374330e2 |
1 | #include <assert.h> |
2 | #include "ssh.h" |
3 | |
d1e726bc |
4 | /* des.c - implementation of DES |
5 | */ |
6 | |
374330e2 |
7 | /* |
d1e726bc |
8 | * Description of DES |
1608bfe3 |
9 | * ------------------ |
d1e726bc |
10 | * |
11 | * Unlike the description in FIPS 46, I'm going to use _sensible_ indices: |
12 | * bits in an n-bit word are numbered from 0 at the LSB to n-1 at the MSB. |
13 | * And S-boxes are indexed by six consecutive bits, not by the outer two |
14 | * followed by the middle four. |
15 | * |
16 | * The DES encryption routine requires a 64-bit input, and a key schedule K |
17 | * containing 16 48-bit elements. |
18 | * |
19 | * First the input is permuted by the initial permutation IP. |
20 | * Then the input is split into 32-bit words L and R. (L is the MSW.) |
21 | * Next, 16 rounds. In each round: |
22 | * (L, R) <- (R, L xor f(R, K[i])) |
23 | * Then the pre-output words L and R are swapped. |
24 | * Then L and R are glued back together into a 64-bit word. (L is the MSW, |
25 | * again, but since we just swapped them, the MSW is the R that came out |
26 | * of the last round.) |
27 | * The 64-bit output block is permuted by the inverse of IP and returned. |
28 | * |
29 | * Decryption is identical except that the elements of K are used in the |
30 | * opposite order. (This wouldn't work if that word swap didn't happen.) |
31 | * |
32 | * The function f, used in each round, accepts a 32-bit word R and a |
33 | * 48-bit key block K. It produces a 32-bit output. |
34 | * |
35 | * First R is expanded to 48 bits using the bit-selection function E. |
36 | * The resulting 48-bit block is XORed with the key block K to produce |
37 | * a 48-bit block X. |
38 | * This block X is split into eight groups of 6 bits. Each group of 6 |
39 | * bits is then looked up in one of the eight S-boxes to convert |
40 | * it to 4 bits. These eight groups of 4 bits are glued back |
41 | * together to produce a 32-bit preoutput block. |
42 | * The preoutput block is permuted using the permutation P and returned. |
43 | * |
44 | * Key setup maps a 64-bit key word into a 16x48-bit key schedule. Although |
45 | * the approved input format for the key is a 64-bit word, eight of the |
46 | * bits are discarded, so the actual quantity of key used is 56 bits. |
47 | * |
48 | * First the input key is converted to two 28-bit words C and D using |
49 | * the bit-selection function PC1. |
50 | * Then 16 rounds of key setup occur. In each round, C and D are each |
51 | * rotated left by either 1 or 2 bits (depending on which round), and |
52 | * then converted into a key schedule element using the bit-selection |
53 | * function PC2. |
54 | * |
55 | * That's the actual algorithm. Now for the tedious details: all those |
56 | * painful permutations and lookup tables. |
57 | * |
58 | * IP is a 64-to-64 bit permutation. Its output contains the following |
59 | * bits of its input (listed in order MSB to LSB of output). |
60 | * |
61 | * 6 14 22 30 38 46 54 62 4 12 20 28 36 44 52 60 |
62 | * 2 10 18 26 34 42 50 58 0 8 16 24 32 40 48 56 |
63 | * 7 15 23 31 39 47 55 63 5 13 21 29 37 45 53 61 |
64 | * 3 11 19 27 35 43 51 59 1 9 17 25 33 41 49 57 |
65 | * |
66 | * E is a 32-to-48 bit selection function. Its output contains the following |
67 | * bits of its input (listed in order MSB to LSB of output). |
68 | * |
69 | * 0 31 30 29 28 27 28 27 26 25 24 23 24 23 22 21 20 19 20 19 18 17 16 15 |
70 | * 16 15 14 13 12 11 12 11 10 9 8 7 8 7 6 5 4 3 4 3 2 1 0 31 |
71 | * |
72 | * The S-boxes are arbitrary table-lookups each mapping a 6-bit input to a |
73 | * 4-bit output. In other words, each S-box is an array[64] of 4-bit numbers. |
74 | * The S-boxes are listed below. The first S-box listed is applied to the |
75 | * most significant six bits of the block X; the last one is applied to the |
76 | * least significant. |
77 | * |
78 | * 14 0 4 15 13 7 1 4 2 14 15 2 11 13 8 1 |
79 | * 3 10 10 6 6 12 12 11 5 9 9 5 0 3 7 8 |
80 | * 4 15 1 12 14 8 8 2 13 4 6 9 2 1 11 7 |
81 | * 15 5 12 11 9 3 7 14 3 10 10 0 5 6 0 13 |
82 | * |
83 | * 15 3 1 13 8 4 14 7 6 15 11 2 3 8 4 14 |
84 | * 9 12 7 0 2 1 13 10 12 6 0 9 5 11 10 5 |
85 | * 0 13 14 8 7 10 11 1 10 3 4 15 13 4 1 2 |
86 | * 5 11 8 6 12 7 6 12 9 0 3 5 2 14 15 9 |
87 | * |
88 | * 10 13 0 7 9 0 14 9 6 3 3 4 15 6 5 10 |
89 | * 1 2 13 8 12 5 7 14 11 12 4 11 2 15 8 1 |
90 | * 13 1 6 10 4 13 9 0 8 6 15 9 3 8 0 7 |
91 | * 11 4 1 15 2 14 12 3 5 11 10 5 14 2 7 12 |
92 | * |
93 | * 7 13 13 8 14 11 3 5 0 6 6 15 9 0 10 3 |
94 | * 1 4 2 7 8 2 5 12 11 1 12 10 4 14 15 9 |
95 | * 10 3 6 15 9 0 0 6 12 10 11 1 7 13 13 8 |
96 | * 15 9 1 4 3 5 14 11 5 12 2 7 8 2 4 14 |
97 | * |
98 | * 2 14 12 11 4 2 1 12 7 4 10 7 11 13 6 1 |
99 | * 8 5 5 0 3 15 15 10 13 3 0 9 14 8 9 6 |
100 | * 4 11 2 8 1 12 11 7 10 1 13 14 7 2 8 13 |
101 | * 15 6 9 15 12 0 5 9 6 10 3 4 0 5 14 3 |
102 | * |
103 | * 12 10 1 15 10 4 15 2 9 7 2 12 6 9 8 5 |
104 | * 0 6 13 1 3 13 4 14 14 0 7 11 5 3 11 8 |
105 | * 9 4 14 3 15 2 5 12 2 9 8 5 12 15 3 10 |
106 | * 7 11 0 14 4 1 10 7 1 6 13 0 11 8 6 13 |
107 | * |
108 | * 4 13 11 0 2 11 14 7 15 4 0 9 8 1 13 10 |
109 | * 3 14 12 3 9 5 7 12 5 2 10 15 6 8 1 6 |
110 | * 1 6 4 11 11 13 13 8 12 1 3 4 7 10 14 7 |
111 | * 10 9 15 5 6 0 8 15 0 14 5 2 9 3 2 12 |
112 | * |
113 | * 13 1 2 15 8 13 4 8 6 10 15 3 11 7 1 4 |
114 | * 10 12 9 5 3 6 14 11 5 0 0 14 12 9 7 2 |
115 | * 7 2 11 1 4 14 1 7 9 4 12 10 14 8 2 13 |
116 | * 0 15 6 12 10 9 13 0 15 3 3 5 5 6 8 11 |
117 | * |
118 | * P is a 32-to-32 bit permutation. Its output contains the following |
119 | * bits of its input (listed in order MSB to LSB of output). |
120 | * |
121 | * 16 25 12 11 3 20 4 15 31 17 9 6 27 14 1 22 |
122 | * 30 24 8 18 0 5 29 23 13 19 2 26 10 21 28 7 |
123 | * |
124 | * PC1 is a 64-to-56 bit selection function. Its output is in two words, |
125 | * C and D. The word C contains the following bits of its input (listed |
126 | * in order MSB to LSB of output). |
127 | * |
128 | * 7 15 23 31 39 47 55 63 6 14 22 30 38 46 |
129 | * 54 62 5 13 21 29 37 45 53 61 4 12 20 28 |
130 | * |
131 | * And the word D contains these bits. |
132 | * |
133 | * 1 9 17 25 33 41 49 57 2 10 18 26 34 42 |
134 | * 50 58 3 11 19 27 35 43 51 59 36 44 52 60 |
135 | * |
136 | * PC2 is a 56-to-48 bit selection function. Its input is in two words, |
137 | * C and D. These are treated as one 56-bit word (with C more significant, |
138 | * so that bits 55 to 28 of the word are bits 27 to 0 of C, and bits 27 to |
139 | * 0 of the word are bits 27 to 0 of D). The output contains the following |
140 | * bits of this 56-bit input word (listed in order MSB to LSB of output). |
141 | * |
142 | * 42 39 45 32 55 51 53 28 41 50 35 46 33 37 44 52 30 48 40 49 29 36 43 54 |
143 | * 15 4 25 19 9 1 26 16 5 11 23 8 12 7 17 0 22 3 10 14 6 20 27 24 |
144 | */ |
145 | |
1608bfe3 |
146 | /* |
147 | * Implementation details |
148 | * ---------------------- |
149 | * |
150 | * If you look at the code in this module, you'll find it looks |
151 | * nothing _like_ the above algorithm. Here I explain the |
152 | * differences... |
153 | * |
154 | * Key setup has not been heavily optimised here. We are not |
155 | * concerned with key agility: we aren't codebreakers. We don't |
156 | * mind a little delay (and it really is a little one; it may be a |
157 | * factor of five or so slower than it could be but it's still not |
158 | * an appreciable length of time) while setting up. The only tweaks |
159 | * in the key setup are ones which change the format of the key |
160 | * schedule to speed up the actual encryption. I'll describe those |
161 | * below. |
162 | * |
163 | * The first and most obvious optimisation is the S-boxes. Since |
164 | * each S-box always targets the same four bits in the final 32-bit |
165 | * word, so the output from (for example) S-box 0 must always be |
166 | * shifted left 28 bits, we can store the already-shifted outputs |
167 | * in the lookup tables. This reduces lookup-and-shift to lookup, |
168 | * so the S-box step is now just a question of ORing together eight |
169 | * table lookups. |
170 | * |
171 | * The permutation P is just a bit order change; it's invariant |
172 | * with respect to OR, in that P(x)|P(y) = P(x|y). Therefore, we |
173 | * can apply P to every entry of the S-box tables and then we don't |
174 | * have to do it in the code of f(). This yields a set of tables |
175 | * which might be called SP-boxes. |
176 | * |
177 | * The bit-selection function E is our next target. Note that E is |
178 | * immediately followed by the operation of splitting into 6-bit |
179 | * chunks. Examining the 6-bit chunks coming out of E we notice |
180 | * they're all contiguous within the word (speaking cyclically - |
181 | * the end two wrap round); so we can extract those bit strings |
182 | * individually rather than explicitly running E. This would yield |
183 | * code such as |
184 | * |
185 | * y |= SPboxes[0][ (rotl(R, 5) ^ top6bitsofK) & 0x3F ]; |
186 | * t |= SPboxes[1][ (rotl(R,11) ^ next6bitsofK) & 0x3F ]; |
187 | * |
188 | * and so on; and the key schedule preparation would have to |
189 | * provide each 6-bit chunk separately. |
190 | * |
191 | * Really we'd like to XOR in the key schedule element before |
192 | * looking up bit strings in R. This we can't do, naively, because |
193 | * the 6-bit strings we want overlap. But look at the strings: |
194 | * |
195 | * 3322222222221111111111 |
196 | * bit 10987654321098765432109876543210 |
197 | * |
198 | * box0 XXXXX X |
199 | * box1 XXXXXX |
200 | * box2 XXXXXX |
201 | * box3 XXXXXX |
202 | * box4 XXXXXX |
203 | * box5 XXXXXX |
204 | * box6 XXXXXX |
205 | * box7 X XXXXX |
206 | * |
207 | * The bit strings we need to XOR in for boxes 0, 2, 4 and 6 don't |
208 | * overlap with each other. Neither do the ones for boxes 1, 3, 5 |
209 | * and 7. So we could provide the key schedule in the form of two |
210 | * words that we can separately XOR into R, and then every S-box |
211 | * index is available as a (cyclically) contiguous 6-bit substring |
212 | * of one or the other of the results. |
213 | * |
214 | * The comments in Eric Young's libdes implementation point out |
215 | * that two of these bit strings require a rotation (rather than a |
216 | * simple shift) to extract. It's unavoidable that at least _one_ |
217 | * must do; but we can actually run the whole inner algorithm (all |
218 | * 16 rounds) rotated one bit to the left, so that what the `real' |
219 | * DES description sees as L=0x80000001 we see as L=0x00000003. |
220 | * This requires rotating all our SP-box entries one bit to the |
221 | * left, and rotating each word of the key schedule elements one to |
222 | * the left, and rotating L and R one bit left just after IP and |
223 | * one bit right again just before FP. And in each round we convert |
224 | * a rotate into a shift, so we've saved a few per cent. |
225 | * |
226 | * That's about it for the inner loop; the SP-box tables as listed |
227 | * below are what I've described here (the original S value, |
228 | * shifted to its final place in the input to P, run through P, and |
229 | * then rotated one bit left). All that remains is to optimise the |
230 | * initial permutation IP. |
231 | * |
232 | * IP is not an arbitrary permutation. It has the nice property |
233 | * that if you take any bit number, write it in binary (6 bits), |
234 | * permute those 6 bits and invert some of them, you get the final |
235 | * position of that bit. Specifically, the bit whose initial |
236 | * position is given (in binary) as fedcba ends up in position |
237 | * AcbFED (where a capital letter denotes the inverse of a bit). |
238 | * |
239 | * We have the 64-bit data in two 32-bit words L and R, where bits |
240 | * in L are those with f=1 and bits in R are those with f=0. We |
241 | * note that we can do a simple transformation: suppose we exchange |
242 | * the bits with f=1,c=0 and the bits with f=0,c=1. This will cause |
243 | * the bit fedcba to be in position cedfba - we've `swapped' bits c |
244 | * and f in the position of each bit! |
245 | * |
246 | * Better still, this transformation is easy. In the example above, |
247 | * bits in L with c=0 are bits 0x0F0F0F0F, and those in R with c=1 |
248 | * are 0xF0F0F0F0. So we can do |
249 | * |
250 | * difference = ((R >> 4) ^ L) & 0x0F0F0F0F |
251 | * R ^= (difference << 4) |
252 | * L ^= difference |
253 | * |
254 | * to perform the swap. Let's denote this by bitswap(4,0x0F0F0F0F). |
255 | * Also, we can invert the bit at the top just by exchanging L and |
256 | * R. So in a few swaps and a few of these bit operations we can |
257 | * do: |
258 | * |
259 | * Initially the position of bit fedcba is fedcba |
260 | * Swap L with R to make it Fedcba |
261 | * Perform bitswap( 4,0x0F0F0F0F) to make it cedFba |
262 | * Perform bitswap(16,0x0000FFFF) to make it ecdFba |
263 | * Swap L with R to make it EcdFba |
264 | * Perform bitswap( 2,0x33333333) to make it bcdFEa |
265 | * Perform bitswap( 8,0x00FF00FF) to make it dcbFEa |
266 | * Swap L with R to make it DcbFEa |
267 | * Perform bitswap( 1,0x55555555) to make it acbFED |
268 | * Swap L with R to make it AcbFED |
269 | * |
270 | * (In the actual code the four swaps are implicit: R and L are |
271 | * simply used the other way round in the first, second and last |
272 | * bitswap operations.) |
273 | * |
274 | * The final permutation is just the inverse of IP, so it can be |
275 | * performed by a similar set of operations. |
276 | */ |
277 | |
d1e726bc |
278 | typedef struct { |
279 | word32 k0246[16], k1357[16]; |
280 | word32 eiv0, eiv1; |
281 | word32 div0, div1; |
282 | } DESContext; |
374330e2 |
283 | |
d1e726bc |
284 | #define rotl(x, c) ( (x << c) | (x >> (32-c)) ) |
285 | #define rotl28(x, c) ( ( (x << c) | (x >> (28-c)) ) & 0x0FFFFFFF) |
374330e2 |
286 | |
d1e726bc |
287 | static word32 bitsel(word32 *input, const int *bitnums, int size) { |
288 | word32 ret = 0; |
289 | while (size--) { |
290 | int bitpos = *bitnums++; |
291 | ret <<= 1; |
292 | if (bitpos >= 0) |
293 | ret |= 1 & (input[bitpos / 32] >> (bitpos % 32)); |
294 | } |
295 | return ret; |
296 | } |
374330e2 |
297 | |
d1e726bc |
298 | void des_key_setup(word32 key_msw, word32 key_lsw, DESContext *sched) { |
299 | |
300 | static const int PC1_Cbits[] = { |
301 | 7, 15, 23, 31, 39, 47, 55, 63, 6, 14, 22, 30, 38, 46, |
302 | 54, 62, 5, 13, 21, 29, 37, 45, 53, 61, 4, 12, 20, 28 |
303 | }; |
304 | static const int PC1_Dbits[] = { |
305 | 1, 9, 17, 25, 33, 41, 49, 57, 2, 10, 18, 26, 34, 42, |
306 | 50, 58, 3, 11, 19, 27, 35, 43, 51, 59, 36, 44, 52, 60 |
307 | }; |
1608bfe3 |
308 | /* |
309 | * The bit numbers in the two lists below don't correspond to |
310 | * the ones in the above description of PC2, because in the |
311 | * above description C and D are concatenated so `bit 28' means |
312 | * bit 0 of C. In this implementation we're using the standard |
313 | * `bitsel' function above and C is in the second word, so bit |
314 | * 0 of C is addressed by writing `32' here. |
315 | */ |
d1e726bc |
316 | static const int PC2_0246[] = { |
317 | 49, 36, 59, 55, -1, -1, 37, 41, 48, 56, 34, 52, -1, -1, 15, 4, |
318 | 25, 19, 9, 1, -1, -1, 12, 7, 17, 0, 22, 3, -1, -1, 46, 43 |
319 | }; |
320 | static const int PC2_1357[] = { |
321 | -1, -1, 57, 32, 45, 54, 39, 50, -1, -1, 44, 53, 33, 40, 47, 58, |
322 | -1, -1, 26, 16, 5, 11, 23, 8, -1, -1, 10, 14, 6, 20, 27, 24 |
323 | }; |
324 | static const int leftshifts[] = {1,1,2,2,2,2,2,2,1,2,2,2,2,2,2,1}; |
325 | |
326 | word32 C, D; |
327 | word32 buf[2]; |
328 | int i; |
329 | |
330 | buf[0] = key_lsw; |
331 | buf[1] = key_msw; |
332 | |
333 | C = bitsel(buf, PC1_Cbits, 28); |
334 | D = bitsel(buf, PC1_Dbits, 28); |
335 | |
336 | for (i = 0; i < 16; i++) { |
337 | C = rotl28(C, leftshifts[i]); |
338 | D = rotl28(D, leftshifts[i]); |
339 | buf[0] = D; |
340 | buf[1] = C; |
341 | sched->k0246[i] = bitsel(buf, PC2_0246, 32); |
342 | sched->k1357[i] = bitsel(buf, PC2_1357, 32); |
343 | } |
374330e2 |
344 | |
d1e726bc |
345 | sched->eiv0 = sched->eiv1 = 0; |
346 | sched->div0 = sched->div1 = 0; /* for good measure */ |
347 | } |
374330e2 |
348 | |
d1e726bc |
349 | static const word32 SPboxes[8][64] = { |
350 | {0x01010400, 0x00000000, 0x00010000, 0x01010404, |
351 | 0x01010004, 0x00010404, 0x00000004, 0x00010000, |
352 | 0x00000400, 0x01010400, 0x01010404, 0x00000400, |
353 | 0x01000404, 0x01010004, 0x01000000, 0x00000004, |
354 | 0x00000404, 0x01000400, 0x01000400, 0x00010400, |
355 | 0x00010400, 0x01010000, 0x01010000, 0x01000404, |
356 | 0x00010004, 0x01000004, 0x01000004, 0x00010004, |
357 | 0x00000000, 0x00000404, 0x00010404, 0x01000000, |
358 | 0x00010000, 0x01010404, 0x00000004, 0x01010000, |
359 | 0x01010400, 0x01000000, 0x01000000, 0x00000400, |
360 | 0x01010004, 0x00010000, 0x00010400, 0x01000004, |
361 | 0x00000400, 0x00000004, 0x01000404, 0x00010404, |
362 | 0x01010404, 0x00010004, 0x01010000, 0x01000404, |
363 | 0x01000004, 0x00000404, 0x00010404, 0x01010400, |
364 | 0x00000404, 0x01000400, 0x01000400, 0x00000000, |
365 | 0x00010004, 0x00010400, 0x00000000, 0x01010004L}, |
366 | |
367 | {0x80108020, 0x80008000, 0x00008000, 0x00108020, |
368 | 0x00100000, 0x00000020, 0x80100020, 0x80008020, |
369 | 0x80000020, 0x80108020, 0x80108000, 0x80000000, |
370 | 0x80008000, 0x00100000, 0x00000020, 0x80100020, |
371 | 0x00108000, 0x00100020, 0x80008020, 0x00000000, |
372 | 0x80000000, 0x00008000, 0x00108020, 0x80100000, |
373 | 0x00100020, 0x80000020, 0x00000000, 0x00108000, |
374 | 0x00008020, 0x80108000, 0x80100000, 0x00008020, |
375 | 0x00000000, 0x00108020, 0x80100020, 0x00100000, |
376 | 0x80008020, 0x80100000, 0x80108000, 0x00008000, |
377 | 0x80100000, 0x80008000, 0x00000020, 0x80108020, |
378 | 0x00108020, 0x00000020, 0x00008000, 0x80000000, |
379 | 0x00008020, 0x80108000, 0x00100000, 0x80000020, |
380 | 0x00100020, 0x80008020, 0x80000020, 0x00100020, |
381 | 0x00108000, 0x00000000, 0x80008000, 0x00008020, |
382 | 0x80000000, 0x80100020, 0x80108020, 0x00108000L}, |
383 | |
384 | {0x00000208, 0x08020200, 0x00000000, 0x08020008, |
385 | 0x08000200, 0x00000000, 0x00020208, 0x08000200, |
386 | 0x00020008, 0x08000008, 0x08000008, 0x00020000, |
387 | 0x08020208, 0x00020008, 0x08020000, 0x00000208, |
388 | 0x08000000, 0x00000008, 0x08020200, 0x00000200, |
389 | 0x00020200, 0x08020000, 0x08020008, 0x00020208, |
390 | 0x08000208, 0x00020200, 0x00020000, 0x08000208, |
391 | 0x00000008, 0x08020208, 0x00000200, 0x08000000, |
392 | 0x08020200, 0x08000000, 0x00020008, 0x00000208, |
393 | 0x00020000, 0x08020200, 0x08000200, 0x00000000, |
394 | 0x00000200, 0x00020008, 0x08020208, 0x08000200, |
395 | 0x08000008, 0x00000200, 0x00000000, 0x08020008, |
396 | 0x08000208, 0x00020000, 0x08000000, 0x08020208, |
397 | 0x00000008, 0x00020208, 0x00020200, 0x08000008, |
398 | 0x08020000, 0x08000208, 0x00000208, 0x08020000, |
399 | 0x00020208, 0x00000008, 0x08020008, 0x00020200L}, |
400 | |
401 | {0x00802001, 0x00002081, 0x00002081, 0x00000080, |
402 | 0x00802080, 0x00800081, 0x00800001, 0x00002001, |
403 | 0x00000000, 0x00802000, 0x00802000, 0x00802081, |
404 | 0x00000081, 0x00000000, 0x00800080, 0x00800001, |
405 | 0x00000001, 0x00002000, 0x00800000, 0x00802001, |
406 | 0x00000080, 0x00800000, 0x00002001, 0x00002080, |
407 | 0x00800081, 0x00000001, 0x00002080, 0x00800080, |
408 | 0x00002000, 0x00802080, 0x00802081, 0x00000081, |
409 | 0x00800080, 0x00800001, 0x00802000, 0x00802081, |
410 | 0x00000081, 0x00000000, 0x00000000, 0x00802000, |
411 | 0x00002080, 0x00800080, 0x00800081, 0x00000001, |
412 | 0x00802001, 0x00002081, 0x00002081, 0x00000080, |
413 | 0x00802081, 0x00000081, 0x00000001, 0x00002000, |
414 | 0x00800001, 0x00002001, 0x00802080, 0x00800081, |
415 | 0x00002001, 0x00002080, 0x00800000, 0x00802001, |
416 | 0x00000080, 0x00800000, 0x00002000, 0x00802080L}, |
417 | |
418 | {0x00000100, 0x02080100, 0x02080000, 0x42000100, |
419 | 0x00080000, 0x00000100, 0x40000000, 0x02080000, |
420 | 0x40080100, 0x00080000, 0x02000100, 0x40080100, |
421 | 0x42000100, 0x42080000, 0x00080100, 0x40000000, |
422 | 0x02000000, 0x40080000, 0x40080000, 0x00000000, |
423 | 0x40000100, 0x42080100, 0x42080100, 0x02000100, |
424 | 0x42080000, 0x40000100, 0x00000000, 0x42000000, |
425 | 0x02080100, 0x02000000, 0x42000000, 0x00080100, |
426 | 0x00080000, 0x42000100, 0x00000100, 0x02000000, |
427 | 0x40000000, 0x02080000, 0x42000100, 0x40080100, |
428 | 0x02000100, 0x40000000, 0x42080000, 0x02080100, |
429 | 0x40080100, 0x00000100, 0x02000000, 0x42080000, |
430 | 0x42080100, 0x00080100, 0x42000000, 0x42080100, |
431 | 0x02080000, 0x00000000, 0x40080000, 0x42000000, |
432 | 0x00080100, 0x02000100, 0x40000100, 0x00080000, |
433 | 0x00000000, 0x40080000, 0x02080100, 0x40000100L}, |
434 | |
435 | {0x20000010, 0x20400000, 0x00004000, 0x20404010, |
436 | 0x20400000, 0x00000010, 0x20404010, 0x00400000, |
437 | 0x20004000, 0x00404010, 0x00400000, 0x20000010, |
438 | 0x00400010, 0x20004000, 0x20000000, 0x00004010, |
439 | 0x00000000, 0x00400010, 0x20004010, 0x00004000, |
440 | 0x00404000, 0x20004010, 0x00000010, 0x20400010, |
441 | 0x20400010, 0x00000000, 0x00404010, 0x20404000, |
442 | 0x00004010, 0x00404000, 0x20404000, 0x20000000, |
443 | 0x20004000, 0x00000010, 0x20400010, 0x00404000, |
444 | 0x20404010, 0x00400000, 0x00004010, 0x20000010, |
445 | 0x00400000, 0x20004000, 0x20000000, 0x00004010, |
446 | 0x20000010, 0x20404010, 0x00404000, 0x20400000, |
447 | 0x00404010, 0x20404000, 0x00000000, 0x20400010, |
448 | 0x00000010, 0x00004000, 0x20400000, 0x00404010, |
449 | 0x00004000, 0x00400010, 0x20004010, 0x00000000, |
450 | 0x20404000, 0x20000000, 0x00400010, 0x20004010L}, |
451 | |
452 | {0x00200000, 0x04200002, 0x04000802, 0x00000000, |
453 | 0x00000800, 0x04000802, 0x00200802, 0x04200800, |
454 | 0x04200802, 0x00200000, 0x00000000, 0x04000002, |
455 | 0x00000002, 0x04000000, 0x04200002, 0x00000802, |
456 | 0x04000800, 0x00200802, 0x00200002, 0x04000800, |
457 | 0x04000002, 0x04200000, 0x04200800, 0x00200002, |
458 | 0x04200000, 0x00000800, 0x00000802, 0x04200802, |
459 | 0x00200800, 0x00000002, 0x04000000, 0x00200800, |
460 | 0x04000000, 0x00200800, 0x00200000, 0x04000802, |
461 | 0x04000802, 0x04200002, 0x04200002, 0x00000002, |
462 | 0x00200002, 0x04000000, 0x04000800, 0x00200000, |
463 | 0x04200800, 0x00000802, 0x00200802, 0x04200800, |
464 | 0x00000802, 0x04000002, 0x04200802, 0x04200000, |
465 | 0x00200800, 0x00000000, 0x00000002, 0x04200802, |
466 | 0x00000000, 0x00200802, 0x04200000, 0x00000800, |
467 | 0x04000002, 0x04000800, 0x00000800, 0x00200002L}, |
468 | |
469 | {0x10001040, 0x00001000, 0x00040000, 0x10041040, |
470 | 0x10000000, 0x10001040, 0x00000040, 0x10000000, |
471 | 0x00040040, 0x10040000, 0x10041040, 0x00041000, |
472 | 0x10041000, 0x00041040, 0x00001000, 0x00000040, |
473 | 0x10040000, 0x10000040, 0x10001000, 0x00001040, |
474 | 0x00041000, 0x00040040, 0x10040040, 0x10041000, |
475 | 0x00001040, 0x00000000, 0x00000000, 0x10040040, |
476 | 0x10000040, 0x10001000, 0x00041040, 0x00040000, |
477 | 0x00041040, 0x00040000, 0x10041000, 0x00001000, |
478 | 0x00000040, 0x10040040, 0x00001000, 0x00041040, |
479 | 0x10001000, 0x00000040, 0x10000040, 0x10040000, |
480 | 0x10040040, 0x10000000, 0x00040000, 0x10001040, |
481 | 0x00000000, 0x10041040, 0x00040040, 0x10000040, |
482 | 0x10040000, 0x10001000, 0x10001040, 0x00000000, |
483 | 0x10041040, 0x00041000, 0x00041000, 0x00001040, |
484 | 0x00001040, 0x00040040, 0x10000000, 0x10041000L} |
485 | }; |
374330e2 |
486 | |
d1e726bc |
487 | #define f(R, K0246, K1357) (\ |
488 | s0246 = R ^ K0246, \ |
489 | s1357 = R ^ K1357, \ |
490 | s0246 = rotl(s0246, 28), \ |
491 | SPboxes[0] [(s0246 >> 24) & 0x3F] | \ |
492 | SPboxes[1] [(s1357 >> 24) & 0x3F] | \ |
493 | SPboxes[2] [(s0246 >> 16) & 0x3F] | \ |
494 | SPboxes[3] [(s1357 >> 16) & 0x3F] | \ |
495 | SPboxes[4] [(s0246 >> 8) & 0x3F] | \ |
496 | SPboxes[5] [(s1357 >> 8) & 0x3F] | \ |
497 | SPboxes[6] [(s0246 ) & 0x3F] | \ |
498 | SPboxes[7] [(s1357 ) & 0x3F]) |
499 | |
500 | #define bitswap(L, R, n, mask) (\ |
501 | swap = mask & ( (R >> n) ^ L ), \ |
502 | R ^= swap << n, \ |
503 | L ^= swap) |
504 | |
505 | /* Initial permutation */ |
506 | #define IP(L, R) (\ |
507 | bitswap(R, L, 4, 0x0F0F0F0F), \ |
508 | bitswap(R, L, 16, 0x0000FFFF), \ |
509 | bitswap(L, R, 2, 0x33333333), \ |
510 | bitswap(L, R, 8, 0x00FF00FF), \ |
511 | bitswap(R, L, 1, 0x55555555)) |
512 | |
513 | /* Final permutation */ |
514 | #define FP(L, R) (\ |
515 | bitswap(R, L, 1, 0x55555555), \ |
516 | bitswap(L, R, 8, 0x00FF00FF), \ |
517 | bitswap(L, R, 2, 0x33333333), \ |
518 | bitswap(R, L, 16, 0x0000FFFF), \ |
519 | bitswap(R, L, 4, 0x0F0F0F0F)) |
520 | |
521 | void des_encipher(word32 *output, word32 L, word32 R, DESContext *sched) { |
522 | word32 swap, s0246, s1357; |
523 | |
524 | IP(L, R); |
525 | |
526 | L = rotl(L, 1); |
527 | R = rotl(R, 1); |
528 | |
529 | L ^= f(R, sched->k0246[ 0], sched->k1357[ 0]); |
530 | R ^= f(L, sched->k0246[ 1], sched->k1357[ 1]); |
531 | L ^= f(R, sched->k0246[ 2], sched->k1357[ 2]); |
532 | R ^= f(L, sched->k0246[ 3], sched->k1357[ 3]); |
533 | L ^= f(R, sched->k0246[ 4], sched->k1357[ 4]); |
534 | R ^= f(L, sched->k0246[ 5], sched->k1357[ 5]); |
535 | L ^= f(R, sched->k0246[ 6], sched->k1357[ 6]); |
536 | R ^= f(L, sched->k0246[ 7], sched->k1357[ 7]); |
537 | L ^= f(R, sched->k0246[ 8], sched->k1357[ 8]); |
538 | R ^= f(L, sched->k0246[ 9], sched->k1357[ 9]); |
539 | L ^= f(R, sched->k0246[10], sched->k1357[10]); |
540 | R ^= f(L, sched->k0246[11], sched->k1357[11]); |
541 | L ^= f(R, sched->k0246[12], sched->k1357[12]); |
542 | R ^= f(L, sched->k0246[13], sched->k1357[13]); |
543 | L ^= f(R, sched->k0246[14], sched->k1357[14]); |
544 | R ^= f(L, sched->k0246[15], sched->k1357[15]); |
545 | |
546 | L = rotl(L, 31); |
547 | R = rotl(R, 31); |
548 | |
549 | swap = L; L = R; R = swap; |
550 | |
551 | FP(L, R); |
552 | |
553 | output[0] = L; |
554 | output[1] = R; |
555 | } |
374330e2 |
556 | |
d1e726bc |
557 | void des_decipher(word32 *output, word32 L, word32 R, DESContext *sched) { |
558 | word32 swap, s0246, s1357; |
374330e2 |
559 | |
d1e726bc |
560 | IP(L, R); |
374330e2 |
561 | |
d1e726bc |
562 | L = rotl(L, 1); |
563 | R = rotl(R, 1); |
374330e2 |
564 | |
d1e726bc |
565 | L ^= f(R, sched->k0246[15], sched->k1357[15]); |
566 | R ^= f(L, sched->k0246[14], sched->k1357[14]); |
567 | L ^= f(R, sched->k0246[13], sched->k1357[13]); |
568 | R ^= f(L, sched->k0246[12], sched->k1357[12]); |
569 | L ^= f(R, sched->k0246[11], sched->k1357[11]); |
570 | R ^= f(L, sched->k0246[10], sched->k1357[10]); |
571 | L ^= f(R, sched->k0246[ 9], sched->k1357[ 9]); |
572 | R ^= f(L, sched->k0246[ 8], sched->k1357[ 8]); |
573 | L ^= f(R, sched->k0246[ 7], sched->k1357[ 7]); |
574 | R ^= f(L, sched->k0246[ 6], sched->k1357[ 6]); |
575 | L ^= f(R, sched->k0246[ 5], sched->k1357[ 5]); |
576 | R ^= f(L, sched->k0246[ 4], sched->k1357[ 4]); |
577 | L ^= f(R, sched->k0246[ 3], sched->k1357[ 3]); |
578 | R ^= f(L, sched->k0246[ 2], sched->k1357[ 2]); |
579 | L ^= f(R, sched->k0246[ 1], sched->k1357[ 1]); |
580 | R ^= f(L, sched->k0246[ 0], sched->k1357[ 0]); |
581 | |
582 | L = rotl(L, 31); |
583 | R = rotl(R, 31); |
584 | |
585 | swap = L; L = R; R = swap; |
586 | |
587 | FP(L, R); |
588 | |
589 | output[0] = L; |
590 | output[1] = R; |
374330e2 |
591 | } |
592 | |
d1e726bc |
593 | #define GET_32BIT_MSB_FIRST(cp) \ |
594 | (((unsigned long)(unsigned char)(cp)[3]) | \ |
595 | ((unsigned long)(unsigned char)(cp)[2] << 8) | \ |
596 | ((unsigned long)(unsigned char)(cp)[1] << 16) | \ |
597 | ((unsigned long)(unsigned char)(cp)[0] << 24)) |
598 | |
599 | #define PUT_32BIT_MSB_FIRST(cp, value) do { \ |
600 | (cp)[3] = (value); \ |
601 | (cp)[2] = (value) >> 8; \ |
602 | (cp)[1] = (value) >> 16; \ |
603 | (cp)[0] = (value) >> 24; } while (0) |
604 | |
605 | static void des_cbc_encrypt(unsigned char *dest, const unsigned char *src, |
606 | unsigned int len, DESContext *sched) { |
607 | word32 out[2], iv0, iv1; |
608 | unsigned int i; |
609 | |
610 | assert((len & 7) == 0); |
611 | |
612 | iv0 = sched->eiv0; |
613 | iv1 = sched->eiv1; |
614 | for (i = 0; i < len; i += 8) { |
615 | iv0 ^= GET_32BIT_MSB_FIRST(src); src += 4; |
616 | iv1 ^= GET_32BIT_MSB_FIRST(src); src += 4; |
617 | des_encipher(out, iv0, iv1, sched); |
618 | iv0 = out[0]; |
619 | iv1 = out[1]; |
620 | PUT_32BIT_MSB_FIRST(dest, iv0); dest += 4; |
621 | PUT_32BIT_MSB_FIRST(dest, iv1); dest += 4; |
374330e2 |
622 | } |
d1e726bc |
623 | sched->eiv0 = iv0; |
624 | sched->eiv1 = iv1; |
374330e2 |
625 | } |
626 | |
d1e726bc |
627 | static void des_cbc_decrypt(unsigned char *dest, const unsigned char *src, |
628 | unsigned int len, DESContext *sched) { |
629 | word32 out[2], iv0, iv1, xL, xR; |
630 | unsigned int i; |
631 | |
632 | assert((len & 7) == 0); |
633 | |
634 | iv0 = sched->div0; |
635 | iv1 = sched->div1; |
636 | for (i = 0; i < len; i += 8) { |
637 | xL = GET_32BIT_MSB_FIRST(src); src += 4; |
638 | xR = GET_32BIT_MSB_FIRST(src); src += 4; |
639 | des_decipher(out, xL, xR, sched); |
640 | iv0 ^= out[0]; |
641 | iv1 ^= out[1]; |
642 | PUT_32BIT_MSB_FIRST(dest, iv0); dest += 4; |
643 | PUT_32BIT_MSB_FIRST(dest, iv1); dest += 4; |
644 | iv0 = xL; |
645 | iv1 = xR; |
374330e2 |
646 | } |
d1e726bc |
647 | sched->div0 = iv0; |
648 | sched->div1 = iv1; |
374330e2 |
649 | } |
650 | |
d1e726bc |
651 | static void des_3cbc_encrypt(unsigned char *dest, const unsigned char *src, |
652 | unsigned int len, DESContext *scheds) { |
653 | des_cbc_encrypt(dest, src, len, &scheds[0]); |
654 | des_cbc_decrypt(dest, src, len, &scheds[1]); |
655 | des_cbc_encrypt(dest, src, len, &scheds[2]); |
374330e2 |
656 | } |
657 | |
d1e726bc |
658 | static void des_3cbc_decrypt(unsigned char *dest, const unsigned char *src, |
659 | unsigned int len, DESContext *scheds) { |
660 | des_cbc_decrypt(dest, src, len, &scheds[2]); |
661 | des_cbc_encrypt(dest, src, len, &scheds[1]); |
662 | des_cbc_decrypt(dest, src, len, &scheds[0]); |
374330e2 |
663 | } |
664 | |
5a468ffb |
665 | static DESContext keys[3]; |
374330e2 |
666 | |
667 | static void des3_sesskey(unsigned char *key) { |
d1e726bc |
668 | des_key_setup(GET_32BIT_MSB_FIRST(key), |
669 | GET_32BIT_MSB_FIRST(key+4), &keys[0]); |
670 | des_key_setup(GET_32BIT_MSB_FIRST(key+8), |
671 | GET_32BIT_MSB_FIRST(key+12), &keys[1]); |
672 | des_key_setup(GET_32BIT_MSB_FIRST(key+16), |
673 | GET_32BIT_MSB_FIRST(key+20), &keys[2]); |
c5e9c988 |
674 | logevent("Initialised triple-DES encryption"); |
374330e2 |
675 | } |
676 | |
677 | static void des3_encrypt_blk(unsigned char *blk, int len) { |
d1e726bc |
678 | des_3cbc_encrypt(blk, blk, len, keys); |
374330e2 |
679 | } |
680 | |
681 | static void des3_decrypt_blk(unsigned char *blk, int len) { |
d1e726bc |
682 | des_3cbc_decrypt(blk, blk, len, keys); |
374330e2 |
683 | } |
684 | |
685 | struct ssh_cipher ssh_3des = { |
686 | des3_sesskey, |
687 | des3_encrypt_blk, |
688 | des3_decrypt_blk |
689 | }; |
690 | |
9697bfd2 |
691 | static void des_sesskey(unsigned char *key) { |
d1e726bc |
692 | des_key_setup(GET_32BIT_MSB_FIRST(key), |
693 | GET_32BIT_MSB_FIRST(key+4), &keys[0]); |
c5e9c988 |
694 | logevent("Initialised single-DES encryption"); |
9697bfd2 |
695 | } |
696 | |
697 | static void des_encrypt_blk(unsigned char *blk, int len) { |
d1e726bc |
698 | des_cbc_encrypt(blk, blk, len, keys); |
9697bfd2 |
699 | } |
700 | |
701 | static void des_decrypt_blk(unsigned char *blk, int len) { |
d1e726bc |
702 | des_cbc_decrypt(blk, blk, len, keys); |
9697bfd2 |
703 | } |
704 | |
705 | struct ssh_cipher ssh_des = { |
706 | des_sesskey, |
707 | des_encrypt_blk, |
708 | des_decrypt_blk |
709 | }; |