| 1 | /*
|
|---|
| 2 | * Implementation of DES encryption for NTLM
|
|---|
| 3 | *
|
|---|
| 4 | * Copyright 1997-2005 Simon Tatham.
|
|---|
| 5 | *
|
|---|
| 6 | * This software is released under the MIT license.
|
|---|
| 7 | */
|
|---|
| 8 |
|
|---|
| 9 | /*
|
|---|
| 10 | * Description of DES
|
|---|
| 11 | * ------------------
|
|---|
| 12 | *
|
|---|
| 13 | * Unlike the description in FIPS 46, I'm going to use _sensible_ indices:
|
|---|
| 14 | * bits in an n-bit word are numbered from 0 at the LSB to n-1 at the MSB.
|
|---|
| 15 | * And S-boxes are indexed by six consecutive bits, not by the outer two
|
|---|
| 16 | * followed by the middle four.
|
|---|
| 17 | *
|
|---|
| 18 | * The DES encryption routine requires a 64-bit input, and a key schedule K
|
|---|
| 19 | * containing 16 48-bit elements.
|
|---|
| 20 | *
|
|---|
| 21 | * First the input is permuted by the initial permutation IP.
|
|---|
| 22 | * Then the input is split into 32-bit words L and R. (L is the MSW.)
|
|---|
| 23 | * Next, 16 rounds. In each round:
|
|---|
| 24 | * (L, R) <- (R, L xor f(R, K[i]))
|
|---|
| 25 | * Then the pre-output words L and R are swapped.
|
|---|
| 26 | * Then L and R are glued back together into a 64-bit word. (L is the MSW,
|
|---|
| 27 | * again, but since we just swapped them, the MSW is the R that came out
|
|---|
| 28 | * of the last round.)
|
|---|
| 29 | * The 64-bit output block is permuted by the inverse of IP and returned.
|
|---|
| 30 | *
|
|---|
| 31 | * Decryption is identical except that the elements of K are used in the
|
|---|
| 32 | * opposite order. (This wouldn't work if that word swap didn't happen.)
|
|---|
| 33 | *
|
|---|
| 34 | * The function f, used in each round, accepts a 32-bit word R and a
|
|---|
| 35 | * 48-bit key block K. It produces a 32-bit output.
|
|---|
| 36 | *
|
|---|
| 37 | * First R is expanded to 48 bits using the bit-selection function E.
|
|---|
| 38 | * The resulting 48-bit block is XORed with the key block K to produce
|
|---|
| 39 | * a 48-bit block X.
|
|---|
| 40 | * This block X is split into eight groups of 6 bits. Each group of 6
|
|---|
| 41 | * bits is then looked up in one of the eight S-boxes to convert
|
|---|
| 42 | * it to 4 bits. These eight groups of 4 bits are glued back
|
|---|
| 43 | * together to produce a 32-bit preoutput block.
|
|---|
| 44 | * The preoutput block is permuted using the permutation P and returned.
|
|---|
| 45 | *
|
|---|
| 46 | * Key setup maps a 64-bit key word into a 16x48-bit key schedule. Although
|
|---|
| 47 | * the approved input format for the key is a 64-bit word, eight of the
|
|---|
| 48 | * bits are discarded, so the actual quantity of key used is 56 bits.
|
|---|
| 49 | *
|
|---|
| 50 | * First the input key is converted to two 28-bit words C and D using
|
|---|
| 51 | * the bit-selection function PC1.
|
|---|
| 52 | * Then 16 rounds of key setup occur. In each round, C and D are each
|
|---|
| 53 | * rotated left by either 1 or 2 bits (depending on which round), and
|
|---|
| 54 | * then converted into a key schedule element using the bit-selection
|
|---|
| 55 | * function PC2.
|
|---|
| 56 | *
|
|---|
| 57 | * That's the actual algorithm. Now for the tedious details: all those
|
|---|
| 58 | * painful permutations and lookup tables.
|
|---|
| 59 | *
|
|---|
| 60 | * IP is a 64-to-64 bit permutation. Its output contains the following
|
|---|
| 61 | * bits of its input (listed in order MSB to LSB of output).
|
|---|
| 62 | *
|
|---|
| 63 | * 6 14 22 30 38 46 54 62 4 12 20 28 36 44 52 60
|
|---|
| 64 | * 2 10 18 26 34 42 50 58 0 8 16 24 32 40 48 56
|
|---|
| 65 | * 7 15 23 31 39 47 55 63 5 13 21 29 37 45 53 61
|
|---|
| 66 | * 3 11 19 27 35 43 51 59 1 9 17 25 33 41 49 57
|
|---|
| 67 | *
|
|---|
| 68 | * E is a 32-to-48 bit selection function. Its output contains the following
|
|---|
| 69 | * bits of its input (listed in order MSB to LSB of output).
|
|---|
| 70 | *
|
|---|
| 71 | * 0 31 30 29 28 27 28 27 26 25 24 23 24 23 22 21 20 19 20 19 18 17 16 15
|
|---|
| 72 | * 16 15 14 13 12 11 12 11 10 9 8 7 8 7 6 5 4 3 4 3 2 1 0 31
|
|---|
| 73 | *
|
|---|
| 74 | * The S-boxes are arbitrary table-lookups each mapping a 6-bit input to a
|
|---|
| 75 | * 4-bit output. In other words, each S-box is an array[64] of 4-bit numbers.
|
|---|
| 76 | * The S-boxes are listed below. The first S-box listed is applied to the
|
|---|
| 77 | * most significant six bits of the block X; the last one is applied to the
|
|---|
| 78 | * least significant.
|
|---|
| 79 | *
|
|---|
| 80 | * 14 0 4 15 13 7 1 4 2 14 15 2 11 13 8 1
|
|---|
| 81 | * 3 10 10 6 6 12 12 11 5 9 9 5 0 3 7 8
|
|---|
| 82 | * 4 15 1 12 14 8 8 2 13 4 6 9 2 1 11 7
|
|---|
| 83 | * 15 5 12 11 9 3 7 14 3 10 10 0 5 6 0 13
|
|---|
| 84 | *
|
|---|
| 85 | * 15 3 1 13 8 4 14 7 6 15 11 2 3 8 4 14
|
|---|
| 86 | * 9 12 7 0 2 1 13 10 12 6 0 9 5 11 10 5
|
|---|
| 87 | * 0 13 14 8 7 10 11 1 10 3 4 15 13 4 1 2
|
|---|
| 88 | * 5 11 8 6 12 7 6 12 9 0 3 5 2 14 15 9
|
|---|
| 89 | *
|
|---|
| 90 | * 10 13 0 7 9 0 14 9 6 3 3 4 15 6 5 10
|
|---|
| 91 | * 1 2 13 8 12 5 7 14 11 12 4 11 2 15 8 1
|
|---|
| 92 | * 13 1 6 10 4 13 9 0 8 6 15 9 3 8 0 7
|
|---|
| 93 | * 11 4 1 15 2 14 12 3 5 11 10 5 14 2 7 12
|
|---|
| 94 | *
|
|---|
| 95 | * 7 13 13 8 14 11 3 5 0 6 6 15 9 0 10 3
|
|---|
| 96 | * 1 4 2 7 8 2 5 12 11 1 12 10 4 14 15 9
|
|---|
| 97 | * 10 3 6 15 9 0 0 6 12 10 11 1 7 13 13 8
|
|---|
| 98 | * 15 9 1 4 3 5 14 11 5 12 2 7 8 2 4 14
|
|---|
| 99 | *
|
|---|
| 100 | * 2 14 12 11 4 2 1 12 7 4 10 7 11 13 6 1
|
|---|
| 101 | * 8 5 5 0 3 15 15 10 13 3 0 9 14 8 9 6
|
|---|
| 102 | * 4 11 2 8 1 12 11 7 10 1 13 14 7 2 8 13
|
|---|
| 103 | * 15 6 9 15 12 0 5 9 6 10 3 4 0 5 14 3
|
|---|
| 104 | *
|
|---|
| 105 | * 12 10 1 15 10 4 15 2 9 7 2 12 6 9 8 5
|
|---|
| 106 | * 0 6 13 1 3 13 4 14 14 0 7 11 5 3 11 8
|
|---|
| 107 | * 9 4 14 3 15 2 5 12 2 9 8 5 12 15 3 10
|
|---|
| 108 | * 7 11 0 14 4 1 10 7 1 6 13 0 11 8 6 13
|
|---|
| 109 | *
|
|---|
| 110 | * 4 13 11 0 2 11 14 7 15 4 0 9 8 1 13 10
|
|---|
| 111 | * 3 14 12 3 9 5 7 12 5 2 10 15 6 8 1 6
|
|---|
| 112 | * 1 6 4 11 11 13 13 8 12 1 3 4 7 10 14 7
|
|---|
| 113 | * 10 9 15 5 6 0 8 15 0 14 5 2 9 3 2 12
|
|---|
| 114 | *
|
|---|
| 115 | * 13 1 2 15 8 13 4 8 6 10 15 3 11 7 1 4
|
|---|
| 116 | * 10 12 9 5 3 6 14 11 5 0 0 14 12 9 7 2
|
|---|
| 117 | * 7 2 11 1 4 14 1 7 9 4 12 10 14 8 2 13
|
|---|
| 118 | * 0 15 6 12 10 9 13 0 15 3 3 5 5 6 8 11
|
|---|
| 119 | *
|
|---|
| 120 | * P is a 32-to-32 bit permutation. Its output contains the following
|
|---|
| 121 | * bits of its input (listed in order MSB to LSB of output).
|
|---|
| 122 | *
|
|---|
| 123 | * 16 25 12 11 3 20 4 15 31 17 9 6 27 14 1 22
|
|---|
| 124 | * 30 24 8 18 0 5 29 23 13 19 2 26 10 21 28 7
|
|---|
| 125 | *
|
|---|
| 126 | * PC1 is a 64-to-56 bit selection function. Its output is in two words,
|
|---|
| 127 | * C and D. The word C contains the following bits of its input (listed
|
|---|
| 128 | * in order MSB to LSB of output).
|
|---|
| 129 | *
|
|---|
| 130 | * 7 15 23 31 39 47 55 63 6 14 22 30 38 46
|
|---|
| 131 | * 54 62 5 13 21 29 37 45 53 61 4 12 20 28
|
|---|
| 132 | *
|
|---|
| 133 | * And the word D contains these bits.
|
|---|
| 134 | *
|
|---|
| 135 | * 1 9 17 25 33 41 49 57 2 10 18 26 34 42
|
|---|
| 136 | * 50 58 3 11 19 27 35 43 51 59 36 44 52 60
|
|---|
| 137 | *
|
|---|
| 138 | * PC2 is a 56-to-48 bit selection function. Its input is in two words,
|
|---|
| 139 | * C and D. These are treated as one 56-bit word (with C more significant,
|
|---|
| 140 | * so that bits 55 to 28 of the word are bits 27 to 0 of C, and bits 27 to
|
|---|
| 141 | * 0 of the word are bits 27 to 0 of D). The output contains the following
|
|---|
| 142 | * bits of this 56-bit input word (listed in order MSB to LSB of output).
|
|---|
| 143 | *
|
|---|
| 144 | * 42 39 45 32 55 51 53 28 41 50 35 46 33 37 44 52 30 48 40 49 29 36 43 54
|
|---|
| 145 | * 15 4 25 19 9 1 26 16 5 11 23 8 12 7 17 0 22 3 10 14 6 20 27 24
|
|---|
| 146 | */
|
|---|
| 147 |
|
|---|
| 148 | /*
|
|---|
| 149 | * Implementation details
|
|---|
| 150 | * ----------------------
|
|---|
| 151 | *
|
|---|
| 152 | * If you look at the code in this module, you'll find it looks
|
|---|
| 153 | * nothing _like_ the above algorithm. Here I explain the
|
|---|
| 154 | * differences...
|
|---|
| 155 | *
|
|---|
| 156 | * Key setup has not been heavily optimised here. We are not
|
|---|
| 157 | * concerned with key agility: we aren't codebreakers. We don't
|
|---|
| 158 | * mind a little delay (and it really is a little one; it may be a
|
|---|
| 159 | * factor of five or so slower than it could be but it's still not
|
|---|
| 160 | * an appreciable length of time) while setting up. The only tweaks
|
|---|
| 161 | * in the key setup are ones which change the format of the key
|
|---|
| 162 | * schedule to speed up the actual encryption. I'll describe those
|
|---|
| 163 | * below.
|
|---|
| 164 | *
|
|---|
| 165 | * The first and most obvious optimisation is the S-boxes. Since
|
|---|
| 166 | * each S-box always targets the same four bits in the final 32-bit
|
|---|
| 167 | * word, so the output from (for example) S-box 0 must always be
|
|---|
| 168 | * shifted left 28 bits, we can store the already-shifted outputs
|
|---|
| 169 | * in the lookup tables. This reduces lookup-and-shift to lookup,
|
|---|
| 170 | * so the S-box step is now just a question of ORing together eight
|
|---|
| 171 | * table lookups.
|
|---|
| 172 | *
|
|---|
| 173 | * The permutation P is just a bit order change; it's invariant
|
|---|
| 174 | * with respect to OR, in that P(x)|P(y) = P(x|y). Therefore, we
|
|---|
| 175 | * can apply P to every entry of the S-box tables and then we don't
|
|---|
| 176 | * have to do it in the code of f(). This yields a set of tables
|
|---|
| 177 | * which might be called SP-boxes.
|
|---|
| 178 | *
|
|---|
| 179 | * The bit-selection function E is our next target. Note that E is
|
|---|
| 180 | * immediately followed by the operation of splitting into 6-bit
|
|---|
| 181 | * chunks. Examining the 6-bit chunks coming out of E we notice
|
|---|
| 182 | * they're all contiguous within the word (speaking cyclically -
|
|---|
| 183 | * the end two wrap round); so we can extract those bit strings
|
|---|
| 184 | * individually rather than explicitly running E. This would yield
|
|---|
| 185 | * code such as
|
|---|
| 186 | *
|
|---|
| 187 | * y |= SPboxes[0][ (rotl(R, 5) ^ top6bitsofK) & 0x3F ];
|
|---|
| 188 | * t |= SPboxes[1][ (rotl(R,11) ^ next6bitsofK) & 0x3F ];
|
|---|
| 189 | *
|
|---|
| 190 | * and so on; and the key schedule preparation would have to
|
|---|
| 191 | * provide each 6-bit chunk separately.
|
|---|
| 192 | *
|
|---|
| 193 | * Really we'd like to XOR in the key schedule element before
|
|---|
| 194 | * looking up bit strings in R. This we can't do, naively, because
|
|---|
| 195 | * the 6-bit strings we want overlap. But look at the strings:
|
|---|
| 196 | *
|
|---|
| 197 | * 3322222222221111111111
|
|---|
| 198 | * bit 10987654321098765432109876543210
|
|---|
| 199 | *
|
|---|
| 200 | * box0 XXXXX X
|
|---|
| 201 | * box1 XXXXXX
|
|---|
| 202 | * box2 XXXXXX
|
|---|
| 203 | * box3 XXXXXX
|
|---|
| 204 | * box4 XXXXXX
|
|---|
| 205 | * box5 XXXXXX
|
|---|
| 206 | * box6 XXXXXX
|
|---|
| 207 | * box7 X XXXXX
|
|---|
| 208 | *
|
|---|
| 209 | * The bit strings we need to XOR in for boxes 0, 2, 4 and 6 don't
|
|---|
| 210 | * overlap with each other. Neither do the ones for boxes 1, 3, 5
|
|---|
| 211 | * and 7. So we could provide the key schedule in the form of two
|
|---|
| 212 | * words that we can separately XOR into R, and then every S-box
|
|---|
| 213 | * index is available as a (cyclically) contiguous 6-bit substring
|
|---|
| 214 | * of one or the other of the results.
|
|---|
| 215 | *
|
|---|
| 216 | * The comments in Eric Young's libdes implementation point out
|
|---|
| 217 | * that two of these bit strings require a rotation (rather than a
|
|---|
| 218 | * simple shift) to extract. It's unavoidable that at least _one_
|
|---|
| 219 | * must do; but we can actually run the whole inner algorithm (all
|
|---|
| 220 | * 16 rounds) rotated one bit to the left, so that what the `real'
|
|---|
| 221 | * DES description sees as L=0x80000001 we see as L=0x00000003.
|
|---|
| 222 | * This requires rotating all our SP-box entries one bit to the
|
|---|
| 223 | * left, and rotating each word of the key schedule elements one to
|
|---|
| 224 | * the left, and rotating L and R one bit left just after IP and
|
|---|
| 225 | * one bit right again just before FP. And in each round we convert
|
|---|
| 226 | * a rotate into a shift, so we've saved a few per cent.
|
|---|
| 227 | *
|
|---|
| 228 | * That's about it for the inner loop; the SP-box tables as listed
|
|---|
| 229 | * below are what I've described here (the original S value,
|
|---|
| 230 | * shifted to its final place in the input to P, run through P, and
|
|---|
| 231 | * then rotated one bit left). All that remains is to optimise the
|
|---|
| 232 | * initial permutation IP.
|
|---|
| 233 | *
|
|---|
| 234 | * IP is not an arbitrary permutation. It has the nice property
|
|---|
| 235 | * that if you take any bit number, write it in binary (6 bits),
|
|---|
| 236 | * permute those 6 bits and invert some of them, you get the final
|
|---|
| 237 | * position of that bit. Specifically, the bit whose initial
|
|---|
| 238 | * position is given (in binary) as fedcba ends up in position
|
|---|
| 239 | * AcbFED (where a capital letter denotes the inverse of a bit).
|
|---|
| 240 | *
|
|---|
| 241 | * We have the 64-bit data in two 32-bit words L and R, where bits
|
|---|
| 242 | * in L are those with f=1 and bits in R are those with f=0. We
|
|---|
| 243 | * note that we can do a simple transformation: suppose we exchange
|
|---|
| 244 | * the bits with f=1,c=0 and the bits with f=0,c=1. This will cause
|
|---|
| 245 | * the bit fedcba to be in position cedfba - we've `swapped' bits c
|
|---|
| 246 | * and f in the position of each bit!
|
|---|
| 247 | *
|
|---|
| 248 | * Better still, this transformation is easy. In the example above,
|
|---|
| 249 | * bits in L with c=0 are bits 0x0F0F0F0F, and those in R with c=1
|
|---|
| 250 | * are 0xF0F0F0F0. So we can do
|
|---|
| 251 | *
|
|---|
| 252 | * difference = ((R >> 4) ^ L) & 0x0F0F0F0F
|
|---|
| 253 | * R ^= (difference << 4)
|
|---|
| 254 | * L ^= difference
|
|---|
| 255 | *
|
|---|
| 256 | * to perform the swap. Let's denote this by bitswap(4,0x0F0F0F0F).
|
|---|
| 257 | * Also, we can invert the bit at the top just by exchanging L and
|
|---|
| 258 | * R. So in a few swaps and a few of these bit operations we can
|
|---|
| 259 | * do:
|
|---|
| 260 | *
|
|---|
| 261 | * Initially the position of bit fedcba is fedcba
|
|---|
| 262 | * Swap L with R to make it Fedcba
|
|---|
| 263 | * Perform bitswap( 4,0x0F0F0F0F) to make it cedFba
|
|---|
| 264 | * Perform bitswap(16,0x0000FFFF) to make it ecdFba
|
|---|
| 265 | * Swap L with R to make it EcdFba
|
|---|
| 266 | * Perform bitswap( 2,0x33333333) to make it bcdFEa
|
|---|
| 267 | * Perform bitswap( 8,0x00FF00FF) to make it dcbFEa
|
|---|
| 268 | * Swap L with R to make it DcbFEa
|
|---|
| 269 | * Perform bitswap( 1,0x55555555) to make it acbFED
|
|---|
| 270 | * Swap L with R to make it AcbFED
|
|---|
| 271 | *
|
|---|
| 272 | * (In the actual code the four swaps are implicit: R and L are
|
|---|
| 273 | * simply used the other way round in the first, second and last
|
|---|
| 274 | * bitswap operations.)
|
|---|
| 275 | *
|
|---|
| 276 | * The final permutation is just the inverse of IP, so it can be
|
|---|
| 277 | * performed by a similar set of operations.
|
|---|
| 278 | */
|
|---|
| 279 |
|
|---|
| 280 | struct des_context {
|
|---|
| 281 | quint32 k0246[16], k1357[16];
|
|---|
| 282 | };
|
|---|
| 283 |
|
|---|
| 284 | #define rotl(x, c) ( (x << c) | (x >> (32-c)) )
|
|---|
| 285 | #define rotl28(x, c) ( ( (x << c) | (x >> (28-c)) ) & 0x0FFFFFFF)
|
|---|
| 286 |
|
|---|
| 287 | static quint32 bitsel(quint32 * input, const int *bitnums, int size)
|
|---|
| 288 | {
|
|---|
| 289 | quint32 ret = 0;
|
|---|
| 290 | while (size--) {
|
|---|
| 291 | int bitpos = *bitnums++;
|
|---|
| 292 | ret <<= 1;
|
|---|
| 293 | if (bitpos >= 0)
|
|---|
| 294 | ret |= 1 & (input[bitpos / 32] >> (bitpos % 32));
|
|---|
| 295 | }
|
|---|
| 296 | return ret;
|
|---|
| 297 | }
|
|---|
| 298 |
|
|---|
| 299 | static inline void des_key_setup(quint32 key_msw, quint32 key_lsw,
|
|---|
| 300 | struct des_context *sched)
|
|---|
| 301 | {
|
|---|
| 302 | /* Tables are modified to work with 56-bit key */
|
|---|
| 303 | static const int PC1_Cbits[] = {
|
|---|
| 304 | 6, 13, 20, 27, 34, 41, 48, 55, 5, 12, 19, 26, 33, 40,
|
|---|
| 305 | 47, 54, 4, 11, 18, 25, 32, 39, 46, 53, 3, 10, 17, 24
|
|---|
| 306 | };
|
|---|
| 307 | static const int PC1_Dbits[] = {
|
|---|
| 308 | 0, 7, 14, 21, 28, 35, 42, 49, 1, 8, 15, 22, 29, 36,
|
|---|
| 309 | 43, 50, 2, 9, 16, 23, 30, 37, 44, 51, 31, 38, 45, 52
|
|---|
| 310 | };
|
|---|
| 311 | /*
|
|---|
| 312 | * The bit numbers in the two lists below don't correspond to
|
|---|
| 313 | * the ones in the above description of PC2, because in the
|
|---|
| 314 | * above description C and D are concatenated so `bit 28' means
|
|---|
| 315 | * bit 0 of C. In this implementation we're using the standard
|
|---|
| 316 | * `bitsel' function above and C is in the second word, so bit
|
|---|
| 317 | * 0 of C is addressed by writing `32' here.
|
|---|
| 318 | */
|
|---|
| 319 | static const int PC2_0246[] = {
|
|---|
| 320 | 49, 36, 59, 55, -1, -1, 37, 41, 48, 56, 34, 52, -1, -1, 15, 4,
|
|---|
| 321 | 25, 19, 9, 1, -1, -1, 12, 7, 17, 0, 22, 3, -1, -1, 46, 43
|
|---|
| 322 | };
|
|---|
| 323 | static const int PC2_1357[] = {
|
|---|
| 324 | -1, -1, 57, 32, 45, 54, 39, 50, -1, -1, 44, 53, 33, 40, 47, 58,
|
|---|
| 325 | -1, -1, 26, 16, 5, 11, 23, 8, -1, -1, 10, 14, 6, 20, 27, 24
|
|---|
| 326 | };
|
|---|
| 327 | static const int leftshifts[] = {
|
|---|
| 328 | 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1
|
|---|
| 329 | };
|
|---|
| 330 |
|
|---|
| 331 | quint32 C, D;
|
|---|
| 332 | quint32 buf[2];
|
|---|
| 333 | int i;
|
|---|
| 334 |
|
|---|
| 335 | buf[0] = key_lsw;
|
|---|
| 336 | buf[1] = key_msw;
|
|---|
| 337 |
|
|---|
| 338 | C = bitsel(buf, PC1_Cbits, 28);
|
|---|
| 339 | D = bitsel(buf, PC1_Dbits, 28);
|
|---|
| 340 |
|
|---|
| 341 | for (i = 0; i < 16; i++) {
|
|---|
| 342 | C = rotl28(C, leftshifts[i]);
|
|---|
| 343 | D = rotl28(D, leftshifts[i]);
|
|---|
| 344 | buf[0] = D;
|
|---|
| 345 | buf[1] = C;
|
|---|
| 346 | sched->k0246[i] = bitsel(buf, PC2_0246, 32);
|
|---|
| 347 | sched->k1357[i] = bitsel(buf, PC2_1357, 32);
|
|---|
| 348 | }
|
|---|
| 349 | }
|
|---|
| 350 |
|
|---|
| 351 | static const quint32 SPboxes[8][64] = {
|
|---|
| 352 | {0x01010400, 0x00000000, 0x00010000, 0x01010404,
|
|---|
| 353 | 0x01010004, 0x00010404, 0x00000004, 0x00010000,
|
|---|
| 354 | 0x00000400, 0x01010400, 0x01010404, 0x00000400,
|
|---|
| 355 | 0x01000404, 0x01010004, 0x01000000, 0x00000004,
|
|---|
| 356 | 0x00000404, 0x01000400, 0x01000400, 0x00010400,
|
|---|
| 357 | 0x00010400, 0x01010000, 0x01010000, 0x01000404,
|
|---|
| 358 | 0x00010004, 0x01000004, 0x01000004, 0x00010004,
|
|---|
| 359 | 0x00000000, 0x00000404, 0x00010404, 0x01000000,
|
|---|
| 360 | 0x00010000, 0x01010404, 0x00000004, 0x01010000,
|
|---|
| 361 | 0x01010400, 0x01000000, 0x01000000, 0x00000400,
|
|---|
| 362 | 0x01010004, 0x00010000, 0x00010400, 0x01000004,
|
|---|
| 363 | 0x00000400, 0x00000004, 0x01000404, 0x00010404,
|
|---|
| 364 | 0x01010404, 0x00010004, 0x01010000, 0x01000404,
|
|---|
| 365 | 0x01000004, 0x00000404, 0x00010404, 0x01010400,
|
|---|
| 366 | 0x00000404, 0x01000400, 0x01000400, 0x00000000,
|
|---|
| 367 | 0x00010004, 0x00010400, 0x00000000, 0x01010004},
|
|---|
| 368 |
|
|---|
| 369 | {0x80108020, 0x80008000, 0x00008000, 0x00108020,
|
|---|
| 370 | 0x00100000, 0x00000020, 0x80100020, 0x80008020,
|
|---|
| 371 | 0x80000020, 0x80108020, 0x80108000, 0x80000000,
|
|---|
| 372 | 0x80008000, 0x00100000, 0x00000020, 0x80100020,
|
|---|
| 373 | 0x00108000, 0x00100020, 0x80008020, 0x00000000,
|
|---|
| 374 | 0x80000000, 0x00008000, 0x00108020, 0x80100000,
|
|---|
| 375 | 0x00100020, 0x80000020, 0x00000000, 0x00108000,
|
|---|
| 376 | 0x00008020, 0x80108000, 0x80100000, 0x00008020,
|
|---|
| 377 | 0x00000000, 0x00108020, 0x80100020, 0x00100000,
|
|---|
| 378 | 0x80008020, 0x80100000, 0x80108000, 0x00008000,
|
|---|
| 379 | 0x80100000, 0x80008000, 0x00000020, 0x80108020,
|
|---|
| 380 | 0x00108020, 0x00000020, 0x00008000, 0x80000000,
|
|---|
| 381 | 0x00008020, 0x80108000, 0x00100000, 0x80000020,
|
|---|
| 382 | 0x00100020, 0x80008020, 0x80000020, 0x00100020,
|
|---|
| 383 | 0x00108000, 0x00000000, 0x80008000, 0x00008020,
|
|---|
| 384 | 0x80000000, 0x80100020, 0x80108020, 0x00108000},
|
|---|
| 385 |
|
|---|
| 386 | {0x00000208, 0x08020200, 0x00000000, 0x08020008,
|
|---|
| 387 | 0x08000200, 0x00000000, 0x00020208, 0x08000200,
|
|---|
| 388 | 0x00020008, 0x08000008, 0x08000008, 0x00020000,
|
|---|
| 389 | 0x08020208, 0x00020008, 0x08020000, 0x00000208,
|
|---|
| 390 | 0x08000000, 0x00000008, 0x08020200, 0x00000200,
|
|---|
| 391 | 0x00020200, 0x08020000, 0x08020008, 0x00020208,
|
|---|
| 392 | 0x08000208, 0x00020200, 0x00020000, 0x08000208,
|
|---|
| 393 | 0x00000008, 0x08020208, 0x00000200, 0x08000000,
|
|---|
| 394 | 0x08020200, 0x08000000, 0x00020008, 0x00000208,
|
|---|
| 395 | 0x00020000, 0x08020200, 0x08000200, 0x00000000,
|
|---|
| 396 | 0x00000200, 0x00020008, 0x08020208, 0x08000200,
|
|---|
| 397 | 0x08000008, 0x00000200, 0x00000000, 0x08020008,
|
|---|
| 398 | 0x08000208, 0x00020000, 0x08000000, 0x08020208,
|
|---|
| 399 | 0x00000008, 0x00020208, 0x00020200, 0x08000008,
|
|---|
| 400 | 0x08020000, 0x08000208, 0x00000208, 0x08020000,
|
|---|
| 401 | 0x00020208, 0x00000008, 0x08020008, 0x00020200},
|
|---|
| 402 |
|
|---|
| 403 | {0x00802001, 0x00002081, 0x00002081, 0x00000080,
|
|---|
| 404 | 0x00802080, 0x00800081, 0x00800001, 0x00002001,
|
|---|
| 405 | 0x00000000, 0x00802000, 0x00802000, 0x00802081,
|
|---|
| 406 | 0x00000081, 0x00000000, 0x00800080, 0x00800001,
|
|---|
| 407 | 0x00000001, 0x00002000, 0x00800000, 0x00802001,
|
|---|
| 408 | 0x00000080, 0x00800000, 0x00002001, 0x00002080,
|
|---|
| 409 | 0x00800081, 0x00000001, 0x00002080, 0x00800080,
|
|---|
| 410 | 0x00002000, 0x00802080, 0x00802081, 0x00000081,
|
|---|
| 411 | 0x00800080, 0x00800001, 0x00802000, 0x00802081,
|
|---|
| 412 | 0x00000081, 0x00000000, 0x00000000, 0x00802000,
|
|---|
| 413 | 0x00002080, 0x00800080, 0x00800081, 0x00000001,
|
|---|
| 414 | 0x00802001, 0x00002081, 0x00002081, 0x00000080,
|
|---|
| 415 | 0x00802081, 0x00000081, 0x00000001, 0x00002000,
|
|---|
| 416 | 0x00800001, 0x00002001, 0x00802080, 0x00800081,
|
|---|
| 417 | 0x00002001, 0x00002080, 0x00800000, 0x00802001,
|
|---|
| 418 | 0x00000080, 0x00800000, 0x00002000, 0x00802080},
|
|---|
| 419 |
|
|---|
| 420 | {0x00000100, 0x02080100, 0x02080000, 0x42000100,
|
|---|
| 421 | 0x00080000, 0x00000100, 0x40000000, 0x02080000,
|
|---|
| 422 | 0x40080100, 0x00080000, 0x02000100, 0x40080100,
|
|---|
| 423 | 0x42000100, 0x42080000, 0x00080100, 0x40000000,
|
|---|
| 424 | 0x02000000, 0x40080000, 0x40080000, 0x00000000,
|
|---|
| 425 | 0x40000100, 0x42080100, 0x42080100, 0x02000100,
|
|---|
| 426 | 0x42080000, 0x40000100, 0x00000000, 0x42000000,
|
|---|
| 427 | 0x02080100, 0x02000000, 0x42000000, 0x00080100,
|
|---|
| 428 | 0x00080000, 0x42000100, 0x00000100, 0x02000000,
|
|---|
| 429 | 0x40000000, 0x02080000, 0x42000100, 0x40080100,
|
|---|
| 430 | 0x02000100, 0x40000000, 0x42080000, 0x02080100,
|
|---|
| 431 | 0x40080100, 0x00000100, 0x02000000, 0x42080000,
|
|---|
| 432 | 0x42080100, 0x00080100, 0x42000000, 0x42080100,
|
|---|
| 433 | 0x02080000, 0x00000000, 0x40080000, 0x42000000,
|
|---|
| 434 | 0x00080100, 0x02000100, 0x40000100, 0x00080000,
|
|---|
| 435 | 0x00000000, 0x40080000, 0x02080100, 0x40000100},
|
|---|
| 436 |
|
|---|
| 437 | {0x20000010, 0x20400000, 0x00004000, 0x20404010,
|
|---|
| 438 | 0x20400000, 0x00000010, 0x20404010, 0x00400000,
|
|---|
| 439 | 0x20004000, 0x00404010, 0x00400000, 0x20000010,
|
|---|
| 440 | 0x00400010, 0x20004000, 0x20000000, 0x00004010,
|
|---|
| 441 | 0x00000000, 0x00400010, 0x20004010, 0x00004000,
|
|---|
| 442 | 0x00404000, 0x20004010, 0x00000010, 0x20400010,
|
|---|
| 443 | 0x20400010, 0x00000000, 0x00404010, 0x20404000,
|
|---|
| 444 | 0x00004010, 0x00404000, 0x20404000, 0x20000000,
|
|---|
| 445 | 0x20004000, 0x00000010, 0x20400010, 0x00404000,
|
|---|
| 446 | 0x20404010, 0x00400000, 0x00004010, 0x20000010,
|
|---|
| 447 | 0x00400000, 0x20004000, 0x20000000, 0x00004010,
|
|---|
| 448 | 0x20000010, 0x20404010, 0x00404000, 0x20400000,
|
|---|
| 449 | 0x00404010, 0x20404000, 0x00000000, 0x20400010,
|
|---|
| 450 | 0x00000010, 0x00004000, 0x20400000, 0x00404010,
|
|---|
| 451 | 0x00004000, 0x00400010, 0x20004010, 0x00000000,
|
|---|
| 452 | 0x20404000, 0x20000000, 0x00400010, 0x20004010},
|
|---|
| 453 |
|
|---|
| 454 | {0x00200000, 0x04200002, 0x04000802, 0x00000000,
|
|---|
| 455 | 0x00000800, 0x04000802, 0x00200802, 0x04200800,
|
|---|
| 456 | 0x04200802, 0x00200000, 0x00000000, 0x04000002,
|
|---|
| 457 | 0x00000002, 0x04000000, 0x04200002, 0x00000802,
|
|---|
| 458 | 0x04000800, 0x00200802, 0x00200002, 0x04000800,
|
|---|
| 459 | 0x04000002, 0x04200000, 0x04200800, 0x00200002,
|
|---|
| 460 | 0x04200000, 0x00000800, 0x00000802, 0x04200802,
|
|---|
| 461 | 0x00200800, 0x00000002, 0x04000000, 0x00200800,
|
|---|
| 462 | 0x04000000, 0x00200800, 0x00200000, 0x04000802,
|
|---|
| 463 | 0x04000802, 0x04200002, 0x04200002, 0x00000002,
|
|---|
| 464 | 0x00200002, 0x04000000, 0x04000800, 0x00200000,
|
|---|
| 465 | 0x04200800, 0x00000802, 0x00200802, 0x04200800,
|
|---|
| 466 | 0x00000802, 0x04000002, 0x04200802, 0x04200000,
|
|---|
| 467 | 0x00200800, 0x00000000, 0x00000002, 0x04200802,
|
|---|
| 468 | 0x00000000, 0x00200802, 0x04200000, 0x00000800,
|
|---|
| 469 | 0x04000002, 0x04000800, 0x00000800, 0x00200002},
|
|---|
| 470 |
|
|---|
| 471 | {0x10001040, 0x00001000, 0x00040000, 0x10041040,
|
|---|
| 472 | 0x10000000, 0x10001040, 0x00000040, 0x10000000,
|
|---|
| 473 | 0x00040040, 0x10040000, 0x10041040, 0x00041000,
|
|---|
| 474 | 0x10041000, 0x00041040, 0x00001000, 0x00000040,
|
|---|
| 475 | 0x10040000, 0x10000040, 0x10001000, 0x00001040,
|
|---|
| 476 | 0x00041000, 0x00040040, 0x10040040, 0x10041000,
|
|---|
| 477 | 0x00001040, 0x00000000, 0x00000000, 0x10040040,
|
|---|
| 478 | 0x10000040, 0x10001000, 0x00041040, 0x00040000,
|
|---|
| 479 | 0x00041040, 0x00040000, 0x10041000, 0x00001000,
|
|---|
| 480 | 0x00000040, 0x10040040, 0x00001000, 0x00041040,
|
|---|
| 481 | 0x10001000, 0x00000040, 0x10000040, 0x10040000,
|
|---|
| 482 | 0x10040040, 0x10000000, 0x00040000, 0x10001040,
|
|---|
| 483 | 0x00000000, 0x10041040, 0x00040040, 0x10000040,
|
|---|
| 484 | 0x10040000, 0x10001000, 0x10001040, 0x00000000,
|
|---|
| 485 | 0x10041040, 0x00041000, 0x00041000, 0x00001040,
|
|---|
| 486 | 0x00001040, 0x00040040, 0x10000000, 0x10041000}
|
|---|
| 487 | };
|
|---|
| 488 |
|
|---|
| 489 | #define f(R, K0246, K1357) (\
|
|---|
| 490 | s0246 = R ^ K0246, \
|
|---|
| 491 | s1357 = R ^ K1357, \
|
|---|
| 492 | s0246 = rotl(s0246, 28), \
|
|---|
| 493 | SPboxes[0] [(s0246 >> 24) & 0x3F] | \
|
|---|
| 494 | SPboxes[1] [(s1357 >> 24) & 0x3F] | \
|
|---|
| 495 | SPboxes[2] [(s0246 >> 16) & 0x3F] | \
|
|---|
| 496 | SPboxes[3] [(s1357 >> 16) & 0x3F] | \
|
|---|
| 497 | SPboxes[4] [(s0246 >> 8) & 0x3F] | \
|
|---|
| 498 | SPboxes[5] [(s1357 >> 8) & 0x3F] | \
|
|---|
| 499 | SPboxes[6] [(s0246 ) & 0x3F] | \
|
|---|
| 500 | SPboxes[7] [(s1357 ) & 0x3F])
|
|---|
| 501 |
|
|---|
| 502 | #define bitswap(L, R, n, mask) (\
|
|---|
| 503 | swap = mask & ( (R >> n) ^ L ), \
|
|---|
| 504 | R ^= swap << n, \
|
|---|
| 505 | L ^= swap)
|
|---|
| 506 |
|
|---|
| 507 | /* Initial permutation */
|
|---|
| 508 | #define IP(L, R) (\
|
|---|
| 509 | bitswap(R, L, 4, 0x0F0F0F0F), \
|
|---|
| 510 | bitswap(R, L, 16, 0x0000FFFF), \
|
|---|
| 511 | bitswap(L, R, 2, 0x33333333), \
|
|---|
| 512 | bitswap(L, R, 8, 0x00FF00FF), \
|
|---|
| 513 | bitswap(R, L, 1, 0x55555555))
|
|---|
| 514 |
|
|---|
| 515 | /* Final permutation */
|
|---|
| 516 | #define FP(L, R) (\
|
|---|
| 517 | bitswap(R, L, 1, 0x55555555), \
|
|---|
| 518 | bitswap(L, R, 8, 0x00FF00FF), \
|
|---|
| 519 | bitswap(L, R, 2, 0x33333333), \
|
|---|
| 520 | bitswap(R, L, 16, 0x0000FFFF), \
|
|---|
| 521 | bitswap(R, L, 4, 0x0F0F0F0F))
|
|---|
| 522 |
|
|---|
| 523 | static void
|
|---|
| 524 | des_encipher(quint32 *output, quint32 L, quint32 R,
|
|---|
| 525 | struct des_context *sched)
|
|---|
| 526 | {
|
|---|
| 527 | quint32 swap, s0246, s1357;
|
|---|
| 528 |
|
|---|
| 529 | IP(L, R);
|
|---|
| 530 |
|
|---|
| 531 | L = rotl(L, 1);
|
|---|
| 532 | R = rotl(R, 1);
|
|---|
| 533 |
|
|---|
| 534 | L ^= f(R, sched->k0246[0], sched->k1357[0]);
|
|---|
| 535 | R ^= f(L, sched->k0246[1], sched->k1357[1]);
|
|---|
| 536 | L ^= f(R, sched->k0246[2], sched->k1357[2]);
|
|---|
| 537 | R ^= f(L, sched->k0246[3], sched->k1357[3]);
|
|---|
| 538 | L ^= f(R, sched->k0246[4], sched->k1357[4]);
|
|---|
| 539 | R ^= f(L, sched->k0246[5], sched->k1357[5]);
|
|---|
| 540 | L ^= f(R, sched->k0246[6], sched->k1357[6]);
|
|---|
| 541 | R ^= f(L, sched->k0246[7], sched->k1357[7]);
|
|---|
| 542 | L ^= f(R, sched->k0246[8], sched->k1357[8]);
|
|---|
| 543 | R ^= f(L, sched->k0246[9], sched->k1357[9]);
|
|---|
| 544 | L ^= f(R, sched->k0246[10], sched->k1357[10]);
|
|---|
| 545 | R ^= f(L, sched->k0246[11], sched->k1357[11]);
|
|---|
| 546 | L ^= f(R, sched->k0246[12], sched->k1357[12]);
|
|---|
| 547 | R ^= f(L, sched->k0246[13], sched->k1357[13]);
|
|---|
| 548 | L ^= f(R, sched->k0246[14], sched->k1357[14]);
|
|---|
| 549 | R ^= f(L, sched->k0246[15], sched->k1357[15]);
|
|---|
| 550 |
|
|---|
| 551 | L = rotl(L, 31);
|
|---|
| 552 | R = rotl(R, 31);
|
|---|
| 553 |
|
|---|
| 554 | swap = L;
|
|---|
| 555 | L = R;
|
|---|
| 556 | R = swap;
|
|---|
| 557 |
|
|---|
| 558 | FP(L, R);
|
|---|
| 559 |
|
|---|
| 560 | output[0] = L;
|
|---|
| 561 | output[1] = R;
|
|---|
| 562 | }
|
|---|
| 563 |
|
|---|
| 564 | #define GET_32BIT_MSB_FIRST(cp) \
|
|---|
| 565 | (((unsigned long)(unsigned char)(cp)[3]) | \
|
|---|
| 566 | ((unsigned long)(unsigned char)(cp)[2] << 8) | \
|
|---|
| 567 | ((unsigned long)(unsigned char)(cp)[1] << 16) | \
|
|---|
| 568 | ((unsigned long)(unsigned char)(cp)[0] << 24))
|
|---|
| 569 |
|
|---|
| 570 | #define PUT_32BIT_MSB_FIRST(cp, value) do { \
|
|---|
| 571 | (cp)[3] = (value); \
|
|---|
| 572 | (cp)[2] = (value) >> 8; \
|
|---|
| 573 | (cp)[1] = (value) >> 16; \
|
|---|
| 574 | (cp)[0] = (value) >> 24; } while (0)
|
|---|
| 575 |
|
|---|
| 576 | static inline void
|
|---|
| 577 | des_cbc_encrypt(unsigned char *dest, const unsigned char *src,
|
|---|
| 578 | struct des_context *sched)
|
|---|
| 579 | {
|
|---|
| 580 | quint32 out[2], L, R;
|
|---|
| 581 |
|
|---|
| 582 | L = GET_32BIT_MSB_FIRST(src);
|
|---|
| 583 | R = GET_32BIT_MSB_FIRST(src + 4);
|
|---|
| 584 | des_encipher(out, L, R, sched);
|
|---|
| 585 | PUT_32BIT_MSB_FIRST(dest, out[0]);
|
|---|
| 586 | PUT_32BIT_MSB_FIRST(dest + 4, out[1]);
|
|---|
| 587 | }
|
|---|
| 588 |
|
|---|
| 589 |
|
|---|
| 590 | static unsigned char *
|
|---|
| 591 | deshash(unsigned char *dst, const unsigned char *key,
|
|---|
| 592 | const unsigned char *src)
|
|---|
| 593 | {
|
|---|
| 594 | struct des_context ctx;
|
|---|
| 595 |
|
|---|
| 596 | des_key_setup(GET_32BIT_MSB_FIRST(key) >> 8,
|
|---|
| 597 | GET_32BIT_MSB_FIRST(key + 3), &ctx);
|
|---|
| 598 |
|
|---|
| 599 | des_cbc_encrypt(dst, src, &ctx);
|
|---|
| 600 |
|
|---|
| 601 | return dst;
|
|---|
| 602 | }
|
|---|
