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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Twofish Cipher 3-way parallel algorithm (x86_64) * * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ #include <linux/linkage.h> .file "twofish-x86_64-asm-3way.S" .text /* structure of crypto context */ #define s0 0 #define s1 1024 #define s2 2048 #define s3 3072 #define w 4096 #define k 4128 /********************************************************************** 3-way twofish **********************************************************************/ #define CTX %rdi #define RIO %rdx #define RAB0 %rax #define RAB1 %rbx #define RAB2 %rcx #define RAB0d %eax #define RAB1d %ebx #define RAB2d %ecx #define RAB0bh %ah #define RAB1bh %bh #define RAB2bh %ch #define RAB0bl %al #define RAB1bl %bl #define RAB2bl %cl #define CD0 0x0(%rsp) #define CD1 0x8(%rsp) #define CD2 0x10(%rsp) # used only before/after all rounds #define RCD0 %r8 #define RCD1 %r9 #define RCD2 %r10 # used only during rounds #define RX0 %r8 #define RX1 %r9 #define RX2 %r10 #define RX0d %r8d #define RX1d %r9d #define RX2d %r10d #define RY0 %r11 #define RY1 %r12 #define RY2 %r13 #define RY0d %r11d #define RY1d %r12d #define RY2d %r13d #define RT0 %rdx #define RT1 %rsi #define RT0d %edx #define RT1d %esi #define RT1bl %sil #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \ movzbl ab ## bl, tmp2 ## d; \ movzbl ab ## bh, tmp1 ## d; \ rorq $(rot), ab; \ op1##l T0(CTX, tmp2, 4), dst ## d; \ op2##l T1(CTX, tmp1, 4), dst ## d; #define swap_ab_with_cd(ab, cd, tmp) \ movq cd, tmp; \ movq ab, cd; \ movq tmp, ab; /* * Combined G1 & G2 function. Reordered with help of rotates to have moves * at beginning. */ #define g1g2_3(ab, cd, Tx0, Tx1, Tx2, Tx3, Ty0, Ty1, Ty2, Ty3, x, y) \ /* G1,1 && G2,1 */ \ do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 0, ab ## 0, x ## 0); \ do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 0, ab ## 0, y ## 0); \ \ do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 1, ab ## 1, x ## 1); \ do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 1, ab ## 1, y ## 1); \ \ do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 2, ab ## 2, x ## 2); \ do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 2, ab ## 2, y ## 2); \ \ /* G1,2 && G2,2 */ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \ swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \ swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \ swap_ab_with_cd(ab ## 2, cd ## 2, RT0); #define enc_round_end(ab, x, y, n) \ addl y ## d, x ## d; \ addl x ## d, y ## d; \ addl k+4*(2*(n))(CTX), x ## d; \ xorl ab ## d, x ## d; \ addl k+4*(2*(n)+1)(CTX), y ## d; \ shrq $32, ab; \ roll $1, ab ## d; \ xorl y ## d, ab ## d; \ shlq $32, ab; \ rorl $1, x ## d; \ orq x, ab; #define dec_round_end(ba, x, y, n) \ addl y ## d, x ## d; \ addl x ## d, y ## d; \ addl k+4*(2*(n))(CTX), x ## d; \ addl k+4*(2*(n)+1)(CTX), y ## d; \ xorl ba ## d, y ## d; \ shrq $32, ba; \ roll $1, ba ## d; \ xorl x ## d, ba ## d; \ shlq $32, ba; \ rorl $1, y ## d; \ orq y, ba; #define encrypt_round3(ab, cd, n) \ g1g2_3(ab, cd, s0, s1, s2, s3, s0, s1, s2, s3, RX, RY); \ \ enc_round_end(ab ## 0, RX0, RY0, n); \ enc_round_end(ab ## 1, RX1, RY1, n); \ enc_round_end(ab ## 2, RX2, RY2, n); #define decrypt_round3(ba, dc, n) \ g1g2_3(ba, dc, s1, s2, s3, s0, s3, s0, s1, s2, RY, RX); \ \ dec_round_end(ba ## 0, RX0, RY0, n); \ dec_round_end(ba ## 1, RX1, RY1, n); \ dec_round_end(ba ## 2, RX2, RY2, n); #define encrypt_cycle3(ab, cd, n) \ encrypt_round3(ab, cd, n*2); \ encrypt_round3(ab, cd, (n*2)+1); #define decrypt_cycle3(ba, dc, n) \ decrypt_round3(ba, dc, (n*2)+1); \ decrypt_round3(ba, dc, (n*2)); #define push_cd() \ pushq RCD2; \ pushq RCD1; \ pushq RCD0; #define pop_cd() \ popq RCD0; \ popq RCD1; \ popq RCD2; #define inpack3(in, n, xy, m) \ movq 4*(n)(in), xy ## 0; \ xorq w+4*m(CTX), xy ## 0; \ \ movq 4*(4+(n))(in), xy ## 1; \ xorq w+4*m(CTX), xy ## 1; \ \ movq 4*(8+(n))(in), xy ## 2; \ xorq w+4*m(CTX), xy ## 2; #define outunpack3(op, out, n, xy, m) \ xorq w+4*m(CTX), xy ## 0; \ op ## q xy ## 0, 4*(n)(out); \ \ xorq w+4*m(CTX), xy ## 1; \ op ## q xy ## 1, 4*(4+(n))(out); \ \ xorq w+4*m(CTX), xy ## 2; \ op ## q xy ## 2, 4*(8+(n))(out); #define inpack_enc3() \ inpack3(RIO, 0, RAB, 0); \ inpack3(RIO, 2, RCD, 2); #define outunpack_enc3(op) \ outunpack3(op, RIO, 2, RAB, 6); \ outunpack3(op, RIO, 0, RCD, 4); #define inpack_dec3() \ inpack3(RIO, 0, RAB, 4); \ rorq $32, RAB0; \ rorq $32, RAB1; \ rorq $32, RAB2; \ inpack3(RIO, 2, RCD, 6); \ rorq $32, RCD0; \ rorq $32, RCD1; \ rorq $32, RCD2; #define outunpack_dec3() \ rorq $32, RCD0; \ rorq $32, RCD1; \ rorq $32, RCD2; \ outunpack3(mov, RIO, 0, RCD, 0); \ rorq $32, RAB0; \ rorq $32, RAB1; \ rorq $32, RAB2; \ outunpack3(mov, RIO, 2, RAB, 2); SYM_FUNC_START(__twofish_enc_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src, RIO * %rcx: bool, if true: xor output */ pushq %r13; pushq %r12; pushq %rbx; pushq %rcx; /* bool xor */ pushq %rsi; /* dst */ inpack_enc3(); push_cd(); encrypt_cycle3(RAB, CD, 0); encrypt_cycle3(RAB, CD, 1); encrypt_cycle3(RAB, CD, 2); encrypt_cycle3(RAB, CD, 3); encrypt_cycle3(RAB, CD, 4); encrypt_cycle3(RAB, CD, 5); encrypt_cycle3(RAB, CD, 6); encrypt_cycle3(RAB, CD, 7); pop_cd(); popq RIO; /* dst */ popq RT1; /* bool xor */ testb RT1bl, RT1bl; jnz .L__enc_xor3; outunpack_enc3(mov); popq %rbx; popq %r12; popq %r13; RET; .L__enc_xor3: outunpack_enc3(xor); popq %rbx; popq %r12; popq %r13; RET; SYM_FUNC_END(__twofish_enc_blk_3way) SYM_FUNC_START(twofish_dec_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst * %rdx: src, RIO */ pushq %r13; pushq %r12; pushq %rbx; pushq %rsi; /* dst */ inpack_dec3(); push_cd(); decrypt_cycle3(RAB, CD, 7); decrypt_cycle3(RAB, CD, 6); decrypt_cycle3(RAB, CD, 5); decrypt_cycle3(RAB, CD, 4); decrypt_cycle3(RAB, CD, 3); decrypt_cycle3(RAB, CD, 2); decrypt_cycle3(RAB, CD, 1); decrypt_cycle3(RAB, CD, 0); pop_cd(); popq RIO; /* dst */ outunpack_dec3(); popq %rbx; popq %r12; popq %r13; RET; SYM_FUNC_END(twofish_dec_blk_3way) |