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
|
.text
.globl ChaCha20_ctr32
.type ChaCha20_ctr32,@function
.align 32
ChaCha20_ctr32:
ltgr %r4,%r4 # %r4==0?
bzr %r14
aghi %r4,-64
lghi %r1,-240
stmg %r6,%r15,48(%r15)
slgr %r2,%r3 # difference
la %r4,0(%r3,%r4) # end of input minus 64
larl %r7,.Lsigma
lgr %r0,%r15
la %r15,0(%r1,%r15)
stg %r0,0(%r15)
lmg %r8,%r11,0(%r5) # load key
lmg %r12,%r13,0(%r6) # load counter
lmg %r6,%r7,0(%r7) # load sigma constant
la %r14,0(%r3)
stg %r2,240+3*8(%r15)
stg %r4,240+4*8(%r15)
stmg %r6,%r13,160(%r15) # copy key schedule to stack
srlg %r10,%r12,32 # 32-bit counter value
j .Loop_outer
.align 16
.Loop_outer:
lm %r0,%r7,160+4*0(%r15) # load x[0]-x[7]
lm %r8,%r9,160+4*10(%r15) # load x[10]-x[11]
lm %r11,%r13,160+4*13(%r15) # load x[13]-x[15]
stm %r8,%r9,160+4*8+4*10(%r15) # offload x[10]-x[11]
lm %r8,%r9,160+4*8(%r15) # load x[8]-x[9]
st %r10,160+4*12(%r15) # save counter
stg %r14,240+2*8(%r15) # save input pointer
lhi %r14,10
j .Loop
.align 4
.Loop:
alr %r0,%r4
alr %r1,%r5
xr %r10,%r0
xr %r11,%r1
rll %r10,%r10,16
rll %r11,%r11,16
alr %r8,%r10
alr %r9,%r11
xr %r4,%r8
xr %r5,%r9
rll %r4,%r4,12
rll %r5,%r5,12
alr %r0,%r4
alr %r1,%r5
xr %r10,%r0
xr %r11,%r1
rll %r10,%r10,8
rll %r11,%r11,8
alr %r8,%r10
alr %r9,%r11
xr %r4,%r8
xr %r5,%r9
rll %r4,%r4,7
rll %r5,%r5,7
stm %r8,%r9,160+4*8+4*8(%r15)
lm %r8,%r9,160+4*8+4*10(%r15)
alr %r2,%r6
alr %r3,%r7
xr %r12,%r2
xr %r13,%r3
rll %r12,%r12,16
rll %r13,%r13,16
alr %r8,%r12
alr %r9,%r13
xr %r6,%r8
xr %r7,%r9
rll %r6,%r6,12
rll %r7,%r7,12
alr %r2,%r6
alr %r3,%r7
xr %r12,%r2
xr %r13,%r3
rll %r12,%r12,8
rll %r13,%r13,8
alr %r8,%r12
alr %r9,%r13
xr %r6,%r8
xr %r7,%r9
rll %r6,%r6,7
rll %r7,%r7,7
alr %r0,%r5
alr %r1,%r6
xr %r13,%r0
xr %r10,%r1
rll %r13,%r13,16
rll %r10,%r10,16
alr %r8,%r13
alr %r9,%r10
xr %r5,%r8
xr %r6,%r9
rll %r5,%r5,12
rll %r6,%r6,12
alr %r0,%r5
alr %r1,%r6
xr %r13,%r0
xr %r10,%r1
rll %r13,%r13,8
rll %r10,%r10,8
alr %r8,%r13
alr %r9,%r10
xr %r5,%r8
xr %r6,%r9
rll %r5,%r5,7
rll %r6,%r6,7
stm %r8,%r9,160+4*8+4*10(%r15)
lm %r8,%r9,160+4*8+4*8(%r15)
alr %r2,%r7
alr %r3,%r4
xr %r11,%r2
xr %r12,%r3
rll %r11,%r11,16
rll %r12,%r12,16
alr %r8,%r11
alr %r9,%r12
xr %r7,%r8
xr %r4,%r9
rll %r7,%r7,12
rll %r4,%r4,12
alr %r2,%r7
alr %r3,%r4
xr %r11,%r2
xr %r12,%r3
rll %r11,%r11,8
rll %r12,%r12,8
alr %r8,%r11
alr %r9,%r12
xr %r7,%r8
xr %r4,%r9
rll %r7,%r7,7
rll %r4,%r4,7
brct %r14,.Loop
lg %r14,240+2*8(%r15) # pull input pointer
stm %r8,%r9,160+4*8+4*8(%r15) # offload x[8]-x[9]
lmg %r8,%r9,240+3*8(%r15)
al %r0,160+4*0(%r15) # accumulate key schedule
al %r1,160+4*1(%r15)
al %r2,160+4*2(%r15)
al %r3,160+4*3(%r15)
al %r4,160+4*4(%r15)
al %r5,160+4*5(%r15)
al %r6,160+4*6(%r15)
al %r7,160+4*7(%r15)
lrvr %r0,%r0
lrvr %r1,%r1
lrvr %r2,%r2
lrvr %r3,%r3
lrvr %r4,%r4
lrvr %r5,%r5
lrvr %r6,%r6
lrvr %r7,%r7
al %r10,160+4*12(%r15)
al %r11,160+4*13(%r15)
al %r12,160+4*14(%r15)
al %r13,160+4*15(%r15)
lrvr %r10,%r10
lrvr %r11,%r11
lrvr %r12,%r12
lrvr %r13,%r13
la %r8,0(%r8,%r14) # reconstruct output pointer
clgr %r14,%r9
jh .Ltail
x %r0,4*0(%r14) # xor with input
x %r1,4*1(%r14)
st %r0,4*0(%r8) # store output
x %r2,4*2(%r14)
st %r1,4*1(%r8)
x %r3,4*3(%r14)
st %r2,4*2(%r8)
x %r4,4*4(%r14)
st %r3,4*3(%r8)
lm %r0,%r3,160+4*8+4*8(%r15) # load x[8]-x[11]
x %r5,4*5(%r14)
st %r4,4*4(%r8)
x %r6,4*6(%r14)
al %r0,160+4*8(%r15)
st %r5,4*5(%r8)
x %r7,4*7(%r14)
al %r1,160+4*9(%r15)
st %r6,4*6(%r8)
x %r10,4*12(%r14)
al %r2,160+4*10(%r15)
st %r7,4*7(%r8)
x %r11,4*13(%r14)
al %r3,160+4*11(%r15)
st %r10,4*12(%r8)
x %r12,4*14(%r14)
st %r11,4*13(%r8)
x %r13,4*15(%r14)
st %r12,4*14(%r8)
lrvr %r0,%r0
st %r13,4*15(%r8)
lrvr %r1,%r1
lrvr %r2,%r2
lrvr %r3,%r3
lhi %r10,1
x %r0,4*8(%r14)
al %r10,160+4*12(%r15) # increment counter
x %r1,4*9(%r14)
st %r0,4*8(%r8)
x %r2,4*10(%r14)
st %r1,4*9(%r8)
x %r3,4*11(%r14)
st %r2,4*10(%r8)
st %r3,4*11(%r8)
clgr %r14,%r9 # done yet?
la %r14,64(%r14)
jl .Loop_outer
.Ldone:
xgr %r0,%r0
xgr %r1,%r1
xgr %r2,%r2
xgr %r3,%r3
stmg %r0,%r3,160+4*4(%r15) # wipe key copy
stmg %r0,%r3,160+4*12(%r15)
lmg %r6,%r15,288(%r15)
br %r14
.align 16
.Ltail:
la %r9,64(%r9)
stm %r0,%r7,160+4*0(%r15)
slgr %r9,%r14
lm %r0,%r3,160+4*8+4*8(%r15)
lghi %r6,0
stm %r10,%r13,160+4*12(%r15)
al %r0,160+4*8(%r15)
al %r1,160+4*9(%r15)
al %r2,160+4*10(%r15)
al %r3,160+4*11(%r15)
lrvr %r0,%r0
lrvr %r1,%r1
lrvr %r2,%r2
lrvr %r3,%r3
stm %r0,%r3,160+4*8(%r15)
.Loop_tail:
llgc %r4,0(%r6,%r14)
llgc %r5,160(%r6,%r15)
xr %r5,%r4
stc %r5,0(%r6,%r8)
la %r6,1(%r6)
brct %r9,.Loop_tail
j .Ldone
.size ChaCha20_ctr32,.-ChaCha20_ctr32
.align 32
.Lsigma:
.long 0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral
.asciz "ChaCha20 for s390x, CRYPTOGAMS by <appro@openssl.org>"
.align 4
|
