Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Camellia Cipher Algorithm (x86_64) * * Copyright (C) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ #include <linux/linkage.h> .file "camellia-x86_64-asm_64.S" .text .extern camellia_sp10011110; .extern camellia_sp22000222; .extern camellia_sp03303033; .extern camellia_sp00444404; .extern camellia_sp02220222; .extern camellia_sp30333033; .extern camellia_sp44044404; .extern camellia_sp11101110; #define sp10011110 camellia_sp10011110 #define sp22000222 camellia_sp22000222 #define sp03303033 camellia_sp03303033 #define sp00444404 camellia_sp00444404 #define sp02220222 camellia_sp02220222 #define sp30333033 camellia_sp30333033 #define sp44044404 camellia_sp44044404 #define sp11101110 camellia_sp11101110 #define CAMELLIA_TABLE_BYTE_LEN 272 /* struct camellia_ctx: */ #define key_table 0 #define key_length CAMELLIA_TABLE_BYTE_LEN /* register macros */ #define CTX %rdi #define RIO %rsi #define RIOd %esi #define RAB0 %rax #define RCD0 %rcx #define RAB1 %rbx #define RCD1 %rdx #define RAB0d %eax #define RCD0d %ecx #define RAB1d %ebx #define RCD1d %edx #define RAB0bl %al #define RCD0bl %cl #define RAB1bl %bl #define RCD1bl %dl #define RAB0bh %ah #define RCD0bh %ch #define RAB1bh %bh #define RCD1bh %dh #define RT0 %rsi #define RT1 %r12 #define RT2 %r8 #define RT0d %esi #define RT1d %r12d #define RT2d %r8d #define RT2bl %r8b #define RXOR %r9 #define RR12 %r10 #define RDST %r11 #define RXORd %r9d #define RXORbl %r9b #define xor2ror16(T0, T1, tmp1, tmp2, ab, dst) \ leaq T0(%rip), tmp1; \ movzbl ab ## bl, tmp2 ## d; \ xorq (tmp1, tmp2, 8), dst; \ leaq T1(%rip), tmp2; \ movzbl ab ## bh, tmp1 ## d; \ rorq $16, ab; \ xorq (tmp2, tmp1, 8), dst; /********************************************************************** 1-way camellia **********************************************************************/ #define roundsm(ab, subkey, cd) \ movq (key_table + ((subkey) * 2) * 4)(CTX), RT2; \ \ xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \ xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \ xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \ xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \ \ xorq RT2, cd ## 0; #define fls(l, r, kl, kr) \ movl (key_table + ((kl) * 2) * 4)(CTX), RT0d; \ andl l ## 0d, RT0d; \ roll $1, RT0d; \ shlq $32, RT0; \ xorq RT0, l ## 0; \ movq (key_table + ((kr) * 2) * 4)(CTX), RT1; \ orq r ## 0, RT1; \ shrq $32, RT1; \ xorq RT1, r ## 0; \ \ movq (key_table + ((kl) * 2) * 4)(CTX), RT2; \ orq l ## 0, RT2; \ shrq $32, RT2; \ xorq RT2, l ## 0; \ movl (key_table + ((kr) * 2) * 4)(CTX), RT0d; \ andl r ## 0d, RT0d; \ roll $1, RT0d; \ shlq $32, RT0; \ xorq RT0, r ## 0; #define enc_rounds(i) \ roundsm(RAB, i + 2, RCD); \ roundsm(RCD, i + 3, RAB); \ roundsm(RAB, i + 4, RCD); \ roundsm(RCD, i + 5, RAB); \ roundsm(RAB, i + 6, RCD); \ roundsm(RCD, i + 7, RAB); #define enc_fls(i) \ fls(RAB, RCD, i + 0, i + 1); #define enc_inpack() \ movq (RIO), RAB0; \ bswapq RAB0; \ rolq $32, RAB0; \ movq 4*2(RIO), RCD0; \ bswapq RCD0; \ rorq $32, RCD0; \ xorq key_table(CTX), RAB0; #define enc_outunpack(op, max) \ xorq key_table(CTX, max, 8), RCD0; \ rorq $32, RCD0; \ bswapq RCD0; \ op ## q RCD0, (RIO); \ rolq $32, RAB0; \ bswapq RAB0; \ op ## q RAB0, 4*2(RIO); #define dec_rounds(i) \ roundsm(RAB, i + 7, RCD); \ roundsm(RCD, i + 6, RAB); \ roundsm(RAB, i + 5, RCD); \ roundsm(RCD, i + 4, RAB); \ roundsm(RAB, i + 3, RCD); \ roundsm(RCD, i + 2, RAB); #define dec_fls(i) \ fls(RAB, RCD, i + 1, i + 0); #define dec_inpack(max) \ movq (RIO), RAB0; \ bswapq RAB0; \ rolq $32, RAB0; \ movq 4*2(RIO), RCD0; \ bswapq RCD0; \ rorq $32, RCD0; \ xorq key_table(CTX, max, 8), RAB0; #define dec_outunpack() \ xorq key_table(CTX), RCD0; \ rorq $32, RCD0; \ bswapq RCD0; \ movq RCD0, (RIO); \ rolq $32, RAB0; \ bswapq RAB0; \ movq RAB0, 4*2(RIO); SYM_FUNC_START(__camellia_enc_blk) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src * %rcx: bool xor */ movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; movq %rdx, RIO; enc_inpack(); enc_rounds(0); enc_fls(8); enc_rounds(8); enc_fls(16); enc_rounds(16); movl $24, RT1d; /* max */ cmpb $16, key_length(CTX); je .L__enc_done; enc_fls(24); enc_rounds(24); movl $32, RT1d; /* max */ .L__enc_done: testb RXORbl, RXORbl; movq RDST, RIO; jnz .L__enc_xor; enc_outunpack(mov, RT1); movq RR12, %r12; RET; .L__enc_xor: enc_outunpack(xor, RT1); movq RR12, %r12; RET; SYM_FUNC_END(__camellia_enc_blk) SYM_FUNC_START(camellia_dec_blk) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src */ cmpl $16, key_length(CTX); movl $32, RT2d; movl $24, RXORd; cmovel RXORd, RT2d; /* max */ movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; dec_inpack(RT2); cmpb $24, RT2bl; je .L__dec_rounds16; dec_rounds(24); dec_fls(24); .L__dec_rounds16: dec_rounds(16); dec_fls(16); dec_rounds(8); dec_fls(8); dec_rounds(0); movq RDST, RIO; dec_outunpack(); movq RR12, %r12; RET; SYM_FUNC_END(camellia_dec_blk) /********************************************************************** 2-way camellia **********************************************************************/ #define roundsm2(ab, subkey, cd) \ movq (key_table + ((subkey) * 2) * 4)(CTX), RT2; \ xorq RT2, cd ## 1; \ \ xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \ xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \ xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \ xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \ \ xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 1, cd ## 1); \ xorq RT2, cd ## 0; \ xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 1, cd ## 1); \ xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 1, cd ## 1); \ xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 1, cd ## 1); #define fls2(l, r, kl, kr) \ movl (key_table + ((kl) * 2) * 4)(CTX), RT0d; \ andl l ## 0d, RT0d; \ roll $1, RT0d; \ shlq $32, RT0; \ xorq RT0, l ## 0; \ movq (key_table + ((kr) * 2) * 4)(CTX), RT1; \ orq r ## 0, RT1; \ shrq $32, RT1; \ xorq RT1, r ## 0; \ \ movl (key_table + ((kl) * 2) * 4)(CTX), RT2d; \ andl l ## 1d, RT2d; \ roll $1, RT2d; \ shlq $32, RT2; \ xorq RT2, l ## 1; \ movq (key_table + ((kr) * 2) * 4)(CTX), RT0; \ orq r ## 1, RT0; \ shrq $32, RT0; \ xorq RT0, r ## 1; \ \ movq (key_table + ((kl) * 2) * 4)(CTX), RT1; \ orq l ## 0, RT1; \ shrq $32, RT1; \ xorq RT1, l ## 0; \ movl (key_table + ((kr) * 2) * 4)(CTX), RT2d; \ andl r ## 0d, RT2d; \ roll $1, RT2d; \ shlq $32, RT2; \ xorq RT2, r ## 0; \ \ movq (key_table + ((kl) * 2) * 4)(CTX), RT0; \ orq l ## 1, RT0; \ shrq $32, RT0; \ xorq RT0, l ## 1; \ movl (key_table + ((kr) * 2) * 4)(CTX), RT1d; \ andl r ## 1d, RT1d; \ roll $1, RT1d; \ shlq $32, RT1; \ xorq RT1, r ## 1; #define enc_rounds2(i) \ roundsm2(RAB, i + 2, RCD); \ roundsm2(RCD, i + 3, RAB); \ roundsm2(RAB, i + 4, RCD); \ roundsm2(RCD, i + 5, RAB); \ roundsm2(RAB, i + 6, RCD); \ roundsm2(RCD, i + 7, RAB); #define enc_fls2(i) \ fls2(RAB, RCD, i + 0, i + 1); #define enc_inpack2() \ movq (RIO), RAB0; \ bswapq RAB0; \ rorq $32, RAB0; \ movq 4*2(RIO), RCD0; \ bswapq RCD0; \ rolq $32, RCD0; \ xorq key_table(CTX), RAB0; \ \ movq 8*2(RIO), RAB1; \ bswapq RAB1; \ rorq $32, RAB1; \ movq 12*2(RIO), RCD1; \ bswapq RCD1; \ rolq $32, RCD1; \ xorq key_table(CTX), RAB1; #define enc_outunpack2(op, max) \ xorq key_table(CTX, max, 8), RCD0; \ rolq $32, RCD0; \ bswapq RCD0; \ op ## q RCD0, (RIO); \ rorq $32, RAB0; \ bswapq RAB0; \ op ## q RAB0, 4*2(RIO); \ \ xorq key_table(CTX, max, 8), RCD1; \ rolq $32, RCD1; \ bswapq RCD1; \ op ## q RCD1, 8*2(RIO); \ rorq $32, RAB1; \ bswapq RAB1; \ op ## q RAB1, 12*2(RIO); #define dec_rounds2(i) \ roundsm2(RAB, i + 7, RCD); \ roundsm2(RCD, i + 6, RAB); \ roundsm2(RAB, i + 5, RCD); \ roundsm2(RCD, i + 4, RAB); \ roundsm2(RAB, i + 3, RCD); \ roundsm2(RCD, i + 2, RAB); #define dec_fls2(i) \ fls2(RAB, RCD, i + 1, i + 0); #define dec_inpack2(max) \ movq (RIO), RAB0; \ bswapq RAB0; \ rorq $32, RAB0; \ movq 4*2(RIO), RCD0; \ bswapq RCD0; \ rolq $32, RCD0; \ xorq key_table(CTX, max, 8), RAB0; \ \ movq 8*2(RIO), RAB1; \ bswapq RAB1; \ rorq $32, RAB1; \ movq 12*2(RIO), RCD1; \ bswapq RCD1; \ rolq $32, RCD1; \ xorq key_table(CTX, max, 8), RAB1; #define dec_outunpack2() \ xorq key_table(CTX), RCD0; \ rolq $32, RCD0; \ bswapq RCD0; \ movq RCD0, (RIO); \ rorq $32, RAB0; \ bswapq RAB0; \ movq RAB0, 4*2(RIO); \ \ xorq key_table(CTX), RCD1; \ rolq $32, RCD1; \ bswapq RCD1; \ movq RCD1, 8*2(RIO); \ rorq $32, RAB1; \ bswapq RAB1; \ movq RAB1, 12*2(RIO); SYM_FUNC_START(__camellia_enc_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src * %rcx: bool xor */ pushq %rbx; movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; movq %rdx, RIO; enc_inpack2(); enc_rounds2(0); enc_fls2(8); enc_rounds2(8); enc_fls2(16); enc_rounds2(16); movl $24, RT2d; /* max */ cmpb $16, key_length(CTX); je .L__enc2_done; enc_fls2(24); enc_rounds2(24); movl $32, RT2d; /* max */ .L__enc2_done: test RXORbl, RXORbl; movq RDST, RIO; jnz .L__enc2_xor; enc_outunpack2(mov, RT2); movq RR12, %r12; popq %rbx; RET; .L__enc2_xor: enc_outunpack2(xor, RT2); movq RR12, %r12; popq %rbx; RET; SYM_FUNC_END(__camellia_enc_blk_2way) SYM_FUNC_START(camellia_dec_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src */ cmpl $16, key_length(CTX); movl $32, RT2d; movl $24, RXORd; cmovel RXORd, RT2d; /* max */ movq %rbx, RXOR; movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; dec_inpack2(RT2); cmpb $24, RT2bl; je .L__dec2_rounds16; dec_rounds2(24); dec_fls2(24); .L__dec2_rounds16: dec_rounds2(16); dec_fls2(16); dec_rounds2(8); dec_fls2(8); dec_rounds2(0); movq RDST, RIO; dec_outunpack2(); movq RR12, %r12; movq RXOR, %rbx; RET; SYM_FUNC_END(camellia_dec_blk_2way) |