third_party/boringssl/win-x86_64/crypto/rc4/rc4-x86_64.asm

   1 default rel
   2 %define XMMWORD
   3 %define YMMWORD
   4 %define ZMMWORD
   5 section .text code align=64
   6
   7 EXTERN  OPENSSL_ia32cap_P
   8
   9 global  asm_RC4
  10
  11 ALIGN   16
  12 asm_RC4:
  13         mov     QWORD[8+rsp],rdi        ;WIN64 prologue
  14         mov     QWORD[16+rsp],rsi
  15         mov     rax,rsp
  16 $L$SEH_begin_asm_RC4:
  17         mov     rdi,rcx
  18         mov     rsi,rdx
  19         mov     rdx,r8
  20         mov     rcx,r9
  21
  22
  23         or      rsi,rsi
  24         jne     NEAR $L$entry
  25         mov     rdi,QWORD[8+rsp]        ;WIN64 epilogue
  26         mov     rsi,QWORD[16+rsp]
  27         DB      0F3h,0C3h               ;repret
  28 $L$entry:
  29         push    rbx
  30         push    r12
  31         push    r13
  32 $L$prologue:
  33         mov     r11,rsi
  34         mov     r12,rdx
  35         mov     r13,rcx
  36         xor     r10,r10
  37         xor     rcx,rcx
  38
  39         lea     rdi,[8+rdi]
  40         mov     r10b,BYTE[((-8))+rdi]
  41         mov     cl,BYTE[((-4))+rdi]
  42         cmp     DWORD[256+rdi],-1
  43         je      NEAR $L$RC4_CHAR
  44         mov     r8d,DWORD[OPENSSL_ia32cap_P]
  45         xor     rbx,rbx
  46         inc     r10b
  47         sub     rbx,r10
  48         sub     r13,r12
  49         mov     eax,DWORD[r10*4+rdi]
  50         test    r11,-16
  51         jz      NEAR $L$loop1
  52         bt      r8d,30
  53         jc      NEAR $L$intel
  54         and     rbx,7
  55         lea     rsi,[1+r10]
  56         jz      NEAR $L$oop8
  57         sub     r11,rbx
  58 $L$oop8_warmup:
  59         add     cl,al
  60         mov     edx,DWORD[rcx*4+rdi]
  61         mov     DWORD[rcx*4+rdi],eax
  62         mov     DWORD[r10*4+rdi],edx
  63         add     al,dl
  64         inc     r10b
  65         mov     edx,DWORD[rax*4+rdi]
  66         mov     eax,DWORD[r10*4+rdi]
  67         xor     dl,BYTE[r12]
  68         mov     BYTE[r13*1+r12],dl
  69         lea     r12,[1+r12]
  70         dec     rbx
  71         jnz     NEAR $L$oop8_warmup
  72
  73         lea     rsi,[1+r10]
  74         jmp     NEAR $L$oop8
  75 ALIGN   16
  76 $L$oop8:
  77         add     cl,al
  78         mov     edx,DWORD[rcx*4+rdi]
  79         mov     DWORD[rcx*4+rdi],eax
  80         mov     ebx,DWORD[rsi*4+rdi]
  81         ror     r8,8
  82         mov     DWORD[r10*4+rdi],edx
  83         add     dl,al
  84         mov     r8b,BYTE[rdx*4+rdi]
  85         add     cl,bl
  86         mov     edx,DWORD[rcx*4+rdi]
  87         mov     DWORD[rcx*4+rdi],ebx
  88         mov     eax,DWORD[4+rsi*4+rdi]
  89         ror     r8,8
  90         mov     DWORD[4+r10*4+rdi],edx
  91         add     dl,bl
  92         mov     r8b,BYTE[rdx*4+rdi]
  93         add     cl,al
  94         mov     edx,DWORD[rcx*4+rdi]
  95         mov     DWORD[rcx*4+rdi],eax
  96         mov     ebx,DWORD[8+rsi*4+rdi]
  97         ror     r8,8
  98         mov     DWORD[8+r10*4+rdi],edx
  99         add     dl,al
 100         mov     r8b,BYTE[rdx*4+rdi]
 101         add     cl,bl
 102         mov     edx,DWORD[rcx*4+rdi]
 103         mov     DWORD[rcx*4+rdi],ebx
 104         mov     eax,DWORD[12+rsi*4+rdi]
 105         ror     r8,8
 106         mov     DWORD[12+r10*4+rdi],edx
 107         add     dl,bl
 108         mov     r8b,BYTE[rdx*4+rdi]
 109         add     cl,al
 110         mov     edx,DWORD[rcx*4+rdi]
 111         mov     DWORD[rcx*4+rdi],eax
 112         mov     ebx,DWORD[16+rsi*4+rdi]
 113         ror     r8,8
 114         mov     DWORD[16+r10*4+rdi],edx
 115         add     dl,al
 116         mov     r8b,BYTE[rdx*4+rdi]
 117         add     cl,bl
 118         mov     edx,DWORD[rcx*4+rdi]
 119         mov     DWORD[rcx*4+rdi],ebx
 120         mov     eax,DWORD[20+rsi*4+rdi]
 121         ror     r8,8
 122         mov     DWORD[20+r10*4+rdi],edx
 123         add     dl,bl
 124         mov     r8b,BYTE[rdx*4+rdi]
 125         add     cl,al
 126         mov     edx,DWORD[rcx*4+rdi]
 127         mov     DWORD[rcx*4+rdi],eax
 128         mov     ebx,DWORD[24+rsi*4+rdi]
 129         ror     r8,8
 130         mov     DWORD[24+r10*4+rdi],edx
 131         add     dl,al
 132         mov     r8b,BYTE[rdx*4+rdi]
 133         add     sil,8
 134         add     cl,bl
 135         mov     edx,DWORD[rcx*4+rdi]
 136         mov     DWORD[rcx*4+rdi],ebx
 137         mov     eax,DWORD[((-4))+rsi*4+rdi]
 138         ror     r8,8
 139         mov     DWORD[28+r10*4+rdi],edx
 140         add     dl,bl
 141         mov     r8b,BYTE[rdx*4+rdi]
 142         add     r10b,8
 143         ror     r8,8
 144         sub     r11,8
 145
 146         xor     r8,QWORD[r12]
 147         mov     QWORD[r13*1+r12],r8
 148         lea     r12,[8+r12]
 149
 150         test    r11,-8
 151         jnz     NEAR $L$oop8
 152         cmp     r11,0
 153         jne     NEAR $L$loop1
 154         jmp     NEAR $L$exit
 155
 156 ALIGN   16
 157 $L$intel:
 158         test    r11,-32
 159         jz      NEAR $L$loop1
 160         and     rbx,15
 161         jz      NEAR $L$oop16_is_hot
 162         sub     r11,rbx
 163 $L$oop16_warmup:
 164         add     cl,al
 165         mov     edx,DWORD[rcx*4+rdi]
 166         mov     DWORD[rcx*4+rdi],eax
 167         mov     DWORD[r10*4+rdi],edx
 168         add     al,dl
 169         inc     r10b
 170         mov     edx,DWORD[rax*4+rdi]
 171         mov     eax,DWORD[r10*4+rdi]
 172         xor     dl,BYTE[r12]
 173         mov     BYTE[r13*1+r12],dl
 174         lea     r12,[1+r12]
 175         dec     rbx
 176         jnz     NEAR $L$oop16_warmup
 177
 178         mov     rbx,rcx
 179         xor     rcx,rcx
 180         mov     cl,bl
 181
 182 $L$oop16_is_hot:
 183         lea     rsi,[r10*4+rdi]
 184         add     cl,al
 185         mov     edx,DWORD[rcx*4+rdi]
 186         pxor    xmm0,xmm0
 187         mov     DWORD[rcx*4+rdi],eax
 188         add     al,dl
 189         mov     ebx,DWORD[4+rsi]
 190         movzx   eax,al
 191         mov     DWORD[rsi],edx
 192         add     cl,bl
 193         pinsrw  xmm0,WORD[rax*4+rdi],0
 194         jmp     NEAR $L$oop16_enter
 195 ALIGN   16
 196 $L$oop16:
 197         add     cl,al
 198         mov     edx,DWORD[rcx*4+rdi]
 199         pxor    xmm2,xmm0
 200         psllq   xmm1,8
 201         pxor    xmm0,xmm0
 202         mov     DWORD[rcx*4+rdi],eax
 203         add     al,dl
 204         mov     ebx,DWORD[4+rsi]
 205         movzx   eax,al
 206         mov     DWORD[rsi],edx
 207         pxor    xmm2,xmm1
 208         add     cl,bl
 209         pinsrw  xmm0,WORD[rax*4+rdi],0
 210         movdqu  XMMWORD[r13*1+r12],xmm2
 211         lea     r12,[16+r12]
 212 $L$oop16_enter:
 213         mov     edx,DWORD[rcx*4+rdi]
 214         pxor    xmm1,xmm1
 215         mov     DWORD[rcx*4+rdi],ebx
 216         add     bl,dl
 217         mov     eax,DWORD[8+rsi]
 218         movzx   ebx,bl
 219         mov     DWORD[4+rsi],edx
 220         add     cl,al
 221         pinsrw  xmm1,WORD[rbx*4+rdi],0
 222         mov     edx,DWORD[rcx*4+rdi]
 223         mov     DWORD[rcx*4+rdi],eax
 224         add     al,dl
 225         mov     ebx,DWORD[12+rsi]
 226         movzx   eax,al
 227         mov     DWORD[8+rsi],edx
 228         add     cl,bl
 229         pinsrw  xmm0,WORD[rax*4+rdi],1
 230         mov     edx,DWORD[rcx*4+rdi]
 231         mov     DWORD[rcx*4+rdi],ebx
 232         add     bl,dl
 233         mov     eax,DWORD[16+rsi]
 234         movzx   ebx,bl
 235         mov     DWORD[12+rsi],edx
 236         add     cl,al
 237         pinsrw  xmm1,WORD[rbx*4+rdi],1
 238         mov     edx,DWORD[rcx*4+rdi]
 239         mov     DWORD[rcx*4+rdi],eax
 240         add     al,dl
 241         mov     ebx,DWORD[20+rsi]
 242         movzx   eax,al
 243         mov     DWORD[16+rsi],edx
 244         add     cl,bl
 245         pinsrw  xmm0,WORD[rax*4+rdi],2
 246         mov     edx,DWORD[rcx*4+rdi]
 247         mov     DWORD[rcx*4+rdi],ebx
 248         add     bl,dl
 249         mov     eax,DWORD[24+rsi]
 250         movzx   ebx,bl
 251         mov     DWORD[20+rsi],edx
 252         add     cl,al
 253         pinsrw  xmm1,WORD[rbx*4+rdi],2
 254         mov     edx,DWORD[rcx*4+rdi]
 255         mov     DWORD[rcx*4+rdi],eax
 256         add     al,dl
 257         mov     ebx,DWORD[28+rsi]
 258         movzx   eax,al
 259         mov     DWORD[24+rsi],edx
 260         add     cl,bl
 261         pinsrw  xmm0,WORD[rax*4+rdi],3
 262         mov     edx,DWORD[rcx*4+rdi]
 263         mov     DWORD[rcx*4+rdi],ebx
 264         add     bl,dl
 265         mov     eax,DWORD[32+rsi]
 266         movzx   ebx,bl
 267         mov     DWORD[28+rsi],edx
 268         add     cl,al
 269         pinsrw  xmm1,WORD[rbx*4+rdi],3
 270         mov     edx,DWORD[rcx*4+rdi]
 271         mov     DWORD[rcx*4+rdi],eax
 272         add     al,dl
 273         mov     ebx,DWORD[36+rsi]
 274         movzx   eax,al
 275         mov     DWORD[32+rsi],edx
 276         add     cl,bl
 277         pinsrw  xmm0,WORD[rax*4+rdi],4
 278         mov     edx,DWORD[rcx*4+rdi]
 279         mov     DWORD[rcx*4+rdi],ebx
 280         add     bl,dl
 281         mov     eax,DWORD[40+rsi]
 282         movzx   ebx,bl
 283         mov     DWORD[36+rsi],edx
 284         add     cl,al
 285         pinsrw  xmm1,WORD[rbx*4+rdi],4
 286         mov     edx,DWORD[rcx*4+rdi]
 287         mov     DWORD[rcx*4+rdi],eax
 288         add     al,dl
 289         mov     ebx,DWORD[44+rsi]
 290         movzx   eax,al
 291         mov     DWORD[40+rsi],edx
 292         add     cl,bl
 293         pinsrw  xmm0,WORD[rax*4+rdi],5
 294         mov     edx,DWORD[rcx*4+rdi]
 295         mov     DWORD[rcx*4+rdi],ebx
 296         add     bl,dl
 297         mov     eax,DWORD[48+rsi]
 298         movzx   ebx,bl
 299         mov     DWORD[44+rsi],edx
 300         add     cl,al
 301         pinsrw  xmm1,WORD[rbx*4+rdi],5
 302         mov     edx,DWORD[rcx*4+rdi]
 303         mov     DWORD[rcx*4+rdi],eax
 304         add     al,dl
 305         mov     ebx,DWORD[52+rsi]
 306         movzx   eax,al
 307         mov     DWORD[48+rsi],edx
 308         add     cl,bl
 309         pinsrw  xmm0,WORD[rax*4+rdi],6
 310         mov     edx,DWORD[rcx*4+rdi]
 311         mov     DWORD[rcx*4+rdi],ebx
 312         add     bl,dl
 313         mov     eax,DWORD[56+rsi]
 314         movzx   ebx,bl
 315         mov     DWORD[52+rsi],edx
 316         add     cl,al
 317         pinsrw  xmm1,WORD[rbx*4+rdi],6
 318         mov     edx,DWORD[rcx*4+rdi]
 319         mov     DWORD[rcx*4+rdi],eax
 320         add     al,dl
 321         mov     ebx,DWORD[60+rsi]
 322         movzx   eax,al
 323         mov     DWORD[56+rsi],edx
 324         add     cl,bl
 325         pinsrw  xmm0,WORD[rax*4+rdi],7
 326         add     r10b,16
 327         movdqu  xmm2,XMMWORD[r12]
 328         mov     edx,DWORD[rcx*4+rdi]
 329         mov     DWORD[rcx*4+rdi],ebx
 330         add     bl,dl
 331         movzx   ebx,bl
 332         mov     DWORD[60+rsi],edx
 333         lea     rsi,[r10*4+rdi]
 334         pinsrw  xmm1,WORD[rbx*4+rdi],7
 335         mov     eax,DWORD[rsi]
 336         mov     rbx,rcx
 337         xor     rcx,rcx
 338         sub     r11,16
 339         mov     cl,bl
 340         test    r11,-16
 341         jnz     NEAR $L$oop16
 342
 343         psllq   xmm1,8
 344         pxor    xmm2,xmm0
 345         pxor    xmm2,xmm1
 346         movdqu  XMMWORD[r13*1+r12],xmm2
 347         lea     r12,[16+r12]
 348
 349         cmp     r11,0
 350         jne     NEAR $L$loop1
 351         jmp     NEAR $L$exit
 352
 353 ALIGN   16
 354 $L$loop1:
 355         add     cl,al
 356         mov     edx,DWORD[rcx*4+rdi]
 357         mov     DWORD[rcx*4+rdi],eax
 358         mov     DWORD[r10*4+rdi],edx
 359         add     al,dl
 360         inc     r10b
 361         mov     edx,DWORD[rax*4+rdi]
 362         mov     eax,DWORD[r10*4+rdi]
 363         xor     dl,BYTE[r12]
 364         mov     BYTE[r13*1+r12],dl
 365         lea     r12,[1+r12]
 366         dec     r11
 367         jnz     NEAR $L$loop1
 368         jmp     NEAR $L$exit
 369
 370 ALIGN   16
 371 $L$RC4_CHAR:
 372         add     r10b,1
 373         movzx   eax,BYTE[r10*1+rdi]
 374         test    r11,-8
 375         jz      NEAR $L$cloop1
 376         jmp     NEAR $L$cloop8
 377 ALIGN   16
 378 $L$cloop8:
 379         mov     r8d,DWORD[r12]
 380         mov     r9d,DWORD[4+r12]
 381         add     cl,al
 382         lea     rsi,[1+r10]
 383         movzx   edx,BYTE[rcx*1+rdi]
 384         movzx   esi,sil
 385         movzx   ebx,BYTE[rsi*1+rdi]
 386         mov     BYTE[rcx*1+rdi],al
 387         cmp     rcx,rsi
 388         mov     BYTE[r10*1+rdi],dl
 389         jne     NEAR $L$cmov0
 390         mov     rbx,rax
 391 $L$cmov0:
 392         add     dl,al
 393         xor     r8b,BYTE[rdx*1+rdi]
 394         ror     r8d,8
 395         add     cl,bl
 396         lea     r10,[1+rsi]
 397         movzx   edx,BYTE[rcx*1+rdi]
 398         movzx   r10d,r10b
 399         movzx   eax,BYTE[r10*1+rdi]
 400         mov     BYTE[rcx*1+rdi],bl
 401         cmp     rcx,r10
 402         mov     BYTE[rsi*1+rdi],dl
 403         jne     NEAR $L$cmov1
 404         mov     rax,rbx
 405 $L$cmov1:
 406         add     dl,bl
 407         xor     r8b,BYTE[rdx*1+rdi]
 408         ror     r8d,8
 409         add     cl,al
 410         lea     rsi,[1+r10]
 411         movzx   edx,BYTE[rcx*1+rdi]
 412         movzx   esi,sil
 413         movzx   ebx,BYTE[rsi*1+rdi]
 414         mov     BYTE[rcx*1+rdi],al
 415         cmp     rcx,rsi
 416         mov     BYTE[r10*1+rdi],dl
 417         jne     NEAR $L$cmov2
 418         mov     rbx,rax
 419 $L$cmov2:
 420         add     dl,al
 421         xor     r8b,BYTE[rdx*1+rdi]
 422         ror     r8d,8
 423         add     cl,bl
 424         lea     r10,[1+rsi]
 425         movzx   edx,BYTE[rcx*1+rdi]
 426         movzx   r10d,r10b
 427         movzx   eax,BYTE[r10*1+rdi]
 428         mov     BYTE[rcx*1+rdi],bl
 429         cmp     rcx,r10
 430         mov     BYTE[rsi*1+rdi],dl
 431         jne     NEAR $L$cmov3
 432         mov     rax,rbx
 433 $L$cmov3:
 434         add     dl,bl
 435         xor     r8b,BYTE[rdx*1+rdi]
 436         ror     r8d,8
 437         add     cl,al
 438         lea     rsi,[1+r10]
 439         movzx   edx,BYTE[rcx*1+rdi]
 440         movzx   esi,sil
 441         movzx   ebx,BYTE[rsi*1+rdi]
 442         mov     BYTE[rcx*1+rdi],al
 443         cmp     rcx,rsi
 444         mov     BYTE[r10*1+rdi],dl
 445         jne     NEAR $L$cmov4
 446         mov     rbx,rax
 447 $L$cmov4:
 448         add     dl,al
 449         xor     r9b,BYTE[rdx*1+rdi]
 450         ror     r9d,8
 451         add     cl,bl
 452         lea     r10,[1+rsi]
 453         movzx   edx,BYTE[rcx*1+rdi]
 454         movzx   r10d,r10b
 455         movzx   eax,BYTE[r10*1+rdi]
 456         mov     BYTE[rcx*1+rdi],bl
 457         cmp     rcx,r10
 458         mov     BYTE[rsi*1+rdi],dl
 459         jne     NEAR $L$cmov5
 460         mov     rax,rbx
 461 $L$cmov5:
 462         add     dl,bl
 463         xor     r9b,BYTE[rdx*1+rdi]
 464         ror     r9d,8
 465         add     cl,al
 466         lea     rsi,[1+r10]
 467         movzx   edx,BYTE[rcx*1+rdi]
 468         movzx   esi,sil
 469         movzx   ebx,BYTE[rsi*1+rdi]
 470         mov     BYTE[rcx*1+rdi],al
 471         cmp     rcx,rsi
 472         mov     BYTE[r10*1+rdi],dl
 473         jne     NEAR $L$cmov6
 474         mov     rbx,rax
 475 $L$cmov6:
 476         add     dl,al
 477         xor     r9b,BYTE[rdx*1+rdi]
 478         ror     r9d,8
 479         add     cl,bl
 480         lea     r10,[1+rsi]
 481         movzx   edx,BYTE[rcx*1+rdi]
 482         movzx   r10d,r10b
 483         movzx   eax,BYTE[r10*1+rdi]
 484         mov     BYTE[rcx*1+rdi],bl
 485         cmp     rcx,r10
 486         mov     BYTE[rsi*1+rdi],dl
 487         jne     NEAR $L$cmov7
 488         mov     rax,rbx
 489 $L$cmov7:
 490         add     dl,bl
 491         xor     r9b,BYTE[rdx*1+rdi]
 492         ror     r9d,8
 493         lea     r11,[((-8))+r11]
 494         mov     DWORD[r13],r8d
 495         lea     r12,[8+r12]
 496         mov     DWORD[4+r13],r9d
 497         lea     r13,[8+r13]
 498
 499         test    r11,-8
 500         jnz     NEAR $L$cloop8
 501         cmp     r11,0
 502         jne     NEAR $L$cloop1
 503         jmp     NEAR $L$exit
 504 ALIGN   16
 505 $L$cloop1:
 506         add     cl,al
 507         movzx   ecx,cl
 508         movzx   edx,BYTE[rcx*1+rdi]
 509         mov     BYTE[rcx*1+rdi],al
 510         mov     BYTE[r10*1+rdi],dl
 511         add     dl,al
 512         add     r10b,1
 513         movzx   edx,dl
 514         movzx   r10d,r10b
 515         movzx   edx,BYTE[rdx*1+rdi]
 516         movzx   eax,BYTE[r10*1+rdi]
 517         xor     dl,BYTE[r12]
 518         lea     r12,[1+r12]
 519         mov     BYTE[r13],dl
 520         lea     r13,[1+r13]
 521         sub     r11,1
 522         jnz     NEAR $L$cloop1
 523         jmp     NEAR $L$exit
 524
 525 ALIGN   16
 526 $L$exit:
 527         sub     r10b,1
 528         mov     DWORD[((-8))+rdi],r10d
 529         mov     DWORD[((-4))+rdi],ecx
 530
 531         mov     r13,QWORD[rsp]
 532         mov     r12,QWORD[8+rsp]
 533         mov     rbx,QWORD[16+rsp]
 534         add     rsp,24
 535 $L$epilogue:
 536         mov     rdi,QWORD[8+rsp]        ;WIN64 epilogue
 537         mov     rsi,QWORD[16+rsp]
 538         DB      0F3h,0C3h               ;repret
 539 $L$SEH_end_asm_RC4:
 540 global  asm_RC4_set_key
 541
 542 ALIGN   16
 543 asm_RC4_set_key:
 544         mov     QWORD[8+rsp],rdi        ;WIN64 prologue
 545         mov     QWORD[16+rsp],rsi
 546         mov     rax,rsp
 547 $L$SEH_begin_asm_RC4_set_key:
 548         mov     rdi,rcx
 549         mov     rsi,rdx
 550         mov     rdx,r8
 551
 552
 553         lea     rdi,[8+rdi]
 554         lea     rdx,[rsi*1+rdx]
 555         neg     rsi
 556         mov     rcx,rsi
 557         xor     eax,eax
 558         xor     r9,r9
 559         xor     r10,r10
 560         xor     r11,r11
 561
 562         mov     r8d,DWORD[OPENSSL_ia32cap_P]
 563         bt      r8d,20
 564         jc      NEAR $L$c1stloop
 565         jmp     NEAR $L$w1stloop
 566
 567 ALIGN   16
 568 $L$w1stloop:
 569         mov     DWORD[rax*4+rdi],eax
 570         add     al,1
 571         jnc     NEAR $L$w1stloop
 572
 573         xor     r9,r9
 574         xor     r8,r8
 575 ALIGN   16
 576 $L$w2ndloop:
 577         mov     r10d,DWORD[r9*4+rdi]
 578         add     r8b,BYTE[rsi*1+rdx]
 579         add     r8b,r10b
 580         add     rsi,1
 581         mov     r11d,DWORD[r8*4+rdi]
 582         cmovz   rsi,rcx
 583         mov     DWORD[r8*4+rdi],r10d
 584         mov     DWORD[r9*4+rdi],r11d
 585         add     r9b,1
 586         jnc     NEAR $L$w2ndloop
 587         jmp     NEAR $L$exit_key
 588
 589 ALIGN   16
 590 $L$c1stloop:
 591         mov     BYTE[rax*1+rdi],al
 592         add     al,1
 593         jnc     NEAR $L$c1stloop
 594
 595         xor     r9,r9
 596         xor     r8,r8
 597 ALIGN   16
 598 $L$c2ndloop:
 599         mov     r10b,BYTE[r9*1+rdi]
 600         add     r8b,BYTE[rsi*1+rdx]
 601         add     r8b,r10b
 602         add     rsi,1
 603         mov     r11b,BYTE[r8*1+rdi]
 604         jnz     NEAR $L$cnowrap
 605         mov     rsi,rcx
 606 $L$cnowrap:
 607         mov     BYTE[r8*1+rdi],r10b
 608         mov     BYTE[r9*1+rdi],r11b
 609         add     r9b,1
 610         jnc     NEAR $L$c2ndloop
 611         mov     DWORD[256+rdi],-1
 612
 613 ALIGN   16
 614 $L$exit_key:
 615         xor     eax,eax
 616         mov     DWORD[((-8))+rdi],eax
 617         mov     DWORD[((-4))+rdi],eax
 618         mov     rdi,QWORD[8+rsp]        ;WIN64 epilogue
 619         mov     rsi,QWORD[16+rsp]
 620         DB      0F3h,0C3h               ;repret
 621 $L$SEH_end_asm_RC4_set_key:
 622 EXTERN  __imp_RtlVirtualUnwind
 623
 624 ALIGN   16
 625 stream_se_handler:
 626         push    rsi
 627         push    rdi
 628         push    rbx
 629         push    rbp
 630         push    r12
 631         push    r13
 632         push    r14
 633         push    r15
 634         pushfq
 635         sub     rsp,64
 636
 637         mov     rax,QWORD[120+r8]
 638         mov     rbx,QWORD[248+r8]
 639
 640         lea     r10,[$L$prologue]
 641         cmp     rbx,r10
 642         jb      NEAR $L$in_prologue
 643
 644         mov     rax,QWORD[152+r8]
 645
 646         lea     r10,[$L$epilogue]
 647         cmp     rbx,r10
 648         jae     NEAR $L$in_prologue
 649
 650         lea     rax,[24+rax]
 651
 652         mov     rbx,QWORD[((-8))+rax]
 653         mov     r12,QWORD[((-16))+rax]
 654         mov     r13,QWORD[((-24))+rax]
 655         mov     QWORD[144+r8],rbx
 656         mov     QWORD[216+r8],r12
 657         mov     QWORD[224+r8],r13
 658
 659 $L$in_prologue:
 660         mov     rdi,QWORD[8+rax]
 661         mov     rsi,QWORD[16+rax]
 662         mov     QWORD[152+r8],rax
 663         mov     QWORD[168+r8],rsi
 664         mov     QWORD[176+r8],rdi
 665
 666         jmp     NEAR $L$common_seh_exit
 667
 668
 669
 670 ALIGN   16
 671 key_se_handler:
 672         push    rsi
 673         push    rdi
 674         push    rbx
 675         push    rbp
 676         push    r12
 677         push    r13
 678         push    r14
 679         push    r15
 680         pushfq
 681         sub     rsp,64
 682
 683         mov     rax,QWORD[152+r8]
 684         mov     rdi,QWORD[8+rax]
 685         mov     rsi,QWORD[16+rax]
 686         mov     QWORD[168+r8],rsi
 687         mov     QWORD[176+r8],rdi
 688
 689 $L$common_seh_exit:
 690
 691         mov     rdi,QWORD[40+r9]
 692         mov     rsi,r8
 693         mov     ecx,154
 694         DD      0xa548f3fc
 695
 696         mov     rsi,r9
 697         xor     rcx,rcx
 698         mov     rdx,QWORD[8+rsi]
 699         mov     r8,QWORD[rsi]
 700         mov     r9,QWORD[16+rsi]
 701         mov     r10,QWORD[40+rsi]
 702         lea     r11,[56+rsi]
 703         lea     r12,[24+rsi]
 704         mov     QWORD[32+rsp],r10
 705         mov     QWORD[40+rsp],r11
 706         mov     QWORD[48+rsp],r12
 707         mov     QWORD[56+rsp],rcx
 708         call    QWORD[__imp_RtlVirtualUnwind]
 709
 710         mov     eax,1
 711         add     rsp,64
 712         popfq
 713         pop     r15
 714         pop     r14
 715         pop     r13
 716         pop     r12
 717         pop     rbp
 718         pop     rbx
 719         pop     rdi
 720         pop     rsi
 721         DB      0F3h,0C3h               ;repret
 722
 723
 724 section .pdata rdata align=4
 725 ALIGN   4
 726         DD      $L$SEH_begin_asm_RC4 wrt ..imagebase
 727         DD      $L$SEH_end_asm_RC4 wrt ..imagebase
 728         DD      $L$SEH_info_asm_RC4 wrt ..imagebase
 729
 730         DD      $L$SEH_begin_asm_RC4_set_key wrt ..imagebase
 731         DD      $L$SEH_end_asm_RC4_set_key wrt ..imagebase
 732         DD      $L$SEH_info_asm_RC4_set_key wrt ..imagebase
 733
 734 section .xdata rdata align=8
 735 ALIGN   8
 736 $L$SEH_info_asm_RC4:
 737 DB      9,0,0,0
 738         DD      stream_se_handler wrt ..imagebase
 739 $L$SEH_info_asm_RC4_set_key:
 740 DB      9,0,0,0
 741         DD      key_se_handler wrt ..imagebase