www.gitorious.org Git - gnutls:gnutls.git/blob - lib/accelerated/x86/macosx/padlock-x86-64-macosx.s

1 /*

4 #

5 # Redistribution and use in source and binary forms, with or without

6 # modification, are permitted provided that the following conditions

7 # are met:

8 #

9 # * Redistributions of source code must retain copyright notices,

10 # this list of conditions and the following disclaimer.

11 #

12 # * Redistributions in binary form must reproduce the above

13 # copyright notice, this list of conditions and the following

14 # disclaimer in the documentation and/or other materials

15 # provided with the distribution.

16 #

17 # * Neither the name of the Andy Polyakov nor the names of its

18 # copyright holder and contributors may be used to endorse or

19 # promote products derived from this software without specific

20 # prior written permission.

21 #

22 # ALTERNATIVELY, provided that this notice is retained in full, this

23 # product may be distributed under the terms of the GNU General Public

24 # License (GPL), in which case the provisions of the GPL apply INSTEAD OF

25 # those given above.

26 #

27 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS

28 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

29 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

30 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT

31 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,

32 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT

33 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,

34 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY

35 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

36 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

37 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

38 #

39 # *** This file is auto-generated ***

40 #

41 */

42 .text

43 .globl _padlock_capability

45 .p2align 4

46 _padlock_capability:

47 movq %rbx,%r8

48 xorl %eax,%eax

49 cpuid

50 xorl %eax,%eax

51 cmpl $1953391939,%ebx

52 jne L$noluck

53 cmpl $1215460705,%edx

54 jne L$noluck

55 cmpl $1936487777,%ecx

56 jne L$noluck

57 movl $3221225472,%eax

58 cpuid

59 movl %eax,%edx

60 xorl %eax,%eax

61 cmpl $3221225473,%edx

62 jb L$noluck

63 movl $3221225473,%eax

64 cpuid

65 movl %edx,%eax

66 andl $4294967279,%eax

67 orl $16,%eax

68 L$noluck:

69 movq %r8,%rbx

70 .byte 0xf3,0xc3

73 .globl _padlock_key_bswap

75 .p2align 4

76 _padlock_key_bswap:

77 movl 240(%rdi),%edx

78 L$bswap_loop:

79 movl (%rdi),%eax

80 bswapl %eax

81 movl %eax,(%rdi)

82 leaq 4(%rdi),%rdi

83 subl $1,%edx

84 jnz L$bswap_loop

85 .byte 0xf3,0xc3

88 .globl _padlock_verify_context

90 .p2align 4

91 _padlock_verify_context:

92 movq %rdi,%rdx

93 pushf

94 leaq L$padlock_saved_context(%rip),%rax

95 call _padlock_verify_ctx

96 leaq 8(%rsp),%rsp

97 .byte 0xf3,0xc3

100

101 .p2align 4

102 _padlock_verify_ctx:

103 movq 8(%rsp),%r8

104 btq $30,%r8

105 jnc L$verified

106 cmpq (%rax),%rdx

107 je L$verified

108 pushf

109 popf

110 L$verified:

111 movq %rdx,(%rax)

112 .byte 0xf3,0xc3

113

114

115 .globl _padlock_reload_key

116

117 .p2align 4

118 _padlock_reload_key:

119 pushf

120 popf

121 .byte 0xf3,0xc3

122

123

124 .globl _padlock_aes_block

125

126 .p2align 4

127 _padlock_aes_block:

128 movq %rbx,%r8

129 movq $1,%rcx

130 leaq 32(%rdx),%rbx

131 leaq 16(%rdx),%rdx

132 .byte 0xf3,0x0f,0xa7,0xc8

133 movq %r8,%rbx

134 .byte 0xf3,0xc3

135

136

137 .globl _padlock_xstore

138

139 .p2align 4

140 _padlock_xstore:

141 movl %esi,%edx

142 .byte 0x0f,0xa7,0xc0

143 .byte 0xf3,0xc3

144

145

146 .globl _padlock_sha1_oneshot

147

148 .p2align 4

149 _padlock_sha1_oneshot:

150 movq %rdx,%rcx

151 movq %rdi,%rdx

152 movups (%rdi),%xmm0

153 subq $128+8,%rsp

154 movl 16(%rdi),%eax

155 movaps %xmm0,(%rsp)

156 movq %rsp,%rdi

157 movl %eax,16(%rsp)

158 xorq %rax,%rax

159 .byte 0xf3,0x0f,0xa6,0xc8

160 movaps (%rsp),%xmm0

161 movl 16(%rsp),%eax

162 addq $128+8,%rsp

163 movups %xmm0,(%rdx)

164 movl %eax,16(%rdx)

165 .byte 0xf3,0xc3

166

167

168 .globl _padlock_sha1_blocks

169

170 .p2align 4

171 _padlock_sha1_blocks:

172 movq %rdx,%rcx

173 movq %rdi,%rdx

174 movups (%rdi),%xmm0

175 subq $128+8,%rsp

176 movl 16(%rdi),%eax

177 movaps %xmm0,(%rsp)

178 movq %rsp,%rdi

179 movl %eax,16(%rsp)

180 movq $-1,%rax

181 .byte 0xf3,0x0f,0xa6,0xc8

182 movaps (%rsp),%xmm0

183 movl 16(%rsp),%eax

184 addq $128+8,%rsp

185 movups %xmm0,(%rdx)

186 movl %eax,16(%rdx)

187 .byte 0xf3,0xc3

188

189

190 .globl _padlock_sha256_oneshot

191

192 .p2align 4

193 _padlock_sha256_oneshot:

194 movq %rdx,%rcx

195 movq %rdi,%rdx

196 movups (%rdi),%xmm0

197 subq $128+8,%rsp

198 movups 16(%rdi),%xmm1

199 movaps %xmm0,(%rsp)

200 movq %rsp,%rdi

201 movaps %xmm1,16(%rsp)

202 xorq %rax,%rax

203 .byte 0xf3,0x0f,0xa6,0xd0

204 movaps (%rsp),%xmm0

205 movaps 16(%rsp),%xmm1

206 addq $128+8,%rsp

207 movups %xmm0,(%rdx)

208 movups %xmm1,16(%rdx)

209 .byte 0xf3,0xc3

210

211

212 .globl _padlock_sha256_blocks

213

214 .p2align 4

215 _padlock_sha256_blocks:

216 movq %rdx,%rcx

217 movq %rdi,%rdx

218 movups (%rdi),%xmm0

219 subq $128+8,%rsp

220 movups 16(%rdi),%xmm1

221 movaps %xmm0,(%rsp)

222 movq %rsp,%rdi

223 movaps %xmm1,16(%rsp)

224 movq $-1,%rax

225 .byte 0xf3,0x0f,0xa6,0xd0

226 movaps (%rsp),%xmm0

227 movaps 16(%rsp),%xmm1

228 addq $128+8,%rsp

229 movups %xmm0,(%rdx)

230 movups %xmm1,16(%rdx)

231 .byte 0xf3,0xc3

232

233

234 .globl _padlock_sha512_blocks

235

236 .p2align 4

237 _padlock_sha512_blocks:

238 movq %rdx,%rcx

239 movq %rdi,%rdx

240 movups (%rdi),%xmm0

241 subq $128+8,%rsp

242 movups 16(%rdi),%xmm1

243 movups 32(%rdi),%xmm2

244 movups 48(%rdi),%xmm3

245 movaps %xmm0,(%rsp)

246 movq %rsp,%rdi

247 movaps %xmm1,16(%rsp)

248 movaps %xmm2,32(%rsp)

249 movaps %xmm3,48(%rsp)

250 .byte 0xf3,0x0f,0xa6,0xe0

251 movaps (%rsp),%xmm0

252 movaps 16(%rsp),%xmm1

253 movaps 32(%rsp),%xmm2

254 movaps 48(%rsp),%xmm3

255 addq $128+8,%rsp

256 movups %xmm0,(%rdx)

257 movups %xmm1,16(%rdx)

258 movups %xmm2,32(%rdx)

259 movups %xmm3,48(%rdx)

260 .byte 0xf3,0xc3

261

262 .globl _padlock_ecb_encrypt

263

264 .p2align 4

265 _padlock_ecb_encrypt:

266 pushq %rbp

267 pushq %rbx

268

269 xorl %eax,%eax

270 testq $15,%rdx

271 jnz L$ecb_abort

272 testq $15,%rcx

273 jnz L$ecb_abort

274 leaq L$padlock_saved_context(%rip),%rax

275 pushf

276 cld

277 call _padlock_verify_ctx

278 leaq 16(%rdx),%rdx

279 xorl %eax,%eax

280 xorl %ebx,%ebx

281 testl $32,(%rdx)

282 jnz L$ecb_aligned

283 testq $15,%rdi

284 setz %al

285 testq $15,%rsi

286 setz %bl

287 testl %ebx,%eax

288 jnz L$ecb_aligned

289 negq %rax

290 movq $512,%rbx

291 notq %rax

292 leaq (%rsp),%rbp

293 cmpq %rbx,%rcx

294 cmovcq %rcx,%rbx

295 andq %rbx,%rax

296 movq %rcx,%rbx

297 negq %rax

298 andq $512-1,%rbx

299 leaq (%rax,%rbp,1),%rsp

300 movq $512,%rax

301 cmovzq %rax,%rbx

302 cmpq %rbx,%rcx

303 ja L$ecb_loop

304 movq %rsi,%rax

305 cmpq %rsp,%rbp

306 cmoveq %rdi,%rax

307 addq %rcx,%rax

308 negq %rax

309 andq $4095,%rax

310 cmpq $128,%rax

311 movq $-128,%rax

312 cmovaeq %rbx,%rax

313 andq %rax,%rbx

314 jz L$ecb_unaligned_tail

315 jmp L$ecb_loop

316 .p2align 4

317 L$ecb_loop:

318 cmpq %rcx,%rbx

319 cmovaq %rcx,%rbx

320 movq %rdi,%r8

321 movq %rsi,%r9

322 movq %rcx,%r10

323 movq %rbx,%rcx

324 movq %rbx,%r11

325 testq $15,%rdi

326 cmovnzq %rsp,%rdi

327 testq $15,%rsi

328 jz L$ecb_inp_aligned

329 shrq $3,%rcx

330 .byte 0xf3,0x48,0xa5

331 subq %rbx,%rdi

332 movq %rbx,%rcx

333 movq %rdi,%rsi

334 L$ecb_inp_aligned:

335 leaq -16(%rdx),%rax

336 leaq 16(%rdx),%rbx

337 shrq $4,%rcx

338 .byte 0xf3,0x0f,0xa7,200

339 movq %r8,%rdi

340 movq %r11,%rbx

341 testq $15,%rdi

342 jz L$ecb_out_aligned

343 movq %rbx,%rcx

344 leaq (%rsp),%rsi

345 shrq $3,%rcx

346 .byte 0xf3,0x48,0xa5

347 subq %rbx,%rdi

348 L$ecb_out_aligned:

349 movq %r9,%rsi

350 movq %r10,%rcx

351 addq %rbx,%rdi

352 addq %rbx,%rsi

353 subq %rbx,%rcx

354 movq $512,%rbx

355 jz L$ecb_break

356 cmpq %rbx,%rcx

357 jae L$ecb_loop

358 L$ecb_unaligned_tail:

359 xorl %eax,%eax

360 cmpq %rsp,%rbp

361 cmoveq %rcx,%rax

362 movq %rdi,%r8

363 movq %rcx,%rbx

364 subq %rax,%rsp

365 shrq $3,%rcx

366 leaq (%rsp),%rdi

367 .byte 0xf3,0x48,0xa5

368 movq %rsp,%rsi

369 movq %r8,%rdi

370 movq %rbx,%rcx

371 jmp L$ecb_loop

372 .p2align 4

373 L$ecb_break:

374 cmpq %rbp,%rsp

375 je L$ecb_done

376

377 pxor %xmm0,%xmm0

378 leaq (%rsp),%rax

379 L$ecb_bzero:

380 movaps %xmm0,(%rax)

381 leaq 16(%rax),%rax

382 cmpq %rax,%rbp

383 ja L$ecb_bzero

384

385 L$ecb_done:

386 leaq (%rbp),%rsp

387 jmp L$ecb_exit

388

389 .p2align 4

390 L$ecb_aligned:

391 leaq (%rsi,%rcx,1),%rbp

392 negq %rbp

393 andq $4095,%rbp

394 xorl %eax,%eax

395 cmpq $128,%rbp

396 movq $128-1,%rbp

397 cmovaeq %rax,%rbp

398 andq %rcx,%rbp

399 subq %rbp,%rcx

400 jz L$ecb_aligned_tail

401 leaq -16(%rdx),%rax

402 leaq 16(%rdx),%rbx

403 shrq $4,%rcx

404 .byte 0xf3,0x0f,0xa7,200

405 testq %rbp,%rbp

406 jz L$ecb_exit

407

408 L$ecb_aligned_tail:

409 movq %rdi,%r8

410 movq %rbp,%rbx

411 movq %rbp,%rcx

412 leaq (%rsp),%rbp

413 subq %rcx,%rsp

414 shrq $3,%rcx

415 leaq (%rsp),%rdi

416 .byte 0xf3,0x48,0xa5

417 leaq (%r8),%rdi

418 leaq (%rsp),%rsi

419 movq %rbx,%rcx

420 jmp L$ecb_loop

421 L$ecb_exit:

422 movl $1,%eax

423 leaq 8(%rsp),%rsp

424 L$ecb_abort:

425 popq %rbx

426 popq %rbp

427 .byte 0xf3,0xc3

428

429 .globl _padlock_cbc_encrypt

430

431 .p2align 4

432 _padlock_cbc_encrypt:

433 pushq %rbp

434 pushq %rbx

435

436 xorl %eax,%eax

437 testq $15,%rdx

438 jnz L$cbc_abort

439 testq $15,%rcx

440 jnz L$cbc_abort

441 leaq L$padlock_saved_context(%rip),%rax

442 pushf

443 cld

444 call _padlock_verify_ctx

445 leaq 16(%rdx),%rdx

446 xorl %eax,%eax

447 xorl %ebx,%ebx

448 testl $32,(%rdx)

449 jnz L$cbc_aligned

450 testq $15,%rdi

451 setz %al

452 testq $15,%rsi

453 setz %bl

454 testl %ebx,%eax

455 jnz L$cbc_aligned

456 negq %rax

457 movq $512,%rbx

458 notq %rax

459 leaq (%rsp),%rbp

460 cmpq %rbx,%rcx

461 cmovcq %rcx,%rbx

462 andq %rbx,%rax

463 movq %rcx,%rbx

464 negq %rax

465 andq $512-1,%rbx

466 leaq (%rax,%rbp,1),%rsp

467 movq $512,%rax

468 cmovzq %rax,%rbx

469 cmpq %rbx,%rcx

470 ja L$cbc_loop

471 movq %rsi,%rax

472 cmpq %rsp,%rbp

473 cmoveq %rdi,%rax

474 addq %rcx,%rax

475 negq %rax

476 andq $4095,%rax

477 cmpq $64,%rax

478 movq $-64,%rax

479 cmovaeq %rbx,%rax

480 andq %rax,%rbx

481 jz L$cbc_unaligned_tail

482 jmp L$cbc_loop

483 .p2align 4

484 L$cbc_loop:

485 cmpq %rcx,%rbx

486 cmovaq %rcx,%rbx

487 movq %rdi,%r8

488 movq %rsi,%r9

489 movq %rcx,%r10

490 movq %rbx,%rcx

491 movq %rbx,%r11

492 testq $15,%rdi

493 cmovnzq %rsp,%rdi

494 testq $15,%rsi

495 jz L$cbc_inp_aligned

496 shrq $3,%rcx

497 .byte 0xf3,0x48,0xa5

498 subq %rbx,%rdi

499 movq %rbx,%rcx

500 movq %rdi,%rsi

501 L$cbc_inp_aligned:

502 leaq -16(%rdx),%rax

503 leaq 16(%rdx),%rbx

504 shrq $4,%rcx

505 .byte 0xf3,0x0f,0xa7,208

506 movdqa (%rax),%xmm0

507 movdqa %xmm0,-16(%rdx)

508 movq %r8,%rdi

509 movq %r11,%rbx

510 testq $15,%rdi

511 jz L$cbc_out_aligned

512 movq %rbx,%rcx

513 leaq (%rsp),%rsi

514 shrq $3,%rcx

515 .byte 0xf3,0x48,0xa5

516 subq %rbx,%rdi

517 L$cbc_out_aligned:

518 movq %r9,%rsi

519 movq %r10,%rcx

520 addq %rbx,%rdi

521 addq %rbx,%rsi

522 subq %rbx,%rcx

523 movq $512,%rbx

524 jz L$cbc_break

525 cmpq %rbx,%rcx

526 jae L$cbc_loop

527 L$cbc_unaligned_tail:

528 xorl %eax,%eax

529 cmpq %rsp,%rbp

530 cmoveq %rcx,%rax

531 movq %rdi,%r8

532 movq %rcx,%rbx

533 subq %rax,%rsp

534 shrq $3,%rcx

535 leaq (%rsp),%rdi

536 .byte 0xf3,0x48,0xa5

537 movq %rsp,%rsi

538 movq %r8,%rdi

539 movq %rbx,%rcx

540 jmp L$cbc_loop

541 .p2align 4

542 L$cbc_break:

543 cmpq %rbp,%rsp

544 je L$cbc_done

545

546 pxor %xmm0,%xmm0

547 leaq (%rsp),%rax

548 L$cbc_bzero:

549 movaps %xmm0,(%rax)

550 leaq 16(%rax),%rax

551 cmpq %rax,%rbp

552 ja L$cbc_bzero

553

554 L$cbc_done:

555 leaq (%rbp),%rsp

556 jmp L$cbc_exit

557

558 .p2align 4

559 L$cbc_aligned:

560 leaq (%rsi,%rcx,1),%rbp

561 negq %rbp

562 andq $4095,%rbp

563 xorl %eax,%eax

564 cmpq $64,%rbp

565 movq $64-1,%rbp

566 cmovaeq %rax,%rbp

567 andq %rcx,%rbp

568 subq %rbp,%rcx

569 jz L$cbc_aligned_tail

570 leaq -16(%rdx),%rax

571 leaq 16(%rdx),%rbx

572 shrq $4,%rcx

573 .byte 0xf3,0x0f,0xa7,208

574 movdqa (%rax),%xmm0

575 movdqa %xmm0,-16(%rdx)

576 testq %rbp,%rbp

577 jz L$cbc_exit

578

579 L$cbc_aligned_tail:

580 movq %rdi,%r8

581 movq %rbp,%rbx

582 movq %rbp,%rcx

583 leaq (%rsp),%rbp

584 subq %rcx,%rsp

585 shrq $3,%rcx

586 leaq (%rsp),%rdi

587 .byte 0xf3,0x48,0xa5

588 leaq (%r8),%rdi

589 leaq (%rsp),%rsi

590 movq %rbx,%rcx

591 jmp L$cbc_loop

592 L$cbc_exit:

593 movl $1,%eax

594 leaq 8(%rsp),%rsp

595 L$cbc_abort:

596 popq %rbx

597 popq %rbp

598 .byte 0xf3,0xc3

599

600 .globl _padlock_cfb_encrypt

601

602 .p2align 4

603 _padlock_cfb_encrypt:

604 pushq %rbp

605 pushq %rbx

606

607 xorl %eax,%eax

608 testq $15,%rdx

609 jnz L$cfb_abort

610 testq $15,%rcx

611 jnz L$cfb_abort

612 leaq L$padlock_saved_context(%rip),%rax

613 pushf

614 cld

615 call _padlock_verify_ctx

616 leaq 16(%rdx),%rdx

617 xorl %eax,%eax

618 xorl %ebx,%ebx

619 testl $32,(%rdx)

620 jnz L$cfb_aligned

621 testq $15,%rdi

622 setz %al

623 testq $15,%rsi

624 setz %bl

625 testl %ebx,%eax

626 jnz L$cfb_aligned

627 negq %rax

628 movq $512,%rbx

629 notq %rax

630 leaq (%rsp),%rbp

631 cmpq %rbx,%rcx

632 cmovcq %rcx,%rbx

633 andq %rbx,%rax

634 movq %rcx,%rbx

635 negq %rax

636 andq $512-1,%rbx

637 leaq (%rax,%rbp,1),%rsp

638 movq $512,%rax

639 cmovzq %rax,%rbx

640 jmp L$cfb_loop

641 .p2align 4

642 L$cfb_loop:

643 cmpq %rcx,%rbx

644 cmovaq %rcx,%rbx

645 movq %rdi,%r8

646 movq %rsi,%r9

647 movq %rcx,%r10

648 movq %rbx,%rcx

649 movq %rbx,%r11

650 testq $15,%rdi

651 cmovnzq %rsp,%rdi

652 testq $15,%rsi

653 jz L$cfb_inp_aligned

654 shrq $3,%rcx

655 .byte 0xf3,0x48,0xa5

656 subq %rbx,%rdi

657 movq %rbx,%rcx

658 movq %rdi,%rsi

659 L$cfb_inp_aligned:

660 leaq -16(%rdx),%rax

661 leaq 16(%rdx),%rbx

662 shrq $4,%rcx

663 .byte 0xf3,0x0f,0xa7,224

664 movdqa (%rax),%xmm0

665 movdqa %xmm0,-16(%rdx)

666 movq %r8,%rdi

667 movq %r11,%rbx

668 testq $15,%rdi

669 jz L$cfb_out_aligned

670 movq %rbx,%rcx

671 leaq (%rsp),%rsi

672 shrq $3,%rcx

673 .byte 0xf3,0x48,0xa5

674 subq %rbx,%rdi

675 L$cfb_out_aligned:

676 movq %r9,%rsi

677 movq %r10,%rcx

678 addq %rbx,%rdi

679 addq %rbx,%rsi

680 subq %rbx,%rcx

681 movq $512,%rbx

682 jnz L$cfb_loop

683 cmpq %rbp,%rsp

684 je L$cfb_done

685

686 pxor %xmm0,%xmm0

687 leaq (%rsp),%rax

688 L$cfb_bzero:

689 movaps %xmm0,(%rax)

690 leaq 16(%rax),%rax

691 cmpq %rax,%rbp

692 ja L$cfb_bzero

693

694 L$cfb_done:

695 leaq (%rbp),%rsp

696 jmp L$cfb_exit

697

698 .p2align 4

699 L$cfb_aligned:

700 leaq -16(%rdx),%rax

701 leaq 16(%rdx),%rbx

702 shrq $4,%rcx

703 .byte 0xf3,0x0f,0xa7,224

704 movdqa (%rax),%xmm0

705 movdqa %xmm0,-16(%rdx)

706 L$cfb_exit:

707 movl $1,%eax

708 leaq 8(%rsp),%rsp

709 L$cfb_abort:

710 popq %rbx

711 popq %rbp

712 .byte 0xf3,0xc3

713

714 .globl _padlock_ofb_encrypt

715

716 .p2align 4

717 _padlock_ofb_encrypt:

718 pushq %rbp

719 pushq %rbx

720

721 xorl %eax,%eax

722 testq $15,%rdx

723 jnz L$ofb_abort

724 testq $15,%rcx

725 jnz L$ofb_abort

726 leaq L$padlock_saved_context(%rip),%rax

727 pushf

728 cld

729 call _padlock_verify_ctx

730 leaq 16(%rdx),%rdx

731 xorl %eax,%eax

732 xorl %ebx,%ebx

733 testl $32,(%rdx)

734 jnz L$ofb_aligned

735 testq $15,%rdi

736 setz %al

737 testq $15,%rsi

738 setz %bl

739 testl %ebx,%eax

740 jnz L$ofb_aligned

741 negq %rax

742 movq $512,%rbx

743 notq %rax

744 leaq (%rsp),%rbp

745 cmpq %rbx,%rcx

746 cmovcq %rcx,%rbx

747 andq %rbx,%rax

748 movq %rcx,%rbx

749 negq %rax

750 andq $512-1,%rbx

751 leaq (%rax,%rbp,1),%rsp

752 movq $512,%rax

753 cmovzq %rax,%rbx

754 jmp L$ofb_loop

755 .p2align 4

756 L$ofb_loop:

757 cmpq %rcx,%rbx

758 cmovaq %rcx,%rbx

759 movq %rdi,%r8

760 movq %rsi,%r9

761 movq %rcx,%r10

762 movq %rbx,%rcx

763 movq %rbx,%r11

764 testq $15,%rdi

765 cmovnzq %rsp,%rdi

766 testq $15,%rsi

767 jz L$ofb_inp_aligned

768 shrq $3,%rcx

769 .byte 0xf3,0x48,0xa5

770 subq %rbx,%rdi

771 movq %rbx,%rcx

772 movq %rdi,%rsi

773 L$ofb_inp_aligned:

774 leaq -16(%rdx),%rax

775 leaq 16(%rdx),%rbx

776 shrq $4,%rcx

777 .byte 0xf3,0x0f,0xa7,232

778 movdqa (%rax),%xmm0

779 movdqa %xmm0,-16(%rdx)

780 movq %r8,%rdi

781 movq %r11,%rbx

782 testq $15,%rdi

783 jz L$ofb_out_aligned

784 movq %rbx,%rcx

785 leaq (%rsp),%rsi

786 shrq $3,%rcx

787 .byte 0xf3,0x48,0xa5

788 subq %rbx,%rdi

789 L$ofb_out_aligned:

790 movq %r9,%rsi

791 movq %r10,%rcx

792 addq %rbx,%rdi

793 addq %rbx,%rsi

794 subq %rbx,%rcx

795 movq $512,%rbx

796 jnz L$ofb_loop

797 cmpq %rbp,%rsp

798 je L$ofb_done

799

800 pxor %xmm0,%xmm0

801 leaq (%rsp),%rax

802 L$ofb_bzero:

803 movaps %xmm0,(%rax)

804 leaq 16(%rax),%rax

805 cmpq %rax,%rbp

806 ja L$ofb_bzero

807

808 L$ofb_done:

809 leaq (%rbp),%rsp

810 jmp L$ofb_exit

811

812 .p2align 4

813 L$ofb_aligned:

814 leaq -16(%rdx),%rax

815 leaq 16(%rdx),%rbx

816 shrq $4,%rcx

817 .byte 0xf3,0x0f,0xa7,232

818 movdqa (%rax),%xmm0

819 movdqa %xmm0,-16(%rdx)

820 L$ofb_exit:

821 movl $1,%eax

822 leaq 8(%rsp),%rsp

823 L$ofb_abort:

824 popq %rbx

825 popq %rbp

826 .byte 0xf3,0xc3

827

828 .globl _padlock_ctr32_encrypt

829

830 .p2align 4

831 _padlock_ctr32_encrypt:

832 pushq %rbp

833 pushq %rbx

834

835 xorl %eax,%eax

836 testq $15,%rdx

837 jnz L$ctr32_abort

838 testq $15,%rcx

839 jnz L$ctr32_abort

840 leaq L$padlock_saved_context(%rip),%rax

841 pushf

842 cld

843 call _padlock_verify_ctx

844 leaq 16(%rdx),%rdx

845 xorl %eax,%eax

846 xorl %ebx,%ebx

847 testl $32,(%rdx)

848 jnz L$ctr32_aligned

849 testq $15,%rdi

850 setz %al

851 testq $15,%rsi

852 setz %bl

853 testl %ebx,%eax

854 jnz L$ctr32_aligned

855 negq %rax

856 movq $512,%rbx

857 notq %rax

858 leaq (%rsp),%rbp

859 cmpq %rbx,%rcx

860 cmovcq %rcx,%rbx

861 andq %rbx,%rax

862 movq %rcx,%rbx

863 negq %rax

864 andq $512-1,%rbx

865 leaq (%rax,%rbp,1),%rsp

866 movq $512,%rax

867 cmovzq %rax,%rbx

868 L$ctr32_reenter:

869 movl -4(%rdx),%eax

870 bswapl %eax

871 negl %eax

872 andl $31,%eax

873 movq $512,%rbx

874 shll $4,%eax

875 cmovzq %rbx,%rax

876 cmpq %rax,%rcx

877 cmovaq %rax,%rbx

878 cmovbeq %rcx,%rbx

879 cmpq %rbx,%rcx

880 ja L$ctr32_loop

881 movq %rsi,%rax

882 cmpq %rsp,%rbp

883 cmoveq %rdi,%rax

884 addq %rcx,%rax

885 negq %rax

886 andq $4095,%rax

887 cmpq $32,%rax

888 movq $-32,%rax

889 cmovaeq %rbx,%rax

890 andq %rax,%rbx

891 jz L$ctr32_unaligned_tail

892 jmp L$ctr32_loop

893 .p2align 4

894 L$ctr32_loop:

895 cmpq %rcx,%rbx

896 cmovaq %rcx,%rbx

897 movq %rdi,%r8

898 movq %rsi,%r9

899 movq %rcx,%r10

900 movq %rbx,%rcx

901 movq %rbx,%r11

902 testq $15,%rdi

903 cmovnzq %rsp,%rdi

904 testq $15,%rsi

905 jz L$ctr32_inp_aligned

906 shrq $3,%rcx

907 .byte 0xf3,0x48,0xa5

908 subq %rbx,%rdi

909 movq %rbx,%rcx

910 movq %rdi,%rsi

911 L$ctr32_inp_aligned:

912 leaq -16(%rdx),%rax

913 leaq 16(%rdx),%rbx

914 shrq $4,%rcx

915 .byte 0xf3,0x0f,0xa7,216

916 movl -4(%rdx),%eax

917 testl $4294901760,%eax

918 jnz L$ctr32_no_carry

919 bswapl %eax

920 addl $65536,%eax

921 bswapl %eax

922 movl %eax,-4(%rdx)

923 L$ctr32_no_carry:

924 movq %r8,%rdi

925 movq %r11,%rbx

926 testq $15,%rdi

927 jz L$ctr32_out_aligned

928 movq %rbx,%rcx

929 leaq (%rsp),%rsi

930 shrq $3,%rcx

931 .byte 0xf3,0x48,0xa5

932 subq %rbx,%rdi

933 L$ctr32_out_aligned:

934 movq %r9,%rsi

935 movq %r10,%rcx

936 addq %rbx,%rdi

937 addq %rbx,%rsi

938 subq %rbx,%rcx

939 movq $512,%rbx

940 jz L$ctr32_break

941 cmpq %rbx,%rcx

942 jae L$ctr32_loop

943 movq %rcx,%rbx

944 movq %rsi,%rax

945 cmpq %rsp,%rbp

946 cmoveq %rdi,%rax

947 addq %rcx,%rax

948 negq %rax

949 andq $4095,%rax

950 cmpq $32,%rax

951 movq $-32,%rax

952 cmovaeq %rbx,%rax

953 andq %rax,%rbx

954 jnz L$ctr32_loop

955 L$ctr32_unaligned_tail:

956 xorl %eax,%eax

957 cmpq %rsp,%rbp

958 cmoveq %rcx,%rax

959 movq %rdi,%r8

960 movq %rcx,%rbx

961 subq %rax,%rsp

962 shrq $3,%rcx

963 leaq (%rsp),%rdi

964 .byte 0xf3,0x48,0xa5

965 movq %rsp,%rsi

966 movq %r8,%rdi

967 movq %rbx,%rcx

968 jmp L$ctr32_loop

969 .p2align 4

970 L$ctr32_break:

971 cmpq %rbp,%rsp

972 je L$ctr32_done

973

974 pxor %xmm0,%xmm0

975 leaq (%rsp),%rax

976 L$ctr32_bzero:

977 movaps %xmm0,(%rax)

978 leaq 16(%rax),%rax

979 cmpq %rax,%rbp

980 ja L$ctr32_bzero

981

982 L$ctr32_done:

983 leaq (%rbp),%rsp

984 jmp L$ctr32_exit

985

986 .p2align 4

987 L$ctr32_aligned:

988 movl -4(%rdx),%eax

989 bswapl %eax

990 negl %eax

991 andl $65535,%eax

992 movq $1048576,%rbx

993 shll $4,%eax

994 cmovzq %rbx,%rax

995 cmpq %rax,%rcx

996 cmovaq %rax,%rbx

997 cmovbeq %rcx,%rbx

998 jbe L$ctr32_aligned_skip

999

1000 L$ctr32_aligned_loop:

1001 movq %rcx,%r10

1002 movq %rbx,%rcx

1003 movq %rbx,%r11

1004

1005 leaq -16(%rdx),%rax

1006 leaq 16(%rdx),%rbx

1007 shrq $4,%rcx

1008 .byte 0xf3,0x0f,0xa7,216

1009

1010 movl -4(%rdx),%eax

1011 bswapl %eax

1012 addl $65536,%eax

1013 bswapl %eax

1014 movl %eax,-4(%rdx)

1015

1016 movq %r10,%rcx

1017 subq %r11,%rcx

1018 movq $1048576,%rbx

1019 jz L$ctr32_exit

1020 cmpq %rbx,%rcx

1021 jae L$ctr32_aligned_loop

1022

1023 L$ctr32_aligned_skip:

1024 leaq (%rsi,%rcx,1),%rbp

1025 negq %rbp

1026 andq $4095,%rbp

1027 xorl %eax,%eax

1028 cmpq $32,%rbp

1029 movq $32-1,%rbp

1030 cmovaeq %rax,%rbp

1031 andq %rcx,%rbp

1032 subq %rbp,%rcx

1033 jz L$ctr32_aligned_tail

1034 leaq -16(%rdx),%rax

1035 leaq 16(%rdx),%rbx

1036 shrq $4,%rcx

1037 .byte 0xf3,0x0f,0xa7,216

1038 testq %rbp,%rbp

1039 jz L$ctr32_exit

1040

1041 L$ctr32_aligned_tail:

1042 movq %rdi,%r8

1043 movq %rbp,%rbx

1044 movq %rbp,%rcx

1045 leaq (%rsp),%rbp

1046 subq %rcx,%rsp

1047 shrq $3,%rcx

1048 leaq (%rsp),%rdi

1049 .byte 0xf3,0x48,0xa5

1050 leaq (%r8),%rdi

1051 leaq (%rsp),%rsi

1052 movq %rbx,%rcx

1053 jmp L$ctr32_loop

1054 L$ctr32_exit:

1055 movl $1,%eax

1056 leaq 8(%rsp),%rsp

1057 L$ctr32_abort:

1058 popq %rbx

1059 popq %rbp

1060 .byte 0xf3,0xc3

1061

1062 .byte 86,73,65,32,80,97,100,108,111,99,107,32,120,56,54,95,54,52,32,109,111,100,117,108,101,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0

1063 .p2align 4

1064 .data

1065 .p2align 3

1066 L$padlock_saved_context:

1067 .quad 0