if (i.reg_operands == 2) |
5766 | 0 | i.tm.base_opcode = 0x29; |
5767 | 0 | else |
5768 | 0 | i.tm.base_opcode = 0x11; |
5769 | 0 | if (i.tm.opcode_modifier.vexw != VEXW1) |
5770 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_NONE; |
5771 | 0 | } |
5772 | |
|
5773 | 0 | if (i.tm.opcode_modifier.vex) |
5774 | 0 | i.tm.opcode_modifier.vexw = VEXWIG; |
5775 | |
|
5776 | 0 | copy_operand (0, 1); |
5777 | 0 | copy_operand (1, 2); |
5778 | |
|
5779 | 0 | i.operands = 2; |
5780 | 0 | i.imm_operands = 0; |
5781 | 0 | } |
5782 | 0 | else if (i.tm.base_opcode == 0x21 |
5783 | 0 | && i.tm.opcode_space == SPACE_0F3A |
5784 | 0 | && i.op[0].imms->X_op == O_constant |
5785 | 0 | && (i.operands == i.reg_operands + 1 |
5786 | 0 | ? i.op[0].imms->X_add_number == 0 |
5787 | 0 | || (i.op[0].imms->X_add_number & 0xf) == 0xf |
5788 | 0 | : (i.op[0].imms->X_add_number & 0x3f) == 0x0e |
5789 | 0 | && (i.reg_operands == 1 || i.op[2].regs == i.op[3].regs))) |
5790 | 0 | { |
5791 | | /* Optimize: -O: |
5792 | | insertps $0b....1111, %xmmN, %xmmM -> xorps %xmmM, %xmmM |
5793 | | insertps $0b00000000, %xmmN, %xmmM -> movss %xmmN, %xmmM |
5794 | | insertps $0b..001110, mem, %xmmN -> movss mem, %xmmN |
5795 | | vinsertps $0b....1111, %xmmN, %xmmM, %xmmK -> vxorps %xmm?, %xmm?, %xmmK |
5796 | | vinsertps $0b00000000, %xmmN, %xmmM, %xmmK -> vmovss %xmmN, %xmmM, %xmmK |
5797 | | vinsertps $0b..001110, mem, %xmmN, %xmmN -> vmovss mem, %xmmN |
5798 | | */ |
5799 | 0 | i.tm.opcode_space = SPACE_0F; |
5800 | 0 | if ((i.op[0].imms->X_add_number & 0xf) == 0xf) |
5801 | 0 | { |
5802 | 0 | i.tm.base_opcode = 0x57; |
5803 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_NONE; |
5804 | |
|
5805 | 0 | --i.operands; |
5806 | |
|
5807 | 0 | copy_operand (i.operands - 1, i.operands); |
5808 | 0 | copy_operand (1, i.operands - 1); |
5809 | 0 | copy_operand (0, 1); |
5810 | | |
5811 | | /* Switch from EVEX to VEX encoding if possible. Sadly we can't |
5812 | | (always) tell use of the {evex} pseudo-prefix (which otherwise |
5813 | | we'd like to respect) from use of %xmm16-%xmm31. */ |
5814 | 0 | if (pp.encoding == encoding_evex) |
5815 | 0 | pp.encoding = encoding_default; |
5816 | 0 | if (i.tm.opcode_modifier.evex |
5817 | 0 | && pp.encoding <= encoding_vex3 |
5818 | 0 | && !(i.op[0].regs->reg_flags & RegVRex)) |
5819 | 0 | { |
5820 | 0 | i.tm.opcode_modifier.evex = 0; |
5821 | 0 | i.tm.opcode_modifier.vex = VEX128; |
5822 | 0 | } |
5823 | | |
5824 | | /* Switch from VEX3 to VEX2 encoding if possible. */ |
5825 | 0 | if (i.tm.opcode_modifier.vex |
5826 | 0 | && pp.encoding <= encoding_vex |
5827 | 0 | && (i.op[0].regs->reg_flags & RegRex)) |
5828 | 0 | { |
5829 | 0 | i.op[0].regs -= 8; |
5830 | 0 | i.op[1].regs = i.op[0].regs; |
5831 | 0 | } |
5832 | 0 | } |
5833 | 0 | else |
5834 | 0 | { |
5835 | 0 | i.tm.base_opcode = 0x10; |
5836 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
5837 | |
|
5838 | 0 | if (i.op[0].imms->X_add_number == 0) |
5839 | 0 | --i.operands; |
5840 | 0 | else |
5841 | 0 | { |
5842 | 0 | i.operands = 2; |
5843 | 0 | i.tm.opcode_modifier.vexvvvv = 0; |
5844 | 0 | } |
5845 | 0 | copy_operand (0, 1); |
5846 | 0 | copy_operand (1, 2); |
5847 | 0 | copy_operand (2, 3); |
5848 | 0 | } |
5849 | |
|
5850 | 0 | i.imm_operands = 0; |
5851 | 0 | } |
5852 | 0 | } |
5853 | | |
5854 | | /* Check whether the promoted (to address size) register is usable as index |
5855 | | register in ModR/M SIB addressing. */ |
5856 | | |
5857 | | static bool is_index (const reg_entry *r) |
5858 | 0 | { |
5859 | 0 | gas_assert (flag_code == CODE_64BIT); |
5860 | | |
5861 | 0 | if (r->reg_type.bitfield.byte) |
5862 | 0 | { |
5863 | 0 | if (!(r->reg_flags & (RegRex | RegRex2 | RegRex64))) |
5864 | 0 | { |
5865 | 0 | if (r->reg_num >= 4) |
5866 | 0 | return false; |
5867 | 0 | r += 8; |
5868 | 0 | } |
5869 | 0 | r += 32; |
5870 | 0 | } |
5871 | 0 | if (r->reg_type.bitfield.word) |
5872 | 0 | r += 32; |
5873 | | /* No need to further check .dword here. */ |
5874 | |
|
5875 | 0 | return r->reg_type.bitfield.baseindex; |
5876 | 0 | } |
5877 | | |
5878 | | /* Try to shorten {nf} encodings, by shortening operand size or switching to |
5879 | | functionally identical encodings. */ |
5880 | | |
5881 | | static void |
5882 | | optimize_nf_encoding (void) |
5883 | 0 | { |
5884 | 0 | if (i.tm.base_opcode == 0x80 |
5885 | 0 | && (i.tm.extension_opcode == 0 || i.tm.extension_opcode == 5) |
5886 | 0 | && i.suffix != BYTE_MNEM_SUFFIX |
5887 | 0 | && !i.types[1].bitfield.byte |
5888 | 0 | && !i.types[2].bitfield.byte |
5889 | 0 | && i.op[0].imms->X_op == O_constant |
5890 | 0 | && i.op[0].imms->X_add_number == 0x80) |
5891 | 0 | { |
5892 | | /* Optimize: -O: |
5893 | | {nf} addw $0x80, ... -> {nf} subw $-0x80, ... |
5894 | | {nf} addl $0x80, ... -> {nf} subl $-0x80, ... |
5895 | | {nf} addq $0x80, ... -> {nf} subq $-0x80, ... |
5896 | | |
5897 | | {nf} subw $0x80, ... -> {nf} addw $-0x80, ... |
5898 | | {nf} subl $0x80, ... -> {nf} addl $-0x80, ... |
5899 | | {nf} subq $0x80, ... -> {nf} addq $-0x80, ... |
5900 | | */ |
5901 | 0 | i.tm.base_opcode |= 3; |
5902 | 0 | i.tm.extension_opcode ^= 5; |
5903 | 0 | i.tm.opcode_modifier.w = 0; |
5904 | 0 | i.op[0].imms->X_add_number = -i.op[0].imms->X_add_number; |
5905 | |
|
5906 | 0 | i.tm.operand_types[0].bitfield.imm8 = 0; |
5907 | 0 | i.tm.operand_types[0].bitfield.imm8s = 1; |
5908 | 0 | i.tm.operand_types[0].bitfield.imm16 = 0; |
5909 | 0 | i.tm.operand_types[0].bitfield.imm32 = 0; |
5910 | 0 | i.tm.operand_types[0].bitfield.imm32s = 0; |
5911 | |
|
5912 | 0 | i.types[0] = i.tm.operand_types[0]; |
5913 | 0 | } |
5914 | 0 | else if ((i.tm.base_opcode | 3) == 0x83 |
5915 | 0 | && (i.tm.extension_opcode == 0 || i.tm.extension_opcode == 5) |
5916 | 0 | && i.op[0].imms->X_op == O_constant |
5917 | 0 | && (i.op[0].imms->X_add_number == 1 |
5918 | 0 | || i.op[0].imms->X_add_number == -1 |
5919 | | /* While for wider than byte operations immediates were suitably |
5920 | | adjusted earlier on, 0xff in the byte case needs covering |
5921 | | explicitly. */ |
5922 | 0 | || (i.op[0].imms->X_add_number == 0xff |
5923 | 0 | && (i.suffix == BYTE_MNEM_SUFFIX |
5924 | 0 | || i.types[i.operands - 1].bitfield.byte)))) |
5925 | 0 | { |
5926 | | /* Optimize: -O: |
5927 | | {nf} add $1, ... -> {nf} inc ... |
5928 | | {nf} add $-1, ... -> {nf} dec ... |
5929 | | {nf} add $0xf...f, ... -> {nf} dec ... |
5930 | | |
5931 | | {nf} sub $1, ... -> {nf} dec ... |
5932 | | {nf} sub $-1, ... -> {nf} inc ... |
5933 | | {nf} sub $0xf...f, ... -> {nf} inc ... |
5934 | | */ |
5935 | 0 | i.tm.base_opcode = 0xfe; |
5936 | 0 | i.tm.extension_opcode |
5937 | 0 | = (i.op[0].imms->X_add_number == 1) != (i.tm.extension_opcode == 0); |
5938 | 0 | i.tm.opcode_modifier.w = 1; |
5939 | |
|
5940 | 0 | copy_operand (0, 1); |
5941 | 0 | copy_operand (1, 2); |
5942 | |
|
5943 | 0 | i.imm_operands = 0; |
5944 | 0 | --i.operands; |
5945 | 0 | } |
5946 | 0 | else if (i.tm.base_opcode == 0xc0 |
5947 | 0 | && i.op[0].imms->X_op == O_constant |
5948 | 0 | && i.op[0].imms->X_add_number |
5949 | 0 | == (i.types[i.operands - 1].bitfield.byte |
5950 | 0 | || i.suffix == BYTE_MNEM_SUFFIX |
5951 | 0 | ? 7 : i.types[i.operands - 1].bitfield.word |
5952 | 0 | || i.suffix == WORD_MNEM_SUFFIX |
5953 | 0 | ? 15 : 63 >> (i.types[i.operands - 1].bitfield.dword |
5954 | 0 | || i.suffix == LONG_MNEM_SUFFIX))) |
5955 | 0 | { |
5956 | | /* Optimize: -O: |
5957 | | {nf} rol $osz-1, ... -> {nf} ror $1, ... |
5958 | | {nf} ror $osz-1, ... -> {nf} rol $1, ... |
5959 | | */ |
5960 | 0 | gas_assert (i.tm.extension_opcode <= 1); |
5961 | 0 | i.tm.extension_opcode ^= 1; |
5962 | 0 | i.tm.base_opcode = 0xd0; |
5963 | 0 | i.tm.operand_types[0].bitfield.imm1 = 1; |
5964 | 0 | i.imm_operands = 0; |
5965 | 0 | } |
5966 | 0 | else if ((i.tm.base_opcode | 2) == 0x6b |
5967 | 0 | && i.op[0].imms->X_op == O_constant |
5968 | 0 | && (i.op[0].imms->X_add_number > 0 |
5969 | 0 | ? !(i.op[0].imms->X_add_number & (i.op[0].imms->X_add_number - 1)) |
5970 | | /* optimize_imm() converts to sign-extended representation where |
5971 | | possible (and input can also come with these specific numbers). */ |
5972 | 0 | : (i.types[i.operands - 1].bitfield.word |
5973 | 0 | && i.op[0].imms->X_add_number == -0x8000) |
5974 | 0 | || (i.types[i.operands - 1].bitfield.dword |
5975 | 0 | && i.op[0].imms->X_add_number + 1 == -0x7fffffff)) |
5976 | | /* 16-bit 3-operand non-ZU forms need leaviong alone, to prevent |
5977 | | zero-extension of the result. Unless, of course, both non- |
5978 | | immediate operands match (which can be converted to the non-NDD |
5979 | | form). */ |
5980 | 0 | && (i.operands < 3 |
5981 | 0 | || !i.types[2].bitfield.word |
5982 | 0 | || i.tm.mnem_off == MN_imulzu |
5983 | 0 | || i.op[2].regs == i.op[1].regs) |
5984 | | /* When merely optimizing for size, exclude cases where we'd convert |
5985 | | from Imm8S to Imm8 encoding, thus not actually reducing size. */ |
5986 | 0 | && (!optimize_for_space |
5987 | 0 | || i.tm.base_opcode == 0x69 |
5988 | 0 | || !(i.op[0].imms->X_add_number & 0x7d))) |
5989 | 0 | { |
5990 | | /* Optimize: -O: |
5991 | | {nf} imul $1<<N, ... -> {nf} shl $N, ... |
5992 | | {nf} imulzu $1<<N, ... -> {nf} shl $N, ... |
5993 | | */ |
5994 | 0 | if (i.op[0].imms->X_add_number != 2) |
5995 | 0 | { |
5996 | 0 | i.tm.base_opcode = 0xc0; |
5997 | 0 | i.op[0].imms->X_add_number = ffs (i.op[0].imms->X_add_number) - 1; |
5998 | 0 | i.tm.operand_types[0].bitfield.imm8 = 1; |
5999 | 0 | i.tm.operand_types[0].bitfield.imm16 = 0; |
6000 | 0 | i.tm.operand_types[0].bitfield.imm32 = 0; |
6001 | 0 | i.tm.operand_types[0].bitfield.imm32s = 0; |
6002 | 0 | } |
6003 | 0 | else |
6004 | 0 | { |
6005 | 0 | i.tm.base_opcode = 0xd0; |
6006 | 0 | i.tm.operand_types[0].bitfield.imm1 = 1; |
6007 | 0 | } |
6008 | 0 | i.types[0] = i.tm.operand_types[0]; |
6009 | 0 | i.tm.extension_opcode = 4; |
6010 | 0 | i.tm.opcode_modifier.w = 1; |
6011 | 0 | i.tm.opcode_modifier.operandconstraint = 0; |
6012 | 0 | if (i.operands == 3) |
6013 | 0 | { |
6014 | 0 | if (i.op[2].regs == i.op[1].regs && i.tm.mnem_off != MN_imulzu) |
6015 | 0 | { |
6016 | | /* Convert to non-NDD form. This is required for 16-bit insns |
6017 | | (to prevent zero-extension) and benign for others. */ |
6018 | 0 | i.operands = 2; |
6019 | 0 | i.reg_operands = 1; |
6020 | 0 | } |
6021 | 0 | else |
6022 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_DST; |
6023 | 0 | } |
6024 | 0 | else if (i.tm.mnem_off == MN_imulzu) |
6025 | 0 | { |
6026 | | /* Convert to NDD form, to effect zero-extension of the result. */ |
6027 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_DST; |
6028 | 0 | i.operands = 3; |
6029 | 0 | i.reg_operands = 2; |
6030 | 0 | copy_operand (2, 1); |
6031 | 0 | } |
6032 | 0 | } |
6033 | | |
6034 | 0 | if (optimize_for_space |
6035 | 0 | && pp.encoding != encoding_evex |
6036 | 0 | && (i.tm.base_opcode == 0x00 |
6037 | 0 | || (i.tm.base_opcode == 0xd0 && i.tm.extension_opcode == 4)) |
6038 | 0 | && !i.mem_operands |
6039 | 0 | && !i.types[1].bitfield.byte |
6040 | | /* 16-bit operand size has extra restrictions: If REX2 was needed, |
6041 | | no size reduction would be possible. Plus 3-operand forms zero- |
6042 | | extend the result, which can't be expressed with LEA. */ |
6043 | 0 | && (!i.types[1].bitfield.word |
6044 | 0 | || (i.operands == 2 && pp.encoding != encoding_egpr)) |
6045 | 0 | && is_plausible_suffix (1) |
6046 | | /* %rsp can't be the index. */ |
6047 | 0 | && (is_index (i.op[1].regs) |
6048 | 0 | || (i.imm_operands == 0 && is_index (i.op[0].regs))) |
6049 | | /* While %rbp, %r13, %r21, and %r29 can be made the index in order to |
6050 | | avoid the otherwise necessary Disp8, if the other operand is also |
6051 | | from that set and REX2 would be required to encode the insn, the |
6052 | | resulting encoding would be no smaller than the EVEX one. */ |
6053 | 0 | && (i.op[1].regs->reg_num != 5 |
6054 | 0 | || pp.encoding != encoding_egpr |
6055 | 0 | || i.imm_operands > 0 |
6056 | 0 | || i.op[0].regs->reg_num != 5)) |
6057 | 0 | { |
6058 | | /* Optimize: -Os: |
6059 | | {nf} addw %N, %M -> leaw (%rM,%rN), %M |
6060 | | {nf} addl %eN, %eM -> leal (%rM,%rN), %eM |
6061 | | {nf} addq %rN, %rM -> leaq (%rM,%rN), %rM |
6062 | | |
6063 | | {nf} shlw $1, %N -> leaw (%rN,%rN), %N |
6064 | | {nf} shll $1, %eN -> leal (%rN,%rN), %eN |
6065 | | {nf} shlq $1, %rN -> leaq (%rN,%rN), %rN |
6066 | | |
6067 | | {nf} addl %eK, %eN, %eM -> leal (%rN,%rK), %eM |
6068 | | {nf} addq %rK, %rN, %rM -> leaq (%rN,%rK), %rM |
6069 | | |
6070 | | {nf} shll $1, %eN, %eM -> leal (%rN,%rN), %eM |
6071 | | {nf} shlq $1, %rN, %rM -> leaq (%rN,%rN), %rM |
6072 | | */ |
6073 | 0 | i.tm.opcode_space = SPACE_BASE; |
6074 | 0 | i.tm.base_opcode = 0x8d; |
6075 | 0 | i.tm.extension_opcode = None; |
6076 | 0 | i.tm.opcode_modifier.evex = 0; |
6077 | 0 | i.tm.opcode_modifier.vexvvvv = 0; |
6078 | 0 | if (i.imm_operands != 0) |
6079 | 0 | i.index_reg = i.base_reg = i.op[1].regs; |
6080 | 0 | else if (!is_index (i.op[0].regs) |
6081 | 0 | || (i.op[1].regs->reg_num == 5 |
6082 | 0 | && i.op[0].regs->reg_num != 5)) |
6083 | 0 | { |
6084 | 0 | i.base_reg = i.op[0].regs; |
6085 | 0 | i.index_reg = i.op[1].regs; |
6086 | 0 | } |
6087 | 0 | else |
6088 | 0 | { |
6089 | 0 | i.base_reg = i.op[1].regs; |
6090 | 0 | i.index_reg = i.op[0].regs; |
6091 | 0 | } |
6092 | 0 | if (i.types[1].bitfield.word) |
6093 | 0 | { |
6094 | | /* NB: No similar adjustment is needed when operand size is 32-bit. */ |
6095 | 0 | i.base_reg += 64; |
6096 | 0 | i.index_reg += 64; |
6097 | 0 | } |
6098 | 0 | i.op[1].regs = i.op[i.operands - 1].regs; |
6099 | |
|
6100 | 0 | operand_type_set (&i.types[0], 0); |
6101 | 0 | i.types[0].bitfield.baseindex = 1; |
6102 | 0 | i.tm.operand_types[0] = i.types[0]; |
6103 | 0 | i.op[0].disps = NULL; |
6104 | 0 | i.flags[0] = Operand_Mem; |
6105 | |
|
6106 | 0 | i.operands = 2; |
6107 | 0 | i.mem_operands = i.reg_operands = 1; |
6108 | 0 | i.imm_operands = 0; |
6109 | 0 | pp.has_nf = false; |
6110 | 0 | } |
6111 | 0 | else if (optimize_for_space |
6112 | 0 | && pp.encoding != encoding_evex |
6113 | 0 | && (i.tm.base_opcode == 0x80 || i.tm.base_opcode == 0x83) |
6114 | 0 | && (i.tm.extension_opcode == 0 |
6115 | 0 | || (i.tm.extension_opcode == 5 |
6116 | 0 | && i.op[0].imms->X_op == O_constant |
6117 | | /* Subtraction of -0x80 will end up smaller only if neither |
6118 | | operand size nor REX/REX2 prefixes are needed. */ |
6119 | 0 | && (i.op[0].imms->X_add_number != -0x80 |
6120 | 0 | || (i.types[1].bitfield.dword |
6121 | 0 | && !(i.op[1].regs->reg_flags & RegRex) |
6122 | 0 | && !(i.op[i.operands - 1].regs->reg_flags & RegRex) |
6123 | 0 | && pp.encoding != encoding_egpr)))) |
6124 | 0 | && !i.mem_operands |
6125 | 0 | && !i.types[1].bitfield.byte |
6126 | | /* 16-bit operand size has extra restrictions: If REX2 was needed, |
6127 | | no size reduction would be possible. Plus 3-operand forms zero- |
6128 | | extend the result, which can't be expressed with LEA. */ |
6129 | 0 | && (!i.types[1].bitfield.word |
6130 | 0 | || (i.operands == 2 && pp.encoding != encoding_egpr)) |
6131 | 0 | && is_plausible_suffix (1)) |
6132 | 0 | { |
6133 | | /* Optimize: -Os: |
6134 | | {nf} addw $N, %M -> leaw N(%rM), %M |
6135 | | {nf} addl $N, %eM -> leal N(%rM), %eM |
6136 | | {nf} addq $N, %rM -> leaq N(%rM), %rM |
6137 | | |
6138 | | {nf} subw $N, %M -> leaw -N(%rM), %M |
6139 | | {nf} subl $N, %eM -> leal -N(%rM), %eM |
6140 | | {nf} subq $N, %rM -> leaq -N(%rM), %rM |
6141 | | |
6142 | | {nf} addl $N, %eK, %eM -> leal N(%rK), %eM |
6143 | | {nf} addq $N, %rK, %rM -> leaq N(%rK), %rM |
6144 | | |
6145 | | {nf} subl $N, %eK, %eM -> leal -N(%rK), %eM |
6146 | | {nf} subq $N, %rK, %rM -> leaq -N(%rK), %rM |
6147 | | */ |
6148 | 0 | i.tm.opcode_space = SPACE_BASE; |
6149 | 0 | i.tm.base_opcode = 0x8d; |
6150 | 0 | if (i.tm.extension_opcode == 5) |
6151 | 0 | i.op[0].imms->X_add_number = -i.op[0].imms->X_add_number; |
6152 | 0 | i.tm.extension_opcode = None; |
6153 | 0 | i.tm.opcode_modifier.evex = 0; |
6154 | 0 | i.tm.opcode_modifier.vexvvvv = 0; |
6155 | 0 | i.base_reg = i.op[1].regs; |
6156 | 0 | if (i.types[1].bitfield.word) |
6157 | 0 | { |
6158 | | /* NB: No similar adjustment is needed when operand size is 32-bit. */ |
6159 | 0 | i.base_reg += 64; |
6160 | 0 | } |
6161 | 0 | i.op[1].regs = i.op[i.operands - 1].regs; |
6162 | |
|
6163 | 0 | operand_type_set (&i.types[0], 0); |
6164 | 0 | i.types[0].bitfield.baseindex = 1; |
6165 | 0 | i.types[0].bitfield.disp32 = 1; |
6166 | 0 | i.op[0].disps = i.op[0].imms; |
6167 | 0 | i.flags[0] = Operand_Mem; |
6168 | 0 | optimize_disp (&i.tm); |
6169 | 0 | i.tm.operand_types[0] = i.types[0]; |
6170 | |
|
6171 | 0 | i.operands = 2; |
6172 | 0 | i.disp_operands = i.mem_operands = i.reg_operands = 1; |
6173 | 0 | i.imm_operands = 0; |
6174 | 0 | pp.has_nf = false; |
6175 | 0 | } |
6176 | 0 | else if (i.tm.base_opcode == 0x6b |
6177 | 0 | && !i.mem_operands |
6178 | 0 | && pp.encoding != encoding_evex |
6179 | 0 | && i.tm.mnem_off != MN_imulzu |
6180 | 0 | && is_plausible_suffix (1) |
6181 | | /* %rsp can't be the index. */ |
6182 | 0 | && is_index (i.op[1].regs) |
6183 | | /* There's no reduction in size for 16-bit forms requiring Disp8 and |
6184 | | REX2. */ |
6185 | 0 | && (!optimize_for_space |
6186 | 0 | || !i.types[1].bitfield.word |
6187 | 0 | || i.op[1].regs->reg_num != 5 |
6188 | 0 | || pp.encoding != encoding_egpr) |
6189 | 0 | && i.op[0].imms->X_op == O_constant |
6190 | 0 | && (i.op[0].imms->X_add_number == 3 |
6191 | 0 | || i.op[0].imms->X_add_number == 5 |
6192 | 0 | || i.op[0].imms->X_add_number == 9)) |
6193 | 0 | { |
6194 | | /* Optimize: -O: |
6195 | | For n one of 3, 5, or 9 |
6196 | | {nf} imulw $n, %N, %M -> leaw (%rN,%rN,n-1), %M |
6197 | | {nf} imull $n, %eN, %eM -> leal (%rN,%rN,n-1), %eM |
6198 | | {nf} imulq $n, %rN, %rM -> leaq (%rN,%rN,n-1), %rM |
6199 | | |
6200 | | {nf} imulw $n, %N -> leaw (%rN,%rN,s), %N |
6201 | | {nf} imull $n, %eN -> leal (%rN,%rN,s), %eN |
6202 | | {nf} imulq $n, %rN -> leaq (%rN,%rN,s), %rN |
6203 | | */ |
6204 | 0 | i.tm.opcode_space = SPACE_BASE; |
6205 | 0 | i.tm.base_opcode = 0x8d; |
6206 | 0 | i.tm.extension_opcode = None; |
6207 | 0 | i.tm.opcode_modifier.evex = 0; |
6208 | 0 | i.base_reg = i.op[1].regs; |
6209 | | /* NB: No similar adjustment is needed when operand size is 32 bits. */ |
6210 | 0 | if (i.types[1].bitfield.word) |
6211 | 0 | i.base_reg += 64; |
6212 | 0 | i.index_reg = i.base_reg; |
6213 | 0 | i.log2_scale_factor = i.op[0].imms->X_add_number == 9 |
6214 | 0 | ? 3 : i.op[0].imms->X_add_number >> 1; |
6215 | |
|
6216 | 0 | operand_type_set (&i.types[0], 0); |
6217 | 0 | i.types[0].bitfield.baseindex = 1; |
6218 | 0 | i.tm.operand_types[0] = i.types[0]; |
6219 | 0 | i.op[0].disps = NULL; |
6220 | 0 | i.flags[0] = Operand_Mem; |
6221 | |
|
6222 | 0 | copy_operand (1, i.operands - 1); |
6223 | |
|
6224 | 0 | i.operands = 2; |
6225 | 0 | i.mem_operands = i.reg_operands = 1; |
6226 | 0 | i.imm_operands = 0; |
6227 | 0 | pp.has_nf = false; |
6228 | 0 | } |
6229 | 0 | else if (cpu_arch_isa_flags.bitfield.cpubmi2 |
6230 | 0 | && pp.encoding == encoding_default |
6231 | 0 | && (i.operands > 2 || !i.mem_operands) |
6232 | 0 | && (i.types[i.operands - 1].bitfield.dword |
6233 | 0 | || i.types[i.operands - 1].bitfield.qword)) |
6234 | 0 | { |
6235 | 0 | if (i.tm.base_opcode == 0xd2) |
6236 | 0 | { |
6237 | | /* Optimize: -O: |
6238 | | <OP> one of sal, sar, shl, shr: |
6239 | | {nf} <OP> %cl, %rN -> <OP>x %{e,r}cx, %rN, %rN (N < 16) |
6240 | | {nf} <OP> %cl, ..., %rN -> <OP>x %{e,r}cx, ..., %rN (no eGPR used) |
6241 | | */ |
6242 | 0 | gas_assert (i.tm.extension_opcode & 4); |
6243 | 0 | i.tm.operand_types[0] = i.tm.operand_types[i.operands - 1]; |
6244 | | /* NB: i.op[0].regs specifying %cl is good enough. */ |
6245 | 0 | i.types[0] = i.types[i.operands - 1]; |
6246 | 0 | if (i.operands == 2) |
6247 | 0 | { |
6248 | 0 | i.tm.operand_types[0].bitfield.baseindex = 0; |
6249 | 0 | i.tm.operand_types[2] = i.tm.operand_types[0]; |
6250 | 0 | i.op[2].regs = i.op[1].regs; |
6251 | 0 | i.types[2] = i.types[1]; |
6252 | 0 | i.reg_operands = i.operands = 3; |
6253 | 0 | } |
6254 | 0 | pp.has_nf = false; |
6255 | 0 | i.tm.opcode_modifier.w = 0; |
6256 | 0 | i.tm.opcode_modifier.evex = 0; |
6257 | 0 | i.tm.opcode_modifier.vex = VEX128; |
6258 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_SRC2; |
6259 | 0 | i.tm.opcode_space = SPACE_0F38; |
6260 | 0 | i.tm.base_opcode = 0xf7; |
6261 | 0 | i.tm.opcode_modifier.opcodeprefix |
6262 | 0 | = !(i.tm.extension_opcode & 1) |
6263 | 0 | ? PREFIX_0X66 /* shlx */ |
6264 | 0 | : i.tm.extension_opcode & 2 |
6265 | 0 | ? PREFIX_0XF3 /* sarx */ |
6266 | 0 | : PREFIX_0XF2 /* shrx */; |
6267 | 0 | i.tm.extension_opcode = None; |
6268 | 0 | } |
6269 | 0 | else if (i.tm.base_opcode == 0xc0 |
6270 | 0 | && i.tm.extension_opcode <= 1 |
6271 | 0 | && i.op[0].imms->X_op == O_constant) |
6272 | 0 | { |
6273 | | /* Optimize: -O: |
6274 | | {nf} rol $I, %rN -> rorx $osz-I, %rN, %rN (I != osz-1, N < 16) |
6275 | | {nf} rol $I, ..., %rN -> rorx $osz-I, ..., %rN (I != osz-1, no eGPR used) |
6276 | | {nf} ror $I, %rN -> rorx $I, %rN, %rN (I != 1, N < 16) |
6277 | | {nf} ror $I, ..., %rN -> rorx $I,..., %rN (I != 1, no eGPR used) |
6278 | | NB: rol -> ror transformation for I == osz-1 was already handled above. |
6279 | | NB2: ror with an immediate of 1 uses a different base opcode. |
6280 | | */ |
6281 | 0 | if (i.operands == 2) |
6282 | 0 | { |
6283 | 0 | copy_operand (2, 1); |
6284 | 0 | i.tm.operand_types[2].bitfield.baseindex = 0; |
6285 | 0 | i.reg_operands = 2; |
6286 | 0 | i.operands = 3; |
6287 | 0 | } |
6288 | 0 | pp.has_nf = false; |
6289 | 0 | i.tm.opcode_modifier.w = 0; |
6290 | 0 | i.tm.opcode_modifier.evex = 0; |
6291 | 0 | i.tm.opcode_modifier.vex = VEX128; |
6292 | 0 | i.tm.opcode_modifier.vexvvvv = 0; |
6293 | 0 | i.tm.opcode_space = SPACE_0F3A; |
6294 | 0 | i.tm.base_opcode = 0xf0; |
6295 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF2; |
6296 | 0 | if (!i.tm.extension_opcode) |
6297 | 0 | i.op[0].imms->X_add_number = |
6298 | 0 | (i.types[i.operands - 1].bitfield.byte |
6299 | 0 | ? 8 : i.types[i.operands - 1].bitfield.word |
6300 | 0 | ? 16 : 64 >> i.types[i.operands - 1].bitfield.dword) |
6301 | 0 | - i.op[0].imms->X_add_number; |
6302 | 0 | i.tm.extension_opcode = None; |
6303 | 0 | } |
6304 | 0 | else if (i.tm.base_opcode == 0xf6 |
6305 | 0 | && i.tm.extension_opcode == 4 |
6306 | 0 | && !i.mem_operands |
6307 | 0 | && i.op[0].regs->reg_num == 2 |
6308 | 0 | && !(i.op[0].regs->reg_flags & RegRex) ) |
6309 | 0 | { |
6310 | | /* Optimize: -O: |
6311 | | {nf} mul %edx -> mulx %eax, %eax, %edx |
6312 | | {nf} mul %rdx -> mulx %rax, %rax, %rdx |
6313 | | */ |
6314 | 0 | i.tm.operand_types[1] = i.tm.operand_types[0]; |
6315 | 0 | i.tm.operand_types[1].bitfield.baseindex = 0; |
6316 | 0 | i.tm.operand_types[2] = i.tm.operand_types[1]; |
6317 | 0 | i.op[2].regs = i.op[0].regs; |
6318 | | /* NB: %eax is good enough also for 64-bit operand size. */ |
6319 | 0 | i.op[1].regs = i.op[0].regs = reg_eax; |
6320 | 0 | i.types[2] = i.types[1] = i.types[0]; |
6321 | 0 | i.reg_operands = i.operands = 3; |
6322 | |
|
6323 | 0 | pp.has_nf = false; |
6324 | 0 | i.tm.opcode_modifier.w = 0; |
6325 | 0 | i.tm.opcode_modifier.evex = 0; |
6326 | 0 | i.tm.opcode_modifier.vex = VEX128; |
6327 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_SRC1; |
6328 | 0 | i.tm.opcode_space = SPACE_0F38; |
6329 | 0 | i.tm.base_opcode = 0xf6; |
6330 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF2; |
6331 | 0 | i.tm.extension_opcode = None; |
6332 | 0 | } |
6333 | 0 | } |
6334 | 0 | } |
6335 | | |
6336 | | static void |
6337 | | s_noopt (int dummy ATTRIBUTE_UNUSED) |
6338 | 0 | { |
6339 | 0 | if (!is_it_end_of_statement ()) |
6340 | 0 | as_warn (_("`.noopt' arguments ignored")); |
6341 | |
|
6342 | 0 | optimize = 0; |
6343 | 0 | optimize_for_space = 0; |
6344 | |
|
6345 | 0 | ignore_rest_of_line (); |
6346 | 0 | } |
6347 | | |
6348 | | /* Return non-zero for load instruction. */ |
6349 | | |
6350 | | static int |
6351 | | load_insn_p (void) |
6352 | 0 | { |
6353 | 0 | unsigned int dest; |
6354 | 0 | int any_vex_p = is_any_vex_encoding (&i.tm); |
6355 | 0 | unsigned int base_opcode = i.tm.base_opcode | 1; |
6356 | |
|
6357 | 0 | if (!any_vex_p) |
6358 | 0 | { |
6359 | | /* Anysize insns: lea, invlpg, clflush, prefetch*, bndmk, bndcl, bndcu, |
6360 | | bndcn, bndstx, bndldx, clflushopt, clwb, cldemote. */ |
6361 | 0 | if (i.tm.opcode_modifier.operandconstraint == ANY_SIZE) |
6362 | 0 | return 0; |
6363 | | |
6364 | | /* pop. */ |
6365 | 0 | if (i.tm.mnem_off == MN_pop) |
6366 | 0 | return 1; |
6367 | 0 | } |
6368 | | |
6369 | 0 | if (i.tm.opcode_space == SPACE_BASE) |
6370 | 0 | { |
6371 | | /* popf, popa. */ |
6372 | 0 | if (i.tm.base_opcode == 0x9d |
6373 | 0 | || i.tm.base_opcode == 0x61) |
6374 | 0 | return 1; |
6375 | | |
6376 | | /* movs, cmps, lods, scas. */ |
6377 | 0 | if ((i.tm.base_opcode | 0xb) == 0xaf) |
6378 | 0 | return 1; |
6379 | | |
6380 | | /* outs, xlatb. */ |
6381 | 0 | if (base_opcode == 0x6f |
6382 | 0 | || i.tm.base_opcode == 0xd7) |
6383 | 0 | return 1; |
6384 | | /* NB: For AMD-specific insns with implicit memory operands, |
6385 | | they're intentionally not covered. */ |
6386 | 0 | } |
6387 | | |
6388 | | /* No memory operand. */ |
6389 | 0 | if (!i.mem_operands) |
6390 | 0 | return 0; |
6391 | | |
6392 | 0 | if (any_vex_p) |
6393 | 0 | { |
6394 | 0 | if (i.tm.mnem_off == MN_vldmxcsr) |
6395 | 0 | return 1; |
6396 | 0 | } |
6397 | 0 | else if (i.tm.opcode_space == SPACE_BASE) |
6398 | 0 | { |
6399 | | /* test, not, neg, mul, imul, div, idiv. */ |
6400 | 0 | if (base_opcode == 0xf7 && i.tm.extension_opcode != 1) |
6401 | 0 | return 1; |
6402 | | |
6403 | | /* inc, dec. */ |
6404 | 0 | if (base_opcode == 0xff && i.tm.extension_opcode <= 1) |
6405 | 0 | return 1; |
6406 | | |
6407 | | /* add, or, adc, sbb, and, sub, xor, cmp. */ |
6408 | 0 | if (i.tm.base_opcode >= 0x80 && i.tm.base_opcode <= 0x83) |
6409 | 0 | return 1; |
6410 | | |
6411 | | /* rol, ror, rcl, rcr, shl/sal, shr, sar. */ |
6412 | 0 | if ((base_opcode == 0xc1 || (base_opcode | 2) == 0xd3) |
6413 | 0 | && i.tm.extension_opcode != 6) |
6414 | 0 | return 1; |
6415 | | |
6416 | | /* Check for x87 instructions. */ |
6417 | 0 | if ((base_opcode | 6) == 0xdf) |
6418 | 0 | { |
6419 | | /* Skip fst, fstp, fstenv, fstcw. */ |
6420 | 0 | if (i.tm.base_opcode == 0xd9 |
6421 | 0 | && (i.tm.extension_opcode == 2 |
6422 | 0 | || i.tm.extension_opcode == 3 |
6423 | 0 | || i.tm.extension_opcode == 6 |
6424 | 0 | || i.tm.extension_opcode == 7)) |
6425 | 0 | return 0; |
6426 | | |
6427 | | /* Skip fisttp, fist, fistp, fstp. */ |
6428 | 0 | if (i.tm.base_opcode == 0xdb |
6429 | 0 | && (i.tm.extension_opcode == 1 |
6430 | 0 | || i.tm.extension_opcode == 2 |
6431 | 0 | || i.tm.extension_opcode == 3 |
6432 | 0 | || i.tm.extension_opcode == 7)) |
6433 | 0 | return 0; |
6434 | | |
6435 | | /* Skip fisttp, fst, fstp, fsave, fstsw. */ |
6436 | 0 | if (i.tm.base_opcode == 0xdd |
6437 | 0 | && (i.tm.extension_opcode == 1 |
6438 | 0 | || i.tm.extension_opcode == 2 |
6439 | 0 | || i.tm.extension_opcode == 3 |
6440 | 0 | || i.tm.extension_opcode == 6 |
6441 | 0 | || i.tm.extension_opcode == 7)) |
6442 | 0 | return 0; |
6443 | | |
6444 | | /* Skip fisttp, fist, fistp, fbstp, fistp. */ |
6445 | 0 | if (i.tm.base_opcode == 0xdf |
6446 | 0 | && (i.tm.extension_opcode == 1 |
6447 | 0 | || i.tm.extension_opcode == 2 |
6448 | 0 | || i.tm.extension_opcode == 3 |
6449 | 0 | || i.tm.extension_opcode == 6 |
6450 | 0 | || i.tm.extension_opcode == 7)) |
6451 | 0 | return 0; |
6452 | | |
6453 | 0 | return 1; |
6454 | 0 | } |
6455 | 0 | } |
6456 | 0 | else if (i.tm.opcode_space == SPACE_0F) |
6457 | 0 | { |
6458 | | /* bt, bts, btr, btc. */ |
6459 | 0 | if (i.tm.base_opcode == 0xba |
6460 | 0 | && (i.tm.extension_opcode | 3) == 7) |
6461 | 0 | return 1; |
6462 | | |
6463 | | /* cmpxchg8b, cmpxchg16b, xrstors, vmptrld. */ |
6464 | 0 | if (i.tm.base_opcode == 0xc7 |
6465 | 0 | && i.tm.opcode_modifier.opcodeprefix == PREFIX_NONE |
6466 | 0 | && (i.tm.extension_opcode == 1 || i.tm.extension_opcode == 3 |
6467 | 0 | || i.tm.extension_opcode == 6)) |
6468 | 0 | return 1; |
6469 | | |
6470 | | /* fxrstor, ldmxcsr, xrstor. */ |
6471 | 0 | if (i.tm.base_opcode == 0xae |
6472 | 0 | && (i.tm.extension_opcode == 1 |
6473 | 0 | || i.tm.extension_opcode == 2 |
6474 | 0 | || i.tm.extension_opcode == 5)) |
6475 | 0 | return 1; |
6476 | | |
6477 | | /* lgdt, lidt, lmsw. */ |
6478 | 0 | if (i.tm.base_opcode == 0x01 |
6479 | 0 | && (i.tm.extension_opcode == 2 |
6480 | 0 | || i.tm.extension_opcode == 3 |
6481 | 0 | || i.tm.extension_opcode == 6)) |
6482 | 0 | return 1; |
6483 | 0 | } |
6484 | | |
6485 | 0 | dest = i.operands - 1; |
6486 | | |
6487 | | /* Check fake imm8 operand and 3 source operands. */ |
6488 | 0 | if ((i.tm.opcode_modifier.immext |
6489 | 0 | || i.reg_operands + i.mem_operands == 4) |
6490 | 0 | && i.types[dest].bitfield.imm8) |
6491 | 0 | dest--; |
6492 | | |
6493 | | /* add, or, adc, sbb, and, sub, xor, cmp, test, xchg. */ |
6494 | 0 | if (i.tm.opcode_space == SPACE_BASE |
6495 | 0 | && ((base_opcode | 0x38) == 0x39 |
6496 | 0 | || (base_opcode | 2) == 0x87)) |
6497 | 0 | return 1; |
6498 | | |
6499 | 0 | if (i.tm.mnem_off == MN_xadd) |
6500 | 0 | return 1; |
6501 | | |
6502 | | /* Check for load instruction. */ |
6503 | 0 | return (i.types[dest].bitfield.class != ClassNone |
6504 | 0 | || i.types[dest].bitfield.instance == Accum); |
6505 | 0 | } |
6506 | | |
6507 | | /* Output lfence, 0xfaee8, after instruction. */ |
6508 | | |
6509 | | static void |
6510 | | insert_lfence_after (void) |
6511 | 2.92k | { |
6512 | 2.92k | if (lfence_after_load && load_insn_p ()) |
6513 | 0 | { |
6514 | | /* There are also two REP string instructions that require |
6515 | | special treatment. Specifically, the compare string (CMPS) |
6516 | | and scan string (SCAS) instructions set EFLAGS in a manner |
6517 | | that depends on the data being compared/scanned. When used |
6518 | | with a REP prefix, the number of iterations may therefore |
6519 | | vary depending on this data. If the data is a program secret |
6520 | | chosen by the adversary using an LVI method, |
6521 | | then this data-dependent behavior may leak some aspect |
6522 | | of the secret. */ |
6523 | 0 | if (((i.tm.base_opcode | 0x9) == 0xaf) |
6524 | 0 | && i.prefix[REP_PREFIX]) |
6525 | 0 | { |
6526 | 0 | as_warn (_("`%s` changes flags which would affect control flow behavior"), |
6527 | 0 | insn_name (&i.tm)); |
6528 | 0 | } |
6529 | 0 | char *p = frag_more (3); |
6530 | 0 | *p++ = 0xf; |
6531 | 0 | *p++ = 0xae; |
6532 | 0 | *p = 0xe8; |
6533 | 0 | } |
6534 | 2.92k | } |
6535 | | |
6536 | | /* Output lfence, 0xfaee8, before instruction. */ |
6537 | | |
6538 | | static void |
6539 | | insert_lfence_before (const struct last_insn *last_insn) |
6540 | 2.92k | { |
6541 | 2.92k | char *p; |
6542 | | |
6543 | 2.92k | if (i.tm.opcode_space != SPACE_BASE) |
6544 | 273 | return; |
6545 | | |
6546 | 2.64k | if (i.tm.base_opcode == 0xff |
6547 | 2.64k | && (i.tm.extension_opcode == 2 || i.tm.extension_opcode == 4)) |
6548 | 0 | { |
6549 | | /* Insert lfence before indirect branch if needed. */ |
6550 | |
|
6551 | 0 | if (lfence_before_indirect_branch == lfence_branch_none) |
6552 | 0 | return; |
6553 | | |
6554 | 0 | if (i.operands != 1) |
6555 | 0 | abort (); |
6556 | | |
6557 | 0 | if (i.reg_operands == 1) |
6558 | 0 | { |
6559 | | /* Indirect branch via register. Don't insert lfence with |
6560 | | -mlfence-after-load=yes. */ |
6561 | 0 | if (lfence_after_load |
6562 | 0 | || lfence_before_indirect_branch == lfence_branch_memory) |
6563 | 0 | return; |
6564 | 0 | } |
6565 | 0 | else if (i.mem_operands == 1 |
6566 | 0 | && lfence_before_indirect_branch != lfence_branch_register) |
6567 | 0 | { |
6568 | 0 | as_warn (_("indirect `%s` with memory operand should be avoided"), |
6569 | 0 | insn_name (&i.tm)); |
6570 | 0 | return; |
6571 | 0 | } |
6572 | 0 | else |
6573 | 0 | return; |
6574 | | |
6575 | 0 | if (last_insn->kind != last_insn_other) |
6576 | 0 | { |
6577 | 0 | as_warn_where (last_insn->file, last_insn->line, |
6578 | 0 | _("`%s` skips -mlfence-before-indirect-branch on `%s`"), |
6579 | 0 | last_insn->name, insn_name (&i.tm)); |
6580 | 0 | return; |
6581 | 0 | } |
6582 | | |
6583 | 0 | p = frag_more (3); |
6584 | 0 | *p++ = 0xf; |
6585 | 0 | *p++ = 0xae; |
6586 | 0 | *p = 0xe8; |
6587 | 0 | return; |
6588 | 0 | } |
6589 | | |
6590 | | /* Output or/not/shl and lfence before near ret. */ |
6591 | 2.64k | if (lfence_before_ret != lfence_before_ret_none |
6592 | 2.64k | && (i.tm.base_opcode | 1) == 0xc3) |
6593 | 0 | { |
6594 | 0 | if (last_insn->kind != last_insn_other) |
6595 | 0 | { |
6596 | 0 | as_warn_where (last_insn->file, last_insn->line, |
6597 | 0 | _("`%s` skips -mlfence-before-ret on `%s`"), |
6598 | 0 | last_insn->name, insn_name (&i.tm)); |
6599 | 0 | return; |
6600 | 0 | } |
6601 | | |
6602 | | /* Near ret ingore operand size override under CPU64. */ |
6603 | 0 | char prefix = flag_code == CODE_64BIT |
6604 | 0 | ? 0x48 |
6605 | 0 | : i.prefix[DATA_PREFIX] ? 0x66 : 0x0; |
6606 | |
|
6607 | 0 | if (lfence_before_ret == lfence_before_ret_not) |
6608 | 0 | { |
6609 | | /* not: 0xf71424, may add prefix |
6610 | | for operand size override or 64-bit code. */ |
6611 | 0 | p = frag_more ((prefix ? 2 : 0) + 6 + 3); |
6612 | 0 | if (prefix) |
6613 | 0 | *p++ = prefix; |
6614 | 0 | *p++ = 0xf7; |
6615 | 0 | *p++ = 0x14; |
6616 | 0 | *p++ = 0x24; |
6617 | 0 | if (prefix) |
6618 | 0 | *p++ = prefix; |
6619 | 0 | *p++ = 0xf7; |
6620 | 0 | *p++ = 0x14; |
6621 | 0 | *p++ = 0x24; |
6622 | 0 | } |
6623 | 0 | else |
6624 | 0 | { |
6625 | 0 | p = frag_more ((prefix ? 1 : 0) + 4 + 3); |
6626 | 0 | if (prefix) |
6627 | 0 | *p++ = prefix; |
6628 | 0 | if (lfence_before_ret == lfence_before_ret_or) |
6629 | 0 | { |
6630 | | /* or: 0x830c2400, may add prefix |
6631 | | for operand size override or 64-bit code. */ |
6632 | 0 | *p++ = 0x83; |
6633 | 0 | *p++ = 0x0c; |
6634 | 0 | } |
6635 | 0 | else |
6636 | 0 | { |
6637 | | /* shl: 0xc1242400, may add prefix |
6638 | | for operand size override or 64-bit code. */ |
6639 | 0 | *p++ = 0xc1; |
6640 | 0 | *p++ = 0x24; |
6641 | 0 | } |
6642 | |
|
6643 | 0 | *p++ = 0x24; |
6644 | 0 | *p++ = 0x0; |
6645 | 0 | } |
6646 | |
|
6647 | 0 | *p++ = 0xf; |
6648 | 0 | *p++ = 0xae; |
6649 | 0 | *p = 0xe8; |
6650 | 0 | } |
6651 | 2.64k | } |
6652 | | |
6653 | | /* Shared helper for md_assemble() and s_insn(). */ |
6654 | | static void init_globals (void) |
6655 | 510k | { |
6656 | 510k | unsigned int j; |
6657 | | |
6658 | 510k | memset (&i, '\0', sizeof (i)); |
6659 | 510k | i.rounding.type = rc_none; |
6660 | 3.06M | for (j = 0; j < MAX_OPERANDS; j++) |
6661 | 2.55M | i.reloc[j] = NO_RELOC; |
6662 | 510k | memset (disp_expressions, '\0', sizeof (disp_expressions)); |
6663 | 510k | memset (im_expressions, '\0', sizeof (im_expressions)); |
6664 | 510k | save_stack_p = save_stack; |
6665 | 510k | } |
6666 | | |
6667 | | /* Helper for md_assemble() to decide whether to prepare for a possible 2nd |
6668 | | parsing pass. Instead of introducing a rarely used new insn attribute this |
6669 | | utilizes a common pattern between affected templates. It is deemed |
6670 | | acceptable that this will lead to unnecessary pass 2 preparations in a |
6671 | | limited set of cases. */ |
6672 | | static INLINE bool may_need_pass2 (const insn_template *t) |
6673 | 85.5k | { |
6674 | 85.5k | return t->opcode_modifier.sse2avx |
6675 | | /* Note that all SSE2AVX templates have at least one operand. */ |
6676 | 85.5k | ? t->operand_types[t->operands - 1].bitfield.class == RegSIMD |
6677 | 85.5k | : (t->opcode_space == SPACE_0F |
6678 | 49.8k | && (t->base_opcode | 1) == 0xbf) |
6679 | 49.8k | || (t->opcode_space == SPACE_BASE |
6680 | 49.8k | && t->base_opcode == 0x63) |
6681 | 49.8k | || (intel_syntax /* shld / shrd may mean suffixed shl / shr. */ |
6682 | 49.8k | && t->opcode_space == SPACE_MAP4 |
6683 | 49.8k | && (t->base_opcode | 8) == 0x2c); |
6684 | 85.5k | } |
6685 | | |
6686 | | #ifdef OBJ_ELF |
6687 | | static enum x86_tls_error_type |
6688 | | x86_check_tls_relocation (enum bfd_reloc_code_real r_type) |
6689 | 1.14k | { |
6690 | 1.14k | switch (r_type) |
6691 | 1.14k | { |
6692 | 0 | case BFD_RELOC_386_TLS_GOTDESC: |
6693 | | /* Check GDesc access model: |
6694 | | |
6695 | | leal x@tlsdesc(%ebx), %reg32 --> Memory reg must be %ebx and |
6696 | | SIB is not supported. |
6697 | | */ |
6698 | 0 | if (i.tm.mnem_off != MN_lea) |
6699 | 0 | return x86_tls_error_insn; |
6700 | 0 | if (i.index_reg) |
6701 | 0 | return x86_tls_error_sib; |
6702 | 0 | if (!i.base_reg) |
6703 | 0 | return x86_tls_error_no_base_reg; |
6704 | 0 | if (i.base_reg->reg_type.bitfield.instance != RegB) |
6705 | 0 | return x86_tls_error_ebx; |
6706 | 0 | if (!i.op[1].regs->reg_type.bitfield.dword) |
6707 | 0 | return x86_tls_error_dest_32bit_reg_size; |
6708 | 0 | break; |
6709 | | |
6710 | 0 | case BFD_RELOC_386_TLS_GD: |
6711 | | /* Check GD access model: |
6712 | | |
6713 | | leal foo@tlsgd(,%ebx,1), %eax --> Only this fixed format is supported. |
6714 | | leal foo@tlsgd(%reg32), %eax --> Dest reg must be '%eax' |
6715 | | Memory reg can't be %eax. |
6716 | | */ |
6717 | 0 | if (i.tm.mnem_off != MN_lea) |
6718 | 0 | return x86_tls_error_insn; |
6719 | 0 | if (i.op[1].regs->reg_type.bitfield.instance != Accum) |
6720 | 0 | return x86_tls_error_dest_eax; |
6721 | 0 | if (!i.op[1].regs->reg_type.bitfield.dword) |
6722 | 0 | return x86_tls_error_dest_32bit_reg_size; |
6723 | 0 | if (i.index_reg) |
6724 | 0 | { |
6725 | 0 | if (i.base_reg) |
6726 | 0 | return x86_tls_error_base_reg; |
6727 | 0 | if (i.index_reg->reg_type.bitfield.instance != RegB) |
6728 | 0 | return x86_tls_error_index_ebx; |
6729 | 0 | if (i.log2_scale_factor) |
6730 | 0 | return x86_tls_error_scale_factor; |
6731 | 0 | } |
6732 | 0 | else |
6733 | 0 | { |
6734 | 0 | if (!i.base_reg) |
6735 | 0 | return x86_tls_error_no_base_reg; |
6736 | 0 | if (i.base_reg->reg_type.bitfield.instance == Accum) |
6737 | 0 | return x86_tls_error_eax; |
6738 | 0 | } |
6739 | 0 | break; |
6740 | | |
6741 | 0 | case BFD_RELOC_386_TLS_LDM: |
6742 | | /* Check LDM access model: |
6743 | | |
6744 | | leal foo@tlsldm(%reg32), %eax --> Dest reg must be '%eax' |
6745 | | Memory reg can't be %eax and SIB |
6746 | | is not supported. |
6747 | | */ |
6748 | 0 | if (i.tm.mnem_off != MN_lea) |
6749 | 0 | return x86_tls_error_insn; |
6750 | 0 | if (i.index_reg) |
6751 | 0 | return x86_tls_error_sib; |
6752 | 0 | if (!i.base_reg) |
6753 | 0 | return x86_tls_error_no_base_reg; |
6754 | 0 | if (i.base_reg->reg_type.bitfield.instance == Accum) |
6755 | 0 | return x86_tls_error_eax; |
6756 | 0 | if (i.op[1].regs->reg_type.bitfield.instance != Accum) |
6757 | 0 | return x86_tls_error_dest_eax; |
6758 | 0 | if (!i.op[1].regs->reg_type.bitfield.dword) |
6759 | 0 | return x86_tls_error_dest_32bit_reg_size; |
6760 | 0 | break; |
6761 | | |
6762 | 84 | case BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
6763 | | /* Check GOTPC32 TLSDESC access model: |
6764 | | |
6765 | | --- LP64 mode --- |
6766 | | leaq x@tlsdesc(%rip), %reg64 --> Memory reg must be %rip. |
6767 | | |
6768 | | --- X32 mode --- |
6769 | | rex/rex2 leal x@tlsdesc(%rip), %reg32 --> Memory reg must be %rip. |
6770 | | |
6771 | | In X32 mode, gas will add rex/rex2 for it later, no need to check |
6772 | | here. |
6773 | | */ |
6774 | 84 | if (i.tm.mnem_off != MN_lea) |
6775 | 84 | return x86_tls_error_insn; |
6776 | 0 | if (!i.base_reg) |
6777 | 0 | return x86_tls_error_no_base_reg; |
6778 | 0 | if (i.base_reg->reg_num != RegIP |
6779 | 0 | || !i.base_reg->reg_type.bitfield.qword) |
6780 | 0 | return x86_tls_error_rip; |
6781 | 0 | if (x86_elf_abi == X86_64_ABI) |
6782 | 0 | { |
6783 | 0 | if (!i.op[1].regs->reg_type.bitfield.qword) |
6784 | 0 | return x86_tls_error_dest_64bit_reg_size; |
6785 | 0 | } |
6786 | 0 | else if (!i.op[1].regs->reg_type.bitfield.dword |
6787 | 0 | && !i.op[1].regs->reg_type.bitfield.qword) |
6788 | 0 | return x86_tls_error_dest_32bit_or_64bit_reg_size; |
6789 | 0 | break; |
6790 | | |
6791 | 692 | case BFD_RELOC_X86_64_TLSGD: |
6792 | | /* Check GD access model: |
6793 | | |
6794 | | leaq foo@tlsgd(%rip), %rdi --> Only this fixed format is supported. |
6795 | | */ |
6796 | 693 | case BFD_RELOC_X86_64_TLSLD: |
6797 | | /* Check LD access model: |
6798 | | |
6799 | | leaq foo@tlsld(%rip), %rdi --> Only this fixed format is supported. |
6800 | | */ |
6801 | 693 | if (i.tm.mnem_off != MN_lea) |
6802 | 693 | return x86_tls_error_insn; |
6803 | 0 | if (!i.base_reg) |
6804 | 0 | return x86_tls_error_no_base_reg; |
6805 | 0 | if (i.base_reg->reg_num != RegIP |
6806 | 0 | || !i.base_reg->reg_type.bitfield.qword) |
6807 | 0 | return x86_tls_error_rip; |
6808 | 0 | if (!i.op[1].regs->reg_type.bitfield.qword |
6809 | 0 | || i.op[1].regs->reg_num != EDI_REG_NUM |
6810 | 0 | || i.op[1].regs->reg_flags) |
6811 | 0 | return x86_tls_error_dest_rdi; |
6812 | 0 | break; |
6813 | | |
6814 | 0 | case BFD_RELOC_386_TLS_GOTIE: |
6815 | | /* Check GOTIE access model: |
6816 | | |
6817 | | subl foo@gotntpoff(%reg1), %reg2 |
6818 | | movl foo@gotntpoff(%reg1), %reg2 |
6819 | | addl foo@gotntpoff(%reg1), %reg2 |
6820 | | |
6821 | | Memory operand: SIB is not supported. |
6822 | | */ |
6823 | 0 | case BFD_RELOC_386_TLS_IE_32: |
6824 | | /* Check IE_32 access model: |
6825 | | |
6826 | | subl foo@gottpoff(%reg1), %reg2 |
6827 | | movl foo@gottpoff(%reg1), %reg2 |
6828 | | addl foo@gottpoff(%reg1), %reg2 |
6829 | | |
6830 | | Memory operand: SIB is not supported. |
6831 | | */ |
6832 | 0 | if (i.tm.mnem_off != MN_sub |
6833 | 0 | && i.tm.mnem_off != MN_add |
6834 | 0 | && i.tm.mnem_off != MN_mov) |
6835 | 0 | return x86_tls_error_insn; |
6836 | 0 | if (i.imm_operands |
6837 | 0 | || i.disp_operands != 1 |
6838 | 0 | || i.reg_operands != 1 |
6839 | 0 | || i.types[1].bitfield.class != Reg) |
6840 | 0 | return x86_tls_error_opcode; |
6841 | 0 | if (!i.base_reg) |
6842 | 0 | return x86_tls_error_no_base_reg; |
6843 | 0 | if (i.index_reg) |
6844 | 0 | return x86_tls_error_sib; |
6845 | 0 | if (!i.base_reg->reg_type.bitfield.dword) |
6846 | 0 | return x86_tls_error_base_reg_size; |
6847 | 0 | if (!i.op[1].regs->reg_type.bitfield.dword) |
6848 | 0 | return x86_tls_error_dest_32bit_reg_size; |
6849 | 0 | break; |
6850 | | |
6851 | 0 | case BFD_RELOC_386_TLS_IE: |
6852 | | /* Check IE access model: |
6853 | | |
6854 | | movl foo@indntpoff, %reg32 --> Mod == 00 && r/m == 5 |
6855 | | addl foo@indntpoff, %reg32 --> Mod == 00 && r/m == 5 |
6856 | | */ |
6857 | 0 | if (i.tm.mnem_off != MN_add && i.tm.mnem_off != MN_mov) |
6858 | 0 | return x86_tls_error_insn; |
6859 | 0 | if (i.imm_operands |
6860 | 0 | || i.disp_operands != 1 |
6861 | 0 | || i.reg_operands != 1 |
6862 | 0 | || i.types[1].bitfield.class != Reg) |
6863 | 0 | return x86_tls_error_opcode; |
6864 | 0 | if (i.base_reg || i.index_reg) |
6865 | 0 | return x86_tls_error_require_no_base_index_reg; |
6866 | 0 | if (!i.op[1].regs->reg_type.bitfield.dword) |
6867 | 0 | return x86_tls_error_dest_32bit_reg_size; |
6868 | 0 | break; |
6869 | | |
6870 | 105 | case BFD_RELOC_X86_64_GOTTPOFF: |
6871 | | /* Check GOTTPOFF access model: |
6872 | | |
6873 | | mov foo@gottpoff(%rip), %reg --> Memory Reg must be %rip. |
6874 | | movrs foo@gottpoff(%rip), %reg --> Memory Reg must be %rip. |
6875 | | add foo@gottpoff(%rip), %reg --> Memory Reg must be %rip. |
6876 | | add %reg1, foo@gottpoff(%rip), %reg2 --> Memory Reg must be %rip. |
6877 | | add foo@gottpoff(%rip), %reg1, %reg2 --> Memory Reg must be %rip. |
6878 | | */ |
6879 | 105 | if (i.tm.mnem_off != MN_add && i.tm.mnem_off != MN_mov |
6880 | 105 | && i.tm.mnem_off != MN_movrs) |
6881 | 105 | return x86_tls_error_insn; |
6882 | 0 | if (i.imm_operands |
6883 | 0 | || i.disp_operands != 1 |
6884 | 0 | || i.types[i.operands - 1].bitfield.class != Reg) |
6885 | 0 | return x86_tls_error_opcode; |
6886 | 0 | if (!i.base_reg) |
6887 | 0 | return x86_tls_error_no_base_reg; |
6888 | 0 | if (i.base_reg->reg_num != RegIP |
6889 | 0 | || !i.base_reg->reg_type.bitfield.qword) |
6890 | 0 | return x86_tls_error_rip; |
6891 | 0 | if (x86_elf_abi == X86_64_ABI) |
6892 | 0 | { |
6893 | 0 | if (!i.op[i.operands - 1].regs->reg_type.bitfield.qword) |
6894 | 0 | return x86_tls_error_dest_64bit_reg_size; |
6895 | 0 | } |
6896 | 0 | else if (!i.op[i.operands - 1].regs->reg_type.bitfield.dword |
6897 | 0 | && !i.op[i.operands - 1].regs->reg_type.bitfield.qword) |
6898 | 0 | return x86_tls_error_dest_32bit_or_64bit_reg_size; |
6899 | 0 | break; |
6900 | | |
6901 | 0 | case BFD_RELOC_386_TLS_DESC_CALL: |
6902 | | /* Check GDesc access model: |
6903 | | |
6904 | | call *x@tlscall(%eax) --> Memory reg must be %eax and |
6905 | | SIB is not supported. |
6906 | | */ |
6907 | 66 | case BFD_RELOC_X86_64_TLSDESC_CALL: |
6908 | | /* Check GDesc access model: |
6909 | | |
6910 | | call *x@tlscall(%rax) <--- LP64 mode. |
6911 | | call *x@tlscall(%eax) <--- X32 mode. |
6912 | | |
6913 | | Only these fixed formats are supported. |
6914 | | */ |
6915 | 66 | if (i.tm.mnem_off != MN_call) |
6916 | 66 | return x86_tls_error_insn; |
6917 | 0 | if (i.index_reg) |
6918 | 0 | return x86_tls_error_sib; |
6919 | 0 | if (!i.base_reg) |
6920 | 0 | return x86_tls_error_no_base_reg; |
6921 | 0 | if (i.base_reg->reg_type.bitfield.instance != Accum) |
6922 | 0 | return x86_tls_error_RegA; |
6923 | 0 | break; |
6924 | | |
6925 | 3 | case BFD_RELOC_NONE: |
6926 | | /* This isn't a relocation. */ |
6927 | 3 | return x86_tls_error_continue; |
6928 | | |
6929 | 191 | default: |
6930 | 191 | break; |
6931 | 1.14k | } |
6932 | | |
6933 | | /* This relocation is OK. */ |
6934 | 191 | return x86_tls_error_none; |
6935 | 1.14k | } |
6936 | | |
6937 | | static void |
6938 | | x86_report_tls_error (enum x86_tls_error_type tls_error, |
6939 | | enum bfd_reloc_code_real r_type) |
6940 | 948 | { |
6941 | 948 | unsigned int k; |
6942 | 8.51k | for (k = 0; k < ARRAY_SIZE (gotrel); k++) |
6943 | 8.51k | if (gotrel[k].rel[object_64bit] == r_type) |
6944 | 948 | break; |
6945 | | |
6946 | 948 | switch (tls_error) |
6947 | 948 | { |
6948 | 948 | case x86_tls_error_insn: |
6949 | 948 | as_bad (_("@%s operator cannot be used with `%s'"), |
6950 | 948 | gotrel[k].str, insn_name (&i.tm)); |
6951 | 948 | return; |
6952 | | |
6953 | 0 | case x86_tls_error_opcode: |
6954 | 0 | as_bad (_("@%s operator can be used with `%s', but format is wrong"), |
6955 | 0 | gotrel[k].str, insn_name (&i.tm)); |
6956 | 0 | return; |
6957 | | |
6958 | 0 | case x86_tls_error_sib: |
6959 | 0 | as_bad (_("@%s operator requires no SIB"), gotrel[k].str); |
6960 | 0 | return; |
6961 | | |
6962 | 0 | case x86_tls_error_no_base_reg: |
6963 | 0 | as_bad (_("@%s operator requires base register"), gotrel[k].str); |
6964 | 0 | return; |
6965 | | |
6966 | 0 | case x86_tls_error_require_no_base_index_reg: |
6967 | 0 | as_bad (_("@%s operator requires no base/index register"), |
6968 | 0 | gotrel[k].str); |
6969 | 0 | return; |
6970 | | |
6971 | 0 | case x86_tls_error_base_reg: |
6972 | 0 | as_bad (_("@%s operator requires no base register"), gotrel[k].str); |
6973 | 0 | return; |
6974 | | |
6975 | 0 | case x86_tls_error_index_ebx: |
6976 | 0 | as_bad (_("@%s operator requires `%sebx' as index register"), |
6977 | 0 | gotrel[k].str, register_prefix); |
6978 | 0 | return; |
6979 | | |
6980 | 0 | case x86_tls_error_eax: |
6981 | 0 | as_bad (_("@%s operator requires `%seax' as base register"), |
6982 | 0 | gotrel[k].str, register_prefix); |
6983 | 0 | return; |
6984 | | |
6985 | 0 | case x86_tls_error_RegA: |
6986 | 0 | as_bad (_("@%s operator requires `%seax/%srax' as base register"), |
6987 | 0 | gotrel[k].str, register_prefix, register_prefix); |
6988 | 0 | return; |
6989 | | |
6990 | 0 | case x86_tls_error_ebx: |
6991 | 0 | as_bad (_("@%s operator requires `%sebx' as base register"), |
6992 | 0 | gotrel[k].str, register_prefix); |
6993 | 0 | return; |
6994 | | |
6995 | 0 | case x86_tls_error_rip: |
6996 | 0 | as_bad (_("@%s operator requires `%srip' as base register"), |
6997 | 0 | gotrel[k].str, register_prefix); |
6998 | 0 | return; |
6999 | | |
7000 | 0 | case x86_tls_error_dest_eax: |
7001 | 0 | as_bad (_("@%s operator requires `%seax' as dest register"), |
7002 | 0 | gotrel[k].str, register_prefix); |
7003 | 0 | return; |
7004 | | |
7005 | 0 | case x86_tls_error_dest_rdi: |
7006 | 0 | as_bad (_("@%s operator requires `%srdi' as dest register"), |
7007 | 0 | gotrel[k].str, register_prefix); |
7008 | 0 | return; |
7009 | | |
7010 | 0 | case x86_tls_error_scale_factor: |
7011 | 0 | as_bad (_("@%s operator requires scale factor of 1"), |
7012 | 0 | gotrel[k].str); |
7013 | 0 | return; |
7014 | | |
7015 | 0 | case x86_tls_error_base_reg_size: |
7016 | 0 | as_bad (_("@%s operator requires 32-bit base register"), |
7017 | 0 | gotrel[k].str); |
7018 | 0 | return; |
7019 | | |
7020 | 0 | case x86_tls_error_dest_32bit_reg_size: |
7021 | 0 | as_bad (_("@%s operator requires 32-bit dest register"), |
7022 | 0 | gotrel[k].str); |
7023 | 0 | return; |
7024 | | |
7025 | 0 | case x86_tls_error_dest_64bit_reg_size: |
7026 | 0 | as_bad (_("@%s operator requires 64-bit dest register"), |
7027 | 0 | gotrel[k].str); |
7028 | 0 | return; |
7029 | | |
7030 | 0 | case x86_tls_error_dest_32bit_or_64bit_reg_size: |
7031 | 0 | as_bad (_("@%s operator requires 32-bit or 64-bit dest register"), |
7032 | 0 | gotrel[k].str); |
7033 | 0 | return; |
7034 | | |
7035 | 0 | default: |
7036 | 0 | abort (); |
7037 | 948 | } |
7038 | 948 | } |
7039 | | #endif |
7040 | | |
7041 | | /* This is the guts of the machine-dependent assembler. LINE points to a |
7042 | | machine dependent instruction. This function is supposed to emit |
7043 | | the frags/bytes it assembles to. */ |
7044 | | |
7045 | | static void |
7046 | | i386_assemble (char *line) |
7047 | 475k | { |
7048 | 475k | unsigned int j; |
7049 | 475k | char mnemonic[MAX_MNEM_SIZE], mnem_suffix = 0, *copy = NULL; |
7050 | 475k | char *xstrdup_copy = NULL; |
7051 | 475k | const char *end, *pass1_mnem = NULL; |
7052 | 475k | enum i386_error pass1_err = 0; |
7053 | 475k | struct pseudo_prefixes orig_pp = pp; |
7054 | 475k | const insn_template *t; |
7055 | 475k | struct last_insn *last_insn |
7056 | 475k | = &seg_info(now_seg)->tc_segment_info_data.last_insn; |
7057 | | |
7058 | | /* Initialize globals. */ |
7059 | 475k | current_templates.end = current_templates.start = NULL; |
7060 | 510k | retry: |
7061 | 510k | init_globals (); |
7062 | | |
7063 | | /* Suppress optimization when the last thing we saw may not have been |
7064 | | a proper instruction (e.g. a stand-alone prefix or .byte). */ |
7065 | 510k | if (last_insn->kind != last_insn_other) |
7066 | 96.9k | pp.no_optimize = true; |
7067 | | |
7068 | | /* First parse an instruction mnemonic & call i386_operand for the operands. |
7069 | | We assume that the scrubber has arranged it so that line[0] is the valid |
7070 | | start of a (possibly prefixed) mnemonic. */ |
7071 | | |
7072 | 510k | end = parse_insn (line, mnemonic, parse_all); |
7073 | 510k | if (end == NULL) |
7074 | 425k | { |
7075 | 425k | if (pass1_mnem != NULL) |
7076 | 34.2k | goto match_error; |
7077 | 391k | if (i.error != no_error) |
7078 | 1.23k | { |
7079 | 1.23k | gas_assert (current_templates.start != NULL); |
7080 | 1.23k | if (may_need_pass2 (current_templates.start) && !i.suffix) |
7081 | 121 | goto no_match; |
7082 | | /* No point in trying a 2nd pass - it'll only find the same suffix |
7083 | | again. */ |
7084 | 1.11k | mnem_suffix = i.suffix; |
7085 | 1.11k | goto match_error; |
7086 | 1.23k | } |
7087 | 390k | return; |
7088 | 391k | } |
7089 | 84.3k | t = current_templates.start; |
7090 | | /* NB: LINE may be change to be the same as XSTRDUP_COPY. */ |
7091 | 84.3k | if (xstrdup_copy != line && may_need_pass2 (t)) |
7092 | 35.5k | { |
7093 | | /* Make a copy of the full line in case we need to retry. */ |
7094 | 35.5k | xstrdup_copy = xstrdup (line); |
7095 | 35.5k | copy = xstrdup_copy; |
7096 | 35.5k | } |
7097 | 84.3k | line += end - line; |
7098 | 84.3k | mnem_suffix = i.suffix; |
7099 | | |
7100 | 84.3k | line = parse_operands (line, mnemonic); |
7101 | 84.3k | this_operand = -1; |
7102 | 84.3k | if (line == NULL) |
7103 | 8.35k | { |
7104 | 8.35k | free (xstrdup_copy); |
7105 | 8.35k | return; |
7106 | 8.35k | } |
7107 | | |
7108 | | /* Now we've parsed the mnemonic into a set of templates, and have the |
7109 | | operands at hand. */ |
7110 | | |
7111 | | /* All Intel opcodes have reversed operands except for "bound", "enter", |
7112 | | "invlpg*", "monitor*", "mwait*", "tpause", "umwait", "pvalidate", |
7113 | | "rmpadjust", "rmpquery", and deprecated forms of "rmpupdate". |
7114 | | We also don't reverse intersegment "jmp" and "call" instructions with |
7115 | | 2 immediate operands so that the immediate segment precedes the offset |
7116 | | consistently in Intel and AT&T modes. */ |
7117 | 75.9k | if (intel_syntax |
7118 | 75.9k | && i.operands > 1 |
7119 | 75.9k | && (t->mnem_off != MN_bound) |
7120 | 75.9k | && !startswith (mnemonic, "invlpg") |
7121 | 75.9k | && !startswith (mnemonic, "monitor") |
7122 | 75.9k | && !startswith (mnemonic, "mwait") |
7123 | 75.9k | && (t->mnem_off != MN_pvalidate) |
7124 | 75.9k | && (!startswith (mnemonic, "rmp") || i.mem_operands) |
7125 | 75.9k | && (t->mnem_off != MN_tpause) |
7126 | 75.9k | && (t->mnem_off != MN_umwait) |
7127 | 75.9k | && !(i.operands == 2 |
7128 | 0 | && operand_type_check (i.types[0], imm) |
7129 | 0 | && operand_type_check (i.types[1], imm))) |
7130 | 0 | swap_operands (); |
7131 | | |
7132 | | /* The order of the immediates should be reversed for 2-immediates EXTRQ |
7133 | | and INSERTQ instructions. Also OUT, UWRMSR, and WRMSRNS want their |
7134 | | immediate to be in the "canonical" place (first), despite it appearing |
7135 | | last (in AT&T syntax, or because of the swapping above) in the incoming |
7136 | | set of operands. */ |
7137 | 75.9k | if ((i.imm_operands == 2 |
7138 | 75.9k | && (t->mnem_off == MN_extrq || t->mnem_off == MN_insertq)) |
7139 | 75.9k | || ((t->mnem_off == MN_out || t->mnem_off == MN_uwrmsr |
7140 | 75.9k | || t->mnem_off == MN_wrmsrns) |
7141 | 75.9k | && i.imm_operands && i.operands > i.imm_operands)) |
7142 | 0 | swap_2_operands (0, 1); |
7143 | | |
7144 | 75.9k | if (i.imm_operands) |
7145 | 4.68k | { |
7146 | | /* For USER_MSR and MSR_IMM instructions, imm32 stands for the name of a |
7147 | | model specific register (MSR). That's an unsigned quantity, whereas all |
7148 | | other insns with 32-bit immediate and 64-bit operand size use |
7149 | | sign-extended immediates (imm32s). Therefore these insns are |
7150 | | special-cased, bypassing the normal handling of immediates here. */ |
7151 | 4.68k | if (is_cpu(current_templates.start, CpuUSER_MSR) |
7152 | 4.68k | || t->mnem_off == MN_rdmsr |
7153 | 4.68k | || t->mnem_off == MN_wrmsrns) |
7154 | 0 | { |
7155 | 0 | for (j = 0; j < i.imm_operands; j++) |
7156 | 0 | i.types[j] = smallest_imm_type (i.op[j].imms->X_add_number); |
7157 | 0 | } |
7158 | 4.68k | else |
7159 | 4.68k | optimize_imm (); |
7160 | 4.68k | } |
7161 | | |
7162 | 75.9k | if (i.disp_operands && !optimize_disp (t)) |
7163 | 0 | return; |
7164 | | |
7165 | | /* Next, we find a template that matches the given insn, |
7166 | | making sure the overlap of the given operands types is consistent |
7167 | | with the template operand types. */ |
7168 | | |
7169 | 75.9k | if (!(t = match_template (mnem_suffix))) |
7170 | 73.0k | { |
7171 | 73.0k | const char *err_msg; |
7172 | | |
7173 | 73.0k | if (copy && !mnem_suffix) |
7174 | 34.1k | { |
7175 | 34.1k | line = copy; |
7176 | 34.1k | copy = NULL; |
7177 | 34.2k | no_match: |
7178 | 34.2k | pass1_err = i.error; |
7179 | 34.2k | pass1_mnem = insn_name (current_templates.start); |
7180 | 34.2k | pp = orig_pp; |
7181 | 34.2k | goto retry; |
7182 | 34.1k | } |
7183 | | |
7184 | | /* If a non-/only-64bit template (group) was found in pass 1, and if |
7185 | | _some_ template (group) was found in pass 2, squash pass 1's |
7186 | | error. */ |
7187 | 38.9k | if (pass1_err == unsupported_64bit) |
7188 | 0 | pass1_mnem = NULL; |
7189 | | |
7190 | 74.2k | match_error: |
7191 | 74.2k | free (xstrdup_copy); |
7192 | | |
7193 | 74.2k | switch (pass1_mnem ? pass1_err : i.error) |
7194 | 74.2k | { |
7195 | 0 | default: |
7196 | 0 | abort (); |
7197 | 0 | case operand_size_mismatch: |
7198 | 0 | err_msg = _("operand size mismatch"); |
7199 | 0 | break; |
7200 | 605 | case operand_type_mismatch: |
7201 | 605 | err_msg = _("operand type mismatch"); |
7202 | 605 | break; |
7203 | 0 | case register_type_mismatch: |
7204 | 0 | err_msg = _("register type mismatch"); |
7205 | 0 | break; |
7206 | 72.0k | case number_of_operands_mismatch: |
7207 | 72.0k | err_msg = _("number of operands mismatch"); |
7208 | 72.0k | break; |
7209 | 376 | case invalid_instruction_suffix: |
7210 | 376 | err_msg = _("invalid instruction suffix"); |
7211 | 376 | break; |
7212 | 0 | case bad_imm4: |
7213 | 0 | err_msg = _("constant doesn't fit in 4 bits"); |
7214 | 0 | break; |
7215 | 0 | case unsupported_with_intel_mnemonic: |
7216 | 0 | err_msg = _("unsupported with Intel mnemonic"); |
7217 | 0 | break; |
7218 | 0 | case unsupported_syntax: |
7219 | 0 | err_msg = _("unsupported syntax"); |
7220 | 0 | break; |
7221 | 0 | case unsupported_EGPR_for_addressing: |
7222 | 0 | err_msg = _("extended GPR cannot be used as base/index"); |
7223 | 0 | break; |
7224 | 0 | case unsupported_nf: |
7225 | 0 | err_msg = _("{nf} unsupported"); |
7226 | 0 | break; |
7227 | 42 | case unsupported: |
7228 | 42 | as_bad (_("unsupported instruction `%s'"), |
7229 | 42 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start)); |
7230 | 42 | return; |
7231 | 1.07k | case unsupported_on_arch: |
7232 | 1.07k | as_bad (_("`%s' is not supported on `%s%s'"), |
7233 | 1.07k | pass1_mnem ? pass1_mnem : insn_name (current_templates.start), |
7234 | 1.07k | cpu_arch_name ? cpu_arch_name : default_arch, |
7235 | 1.07k | cpu_sub_arch_name ? cpu_sub_arch_name : ""); |
7236 | 1.07k | return; |
7237 | 163 | case unsupported_64bit: |
7238 | 163 | if (ISLOWER (mnem_suffix)) |
7239 | 68 | { |
7240 | 68 | if (flag_code == CODE_64BIT) |
7241 | 1 | as_bad (_("`%s%c' is not supported in 64-bit mode"), |
7242 | 1 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start), |
7243 | 1 | mnem_suffix); |
7244 | 67 | else |
7245 | 67 | as_bad (_("`%s%c' is only supported in 64-bit mode"), |
7246 | 67 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start), |
7247 | 67 | mnem_suffix); |
7248 | 68 | } |
7249 | 95 | else |
7250 | 95 | { |
7251 | 95 | if (flag_code == CODE_64BIT) |
7252 | 2 | as_bad (_("`%s' is not supported in 64-bit mode"), |
7253 | 2 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start)); |
7254 | 93 | else |
7255 | 93 | as_bad (_("`%s' is only supported in 64-bit mode"), |
7256 | 93 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start)); |
7257 | 95 | } |
7258 | 163 | return; |
7259 | 0 | case no_vex_encoding: |
7260 | 0 | err_msg = _("no VEX/XOP encoding"); |
7261 | 0 | break; |
7262 | 0 | case no_evex_encoding: |
7263 | 0 | err_msg = _("no EVEX encoding"); |
7264 | 0 | break; |
7265 | 0 | case invalid_sib_address: |
7266 | 0 | err_msg = _("invalid SIB address"); |
7267 | 0 | break; |
7268 | 0 | case invalid_vsib_address: |
7269 | 0 | err_msg = _("invalid VSIB address"); |
7270 | 0 | break; |
7271 | 0 | case invalid_vector_register_set: |
7272 | 0 | err_msg = _("mask, index, and destination registers must be distinct"); |
7273 | 0 | break; |
7274 | 0 | case invalid_tmm_register_set: |
7275 | 0 | err_msg = _("all tmm registers must be distinct"); |
7276 | 0 | break; |
7277 | 0 | case invalid_dest_and_src_register_set: |
7278 | 0 | err_msg = _("destination and source registers must be distinct"); |
7279 | 0 | break; |
7280 | 0 | case invalid_dest_register_set: |
7281 | 0 | err_msg = _("two dest registers must be distinct"); |
7282 | 0 | break; |
7283 | 0 | case invalid_pseudo_prefix: |
7284 | 0 | err_msg = _("rex2 pseudo prefix cannot be used"); |
7285 | 0 | break; |
7286 | 0 | case unsupported_vector_index_register: |
7287 | 0 | err_msg = _("unsupported vector index register"); |
7288 | 0 | break; |
7289 | 0 | case unsupported_broadcast: |
7290 | 0 | err_msg = _("unsupported broadcast"); |
7291 | 0 | break; |
7292 | 0 | case broadcast_needed: |
7293 | 0 | err_msg = _("broadcast is needed for operand of such type"); |
7294 | 0 | break; |
7295 | 0 | case unsupported_masking: |
7296 | 0 | err_msg = _("unsupported masking"); |
7297 | 0 | break; |
7298 | 0 | case mask_not_on_destination: |
7299 | 0 | err_msg = _("mask not on destination operand"); |
7300 | 0 | break; |
7301 | 0 | case no_default_mask: |
7302 | 0 | err_msg = _("default mask isn't allowed"); |
7303 | 0 | break; |
7304 | 0 | case unsupported_rc_sae: |
7305 | 0 | err_msg = _("unsupported static rounding/sae"); |
7306 | 0 | break; |
7307 | 0 | case unsupported_vector_size: |
7308 | 0 | as_bad (_("vector size above %u required for `%s'"), 128u << vector_size, |
7309 | 0 | pass1_mnem ? pass1_mnem : insn_name (current_templates.start)); |
7310 | 0 | return; |
7311 | 0 | case unsupported_rsp_register: |
7312 | 0 | err_msg = _("'rsp' register cannot be used"); |
7313 | 0 | break; |
7314 | 0 | case internal_error: |
7315 | 0 | err_msg = _("internal error"); |
7316 | 0 | break; |
7317 | 74.2k | } |
7318 | 72.9k | as_bad (_("%s for `%s'"), err_msg, |
7319 | 72.9k | pass1_mnem ? pass1_mnem : insn_name (current_templates.start)); |
7320 | 72.9k | return; |
7321 | 74.2k | } |
7322 | | |
7323 | 2.92k | free (xstrdup_copy); |
7324 | | |
7325 | 2.92k | if (sse_check != check_none |
7326 | | /* The opcode space check isn't strictly needed; it's there only to |
7327 | | bypass the logic below when easily possible. */ |
7328 | 2.92k | && t->opcode_space >= SPACE_0F |
7329 | 2.92k | && t->opcode_space <= SPACE_0F3A |
7330 | 2.92k | && !is_cpu (&i.tm, CpuSSE4a) |
7331 | 2.92k | && !is_any_vex_encoding (t)) |
7332 | 0 | { |
7333 | | /* Some KL and all WideKL insns have only implicit %xmm operands. */ |
7334 | 0 | bool simd = is_cpu (t, CpuKL) || is_cpu (t, CpuWideKL); |
7335 | |
|
7336 | 0 | for (j = 0; j < t->operands; ++j) |
7337 | 0 | { |
7338 | 0 | if (t->operand_types[j].bitfield.class == RegMMX) |
7339 | 0 | break; |
7340 | 0 | if (t->operand_types[j].bitfield.class == RegSIMD) |
7341 | 0 | simd = true; |
7342 | 0 | } |
7343 | |
|
7344 | 0 | if (j >= t->operands && simd) |
7345 | 0 | (sse_check == check_warning |
7346 | 0 | ? as_warn |
7347 | 0 | : as_bad) (_("SSE instruction `%s' is used"), insn_name (&i.tm)); |
7348 | 0 | } |
7349 | | |
7350 | 2.92k | if (i.tm.opcode_modifier.fwait) |
7351 | 6 | if (!add_prefix (FWAIT_OPCODE)) |
7352 | 0 | return; |
7353 | | |
7354 | | /* Check if REP prefix is OK. */ |
7355 | 2.92k | if (i.rep_prefix && i.tm.opcode_modifier.prefixok != PrefixRep) |
7356 | 0 | { |
7357 | 0 | as_bad (_("invalid instruction `%s' after `%s'"), |
7358 | 0 | insn_name (&i.tm), i.rep_prefix); |
7359 | 0 | return; |
7360 | 0 | } |
7361 | | |
7362 | | /* Check for lock without a lockable instruction. Destination operand |
7363 | | must be memory unless it is xchg (0x86). */ |
7364 | 2.92k | if (i.prefix[LOCK_PREFIX]) |
7365 | 0 | { |
7366 | 0 | if (i.tm.opcode_modifier.prefixok < PrefixLock |
7367 | 0 | || i.mem_operands == 0 |
7368 | 0 | || (i.tm.base_opcode != 0x86 |
7369 | 0 | && !(i.flags[i.operands - 1] & Operand_Mem))) |
7370 | 0 | { |
7371 | 0 | as_bad (_("expecting lockable instruction after `lock'")); |
7372 | 0 | return; |
7373 | 0 | } |
7374 | | |
7375 | | /* Zap the redundant prefix from XCHG when optimizing. */ |
7376 | 0 | if (i.tm.base_opcode == 0x86 && optimize && !pp.no_optimize) |
7377 | 0 | i.prefix[LOCK_PREFIX] = 0; |
7378 | 0 | } |
7379 | | |
7380 | 2.92k | #ifdef OBJ_ELF |
7381 | 2.92k | if (i.has_gotrel && tls_check) |
7382 | 1.13k | { |
7383 | 1.13k | enum x86_tls_error_type tls_error; |
7384 | 1.14k | for (j = 0; j < i.operands; ++j) |
7385 | 1.14k | { |
7386 | 1.14k | tls_error = x86_check_tls_relocation (i.reloc[j]); |
7387 | 1.14k | if (tls_error == x86_tls_error_continue) |
7388 | 3 | continue; |
7389 | | |
7390 | 1.13k | if (tls_error != x86_tls_error_none) |
7391 | 948 | x86_report_tls_error (tls_error, i.reloc[j]); |
7392 | 1.13k | break; |
7393 | 1.14k | } |
7394 | 1.13k | } |
7395 | 2.92k | #endif |
7396 | | |
7397 | 2.92k | if ((is_any_vex_encoding (&i.tm) && i.tm.opcode_space != SPACE_MAP4) |
7398 | 2.92k | || i.tm.operand_types[i.imm_operands].bitfield.class >= RegMMX |
7399 | 2.92k | || i.tm.operand_types[i.imm_operands + 1].bitfield.class >= RegMMX) |
7400 | 35 | { |
7401 | | /* Check for data size prefix on VEX/XOP/EVEX encoded and SIMD insns. */ |
7402 | 35 | if (i.prefix[DATA_PREFIX]) |
7403 | 0 | { |
7404 | 0 | as_bad (_("data size prefix invalid with `%s'"), insn_name (&i.tm)); |
7405 | 0 | return; |
7406 | 0 | } |
7407 | 35 | } |
7408 | | |
7409 | | /* Check if HLE prefix is OK. */ |
7410 | 2.92k | if (i.hle_prefix && !check_hle ()) |
7411 | 0 | return; |
7412 | | |
7413 | | /* Check BND prefix. */ |
7414 | 2.92k | if (i.bnd_prefix && !i.tm.opcode_modifier.bndprefixok) |
7415 | 0 | as_bad (_("expecting valid branch instruction after `bnd'")); |
7416 | | |
7417 | | /* Check NOTRACK prefix. */ |
7418 | 2.92k | if (i.notrack_prefix && i.tm.opcode_modifier.prefixok != PrefixNoTrack) |
7419 | 0 | as_bad (_("expecting indirect branch instruction after `notrack'")); |
7420 | | |
7421 | 2.92k | if (is_cpu (&i.tm, CpuMPX)) |
7422 | 0 | { |
7423 | 0 | if (flag_code == CODE_64BIT && i.prefix[ADDR_PREFIX]) |
7424 | 0 | as_bad (_("32-bit address isn't allowed in 64-bit MPX instructions.")); |
7425 | 0 | else if (flag_code != CODE_16BIT |
7426 | 0 | ? i.prefix[ADDR_PREFIX] |
7427 | 0 | : i.mem_operands && !i.prefix[ADDR_PREFIX]) |
7428 | 0 | as_bad (_("16-bit address isn't allowed in MPX instructions")); |
7429 | 0 | } |
7430 | | |
7431 | | /* Insert BND prefix. */ |
7432 | 2.92k | if (add_bnd_prefix && i.tm.opcode_modifier.bndprefixok) |
7433 | 0 | { |
7434 | 0 | if (!i.prefix[BND_PREFIX]) |
7435 | 0 | add_prefix (BND_PREFIX_OPCODE); |
7436 | 0 | else if (i.prefix[BND_PREFIX] != BND_PREFIX_OPCODE) |
7437 | 0 | { |
7438 | 0 | as_warn (_("replacing `rep'/`repe' prefix by `bnd'")); |
7439 | 0 | i.prefix[BND_PREFIX] = BND_PREFIX_OPCODE; |
7440 | 0 | } |
7441 | 0 | } |
7442 | | |
7443 | | /* Check string instruction segment overrides. */ |
7444 | 2.92k | if (i.tm.opcode_modifier.isstring >= IS_STRING_ES_OP0) |
7445 | 2 | { |
7446 | 2 | gas_assert (i.mem_operands); |
7447 | 2 | if (!check_string ()) |
7448 | 0 | return; |
7449 | 2 | i.disp_operands = 0; |
7450 | 2 | } |
7451 | | |
7452 | | /* The memory operand of (%dx) should be only used with input/output |
7453 | | instructions (base opcodes: 0x6c, 0x6e, 0xec, 0xee). */ |
7454 | 2.92k | if (i.input_output_operand |
7455 | 2.92k | && ((i.tm.base_opcode | 0x82) != 0xee |
7456 | 0 | || i.tm.opcode_space != SPACE_BASE)) |
7457 | 0 | { |
7458 | 0 | as_bad (_("input/output port address isn't allowed with `%s'"), |
7459 | 0 | insn_name (&i.tm)); |
7460 | 0 | return; |
7461 | 0 | } |
7462 | | |
7463 | 2.92k | if (optimize && !pp.no_optimize && i.tm.opcode_modifier.optimize) |
7464 | 0 | { |
7465 | 0 | if (pp.has_nf) |
7466 | 0 | optimize_nf_encoding (); |
7467 | 0 | optimize_encoding (); |
7468 | 0 | } |
7469 | | |
7470 | | /* Past optimization there's no need to distinguish encoding_evex, |
7471 | | encoding_evex512, and encoding_egpr anymore. */ |
7472 | 2.92k | if (pp.encoding == encoding_evex512) |
7473 | 0 | pp.encoding = encoding_evex; |
7474 | 2.92k | else if (pp.encoding == encoding_egpr) |
7475 | 0 | pp.encoding = is_any_vex_encoding (&i.tm) ? encoding_evex |
7476 | 0 | : encoding_default; |
7477 | | |
7478 | | /* Similarly {nf} can now be taken to imply {evex}. */ |
7479 | 2.92k | if (pp.has_nf && pp.encoding == encoding_default) |
7480 | 0 | pp.encoding = encoding_evex; |
7481 | | |
7482 | 2.92k | if (use_unaligned_vector_move) |
7483 | 0 | encode_with_unaligned_vector_move (); |
7484 | | |
7485 | 2.92k | if (!process_suffix (t)) |
7486 | 0 | return; |
7487 | | |
7488 | | /* Check if IP-relative addressing requirements can be satisfied. */ |
7489 | 2.92k | if (is_cpu (&i.tm, CpuPREFETCHI) |
7490 | 2.92k | && !(i.base_reg && i.base_reg->reg_num == RegIP)) |
7491 | 0 | as_warn (_("'%s' only supports RIP-relative address"), insn_name (&i.tm)); |
7492 | | |
7493 | | /* Update operand types and check extended states. */ |
7494 | 7.39k | for (j = 0; j < i.operands; j++) |
7495 | 4.46k | { |
7496 | 4.46k | enum operand_class class = i.types[j].bitfield.class; |
7497 | | |
7498 | 4.46k | i.types[j] = operand_type_and (i.types[j], i.tm.operand_types[j]); |
7499 | 4.46k | switch (i.tm.operand_types[j].bitfield.class) |
7500 | 4.46k | { |
7501 | 1.85k | default: |
7502 | 1.85k | break; |
7503 | 1.85k | case RegMMX: |
7504 | 0 | i.xstate |= xstate_mmx; |
7505 | 0 | break; |
7506 | 0 | case RegMask: |
7507 | 0 | i.xstate |= xstate_mask; |
7508 | 0 | break; |
7509 | 0 | case RegSIMD: |
7510 | 0 | if (i.tm.operand_types[j].bitfield.tmmword) |
7511 | 0 | i.xstate |= xstate_tmm; |
7512 | 0 | else if (i.tm.operand_types[j].bitfield.zmmword |
7513 | 0 | && !i.tm.opcode_modifier.vex |
7514 | 0 | && vector_size >= VSZ512) |
7515 | 0 | i.xstate |= xstate_zmm; |
7516 | 0 | else if (i.tm.operand_types[j].bitfield.ymmword |
7517 | 0 | && vector_size >= VSZ256) |
7518 | 0 | i.xstate |= xstate_ymm; |
7519 | 0 | else if (i.tm.operand_types[j].bitfield.xmmword) |
7520 | 0 | i.xstate |= xstate_xmm; |
7521 | 0 | break; |
7522 | 2.61k | case ClassNone: |
7523 | 2.61k | i.types[j].bitfield.class = class; |
7524 | 2.61k | break; |
7525 | 4.46k | } |
7526 | 4.46k | } |
7527 | | |
7528 | | /* Make still unresolved immediate matches conform to size of immediate |
7529 | | given in i.suffix. */ |
7530 | 2.92k | if (!finalize_imm ()) |
7531 | 0 | return; |
7532 | | |
7533 | 2.92k | if (i.types[0].bitfield.imm1) |
7534 | 0 | i.imm_operands = 0; /* kludge for shift insns. */ |
7535 | | |
7536 | | /* For insns with operands there are more diddles to do to the opcode. */ |
7537 | 2.92k | if (i.operands) |
7538 | 2.62k | { |
7539 | 2.62k | if (!process_operands ()) |
7540 | 0 | return; |
7541 | 2.62k | } |
7542 | 293 | else if (!quiet_warnings && i.tm.opcode_modifier.operandconstraint == UGH) |
7543 | 6 | { |
7544 | | /* UnixWare fsub no args is alias for fsubp, fadd -> faddp, etc. */ |
7545 | 6 | as_warn (_("translating to `%sp'"), insn_name (&i.tm)); |
7546 | 6 | } |
7547 | | |
7548 | 2.92k | if (is_any_vex_encoding (&i.tm)) |
7549 | 35 | { |
7550 | 35 | if (!cpu_arch_flags.bitfield.cpui286) |
7551 | 0 | { |
7552 | 0 | as_bad (_("instruction `%s' isn't supported outside of protected mode."), |
7553 | 0 | insn_name (&i.tm)); |
7554 | 0 | return; |
7555 | 0 | } |
7556 | | |
7557 | | /* Check for explicit REX prefix. */ |
7558 | 35 | if ((i.prefix[REX_PREFIX] |
7559 | 35 | && (i.tm.opcode_space != SPACE_MAP4 |
7560 | | /* To mimic behavior for legacy insns, permit use of REX64 for promoted |
7561 | | legacy instructions. */ |
7562 | 0 | || i.prefix[REX_PREFIX] != (REX_OPCODE | REX_W))) |
7563 | 35 | || pp.rex_encoding) |
7564 | 0 | { |
7565 | 0 | as_bad (_("REX prefix invalid with `%s'"), insn_name (&i.tm)); |
7566 | 0 | return; |
7567 | 0 | } |
7568 | | |
7569 | | /* Check for explicit REX2 prefix. */ |
7570 | 35 | if (pp.rex2_encoding) |
7571 | 0 | { |
7572 | 0 | as_bad (_("{rex2} prefix invalid with `%s'"), insn_name (&i.tm)); |
7573 | 0 | return; |
7574 | 0 | } |
7575 | | |
7576 | 35 | if (is_apx_evex_encoding ()) |
7577 | 0 | { |
7578 | 0 | if (!build_apx_evex_prefix (false)) |
7579 | 0 | return; |
7580 | 0 | } |
7581 | 35 | else if (i.tm.opcode_modifier.vex) |
7582 | 35 | build_vex_prefix (t); |
7583 | 0 | else |
7584 | 0 | build_evex_prefix (); |
7585 | | |
7586 | | /* The individual REX.RXBW bits got consumed. */ |
7587 | 35 | i.rex &= REX_OPCODE; |
7588 | | |
7589 | | /* The rex2 bits got consumed. */ |
7590 | 35 | i.rex2 = 0; |
7591 | 35 | } |
7592 | | |
7593 | | /* Handle conversion of 'int $3' --> special int3 insn. */ |
7594 | 2.92k | if (i.tm.mnem_off == MN_int |
7595 | 2.92k | && i.op[0].imms->X_add_number == 3) |
7596 | 0 | { |
7597 | 0 | i.tm.base_opcode = INT3_OPCODE; |
7598 | 0 | i.imm_operands = 0; |
7599 | 0 | } |
7600 | | |
7601 | 2.92k | if ((i.tm.opcode_modifier.jump == JUMP |
7602 | 2.92k | || i.tm.opcode_modifier.jump == JUMP_BYTE |
7603 | 2.92k | || i.tm.opcode_modifier.jump == JUMP_DWORD) |
7604 | 2.92k | && i.op[0].disps->X_op == O_constant) |
7605 | 34 | { |
7606 | | /* Convert "jmp constant" (and "call constant") to a jump (call) to |
7607 | | the absolute address given by the constant. Since ix86 jumps and |
7608 | | calls are pc relative, we need to generate a reloc. */ |
7609 | 34 | i.op[0].disps->X_add_symbol = &abs_symbol; |
7610 | 34 | i.op[0].disps->X_op = O_symbol; |
7611 | 34 | } |
7612 | | |
7613 | 2.92k | establish_rex (); |
7614 | | |
7615 | 2.92k | insert_lfence_before (last_insn); |
7616 | | |
7617 | | /* We are ready to output the insn. */ |
7618 | 2.92k | output_insn (last_insn); |
7619 | | |
7620 | 2.92k | #ifdef OBJ_ELF |
7621 | | /* PS: SCFI is enabled only for System V AMD64 ABI. The ABI check has been |
7622 | | performed in i386_target_format. */ |
7623 | 2.92k | if (flag_synth_cfi) |
7624 | 0 | { |
7625 | 0 | ginsnS *ginsn; |
7626 | 0 | ginsn = x86_ginsn_new (symbol_temp_new_now (), frch_ginsn_gen_mode ()); |
7627 | 0 | frch_ginsn_data_append (ginsn); |
7628 | 0 | } |
7629 | 2.92k | #endif |
7630 | | |
7631 | 2.92k | insert_lfence_after (); |
7632 | | |
7633 | 2.92k | if (i.tm.opcode_modifier.isprefix) |
7634 | 44 | { |
7635 | 44 | last_insn->kind = last_insn_prefix; |
7636 | 44 | last_insn->name = insn_name (&i.tm); |
7637 | 44 | last_insn->file = as_where (&last_insn->line); |
7638 | 44 | } |
7639 | 2.87k | else |
7640 | 2.87k | last_insn->kind = last_insn_other; |
7641 | 2.92k | } |
7642 | | |
7643 | | void |
7644 | | md_assemble (char *line) |
7645 | 475k | { |
7646 | 475k | i386_assemble (line); |
7647 | 475k | current_templates.start = NULL; |
7648 | 475k | memset (&pp, 0, sizeof (pp)); |
7649 | 475k | } |
7650 | | |
7651 | | /* The Q suffix is generally valid only in 64-bit mode, with very few |
7652 | | exceptions: fild, fistp, fisttp, and cmpxchg8b. Note that for fild |
7653 | | and fisttp only one of their two templates is matched below: That's |
7654 | | sufficient since other relevant attributes are the same between both |
7655 | | respective templates. */ |
7656 | | static INLINE bool q_suffix_allowed(const insn_template *t) |
7657 | 690 | { |
7658 | 690 | return flag_code == CODE_64BIT |
7659 | 690 | || (t->opcode_space == SPACE_BASE |
7660 | 670 | && t->base_opcode == 0xdf |
7661 | 670 | && (t->extension_opcode & 1)) /* fild / fistp / fisttp */ |
7662 | 690 | || t->mnem_off == MN_cmpxchg8b; |
7663 | 690 | } |
7664 | | |
7665 | | static const char * |
7666 | | parse_insn (const char *line, char *mnemonic, enum parse_mode mode) |
7667 | 514k | { |
7668 | 514k | const char *l = line, *token_start = l; |
7669 | 514k | char *mnem_p; |
7670 | 514k | bool pass1 = !current_templates.start; |
7671 | 514k | int supported; |
7672 | 514k | const insn_template *t; |
7673 | 514k | char *dot_p = NULL; |
7674 | | |
7675 | 550k | while (1) |
7676 | 550k | { |
7677 | 550k | const char *split; |
7678 | | |
7679 | 550k | mnem_p = mnemonic; |
7680 | | /* Pseudo-prefixes start with an opening figure brace. */ |
7681 | 550k | if ((*mnem_p = *l) == '{') |
7682 | 4.15k | { |
7683 | 4.15k | ++mnem_p; |
7684 | 4.15k | ++l; |
7685 | 4.15k | if (is_whitespace (*l)) |
7686 | 2.32k | ++l; |
7687 | 4.15k | } |
7688 | 546k | else if (mode == parse_pseudo_prefix) |
7689 | 50 | break; |
7690 | 2.53M | while ((*mnem_p = mnemonic_chars[(unsigned char) *l]) != 0) |
7691 | 1.98M | { |
7692 | 1.98M | if (*mnem_p == '.') |
7693 | 40.9k | dot_p = mnem_p; |
7694 | 1.98M | mnem_p++; |
7695 | 1.98M | if (mnem_p >= mnemonic + MAX_MNEM_SIZE) |
7696 | 4.38k | { |
7697 | 4.38k | too_long: |
7698 | 4.38k | as_bad (_("no such instruction: `%s'"), token_start); |
7699 | 4.38k | return NULL; |
7700 | 4.38k | } |
7701 | 1.98M | l++; |
7702 | 1.98M | } |
7703 | 546k | split = l; |
7704 | 546k | if (is_whitespace (*l)) |
7705 | 137k | ++l; |
7706 | | /* Pseudo-prefixes end with a closing figure brace. */ |
7707 | 546k | if (*mnemonic == '{' && *l == '}') |
7708 | 58 | { |
7709 | 58 | *mnem_p++ = *l++; |
7710 | 58 | if (mnem_p >= mnemonic + MAX_MNEM_SIZE) |
7711 | 0 | goto too_long; |
7712 | 58 | *mnem_p = '\0'; |
7713 | | |
7714 | 58 | if (is_whitespace (*l)) |
7715 | 48 | ++l; |
7716 | 58 | } |
7717 | 546k | else if (l == split |
7718 | 546k | && *l != END_OF_INSN |
7719 | 546k | && (intel_syntax |
7720 | 295k | || (*l != PREFIX_SEPARATOR && *l != ','))) |
7721 | 283k | { |
7722 | 283k | if (mode != parse_all) |
7723 | 3.24k | break; |
7724 | 280k | as_bad (_("invalid character %s in mnemonic"), |
7725 | 280k | output_invalid (*split)); |
7726 | 280k | return NULL; |
7727 | 283k | } |
7728 | 262k | if (token_start == l) |
7729 | 2.75k | { |
7730 | 2.75k | if (!intel_syntax && *l == PREFIX_SEPARATOR) |
7731 | 23 | as_bad (_("expecting prefix; got nothing")); |
7732 | 2.72k | else |
7733 | 2.72k | as_bad (_("expecting mnemonic; got nothing")); |
7734 | 2.75k | return NULL; |
7735 | 2.75k | } |
7736 | | |
7737 | | /* Look up instruction (or prefix) via hash table. */ |
7738 | 259k | op_lookup (mnemonic); |
7739 | | |
7740 | 259k | if (*l != END_OF_INSN |
7741 | 259k | && current_templates.start |
7742 | 259k | && current_templates.start->opcode_modifier.isprefix) |
7743 | 38.5k | { |
7744 | 38.5k | supported = cpu_flags_match (current_templates.start); |
7745 | 38.5k | if (!(supported & CPU_FLAGS_64BIT_MATCH)) |
7746 | 2.66k | { |
7747 | 2.66k | as_bad ((flag_code != CODE_64BIT |
7748 | 2.66k | ? _("`%s' is only supported in 64-bit mode") |
7749 | 2.66k | : _("`%s' is not supported in 64-bit mode")), |
7750 | 2.66k | insn_name (current_templates.start)); |
7751 | 2.66k | return NULL; |
7752 | 2.66k | } |
7753 | 35.8k | if (supported != CPU_FLAGS_PERFECT_MATCH) |
7754 | 34 | { |
7755 | 34 | as_bad (_("`%s' is not supported on `%s%s'"), |
7756 | 34 | insn_name (current_templates.start), |
7757 | 34 | cpu_arch_name ? cpu_arch_name : default_arch, |
7758 | 34 | cpu_sub_arch_name ? cpu_sub_arch_name : ""); |
7759 | 34 | return NULL; |
7760 | 34 | } |
7761 | | /* If we are in 16-bit mode, do not allow addr16 or data16. |
7762 | | Similarly, in 32-bit mode, do not allow addr32 or data32. */ |
7763 | 35.8k | if ((current_templates.start->opcode_modifier.size == SIZE16 |
7764 | 35.8k | || current_templates.start->opcode_modifier.size == SIZE32) |
7765 | 35.8k | && flag_code != CODE_64BIT |
7766 | 35.8k | && ((current_templates.start->opcode_modifier.size == SIZE32) |
7767 | 260 | ^ (flag_code == CODE_16BIT))) |
7768 | 228 | { |
7769 | 228 | as_bad (_("redundant %s prefix"), |
7770 | 228 | insn_name (current_templates.start)); |
7771 | 228 | return NULL; |
7772 | 228 | } |
7773 | | |
7774 | 35.6k | if (current_templates.start->base_opcode == PSEUDO_PREFIX) |
7775 | 50 | { |
7776 | | /* Handle pseudo prefixes. */ |
7777 | 50 | switch (current_templates.start->extension_opcode) |
7778 | 50 | { |
7779 | 0 | case Prefix_Disp8: |
7780 | | /* {disp8} */ |
7781 | 0 | pp.disp_encoding = disp_encoding_8bit; |
7782 | 0 | break; |
7783 | 16 | case Prefix_Disp16: |
7784 | | /* {disp16} */ |
7785 | 16 | pp.disp_encoding = disp_encoding_16bit; |
7786 | 16 | break; |
7787 | 32 | case Prefix_Disp32: |
7788 | | /* {disp32} */ |
7789 | 32 | pp.disp_encoding = disp_encoding_32bit; |
7790 | 32 | break; |
7791 | 0 | case Prefix_Load: |
7792 | | /* {load} */ |
7793 | 0 | pp.dir_encoding = dir_encoding_load; |
7794 | 0 | break; |
7795 | 0 | case Prefix_Store: |
7796 | | /* {store} */ |
7797 | 0 | pp.dir_encoding = dir_encoding_store; |
7798 | 0 | break; |
7799 | 0 | case Prefix_VEX: |
7800 | | /* {vex} */ |
7801 | 0 | pp.encoding = encoding_vex; |
7802 | 0 | break; |
7803 | 0 | case Prefix_VEX3: |
7804 | | /* {vex3} */ |
7805 | 0 | pp.encoding = encoding_vex3; |
7806 | 0 | break; |
7807 | 0 | case Prefix_EVEX: |
7808 | | /* {evex} */ |
7809 | 0 | pp.encoding = encoding_evex; |
7810 | 0 | break; |
7811 | 0 | case Prefix_REX: |
7812 | | /* {rex} */ |
7813 | 0 | pp.rex_encoding = true; |
7814 | 0 | break; |
7815 | 0 | case Prefix_REX2: |
7816 | | /* {rex2} */ |
7817 | 0 | pp.rex2_encoding = true; |
7818 | 0 | break; |
7819 | 0 | case Prefix_NF: |
7820 | | /* {nf} */ |
7821 | 0 | pp.has_nf = true; |
7822 | 0 | break; |
7823 | 2 | case Prefix_NoOptimize: |
7824 | | /* {nooptimize} */ |
7825 | 2 | pp.no_optimize = true; |
7826 | 2 | break; |
7827 | 0 | case Prefix_NoImm8s: |
7828 | | /* {noimm8s} */ |
7829 | 0 | pp.no_imm8s = true; |
7830 | 0 | break; |
7831 | 0 | default: |
7832 | 0 | abort (); |
7833 | 50 | } |
7834 | 50 | if (pp.has_nf |
7835 | 50 | && pp.encoding != encoding_default |
7836 | 50 | && pp.encoding != encoding_evex) |
7837 | 0 | { |
7838 | 0 | as_bad (_("{nf} cannot be combined with {vex}/{vex3}")); |
7839 | 0 | return NULL; |
7840 | 0 | } |
7841 | 50 | } |
7842 | 35.5k | else |
7843 | 35.5k | { |
7844 | | /* Add prefix, checking for repeated prefixes. */ |
7845 | 35.5k | switch (add_prefix (current_templates.start->base_opcode)) |
7846 | 35.5k | { |
7847 | 0 | case PREFIX_EXIST: |
7848 | 0 | return NULL; |
7849 | 0 | case PREFIX_DS: |
7850 | 0 | if (is_cpu (current_templates.start, CpuIBT)) |
7851 | 0 | i.notrack_prefix = insn_name (current_templates.start); |
7852 | 0 | break; |
7853 | 13 | case PREFIX_REP: |
7854 | 13 | if (is_cpu (current_templates.start, CpuHLE)) |
7855 | 0 | i.hle_prefix = insn_name (current_templates.start); |
7856 | 13 | else if (is_cpu (current_templates.start, CpuMPX)) |
7857 | 0 | i.bnd_prefix = insn_name (current_templates.start); |
7858 | 13 | else |
7859 | 13 | i.rep_prefix = insn_name (current_templates.start); |
7860 | 13 | break; |
7861 | 35.5k | default: |
7862 | 35.5k | break; |
7863 | 35.5k | } |
7864 | 35.5k | } |
7865 | | /* Skip past PREFIX_SEPARATOR and reset token_start. */ |
7866 | 35.6k | l += (!intel_syntax && *l == PREFIX_SEPARATOR); |
7867 | 35.6k | if (is_whitespace (*l)) |
7868 | 8 | ++l; |
7869 | 35.6k | token_start = l; |
7870 | 35.6k | } |
7871 | 221k | else |
7872 | 221k | break; |
7873 | 259k | } |
7874 | | |
7875 | 224k | if (mode != parse_all) |
7876 | 4.01k | return token_start; |
7877 | | |
7878 | 220k | if (!current_templates.start) |
7879 | 101k | { |
7880 | | #ifdef TE_SOLARIS |
7881 | | /* Sun specifies an alternative form for CMOVcc: Size suffix (if any) |
7882 | | first, then a dot, then the condition code mnemonic. */ |
7883 | | if ((mnemonic + 4 == dot_p && !memcmp (mnemonic, "cmov", 4)) |
7884 | | /* While doc doesn't say so, gcc assumes it: Same for FCMOVcc, |
7885 | | except that there's no size suffix to care about. */ |
7886 | | || (mnemonic + 5 == dot_p && !memcmp (mnemonic, "fcmov", 5))) |
7887 | | { |
7888 | | /* Simply strip the dot. */ |
7889 | | memmove (dot_p, dot_p + 1, mnem_p - dot_p); |
7890 | | dot_p = mnem_p - 1; |
7891 | | } |
7892 | | else if (!intel_syntax |
7893 | | && mnemonic + 5 == dot_p |
7894 | | && !memcmp (mnemonic, "cmov", 4) |
7895 | | && strchr ("lqw", TOLOWER (dot_p[-1]))) |
7896 | | { |
7897 | | /* Strip the dot, while moving the suffix. */ |
7898 | | char suffix = dot_p[-1]; |
7899 | | |
7900 | | memmove (dot_p - 1, dot_p + 1, mnem_p - dot_p); |
7901 | | mnem_p[-2] = suffix; |
7902 | | dot_p = mnem_p - 1; |
7903 | | } |
7904 | | else |
7905 | | #endif |
7906 | | /* Deprecated functionality (new code should use pseudo-prefixes instead): |
7907 | | Check if we should swap operand or force 32bit displacement in |
7908 | | encoding. */ |
7909 | 101k | if (mnem_p - 2 == dot_p && dot_p[1] == 's') |
7910 | 808 | { |
7911 | 808 | if (pp.dir_encoding == dir_encoding_default) |
7912 | 808 | pp.dir_encoding = dir_encoding_swap; |
7913 | 0 | else |
7914 | 0 | as_warn (_("ignoring `.s' suffix due to earlier `{%s}'"), |
7915 | 0 | pp.dir_encoding == dir_encoding_load ? "load" : "store"); |
7916 | 808 | } |
7917 | 101k | else if (mnem_p - 3 == dot_p |
7918 | 101k | && dot_p[1] == 'd' |
7919 | 101k | && dot_p[2] == '8') |
7920 | 0 | { |
7921 | 0 | if (pp.disp_encoding == disp_encoding_default) |
7922 | 0 | pp.disp_encoding = disp_encoding_8bit; |
7923 | 0 | else if (pp.disp_encoding != disp_encoding_8bit) |
7924 | 0 | as_warn (_("ignoring `.d8' suffix due to earlier `{disp<N>}'")); |
7925 | 0 | } |
7926 | 101k | else if (mnem_p - 4 == dot_p |
7927 | 101k | && dot_p[1] == 'd' |
7928 | 101k | && dot_p[2] == '3' |
7929 | 101k | && dot_p[3] == '2') |
7930 | 0 | { |
7931 | 0 | if (pp.disp_encoding == disp_encoding_default) |
7932 | 0 | pp.disp_encoding = disp_encoding_32bit; |
7933 | 0 | else if (pp.disp_encoding != disp_encoding_32bit) |
7934 | 0 | as_warn (_("ignoring `.d32' suffix due to earlier `{disp<N>}'")); |
7935 | 0 | } |
7936 | 101k | else |
7937 | 101k | goto check_suffix; |
7938 | 808 | mnem_p = dot_p; |
7939 | 808 | *dot_p = '\0'; |
7940 | 808 | op_lookup (mnemonic); |
7941 | 808 | } |
7942 | | |
7943 | 119k | if (!current_templates.start || !pass1) |
7944 | 34.3k | { |
7945 | 34.3k | current_templates.start = NULL; |
7946 | | |
7947 | 135k | check_suffix: |
7948 | 135k | if (mnem_p > mnemonic) |
7949 | 135k | { |
7950 | | /* See if we can get a match by trimming off a suffix. */ |
7951 | 135k | switch (mnem_p[-1]) |
7952 | 135k | { |
7953 | 578 | case WORD_MNEM_SUFFIX: |
7954 | 578 | if (intel_syntax && (intel_float_operand (mnemonic) & 2)) |
7955 | 0 | i.suffix = SHORT_MNEM_SUFFIX; |
7956 | 578 | else |
7957 | | /* Fall through. */ |
7958 | 4.81k | case BYTE_MNEM_SUFFIX: |
7959 | 5.22k | case QWORD_MNEM_SUFFIX: |
7960 | 5.22k | i.suffix = mnem_p[-1]; |
7961 | 5.22k | mnem_p[-1] = '\0'; |
7962 | 5.22k | op_lookup (mnemonic); |
7963 | 5.22k | break; |
7964 | 39.6k | case SHORT_MNEM_SUFFIX: |
7965 | 41.8k | case LONG_MNEM_SUFFIX: |
7966 | 41.8k | if (!intel_syntax) |
7967 | 41.8k | { |
7968 | 41.8k | i.suffix = mnem_p[-1]; |
7969 | 41.8k | mnem_p[-1] = '\0'; |
7970 | 41.8k | op_lookup (mnemonic); |
7971 | 41.8k | } |
7972 | 41.8k | break; |
7973 | | |
7974 | | /* Intel Syntax. */ |
7975 | 2.52k | case 'd': |
7976 | 2.52k | if (intel_syntax) |
7977 | 0 | { |
7978 | 0 | if (intel_float_operand (mnemonic) == 1) |
7979 | 0 | i.suffix = SHORT_MNEM_SUFFIX; |
7980 | 0 | else |
7981 | 0 | i.suffix = LONG_MNEM_SUFFIX; |
7982 | 0 | mnem_p[-1] = '\0'; |
7983 | 0 | op_lookup (mnemonic); |
7984 | 0 | } |
7985 | | /* For compatibility reasons accept MOVSD and CMPSD without |
7986 | | operands even in AT&T mode. */ |
7987 | 2.52k | else if (*l == END_OF_INSN) |
7988 | 1.78k | { |
7989 | 1.78k | mnem_p[-1] = '\0'; |
7990 | 1.78k | op_lookup (mnemonic); |
7991 | 1.78k | if (current_templates.start != NULL |
7992 | | /* MOVS or CMPS */ |
7993 | 1.78k | && (current_templates.start->base_opcode | 2) == 0xa6 |
7994 | 1.78k | && current_templates.start->opcode_space |
7995 | 0 | == SPACE_BASE |
7996 | 1.78k | && mnem_p[-2] == 's') |
7997 | 0 | { |
7998 | 0 | as_warn (_("found `%sd'; assuming `%sl' was meant"), |
7999 | 0 | mnemonic, mnemonic); |
8000 | 0 | i.suffix = LONG_MNEM_SUFFIX; |
8001 | 0 | } |
8002 | 1.78k | else |
8003 | 1.78k | { |
8004 | 1.78k | current_templates.start = NULL; |
8005 | 1.78k | mnem_p[-1] = 'd'; |
8006 | 1.78k | } |
8007 | 1.78k | } |
8008 | 2.52k | break; |
8009 | 135k | } |
8010 | 135k | } |
8011 | | |
8012 | 135k | if (!current_templates.start) |
8013 | 134k | { |
8014 | 134k | if (pass1) |
8015 | 100k | as_bad (_("no such instruction: `%s'"), token_start); |
8016 | 134k | return NULL; |
8017 | 134k | } |
8018 | 135k | } |
8019 | | |
8020 | | /* Handle SCC OSZC flgs. */ |
8021 | 85.9k | if (current_templates.start->opcode_modifier.operandconstraint == SCC) |
8022 | 26 | { |
8023 | 26 | int length = check_Scc_OszcOperations (l); |
8024 | 26 | if (length < 0) |
8025 | 0 | return NULL; |
8026 | 26 | l += length; |
8027 | 26 | } |
8028 | | |
8029 | 85.9k | if ((current_templates.start->opcode_modifier.jump == JUMP |
8030 | 85.9k | || current_templates.start->opcode_modifier.jump == JUMP_BYTE) |
8031 | 85.9k | && *l == ',') |
8032 | 136 | { |
8033 | | /* Check for a branch hint. We allow ",pt" and ",pn" for |
8034 | | predict taken and predict not taken respectively. |
8035 | | I'm not sure that branch hints actually do anything on loop |
8036 | | and jcxz insns (JumpByte) for current Pentium4 chips. They |
8037 | | may work in the future and it doesn't hurt to accept them |
8038 | | now. */ |
8039 | 136 | token_start = l++; |
8040 | 136 | if (is_whitespace (*l)) |
8041 | 0 | ++l; |
8042 | 136 | if (TOLOWER (*l) == 'p' && ISALPHA (l[1]) |
8043 | 136 | && (l[2] == END_OF_INSN || is_whitespace (l[2]))) |
8044 | 0 | { |
8045 | 0 | if (TOLOWER (l[1]) == 't') |
8046 | 0 | { |
8047 | 0 | if (!add_prefix (DS_PREFIX_OPCODE)) |
8048 | 0 | return NULL; |
8049 | 0 | l += 2; |
8050 | 0 | } |
8051 | 0 | else if (TOLOWER (l[1]) == 'n') |
8052 | 0 | { |
8053 | 0 | if (!add_prefix (CS_PREFIX_OPCODE)) |
8054 | 0 | return NULL; |
8055 | 0 | l += 2; |
8056 | 0 | } |
8057 | 0 | else |
8058 | 0 | l = token_start; |
8059 | 0 | } |
8060 | 136 | else |
8061 | 136 | l = token_start; |
8062 | 136 | } |
8063 | | /* Any other comma loses. */ |
8064 | 85.9k | if (*l == ',') |
8065 | 383 | { |
8066 | 383 | as_bad (_("invalid character %s in mnemonic"), |
8067 | 383 | output_invalid (*l)); |
8068 | 383 | return NULL; |
8069 | 383 | } |
8070 | | |
8071 | | /* Check if instruction is supported on specified architecture. */ |
8072 | 85.5k | supported = 0; |
8073 | 135k | for (t = current_templates.start; t < current_templates.end; ++t) |
8074 | 133k | { |
8075 | 133k | supported |= cpu_flags_match (t); |
8076 | | |
8077 | 133k | if (i.suffix == QWORD_MNEM_SUFFIX && !q_suffix_allowed (t)) |
8078 | 670 | supported &= ~CPU_FLAGS_64BIT_MATCH; |
8079 | | |
8080 | 133k | if (supported == CPU_FLAGS_PERFECT_MATCH) |
8081 | 84.3k | return l; |
8082 | 133k | } |
8083 | | |
8084 | 1.25k | if (pass1) |
8085 | 1.23k | { |
8086 | 1.23k | if (supported & CPU_FLAGS_64BIT_MATCH) |
8087 | 1.07k | i.error = unsupported_on_arch; |
8088 | 163 | else |
8089 | 163 | i.error = unsupported_64bit; |
8090 | 1.23k | } |
8091 | | |
8092 | 1.25k | return NULL; |
8093 | 85.5k | } |
8094 | | |
8095 | | static char * |
8096 | | parse_operands (char *l, const char *mnemonic) |
8097 | 84.4k | { |
8098 | 84.4k | char *token_start; |
8099 | | |
8100 | | /* 1 if operand is pending after ','. */ |
8101 | 84.4k | unsigned int expecting_operand = 0; |
8102 | | |
8103 | 128k | while (*l != END_OF_INSN) |
8104 | 51.9k | { |
8105 | | /* Non-zero if operand parens not balanced. */ |
8106 | 51.9k | unsigned int paren_not_balanced = 0; |
8107 | | /* True if inside double quotes. */ |
8108 | 51.9k | bool in_quotes = false; |
8109 | | |
8110 | | /* Skip optional white space before operand. */ |
8111 | 51.9k | if (is_whitespace (*l)) |
8112 | 1.79k | ++l; |
8113 | 51.9k | if (!is_operand_char (*l) && *l != END_OF_INSN && *l != '"') |
8114 | 1.16k | { |
8115 | 1.16k | as_bad (_("invalid character %s before operand %d"), |
8116 | 1.16k | output_invalid (*l), |
8117 | 1.16k | i.operands + 1); |
8118 | 1.16k | return NULL; |
8119 | 1.16k | } |
8120 | 50.7k | token_start = l; /* After white space. */ |
8121 | 1.08M | while (in_quotes || paren_not_balanced || *l != ',') |
8122 | 1.07M | { |
8123 | 1.07M | if (*l == END_OF_INSN) |
8124 | 42.6k | { |
8125 | 42.6k | if (in_quotes) |
8126 | 105 | { |
8127 | 105 | as_bad (_("unbalanced double quotes in operand %d."), |
8128 | 105 | i.operands + 1); |
8129 | 105 | return NULL; |
8130 | 105 | } |
8131 | 42.5k | if (paren_not_balanced) |
8132 | 1.61k | { |
8133 | 1.61k | know (!intel_syntax); |
8134 | 1.61k | as_bad (_("unbalanced parenthesis in operand %d."), |
8135 | 1.61k | i.operands + 1); |
8136 | 1.61k | return NULL; |
8137 | 1.61k | } |
8138 | 40.9k | else |
8139 | 40.9k | break; /* we are done */ |
8140 | 42.5k | } |
8141 | 1.03M | else if (*l == '\\' && l[1] == '"') |
8142 | 6 | ++l; |
8143 | 1.03M | else if (*l == '"') |
8144 | 493 | in_quotes = !in_quotes; |
8145 | 1.03M | else if (!in_quotes && !is_operand_char (*l) && !is_whitespace (*l)) |
8146 | 4.59k | { |
8147 | 4.59k | as_bad (_("invalid character %s in operand %d"), |
8148 | 4.59k | output_invalid (*l), |
8149 | 4.59k | i.operands + 1); |
8150 | 4.59k | return NULL; |
8151 | 4.59k | } |
8152 | 1.03M | if (!intel_syntax && !in_quotes) |
8153 | 1.02M | { |
8154 | 1.02M | if (*l == '(') |
8155 | 17.8k | ++paren_not_balanced; |
8156 | 1.02M | if (*l == ')') |
8157 | 427 | --paren_not_balanced; |
8158 | 1.02M | } |
8159 | 1.03M | l++; |
8160 | 1.03M | } |
8161 | 44.4k | if (l != token_start) |
8162 | 44.4k | { /* Yes, we've read in another operand. */ |
8163 | 44.4k | unsigned int operand_ok; |
8164 | 44.4k | this_operand = i.operands++; |
8165 | 44.4k | if (i.operands > MAX_OPERANDS) |
8166 | 0 | { |
8167 | 0 | as_bad (_("spurious operands; (%d operands/instruction max)"), |
8168 | 0 | MAX_OPERANDS); |
8169 | 0 | return NULL; |
8170 | 0 | } |
8171 | 44.4k | i.types[this_operand].bitfield.unspecified = 1; |
8172 | | /* Now parse operand adding info to 'i' as we go along. */ |
8173 | 44.4k | END_STRING_AND_SAVE (l); |
8174 | | |
8175 | 44.4k | if (i.mem_operands > 1) |
8176 | 26 | { |
8177 | 26 | as_bad (_("too many memory references for `%s'"), |
8178 | 26 | mnemonic); |
8179 | 26 | return 0; |
8180 | 26 | } |
8181 | | |
8182 | 44.4k | if (intel_syntax) |
8183 | 0 | operand_ok = |
8184 | 0 | i386_intel_operand (token_start, |
8185 | 0 | intel_float_operand (mnemonic)); |
8186 | 44.4k | else |
8187 | 44.4k | operand_ok = i386_att_operand (token_start); |
8188 | | |
8189 | 44.4k | RESTORE_END_STRING (l); |
8190 | 44.4k | if (!operand_ok) |
8191 | 796 | return NULL; |
8192 | 44.4k | } |
8193 | 33 | else |
8194 | 33 | { |
8195 | 33 | if (expecting_operand) |
8196 | 20 | { |
8197 | 44 | expecting_operand_after_comma: |
8198 | 44 | as_bad (_("expecting operand after ','; got nothing")); |
8199 | 44 | return NULL; |
8200 | 20 | } |
8201 | 13 | if (*l == ',') |
8202 | 6 | { |
8203 | 6 | as_bad (_("expecting operand before ','; got nothing")); |
8204 | 6 | return NULL; |
8205 | 6 | } |
8206 | 13 | } |
8207 | | |
8208 | | /* Now *l must be either ',' or END_OF_INSN. */ |
8209 | 43.6k | if (*l == ',') |
8210 | 3.42k | { |
8211 | 3.42k | if (*++l == END_OF_INSN) |
8212 | 24 | { |
8213 | | /* Just skip it, if it's \n complain. */ |
8214 | 24 | goto expecting_operand_after_comma; |
8215 | 24 | } |
8216 | 3.40k | expecting_operand = 1; |
8217 | 3.40k | } |
8218 | 43.6k | } |
8219 | 76.0k | return l; |
8220 | 84.4k | } |
8221 | | |
8222 | | static void |
8223 | | copy_operand (unsigned int to, unsigned int from) |
8224 | 0 | { |
8225 | 0 | i.types[to] = i.types[from]; |
8226 | 0 | i.tm.operand_types[to] = i.tm.operand_types[from]; |
8227 | 0 | i.flags[to] = i.flags[from]; |
8228 | 0 | i.op[to] = i.op[from]; |
8229 | 0 | i.reloc[to] = i.reloc[from]; |
8230 | 0 | i.imm_bits[to] = i.imm_bits[from]; |
8231 | | /* Note: i.mask and i.broadcast aren't handled here, as what (if |
8232 | | anything) to do there depends on context. */ |
8233 | 0 | } |
8234 | | |
8235 | | static void |
8236 | | swap_2_operands (unsigned int xchg1, unsigned int xchg2) |
8237 | 0 | { |
8238 | 0 | union i386_op temp_op; |
8239 | 0 | i386_operand_type temp_type; |
8240 | 0 | unsigned int temp_flags; |
8241 | 0 | enum bfd_reloc_code_real temp_reloc; |
8242 | |
|
8243 | 0 | temp_type = i.types[xchg2]; |
8244 | 0 | i.types[xchg2] = i.types[xchg1]; |
8245 | 0 | i.types[xchg1] = temp_type; |
8246 | |
|
8247 | 0 | temp_flags = i.flags[xchg2]; |
8248 | 0 | i.flags[xchg2] = i.flags[xchg1]; |
8249 | 0 | i.flags[xchg1] = temp_flags; |
8250 | |
|
8251 | 0 | temp_op = i.op[xchg2]; |
8252 | 0 | i.op[xchg2] = i.op[xchg1]; |
8253 | 0 | i.op[xchg1] = temp_op; |
8254 | |
|
8255 | 0 | temp_reloc = i.reloc[xchg2]; |
8256 | 0 | i.reloc[xchg2] = i.reloc[xchg1]; |
8257 | 0 | i.reloc[xchg1] = temp_reloc; |
8258 | |
|
8259 | 0 | temp_flags = i.imm_bits[xchg2]; |
8260 | 0 | i.imm_bits[xchg2] = i.imm_bits[xchg1]; |
8261 | 0 | i.imm_bits[xchg1] = temp_flags; |
8262 | |
|
8263 | 0 | if (i.mask.reg) |
8264 | 0 | { |
8265 | 0 | if (i.mask.operand == xchg1) |
8266 | 0 | i.mask.operand = xchg2; |
8267 | 0 | else if (i.mask.operand == xchg2) |
8268 | 0 | i.mask.operand = xchg1; |
8269 | 0 | } |
8270 | 0 | if (i.broadcast.type || i.broadcast.bytes) |
8271 | 0 | { |
8272 | 0 | if (i.broadcast.operand == xchg1) |
8273 | 0 | i.broadcast.operand = xchg2; |
8274 | 0 | else if (i.broadcast.operand == xchg2) |
8275 | 0 | i.broadcast.operand = xchg1; |
8276 | 0 | } |
8277 | 0 | } |
8278 | | |
8279 | | static void |
8280 | | swap_operands (void) |
8281 | 0 | { |
8282 | 0 | switch (i.operands) |
8283 | 0 | { |
8284 | 0 | case 5: |
8285 | 0 | case 4: |
8286 | 0 | swap_2_operands (1, i.operands - 2); |
8287 | | /* Fall through. */ |
8288 | 0 | case 3: |
8289 | 0 | case 2: |
8290 | 0 | swap_2_operands (0, i.operands - 1); |
8291 | 0 | break; |
8292 | 0 | default: |
8293 | 0 | abort (); |
8294 | 0 | } |
8295 | | |
8296 | 0 | if (i.mem_operands == 2) |
8297 | 0 | { |
8298 | 0 | const reg_entry *temp_seg; |
8299 | 0 | temp_seg = i.seg[0]; |
8300 | 0 | i.seg[0] = i.seg[1]; |
8301 | 0 | i.seg[1] = temp_seg; |
8302 | 0 | } |
8303 | 0 | } |
8304 | | |
8305 | | /* Try to ensure constant immediates are represented in the smallest |
8306 | | opcode possible. */ |
8307 | | static void |
8308 | | optimize_imm (void) |
8309 | 4.68k | { |
8310 | 4.68k | char guess_suffix = 0; |
8311 | 4.68k | int op; |
8312 | | |
8313 | 4.68k | if (i.suffix) |
8314 | 234 | guess_suffix = i.suffix; |
8315 | 4.44k | else if (i.reg_operands) |
8316 | 0 | { |
8317 | | /* Figure out a suffix from the last register operand specified. |
8318 | | We can't do this properly yet, i.e. excluding special register |
8319 | | instances, but the following works for instructions with |
8320 | | immediates. In any case, we can't set i.suffix yet. */ |
8321 | 0 | for (op = i.operands; --op >= 0;) |
8322 | 0 | if (i.types[op].bitfield.class != Reg) |
8323 | 0 | continue; |
8324 | 0 | else if (i.types[op].bitfield.byte) |
8325 | 0 | { |
8326 | 0 | guess_suffix = BYTE_MNEM_SUFFIX; |
8327 | 0 | break; |
8328 | 0 | } |
8329 | 0 | else if (i.types[op].bitfield.word) |
8330 | 0 | { |
8331 | 0 | guess_suffix = WORD_MNEM_SUFFIX; |
8332 | 0 | break; |
8333 | 0 | } |
8334 | 0 | else if (i.types[op].bitfield.dword) |
8335 | 0 | { |
8336 | 0 | guess_suffix = LONG_MNEM_SUFFIX; |
8337 | 0 | break; |
8338 | 0 | } |
8339 | 0 | else if (i.types[op].bitfield.qword) |
8340 | 0 | { |
8341 | 0 | guess_suffix = QWORD_MNEM_SUFFIX; |
8342 | 0 | break; |
8343 | 0 | } |
8344 | 0 | } |
8345 | 4.44k | else if ((flag_code == CODE_16BIT) |
8346 | 4.44k | ^ (i.prefix[DATA_PREFIX] != 0 && !(i.prefix[REX_PREFIX] & REX_W))) |
8347 | 289 | guess_suffix = WORD_MNEM_SUFFIX; |
8348 | 4.15k | else if (flag_code != CODE_64BIT |
8349 | 4.15k | || (!(i.prefix[REX_PREFIX] & REX_W) |
8350 | | /* A more generic (but also more involved) way of dealing |
8351 | | with the special case(s) would be to go look for |
8352 | | DefaultSize attributes on any of the templates. */ |
8353 | 1.83k | && current_templates.start->mnem_off != MN_push |
8354 | 1.83k | && current_templates.start->mnem_off != MN_jmpabs)) |
8355 | 4.15k | guess_suffix = LONG_MNEM_SUFFIX; |
8356 | | |
8357 | 11.3k | for (op = i.operands; --op >= 0;) |
8358 | 6.62k | if (operand_type_check (i.types[op], imm)) |
8359 | 4.68k | { |
8360 | 4.68k | switch (i.op[op].imms->X_op) |
8361 | 4.68k | { |
8362 | 2.45k | case O_constant: |
8363 | | /* If a suffix is given, this operand may be shortened. */ |
8364 | 2.45k | switch (guess_suffix) |
8365 | 2.45k | { |
8366 | 2.07k | case LONG_MNEM_SUFFIX: |
8367 | 2.07k | i.types[op].bitfield.imm32 = 1; |
8368 | 2.07k | i.types[op].bitfield.imm64 = 1; |
8369 | 2.07k | break; |
8370 | 220 | case WORD_MNEM_SUFFIX: |
8371 | 220 | i.types[op].bitfield.imm16 = 1; |
8372 | 220 | i.types[op].bitfield.imm32 = 1; |
8373 | 220 | i.types[op].bitfield.imm32s = 1; |
8374 | 220 | i.types[op].bitfield.imm64 = 1; |
8375 | 220 | break; |
8376 | 163 | case BYTE_MNEM_SUFFIX: |
8377 | 163 | i.types[op].bitfield.imm8 = 1; |
8378 | 163 | i.types[op].bitfield.imm8s = 1; |
8379 | 163 | i.types[op].bitfield.imm16 = 1; |
8380 | 163 | i.types[op].bitfield.imm32 = 1; |
8381 | 163 | i.types[op].bitfield.imm32s = 1; |
8382 | 163 | i.types[op].bitfield.imm64 = 1; |
8383 | 163 | break; |
8384 | 2.45k | } |
8385 | | |
8386 | | /* If this operand is at most 16 bits, convert it |
8387 | | to a signed 16 bit number before trying to see |
8388 | | whether it will fit in an even smaller size. |
8389 | | This allows a 16-bit operand such as $0xffe0 to |
8390 | | be recognised as within Imm8S range. */ |
8391 | 2.45k | if ((i.types[op].bitfield.imm16) |
8392 | 2.45k | && fits_in_unsigned_word (i.op[op].imms->X_add_number)) |
8393 | 300 | { |
8394 | 300 | i.op[op].imms->X_add_number = ((i.op[op].imms->X_add_number |
8395 | 300 | ^ 0x8000) - 0x8000); |
8396 | 300 | } |
8397 | 2.45k | #ifdef BFD64 |
8398 | | /* Store 32-bit immediate in 64-bit for 64-bit BFD. */ |
8399 | 2.45k | if ((i.types[op].bitfield.imm32) |
8400 | 2.45k | && fits_in_unsigned_long (i.op[op].imms->X_add_number)) |
8401 | 1.05k | { |
8402 | 1.05k | i.op[op].imms->X_add_number = ((i.op[op].imms->X_add_number |
8403 | 1.05k | ^ ((offsetT) 1 << 31)) |
8404 | 1.05k | - ((offsetT) 1 << 31)); |
8405 | 1.05k | } |
8406 | 2.45k | #endif |
8407 | 2.45k | i.types[op] |
8408 | 2.45k | = operand_type_or (i.types[op], |
8409 | 2.45k | smallest_imm_type (i.op[op].imms->X_add_number)); |
8410 | | |
8411 | | /* We must avoid matching of Imm32 templates when 64bit |
8412 | | only immediate is available. */ |
8413 | 2.45k | if (guess_suffix == QWORD_MNEM_SUFFIX) |
8414 | 1 | i.types[op].bitfield.imm32 = 0; |
8415 | 2.45k | break; |
8416 | | |
8417 | 0 | case O_absent: |
8418 | 0 | case O_register: |
8419 | 0 | abort (); |
8420 | | |
8421 | | /* Symbols and expressions. */ |
8422 | 2.22k | default: |
8423 | | /* Convert symbolic operand to proper sizes for matching, but don't |
8424 | | prevent matching a set of insns that only supports sizes other |
8425 | | than those matching the insn suffix. */ |
8426 | 2.22k | { |
8427 | 2.22k | i386_operand_type mask, allowed; |
8428 | 2.22k | const insn_template *t = current_templates.start; |
8429 | | |
8430 | 2.22k | operand_type_set (&mask, 0); |
8431 | 2.22k | switch (guess_suffix) |
8432 | 2.22k | { |
8433 | 1 | case QWORD_MNEM_SUFFIX: |
8434 | 1 | mask.bitfield.imm64 = 1; |
8435 | 1 | mask.bitfield.imm32s = 1; |
8436 | 1 | break; |
8437 | 2.09k | case LONG_MNEM_SUFFIX: |
8438 | 2.09k | mask.bitfield.imm32 = 1; |
8439 | 2.09k | break; |
8440 | 69 | case WORD_MNEM_SUFFIX: |
8441 | 69 | mask.bitfield.imm16 = 1; |
8442 | 69 | break; |
8443 | 39 | case BYTE_MNEM_SUFFIX: |
8444 | 39 | mask.bitfield.imm8 = 1; |
8445 | 39 | break; |
8446 | 26 | default: |
8447 | 26 | break; |
8448 | 2.22k | } |
8449 | | |
8450 | 2.22k | allowed = operand_type_and (t->operand_types[op], mask); |
8451 | 22.0k | while (++t < current_templates.end) |
8452 | 19.8k | { |
8453 | 19.8k | allowed = operand_type_or (allowed, t->operand_types[op]); |
8454 | 19.8k | allowed = operand_type_and (allowed, mask); |
8455 | 19.8k | } |
8456 | | |
8457 | 2.22k | if (!operand_type_all_zero (&allowed)) |
8458 | 2.18k | i.types[op] = operand_type_and (i.types[op], mask); |
8459 | 2.22k | } |
8460 | 0 | break; |
8461 | 4.68k | } |
8462 | 4.68k | } |
8463 | 4.68k | } |
8464 | | |
8465 | | /* Try to use the smallest displacement type too. */ |
8466 | | static bool |
8467 | | optimize_disp (const insn_template *t) |
8468 | 37.3k | { |
8469 | 37.3k | unsigned int op; |
8470 | | |
8471 | 37.3k | if (!want_disp32 (t) |
8472 | 37.3k | && (!t->opcode_modifier.jump |
8473 | 34.0k | || i.jumpabsolute || i.types[0].bitfield.baseindex)) |
8474 | 34.0k | { |
8475 | 68.1k | for (op = i.imm_operands; op < i.operands; ++op) |
8476 | 34.0k | { |
8477 | 34.0k | const expressionS *exp = i.op[op].disps; |
8478 | | |
8479 | 34.0k | if (!operand_type_check (i.types[op], disp)) |
8480 | 0 | continue; |
8481 | | |
8482 | 34.0k | if (exp->X_op != O_constant) |
8483 | 34.0k | continue; |
8484 | | |
8485 | | /* Since displacement is signed extended to 64bit, don't allow |
8486 | | disp32 if it is out of range. */ |
8487 | 55 | if (fits_in_signed_long (exp->X_add_number)) |
8488 | 55 | continue; |
8489 | | |
8490 | 0 | i.types[op].bitfield.disp32 = 0; |
8491 | 0 | if (i.types[op].bitfield.baseindex) |
8492 | 0 | { |
8493 | 0 | as_bad (_("0x%" PRIx64 " out of range of signed 32bit displacement"), |
8494 | 0 | (uint64_t) exp->X_add_number); |
8495 | 0 | return false; |
8496 | 0 | } |
8497 | 0 | } |
8498 | 34.0k | } |
8499 | | |
8500 | | /* Don't optimize displacement for movabs / jmpabs since they only take |
8501 | | 64-bit displacement. */ |
8502 | 37.3k | if (pp.disp_encoding > disp_encoding_8bit |
8503 | 37.3k | || t->mnem_off == MN_movabs || t->mnem_off == MN_jmpabs) |
8504 | 0 | return true; |
8505 | | |
8506 | 76.9k | for (op = i.operands; op-- > 0;) |
8507 | 39.6k | if (operand_type_check (i.types[op], disp)) |
8508 | 37.7k | { |
8509 | 37.7k | if (i.op[op].disps->X_op == O_constant) |
8510 | 2.04k | { |
8511 | 2.04k | offsetT op_disp = i.op[op].disps->X_add_number; |
8512 | | |
8513 | 2.04k | if (!op_disp && i.types[op].bitfield.baseindex) |
8514 | 0 | { |
8515 | 0 | i.types[op] = operand_type_and_not (i.types[op], anydisp); |
8516 | 0 | i.op[op].disps = NULL; |
8517 | 0 | i.disp_operands--; |
8518 | 0 | continue; |
8519 | 0 | } |
8520 | | |
8521 | 2.04k | if (i.types[op].bitfield.disp16 |
8522 | 2.04k | && fits_in_unsigned_word (op_disp)) |
8523 | 169 | { |
8524 | | /* If this operand is at most 16 bits, convert |
8525 | | to a signed 16 bit number and don't use 64bit |
8526 | | displacement. */ |
8527 | 169 | op_disp = ((op_disp ^ 0x8000) - 0x8000); |
8528 | 169 | i.types[op].bitfield.disp64 = 0; |
8529 | 169 | } |
8530 | | |
8531 | 2.04k | #ifdef BFD64 |
8532 | | /* Optimize 64-bit displacement to 32-bit for 64-bit BFD. */ |
8533 | 2.04k | if ((flag_code != CODE_64BIT |
8534 | 2.04k | ? i.types[op].bitfield.disp32 |
8535 | 2.04k | : want_disp32 (t) |
8536 | 61 | && (!t->opcode_modifier.jump |
8537 | 0 | || i.jumpabsolute || i.types[op].bitfield.baseindex)) |
8538 | 2.04k | && fits_in_unsigned_long (op_disp)) |
8539 | 1.30k | { |
8540 | | /* If this operand is at most 32 bits, convert |
8541 | | to a signed 32 bit number and don't use 64bit |
8542 | | displacement. */ |
8543 | 1.30k | op_disp = (op_disp ^ ((offsetT) 1 << 31)) - ((addressT) 1 << 31); |
8544 | 1.30k | i.types[op].bitfield.disp64 = 0; |
8545 | 1.30k | i.types[op].bitfield.disp32 = 1; |
8546 | 1.30k | } |
8547 | | |
8548 | 2.04k | if (flag_code == CODE_64BIT && fits_in_signed_long (op_disp)) |
8549 | 57 | { |
8550 | 57 | i.types[op].bitfield.disp64 = 0; |
8551 | 57 | i.types[op].bitfield.disp32 = 1; |
8552 | 57 | } |
8553 | 2.04k | #endif |
8554 | 2.04k | if ((i.types[op].bitfield.disp32 |
8555 | 2.04k | || i.types[op].bitfield.disp16) |
8556 | 2.04k | && fits_in_disp8 (op_disp)) |
8557 | 1.53k | i.types[op].bitfield.disp8 = 1; |
8558 | | |
8559 | 2.04k | i.op[op].disps->X_add_number = op_disp; |
8560 | 2.04k | } |
8561 | 35.6k | else if (i.reloc[op] == BFD_RELOC_386_TLS_DESC_CALL |
8562 | 35.6k | || i.reloc[op] == BFD_RELOC_X86_64_TLSDESC_CALL) |
8563 | 222 | { |
8564 | 222 | fix_new_exp (frag_now, frag_more (0) - frag_now->fr_literal, 0, |
8565 | 222 | i.op[op].disps, 0, i.reloc[op]); |
8566 | 222 | i.types[op] = operand_type_and_not (i.types[op], anydisp); |
8567 | 222 | } |
8568 | 35.4k | else |
8569 | | /* We only support 64bit displacement on constants. */ |
8570 | 35.4k | i.types[op].bitfield.disp64 = 0; |
8571 | 37.7k | } |
8572 | | |
8573 | 37.3k | return true; |
8574 | 37.3k | } |
8575 | | |
8576 | | /* Return 1 if there is a match in broadcast bytes between operand |
8577 | | GIVEN and instruction template T. */ |
8578 | | |
8579 | | static INLINE int |
8580 | | match_broadcast_size (const insn_template *t, unsigned int given) |
8581 | 0 | { |
8582 | 0 | return ((t->opcode_modifier.broadcast == BYTE_BROADCAST |
8583 | 0 | && i.types[given].bitfield.byte) |
8584 | 0 | || (t->opcode_modifier.broadcast == WORD_BROADCAST |
8585 | 0 | && i.types[given].bitfield.word) |
8586 | 0 | || (t->opcode_modifier.broadcast == DWORD_BROADCAST |
8587 | 0 | && i.types[given].bitfield.dword) |
8588 | 0 | || (t->opcode_modifier.broadcast == QWORD_BROADCAST |
8589 | 0 | && i.types[given].bitfield.qword)); |
8590 | 0 | } |
8591 | | |
8592 | | /* Check if operands are valid for the instruction. */ |
8593 | | |
8594 | | static int |
8595 | | check_VecOperands (const insn_template *t) |
8596 | 2.62k | { |
8597 | 2.62k | unsigned int op; |
8598 | 2.62k | i386_cpu_flags cpu; |
8599 | | |
8600 | | /* Templates allowing for ZMMword as well as YMMword and/or XMMword for |
8601 | | any one operand are implicity requiring AVX512VL support if the actual |
8602 | | operand size is YMMword or XMMword. Since this function runs after |
8603 | | template matching, there's no need to check for YMMword/XMMword in |
8604 | | the template. */ |
8605 | 2.62k | cpu = cpu_flags_and (cpu_flags_from_attr (t->cpu), avx512); |
8606 | 2.62k | if (!cpu_flags_all_zero (&cpu) |
8607 | 2.62k | && !is_cpu (t, CpuAVX512VL) |
8608 | 2.62k | && !cpu_arch_flags.bitfield.cpuavx512vl |
8609 | 2.62k | && (!t->opcode_modifier.vex || need_evex_encoding (t))) |
8610 | 0 | { |
8611 | 0 | for (op = 0; op < t->operands; ++op) |
8612 | 0 | { |
8613 | 0 | if (t->operand_types[op].bitfield.zmmword |
8614 | 0 | && (i.types[op].bitfield.ymmword |
8615 | 0 | || i.types[op].bitfield.xmmword)) |
8616 | 0 | { |
8617 | 0 | i.error = operand_size_mismatch; |
8618 | 0 | return 1; |
8619 | 0 | } |
8620 | 0 | } |
8621 | 0 | } |
8622 | | |
8623 | | /* Somewhat similarly, templates specifying both AVX and AVX2 are |
8624 | | requiring AVX2 support if the actual operand size is YMMword. */ |
8625 | 2.62k | if (maybe_cpu (t, CpuAVX) && maybe_cpu (t, CpuAVX2) |
8626 | 2.62k | && !cpu_arch_flags.bitfield.cpuavx2) |
8627 | 0 | { |
8628 | 0 | for (op = 0; op < t->operands; ++op) |
8629 | 0 | { |
8630 | 0 | if (t->operand_types[op].bitfield.xmmword |
8631 | 0 | && i.types[op].bitfield.ymmword) |
8632 | 0 | { |
8633 | 0 | i.error = operand_size_mismatch; |
8634 | 0 | return 1; |
8635 | 0 | } |
8636 | 0 | } |
8637 | 0 | } |
8638 | | |
8639 | | /* Without VSIB byte, we can't have a vector register for index. */ |
8640 | 2.62k | if (!t->opcode_modifier.sib |
8641 | 2.62k | && i.index_reg |
8642 | 2.62k | && (i.index_reg->reg_type.bitfield.xmmword |
8643 | 0 | || i.index_reg->reg_type.bitfield.ymmword |
8644 | 0 | || i.index_reg->reg_type.bitfield.zmmword)) |
8645 | 0 | { |
8646 | 0 | i.error = unsupported_vector_index_register; |
8647 | 0 | return 1; |
8648 | 0 | } |
8649 | | |
8650 | | /* Check if default mask is allowed. */ |
8651 | 2.62k | if (t->opcode_modifier.operandconstraint == NO_DEFAULT_MASK |
8652 | 2.62k | && (!i.mask.reg || i.mask.reg->reg_num == 0)) |
8653 | 0 | { |
8654 | 0 | i.error = no_default_mask; |
8655 | 0 | return 1; |
8656 | 0 | } |
8657 | | |
8658 | | /* For VSIB byte, we need a vector register for index, and all vector |
8659 | | registers must be distinct. */ |
8660 | 2.62k | if (t->opcode_modifier.sib && t->opcode_modifier.sib != SIBMEM) |
8661 | 0 | { |
8662 | 0 | if (!i.index_reg |
8663 | 0 | || !((t->opcode_modifier.sib == VECSIB128 |
8664 | 0 | && i.index_reg->reg_type.bitfield.xmmword) |
8665 | 0 | || (t->opcode_modifier.sib == VECSIB256 |
8666 | 0 | && i.index_reg->reg_type.bitfield.ymmword) |
8667 | 0 | || (t->opcode_modifier.sib == VECSIB512 |
8668 | 0 | && i.index_reg->reg_type.bitfield.zmmword))) |
8669 | 0 | { |
8670 | 0 | i.error = invalid_vsib_address; |
8671 | 0 | return 1; |
8672 | 0 | } |
8673 | | |
8674 | 0 | gas_assert (i.reg_operands == 2 || i.mask.reg); |
8675 | 0 | if (i.reg_operands == 2 && !i.mask.reg) |
8676 | 0 | { |
8677 | 0 | gas_assert (i.types[0].bitfield.class == RegSIMD); |
8678 | 0 | gas_assert (i.types[0].bitfield.xmmword |
8679 | 0 | || i.types[0].bitfield.ymmword); |
8680 | 0 | gas_assert (i.types[2].bitfield.class == RegSIMD); |
8681 | 0 | gas_assert (i.types[2].bitfield.xmmword |
8682 | 0 | || i.types[2].bitfield.ymmword); |
8683 | 0 | if (operand_check == check_none) |
8684 | 0 | return 0; |
8685 | 0 | if (register_number (i.op[0].regs) |
8686 | 0 | != register_number (i.index_reg) |
8687 | 0 | && register_number (i.op[2].regs) |
8688 | 0 | != register_number (i.index_reg) |
8689 | 0 | && register_number (i.op[0].regs) |
8690 | 0 | != register_number (i.op[2].regs)) |
8691 | 0 | return 0; |
8692 | 0 | if (operand_check == check_error) |
8693 | 0 | { |
8694 | 0 | i.error = invalid_vector_register_set; |
8695 | 0 | return 1; |
8696 | 0 | } |
8697 | 0 | as_warn (_("mask, index, and destination registers should be distinct")); |
8698 | 0 | } |
8699 | 0 | else if (i.reg_operands == 1 && i.mask.reg) |
8700 | 0 | { |
8701 | 0 | if (i.types[1].bitfield.class == RegSIMD |
8702 | 0 | && (i.types[1].bitfield.xmmword |
8703 | 0 | || i.types[1].bitfield.ymmword |
8704 | 0 | || i.types[1].bitfield.zmmword) |
8705 | 0 | && (register_number (i.op[1].regs) |
8706 | 0 | == register_number (i.index_reg))) |
8707 | 0 | { |
8708 | 0 | if (operand_check == check_error) |
8709 | 0 | { |
8710 | 0 | i.error = invalid_vector_register_set; |
8711 | 0 | return 1; |
8712 | 0 | } |
8713 | 0 | if (operand_check != check_none) |
8714 | 0 | as_warn (_("index and destination registers should be distinct")); |
8715 | 0 | } |
8716 | 0 | } |
8717 | 0 | } |
8718 | | |
8719 | | /* For AMX instructions with 3 TMM register operands, all operands |
8720 | | must be distinct. */ |
8721 | 2.62k | if (i.reg_operands == 3 |
8722 | 2.62k | && t->operand_types[0].bitfield.tmmword |
8723 | 2.62k | && (i.op[0].regs == i.op[1].regs |
8724 | 0 | || i.op[0].regs == i.op[2].regs |
8725 | 0 | || i.op[1].regs == i.op[2].regs)) |
8726 | 0 | { |
8727 | 0 | i.error = invalid_tmm_register_set; |
8728 | 0 | return 1; |
8729 | 0 | } |
8730 | | |
8731 | | /* For some special instructions require that destination must be distinct |
8732 | | from source registers. */ |
8733 | 2.62k | if (t->opcode_modifier.operandconstraint == DISTINCT_DEST) |
8734 | 0 | { |
8735 | 0 | unsigned int dest_reg = i.operands - 1; |
8736 | |
|
8737 | 0 | know (i.operands >= 3); |
8738 | | |
8739 | | /* #UD if dest_reg == src1_reg or dest_reg == src2_reg. */ |
8740 | 0 | if (i.op[dest_reg - 1].regs == i.op[dest_reg].regs |
8741 | 0 | || (i.reg_operands > 2 |
8742 | 0 | && i.op[dest_reg - 2].regs == i.op[dest_reg].regs)) |
8743 | 0 | { |
8744 | 0 | i.error = invalid_dest_and_src_register_set; |
8745 | 0 | return 1; |
8746 | 0 | } |
8747 | 0 | } |
8748 | | |
8749 | | /* Check if broadcast is supported by the instruction and is applied |
8750 | | to the memory operand. */ |
8751 | 2.62k | if (i.broadcast.type || i.broadcast.bytes) |
8752 | 0 | { |
8753 | 0 | i386_operand_type type, overlap; |
8754 | | |
8755 | | /* Check if specified broadcast is supported in this instruction, |
8756 | | and its broadcast bytes match the memory operand. */ |
8757 | 0 | op = i.broadcast.operand; |
8758 | 0 | if (!t->opcode_modifier.broadcast |
8759 | 0 | || !(i.flags[op] & Operand_Mem) |
8760 | 0 | || (!i.types[op].bitfield.unspecified |
8761 | 0 | && !match_broadcast_size (t, op))) |
8762 | 0 | { |
8763 | 0 | bad_broadcast: |
8764 | 0 | i.error = unsupported_broadcast; |
8765 | 0 | return 1; |
8766 | 0 | } |
8767 | | |
8768 | 0 | operand_type_set (&type, 0); |
8769 | 0 | switch (get_broadcast_bytes (t, false)) |
8770 | 0 | { |
8771 | 0 | case 2: |
8772 | 0 | type.bitfield.word = 1; |
8773 | 0 | break; |
8774 | 0 | case 4: |
8775 | 0 | type.bitfield.dword = 1; |
8776 | 0 | break; |
8777 | 0 | case 8: |
8778 | 0 | type.bitfield.qword = 1; |
8779 | 0 | break; |
8780 | 0 | case 16: |
8781 | 0 | type.bitfield.xmmword = 1; |
8782 | 0 | break; |
8783 | 0 | case 32: |
8784 | 0 | if (vector_size < VSZ256) |
8785 | 0 | goto bad_broadcast; |
8786 | 0 | type.bitfield.ymmword = 1; |
8787 | 0 | break; |
8788 | 0 | case 64: |
8789 | 0 | if (vector_size < VSZ512) |
8790 | 0 | goto bad_broadcast; |
8791 | 0 | type.bitfield.zmmword = 1; |
8792 | 0 | break; |
8793 | 0 | default: |
8794 | 0 | goto bad_broadcast; |
8795 | 0 | } |
8796 | | |
8797 | 0 | overlap = operand_type_and (type, t->operand_types[op]); |
8798 | 0 | if (t->operand_types[op].bitfield.class == RegSIMD |
8799 | 0 | && t->operand_types[op].bitfield.byte |
8800 | 0 | + t->operand_types[op].bitfield.word |
8801 | 0 | + t->operand_types[op].bitfield.dword |
8802 | 0 | + t->operand_types[op].bitfield.qword > 1) |
8803 | 0 | { |
8804 | 0 | overlap.bitfield.xmmword = 0; |
8805 | 0 | overlap.bitfield.ymmword = 0; |
8806 | 0 | overlap.bitfield.zmmword = 0; |
8807 | 0 | } |
8808 | 0 | if (operand_type_all_zero (&overlap)) |
8809 | 0 | goto bad_broadcast; |
8810 | | |
8811 | 0 | if (t->opcode_modifier.checkoperandsize) |
8812 | 0 | { |
8813 | 0 | unsigned int j; |
8814 | |
|
8815 | 0 | type.bitfield.baseindex = 1; |
8816 | 0 | for (j = i.imm_operands; j < i.operands; ++j) |
8817 | 0 | { |
8818 | 0 | if (j != op |
8819 | 0 | && !operand_type_register_match(i.types[j], |
8820 | 0 | t->operand_types[j], |
8821 | 0 | type, |
8822 | 0 | t->operand_types[op])) |
8823 | 0 | goto bad_broadcast; |
8824 | 0 | } |
8825 | 0 | } |
8826 | 0 | } |
8827 | | /* If broadcast is supported in this instruction, we need to check if |
8828 | | operand of one-element size isn't specified without broadcast. */ |
8829 | 2.62k | else if (t->opcode_modifier.broadcast && i.mem_operands) |
8830 | 0 | { |
8831 | | /* Find memory operand. */ |
8832 | 0 | for (op = i.imm_operands; op < i.operands; op++) |
8833 | 0 | if (i.flags[op] & Operand_Mem) |
8834 | 0 | break; |
8835 | 0 | gas_assert (op < i.operands); |
8836 | | /* Check size of the memory operand. */ |
8837 | 0 | if (match_broadcast_size (t, op)) |
8838 | 0 | { |
8839 | 0 | i.error = broadcast_needed; |
8840 | 0 | return 1; |
8841 | 0 | } |
8842 | 0 | } |
8843 | 2.62k | else |
8844 | 2.62k | op = MAX_OPERANDS - 1; /* Avoid uninitialized variable warning. */ |
8845 | | |
8846 | | /* Check if requested masking is supported. */ |
8847 | 2.62k | if (i.mask.reg) |
8848 | 0 | { |
8849 | 0 | if (!t->opcode_modifier.masking) |
8850 | 0 | { |
8851 | 0 | i.error = unsupported_masking; |
8852 | 0 | return 1; |
8853 | 0 | } |
8854 | | |
8855 | | /* Common rules for masking: |
8856 | | - mask register destinations permit only zeroing-masking, without |
8857 | | that actually being expressed by a {z} operand suffix or EVEX.z, |
8858 | | - memory destinations allow only merging-masking, |
8859 | | - scatter/gather insns (i.e. ones using vSIB) only allow merging- |
8860 | | masking. */ |
8861 | 0 | if (i.mask.zeroing |
8862 | 0 | && (t->operand_types[t->operands - 1].bitfield.class == RegMask |
8863 | 0 | || (i.flags[t->operands - 1] & Operand_Mem) |
8864 | 0 | || t->opcode_modifier.sib)) |
8865 | 0 | { |
8866 | 0 | i.error = unsupported_masking; |
8867 | 0 | return 1; |
8868 | 0 | } |
8869 | 0 | } |
8870 | | |
8871 | | /* Check if masking is applied to dest operand. */ |
8872 | 2.62k | if (i.mask.reg && (i.mask.operand != i.operands - 1)) |
8873 | 0 | { |
8874 | 0 | i.error = mask_not_on_destination; |
8875 | 0 | return 1; |
8876 | 0 | } |
8877 | | |
8878 | | /* Check RC/SAE. */ |
8879 | 2.62k | if (i.rounding.type != rc_none) |
8880 | 0 | { |
8881 | 0 | if (!t->opcode_modifier.sae |
8882 | 0 | || ((i.rounding.type != saeonly) != t->opcode_modifier.staticrounding) |
8883 | 0 | || i.mem_operands) |
8884 | 0 | { |
8885 | 0 | i.error = unsupported_rc_sae; |
8886 | 0 | return 1; |
8887 | 0 | } |
8888 | | |
8889 | | /* Non-EVEX.{LIG,512} forms need to have a ZMM or YMM register as at |
8890 | | least one operand. There's no need to check all operands, though: |
8891 | | Either of the last two operands will be of the right size in all |
8892 | | relevant templates. */ |
8893 | 0 | if (t->opcode_modifier.evex != EVEXLIG |
8894 | 0 | && t->opcode_modifier.evex != EVEX512 |
8895 | 0 | && !i.types[t->operands - 1].bitfield.zmmword |
8896 | 0 | && !i.types[t->operands - 2].bitfield.zmmword) |
8897 | 0 | { |
8898 | 0 | i.error = operand_size_mismatch; |
8899 | 0 | return 1; |
8900 | 0 | } |
8901 | 0 | } |
8902 | | |
8903 | | /* Check the special Imm4 cases; must be the first operand. */ |
8904 | 2.62k | if ((is_cpu (t, CpuXOP) && t->operands == 5) |
8905 | 2.62k | || (t->opcode_space == SPACE_0F3A |
8906 | 2.62k | && (t->base_opcode | 3) == 0x0b |
8907 | 2.62k | && (is_cpu (t, CpuAPX_F) |
8908 | 0 | || (t->opcode_modifier.sse2avx && t->opcode_modifier.evex |
8909 | 0 | && (!t->opcode_modifier.vex |
8910 | 0 | || (pp.encoding != encoding_default |
8911 | 0 | && pp.encoding != encoding_vex |
8912 | 0 | && pp.encoding != encoding_vex3)))))) |
8913 | 0 | { |
8914 | 0 | if (i.op[0].imms->X_op != O_constant |
8915 | 0 | || !fits_in_imm4 (i.op[0].imms->X_add_number)) |
8916 | 0 | { |
8917 | 0 | i.error = bad_imm4; |
8918 | 0 | return 1; |
8919 | 0 | } |
8920 | | |
8921 | | /* Turn off Imm<N> so that update_imm won't complain. */ |
8922 | 0 | if (t->operands == 5) |
8923 | 0 | operand_type_set (&i.types[0], 0); |
8924 | 0 | } |
8925 | | |
8926 | | /* Check vector Disp8 operand. */ |
8927 | 2.62k | if (t->opcode_modifier.disp8memshift |
8928 | 2.62k | && (!t->opcode_modifier.vex |
8929 | 0 | || need_evex_encoding (t)) |
8930 | 2.62k | && pp.disp_encoding <= disp_encoding_8bit) |
8931 | 0 | { |
8932 | 0 | if (i.broadcast.type || i.broadcast.bytes) |
8933 | 0 | i.memshift = t->opcode_modifier.broadcast - 1; |
8934 | 0 | else if (t->opcode_modifier.disp8memshift != DISP8_SHIFT_VL) |
8935 | 0 | i.memshift = t->opcode_modifier.disp8memshift; |
8936 | 0 | else |
8937 | 0 | { |
8938 | 0 | const i386_operand_type *type = NULL, *fallback = NULL; |
8939 | |
|
8940 | 0 | i.memshift = 0; |
8941 | 0 | for (op = i.imm_operands; op < i.operands; op++) |
8942 | 0 | if (i.flags[op] & Operand_Mem) |
8943 | 0 | { |
8944 | 0 | if (t->opcode_modifier.evex == EVEXLIG) |
8945 | 0 | i.memshift = 2 + (i.suffix == QWORD_MNEM_SUFFIX); |
8946 | 0 | else if (t->operand_types[op].bitfield.xmmword |
8947 | 0 | + t->operand_types[op].bitfield.ymmword |
8948 | 0 | + t->operand_types[op].bitfield.zmmword <= 1) |
8949 | 0 | type = &t->operand_types[op]; |
8950 | 0 | else if (!i.types[op].bitfield.unspecified) |
8951 | 0 | type = &i.types[op]; |
8952 | 0 | else /* Ambiguities get resolved elsewhere. */ |
8953 | 0 | fallback = &t->operand_types[op]; |
8954 | 0 | } |
8955 | 0 | else if (i.types[op].bitfield.class == RegSIMD |
8956 | 0 | && t->opcode_modifier.evex != EVEXLIG) |
8957 | 0 | { |
8958 | 0 | if (i.types[op].bitfield.zmmword) |
8959 | 0 | i.memshift = 6; |
8960 | 0 | else if (i.types[op].bitfield.ymmword && i.memshift < 5) |
8961 | 0 | i.memshift = 5; |
8962 | 0 | else if (i.types[op].bitfield.xmmword && i.memshift < 4) |
8963 | 0 | i.memshift = 4; |
8964 | 0 | } |
8965 | |
|
8966 | 0 | if (!type && !i.memshift) |
8967 | 0 | type = fallback; |
8968 | 0 | if (type) |
8969 | 0 | { |
8970 | 0 | if (type->bitfield.zmmword) |
8971 | 0 | i.memshift = 6; |
8972 | 0 | else if (type->bitfield.ymmword) |
8973 | 0 | i.memshift = 5; |
8974 | 0 | else if (type->bitfield.xmmword) |
8975 | 0 | i.memshift = 4; |
8976 | 0 | } |
8977 | | |
8978 | | /* For the check in fits_in_disp8(). */ |
8979 | 0 | if (i.memshift == 0) |
8980 | 0 | i.memshift = -1; |
8981 | 0 | } |
8982 | |
|
8983 | 0 | for (op = i.imm_operands; op < i.operands; op++) |
8984 | 0 | if (operand_type_check (i.types[op], disp) |
8985 | 0 | && i.op[op].disps->X_op == O_constant) |
8986 | 0 | { |
8987 | | /* Make sure to leave i.types[op].bitfield.disp8 alone upon |
8988 | | secondary invocations of match_template(). */ |
8989 | 0 | if (fits_in_disp8 (i.op[op].disps->X_add_number)) |
8990 | 0 | { |
8991 | 0 | if (!i.tm.mnem_off) |
8992 | 0 | i.types[op].bitfield.disp8 = 1; |
8993 | 0 | return 0; |
8994 | 0 | } |
8995 | 0 | if (!i.tm.mnem_off) |
8996 | 0 | i.types[op].bitfield.disp8 = 0; |
8997 | 0 | } |
8998 | 0 | } |
8999 | | |
9000 | 2.62k | i.memshift = 0; |
9001 | | |
9002 | 2.62k | return 0; |
9003 | 2.62k | } |
9004 | | |
9005 | | /* Check if encoding requirements are met by the instruction. */ |
9006 | | |
9007 | | static int |
9008 | | VEX_check_encoding (const insn_template *t) |
9009 | 2.92k | { |
9010 | 2.92k | if (pp.encoding == encoding_error) |
9011 | 0 | { |
9012 | 0 | i.error = unsupported; |
9013 | 0 | return 1; |
9014 | 0 | } |
9015 | | |
9016 | | /* Vector size restrictions. */ |
9017 | 2.92k | if ((vector_size < VSZ512 |
9018 | 2.92k | && t->opcode_modifier.evex == EVEX512) |
9019 | 2.92k | || (vector_size < VSZ256 |
9020 | 2.92k | && (t->opcode_modifier.evex == EVEX256 |
9021 | 0 | || t->opcode_modifier.vex == VEX256))) |
9022 | 0 | { |
9023 | 0 | i.error = unsupported_vector_size; |
9024 | 0 | return 1; |
9025 | 0 | } |
9026 | | |
9027 | 2.92k | switch (pp.encoding) |
9028 | 2.92k | { |
9029 | 0 | case encoding_vex: |
9030 | 0 | case encoding_vex3: |
9031 | | /* This instruction must be encoded with VEX prefix. */ |
9032 | 0 | if (!t->opcode_modifier.vex) |
9033 | 0 | { |
9034 | 0 | i.error = no_vex_encoding; |
9035 | 0 | return 1; |
9036 | 0 | } |
9037 | 0 | break; |
9038 | | |
9039 | 2.92k | case encoding_default: |
9040 | 2.92k | if (!pp.has_nf) |
9041 | 2.92k | break; |
9042 | | /* Fall through. */ |
9043 | 0 | case encoding_evex: |
9044 | 0 | case encoding_evex512: |
9045 | | /* This instruction must be encoded with EVEX prefix. */ |
9046 | 0 | if (!t->opcode_modifier.evex) |
9047 | 0 | { |
9048 | 0 | i.error = no_evex_encoding; |
9049 | 0 | return 1; |
9050 | 0 | } |
9051 | 0 | break; |
9052 | | |
9053 | 0 | case encoding_egpr: |
9054 | | /* This instruction must be encoded with REX2 or EVEX prefix. */ |
9055 | 0 | if (t->opcode_modifier.vex && !t->opcode_modifier.evex) |
9056 | 0 | { |
9057 | 0 | i.error = no_evex_encoding; |
9058 | 0 | return 1; |
9059 | 0 | } |
9060 | 0 | break; |
9061 | | |
9062 | 0 | default: |
9063 | 0 | abort (); |
9064 | 2.92k | } |
9065 | | |
9066 | 2.92k | return 0; |
9067 | 2.92k | } |
9068 | | |
9069 | | /* Check if Egprs operands are valid for the instruction. */ |
9070 | | |
9071 | | static bool |
9072 | | check_EgprOperands (const insn_template *t) |
9073 | 2.62k | { |
9074 | 2.62k | if (!t->opcode_modifier.noegpr) |
9075 | 2.06k | return false; |
9076 | | |
9077 | 1.08k | for (unsigned int op = i.imm_operands; op < i.operands; op++) |
9078 | 523 | { |
9079 | 523 | if (i.types[op].bitfield.class != Reg) |
9080 | 523 | continue; |
9081 | | |
9082 | 0 | if (i.op[op].regs->reg_flags & RegRex2) |
9083 | 0 | { |
9084 | 0 | i.error = register_type_mismatch; |
9085 | 0 | return true; |
9086 | 0 | } |
9087 | 0 | } |
9088 | | |
9089 | 565 | if ((i.index_reg && (i.index_reg->reg_flags & RegRex2)) |
9090 | 565 | || (i.base_reg && (i.base_reg->reg_flags & RegRex2))) |
9091 | 0 | { |
9092 | 0 | i.error = unsupported_EGPR_for_addressing; |
9093 | 0 | return true; |
9094 | 0 | } |
9095 | | |
9096 | | /* Check if pseudo prefix {rex2} is valid. */ |
9097 | 565 | if (pp.rex2_encoding && !t->opcode_modifier.sse2avx) |
9098 | 0 | { |
9099 | 0 | i.error = invalid_pseudo_prefix; |
9100 | 0 | return true; |
9101 | 0 | } |
9102 | | |
9103 | 565 | return false; |
9104 | 565 | } |
9105 | | |
9106 | | /* Check if APX operands are valid for the instruction. */ |
9107 | | static bool |
9108 | | check_APX_operands (const insn_template *t) |
9109 | 2.62k | { |
9110 | | /* Push2* and Pop2* cannot use RSP and Pop2* cannot pop two same registers. |
9111 | | */ |
9112 | 2.62k | switch (t->mnem_off) |
9113 | 2.62k | { |
9114 | 0 | case MN_pop2: |
9115 | 0 | case MN_pop2p: |
9116 | 0 | if (register_number (i.op[0].regs) == register_number (i.op[1].regs)) |
9117 | 0 | { |
9118 | 0 | i.error = invalid_dest_register_set; |
9119 | 0 | return 1; |
9120 | 0 | } |
9121 | | /* fall through */ |
9122 | 0 | case MN_push2: |
9123 | 0 | case MN_push2p: |
9124 | 0 | if (register_number (i.op[0].regs) == 4 |
9125 | 0 | || register_number (i.op[1].regs) == 4) |
9126 | 0 | { |
9127 | 0 | i.error = unsupported_rsp_register; |
9128 | 0 | return 1; |
9129 | 0 | } |
9130 | 0 | break; |
9131 | 2.62k | } |
9132 | 2.62k | return 0; |
9133 | 2.62k | } |
9134 | | |
9135 | | /* Check if the instruction use the REX registers or REX prefix. */ |
9136 | | static bool |
9137 | | check_Rex_required (void) |
9138 | 0 | { |
9139 | 0 | for (unsigned int op = i.imm_operands; op < i.operands; op++) |
9140 | 0 | { |
9141 | 0 | if (i.types[op].bitfield.class != Reg) |
9142 | 0 | continue; |
9143 | | |
9144 | 0 | if (i.op[op].regs->reg_flags & (RegRex | RegRex64)) |
9145 | 0 | return true; |
9146 | 0 | } |
9147 | | |
9148 | 0 | if ((i.index_reg && (i.index_reg->reg_flags & RegRex)) |
9149 | 0 | || (i.base_reg && (i.base_reg->reg_flags & RegRex))) |
9150 | 0 | return true; |
9151 | | |
9152 | | /* Check pseudo prefix {rex} are valid. */ |
9153 | 0 | return pp.rex_encoding; |
9154 | 0 | } |
9155 | | |
9156 | | /* Optimize APX NDD insns to legacy insns. */ |
9157 | | static unsigned int |
9158 | | can_convert_NDD_to_legacy (const insn_template *t) |
9159 | 0 | { |
9160 | 0 | unsigned int match_dest_op = ~0; |
9161 | |
|
9162 | 0 | if (!pp.has_nf && i.reg_operands >= 2) |
9163 | 0 | { |
9164 | 0 | unsigned int dest = i.operands - 1; |
9165 | 0 | unsigned int src1 = i.operands - 2; |
9166 | 0 | unsigned int src2 = (i.operands > 3) ? i.operands - 3 : 0; |
9167 | |
|
9168 | 0 | if (i.types[src1].bitfield.class == Reg |
9169 | 0 | && i.op[src1].regs == i.op[dest].regs) |
9170 | 0 | match_dest_op = src1; |
9171 | | /* If the first operand is the same as the third operand, |
9172 | | these instructions need to support the ability to commutative |
9173 | | the first two operands and still not change the semantics in order |
9174 | | to be optimized. */ |
9175 | 0 | else if (optimize > 1 |
9176 | 0 | && t->opcode_modifier.commutative |
9177 | 0 | && i.types[src2].bitfield.class == Reg |
9178 | 0 | && i.op[src2].regs == i.op[dest].regs) |
9179 | 0 | match_dest_op = src2; |
9180 | 0 | } |
9181 | 0 | return match_dest_op; |
9182 | 0 | } |
9183 | | |
9184 | | /* Helper function for the progress() macro in match_template(). */ |
9185 | | static INLINE enum i386_error progress (enum i386_error new, |
9186 | | enum i386_error last, |
9187 | | unsigned int line, unsigned int *line_p) |
9188 | 88.9k | { |
9189 | 88.9k | if (line <= *line_p) |
9190 | 54.2k | return last; |
9191 | 34.6k | *line_p = line; |
9192 | 34.6k | return new; |
9193 | 88.9k | } |
9194 | | |
9195 | | static const insn_template * |
9196 | | match_template (char mnem_suffix) |
9197 | 76.2k | { |
9198 | | /* Points to template once we've found it. */ |
9199 | 76.2k | const insn_template *t; |
9200 | 76.2k | i386_operand_type overlap0, overlap1, overlap2, overlap3; |
9201 | 76.2k | i386_operand_type overlap4; |
9202 | 76.2k | unsigned int found_reverse_match; |
9203 | 76.2k | i386_operand_type operand_types [MAX_OPERANDS]; |
9204 | 76.2k | int addr_prefix_disp; |
9205 | 76.2k | unsigned int j, size_match, check_register, errline = __LINE__; |
9206 | 76.2k | enum i386_error specific_error = number_of_operands_mismatch; |
9207 | 88.9k | #define progress(err) progress (err, specific_error, __LINE__, &errline) |
9208 | | |
9209 | | #if MAX_OPERANDS != 5 |
9210 | | # error "MAX_OPERANDS must be 5." |
9211 | | #endif |
9212 | | |
9213 | 76.2k | found_reverse_match = 0; |
9214 | 76.2k | addr_prefix_disp = -1; |
9215 | | |
9216 | 540k | for (t = current_templates.start; t < current_templates.end; t++) |
9217 | 467k | { |
9218 | 467k | addr_prefix_disp = -1; |
9219 | 467k | found_reverse_match = 0; |
9220 | | |
9221 | | /* Must have right number of operands. */ |
9222 | 467k | if (i.operands != t->operands) |
9223 | 452k | continue; |
9224 | | |
9225 | | /* Skip SSE2AVX templates when inapplicable. */ |
9226 | 14.4k | if (t->opcode_modifier.sse2avx |
9227 | 14.4k | && (!sse2avx || i.prefix[DATA_PREFIX])) |
9228 | 89 | { |
9229 | | /* Another non-SSE2AVX template has to follow. */ |
9230 | 89 | gas_assert (t + 1 < current_templates.end); |
9231 | 89 | continue; |
9232 | 89 | } |
9233 | | |
9234 | | /* Check processor support. */ |
9235 | 14.3k | specific_error = progress (unsupported); |
9236 | 14.3k | if (cpu_flags_match (t) != CPU_FLAGS_PERFECT_MATCH) |
9237 | 4.58k | continue; |
9238 | | |
9239 | | /* Check AT&T mnemonic. */ |
9240 | 9.81k | specific_error = progress (unsupported_with_intel_mnemonic); |
9241 | 9.81k | if (!intel_syntax && intel_mnemonic |
9242 | 9.81k | && t->opcode_modifier.dialect == ATT_MNEMONIC) |
9243 | 0 | continue; |
9244 | | |
9245 | | /* Check AT&T/Intel syntax. */ |
9246 | 9.81k | specific_error = progress (unsupported_syntax); |
9247 | 9.81k | if (intel_syntax |
9248 | 9.81k | ? t->opcode_modifier.dialect >= ATT_SYNTAX |
9249 | 9.81k | : t->opcode_modifier.dialect == INTEL_SYNTAX) |
9250 | 0 | continue; |
9251 | | |
9252 | | /* Check NF support. */ |
9253 | 9.81k | specific_error = progress (unsupported_nf); |
9254 | 9.81k | if (pp.has_nf && !t->opcode_modifier.nf) |
9255 | 0 | continue; |
9256 | | |
9257 | | /* Check Intel64/AMD64 ISA. */ |
9258 | 9.81k | switch (isa64) |
9259 | 9.81k | { |
9260 | 9.81k | default: |
9261 | | /* Default: Don't accept Intel64. */ |
9262 | 9.81k | if (t->opcode_modifier.isa64 == INTEL64) |
9263 | 114 | continue; |
9264 | 9.70k | break; |
9265 | 9.70k | case amd64: |
9266 | | /* -mamd64: Don't accept Intel64 and Intel64 only. */ |
9267 | 0 | if (t->opcode_modifier.isa64 >= INTEL64) |
9268 | 0 | continue; |
9269 | 0 | break; |
9270 | 0 | case intel64: |
9271 | | /* -mintel64: Don't accept AMD64. */ |
9272 | 0 | if (t->opcode_modifier.isa64 == AMD64 && flag_code == CODE_64BIT) |
9273 | 0 | continue; |
9274 | 0 | break; |
9275 | 9.81k | } |
9276 | | |
9277 | | /* Check the suffix. */ |
9278 | 9.70k | specific_error = progress (invalid_instruction_suffix); |
9279 | 9.70k | if ((t->opcode_modifier.no_bsuf && mnem_suffix == BYTE_MNEM_SUFFIX) |
9280 | 9.70k | || (t->opcode_modifier.no_wsuf && mnem_suffix == WORD_MNEM_SUFFIX) |
9281 | 9.70k | || (t->opcode_modifier.no_lsuf && mnem_suffix == LONG_MNEM_SUFFIX) |
9282 | 9.70k | || (t->opcode_modifier.no_ssuf && mnem_suffix == SHORT_MNEM_SUFFIX) |
9283 | 9.70k | || (t->opcode_modifier.no_qsuf && mnem_suffix == QWORD_MNEM_SUFFIX)) |
9284 | 649 | continue; |
9285 | | |
9286 | 9.05k | specific_error = progress (operand_size_mismatch); |
9287 | 9.05k | size_match = operand_size_match (t); |
9288 | 9.05k | if (!size_match) |
9289 | 0 | continue; |
9290 | | |
9291 | | /* This is intentionally not |
9292 | | |
9293 | | if (i.jumpabsolute != (t->opcode_modifier.jump == JUMP_ABSOLUTE)) |
9294 | | |
9295 | | as the case of a missing * on the operand is accepted (perhaps with |
9296 | | a warning, issued further down). */ |
9297 | 9.05k | specific_error = progress (operand_type_mismatch); |
9298 | 9.05k | if (i.jumpabsolute && t->opcode_modifier.jump != JUMP_ABSOLUTE) |
9299 | 16 | continue; |
9300 | | |
9301 | | /* In Intel syntax, normally we can check for memory operand size when |
9302 | | there is no mnemonic suffix. But jmp and call have 2 different |
9303 | | encodings with Dword memory operand size. Skip the "near" one |
9304 | | (permitting a register operand) when "far" was requested. */ |
9305 | 9.03k | if (i.far_branch |
9306 | 9.03k | && t->opcode_modifier.jump == JUMP_ABSOLUTE |
9307 | 9.03k | && t->operand_types[0].bitfield.class == Reg) |
9308 | 0 | continue; |
9309 | | |
9310 | 54.2k | for (j = 0; j < MAX_OPERANDS; j++) |
9311 | 45.1k | operand_types[j] = t->operand_types[j]; |
9312 | | |
9313 | | /* In general, don't allow 32-bit operands on pre-386. */ |
9314 | 9.03k | specific_error = progress (mnem_suffix ? invalid_instruction_suffix |
9315 | 9.03k | : operand_size_mismatch); |
9316 | 9.03k | j = i.imm_operands + (t->operands > i.imm_operands + 1); |
9317 | 9.03k | if (i.suffix == LONG_MNEM_SUFFIX |
9318 | 9.03k | && !cpu_arch_flags.bitfield.cpui386 |
9319 | 9.03k | && (intel_syntax |
9320 | 0 | ? (t->opcode_modifier.mnemonicsize != IGNORESIZE |
9321 | 0 | && !intel_float_operand (insn_name (t))) |
9322 | 0 | : intel_float_operand (insn_name (t)) != 2) |
9323 | 9.03k | && (t->operands == i.imm_operands |
9324 | 0 | || (operand_types[i.imm_operands].bitfield.class != RegMMX |
9325 | 0 | && operand_types[i.imm_operands].bitfield.class != RegSIMD |
9326 | 0 | && operand_types[i.imm_operands].bitfield.class != RegMask) |
9327 | 0 | || (operand_types[j].bitfield.class != RegMMX |
9328 | 0 | && operand_types[j].bitfield.class != RegSIMD |
9329 | 0 | && operand_types[j].bitfield.class != RegMask)) |
9330 | 9.03k | && !t->opcode_modifier.sib) |
9331 | 0 | continue; |
9332 | | |
9333 | | /* Do not verify operands when there are none. */ |
9334 | 9.03k | if (!t->operands) |
9335 | 293 | { |
9336 | 293 | if (VEX_check_encoding (t)) |
9337 | 0 | { |
9338 | 0 | specific_error = progress (i.error); |
9339 | 0 | continue; |
9340 | 0 | } |
9341 | | |
9342 | | /* Check if pseudo prefix {rex2} is valid. */ |
9343 | 293 | if (t->opcode_modifier.noegpr && pp.rex2_encoding) |
9344 | 0 | { |
9345 | 0 | specific_error = progress (invalid_pseudo_prefix); |
9346 | 0 | continue; |
9347 | 0 | } |
9348 | | |
9349 | | /* We've found a match; break out of loop. */ |
9350 | 293 | break; |
9351 | 293 | } |
9352 | | |
9353 | 8.74k | if (!t->opcode_modifier.jump |
9354 | 8.74k | || t->opcode_modifier.jump == JUMP_ABSOLUTE) |
9355 | 8.26k | { |
9356 | | /* There should be only one Disp operand. */ |
9357 | 24.7k | for (j = 0; j < MAX_OPERANDS; j++) |
9358 | 22.5k | if (operand_type_check (operand_types[j], disp)) |
9359 | 6.11k | break; |
9360 | 8.26k | if (j < MAX_OPERANDS) |
9361 | 6.11k | { |
9362 | 6.11k | bool override = (i.prefix[ADDR_PREFIX] != 0); |
9363 | | |
9364 | 6.11k | addr_prefix_disp = j; |
9365 | | |
9366 | | /* Address size prefix will turn Disp64 operand into Disp32 and |
9367 | | Disp32/Disp16 one into Disp16/Disp32 respectively. */ |
9368 | 6.11k | switch (flag_code) |
9369 | 6.11k | { |
9370 | 720 | case CODE_16BIT: |
9371 | 720 | override = !override; |
9372 | | /* Fall through. */ |
9373 | 5.78k | case CODE_32BIT: |
9374 | 5.78k | if (operand_types[j].bitfield.disp32 |
9375 | 5.78k | && operand_types[j].bitfield.disp16) |
9376 | 5.78k | { |
9377 | 5.78k | operand_types[j].bitfield.disp16 = override; |
9378 | 5.78k | operand_types[j].bitfield.disp32 = !override; |
9379 | 5.78k | } |
9380 | 5.78k | gas_assert (!operand_types[j].bitfield.disp64); |
9381 | 5.78k | break; |
9382 | | |
9383 | 5.78k | case CODE_64BIT: |
9384 | 334 | if (operand_types[j].bitfield.disp64) |
9385 | 1 | { |
9386 | 1 | gas_assert (!operand_types[j].bitfield.disp32); |
9387 | 1 | operand_types[j].bitfield.disp32 = override; |
9388 | 1 | operand_types[j].bitfield.disp64 = !override; |
9389 | 1 | } |
9390 | 334 | operand_types[j].bitfield.disp16 = 0; |
9391 | 334 | break; |
9392 | 6.11k | } |
9393 | 6.11k | } |
9394 | 8.26k | } |
9395 | | |
9396 | | /* We check register size if needed. */ |
9397 | 8.74k | if (t->opcode_modifier.checkoperandsize) |
9398 | 2.05k | { |
9399 | 2.05k | check_register = (1 << t->operands) - 1; |
9400 | 2.05k | if (i.broadcast.type || i.broadcast.bytes) |
9401 | 0 | check_register &= ~(1 << i.broadcast.operand); |
9402 | 2.05k | } |
9403 | 6.68k | else |
9404 | 6.68k | check_register = 0; |
9405 | | |
9406 | 8.74k | overlap0 = operand_type_and (i.types[0], operand_types[0]); |
9407 | 8.74k | switch (t->operands) |
9408 | 8.74k | { |
9409 | 1.16k | case 1: |
9410 | 1.16k | if (!operand_type_match (overlap0, i.types[0])) |
9411 | 376 | { |
9412 | 376 | specific_error = progress (i.error); |
9413 | 376 | continue; |
9414 | 376 | } |
9415 | | |
9416 | | /* Allow the ModR/M encoding to be requested by using the {load} or |
9417 | | {store} pseudo prefix on an applicable insn. */ |
9418 | 789 | if (!t->opcode_modifier.modrm |
9419 | 789 | && i.reg_operands == 1 |
9420 | 789 | && ((pp.dir_encoding == dir_encoding_load |
9421 | 0 | && t->mnem_off != MN_pop) |
9422 | 0 | || (pp.dir_encoding == dir_encoding_store |
9423 | 0 | && t->mnem_off != MN_push)) |
9424 | | /* Avoid BSWAP. */ |
9425 | 789 | && t->mnem_off != MN_bswap) |
9426 | 0 | continue; |
9427 | 789 | break; |
9428 | | |
9429 | 7.58k | case 2: |
9430 | | /* xchg %eax, %eax is a special case. It is an alias for nop |
9431 | | only in 32bit mode and we can use opcode 0x90. In 64bit |
9432 | | mode, we can't use 0x90 for xchg %eax, %eax since it should |
9433 | | zero-extend %eax to %rax. */ |
9434 | 7.58k | if (t->base_opcode == 0x90 |
9435 | 7.58k | && t->opcode_space == SPACE_BASE) |
9436 | 0 | { |
9437 | 0 | if (flag_code == CODE_64BIT |
9438 | 0 | && i.types[0].bitfield.instance == Accum |
9439 | 0 | && i.types[0].bitfield.dword |
9440 | 0 | && i.types[1].bitfield.instance == Accum) |
9441 | 0 | continue; |
9442 | | |
9443 | | /* Allow the ModR/M encoding to be requested by using the |
9444 | | {load} or {store} pseudo prefix. */ |
9445 | 0 | if (pp.dir_encoding == dir_encoding_load |
9446 | 0 | || pp.dir_encoding == dir_encoding_store) |
9447 | 0 | continue; |
9448 | 0 | } |
9449 | | |
9450 | 7.58k | if (t->base_opcode == MOV_AX_DISP32 |
9451 | 7.58k | && t->opcode_space == SPACE_BASE |
9452 | 7.58k | && t->mnem_off != MN_movabs) |
9453 | 11 | { |
9454 | | /* Force 0x8b encoding for "mov foo@GOT, %eax". */ |
9455 | 11 | if (i.reloc[0] == BFD_RELOC_386_GOT32) |
9456 | 0 | continue; |
9457 | | |
9458 | | /* xrelease mov %eax, <disp> is another special case. It must not |
9459 | | match the accumulator-only encoding of mov. */ |
9460 | 11 | if (i.hle_prefix) |
9461 | 0 | continue; |
9462 | | |
9463 | | /* Allow the ModR/M encoding to be requested by using a suitable |
9464 | | {load} or {store} pseudo prefix. */ |
9465 | 11 | if (pp.dir_encoding == (i.types[0].bitfield.instance == Accum |
9466 | 11 | ? dir_encoding_store |
9467 | 11 | : dir_encoding_load) |
9468 | 11 | && !i.types[0].bitfield.disp64 |
9469 | 11 | && !i.types[1].bitfield.disp64) |
9470 | 0 | continue; |
9471 | 11 | } |
9472 | | |
9473 | | /* Allow the ModR/M encoding to be requested by using the {load} or |
9474 | | {store} pseudo prefix on an applicable insn. */ |
9475 | 7.58k | if (!t->opcode_modifier.modrm |
9476 | 7.58k | && i.reg_operands == 1 |
9477 | 7.58k | && i.imm_operands == 1 |
9478 | 7.58k | && (pp.dir_encoding == dir_encoding_load |
9479 | 0 | || pp.dir_encoding == dir_encoding_store) |
9480 | 7.58k | && t->opcode_space == SPACE_BASE) |
9481 | 0 | { |
9482 | 0 | if (t->base_opcode == 0xb0 /* mov $imm, %reg */ |
9483 | 0 | && pp.dir_encoding == dir_encoding_store) |
9484 | 0 | continue; |
9485 | | |
9486 | 0 | if ((t->base_opcode | 0x38) == 0x3c /* <alu> $imm, %acc */ |
9487 | 0 | && (t->base_opcode != 0x3c /* cmp $imm, %acc */ |
9488 | 0 | || pp.dir_encoding == dir_encoding_load)) |
9489 | 0 | continue; |
9490 | | |
9491 | 0 | if (t->base_opcode == 0xa8 /* test $imm, %acc */ |
9492 | 0 | && pp.dir_encoding == dir_encoding_load) |
9493 | 0 | continue; |
9494 | 0 | } |
9495 | | /* Fall through. */ |
9496 | | |
9497 | 7.58k | case 3: |
9498 | 7.58k | if (!(size_match & MATCH_STRAIGHT)) |
9499 | 0 | goto check_reverse; |
9500 | | /* Reverse direction of operands if swapping is possible in the first |
9501 | | place (operands need to be symmetric) and |
9502 | | - the load form is requested, and the template is a store form, |
9503 | | - the store form is requested, and the template is a load form, |
9504 | | - the non-default (swapped) form is requested. */ |
9505 | 7.58k | overlap1 = operand_type_and (operand_types[0], operand_types[1]); |
9506 | | |
9507 | 7.58k | j = i.operands - 1 - (t->opcode_space == SPACE_MAP4 |
9508 | 7.58k | && t->opcode_modifier.vexvvvv); |
9509 | | |
9510 | 7.58k | if (t->opcode_modifier.d && i.reg_operands == i.operands |
9511 | 7.58k | && !operand_type_all_zero (&overlap1)) |
9512 | 0 | switch (pp.dir_encoding) |
9513 | 0 | { |
9514 | 0 | case dir_encoding_load: |
9515 | 0 | if (operand_type_check (operand_types[j], anymem) |
9516 | 0 | || t->opcode_modifier.regmem) |
9517 | 0 | goto check_reverse; |
9518 | 0 | break; |
9519 | | |
9520 | 0 | case dir_encoding_store: |
9521 | 0 | if (!operand_type_check (operand_types[j], anymem) |
9522 | 0 | && !t->opcode_modifier.regmem) |
9523 | 0 | goto check_reverse; |
9524 | 0 | break; |
9525 | | |
9526 | 0 | case dir_encoding_swap: |
9527 | 0 | goto check_reverse; |
9528 | | |
9529 | 0 | case dir_encoding_default: |
9530 | 0 | break; |
9531 | 0 | } |
9532 | | |
9533 | | /* If we want store form, we skip the current load. */ |
9534 | 7.58k | if ((pp.dir_encoding == dir_encoding_store |
9535 | 7.58k | || pp.dir_encoding == dir_encoding_swap) |
9536 | 7.58k | && i.mem_operands == 0 |
9537 | 7.58k | && t->opcode_modifier.load) |
9538 | 0 | continue; |
9539 | | /* Fall through. */ |
9540 | 7.58k | case 4: |
9541 | 7.58k | case 5: |
9542 | 7.58k | overlap1 = operand_type_and (i.types[1], operand_types[1]); |
9543 | 7.58k | if (!operand_type_match (overlap0, i.types[0]) |
9544 | 7.58k | || !operand_type_match (overlap1, i.types[1]) |
9545 | 7.58k | || ((check_register & 3) == 3 |
9546 | 1.84k | && !operand_type_register_match (i.types[0], |
9547 | 0 | operand_types[0], |
9548 | 0 | i.types[1], |
9549 | 0 | operand_types[1]))) |
9550 | 5.74k | { |
9551 | 5.74k | specific_error = progress (i.error); |
9552 | | |
9553 | | /* Check if other direction is valid ... */ |
9554 | 5.74k | if (!t->opcode_modifier.d) |
9555 | 3.64k | continue; |
9556 | | |
9557 | 2.09k | check_reverse: |
9558 | 2.09k | if (!(size_match & MATCH_REVERSE)) |
9559 | 0 | continue; |
9560 | | /* Try reversing direction of operands. */ |
9561 | 2.09k | j = is_cpu (t, CpuFMA4) |
9562 | 2.09k | || is_cpu (t, CpuXOP) |
9563 | 2.09k | || is_cpu (t, CpuAPX_F) ? 1 : i.operands - 1; |
9564 | 2.09k | overlap0 = operand_type_and (i.types[0], operand_types[j]); |
9565 | 2.09k | overlap1 = operand_type_and (i.types[j], operand_types[0]); |
9566 | 2.09k | overlap2 = operand_type_and (i.types[1], operand_types[1]); |
9567 | 2.09k | gas_assert (t->operands != 3 || !check_register |
9568 | 2.09k | || is_cpu (t, CpuAPX_F)); |
9569 | 2.09k | if (!operand_type_match (overlap0, i.types[0]) |
9570 | 2.09k | || !operand_type_match (overlap1, i.types[j]) |
9571 | 2.09k | || (t->operands == 3 |
9572 | 0 | && !operand_type_match (overlap2, i.types[1])) |
9573 | 2.09k | || (check_register |
9574 | 0 | && !operand_type_register_match (i.types[0], |
9575 | 0 | operand_types[j], |
9576 | 0 | i.types[j], |
9577 | 0 | operand_types[0]))) |
9578 | 2.09k | { |
9579 | | /* Does not match either direction. */ |
9580 | 2.09k | specific_error = progress (i.error); |
9581 | 2.09k | continue; |
9582 | 2.09k | } |
9583 | | /* found_reverse_match holds which variant of D |
9584 | | we've found. */ |
9585 | 0 | if (!t->opcode_modifier.d) |
9586 | 0 | found_reverse_match = 0; |
9587 | 0 | else if (operand_types[0].bitfield.tbyte) |
9588 | 0 | { |
9589 | 0 | if (t->opcode_modifier.operandconstraint != UGH) |
9590 | 0 | found_reverse_match = Opcode_FloatD; |
9591 | 0 | else |
9592 | 0 | found_reverse_match = ~0; |
9593 | | /* FSUB{,R} and FDIV{,R} may need a 2nd bit flipped. */ |
9594 | 0 | if ((t->extension_opcode & 4) |
9595 | 0 | && (intel_syntax || intel_mnemonic)) |
9596 | 0 | found_reverse_match |= Opcode_FloatR; |
9597 | 0 | } |
9598 | 0 | else if (is_cpu (t, CpuFMA4) || is_cpu (t, CpuXOP)) |
9599 | 0 | { |
9600 | 0 | found_reverse_match = Opcode_VexW; |
9601 | 0 | goto check_operands_345; |
9602 | 0 | } |
9603 | 0 | else if (t->opcode_space == SPACE_MAP4 |
9604 | 0 | && t->operands >= 3) |
9605 | 0 | { |
9606 | 0 | found_reverse_match = Opcode_D; |
9607 | 0 | goto check_operands_345; |
9608 | 0 | } |
9609 | 0 | else if (t->opcode_modifier.commutative |
9610 | | /* CFCMOVcc also wants its major opcode unaltered. */ |
9611 | 0 | || (t->opcode_space == SPACE_MAP4 |
9612 | 0 | && (t->base_opcode | 0xf) == 0x4f)) |
9613 | 0 | found_reverse_match = ~0; |
9614 | 0 | else if (t->opcode_space != SPACE_BASE |
9615 | 0 | && (t->opcode_space != SPACE_MAP4 |
9616 | | /* MOVBE, originating from SPACE_0F38, also |
9617 | | belongs here. */ |
9618 | 0 | || t->mnem_off == MN_movbe) |
9619 | 0 | && (t->opcode_space != SPACE_0F |
9620 | | /* MOV to/from CR/DR/TR, as an exception, follow |
9621 | | the base opcode space encoding model. */ |
9622 | 0 | || (t->base_opcode | 7) != 0x27)) |
9623 | 0 | found_reverse_match = (t->base_opcode & 0xee) != 0x6e |
9624 | 0 | ? Opcode_ExtD : Opcode_SIMD_IntD; |
9625 | 0 | else |
9626 | 0 | found_reverse_match = Opcode_D; |
9627 | 0 | } |
9628 | 1.84k | else |
9629 | 1.84k | { |
9630 | | /* Found a forward 2 operand match here. */ |
9631 | 1.84k | check_operands_345: |
9632 | 1.84k | switch (t->operands) |
9633 | 1.84k | { |
9634 | 0 | case 5: |
9635 | 0 | overlap4 = operand_type_and (i.types[4], operand_types[4]); |
9636 | 0 | if (!operand_type_match (overlap4, i.types[4]) |
9637 | 0 | || !operand_type_register_match (i.types[3], |
9638 | 0 | operand_types[3], |
9639 | 0 | i.types[4], |
9640 | 0 | operand_types[4])) |
9641 | 0 | { |
9642 | 0 | specific_error = progress (i.error); |
9643 | 0 | continue; |
9644 | 0 | } |
9645 | | /* Fall through. */ |
9646 | 0 | case 4: |
9647 | 0 | overlap3 = operand_type_and (i.types[3], operand_types[3]); |
9648 | 0 | if (!operand_type_match (overlap3, i.types[3]) |
9649 | 0 | || ((check_register & 0xa) == 0xa |
9650 | 0 | && !operand_type_register_match (i.types[1], |
9651 | 0 | operand_types[1], |
9652 | 0 | i.types[3], |
9653 | 0 | operand_types[3])) |
9654 | 0 | || ((check_register & 0xc) == 0xc |
9655 | 0 | && !operand_type_register_match (i.types[2], |
9656 | 0 | operand_types[2], |
9657 | 0 | i.types[3], |
9658 | 0 | operand_types[3]))) |
9659 | 0 | { |
9660 | 0 | specific_error = progress (i.error); |
9661 | 0 | continue; |
9662 | 0 | } |
9663 | | /* Fall through. */ |
9664 | 0 | case 3: |
9665 | 0 | overlap2 = operand_type_and (i.types[2], operand_types[2]); |
9666 | 0 | if (!operand_type_match (overlap2, i.types[2]) |
9667 | 0 | || ((check_register & 5) == 5 |
9668 | 0 | && !operand_type_register_match (i.types[0], |
9669 | 0 | operand_types[0], |
9670 | 0 | i.types[2], |
9671 | 0 | operand_types[2])) |
9672 | 0 | || ((check_register & 6) == 6 |
9673 | 0 | && !operand_type_register_match (i.types[1], |
9674 | 0 | operand_types[1], |
9675 | 0 | i.types[2], |
9676 | 0 | operand_types[2]))) |
9677 | 0 | { |
9678 | 0 | specific_error = progress (i.error); |
9679 | 0 | continue; |
9680 | 0 | } |
9681 | 0 | break; |
9682 | 1.84k | } |
9683 | 1.84k | } |
9684 | | /* Found either forward/reverse 2, 3 or 4 operand match here: |
9685 | | slip through to break. */ |
9686 | 8.74k | } |
9687 | | |
9688 | | /* Check if VEX/EVEX encoding requirements can be satisfied. */ |
9689 | 2.62k | if (VEX_check_encoding (t)) |
9690 | 0 | { |
9691 | 0 | specific_error = progress (i.error); |
9692 | 0 | continue; |
9693 | 0 | } |
9694 | | |
9695 | | /* Check if EGPR operands(r16-r31) are valid. */ |
9696 | 2.62k | if (check_EgprOperands (t)) |
9697 | 0 | { |
9698 | 0 | specific_error = progress (i.error); |
9699 | 0 | continue; |
9700 | 0 | } |
9701 | | |
9702 | | /* Check if vector operands are valid. */ |
9703 | 2.62k | if (check_VecOperands (t)) |
9704 | 0 | { |
9705 | 0 | specific_error = progress (i.error); |
9706 | 0 | continue; |
9707 | 0 | } |
9708 | | |
9709 | | /* Check if APX operands are valid. */ |
9710 | 2.62k | if (check_APX_operands (t)) |
9711 | 0 | { |
9712 | 0 | specific_error = progress (i.error); |
9713 | 0 | continue; |
9714 | 0 | } |
9715 | | |
9716 | | /* Check whether to use the shorter VEX encoding for certain insns where |
9717 | | the EVEX encoding comes first in the table. This requires the respective |
9718 | | AVX-* feature to be explicitly enabled. |
9719 | | |
9720 | | Most of the respective insns have just a single EVEX and a single VEX |
9721 | | template. The one that's presently different is generated using the |
9722 | | Vxy / Exy constructs: There are 3 suffix-less EVEX forms, the latter |
9723 | | two of which may fall back to their two corresponding VEX forms. */ |
9724 | 2.62k | j = t->mnem_off != MN_vcvtneps2bf16 ? 1 : 2; |
9725 | 2.62k | if ((t == current_templates.start || j > 1) |
9726 | 2.62k | && t->opcode_modifier.disp8memshift |
9727 | 2.62k | && !t->opcode_modifier.vex |
9728 | 2.62k | && !need_evex_encoding (t) |
9729 | 2.62k | && t + j < current_templates.end |
9730 | 2.62k | && t[j].opcode_modifier.vex) |
9731 | 0 | { |
9732 | 0 | i386_cpu_flags cpu; |
9733 | 0 | unsigned int memshift = i.memshift; |
9734 | |
|
9735 | 0 | i.memshift = 0; |
9736 | 0 | cpu = cpu_flags_and (cpu_flags_from_attr (t[j].cpu), |
9737 | 0 | cpu_arch_isa_flags); |
9738 | 0 | if (!cpu_flags_all_zero (&cpu) |
9739 | 0 | && (!i.types[0].bitfield.disp8 |
9740 | 0 | || !operand_type_check (i.types[0], disp) |
9741 | 0 | || i.op[0].disps->X_op != O_constant |
9742 | 0 | || fits_in_disp8 (i.op[0].disps->X_add_number))) |
9743 | 0 | { |
9744 | 0 | specific_error = progress (internal_error); |
9745 | 0 | t += j - 1; |
9746 | 0 | continue; |
9747 | 0 | } |
9748 | 0 | i.memshift = memshift; |
9749 | 0 | } |
9750 | | |
9751 | | /* If we can optimize a NDD insn to legacy insn, like |
9752 | | add %r16, %r8, %r8 -> add %r16, %r8, |
9753 | | add %r8, %r16, %r8 -> add %r16, %r8, then rematch template. |
9754 | | Note that the semantics have not been changed. */ |
9755 | 2.62k | if (optimize |
9756 | 2.62k | && !pp.no_optimize |
9757 | 2.62k | && pp.encoding != encoding_evex |
9758 | 2.62k | && ((t + 1 < current_templates.end |
9759 | 0 | && !t[1].opcode_modifier.evex |
9760 | 0 | && t[1].opcode_space <= SPACE_0F38 |
9761 | 0 | && t->opcode_modifier.vexvvvv == VexVVVV_DST) |
9762 | 0 | || t->mnem_off == MN_movbe) |
9763 | 2.62k | && (i.types[i.operands - 1].bitfield.dword |
9764 | 0 | || i.types[i.operands - 1].bitfield.qword)) |
9765 | 0 | { |
9766 | 0 | unsigned int match_dest_op = can_convert_NDD_to_legacy (t); |
9767 | |
|
9768 | 0 | if (match_dest_op != (unsigned int) ~0) |
9769 | 0 | { |
9770 | 0 | size_match = true; |
9771 | | /* We ensure that the next template has the same input |
9772 | | operands as the original matching template by the first |
9773 | | opernd (ATT). To avoid someone support new NDD insns and |
9774 | | put it in the wrong position. */ |
9775 | 0 | overlap0 = operand_type_and (i.types[0], |
9776 | 0 | t[1].operand_types[0]); |
9777 | 0 | if (t->opcode_modifier.d) |
9778 | 0 | overlap1 = operand_type_and (i.types[0], |
9779 | 0 | t[1].operand_types[1]); |
9780 | 0 | if (!operand_type_match (overlap0, i.types[0]) |
9781 | 0 | && (!t->opcode_modifier.d |
9782 | 0 | || !operand_type_match (overlap1, i.types[0]))) |
9783 | 0 | size_match = false; |
9784 | |
|
9785 | 0 | if (size_match |
9786 | 0 | && (t[1].opcode_space <= SPACE_0F |
9787 | | /* Some non-legacy-map0/1 insns can be shorter when |
9788 | | legacy-encoded and when no REX prefix is required. */ |
9789 | 0 | || (!check_EgprOperands (t + 1) |
9790 | 0 | && !check_Rex_required () |
9791 | 0 | && !i.op[i.operands - 1].regs->reg_type.bitfield.qword))) |
9792 | 0 | { |
9793 | 0 | if (i.operands > 2 && match_dest_op == i.operands - 3) |
9794 | 0 | { |
9795 | 0 | swap_2_operands (match_dest_op, i.operands - 2); |
9796 | | |
9797 | | /* CMOVcc is marked commutative, but then also needs its |
9798 | | encoded condition inverted. */ |
9799 | 0 | if ((t->base_opcode | 0xf) == 0x4f) |
9800 | 0 | i.invert_cond = true; |
9801 | 0 | } |
9802 | |
|
9803 | 0 | --i.operands; |
9804 | 0 | --i.reg_operands; |
9805 | |
|
9806 | 0 | if (t->mnem_off == MN_movbe) |
9807 | 0 | { |
9808 | 0 | gas_assert (t[1].mnem_off == MN_bswap); |
9809 | 0 | ++current_templates.end; |
9810 | 0 | } |
9811 | | |
9812 | 0 | specific_error = progress (internal_error); |
9813 | 0 | continue; |
9814 | 0 | } |
9815 | |
|
9816 | 0 | } |
9817 | 0 | } |
9818 | | |
9819 | | /* We've found a match; break out of loop. */ |
9820 | 2.62k | break; |
9821 | 2.62k | } |
9822 | | |
9823 | 76.2k | #undef progress |
9824 | | |
9825 | 76.2k | if (t == current_templates.end) |
9826 | 73.3k | { |
9827 | | /* We found no match. */ |
9828 | 73.3k | i.error = specific_error; |
9829 | 73.3k | return NULL; |
9830 | 73.3k | } |
9831 | | |
9832 | | /* Don't emit diagnostics or install the template when one was already |
9833 | | installed, i.e. when called from process_suffix(). */ |
9834 | 2.92k | if (i.tm.mnem_off) |
9835 | 0 | return t; |
9836 | | |
9837 | 2.92k | if (!quiet_warnings) |
9838 | 2.92k | { |
9839 | 2.92k | if (!intel_syntax |
9840 | 2.92k | && (i.jumpabsolute != (t->opcode_modifier.jump == JUMP_ABSOLUTE))) |
9841 | 8 | as_warn (_("indirect %s without `*'"), insn_name (t)); |
9842 | | |
9843 | 2.92k | if (t->opcode_modifier.isprefix |
9844 | 2.92k | && t->opcode_modifier.mnemonicsize == IGNORESIZE) |
9845 | 1 | { |
9846 | | /* Warn them that a data or address size prefix doesn't |
9847 | | affect assembly of the next line of code. */ |
9848 | 1 | as_warn (_("stand-alone `%s' prefix"), insn_name (t)); |
9849 | 1 | } |
9850 | | |
9851 | 2.92k | if (intel_syntax && mnem_suffix && !t->opcode_modifier.intelsuffix) |
9852 | 0 | { |
9853 | 0 | static bool noticed; |
9854 | |
|
9855 | 0 | as_warn (_("mnemonic suffix used with `%s'"), insn_name (t)); |
9856 | 0 | if (!noticed) |
9857 | 0 | { |
9858 | 0 | noticed = true; |
9859 | 0 | as_warn (_( |
9860 | 0 | "NOTE: Such forms are deprecated and will be rejected by a future version of the assembler")); |
9861 | 0 | } |
9862 | 0 | } |
9863 | 2.92k | } |
9864 | | |
9865 | | /* Copy the template we found. */ |
9866 | 2.92k | install_template (t); |
9867 | | |
9868 | 2.92k | if (addr_prefix_disp != -1) |
9869 | 2.10k | i.tm.operand_types[addr_prefix_disp] |
9870 | 2.10k | = operand_types[addr_prefix_disp]; |
9871 | | |
9872 | | /* APX insns acting on byte operands are WIG, yet that can't be expressed |
9873 | | in the templates (they're also covering word/dword/qword operands). */ |
9874 | 2.92k | if (t->opcode_space == SPACE_MAP4 && !t->opcode_modifier.vexw && |
9875 | 2.92k | i.types[i.operands - 1].bitfield.byte) |
9876 | 0 | { |
9877 | 0 | gas_assert (t->opcode_modifier.w); |
9878 | 0 | i.tm.opcode_modifier.vexw = VEXWIG; |
9879 | 0 | } |
9880 | | |
9881 | 2.92k | switch (found_reverse_match) |
9882 | 2.92k | { |
9883 | 2.92k | case 0: |
9884 | 2.92k | break; |
9885 | | |
9886 | 0 | case Opcode_FloatR: |
9887 | 0 | case Opcode_FloatR | Opcode_FloatD: |
9888 | 0 | i.tm.extension_opcode ^= Opcode_FloatR >> 3; |
9889 | 0 | found_reverse_match &= Opcode_FloatD; |
9890 | | |
9891 | | /* Fall through. */ |
9892 | 0 | default: |
9893 | | /* If we found a reverse match we must alter the opcode direction |
9894 | | bit and clear/flip the regmem modifier one. found_reverse_match |
9895 | | holds bits to change (different for int & float insns). */ |
9896 | |
|
9897 | 0 | i.tm.base_opcode ^= found_reverse_match; |
9898 | |
|
9899 | 0 | if (i.tm.opcode_space == SPACE_MAP4) |
9900 | 0 | goto swap_first_2; |
9901 | | |
9902 | | /* Certain SIMD insns have their load forms specified in the opcode |
9903 | | table, and hence we need to _set_ RegMem instead of clearing it. |
9904 | | We need to avoid setting the bit though on insns like KMOVW. */ |
9905 | 0 | i.tm.opcode_modifier.regmem |
9906 | 0 | = i.tm.opcode_modifier.modrm && i.tm.opcode_modifier.d |
9907 | 0 | && i.tm.operands > 2U - i.tm.opcode_modifier.sse2avx |
9908 | 0 | && !i.tm.opcode_modifier.regmem; |
9909 | | |
9910 | | /* Fall through. */ |
9911 | 0 | case ~0: |
9912 | 0 | if (i.tm.opcode_space == SPACE_MAP4 |
9913 | 0 | && !t->opcode_modifier.commutative) |
9914 | 0 | i.tm.opcode_modifier.operandconstraint = EVEX_NF; |
9915 | 0 | i.tm.operand_types[0] = operand_types[i.operands - 1]; |
9916 | 0 | i.tm.operand_types[i.operands - 1] = operand_types[0]; |
9917 | 0 | break; |
9918 | | |
9919 | 0 | case Opcode_VexW: |
9920 | | /* Only the first two register operands need reversing, alongside |
9921 | | flipping VEX.W. */ |
9922 | 0 | i.tm.opcode_modifier.vexw ^= VEXW0 ^ VEXW1; |
9923 | | |
9924 | | /* In 3-operand insns XOP.W changes which operand goes into XOP.vvvv. */ |
9925 | 0 | i.tm.opcode_modifier.vexvvvv = VexVVVV_SRC1; |
9926 | |
|
9927 | 0 | swap_first_2: |
9928 | 0 | j = i.tm.operand_types[0].bitfield.imm8; |
9929 | 0 | i.tm.operand_types[j] = operand_types[j + 1]; |
9930 | 0 | i.tm.operand_types[j + 1] = operand_types[j]; |
9931 | 0 | break; |
9932 | 2.92k | } |
9933 | | |
9934 | 2.92k | return t; |
9935 | 2.92k | } |
9936 | | |
9937 | | static int |
9938 | | check_string (void) |
9939 | 2 | { |
9940 | 2 | unsigned int es_op = i.tm.opcode_modifier.isstring - IS_STRING_ES_OP0; |
9941 | 2 | unsigned int op = i.tm.operand_types[0].bitfield.baseindex ? es_op : 0; |
9942 | | |
9943 | 2 | if (i.seg[op] != NULL && i.seg[op] != reg_es) |
9944 | 0 | { |
9945 | 0 | as_bad (_("`%s' operand %u must use `%ses' segment"), |
9946 | 0 | insn_name (&i.tm), |
9947 | 0 | intel_syntax ? i.tm.operands - es_op : es_op + 1, |
9948 | 0 | register_prefix); |
9949 | 0 | return 0; |
9950 | 0 | } |
9951 | | |
9952 | | /* There's only ever one segment override allowed per instruction. |
9953 | | This instruction possibly has a legal segment override on the |
9954 | | second operand, so copy the segment to where non-string |
9955 | | instructions store it, allowing common code. */ |
9956 | 2 | i.seg[op] = i.seg[1]; |
9957 | | |
9958 | 2 | return 1; |
9959 | 2 | } |
9960 | | |
9961 | | static int |
9962 | | process_suffix (const insn_template *t) |
9963 | 2.92k | { |
9964 | 2.92k | bool is_movx = false; |
9965 | | |
9966 | | /* If matched instruction specifies an explicit instruction mnemonic |
9967 | | suffix, use it. */ |
9968 | 2.92k | if (i.tm.opcode_modifier.size == SIZE16) |
9969 | 4 | i.suffix = WORD_MNEM_SUFFIX; |
9970 | 2.91k | else if (i.tm.opcode_modifier.size == SIZE32) |
9971 | 11 | i.suffix = LONG_MNEM_SUFFIX; |
9972 | 2.90k | else if (i.tm.opcode_modifier.size == SIZE64) |
9973 | 9 | i.suffix = QWORD_MNEM_SUFFIX; |
9974 | 2.89k | else if (i.reg_operands |
9975 | 2.89k | && (i.operands > 1 || i.types[0].bitfield.class == Reg) |
9976 | 2.89k | && i.tm.opcode_modifier.operandconstraint != ADDR_PREFIX_OP_REG) |
9977 | 0 | { |
9978 | 0 | unsigned int numop = i.operands; |
9979 | | |
9980 | | /* MOVSX/MOVZX */ |
9981 | 0 | is_movx = (i.tm.opcode_space == SPACE_0F |
9982 | 0 | && (i.tm.base_opcode | 8) == 0xbe) |
9983 | 0 | || (i.tm.opcode_space == SPACE_BASE |
9984 | 0 | && i.tm.base_opcode == 0x63 |
9985 | 0 | && is_cpu (&i.tm, Cpu64)); |
9986 | | |
9987 | | /* movsx/movzx want only their source operand considered here, for the |
9988 | | ambiguity checking below. The suffix will be replaced afterwards |
9989 | | to represent the destination (register). */ |
9990 | 0 | if (is_movx && (i.tm.opcode_modifier.w || i.tm.base_opcode == 0x63)) |
9991 | 0 | --i.operands; |
9992 | | |
9993 | | /* crc32 needs REX.W set regardless of suffix / source operand size. */ |
9994 | 0 | if (i.tm.mnem_off == MN_crc32 && i.tm.operand_types[1].bitfield.qword) |
9995 | 0 | i.rex |= REX_W; |
9996 | | |
9997 | | /* If there's no instruction mnemonic suffix we try to invent one |
9998 | | based on GPR operands. */ |
9999 | 0 | if (!i.suffix) |
10000 | 0 | { |
10001 | | /* We take i.suffix from the last register operand specified, |
10002 | | Destination register type is more significant than source |
10003 | | register type. crc32 in SSE4.2 prefers source register |
10004 | | type. */ |
10005 | 0 | unsigned int op = i.tm.mnem_off == MN_crc32 ? 1 : i.operands; |
10006 | |
|
10007 | 0 | while (op--) |
10008 | 0 | if (i.tm.operand_types[op].bitfield.instance == InstanceNone |
10009 | 0 | || i.tm.operand_types[op].bitfield.instance == Accum) |
10010 | 0 | { |
10011 | 0 | if (i.types[op].bitfield.class != Reg) |
10012 | 0 | continue; |
10013 | 0 | if (i.types[op].bitfield.byte) |
10014 | 0 | i.suffix = BYTE_MNEM_SUFFIX; |
10015 | 0 | else if (i.types[op].bitfield.word) |
10016 | 0 | i.suffix = WORD_MNEM_SUFFIX; |
10017 | 0 | else if (i.types[op].bitfield.dword) |
10018 | 0 | i.suffix = LONG_MNEM_SUFFIX; |
10019 | 0 | else if (i.types[op].bitfield.qword) |
10020 | 0 | i.suffix = QWORD_MNEM_SUFFIX; |
10021 | 0 | else |
10022 | 0 | continue; |
10023 | 0 | break; |
10024 | 0 | } |
10025 | | |
10026 | | /* As an exception, movsx/movzx silently default to a byte source |
10027 | | in AT&T mode. */ |
10028 | 0 | if (is_movx && i.tm.opcode_modifier.w && !i.suffix && !intel_syntax) |
10029 | 0 | i.suffix = BYTE_MNEM_SUFFIX; |
10030 | 0 | } |
10031 | 0 | else if (i.suffix == BYTE_MNEM_SUFFIX) |
10032 | 0 | { |
10033 | 0 | if (!check_byte_reg ()) |
10034 | 0 | return 0; |
10035 | 0 | } |
10036 | 0 | else if (i.suffix == LONG_MNEM_SUFFIX) |
10037 | 0 | { |
10038 | 0 | if (!check_long_reg ()) |
10039 | 0 | return 0; |
10040 | 0 | } |
10041 | 0 | else if (i.suffix == QWORD_MNEM_SUFFIX) |
10042 | 0 | { |
10043 | 0 | if (!check_qword_reg ()) |
10044 | 0 | return 0; |
10045 | 0 | } |
10046 | 0 | else if (i.suffix == WORD_MNEM_SUFFIX) |
10047 | 0 | { |
10048 | 0 | if (!check_word_reg ()) |
10049 | 0 | return 0; |
10050 | 0 | } |
10051 | 0 | else if (intel_syntax |
10052 | 0 | && i.tm.opcode_modifier.mnemonicsize == IGNORESIZE) |
10053 | | /* Do nothing if the instruction is going to ignore the prefix. */ |
10054 | 0 | ; |
10055 | 0 | else |
10056 | 0 | abort (); |
10057 | | |
10058 | | /* Undo the movsx/movzx change done above. */ |
10059 | 0 | i.operands = numop; |
10060 | 0 | } |
10061 | 2.89k | else if (i.tm.opcode_modifier.mnemonicsize == DEFAULTSIZE |
10062 | 2.89k | && !i.suffix) |
10063 | 340 | { |
10064 | 340 | i.suffix = stackop_size; |
10065 | 340 | if (stackop_size == LONG_MNEM_SUFFIX) |
10066 | 0 | { |
10067 | | /* stackop_size is set to LONG_MNEM_SUFFIX for the |
10068 | | .code16gcc directive to support 16-bit mode with |
10069 | | 32-bit address. For IRET without a suffix, generate |
10070 | | 16-bit IRET (opcode 0xcf) to return from an interrupt |
10071 | | handler. */ |
10072 | 0 | if (i.tm.base_opcode == 0xcf) |
10073 | 0 | { |
10074 | 0 | i.suffix = WORD_MNEM_SUFFIX; |
10075 | 0 | as_warn (_("generating 16-bit `iret' for .code16gcc directive")); |
10076 | 0 | } |
10077 | | /* Warn about changed behavior for segment register push/pop. */ |
10078 | 0 | else if ((i.tm.base_opcode | 1) == 0x07) |
10079 | 0 | as_warn (_("generating 32-bit `%s', unlike earlier gas versions"), |
10080 | 0 | insn_name (&i.tm)); |
10081 | 0 | } |
10082 | 340 | } |
10083 | 2.55k | else if (!i.suffix |
10084 | 2.55k | && (i.tm.opcode_modifier.jump == JUMP_ABSOLUTE |
10085 | 2.44k | || i.tm.opcode_modifier.jump == JUMP_BYTE |
10086 | 2.44k | || i.tm.opcode_modifier.jump == JUMP_INTERSEGMENT |
10087 | 2.44k | || (i.tm.opcode_space == SPACE_0F |
10088 | 2.44k | && i.tm.base_opcode == 0x01 /* [ls][gi]dt */ |
10089 | 2.44k | && i.tm.extension_opcode <= 3))) |
10090 | 197 | { |
10091 | 197 | switch (flag_code) |
10092 | 197 | { |
10093 | 138 | case CODE_64BIT: |
10094 | 138 | if (!i.tm.opcode_modifier.no_qsuf) |
10095 | 138 | { |
10096 | 138 | if (i.tm.opcode_modifier.jump == JUMP_BYTE |
10097 | 138 | || i.tm.opcode_modifier.no_lsuf) |
10098 | 138 | i.suffix = QWORD_MNEM_SUFFIX; |
10099 | 138 | break; |
10100 | 138 | } |
10101 | | /* Fall through. */ |
10102 | 26 | case CODE_32BIT: |
10103 | 26 | if (!i.tm.opcode_modifier.no_lsuf) |
10104 | 26 | i.suffix = LONG_MNEM_SUFFIX; |
10105 | 26 | break; |
10106 | 33 | case CODE_16BIT: |
10107 | 33 | if (!i.tm.opcode_modifier.no_wsuf) |
10108 | 33 | i.suffix = WORD_MNEM_SUFFIX; |
10109 | 33 | break; |
10110 | 197 | } |
10111 | 197 | } |
10112 | | |
10113 | 2.92k | if (!i.suffix |
10114 | 2.92k | && (i.tm.opcode_modifier.mnemonicsize != DEFAULTSIZE |
10115 | | /* Also cover lret/retf/iret in 64-bit mode. */ |
10116 | 2.58k | || (flag_code == CODE_64BIT |
10117 | 340 | && !i.tm.opcode_modifier.no_lsuf |
10118 | 340 | && !i.tm.opcode_modifier.no_qsuf)) |
10119 | 2.92k | && i.tm.opcode_modifier.mnemonicsize != IGNORESIZE |
10120 | | /* Explicit sizing prefixes are assumed to disambiguate insns. */ |
10121 | 2.92k | && !i.prefix[DATA_PREFIX] && !(i.prefix[REX_PREFIX] & REX_W) |
10122 | | /* Accept FLDENV et al without suffix. */ |
10123 | 2.92k | && (i.tm.opcode_modifier.no_ssuf || i.tm.opcode_modifier.floatmf)) |
10124 | 2.24k | { |
10125 | 2.24k | unsigned int suffixes, evex = 0; |
10126 | | |
10127 | 2.24k | suffixes = !i.tm.opcode_modifier.no_bsuf; |
10128 | 2.24k | if (!i.tm.opcode_modifier.no_wsuf) |
10129 | 1.78k | suffixes |= 1 << 1; |
10130 | 2.24k | if (!i.tm.opcode_modifier.no_lsuf) |
10131 | 1.78k | suffixes |= 1 << 2; |
10132 | 2.24k | if (!i.tm.opcode_modifier.no_ssuf) |
10133 | 0 | suffixes |= 1 << 4; |
10134 | 2.24k | if (flag_code == CODE_64BIT && !i.tm.opcode_modifier.no_qsuf) |
10135 | 55 | suffixes |= 1 << 5; |
10136 | | |
10137 | | /* Operand size may be ambiguous only across multiple templates. Avoid |
10138 | | the extra effort though if we already know that multiple suffixes / |
10139 | | operand sizes are allowed. Also limit this to non-SIMD operand sizes |
10140 | | (i.e. ones expressable via suffixes) for now. |
10141 | | There's one special case though that needs excluding: Insns taking |
10142 | | Disp<N> operands also match templates permitting BaseIndex. JMP in |
10143 | | particular would thus wrongly trigger the check further down. Cover |
10144 | | JUMP_DWORD insns here as well, just in case. */ |
10145 | 2.24k | if (i.tm.opcode_modifier.jump != JUMP |
10146 | 2.24k | && i.tm.opcode_modifier.jump != JUMP_DWORD) |
10147 | 2.09k | while (!(suffixes & (suffixes - 1))) |
10148 | 304 | { |
10149 | | /* Sadly check_VecOperands(), running ahead of install_template(), |
10150 | | may update i.memshift. Save and restore the value here. */ |
10151 | 304 | unsigned int memshift = i.memshift; |
10152 | | |
10153 | 304 | current_templates.start = t + 1; |
10154 | 304 | t = match_template (0); |
10155 | 304 | i.memshift = memshift; |
10156 | 304 | if (t == NULL) |
10157 | 304 | break; |
10158 | 0 | if (!t->opcode_modifier.no_bsuf) |
10159 | 0 | suffixes |= 1 << 0; |
10160 | 0 | if (!t->opcode_modifier.no_wsuf) |
10161 | 0 | suffixes |= 1 << 1; |
10162 | 0 | if (!t->opcode_modifier.no_lsuf) |
10163 | 0 | suffixes |= 1 << 2; |
10164 | 0 | if (!t->opcode_modifier.no_ssuf) |
10165 | 0 | suffixes |= 1 << 4; |
10166 | 0 | if (flag_code == CODE_64BIT && !t->opcode_modifier.no_qsuf) |
10167 | 0 | suffixes |= 1 << 5; |
10168 | 0 | } |
10169 | | |
10170 | | /* For [XYZ]MMWORD operands inspect operand sizes. While generally |
10171 | | also suitable for AT&T syntax mode, it was requested that this be |
10172 | | restricted to just Intel syntax. */ |
10173 | 2.24k | if (intel_syntax && is_any_vex_encoding (&i.tm) |
10174 | 2.24k | && !i.broadcast.type && !i.broadcast.bytes) |
10175 | 0 | { |
10176 | 0 | unsigned int op; |
10177 | |
|
10178 | 0 | for (op = 0; op < i.tm.operands; ++op) |
10179 | 0 | { |
10180 | 0 | if (vector_size < VSZ512) |
10181 | 0 | { |
10182 | 0 | i.tm.operand_types[op].bitfield.zmmword = 0; |
10183 | 0 | if (vector_size < VSZ256) |
10184 | 0 | { |
10185 | 0 | i.tm.operand_types[op].bitfield.ymmword = 0; |
10186 | 0 | if (i.tm.operand_types[op].bitfield.xmmword |
10187 | 0 | && i.tm.opcode_modifier.evex == EVEXDYN) |
10188 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
10189 | 0 | } |
10190 | 0 | else if (i.tm.operand_types[op].bitfield.ymmword |
10191 | 0 | && !i.tm.operand_types[op].bitfield.xmmword |
10192 | 0 | && i.tm.opcode_modifier.evex == EVEXDYN) |
10193 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
10194 | 0 | } |
10195 | 0 | else if (i.tm.opcode_modifier.evex |
10196 | 0 | && !cpu_arch_flags.bitfield.cpuavx512vl) |
10197 | 0 | { |
10198 | 0 | if (i.tm.operand_types[op].bitfield.ymmword) |
10199 | 0 | i.tm.operand_types[op].bitfield.xmmword = 0; |
10200 | 0 | if (i.tm.operand_types[op].bitfield.zmmword) |
10201 | 0 | i.tm.operand_types[op].bitfield.ymmword = 0; |
10202 | 0 | if (i.tm.opcode_modifier.evex == EVEXDYN) |
10203 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
10204 | 0 | } |
10205 | |
|
10206 | 0 | if (i.tm.operand_types[op].bitfield.xmmword |
10207 | 0 | + i.tm.operand_types[op].bitfield.ymmword |
10208 | 0 | + i.tm.operand_types[op].bitfield.zmmword < 2) |
10209 | 0 | continue; |
10210 | | |
10211 | | /* Any properly sized operand disambiguates the insn. */ |
10212 | 0 | if (i.types[op].bitfield.xmmword |
10213 | 0 | || i.types[op].bitfield.ymmword |
10214 | 0 | || i.types[op].bitfield.zmmword) |
10215 | 0 | { |
10216 | 0 | suffixes &= ~(7 << 6); |
10217 | 0 | evex = 0; |
10218 | 0 | break; |
10219 | 0 | } |
10220 | | |
10221 | 0 | if ((i.flags[op] & Operand_Mem) |
10222 | 0 | && i.tm.operand_types[op].bitfield.unspecified) |
10223 | 0 | { |
10224 | 0 | if (i.tm.operand_types[op].bitfield.xmmword) |
10225 | 0 | suffixes |= 1 << 6; |
10226 | 0 | if (i.tm.operand_types[op].bitfield.ymmword) |
10227 | 0 | suffixes |= 1 << 7; |
10228 | 0 | if (i.tm.operand_types[op].bitfield.zmmword) |
10229 | 0 | suffixes |= 1 << 8; |
10230 | 0 | if (i.tm.opcode_modifier.evex) |
10231 | 0 | evex = EVEX512; |
10232 | 0 | } |
10233 | 0 | } |
10234 | 0 | } |
10235 | | |
10236 | | /* Are multiple suffixes / operand sizes allowed? */ |
10237 | 2.24k | if (suffixes & (suffixes - 1)) |
10238 | 1.78k | { |
10239 | 1.78k | if (intel_syntax |
10240 | 1.78k | && (i.tm.opcode_modifier.mnemonicsize != DEFAULTSIZE |
10241 | 0 | || operand_check == check_error)) |
10242 | 0 | { |
10243 | 0 | as_bad (_("ambiguous operand size for `%s'"), insn_name (&i.tm)); |
10244 | 0 | return 0; |
10245 | 0 | } |
10246 | 1.78k | if (operand_check == check_error) |
10247 | 0 | { |
10248 | 0 | as_bad (_("no instruction mnemonic suffix given and " |
10249 | 0 | "no register operands; can't size `%s'"), insn_name (&i.tm)); |
10250 | 0 | return 0; |
10251 | 0 | } |
10252 | 1.78k | if (operand_check == check_warning) |
10253 | 1.78k | as_warn (_("%s; using default for `%s'"), |
10254 | 1.78k | intel_syntax |
10255 | 1.78k | ? _("ambiguous operand size") |
10256 | 1.78k | : _("no instruction mnemonic suffix given and " |
10257 | 1.78k | "no register operands"), |
10258 | 1.78k | insn_name (&i.tm)); |
10259 | | |
10260 | 1.78k | if (i.tm.opcode_modifier.floatmf) |
10261 | 0 | i.suffix = SHORT_MNEM_SUFFIX; |
10262 | 1.78k | else if (is_movx) |
10263 | 0 | /* handled below */; |
10264 | 1.78k | else if (evex) |
10265 | 0 | i.tm.opcode_modifier.evex = evex; |
10266 | 1.78k | else if (flag_code == CODE_16BIT) |
10267 | 193 | i.suffix = WORD_MNEM_SUFFIX; |
10268 | 1.59k | else if (!i.tm.opcode_modifier.no_lsuf) |
10269 | 1.59k | i.suffix = LONG_MNEM_SUFFIX; |
10270 | 0 | else |
10271 | 0 | i.suffix = QWORD_MNEM_SUFFIX; |
10272 | 1.78k | } |
10273 | 2.24k | } |
10274 | | |
10275 | 2.92k | if (is_movx) |
10276 | 0 | { |
10277 | | /* In Intel syntax, movsx/movzx must have a "suffix" (checked above). |
10278 | | In AT&T syntax, if there is no suffix (warned about above), the default |
10279 | | will be byte extension. */ |
10280 | 0 | if (i.tm.opcode_modifier.w && i.suffix && i.suffix != BYTE_MNEM_SUFFIX) |
10281 | 0 | i.tm.base_opcode |= 1; |
10282 | | |
10283 | | /* For further processing, the suffix should represent the destination |
10284 | | (register). This is already the case when one was used with |
10285 | | mov[sz][bw]*, but we need to replace it for mov[sz]x, or if there was |
10286 | | no suffix to begin with. */ |
10287 | 0 | if (i.tm.opcode_modifier.w || i.tm.base_opcode == 0x63 || !i.suffix) |
10288 | 0 | { |
10289 | 0 | if (i.types[1].bitfield.word) |
10290 | 0 | i.suffix = WORD_MNEM_SUFFIX; |
10291 | 0 | else if (i.types[1].bitfield.qword) |
10292 | 0 | i.suffix = QWORD_MNEM_SUFFIX; |
10293 | 0 | else |
10294 | 0 | i.suffix = LONG_MNEM_SUFFIX; |
10295 | |
|
10296 | 0 | i.tm.opcode_modifier.w = 0; |
10297 | 0 | } |
10298 | 0 | } |
10299 | | |
10300 | 2.92k | if (!i.tm.opcode_modifier.modrm && i.reg_operands && i.tm.operands < 3) |
10301 | 0 | i.short_form = (i.tm.operand_types[0].bitfield.class == Reg) |
10302 | 0 | != (i.tm.operand_types[1].bitfield.class == Reg); |
10303 | | |
10304 | | /* Change the opcode based on the operand size given by i.suffix. */ |
10305 | 2.92k | switch (i.suffix) |
10306 | 2.92k | { |
10307 | | /* Size floating point instruction. */ |
10308 | 1.63k | case LONG_MNEM_SUFFIX: |
10309 | 1.63k | if (i.tm.opcode_modifier.floatmf) |
10310 | 0 | { |
10311 | 0 | i.tm.base_opcode ^= 4; |
10312 | 0 | break; |
10313 | 0 | } |
10314 | | /* fall through */ |
10315 | 1.86k | case WORD_MNEM_SUFFIX: |
10316 | 2.00k | case QWORD_MNEM_SUFFIX: |
10317 | | /* It's not a byte, select word/dword operation. */ |
10318 | 2.00k | if (i.tm.opcode_modifier.w) |
10319 | 1.42k | { |
10320 | 1.42k | if (i.short_form) |
10321 | 0 | i.tm.base_opcode |= 8; |
10322 | 1.42k | else |
10323 | 1.42k | i.tm.base_opcode |= 1; |
10324 | 1.42k | } |
10325 | | |
10326 | | /* Set mode64 for an operand. */ |
10327 | 2.00k | if (i.suffix == QWORD_MNEM_SUFFIX) |
10328 | 148 | { |
10329 | 148 | if (flag_code == CODE_64BIT |
10330 | 148 | && !i.tm.opcode_modifier.norex64 |
10331 | 148 | && !i.tm.opcode_modifier.vexw |
10332 | | /* Special case for xchg %rax,%rax. It is NOP and doesn't |
10333 | | need rex64. */ |
10334 | 148 | && ! (i.operands == 2 |
10335 | 10 | && i.tm.base_opcode == 0x90 |
10336 | 10 | && i.tm.opcode_space == SPACE_BASE |
10337 | 10 | && i.types[0].bitfield.instance == Accum |
10338 | 10 | && i.types[1].bitfield.instance == Accum)) |
10339 | 10 | i.rex |= REX_W; |
10340 | | |
10341 | 148 | break; |
10342 | 148 | } |
10343 | | |
10344 | | /* fall through */ |
10345 | 1.86k | case SHORT_MNEM_SUFFIX: |
10346 | | /* Now select between word & dword operations via the operand |
10347 | | size prefix, except for instructions that will ignore this |
10348 | | prefix anyway. */ |
10349 | 1.86k | if (i.tm.opcode_modifier.mnemonicsize != IGNORESIZE |
10350 | 1.86k | && !i.tm.opcode_modifier.floatmf |
10351 | 1.86k | && (!is_any_vex_encoding (&i.tm) |
10352 | 1.85k | || i.tm.opcode_space == SPACE_MAP4) |
10353 | 1.86k | && ((i.suffix == LONG_MNEM_SUFFIX) == (flag_code == CODE_16BIT) |
10354 | 1.85k | || (flag_code == CODE_64BIT |
10355 | 1.85k | && i.tm.opcode_modifier.jump == JUMP_BYTE))) |
10356 | 3 | { |
10357 | 3 | unsigned int prefix = DATA_PREFIX_OPCODE; |
10358 | | |
10359 | 3 | if (i.tm.opcode_modifier.jump == JUMP_BYTE) /* jcxz, loop */ |
10360 | 0 | prefix = ADDR_PREFIX_OPCODE; |
10361 | | |
10362 | | /* The DATA PREFIX of EVEX promoted from legacy APX instructions |
10363 | | needs to be adjusted. */ |
10364 | 3 | if (i.tm.opcode_space == SPACE_MAP4) |
10365 | 0 | { |
10366 | 0 | gas_assert (!i.tm.opcode_modifier.opcodeprefix); |
10367 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0X66; |
10368 | 0 | } |
10369 | 3 | else if (!add_prefix (prefix)) |
10370 | 0 | return 0; |
10371 | 3 | } |
10372 | | |
10373 | 1.86k | break; |
10374 | | |
10375 | 1.86k | case 0: |
10376 | | /* Select word/dword/qword operation with explicit data sizing prefix |
10377 | | when there are no suitable register operands. */ |
10378 | 801 | if (i.tm.opcode_modifier.w |
10379 | 801 | && (i.prefix[DATA_PREFIX] || (i.prefix[REX_PREFIX] & REX_W)) |
10380 | 801 | && (!i.reg_operands |
10381 | 0 | || (i.reg_operands == 1 |
10382 | | /* ShiftCount */ |
10383 | 0 | && (i.tm.operand_types[0].bitfield.instance == RegC |
10384 | | /* InOutPortReg */ |
10385 | 0 | || i.tm.operand_types[0].bitfield.instance == RegD |
10386 | 0 | || i.tm.operand_types[1].bitfield.instance == RegD |
10387 | 0 | || i.tm.mnem_off == MN_crc32)))) |
10388 | 0 | i.tm.base_opcode |= 1; |
10389 | 801 | break; |
10390 | 2.92k | } |
10391 | | |
10392 | 2.92k | if (i.tm.opcode_modifier.operandconstraint == ADDR_PREFIX_OP_REG) |
10393 | 0 | { |
10394 | 0 | gas_assert (!i.suffix); |
10395 | 0 | gas_assert (i.reg_operands); |
10396 | | |
10397 | 0 | if (i.tm.operand_types[0].bitfield.instance == Accum |
10398 | 0 | || i.operands == 1) |
10399 | 0 | { |
10400 | | /* The address size override prefix changes the size of the |
10401 | | first operand. */ |
10402 | 0 | if (flag_code == CODE_64BIT |
10403 | 0 | && i.op[0].regs->reg_type.bitfield.word) |
10404 | 0 | { |
10405 | 0 | as_bad (_("16-bit addressing unavailable for `%s'"), |
10406 | 0 | insn_name (&i.tm)); |
10407 | 0 | return 0; |
10408 | 0 | } |
10409 | | |
10410 | 0 | if ((flag_code == CODE_32BIT |
10411 | 0 | ? i.op[0].regs->reg_type.bitfield.word |
10412 | 0 | : i.op[0].regs->reg_type.bitfield.dword) |
10413 | 0 | && !add_prefix (ADDR_PREFIX_OPCODE)) |
10414 | 0 | return 0; |
10415 | 0 | } |
10416 | 0 | else |
10417 | 0 | { |
10418 | | /* Check invalid register operand when the address size override |
10419 | | prefix changes the size of register operands. */ |
10420 | 0 | unsigned int op; |
10421 | 0 | enum { need_word, need_dword, need_qword } need; |
10422 | | |
10423 | | /* Check the register operand for the address size prefix if |
10424 | | the memory operand has no real registers, like symbol, DISP |
10425 | | or bogus (x32-only) symbol(%rip) when symbol(%eip) is meant. */ |
10426 | 0 | if (i.mem_operands == 1 |
10427 | 0 | && i.reg_operands == 1 |
10428 | 0 | && i.operands == 2 |
10429 | 0 | && i.types[1].bitfield.class == Reg |
10430 | 0 | && (flag_code == CODE_32BIT |
10431 | 0 | ? i.op[1].regs->reg_type.bitfield.word |
10432 | 0 | : i.op[1].regs->reg_type.bitfield.dword) |
10433 | 0 | && ((i.base_reg == NULL && i.index_reg == NULL) |
10434 | 0 | #ifdef OBJ_ELF |
10435 | 0 | || (x86_elf_abi == X86_64_X32_ABI |
10436 | 0 | && i.base_reg |
10437 | 0 | && i.base_reg->reg_num == RegIP |
10438 | 0 | && i.base_reg->reg_type.bitfield.qword)) |
10439 | | #else |
10440 | | || 0) |
10441 | | #endif |
10442 | 0 | && !add_prefix (ADDR_PREFIX_OPCODE)) |
10443 | 0 | return 0; |
10444 | | |
10445 | 0 | if (flag_code == CODE_32BIT) |
10446 | 0 | need = i.prefix[ADDR_PREFIX] ? need_word : need_dword; |
10447 | 0 | else if (i.prefix[ADDR_PREFIX]) |
10448 | 0 | need = need_dword; |
10449 | 0 | else |
10450 | 0 | need = flag_code == CODE_64BIT ? need_qword : need_word; |
10451 | |
|
10452 | 0 | for (op = i.imm_operands; op < i.operands; op++) |
10453 | 0 | { |
10454 | 0 | if (i.types[op].bitfield.class != Reg) |
10455 | 0 | continue; |
10456 | | |
10457 | 0 | switch (need) |
10458 | 0 | { |
10459 | 0 | case need_word: |
10460 | 0 | if (i.op[op].regs->reg_type.bitfield.word) |
10461 | 0 | continue; |
10462 | 0 | break; |
10463 | 0 | case need_dword: |
10464 | 0 | if (i.op[op].regs->reg_type.bitfield.dword) |
10465 | 0 | continue; |
10466 | 0 | break; |
10467 | 0 | case need_qword: |
10468 | 0 | if (i.op[op].regs->reg_type.bitfield.qword) |
10469 | 0 | continue; |
10470 | 0 | break; |
10471 | 0 | } |
10472 | | |
10473 | 0 | as_bad (_("invalid register operand size for `%s'"), |
10474 | 0 | insn_name (&i.tm)); |
10475 | 0 | return 0; |
10476 | 0 | } |
10477 | 0 | } |
10478 | 0 | } |
10479 | | |
10480 | 2.92k | return 1; |
10481 | 2.92k | } |
10482 | | |
10483 | | static int |
10484 | | check_byte_reg (void) |
10485 | 0 | { |
10486 | 0 | int op; |
10487 | |
|
10488 | 0 | for (op = i.operands; --op >= 0;) |
10489 | 0 | { |
10490 | | /* Skip non-register operands. */ |
10491 | 0 | if (i.types[op].bitfield.class != Reg) |
10492 | 0 | continue; |
10493 | | |
10494 | | /* If this is an eight bit register, it's OK. */ |
10495 | 0 | if (i.types[op].bitfield.byte) |
10496 | 0 | { |
10497 | 0 | if (i.tm.opcode_modifier.checkoperandsize) |
10498 | 0 | break; |
10499 | 0 | continue; |
10500 | 0 | } |
10501 | | |
10502 | | /* I/O port address operands are OK too. */ |
10503 | 0 | if (i.tm.operand_types[op].bitfield.instance == RegD |
10504 | 0 | && i.tm.operand_types[op].bitfield.word) |
10505 | 0 | continue; |
10506 | | |
10507 | | /* crc32 only wants its source operand checked here. */ |
10508 | 0 | if (i.tm.mnem_off == MN_crc32 && op != 0) |
10509 | 0 | continue; |
10510 | | |
10511 | | /* Any other register is bad. */ |
10512 | 0 | as_bad (_("`%s%s' not allowed with `%s%c'"), |
10513 | 0 | register_prefix, i.op[op].regs->reg_name, |
10514 | 0 | insn_name (&i.tm), i.suffix); |
10515 | 0 | return 0; |
10516 | 0 | } |
10517 | 0 | return 1; |
10518 | 0 | } |
10519 | | |
10520 | | static int |
10521 | | check_long_reg (void) |
10522 | 0 | { |
10523 | 0 | int op; |
10524 | |
|
10525 | 0 | for (op = i.operands; --op >= 0;) |
10526 | | /* Skip non-register operands. */ |
10527 | 0 | if (i.types[op].bitfield.class != Reg) |
10528 | 0 | continue; |
10529 | | /* Reject eight bit registers, except where the template requires |
10530 | | them. (eg. movzb) */ |
10531 | 0 | else if (i.types[op].bitfield.byte |
10532 | 0 | && (i.tm.operand_types[op].bitfield.word |
10533 | 0 | || i.tm.operand_types[op].bitfield.dword |
10534 | 0 | || i.tm.operand_types[op].bitfield.qword)) |
10535 | 0 | { |
10536 | 0 | as_bad (_("`%s%s' not allowed with `%s%c'"), |
10537 | 0 | register_prefix, |
10538 | 0 | i.op[op].regs->reg_name, |
10539 | 0 | insn_name (&i.tm), |
10540 | 0 | i.suffix); |
10541 | 0 | return 0; |
10542 | 0 | } |
10543 | | /* Error if the e prefix on a general reg is missing, or if the r |
10544 | | prefix on a general reg is present. */ |
10545 | 0 | else if ((i.types[op].bitfield.word |
10546 | 0 | || i.types[op].bitfield.qword) |
10547 | 0 | && i.tm.operand_types[op].bitfield.dword) |
10548 | 0 | { |
10549 | 0 | as_bad (_("incorrect register `%s%s' used with `%c' suffix"), |
10550 | 0 | register_prefix, i.op[op].regs->reg_name, |
10551 | 0 | i.suffix); |
10552 | 0 | return 0; |
10553 | 0 | } |
10554 | 0 | else if (i.tm.opcode_modifier.checkoperandsize) |
10555 | 0 | break; |
10556 | | |
10557 | 0 | return 1; |
10558 | 0 | } |
10559 | | |
10560 | | static int |
10561 | | check_qword_reg (void) |
10562 | 0 | { |
10563 | 0 | int op; |
10564 | |
|
10565 | 0 | for (op = i.operands; --op >= 0; ) |
10566 | | /* Skip non-register operands. */ |
10567 | 0 | if (i.types[op].bitfield.class != Reg) |
10568 | 0 | continue; |
10569 | | /* Reject eight bit registers, except where the template requires |
10570 | | them. (eg. movzb) */ |
10571 | 0 | else if (i.types[op].bitfield.byte |
10572 | 0 | && (i.tm.operand_types[op].bitfield.word |
10573 | 0 | || i.tm.operand_types[op].bitfield.dword |
10574 | 0 | || i.tm.operand_types[op].bitfield.qword)) |
10575 | 0 | { |
10576 | 0 | as_bad (_("`%s%s' not allowed with `%s%c'"), |
10577 | 0 | register_prefix, |
10578 | 0 | i.op[op].regs->reg_name, |
10579 | 0 | insn_name (&i.tm), |
10580 | 0 | i.suffix); |
10581 | 0 | return 0; |
10582 | 0 | } |
10583 | | /* Error if the r prefix on a general reg is missing. */ |
10584 | 0 | else if ((i.types[op].bitfield.word |
10585 | 0 | || i.types[op].bitfield.dword) |
10586 | 0 | && i.tm.operand_types[op].bitfield.qword) |
10587 | 0 | { |
10588 | 0 | as_bad (_("incorrect register `%s%s' used with `%c' suffix"), |
10589 | 0 | register_prefix, i.op[op].regs->reg_name, i.suffix); |
10590 | 0 | return 0; |
10591 | 0 | } |
10592 | 0 | else if (i.tm.opcode_modifier.checkoperandsize) |
10593 | 0 | break; |
10594 | | |
10595 | 0 | return 1; |
10596 | 0 | } |
10597 | | |
10598 | | static int |
10599 | | check_word_reg (void) |
10600 | 0 | { |
10601 | 0 | int op; |
10602 | 0 | for (op = i.operands; --op >= 0;) |
10603 | | /* Skip non-register operands. */ |
10604 | 0 | if (i.types[op].bitfield.class != Reg) |
10605 | 0 | continue; |
10606 | | /* Reject eight bit registers, except where the template requires |
10607 | | them. (eg. movzb) */ |
10608 | 0 | else if (i.types[op].bitfield.byte |
10609 | 0 | && (i.tm.operand_types[op].bitfield.word |
10610 | 0 | || i.tm.operand_types[op].bitfield.dword |
10611 | 0 | || i.tm.operand_types[op].bitfield.qword)) |
10612 | 0 | { |
10613 | 0 | as_bad (_("`%s%s' not allowed with `%s%c'"), |
10614 | 0 | register_prefix, |
10615 | 0 | i.op[op].regs->reg_name, |
10616 | 0 | insn_name (&i.tm), |
10617 | 0 | i.suffix); |
10618 | 0 | return 0; |
10619 | 0 | } |
10620 | | /* Error if the e or r prefix on a general reg is present. */ |
10621 | 0 | else if ((i.types[op].bitfield.dword |
10622 | 0 | || i.types[op].bitfield.qword) |
10623 | 0 | && i.tm.operand_types[op].bitfield.word) |
10624 | 0 | { |
10625 | 0 | as_bad (_("incorrect register `%s%s' used with `%c' suffix"), |
10626 | 0 | register_prefix, i.op[op].regs->reg_name, |
10627 | 0 | i.suffix); |
10628 | 0 | return 0; |
10629 | 0 | } |
10630 | 0 | else if (i.tm.opcode_modifier.checkoperandsize) |
10631 | 0 | break; |
10632 | | |
10633 | 0 | return 1; |
10634 | 0 | } |
10635 | | |
10636 | | static int |
10637 | | update_imm (unsigned int j) |
10638 | 4.46k | { |
10639 | 4.46k | i386_operand_type overlap = i.types[j]; |
10640 | | |
10641 | 4.46k | if (i.tm.operand_types[j].bitfield.imm8 |
10642 | 4.46k | && i.tm.operand_types[j].bitfield.imm8s |
10643 | 4.46k | && overlap.bitfield.imm8 && overlap.bitfield.imm8s) |
10644 | 23 | { |
10645 | | /* This combination is used on 8-bit immediates where e.g. $~0 is |
10646 | | desirable to permit. We're past operand type matching, so simply |
10647 | | put things back in the shape they were before introducing the |
10648 | | distinction between Imm8, Imm8S, and Imm8|Imm8S. */ |
10649 | 23 | overlap.bitfield.imm8s = 0; |
10650 | 23 | } |
10651 | | |
10652 | 4.46k | if (overlap.bitfield.imm8 |
10653 | 4.46k | + overlap.bitfield.imm8s |
10654 | 4.46k | + overlap.bitfield.imm16 |
10655 | 4.46k | + overlap.bitfield.imm32 |
10656 | 4.46k | + overlap.bitfield.imm32s |
10657 | 4.46k | + overlap.bitfield.imm64 > 1) |
10658 | 410 | { |
10659 | 410 | static const i386_operand_type imm16 = { .bitfield = { .imm16 = 1 } }; |
10660 | 410 | static const i386_operand_type imm32 = { .bitfield = { .imm32 = 1 } }; |
10661 | 410 | static const i386_operand_type imm32s = { .bitfield = { .imm32s = 1 } }; |
10662 | 410 | static const i386_operand_type imm16_32 = { .bitfield = |
10663 | 410 | { .imm16 = 1, .imm32 = 1 } |
10664 | 410 | }; |
10665 | 410 | static const i386_operand_type imm16_32s = { .bitfield = |
10666 | 410 | { .imm16 = 1, .imm32s = 1 } |
10667 | 410 | }; |
10668 | 410 | static const i386_operand_type imm16_32_32s = { .bitfield = |
10669 | 410 | { .imm16 = 1, .imm32 = 1, .imm32s = 1 } |
10670 | 410 | }; |
10671 | | |
10672 | 410 | if (i.suffix) |
10673 | 410 | { |
10674 | 410 | i386_operand_type temp; |
10675 | | |
10676 | 410 | operand_type_set (&temp, 0); |
10677 | 410 | if (i.suffix == BYTE_MNEM_SUFFIX) |
10678 | 67 | { |
10679 | 67 | temp.bitfield.imm8 = overlap.bitfield.imm8; |
10680 | 67 | temp.bitfield.imm8s = overlap.bitfield.imm8s; |
10681 | 67 | } |
10682 | 343 | else if (i.suffix == WORD_MNEM_SUFFIX) |
10683 | 28 | temp.bitfield.imm16 = overlap.bitfield.imm16; |
10684 | 315 | else if (i.suffix == QWORD_MNEM_SUFFIX) |
10685 | 0 | { |
10686 | 0 | temp.bitfield.imm64 = overlap.bitfield.imm64; |
10687 | 0 | temp.bitfield.imm32s = overlap.bitfield.imm32s; |
10688 | 0 | } |
10689 | 315 | else |
10690 | 315 | temp.bitfield.imm32 = overlap.bitfield.imm32; |
10691 | 410 | overlap = temp; |
10692 | 410 | } |
10693 | 0 | else if (operand_type_equal (&overlap, &imm16_32_32s) |
10694 | 0 | || operand_type_equal (&overlap, &imm16_32) |
10695 | 0 | || operand_type_equal (&overlap, &imm16_32s)) |
10696 | 0 | { |
10697 | 0 | if ((flag_code == CODE_16BIT) |
10698 | 0 | ^ (i.prefix[DATA_PREFIX] != 0 && !(i.prefix[REX_PREFIX] & REX_W))) |
10699 | 0 | overlap = imm16; |
10700 | 0 | else |
10701 | 0 | overlap = imm32s; |
10702 | 0 | } |
10703 | 0 | else if (i.prefix[REX_PREFIX] & REX_W) |
10704 | 0 | overlap = operand_type_and (overlap, imm32s); |
10705 | 0 | else if (i.prefix[DATA_PREFIX]) |
10706 | 0 | overlap = operand_type_and (overlap, |
10707 | 0 | flag_code != CODE_16BIT ? imm16 : imm32); |
10708 | 410 | if (overlap.bitfield.imm8 |
10709 | 410 | + overlap.bitfield.imm8s |
10710 | 410 | + overlap.bitfield.imm16 |
10711 | 410 | + overlap.bitfield.imm32 |
10712 | 410 | + overlap.bitfield.imm32s |
10713 | 410 | + overlap.bitfield.imm64 != 1) |
10714 | 0 | { |
10715 | 0 | as_bad (_("no instruction mnemonic suffix given; " |
10716 | 0 | "can't determine immediate size")); |
10717 | 0 | return 0; |
10718 | 0 | } |
10719 | 410 | } |
10720 | 4.46k | i.types[j] = overlap; |
10721 | | |
10722 | 4.46k | return 1; |
10723 | 4.46k | } |
10724 | | |
10725 | | static int |
10726 | | finalize_imm (void) |
10727 | 2.92k | { |
10728 | 2.92k | unsigned int j, n; |
10729 | | |
10730 | | /* Update the first 2 immediate operands. */ |
10731 | 2.92k | n = i.operands > 2 ? 2 : i.operands; |
10732 | 2.92k | if (n) |
10733 | 2.62k | { |
10734 | 7.09k | for (j = 0; j < n; j++) |
10735 | 4.46k | if (update_imm (j) == 0) |
10736 | 0 | return 0; |
10737 | | |
10738 | | /* The 3rd operand can't be immediate operand. */ |
10739 | 2.62k | gas_assert (operand_type_check (i.types[2], imm) == 0); |
10740 | 2.62k | } |
10741 | | |
10742 | 2.92k | return 1; |
10743 | 2.92k | } |
10744 | | |
10745 | | static INLINE void set_rex_vrex (const reg_entry *r, unsigned int rex_bit, |
10746 | | bool do_sse2avx) |
10747 | 0 | { |
10748 | 0 | if (r->reg_flags & RegRex) |
10749 | 0 | { |
10750 | 0 | if (i.rex & rex_bit) |
10751 | 0 | as_bad (_("same type of prefix used twice")); |
10752 | 0 | i.rex |= rex_bit; |
10753 | 0 | } |
10754 | 0 | else if (do_sse2avx && (i.rex & rex_bit) && i.vex.register_specifier) |
10755 | 0 | { |
10756 | 0 | gas_assert (i.vex.register_specifier == r); |
10757 | 0 | i.vex.register_specifier += 8; |
10758 | 0 | } |
10759 | | |
10760 | 0 | if (r->reg_flags & RegVRex) |
10761 | 0 | i.vrex |= rex_bit; |
10762 | |
|
10763 | 0 | if (r->reg_flags & RegRex2) |
10764 | 0 | i.rex2 |= rex_bit; |
10765 | 0 | } |
10766 | | |
10767 | | static INLINE void |
10768 | | set_rex_rex2 (const reg_entry *r, unsigned int rex_bit) |
10769 | 0 | { |
10770 | 0 | if ((r->reg_flags & RegRex) != 0) |
10771 | 0 | i.rex |= rex_bit; |
10772 | 0 | if ((r->reg_flags & RegRex2) != 0) |
10773 | 0 | i.rex2 |= rex_bit; |
10774 | 0 | } |
10775 | | |
10776 | | static int |
10777 | | process_operands (void) |
10778 | 2.62k | { |
10779 | | /* Default segment register this instruction will use for memory |
10780 | | accesses. 0 means unknown. This is only for optimizing out |
10781 | | unnecessary segment overrides. */ |
10782 | 2.62k | const reg_entry *default_seg = NULL; |
10783 | | |
10784 | 5.21k | for (unsigned int j = i.imm_operands; j < i.operands; j++) |
10785 | 2.58k | if (i.types[j].bitfield.instance != InstanceNone) |
10786 | 0 | i.reg_operands--; |
10787 | | |
10788 | 2.62k | if (i.tm.opcode_modifier.sse2avx) |
10789 | 0 | { |
10790 | | /* Legacy encoded insns allow explicit REX prefixes, so these prefixes |
10791 | | need converting. */ |
10792 | 0 | i.rex |= i.prefix[REX_PREFIX] & (REX_W | REX_R | REX_X | REX_B); |
10793 | 0 | i.prefix[REX_PREFIX] = 0; |
10794 | 0 | pp.rex_encoding = 0; |
10795 | 0 | pp.rex2_encoding = 0; |
10796 | 0 | } |
10797 | | /* ImmExt should be processed after SSE2AVX. */ |
10798 | 2.62k | else if (i.tm.opcode_modifier.immext) |
10799 | 0 | process_immext (); |
10800 | | |
10801 | | /* TILEZERO is unusual in that it has a single operand encoded in ModR/M.reg, |
10802 | | not ModR/M.rm. To avoid special casing this in build_modrm_byte(), fake a |
10803 | | new destination operand here, while converting the source one to register |
10804 | | number 0. */ |
10805 | 2.62k | if (i.tm.mnem_off == MN_tilezero) |
10806 | 0 | { |
10807 | 0 | copy_operand (1, 0); |
10808 | 0 | i.op[0].regs -= i.op[0].regs->reg_num; |
10809 | 0 | i.operands++; |
10810 | 0 | i.reg_operands++; |
10811 | 0 | i.tm.operands++; |
10812 | 0 | } |
10813 | | |
10814 | 2.62k | if (i.tm.opcode_modifier.sse2avx && i.tm.opcode_modifier.vexvvvv) |
10815 | 0 | { |
10816 | 0 | static const i386_operand_type regxmm = { |
10817 | 0 | .bitfield = { .class = RegSIMD, .xmmword = 1 } |
10818 | 0 | }; |
10819 | 0 | unsigned int dupl = i.operands; |
10820 | 0 | unsigned int dest = dupl - 1; |
10821 | 0 | unsigned int j; |
10822 | | |
10823 | | /* The destination must be an xmm register. */ |
10824 | 0 | gas_assert (i.reg_operands |
10825 | 0 | && MAX_OPERANDS > dupl |
10826 | 0 | && operand_type_equal (&i.types[dest], ®xmm)); |
10827 | | |
10828 | 0 | if (i.tm.operand_types[0].bitfield.instance == Accum |
10829 | 0 | && i.tm.operand_types[0].bitfield.xmmword) |
10830 | 0 | { |
10831 | | /* Keep xmm0 for instructions with VEX prefix and 3 |
10832 | | sources. */ |
10833 | 0 | i.tm.operand_types[0].bitfield.instance = InstanceNone; |
10834 | 0 | i.tm.operand_types[0].bitfield.class = RegSIMD; |
10835 | 0 | i.reg_operands++; |
10836 | 0 | goto duplicate; |
10837 | 0 | } |
10838 | | |
10839 | 0 | if (i.tm.opcode_modifier.operandconstraint == IMPLICIT_1ST_XMM0) |
10840 | 0 | { |
10841 | 0 | gas_assert ((MAX_OPERANDS - 1) > dupl); |
10842 | | |
10843 | | /* Add the implicit xmm0 for instructions with VEX prefix |
10844 | | and 3 sources. */ |
10845 | 0 | for (j = i.operands; j > 0; j--) |
10846 | 0 | copy_operand (j, j - 1); |
10847 | 0 | i.op[0].regs = str_hash_find (reg_hash, "xmm0"); |
10848 | 0 | i.types[0] = regxmm; |
10849 | 0 | i.tm.operand_types[0] = regxmm; |
10850 | |
|
10851 | 0 | i.operands += 2; |
10852 | 0 | i.reg_operands += 2; |
10853 | 0 | i.tm.operands += 2; |
10854 | |
|
10855 | 0 | dupl++; |
10856 | 0 | dest++; |
10857 | 0 | } |
10858 | 0 | else |
10859 | 0 | { |
10860 | 0 | duplicate: |
10861 | 0 | i.operands++; |
10862 | 0 | i.reg_operands++; |
10863 | 0 | i.tm.operands++; |
10864 | 0 | } |
10865 | | |
10866 | 0 | copy_operand (dupl, dest); |
10867 | |
|
10868 | 0 | if (i.tm.opcode_modifier.immext) |
10869 | 0 | process_immext (); |
10870 | 0 | } |
10871 | 2.62k | else if (i.tm.operand_types[0].bitfield.instance == Accum |
10872 | 2.62k | && i.tm.opcode_modifier.modrm) |
10873 | 0 | { |
10874 | 0 | unsigned int j; |
10875 | |
|
10876 | 0 | for (j = 1; j < i.operands; j++) |
10877 | 0 | copy_operand (j - 1, j); |
10878 | | |
10879 | | /* No adjustment to i.reg_operands: This was already done at the top |
10880 | | of the function. */ |
10881 | 0 | i.operands--; |
10882 | 0 | i.tm.operands--; |
10883 | 0 | } |
10884 | 2.62k | else if (i.tm.opcode_modifier.operandconstraint == IMPLICIT_GROUP) |
10885 | 0 | { |
10886 | 0 | unsigned int op, extra; |
10887 | 0 | const reg_entry *first; |
10888 | | |
10889 | | /* The second operand must be {x,y,z,t}mmN. */ |
10890 | 0 | gas_assert ((i.operands == 2 || i.operands == 3) |
10891 | 0 | && i.types[1].bitfield.class == RegSIMD); |
10892 | | |
10893 | 0 | switch (i.types[i.operands - 1].bitfield.class) |
10894 | 0 | { |
10895 | 0 | case RegSIMD: |
10896 | 0 | op = 1; |
10897 | 0 | if (i.operands == 2) |
10898 | 0 | { |
10899 | | /* AMX-TRANSPOSE operand 2: N must be a multiple of 2. */ |
10900 | 0 | extra = 1; |
10901 | 0 | } |
10902 | 0 | else |
10903 | 0 | { |
10904 | | /* AVX512-{4FMAPS,4VNNIW} operand 2: N must be a multiple of 4. */ |
10905 | 0 | extra = 3; |
10906 | 0 | } |
10907 | 0 | break; |
10908 | | |
10909 | 0 | case RegMask: |
10910 | | /* AVX512-VP2INTERSECT operand 3: N must be a multiple of 2. */ |
10911 | 0 | op = 2; |
10912 | 0 | extra = 1; |
10913 | 0 | break; |
10914 | | |
10915 | 0 | default: |
10916 | 0 | abort (); |
10917 | 0 | } |
10918 | | |
10919 | 0 | first = i.op[op].regs - (register_number (i.op[op].regs) & extra); |
10920 | 0 | if (i.op[op].regs != first) |
10921 | 0 | as_warn (_("operand %u `%s%s' implicitly denotes" |
10922 | 0 | " `%s%s' to `%s%s' group in `%s'"), |
10923 | 0 | intel_syntax ? i.operands - op : op + 1, |
10924 | 0 | register_prefix, i.op[op].regs->reg_name, |
10925 | 0 | register_prefix, first[0].reg_name, |
10926 | 0 | register_prefix, first[extra].reg_name, |
10927 | 0 | insn_name (&i.tm)); |
10928 | 0 | } |
10929 | 2.62k | else if (i.tm.opcode_modifier.operandconstraint == REG_KLUDGE) |
10930 | 0 | { |
10931 | | /* The imul $imm, %reg instruction is converted into |
10932 | | imul $imm, %reg, %reg, and the clr %reg instruction |
10933 | | is converted into xor %reg, %reg. */ |
10934 | |
|
10935 | 0 | unsigned int first_reg_op; |
10936 | |
|
10937 | 0 | if (operand_type_check (i.types[0], reg)) |
10938 | 0 | first_reg_op = 0; |
10939 | 0 | else |
10940 | 0 | first_reg_op = 1; |
10941 | | /* Pretend we saw the extra register operand. */ |
10942 | 0 | gas_assert (i.reg_operands == 1 |
10943 | 0 | && i.op[first_reg_op + 1].regs == 0); |
10944 | 0 | i.op[first_reg_op + 1].regs = i.op[first_reg_op].regs; |
10945 | 0 | i.types[first_reg_op + 1] = i.types[first_reg_op]; |
10946 | 0 | i.operands++; |
10947 | 0 | i.reg_operands++; |
10948 | | |
10949 | | /* For IMULZU switch around the constraint. */ |
10950 | 0 | if (i.tm.mnem_off == MN_imulzu) |
10951 | 0 | i.tm.opcode_modifier.operandconstraint = ZERO_UPPER; |
10952 | 0 | } |
10953 | | |
10954 | 2.62k | if (i.tm.opcode_modifier.modrm) |
10955 | 2.09k | { |
10956 | | /* The opcode is completed (modulo i.tm.extension_opcode which |
10957 | | must be put into the modrm byte). Now, we make the modrm and |
10958 | | index base bytes based on all the info we've collected. */ |
10959 | | |
10960 | 2.09k | default_seg = build_modrm_byte (); |
10961 | | |
10962 | 2.09k | if (!quiet_warnings && i.tm.opcode_modifier.operandconstraint == UGH) |
10963 | 0 | { |
10964 | | /* Warn about some common errors, but press on regardless. */ |
10965 | 0 | if (i.operands == 2) |
10966 | 0 | { |
10967 | | /* Reversed arguments on faddp or fmulp. */ |
10968 | 0 | as_warn (_("translating to `%s %s%s,%s%s'"), insn_name (&i.tm), |
10969 | 0 | register_prefix, i.op[!intel_syntax].regs->reg_name, |
10970 | 0 | register_prefix, i.op[intel_syntax].regs->reg_name); |
10971 | 0 | } |
10972 | 0 | else if (i.tm.opcode_modifier.mnemonicsize == IGNORESIZE) |
10973 | 0 | { |
10974 | | /* Extraneous `l' suffix on fp insn. */ |
10975 | 0 | as_warn (_("translating to `%s %s%s'"), insn_name (&i.tm), |
10976 | 0 | register_prefix, i.op[0].regs->reg_name); |
10977 | 0 | } |
10978 | 0 | } |
10979 | 2.09k | } |
10980 | 530 | else if (i.types[0].bitfield.class == SReg && !dot_insn ()) |
10981 | 0 | { |
10982 | 0 | if (flag_code != CODE_64BIT |
10983 | 0 | ? i.tm.base_opcode == POP_SEG_SHORT |
10984 | 0 | && i.op[0].regs->reg_num == 1 |
10985 | 0 | : (i.tm.base_opcode | 1) == (POP_SEG386_SHORT & 0xff) |
10986 | 0 | && i.op[0].regs->reg_num < 4) |
10987 | 0 | { |
10988 | 0 | as_bad (_("you can't `%s %s%s'"), |
10989 | 0 | insn_name (&i.tm), register_prefix, i.op[0].regs->reg_name); |
10990 | 0 | return 0; |
10991 | 0 | } |
10992 | 0 | if (i.op[0].regs->reg_num > 3 |
10993 | 0 | && i.tm.opcode_space == SPACE_BASE ) |
10994 | 0 | { |
10995 | 0 | i.tm.base_opcode ^= (POP_SEG_SHORT ^ POP_SEG386_SHORT) & 0xff; |
10996 | 0 | i.tm.opcode_space = SPACE_0F; |
10997 | 0 | } |
10998 | 0 | i.tm.base_opcode |= (i.op[0].regs->reg_num << 3); |
10999 | 0 | } |
11000 | 530 | else if (i.tm.opcode_space == SPACE_BASE |
11001 | 530 | && (i.tm.base_opcode & ~3) == MOV_AX_DISP32) |
11002 | 0 | { |
11003 | 0 | default_seg = reg_ds; |
11004 | 0 | } |
11005 | 530 | else if (i.tm.opcode_modifier.isstring) |
11006 | 2 | { |
11007 | | /* For the string instructions that allow a segment override |
11008 | | on one of their operands, the default segment is ds. */ |
11009 | 2 | default_seg = reg_ds; |
11010 | 2 | } |
11011 | 528 | else if (i.short_form) |
11012 | 0 | { |
11013 | | /* The register operand is in the 1st or 2nd non-immediate operand. */ |
11014 | 0 | const reg_entry *r = i.op[i.imm_operands].regs; |
11015 | |
|
11016 | 0 | if (!dot_insn () |
11017 | 0 | && r->reg_type.bitfield.instance == Accum |
11018 | 0 | && i.op[i.imm_operands + 1].regs) |
11019 | 0 | r = i.op[i.imm_operands + 1].regs; |
11020 | | /* Register goes in low 3 bits of opcode. */ |
11021 | 0 | i.tm.base_opcode |= r->reg_num; |
11022 | 0 | set_rex_vrex (r, REX_B, false); |
11023 | |
|
11024 | 0 | if (dot_insn () && i.reg_operands == 2) |
11025 | 0 | { |
11026 | 0 | gas_assert (is_any_vex_encoding (&i.tm) |
11027 | 0 | || pp.encoding != encoding_default); |
11028 | 0 | i.vex.register_specifier = i.op[i.operands - 1].regs; |
11029 | 0 | } |
11030 | 0 | } |
11031 | 528 | else if (i.reg_operands == 1 |
11032 | 528 | && !i.flags[i.operands - 1] |
11033 | 528 | && i.tm.operand_types[i.operands - 1].bitfield.instance |
11034 | 0 | == InstanceNone) |
11035 | 0 | { |
11036 | 0 | gas_assert (is_any_vex_encoding (&i.tm) |
11037 | 0 | || pp.encoding != encoding_default); |
11038 | 0 | i.vex.register_specifier = i.op[i.operands - 1].regs; |
11039 | 0 | } |
11040 | | |
11041 | 2.62k | if ((i.seg[0] || i.prefix[SEG_PREFIX]) |
11042 | 2.62k | && i.tm.mnem_off == MN_lea) |
11043 | 0 | { |
11044 | 0 | if (!quiet_warnings) |
11045 | 0 | as_warn (_("segment override on `%s' is ineffectual"), insn_name (&i.tm)); |
11046 | 0 | if (optimize && !pp.no_optimize) |
11047 | 0 | { |
11048 | 0 | i.seg[0] = NULL; |
11049 | 0 | i.prefix[SEG_PREFIX] = 0; |
11050 | 0 | } |
11051 | 0 | } |
11052 | | |
11053 | | /* If a segment was explicitly specified, and the specified segment |
11054 | | is neither the default nor the one already recorded from a prefix, |
11055 | | use an opcode prefix to select it. If we never figured out what |
11056 | | the default segment is, then default_seg will be zero at this |
11057 | | point, and the specified segment prefix will always be used. */ |
11058 | 2.62k | if (i.seg[0] |
11059 | 2.62k | && i.seg[0] != default_seg |
11060 | 2.62k | && i386_seg_prefixes[i.seg[0]->reg_num] != i.prefix[SEG_PREFIX]) |
11061 | 0 | { |
11062 | 0 | if (!add_prefix (i386_seg_prefixes[i.seg[0]->reg_num])) |
11063 | 0 | return 0; |
11064 | 0 | } |
11065 | 2.62k | return 1; |
11066 | 2.62k | } |
11067 | | |
11068 | | static const reg_entry * |
11069 | | build_modrm_byte (void) |
11070 | 2.09k | { |
11071 | 2.09k | const reg_entry *default_seg = NULL; |
11072 | 2.09k | unsigned int source = i.imm_operands - i.tm.opcode_modifier.immext |
11073 | | /* Compensate for kludge in md_assemble(). */ |
11074 | 2.09k | + i.tm.operand_types[0].bitfield.imm1; |
11075 | 2.09k | unsigned int dest = i.operands - 1 - i.tm.opcode_modifier.immext; |
11076 | 2.09k | unsigned int v, op, reg_slot; |
11077 | | |
11078 | | /* Accumulator (in particular %st), shift count (%cl), and alike need |
11079 | | to be skipped just like immediate operands do. */ |
11080 | 2.09k | if (i.tm.operand_types[source].bitfield.instance) |
11081 | 0 | ++source; |
11082 | 2.09k | while (i.tm.operand_types[dest].bitfield.instance) |
11083 | 0 | --dest; |
11084 | | |
11085 | 2.09k | for (op = source; op < i.operands; ++op) |
11086 | 2.09k | if (i.tm.operand_types[op].bitfield.baseindex) |
11087 | 2.09k | break; |
11088 | | |
11089 | 2.09k | if (i.reg_operands + i.mem_operands + (i.tm.extension_opcode != None) |
11090 | 2.09k | + (i.tm.opcode_modifier.operandconstraint == SCC) == 4) |
11091 | 0 | { |
11092 | 0 | expressionS *exp; |
11093 | | |
11094 | | /* There are 2 kinds of instructions: |
11095 | | 1. 5 operands: 4 register operands or 3 register operands |
11096 | | plus 1 memory operand plus one Imm4 operand, VexXDS, and |
11097 | | VexW0 or VexW1. The destination must be either XMM, YMM or |
11098 | | ZMM register. |
11099 | | 2. 4 operands: 4 register operands or 3 register operands |
11100 | | plus 1 memory operand, with VexXDS. |
11101 | | 3. Other equivalent combinations when coming from s_insn(). */ |
11102 | 0 | if (!dot_insn ()) |
11103 | 0 | { |
11104 | 0 | gas_assert (i.tm.opcode_modifier.vexvvvv |
11105 | 0 | && i.tm.opcode_modifier.vexw); |
11106 | 0 | gas_assert (i.tm.operand_types[dest].bitfield.class == RegSIMD); |
11107 | 0 | } |
11108 | | |
11109 | | /* Of the first two non-immediate operands the one with the template |
11110 | | not allowing for a memory one is encoded in the immediate operand. */ |
11111 | 0 | if (source == op) |
11112 | 0 | reg_slot = source + 1; |
11113 | 0 | else |
11114 | 0 | reg_slot = source++; |
11115 | |
|
11116 | 0 | if (!dot_insn ()) |
11117 | 0 | { |
11118 | 0 | gas_assert (i.tm.operand_types[reg_slot].bitfield.class == RegSIMD); |
11119 | 0 | gas_assert (!(i.op[reg_slot].regs->reg_flags & RegVRex)); |
11120 | 0 | } |
11121 | 0 | else |
11122 | 0 | gas_assert (i.tm.operand_types[reg_slot].bitfield.class != ClassNone); |
11123 | | |
11124 | 0 | if (i.imm_operands == 0) |
11125 | 0 | { |
11126 | | /* When there is no immediate operand, generate an 8bit |
11127 | | immediate operand to encode the first operand. */ |
11128 | 0 | exp = &im_expressions[i.imm_operands++]; |
11129 | 0 | i.op[i.operands].imms = exp; |
11130 | 0 | i.types[i.operands].bitfield.imm8 = 1; |
11131 | 0 | i.operands++; |
11132 | |
|
11133 | 0 | exp->X_op = O_constant; |
11134 | 0 | } |
11135 | 0 | else |
11136 | 0 | { |
11137 | 0 | gas_assert (i.imm_operands == 1); |
11138 | 0 | gas_assert (fits_in_imm4 (i.op[0].imms->X_add_number)); |
11139 | 0 | gas_assert (!i.tm.opcode_modifier.immext); |
11140 | | |
11141 | | /* Turn on Imm8 again so that output_imm will generate it. */ |
11142 | 0 | i.types[0].bitfield.imm8 = 1; |
11143 | |
|
11144 | 0 | exp = i.op[0].imms; |
11145 | 0 | } |
11146 | 0 | exp->X_add_number |= register_number (i.op[reg_slot].regs) |
11147 | 0 | << (3 + !(i.tm.opcode_modifier.evex |
11148 | 0 | || pp.encoding == encoding_evex)); |
11149 | 0 | } |
11150 | | |
11151 | 2.09k | switch (i.tm.opcode_modifier.vexvvvv) |
11152 | 2.09k | { |
11153 | | /* VEX.vvvv encodes the last source register operand. */ |
11154 | 0 | case VexVVVV_SRC2: |
11155 | 0 | v = source++; |
11156 | 0 | break; |
11157 | | /* VEX.vvvv encodes the first source register operand. */ |
11158 | 0 | case VexVVVV_SRC1: |
11159 | 0 | v = dest - 1; |
11160 | 0 | break; |
11161 | | /* VEX.vvvv encodes the destination register operand. */ |
11162 | 0 | case VexVVVV_DST: |
11163 | 0 | v = dest--; |
11164 | 0 | break; |
11165 | 2.09k | default: |
11166 | 2.09k | v = ~0; |
11167 | 2.09k | break; |
11168 | 2.09k | } |
11169 | | |
11170 | 2.09k | if (dest == source) |
11171 | 2.09k | dest = ~0; |
11172 | | |
11173 | 2.09k | gas_assert (source < dest); |
11174 | | |
11175 | 2.09k | if (v < MAX_OPERANDS) |
11176 | 0 | { |
11177 | 0 | gas_assert (i.tm.opcode_modifier.vexvvvv); |
11178 | 0 | i.vex.register_specifier = i.op[v].regs; |
11179 | 0 | } |
11180 | | |
11181 | 2.09k | if (op < i.operands) |
11182 | 2.09k | { |
11183 | 2.09k | if (i.mem_operands) |
11184 | 2.09k | { |
11185 | 2.09k | unsigned int fake_zero_displacement = 0; |
11186 | | |
11187 | 2.09k | gas_assert (i.flags[op] & Operand_Mem); |
11188 | | |
11189 | 2.09k | if (i.tm.opcode_modifier.sib) |
11190 | 0 | { |
11191 | | /* The index register of VSIB shouldn't be RegIZ. */ |
11192 | 0 | if (i.tm.opcode_modifier.sib != SIBMEM |
11193 | 0 | && i.index_reg->reg_num == RegIZ) |
11194 | 0 | abort (); |
11195 | | |
11196 | 0 | i.rm.regmem = ESCAPE_TO_TWO_BYTE_ADDRESSING; |
11197 | 0 | if (!i.base_reg) |
11198 | 0 | { |
11199 | 0 | i.sib.base = NO_BASE_REGISTER; |
11200 | 0 | i.sib.scale = i.log2_scale_factor; |
11201 | 0 | i.types[op] = operand_type_and_not (i.types[op], anydisp); |
11202 | 0 | i.types[op].bitfield.disp32 = 1; |
11203 | 0 | } |
11204 | | |
11205 | | /* Since the mandatory SIB always has index register, so |
11206 | | the code logic remains unchanged. The non-mandatory SIB |
11207 | | without index register is allowed and will be handled |
11208 | | later. */ |
11209 | 0 | if (i.index_reg) |
11210 | 0 | { |
11211 | 0 | if (i.index_reg->reg_num == RegIZ) |
11212 | 0 | i.sib.index = NO_INDEX_REGISTER; |
11213 | 0 | else |
11214 | 0 | i.sib.index = i.index_reg->reg_num; |
11215 | 0 | set_rex_vrex (i.index_reg, REX_X, false); |
11216 | 0 | } |
11217 | 0 | } |
11218 | | |
11219 | 2.09k | default_seg = reg_ds; |
11220 | | |
11221 | 2.09k | if (i.base_reg == 0) |
11222 | 2.09k | { |
11223 | 2.09k | i.rm.mode = 0; |
11224 | 2.09k | if (!i.disp_operands) |
11225 | 0 | fake_zero_displacement = 1; |
11226 | 2.09k | if (i.index_reg == 0) |
11227 | 2.09k | { |
11228 | | /* Both check for VSIB and mandatory non-vector SIB. */ |
11229 | 2.09k | gas_assert (!i.tm.opcode_modifier.sib |
11230 | 2.09k | || i.tm.opcode_modifier.sib == SIBMEM); |
11231 | | /* Operand is just <disp> */ |
11232 | 2.09k | i.types[op] = operand_type_and_not (i.types[op], anydisp); |
11233 | 2.09k | if (flag_code == CODE_64BIT) |
11234 | 224 | { |
11235 | | /* 64bit mode overwrites the 32bit absolute |
11236 | | addressing by RIP relative addressing and |
11237 | | absolute addressing is encoded by one of the |
11238 | | redundant SIB forms. */ |
11239 | 224 | i.rm.regmem = ESCAPE_TO_TWO_BYTE_ADDRESSING; |
11240 | 224 | i.sib.base = NO_BASE_REGISTER; |
11241 | 224 | i.sib.index = NO_INDEX_REGISTER; |
11242 | 224 | i.types[op].bitfield.disp32 = 1; |
11243 | 224 | } |
11244 | 1.87k | else if ((flag_code == CODE_16BIT) |
11245 | 1.87k | ^ (i.prefix[ADDR_PREFIX] != 0)) |
11246 | 264 | { |
11247 | 264 | i.rm.regmem = NO_BASE_REGISTER_16; |
11248 | 264 | i.types[op].bitfield.disp16 = 1; |
11249 | 264 | } |
11250 | 1.61k | else |
11251 | 1.61k | { |
11252 | 1.61k | i.rm.regmem = NO_BASE_REGISTER; |
11253 | 1.61k | i.types[op].bitfield.disp32 = 1; |
11254 | 1.61k | } |
11255 | 2.09k | } |
11256 | 0 | else if (!i.tm.opcode_modifier.sib) |
11257 | 0 | { |
11258 | | /* !i.base_reg && i.index_reg */ |
11259 | 0 | if (i.index_reg->reg_num == RegIZ) |
11260 | 0 | i.sib.index = NO_INDEX_REGISTER; |
11261 | 0 | else |
11262 | 0 | i.sib.index = i.index_reg->reg_num; |
11263 | 0 | i.sib.base = NO_BASE_REGISTER; |
11264 | 0 | i.sib.scale = i.log2_scale_factor; |
11265 | 0 | i.rm.regmem = ESCAPE_TO_TWO_BYTE_ADDRESSING; |
11266 | 0 | i.types[op] = operand_type_and_not (i.types[op], anydisp); |
11267 | 0 | i.types[op].bitfield.disp32 = 1; |
11268 | 0 | set_rex_rex2 (i.index_reg, REX_X); |
11269 | 0 | } |
11270 | 2.09k | } |
11271 | | /* RIP addressing for 64bit mode. */ |
11272 | 0 | else if (i.base_reg->reg_num == RegIP) |
11273 | 0 | { |
11274 | 0 | gas_assert (!i.tm.opcode_modifier.sib); |
11275 | 0 | i.rm.regmem = NO_BASE_REGISTER; |
11276 | 0 | i.types[op].bitfield.disp8 = 0; |
11277 | 0 | i.types[op].bitfield.disp16 = 0; |
11278 | 0 | i.types[op].bitfield.disp32 = 1; |
11279 | 0 | i.types[op].bitfield.disp64 = 0; |
11280 | 0 | i.flags[op] |= Operand_PCrel; |
11281 | 0 | if (! i.disp_operands) |
11282 | 0 | fake_zero_displacement = 1; |
11283 | 0 | } |
11284 | 0 | else if (i.base_reg->reg_type.bitfield.word) |
11285 | 0 | { |
11286 | 0 | gas_assert (!i.tm.opcode_modifier.sib); |
11287 | 0 | switch (i.base_reg->reg_num) |
11288 | 0 | { |
11289 | 0 | case 3: /* (%bx) */ |
11290 | 0 | if (i.index_reg == 0) |
11291 | 0 | i.rm.regmem = 7; |
11292 | 0 | else /* (%bx,%si) -> 0, or (%bx,%di) -> 1 */ |
11293 | 0 | i.rm.regmem = i.index_reg->reg_num - 6; |
11294 | 0 | break; |
11295 | 0 | case 5: /* (%bp) */ |
11296 | 0 | default_seg = reg_ss; |
11297 | 0 | if (i.index_reg == 0) |
11298 | 0 | { |
11299 | 0 | i.rm.regmem = 6; |
11300 | 0 | if (operand_type_check (i.types[op], disp) == 0) |
11301 | 0 | { |
11302 | | /* fake (%bp) into 0(%bp) */ |
11303 | 0 | if (pp.disp_encoding == disp_encoding_16bit) |
11304 | 0 | i.types[op].bitfield.disp16 = 1; |
11305 | 0 | else |
11306 | 0 | i.types[op].bitfield.disp8 = 1; |
11307 | 0 | fake_zero_displacement = 1; |
11308 | 0 | } |
11309 | 0 | } |
11310 | 0 | else /* (%bp,%si) -> 2, or (%bp,%di) -> 3 */ |
11311 | 0 | i.rm.regmem = i.index_reg->reg_num - 6 + 2; |
11312 | 0 | break; |
11313 | 0 | default: /* (%si) -> 4 or (%di) -> 5 */ |
11314 | 0 | i.rm.regmem = i.base_reg->reg_num - 6 + 4; |
11315 | 0 | } |
11316 | 0 | if (!fake_zero_displacement |
11317 | 0 | && !i.disp_operands |
11318 | 0 | && pp.disp_encoding) |
11319 | 0 | { |
11320 | 0 | fake_zero_displacement = 1; |
11321 | 0 | if (pp.disp_encoding == disp_encoding_8bit) |
11322 | 0 | i.types[op].bitfield.disp8 = 1; |
11323 | 0 | else |
11324 | 0 | i.types[op].bitfield.disp16 = 1; |
11325 | 0 | } |
11326 | 0 | i.rm.mode = mode_from_disp_size (i.types[op]); |
11327 | 0 | } |
11328 | 0 | else /* i.base_reg and 32/64 bit mode */ |
11329 | 0 | { |
11330 | 0 | if (operand_type_check (i.types[op], disp)) |
11331 | 0 | { |
11332 | 0 | i.types[op].bitfield.disp16 = 0; |
11333 | 0 | i.types[op].bitfield.disp64 = 0; |
11334 | 0 | i.types[op].bitfield.disp32 = 1; |
11335 | 0 | } |
11336 | |
|
11337 | 0 | if (!i.tm.opcode_modifier.sib) |
11338 | 0 | i.rm.regmem = i.base_reg->reg_num; |
11339 | 0 | set_rex_rex2 (i.base_reg, REX_B); |
11340 | 0 | i.sib.base = i.base_reg->reg_num; |
11341 | | /* x86-64 ignores REX prefix bit here to avoid decoder |
11342 | | complications. */ |
11343 | 0 | if (!(i.base_reg->reg_flags & RegRex) |
11344 | 0 | && (i.base_reg->reg_num == EBP_REG_NUM |
11345 | 0 | || i.base_reg->reg_num == ESP_REG_NUM)) |
11346 | 0 | default_seg = reg_ss; |
11347 | 0 | if (i.base_reg->reg_num == 5 && i.disp_operands == 0) |
11348 | 0 | { |
11349 | 0 | fake_zero_displacement = 1; |
11350 | 0 | if (pp.disp_encoding == disp_encoding_32bit) |
11351 | 0 | i.types[op].bitfield.disp32 = 1; |
11352 | 0 | else |
11353 | 0 | i.types[op].bitfield.disp8 = 1; |
11354 | 0 | } |
11355 | 0 | i.sib.scale = i.log2_scale_factor; |
11356 | 0 | if (i.index_reg == 0) |
11357 | 0 | { |
11358 | | /* Only check for VSIB. */ |
11359 | 0 | gas_assert (i.tm.opcode_modifier.sib != VECSIB128 |
11360 | 0 | && i.tm.opcode_modifier.sib != VECSIB256 |
11361 | 0 | && i.tm.opcode_modifier.sib != VECSIB512); |
11362 | | |
11363 | | /* <disp>(%esp) becomes two byte modrm with no index |
11364 | | register. We've already stored the code for esp |
11365 | | in i.rm.regmem ie. ESCAPE_TO_TWO_BYTE_ADDRESSING. |
11366 | | Any base register besides %esp will not use the |
11367 | | extra modrm byte. */ |
11368 | 0 | i.sib.index = NO_INDEX_REGISTER; |
11369 | 0 | } |
11370 | 0 | else if (!i.tm.opcode_modifier.sib) |
11371 | 0 | { |
11372 | 0 | if (i.index_reg->reg_num == RegIZ) |
11373 | 0 | i.sib.index = NO_INDEX_REGISTER; |
11374 | 0 | else |
11375 | 0 | i.sib.index = i.index_reg->reg_num; |
11376 | 0 | i.rm.regmem = ESCAPE_TO_TWO_BYTE_ADDRESSING; |
11377 | 0 | set_rex_rex2 (i.index_reg, REX_X); |
11378 | 0 | } |
11379 | | |
11380 | 0 | if (i.disp_operands |
11381 | 0 | && (i.reloc[op] == BFD_RELOC_386_TLS_DESC_CALL |
11382 | 0 | || i.reloc[op] == BFD_RELOC_X86_64_TLSDESC_CALL)) |
11383 | 0 | i.rm.mode = 0; |
11384 | 0 | else |
11385 | 0 | { |
11386 | 0 | if (!fake_zero_displacement |
11387 | 0 | && !i.disp_operands |
11388 | 0 | && pp.disp_encoding) |
11389 | 0 | { |
11390 | 0 | fake_zero_displacement = 1; |
11391 | 0 | if (pp.disp_encoding == disp_encoding_8bit) |
11392 | 0 | i.types[op].bitfield.disp8 = 1; |
11393 | 0 | else |
11394 | 0 | i.types[op].bitfield.disp32 = 1; |
11395 | 0 | } |
11396 | 0 | i.rm.mode = mode_from_disp_size (i.types[op]); |
11397 | 0 | } |
11398 | 0 | } |
11399 | | |
11400 | 2.09k | if (fake_zero_displacement) |
11401 | 0 | { |
11402 | | /* Fakes a zero displacement assuming that i.types[op] |
11403 | | holds the correct displacement size. */ |
11404 | 0 | expressionS *exp; |
11405 | |
|
11406 | 0 | gas_assert (i.op[op].disps == 0); |
11407 | 0 | exp = &disp_expressions[i.disp_operands++]; |
11408 | 0 | i.op[op].disps = exp; |
11409 | 0 | exp->X_op = O_constant; |
11410 | 0 | exp->X_add_number = 0; |
11411 | 0 | exp->X_add_symbol = (symbolS *) 0; |
11412 | 0 | exp->X_op_symbol = (symbolS *) 0; |
11413 | 0 | } |
11414 | 2.09k | } |
11415 | 0 | else |
11416 | 0 | { |
11417 | 0 | i.rm.mode = 3; |
11418 | 0 | i.rm.regmem = i.op[op].regs->reg_num; |
11419 | 0 | set_rex_vrex (i.op[op].regs, REX_B, false); |
11420 | 0 | } |
11421 | | |
11422 | 2.09k | if (op == dest) |
11423 | 0 | dest = ~0; |
11424 | 2.09k | if (op == source) |
11425 | 2.09k | source = ~0; |
11426 | 2.09k | } |
11427 | 0 | else |
11428 | 0 | { |
11429 | 0 | i.rm.mode = 3; |
11430 | 0 | if (!i.tm.opcode_modifier.regmem) |
11431 | 0 | { |
11432 | 0 | gas_assert (source < MAX_OPERANDS); |
11433 | 0 | i.rm.regmem = i.op[source].regs->reg_num; |
11434 | 0 | set_rex_vrex (i.op[source].regs, REX_B, |
11435 | 0 | dest >= MAX_OPERANDS && i.tm.opcode_modifier.sse2avx); |
11436 | 0 | source = ~0; |
11437 | 0 | } |
11438 | 0 | else |
11439 | 0 | { |
11440 | 0 | gas_assert (dest < MAX_OPERANDS); |
11441 | 0 | i.rm.regmem = i.op[dest].regs->reg_num; |
11442 | 0 | set_rex_vrex (i.op[dest].regs, REX_B, i.tm.opcode_modifier.sse2avx); |
11443 | 0 | dest = ~0; |
11444 | 0 | } |
11445 | 0 | } |
11446 | | |
11447 | | /* Fill in i.rm.reg field with extension opcode (if any) or the |
11448 | | appropriate register. */ |
11449 | 2.09k | if (i.tm.extension_opcode != None) |
11450 | 2.09k | i.rm.reg = i.tm.extension_opcode; |
11451 | 0 | else if (!i.tm.opcode_modifier.regmem && dest < MAX_OPERANDS) |
11452 | 0 | { |
11453 | 0 | i.rm.reg = i.op[dest].regs->reg_num; |
11454 | 0 | set_rex_vrex (i.op[dest].regs, REX_R, i.tm.opcode_modifier.sse2avx); |
11455 | 0 | } |
11456 | 0 | else |
11457 | 0 | { |
11458 | 0 | gas_assert (source < MAX_OPERANDS); |
11459 | 0 | i.rm.reg = i.op[source].regs->reg_num; |
11460 | 0 | set_rex_vrex (i.op[source].regs, REX_R, false); |
11461 | 0 | } |
11462 | | |
11463 | 2.09k | if (flag_code != CODE_64BIT && (i.rex & REX_R)) |
11464 | 0 | { |
11465 | 0 | gas_assert (i.types[!i.tm.opcode_modifier.regmem].bitfield.class == RegCR); |
11466 | 0 | i.rex &= ~REX_R; |
11467 | 0 | add_prefix (LOCK_PREFIX_OPCODE); |
11468 | 0 | } |
11469 | | |
11470 | 2.09k | return default_seg; |
11471 | 2.09k | } |
11472 | | |
11473 | | static INLINE void |
11474 | | frag_opcode_byte (unsigned char byte) |
11475 | 2.34k | { |
11476 | 2.34k | if (now_seg != absolute_section) |
11477 | 1.07k | FRAG_APPEND_1_CHAR (byte); |
11478 | 1.27k | else |
11479 | 1.27k | ++abs_section_offset; |
11480 | 2.34k | } |
11481 | | |
11482 | | static unsigned int |
11483 | | flip_code16 (unsigned int code16) |
11484 | 0 | { |
11485 | 0 | gas_assert (i.tm.operands == 1); |
11486 | | |
11487 | 0 | return !(i.prefix[REX_PREFIX] & REX_W) |
11488 | 0 | && (code16 ? i.tm.operand_types[0].bitfield.disp32 |
11489 | 0 | : i.tm.operand_types[0].bitfield.disp16) |
11490 | 0 | ? CODE16 : 0; |
11491 | 0 | } |
11492 | | |
11493 | | static void |
11494 | | output_branch (void) |
11495 | 153 | { |
11496 | 153 | char *p; |
11497 | 153 | int size; |
11498 | 153 | int code16; |
11499 | 153 | int prefix; |
11500 | 153 | relax_substateT subtype; |
11501 | 153 | symbolS *sym; |
11502 | 153 | offsetT off; |
11503 | | |
11504 | 153 | if (now_seg == absolute_section) |
11505 | 28 | { |
11506 | 28 | as_bad (_("relaxable branches not supported in absolute section")); |
11507 | 28 | return; |
11508 | 28 | } |
11509 | | |
11510 | 125 | code16 = flag_code == CODE_16BIT ? CODE16 : 0; |
11511 | 125 | size = pp.disp_encoding > disp_encoding_8bit ? BIG : SMALL; |
11512 | | |
11513 | 125 | prefix = 0; |
11514 | 125 | if (i.prefix[DATA_PREFIX] != 0) |
11515 | 0 | { |
11516 | 0 | prefix = 1; |
11517 | 0 | i.prefixes -= 1; |
11518 | 0 | code16 ^= flip_code16(code16); |
11519 | 0 | } |
11520 | | /* Pentium4 branch hints. */ |
11521 | 125 | if (i.prefix[SEG_PREFIX] == CS_PREFIX_OPCODE /* not taken */ |
11522 | 125 | || i.prefix[SEG_PREFIX] == DS_PREFIX_OPCODE /* taken */) |
11523 | 0 | { |
11524 | 0 | prefix++; |
11525 | 0 | i.prefixes--; |
11526 | 0 | } |
11527 | 125 | if (i.prefix[REX_PREFIX] != 0) |
11528 | 0 | { |
11529 | 0 | prefix++; |
11530 | 0 | i.prefixes--; |
11531 | 0 | } |
11532 | | |
11533 | | /* BND prefixed jump. */ |
11534 | 125 | if (i.prefix[BND_PREFIX] != 0) |
11535 | 0 | { |
11536 | 0 | prefix++; |
11537 | 0 | i.prefixes--; |
11538 | 0 | } |
11539 | | |
11540 | 125 | if (i.prefixes != 0) |
11541 | 0 | as_warn (_("skipping prefixes on `%s'"), insn_name (&i.tm)); |
11542 | | |
11543 | | /* It's always a symbol; End frag & setup for relax. |
11544 | | Make sure there is enough room in this frag for the largest |
11545 | | instruction we may generate in md_convert_frag. This is 2 |
11546 | | bytes for the opcode and room for the prefix and largest |
11547 | | displacement. */ |
11548 | 125 | frag_grow (prefix + 2 + 4); |
11549 | | /* Prefix and 1 opcode byte go in fr_fix. */ |
11550 | 125 | p = frag_more (prefix + 1); |
11551 | 125 | if (i.prefix[DATA_PREFIX] != 0) |
11552 | 0 | *p++ = DATA_PREFIX_OPCODE; |
11553 | 125 | if (i.prefix[SEG_PREFIX] == CS_PREFIX_OPCODE |
11554 | 125 | || i.prefix[SEG_PREFIX] == DS_PREFIX_OPCODE) |
11555 | 0 | *p++ = i.prefix[SEG_PREFIX]; |
11556 | 125 | if (i.prefix[BND_PREFIX] != 0) |
11557 | 0 | *p++ = BND_PREFIX_OPCODE; |
11558 | 125 | if (i.prefix[REX_PREFIX] != 0) |
11559 | 0 | *p++ = i.prefix[REX_PREFIX]; |
11560 | 125 | *p = i.tm.base_opcode; |
11561 | | |
11562 | 125 | if ((unsigned char) *p == JUMP_PC_RELATIVE) |
11563 | 0 | subtype = ENCODE_RELAX_STATE (UNCOND_JUMP, size); |
11564 | 125 | else if (cpu_arch_flags.bitfield.cpui386) |
11565 | 125 | subtype = ENCODE_RELAX_STATE (COND_JUMP, size); |
11566 | 0 | else |
11567 | 0 | subtype = ENCODE_RELAX_STATE (COND_JUMP86, size); |
11568 | 125 | subtype |= code16; |
11569 | | |
11570 | 125 | sym = i.op[0].disps->X_add_symbol; |
11571 | 125 | off = i.op[0].disps->X_add_number; |
11572 | | |
11573 | 125 | if (i.op[0].disps->X_op != O_constant |
11574 | 125 | && i.op[0].disps->X_op != O_symbol) |
11575 | 82 | { |
11576 | | /* Handle complex expressions. */ |
11577 | 82 | sym = make_expr_symbol (i.op[0].disps); |
11578 | 82 | off = 0; |
11579 | 82 | } |
11580 | | |
11581 | | /* 1 possible extra opcode + 4 byte displacement go in var part. |
11582 | | Pass reloc in fr_var. */ |
11583 | 125 | frag_var (rs_machine_dependent, 5, i.reloc[0], subtype, sym, off, p); |
11584 | 125 | } |
11585 | | |
11586 | | /* PLT32 relocation is ELF only. */ |
11587 | | #ifdef OBJ_ELF |
11588 | | /* Return TRUE iff PLT32 relocation should be used for branching to |
11589 | | symbol S. */ |
11590 | | |
11591 | | static bool |
11592 | | need_plt32_p (symbolS *s) |
11593 | 6 | { |
11594 | | #ifdef TE_SOLARIS |
11595 | | /* Don't emit PLT32 relocation on Solaris: neither native linker nor |
11596 | | krtld support it. */ |
11597 | | return false; |
11598 | | #endif |
11599 | | |
11600 | | /* Since there is no need to prepare for PLT branch on x86-64, we |
11601 | | can generate R_X86_64_PLT32, instead of R_X86_64_PC32, which can |
11602 | | be used as a marker for 32-bit PC-relative branches. */ |
11603 | 6 | if (!object_64bit) |
11604 | 0 | return false; |
11605 | | |
11606 | 6 | if (s == NULL) |
11607 | 0 | return false; |
11608 | | |
11609 | | /* Weak or undefined symbol need PLT32 relocation. */ |
11610 | 6 | if (S_IS_WEAK (s) || !S_IS_DEFINED (s)) |
11611 | 0 | return true; |
11612 | | |
11613 | | /* Non-global symbol doesn't need PLT32 relocation. */ |
11614 | 6 | if (! S_IS_EXTERNAL (s)) |
11615 | 6 | return false; |
11616 | | |
11617 | | /* Other global symbols need PLT32 relocation. NB: Symbol with |
11618 | | non-default visibilities are treated as normal global symbol |
11619 | | so that PLT32 relocation can be used as a marker for 32-bit |
11620 | | PC-relative branches. It is useful for linker relaxation. */ |
11621 | 0 | return true; |
11622 | 6 | } |
11623 | | #endif |
11624 | | |
11625 | | static void |
11626 | | output_jump (void) |
11627 | 331 | { |
11628 | 331 | char *p; |
11629 | 331 | int size; |
11630 | 331 | fixS *fixP; |
11631 | 331 | bfd_reloc_code_real_type jump_reloc = i.reloc[0]; |
11632 | | |
11633 | 331 | if (i.tm.opcode_modifier.jump == JUMP_BYTE) |
11634 | 2 | { |
11635 | | /* This is a loop or jecxz type instruction. */ |
11636 | 2 | size = 1; |
11637 | 2 | if (i.prefix[ADDR_PREFIX] != 0) |
11638 | 0 | { |
11639 | 0 | frag_opcode_byte (ADDR_PREFIX_OPCODE); |
11640 | 0 | i.prefixes -= 1; |
11641 | 0 | } |
11642 | | /* Pentium4 branch hints. */ |
11643 | 2 | if (i.prefix[SEG_PREFIX] == CS_PREFIX_OPCODE /* not taken */ |
11644 | 2 | || i.prefix[SEG_PREFIX] == DS_PREFIX_OPCODE /* taken */) |
11645 | 0 | { |
11646 | 0 | frag_opcode_byte (i.prefix[SEG_PREFIX]); |
11647 | 0 | i.prefixes--; |
11648 | 0 | } |
11649 | 2 | } |
11650 | 329 | else |
11651 | 329 | { |
11652 | 329 | int code16; |
11653 | | |
11654 | 329 | code16 = 0; |
11655 | 329 | if (flag_code == CODE_16BIT) |
11656 | 136 | code16 = CODE16; |
11657 | | |
11658 | 329 | if (i.prefix[DATA_PREFIX] != 0) |
11659 | 0 | { |
11660 | 0 | frag_opcode_byte (DATA_PREFIX_OPCODE); |
11661 | 0 | i.prefixes -= 1; |
11662 | 0 | code16 ^= flip_code16(code16); |
11663 | 0 | } |
11664 | | |
11665 | 329 | size = 4; |
11666 | 329 | if (code16) |
11667 | 136 | size = 2; |
11668 | 329 | } |
11669 | | |
11670 | | /* BND prefixed jump. */ |
11671 | 331 | if (i.prefix[BND_PREFIX] != 0) |
11672 | 0 | { |
11673 | 0 | frag_opcode_byte (i.prefix[BND_PREFIX]); |
11674 | 0 | i.prefixes -= 1; |
11675 | 0 | } |
11676 | | |
11677 | 331 | if (i.prefix[REX_PREFIX] != 0) |
11678 | 0 | { |
11679 | 0 | frag_opcode_byte (i.prefix[REX_PREFIX]); |
11680 | 0 | i.prefixes -= 1; |
11681 | 0 | } |
11682 | | |
11683 | 331 | if (i.prefixes != 0) |
11684 | 0 | as_warn (_("skipping prefixes on `%s'"), insn_name (&i.tm)); |
11685 | | |
11686 | 331 | if (now_seg == absolute_section) |
11687 | 54 | { |
11688 | 54 | abs_section_offset += i.opcode_length + size; |
11689 | 54 | return; |
11690 | 54 | } |
11691 | | |
11692 | 277 | p = frag_more (i.opcode_length + size); |
11693 | 277 | switch (i.opcode_length) |
11694 | 277 | { |
11695 | 0 | case 2: |
11696 | 0 | *p++ = i.tm.base_opcode >> 8; |
11697 | | /* Fall through. */ |
11698 | 277 | case 1: |
11699 | 277 | *p++ = i.tm.base_opcode; |
11700 | 277 | break; |
11701 | 0 | default: |
11702 | 0 | abort (); |
11703 | 277 | } |
11704 | | |
11705 | 277 | #ifdef OBJ_ELF |
11706 | 277 | if (flag_code == CODE_64BIT && size == 4 |
11707 | 277 | && jump_reloc == NO_RELOC && i.op[0].disps->X_add_number == 0 |
11708 | 277 | && need_plt32_p (i.op[0].disps->X_add_symbol)) |
11709 | 0 | jump_reloc = BFD_RELOC_X86_64_PLT32; |
11710 | 277 | #endif |
11711 | | |
11712 | 277 | jump_reloc = reloc (size, 1, 1, jump_reloc); |
11713 | | |
11714 | 277 | fixP = fix_new_exp (frag_now, p - frag_now->fr_literal, size, |
11715 | 277 | i.op[0].disps, 1, jump_reloc); |
11716 | | |
11717 | | /* All jumps handled here are signed, but don't unconditionally use a |
11718 | | signed limit check for 32 and 16 bit jumps as we want to allow wrap |
11719 | | around at 4G (outside of 64-bit mode) and 64k (except for XBEGIN) |
11720 | | respectively. */ |
11721 | 277 | switch (size) |
11722 | 277 | { |
11723 | 1 | case 1: |
11724 | 1 | fixP->fx_signed = 1; |
11725 | 1 | break; |
11726 | | |
11727 | 136 | case 2: |
11728 | 136 | if (i.tm.mnem_off == MN_xbegin) |
11729 | 0 | fixP->fx_signed = 1; |
11730 | 136 | break; |
11731 | | |
11732 | 140 | case 4: |
11733 | 140 | if (flag_code == CODE_64BIT) |
11734 | 6 | fixP->fx_signed = 1; |
11735 | 140 | break; |
11736 | 277 | } |
11737 | 277 | } |
11738 | | |
11739 | | static void |
11740 | | output_interseg_jump (void) |
11741 | 0 | { |
11742 | 0 | char *p; |
11743 | 0 | int size; |
11744 | 0 | int prefix; |
11745 | 0 | int code16; |
11746 | |
|
11747 | 0 | code16 = 0; |
11748 | 0 | if (flag_code == CODE_16BIT) |
11749 | 0 | code16 = CODE16; |
11750 | |
|
11751 | 0 | prefix = 0; |
11752 | 0 | if (i.prefix[DATA_PREFIX] != 0) |
11753 | 0 | { |
11754 | 0 | prefix = 1; |
11755 | 0 | i.prefixes -= 1; |
11756 | 0 | code16 ^= CODE16; |
11757 | 0 | } |
11758 | |
|
11759 | 0 | gas_assert (!i.prefix[REX_PREFIX]); |
11760 | | |
11761 | 0 | size = 4; |
11762 | 0 | if (code16) |
11763 | 0 | size = 2; |
11764 | |
|
11765 | 0 | if (i.prefixes != 0) |
11766 | 0 | as_warn (_("skipping prefixes on `%s'"), insn_name (&i.tm)); |
11767 | |
|
11768 | 0 | if (now_seg == absolute_section) |
11769 | 0 | { |
11770 | 0 | abs_section_offset += prefix + 1 + 2 + size; |
11771 | 0 | return; |
11772 | 0 | } |
11773 | | |
11774 | | /* 1 opcode; 2 segment; offset */ |
11775 | 0 | p = frag_more (prefix + 1 + 2 + size); |
11776 | |
|
11777 | 0 | if (i.prefix[DATA_PREFIX] != 0) |
11778 | 0 | *p++ = DATA_PREFIX_OPCODE; |
11779 | |
|
11780 | 0 | if (i.prefix[REX_PREFIX] != 0) |
11781 | 0 | *p++ = i.prefix[REX_PREFIX]; |
11782 | |
|
11783 | 0 | *p++ = i.tm.base_opcode; |
11784 | 0 | if (i.op[1].imms->X_op == O_constant) |
11785 | 0 | { |
11786 | 0 | offsetT n = i.op[1].imms->X_add_number; |
11787 | |
|
11788 | 0 | if (size == 2 |
11789 | 0 | && !fits_in_unsigned_word (n) |
11790 | 0 | && !fits_in_signed_word (n)) |
11791 | 0 | { |
11792 | 0 | as_bad (_("16-bit jump out of range")); |
11793 | 0 | return; |
11794 | 0 | } |
11795 | 0 | md_number_to_chars (p, n, size); |
11796 | 0 | } |
11797 | 0 | else |
11798 | 0 | fix_new_exp (frag_now, p - frag_now->fr_literal, size, |
11799 | 0 | i.op[1].imms, 0, reloc (size, 0, 0, i.reloc[1])); |
11800 | | |
11801 | 0 | p += size; |
11802 | 0 | if (i.op[0].imms->X_op == O_constant) |
11803 | 0 | md_number_to_chars (p, (valueT) i.op[0].imms->X_add_number, 2); |
11804 | 0 | else |
11805 | 0 | fix_new_exp (frag_now, p - frag_now->fr_literal, 2, |
11806 | 0 | i.op[0].imms, 0, reloc (2, 0, 0, i.reloc[0])); |
11807 | 0 | } |
11808 | | |
11809 | | /* Hook used to reject pseudo-prefixes misplaced at the start of a line. */ |
11810 | | |
11811 | | void i386_start_line (void) |
11812 | 6.89M | { |
11813 | 6.89M | struct pseudo_prefixes last_pp; |
11814 | | |
11815 | 6.89M | memcpy (&last_pp, &pp, sizeof (pp)); |
11816 | 6.89M | memset (&pp, 0, sizeof (pp)); |
11817 | 6.89M | if (memcmp (&pp, &last_pp, sizeof (pp))) |
11818 | 2 | as_bad_where (frag_now->fr_file, frag_now->fr_line, |
11819 | 2 | _("pseudo prefix without instruction")); |
11820 | 6.89M | } |
11821 | | |
11822 | | /* Hook used to warn about pseudo-prefixes ahead of a label. */ |
11823 | | |
11824 | | bool i386_check_label (void) |
11825 | 7.17k | { |
11826 | 7.17k | struct pseudo_prefixes last_pp; |
11827 | | |
11828 | 7.17k | memcpy (&last_pp, &pp, sizeof (pp)); |
11829 | 7.17k | memset (&pp, 0, sizeof (pp)); |
11830 | 7.17k | if (memcmp (&pp, &last_pp, sizeof (pp))) |
11831 | 0 | as_warn (_("pseudo prefix ahead of label; ignoring")); |
11832 | 7.17k | return true; |
11833 | 7.17k | } |
11834 | | |
11835 | | /* Hook used to parse pseudo-prefixes off of the start of a line. */ |
11836 | | |
11837 | | int |
11838 | | i386_unrecognized_line (int ch) |
11839 | 262k | { |
11840 | 262k | char mnemonic[MAX_MNEM_SIZE]; |
11841 | 262k | const char *end; |
11842 | | |
11843 | 262k | if (ch != '{') |
11844 | 258k | return 0; |
11845 | | |
11846 | 4.12k | --input_line_pointer; |
11847 | 4.12k | know (*input_line_pointer == ch); |
11848 | | |
11849 | 4.12k | end = parse_insn (input_line_pointer, mnemonic, parse_pseudo_prefix); |
11850 | 4.12k | if (end == NULL) |
11851 | 712 | { |
11852 | | /* Diagnostic was already issued. */ |
11853 | 712 | ignore_rest_of_line (); |
11854 | 712 | memset (&pp, 0, sizeof (pp)); |
11855 | 712 | return 1; |
11856 | 712 | } |
11857 | | |
11858 | 3.41k | if (end == input_line_pointer) |
11859 | 3.36k | { |
11860 | 3.36k | ++input_line_pointer; |
11861 | 3.36k | return 0; |
11862 | 3.36k | } |
11863 | | |
11864 | 50 | input_line_pointer += end - input_line_pointer; |
11865 | 50 | return 1; |
11866 | 3.41k | } |
11867 | | |
11868 | | #ifdef OBJ_ELF |
11869 | | void |
11870 | | x86_cleanup (void) |
11871 | 28 | { |
11872 | 28 | char *p; |
11873 | 28 | asection *seg = now_seg; |
11874 | 28 | subsegT subseg = now_subseg; |
11875 | 28 | asection *sec; |
11876 | 28 | unsigned int alignment, align_size_1; |
11877 | 28 | unsigned int isa_1_descsz, feature_2_descsz, descsz; |
11878 | 28 | unsigned int isa_1_descsz_raw, feature_2_descsz_raw; |
11879 | 28 | unsigned int padding; |
11880 | | |
11881 | 28 | if (!x86_used_note) |
11882 | 0 | return; |
11883 | | |
11884 | 28 | x86_feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_X86; |
11885 | | |
11886 | | /* The .note.gnu.property section layout: |
11887 | | |
11888 | | Field Length Contents |
11889 | | ---- ---- ---- |
11890 | | n_namsz 4 4 |
11891 | | n_descsz 4 The note descriptor size |
11892 | | n_type 4 NT_GNU_PROPERTY_TYPE_0 |
11893 | | n_name 4 "GNU" |
11894 | | n_desc n_descsz The program property array |
11895 | | .... .... .... |
11896 | | */ |
11897 | | |
11898 | | /* Create the .note.gnu.property section. */ |
11899 | 28 | sec = subseg_new (NOTE_GNU_PROPERTY_SECTION_NAME, 0); |
11900 | 28 | bfd_set_section_flags (sec, |
11901 | 28 | (SEC_ALLOC |
11902 | 28 | | SEC_LOAD |
11903 | 28 | | SEC_DATA |
11904 | 28 | | SEC_HAS_CONTENTS |
11905 | 28 | | SEC_READONLY)); |
11906 | | |
11907 | 28 | if (get_elf_backend_data (stdoutput)->s->elfclass == ELFCLASS64) |
11908 | 28 | { |
11909 | 28 | align_size_1 = 7; |
11910 | 28 | alignment = 3; |
11911 | 28 | } |
11912 | 0 | else |
11913 | 0 | { |
11914 | 0 | align_size_1 = 3; |
11915 | 0 | alignment = 2; |
11916 | 0 | } |
11917 | | |
11918 | 28 | bfd_set_section_alignment (sec, alignment); |
11919 | 28 | elf_section_type (sec) = SHT_NOTE; |
11920 | | |
11921 | | /* GNU_PROPERTY_X86_ISA_1_USED: 4-byte type + 4-byte data size |
11922 | | + 4-byte data */ |
11923 | 28 | isa_1_descsz_raw = 4 + 4 + 4; |
11924 | | /* Align GNU_PROPERTY_X86_ISA_1_USED. */ |
11925 | 28 | isa_1_descsz = (isa_1_descsz_raw + align_size_1) & ~align_size_1; |
11926 | | |
11927 | 28 | feature_2_descsz_raw = isa_1_descsz; |
11928 | | /* GNU_PROPERTY_X86_FEATURE_2_USED: 4-byte type + 4-byte data size |
11929 | | + 4-byte data */ |
11930 | 28 | feature_2_descsz_raw += 4 + 4 + 4; |
11931 | | /* Align GNU_PROPERTY_X86_FEATURE_2_USED. */ |
11932 | 28 | feature_2_descsz = ((feature_2_descsz_raw + align_size_1) |
11933 | 28 | & ~align_size_1); |
11934 | | |
11935 | 28 | descsz = feature_2_descsz; |
11936 | | /* Section size: n_namsz + n_descsz + n_type + n_name + n_descsz. */ |
11937 | 28 | p = frag_more (4 + 4 + 4 + 4 + descsz); |
11938 | | |
11939 | | /* Write n_namsz. */ |
11940 | 28 | md_number_to_chars (p, (valueT) 4, 4); |
11941 | | |
11942 | | /* Write n_descsz. */ |
11943 | 28 | md_number_to_chars (p + 4, (valueT) descsz, 4); |
11944 | | |
11945 | | /* Write n_type. */ |
11946 | 28 | md_number_to_chars (p + 4 * 2, (valueT) NT_GNU_PROPERTY_TYPE_0, 4); |
11947 | | |
11948 | | /* Write n_name. */ |
11949 | 28 | memcpy (p + 4 * 3, "GNU", 4); |
11950 | | |
11951 | | /* Write 4-byte type. */ |
11952 | 28 | md_number_to_chars (p + 4 * 4, |
11953 | 28 | (valueT) GNU_PROPERTY_X86_ISA_1_USED, 4); |
11954 | | |
11955 | | /* Write 4-byte data size. */ |
11956 | 28 | md_number_to_chars (p + 4 * 5, (valueT) 4, 4); |
11957 | | |
11958 | | /* Write 4-byte data. */ |
11959 | 28 | md_number_to_chars (p + 4 * 6, (valueT) x86_isa_1_used, 4); |
11960 | | |
11961 | | /* Zero out paddings. */ |
11962 | 28 | padding = isa_1_descsz - isa_1_descsz_raw; |
11963 | 28 | if (padding) |
11964 | 28 | memset (p + 4 * 7, 0, padding); |
11965 | | |
11966 | | /* Write 4-byte type. */ |
11967 | 28 | md_number_to_chars (p + isa_1_descsz + 4 * 4, |
11968 | 28 | (valueT) GNU_PROPERTY_X86_FEATURE_2_USED, 4); |
11969 | | |
11970 | | /* Write 4-byte data size. */ |
11971 | 28 | md_number_to_chars (p + isa_1_descsz + 4 * 5, (valueT) 4, 4); |
11972 | | |
11973 | | /* Write 4-byte data. */ |
11974 | 28 | md_number_to_chars (p + isa_1_descsz + 4 * 6, |
11975 | 28 | (valueT) x86_feature_2_used, 4); |
11976 | | |
11977 | | /* Zero out paddings. */ |
11978 | 28 | padding = feature_2_descsz - feature_2_descsz_raw; |
11979 | 28 | if (padding) |
11980 | 28 | memset (p + isa_1_descsz + 4 * 7, 0, padding); |
11981 | | |
11982 | | /* We probably can't restore the current segment, for there likely |
11983 | | isn't one yet... */ |
11984 | 28 | if (seg && subseg) |
11985 | 7 | subseg_set (seg, subseg); |
11986 | 28 | } |
11987 | | |
11988 | | #include "tc-i386-ginsn.c" |
11989 | | |
11990 | | /* Whether SFrame stack trace info is supported. */ |
11991 | | bool |
11992 | | x86_support_sframe_p (void) |
11993 | 5 | { |
11994 | | /* At this time, SFrame stack trace is supported for AMD64 ABI only. */ |
11995 | 5 | return (x86_elf_abi == X86_64_ABI); |
11996 | 5 | } |
11997 | | |
11998 | | /* Whether SFrame return address tracking is needed. */ |
11999 | | bool |
12000 | | x86_sframe_ra_tracking_p (void) |
12001 | 9 | { |
12002 | | /* In AMD64, return address is always stored on the stack at a fixed offset |
12003 | | from the CFA (provided via x86_sframe_cfa_ra_offset ()). |
12004 | | Do not track explicitly via an SFrame Frame Row Entry. */ |
12005 | 9 | return false; |
12006 | 9 | } |
12007 | | |
12008 | | /* The fixed offset from CFA for SFrame to recover the return address. |
12009 | | (useful only when SFrame RA tracking is not needed). */ |
12010 | | offsetT |
12011 | | x86_sframe_cfa_ra_offset (void) |
12012 | 1 | { |
12013 | 1 | gas_assert (x86_elf_abi == X86_64_ABI); |
12014 | 1 | return (offsetT) -8; |
12015 | 1 | } |
12016 | | |
12017 | | /* The abi/arch identifier for SFrame. */ |
12018 | | unsigned char |
12019 | | x86_sframe_get_abi_arch (void) |
12020 | 4 | { |
12021 | 4 | unsigned char sframe_abi_arch = 0; |
12022 | | |
12023 | 4 | if (x86_support_sframe_p ()) |
12024 | 4 | { |
12025 | 4 | gas_assert (!target_big_endian); |
12026 | 4 | sframe_abi_arch = SFRAME_ABI_AMD64_ENDIAN_LITTLE; |
12027 | 4 | } |
12028 | | |
12029 | 4 | return sframe_abi_arch; |
12030 | 4 | } |
12031 | | |
12032 | | #endif |
12033 | | |
12034 | | static unsigned int |
12035 | | encoding_length (const fragS *start_frag, offsetT start_off, |
12036 | | const char *frag_now_ptr) |
12037 | 1.05k | { |
12038 | 1.05k | unsigned int len = 0; |
12039 | | |
12040 | 1.05k | if (start_frag != frag_now) |
12041 | 3 | { |
12042 | 3 | const fragS *fr = start_frag; |
12043 | | |
12044 | 3 | do { |
12045 | 3 | len += fr->fr_fix; |
12046 | 3 | fr = fr->fr_next; |
12047 | 3 | } while (fr && fr != frag_now); |
12048 | 3 | } |
12049 | | |
12050 | 1.05k | return len - start_off + (frag_now_ptr - frag_now->fr_literal); |
12051 | 1.05k | } |
12052 | | |
12053 | | /* Return 1 for test, and, cmp, add, sub, inc and dec which may |
12054 | | be macro-fused with conditional jumps. |
12055 | | NB: If TEST/AND/CMP/ADD/SUB/INC/DEC is of RIP relative address, |
12056 | | or is one of the following format: |
12057 | | |
12058 | | cmp m, imm |
12059 | | add m, imm |
12060 | | sub m, imm |
12061 | | test m, imm |
12062 | | and m, imm |
12063 | | inc m |
12064 | | dec m |
12065 | | |
12066 | | it is unfusible. */ |
12067 | | |
12068 | | static int |
12069 | | maybe_fused_with_jcc_p (enum mf_cmp_kind* mf_cmp_p) |
12070 | 0 | { |
12071 | | /* No RIP address. */ |
12072 | 0 | if (i.base_reg && i.base_reg->reg_num == RegIP) |
12073 | 0 | return 0; |
12074 | | |
12075 | | /* No opcodes outside of base encoding space. */ |
12076 | 0 | if (i.tm.opcode_space != SPACE_BASE) |
12077 | 0 | return 0; |
12078 | | |
12079 | | /* add, sub without add/sub m, imm. */ |
12080 | 0 | if (i.tm.base_opcode <= 5 |
12081 | 0 | || (i.tm.base_opcode >= 0x28 && i.tm.base_opcode <= 0x2d) |
12082 | 0 | || ((i.tm.base_opcode | 3) == 0x83 |
12083 | 0 | && (i.tm.extension_opcode == 0x5 |
12084 | 0 | || i.tm.extension_opcode == 0x0))) |
12085 | 0 | { |
12086 | 0 | *mf_cmp_p = mf_cmp_alu_cmp; |
12087 | 0 | return !(i.mem_operands && i.imm_operands); |
12088 | 0 | } |
12089 | | |
12090 | | /* and without and m, imm. */ |
12091 | 0 | if ((i.tm.base_opcode >= 0x20 && i.tm.base_opcode <= 0x25) |
12092 | 0 | || ((i.tm.base_opcode | 3) == 0x83 |
12093 | 0 | && i.tm.extension_opcode == 0x4)) |
12094 | 0 | { |
12095 | 0 | *mf_cmp_p = mf_cmp_test_and; |
12096 | 0 | return !(i.mem_operands && i.imm_operands); |
12097 | 0 | } |
12098 | | |
12099 | | /* test without test m imm. */ |
12100 | 0 | if ((i.tm.base_opcode | 1) == 0x85 |
12101 | 0 | || (i.tm.base_opcode | 1) == 0xa9 |
12102 | 0 | || ((i.tm.base_opcode | 1) == 0xf7 |
12103 | 0 | && i.tm.extension_opcode == 0)) |
12104 | 0 | { |
12105 | 0 | *mf_cmp_p = mf_cmp_test_and; |
12106 | 0 | return !(i.mem_operands && i.imm_operands); |
12107 | 0 | } |
12108 | | |
12109 | | /* cmp without cmp m, imm. */ |
12110 | 0 | if ((i.tm.base_opcode >= 0x38 && i.tm.base_opcode <= 0x3d) |
12111 | 0 | || ((i.tm.base_opcode | 3) == 0x83 |
12112 | 0 | && (i.tm.extension_opcode == 0x7))) |
12113 | 0 | { |
12114 | 0 | *mf_cmp_p = mf_cmp_alu_cmp; |
12115 | 0 | return !(i.mem_operands && i.imm_operands); |
12116 | 0 | } |
12117 | | |
12118 | | /* inc, dec without inc/dec m. */ |
12119 | 0 | if ((is_cpu (&i.tm, CpuNo64) |
12120 | 0 | && (i.tm.base_opcode | 0xf) == 0x4f) |
12121 | 0 | || ((i.tm.base_opcode | 1) == 0xff |
12122 | 0 | && i.tm.extension_opcode <= 0x1)) |
12123 | 0 | { |
12124 | 0 | *mf_cmp_p = mf_cmp_incdec; |
12125 | 0 | return !i.mem_operands; |
12126 | 0 | } |
12127 | | |
12128 | 0 | return 0; |
12129 | 0 | } |
12130 | | |
12131 | | /* Return 1 if a FUSED_JCC_PADDING frag should be generated. */ |
12132 | | |
12133 | | static int |
12134 | | add_fused_jcc_padding_frag_p (enum mf_cmp_kind *mf_cmp_p, |
12135 | | const struct last_insn *last_insn) |
12136 | 2.92k | { |
12137 | | /* NB: Don't work with COND_JUMP86 without i386. */ |
12138 | 2.92k | if (!align_branch_power |
12139 | 2.92k | || now_seg == absolute_section |
12140 | 2.92k | || !cpu_arch_flags.bitfield.cpui386 |
12141 | 2.92k | || !(align_branch & align_branch_fused_bit)) |
12142 | 2.92k | return 0; |
12143 | | |
12144 | 0 | if (maybe_fused_with_jcc_p (mf_cmp_p)) |
12145 | 0 | { |
12146 | 0 | if (last_insn->kind == last_insn_other) |
12147 | 0 | return 1; |
12148 | 0 | if (flag_debug) |
12149 | 0 | as_warn_where (last_insn->file, last_insn->line, |
12150 | 0 | _("`%s` skips -malign-branch-boundary on `%s`"), |
12151 | 0 | last_insn->name, insn_name (&i.tm)); |
12152 | 0 | } |
12153 | | |
12154 | 0 | return 0; |
12155 | 0 | } |
12156 | | |
12157 | | /* Return 1 if a BRANCH_PREFIX frag should be generated. */ |
12158 | | |
12159 | | static int |
12160 | | add_branch_prefix_frag_p (const struct last_insn *last_insn) |
12161 | 2.92k | { |
12162 | | /* NB: Don't work with COND_JUMP86 without i386. Don't add prefix |
12163 | | to PadLock instructions since they include prefixes in opcode. */ |
12164 | 2.92k | if (!align_branch_power |
12165 | 2.92k | || !align_branch_prefix_size |
12166 | 2.92k | || now_seg == absolute_section |
12167 | 2.92k | || is_cpu (&i.tm, CpuPadLock) |
12168 | 2.92k | || is_cpu (&i.tm, CpuPadLockRNG2) |
12169 | 2.92k | || is_cpu (&i.tm, CpuPadLockPHE2) |
12170 | 2.92k | || is_cpu (&i.tm, CpuPadLockXMODX) |
12171 | 2.92k | || !cpu_arch_flags.bitfield.cpui386) |
12172 | 2.92k | return 0; |
12173 | | |
12174 | | /* Don't add prefix if it is a prefix or there is no operand in case |
12175 | | that segment prefix is special. */ |
12176 | 0 | if (!i.operands || i.tm.opcode_modifier.isprefix) |
12177 | 0 | return 0; |
12178 | | |
12179 | 0 | if (last_insn->kind == last_insn_other) |
12180 | 0 | return 1; |
12181 | | |
12182 | 0 | if (flag_debug) |
12183 | 0 | as_warn_where (last_insn->file, last_insn->line, |
12184 | 0 | _("`%s` skips -malign-branch-boundary on `%s`"), |
12185 | 0 | last_insn->name, insn_name (&i.tm)); |
12186 | |
|
12187 | 0 | return 0; |
12188 | 0 | } |
12189 | | |
12190 | | /* Return 1 if a BRANCH_PADDING frag should be generated. */ |
12191 | | |
12192 | | static int |
12193 | | add_branch_padding_frag_p (enum align_branch_kind *branch_p, |
12194 | | enum mf_jcc_kind *mf_jcc_p, |
12195 | | const struct last_insn *last_insn) |
12196 | 3.41k | { |
12197 | 3.41k | int add_padding; |
12198 | | |
12199 | | /* NB: Don't work with COND_JUMP86 without i386. */ |
12200 | 3.41k | if (!align_branch_power |
12201 | 3.41k | || now_seg == absolute_section |
12202 | 3.41k | || !cpu_arch_flags.bitfield.cpui386 |
12203 | 3.41k | || i.tm.opcode_space != SPACE_BASE) |
12204 | 3.41k | return 0; |
12205 | | |
12206 | 0 | add_padding = 0; |
12207 | | |
12208 | | /* Check for jcc and direct jmp. */ |
12209 | 0 | if (i.tm.opcode_modifier.jump == JUMP) |
12210 | 0 | { |
12211 | 0 | if (i.tm.base_opcode == JUMP_PC_RELATIVE) |
12212 | 0 | { |
12213 | 0 | *branch_p = align_branch_jmp; |
12214 | 0 | add_padding = align_branch & align_branch_jmp_bit; |
12215 | 0 | } |
12216 | 0 | else |
12217 | 0 | { |
12218 | | /* Because J<cc> and JN<cc> share same group in macro-fusible table, |
12219 | | igore the lowest bit. */ |
12220 | 0 | *mf_jcc_p = (i.tm.base_opcode & 0x0e) >> 1; |
12221 | 0 | *branch_p = align_branch_jcc; |
12222 | 0 | if ((align_branch & align_branch_jcc_bit)) |
12223 | 0 | add_padding = 1; |
12224 | 0 | } |
12225 | 0 | } |
12226 | 0 | else if ((i.tm.base_opcode | 1) == 0xc3) |
12227 | 0 | { |
12228 | | /* Near ret. */ |
12229 | 0 | *branch_p = align_branch_ret; |
12230 | 0 | if ((align_branch & align_branch_ret_bit)) |
12231 | 0 | add_padding = 1; |
12232 | 0 | } |
12233 | 0 | else |
12234 | 0 | { |
12235 | | /* Check for indirect jmp, direct and indirect calls. */ |
12236 | 0 | if (i.tm.base_opcode == 0xe8) |
12237 | 0 | { |
12238 | | /* Direct call. */ |
12239 | 0 | *branch_p = align_branch_call; |
12240 | 0 | if ((align_branch & align_branch_call_bit)) |
12241 | 0 | add_padding = 1; |
12242 | 0 | } |
12243 | 0 | else if (i.tm.base_opcode == 0xff |
12244 | 0 | && (i.tm.extension_opcode == 2 |
12245 | 0 | || i.tm.extension_opcode == 4)) |
12246 | 0 | { |
12247 | | /* Indirect call and jmp. */ |
12248 | 0 | *branch_p = align_branch_indirect; |
12249 | 0 | if ((align_branch & align_branch_indirect_bit)) |
12250 | 0 | add_padding = 1; |
12251 | 0 | } |
12252 | |
|
12253 | 0 | if (add_padding |
12254 | 0 | && i.disp_operands |
12255 | 0 | && tls_get_addr |
12256 | 0 | && (i.op[0].disps->X_op == O_symbol |
12257 | 0 | || (i.op[0].disps->X_op == O_subtract |
12258 | 0 | && i.op[0].disps->X_op_symbol == GOT_symbol))) |
12259 | 0 | { |
12260 | 0 | symbolS *s = i.op[0].disps->X_add_symbol; |
12261 | | /* No padding to call to global or undefined tls_get_addr. */ |
12262 | 0 | if ((S_IS_EXTERNAL (s) || !S_IS_DEFINED (s)) |
12263 | 0 | && strcmp (S_GET_NAME (s), tls_get_addr) == 0) |
12264 | 0 | return 0; |
12265 | 0 | } |
12266 | 0 | } |
12267 | | |
12268 | 0 | if (add_padding |
12269 | 0 | && last_insn->kind != last_insn_other) |
12270 | 0 | { |
12271 | 0 | if (flag_debug) |
12272 | 0 | as_warn_where (last_insn->file, last_insn->line, |
12273 | 0 | _("`%s` skips -malign-branch-boundary on `%s`"), |
12274 | 0 | last_insn->name, insn_name (&i.tm)); |
12275 | 0 | return 0; |
12276 | 0 | } |
12277 | | |
12278 | 0 | return add_padding; |
12279 | 0 | } |
12280 | | |
12281 | | static void |
12282 | | output_insn (const struct last_insn *last_insn) |
12283 | 3.41k | { |
12284 | 3.41k | fragS *insn_start_frag; |
12285 | 3.41k | offsetT insn_start_off; |
12286 | 3.41k | fragS *fragP = NULL; |
12287 | 3.41k | enum align_branch_kind branch = align_branch_none; |
12288 | | /* The initializer is arbitrary just to avoid uninitialized error. |
12289 | | it's actually either assigned in add_branch_padding_frag_p |
12290 | | or never be used. */ |
12291 | 3.41k | enum mf_jcc_kind mf_jcc = mf_jcc_jo; |
12292 | | |
12293 | 3.41k | #ifdef OBJ_ELF |
12294 | 3.41k | if (x86_used_note && now_seg != absolute_section) |
12295 | 1.45k | { |
12296 | 1.45k | unsigned int feature_2_used = 0; |
12297 | | |
12298 | 1.45k | if ((i.xstate & xstate_tmm) == xstate_tmm |
12299 | 1.45k | || is_cpu (&i.tm, CpuAMX_TILE)) |
12300 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_TMM; |
12301 | | |
12302 | 1.45k | if (is_cpu (&i.tm, Cpu8087) |
12303 | 1.45k | || is_cpu (&i.tm, Cpu287) |
12304 | 1.45k | || is_cpu (&i.tm, Cpu387) |
12305 | 1.45k | || is_cpu (&i.tm, Cpu687) |
12306 | 1.45k | || is_cpu (&i.tm, CpuFISTTP)) |
12307 | 4 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_X87; |
12308 | | |
12309 | 1.45k | if ((i.xstate & xstate_mmx) |
12310 | 1.45k | || i.tm.mnem_off == MN_emms |
12311 | 1.45k | || i.tm.mnem_off == MN_femms) |
12312 | 26 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_MMX; |
12313 | | |
12314 | 1.45k | if (i.index_reg) |
12315 | 0 | { |
12316 | 0 | if (i.index_reg->reg_type.bitfield.zmmword) |
12317 | 0 | i.xstate |= xstate_zmm; |
12318 | 0 | else if (i.index_reg->reg_type.bitfield.ymmword) |
12319 | 0 | i.xstate |= xstate_ymm; |
12320 | 0 | else if (i.index_reg->reg_type.bitfield.xmmword) |
12321 | 0 | i.xstate |= xstate_xmm; |
12322 | 0 | } |
12323 | | |
12324 | | /* vzeroall / vzeroupper */ |
12325 | 1.45k | if (i.tm.base_opcode == 0x77 && is_cpu (&i.tm, CpuAVX)) |
12326 | 0 | i.xstate |= xstate_ymm; |
12327 | | |
12328 | 1.45k | if ((i.xstate & xstate_xmm) |
12329 | | /* ldmxcsr / stmxcsr / vldmxcsr / vstmxcsr */ |
12330 | 1.45k | || (i.tm.base_opcode == 0xae |
12331 | 1.45k | && (is_cpu (&i.tm, CpuSSE) |
12332 | 23 | || is_cpu (&i.tm, CpuAVX))) |
12333 | 1.45k | || is_cpu (&i.tm, CpuWideKL) |
12334 | 1.45k | || is_cpu (&i.tm, CpuKL)) |
12335 | 23 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_XMM; |
12336 | | |
12337 | 1.45k | if ((i.xstate & xstate_ymm) == xstate_ymm) |
12338 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_YMM; |
12339 | 1.45k | if ((i.xstate & xstate_zmm) == xstate_zmm) |
12340 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_ZMM; |
12341 | 1.45k | if (i.mask.reg || (i.xstate & xstate_mask) == xstate_mask) |
12342 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_MASK; |
12343 | 1.45k | if (is_cpu (&i.tm, CpuFXSR)) |
12344 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_FXSR; |
12345 | 1.45k | if (is_cpu (&i.tm, CpuXsave)) |
12346 | 1 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_XSAVE; |
12347 | 1.45k | if (is_cpu (&i.tm, CpuXsaveopt)) |
12348 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_XSAVEOPT; |
12349 | 1.45k | if (is_cpu (&i.tm, CpuXSAVEC)) |
12350 | 0 | feature_2_used |= GNU_PROPERTY_X86_FEATURE_2_XSAVEC; |
12351 | | |
12352 | 1.45k | x86_feature_2_used |= feature_2_used; |
12353 | | |
12354 | 1.45k | if (object_64bit |
12355 | 1.45k | || (feature_2_used |
12356 | 0 | & (GNU_PROPERTY_X86_FEATURE_2_XMM |
12357 | 0 | | GNU_PROPERTY_X86_FEATURE_2_FXSR)) != 0 |
12358 | 1.45k | || is_cpu (&i.tm, CpuCMOV) |
12359 | 1.45k | || is_cpu (&i.tm, CpuSYSCALL) |
12360 | 1.45k | || i.tm.mnem_off == MN_cmpxchg8b) |
12361 | 1.45k | x86_isa_1_used |= GNU_PROPERTY_X86_ISA_1_BASELINE; |
12362 | 1.45k | if (is_cpu (&i.tm, CpuSSE3) |
12363 | 1.45k | || is_cpu (&i.tm, CpuSSSE3) |
12364 | 1.45k | || is_cpu (&i.tm, CpuSSE4_1) |
12365 | 1.45k | || is_cpu (&i.tm, CpuSSE4_2) |
12366 | 1.45k | || is_cpu (&i.tm, CpuCX16) |
12367 | 1.45k | || is_cpu (&i.tm, CpuPOPCNT) |
12368 | | /* LAHF-SAHF insns in 64-bit mode. */ |
12369 | 1.45k | || (flag_code == CODE_64BIT |
12370 | 1.45k | && (i.tm.base_opcode | 1) == 0x9f |
12371 | 1.45k | && i.tm.opcode_space == SPACE_BASE)) |
12372 | 0 | x86_isa_1_used |= GNU_PROPERTY_X86_ISA_1_V2; |
12373 | 1.45k | if (is_cpu (&i.tm, CpuAVX) |
12374 | 1.45k | || is_cpu (&i.tm, CpuAVX2) |
12375 | | /* Any VEX encoded insns execpt for AVX512F, AVX512BW, AVX512DQ, |
12376 | | XOP, FMA4, LPW, TBM, and AMX. */ |
12377 | 1.45k | || (i.tm.opcode_modifier.vex |
12378 | 1.43k | && !is_cpu (&i.tm, CpuAVX512F) |
12379 | 1.43k | && !is_cpu (&i.tm, CpuAVX512BW) |
12380 | 1.43k | && !is_cpu (&i.tm, CpuAVX512DQ) |
12381 | 1.43k | && !is_cpu (&i.tm, CpuXOP) |
12382 | 1.43k | && !is_cpu (&i.tm, CpuFMA4) |
12383 | 1.43k | && !is_cpu (&i.tm, CpuLWP) |
12384 | 1.43k | && !is_cpu (&i.tm, CpuTBM) |
12385 | 1.43k | && !(feature_2_used & GNU_PROPERTY_X86_FEATURE_2_TMM)) |
12386 | 1.45k | || is_cpu (&i.tm, CpuLZCNT) |
12387 | 1.45k | || is_cpu (&i.tm, CpuMovbe) |
12388 | 1.45k | || is_cpu (&i.tm, CpuXSAVES) |
12389 | 1.45k | || (feature_2_used |
12390 | 1.41k | & (GNU_PROPERTY_X86_FEATURE_2_XSAVE |
12391 | 1.41k | | GNU_PROPERTY_X86_FEATURE_2_XSAVEOPT |
12392 | 1.41k | | GNU_PROPERTY_X86_FEATURE_2_XSAVEC)) != 0) |
12393 | 45 | x86_isa_1_used |= GNU_PROPERTY_X86_ISA_1_V3; |
12394 | 1.45k | if (is_cpu (&i.tm, CpuAVX512F) |
12395 | 1.45k | || is_cpu (&i.tm, CpuAVX512BW) |
12396 | 1.45k | || is_cpu (&i.tm, CpuAVX512DQ) |
12397 | 1.45k | || is_cpu (&i.tm, CpuAVX512VL) |
12398 | | /* Any EVEX encoded insns except for AVX512ER, AVX512PF, |
12399 | | AVX512-4FMAPS, and AVX512-4VNNIW. */ |
12400 | 1.45k | || (i.tm.opcode_modifier.evex |
12401 | 1.45k | && !is_cpu (&i.tm, CpuAVX512ER) |
12402 | 1.45k | && !is_cpu (&i.tm, CpuAVX512PF) |
12403 | 1.45k | && !is_cpu (&i.tm, CpuAVX512_4FMAPS) |
12404 | 1.45k | && !is_cpu (&i.tm, CpuAVX512_4VNNIW))) |
12405 | 0 | x86_isa_1_used |= GNU_PROPERTY_X86_ISA_1_V4; |
12406 | 1.45k | } |
12407 | 3.41k | #endif |
12408 | | |
12409 | | /* Tie dwarf2 debug info to the address at the start of the insn. |
12410 | | We can't do this after the insn has been output as the current |
12411 | | frag may have been closed off. eg. by frag_var. */ |
12412 | 3.41k | dwarf2_emit_insn (0); |
12413 | | |
12414 | 3.41k | insn_start_frag = frag_now; |
12415 | 3.41k | insn_start_off = frag_now_fix (); |
12416 | | |
12417 | 3.41k | if (add_branch_padding_frag_p (&branch, &mf_jcc, last_insn)) |
12418 | 0 | { |
12419 | 0 | char *p; |
12420 | | /* Branch can be 8 bytes. Leave some room for prefixes. */ |
12421 | 0 | unsigned int max_branch_padding_size = 14; |
12422 | | |
12423 | | /* Align section to boundary. */ |
12424 | 0 | record_alignment (now_seg, align_branch_power); |
12425 | | |
12426 | | /* Make room for padding. */ |
12427 | 0 | frag_grow (max_branch_padding_size); |
12428 | | |
12429 | | /* Start of the padding. */ |
12430 | 0 | p = frag_more (0); |
12431 | |
|
12432 | 0 | fragP = frag_now; |
12433 | |
|
12434 | 0 | frag_var (rs_machine_dependent, max_branch_padding_size, 0, |
12435 | 0 | ENCODE_RELAX_STATE (BRANCH_PADDING, 0), |
12436 | 0 | NULL, 0, p); |
12437 | |
|
12438 | 0 | fragP->tc_frag_data.mf_type = mf_jcc; |
12439 | 0 | fragP->tc_frag_data.branch_type = branch; |
12440 | 0 | fragP->tc_frag_data.max_bytes = max_branch_padding_size; |
12441 | 0 | } |
12442 | | |
12443 | 3.41k | if (!cpu_arch_flags.bitfield.cpui386 && (flag_code != CODE_16BIT) |
12444 | 3.41k | && !pre_386_16bit_warned) |
12445 | 0 | { |
12446 | 0 | as_warn (_("use .code16 to ensure correct addressing mode")); |
12447 | 0 | pre_386_16bit_warned = true; |
12448 | 0 | } |
12449 | | |
12450 | | /* Output jumps. */ |
12451 | 3.41k | if (i.tm.opcode_modifier.jump == JUMP) |
12452 | 153 | output_branch (); |
12453 | 3.25k | else if (i.tm.opcode_modifier.jump == JUMP_BYTE |
12454 | 3.25k | || i.tm.opcode_modifier.jump == JUMP_DWORD) |
12455 | 331 | output_jump (); |
12456 | 2.92k | else if (i.tm.opcode_modifier.jump == JUMP_INTERSEGMENT) |
12457 | 0 | output_interseg_jump (); |
12458 | 2.92k | else |
12459 | 2.92k | { |
12460 | | /* Output normal instructions here. */ |
12461 | 2.92k | char *p; |
12462 | 2.92k | unsigned char *q; |
12463 | 2.92k | unsigned int j; |
12464 | 2.92k | enum mf_cmp_kind mf_cmp; |
12465 | | |
12466 | 2.92k | if (avoid_fence |
12467 | 2.92k | && (i.tm.base_opcode == 0xaee8 |
12468 | 0 | || i.tm.base_opcode == 0xaef0 |
12469 | 0 | || i.tm.base_opcode == 0xaef8)) |
12470 | 0 | { |
12471 | | /* Encode lfence, mfence, and sfence as |
12472 | | f0 83 04 24 00 lock addl $0x0, (%{re}sp). */ |
12473 | 0 | if (flag_code == CODE_16BIT) |
12474 | 0 | as_bad (_("Cannot convert `%s' in 16-bit mode"), insn_name (&i.tm)); |
12475 | 0 | else if (omit_lock_prefix) |
12476 | 0 | as_bad (_("Cannot convert `%s' with `-momit-lock-prefix=yes' in effect"), |
12477 | 0 | insn_name (&i.tm)); |
12478 | 0 | else if (now_seg != absolute_section) |
12479 | 0 | { |
12480 | 0 | offsetT val = 0x240483f0ULL; |
12481 | |
|
12482 | 0 | p = frag_more (5); |
12483 | 0 | md_number_to_chars (p, val, 5); |
12484 | 0 | } |
12485 | 0 | else |
12486 | 0 | abs_section_offset += 5; |
12487 | 0 | return; |
12488 | 0 | } |
12489 | | |
12490 | | /* Some processors fail on LOCK prefix. This options makes |
12491 | | assembler ignore LOCK prefix and serves as a workaround. */ |
12492 | 2.92k | if (omit_lock_prefix) |
12493 | 0 | { |
12494 | 0 | if (i.tm.base_opcode == LOCK_PREFIX_OPCODE |
12495 | 0 | && i.tm.opcode_modifier.isprefix) |
12496 | 0 | return; |
12497 | 0 | i.prefix[LOCK_PREFIX] = 0; |
12498 | 0 | } |
12499 | | |
12500 | 2.92k | if (branch) |
12501 | | /* Skip if this is a branch. */ |
12502 | 0 | ; |
12503 | 2.92k | else if (add_fused_jcc_padding_frag_p (&mf_cmp, last_insn)) |
12504 | 0 | { |
12505 | | /* Make room for padding. */ |
12506 | 0 | frag_grow (MAX_FUSED_JCC_PADDING_SIZE); |
12507 | 0 | p = frag_more (0); |
12508 | |
|
12509 | 0 | fragP = frag_now; |
12510 | |
|
12511 | 0 | frag_var (rs_machine_dependent, MAX_FUSED_JCC_PADDING_SIZE, 0, |
12512 | 0 | ENCODE_RELAX_STATE (FUSED_JCC_PADDING, 0), |
12513 | 0 | NULL, 0, p); |
12514 | |
|
12515 | 0 | fragP->tc_frag_data.mf_type = mf_cmp; |
12516 | 0 | fragP->tc_frag_data.branch_type = align_branch_fused; |
12517 | 0 | fragP->tc_frag_data.max_bytes = MAX_FUSED_JCC_PADDING_SIZE; |
12518 | 0 | } |
12519 | 2.92k | else if (add_branch_prefix_frag_p (last_insn)) |
12520 | 0 | { |
12521 | 0 | unsigned int max_prefix_size = align_branch_prefix_size; |
12522 | | |
12523 | | /* Make room for padding. */ |
12524 | 0 | frag_grow (max_prefix_size); |
12525 | 0 | p = frag_more (0); |
12526 | |
|
12527 | 0 | fragP = frag_now; |
12528 | |
|
12529 | 0 | frag_var (rs_machine_dependent, max_prefix_size, 0, |
12530 | 0 | ENCODE_RELAX_STATE (BRANCH_PREFIX, 0), |
12531 | 0 | NULL, 0, p); |
12532 | |
|
12533 | 0 | fragP->tc_frag_data.max_bytes = max_prefix_size; |
12534 | 0 | } |
12535 | | |
12536 | | /* Since the VEX/EVEX prefix contains the implicit prefix, we |
12537 | | don't need the explicit prefix. */ |
12538 | 2.92k | if (!is_any_vex_encoding (&i.tm)) |
12539 | 2.41k | { |
12540 | 2.41k | switch (i.tm.opcode_modifier.opcodeprefix) |
12541 | 2.41k | { |
12542 | 0 | case PREFIX_0X66: |
12543 | 0 | add_prefix (0x66); |
12544 | 0 | break; |
12545 | 0 | case PREFIX_0XF2: |
12546 | 0 | add_prefix (0xf2); |
12547 | 0 | break; |
12548 | 1 | case PREFIX_0XF3: |
12549 | 1 | if ((!is_cpu (&i.tm, CpuPadLock) |
12550 | 1 | && !is_cpu (&i.tm, CpuPadLockRNG2) |
12551 | 1 | && !is_cpu (&i.tm, CpuPadLockPHE2) |
12552 | 1 | && !is_cpu (&i.tm, CpuPadLockXMODX)) |
12553 | 1 | || (i.prefix[REP_PREFIX] != 0xf3)) |
12554 | 1 | add_prefix (0xf3); |
12555 | 1 | break; |
12556 | 2.41k | case PREFIX_NONE: |
12557 | 2.41k | switch (i.opcode_length) |
12558 | 2.41k | { |
12559 | 25 | case 2: |
12560 | 25 | break; |
12561 | 2.38k | case 1: |
12562 | | /* Check for pseudo prefixes. */ |
12563 | 2.38k | if (!i.tm.opcode_modifier.isprefix || i.tm.base_opcode) |
12564 | 2.38k | break; |
12565 | 0 | as_bad_where (insn_start_frag->fr_file, |
12566 | 0 | insn_start_frag->fr_line, |
12567 | 0 | _("pseudo prefix without instruction")); |
12568 | 0 | return; |
12569 | 0 | default: |
12570 | 0 | abort (); |
12571 | 2.41k | } |
12572 | 2.41k | break; |
12573 | 2.41k | default: |
12574 | 0 | abort (); |
12575 | 2.41k | } |
12576 | | |
12577 | 2.41k | #ifdef OBJ_ELF |
12578 | | /* For x32, add a dummy REX_OPCODE prefix for mov/add with |
12579 | | R_X86_64_GOTTPOFF relocation so that linker can safely |
12580 | | perform IE->LE optimization. A dummy REX_OPCODE prefix |
12581 | | is also needed for lea with R_X86_64_GOTPC32_TLSDESC |
12582 | | relocation for GDesc -> IE/LE optimization. */ |
12583 | 2.41k | if (x86_elf_abi == X86_64_X32_ABI |
12584 | 2.41k | && !is_apx_rex2_encoding () |
12585 | 2.41k | && (dot_insn () ? i.insn_opcode_space |
12586 | 0 | : i.tm.opcode_space) == SPACE_BASE |
12587 | 2.41k | && i.operands == 2 |
12588 | 2.41k | && (i.reloc[0] == BFD_RELOC_X86_64_GOTTPOFF |
12589 | 0 | || i.reloc[0] == BFD_RELOC_X86_64_GOTPC32_TLSDESC) |
12590 | 2.41k | && i.prefix[REX_PREFIX] == 0) |
12591 | 0 | add_prefix (REX_OPCODE); |
12592 | 2.41k | #endif |
12593 | | |
12594 | | /* The prefix bytes. */ |
12595 | 19.3k | for (j = ARRAY_SIZE (i.prefix), q = i.prefix; j > 0; j--, q++) |
12596 | 16.9k | if (*q) |
12597 | 20 | frag_opcode_byte (*q); |
12598 | | |
12599 | 2.41k | if (is_apx_rex2_encoding ()) |
12600 | 0 | { |
12601 | 0 | frag_opcode_byte (i.vex.bytes[0]); |
12602 | 0 | frag_opcode_byte (i.vex.bytes[1]); |
12603 | 0 | } |
12604 | 2.41k | } |
12605 | 512 | else |
12606 | 512 | { |
12607 | 4.09k | for (j = 0, q = i.prefix; j < ARRAY_SIZE (i.prefix); j++, q++) |
12608 | 3.58k | if (*q) |
12609 | 0 | switch (j) |
12610 | 0 | { |
12611 | 0 | case SEG_PREFIX: |
12612 | 0 | case ADDR_PREFIX: |
12613 | 0 | frag_opcode_byte (*q); |
12614 | 0 | break; |
12615 | 0 | default: |
12616 | | /* There should be no other prefixes for instructions |
12617 | | with VEX prefix. */ |
12618 | 0 | abort (); |
12619 | 0 | } |
12620 | | |
12621 | | /* For EVEX instructions i.vrex should become 0 after |
12622 | | build_evex_prefix. For VEX instructions upper 16 registers |
12623 | | aren't available, so VREX should be 0. */ |
12624 | 512 | if (i.vrex) |
12625 | 0 | abort (); |
12626 | | /* Now the VEX prefix. */ |
12627 | 512 | if (now_seg != absolute_section) |
12628 | 44 | { |
12629 | 44 | p = frag_more (i.vex.length); |
12630 | 153 | for (j = 0; j < i.vex.length; j++) |
12631 | 109 | p[j] = i.vex.bytes[j]; |
12632 | 44 | } |
12633 | 468 | else |
12634 | 468 | abs_section_offset += i.vex.length; |
12635 | 512 | } |
12636 | | |
12637 | | /* Now the opcode; be careful about word order here! */ |
12638 | 2.92k | j = i.opcode_length; |
12639 | 2.92k | if (!i.vex.length) |
12640 | 2.41k | switch (i.tm.opcode_space) |
12641 | 2.41k | { |
12642 | 2.17k | case SPACE_BASE: |
12643 | 2.17k | break; |
12644 | 238 | case SPACE_0F: |
12645 | 238 | ++j; |
12646 | 238 | break; |
12647 | 0 | case SPACE_0F38: |
12648 | 0 | case SPACE_0F3A: |
12649 | 0 | j += 2; |
12650 | 0 | break; |
12651 | 0 | default: |
12652 | 0 | abort (); |
12653 | 2.41k | } |
12654 | | |
12655 | 2.92k | if (now_seg == absolute_section) |
12656 | 1.87k | abs_section_offset += j; |
12657 | 1.05k | else if (j == 1) |
12658 | 814 | { |
12659 | 814 | FRAG_APPEND_1_CHAR (i.tm.base_opcode); |
12660 | 814 | } |
12661 | 239 | else |
12662 | 239 | { |
12663 | 239 | p = frag_more (j); |
12664 | 239 | if (!i.vex.length |
12665 | 239 | && i.tm.opcode_space != SPACE_BASE) |
12666 | 225 | { |
12667 | 225 | *p++ = 0x0f; |
12668 | 225 | if (i.tm.opcode_space != SPACE_0F) |
12669 | 0 | *p++ = i.tm.opcode_space == SPACE_0F38 |
12670 | 0 | ? 0x38 : 0x3a; |
12671 | 225 | } |
12672 | | |
12673 | 239 | switch (i.opcode_length) |
12674 | 239 | { |
12675 | 19 | case 2: |
12676 | | /* Put out high byte first: can't use md_number_to_chars! */ |
12677 | 19 | *p++ = (i.tm.base_opcode >> 8) & 0xff; |
12678 | | /* Fall through. */ |
12679 | 239 | case 1: |
12680 | 239 | *p = i.tm.base_opcode & 0xff; |
12681 | 239 | break; |
12682 | 0 | default: |
12683 | 0 | abort (); |
12684 | 0 | break; |
12685 | 239 | } |
12686 | | |
12687 | 239 | } |
12688 | | |
12689 | | /* Now the modrm byte and sib byte (if present). */ |
12690 | 2.92k | if (i.tm.opcode_modifier.modrm) |
12691 | 2.09k | { |
12692 | 2.09k | frag_opcode_byte ((i.rm.regmem << 0) |
12693 | 2.09k | | (i.rm.reg << 3) |
12694 | 2.09k | | (i.rm.mode << 6)); |
12695 | | /* If i.rm.regmem == ESP (4) |
12696 | | && i.rm.mode != (Register mode) |
12697 | | && not 16 bit |
12698 | | ==> need second modrm byte. */ |
12699 | 2.09k | if (i.rm.regmem == ESCAPE_TO_TWO_BYTE_ADDRESSING |
12700 | 2.09k | && i.rm.mode != 3 |
12701 | 2.09k | && !(i.base_reg && i.base_reg->reg_type.bitfield.word)) |
12702 | 224 | frag_opcode_byte ((i.sib.base << 0) |
12703 | 224 | | (i.sib.index << 3) |
12704 | 224 | | (i.sib.scale << 6)); |
12705 | 2.09k | } |
12706 | | |
12707 | 2.92k | if (i.disp_operands) |
12708 | 2.09k | output_disp (insn_start_frag, insn_start_off); |
12709 | | |
12710 | 2.92k | if (i.imm_operands) |
12711 | 1.88k | output_imm (insn_start_frag, insn_start_off); |
12712 | | |
12713 | | /* |
12714 | | * frag_now_fix () returning plain abs_section_offset when we're in the |
12715 | | * absolute section, and abs_section_offset not getting updated as data |
12716 | | * gets added to the frag breaks the logic below. |
12717 | | */ |
12718 | 2.92k | if (now_seg != absolute_section) |
12719 | 1.05k | { |
12720 | 1.05k | j = encoding_length (insn_start_frag, insn_start_off, frag_more (0)); |
12721 | 1.05k | if (j > 15) |
12722 | 0 | { |
12723 | 0 | if (dot_insn ()) |
12724 | 0 | as_warn (_("instruction length of %u bytes exceeds the limit of 15"), |
12725 | 0 | j); |
12726 | 0 | else |
12727 | 0 | as_bad (_("instruction length of %u bytes exceeds the limit of 15"), |
12728 | 0 | j); |
12729 | 0 | } |
12730 | 1.05k | else if (fragP) |
12731 | 0 | { |
12732 | | /* NB: Don't add prefix with GOTPC relocation since |
12733 | | output_disp() above depends on the fixed encoding |
12734 | | length. Can't add prefix with TLS relocation since |
12735 | | it breaks TLS linker optimization. */ |
12736 | 0 | unsigned int max = i.has_gotpc_tls_reloc ? 0 : 15 - j; |
12737 | | /* Prefix count on the current instruction. */ |
12738 | 0 | unsigned int count = i.vex.length; |
12739 | 0 | unsigned int k; |
12740 | 0 | for (k = 0; k < ARRAY_SIZE (i.prefix); k++) |
12741 | | /* REX byte is encoded in VEX/EVEX prefix. */ |
12742 | 0 | if (i.prefix[k] && (k != REX_PREFIX || !i.vex.length)) |
12743 | 0 | count++; |
12744 | | |
12745 | | /* Count prefixes for extended opcode maps. */ |
12746 | 0 | if (!i.vex.length) |
12747 | 0 | switch (i.tm.opcode_space) |
12748 | 0 | { |
12749 | 0 | case SPACE_BASE: |
12750 | 0 | break; |
12751 | 0 | case SPACE_0F: |
12752 | 0 | count++; |
12753 | 0 | break; |
12754 | 0 | case SPACE_0F38: |
12755 | 0 | case SPACE_0F3A: |
12756 | 0 | count += 2; |
12757 | 0 | break; |
12758 | 0 | default: |
12759 | 0 | abort (); |
12760 | 0 | } |
12761 | | |
12762 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) |
12763 | 0 | == BRANCH_PREFIX) |
12764 | 0 | { |
12765 | | /* Set the maximum prefix size in BRANCH_PREFIX |
12766 | | frag. */ |
12767 | 0 | if (fragP->tc_frag_data.max_bytes > max) |
12768 | 0 | fragP->tc_frag_data.max_bytes = max; |
12769 | 0 | if (fragP->tc_frag_data.max_bytes > count) |
12770 | 0 | fragP->tc_frag_data.max_bytes -= count; |
12771 | 0 | else |
12772 | 0 | fragP->tc_frag_data.max_bytes = 0; |
12773 | 0 | } |
12774 | 0 | else |
12775 | 0 | { |
12776 | | /* Remember the maximum prefix size in FUSED_JCC_PADDING |
12777 | | frag. */ |
12778 | 0 | unsigned int max_prefix_size; |
12779 | 0 | if (align_branch_prefix_size > max) |
12780 | 0 | max_prefix_size = max; |
12781 | 0 | else |
12782 | 0 | max_prefix_size = align_branch_prefix_size; |
12783 | 0 | if (max_prefix_size > count) |
12784 | 0 | fragP->tc_frag_data.max_prefix_length |
12785 | 0 | = max_prefix_size - count; |
12786 | 0 | } |
12787 | | |
12788 | | /* Use existing segment prefix if possible. Use CS |
12789 | | segment prefix in 64-bit mode. In 32-bit mode, use SS |
12790 | | segment prefix with ESP/EBP base register and use DS |
12791 | | segment prefix without ESP/EBP base register. */ |
12792 | 0 | if (i.prefix[SEG_PREFIX]) |
12793 | 0 | fragP->tc_frag_data.default_prefix = i.prefix[SEG_PREFIX]; |
12794 | 0 | else if (flag_code == CODE_64BIT) |
12795 | 0 | fragP->tc_frag_data.default_prefix = CS_PREFIX_OPCODE; |
12796 | 0 | else if (i.base_reg |
12797 | 0 | && (i.base_reg->reg_num == 4 |
12798 | 0 | || i.base_reg->reg_num == 5)) |
12799 | 0 | fragP->tc_frag_data.default_prefix = SS_PREFIX_OPCODE; |
12800 | 0 | else |
12801 | 0 | fragP->tc_frag_data.default_prefix = DS_PREFIX_OPCODE; |
12802 | 0 | } |
12803 | 1.05k | } |
12804 | 2.92k | } |
12805 | | |
12806 | | /* NB: Don't work with COND_JUMP86 without i386. */ |
12807 | 3.41k | if (align_branch_power |
12808 | 3.41k | && now_seg != absolute_section |
12809 | 3.41k | && cpu_arch_flags.bitfield.cpui386) |
12810 | 0 | { |
12811 | | /* Terminate each frag so that we can add prefix and check for |
12812 | | fused jcc. */ |
12813 | 0 | frag_wane (frag_now); |
12814 | 0 | frag_new (0); |
12815 | 0 | } |
12816 | | |
12817 | | #ifdef DEBUG386 |
12818 | | if (flag_debug) |
12819 | | { |
12820 | | pi ("" /*line*/, &i); |
12821 | | } |
12822 | | #endif /* DEBUG386 */ |
12823 | 3.41k | } |
12824 | | |
12825 | | /* Return the size of the displacement operand N. */ |
12826 | | |
12827 | | static int |
12828 | | disp_size (unsigned int n) |
12829 | 2.09k | { |
12830 | 2.09k | int size = 4; |
12831 | | |
12832 | 2.09k | if (i.types[n].bitfield.disp64) |
12833 | 0 | size = 8; |
12834 | 2.09k | else if (i.types[n].bitfield.disp8) |
12835 | 0 | size = 1; |
12836 | 2.09k | else if (i.types[n].bitfield.disp16) |
12837 | 264 | size = 2; |
12838 | 2.09k | return size; |
12839 | 2.09k | } |
12840 | | |
12841 | | /* Return the size of the immediate operand N. */ |
12842 | | |
12843 | | static int |
12844 | | imm_size (unsigned int n) |
12845 | 1.88k | { |
12846 | 1.88k | int size = 4; |
12847 | 1.88k | if (i.types[n].bitfield.imm64) |
12848 | 0 | size = 8; |
12849 | 1.88k | else if (i.types[n].bitfield.imm8 || i.types[n].bitfield.imm8s) |
12850 | 497 | size = 1; |
12851 | 1.38k | else if (i.types[n].bitfield.imm16) |
12852 | 57 | size = 2; |
12853 | 1.88k | return size; |
12854 | 1.88k | } |
12855 | | |
12856 | | static void |
12857 | | output_disp (fragS *insn_start_frag, offsetT insn_start_off) |
12858 | 2.09k | { |
12859 | 2.09k | char *p; |
12860 | 2.09k | unsigned int n; |
12861 | | |
12862 | 6.03k | for (n = 0; n < i.operands; n++) |
12863 | 3.93k | { |
12864 | 3.93k | if (operand_type_check (i.types[n], disp)) |
12865 | 2.09k | { |
12866 | 2.09k | int size = disp_size (n); |
12867 | | |
12868 | 2.09k | if (now_seg == absolute_section) |
12869 | 1.22k | abs_section_offset += size; |
12870 | 873 | else if (i.op[n].disps->X_op == O_constant) |
12871 | 591 | { |
12872 | 591 | offsetT val = i.op[n].disps->X_add_number; |
12873 | | |
12874 | 591 | val = offset_in_range (val >> (size == 1 ? i.memshift : 0), |
12875 | 591 | size); |
12876 | 591 | p = frag_more (size); |
12877 | 591 | md_number_to_chars (p, val, size); |
12878 | 591 | } |
12879 | 282 | else |
12880 | 282 | { |
12881 | 282 | enum bfd_reloc_code_real reloc_type; |
12882 | 282 | bool pcrel = (i.flags[n] & Operand_PCrel) != 0; |
12883 | 282 | bool sign = (flag_code == CODE_64BIT && size == 4 |
12884 | 282 | && (!want_disp32 (&i.tm) |
12885 | 169 | || (i.tm.opcode_modifier.jump && !i.jumpabsolute |
12886 | 0 | && !i.types[n].bitfield.baseindex))) |
12887 | 282 | || pcrel; |
12888 | 282 | fixS *fixP; |
12889 | | |
12890 | | /* We can't have 8 bit displacement here. */ |
12891 | 282 | gas_assert (!i.types[n].bitfield.disp8); |
12892 | | |
12893 | | /* The PC relative address is computed relative |
12894 | | to the instruction boundary, so in case immediate |
12895 | | fields follows, we need to adjust the value. */ |
12896 | 282 | if (pcrel && i.imm_operands) |
12897 | 0 | { |
12898 | 0 | unsigned int n1; |
12899 | 0 | int sz = 0; |
12900 | |
|
12901 | 0 | for (n1 = 0; n1 < i.operands; n1++) |
12902 | 0 | if (operand_type_check (i.types[n1], imm)) |
12903 | 0 | { |
12904 | | /* Only one immediate is allowed for PC |
12905 | | relative address, except with .insn. */ |
12906 | 0 | gas_assert (sz == 0 || dot_insn ()); |
12907 | 0 | sz += imm_size (n1); |
12908 | 0 | } |
12909 | | /* We should find at least one immediate. */ |
12910 | 0 | gas_assert (sz != 0); |
12911 | 0 | i.op[n].disps->X_add_number -= sz; |
12912 | 0 | } |
12913 | | |
12914 | 282 | p = frag_more (size); |
12915 | 282 | reloc_type = reloc (size, pcrel, sign, i.reloc[n]); |
12916 | 282 | if (GOT_symbol |
12917 | 282 | && GOT_symbol == i.op[n].disps->X_add_symbol |
12918 | 282 | && (((reloc_type == BFD_RELOC_32 |
12919 | 0 | || reloc_type == BFD_RELOC_X86_64_32S |
12920 | 0 | || (reloc_type == BFD_RELOC_64 |
12921 | 0 | && object_64bit)) |
12922 | 0 | && (i.op[n].disps->X_op == O_symbol |
12923 | 0 | || (i.op[n].disps->X_op == O_add |
12924 | 0 | && ((symbol_get_value_expression |
12925 | 0 | (i.op[n].disps->X_op_symbol)->X_op) |
12926 | 0 | == O_subtract)))) |
12927 | 0 | || reloc_type == BFD_RELOC_32_PCREL)) |
12928 | 0 | { |
12929 | 0 | if (!object_64bit) |
12930 | 0 | { |
12931 | 0 | reloc_type = BFD_RELOC_386_GOTPC; |
12932 | 0 | i.has_gotpc_tls_reloc = true; |
12933 | 0 | i.op[n].disps->X_add_number += |
12934 | 0 | encoding_length (insn_start_frag, insn_start_off, p); |
12935 | 0 | } |
12936 | 0 | else if (reloc_type == BFD_RELOC_64) |
12937 | 0 | reloc_type = BFD_RELOC_X86_64_GOTPC64; |
12938 | 0 | else |
12939 | | /* Don't do the adjustment for x86-64, as there |
12940 | | the pcrel addressing is relative to the _next_ |
12941 | | insn, and that is taken care of in other code. */ |
12942 | 0 | reloc_type = BFD_RELOC_X86_64_GOTPC32; |
12943 | 0 | } |
12944 | 282 | else if (align_branch_power) |
12945 | 0 | { |
12946 | 0 | switch (reloc_type) |
12947 | 0 | { |
12948 | 0 | case BFD_RELOC_386_TLS_GD: |
12949 | 0 | case BFD_RELOC_386_TLS_LDM: |
12950 | 0 | case BFD_RELOC_386_TLS_IE: |
12951 | 0 | case BFD_RELOC_386_TLS_IE_32: |
12952 | 0 | case BFD_RELOC_386_TLS_GOTIE: |
12953 | 0 | case BFD_RELOC_386_TLS_GOTDESC: |
12954 | 0 | case BFD_RELOC_386_TLS_DESC_CALL: |
12955 | 0 | case BFD_RELOC_X86_64_TLSGD: |
12956 | 0 | case BFD_RELOC_X86_64_TLSLD: |
12957 | 0 | case BFD_RELOC_X86_64_GOTTPOFF: |
12958 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTTPOFF: |
12959 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTTPOFF: |
12960 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTTPOFF: |
12961 | 0 | case BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
12962 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC: |
12963 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPC32_TLSDESC: |
12964 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPC32_TLSDESC: |
12965 | 0 | case BFD_RELOC_X86_64_TLSDESC_CALL: |
12966 | 0 | i.has_gotpc_tls_reloc = true; |
12967 | 0 | default: |
12968 | 0 | break; |
12969 | 0 | } |
12970 | 0 | } |
12971 | 282 | fixP = fix_new_exp (frag_now, p - frag_now->fr_literal, |
12972 | 282 | size, i.op[n].disps, pcrel, |
12973 | 282 | reloc_type); |
12974 | | |
12975 | 282 | if (flag_code == CODE_64BIT && size == 4 && pcrel |
12976 | 282 | && !i.prefix[ADDR_PREFIX]) |
12977 | 0 | fixP->fx_signed = 1; |
12978 | | |
12979 | 282 | if (i.base_reg && i.base_reg->reg_num == RegIP) |
12980 | 0 | { |
12981 | 0 | if (reloc_type == BFD_RELOC_X86_64_GOTPC32_TLSDESC) |
12982 | 0 | { |
12983 | | /* Set fx_tcbit for REX2 prefix. */ |
12984 | 0 | if (is_apx_rex2_encoding ()) |
12985 | 0 | fixP->fx_tcbit = 1; |
12986 | 0 | continue; |
12987 | 0 | } |
12988 | 0 | } |
12989 | | /* In 64-bit, i386_validate_fix updates only (%rip) |
12990 | | relocations. */ |
12991 | 282 | else if (object_64bit) |
12992 | 282 | continue; |
12993 | | |
12994 | 0 | #ifdef OBJ_ELF |
12995 | | /* Check for "call/jmp *mem", "push mem", "mov mem, %reg", |
12996 | | "movrs mem, %reg", "test %reg, mem" and "binop mem, %reg" where |
12997 | | binop is one of adc, add, and, cmp, or, sbb, sub, xor, or imul |
12998 | | instructions without data prefix. Always generate |
12999 | | R_386_GOT32X for "sym*GOT" operand in 32-bit mode. */ |
13000 | 0 | unsigned int space = dot_insn () ? i.insn_opcode_space |
13001 | 0 | : i.tm.opcode_space; |
13002 | 0 | if (i.prefix[DATA_PREFIX] == 0 |
13003 | 0 | && (i.rm.mode == 2 |
13004 | 0 | || (i.rm.mode == 0 && i.rm.regmem == 5)) |
13005 | 0 | && ((space == SPACE_BASE |
13006 | 0 | && i.tm.base_opcode == 0xff |
13007 | 0 | && (i.rm.reg == 2 || i.rm.reg == 4 || i.rm.reg == 6)) |
13008 | 0 | || ((space == SPACE_BASE |
13009 | 0 | || space == SPACE_0F38 |
13010 | 0 | || space == SPACE_MAP4) |
13011 | 0 | && i.tm.base_opcode == 0x8b) |
13012 | 0 | || ((space == SPACE_BASE |
13013 | 0 | || space == SPACE_MAP4) |
13014 | 0 | && (i.tm.base_opcode == 0x85 |
13015 | 0 | || (i.tm.base_opcode |
13016 | 0 | | (i.operands > 2 ? 0x3a : 0x38)) == 0x3b)) |
13017 | 0 | || (((space == SPACE_0F |
13018 | | /* Because of the 0F prefix, no suitable relocation |
13019 | | exists for this unless it's REX2-encoded. */ |
13020 | 0 | && is_apx_rex2_encoding ()) |
13021 | 0 | || space == SPACE_MAP4) |
13022 | 0 | && i.tm.base_opcode == 0xaf))) |
13023 | 0 | { |
13024 | 0 | if (object_64bit) |
13025 | 0 | { |
13026 | 0 | if (reloc_type == BFD_RELOC_X86_64_GOTTPOFF) |
13027 | 0 | { |
13028 | 0 | if (space == SPACE_MAP4) |
13029 | 0 | fixP->fx_tcbit3 = 1; |
13030 | 0 | else if (space == SPACE_0F38 && i.rex) |
13031 | 0 | fixP->fx_tcbit2 = 1; |
13032 | 0 | else if (space == SPACE_0F38 || is_apx_rex2_encoding ()) |
13033 | 0 | fixP->fx_tcbit = 1; |
13034 | 0 | } |
13035 | 0 | else if (generate_relax_relocations) |
13036 | 0 | { |
13037 | 0 | if (space == SPACE_MAP4) |
13038 | 0 | { |
13039 | 0 | fixP->fx_tcbit3 = 1; |
13040 | 0 | fixP->fx_tcbit2 = 1; |
13041 | 0 | } |
13042 | 0 | else if (space == SPACE_0F38) |
13043 | 0 | { |
13044 | 0 | fixP->fx_tcbit3 = 1; |
13045 | 0 | if (i.rex) |
13046 | 0 | fixP->fx_tcbit = 1; |
13047 | 0 | } |
13048 | 0 | else if (is_apx_rex2_encoding ()) |
13049 | 0 | fixP->fx_tcbit3 = 1; |
13050 | 0 | else if (i.rex) |
13051 | 0 | fixP->fx_tcbit2 = 1; |
13052 | 0 | else |
13053 | 0 | fixP->fx_tcbit = 1; |
13054 | 0 | } |
13055 | 0 | } |
13056 | 0 | else if (generate_relax_relocations |
13057 | 0 | ? (!shared || i.rm.mode != 0 || i.rm.regmem != 5) |
13058 | 0 | : (!shared && i.rm.mode == 0 && i.rm.regmem == 5)) |
13059 | 0 | fixP->fx_tcbit2 = 1; |
13060 | 0 | } |
13061 | 0 | #endif |
13062 | 0 | } |
13063 | 2.09k | } |
13064 | 3.93k | } |
13065 | 2.09k | } |
13066 | | |
13067 | | static void |
13068 | | output_imm (fragS *insn_start_frag, offsetT insn_start_off) |
13069 | 1.88k | { |
13070 | 1.88k | char *p; |
13071 | 1.88k | unsigned int n; |
13072 | | |
13073 | 5.60k | for (n = 0; n < i.operands; n++) |
13074 | 3.72k | { |
13075 | 3.72k | if (operand_type_check (i.types[n], imm)) |
13076 | 1.88k | { |
13077 | 1.88k | int size = imm_size (n); |
13078 | | |
13079 | 1.88k | if (now_seg == absolute_section) |
13080 | 1.21k | abs_section_offset += size; |
13081 | 669 | else if (i.op[n].imms->X_op == O_constant) |
13082 | 260 | { |
13083 | 260 | offsetT val; |
13084 | | |
13085 | 260 | val = offset_in_range (i.op[n].imms->X_add_number, |
13086 | 260 | size); |
13087 | 260 | p = frag_more (size); |
13088 | 260 | md_number_to_chars (p, val, size); |
13089 | 260 | } |
13090 | 409 | else |
13091 | 409 | { |
13092 | | /* Not absolute_section. |
13093 | | Need a 32-bit fixup (don't support 8bit |
13094 | | non-absolute imms). Try to support other |
13095 | | sizes ... */ |
13096 | 409 | enum bfd_reloc_code_real reloc_type; |
13097 | 409 | int sign; |
13098 | | |
13099 | 409 | if (i.types[n].bitfield.imm32s |
13100 | 409 | && (i.suffix == QWORD_MNEM_SUFFIX |
13101 | 1 | || (!i.suffix && i.tm.opcode_modifier.no_lsuf) |
13102 | 1 | || (i.prefix[REX_PREFIX] & REX_W) |
13103 | 1 | || dot_insn ())) |
13104 | 1 | sign = 1; |
13105 | 408 | else |
13106 | 408 | sign = 0; |
13107 | | |
13108 | 409 | p = frag_more (size); |
13109 | 409 | reloc_type = reloc (size, 0, sign, i.reloc[n]); |
13110 | | |
13111 | | /* This is tough to explain. We end up with this one if we |
13112 | | * have operands that look like |
13113 | | * "_GLOBAL_OFFSET_TABLE_+[.-.L284]". The goal here is to |
13114 | | * obtain the absolute address of the GOT, and it is strongly |
13115 | | * preferable from a performance point of view to avoid using |
13116 | | * a runtime relocation for this. The actual sequence of |
13117 | | * instructions often look something like: |
13118 | | * |
13119 | | * call .L66 |
13120 | | * .L66: |
13121 | | * popl %ebx |
13122 | | * addl $_GLOBAL_OFFSET_TABLE_+[.-.L66],%ebx |
13123 | | * |
13124 | | * The call and pop essentially return the absolute address |
13125 | | * of the label .L66 and store it in %ebx. The linker itself |
13126 | | * will ultimately change the first operand of the addl so |
13127 | | * that %ebx points to the GOT, but to keep things simple, the |
13128 | | * .o file must have this operand set so that it generates not |
13129 | | * the absolute address of .L66, but the absolute address of |
13130 | | * itself. This allows the linker itself simply treat a GOTPC |
13131 | | * relocation as asking for a pcrel offset to the GOT to be |
13132 | | * added in, and the addend of the relocation is stored in the |
13133 | | * operand field for the instruction itself. |
13134 | | * |
13135 | | * Our job here is to fix the operand so that it would add |
13136 | | * the correct offset so that %ebx would point to itself. The |
13137 | | * thing that is tricky is that .-.L66 will point to the |
13138 | | * beginning of the instruction, so we need to further modify |
13139 | | * the operand so that it will point to itself. There are |
13140 | | * other cases where you have something like: |
13141 | | * |
13142 | | * .long $_GLOBAL_OFFSET_TABLE_+[.-.L66] |
13143 | | * |
13144 | | * and here no correction would be required. Internally in |
13145 | | * the assembler we treat operands of this form as not being |
13146 | | * pcrel since the '.' is explicitly mentioned, and I wonder |
13147 | | * whether it would simplify matters to do it this way. Who |
13148 | | * knows. In earlier versions of the PIC patches, the |
13149 | | * pcrel_adjust field was used to store the correction, but |
13150 | | * since the expression is not pcrel, I felt it would be |
13151 | | * confusing to do it this way. */ |
13152 | | |
13153 | 409 | if ((reloc_type == BFD_RELOC_32 |
13154 | 409 | || reloc_type == BFD_RELOC_X86_64_32S |
13155 | 409 | || reloc_type == BFD_RELOC_64) |
13156 | 409 | && GOT_symbol |
13157 | 409 | && GOT_symbol == i.op[n].imms->X_add_symbol |
13158 | 409 | && (i.op[n].imms->X_op == O_symbol |
13159 | 0 | || (i.op[n].imms->X_op == O_add |
13160 | 0 | && ((symbol_get_value_expression |
13161 | 0 | (i.op[n].imms->X_op_symbol)->X_op) |
13162 | 0 | == O_subtract)))) |
13163 | 0 | { |
13164 | 0 | if (!object_64bit) |
13165 | 0 | reloc_type = BFD_RELOC_386_GOTPC; |
13166 | 0 | else if (size == 4) |
13167 | 0 | reloc_type = BFD_RELOC_X86_64_GOTPC32; |
13168 | 0 | else if (size == 8) |
13169 | 0 | reloc_type = BFD_RELOC_X86_64_GOTPC64; |
13170 | 0 | i.has_gotpc_tls_reloc = true; |
13171 | 0 | i.op[n].imms->X_add_number += |
13172 | 0 | encoding_length (insn_start_frag, insn_start_off, p); |
13173 | 0 | } |
13174 | 409 | fix_new_exp (frag_now, p - frag_now->fr_literal, size, |
13175 | 409 | i.op[n].imms, 0, reloc_type); |
13176 | 409 | } |
13177 | 1.88k | } |
13178 | 3.72k | } |
13179 | 1.88k | } |
13180 | | |
13181 | | /* x86_cons_fix_new is called via the expression parsing code when a |
13182 | | reloc is needed. We use this hook to get the correct .got reloc. */ |
13183 | | static int cons_sign = -1; |
13184 | | |
13185 | | void |
13186 | | x86_cons_fix_new (fragS *frag, unsigned int off, unsigned int len, |
13187 | | expressionS *exp, bfd_reloc_code_real_type r) |
13188 | 1.66k | { |
13189 | 1.66k | r = reloc (len, 0, cons_sign, r); |
13190 | | |
13191 | | #ifdef TE_PE |
13192 | | if (exp->X_op == O_secrel) |
13193 | | { |
13194 | | exp->X_op = O_symbol; |
13195 | | r = BFD_RELOC_32_SECREL; |
13196 | | } |
13197 | | else if (exp->X_op == O_secidx) |
13198 | | r = BFD_RELOC_16_SECIDX; |
13199 | | #endif |
13200 | | |
13201 | 1.66k | fix_new_exp (frag, off, len, exp, 0, r); |
13202 | 1.66k | } |
13203 | | |
13204 | | /* Export the ABI address size for use by TC_ADDRESS_BYTES for the |
13205 | | purpose of the `.dc.a' internal pseudo-op. */ |
13206 | | |
13207 | | int |
13208 | | x86_address_bytes (void) |
13209 | 0 | { |
13210 | 0 | if ((stdoutput->arch_info->mach & bfd_mach_x64_32)) |
13211 | 0 | return 4; |
13212 | 0 | return stdoutput->arch_info->bits_per_address / 8; |
13213 | 0 | } |
13214 | | |
13215 | | #if (defined (OBJ_ELF) || defined (OBJ_MACH_O) || defined (TE_PE)) |
13216 | | /* Parse operands of the form |
13217 | | <symbol>@GOTOFF+<nnn> |
13218 | | and similar .plt or .got references. |
13219 | | |
13220 | | If we find one, set up the correct relocation in RELOC and copy the |
13221 | | input string, minus the `@GOTOFF' into a malloc'd buffer for |
13222 | | parsing by the calling routine. Return this buffer, and if ADJUST |
13223 | | is non-null set it to the length of the string we removed from the |
13224 | | input line. Otherwise return NULL. */ |
13225 | | static char * |
13226 | | lex_got (enum bfd_reloc_code_real *rel, |
13227 | | int *adjust, |
13228 | | i386_operand_type *types) |
13229 | 46.5k | { |
13230 | | /* Some of the relocations depend on the size of what field is to |
13231 | | be relocated. But in our callers i386_immediate and i386_displacement |
13232 | | we don't yet know the operand size (this will be set by insn |
13233 | | matching). Hence we record the word32 relocation here, |
13234 | | and adjust the reloc according to the real size in reloc(). */ |
13235 | 46.5k | char *cp; |
13236 | 46.5k | unsigned int j; |
13237 | | |
13238 | 1.12M | for (cp = input_line_pointer; *cp != '@'; cp++) |
13239 | 1.12M | if (is_end_of_stmt (*cp) || *cp == ',') |
13240 | 44.0k | return NULL; |
13241 | | |
13242 | 29.6k | for (j = 0; j < ARRAY_SIZE (gotrel); j++) |
13243 | 29.1k | { |
13244 | 29.1k | int len = gotrel[j].len; |
13245 | 29.1k | if (strncasecmp (cp + 1, gotrel[j].str, len) == 0) |
13246 | 1.96k | { |
13247 | 1.96k | if (gotrel[j].rel[object_64bit] != 0) |
13248 | 1.96k | { |
13249 | 1.96k | int first, second; |
13250 | 1.96k | char *tmpbuf, *past_reloc; |
13251 | | |
13252 | 1.96k | i.has_gotrel = true; |
13253 | 1.96k | *rel = gotrel[j].rel[object_64bit]; |
13254 | | |
13255 | 1.96k | if (types) |
13256 | 1.82k | { |
13257 | 1.82k | if (flag_code != CODE_64BIT) |
13258 | 1.66k | { |
13259 | 1.66k | types->bitfield.imm32 = 1; |
13260 | 1.66k | types->bitfield.disp32 = 1; |
13261 | 1.66k | } |
13262 | 163 | else |
13263 | 163 | *types = gotrel[j].types64; |
13264 | 1.82k | } |
13265 | | |
13266 | 1.96k | if (gotrel[j].need_GOT_symbol && GOT_symbol == NULL) |
13267 | 12 | GOT_symbol = symbol_find_or_make (GLOBAL_OFFSET_TABLE_NAME); |
13268 | | |
13269 | | /* The length of the first part of our input line. */ |
13270 | 1.96k | first = cp - input_line_pointer; |
13271 | | |
13272 | | /* The second part goes from after the reloc token until |
13273 | | (and including) an end_of_line char or comma. */ |
13274 | 1.96k | past_reloc = cp + 1 + len; |
13275 | 1.96k | cp = past_reloc; |
13276 | 24.2k | while (!is_end_of_stmt (*cp) && *cp != ',') |
13277 | 22.2k | ++cp; |
13278 | 1.96k | second = cp + 1 - past_reloc; |
13279 | | |
13280 | | /* Allocate and copy string. The trailing NUL shouldn't |
13281 | | be necessary, but be safe. */ |
13282 | 1.96k | tmpbuf = XNEWVEC (char, first + second + 2); |
13283 | 1.96k | memcpy (tmpbuf, input_line_pointer, first); |
13284 | 1.96k | if (second != 0 && !is_whitespace (*past_reloc)) |
13285 | | /* Replace the relocation token with ' ', so that |
13286 | | errors like foo@GOTOFF1 will be detected. */ |
13287 | 1.95k | tmpbuf[first++] = ' '; |
13288 | 7 | else |
13289 | | /* Increment length by 1 if the relocation token is |
13290 | | removed. */ |
13291 | 7 | len++; |
13292 | 1.96k | if (adjust) |
13293 | 136 | *adjust = len; |
13294 | 1.96k | memcpy (tmpbuf + first, past_reloc, second); |
13295 | 1.96k | tmpbuf[first + second] = '\0'; |
13296 | 1.96k | return tmpbuf; |
13297 | 1.96k | } |
13298 | | |
13299 | 0 | as_bad (_("@%s reloc is not supported with %d-bit output format"), |
13300 | 0 | gotrel[j].str, 1 << (5 + object_64bit)); |
13301 | 0 | return NULL; |
13302 | 1.96k | } |
13303 | 29.1k | } |
13304 | | |
13305 | | /* Might be a symbol version string. Don't as_bad here. */ |
13306 | 528 | return NULL; |
13307 | 2.49k | } |
13308 | | #else |
13309 | | # define lex_got(reloc, adjust, types) NULL |
13310 | | #endif |
13311 | | |
13312 | | bfd_reloc_code_real_type |
13313 | | x86_cons (expressionS *exp, int size) |
13314 | 2.31k | { |
13315 | 2.31k | bfd_reloc_code_real_type got_reloc = NO_RELOC; |
13316 | | |
13317 | 2.31k | intel_syntax = -intel_syntax; |
13318 | 2.31k | exp->X_md = 0; |
13319 | 2.31k | expr_mode = expr_operator_none; |
13320 | | |
13321 | 2.31k | #if defined (OBJ_ELF) || defined (TE_PE) |
13322 | 2.31k | if (size == 4 |
13323 | | # ifdef TE_PE |
13324 | | || (size == 2) |
13325 | | # endif |
13326 | 2.31k | || (object_64bit && size == 8)) |
13327 | 2.27k | { |
13328 | | /* Handle @GOTOFF and the like in an expression. */ |
13329 | 2.27k | char *save; |
13330 | 2.27k | char *gotfree_input_line; |
13331 | 2.27k | int adjust = 0; |
13332 | | |
13333 | 2.27k | save = input_line_pointer; |
13334 | 2.27k | gotfree_input_line = lex_got (&got_reloc, &adjust, NULL); |
13335 | 2.27k | if (gotfree_input_line) |
13336 | 136 | input_line_pointer = gotfree_input_line; |
13337 | | |
13338 | 2.27k | expression (exp); |
13339 | | |
13340 | 2.27k | if (gotfree_input_line) |
13341 | 136 | { |
13342 | | /* expression () has merrily parsed up to the end of line, |
13343 | | or a comma - in the wrong buffer. Transfer how far |
13344 | | input_line_pointer has moved to the right buffer. */ |
13345 | 136 | input_line_pointer = (save |
13346 | 136 | + (input_line_pointer - gotfree_input_line) |
13347 | 136 | + adjust); |
13348 | 136 | free (gotfree_input_line); |
13349 | 136 | if (exp->X_op == O_constant |
13350 | 136 | || exp->X_op == O_absent |
13351 | 136 | || exp->X_op == O_illegal |
13352 | 136 | || exp->X_op == O_register |
13353 | 136 | || exp->X_op == O_big) |
13354 | 13 | { |
13355 | 13 | char c = *input_line_pointer; |
13356 | 13 | *input_line_pointer = 0; |
13357 | 13 | as_bad (_("missing or invalid expression `%s'"), save); |
13358 | 13 | *input_line_pointer = c; |
13359 | 13 | } |
13360 | 123 | else if ((got_reloc == BFD_RELOC_386_PLT32 |
13361 | 123 | || got_reloc == BFD_RELOC_X86_64_PLT32) |
13362 | 123 | && exp->X_op != O_symbol) |
13363 | 0 | { |
13364 | 0 | char c = *input_line_pointer; |
13365 | 0 | *input_line_pointer = 0; |
13366 | 0 | as_bad (_("invalid PLT expression `%s'"), save); |
13367 | 0 | *input_line_pointer = c; |
13368 | 0 | } |
13369 | 136 | } |
13370 | 2.27k | } |
13371 | 37 | else |
13372 | 37 | #endif |
13373 | 37 | expression (exp); |
13374 | | |
13375 | 2.31k | intel_syntax = -intel_syntax; |
13376 | | |
13377 | 2.31k | if (intel_syntax) |
13378 | 0 | i386_intel_simplify (exp); |
13379 | | |
13380 | | /* If not 64bit, massage value, to account for wraparound when !BFD64. */ |
13381 | 2.31k | if (size <= 4 && expr_mode == expr_operator_present |
13382 | 2.31k | && exp->X_op == O_constant && !object_64bit) |
13383 | 0 | exp->X_add_number = extend_to_32bit_address (exp->X_add_number); |
13384 | | |
13385 | 2.31k | return got_reloc; |
13386 | 2.31k | } |
13387 | | |
13388 | | static void |
13389 | | signed_cons (int size) |
13390 | 0 | { |
13391 | 0 | if (object_64bit) |
13392 | 0 | cons_sign = 1; |
13393 | 0 | cons (size); |
13394 | 0 | cons_sign = -1; |
13395 | 0 | } |
13396 | | |
13397 | | static void |
13398 | | s_insn (int dummy ATTRIBUTE_UNUSED) |
13399 | 598 | { |
13400 | 598 | char mnemonic[MAX_MNEM_SIZE], *line = input_line_pointer, *ptr; |
13401 | 598 | char *saved_ilp = find_end_of_line (line, false), saved_char; |
13402 | 598 | const char *end; |
13403 | 598 | unsigned int j; |
13404 | 598 | valueT val; |
13405 | 598 | bool vex = false, xop = false; |
13406 | 598 | enum { evex_none, evex_basic, evex_nd } evex = evex_none; |
13407 | 598 | struct last_insn *last_insn; |
13408 | | |
13409 | 598 | init_globals (); |
13410 | | |
13411 | 598 | saved_char = *saved_ilp; |
13412 | 598 | *saved_ilp = 0; |
13413 | | |
13414 | 598 | end = parse_insn (line, mnemonic, parse_prefix); |
13415 | 598 | if (end == NULL) |
13416 | 0 | { |
13417 | 0 | bad: |
13418 | 0 | *saved_ilp = saved_char; |
13419 | 0 | ignore_rest_of_line (); |
13420 | 0 | i.tm.mnem_off = 0; |
13421 | 0 | memset (&pp, 0, sizeof (pp)); |
13422 | 0 | return; |
13423 | 0 | } |
13424 | 598 | line += end - line; |
13425 | | |
13426 | 598 | current_templates.start = &i.tm; |
13427 | 598 | current_templates.end = &i.tm + 1; |
13428 | 598 | i.tm.mnem_off = MN__insn; |
13429 | 598 | i.tm.extension_opcode = None; |
13430 | | |
13431 | 598 | if (startswith (line, "VEX") |
13432 | 598 | && (line[3] == '.' || is_whitespace (line[3]))) |
13433 | 585 | { |
13434 | 585 | vex = true; |
13435 | 585 | line += 3; |
13436 | 585 | } |
13437 | 13 | else if (startswith (line, "XOP") && ISDIGIT (line[3])) |
13438 | 0 | { |
13439 | 0 | char *e; |
13440 | 0 | unsigned long n = strtoul (line + 3, &e, 16); |
13441 | |
|
13442 | 0 | if (e == line + 5 && n >= 0x08 && n <= 0x1f |
13443 | 0 | && (*e == '.' || is_whitespace (*e))) |
13444 | 0 | { |
13445 | 0 | xop = true; |
13446 | | /* Arrange for build_vex_prefix() to emit 0x8f. */ |
13447 | 0 | i.tm.opcode_space = SPACE_XOP08; |
13448 | 0 | i.insn_opcode_space = n; |
13449 | 0 | line = e; |
13450 | 0 | } |
13451 | 0 | } |
13452 | 13 | else if (startswith (line, "EVEX") |
13453 | 13 | && (line[4] == '.' || is_whitespace (line[4]))) |
13454 | 0 | { |
13455 | 0 | evex = evex_basic; |
13456 | 0 | line += 4; |
13457 | 0 | } |
13458 | | |
13459 | 598 | if (vex || xop |
13460 | 598 | ? pp.encoding == encoding_evex |
13461 | 598 | : evex |
13462 | 13 | ? pp.encoding == encoding_vex |
13463 | 0 | || pp.encoding == encoding_vex3 |
13464 | 13 | : pp.encoding != encoding_default) |
13465 | 0 | { |
13466 | 0 | as_bad (_("pseudo-prefix conflicts with encoding specifier")); |
13467 | 0 | goto bad; |
13468 | 0 | } |
13469 | | |
13470 | 598 | if (line > end && pp.encoding == encoding_default) |
13471 | 585 | pp.encoding = evex ? encoding_evex : encoding_vex; |
13472 | | |
13473 | 598 | if (pp.encoding != encoding_default) |
13474 | 585 | { |
13475 | | /* Only address size and segment override prefixes are permitted with |
13476 | | VEX/XOP/EVEX encodings. */ |
13477 | 585 | const unsigned char *p = i.prefix; |
13478 | | |
13479 | 4.68k | for (j = 0; j < ARRAY_SIZE (i.prefix); ++j, ++p) |
13480 | 4.09k | { |
13481 | 4.09k | if (!*p) |
13482 | 4.09k | continue; |
13483 | | |
13484 | 0 | switch (j) |
13485 | 0 | { |
13486 | 0 | case SEG_PREFIX: |
13487 | 0 | case ADDR_PREFIX: |
13488 | 0 | break; |
13489 | 0 | default: |
13490 | 0 | as_bad (_("illegal prefix used with VEX/XOP/EVEX")); |
13491 | 0 | goto bad; |
13492 | 0 | } |
13493 | 0 | } |
13494 | 585 | } |
13495 | | |
13496 | 598 | if (line > end && *line == '.') |
13497 | 0 | { |
13498 | | /* Length specifier (VEX.L, XOP.L, EVEX.L'L). */ |
13499 | 0 | switch (line[1]) |
13500 | 0 | { |
13501 | 0 | case 'L': |
13502 | 0 | switch (line[2]) |
13503 | 0 | { |
13504 | 0 | case '0': |
13505 | 0 | if (evex) |
13506 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
13507 | 0 | else |
13508 | 0 | i.tm.opcode_modifier.vex = VEX128; |
13509 | 0 | break; |
13510 | | |
13511 | 0 | case '1': |
13512 | 0 | if (evex) |
13513 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
13514 | 0 | else |
13515 | 0 | i.tm.opcode_modifier.vex = VEX256; |
13516 | 0 | break; |
13517 | | |
13518 | 0 | case '2': |
13519 | 0 | if (evex) |
13520 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
13521 | 0 | break; |
13522 | | |
13523 | 0 | case '3': |
13524 | 0 | if (evex) |
13525 | 0 | i.tm.opcode_modifier.evex = EVEX_L3; |
13526 | 0 | break; |
13527 | | |
13528 | 0 | case 'I': |
13529 | 0 | if (line[3] == 'G') |
13530 | 0 | { |
13531 | 0 | if (evex) |
13532 | 0 | i.tm.opcode_modifier.evex = EVEXLIG; |
13533 | 0 | else |
13534 | 0 | i.tm.opcode_modifier.vex = VEXScalar; /* LIG */ |
13535 | 0 | ++line; |
13536 | 0 | } |
13537 | 0 | break; |
13538 | 0 | } |
13539 | | |
13540 | 0 | if (i.tm.opcode_modifier.vex || i.tm.opcode_modifier.evex) |
13541 | 0 | line += 3; |
13542 | 0 | break; |
13543 | | |
13544 | 0 | case '1': |
13545 | 0 | if (line[2] == '2' && line[3] == '8') |
13546 | 0 | { |
13547 | 0 | if (evex) |
13548 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
13549 | 0 | else |
13550 | 0 | i.tm.opcode_modifier.vex = VEX128; |
13551 | 0 | line += 4; |
13552 | 0 | } |
13553 | 0 | break; |
13554 | | |
13555 | 0 | case '2': |
13556 | 0 | if (line[2] == '5' && line[3] == '6') |
13557 | 0 | { |
13558 | 0 | if (evex) |
13559 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
13560 | 0 | else |
13561 | 0 | i.tm.opcode_modifier.vex = VEX256; |
13562 | 0 | line += 4; |
13563 | 0 | } |
13564 | 0 | break; |
13565 | | |
13566 | 0 | case '5': |
13567 | 0 | if (evex && line[2] == '1' && line[3] == '2') |
13568 | 0 | { |
13569 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
13570 | 0 | line += 4; |
13571 | 0 | } |
13572 | 0 | break; |
13573 | 0 | } |
13574 | 0 | } |
13575 | | |
13576 | 598 | if (line > end && *line == '.') |
13577 | 0 | { |
13578 | | /* embedded prefix (VEX.pp, XOP.pp, EVEX.pp). */ |
13579 | 0 | switch (line[1]) |
13580 | 0 | { |
13581 | 0 | case 'N': |
13582 | 0 | if (line[2] == 'P') |
13583 | 0 | line += 3; |
13584 | 0 | break; |
13585 | | |
13586 | 0 | case '6': |
13587 | 0 | if (line[2] == '6') |
13588 | 0 | { |
13589 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0X66; |
13590 | 0 | line += 3; |
13591 | 0 | } |
13592 | 0 | break; |
13593 | | |
13594 | 0 | case 'F': case 'f': |
13595 | 0 | if (line[2] == '3') |
13596 | 0 | { |
13597 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF3; |
13598 | 0 | line += 3; |
13599 | 0 | } |
13600 | 0 | else if (line[2] == '2') |
13601 | 0 | { |
13602 | 0 | i.tm.opcode_modifier.opcodeprefix = PREFIX_0XF2; |
13603 | 0 | line += 3; |
13604 | 0 | } |
13605 | 0 | break; |
13606 | 0 | } |
13607 | 0 | } |
13608 | | |
13609 | 598 | if (line > end && !xop && *line == '.') |
13610 | 0 | { |
13611 | | /* Encoding space (VEX.mmmmm, EVEX.mmmm). */ |
13612 | 0 | switch (line[1]) |
13613 | 0 | { |
13614 | 0 | case '0': |
13615 | 0 | if (TOUPPER (line[2]) != 'F') |
13616 | 0 | break; |
13617 | 0 | if (line[3] == '.' || is_whitespace (line[3])) |
13618 | 0 | { |
13619 | 0 | i.insn_opcode_space = SPACE_0F; |
13620 | 0 | line += 3; |
13621 | 0 | } |
13622 | 0 | else if (line[3] == '3' |
13623 | 0 | && (line[4] == '8' || TOUPPER (line[4]) == 'A') |
13624 | 0 | && (line[5] == '.' || is_whitespace (line[5]))) |
13625 | 0 | { |
13626 | 0 | i.insn_opcode_space = line[4] == '8' ? SPACE_0F38 : SPACE_0F3A; |
13627 | 0 | line += 5; |
13628 | 0 | } |
13629 | 0 | break; |
13630 | | |
13631 | 0 | case 'M': |
13632 | 0 | if (ISDIGIT (line[2]) && line[2] != '0') |
13633 | 0 | { |
13634 | 0 | char *e; |
13635 | 0 | unsigned long n = strtoul (line + 2, &e, 10); |
13636 | |
|
13637 | 0 | if (n <= (evex ? 15 : 31) |
13638 | 0 | && (*e == '.' || is_whitespace (*e))) |
13639 | 0 | { |
13640 | 0 | i.insn_opcode_space = n; |
13641 | 0 | line = e; |
13642 | 0 | } |
13643 | 0 | } |
13644 | 0 | break; |
13645 | 0 | } |
13646 | 0 | } |
13647 | | |
13648 | 598 | if (line > end && *line == '.' && line[1] == 'W') |
13649 | 0 | { |
13650 | | /* VEX.W, XOP.W, EVEX.W */ |
13651 | 0 | switch (line[2]) |
13652 | 0 | { |
13653 | 0 | case '0': |
13654 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
13655 | 0 | break; |
13656 | | |
13657 | 0 | case '1': |
13658 | 0 | i.tm.opcode_modifier.vexw = VEXW1; |
13659 | 0 | break; |
13660 | | |
13661 | 0 | case 'I': |
13662 | 0 | if (line[3] == 'G') |
13663 | 0 | { |
13664 | 0 | i.tm.opcode_modifier.vexw = VEXWIG; |
13665 | 0 | ++line; |
13666 | 0 | } |
13667 | 0 | break; |
13668 | 0 | } |
13669 | | |
13670 | 0 | if (i.tm.opcode_modifier.vexw) |
13671 | 0 | line += 3; |
13672 | 0 | } |
13673 | | |
13674 | 598 | if (line > end && evex && *line == '.') |
13675 | 0 | { |
13676 | 0 | if (line[1] == 'N' && line[2] == 'D') |
13677 | 0 | { |
13678 | 0 | evex = evex_nd; |
13679 | 0 | line += 3; |
13680 | 0 | } |
13681 | 0 | else if (line[1] == 'Z' && line[2] == 'U') |
13682 | 0 | { |
13683 | 0 | i.tm.opcode_modifier.operandconstraint = ZERO_UPPER; |
13684 | 0 | line += 3; |
13685 | 0 | } |
13686 | 0 | } |
13687 | | |
13688 | 598 | if (line > end && *line && !is_whitespace (*line)) |
13689 | 0 | { |
13690 | | /* Improve diagnostic a little. */ |
13691 | 0 | if (*line == '.' && line[1] && !is_whitespace (line[1])) |
13692 | 0 | ++line; |
13693 | 0 | goto done; |
13694 | 0 | } |
13695 | | |
13696 | | /* Before processing the opcode expression, find trailing "+r" or |
13697 | | "/<digit>" specifiers. */ |
13698 | 6.37k | for (ptr = line; ; ++ptr) |
13699 | 6.97k | { |
13700 | 6.97k | unsigned long n; |
13701 | 6.97k | char *e; |
13702 | | |
13703 | 6.97k | ptr = strpbrk (ptr, "+/,"); |
13704 | 6.97k | if (ptr == NULL || *ptr == ',') |
13705 | 598 | break; |
13706 | | |
13707 | 6.37k | if (*ptr == '+' && ptr[1] == 'r' |
13708 | 6.37k | && (ptr[2] == ',' || (is_whitespace (ptr[2]) && ptr[3] == ','))) |
13709 | 0 | { |
13710 | 0 | *ptr = ' '; |
13711 | 0 | ptr[1] = ' '; |
13712 | 0 | i.short_form = true; |
13713 | 0 | break; |
13714 | 0 | } |
13715 | | |
13716 | 6.37k | if (*ptr == '/' && ISDIGIT (ptr[1]) |
13717 | 6.37k | && (n = strtoul (ptr + 1, &e, 8)) < 8 |
13718 | 6.37k | && e == ptr + 2 |
13719 | 6.37k | && (ptr[2] == ',' || (is_whitespace (ptr[2]) && ptr[3] == ','))) |
13720 | 0 | { |
13721 | 0 | *ptr = ' '; |
13722 | 0 | ptr[1] = ' '; |
13723 | 0 | i.tm.extension_opcode = n; |
13724 | 0 | i.tm.opcode_modifier.modrm = 1; |
13725 | 0 | break; |
13726 | 0 | } |
13727 | 6.37k | } |
13728 | | |
13729 | 598 | input_line_pointer = line; |
13730 | 598 | val = get_absolute_expression (); |
13731 | 598 | line = input_line_pointer; |
13732 | | |
13733 | 598 | if (i.short_form && (val & 7)) |
13734 | 0 | as_warn ("`+r' assumes low three opcode bits to be clear"); |
13735 | | |
13736 | 603 | for (j = 1; j < sizeof(val); ++j) |
13737 | 603 | if (!(val >> (j * 8))) |
13738 | 598 | break; |
13739 | | |
13740 | | /* Trim off a prefix if present. */ |
13741 | 598 | if (j > 1 && !vex && !xop && !evex) |
13742 | 1 | { |
13743 | 1 | uint8_t byte = val >> ((j - 1) * 8); |
13744 | | |
13745 | 1 | switch (byte) |
13746 | 1 | { |
13747 | 0 | case DATA_PREFIX_OPCODE: |
13748 | 0 | case REPE_PREFIX_OPCODE: |
13749 | 0 | case REPNE_PREFIX_OPCODE: |
13750 | 0 | if (!add_prefix (byte)) |
13751 | 0 | goto bad; |
13752 | 0 | val &= ((uint64_t)1 << (--j * 8)) - 1; |
13753 | 0 | break; |
13754 | 1 | } |
13755 | 1 | } |
13756 | | |
13757 | 598 | if (evex == evex_basic && *line == '{') |
13758 | 0 | { |
13759 | 0 | int length = check_Scc_OszcOperations (line); |
13760 | |
|
13761 | 0 | if (length > 0) |
13762 | 0 | { |
13763 | 0 | line += length; |
13764 | 0 | if (is_whitespace (*line)) |
13765 | 0 | ++line; |
13766 | |
|
13767 | 0 | if (i.tm.opcode_modifier.operandconstraint) |
13768 | 0 | { |
13769 | 0 | as_bad (_("SCC/OSZC specifier cannot be used here")); |
13770 | 0 | goto bad; |
13771 | 0 | } |
13772 | 0 | i.tm.opcode_modifier.operandconstraint = SCC; |
13773 | 0 | } |
13774 | 0 | } |
13775 | | |
13776 | | /* Parse operands, if any, before evaluating encoding space. */ |
13777 | 598 | if (*line == ',') |
13778 | 108 | { |
13779 | 108 | i.memshift = -1; |
13780 | | |
13781 | 108 | ptr = parse_operands (line + 1, &i386_mnemonics[MN__insn]); |
13782 | 108 | this_operand = -1; |
13783 | 108 | if (!ptr) |
13784 | 0 | goto bad; |
13785 | 108 | line = ptr; |
13786 | | |
13787 | 108 | if (!i.operands) |
13788 | 0 | { |
13789 | 0 | as_bad (_("expecting operand after ','; got nothing")); |
13790 | 0 | goto done; |
13791 | 0 | } |
13792 | | |
13793 | 108 | if (i.mem_operands > 1) |
13794 | 0 | { |
13795 | 0 | as_bad (_("too many memory references for `%s'"), |
13796 | 0 | &i386_mnemonics[MN__insn]); |
13797 | 0 | goto done; |
13798 | 0 | } |
13799 | | |
13800 | | /* No need to distinguish encoding_evex and encoding_evex512. */ |
13801 | 108 | if (pp.encoding == encoding_evex512) |
13802 | 0 | pp.encoding = encoding_evex; |
13803 | 108 | } |
13804 | | |
13805 | | /* Trim off encoding space. */ |
13806 | 598 | if (j > 1 && !i.insn_opcode_space && (val >> ((j - 1) * 8)) == 0x0f) |
13807 | 0 | { |
13808 | 0 | uint8_t byte = val >> ((--j - 1) * 8); |
13809 | |
|
13810 | 0 | i.insn_opcode_space = SPACE_0F; |
13811 | 0 | switch (byte & -(j > 1 && !pp.rex2_encoding |
13812 | 0 | && (pp.encoding != encoding_egpr || evex))) |
13813 | 0 | { |
13814 | 0 | case 0x38: |
13815 | 0 | i.insn_opcode_space = SPACE_0F38; |
13816 | 0 | --j; |
13817 | 0 | break; |
13818 | 0 | case 0x3a: |
13819 | 0 | i.insn_opcode_space = SPACE_0F3A; |
13820 | 0 | --j; |
13821 | 0 | break; |
13822 | 0 | } |
13823 | 0 | i.tm.opcode_space = i.insn_opcode_space; |
13824 | 0 | val &= ((uint64_t)1 << (j * 8)) - 1; |
13825 | 0 | } |
13826 | 598 | if (!i.tm.opcode_space && (vex || evex)) |
13827 | | /* Arrange for build_vex_prefix() to properly emit 0xC4/0xC5. |
13828 | | Also avoid hitting abort() there or in build_evex_prefix(). */ |
13829 | 585 | i.tm.opcode_space = i.insn_opcode_space == SPACE_0F ? SPACE_0F |
13830 | 585 | : SPACE_0F38; |
13831 | | |
13832 | 598 | if (j > 2) |
13833 | 1 | { |
13834 | 1 | as_bad (_("opcode residual (%#"PRIx64") too wide"), (uint64_t) val); |
13835 | 1 | goto done; |
13836 | 1 | } |
13837 | 597 | i.opcode_length = j; |
13838 | | |
13839 | | /* Handle operands, if any. */ |
13840 | 597 | if (i.operands) |
13841 | 108 | { |
13842 | 108 | i386_operand_type combined; |
13843 | 108 | expressionS *disp_exp = NULL; |
13844 | 108 | bool changed; |
13845 | | |
13846 | 108 | if (pp.encoding == encoding_egpr) |
13847 | 0 | { |
13848 | 0 | if (vex || xop) |
13849 | 0 | { |
13850 | 0 | as_bad (_("eGPR use conflicts with encoding specifier")); |
13851 | 0 | goto done; |
13852 | 0 | } |
13853 | 0 | if (evex) |
13854 | 0 | pp.encoding = encoding_evex; |
13855 | 0 | else |
13856 | 0 | pp.encoding = encoding_default; |
13857 | 0 | } |
13858 | | |
13859 | | /* Are we to emit ModR/M encoding? */ |
13860 | 108 | if (!i.short_form |
13861 | 108 | && (i.mem_operands |
13862 | 108 | || i.reg_operands > (pp.encoding != encoding_default) |
13863 | 108 | || i.tm.extension_opcode != None)) |
13864 | 108 | i.tm.opcode_modifier.modrm = 1; |
13865 | | |
13866 | 108 | if (!i.tm.opcode_modifier.modrm |
13867 | 108 | && (i.reg_operands |
13868 | 0 | > i.short_form + 0U + (pp.encoding != encoding_default) |
13869 | 0 | || i.mem_operands)) |
13870 | 0 | { |
13871 | 0 | as_bad (_("too many register/memory operands")); |
13872 | 0 | goto done; |
13873 | 0 | } |
13874 | | |
13875 | | /* Enforce certain constraints on operands. */ |
13876 | 108 | switch (i.reg_operands + i.mem_operands |
13877 | 108 | + (i.tm.extension_opcode != None) |
13878 | 108 | + (i.tm.opcode_modifier.operandconstraint == SCC)) |
13879 | 108 | { |
13880 | 0 | case 0: |
13881 | 0 | if (i.short_form) |
13882 | 0 | { |
13883 | 0 | as_bad (_("too few register/memory operands")); |
13884 | 0 | goto done; |
13885 | 0 | } |
13886 | | /* Fall through. */ |
13887 | 108 | case 1: |
13888 | 108 | if (i.tm.opcode_modifier.modrm) |
13889 | 108 | { |
13890 | 108 | as_bad (_("too few register/memory operands")); |
13891 | 108 | goto done; |
13892 | 108 | } |
13893 | | /* Fall through. */ |
13894 | 0 | case 2: |
13895 | 0 | if (evex == evex_nd) |
13896 | 0 | { |
13897 | 0 | as_bad (_("too few register/memory operands")); |
13898 | 0 | goto done; |
13899 | 0 | } |
13900 | 0 | break; |
13901 | | |
13902 | 0 | case 4: |
13903 | 0 | if (i.imm_operands |
13904 | 0 | && (i.op[0].imms->X_op != O_constant |
13905 | 0 | || !fits_in_imm4 (i.op[0].imms->X_add_number))) |
13906 | 0 | { |
13907 | 0 | as_bad (_("constant doesn't fit in %d bits"), evex ? 3 : 4); |
13908 | 0 | goto done; |
13909 | 0 | } |
13910 | | /* Fall through. */ |
13911 | 0 | case 3: |
13912 | 0 | if (i.tm.opcode_modifier.operandconstraint == SCC) |
13913 | 0 | break; |
13914 | 0 | if (pp.encoding != encoding_default) |
13915 | 0 | { |
13916 | 0 | i.tm.opcode_modifier.vexvvvv = (i.tm.extension_opcode == None |
13917 | 0 | && evex != evex_nd) |
13918 | 0 | ? VexVVVV_SRC1 : VexVVVV_DST; |
13919 | 0 | break; |
13920 | 0 | } |
13921 | | /* Fall through. */ |
13922 | 0 | default: |
13923 | 0 | as_bad (_("too many register/memory operands")); |
13924 | 0 | goto done; |
13925 | 108 | } |
13926 | | |
13927 | | /* Bring operands into canonical order (imm, mem, reg). */ |
13928 | 0 | do |
13929 | 0 | { |
13930 | 0 | changed = false; |
13931 | |
|
13932 | 0 | for (j = 1; j < i.operands; ++j) |
13933 | 0 | { |
13934 | 0 | if ((!operand_type_check (i.types[j - 1], imm) |
13935 | 0 | && operand_type_check (i.types[j], imm)) |
13936 | 0 | || (i.types[j - 1].bitfield.class != ClassNone |
13937 | 0 | && i.types[j].bitfield.class == ClassNone)) |
13938 | 0 | { |
13939 | 0 | swap_2_operands (j - 1, j); |
13940 | 0 | changed = true; |
13941 | 0 | } |
13942 | 0 | } |
13943 | 0 | } |
13944 | 0 | while (changed); |
13945 | | |
13946 | | /* For Intel syntax swap the order of register operands. */ |
13947 | 0 | if (intel_syntax) |
13948 | 0 | switch (i.reg_operands) |
13949 | 0 | { |
13950 | 0 | case 0: |
13951 | 0 | case 1: |
13952 | 0 | break; |
13953 | | |
13954 | 0 | case 4: |
13955 | 0 | swap_2_operands (i.imm_operands + i.mem_operands + 1, i.operands - 2); |
13956 | | /* Fall through. */ |
13957 | 0 | case 3: |
13958 | 0 | case 2: |
13959 | 0 | swap_2_operands (i.imm_operands + i.mem_operands, i.operands - 1); |
13960 | 0 | break; |
13961 | | |
13962 | 0 | default: |
13963 | 0 | abort (); |
13964 | 0 | } |
13965 | | |
13966 | | /* Enforce constraints when using VSIB. */ |
13967 | 0 | if (i.index_reg |
13968 | 0 | && (i.index_reg->reg_type.bitfield.xmmword |
13969 | 0 | || i.index_reg->reg_type.bitfield.ymmword |
13970 | 0 | || i.index_reg->reg_type.bitfield.zmmword)) |
13971 | 0 | { |
13972 | 0 | if (pp.encoding == encoding_default) |
13973 | 0 | { |
13974 | 0 | as_bad (_("VSIB unavailable with legacy encoding")); |
13975 | 0 | goto done; |
13976 | 0 | } |
13977 | | |
13978 | 0 | if (pp.encoding == encoding_evex |
13979 | 0 | && i.reg_operands > 1) |
13980 | 0 | { |
13981 | | /* We could allow two register operands, encoding the 2nd one in |
13982 | | an 8-bit immediate like for 4-register-operand insns, but that |
13983 | | would require ugly fiddling with process_operands() and/or |
13984 | | build_modrm_byte(). */ |
13985 | 0 | as_bad (_("too many register operands with VSIB")); |
13986 | 0 | goto done; |
13987 | 0 | } |
13988 | | |
13989 | 0 | i.tm.opcode_modifier.sib = 1; |
13990 | 0 | } |
13991 | | |
13992 | | /* Establish operand size encoding. */ |
13993 | 0 | operand_type_set (&combined, 0); |
13994 | |
|
13995 | 0 | for (j = i.imm_operands; j < i.operands; ++j) |
13996 | 0 | { |
13997 | | /* Look for 8-bit operands that use old registers. */ |
13998 | 0 | if (pp.encoding != encoding_default |
13999 | 0 | && flag_code == CODE_64BIT |
14000 | 0 | && i.types[j].bitfield.class == Reg |
14001 | 0 | && i.types[j].bitfield.byte |
14002 | 0 | && !(i.op[j].regs->reg_flags & (RegRex | RegRex2 | RegRex64)) |
14003 | 0 | && i.op[j].regs->reg_num > 3) |
14004 | 0 | as_bad (_("can't encode register '%s%s' with VEX/XOP/EVEX"), |
14005 | 0 | register_prefix, i.op[j].regs->reg_name); |
14006 | |
|
14007 | 0 | i.types[j].bitfield.instance = InstanceNone; |
14008 | |
|
14009 | 0 | if (operand_type_check (i.types[j], disp)) |
14010 | 0 | { |
14011 | 0 | i.types[j].bitfield.baseindex = 1; |
14012 | 0 | disp_exp = i.op[j].disps; |
14013 | 0 | } |
14014 | |
|
14015 | 0 | if (evex && i.types[j].bitfield.baseindex) |
14016 | 0 | { |
14017 | 0 | unsigned int n = i.memshift; |
14018 | |
|
14019 | 0 | if (i.types[j].bitfield.byte) |
14020 | 0 | n = 0; |
14021 | 0 | else if (i.types[j].bitfield.word) |
14022 | 0 | n = 1; |
14023 | 0 | else if (i.types[j].bitfield.dword) |
14024 | 0 | n = 2; |
14025 | 0 | else if (i.types[j].bitfield.qword) |
14026 | 0 | n = 3; |
14027 | 0 | else if (i.types[j].bitfield.xmmword) |
14028 | 0 | n = 4; |
14029 | 0 | else if (i.types[j].bitfield.ymmword) |
14030 | 0 | n = 5; |
14031 | 0 | else if (i.types[j].bitfield.zmmword) |
14032 | 0 | n = 6; |
14033 | |
|
14034 | 0 | if (i.memshift < 32 && n != i.memshift) |
14035 | 0 | as_warn ("conflicting memory operand size specifiers"); |
14036 | 0 | i.memshift = n; |
14037 | 0 | } |
14038 | |
|
14039 | 0 | if ((i.broadcast.type || i.broadcast.bytes) |
14040 | 0 | && j == i.broadcast.operand) |
14041 | 0 | continue; |
14042 | | |
14043 | 0 | combined = operand_type_or (combined, i.types[j]); |
14044 | 0 | combined.bitfield.class = ClassNone; |
14045 | 0 | } |
14046 | |
|
14047 | 0 | switch ((i.broadcast.type ? i.broadcast.type : 1) |
14048 | 0 | << (i.memshift < 32 ? i.memshift : 0)) |
14049 | 0 | { |
14050 | 0 | case 64: combined.bitfield.zmmword = 1; break; |
14051 | 0 | case 32: combined.bitfield.ymmword = 1; break; |
14052 | 0 | case 16: combined.bitfield.xmmword = 1; break; |
14053 | 0 | case 8: combined.bitfield.qword = 1; break; |
14054 | 0 | case 4: combined.bitfield.dword = 1; break; |
14055 | 0 | } |
14056 | | |
14057 | 0 | if (pp.encoding == encoding_default) |
14058 | 0 | { |
14059 | 0 | if (flag_code == CODE_64BIT && combined.bitfield.qword) |
14060 | 0 | i.rex |= REX_W; |
14061 | 0 | else if ((flag_code == CODE_16BIT ? combined.bitfield.dword |
14062 | 0 | : combined.bitfield.word) |
14063 | 0 | && !add_prefix (DATA_PREFIX_OPCODE)) |
14064 | 0 | goto done; |
14065 | 0 | } |
14066 | 0 | else if (!i.tm.opcode_modifier.vexw) |
14067 | 0 | { |
14068 | 0 | if (flag_code == CODE_64BIT) |
14069 | 0 | { |
14070 | 0 | if (combined.bitfield.qword) |
14071 | 0 | i.tm.opcode_modifier.vexw = VEXW1; |
14072 | 0 | else if (combined.bitfield.dword) |
14073 | 0 | i.tm.opcode_modifier.vexw = VEXW0; |
14074 | 0 | } |
14075 | |
|
14076 | 0 | if (!i.tm.opcode_modifier.vexw) |
14077 | 0 | i.tm.opcode_modifier.vexw = VEXWIG; |
14078 | 0 | } |
14079 | | |
14080 | 0 | if (vex || xop) |
14081 | 0 | { |
14082 | 0 | if (!i.tm.opcode_modifier.vex) |
14083 | 0 | { |
14084 | 0 | if (combined.bitfield.ymmword) |
14085 | 0 | i.tm.opcode_modifier.vex = VEX256; |
14086 | 0 | else if (combined.bitfield.xmmword) |
14087 | 0 | i.tm.opcode_modifier.vex = VEX128; |
14088 | 0 | } |
14089 | 0 | } |
14090 | 0 | else if (evex) |
14091 | 0 | { |
14092 | 0 | if (!i.tm.opcode_modifier.evex) |
14093 | 0 | { |
14094 | | /* Do _not_ consider AVX512VL here. */ |
14095 | 0 | if (combined.bitfield.zmmword) |
14096 | 0 | i.tm.opcode_modifier.evex = EVEX512; |
14097 | 0 | else if (combined.bitfield.ymmword) |
14098 | 0 | i.tm.opcode_modifier.evex = EVEX256; |
14099 | 0 | else if (combined.bitfield.xmmword) |
14100 | 0 | i.tm.opcode_modifier.evex = EVEX128; |
14101 | 0 | } |
14102 | |
|
14103 | 0 | if (i.memshift >= 32) |
14104 | 0 | { |
14105 | 0 | unsigned int n = 0; |
14106 | |
|
14107 | 0 | switch (i.tm.opcode_modifier.evex) |
14108 | 0 | { |
14109 | 0 | case EVEX512: n = 64; break; |
14110 | 0 | case EVEX256: n = 32; break; |
14111 | 0 | case EVEX128: n = 16; break; |
14112 | 0 | } |
14113 | | |
14114 | 0 | if (i.broadcast.type) |
14115 | 0 | n /= i.broadcast.type; |
14116 | |
|
14117 | 0 | if (n > 0) |
14118 | 0 | for (i.memshift = 0; !(n & 1); n >>= 1) |
14119 | 0 | ++i.memshift; |
14120 | 0 | else if (disp_exp != NULL && disp_exp->X_op == O_constant |
14121 | 0 | && disp_exp->X_add_number != 0 |
14122 | 0 | && pp.disp_encoding != disp_encoding_32bit) |
14123 | 0 | { |
14124 | 0 | if (!quiet_warnings) |
14125 | 0 | as_warn ("cannot determine memory operand size"); |
14126 | 0 | pp.disp_encoding = disp_encoding_32bit; |
14127 | 0 | } |
14128 | 0 | } |
14129 | 0 | } |
14130 | | |
14131 | 0 | if (i.memshift >= 32) |
14132 | 0 | i.memshift = 0; |
14133 | 0 | else if (!evex) |
14134 | 0 | pp.encoding = encoding_error; |
14135 | |
|
14136 | 0 | if (i.disp_operands && !optimize_disp (&i.tm)) |
14137 | 0 | goto done; |
14138 | | |
14139 | | /* Establish size for immediate operands. */ |
14140 | 0 | for (j = 0; j < i.imm_operands; ++j) |
14141 | 0 | { |
14142 | 0 | expressionS *expP = i.op[j].imms; |
14143 | |
|
14144 | 0 | gas_assert (operand_type_check (i.types[j], imm)); |
14145 | 0 | operand_type_set (&i.types[j], 0); |
14146 | |
|
14147 | 0 | if (i.imm_bits[j] > 32) |
14148 | 0 | i.types[j].bitfield.imm64 = 1; |
14149 | 0 | else if (i.imm_bits[j] > 16) |
14150 | 0 | { |
14151 | 0 | if (flag_code == CODE_64BIT && (i.flags[j] & Operand_Signed)) |
14152 | 0 | i.types[j].bitfield.imm32s = 1; |
14153 | 0 | else |
14154 | 0 | i.types[j].bitfield.imm32 = 1; |
14155 | 0 | } |
14156 | 0 | else if (i.imm_bits[j] > 8) |
14157 | 0 | i.types[j].bitfield.imm16 = 1; |
14158 | 0 | else if (i.imm_bits[j] > 0) |
14159 | 0 | { |
14160 | 0 | if (i.flags[j] & Operand_Signed) |
14161 | 0 | i.types[j].bitfield.imm8s = 1; |
14162 | 0 | else |
14163 | 0 | i.types[j].bitfield.imm8 = 1; |
14164 | 0 | } |
14165 | 0 | else if (expP->X_op == O_constant) |
14166 | 0 | { |
14167 | 0 | i.types[j] = smallest_imm_type (expP->X_add_number); |
14168 | 0 | i.types[j].bitfield.imm1 = 0; |
14169 | | /* Oddly enough imm_size() checks imm64 first, so the bit needs |
14170 | | zapping since smallest_imm_type() sets it unconditionally. */ |
14171 | 0 | if (flag_code != CODE_64BIT) |
14172 | 0 | { |
14173 | 0 | i.types[j].bitfield.imm64 = 0; |
14174 | 0 | i.types[j].bitfield.imm32s = 0; |
14175 | 0 | i.types[j].bitfield.imm32 = 1; |
14176 | 0 | } |
14177 | 0 | else if (i.types[j].bitfield.imm32 || i.types[j].bitfield.imm32s) |
14178 | 0 | i.types[j].bitfield.imm64 = 0; |
14179 | 0 | } |
14180 | 0 | else |
14181 | | /* Non-constant expressions are sized heuristically. */ |
14182 | 0 | switch (flag_code) |
14183 | 0 | { |
14184 | 0 | case CODE_64BIT: i.types[j].bitfield.imm32s = 1; break; |
14185 | 0 | case CODE_32BIT: i.types[j].bitfield.imm32 = 1; break; |
14186 | 0 | case CODE_16BIT: i.types[j].bitfield.imm16 = 1; break; |
14187 | 0 | } |
14188 | 0 | } |
14189 | | |
14190 | 0 | for (j = 0; j < i.operands; ++j) |
14191 | 0 | i.tm.operand_types[j] = i.types[j]; |
14192 | |
|
14193 | 0 | process_operands (); |
14194 | 0 | } |
14195 | | |
14196 | | /* Don't set opcode until after processing operands, to avoid any |
14197 | | potential special casing there. */ |
14198 | 489 | i.tm.base_opcode |= val; |
14199 | | |
14200 | 489 | if (pp.encoding == encoding_error |
14201 | 489 | || (pp.encoding != encoding_evex |
14202 | 489 | ? i.broadcast.type || i.broadcast.bytes |
14203 | 489 | || i.rounding.type != rc_none |
14204 | 489 | || i.mask.reg |
14205 | 489 | : (i.mem_operands && i.rounding.type != rc_none) |
14206 | 0 | || ((i.broadcast.type || i.broadcast.bytes) |
14207 | 0 | && !(i.flags[i.broadcast.operand] & Operand_Mem)))) |
14208 | 0 | { |
14209 | 0 | as_bad (_("conflicting .insn operands")); |
14210 | 0 | goto done; |
14211 | 0 | } |
14212 | | |
14213 | 489 | if (vex || xop) |
14214 | 477 | { |
14215 | 477 | if (is_apx_evex_encoding ()) |
14216 | 0 | { |
14217 | 0 | as_bad (_("APX functionality cannot be used with %s encodings"), |
14218 | 0 | vex ? "VEX" : "XOP"); |
14219 | 0 | goto done; |
14220 | 0 | } |
14221 | | |
14222 | 477 | if (!i.tm.opcode_modifier.vex) |
14223 | 477 | i.tm.opcode_modifier.vex = VEXScalar; /* LIG */ |
14224 | | |
14225 | 477 | build_vex_prefix (NULL); |
14226 | 477 | i.rex &= REX_OPCODE; |
14227 | 477 | } |
14228 | 12 | else if (evex) |
14229 | 0 | { |
14230 | 0 | if (!i.tm.opcode_modifier.evex) |
14231 | 0 | i.tm.opcode_modifier.evex = EVEXLIG; |
14232 | | |
14233 | | /* To keep earlier .insn uses working as far as possible, take the |
14234 | | legacy path when opcode space is 4 bits wide (impossible to encode in |
14235 | | extended EVEX), and when no "extended" syntax elements are used. */ |
14236 | 0 | if ((!is_apx_evex_encoding () || i.insn_opcode_space > 7) |
14237 | 0 | && evex == evex_basic |
14238 | 0 | && !i.tm.opcode_modifier.operandconstraint) |
14239 | 0 | build_evex_prefix (); |
14240 | 0 | else if (i.insn_opcode_space > 7) |
14241 | 0 | { |
14242 | 0 | as_bad (_("opcode space cannot be larger than 7")); |
14243 | 0 | goto done; |
14244 | 0 | } |
14245 | 0 | else if (evex == evex_nd && (i.broadcast.type || i.broadcast.bytes)) |
14246 | 0 | { |
14247 | 0 | as_bad (_("ND and broadcast cannot be used at the same time")); |
14248 | 0 | goto done; |
14249 | 0 | } |
14250 | 0 | else if (pp.has_nf && i.mask.reg) |
14251 | 0 | { |
14252 | 0 | as_bad (_("{nf} and masking cannot be used at the same time")); |
14253 | 0 | goto done; |
14254 | 0 | } |
14255 | 0 | else if (i.tm.opcode_modifier.operandconstraint == SCC |
14256 | 0 | && (pp.has_nf || i.mask.reg)) |
14257 | 0 | { |
14258 | 0 | as_bad (_("SCC cannot be used at the same time {nf} / masking")); |
14259 | 0 | goto done; |
14260 | 0 | } |
14261 | 0 | else if (!build_apx_evex_prefix (evex == evex_nd)) |
14262 | 0 | goto done; |
14263 | 0 | i.rex &= REX_OPCODE; |
14264 | 0 | } |
14265 | 12 | else |
14266 | 12 | establish_rex (); |
14267 | | |
14268 | 489 | last_insn = &seg_info(now_seg)->tc_segment_info_data.last_insn; |
14269 | 489 | output_insn (last_insn); |
14270 | 489 | last_insn->kind = last_insn_directive; |
14271 | 489 | last_insn->name = ".insn directive"; |
14272 | 489 | last_insn->file = as_where (&last_insn->line); |
14273 | | |
14274 | 489 | #ifdef OBJ_ELF |
14275 | | /* PS: SCFI is enabled only for System V AMD64 ABI. The ABI check has been |
14276 | | performed in i386_target_format. */ |
14277 | 489 | if (flag_synth_cfi) |
14278 | 0 | as_bad (_("SCFI: hand-crafting instructions not supported")); |
14279 | 489 | #endif |
14280 | | |
14281 | 598 | done: |
14282 | 598 | *saved_ilp = saved_char; |
14283 | 598 | input_line_pointer = line; |
14284 | | |
14285 | 598 | demand_empty_rest_of_line (); |
14286 | | |
14287 | | /* Make sure dot_insn() won't yield "true" anymore. */ |
14288 | 598 | i.tm.mnem_off = 0; |
14289 | | |
14290 | 598 | current_templates.start = NULL; |
14291 | 598 | memset (&pp, 0, sizeof (pp)); |
14292 | 598 | } |
14293 | | |
14294 | | #ifdef TE_PE |
14295 | | static void |
14296 | | pe_directive_secrel (int dummy ATTRIBUTE_UNUSED) |
14297 | | { |
14298 | | expressionS exp; |
14299 | | |
14300 | | do |
14301 | | { |
14302 | | expression (&exp); |
14303 | | if (exp.X_op == O_symbol) |
14304 | | exp.X_op = O_secrel; |
14305 | | |
14306 | | emit_expr (&exp, 4); |
14307 | | } |
14308 | | while (*input_line_pointer++ == ','); |
14309 | | |
14310 | | input_line_pointer--; |
14311 | | demand_empty_rest_of_line (); |
14312 | | } |
14313 | | |
14314 | | static void |
14315 | | pe_directive_secidx (int dummy ATTRIBUTE_UNUSED) |
14316 | | { |
14317 | | expressionS exp; |
14318 | | |
14319 | | do |
14320 | | { |
14321 | | expression (&exp); |
14322 | | if (exp.X_op == O_symbol) |
14323 | | exp.X_op = O_secidx; |
14324 | | |
14325 | | emit_expr (&exp, 2); |
14326 | | } |
14327 | | while (*input_line_pointer++ == ','); |
14328 | | |
14329 | | input_line_pointer--; |
14330 | | demand_empty_rest_of_line (); |
14331 | | } |
14332 | | #endif |
14333 | | |
14334 | | /* Handle Rounding Control / SAE specifiers. */ |
14335 | | |
14336 | | static char * |
14337 | | RC_SAE_specifier (const char *pstr) |
14338 | 32 | { |
14339 | 32 | unsigned int j; |
14340 | | |
14341 | 192 | for (j = 0; j < ARRAY_SIZE (RC_NamesTable); j++) |
14342 | 160 | { |
14343 | 160 | if (!strncmp (pstr, RC_NamesTable[j].name, RC_NamesTable[j].len)) |
14344 | 0 | { |
14345 | 0 | if (i.rounding.type != rc_none) |
14346 | 0 | { |
14347 | 0 | as_bad (_("duplicated `{%s}'"), RC_NamesTable[j].name); |
14348 | 0 | return NULL; |
14349 | 0 | } |
14350 | | |
14351 | 0 | switch (pp.encoding) |
14352 | 0 | { |
14353 | 0 | case encoding_default: |
14354 | 0 | case encoding_egpr: |
14355 | 0 | pp.encoding = encoding_evex512; |
14356 | 0 | break; |
14357 | 0 | case encoding_evex: |
14358 | 0 | case encoding_evex512: |
14359 | 0 | break; |
14360 | 0 | default: |
14361 | 0 | return NULL; |
14362 | 0 | } |
14363 | | |
14364 | 0 | i.rounding.type = RC_NamesTable[j].type; |
14365 | |
|
14366 | 0 | return (char *)(pstr + RC_NamesTable[j].len); |
14367 | 0 | } |
14368 | 160 | } |
14369 | | |
14370 | 32 | return NULL; |
14371 | 32 | } |
14372 | | |
14373 | | /* Handle Vector operations. */ |
14374 | | |
14375 | | static char * |
14376 | | check_VecOperations (char *op_string) |
14377 | 0 | { |
14378 | 0 | const reg_entry *mask; |
14379 | 0 | const char *saved; |
14380 | 0 | char *end_op; |
14381 | |
|
14382 | 0 | while (*op_string) |
14383 | 0 | { |
14384 | 0 | saved = op_string; |
14385 | 0 | if (*op_string == '{') |
14386 | 0 | { |
14387 | 0 | op_string++; |
14388 | 0 | if (is_whitespace (*op_string)) |
14389 | 0 | op_string++; |
14390 | | |
14391 | | /* Check broadcasts. */ |
14392 | 0 | if (startswith (op_string, "1to")) |
14393 | 0 | { |
14394 | 0 | unsigned int bcst_type; |
14395 | |
|
14396 | 0 | if (i.broadcast.type) |
14397 | 0 | goto duplicated_vec_op; |
14398 | | |
14399 | 0 | op_string += 3; |
14400 | 0 | if (*op_string == '8') |
14401 | 0 | bcst_type = 8; |
14402 | 0 | else if (*op_string == '4') |
14403 | 0 | bcst_type = 4; |
14404 | 0 | else if (*op_string == '2') |
14405 | 0 | bcst_type = 2; |
14406 | 0 | else if (*op_string == '1' |
14407 | 0 | && *(op_string+1) == '6') |
14408 | 0 | { |
14409 | 0 | bcst_type = 16; |
14410 | 0 | op_string++; |
14411 | 0 | } |
14412 | 0 | else if (*op_string == '3' |
14413 | 0 | && *(op_string+1) == '2') |
14414 | 0 | { |
14415 | 0 | bcst_type = 32; |
14416 | 0 | op_string++; |
14417 | 0 | } |
14418 | 0 | else |
14419 | 0 | { |
14420 | 0 | as_bad (_("Unsupported broadcast: `%s'"), saved); |
14421 | 0 | return NULL; |
14422 | 0 | } |
14423 | 0 | op_string++; |
14424 | |
|
14425 | 0 | switch (pp.encoding) |
14426 | 0 | { |
14427 | 0 | case encoding_default: |
14428 | 0 | case encoding_egpr: |
14429 | 0 | pp.encoding = encoding_evex; |
14430 | 0 | break; |
14431 | 0 | case encoding_evex: |
14432 | 0 | case encoding_evex512: |
14433 | 0 | break; |
14434 | 0 | default: |
14435 | 0 | goto unknown_vec_op; |
14436 | 0 | } |
14437 | | |
14438 | 0 | i.broadcast.type = bcst_type; |
14439 | 0 | i.broadcast.operand = this_operand; |
14440 | | |
14441 | | /* For .insn a data size specifier may be appended. */ |
14442 | 0 | if (dot_insn () && *op_string == ':') |
14443 | 0 | goto dot_insn_modifier; |
14444 | 0 | } |
14445 | | /* Check .insn special cases. */ |
14446 | 0 | else if (dot_insn () && *op_string == ':') |
14447 | 0 | { |
14448 | 0 | dot_insn_modifier: |
14449 | 0 | switch (op_string[1]) |
14450 | 0 | { |
14451 | 0 | unsigned long n; |
14452 | | |
14453 | 0 | case 'd': |
14454 | 0 | if (i.memshift < 32) |
14455 | 0 | goto duplicated_vec_op; |
14456 | | |
14457 | 0 | n = strtoul (op_string + 2, &end_op, 0); |
14458 | 0 | if (n) |
14459 | 0 | for (i.memshift = 0; !(n & 1); n >>= 1) |
14460 | 0 | ++i.memshift; |
14461 | 0 | if (i.memshift < 32 && n == 1) |
14462 | 0 | op_string = end_op; |
14463 | 0 | break; |
14464 | | |
14465 | 0 | case 's': case 'u': |
14466 | | /* This isn't really a "vector" operation, but a sign/size |
14467 | | specifier for immediate operands of .insn. Note that AT&T |
14468 | | syntax handles the same in i386_immediate(). */ |
14469 | 0 | if (!intel_syntax) |
14470 | 0 | break; |
14471 | | |
14472 | 0 | if (i.imm_bits[this_operand]) |
14473 | 0 | goto duplicated_vec_op; |
14474 | | |
14475 | 0 | n = strtoul (op_string + 2, &end_op, 0); |
14476 | 0 | if (n && n <= (flag_code == CODE_64BIT ? 64 : 32)) |
14477 | 0 | { |
14478 | 0 | i.imm_bits[this_operand] = n; |
14479 | 0 | if (op_string[1] == 's') |
14480 | 0 | i.flags[this_operand] |= Operand_Signed; |
14481 | 0 | op_string = end_op; |
14482 | 0 | } |
14483 | 0 | break; |
14484 | 0 | } |
14485 | 0 | } |
14486 | | /* Check masking operation. */ |
14487 | 0 | else if ((mask = parse_register (op_string, &end_op)) != NULL) |
14488 | 0 | { |
14489 | 0 | if (mask == &bad_reg) |
14490 | 0 | return NULL; |
14491 | | |
14492 | | /* k0 can't be used for write mask. */ |
14493 | 0 | if (mask->reg_type.bitfield.class != RegMask || !mask->reg_num) |
14494 | 0 | { |
14495 | 0 | as_bad (_("`%s%s' can't be used for write mask"), |
14496 | 0 | register_prefix, mask->reg_name); |
14497 | 0 | return NULL; |
14498 | 0 | } |
14499 | | |
14500 | 0 | if (!i.mask.reg) |
14501 | 0 | { |
14502 | 0 | i.mask.reg = mask; |
14503 | 0 | i.mask.operand = this_operand; |
14504 | 0 | } |
14505 | 0 | else if (i.mask.reg->reg_num) |
14506 | 0 | goto duplicated_vec_op; |
14507 | 0 | else |
14508 | 0 | { |
14509 | 0 | i.mask.reg = mask; |
14510 | | |
14511 | | /* Only "{z}" is allowed here. No need to check |
14512 | | zeroing mask explicitly. */ |
14513 | 0 | if (i.mask.operand != (unsigned int) this_operand) |
14514 | 0 | { |
14515 | 0 | as_bad (_("invalid write mask `%s'"), saved); |
14516 | 0 | return NULL; |
14517 | 0 | } |
14518 | 0 | } |
14519 | | |
14520 | 0 | op_string = end_op; |
14521 | 0 | } |
14522 | | /* Check zeroing-flag for masking operation. */ |
14523 | 0 | else if (*op_string == 'z') |
14524 | 0 | { |
14525 | 0 | if (!i.mask.reg) |
14526 | 0 | { |
14527 | 0 | i.mask.reg = reg_k0; |
14528 | 0 | i.mask.zeroing = 1; |
14529 | 0 | i.mask.operand = this_operand; |
14530 | 0 | } |
14531 | 0 | else |
14532 | 0 | { |
14533 | 0 | if (i.mask.zeroing) |
14534 | 0 | { |
14535 | 0 | duplicated_vec_op: |
14536 | 0 | as_bad (_("duplicated `%s'"), saved); |
14537 | 0 | return NULL; |
14538 | 0 | } |
14539 | | |
14540 | 0 | i.mask.zeroing = 1; |
14541 | | |
14542 | | /* Only "{%k}" is allowed here. No need to check mask |
14543 | | register explicitly. */ |
14544 | 0 | if (i.mask.operand != (unsigned int) this_operand) |
14545 | 0 | { |
14546 | 0 | as_bad (_("invalid zeroing-masking `%s'"), |
14547 | 0 | saved); |
14548 | 0 | return NULL; |
14549 | 0 | } |
14550 | 0 | } |
14551 | | |
14552 | 0 | op_string++; |
14553 | 0 | } |
14554 | 0 | else if (intel_syntax |
14555 | 0 | && (op_string = RC_SAE_specifier (op_string)) != NULL) |
14556 | 0 | i.rounding.modifier = true; |
14557 | 0 | else |
14558 | 0 | goto unknown_vec_op; |
14559 | | |
14560 | 0 | if (is_whitespace (*op_string)) |
14561 | 0 | op_string++; |
14562 | 0 | if (*op_string != '}') |
14563 | 0 | { |
14564 | 0 | as_bad (_("missing `}' in `%s'"), saved); |
14565 | 0 | return NULL; |
14566 | 0 | } |
14567 | 0 | op_string++; |
14568 | |
|
14569 | 0 | if (is_whitespace (*op_string)) |
14570 | 0 | ++op_string; |
14571 | |
|
14572 | 0 | continue; |
14573 | 0 | } |
14574 | 0 | unknown_vec_op: |
14575 | | /* We don't know this one. */ |
14576 | 0 | as_bad (_("unknown vector operation: `%s'"), saved); |
14577 | 0 | return NULL; |
14578 | 0 | } |
14579 | | |
14580 | 0 | if (i.mask.reg && i.mask.zeroing && !i.mask.reg->reg_num) |
14581 | 0 | { |
14582 | 0 | as_bad (_("zeroing-masking only allowed with write mask")); |
14583 | 0 | return NULL; |
14584 | 0 | } |
14585 | | |
14586 | 0 | return op_string; |
14587 | 0 | } |
14588 | | |
14589 | | static int |
14590 | | i386_immediate (char *imm_start) |
14591 | 5.32k | { |
14592 | 5.32k | char *save_input_line_pointer; |
14593 | 5.32k | char *gotfree_input_line; |
14594 | 5.32k | segT exp_seg = 0; |
14595 | 5.32k | expressionS *exp; |
14596 | 5.32k | i386_operand_type types; |
14597 | | |
14598 | 5.32k | operand_type_set (&types, ~0); |
14599 | | |
14600 | 5.32k | if (i.imm_operands == MAX_IMMEDIATE_OPERANDS) |
14601 | 6 | { |
14602 | 6 | as_bad (_("at most %d immediate operands are allowed"), |
14603 | 6 | MAX_IMMEDIATE_OPERANDS); |
14604 | 6 | return 0; |
14605 | 6 | } |
14606 | | |
14607 | 5.32k | exp = &im_expressions[i.imm_operands++]; |
14608 | 5.32k | i.op[this_operand].imms = exp; |
14609 | | |
14610 | 5.32k | if (is_whitespace (*imm_start)) |
14611 | 1 | ++imm_start; |
14612 | | |
14613 | 5.32k | save_input_line_pointer = input_line_pointer; |
14614 | 5.32k | input_line_pointer = imm_start; |
14615 | | |
14616 | 5.32k | gotfree_input_line = lex_got (&i.reloc[this_operand], NULL, &types); |
14617 | 5.32k | if (gotfree_input_line) |
14618 | 1.00k | input_line_pointer = gotfree_input_line; |
14619 | | |
14620 | 5.32k | expr_mode = expr_operator_none; |
14621 | 5.32k | exp_seg = expression (exp); |
14622 | | |
14623 | | /* For .insn immediates there may be a size specifier. */ |
14624 | 5.32k | if (dot_insn () && *input_line_pointer == '{' && input_line_pointer[1] == ':' |
14625 | 5.32k | && (input_line_pointer[2] == 's' || input_line_pointer[2] == 'u')) |
14626 | 0 | { |
14627 | 0 | char *e; |
14628 | 0 | unsigned long n = strtoul (input_line_pointer + 3, &e, 0); |
14629 | |
|
14630 | 0 | if (*e == '}' && n && n <= (flag_code == CODE_64BIT ? 64 : 32)) |
14631 | 0 | { |
14632 | 0 | i.imm_bits[this_operand] = n; |
14633 | 0 | if (input_line_pointer[2] == 's') |
14634 | 0 | i.flags[this_operand] |= Operand_Signed; |
14635 | 0 | input_line_pointer = e + 1; |
14636 | 0 | } |
14637 | 0 | } |
14638 | | |
14639 | 5.32k | SKIP_WHITESPACE (); |
14640 | 5.32k | if (*input_line_pointer) |
14641 | 2.41k | as_bad (_("junk `%s' after expression"), input_line_pointer); |
14642 | | |
14643 | 5.32k | input_line_pointer = save_input_line_pointer; |
14644 | 5.32k | if (gotfree_input_line) |
14645 | 1.00k | { |
14646 | 1.00k | free (gotfree_input_line); |
14647 | | |
14648 | 1.00k | if (exp->X_op == O_constant) |
14649 | 52 | exp->X_op = O_illegal; |
14650 | 1.00k | } |
14651 | | |
14652 | 5.32k | if (exp_seg == reg_section) |
14653 | 0 | { |
14654 | 0 | as_bad (_("illegal immediate register operand %s"), imm_start); |
14655 | 0 | return 0; |
14656 | 0 | } |
14657 | | |
14658 | 5.32k | return i386_finalize_immediate (exp_seg, exp, types, imm_start); |
14659 | 5.32k | } |
14660 | | |
14661 | | static int |
14662 | | i386_finalize_immediate (segT exp_seg ATTRIBUTE_UNUSED, expressionS *exp, |
14663 | | i386_operand_type types, const char *imm_start) |
14664 | 5.32k | { |
14665 | 5.32k | if (exp->X_op == O_absent || exp->X_op == O_illegal || exp->X_op == O_big) |
14666 | 139 | { |
14667 | 139 | if (imm_start) |
14668 | 139 | as_bad (_("missing or invalid immediate expression `%s'"), |
14669 | 139 | imm_start); |
14670 | 139 | return 0; |
14671 | 139 | } |
14672 | 5.18k | else if (exp->X_op == O_constant) |
14673 | 2.91k | { |
14674 | | /* Size it properly later. */ |
14675 | 2.91k | i.types[this_operand].bitfield.imm64 = 1; |
14676 | | |
14677 | | /* If not 64bit, sign/zero extend val, to account for wraparound |
14678 | | when !BFD64. */ |
14679 | 2.91k | if (expr_mode == expr_operator_present |
14680 | 2.91k | && flag_code != CODE_64BIT && !object_64bit) |
14681 | 0 | exp->X_add_number = extend_to_32bit_address (exp->X_add_number); |
14682 | 2.91k | } |
14683 | | #ifdef OBJ_AOUT |
14684 | | else if (exp_seg != absolute_section |
14685 | | && exp_seg != text_section |
14686 | | && exp_seg != data_section |
14687 | | && exp_seg != bss_section |
14688 | | && exp_seg != undefined_section |
14689 | | && !bfd_is_com_section (exp_seg)) |
14690 | | { |
14691 | | as_bad (_("unimplemented segment %s in operand"), exp_seg->name); |
14692 | | return 0; |
14693 | | } |
14694 | | #endif |
14695 | 2.26k | else |
14696 | 2.26k | { |
14697 | | /* This is an address. The size of the address will be |
14698 | | determined later, depending on destination register, |
14699 | | suffix, or the default for the section. */ |
14700 | 2.26k | i.types[this_operand].bitfield.imm8 = 1; |
14701 | 2.26k | i.types[this_operand].bitfield.imm16 = 1; |
14702 | 2.26k | i.types[this_operand].bitfield.imm32 = 1; |
14703 | 2.26k | i.types[this_operand].bitfield.imm32s = 1; |
14704 | 2.26k | i.types[this_operand].bitfield.imm64 = 1; |
14705 | 2.26k | i.types[this_operand] = operand_type_and (i.types[this_operand], |
14706 | 2.26k | types); |
14707 | 2.26k | } |
14708 | | |
14709 | 5.18k | return 1; |
14710 | 5.32k | } |
14711 | | |
14712 | | static char * |
14713 | | i386_scale (char *scale) |
14714 | 18 | { |
14715 | 18 | offsetT val; |
14716 | 18 | char *save = input_line_pointer; |
14717 | | |
14718 | 18 | input_line_pointer = scale; |
14719 | 18 | val = get_absolute_expression (); |
14720 | | |
14721 | 18 | switch (val) |
14722 | 18 | { |
14723 | 0 | case 1: |
14724 | 0 | i.log2_scale_factor = 0; |
14725 | 0 | break; |
14726 | 0 | case 2: |
14727 | 0 | i.log2_scale_factor = 1; |
14728 | 0 | break; |
14729 | 0 | case 4: |
14730 | 0 | i.log2_scale_factor = 2; |
14731 | 0 | break; |
14732 | 0 | case 8: |
14733 | 0 | i.log2_scale_factor = 3; |
14734 | 0 | break; |
14735 | 18 | default: |
14736 | 18 | { |
14737 | 18 | char sep = *input_line_pointer; |
14738 | | |
14739 | 18 | *input_line_pointer = '\0'; |
14740 | 18 | as_bad (_("expecting scale factor of 1, 2, 4, or 8: got `%s'"), |
14741 | 18 | scale); |
14742 | 18 | *input_line_pointer = sep; |
14743 | 18 | input_line_pointer = save; |
14744 | 18 | return NULL; |
14745 | 0 | } |
14746 | 18 | } |
14747 | 0 | if (i.log2_scale_factor != 0 && i.index_reg == 0) |
14748 | 0 | { |
14749 | 0 | as_warn (_("scale factor of %d without an index register"), |
14750 | 0 | 1 << i.log2_scale_factor); |
14751 | 0 | i.log2_scale_factor = 0; |
14752 | 0 | } |
14753 | 0 | scale = input_line_pointer; |
14754 | 0 | input_line_pointer = save; |
14755 | 0 | return scale; |
14756 | 18 | } |
14757 | | |
14758 | | static int |
14759 | | i386_displacement (char *disp_start, char *disp_end) |
14760 | 38.9k | { |
14761 | 38.9k | expressionS *exp; |
14762 | 38.9k | segT exp_seg = 0; |
14763 | 38.9k | char *save_input_line_pointer; |
14764 | 38.9k | char *gotfree_input_line; |
14765 | 38.9k | int override; |
14766 | 38.9k | i386_operand_type bigdisp, types = anydisp; |
14767 | 38.9k | int ret; |
14768 | | |
14769 | 38.9k | if (i.disp_operands == MAX_MEMORY_OPERANDS) |
14770 | 0 | { |
14771 | 0 | as_bad (_("at most %d displacement operands are allowed"), |
14772 | 0 | MAX_MEMORY_OPERANDS); |
14773 | 0 | return 0; |
14774 | 0 | } |
14775 | | |
14776 | 38.9k | operand_type_set (&bigdisp, 0); |
14777 | 38.9k | if (i.jumpabsolute |
14778 | 38.9k | || i.types[this_operand].bitfield.baseindex |
14779 | 38.9k | || (current_templates.start->opcode_modifier.jump != JUMP |
14780 | 38.9k | && current_templates.start->opcode_modifier.jump != JUMP_DWORD)) |
14781 | 38.3k | { |
14782 | 38.3k | i386_addressing_mode (); |
14783 | 38.3k | override = (i.prefix[ADDR_PREFIX] != 0); |
14784 | 38.3k | if (flag_code == CODE_64BIT) |
14785 | 34.0k | { |
14786 | 34.0k | bigdisp.bitfield.disp32 = 1; |
14787 | 34.0k | if (!override) |
14788 | 34.0k | bigdisp.bitfield.disp64 = 1; |
14789 | 34.0k | } |
14790 | 4.29k | else if ((flag_code == CODE_16BIT) ^ override) |
14791 | 655 | bigdisp.bitfield.disp16 = 1; |
14792 | 3.63k | else |
14793 | 3.63k | bigdisp.bitfield.disp32 = 1; |
14794 | 38.3k | } |
14795 | 550 | else |
14796 | 550 | { |
14797 | | /* For PC-relative branches, the width of the displacement may be |
14798 | | dependent upon data size, but is never dependent upon address size. |
14799 | | Also make sure to not unintentionally match against a non-PC-relative |
14800 | | branch template. */ |
14801 | 550 | const insn_template *t = current_templates.start; |
14802 | 550 | bool has_intel64 = false; |
14803 | | |
14804 | 1.21k | while (++t < current_templates.end) |
14805 | 990 | { |
14806 | 990 | if (t->opcode_modifier.jump |
14807 | 990 | != current_templates.start->opcode_modifier.jump) |
14808 | 330 | break; |
14809 | 660 | if ((t->opcode_modifier.isa64 >= INTEL64)) |
14810 | 330 | has_intel64 = true; |
14811 | 660 | } |
14812 | 550 | current_templates.end = t; |
14813 | | |
14814 | 550 | override = (i.prefix[DATA_PREFIX] != 0); |
14815 | 550 | if (flag_code == CODE_64BIT) |
14816 | 17 | { |
14817 | 17 | if ((override || i.suffix == WORD_MNEM_SUFFIX) |
14818 | 17 | && (!intel64 || !has_intel64)) |
14819 | 0 | bigdisp.bitfield.disp16 = 1; |
14820 | 17 | else |
14821 | 17 | bigdisp.bitfield.disp32 = 1; |
14822 | 17 | } |
14823 | 533 | else |
14824 | 533 | { |
14825 | 533 | if (!override) |
14826 | 533 | override = (i.suffix == (flag_code != CODE_16BIT |
14827 | 533 | ? WORD_MNEM_SUFFIX |
14828 | 533 | : LONG_MNEM_SUFFIX)); |
14829 | 533 | bigdisp.bitfield.disp32 = 1; |
14830 | 533 | if ((flag_code == CODE_16BIT) ^ override) |
14831 | 202 | { |
14832 | 202 | bigdisp.bitfield.disp32 = 0; |
14833 | 202 | bigdisp.bitfield.disp16 = 1; |
14834 | 202 | } |
14835 | 533 | } |
14836 | 550 | } |
14837 | 38.9k | i.types[this_operand] = operand_type_or (i.types[this_operand], |
14838 | 38.9k | bigdisp); |
14839 | | |
14840 | 38.9k | exp = &disp_expressions[i.disp_operands]; |
14841 | 38.9k | i.op[this_operand].disps = exp; |
14842 | 38.9k | i.disp_operands++; |
14843 | 38.9k | save_input_line_pointer = input_line_pointer; |
14844 | 38.9k | input_line_pointer = disp_start; |
14845 | 38.9k | END_STRING_AND_SAVE (disp_end); |
14846 | | |
14847 | 38.9k | #ifndef GCC_ASM_O_HACK |
14848 | 38.9k | #define GCC_ASM_O_HACK 0 |
14849 | 38.9k | #endif |
14850 | | #if GCC_ASM_O_HACK |
14851 | | END_STRING_AND_SAVE (disp_end + 1); |
14852 | | if (i.types[this_operand].bitfield.baseIndex |
14853 | | && displacement_string_end[-1] == '+') |
14854 | | { |
14855 | | /* This hack is to avoid a warning when using the "o" |
14856 | | constraint within gcc asm statements. |
14857 | | For instance: |
14858 | | |
14859 | | #define _set_tssldt_desc(n,addr,limit,type) \ |
14860 | | __asm__ __volatile__ ( \ |
14861 | | "movw %w2,%0\n\t" \ |
14862 | | "movw %w1,2+%0\n\t" \ |
14863 | | "rorl $16,%1\n\t" \ |
14864 | | "movb %b1,4+%0\n\t" \ |
14865 | | "movb %4,5+%0\n\t" \ |
14866 | | "movb $0,6+%0\n\t" \ |
14867 | | "movb %h1,7+%0\n\t" \ |
14868 | | "rorl $16,%1" \ |
14869 | | : "=o"(*(n)) : "q" (addr), "ri"(limit), "i"(type)) |
14870 | | |
14871 | | This works great except that the output assembler ends |
14872 | | up looking a bit weird if it turns out that there is |
14873 | | no offset. You end up producing code that looks like: |
14874 | | |
14875 | | #APP |
14876 | | movw $235,(%eax) |
14877 | | movw %dx,2+(%eax) |
14878 | | rorl $16,%edx |
14879 | | movb %dl,4+(%eax) |
14880 | | movb $137,5+(%eax) |
14881 | | movb $0,6+(%eax) |
14882 | | movb %dh,7+(%eax) |
14883 | | rorl $16,%edx |
14884 | | #NO_APP |
14885 | | |
14886 | | So here we provide the missing zero. */ |
14887 | | |
14888 | | *displacement_string_end = '0'; |
14889 | | } |
14890 | | #endif |
14891 | 38.9k | gotfree_input_line = lex_got (&i.reloc[this_operand], NULL, &types); |
14892 | 38.9k | if (gotfree_input_line) |
14893 | 827 | input_line_pointer = gotfree_input_line; |
14894 | | |
14895 | 38.9k | expr_mode = expr_operator_none; |
14896 | 38.9k | exp_seg = expression (exp); |
14897 | | |
14898 | 38.9k | SKIP_WHITESPACE (); |
14899 | 38.9k | if (*input_line_pointer) |
14900 | 2.27k | as_bad (_("junk `%s' after expression"), input_line_pointer); |
14901 | | #if GCC_ASM_O_HACK |
14902 | | RESTORE_END_STRING (disp_end + 1); |
14903 | | #endif |
14904 | 38.9k | input_line_pointer = save_input_line_pointer; |
14905 | 38.9k | if (gotfree_input_line) |
14906 | 827 | { |
14907 | 827 | free (gotfree_input_line); |
14908 | | |
14909 | 827 | if (exp->X_op == O_constant || exp->X_op == O_register) |
14910 | 377 | exp->X_op = O_illegal; |
14911 | 827 | } |
14912 | | |
14913 | 38.9k | ret = i386_finalize_displacement (exp_seg, exp, types, disp_start); |
14914 | | |
14915 | 38.9k | RESTORE_END_STRING (disp_end); |
14916 | | |
14917 | 38.9k | return ret; |
14918 | 38.9k | } |
14919 | | |
14920 | | static int |
14921 | | i386_finalize_displacement (segT exp_seg ATTRIBUTE_UNUSED, expressionS *exp, |
14922 | | i386_operand_type types, const char *disp_start) |
14923 | 38.9k | { |
14924 | 38.9k | int ret = 1; |
14925 | | |
14926 | | /* We do this to make sure that the section symbol is in |
14927 | | the symbol table. We will ultimately change the relocation |
14928 | | to be relative to the beginning of the section. */ |
14929 | 38.9k | if (i.reloc[this_operand] == BFD_RELOC_386_GOTOFF |
14930 | 38.9k | || i.reloc[this_operand] == BFD_RELOC_X86_64_GOTPCREL |
14931 | 38.9k | || i.reloc[this_operand] == BFD_RELOC_X86_64_GOTOFF64) |
14932 | 21 | { |
14933 | 21 | if (exp->X_op != O_symbol) |
14934 | 11 | goto inv_disp; |
14935 | | |
14936 | 10 | if (S_IS_LOCAL (exp->X_add_symbol) |
14937 | 10 | && S_GET_SEGMENT (exp->X_add_symbol) != undefined_section |
14938 | 10 | && S_GET_SEGMENT (exp->X_add_symbol) != expr_section) |
14939 | 0 | section_symbol (S_GET_SEGMENT (exp->X_add_symbol)); |
14940 | 10 | exp->X_op = O_subtract; |
14941 | 10 | exp->X_op_symbol = GOT_symbol; |
14942 | 10 | if (i.reloc[this_operand] == BFD_RELOC_X86_64_GOTPCREL) |
14943 | 7 | i.reloc[this_operand] = BFD_RELOC_32_PCREL; |
14944 | 3 | else if (i.reloc[this_operand] == BFD_RELOC_X86_64_GOTOFF64) |
14945 | 3 | i.reloc[this_operand] = BFD_RELOC_64; |
14946 | 0 | else |
14947 | 0 | i.reloc[this_operand] = BFD_RELOC_32; |
14948 | 10 | } |
14949 | | |
14950 | 38.9k | else if (exp->X_op == O_absent |
14951 | 38.9k | || exp->X_op == O_illegal |
14952 | 38.9k | || exp->X_op == O_big) |
14953 | 493 | { |
14954 | 504 | inv_disp: |
14955 | 504 | as_bad (_("missing or invalid displacement expression `%s'"), |
14956 | 504 | disp_start); |
14957 | 504 | ret = 0; |
14958 | 504 | } |
14959 | | |
14960 | 38.4k | else if (exp->X_op == O_constant) |
14961 | 2.16k | { |
14962 | | /* Sizing gets taken care of by optimize_disp(). |
14963 | | |
14964 | | If not 64bit, sign/zero extend val, to account for wraparound |
14965 | | when !BFD64. */ |
14966 | 2.16k | if (expr_mode == expr_operator_present |
14967 | 2.16k | && flag_code != CODE_64BIT && !object_64bit) |
14968 | 0 | exp->X_add_number = extend_to_32bit_address (exp->X_add_number); |
14969 | 2.16k | } |
14970 | | |
14971 | | #ifdef OBJ_AOUT |
14972 | | else if (exp_seg != absolute_section |
14973 | | && exp_seg != text_section |
14974 | | && exp_seg != data_section |
14975 | | && exp_seg != bss_section |
14976 | | && exp_seg != undefined_section |
14977 | | && !bfd_is_com_section (exp_seg)) |
14978 | | { |
14979 | | as_bad (_("unimplemented segment %s in operand"), exp_seg->name); |
14980 | | ret = 0; |
14981 | | } |
14982 | | #endif |
14983 | | |
14984 | 36.2k | else if (current_templates.start->opcode_modifier.jump == JUMP_BYTE) |
14985 | 2 | i.types[this_operand].bitfield.disp8 = 1; |
14986 | | |
14987 | | /* Check if this is a displacement only operand. */ |
14988 | 38.9k | if (!i.types[this_operand].bitfield.baseindex) |
14989 | 38.9k | i.types[this_operand] = |
14990 | 38.9k | operand_type_or (operand_type_and_not (i.types[this_operand], anydisp), |
14991 | 38.9k | operand_type_and (i.types[this_operand], types)); |
14992 | | |
14993 | 38.9k | return ret; |
14994 | 38.9k | } |
14995 | | |
14996 | | /* Return the active addressing mode, taking address override and |
14997 | | registers forming the address into consideration. Update the |
14998 | | address override prefix if necessary. */ |
14999 | | |
15000 | | static enum flag_code |
15001 | | i386_addressing_mode (void) |
15002 | 76.8k | { |
15003 | 76.8k | enum flag_code addr_mode; |
15004 | | |
15005 | 76.8k | if (i.prefix[ADDR_PREFIX]) |
15006 | 0 | addr_mode = flag_code == CODE_32BIT ? CODE_16BIT : CODE_32BIT; |
15007 | 76.8k | else if (flag_code == CODE_16BIT |
15008 | 76.8k | && is_cpu (current_templates.start, CpuMPX) |
15009 | | /* Avoid replacing the "16-bit addressing not allowed" diagnostic |
15010 | | from md_assemble() by "is not a valid base/index expression" |
15011 | | when there is a base and/or index. */ |
15012 | 76.8k | && !i.types[this_operand].bitfield.baseindex) |
15013 | 0 | { |
15014 | | /* MPX insn memory operands with neither base nor index must be forced |
15015 | | to use 32-bit addressing in 16-bit mode. */ |
15016 | 0 | addr_mode = CODE_32BIT; |
15017 | 0 | i.prefix[ADDR_PREFIX] = ADDR_PREFIX_OPCODE; |
15018 | 0 | ++i.prefixes; |
15019 | 0 | gas_assert (!i.types[this_operand].bitfield.disp16); |
15020 | 0 | gas_assert (!i.types[this_operand].bitfield.disp32); |
15021 | 0 | } |
15022 | 76.8k | else |
15023 | 76.8k | { |
15024 | 76.8k | addr_mode = flag_code; |
15025 | | |
15026 | 76.8k | #if INFER_ADDR_PREFIX |
15027 | 76.8k | if (i.mem_operands == 0) |
15028 | 75.5k | { |
15029 | | /* Infer address prefix from the first memory operand. */ |
15030 | 75.5k | const reg_entry *addr_reg = i.base_reg; |
15031 | | |
15032 | 75.5k | if (addr_reg == NULL) |
15033 | 75.5k | addr_reg = i.index_reg; |
15034 | | |
15035 | 75.5k | if (addr_reg) |
15036 | 0 | { |
15037 | 0 | if (addr_reg->reg_type.bitfield.dword) |
15038 | 0 | addr_mode = CODE_32BIT; |
15039 | 0 | else if (flag_code != CODE_64BIT |
15040 | 0 | && addr_reg->reg_type.bitfield.word) |
15041 | 0 | addr_mode = CODE_16BIT; |
15042 | |
|
15043 | 0 | if (addr_mode != flag_code) |
15044 | 0 | { |
15045 | 0 | i.prefix[ADDR_PREFIX] = ADDR_PREFIX_OPCODE; |
15046 | 0 | i.prefixes += 1; |
15047 | | /* Change the size of any displacement too. At most one |
15048 | | of Disp16 or Disp32 is set. |
15049 | | FIXME. There doesn't seem to be any real need for |
15050 | | separate Disp16 and Disp32 flags. The same goes for |
15051 | | Imm16 and Imm32. Removing them would probably clean |
15052 | | up the code quite a lot. */ |
15053 | 0 | if (flag_code != CODE_64BIT |
15054 | 0 | && (i.types[this_operand].bitfield.disp16 |
15055 | 0 | || i.types[this_operand].bitfield.disp32)) |
15056 | 0 | { |
15057 | 0 | static const i386_operand_type disp16_32 = { |
15058 | 0 | .bitfield = { .disp16 = 1, .disp32 = 1 } |
15059 | 0 | }; |
15060 | |
|
15061 | 0 | i.types[this_operand] |
15062 | 0 | = operand_type_xor (i.types[this_operand], disp16_32); |
15063 | 0 | } |
15064 | 0 | } |
15065 | 0 | } |
15066 | 75.5k | } |
15067 | 76.8k | #endif |
15068 | 76.8k | } |
15069 | | |
15070 | 76.8k | return addr_mode; |
15071 | 76.8k | } |
15072 | | |
15073 | | /* Make sure the memory operand we've been dealt is valid. |
15074 | | Return 1 on success, 0 on a failure. */ |
15075 | | |
15076 | | static int |
15077 | | i386_index_check (const char *operand_string) |
15078 | 38.4k | { |
15079 | 38.4k | const char *kind = "base/index"; |
15080 | 38.4k | enum flag_code addr_mode = i386_addressing_mode (); |
15081 | 38.4k | const insn_template *t = current_templates.end - 1; |
15082 | | |
15083 | 38.4k | if (t->opcode_modifier.isstring) |
15084 | 6 | { |
15085 | | /* Memory operands of string insns are special in that they only allow |
15086 | | a single register (rDI or rSI) as their memory address. */ |
15087 | 6 | const reg_entry *expected_reg; |
15088 | 6 | static const char di_si[][2][4] = |
15089 | 6 | { |
15090 | 6 | { "esi", "edi" }, |
15091 | 6 | { "si", "di" }, |
15092 | 6 | { "rsi", "rdi" } |
15093 | 6 | }; |
15094 | | /* For a few other insns with fixed register addressing we (ab)use the |
15095 | | IsString attribute as well. */ |
15096 | 6 | static const char loregs[][4][4] = |
15097 | 6 | { |
15098 | 6 | { "eax", "ecx", "edx", "ebx" }, |
15099 | 6 | { "ax", "cx", "dx", "bx" }, |
15100 | 6 | { "rax", "rcx", "rdx", "rbx" } |
15101 | 6 | }; |
15102 | | |
15103 | 6 | kind = "string address"; |
15104 | | |
15105 | 6 | if (t->opcode_modifier.prefixok == PrefixRep) |
15106 | 6 | { |
15107 | 6 | int es_op = t->opcode_modifier.isstring - IS_STRING_ES_OP0; |
15108 | 6 | int op = 0; |
15109 | | |
15110 | 6 | if (!t->operand_types[0].bitfield.baseindex |
15111 | 6 | || ((!i.mem_operands != !intel_syntax) |
15112 | 6 | && t->operand_types[1].bitfield.baseindex)) |
15113 | 2 | op = 1; |
15114 | 6 | expected_reg = str_hash_find (reg_hash, |
15115 | 6 | di_si[addr_mode][op == es_op]); |
15116 | 6 | } |
15117 | 0 | else |
15118 | 0 | { |
15119 | 0 | unsigned int op = t->operand_types[0].bitfield.baseindex ? 0 : 1; |
15120 | |
|
15121 | 0 | if (!t->operand_types[op].bitfield.instance) |
15122 | 0 | return 1; /* Operand mismatch will be detected elsewhere. */ |
15123 | 0 | expected_reg |
15124 | 0 | = str_hash_find (reg_hash, |
15125 | 0 | loregs[addr_mode][t->operand_types[op] |
15126 | 0 | .bitfield.instance - 1]); |
15127 | 0 | } |
15128 | | |
15129 | 6 | if (i.base_reg != expected_reg |
15130 | 6 | || i.index_reg |
15131 | 6 | || operand_type_check (i.types[this_operand], disp)) |
15132 | 6 | { |
15133 | | /* The second memory operand must have the same size as |
15134 | | the first one. */ |
15135 | 6 | if (i.mem_operands |
15136 | 6 | && i.base_reg |
15137 | 6 | && !((addr_mode == CODE_64BIT |
15138 | 0 | && i.base_reg->reg_type.bitfield.qword) |
15139 | 0 | || (addr_mode == CODE_32BIT |
15140 | 0 | ? i.base_reg->reg_type.bitfield.dword |
15141 | 0 | : i.base_reg->reg_type.bitfield.word))) |
15142 | 0 | goto bad_address; |
15143 | | |
15144 | 6 | as_warn (_("`%s' is not valid here (expected `%c%s%s%c')"), |
15145 | 6 | operand_string, |
15146 | 6 | intel_syntax ? '[' : '(', |
15147 | 6 | register_prefix, |
15148 | 6 | expected_reg->reg_name, |
15149 | 6 | intel_syntax ? ']' : ')'); |
15150 | 6 | return 1; |
15151 | 6 | } |
15152 | 0 | else |
15153 | 0 | return 1; |
15154 | | |
15155 | 0 | bad_address: |
15156 | 0 | as_bad (_("`%s' is not a valid %s expression"), |
15157 | 0 | operand_string, kind); |
15158 | 0 | return 0; |
15159 | 6 | } |
15160 | 38.4k | else |
15161 | 38.4k | { |
15162 | 38.4k | t = current_templates.start; |
15163 | | |
15164 | 38.4k | if (addr_mode != CODE_16BIT) |
15165 | 37.6k | { |
15166 | | /* 32-bit/64-bit checks. */ |
15167 | 37.6k | if (pp.disp_encoding == disp_encoding_16bit) |
15168 | 0 | { |
15169 | 0 | bad_disp: |
15170 | 0 | as_bad (_("invalid `%s' prefix"), |
15171 | 0 | addr_mode == CODE_16BIT ? "{disp32}" : "{disp16}"); |
15172 | 0 | return 0; |
15173 | 0 | } |
15174 | | |
15175 | 37.6k | if ((i.base_reg |
15176 | 37.6k | && ((addr_mode == CODE_64BIT |
15177 | 0 | ? !i.base_reg->reg_type.bitfield.qword |
15178 | 0 | : !i.base_reg->reg_type.bitfield.dword) |
15179 | 0 | || (i.index_reg && i.base_reg->reg_num == RegIP) |
15180 | 0 | || i.base_reg->reg_num == RegIZ)) |
15181 | 37.6k | || (i.index_reg |
15182 | 37.6k | && !i.index_reg->reg_type.bitfield.xmmword |
15183 | 37.6k | && !i.index_reg->reg_type.bitfield.ymmword |
15184 | 37.6k | && !i.index_reg->reg_type.bitfield.zmmword |
15185 | 37.6k | && ((addr_mode == CODE_64BIT |
15186 | 0 | ? !i.index_reg->reg_type.bitfield.qword |
15187 | 0 | : !i.index_reg->reg_type.bitfield.dword) |
15188 | 0 | || !i.index_reg->reg_type.bitfield.baseindex))) |
15189 | 0 | goto bad_address; |
15190 | | |
15191 | | /* bndmk, bndldx, bndstx and mandatory non-vector SIB have special restrictions. */ |
15192 | 37.6k | if (t->mnem_off == MN_bndmk |
15193 | 37.6k | || t->mnem_off == MN_bndldx |
15194 | 37.6k | || t->mnem_off == MN_bndstx |
15195 | 37.6k | || t->opcode_modifier.sib == SIBMEM) |
15196 | 0 | { |
15197 | | /* They cannot use RIP-relative addressing. */ |
15198 | 0 | if (i.base_reg && i.base_reg->reg_num == RegIP) |
15199 | 0 | { |
15200 | 0 | as_bad (_("`%s' cannot be used here"), operand_string); |
15201 | 0 | return 0; |
15202 | 0 | } |
15203 | | |
15204 | | /* bndldx and bndstx ignore their scale factor. */ |
15205 | 0 | if ((t->mnem_off == MN_bndldx || t->mnem_off == MN_bndstx) |
15206 | 0 | && i.log2_scale_factor) |
15207 | 0 | as_warn (_("register scaling is being ignored here")); |
15208 | 0 | } |
15209 | 37.6k | } |
15210 | 811 | else |
15211 | 811 | { |
15212 | | /* 16-bit checks. */ |
15213 | 811 | if (pp.disp_encoding == disp_encoding_32bit) |
15214 | 0 | goto bad_disp; |
15215 | | |
15216 | 811 | if ((i.base_reg |
15217 | 811 | && (!i.base_reg->reg_type.bitfield.word |
15218 | 0 | || !i.base_reg->reg_type.bitfield.baseindex)) |
15219 | 811 | || (i.index_reg |
15220 | 811 | && (!i.index_reg->reg_type.bitfield.word |
15221 | 0 | || !i.index_reg->reg_type.bitfield.baseindex |
15222 | 0 | || !(i.base_reg |
15223 | 0 | && i.base_reg->reg_num < 6 |
15224 | 0 | && i.index_reg->reg_num >= 6 |
15225 | 0 | && i.log2_scale_factor == 0)))) |
15226 | 0 | goto bad_address; |
15227 | 811 | } |
15228 | 38.4k | } |
15229 | 38.4k | return 1; |
15230 | 38.4k | } |
15231 | | |
15232 | | /* Handle vector immediates. */ |
15233 | | |
15234 | | static int |
15235 | | RC_SAE_immediate (const char *imm_start) |
15236 | 39.0k | { |
15237 | 39.0k | const char *pstr = imm_start; |
15238 | | |
15239 | 39.0k | if (*pstr != '{') |
15240 | 39.0k | return 0; |
15241 | | |
15242 | 32 | pstr++; |
15243 | 32 | if (is_whitespace (*pstr)) |
15244 | 0 | pstr++; |
15245 | | |
15246 | 32 | pstr = RC_SAE_specifier (pstr); |
15247 | 32 | if (pstr == NULL) |
15248 | 32 | return 0; |
15249 | | |
15250 | 0 | if (is_whitespace (*pstr)) |
15251 | 0 | pstr++; |
15252 | |
|
15253 | 0 | if (*pstr++ != '}') |
15254 | 0 | { |
15255 | 0 | as_bad (_("Missing '}': '%s'"), imm_start); |
15256 | 0 | return 0; |
15257 | 0 | } |
15258 | 0 | /* RC/SAE immediate string should contain nothing more. */; |
15259 | 0 | if (*pstr != 0) |
15260 | 0 | { |
15261 | 0 | as_bad (_("Junk after '}': '%s'"), imm_start); |
15262 | 0 | return 0; |
15263 | 0 | } |
15264 | | |
15265 | | /* Internally this doesn't count as an operand. */ |
15266 | 0 | --i.operands; |
15267 | |
|
15268 | 0 | return 1; |
15269 | 0 | } |
15270 | | |
15271 | | static INLINE bool starts_memory_operand (char c) |
15272 | 39.0k | { |
15273 | 39.0k | return ISDIGIT (c) |
15274 | 39.0k | || is_name_beginner (c) |
15275 | 39.0k | || strchr ("([\"+-!~", c); |
15276 | 39.0k | } |
15277 | | |
15278 | | /* Parse OPERAND_STRING into the i386_insn structure I. Returns zero |
15279 | | on error. */ |
15280 | | |
15281 | | static int |
15282 | | i386_att_operand (char *operand_string) |
15283 | 44.4k | { |
15284 | 44.4k | const reg_entry *r; |
15285 | 44.4k | char *end_op; |
15286 | 44.4k | char *op_string = operand_string; |
15287 | | |
15288 | 44.4k | if (is_whitespace (*op_string)) |
15289 | 0 | ++op_string; |
15290 | | |
15291 | | /* We check for an absolute prefix (differentiating, |
15292 | | for example, 'jmp pc_relative_label' from 'jmp *absolute_label'. */ |
15293 | 44.4k | if (*op_string == ABSOLUTE_PREFIX |
15294 | 44.4k | && current_templates.start->opcode_modifier.jump) |
15295 | 16 | { |
15296 | 16 | ++op_string; |
15297 | 16 | if (is_whitespace (*op_string)) |
15298 | 0 | ++op_string; |
15299 | 16 | i.jumpabsolute = true; |
15300 | 16 | } |
15301 | | |
15302 | | /* Check if operand is a register. */ |
15303 | 44.4k | if ((r = parse_register (op_string, &end_op)) != NULL) |
15304 | 0 | { |
15305 | 0 | i386_operand_type temp; |
15306 | |
|
15307 | 0 | if (r == &bad_reg) |
15308 | 0 | return 0; |
15309 | | |
15310 | | /* Check for a segment override by searching for ':' after a |
15311 | | segment register. */ |
15312 | 0 | op_string = end_op; |
15313 | 0 | if (is_whitespace (*op_string)) |
15314 | 0 | ++op_string; |
15315 | 0 | if (*op_string == ':' && r->reg_type.bitfield.class == SReg) |
15316 | 0 | { |
15317 | 0 | i.seg[i.mem_operands] = r; |
15318 | | |
15319 | | /* Skip the ':' and whitespace. */ |
15320 | 0 | ++op_string; |
15321 | 0 | if (is_whitespace (*op_string)) |
15322 | 0 | ++op_string; |
15323 | | |
15324 | | /* Handle case of %es:*foo. */ |
15325 | 0 | if (!i.jumpabsolute && *op_string == ABSOLUTE_PREFIX |
15326 | 0 | && current_templates.start->opcode_modifier.jump) |
15327 | 0 | { |
15328 | 0 | ++op_string; |
15329 | 0 | if (is_whitespace (*op_string)) |
15330 | 0 | ++op_string; |
15331 | 0 | i.jumpabsolute = true; |
15332 | 0 | } |
15333 | |
|
15334 | 0 | if (!starts_memory_operand (*op_string)) |
15335 | 0 | { |
15336 | 0 | as_bad (_("bad memory operand `%s'"), op_string); |
15337 | 0 | return 0; |
15338 | 0 | } |
15339 | 0 | goto do_memory_reference; |
15340 | 0 | } |
15341 | | |
15342 | | /* Handle vector operations. */ |
15343 | 0 | if (*op_string == '{') |
15344 | 0 | { |
15345 | 0 | op_string = check_VecOperations (op_string); |
15346 | 0 | if (op_string == NULL) |
15347 | 0 | return 0; |
15348 | 0 | } |
15349 | | |
15350 | 0 | if (*op_string) |
15351 | 0 | { |
15352 | 0 | as_bad (_("junk `%s' after register"), op_string); |
15353 | 0 | return 0; |
15354 | 0 | } |
15355 | | |
15356 | | /* Reject pseudo registers for .insn. */ |
15357 | 0 | if (dot_insn () && r->reg_type.bitfield.class == ClassNone) |
15358 | 0 | { |
15359 | 0 | as_bad (_("`%s%s' cannot be used here"), |
15360 | 0 | register_prefix, r->reg_name); |
15361 | 0 | return 0; |
15362 | 0 | } |
15363 | | |
15364 | 0 | temp = r->reg_type; |
15365 | 0 | temp.bitfield.baseindex = 0; |
15366 | 0 | i.types[this_operand] = operand_type_or (i.types[this_operand], |
15367 | 0 | temp); |
15368 | 0 | i.types[this_operand].bitfield.unspecified = 0; |
15369 | 0 | i.op[this_operand].regs = r; |
15370 | 0 | i.reg_operands++; |
15371 | | |
15372 | | /* A GPR may follow an RC or SAE immediate only if a (vector) register |
15373 | | operand was also present earlier on. */ |
15374 | 0 | if (i.rounding.type != rc_none && temp.bitfield.class == Reg |
15375 | 0 | && i.reg_operands == 1) |
15376 | 0 | { |
15377 | 0 | unsigned int j; |
15378 | |
|
15379 | 0 | for (j = 0; j < ARRAY_SIZE (RC_NamesTable); ++j) |
15380 | 0 | if (i.rounding.type == RC_NamesTable[j].type) |
15381 | 0 | break; |
15382 | 0 | as_bad (_("`%s': misplaced `{%s}'"), |
15383 | 0 | insn_name (current_templates.start), RC_NamesTable[j].name); |
15384 | 0 | return 0; |
15385 | 0 | } |
15386 | 0 | } |
15387 | 44.4k | else if (*op_string == REGISTER_PREFIX) |
15388 | 25 | { |
15389 | 25 | as_bad (_("bad register name `%s'"), op_string); |
15390 | 25 | return 0; |
15391 | 25 | } |
15392 | 44.3k | else if (*op_string == IMMEDIATE_PREFIX) |
15393 | 5.32k | { |
15394 | 5.32k | ++op_string; |
15395 | 5.32k | if (i.jumpabsolute) |
15396 | 0 | { |
15397 | 0 | as_bad (_("immediate operand illegal with absolute jump")); |
15398 | 0 | return 0; |
15399 | 0 | } |
15400 | 5.32k | if (!i386_immediate (op_string)) |
15401 | 145 | return 0; |
15402 | 5.18k | if (i.rounding.type != rc_none) |
15403 | 0 | { |
15404 | 0 | as_bad (_("`%s': RC/SAE operand must follow immediate operands"), |
15405 | 0 | insn_name (current_templates.start)); |
15406 | 0 | return 0; |
15407 | 0 | } |
15408 | 5.18k | } |
15409 | 39.0k | else if (RC_SAE_immediate (operand_string)) |
15410 | 0 | { |
15411 | | /* If it is a RC or SAE immediate, do the necessary placement check: |
15412 | | Only another immediate or a GPR may precede it. */ |
15413 | 0 | if (i.mem_operands || i.reg_operands + i.imm_operands > 1 |
15414 | 0 | || (i.reg_operands == 1 |
15415 | 0 | && i.op[0].regs->reg_type.bitfield.class != Reg)) |
15416 | 0 | { |
15417 | 0 | as_bad (_("`%s': misplaced `%s'"), |
15418 | 0 | insn_name (current_templates.start), operand_string); |
15419 | 0 | return 0; |
15420 | 0 | } |
15421 | 0 | } |
15422 | 39.0k | else if (starts_memory_operand (*op_string)) |
15423 | 39.0k | { |
15424 | | /* This is a memory reference of some sort. */ |
15425 | 39.0k | char *base_string; |
15426 | | |
15427 | | /* Start and end of displacement string expression (if found). */ |
15428 | 39.0k | char *displacement_string_start; |
15429 | 39.0k | char *displacement_string_end; |
15430 | | |
15431 | 39.0k | do_memory_reference: |
15432 | | /* Check for base index form. We detect the base index form by |
15433 | | looking for an ')' at the end of the operand, searching |
15434 | | for the '(' matching it, and finding a REGISTER_PREFIX or ',' |
15435 | | after the '('. */ |
15436 | 39.0k | base_string = op_string + strlen (op_string); |
15437 | | |
15438 | | /* Handle vector operations. */ |
15439 | 39.0k | --base_string; |
15440 | 39.0k | if (is_whitespace (*base_string)) |
15441 | 272 | --base_string; |
15442 | | |
15443 | 39.0k | if (*base_string == '}') |
15444 | 57 | { |
15445 | 57 | char *vop_start = NULL; |
15446 | | |
15447 | 3.27k | while (base_string-- > op_string) |
15448 | 3.22k | { |
15449 | 3.22k | if (*base_string == '"') |
15450 | 0 | break; |
15451 | 3.22k | if (*base_string != '{') |
15452 | 3.20k | continue; |
15453 | | |
15454 | 12 | vop_start = base_string; |
15455 | | |
15456 | 12 | --base_string; |
15457 | 12 | if (is_whitespace (*base_string)) |
15458 | 0 | --base_string; |
15459 | | |
15460 | 12 | if (*base_string != '}') |
15461 | 0 | break; |
15462 | | |
15463 | 12 | vop_start = NULL; |
15464 | 12 | } |
15465 | | |
15466 | 57 | if (!vop_start) |
15467 | 57 | { |
15468 | 57 | as_bad (_("unbalanced figure braces")); |
15469 | 57 | return 0; |
15470 | 57 | } |
15471 | | |
15472 | 0 | if (check_VecOperations (vop_start) == NULL) |
15473 | 0 | return 0; |
15474 | 0 | } |
15475 | | |
15476 | | /* If we only have a displacement, set-up for it to be parsed later. */ |
15477 | 38.9k | displacement_string_start = op_string; |
15478 | 38.9k | displacement_string_end = base_string + 1; |
15479 | | |
15480 | 38.9k | if (*base_string == ')') |
15481 | 62 | { |
15482 | 62 | char *temp_string; |
15483 | 62 | unsigned int parens_not_balanced = 0; |
15484 | 62 | bool in_quotes = false; |
15485 | | |
15486 | | /* We've already checked that the number of left & right ()'s are |
15487 | | equal, and that there's a matching set of double quotes. */ |
15488 | 62 | end_op = base_string; |
15489 | 1.45k | for (temp_string = op_string; temp_string < end_op; temp_string++) |
15490 | 1.38k | { |
15491 | 1.38k | if (*temp_string == '\\' && temp_string[1] == '"') |
15492 | 0 | ++temp_string; |
15493 | 1.38k | else if (*temp_string == '"') |
15494 | 20 | in_quotes = !in_quotes; |
15495 | 1.36k | else if (!in_quotes) |
15496 | 1.36k | { |
15497 | 1.36k | if (*temp_string == '(' && !parens_not_balanced++) |
15498 | 63 | base_string = temp_string; |
15499 | 1.36k | if (*temp_string == ')') |
15500 | 2 | --parens_not_balanced; |
15501 | 1.36k | } |
15502 | 1.38k | } |
15503 | | |
15504 | 62 | temp_string = base_string; |
15505 | | |
15506 | | /* Skip past '(' and whitespace. */ |
15507 | 62 | gas_assert (*base_string == '('); |
15508 | 62 | ++base_string; |
15509 | 62 | if (is_whitespace (*base_string)) |
15510 | 24 | ++base_string; |
15511 | | |
15512 | 62 | if (*base_string == ',' |
15513 | 62 | || ((i.base_reg = parse_register (base_string, &end_op)) |
15514 | 44 | != NULL)) |
15515 | 18 | { |
15516 | 18 | displacement_string_end = temp_string; |
15517 | | |
15518 | 18 | i.types[this_operand].bitfield.baseindex = 1; |
15519 | | |
15520 | 18 | if (i.base_reg) |
15521 | 0 | { |
15522 | 0 | if (i.base_reg == &bad_reg) |
15523 | 0 | return 0; |
15524 | 0 | base_string = end_op; |
15525 | 0 | if (is_whitespace (*base_string)) |
15526 | 0 | ++base_string; |
15527 | 0 | } |
15528 | | |
15529 | | /* There may be an index reg or scale factor here. */ |
15530 | 18 | if (*base_string == ',') |
15531 | 18 | { |
15532 | 18 | ++base_string; |
15533 | 18 | if (is_whitespace (*base_string)) |
15534 | 0 | ++base_string; |
15535 | | |
15536 | 18 | if ((i.index_reg = parse_register (base_string, &end_op)) |
15537 | 18 | != NULL) |
15538 | 0 | { |
15539 | 0 | if (i.index_reg == &bad_reg) |
15540 | 0 | return 0; |
15541 | 0 | base_string = end_op; |
15542 | 0 | if (is_whitespace (*base_string)) |
15543 | 0 | ++base_string; |
15544 | 0 | if (*base_string == ',') |
15545 | 0 | { |
15546 | 0 | ++base_string; |
15547 | 0 | if (is_whitespace (*base_string)) |
15548 | 0 | ++base_string; |
15549 | 0 | } |
15550 | 0 | else if (*base_string != ')') |
15551 | 0 | { |
15552 | 0 | as_bad (_("expecting `,' or `)' " |
15553 | 0 | "after index register in `%s'"), |
15554 | 0 | operand_string); |
15555 | 0 | return 0; |
15556 | 0 | } |
15557 | 0 | } |
15558 | 18 | else if (*base_string == REGISTER_PREFIX) |
15559 | 0 | { |
15560 | 0 | end_op = strchr (base_string, ','); |
15561 | 0 | if (end_op) |
15562 | 0 | *end_op = '\0'; |
15563 | 0 | as_bad (_("bad register name `%s'"), base_string); |
15564 | 0 | return 0; |
15565 | 0 | } |
15566 | | |
15567 | | /* Check for scale factor. */ |
15568 | 18 | if (*base_string != ')') |
15569 | 18 | { |
15570 | 18 | char *end_scale = i386_scale (base_string); |
15571 | | |
15572 | 18 | if (!end_scale) |
15573 | 18 | return 0; |
15574 | | |
15575 | 0 | base_string = end_scale; |
15576 | 0 | if (is_whitespace (*base_string)) |
15577 | 0 | ++base_string; |
15578 | 0 | if (*base_string != ')') |
15579 | 0 | { |
15580 | 0 | as_bad (_("expecting `)' " |
15581 | 0 | "after scale factor in `%s'"), |
15582 | 0 | operand_string); |
15583 | 0 | return 0; |
15584 | 0 | } |
15585 | 0 | } |
15586 | 0 | else if (!i.index_reg) |
15587 | 0 | { |
15588 | 0 | as_bad (_("expecting index register or scale factor " |
15589 | 0 | "after `,'; got '%c'"), |
15590 | 0 | *base_string); |
15591 | 0 | return 0; |
15592 | 0 | } |
15593 | 18 | } |
15594 | 0 | else if (*base_string != ')') |
15595 | 0 | { |
15596 | 0 | as_bad (_("expecting `,' or `)' " |
15597 | 0 | "after base register in `%s'"), |
15598 | 0 | operand_string); |
15599 | 0 | return 0; |
15600 | 0 | } |
15601 | 18 | } |
15602 | 44 | else if (*base_string == REGISTER_PREFIX) |
15603 | 0 | { |
15604 | 0 | end_op = strchr (base_string, ','); |
15605 | 0 | if (end_op) |
15606 | 0 | *end_op = '\0'; |
15607 | 0 | as_bad (_("bad register name `%s'"), base_string); |
15608 | 0 | return 0; |
15609 | 0 | } |
15610 | 62 | } |
15611 | | |
15612 | | /* If there's an expression beginning the operand, parse it, |
15613 | | assuming displacement_string_start and |
15614 | | displacement_string_end are meaningful. */ |
15615 | 38.9k | if (displacement_string_start != displacement_string_end) |
15616 | 38.9k | { |
15617 | 38.9k | if (!i386_displacement (displacement_string_start, |
15618 | 38.9k | displacement_string_end)) |
15619 | 504 | return 0; |
15620 | 38.9k | } |
15621 | | |
15622 | | /* Special case for (%dx) while doing input/output op. */ |
15623 | 38.4k | if (i.base_reg |
15624 | 38.4k | && i.base_reg->reg_type.bitfield.instance == RegD |
15625 | 38.4k | && i.base_reg->reg_type.bitfield.word |
15626 | 38.4k | && i.index_reg == 0 |
15627 | 38.4k | && i.log2_scale_factor == 0 |
15628 | 38.4k | && i.seg[i.mem_operands] == 0 |
15629 | 38.4k | && !operand_type_check (i.types[this_operand], disp)) |
15630 | 0 | { |
15631 | 0 | i.types[this_operand] = i.base_reg->reg_type; |
15632 | 0 | i.op[this_operand].regs = i.base_reg; |
15633 | 0 | i.base_reg = NULL; |
15634 | 0 | i.input_output_operand = true; |
15635 | 0 | return 1; |
15636 | 0 | } |
15637 | | |
15638 | 38.4k | if (i386_index_check (operand_string) == 0) |
15639 | 0 | return 0; |
15640 | 38.4k | i.flags[this_operand] |= Operand_Mem; |
15641 | 38.4k | i.mem_operands++; |
15642 | 38.4k | } |
15643 | 47 | else |
15644 | 47 | { |
15645 | | /* It's not a memory operand; argh! */ |
15646 | 47 | as_bad (_("invalid char %s beginning operand %d `%s'"), |
15647 | 47 | output_invalid (*op_string), |
15648 | 47 | this_operand + 1, |
15649 | 47 | op_string); |
15650 | 47 | return 0; |
15651 | 47 | } |
15652 | 43.6k | return 1; /* Normal return. */ |
15653 | 44.4k | } |
15654 | | |
15655 | | /* Calculate the maximum variable size (i.e., excluding fr_fix) |
15656 | | that an rs_machine_dependent frag may reach. */ |
15657 | | |
15658 | | unsigned int |
15659 | | i386_frag_max_var (fragS *frag) |
15660 | 0 | { |
15661 | | /* The only relaxable frags are for jumps. |
15662 | | Unconditional jumps can grow by 4 bytes and others by 5 bytes. */ |
15663 | 0 | gas_assert (frag->fr_type == rs_machine_dependent); |
15664 | 0 | return TYPE_FROM_RELAX_STATE (frag->fr_subtype) == UNCOND_JUMP ? 4 : 5; |
15665 | 0 | } |
15666 | | |
15667 | | #ifdef OBJ_ELF |
15668 | | static int |
15669 | | elf_symbol_resolved_in_segment_p (symbolS *fr_symbol, offsetT fr_var) |
15670 | 0 | { |
15671 | | /* STT_GNU_IFUNC symbol must go through PLT. */ |
15672 | 0 | if ((symbol_get_bfdsym (fr_symbol)->flags |
15673 | 0 | & BSF_GNU_INDIRECT_FUNCTION) != 0) |
15674 | 0 | return 0; |
15675 | | |
15676 | 0 | if (!S_IS_EXTERNAL (fr_symbol)) |
15677 | | /* Symbol may be weak or local. */ |
15678 | 0 | return !S_IS_WEAK (fr_symbol); |
15679 | | |
15680 | | /* Global symbols with non-default visibility can't be preempted. */ |
15681 | 0 | if (ELF_ST_VISIBILITY (S_GET_OTHER (fr_symbol)) != STV_DEFAULT) |
15682 | 0 | return 1; |
15683 | | |
15684 | 0 | if (fr_var != NO_RELOC) |
15685 | 0 | switch ((enum bfd_reloc_code_real) fr_var) |
15686 | 0 | { |
15687 | 0 | case BFD_RELOC_386_PLT32: |
15688 | 0 | case BFD_RELOC_X86_64_PLT32: |
15689 | | /* Symbol with PLT relocation may be preempted. */ |
15690 | 0 | return 0; |
15691 | 0 | default: |
15692 | 0 | abort (); |
15693 | 0 | } |
15694 | | |
15695 | | /* Global symbols with default visibility in a shared library may be |
15696 | | preempted by another definition. */ |
15697 | 0 | return !shared; |
15698 | 0 | } |
15699 | | #endif |
15700 | | |
15701 | | /* Table 3-2. Macro-Fusible Instructions in Haswell Microarchitecture |
15702 | | Note also work for Skylake and Cascadelake. |
15703 | | --------------------------------------------------------------------- |
15704 | | | JCC | ADD/SUB/CMP | INC/DEC | TEST/AND | |
15705 | | | ------ | ----------- | ------- | -------- | |
15706 | | | Jo | N | N | Y | |
15707 | | | Jno | N | N | Y | |
15708 | | | Jc/Jb | Y | N | Y | |
15709 | | | Jae/Jnb | Y | N | Y | |
15710 | | | Je/Jz | Y | Y | Y | |
15711 | | | Jne/Jnz | Y | Y | Y | |
15712 | | | Jna/Jbe | Y | N | Y | |
15713 | | | Ja/Jnbe | Y | N | Y | |
15714 | | | Js | N | N | Y | |
15715 | | | Jns | N | N | Y | |
15716 | | | Jp/Jpe | N | N | Y | |
15717 | | | Jnp/Jpo | N | N | Y | |
15718 | | | Jl/Jnge | Y | Y | Y | |
15719 | | | Jge/Jnl | Y | Y | Y | |
15720 | | | Jle/Jng | Y | Y | Y | |
15721 | | | Jg/Jnle | Y | Y | Y | |
15722 | | --------------------------------------------------------------------- */ |
15723 | | static int |
15724 | | i386_macro_fusible_p (enum mf_cmp_kind mf_cmp, enum mf_jcc_kind mf_jcc) |
15725 | 0 | { |
15726 | 0 | if (mf_cmp == mf_cmp_alu_cmp) |
15727 | 0 | return ((mf_jcc >= mf_jcc_jc && mf_jcc <= mf_jcc_jna) |
15728 | 0 | || mf_jcc == mf_jcc_jl || mf_jcc == mf_jcc_jle); |
15729 | 0 | if (mf_cmp == mf_cmp_incdec) |
15730 | 0 | return (mf_jcc == mf_jcc_je || mf_jcc == mf_jcc_jl |
15731 | 0 | || mf_jcc == mf_jcc_jle); |
15732 | 0 | if (mf_cmp == mf_cmp_test_and) |
15733 | 0 | return 1; |
15734 | 0 | return 0; |
15735 | 0 | } |
15736 | | |
15737 | | /* Return the next non-empty frag. */ |
15738 | | |
15739 | | static fragS * |
15740 | | i386_next_non_empty_frag (fragS *fragP) |
15741 | 0 | { |
15742 | | /* There may be a frag with a ".fill 0" when there is no room in |
15743 | | the current frag for frag_grow in output_insn. */ |
15744 | 0 | for (fragP = fragP->fr_next; |
15745 | 0 | (fragP != NULL |
15746 | 0 | && fragP->fr_type == rs_fill |
15747 | 0 | && fragP->fr_fix == 0); |
15748 | 0 | fragP = fragP->fr_next) |
15749 | 0 | ; |
15750 | 0 | return fragP; |
15751 | 0 | } |
15752 | | |
15753 | | /* Return the next jcc frag after BRANCH_PADDING. */ |
15754 | | |
15755 | | static fragS * |
15756 | | i386_next_fusible_jcc_frag (fragS *maybe_cmp_fragP, fragS *pad_fragP) |
15757 | 0 | { |
15758 | 0 | fragS *branch_fragP; |
15759 | 0 | if (!pad_fragP) |
15760 | 0 | return NULL; |
15761 | | |
15762 | 0 | if (pad_fragP->fr_type == rs_machine_dependent |
15763 | 0 | && (TYPE_FROM_RELAX_STATE (pad_fragP->fr_subtype) |
15764 | 0 | == BRANCH_PADDING)) |
15765 | 0 | { |
15766 | 0 | branch_fragP = i386_next_non_empty_frag (pad_fragP); |
15767 | 0 | if (branch_fragP->fr_type != rs_machine_dependent) |
15768 | 0 | return NULL; |
15769 | 0 | if (TYPE_FROM_RELAX_STATE (branch_fragP->fr_subtype) == COND_JUMP |
15770 | 0 | && i386_macro_fusible_p (maybe_cmp_fragP->tc_frag_data.mf_type, |
15771 | 0 | pad_fragP->tc_frag_data.mf_type)) |
15772 | 0 | return branch_fragP; |
15773 | 0 | } |
15774 | | |
15775 | 0 | return NULL; |
15776 | 0 | } |
15777 | | |
15778 | | /* Classify BRANCH_PADDING, BRANCH_PREFIX and FUSED_JCC_PADDING frags. */ |
15779 | | |
15780 | | static void |
15781 | | i386_classify_machine_dependent_frag (fragS *fragP) |
15782 | 0 | { |
15783 | 0 | fragS *cmp_fragP; |
15784 | 0 | fragS *pad_fragP; |
15785 | 0 | fragS *branch_fragP; |
15786 | 0 | fragS *next_fragP; |
15787 | 0 | unsigned int max_prefix_length; |
15788 | |
|
15789 | 0 | if (fragP->tc_frag_data.classified) |
15790 | 0 | return; |
15791 | | |
15792 | | /* First scan for BRANCH_PADDING and FUSED_JCC_PADDING. Convert |
15793 | | FUSED_JCC_PADDING and merge BRANCH_PADDING. */ |
15794 | 0 | for (next_fragP = fragP; |
15795 | 0 | next_fragP != NULL; |
15796 | 0 | next_fragP = next_fragP->fr_next) |
15797 | 0 | { |
15798 | 0 | next_fragP->tc_frag_data.classified = 1; |
15799 | 0 | if (next_fragP->fr_type == rs_machine_dependent) |
15800 | 0 | switch (TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype)) |
15801 | 0 | { |
15802 | 0 | case BRANCH_PADDING: |
15803 | | /* The BRANCH_PADDING frag must be followed by a branch |
15804 | | frag. */ |
15805 | 0 | branch_fragP = i386_next_non_empty_frag (next_fragP); |
15806 | 0 | next_fragP->tc_frag_data.u.branch_fragP = branch_fragP; |
15807 | 0 | break; |
15808 | 0 | case FUSED_JCC_PADDING: |
15809 | | /* Check if this is a fused jcc: |
15810 | | FUSED_JCC_PADDING |
15811 | | CMP like instruction |
15812 | | BRANCH_PADDING |
15813 | | COND_JUMP |
15814 | | */ |
15815 | 0 | cmp_fragP = i386_next_non_empty_frag (next_fragP); |
15816 | 0 | pad_fragP = i386_next_non_empty_frag (cmp_fragP); |
15817 | 0 | branch_fragP = i386_next_fusible_jcc_frag (next_fragP, pad_fragP); |
15818 | 0 | if (branch_fragP) |
15819 | 0 | { |
15820 | | /* The BRANCH_PADDING frag is merged with the |
15821 | | FUSED_JCC_PADDING frag. */ |
15822 | 0 | next_fragP->tc_frag_data.u.branch_fragP = branch_fragP; |
15823 | | /* CMP like instruction size. */ |
15824 | 0 | next_fragP->tc_frag_data.cmp_size = cmp_fragP->fr_fix; |
15825 | 0 | frag_wane (pad_fragP); |
15826 | | /* Skip to branch_fragP. */ |
15827 | 0 | next_fragP = branch_fragP; |
15828 | 0 | } |
15829 | 0 | else if (next_fragP->tc_frag_data.max_prefix_length) |
15830 | 0 | { |
15831 | | /* Turn FUSED_JCC_PADDING into BRANCH_PREFIX if it isn't |
15832 | | a fused jcc. */ |
15833 | 0 | next_fragP->fr_subtype |
15834 | 0 | = ENCODE_RELAX_STATE (BRANCH_PREFIX, 0); |
15835 | 0 | next_fragP->tc_frag_data.max_bytes |
15836 | 0 | = next_fragP->tc_frag_data.max_prefix_length; |
15837 | | /* This will be updated in the BRANCH_PREFIX scan. */ |
15838 | 0 | next_fragP->tc_frag_data.max_prefix_length = 0; |
15839 | 0 | } |
15840 | 0 | else |
15841 | 0 | frag_wane (next_fragP); |
15842 | 0 | break; |
15843 | 0 | } |
15844 | 0 | } |
15845 | | |
15846 | | /* Stop if there is no BRANCH_PREFIX. */ |
15847 | 0 | if (!align_branch_prefix_size) |
15848 | 0 | return; |
15849 | | |
15850 | | /* Scan for BRANCH_PREFIX. */ |
15851 | 0 | for (; fragP != NULL; fragP = fragP->fr_next) |
15852 | 0 | { |
15853 | 0 | if (fragP->fr_type != rs_machine_dependent |
15854 | 0 | || (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) |
15855 | 0 | != BRANCH_PREFIX)) |
15856 | 0 | continue; |
15857 | | |
15858 | | /* Count all BRANCH_PREFIX frags before BRANCH_PADDING and |
15859 | | COND_JUMP_PREFIX. */ |
15860 | 0 | max_prefix_length = 0; |
15861 | 0 | for (next_fragP = fragP; |
15862 | 0 | next_fragP != NULL; |
15863 | 0 | next_fragP = next_fragP->fr_next) |
15864 | 0 | { |
15865 | 0 | if (next_fragP->fr_type == rs_fill) |
15866 | | /* Skip rs_fill frags. */ |
15867 | 0 | continue; |
15868 | 0 | else if (next_fragP->fr_type != rs_machine_dependent) |
15869 | | /* Stop for all other frags. */ |
15870 | 0 | break; |
15871 | | |
15872 | | /* rs_machine_dependent frags. */ |
15873 | 0 | if (TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype) |
15874 | 0 | == BRANCH_PREFIX) |
15875 | 0 | { |
15876 | | /* Count BRANCH_PREFIX frags. */ |
15877 | 0 | if (max_prefix_length >= MAX_FUSED_JCC_PADDING_SIZE) |
15878 | 0 | { |
15879 | 0 | max_prefix_length = MAX_FUSED_JCC_PADDING_SIZE; |
15880 | 0 | frag_wane (next_fragP); |
15881 | 0 | } |
15882 | 0 | else |
15883 | 0 | max_prefix_length |
15884 | 0 | += next_fragP->tc_frag_data.max_bytes; |
15885 | 0 | } |
15886 | 0 | else if ((TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype) |
15887 | 0 | == BRANCH_PADDING) |
15888 | 0 | || (TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype) |
15889 | 0 | == FUSED_JCC_PADDING)) |
15890 | 0 | { |
15891 | | /* Stop at BRANCH_PADDING and FUSED_JCC_PADDING. */ |
15892 | 0 | fragP->tc_frag_data.u.padding_fragP = next_fragP; |
15893 | 0 | break; |
15894 | 0 | } |
15895 | 0 | else |
15896 | | /* Stop for other rs_machine_dependent frags. */ |
15897 | 0 | break; |
15898 | 0 | } |
15899 | |
|
15900 | 0 | fragP->tc_frag_data.max_prefix_length = max_prefix_length; |
15901 | | |
15902 | | /* Skip to the next frag. */ |
15903 | 0 | fragP = next_fragP; |
15904 | 0 | } |
15905 | 0 | } |
15906 | | |
15907 | | /* Compute padding size for |
15908 | | |
15909 | | FUSED_JCC_PADDING |
15910 | | CMP like instruction |
15911 | | BRANCH_PADDING |
15912 | | COND_JUMP/UNCOND_JUMP |
15913 | | |
15914 | | or |
15915 | | |
15916 | | BRANCH_PADDING |
15917 | | COND_JUMP/UNCOND_JUMP |
15918 | | */ |
15919 | | |
15920 | | static int |
15921 | | i386_branch_padding_size (fragS *fragP, offsetT address) |
15922 | 0 | { |
15923 | 0 | unsigned int offset, size, padding_size; |
15924 | 0 | fragS *branch_fragP = fragP->tc_frag_data.u.branch_fragP; |
15925 | | |
15926 | | /* The start address of the BRANCH_PADDING or FUSED_JCC_PADDING frag. */ |
15927 | 0 | if (!address) |
15928 | 0 | address = fragP->fr_address; |
15929 | 0 | address += fragP->fr_fix; |
15930 | | |
15931 | | /* CMP like instrunction size. */ |
15932 | 0 | size = fragP->tc_frag_data.cmp_size; |
15933 | | |
15934 | | /* The base size of the branch frag. */ |
15935 | 0 | size += branch_fragP->fr_fix; |
15936 | | |
15937 | | /* Add opcode and displacement bytes for the rs_machine_dependent |
15938 | | branch frag. */ |
15939 | 0 | if (branch_fragP->fr_type == rs_machine_dependent) |
15940 | 0 | size += md_relax_table[branch_fragP->fr_subtype].rlx_length; |
15941 | | |
15942 | | /* Check if branch is within boundary and doesn't end at the last |
15943 | | byte. */ |
15944 | 0 | offset = address & ((1U << align_branch_power) - 1); |
15945 | 0 | if ((offset + size) >= (1U << align_branch_power)) |
15946 | | /* Padding needed to avoid crossing boundary. */ |
15947 | 0 | padding_size = (1U << align_branch_power) - offset; |
15948 | 0 | else |
15949 | | /* No padding needed. */ |
15950 | 0 | padding_size = 0; |
15951 | | |
15952 | | /* The return value may be saved in tc_frag_data.length which is |
15953 | | unsigned byte. */ |
15954 | 0 | if (!fits_in_unsigned_byte (padding_size)) |
15955 | 0 | abort (); |
15956 | | |
15957 | 0 | return padding_size; |
15958 | 0 | } |
15959 | | |
15960 | | /* i386_generic_table_relax_frag() |
15961 | | |
15962 | | Handle BRANCH_PADDING, BRANCH_PREFIX and FUSED_JCC_PADDING frags to |
15963 | | grow/shrink padding to align branch frags. Hand others to |
15964 | | relax_frag(). */ |
15965 | | |
15966 | | long |
15967 | | i386_generic_table_relax_frag (segT segment, fragS *fragP, long stretch) |
15968 | 0 | { |
15969 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PADDING |
15970 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == FUSED_JCC_PADDING) |
15971 | 0 | { |
15972 | 0 | long padding_size = i386_branch_padding_size (fragP, 0); |
15973 | 0 | long grow = padding_size - fragP->tc_frag_data.length; |
15974 | | |
15975 | | /* When the BRANCH_PREFIX frag is used, the computed address |
15976 | | must match the actual address and there should be no padding. */ |
15977 | 0 | if (fragP->tc_frag_data.padding_address |
15978 | 0 | && (fragP->tc_frag_data.padding_address != fragP->fr_address |
15979 | 0 | || padding_size)) |
15980 | 0 | abort (); |
15981 | | |
15982 | | /* Update the padding size. */ |
15983 | 0 | if (grow) |
15984 | 0 | fragP->tc_frag_data.length = padding_size; |
15985 | |
|
15986 | 0 | return grow; |
15987 | 0 | } |
15988 | 0 | else if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PREFIX) |
15989 | 0 | { |
15990 | 0 | fragS *padding_fragP, *next_fragP; |
15991 | 0 | long padding_size, left_size, last_size; |
15992 | |
|
15993 | 0 | padding_fragP = fragP->tc_frag_data.u.padding_fragP; |
15994 | 0 | if (!padding_fragP) |
15995 | | /* Use the padding set by the leading BRANCH_PREFIX frag. */ |
15996 | 0 | return (fragP->tc_frag_data.length |
15997 | 0 | - fragP->tc_frag_data.last_length); |
15998 | | |
15999 | | /* Compute the relative address of the padding frag in the very |
16000 | | first time where the BRANCH_PREFIX frag sizes are zero. */ |
16001 | 0 | if (!fragP->tc_frag_data.padding_address) |
16002 | 0 | fragP->tc_frag_data.padding_address |
16003 | 0 | = padding_fragP->fr_address - (fragP->fr_address - stretch); |
16004 | | |
16005 | | /* First update the last length from the previous interation. */ |
16006 | 0 | left_size = fragP->tc_frag_data.prefix_length; |
16007 | 0 | for (next_fragP = fragP; |
16008 | 0 | next_fragP != padding_fragP; |
16009 | 0 | next_fragP = next_fragP->fr_next) |
16010 | 0 | if (next_fragP->fr_type == rs_machine_dependent |
16011 | 0 | && (TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype) |
16012 | 0 | == BRANCH_PREFIX)) |
16013 | 0 | { |
16014 | 0 | if (left_size) |
16015 | 0 | { |
16016 | 0 | int max = next_fragP->tc_frag_data.max_bytes; |
16017 | 0 | if (max) |
16018 | 0 | { |
16019 | 0 | int size; |
16020 | 0 | if (max > left_size) |
16021 | 0 | size = left_size; |
16022 | 0 | else |
16023 | 0 | size = max; |
16024 | 0 | left_size -= size; |
16025 | 0 | next_fragP->tc_frag_data.last_length = size; |
16026 | 0 | } |
16027 | 0 | } |
16028 | 0 | else |
16029 | 0 | next_fragP->tc_frag_data.last_length = 0; |
16030 | 0 | } |
16031 | | |
16032 | | /* Check the padding size for the padding frag. */ |
16033 | 0 | padding_size = i386_branch_padding_size |
16034 | 0 | (padding_fragP, (fragP->fr_address |
16035 | 0 | + fragP->tc_frag_data.padding_address)); |
16036 | |
|
16037 | 0 | last_size = fragP->tc_frag_data.prefix_length; |
16038 | | /* Check if there is change from the last interation. */ |
16039 | 0 | if (padding_size == last_size) |
16040 | 0 | { |
16041 | | /* Update the expected address of the padding frag. */ |
16042 | 0 | padding_fragP->tc_frag_data.padding_address |
16043 | 0 | = (fragP->fr_address + padding_size |
16044 | 0 | + fragP->tc_frag_data.padding_address); |
16045 | 0 | return 0; |
16046 | 0 | } |
16047 | | |
16048 | 0 | if (padding_size > fragP->tc_frag_data.max_prefix_length) |
16049 | 0 | { |
16050 | | /* No padding if there is no sufficient room. Clear the |
16051 | | expected address of the padding frag. */ |
16052 | 0 | padding_fragP->tc_frag_data.padding_address = 0; |
16053 | 0 | padding_size = 0; |
16054 | 0 | } |
16055 | 0 | else |
16056 | | /* Store the expected address of the padding frag. */ |
16057 | 0 | padding_fragP->tc_frag_data.padding_address |
16058 | 0 | = (fragP->fr_address + padding_size |
16059 | 0 | + fragP->tc_frag_data.padding_address); |
16060 | |
|
16061 | 0 | fragP->tc_frag_data.prefix_length = padding_size; |
16062 | | |
16063 | | /* Update the length for the current interation. */ |
16064 | 0 | left_size = padding_size; |
16065 | 0 | for (next_fragP = fragP; |
16066 | 0 | next_fragP != padding_fragP; |
16067 | 0 | next_fragP = next_fragP->fr_next) |
16068 | 0 | if (next_fragP->fr_type == rs_machine_dependent |
16069 | 0 | && (TYPE_FROM_RELAX_STATE (next_fragP->fr_subtype) |
16070 | 0 | == BRANCH_PREFIX)) |
16071 | 0 | { |
16072 | 0 | if (left_size) |
16073 | 0 | { |
16074 | 0 | int max = next_fragP->tc_frag_data.max_bytes; |
16075 | 0 | if (max) |
16076 | 0 | { |
16077 | 0 | int size; |
16078 | 0 | if (max > left_size) |
16079 | 0 | size = left_size; |
16080 | 0 | else |
16081 | 0 | size = max; |
16082 | 0 | left_size -= size; |
16083 | 0 | next_fragP->tc_frag_data.length = size; |
16084 | 0 | } |
16085 | 0 | } |
16086 | 0 | else |
16087 | 0 | next_fragP->tc_frag_data.length = 0; |
16088 | 0 | } |
16089 | |
|
16090 | 0 | return (fragP->tc_frag_data.length |
16091 | 0 | - fragP->tc_frag_data.last_length); |
16092 | 0 | } |
16093 | 0 | return relax_frag (segment, fragP, stretch); |
16094 | 0 | } |
16095 | | |
16096 | | /* md_estimate_size_before_relax() |
16097 | | |
16098 | | Called just before relax() for rs_machine_dependent frags. The x86 |
16099 | | assembler uses these frags to handle variable size jump |
16100 | | instructions. |
16101 | | |
16102 | | Any symbol that is now undefined will not become defined. |
16103 | | Return the correct fr_subtype in the frag. |
16104 | | Return the initial "guess for variable size of frag" to caller. |
16105 | | The guess is actually the growth beyond the fixed part. Whatever |
16106 | | we do to grow the fixed or variable part contributes to our |
16107 | | returned value. */ |
16108 | | |
16109 | | int |
16110 | | md_estimate_size_before_relax (fragS *fragP, segT segment) |
16111 | 0 | { |
16112 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PADDING |
16113 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PREFIX |
16114 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == FUSED_JCC_PADDING) |
16115 | 0 | { |
16116 | 0 | i386_classify_machine_dependent_frag (fragP); |
16117 | 0 | return fragP->tc_frag_data.length; |
16118 | 0 | } |
16119 | | |
16120 | | /* We've already got fragP->fr_subtype right; all we have to do is |
16121 | | check for un-relaxable symbols. On an ELF system, we can't relax |
16122 | | an externally visible symbol, because it may be overridden by a |
16123 | | shared library. */ |
16124 | 0 | if (S_GET_SEGMENT (fragP->fr_symbol) != segment |
16125 | 0 | #ifdef OBJ_ELF |
16126 | 0 | || !elf_symbol_resolved_in_segment_p (fragP->fr_symbol, |
16127 | 0 | fragP->fr_var) |
16128 | 0 | #endif |
16129 | | #if defined (OBJ_COFF) && defined (TE_PE) |
16130 | | || S_IS_WEAK (fragP->fr_symbol) |
16131 | | #endif |
16132 | 0 | ) |
16133 | 0 | { |
16134 | | /* Symbol is undefined in this segment, or we need to keep a |
16135 | | reloc so that weak symbols can be overridden. */ |
16136 | 0 | int size = (fragP->fr_subtype & CODE16) ? 2 : 4; |
16137 | 0 | enum bfd_reloc_code_real reloc_type; |
16138 | 0 | unsigned char *opcode; |
16139 | 0 | int old_fr_fix; |
16140 | 0 | fixS *fixP = NULL; |
16141 | |
|
16142 | 0 | if (fragP->fr_var != NO_RELOC) |
16143 | 0 | reloc_type = (enum bfd_reloc_code_real) fragP->fr_var; |
16144 | 0 | else if (size == 2) |
16145 | 0 | reloc_type = BFD_RELOC_16_PCREL; |
16146 | 0 | #ifdef OBJ_ELF |
16147 | 0 | else if (fragP->tc_frag_data.code == CODE_64BIT |
16148 | 0 | && fragP->fr_offset == 0 |
16149 | 0 | && need_plt32_p (fragP->fr_symbol)) |
16150 | 0 | reloc_type = BFD_RELOC_X86_64_PLT32; |
16151 | 0 | #endif |
16152 | 0 | else |
16153 | 0 | reloc_type = BFD_RELOC_32_PCREL; |
16154 | |
|
16155 | 0 | old_fr_fix = fragP->fr_fix; |
16156 | 0 | opcode = (unsigned char *) fragP->fr_opcode; |
16157 | |
|
16158 | 0 | switch (TYPE_FROM_RELAX_STATE (fragP->fr_subtype)) |
16159 | 0 | { |
16160 | 0 | case UNCOND_JUMP: |
16161 | | /* Make jmp (0xeb) a (d)word displacement jump. */ |
16162 | 0 | opcode[0] = 0xe9; |
16163 | 0 | fragP->fr_fix += size; |
16164 | 0 | fixP = fix_new (fragP, old_fr_fix, size, |
16165 | 0 | fragP->fr_symbol, |
16166 | 0 | fragP->fr_offset, 1, |
16167 | 0 | reloc_type); |
16168 | 0 | break; |
16169 | | |
16170 | 0 | case COND_JUMP86: |
16171 | 0 | if (size == 2 |
16172 | 0 | && (!no_cond_jump_promotion || fragP->fr_var != NO_RELOC)) |
16173 | 0 | { |
16174 | | /* Negate the condition, and branch past an |
16175 | | unconditional jump. */ |
16176 | 0 | opcode[0] ^= 1; |
16177 | 0 | opcode[1] = 3; |
16178 | | /* Insert an unconditional jump. */ |
16179 | 0 | opcode[2] = 0xe9; |
16180 | | /* We added two extra opcode bytes, and have a two byte |
16181 | | offset. */ |
16182 | 0 | fragP->fr_fix += 2 + 2; |
16183 | 0 | fix_new (fragP, old_fr_fix + 2, 2, |
16184 | 0 | fragP->fr_symbol, |
16185 | 0 | fragP->fr_offset, 1, |
16186 | 0 | reloc_type); |
16187 | 0 | break; |
16188 | 0 | } |
16189 | | /* Fall through. */ |
16190 | | |
16191 | 0 | case COND_JUMP: |
16192 | 0 | if (no_cond_jump_promotion && fragP->fr_var == NO_RELOC) |
16193 | 0 | { |
16194 | 0 | fragP->fr_fix += 1; |
16195 | 0 | fixP = fix_new (fragP, old_fr_fix, 1, |
16196 | 0 | fragP->fr_symbol, |
16197 | 0 | fragP->fr_offset, 1, |
16198 | 0 | BFD_RELOC_8_PCREL); |
16199 | 0 | fixP->fx_signed = 1; |
16200 | 0 | break; |
16201 | 0 | } |
16202 | | |
16203 | | /* This changes the byte-displacement jump 0x7N |
16204 | | to the (d)word-displacement jump 0x0f,0x8N. */ |
16205 | 0 | opcode[1] = opcode[0] + 0x10; |
16206 | 0 | opcode[0] = TWO_BYTE_OPCODE_ESCAPE; |
16207 | | /* We've added an opcode byte. */ |
16208 | 0 | fragP->fr_fix += 1 + size; |
16209 | 0 | fixP = fix_new (fragP, old_fr_fix + 1, size, |
16210 | 0 | fragP->fr_symbol, |
16211 | 0 | fragP->fr_offset, 1, |
16212 | 0 | reloc_type); |
16213 | 0 | break; |
16214 | | |
16215 | 0 | default: |
16216 | 0 | BAD_CASE (fragP->fr_subtype); |
16217 | 0 | break; |
16218 | 0 | } |
16219 | | |
16220 | | /* All jumps handled here are signed, but don't unconditionally use a |
16221 | | signed limit check for 32 and 16 bit jumps as we want to allow wrap |
16222 | | around at 4G (outside of 64-bit mode) and 64k. */ |
16223 | 0 | if (size == 4 && flag_code == CODE_64BIT) |
16224 | 0 | fixP->fx_signed = 1; |
16225 | |
|
16226 | 0 | frag_wane (fragP); |
16227 | 0 | return fragP->fr_fix - old_fr_fix; |
16228 | 0 | } |
16229 | | |
16230 | | /* Guess size depending on current relax state. Initially the relax |
16231 | | state will correspond to a short jump and we return 1, because |
16232 | | the variable part of the frag (the branch offset) is one byte |
16233 | | long. However, we can relax a section more than once and in that |
16234 | | case we must either set fr_subtype back to the unrelaxed state, |
16235 | | or return the value for the appropriate branch. */ |
16236 | 0 | return md_relax_table[fragP->fr_subtype].rlx_length; |
16237 | 0 | } |
16238 | | |
16239 | | /* Called after relax() is finished. |
16240 | | |
16241 | | In: Address of frag. |
16242 | | fr_type == rs_machine_dependent. |
16243 | | fr_subtype is what the address relaxed to. |
16244 | | |
16245 | | Out: Any fixSs and constants are set up. |
16246 | | Caller will turn frag into a ".space 0". */ |
16247 | | |
16248 | | void |
16249 | | md_convert_frag (bfd *abfd ATTRIBUTE_UNUSED, segT sec ATTRIBUTE_UNUSED, |
16250 | | fragS *fragP) |
16251 | 0 | { |
16252 | 0 | unsigned char *opcode; |
16253 | 0 | unsigned char *where_to_put_displacement = NULL; |
16254 | 0 | offsetT target_address; |
16255 | 0 | offsetT opcode_address; |
16256 | 0 | unsigned int extension = 0; |
16257 | 0 | offsetT displacement_from_opcode_start; |
16258 | |
|
16259 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PADDING |
16260 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == FUSED_JCC_PADDING |
16261 | 0 | || TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PREFIX) |
16262 | 0 | { |
16263 | | /* Generate nop padding. */ |
16264 | 0 | unsigned int size = fragP->tc_frag_data.length; |
16265 | 0 | if (size) |
16266 | 0 | { |
16267 | 0 | if (size > fragP->tc_frag_data.max_bytes) |
16268 | 0 | abort (); |
16269 | | |
16270 | 0 | if (flag_debug) |
16271 | 0 | { |
16272 | 0 | const char *msg; |
16273 | 0 | const char *branch = "branch"; |
16274 | 0 | const char *prefix = ""; |
16275 | 0 | fragS *padding_fragP; |
16276 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) |
16277 | 0 | == BRANCH_PREFIX) |
16278 | 0 | { |
16279 | 0 | padding_fragP = fragP->tc_frag_data.u.padding_fragP; |
16280 | 0 | switch (fragP->tc_frag_data.default_prefix) |
16281 | 0 | { |
16282 | 0 | default: |
16283 | 0 | abort (); |
16284 | 0 | break; |
16285 | 0 | case CS_PREFIX_OPCODE: |
16286 | 0 | prefix = " cs"; |
16287 | 0 | break; |
16288 | 0 | case DS_PREFIX_OPCODE: |
16289 | 0 | prefix = " ds"; |
16290 | 0 | break; |
16291 | 0 | case ES_PREFIX_OPCODE: |
16292 | 0 | prefix = " es"; |
16293 | 0 | break; |
16294 | 0 | case FS_PREFIX_OPCODE: |
16295 | 0 | prefix = " fs"; |
16296 | 0 | break; |
16297 | 0 | case GS_PREFIX_OPCODE: |
16298 | 0 | prefix = " gs"; |
16299 | 0 | break; |
16300 | 0 | case SS_PREFIX_OPCODE: |
16301 | 0 | prefix = " ss"; |
16302 | 0 | break; |
16303 | 0 | } |
16304 | 0 | if (padding_fragP) |
16305 | 0 | msg = _("%s:%u: add %d%s at 0x%llx to align " |
16306 | 0 | "%s within %d-byte boundary\n"); |
16307 | 0 | else |
16308 | 0 | msg = _("%s:%u: add additional %d%s at 0x%llx to " |
16309 | 0 | "align %s within %d-byte boundary\n"); |
16310 | 0 | } |
16311 | 0 | else |
16312 | 0 | { |
16313 | 0 | padding_fragP = fragP; |
16314 | 0 | msg = _("%s:%u: add %d%s-byte nop at 0x%llx to align " |
16315 | 0 | "%s within %d-byte boundary\n"); |
16316 | 0 | } |
16317 | | |
16318 | 0 | if (padding_fragP) |
16319 | 0 | switch (padding_fragP->tc_frag_data.branch_type) |
16320 | 0 | { |
16321 | 0 | case align_branch_jcc: |
16322 | 0 | branch = "jcc"; |
16323 | 0 | break; |
16324 | 0 | case align_branch_fused: |
16325 | 0 | branch = "fused jcc"; |
16326 | 0 | break; |
16327 | 0 | case align_branch_jmp: |
16328 | 0 | branch = "jmp"; |
16329 | 0 | break; |
16330 | 0 | case align_branch_call: |
16331 | 0 | branch = "call"; |
16332 | 0 | break; |
16333 | 0 | case align_branch_indirect: |
16334 | 0 | branch = "indiret branch"; |
16335 | 0 | break; |
16336 | 0 | case align_branch_ret: |
16337 | 0 | branch = "ret"; |
16338 | 0 | break; |
16339 | 0 | default: |
16340 | 0 | break; |
16341 | 0 | } |
16342 | | |
16343 | 0 | fprintf (stdout, msg, |
16344 | 0 | fragP->fr_file, fragP->fr_line, size, prefix, |
16345 | 0 | (long long) fragP->fr_address, branch, |
16346 | 0 | 1 << align_branch_power); |
16347 | 0 | } |
16348 | 0 | if (TYPE_FROM_RELAX_STATE (fragP->fr_subtype) == BRANCH_PREFIX) |
16349 | 0 | memset (fragP->fr_opcode, |
16350 | 0 | fragP->tc_frag_data.default_prefix, size); |
16351 | 0 | else |
16352 | 0 | i386_generate_nops (fragP, (char *) fragP->fr_opcode, |
16353 | 0 | size, 0); |
16354 | 0 | fragP->fr_fix += size; |
16355 | 0 | } |
16356 | 0 | return; |
16357 | 0 | } |
16358 | | |
16359 | 0 | opcode = (unsigned char *) fragP->fr_opcode; |
16360 | | |
16361 | | /* Address we want to reach in file space. */ |
16362 | 0 | target_address = S_GET_VALUE (fragP->fr_symbol) + fragP->fr_offset; |
16363 | | |
16364 | | /* Address opcode resides at in file space. */ |
16365 | 0 | opcode_address = fragP->fr_address + fragP->fr_fix; |
16366 | | |
16367 | | /* Displacement from opcode start to fill into instruction. */ |
16368 | 0 | displacement_from_opcode_start = target_address - opcode_address; |
16369 | |
|
16370 | 0 | if ((fragP->fr_subtype & BIG) == 0) |
16371 | 0 | { |
16372 | | /* Don't have to change opcode. */ |
16373 | 0 | extension = 1; /* 1 opcode + 1 displacement */ |
16374 | 0 | where_to_put_displacement = &opcode[1]; |
16375 | 0 | } |
16376 | 0 | else |
16377 | 0 | { |
16378 | 0 | if (no_cond_jump_promotion |
16379 | 0 | && TYPE_FROM_RELAX_STATE (fragP->fr_subtype) != UNCOND_JUMP) |
16380 | 0 | as_warn_where (fragP->fr_file, fragP->fr_line, |
16381 | 0 | _("long jump required")); |
16382 | |
|
16383 | 0 | switch (fragP->fr_subtype) |
16384 | 0 | { |
16385 | 0 | case ENCODE_RELAX_STATE (UNCOND_JUMP, BIG): |
16386 | 0 | extension = 4; /* 1 opcode + 4 displacement */ |
16387 | 0 | opcode[0] = 0xe9; |
16388 | 0 | where_to_put_displacement = &opcode[1]; |
16389 | 0 | break; |
16390 | | |
16391 | 0 | case ENCODE_RELAX_STATE (UNCOND_JUMP, BIG16): |
16392 | 0 | extension = 2; /* 1 opcode + 2 displacement */ |
16393 | 0 | opcode[0] = 0xe9; |
16394 | 0 | where_to_put_displacement = &opcode[1]; |
16395 | 0 | break; |
16396 | | |
16397 | 0 | case ENCODE_RELAX_STATE (COND_JUMP, BIG): |
16398 | 0 | case ENCODE_RELAX_STATE (COND_JUMP86, BIG): |
16399 | 0 | extension = 5; /* 2 opcode + 4 displacement */ |
16400 | 0 | opcode[1] = opcode[0] + 0x10; |
16401 | 0 | opcode[0] = TWO_BYTE_OPCODE_ESCAPE; |
16402 | 0 | where_to_put_displacement = &opcode[2]; |
16403 | 0 | break; |
16404 | | |
16405 | 0 | case ENCODE_RELAX_STATE (COND_JUMP, BIG16): |
16406 | 0 | extension = 3; /* 2 opcode + 2 displacement */ |
16407 | 0 | opcode[1] = opcode[0] + 0x10; |
16408 | 0 | opcode[0] = TWO_BYTE_OPCODE_ESCAPE; |
16409 | 0 | where_to_put_displacement = &opcode[2]; |
16410 | 0 | break; |
16411 | | |
16412 | 0 | case ENCODE_RELAX_STATE (COND_JUMP86, BIG16): |
16413 | 0 | extension = 4; |
16414 | 0 | opcode[0] ^= 1; |
16415 | 0 | opcode[1] = 3; |
16416 | 0 | opcode[2] = 0xe9; |
16417 | 0 | where_to_put_displacement = &opcode[3]; |
16418 | 0 | break; |
16419 | | |
16420 | 0 | default: |
16421 | 0 | BAD_CASE (fragP->fr_subtype); |
16422 | 0 | break; |
16423 | 0 | } |
16424 | 0 | } |
16425 | | |
16426 | | /* If size if less then four we are sure that the operand fits, |
16427 | | but if it's 4, then it could be that the displacement is larger |
16428 | | then -/+ 2GB. */ |
16429 | 0 | if (DISP_SIZE_FROM_RELAX_STATE (fragP->fr_subtype) == 4 |
16430 | 0 | && object_64bit |
16431 | 0 | && ((addressT) (displacement_from_opcode_start - extension |
16432 | 0 | + ((addressT) 1 << 31)) |
16433 | 0 | > (((addressT) 2 << 31) - 1))) |
16434 | 0 | { |
16435 | 0 | as_bad_where (fragP->fr_file, fragP->fr_line, |
16436 | 0 | _("jump target out of range")); |
16437 | | /* Make us emit 0. */ |
16438 | 0 | displacement_from_opcode_start = extension; |
16439 | 0 | } |
16440 | | /* Now put displacement after opcode. */ |
16441 | 0 | md_number_to_chars ((char *) where_to_put_displacement, |
16442 | 0 | (valueT) (displacement_from_opcode_start - extension), |
16443 | 0 | DISP_SIZE_FROM_RELAX_STATE (fragP->fr_subtype)); |
16444 | 0 | fragP->fr_fix += extension; |
16445 | 0 | } |
16446 | | |
16447 | | /* Apply a fixup (fixP) to segment data, once it has been determined |
16448 | | by our caller that we have all the info we need to fix it up. |
16449 | | |
16450 | | Parameter valP is the pointer to the value of the bits. |
16451 | | |
16452 | | On the 386, immediates, displacements, and data pointers are all in |
16453 | | the same (little-endian) format, so we don't need to care about which |
16454 | | we are handling. */ |
16455 | | |
16456 | | void |
16457 | | md_apply_fix (fixS *fixP, valueT *valP, segT seg ATTRIBUTE_UNUSED) |
16458 | 0 | { |
16459 | 0 | char *p = fixP->fx_where + fixP->fx_frag->fr_literal; |
16460 | 0 | valueT value = *valP; |
16461 | |
|
16462 | 0 | #if !defined (TE_Mach) |
16463 | 0 | if (fixP->fx_pcrel) |
16464 | 0 | { |
16465 | 0 | switch (fixP->fx_r_type) |
16466 | 0 | { |
16467 | 0 | default: |
16468 | 0 | break; |
16469 | | |
16470 | 0 | case BFD_RELOC_64: |
16471 | 0 | fixP->fx_r_type = BFD_RELOC_64_PCREL; |
16472 | 0 | break; |
16473 | 0 | case BFD_RELOC_32: |
16474 | 0 | case BFD_RELOC_X86_64_32S: |
16475 | 0 | fixP->fx_r_type = BFD_RELOC_32_PCREL; |
16476 | 0 | break; |
16477 | 0 | case BFD_RELOC_16: |
16478 | 0 | fixP->fx_r_type = BFD_RELOC_16_PCREL; |
16479 | 0 | break; |
16480 | 0 | case BFD_RELOC_8: |
16481 | 0 | fixP->fx_r_type = BFD_RELOC_8_PCREL; |
16482 | 0 | break; |
16483 | 0 | } |
16484 | 0 | } |
16485 | | |
16486 | 0 | if (fixP->fx_addsy != NULL |
16487 | 0 | && (fixP->fx_r_type == BFD_RELOC_32_PCREL |
16488 | 0 | || fixP->fx_r_type == BFD_RELOC_64_PCREL |
16489 | 0 | || fixP->fx_r_type == BFD_RELOC_16_PCREL |
16490 | 0 | || fixP->fx_r_type == BFD_RELOC_8_PCREL) |
16491 | 0 | && !use_rela_relocations) |
16492 | 0 | { |
16493 | | /* This is a hack. There should be a better way to handle this. |
16494 | | This covers for the fact that bfd_install_relocation will |
16495 | | subtract the current location (for partial_inplace, PC relative |
16496 | | relocations); see more below. */ |
16497 | 0 | #if defined (OBJ_ELF) || defined (TE_PE) |
16498 | 0 | value += fixP->fx_where + fixP->fx_frag->fr_address; |
16499 | 0 | #endif |
16500 | 0 | #ifdef OBJ_ELF |
16501 | 0 | segT sym_seg = S_GET_SEGMENT (fixP->fx_addsy); |
16502 | |
|
16503 | 0 | if ((sym_seg == seg |
16504 | 0 | || (symbol_section_p (fixP->fx_addsy) |
16505 | 0 | && sym_seg != absolute_section)) |
16506 | 0 | && !generic_force_reloc (fixP)) |
16507 | 0 | { |
16508 | | /* Yes, we add the values in twice. This is because |
16509 | | bfd_install_relocation subtracts them out again. I think |
16510 | | bfd_install_relocation is broken, but I don't dare change |
16511 | | it. FIXME. */ |
16512 | 0 | value += fixP->fx_where + fixP->fx_frag->fr_address; |
16513 | 0 | } |
16514 | 0 | #endif |
16515 | | #if defined (OBJ_COFF) && defined (TE_PE) |
16516 | | /* For some reason, the PE format does not store a |
16517 | | section address offset for a PC relative symbol. */ |
16518 | | if (S_GET_SEGMENT (fixP->fx_addsy) != seg |
16519 | | || S_IS_WEAK (fixP->fx_addsy)) |
16520 | | value += md_pcrel_from (fixP); |
16521 | | #endif |
16522 | 0 | } |
16523 | | #if defined (OBJ_COFF) && defined (TE_PE) |
16524 | | if (fixP->fx_addsy != NULL |
16525 | | && S_IS_WEAK (fixP->fx_addsy) |
16526 | | /* PR 16858: Do not modify weak function references. */ |
16527 | | && ! fixP->fx_pcrel) |
16528 | | { |
16529 | | #if !defined (TE_PEP) |
16530 | | /* For x86 PE weak function symbols are neither PC-relative |
16531 | | nor do they set S_IS_FUNCTION. So the only reliable way |
16532 | | to detect them is to check the flags of their containing |
16533 | | section. */ |
16534 | | if (S_GET_SEGMENT (fixP->fx_addsy) != NULL |
16535 | | && S_GET_SEGMENT (fixP->fx_addsy)->flags & SEC_CODE) |
16536 | | ; |
16537 | | else |
16538 | | #endif |
16539 | | value -= S_GET_VALUE (fixP->fx_addsy); |
16540 | | } |
16541 | | #endif |
16542 | | |
16543 | | /* Fix a few things - the dynamic linker expects certain values here, |
16544 | | and we must not disappoint it. */ |
16545 | 0 | #ifdef OBJ_ELF |
16546 | 0 | if (fixP->fx_addsy) |
16547 | 0 | switch (fixP->fx_r_type) |
16548 | 0 | { |
16549 | 0 | case BFD_RELOC_386_PLT32: |
16550 | 0 | case BFD_RELOC_X86_64_PLT32: |
16551 | | /* Make the jump instruction point to the address of the operand. |
16552 | | At runtime we merely add the offset to the actual PLT entry. |
16553 | | NB: Subtract the offset size only for jump instructions. */ |
16554 | 0 | if (fixP->fx_pcrel) |
16555 | 0 | value = -4; |
16556 | 0 | break; |
16557 | | |
16558 | 0 | case BFD_RELOC_386_TLS_GD: |
16559 | 0 | case BFD_RELOC_386_TLS_LDM: |
16560 | 0 | case BFD_RELOC_386_TLS_IE_32: |
16561 | 0 | case BFD_RELOC_386_TLS_IE: |
16562 | 0 | case BFD_RELOC_386_TLS_GOTIE: |
16563 | 0 | case BFD_RELOC_386_TLS_GOTDESC: |
16564 | 0 | case BFD_RELOC_X86_64_TLSGD: |
16565 | 0 | case BFD_RELOC_X86_64_TLSLD: |
16566 | 0 | case BFD_RELOC_X86_64_GOTTPOFF: |
16567 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTTPOFF: |
16568 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTTPOFF: |
16569 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTTPOFF: |
16570 | 0 | case BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
16571 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC: |
16572 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPC32_TLSDESC: |
16573 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPC32_TLSDESC: |
16574 | 0 | value = 0; /* Fully resolved at runtime. No addend. */ |
16575 | | /* Fallthrough */ |
16576 | 0 | case BFD_RELOC_386_TLS_LE: |
16577 | 0 | case BFD_RELOC_386_TLS_LDO_32: |
16578 | 0 | case BFD_RELOC_386_TLS_LE_32: |
16579 | 0 | case BFD_RELOC_X86_64_DTPOFF32: |
16580 | 0 | case BFD_RELOC_X86_64_DTPOFF64: |
16581 | 0 | case BFD_RELOC_X86_64_TPOFF32: |
16582 | 0 | case BFD_RELOC_X86_64_TPOFF64: |
16583 | 0 | S_SET_THREAD_LOCAL (fixP->fx_addsy); |
16584 | 0 | break; |
16585 | | |
16586 | 0 | case BFD_RELOC_386_TLS_DESC_CALL: |
16587 | 0 | case BFD_RELOC_X86_64_TLSDESC_CALL: |
16588 | 0 | value = 0; /* Fully resolved at runtime. No addend. */ |
16589 | 0 | S_SET_THREAD_LOCAL (fixP->fx_addsy); |
16590 | 0 | fixP->fx_done = 0; |
16591 | 0 | return; |
16592 | | |
16593 | 0 | case BFD_RELOC_VTABLE_INHERIT: |
16594 | 0 | case BFD_RELOC_VTABLE_ENTRY: |
16595 | 0 | fixP->fx_done = 0; |
16596 | 0 | return; |
16597 | | |
16598 | 0 | default: |
16599 | 0 | break; |
16600 | 0 | } |
16601 | 0 | #endif /* OBJ_ELF */ |
16602 | | |
16603 | | /* If not 64bit, massage value, to account for wraparound when !BFD64. */ |
16604 | 0 | if (!object_64bit) |
16605 | 0 | value = extend_to_32bit_address (value); |
16606 | |
|
16607 | 0 | *valP = value; |
16608 | 0 | #endif /* !defined (TE_Mach) */ |
16609 | | |
16610 | | /* Are we finished with this relocation now? */ |
16611 | 0 | if (fixP->fx_addsy == NULL) |
16612 | 0 | { |
16613 | 0 | fixP->fx_done = 1; |
16614 | 0 | switch (fixP->fx_r_type) |
16615 | 0 | { |
16616 | 0 | case BFD_RELOC_X86_64_32S: |
16617 | 0 | fixP->fx_signed = 1; |
16618 | 0 | break; |
16619 | | |
16620 | 0 | default: |
16621 | 0 | break; |
16622 | 0 | } |
16623 | 0 | } |
16624 | | #if defined (OBJ_COFF) && defined (TE_PE) |
16625 | | else if (fixP->fx_addsy != NULL && S_IS_WEAK (fixP->fx_addsy)) |
16626 | | { |
16627 | | fixP->fx_done = 0; |
16628 | | /* Remember value for tc_gen_reloc. */ |
16629 | | fixP->fx_addnumber = value; |
16630 | | /* Clear out the frag for now. */ |
16631 | | value = 0; |
16632 | | } |
16633 | | #endif |
16634 | 0 | else if (use_rela_relocations) |
16635 | 0 | { |
16636 | 0 | if (!disallow_64bit_reloc || fixP->fx_r_type == NO_RELOC) |
16637 | 0 | fixP->fx_no_overflow = 1; |
16638 | | /* Remember value for tc_gen_reloc. */ |
16639 | 0 | fixP->fx_addnumber = value; |
16640 | 0 | value = 0; |
16641 | 0 | } |
16642 | | |
16643 | 0 | md_number_to_chars (p, value, fixP->fx_size); |
16644 | 0 | } |
16645 | | |
16646 | | const char * |
16647 | | md_atof (int type, char *litP, int *sizeP) |
16648 | 1.88k | { |
16649 | | /* This outputs the LITTLENUMs in REVERSE order; |
16650 | | in accord with the bigendian 386. */ |
16651 | 1.88k | return ieee_md_atof (type, litP, sizeP, false); |
16652 | 1.88k | } |
16653 | | |
16654 | | static char output_invalid_buf[sizeof (unsigned char) * 2 + 6]; |
16655 | | |
16656 | | static char * |
16657 | | output_invalid (int c) |
16658 | 286k | { |
16659 | 286k | if (ISPRINT (c)) |
16660 | 27.7k | snprintf (output_invalid_buf, sizeof (output_invalid_buf), |
16661 | 27.7k | "'%c'", c); |
16662 | 258k | else |
16663 | 258k | snprintf (output_invalid_buf, sizeof (output_invalid_buf), |
16664 | 258k | "(0x%x)", (unsigned char) c); |
16665 | 286k | return output_invalid_buf; |
16666 | 286k | } |
16667 | | |
16668 | | /* Verify that @r can be used in the current context. */ |
16669 | | |
16670 | | static bool check_register (const reg_entry *r) |
16671 | 670 | { |
16672 | 670 | if (allow_pseudo_reg) |
16673 | 0 | return true; |
16674 | | |
16675 | 670 | if (operand_type_all_zero (&r->reg_type)) |
16676 | 0 | return false; |
16677 | | |
16678 | 670 | if ((r->reg_type.bitfield.dword |
16679 | 670 | || (r->reg_type.bitfield.class == SReg && r->reg_num > 3) |
16680 | 670 | || r->reg_type.bitfield.class == RegCR |
16681 | 670 | || r->reg_type.bitfield.class == RegDR) |
16682 | 670 | && !cpu_arch_flags.bitfield.cpui386) |
16683 | 0 | return false; |
16684 | | |
16685 | 670 | if (r->reg_type.bitfield.class == RegTR |
16686 | 670 | && (flag_code == CODE_64BIT |
16687 | 0 | || !cpu_arch_flags.bitfield.cpui386 |
16688 | 0 | || cpu_arch_isa_flags.bitfield.cpui586 |
16689 | 0 | || cpu_arch_isa_flags.bitfield.cpui686)) |
16690 | 0 | return false; |
16691 | | |
16692 | 670 | if (r->reg_type.bitfield.class == RegMMX && !cpu_arch_flags.bitfield.cpummx) |
16693 | 0 | return false; |
16694 | | |
16695 | 670 | if (!cpu_arch_flags.bitfield.cpuavx512f) |
16696 | 670 | { |
16697 | 670 | if (r->reg_type.bitfield.zmmword |
16698 | 670 | || r->reg_type.bitfield.class == RegMask) |
16699 | 0 | return false; |
16700 | | |
16701 | 670 | if (!cpu_arch_flags.bitfield.cpuavx) |
16702 | 437 | { |
16703 | 437 | if (r->reg_type.bitfield.ymmword) |
16704 | 10 | return false; |
16705 | | |
16706 | 427 | if (!cpu_arch_flags.bitfield.cpusse && r->reg_type.bitfield.xmmword) |
16707 | 2 | return false; |
16708 | 427 | } |
16709 | 670 | } |
16710 | | |
16711 | 658 | if (r->reg_type.bitfield.zmmword) |
16712 | 0 | { |
16713 | 0 | if (vector_size < VSZ512) |
16714 | 0 | return false; |
16715 | | |
16716 | | /* Don't update pp when not dealing with insn operands. */ |
16717 | 0 | switch (current_templates.start ? pp.encoding : encoding_evex) |
16718 | 0 | { |
16719 | 0 | case encoding_default: |
16720 | 0 | case encoding_egpr: |
16721 | 0 | pp.encoding = encoding_evex512; |
16722 | 0 | break; |
16723 | 0 | case encoding_evex: |
16724 | 0 | case encoding_evex512: |
16725 | 0 | break; |
16726 | 0 | default: |
16727 | 0 | pp.encoding = encoding_error; |
16728 | 0 | break; |
16729 | 0 | } |
16730 | 0 | } |
16731 | | |
16732 | 658 | if (vector_size < VSZ256 && r->reg_type.bitfield.ymmword) |
16733 | 0 | return false; |
16734 | | |
16735 | 658 | if (r->reg_type.bitfield.tmmword |
16736 | 658 | && (!cpu_arch_flags.bitfield.cpuamx_tile |
16737 | 50 | || flag_code != CODE_64BIT)) |
16738 | 50 | return false; |
16739 | | |
16740 | 608 | if (r->reg_type.bitfield.class == RegBND && !cpu_arch_flags.bitfield.cpumpx) |
16741 | 49 | return false; |
16742 | | |
16743 | | /* Don't allow fake index register unless allow_index_reg isn't 0. */ |
16744 | 559 | if (!allow_index_reg && r->reg_num == RegIZ) |
16745 | 0 | return false; |
16746 | | |
16747 | | /* Upper 16 vector registers are only available with VREX in 64bit |
16748 | | mode, and require EVEX encoding. */ |
16749 | 559 | if (r->reg_flags & RegVRex) |
16750 | 2 | { |
16751 | 2 | if (!cpu_arch_flags.bitfield.cpuavx512f |
16752 | 2 | || flag_code != CODE_64BIT) |
16753 | 2 | return false; |
16754 | | |
16755 | | /* Don't update pp when not dealing with insn operands. */ |
16756 | 0 | switch (current_templates.start ? pp.encoding : encoding_evex) |
16757 | 0 | { |
16758 | 0 | case encoding_default: |
16759 | 0 | case encoding_egpr: |
16760 | 0 | case encoding_evex512: |
16761 | 0 | pp.encoding = encoding_evex; |
16762 | 0 | break; |
16763 | 0 | case encoding_evex: |
16764 | 0 | break; |
16765 | 0 | default: |
16766 | 0 | pp.encoding = encoding_error; |
16767 | 0 | break; |
16768 | 0 | } |
16769 | 0 | } |
16770 | | |
16771 | 557 | if (r->reg_flags & RegRex2) |
16772 | 1 | { |
16773 | 1 | if (!cpu_arch_flags.bitfield.cpuapx_f |
16774 | 1 | || flag_code != CODE_64BIT) |
16775 | 1 | return false; |
16776 | | |
16777 | | /* Don't update pp when not dealing with insn operands. */ |
16778 | 0 | switch (current_templates.start ? pp.encoding : encoding_egpr) |
16779 | 0 | { |
16780 | 0 | case encoding_default: |
16781 | 0 | pp.encoding = encoding_egpr; |
16782 | 0 | break; |
16783 | 0 | case encoding_egpr: |
16784 | 0 | case encoding_evex: |
16785 | 0 | case encoding_evex512: |
16786 | 0 | break; |
16787 | 0 | default: |
16788 | 0 | pp.encoding = encoding_error; |
16789 | 0 | break; |
16790 | 0 | } |
16791 | 0 | } |
16792 | | |
16793 | 556 | if (((r->reg_flags & (RegRex64 | RegRex)) || r->reg_type.bitfield.qword) |
16794 | 556 | && (!cpu_arch_flags.bitfield.cpu64 |
16795 | 5 | || r->reg_type.bitfield.class != RegCR |
16796 | 5 | || dot_insn ()) |
16797 | 556 | && flag_code != CODE_64BIT) |
16798 | 5 | return false; |
16799 | | |
16800 | 551 | if (r->reg_type.bitfield.class == SReg && r->reg_num == RegFlat |
16801 | 551 | && !intel_syntax) |
16802 | 0 | return false; |
16803 | | |
16804 | 551 | return true; |
16805 | 551 | } |
16806 | | |
16807 | | /* REG_STRING starts *before* REGISTER_PREFIX. */ |
16808 | | |
16809 | | static const reg_entry * |
16810 | | parse_real_register (const char *reg_string, char **end_op) |
16811 | 4.75k | { |
16812 | 4.75k | const char *s = reg_string; |
16813 | 4.75k | char *p; |
16814 | 4.75k | char reg_name_given[MAX_REG_NAME_SIZE + 1]; |
16815 | 4.75k | const reg_entry *r; |
16816 | | |
16817 | | /* Skip possible REGISTER_PREFIX and possible whitespace. */ |
16818 | 4.75k | if (*s == REGISTER_PREFIX) |
16819 | 4.75k | ++s; |
16820 | | |
16821 | 4.75k | if (is_whitespace (*s)) |
16822 | 0 | ++s; |
16823 | | |
16824 | 4.75k | p = reg_name_given; |
16825 | 6.61k | while ((*p++ = register_chars[(unsigned char) *s]) != '\0') |
16826 | 1.85k | { |
16827 | 1.85k | if (p >= reg_name_given + MAX_REG_NAME_SIZE) |
16828 | 2 | return (const reg_entry *) NULL; |
16829 | 1.85k | s++; |
16830 | 1.85k | } |
16831 | | |
16832 | 4.75k | if (is_part_of_name (*s)) |
16833 | 374 | return (const reg_entry *) NULL; |
16834 | | |
16835 | 4.37k | *end_op = (char *) s; |
16836 | | |
16837 | 4.37k | r = str_hash_find (reg_hash, reg_name_given); |
16838 | | |
16839 | | /* Handle floating point regs, allowing spaces in the (i) part. */ |
16840 | 4.37k | if (r == reg_st0) |
16841 | 1 | { |
16842 | 1 | if (!cpu_arch_flags.bitfield.cpu8087 |
16843 | 1 | && !cpu_arch_flags.bitfield.cpu287 |
16844 | 1 | && !cpu_arch_flags.bitfield.cpu387 |
16845 | 1 | && !allow_pseudo_reg) |
16846 | 0 | return (const reg_entry *) NULL; |
16847 | | |
16848 | 1 | if (is_whitespace (*s)) |
16849 | 0 | ++s; |
16850 | 1 | if (*s == '(') |
16851 | 1 | { |
16852 | 1 | ++s; |
16853 | 1 | if (is_whitespace (*s)) |
16854 | 0 | ++s; |
16855 | 1 | if (*s >= '0' && *s <= '7') |
16856 | 1 | { |
16857 | 1 | int fpr = *s - '0'; |
16858 | 1 | ++s; |
16859 | 1 | if (is_whitespace (*s)) |
16860 | 0 | ++s; |
16861 | 1 | if (*s == ')') |
16862 | 0 | { |
16863 | 0 | *end_op = (char *) s + 1; |
16864 | 0 | know (r[fpr].reg_num == fpr); |
16865 | 0 | return r + fpr; |
16866 | 0 | } |
16867 | 1 | } |
16868 | | /* We have "%st(" then garbage. */ |
16869 | 1 | return (const reg_entry *) NULL; |
16870 | 1 | } |
16871 | 1 | } |
16872 | | |
16873 | 4.37k | return r && check_register (r) ? r : NULL; |
16874 | 4.37k | } |
16875 | | |
16876 | | /* REG_STRING starts *before* REGISTER_PREFIX. */ |
16877 | | |
16878 | | static const reg_entry * |
16879 | | parse_register (const char *reg_string, char **end_op) |
16880 | 44.4k | { |
16881 | 44.4k | const reg_entry *r; |
16882 | | |
16883 | 44.4k | if (*reg_string == REGISTER_PREFIX || allow_naked_reg) |
16884 | 25 | r = parse_real_register (reg_string, end_op); |
16885 | 44.4k | else |
16886 | 44.4k | r = NULL; |
16887 | 44.4k | if (!r) |
16888 | 44.4k | { |
16889 | 44.4k | char *save = input_line_pointer; |
16890 | 44.4k | char *buf = xstrdup (reg_string), *name; |
16891 | 44.4k | symbolS *symbolP; |
16892 | | |
16893 | 44.4k | input_line_pointer = buf; |
16894 | 44.4k | get_symbol_name (&name); |
16895 | 44.4k | symbolP = symbol_find (name); |
16896 | 44.5k | while (symbolP && symbol_equated_p (symbolP)) |
16897 | 530 | { |
16898 | 530 | const expressionS *e = symbol_get_value_expression(symbolP); |
16899 | | |
16900 | 530 | if (e->X_add_number) |
16901 | 458 | break; |
16902 | 72 | symbolP = e->X_add_symbol; |
16903 | 72 | } |
16904 | 44.4k | if (symbolP && S_GET_SEGMENT (symbolP) == reg_section) |
16905 | 0 | { |
16906 | 0 | const expressionS *e = symbol_get_value_expression (symbolP); |
16907 | |
|
16908 | 0 | if (e->X_op == O_register) |
16909 | 0 | { |
16910 | 0 | know ((valueT) e->X_add_number < i386_regtab_size); |
16911 | 0 | r = i386_regtab + e->X_add_number; |
16912 | 0 | *end_op = (char *) reg_string + (input_line_pointer - buf); |
16913 | 0 | } |
16914 | 0 | if (r && !check_register (r)) |
16915 | 0 | { |
16916 | 0 | as_bad (_("register '%s%s' cannot be used here"), |
16917 | 0 | register_prefix, r->reg_name); |
16918 | 0 | r = &bad_reg; |
16919 | 0 | } |
16920 | 0 | } |
16921 | 44.4k | input_line_pointer = save; |
16922 | 44.4k | free (buf); |
16923 | 44.4k | } |
16924 | 44.4k | return r; |
16925 | 44.4k | } |
16926 | | |
16927 | | int |
16928 | | i386_parse_name (char *name, |
16929 | | expressionS *e, |
16930 | | enum expr_mode mode, |
16931 | | char *nextcharP) |
16932 | 86.9k | { |
16933 | 86.9k | const reg_entry *r = NULL; |
16934 | 86.9k | char *end = input_line_pointer; |
16935 | | |
16936 | | /* We only know the terminating character here. It being double quote could |
16937 | | be the closing one of a quoted symbol name, or an opening one from a |
16938 | | following string (or another quoted symbol name). Since the latter can't |
16939 | | be valid syntax for anything, bailing in either case is good enough. */ |
16940 | 86.9k | if (*nextcharP == '"') |
16941 | 9.20k | return 0; |
16942 | | |
16943 | 77.7k | *end = *nextcharP; |
16944 | 77.7k | if (*name == REGISTER_PREFIX || allow_naked_reg) |
16945 | 44 | r = parse_real_register (name, &input_line_pointer); |
16946 | 77.7k | if (r && end <= input_line_pointer) |
16947 | 0 | { |
16948 | 0 | *nextcharP = *input_line_pointer; |
16949 | 0 | *input_line_pointer = 0; |
16950 | 0 | e->X_op = O_register; |
16951 | 0 | e->X_add_number = r - i386_regtab; |
16952 | 0 | return 1; |
16953 | 0 | } |
16954 | 77.7k | input_line_pointer = end; |
16955 | 77.7k | *end = 0; |
16956 | 77.7k | return intel_syntax ? i386_intel_parse_name (name, e, mode) : 0; |
16957 | 77.7k | } |
16958 | | |
16959 | | void |
16960 | | md_operand (expressionS *e) |
16961 | 27.6k | { |
16962 | 27.6k | char *end; |
16963 | 27.6k | const reg_entry *r; |
16964 | | |
16965 | 27.6k | switch (*input_line_pointer) |
16966 | 27.6k | { |
16967 | 4.68k | case REGISTER_PREFIX: |
16968 | 4.68k | r = parse_real_register (input_line_pointer, &end); |
16969 | 4.68k | if (r) |
16970 | 511 | { |
16971 | 511 | e->X_op = O_register; |
16972 | 511 | e->X_add_number = r - i386_regtab; |
16973 | 511 | input_line_pointer = end; |
16974 | 511 | } |
16975 | 4.68k | break; |
16976 | | |
16977 | 0 | case '[': |
16978 | 0 | gas_assert (intel_syntax); |
16979 | 0 | end = input_line_pointer++; |
16980 | 0 | expression (e); |
16981 | 0 | if (*input_line_pointer == ']') |
16982 | 0 | { |
16983 | 0 | ++input_line_pointer; |
16984 | 0 | e->X_op_symbol = make_expr_symbol (e); |
16985 | 0 | e->X_add_symbol = NULL; |
16986 | 0 | e->X_add_number = 0; |
16987 | 0 | e->X_op = O_index; |
16988 | 0 | } |
16989 | 0 | else |
16990 | 0 | { |
16991 | 0 | e->X_op = O_absent; |
16992 | 0 | input_line_pointer = end; |
16993 | 0 | } |
16994 | 0 | break; |
16995 | 27.6k | } |
16996 | 27.6k | } |
16997 | | |
16998 | | #ifdef BFD64 |
16999 | | /* To maintain consistency with !BFD64 builds of gas record, whether any |
17000 | | (binary) operator was involved in an expression. As expressions are |
17001 | | evaluated in only 32 bits when !BFD64, we use this to decide whether to |
17002 | | truncate results. */ |
17003 | | bool i386_record_operator (operatorT op, |
17004 | | const expressionS *left, |
17005 | | const expressionS *right) |
17006 | 142k | { |
17007 | 142k | if (op == O_absent) |
17008 | 5.61k | return false; |
17009 | | |
17010 | 136k | if (!left) |
17011 | 54.8k | { |
17012 | | /* Since the expression parser applies unary operators fine to bignum |
17013 | | operands, we don't need to be concerned of respective operands not |
17014 | | fitting in 32 bits. */ |
17015 | 54.8k | if (right->X_op == O_constant && right->X_unsigned |
17016 | 54.8k | && !fits_in_unsigned_long (right->X_add_number)) |
17017 | 653 | return false; |
17018 | 54.8k | } |
17019 | | /* This isn't entirely right: The pattern can also result when constant |
17020 | | expressions are folded (e.g. 0xffffffff + 1). */ |
17021 | 82.0k | else if ((left->X_op == O_constant && left->X_unsigned |
17022 | 82.0k | && !fits_in_unsigned_long (left->X_add_number)) |
17023 | 82.0k | || (right->X_op == O_constant && right->X_unsigned |
17024 | 81.7k | && !fits_in_unsigned_long (right->X_add_number))) |
17025 | 1.91k | expr_mode = expr_large_value; |
17026 | | |
17027 | 136k | if (expr_mode != expr_large_value) |
17028 | 125k | expr_mode = expr_operator_present; |
17029 | | |
17030 | 136k | return false; |
17031 | 136k | } |
17032 | | #endif |
17033 | | |
17034 | | const char md_shortopts[] = |
17035 | | #ifdef OBJ_ELF |
17036 | | "kVQ:" |
17037 | | # ifdef TE_SOLARIS |
17038 | | "s" |
17039 | | # endif |
17040 | | #endif |
17041 | | "qnO::"; |
17042 | | |
17043 | 0 | #define OPTION_32 (OPTION_MD_BASE + 0) |
17044 | 0 | #define OPTION_64 (OPTION_MD_BASE + 1) |
17045 | 0 | #define OPTION_DIVIDE (OPTION_MD_BASE + 2) |
17046 | 0 | #define OPTION_MARCH (OPTION_MD_BASE + 3) |
17047 | 0 | #define OPTION_MTUNE (OPTION_MD_BASE + 4) |
17048 | 0 | #define OPTION_MMNEMONIC (OPTION_MD_BASE + 5) |
17049 | 0 | #define OPTION_MSYNTAX (OPTION_MD_BASE + 6) |
17050 | 0 | #define OPTION_MINDEX_REG (OPTION_MD_BASE + 7) |
17051 | 0 | #define OPTION_MNAKED_REG (OPTION_MD_BASE + 8) |
17052 | 0 | #define OPTION_MRELAX_RELOCATIONS (OPTION_MD_BASE + 9) |
17053 | 0 | #define OPTION_MSSE2AVX (OPTION_MD_BASE + 10) |
17054 | 0 | #define OPTION_MSSE_CHECK (OPTION_MD_BASE + 11) |
17055 | 0 | #define OPTION_MOPERAND_CHECK (OPTION_MD_BASE + 12) |
17056 | 0 | #define OPTION_MAVXSCALAR (OPTION_MD_BASE + 13) |
17057 | 0 | #define OPTION_X32 (OPTION_MD_BASE + 14) |
17058 | 0 | #define OPTION_MADD_BND_PREFIX (OPTION_MD_BASE + 15) |
17059 | 0 | #define OPTION_MEVEXLIG (OPTION_MD_BASE + 16) |
17060 | 0 | #define OPTION_MEVEXWIG (OPTION_MD_BASE + 17) |
17061 | | #define OPTION_MBIG_OBJ (OPTION_MD_BASE + 18) |
17062 | 0 | #define OPTION_MOMIT_LOCK_PREFIX (OPTION_MD_BASE + 19) |
17063 | 0 | #define OPTION_MEVEXRCIG (OPTION_MD_BASE + 20) |
17064 | 0 | #define OPTION_MSHARED (OPTION_MD_BASE + 21) |
17065 | 0 | #define OPTION_MAMD64 (OPTION_MD_BASE + 22) |
17066 | 0 | #define OPTION_MINTEL64 (OPTION_MD_BASE + 23) |
17067 | 0 | #define OPTION_MFENCE_AS_LOCK_ADD (OPTION_MD_BASE + 24) |
17068 | 0 | #define OPTION_X86_USED_NOTE (OPTION_MD_BASE + 25) |
17069 | 0 | #define OPTION_MVEXWIG (OPTION_MD_BASE + 26) |
17070 | 0 | #define OPTION_MALIGN_BRANCH_BOUNDARY (OPTION_MD_BASE + 27) |
17071 | 0 | #define OPTION_MALIGN_BRANCH_PREFIX_SIZE (OPTION_MD_BASE + 28) |
17072 | 0 | #define OPTION_MALIGN_BRANCH (OPTION_MD_BASE + 29) |
17073 | 0 | #define OPTION_MBRANCHES_WITH_32B_BOUNDARIES (OPTION_MD_BASE + 30) |
17074 | 0 | #define OPTION_MLFENCE_AFTER_LOAD (OPTION_MD_BASE + 31) |
17075 | 0 | #define OPTION_MLFENCE_BEFORE_INDIRECT_BRANCH (OPTION_MD_BASE + 32) |
17076 | 0 | #define OPTION_MLFENCE_BEFORE_RET (OPTION_MD_BASE + 33) |
17077 | 0 | #define OPTION_MUSE_UNALIGNED_VECTOR_MOVE (OPTION_MD_BASE + 34) |
17078 | 0 | #define OPTION_MTLS_CHECK (OPTION_MD_BASE + 35) |
17079 | | |
17080 | | const struct option md_longopts[] = |
17081 | | { |
17082 | | {"32", no_argument, NULL, OPTION_32}, |
17083 | | #if (defined (OBJ_ELF) || defined (TE_PE) || defined (OBJ_MACH_O)) \ |
17084 | | && defined (BFD64) |
17085 | | {"64", no_argument, NULL, OPTION_64}, |
17086 | | #endif |
17087 | | #ifdef OBJ_ELF |
17088 | | # ifdef BFD64 |
17089 | | {"x32", no_argument, NULL, OPTION_X32}, |
17090 | | # endif |
17091 | | {"mshared", no_argument, NULL, OPTION_MSHARED}, |
17092 | | {"mx86-used-note", required_argument, NULL, OPTION_X86_USED_NOTE}, |
17093 | | #endif |
17094 | | {"divide", no_argument, NULL, OPTION_DIVIDE}, |
17095 | | {"march", required_argument, NULL, OPTION_MARCH}, |
17096 | | {"mtune", required_argument, NULL, OPTION_MTUNE}, |
17097 | | {"mmnemonic", required_argument, NULL, OPTION_MMNEMONIC}, |
17098 | | {"msyntax", required_argument, NULL, OPTION_MSYNTAX}, |
17099 | | {"mindex-reg", no_argument, NULL, OPTION_MINDEX_REG}, |
17100 | | {"mnaked-reg", no_argument, NULL, OPTION_MNAKED_REG}, |
17101 | | {"msse2avx", no_argument, NULL, OPTION_MSSE2AVX}, |
17102 | | {"muse-unaligned-vector-move", no_argument, NULL, OPTION_MUSE_UNALIGNED_VECTOR_MOVE}, |
17103 | | {"msse-check", required_argument, NULL, OPTION_MSSE_CHECK}, |
17104 | | {"moperand-check", required_argument, NULL, OPTION_MOPERAND_CHECK}, |
17105 | | {"mavxscalar", required_argument, NULL, OPTION_MAVXSCALAR}, |
17106 | | {"mvexwig", required_argument, NULL, OPTION_MVEXWIG}, |
17107 | | {"madd-bnd-prefix", no_argument, NULL, OPTION_MADD_BND_PREFIX}, |
17108 | | {"mevexlig", required_argument, NULL, OPTION_MEVEXLIG}, |
17109 | | {"mevexwig", required_argument, NULL, OPTION_MEVEXWIG}, |
17110 | | # if defined (TE_PE) || defined (TE_PEP) |
17111 | | {"mbig-obj", no_argument, NULL, OPTION_MBIG_OBJ}, |
17112 | | #endif |
17113 | | {"momit-lock-prefix", required_argument, NULL, OPTION_MOMIT_LOCK_PREFIX}, |
17114 | | {"mfence-as-lock-add", required_argument, NULL, OPTION_MFENCE_AS_LOCK_ADD}, |
17115 | | {"mrelax-relocations", required_argument, NULL, OPTION_MRELAX_RELOCATIONS}, |
17116 | | {"mevexrcig", required_argument, NULL, OPTION_MEVEXRCIG}, |
17117 | | {"malign-branch-boundary", required_argument, NULL, OPTION_MALIGN_BRANCH_BOUNDARY}, |
17118 | | {"malign-branch-prefix-size", required_argument, NULL, OPTION_MALIGN_BRANCH_PREFIX_SIZE}, |
17119 | | {"malign-branch", required_argument, NULL, OPTION_MALIGN_BRANCH}, |
17120 | | {"mbranches-within-32B-boundaries", no_argument, NULL, OPTION_MBRANCHES_WITH_32B_BOUNDARIES}, |
17121 | | {"mlfence-after-load", required_argument, NULL, OPTION_MLFENCE_AFTER_LOAD}, |
17122 | | {"mlfence-before-indirect-branch", required_argument, NULL, |
17123 | | OPTION_MLFENCE_BEFORE_INDIRECT_BRANCH}, |
17124 | | {"mlfence-before-ret", required_argument, NULL, OPTION_MLFENCE_BEFORE_RET}, |
17125 | | {"mamd64", no_argument, NULL, OPTION_MAMD64}, |
17126 | | {"mintel64", no_argument, NULL, OPTION_MINTEL64}, |
17127 | | {"mtls-check", required_argument, NULL, OPTION_MTLS_CHECK}, |
17128 | | {NULL, no_argument, NULL, 0} |
17129 | | }; |
17130 | | const size_t md_longopts_size = sizeof (md_longopts); |
17131 | | |
17132 | | int |
17133 | | md_parse_option (int c, const char *arg) |
17134 | 0 | { |
17135 | 0 | unsigned int j; |
17136 | 0 | char *arch, *next, *saved, *type; |
17137 | |
|
17138 | 0 | switch (c) |
17139 | 0 | { |
17140 | 0 | case 'n': |
17141 | 0 | optimize_align_code = 0; |
17142 | 0 | break; |
17143 | | |
17144 | 0 | case 'q': |
17145 | 0 | quiet_warnings = 1; |
17146 | 0 | break; |
17147 | | |
17148 | 0 | #ifdef OBJ_ELF |
17149 | | /* -Qy, -Qn: SVR4 arguments controlling whether a .comment section |
17150 | | should be emitted or not. FIXME: Not implemented. */ |
17151 | 0 | case 'Q': |
17152 | 0 | if ((arg[0] != 'y' && arg[0] != 'n') || arg[1]) |
17153 | 0 | return 0; |
17154 | 0 | break; |
17155 | | |
17156 | | /* -V: SVR4 argument to print version ID. */ |
17157 | 0 | case 'V': |
17158 | 0 | print_version_id (); |
17159 | 0 | break; |
17160 | | |
17161 | | /* -k: Ignore for FreeBSD compatibility. */ |
17162 | 0 | case 'k': |
17163 | 0 | break; |
17164 | | |
17165 | | # ifdef TE_SOLARIS |
17166 | | case 's': |
17167 | | /* -s: On i386 Solaris, this tells the native assembler to use |
17168 | | .stab instead of .stab.excl. We always use .stab anyhow. */ |
17169 | | break; |
17170 | | # endif |
17171 | | |
17172 | 0 | case OPTION_MSHARED: |
17173 | 0 | shared = 1; |
17174 | 0 | break; |
17175 | | |
17176 | 0 | case OPTION_X86_USED_NOTE: |
17177 | 0 | if (strcasecmp (arg, "yes") == 0) |
17178 | 0 | x86_used_note = 1; |
17179 | 0 | else if (strcasecmp (arg, "no") == 0) |
17180 | 0 | x86_used_note = 0; |
17181 | 0 | else |
17182 | 0 | as_fatal (_("invalid -mx86-used-note= option: `%s'"), arg); |
17183 | 0 | break; |
17184 | 0 | #endif |
17185 | | |
17186 | 0 | #ifdef BFD64 |
17187 | | |
17188 | 0 | #if (defined (OBJ_ELF) || defined (TE_PE) || defined (OBJ_MACH_O)) |
17189 | 0 | case OPTION_64: |
17190 | 0 | { |
17191 | 0 | const char **list, **l; |
17192 | |
|
17193 | 0 | list = bfd_target_list (); |
17194 | 0 | for (l = list; *l != NULL; l++) |
17195 | 0 | if (startswith (*l, "elf64-x86-64") |
17196 | 0 | || strcmp (*l, "coff-x86-64") == 0 |
17197 | 0 | || strcmp (*l, "pe-x86-64") == 0 |
17198 | 0 | || strcmp (*l, "pei-x86-64") == 0 |
17199 | 0 | || strcmp (*l, "mach-o-x86-64") == 0) |
17200 | 0 | { |
17201 | 0 | default_arch = "x86_64"; |
17202 | 0 | break; |
17203 | 0 | } |
17204 | 0 | if (*l == NULL) |
17205 | 0 | as_fatal (_("no compiled in support for x86_64")); |
17206 | 0 | free (list); |
17207 | 0 | } |
17208 | 0 | break; |
17209 | 0 | #endif |
17210 | | |
17211 | 0 | #ifdef OBJ_ELF |
17212 | 0 | case OPTION_X32: |
17213 | 0 | { |
17214 | 0 | const char **list, **l; |
17215 | |
|
17216 | 0 | list = bfd_target_list (); |
17217 | 0 | for (l = list; *l != NULL; l++) |
17218 | 0 | if (startswith (*l, "elf32-x86-64")) |
17219 | 0 | { |
17220 | 0 | default_arch = "x86_64:32"; |
17221 | 0 | break; |
17222 | 0 | } |
17223 | 0 | if (*l == NULL) |
17224 | 0 | as_fatal (_("no compiled in support for 32bit x86_64")); |
17225 | 0 | free (list); |
17226 | 0 | } |
17227 | 0 | break; |
17228 | 0 | #endif |
17229 | | |
17230 | 0 | #endif /* BFD64 */ |
17231 | | |
17232 | 0 | case OPTION_32: |
17233 | 0 | { |
17234 | 0 | const char **list, **l; |
17235 | |
|
17236 | 0 | list = bfd_target_list (); |
17237 | 0 | for (l = list; *l != NULL; l++) |
17238 | 0 | if (strstr (*l, "-i386") |
17239 | 0 | || strstr (*l, "-go32")) |
17240 | 0 | { |
17241 | 0 | default_arch = "i386"; |
17242 | 0 | break; |
17243 | 0 | } |
17244 | 0 | if (*l == NULL) |
17245 | 0 | as_fatal (_("no compiled in support for ix86")); |
17246 | 0 | free (list); |
17247 | 0 | } |
17248 | 0 | break; |
17249 | | |
17250 | 0 | case OPTION_DIVIDE: |
17251 | | #ifdef SVR4_COMMENT_CHARS |
17252 | | { |
17253 | | char *n, *t; |
17254 | | const char *s; |
17255 | | |
17256 | | n = XNEWVEC (char, strlen (i386_comment_chars) + 1); |
17257 | | t = n; |
17258 | | for (s = i386_comment_chars; *s != '\0'; s++) |
17259 | | if (*s != '/') |
17260 | | *t++ = *s; |
17261 | | *t = '\0'; |
17262 | | i386_comment_chars = n; |
17263 | | } |
17264 | | #endif |
17265 | 0 | break; |
17266 | | |
17267 | 0 | case OPTION_MARCH: |
17268 | 0 | saved = xstrdup (arg); |
17269 | 0 | arch = saved; |
17270 | | /* Allow -march=+nosse. */ |
17271 | 0 | if (*arch == '+') |
17272 | 0 | arch++; |
17273 | 0 | do |
17274 | 0 | { |
17275 | 0 | char *vsz; |
17276 | |
|
17277 | 0 | if (*arch == '.') |
17278 | 0 | as_fatal (_("invalid -march= option: `%s'"), arg); |
17279 | 0 | next = strchr (arch, '+'); |
17280 | 0 | if (next) |
17281 | 0 | *next++ = '\0'; |
17282 | 0 | vsz = strchr (arch, '/'); |
17283 | 0 | if (vsz) |
17284 | 0 | *vsz++ = '\0'; |
17285 | 0 | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
17286 | 0 | { |
17287 | 0 | if (vsz && cpu_arch[j].vsz != vsz_set) |
17288 | 0 | continue; |
17289 | | |
17290 | 0 | if (arch == saved && cpu_arch[j].type != PROCESSOR_NONE |
17291 | 0 | && strcmp (arch, cpu_arch[j].name) == 0) |
17292 | 0 | { |
17293 | | /* Processor. */ |
17294 | 0 | if (! cpu_arch[j].enable.bitfield.cpui386) |
17295 | 0 | continue; |
17296 | | |
17297 | 0 | cpu_arch_name = cpu_arch[j].name; |
17298 | 0 | free (cpu_sub_arch_name); |
17299 | 0 | cpu_sub_arch_name = NULL; |
17300 | 0 | cpu_arch_flags = cpu_arch[j].enable; |
17301 | 0 | cpu_arch_isa = cpu_arch[j].type; |
17302 | 0 | cpu_arch_isa_flags = cpu_arch[j].enable; |
17303 | 0 | if (!cpu_arch_tune_set) |
17304 | 0 | cpu_arch_tune = cpu_arch_isa; |
17305 | 0 | vector_size = VSZ_DEFAULT; |
17306 | 0 | break; |
17307 | 0 | } |
17308 | 0 | else if (cpu_arch[j].type == PROCESSOR_NONE |
17309 | 0 | && strcmp (arch, cpu_arch[j].name) == 0 |
17310 | 0 | && !cpu_flags_all_zero (&cpu_arch[j].enable)) |
17311 | 0 | { |
17312 | | /* ISA extension. */ |
17313 | 0 | isa_enable (j); |
17314 | |
|
17315 | 0 | switch (cpu_arch[j].vsz) |
17316 | 0 | { |
17317 | 0 | default: |
17318 | 0 | break; |
17319 | | |
17320 | 0 | case vsz_set: |
17321 | 0 | if (vsz) |
17322 | 0 | { |
17323 | 0 | char *end; |
17324 | 0 | unsigned long val = strtoul (vsz, &end, 0); |
17325 | |
|
17326 | 0 | if (*end) |
17327 | 0 | val = 0; |
17328 | 0 | switch (val) |
17329 | 0 | { |
17330 | 0 | case 512: vector_size = VSZ512; break; |
17331 | 0 | case 256: vector_size = VSZ256; break; |
17332 | 0 | case 128: vector_size = VSZ128; break; |
17333 | 0 | default: |
17334 | 0 | as_warn (_("Unrecognized vector size specifier ignored")); |
17335 | 0 | break; |
17336 | 0 | } |
17337 | 0 | break; |
17338 | 0 | } |
17339 | | /* Fall through. */ |
17340 | 0 | case vsz_reset: |
17341 | 0 | vector_size = VSZ_DEFAULT; |
17342 | 0 | break; |
17343 | 0 | } |
17344 | | |
17345 | 0 | break; |
17346 | 0 | } |
17347 | 0 | } |
17348 | | |
17349 | 0 | if (j >= ARRAY_SIZE (cpu_arch) && startswith (arch, "no")) |
17350 | 0 | { |
17351 | | /* Disable an ISA extension. */ |
17352 | 0 | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
17353 | 0 | if (cpu_arch[j].type == PROCESSOR_NONE |
17354 | 0 | && strcmp (arch + 2, cpu_arch[j].name) == 0) |
17355 | 0 | { |
17356 | 0 | isa_disable (j); |
17357 | 0 | if (cpu_arch[j].vsz == vsz_set) |
17358 | 0 | vector_size = VSZ_DEFAULT; |
17359 | 0 | break; |
17360 | 0 | } |
17361 | 0 | } |
17362 | |
|
17363 | 0 | if (j >= ARRAY_SIZE (cpu_arch)) |
17364 | 0 | as_fatal (_("invalid -march= option: `%s'"), arg); |
17365 | | |
17366 | 0 | arch = next; |
17367 | 0 | } |
17368 | 0 | while (next != NULL); |
17369 | 0 | free (saved); |
17370 | 0 | break; |
17371 | | |
17372 | 0 | case OPTION_MTUNE: |
17373 | 0 | if (*arg == '.') |
17374 | 0 | as_fatal (_("invalid -mtune= option: `%s'"), arg); |
17375 | 0 | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
17376 | 0 | { |
17377 | 0 | if (cpu_arch[j].type != PROCESSOR_NONE |
17378 | 0 | && strcmp (arg, cpu_arch[j].name) == 0) |
17379 | 0 | { |
17380 | 0 | cpu_arch_tune_set = 1; |
17381 | 0 | cpu_arch_tune = cpu_arch [j].type; |
17382 | 0 | break; |
17383 | 0 | } |
17384 | 0 | } |
17385 | 0 | if (j >= ARRAY_SIZE (cpu_arch)) |
17386 | 0 | as_fatal (_("invalid -mtune= option: `%s'"), arg); |
17387 | 0 | break; |
17388 | | |
17389 | 0 | case OPTION_MMNEMONIC: |
17390 | 0 | if (strcasecmp (arg, "att") == 0) |
17391 | 0 | intel_mnemonic = 0; |
17392 | 0 | else if (strcasecmp (arg, "intel") == 0) |
17393 | 0 | intel_mnemonic = 1; |
17394 | 0 | else |
17395 | 0 | as_fatal (_("invalid -mmnemonic= option: `%s'"), arg); |
17396 | 0 | break; |
17397 | | |
17398 | 0 | case OPTION_MSYNTAX: |
17399 | 0 | if (strcasecmp (arg, "att") == 0) |
17400 | 0 | _set_intel_syntax (0); |
17401 | 0 | else if (strcasecmp (arg, "intel") == 0) |
17402 | 0 | _set_intel_syntax (1); |
17403 | 0 | else |
17404 | 0 | as_fatal (_("invalid -msyntax= option: `%s'"), arg); |
17405 | 0 | break; |
17406 | | |
17407 | 0 | case OPTION_MINDEX_REG: |
17408 | 0 | allow_index_reg = 1; |
17409 | 0 | break; |
17410 | | |
17411 | 0 | case OPTION_MNAKED_REG: |
17412 | 0 | allow_naked_reg = 1; |
17413 | 0 | register_prefix = ""; |
17414 | 0 | break; |
17415 | | |
17416 | 0 | case OPTION_MSSE2AVX: |
17417 | 0 | sse2avx = 1; |
17418 | 0 | break; |
17419 | | |
17420 | 0 | case OPTION_MUSE_UNALIGNED_VECTOR_MOVE: |
17421 | 0 | use_unaligned_vector_move = 1; |
17422 | 0 | break; |
17423 | | |
17424 | 0 | case OPTION_MSSE_CHECK: |
17425 | 0 | if (strcasecmp (arg, "error") == 0) |
17426 | 0 | sse_check = check_error; |
17427 | 0 | else if (strcasecmp (arg, "warning") == 0) |
17428 | 0 | sse_check = check_warning; |
17429 | 0 | else if (strcasecmp (arg, "none") == 0) |
17430 | 0 | sse_check = check_none; |
17431 | 0 | else |
17432 | 0 | as_fatal (_("invalid -msse-check= option: `%s'"), arg); |
17433 | 0 | break; |
17434 | | |
17435 | 0 | case OPTION_MOPERAND_CHECK: |
17436 | 0 | if (strcasecmp (arg, "error") == 0) |
17437 | 0 | operand_check = check_error; |
17438 | 0 | else if (strcasecmp (arg, "warning") == 0) |
17439 | 0 | operand_check = check_warning; |
17440 | 0 | else if (strcasecmp (arg, "none") == 0) |
17441 | 0 | operand_check = check_none; |
17442 | 0 | else |
17443 | 0 | as_fatal (_("invalid -moperand-check= option: `%s'"), arg); |
17444 | 0 | break; |
17445 | | |
17446 | 0 | case OPTION_MAVXSCALAR: |
17447 | 0 | if (strcasecmp (arg, "128") == 0) |
17448 | 0 | avxscalar = vex128; |
17449 | 0 | else if (strcasecmp (arg, "256") == 0) |
17450 | 0 | avxscalar = vex256; |
17451 | 0 | else |
17452 | 0 | as_fatal (_("invalid -mavxscalar= option: `%s'"), arg); |
17453 | 0 | break; |
17454 | | |
17455 | 0 | case OPTION_MVEXWIG: |
17456 | 0 | if (strcmp (arg, "0") == 0) |
17457 | 0 | vexwig = vexw0; |
17458 | 0 | else if (strcmp (arg, "1") == 0) |
17459 | 0 | vexwig = vexw1; |
17460 | 0 | else |
17461 | 0 | as_fatal (_("invalid -mvexwig= option: `%s'"), arg); |
17462 | 0 | break; |
17463 | | |
17464 | 0 | case OPTION_MADD_BND_PREFIX: |
17465 | 0 | add_bnd_prefix = 1; |
17466 | 0 | break; |
17467 | | |
17468 | 0 | case OPTION_MEVEXLIG: |
17469 | 0 | if (strcmp (arg, "128") == 0) |
17470 | 0 | evexlig = evexl128; |
17471 | 0 | else if (strcmp (arg, "256") == 0) |
17472 | 0 | evexlig = evexl256; |
17473 | 0 | else if (strcmp (arg, "512") == 0) |
17474 | 0 | evexlig = evexl512; |
17475 | 0 | else |
17476 | 0 | as_fatal (_("invalid -mevexlig= option: `%s'"), arg); |
17477 | 0 | break; |
17478 | | |
17479 | 0 | case OPTION_MEVEXRCIG: |
17480 | 0 | if (strcmp (arg, "rne") == 0) |
17481 | 0 | evexrcig = rne; |
17482 | 0 | else if (strcmp (arg, "rd") == 0) |
17483 | 0 | evexrcig = rd; |
17484 | 0 | else if (strcmp (arg, "ru") == 0) |
17485 | 0 | evexrcig = ru; |
17486 | 0 | else if (strcmp (arg, "rz") == 0) |
17487 | 0 | evexrcig = rz; |
17488 | 0 | else |
17489 | 0 | as_fatal (_("invalid -mevexrcig= option: `%s'"), arg); |
17490 | 0 | break; |
17491 | | |
17492 | 0 | case OPTION_MEVEXWIG: |
17493 | 0 | if (strcmp (arg, "0") == 0) |
17494 | 0 | evexwig = evexw0; |
17495 | 0 | else if (strcmp (arg, "1") == 0) |
17496 | 0 | evexwig = evexw1; |
17497 | 0 | else |
17498 | 0 | as_fatal (_("invalid -mevexwig= option: `%s'"), arg); |
17499 | 0 | break; |
17500 | | |
17501 | | # if defined (TE_PE) || defined (TE_PEP) |
17502 | | case OPTION_MBIG_OBJ: |
17503 | | use_big_obj = 1; |
17504 | | break; |
17505 | | #endif |
17506 | | |
17507 | 0 | case OPTION_MOMIT_LOCK_PREFIX: |
17508 | 0 | if (strcasecmp (arg, "yes") == 0) |
17509 | 0 | omit_lock_prefix = 1; |
17510 | 0 | else if (strcasecmp (arg, "no") == 0) |
17511 | 0 | omit_lock_prefix = 0; |
17512 | 0 | else |
17513 | 0 | as_fatal (_("invalid -momit-lock-prefix= option: `%s'"), arg); |
17514 | 0 | break; |
17515 | | |
17516 | 0 | case OPTION_MFENCE_AS_LOCK_ADD: |
17517 | 0 | if (strcasecmp (arg, "yes") == 0) |
17518 | 0 | avoid_fence = 1; |
17519 | 0 | else if (strcasecmp (arg, "no") == 0) |
17520 | 0 | avoid_fence = 0; |
17521 | 0 | else |
17522 | 0 | as_fatal (_("invalid -mfence-as-lock-add= option: `%s'"), arg); |
17523 | 0 | break; |
17524 | | |
17525 | 0 | case OPTION_MLFENCE_AFTER_LOAD: |
17526 | 0 | if (strcasecmp (arg, "yes") == 0) |
17527 | 0 | lfence_after_load = 1; |
17528 | 0 | else if (strcasecmp (arg, "no") == 0) |
17529 | 0 | lfence_after_load = 0; |
17530 | 0 | else |
17531 | 0 | as_fatal (_("invalid -mlfence-after-load= option: `%s'"), arg); |
17532 | 0 | break; |
17533 | | |
17534 | 0 | case OPTION_MLFENCE_BEFORE_INDIRECT_BRANCH: |
17535 | 0 | if (strcasecmp (arg, "all") == 0) |
17536 | 0 | { |
17537 | 0 | lfence_before_indirect_branch = lfence_branch_all; |
17538 | 0 | if (lfence_before_ret == lfence_before_ret_none) |
17539 | 0 | lfence_before_ret = lfence_before_ret_shl; |
17540 | 0 | } |
17541 | 0 | else if (strcasecmp (arg, "memory") == 0) |
17542 | 0 | lfence_before_indirect_branch = lfence_branch_memory; |
17543 | 0 | else if (strcasecmp (arg, "register") == 0) |
17544 | 0 | lfence_before_indirect_branch = lfence_branch_register; |
17545 | 0 | else if (strcasecmp (arg, "none") == 0) |
17546 | 0 | lfence_before_indirect_branch = lfence_branch_none; |
17547 | 0 | else |
17548 | 0 | as_fatal (_("invalid -mlfence-before-indirect-branch= option: `%s'"), |
17549 | 0 | arg); |
17550 | 0 | break; |
17551 | | |
17552 | 0 | case OPTION_MLFENCE_BEFORE_RET: |
17553 | 0 | if (strcasecmp (arg, "or") == 0) |
17554 | 0 | lfence_before_ret = lfence_before_ret_or; |
17555 | 0 | else if (strcasecmp (arg, "not") == 0) |
17556 | 0 | lfence_before_ret = lfence_before_ret_not; |
17557 | 0 | else if (strcasecmp (arg, "shl") == 0 || strcasecmp (arg, "yes") == 0) |
17558 | 0 | lfence_before_ret = lfence_before_ret_shl; |
17559 | 0 | else if (strcasecmp (arg, "none") == 0) |
17560 | 0 | lfence_before_ret = lfence_before_ret_none; |
17561 | 0 | else |
17562 | 0 | as_fatal (_("invalid -mlfence-before-ret= option: `%s'"), |
17563 | 0 | arg); |
17564 | 0 | break; |
17565 | | |
17566 | 0 | case OPTION_MRELAX_RELOCATIONS: |
17567 | 0 | if (strcasecmp (arg, "yes") == 0) |
17568 | 0 | generate_relax_relocations = 1; |
17569 | 0 | else if (strcasecmp (arg, "no") == 0) |
17570 | 0 | generate_relax_relocations = 0; |
17571 | 0 | else |
17572 | 0 | as_fatal (_("invalid -mrelax-relocations= option: `%s'"), arg); |
17573 | 0 | break; |
17574 | | |
17575 | 0 | case OPTION_MALIGN_BRANCH_BOUNDARY: |
17576 | 0 | { |
17577 | 0 | char *end; |
17578 | 0 | long int align = strtoul (arg, &end, 0); |
17579 | 0 | if (*end == '\0') |
17580 | 0 | { |
17581 | 0 | if (align == 0) |
17582 | 0 | { |
17583 | 0 | align_branch_power = 0; |
17584 | 0 | break; |
17585 | 0 | } |
17586 | 0 | else if (align >= 16) |
17587 | 0 | { |
17588 | 0 | int align_power; |
17589 | 0 | for (align_power = 0; |
17590 | 0 | (align & 1) == 0; |
17591 | 0 | align >>= 1, align_power++) |
17592 | 0 | continue; |
17593 | | /* Limit alignment power to 31. */ |
17594 | 0 | if (align == 1 && align_power < 32) |
17595 | 0 | { |
17596 | 0 | align_branch_power = align_power; |
17597 | 0 | break; |
17598 | 0 | } |
17599 | 0 | } |
17600 | 0 | } |
17601 | 0 | as_fatal (_("invalid -malign-branch-boundary= value: %s"), arg); |
17602 | 0 | } |
17603 | 0 | break; |
17604 | | |
17605 | 0 | case OPTION_MALIGN_BRANCH_PREFIX_SIZE: |
17606 | 0 | { |
17607 | 0 | char *end; |
17608 | 0 | int align = strtoul (arg, &end, 0); |
17609 | | /* Some processors only support 5 prefixes. */ |
17610 | 0 | if (*end == '\0' && align >= 0 && align < 6) |
17611 | 0 | { |
17612 | 0 | align_branch_prefix_size = align; |
17613 | 0 | break; |
17614 | 0 | } |
17615 | 0 | as_fatal (_("invalid -malign-branch-prefix-size= value: %s"), |
17616 | 0 | arg); |
17617 | 0 | } |
17618 | 0 | break; |
17619 | | |
17620 | 0 | case OPTION_MALIGN_BRANCH: |
17621 | 0 | align_branch = 0; |
17622 | 0 | saved = xstrdup (arg); |
17623 | 0 | type = saved; |
17624 | 0 | do |
17625 | 0 | { |
17626 | 0 | next = strchr (type, '+'); |
17627 | 0 | if (next) |
17628 | 0 | *next++ = '\0'; |
17629 | 0 | if (strcasecmp (type, "jcc") == 0) |
17630 | 0 | align_branch |= align_branch_jcc_bit; |
17631 | 0 | else if (strcasecmp (type, "fused") == 0) |
17632 | 0 | align_branch |= align_branch_fused_bit; |
17633 | 0 | else if (strcasecmp (type, "jmp") == 0) |
17634 | 0 | align_branch |= align_branch_jmp_bit; |
17635 | 0 | else if (strcasecmp (type, "call") == 0) |
17636 | 0 | align_branch |= align_branch_call_bit; |
17637 | 0 | else if (strcasecmp (type, "ret") == 0) |
17638 | 0 | align_branch |= align_branch_ret_bit; |
17639 | 0 | else if (strcasecmp (type, "indirect") == 0) |
17640 | 0 | align_branch |= align_branch_indirect_bit; |
17641 | 0 | else |
17642 | 0 | as_fatal (_("invalid -malign-branch= option: `%s'"), arg); |
17643 | 0 | type = next; |
17644 | 0 | } |
17645 | 0 | while (next != NULL); |
17646 | 0 | free (saved); |
17647 | 0 | break; |
17648 | | |
17649 | 0 | case OPTION_MBRANCHES_WITH_32B_BOUNDARIES: |
17650 | 0 | align_branch_power = 5; |
17651 | 0 | align_branch_prefix_size = 5; |
17652 | 0 | align_branch = (align_branch_jcc_bit |
17653 | 0 | | align_branch_fused_bit |
17654 | 0 | | align_branch_jmp_bit); |
17655 | 0 | break; |
17656 | | |
17657 | 0 | case OPTION_MAMD64: |
17658 | 0 | isa64 = amd64; |
17659 | 0 | break; |
17660 | | |
17661 | 0 | case OPTION_MINTEL64: |
17662 | 0 | isa64 = intel64; |
17663 | 0 | break; |
17664 | | |
17665 | 0 | case 'O': |
17666 | 0 | if (arg == NULL) |
17667 | 0 | { |
17668 | 0 | optimize = 1; |
17669 | | /* Turn off -Os. */ |
17670 | 0 | optimize_for_space = 0; |
17671 | 0 | } |
17672 | 0 | else if (*arg == 's') |
17673 | 0 | { |
17674 | 0 | optimize_for_space = 1; |
17675 | | /* Turn on all encoding optimizations. */ |
17676 | 0 | optimize = INT_MAX; |
17677 | 0 | } |
17678 | 0 | else |
17679 | 0 | { |
17680 | 0 | optimize = atoi (arg); |
17681 | | /* Turn off -Os. */ |
17682 | 0 | optimize_for_space = 0; |
17683 | 0 | } |
17684 | 0 | break; |
17685 | 0 | case OPTION_MTLS_CHECK: |
17686 | 0 | if (strcasecmp (arg, "yes") == 0) |
17687 | 0 | tls_check = true; |
17688 | 0 | else if (strcasecmp (arg, "no") == 0) |
17689 | 0 | tls_check = false; |
17690 | 0 | else |
17691 | 0 | as_fatal (_("invalid -mtls-check= option: `%s'"), arg); |
17692 | 0 | break; |
17693 | | |
17694 | 0 | default: |
17695 | 0 | return 0; |
17696 | 0 | } |
17697 | 0 | return 1; |
17698 | 0 | } |
17699 | | |
17700 | 0 | #define MESSAGE_TEMPLATE \ |
17701 | 0 | " " |
17702 | | |
17703 | | static char * |
17704 | | output_message (FILE *stream, char *p, char *message, char *start, |
17705 | | int *left_p, const char *name, int len) |
17706 | 0 | { |
17707 | 0 | int size = sizeof (MESSAGE_TEMPLATE); |
17708 | 0 | int left = *left_p; |
17709 | | |
17710 | | /* Reserve 2 spaces for ", " or ",\0" */ |
17711 | 0 | left -= len + 2; |
17712 | | |
17713 | | /* Check if there is any room. */ |
17714 | 0 | if (left >= 0) |
17715 | 0 | { |
17716 | 0 | if (p != start) |
17717 | 0 | { |
17718 | 0 | *p++ = ','; |
17719 | 0 | *p++ = ' '; |
17720 | 0 | } |
17721 | 0 | p = mempcpy (p, name, len); |
17722 | 0 | } |
17723 | 0 | else |
17724 | 0 | { |
17725 | | /* Output the current message now and start a new one. */ |
17726 | 0 | *p++ = ','; |
17727 | 0 | *p = '\0'; |
17728 | 0 | fprintf (stream, "%s\n", message); |
17729 | 0 | p = start; |
17730 | 0 | left = size - (start - message) - len - 2; |
17731 | |
|
17732 | 0 | gas_assert (left >= 0); |
17733 | | |
17734 | 0 | p = mempcpy (p, name, len); |
17735 | 0 | } |
17736 | | |
17737 | 0 | *left_p = left; |
17738 | 0 | return p; |
17739 | 0 | } |
17740 | | |
17741 | | static void |
17742 | | show_arch (FILE *stream, int ext, int check) |
17743 | 0 | { |
17744 | 0 | static char message[] = MESSAGE_TEMPLATE; |
17745 | 0 | char *start = message + 27; |
17746 | 0 | char *p; |
17747 | 0 | int size = sizeof (MESSAGE_TEMPLATE); |
17748 | 0 | int left; |
17749 | 0 | const char *name; |
17750 | 0 | int len; |
17751 | 0 | unsigned int j; |
17752 | |
|
17753 | 0 | p = start; |
17754 | 0 | left = size - (start - message); |
17755 | |
|
17756 | 0 | if (!ext && check) |
17757 | 0 | { |
17758 | 0 | p = output_message (stream, p, message, start, &left, |
17759 | 0 | STRING_COMMA_LEN ("default")); |
17760 | 0 | p = output_message (stream, p, message, start, &left, |
17761 | 0 | STRING_COMMA_LEN ("push")); |
17762 | 0 | p = output_message (stream, p, message, start, &left, |
17763 | 0 | STRING_COMMA_LEN ("pop")); |
17764 | 0 | } |
17765 | |
|
17766 | 0 | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
17767 | 0 | { |
17768 | | /* Should it be skipped? */ |
17769 | 0 | if (cpu_arch [j].skip) |
17770 | 0 | continue; |
17771 | | |
17772 | 0 | name = cpu_arch [j].name; |
17773 | 0 | len = cpu_arch [j].len; |
17774 | 0 | if (cpu_arch[j].type == PROCESSOR_NONE) |
17775 | 0 | { |
17776 | | /* It is an extension. Skip if we aren't asked to show it. */ |
17777 | 0 | if (!ext || cpu_flags_all_zero (&cpu_arch[j].enable)) |
17778 | 0 | continue; |
17779 | 0 | } |
17780 | 0 | else if (ext) |
17781 | 0 | { |
17782 | | /* It is an processor. Skip if we show only extension. */ |
17783 | 0 | continue; |
17784 | 0 | } |
17785 | 0 | else if (check && ! cpu_arch[j].enable.bitfield.cpui386) |
17786 | 0 | { |
17787 | | /* It is an impossible processor - skip. */ |
17788 | 0 | continue; |
17789 | 0 | } |
17790 | | |
17791 | 0 | p = output_message (stream, p, message, start, &left, name, len); |
17792 | 0 | } |
17793 | | |
17794 | | /* Display disabled extensions. */ |
17795 | 0 | if (ext) |
17796 | 0 | for (j = 0; j < ARRAY_SIZE (cpu_arch); j++) |
17797 | 0 | { |
17798 | 0 | char *str; |
17799 | |
|
17800 | 0 | if (cpu_arch[j].type != PROCESSOR_NONE |
17801 | 0 | || !cpu_flags_all_zero (&cpu_arch[j].enable)) |
17802 | 0 | continue; |
17803 | 0 | str = xasprintf ("no%s", cpu_arch[j].name); |
17804 | 0 | p = output_message (stream, p, message, start, &left, str, |
17805 | 0 | strlen (str)); |
17806 | 0 | free (str); |
17807 | 0 | } |
17808 | |
|
17809 | 0 | *p = '\0'; |
17810 | 0 | fprintf (stream, "%s\n", message); |
17811 | 0 | } |
17812 | | |
17813 | | void |
17814 | | md_show_usage (FILE *stream) |
17815 | 0 | { |
17816 | 0 | #ifdef OBJ_ELF |
17817 | 0 | fprintf (stream, _("\ |
17818 | 0 | -Qy, -Qn ignored\n\ |
17819 | 0 | -V print assembler version number\n\ |
17820 | 0 | -k ignored\n")); |
17821 | 0 | #endif |
17822 | 0 | fprintf (stream, _("\ |
17823 | 0 | -n do not optimize code alignment\n\ |
17824 | 0 | -O{012s} attempt some code optimizations\n\ |
17825 | 0 | -q quieten some warnings\n")); |
17826 | 0 | #ifdef OBJ_ELF |
17827 | 0 | fprintf (stream, _("\ |
17828 | 0 | -s ignored\n")); |
17829 | 0 | #endif |
17830 | 0 | #ifdef BFD64 |
17831 | 0 | # ifdef OBJ_ELF |
17832 | 0 | fprintf (stream, _("\ |
17833 | 0 | --32/--64/--x32 generate 32bit/64bit/x32 object\n")); |
17834 | | # elif defined (TE_PE) || defined (TE_PEP) || defined (OBJ_MACH_O) |
17835 | | fprintf (stream, _("\ |
17836 | | --32/--64 generate 32bit/64bit object\n")); |
17837 | | # endif |
17838 | 0 | #endif |
17839 | | #ifdef SVR4_COMMENT_CHARS |
17840 | | fprintf (stream, _("\ |
17841 | | --divide do not treat `/' as a comment character\n")); |
17842 | | #else |
17843 | 0 | fprintf (stream, _("\ |
17844 | 0 | --divide ignored\n")); |
17845 | 0 | #endif |
17846 | 0 | fprintf (stream, _("\ |
17847 | 0 | -march=CPU[,+EXTENSION...]\n\ |
17848 | 0 | generate code for CPU and EXTENSION, CPU is one of:\n")); |
17849 | 0 | show_arch (stream, 0, 1); |
17850 | 0 | fprintf (stream, _("\ |
17851 | 0 | EXTENSION is combination of (possibly \"no\"-prefixed):\n")); |
17852 | 0 | show_arch (stream, 1, 0); |
17853 | 0 | fprintf (stream, _("\ |
17854 | 0 | -mtune=CPU optimize for CPU, CPU is one of:\n")); |
17855 | 0 | show_arch (stream, 0, 0); |
17856 | 0 | fprintf (stream, _("\ |
17857 | 0 | -msse2avx encode SSE instructions with VEX prefix\n")); |
17858 | 0 | fprintf (stream, _("\ |
17859 | 0 | -muse-unaligned-vector-move\n\ |
17860 | 0 | encode aligned vector move as unaligned vector move\n")); |
17861 | 0 | fprintf (stream, _("\ |
17862 | 0 | -msse-check=[none|error|warning] (default: none)\n\ |
17863 | 0 | check SSE instructions\n")); |
17864 | 0 | fprintf (stream, _("\ |
17865 | 0 | -moperand-check=[none|error|warning] (default: warning)\n\ |
17866 | 0 | check operand combinations for validity\n")); |
17867 | 0 | fprintf (stream, _("\ |
17868 | 0 | -mavxscalar=[128|256] (default: 128)\n\ |
17869 | 0 | encode scalar AVX instructions with specific vector\n\ |
17870 | 0 | length\n")); |
17871 | 0 | fprintf (stream, _("\ |
17872 | 0 | -mvexwig=[0|1] (default: 0)\n\ |
17873 | 0 | encode VEX instructions with specific VEX.W value\n\ |
17874 | 0 | for VEX.W bit ignored instructions\n")); |
17875 | 0 | fprintf (stream, _("\ |
17876 | 0 | -mevexlig=[128|256|512] (default: 128)\n\ |
17877 | 0 | encode scalar EVEX instructions with specific vector\n\ |
17878 | 0 | length\n")); |
17879 | 0 | fprintf (stream, _("\ |
17880 | 0 | -mevexwig=[0|1] (default: 0)\n\ |
17881 | 0 | encode EVEX instructions with specific EVEX.W value\n\ |
17882 | 0 | for EVEX.W bit ignored instructions\n")); |
17883 | 0 | fprintf (stream, _("\ |
17884 | 0 | -mevexrcig=[rne|rd|ru|rz] (default: rne)\n\ |
17885 | 0 | encode EVEX instructions with specific EVEX.RC value\n\ |
17886 | 0 | for SAE-only ignored instructions\n")); |
17887 | 0 | fprintf (stream, _("\ |
17888 | 0 | -mmnemonic=[att|intel] ")); |
17889 | 0 | if (SYSV386_COMPAT) |
17890 | 0 | fprintf (stream, _("(default: att)\n")); |
17891 | 0 | else |
17892 | 0 | fprintf (stream, _("(default: intel)\n")); |
17893 | 0 | fprintf (stream, _("\ |
17894 | 0 | use AT&T/Intel mnemonic (AT&T syntax only)\n")); |
17895 | 0 | fprintf (stream, _("\ |
17896 | 0 | -msyntax=[att|intel] (default: att)\n\ |
17897 | 0 | use AT&T/Intel syntax\n")); |
17898 | 0 | fprintf (stream, _("\ |
17899 | 0 | -mindex-reg support pseudo index registers\n")); |
17900 | 0 | fprintf (stream, _("\ |
17901 | 0 | -mnaked-reg don't require `%%' prefix for registers\n")); |
17902 | 0 | fprintf (stream, _("\ |
17903 | 0 | -madd-bnd-prefix add BND prefix for all valid branches\n")); |
17904 | 0 | #ifdef OBJ_ELF |
17905 | 0 | fprintf (stream, _("\ |
17906 | 0 | -mshared disable branch optimization for shared code\n")); |
17907 | 0 | fprintf (stream, _("\ |
17908 | 0 | -mx86-used-note=[no|yes] ")); |
17909 | 0 | if (DEFAULT_X86_USED_NOTE) |
17910 | 0 | fprintf (stream, _("(default: yes)\n")); |
17911 | 0 | else |
17912 | 0 | fprintf (stream, _("(default: no)\n")); |
17913 | 0 | fprintf (stream, _("\ |
17914 | 0 | generate x86 used ISA and feature properties\n")); |
17915 | 0 | #endif |
17916 | | #if defined (TE_PE) || defined (TE_PEP) |
17917 | | fprintf (stream, _("\ |
17918 | | -mbig-obj generate big object files\n")); |
17919 | | #endif |
17920 | 0 | fprintf (stream, _("\ |
17921 | 0 | -momit-lock-prefix=[no|yes] (default: no)\n\ |
17922 | 0 | strip all lock prefixes\n")); |
17923 | 0 | fprintf (stream, _("\ |
17924 | 0 | -mfence-as-lock-add=[no|yes] (default: no)\n\ |
17925 | 0 | encode lfence, mfence and sfence as\n\ |
17926 | 0 | lock addl $0x0, (%%{re}sp)\n")); |
17927 | 0 | fprintf (stream, _("\ |
17928 | 0 | -mrelax-relocations=[no|yes] ")); |
17929 | 0 | if (DEFAULT_GENERATE_X86_RELAX_RELOCATIONS) |
17930 | 0 | fprintf (stream, _("(default: yes)\n")); |
17931 | 0 | else |
17932 | 0 | fprintf (stream, _("(default: no)\n")); |
17933 | 0 | fprintf (stream, _("\ |
17934 | 0 | generate relax relocations\n")); |
17935 | 0 | #ifdef OBJ_ELF |
17936 | 0 | fprintf (stream, _("\ |
17937 | 0 | -mtls-check=[no|yes] ")); |
17938 | 0 | if (DEFAULT_X86_TLS_CHECK) |
17939 | 0 | fprintf (stream, _("(default: yes)\n")); |
17940 | 0 | else |
17941 | 0 | fprintf (stream, _("(default: no)\n")); |
17942 | 0 | fprintf (stream, _("\ |
17943 | 0 | check TLS relocation\n")); |
17944 | 0 | #endif |
17945 | 0 | fprintf (stream, _("\ |
17946 | 0 | -malign-branch-boundary=NUM (default: 0)\n\ |
17947 | 0 | align branches within NUM byte boundary\n")); |
17948 | 0 | fprintf (stream, _("\ |
17949 | 0 | -malign-branch=TYPE[+TYPE...] (default: jcc+fused+jmp)\n\ |
17950 | 0 | TYPE is combination of jcc, fused, jmp, call, ret,\n\ |
17951 | 0 | indirect\n\ |
17952 | 0 | specify types of branches to align\n")); |
17953 | 0 | fprintf (stream, _("\ |
17954 | 0 | -malign-branch-prefix-size=NUM (default: 5)\n\ |
17955 | 0 | align branches with NUM prefixes per instruction\n")); |
17956 | 0 | fprintf (stream, _("\ |
17957 | 0 | -mbranches-within-32B-boundaries\n\ |
17958 | 0 | align branches within 32 byte boundary\n")); |
17959 | 0 | fprintf (stream, _("\ |
17960 | 0 | -mlfence-after-load=[no|yes] (default: no)\n\ |
17961 | 0 | generate lfence after load\n")); |
17962 | 0 | fprintf (stream, _("\ |
17963 | 0 | -mlfence-before-indirect-branch=[none|all|register|memory] (default: none)\n\ |
17964 | 0 | generate lfence before indirect near branch\n")); |
17965 | 0 | fprintf (stream, _("\ |
17966 | 0 | -mlfence-before-ret=[none|or|not|shl|yes] (default: none)\n\ |
17967 | 0 | generate lfence before ret\n")); |
17968 | 0 | fprintf (stream, _("\ |
17969 | 0 | -mamd64 accept only AMD64 ISA [default]\n")); |
17970 | 0 | fprintf (stream, _("\ |
17971 | 0 | -mintel64 accept only Intel64 ISA\n")); |
17972 | 0 | } |
17973 | | |
17974 | | #if (defined (OBJ_ELF) || defined (TE_PE) || defined (OBJ_MACH_O)) |
17975 | | |
17976 | | /* Pick the target format to use. */ |
17977 | | |
17978 | | const char * |
17979 | | i386_target_format (void) |
17980 | 28 | { |
17981 | 28 | if (startswith (default_arch, "x86_64")) |
17982 | 28 | { |
17983 | 28 | update_code_flag (CODE_64BIT, 1); |
17984 | 28 | #ifdef OBJ_ELF |
17985 | 28 | if (default_arch[6] == '\0') |
17986 | 28 | x86_elf_abi = X86_64_ABI; |
17987 | 0 | else |
17988 | 0 | x86_elf_abi = X86_64_X32_ABI; |
17989 | 28 | #endif |
17990 | 28 | } |
17991 | 0 | else if (!strcmp (default_arch, "i386")) |
17992 | 0 | update_code_flag (CODE_32BIT, 1); |
17993 | 0 | else if (!strcmp (default_arch, "iamcu")) |
17994 | 0 | { |
17995 | 0 | update_code_flag (CODE_32BIT, 1); |
17996 | 0 | if (cpu_arch_isa == PROCESSOR_UNKNOWN) |
17997 | 0 | { |
17998 | 0 | static const i386_cpu_flags iamcu_flags = CPU_IAMCU_FLAGS; |
17999 | 0 | cpu_arch_name = "iamcu"; |
18000 | 0 | free (cpu_sub_arch_name); |
18001 | 0 | cpu_sub_arch_name = NULL; |
18002 | 0 | cpu_arch_flags = iamcu_flags; |
18003 | 0 | cpu_arch_isa = PROCESSOR_IAMCU; |
18004 | 0 | cpu_arch_isa_flags = iamcu_flags; |
18005 | 0 | if (!cpu_arch_tune_set) |
18006 | 0 | cpu_arch_tune = PROCESSOR_IAMCU; |
18007 | 0 | } |
18008 | 0 | else if (cpu_arch_isa != PROCESSOR_IAMCU) |
18009 | 0 | as_fatal (_("Intel MCU doesn't support `%s' architecture"), |
18010 | 0 | cpu_arch_name); |
18011 | 0 | } |
18012 | 0 | else |
18013 | 0 | as_fatal (_("unknown architecture")); |
18014 | | |
18015 | 28 | #ifdef OBJ_ELF |
18016 | 28 | if (flag_synth_cfi && x86_elf_abi != X86_64_ABI) |
18017 | 0 | as_fatal (_("SCFI is not supported for this ABI")); |
18018 | 28 | #endif |
18019 | | |
18020 | 28 | if (cpu_flags_all_zero (&cpu_arch_isa_flags)) |
18021 | 1 | cpu_arch_isa_flags = cpu_arch[flag_code == CODE_64BIT].enable; |
18022 | | |
18023 | 28 | switch (OUTPUT_FLAVOR) |
18024 | 28 | { |
18025 | | #ifdef TE_PE |
18026 | | case bfd_target_coff_flavour: |
18027 | | if (flag_code == CODE_64BIT) |
18028 | | { |
18029 | | object_64bit = 1; |
18030 | | return use_big_obj ? "pe-bigobj-x86-64" : "pe-x86-64"; |
18031 | | } |
18032 | | return use_big_obj ? "pe-bigobj-i386" : "pe-i386"; |
18033 | | #endif |
18034 | 0 | #ifdef OBJ_ELF |
18035 | 28 | case bfd_target_elf_flavour: |
18036 | 28 | { |
18037 | 28 | const char *format; |
18038 | | |
18039 | 28 | switch (x86_elf_abi) |
18040 | 28 | { |
18041 | 0 | default: |
18042 | 0 | format = ELF_TARGET_FORMAT; |
18043 | 0 | #ifndef TE_SOLARIS |
18044 | 0 | tls_get_addr = "___tls_get_addr"; |
18045 | 0 | #endif |
18046 | 0 | break; |
18047 | 28 | case X86_64_ABI: |
18048 | 28 | use_rela_relocations = 1; |
18049 | 28 | object_64bit = 1; |
18050 | 28 | #ifndef TE_SOLARIS |
18051 | 28 | tls_get_addr = "__tls_get_addr"; |
18052 | 28 | #endif |
18053 | 28 | format = ELF_TARGET_FORMAT64; |
18054 | 28 | break; |
18055 | 0 | case X86_64_X32_ABI: |
18056 | 0 | use_rela_relocations = 1; |
18057 | 0 | object_64bit = 1; |
18058 | 0 | #ifndef TE_SOLARIS |
18059 | 0 | tls_get_addr = "__tls_get_addr"; |
18060 | 0 | #endif |
18061 | 0 | disallow_64bit_reloc = 1; |
18062 | 0 | format = ELF_TARGET_FORMAT32; |
18063 | 0 | break; |
18064 | 28 | } |
18065 | 28 | if (cpu_arch_isa == PROCESSOR_IAMCU) |
18066 | 0 | { |
18067 | 0 | if (x86_elf_abi != I386_ABI) |
18068 | 0 | as_fatal (_("Intel MCU is 32bit only")); |
18069 | 0 | return ELF_TARGET_IAMCU_FORMAT; |
18070 | 0 | } |
18071 | 28 | else |
18072 | 28 | return format; |
18073 | 28 | } |
18074 | 0 | #endif |
18075 | | #if defined (OBJ_MACH_O) |
18076 | | case bfd_target_mach_o_flavour: |
18077 | | if (flag_code == CODE_64BIT) |
18078 | | { |
18079 | | use_rela_relocations = 1; |
18080 | | object_64bit = 1; |
18081 | | return "mach-o-x86-64"; |
18082 | | } |
18083 | | else |
18084 | | return "mach-o-i386"; |
18085 | | #endif |
18086 | 0 | default: |
18087 | 0 | abort (); |
18088 | 0 | return NULL; |
18089 | 28 | } |
18090 | 28 | } |
18091 | | |
18092 | | #endif /* ELF / PE / MACH_O */ |
18093 | | |
18094 | | #ifdef OBJ_ELF |
18095 | | symbolS * |
18096 | | md_undefined_symbol (char *name) |
18097 | 6.23k | { |
18098 | 6.23k | if (name[0] == GLOBAL_OFFSET_TABLE_NAME[0] |
18099 | 6.23k | && name[1] == GLOBAL_OFFSET_TABLE_NAME[1] |
18100 | 6.23k | && name[2] == GLOBAL_OFFSET_TABLE_NAME[2] |
18101 | 6.23k | && strcmp (name, GLOBAL_OFFSET_TABLE_NAME) == 0) |
18102 | 12 | { |
18103 | 12 | if (!GOT_symbol) |
18104 | 12 | { |
18105 | 12 | if (symbol_find (name)) |
18106 | 0 | as_bad (_("GOT already in symbol table")); |
18107 | 12 | GOT_symbol = symbol_new (name, undefined_section, |
18108 | 12 | &zero_address_frag, 0); |
18109 | 12 | }; |
18110 | 12 | return GOT_symbol; |
18111 | 12 | } |
18112 | 6.21k | return NULL; |
18113 | 6.23k | } |
18114 | | #endif |
18115 | | |
18116 | | #ifdef OBJ_AOUT |
18117 | | /* Round up a section size to the appropriate boundary. */ |
18118 | | |
18119 | | valueT |
18120 | | md_section_align (segT segment, valueT size) |
18121 | | { |
18122 | | /* For a.out, force the section size to be aligned. If we don't do |
18123 | | this, BFD will align it for us, but it will not write out the |
18124 | | final bytes of the section. This may be a bug in BFD, but it is |
18125 | | easier to fix it here since that is how the other a.out targets |
18126 | | work. */ |
18127 | | int align = bfd_section_alignment (segment); |
18128 | | |
18129 | | return ((size + (1 << align) - 1) & (-((valueT) 1 << align))); |
18130 | | } |
18131 | | #endif |
18132 | | |
18133 | | /* On the i386, PC-relative offsets are relative to the start of the |
18134 | | next instruction. That is, the address of the offset, plus its |
18135 | | size, since the offset is always the last part of the insn. */ |
18136 | | |
18137 | | long |
18138 | | md_pcrel_from (fixS *fixP) |
18139 | 0 | { |
18140 | 0 | return fixP->fx_size + fixP->fx_where + fixP->fx_frag->fr_address; |
18141 | 0 | } |
18142 | | |
18143 | | #ifdef OBJ_AOUT |
18144 | | |
18145 | | static void |
18146 | | s_bss (int ignore ATTRIBUTE_UNUSED) |
18147 | | { |
18148 | | int temp; |
18149 | | |
18150 | | temp = get_absolute_expression (); |
18151 | | subseg_set (bss_section, (subsegT) temp); |
18152 | | demand_empty_rest_of_line (); |
18153 | | } |
18154 | | |
18155 | | #endif |
18156 | | |
18157 | | /* Remember constant directive. */ |
18158 | | |
18159 | | void |
18160 | | i386_cons_align (int ignore ATTRIBUTE_UNUSED) |
18161 | 6.90k | { |
18162 | 6.90k | struct last_insn *last_insn |
18163 | 6.90k | = &seg_info(now_seg)->tc_segment_info_data.last_insn; |
18164 | | |
18165 | 6.90k | if (bfd_section_flags (now_seg) & SEC_CODE) |
18166 | 3.65k | { |
18167 | 3.65k | last_insn->kind = last_insn_directive; |
18168 | 3.65k | last_insn->name = "constant directive"; |
18169 | 3.65k | last_insn->file = as_where (&last_insn->line); |
18170 | 3.65k | } |
18171 | 6.90k | } |
18172 | | |
18173 | | int |
18174 | | i386_validate_fix (fixS *fixp) |
18175 | 0 | { |
18176 | 0 | if (fixp->fx_addsy && S_GET_SEGMENT(fixp->fx_addsy) == reg_section) |
18177 | 0 | { |
18178 | 0 | reloc_howto_type *howto; |
18179 | |
|
18180 | 0 | howto = bfd_reloc_type_lookup (stdoutput, fixp->fx_r_type); |
18181 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18182 | 0 | _("invalid %s relocation against register"), |
18183 | 0 | howto ? howto->name : "<unknown>"); |
18184 | 0 | return 0; |
18185 | 0 | } |
18186 | | |
18187 | 0 | #ifdef OBJ_ELF |
18188 | 0 | if (fixp->fx_r_type == BFD_RELOC_SIZE32 |
18189 | 0 | || fixp->fx_r_type == BFD_RELOC_SIZE64) |
18190 | 0 | return fixp->fx_addsy |
18191 | 0 | && (!S_IS_DEFINED (fixp->fx_addsy) |
18192 | 0 | || S_IS_EXTERNAL (fixp->fx_addsy)); |
18193 | | |
18194 | | /* BFD_RELOC_X86_64_GOTTPOFF: |
18195 | | 1. fx_tcbit -> BFD_RELOC_X86_64_CODE_4_GOTTPOFF |
18196 | | 2. fx_tcbit2 -> BFD_RELOC_X86_64_CODE_5_GOTTPOFF |
18197 | | 3. fx_tcbit3 -> BFD_RELOC_X86_64_CODE_6_GOTTPOFF |
18198 | | BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
18199 | | 1. fx_tcbit -> BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC |
18200 | | BFD_RELOC_32_PCREL: |
18201 | | 1. fx_tcbit && fx_tcbit3 -> BFD_RELOC_X86_64_CODE_5_GOTPCRELX |
18202 | | 2. fx_tcbit -> BFD_RELOC_X86_64_GOTPCRELX |
18203 | | 3. fx_tcbit2 && fx_tcbit3 -> BFD_RELOC_X86_64_CODE_6_GOTPCRELX |
18204 | | 4. fx_tcbit2 -> BFD_RELOC_X86_64_REX_GOTPCRELX |
18205 | | 5. fx_tcbit3 -> BFD_RELOC_X86_64_CODE_4_GOTPCRELX |
18206 | | 6. else -> BFD_RELOC_X86_64_GOTPCREL |
18207 | | */ |
18208 | 0 | if (fixp->fx_r_type == BFD_RELOC_X86_64_GOTTPOFF) |
18209 | 0 | { |
18210 | 0 | if (fixp->fx_tcbit) |
18211 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_CODE_4_GOTTPOFF; |
18212 | 0 | else if (fixp->fx_tcbit2) |
18213 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_CODE_5_GOTTPOFF; |
18214 | 0 | else if (fixp->fx_tcbit3) |
18215 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_CODE_6_GOTTPOFF; |
18216 | 0 | } |
18217 | 0 | else if (fixp->fx_r_type == BFD_RELOC_X86_64_GOTPC32_TLSDESC |
18218 | 0 | && fixp->fx_tcbit) |
18219 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC; |
18220 | 0 | #endif |
18221 | |
|
18222 | 0 | if (fixp->fx_subsy) |
18223 | 0 | { |
18224 | 0 | if (fixp->fx_subsy == GOT_symbol) |
18225 | 0 | { |
18226 | 0 | if (fixp->fx_r_type == BFD_RELOC_32_PCREL) |
18227 | 0 | { |
18228 | 0 | if (!object_64bit) |
18229 | 0 | abort (); |
18230 | 0 | #ifdef OBJ_ELF |
18231 | 0 | if (fixp->fx_tcbit) |
18232 | 0 | fixp->fx_r_type = fixp->fx_tcbit3 |
18233 | 0 | ? BFD_RELOC_X86_64_CODE_5_GOTPCRELX |
18234 | 0 | : BFD_RELOC_X86_64_GOTPCRELX; |
18235 | 0 | else if (fixp->fx_tcbit2) |
18236 | 0 | fixp->fx_r_type = fixp->fx_tcbit3 |
18237 | 0 | ? BFD_RELOC_X86_64_CODE_6_GOTPCRELX |
18238 | 0 | : BFD_RELOC_X86_64_REX_GOTPCRELX; |
18239 | 0 | else if (fixp->fx_tcbit3) |
18240 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_CODE_4_GOTPCRELX; |
18241 | 0 | else |
18242 | 0 | #endif |
18243 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_GOTPCREL; |
18244 | 0 | } |
18245 | 0 | else |
18246 | 0 | { |
18247 | 0 | if (!object_64bit) |
18248 | 0 | fixp->fx_r_type = BFD_RELOC_386_GOTOFF; |
18249 | 0 | else |
18250 | 0 | fixp->fx_r_type = BFD_RELOC_X86_64_GOTOFF64; |
18251 | 0 | } |
18252 | 0 | fixp->fx_subsy = 0; |
18253 | 0 | } |
18254 | 0 | } |
18255 | 0 | #ifdef OBJ_ELF |
18256 | 0 | else |
18257 | 0 | { |
18258 | | /* NB: Commit 292676c1 resolved PLT32 reloc aganst local symbol |
18259 | | to section. Since PLT32 relocation must be against symbols, |
18260 | | turn such PLT32 relocation into PC32 relocation. NB: We can |
18261 | | turn PLT32 relocation into PC32 relocation only for PC-relative |
18262 | | relocations since non-PC-relative relocations need PLT entries. |
18263 | | */ |
18264 | 0 | if (fixp->fx_addsy |
18265 | 0 | && fixp->fx_pcrel |
18266 | 0 | && (fixp->fx_r_type == BFD_RELOC_386_PLT32 |
18267 | 0 | || fixp->fx_r_type == BFD_RELOC_X86_64_PLT32) |
18268 | 0 | && symbol_section_p (fixp->fx_addsy)) |
18269 | 0 | fixp->fx_r_type = BFD_RELOC_32_PCREL; |
18270 | 0 | if (!object_64bit) |
18271 | 0 | { |
18272 | 0 | if (fixp->fx_r_type == BFD_RELOC_386_GOT32 |
18273 | 0 | && fixp->fx_tcbit2) |
18274 | 0 | fixp->fx_r_type = BFD_RELOC_386_GOT32X; |
18275 | 0 | } |
18276 | 0 | } |
18277 | 0 | #endif |
18278 | | |
18279 | 0 | return 1; |
18280 | 0 | } |
18281 | | |
18282 | | arelent * |
18283 | | tc_gen_reloc (asection *section ATTRIBUTE_UNUSED, fixS *fixp) |
18284 | 0 | { |
18285 | 0 | arelent *rel; |
18286 | 0 | bfd_reloc_code_real_type code; |
18287 | |
|
18288 | 0 | switch (fixp->fx_r_type) |
18289 | 0 | { |
18290 | 0 | #ifdef OBJ_ELF |
18291 | 0 | symbolS *sym; |
18292 | | |
18293 | 0 | case BFD_RELOC_SIZE32: |
18294 | 0 | case BFD_RELOC_SIZE64: |
18295 | 0 | if (fixp->fx_addsy |
18296 | 0 | && !bfd_is_abs_section (S_GET_SEGMENT (fixp->fx_addsy)) |
18297 | 0 | && (!fixp->fx_subsy |
18298 | 0 | || bfd_is_abs_section (S_GET_SEGMENT (fixp->fx_subsy)))) |
18299 | 0 | sym = fixp->fx_addsy; |
18300 | 0 | else if (fixp->fx_subsy |
18301 | 0 | && !bfd_is_abs_section (S_GET_SEGMENT (fixp->fx_subsy)) |
18302 | 0 | && (!fixp->fx_addsy |
18303 | 0 | || bfd_is_abs_section (S_GET_SEGMENT (fixp->fx_addsy)))) |
18304 | 0 | sym = fixp->fx_subsy; |
18305 | 0 | else |
18306 | 0 | sym = NULL; |
18307 | 0 | if (sym && S_IS_DEFINED (sym) && !S_IS_EXTERNAL (sym)) |
18308 | 0 | { |
18309 | | /* Resolve size relocation against local symbol to size of |
18310 | | the symbol plus addend. */ |
18311 | 0 | valueT value = S_GET_SIZE (sym); |
18312 | |
|
18313 | 0 | if (symbol_get_bfdsym (sym)->flags & BSF_SECTION_SYM) |
18314 | 0 | value = bfd_section_size (S_GET_SEGMENT (sym)); |
18315 | 0 | if (sym == fixp->fx_subsy) |
18316 | 0 | { |
18317 | 0 | value = -value; |
18318 | 0 | if (fixp->fx_addsy) |
18319 | 0 | value += S_GET_VALUE (fixp->fx_addsy); |
18320 | 0 | } |
18321 | 0 | else if (fixp->fx_subsy) |
18322 | 0 | value -= S_GET_VALUE (fixp->fx_subsy); |
18323 | 0 | value += fixp->fx_offset; |
18324 | 0 | if (fixp->fx_r_type == BFD_RELOC_SIZE32 |
18325 | 0 | && object_64bit |
18326 | 0 | && !fits_in_unsigned_long (value)) |
18327 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18328 | 0 | _("symbol size computation overflow")); |
18329 | 0 | fixp->fx_addsy = NULL; |
18330 | 0 | fixp->fx_subsy = NULL; |
18331 | 0 | md_apply_fix (fixp, (valueT *) &value, NULL); |
18332 | 0 | return NULL; |
18333 | 0 | } |
18334 | 0 | if (!fixp->fx_addsy || fixp->fx_subsy) |
18335 | 0 | { |
18336 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18337 | 0 | "unsupported expression involving @size"); |
18338 | 0 | return NULL; |
18339 | 0 | } |
18340 | 0 | #endif |
18341 | | /* Fall through. */ |
18342 | | |
18343 | 0 | case BFD_RELOC_X86_64_PLT32: |
18344 | 0 | case BFD_RELOC_X86_64_GOT32: |
18345 | 0 | case BFD_RELOC_X86_64_GOTPCREL: |
18346 | 0 | case BFD_RELOC_X86_64_GOTPCRELX: |
18347 | 0 | case BFD_RELOC_X86_64_REX_GOTPCRELX: |
18348 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPCRELX: |
18349 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPCRELX: |
18350 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPCRELX: |
18351 | 0 | case BFD_RELOC_386_PLT32: |
18352 | 0 | case BFD_RELOC_386_GOT32: |
18353 | 0 | case BFD_RELOC_386_GOT32X: |
18354 | 0 | case BFD_RELOC_386_GOTOFF: |
18355 | 0 | case BFD_RELOC_386_GOTPC: |
18356 | 0 | case BFD_RELOC_386_TLS_GD: |
18357 | 0 | case BFD_RELOC_386_TLS_LDM: |
18358 | 0 | case BFD_RELOC_386_TLS_LDO_32: |
18359 | 0 | case BFD_RELOC_386_TLS_IE_32: |
18360 | 0 | case BFD_RELOC_386_TLS_IE: |
18361 | 0 | case BFD_RELOC_386_TLS_GOTIE: |
18362 | 0 | case BFD_RELOC_386_TLS_LE_32: |
18363 | 0 | case BFD_RELOC_386_TLS_LE: |
18364 | 0 | case BFD_RELOC_386_TLS_GOTDESC: |
18365 | 0 | case BFD_RELOC_386_TLS_DESC_CALL: |
18366 | 0 | case BFD_RELOC_X86_64_TLSGD: |
18367 | 0 | case BFD_RELOC_X86_64_TLSLD: |
18368 | 0 | case BFD_RELOC_X86_64_DTPOFF32: |
18369 | 0 | case BFD_RELOC_X86_64_DTPOFF64: |
18370 | 0 | case BFD_RELOC_X86_64_GOTTPOFF: |
18371 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTTPOFF: |
18372 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTTPOFF: |
18373 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTTPOFF: |
18374 | 0 | case BFD_RELOC_X86_64_TPOFF32: |
18375 | 0 | case BFD_RELOC_X86_64_TPOFF64: |
18376 | 0 | case BFD_RELOC_X86_64_GOTOFF64: |
18377 | 0 | case BFD_RELOC_X86_64_GOTPC32: |
18378 | 0 | case BFD_RELOC_X86_64_GOT64: |
18379 | 0 | case BFD_RELOC_X86_64_GOTPCREL64: |
18380 | 0 | case BFD_RELOC_X86_64_GOTPC64: |
18381 | 0 | case BFD_RELOC_X86_64_GOTPLT64: |
18382 | 0 | case BFD_RELOC_X86_64_PLTOFF64: |
18383 | 0 | case BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
18384 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC: |
18385 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPC32_TLSDESC: |
18386 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPC32_TLSDESC: |
18387 | 0 | case BFD_RELOC_X86_64_TLSDESC_CALL: |
18388 | 0 | case BFD_RELOC_RVA: |
18389 | 0 | case BFD_RELOC_VTABLE_ENTRY: |
18390 | 0 | case BFD_RELOC_VTABLE_INHERIT: |
18391 | | #ifdef TE_PE |
18392 | | case BFD_RELOC_32_SECREL: |
18393 | | case BFD_RELOC_16_SECIDX: |
18394 | | #endif |
18395 | 0 | code = fixp->fx_r_type; |
18396 | 0 | break; |
18397 | 0 | case BFD_RELOC_X86_64_32S: |
18398 | 0 | if (!fixp->fx_pcrel) |
18399 | 0 | { |
18400 | | /* Don't turn BFD_RELOC_X86_64_32S into BFD_RELOC_32. */ |
18401 | 0 | code = fixp->fx_r_type; |
18402 | 0 | break; |
18403 | 0 | } |
18404 | | /* Fall through. */ |
18405 | 0 | default: |
18406 | 0 | if (fixp->fx_pcrel) |
18407 | 0 | { |
18408 | 0 | switch (fixp->fx_size) |
18409 | 0 | { |
18410 | 0 | default: |
18411 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18412 | 0 | _("can not do %d byte pc-relative relocation"), |
18413 | 0 | fixp->fx_size); |
18414 | 0 | code = BFD_RELOC_32_PCREL; |
18415 | 0 | break; |
18416 | 0 | case 1: code = BFD_RELOC_8_PCREL; break; |
18417 | 0 | case 2: code = BFD_RELOC_16_PCREL; break; |
18418 | 0 | case 4: code = BFD_RELOC_32_PCREL; break; |
18419 | 0 | #ifdef BFD64 |
18420 | 0 | case 8: code = BFD_RELOC_64_PCREL; break; |
18421 | 0 | #endif |
18422 | 0 | } |
18423 | 0 | } |
18424 | 0 | else |
18425 | 0 | { |
18426 | 0 | switch (fixp->fx_size) |
18427 | 0 | { |
18428 | 0 | default: |
18429 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18430 | 0 | _("can not do %d byte relocation"), |
18431 | 0 | fixp->fx_size); |
18432 | 0 | code = BFD_RELOC_32; |
18433 | 0 | break; |
18434 | 0 | case 1: code = BFD_RELOC_8; break; |
18435 | 0 | case 2: code = BFD_RELOC_16; break; |
18436 | 0 | case 4: code = BFD_RELOC_32; break; |
18437 | 0 | #ifdef BFD64 |
18438 | 0 | case 8: code = BFD_RELOC_64; break; |
18439 | 0 | #endif |
18440 | 0 | } |
18441 | 0 | } |
18442 | 0 | break; |
18443 | 0 | } |
18444 | | |
18445 | 0 | if ((code == BFD_RELOC_32 |
18446 | 0 | || code == BFD_RELOC_32_PCREL |
18447 | 0 | || code == BFD_RELOC_X86_64_32S) |
18448 | 0 | && GOT_symbol |
18449 | 0 | && fixp->fx_addsy == GOT_symbol) |
18450 | 0 | { |
18451 | 0 | if (!object_64bit) |
18452 | 0 | code = BFD_RELOC_386_GOTPC; |
18453 | 0 | else |
18454 | 0 | code = BFD_RELOC_X86_64_GOTPC32; |
18455 | 0 | } |
18456 | 0 | if ((code == BFD_RELOC_64 || code == BFD_RELOC_64_PCREL) |
18457 | 0 | && GOT_symbol |
18458 | 0 | && fixp->fx_addsy == GOT_symbol) |
18459 | 0 | { |
18460 | 0 | code = BFD_RELOC_X86_64_GOTPC64; |
18461 | 0 | } |
18462 | |
|
18463 | 0 | rel = notes_alloc (sizeof (arelent)); |
18464 | 0 | rel->sym_ptr_ptr = notes_alloc (sizeof (asymbol *)); |
18465 | 0 | *rel->sym_ptr_ptr = symbol_get_bfdsym (fixp->fx_addsy); |
18466 | |
|
18467 | 0 | rel->address = fixp->fx_frag->fr_address + fixp->fx_where; |
18468 | |
|
18469 | 0 | if (!use_rela_relocations) |
18470 | 0 | { |
18471 | | /* HACK: Since i386 ELF uses Rel instead of Rela, encode the |
18472 | | vtable entry to be used in the relocation's section offset. */ |
18473 | 0 | if (fixp->fx_r_type == BFD_RELOC_VTABLE_ENTRY) |
18474 | 0 | rel->address = fixp->fx_offset; |
18475 | | #if defined (OBJ_COFF) && defined (TE_PE) |
18476 | | else if (fixp->fx_addsy && S_IS_WEAK (fixp->fx_addsy)) |
18477 | | rel->addend = fixp->fx_addnumber - (S_GET_VALUE (fixp->fx_addsy) * 2); |
18478 | | else |
18479 | | #endif |
18480 | 0 | rel->addend = 0; |
18481 | 0 | } |
18482 | | /* Use the rela in 64bit mode. */ |
18483 | 0 | else |
18484 | 0 | { |
18485 | 0 | if (disallow_64bit_reloc) |
18486 | 0 | switch (code) |
18487 | 0 | { |
18488 | 0 | case BFD_RELOC_X86_64_DTPOFF64: |
18489 | 0 | case BFD_RELOC_X86_64_TPOFF64: |
18490 | 0 | case BFD_RELOC_64_PCREL: |
18491 | 0 | case BFD_RELOC_X86_64_GOTOFF64: |
18492 | 0 | case BFD_RELOC_X86_64_GOT64: |
18493 | 0 | case BFD_RELOC_X86_64_GOTPCREL64: |
18494 | 0 | case BFD_RELOC_X86_64_GOTPC64: |
18495 | 0 | case BFD_RELOC_X86_64_GOTPLT64: |
18496 | 0 | case BFD_RELOC_X86_64_PLTOFF64: |
18497 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18498 | 0 | _("cannot represent relocation type %s in x32 mode"), |
18499 | 0 | bfd_get_reloc_code_name (code)); |
18500 | 0 | break; |
18501 | 0 | default: |
18502 | 0 | break; |
18503 | 0 | } |
18504 | | |
18505 | 0 | if (!fixp->fx_pcrel) |
18506 | 0 | rel->addend = fixp->fx_offset; |
18507 | 0 | else |
18508 | 0 | switch (code) |
18509 | 0 | { |
18510 | 0 | case BFD_RELOC_X86_64_PLT32: |
18511 | 0 | case BFD_RELOC_X86_64_GOT32: |
18512 | 0 | case BFD_RELOC_X86_64_GOTPCREL: |
18513 | 0 | case BFD_RELOC_X86_64_GOTPCRELX: |
18514 | 0 | case BFD_RELOC_X86_64_REX_GOTPCRELX: |
18515 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPCRELX: |
18516 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPCRELX: |
18517 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPCRELX: |
18518 | 0 | case BFD_RELOC_X86_64_TLSGD: |
18519 | 0 | case BFD_RELOC_X86_64_TLSLD: |
18520 | 0 | case BFD_RELOC_X86_64_GOTTPOFF: |
18521 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTTPOFF: |
18522 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTTPOFF: |
18523 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTTPOFF: |
18524 | 0 | case BFD_RELOC_X86_64_GOTPC32_TLSDESC: |
18525 | 0 | case BFD_RELOC_X86_64_CODE_4_GOTPC32_TLSDESC: |
18526 | 0 | case BFD_RELOC_X86_64_CODE_5_GOTPC32_TLSDESC: |
18527 | 0 | case BFD_RELOC_X86_64_CODE_6_GOTPC32_TLSDESC: |
18528 | 0 | case BFD_RELOC_X86_64_TLSDESC_CALL: |
18529 | 0 | rel->addend = fixp->fx_offset - fixp->fx_size; |
18530 | 0 | break; |
18531 | 0 | default: |
18532 | 0 | rel->addend = (section->vma |
18533 | 0 | - fixp->fx_size |
18534 | 0 | + fixp->fx_addnumber |
18535 | 0 | + md_pcrel_from (fixp)); |
18536 | 0 | break; |
18537 | 0 | } |
18538 | 0 | } |
18539 | | |
18540 | 0 | rel->howto = bfd_reloc_type_lookup (stdoutput, code); |
18541 | 0 | if (rel->howto == NULL) |
18542 | 0 | { |
18543 | 0 | as_bad_where (fixp->fx_file, fixp->fx_line, |
18544 | 0 | _("cannot represent relocation type %s"), |
18545 | 0 | bfd_get_reloc_code_name (code)); |
18546 | | /* Set howto to a garbage value so that we can keep going. */ |
18547 | 0 | rel->howto = bfd_reloc_type_lookup (stdoutput, BFD_RELOC_32); |
18548 | 0 | gas_assert (rel->howto != NULL); |
18549 | 0 | } |
18550 | | |
18551 | 0 | return rel; |
18552 | 0 | } |
18553 | | |
18554 | | #include "tc-i386-intel.c" |
18555 | | |
18556 | | void |
18557 | | tc_x86_parse_to_dw2regnum (expressionS *exp) |
18558 | 4 | { |
18559 | 4 | int saved_naked_reg; |
18560 | 4 | char saved_register_dot; |
18561 | | |
18562 | 4 | saved_naked_reg = allow_naked_reg; |
18563 | 4 | allow_naked_reg = 1; |
18564 | 4 | saved_register_dot = register_chars['.']; |
18565 | 4 | register_chars['.'] = '.'; |
18566 | 4 | allow_pseudo_reg = 1; |
18567 | 4 | expression_and_evaluate (exp); |
18568 | 4 | allow_pseudo_reg = 0; |
18569 | 4 | register_chars['.'] = saved_register_dot; |
18570 | 4 | allow_naked_reg = saved_naked_reg; |
18571 | | |
18572 | 4 | if (exp->X_op == O_register && exp->X_add_number >= 0) |
18573 | 0 | { |
18574 | 0 | exp->X_op = O_illegal; |
18575 | 0 | if ((addressT) exp->X_add_number < i386_regtab_size) |
18576 | 0 | { |
18577 | 0 | exp->X_add_number = i386_regtab[exp->X_add_number] |
18578 | 0 | .dw2_regnum[object_64bit]; |
18579 | 0 | if (exp->X_add_number != Dw2Inval) |
18580 | 0 | exp->X_op = O_constant; |
18581 | 0 | } |
18582 | 0 | } |
18583 | 4 | } |
18584 | | |
18585 | | void |
18586 | | tc_x86_frame_initial_instructions (void) |
18587 | 5 | { |
18588 | 5 | cfi_add_CFA_def_cfa (object_64bit ? REG_SP : 4, -x86_cie_data_alignment); |
18589 | 5 | cfi_add_CFA_offset (x86_dwarf2_return_column, x86_cie_data_alignment); |
18590 | 5 | } |
18591 | | |
18592 | | int |
18593 | | x86_dwarf2_addr_size (void) |
18594 | 13 | { |
18595 | 13 | #ifdef OBJ_ELF |
18596 | 13 | if (x86_elf_abi == X86_64_X32_ABI) |
18597 | 0 | return 4; |
18598 | 13 | #endif |
18599 | 13 | return bfd_arch_bits_per_address (stdoutput) / 8; |
18600 | 13 | } |
18601 | | |
18602 | | #ifdef TE_PE |
18603 | | void |
18604 | | tc_pe_dwarf2_emit_offset (symbolS *symbol, unsigned int size) |
18605 | | { |
18606 | | expressionS exp; |
18607 | | |
18608 | | exp.X_op = O_secrel; |
18609 | | exp.X_add_symbol = symbol; |
18610 | | exp.X_add_number = 0; |
18611 | | emit_expr (&exp, size); |
18612 | | } |
18613 | | #endif |
18614 | | |
18615 | | #ifdef OBJ_ELF |
18616 | | int |
18617 | | i386_elf_section_type (const char *str, size_t len) |
18618 | 0 | { |
18619 | 0 | if (flag_code == CODE_64BIT |
18620 | 0 | && len == sizeof ("unwind") - 1 |
18621 | 0 | && startswith (str, "unwind")) |
18622 | 0 | return SHT_X86_64_UNWIND; |
18623 | | |
18624 | 0 | return -1; |
18625 | 0 | } |
18626 | | |
18627 | | void |
18628 | | i386_elf_section_change_hook (void) |
18629 | 2.53k | { |
18630 | 2.53k | struct i386_segment_info *info = &seg_info(now_seg)->tc_segment_info_data; |
18631 | 2.53k | struct i386_segment_info *curr, *prev; |
18632 | | |
18633 | 2.53k | if (info->subseg == now_subseg) |
18634 | 2.09k | return; |
18635 | | |
18636 | | /* Find the (or make a) list entry to save state into. */ |
18637 | 1.31k | for (prev = info; (curr = prev->next) != NULL; prev = curr) |
18638 | 1.26k | if (curr->subseg == info->subseg) |
18639 | 390 | break; |
18640 | 440 | if (!curr) |
18641 | 50 | { |
18642 | 50 | curr = notes_alloc (sizeof (*curr)); |
18643 | 50 | curr->subseg = info->subseg; |
18644 | 50 | curr->next = NULL; |
18645 | 50 | prev->next = curr; |
18646 | 50 | } |
18647 | 440 | curr->last_insn = info->last_insn; |
18648 | | |
18649 | | /* Find the list entry to load state from. */ |
18650 | 1.34k | for (curr = info->next; curr; curr = curr->next) |
18651 | 1.30k | if (curr->subseg == now_subseg) |
18652 | 400 | break; |
18653 | 440 | if (curr) |
18654 | 400 | info->last_insn = curr->last_insn; |
18655 | 40 | else |
18656 | 40 | memset (&info->last_insn, 0, sizeof (info->last_insn)); |
18657 | 440 | info->subseg = now_subseg; |
18658 | 440 | } |
18659 | | |
18660 | | #ifdef TE_SOLARIS |
18661 | | void |
18662 | | i386_solaris_fix_up_eh_frame (segT sec) |
18663 | | { |
18664 | | if (flag_code == CODE_64BIT) |
18665 | | elf_section_type (sec) = SHT_X86_64_UNWIND; |
18666 | | } |
18667 | | #endif |
18668 | | |
18669 | | /* For ELF on x86-64, add support for SHF_X86_64_LARGE. */ |
18670 | | |
18671 | | bfd_vma |
18672 | | x86_64_section_letter (int letter, const char **ptr_msg) |
18673 | 0 | { |
18674 | 0 | if (flag_code == CODE_64BIT) |
18675 | 0 | { |
18676 | 0 | if (letter == 'l') |
18677 | 0 | return SHF_X86_64_LARGE; |
18678 | | |
18679 | 0 | *ptr_msg = _("bad .section directive: want a,l,w,x,M,S,G,T in string"); |
18680 | 0 | } |
18681 | 0 | else |
18682 | 0 | *ptr_msg = _("bad .section directive: want a,w,x,M,S,G,T in string"); |
18683 | 0 | return -1; |
18684 | 0 | } |
18685 | | |
18686 | | static void |
18687 | | handle_large_common (int small ATTRIBUTE_UNUSED) |
18688 | 0 | { |
18689 | 0 | if (flag_code != CODE_64BIT) |
18690 | 0 | { |
18691 | 0 | s_comm_internal (0, elf_common_parse); |
18692 | 0 | as_warn (_(".largecomm supported only in 64bit mode, producing .comm")); |
18693 | 0 | } |
18694 | 0 | else |
18695 | 0 | { |
18696 | 0 | static segT lbss_section; |
18697 | 0 | asection *saved_com_section_ptr = elf_com_section_ptr; |
18698 | 0 | asection *saved_bss_section = bss_section; |
18699 | |
|
18700 | 0 | if (lbss_section == NULL) |
18701 | 0 | { |
18702 | 0 | flagword applicable; |
18703 | 0 | segT seg = now_seg; |
18704 | 0 | subsegT subseg = now_subseg; |
18705 | | |
18706 | | /* The .lbss section is for local .largecomm symbols. */ |
18707 | 0 | lbss_section = subseg_new (".lbss", 0); |
18708 | 0 | applicable = bfd_applicable_section_flags (stdoutput); |
18709 | 0 | bfd_set_section_flags (lbss_section, applicable & SEC_ALLOC); |
18710 | 0 | seg_info (lbss_section)->bss = 1; |
18711 | |
|
18712 | 0 | subseg_set (seg, subseg); |
18713 | 0 | } |
18714 | |
|
18715 | 0 | elf_com_section_ptr = &_bfd_elf_large_com_section; |
18716 | 0 | bss_section = lbss_section; |
18717 | |
|
18718 | 0 | s_comm_internal (0, elf_common_parse); |
18719 | |
|
18720 | 0 | elf_com_section_ptr = saved_com_section_ptr; |
18721 | 0 | bss_section = saved_bss_section; |
18722 | 0 | } |
18723 | 0 | } |
18724 | | #endif /* OBJ_ELF */ |