xref: /freebsd/sys/crypto/openssl/powerpc64le/vpaes-ppc.S (revision e6bfd18d21b225af6a0ed67ceeaf1293b7b9eba5)
1/* $FreeBSD$ */
2/* Do not modify. This file is auto-generated from vpaes-ppc.pl. */
3.machine	"any"
4
5.abiversion	2
6.text
7
8.align	7
9_vpaes_consts:
10.Lk_mc_forward:
11.byte	0x0e,0x0d,0x0c,0x0f,0x0a,0x09,0x08,0x0b,0x06,0x05,0x04,0x07,0x02,0x01,0x00,0x03
12.byte	0x0a,0x09,0x08,0x0b,0x06,0x05,0x04,0x07,0x02,0x01,0x00,0x03,0x0e,0x0d,0x0c,0x0f
13.byte	0x06,0x05,0x04,0x07,0x02,0x01,0x00,0x03,0x0e,0x0d,0x0c,0x0f,0x0a,0x09,0x08,0x0b
14.byte	0x02,0x01,0x00,0x03,0x0e,0x0d,0x0c,0x0f,0x0a,0x09,0x08,0x0b,0x06,0x05,0x04,0x07
15.Lk_mc_backward:
16.byte	0x0c,0x0f,0x0e,0x0d,0x08,0x0b,0x0a,0x09,0x04,0x07,0x06,0x05,0x00,0x03,0x02,0x01
17.byte	0x00,0x03,0x02,0x01,0x0c,0x0f,0x0e,0x0d,0x08,0x0b,0x0a,0x09,0x04,0x07,0x06,0x05
18.byte	0x04,0x07,0x06,0x05,0x00,0x03,0x02,0x01,0x0c,0x0f,0x0e,0x0d,0x08,0x0b,0x0a,0x09
19.byte	0x08,0x0b,0x0a,0x09,0x04,0x07,0x06,0x05,0x00,0x03,0x02,0x01,0x0c,0x0f,0x0e,0x0d
20.Lk_sr:
21.byte	0x0f,0x0e,0x0d,0x0c,0x0b,0x0a,0x09,0x08,0x07,0x06,0x05,0x04,0x03,0x02,0x01,0x00
22.byte	0x0f,0x0a,0x05,0x00,0x0b,0x06,0x01,0x0c,0x07,0x02,0x0d,0x08,0x03,0x0e,0x09,0x04
23.byte	0x0f,0x06,0x0d,0x04,0x0b,0x02,0x09,0x00,0x07,0x0e,0x05,0x0c,0x03,0x0a,0x01,0x08
24.byte	0x0f,0x02,0x05,0x08,0x0b,0x0e,0x01,0x04,0x07,0x0a,0x0d,0x00,0x03,0x06,0x09,0x0c
25
26
27
28
29.Lk_inv:
30.byte	0x04,0x07,0x03,0x09,0x0a,0x0b,0x0c,0x02,0x0e,0x05,0x06,0x0f,0x0d,0x08,0x01,0xf0
31.byte	0x03,0x0d,0x0e,0x0c,0x02,0x05,0x08,0x09,0x01,0x04,0x0a,0x06,0x0f,0x0b,0x07,0xf0
32.Lk_ipt:
33.byte	0xca,0xba,0xe0,0x90,0x52,0x22,0x78,0x08,0xc2,0xb2,0xe8,0x98,0x5a,0x2a,0x70,0x00
34.byte	0xcd,0x80,0xb1,0xfc,0xb0,0xfd,0xcc,0x81,0x4c,0x01,0x30,0x7d,0x31,0x7c,0x4d,0x00
35.Lk_sbo:
36.byte	0x15,0xaa,0xbf,0x7a,0xc5,0x02,0xa8,0x78,0xd0,0xd2,0x6d,0x17,0x6f,0xbd,0xc7,0x00
37.byte	0x8e,0x1e,0x90,0xd1,0x41,0x2b,0x35,0xfa,0xcf,0xe4,0x74,0xa5,0x5f,0xbb,0x6a,0x00
38.Lk_sb1:
39.byte	0x3b,0xf7,0xcc,0xc1,0x0d,0x2e,0xd9,0xef,0x36,0x18,0xd4,0x15,0xfa,0xe2,0x23,0x00
40.byte	0xa5,0xdf,0x7a,0x6e,0x14,0x2a,0xf5,0x44,0xb1,0x9b,0xe1,0x8f,0xcb,0x50,0x3e,0x00
41.Lk_sb2:
42.byte	0xc2,0xa1,0x63,0xc8,0xab,0x82,0x23,0x4a,0x69,0xeb,0x88,0x40,0x0a,0xe1,0x29,0x00
43.byte	0x5e,0xb7,0xe9,0x55,0xbc,0x98,0x2f,0xcd,0xe2,0x7a,0x93,0xc6,0x0b,0x71,0x24,0x00
44
45
46
47
48.Lk_dipt:
49.byte	0x15,0x4a,0x41,0x1e,0x11,0x4e,0x45,0x1a,0x0f,0x50,0x5b,0x04,0x0b,0x54,0x5f,0x00
50.byte	0x12,0x77,0x17,0x72,0xf4,0x91,0xf1,0x94,0x86,0xe3,0x83,0xe6,0x60,0x05,0x65,0x00
51.Lk_dsbo:
52.byte	0xc7,0xaa,0x6d,0xb9,0xd4,0x94,0x3e,0x2d,0x13,0x87,0xea,0x53,0x7e,0xf9,0x40,0x00
53.byte	0xca,0x4b,0x81,0x59,0xd8,0xc5,0x8e,0x9c,0x12,0xd7,0x56,0x0f,0x93,0x44,0x1d,0x00
54.Lk_dsb9:
55.byte	0xca,0xd5,0x1f,0x50,0x4f,0x99,0x4c,0xc9,0x85,0x1c,0x03,0x53,0x9a,0x86,0xd6,0x00
56.byte	0x72,0x5e,0x2c,0x9e,0xb2,0xfb,0xa5,0x65,0xc0,0x3b,0x17,0x89,0xec,0xd7,0x49,0x00
57.Lk_dsbd:
58.byte	0xf5,0x6e,0x9b,0x13,0x88,0x2a,0x44,0x39,0x7d,0x57,0xcc,0xdf,0xe6,0xb1,0xa2,0x00
59.byte	0x29,0x31,0x18,0x0d,0x15,0xde,0xef,0xd3,0x3c,0xe2,0xfa,0xf7,0x24,0xc6,0xcb,0x00
60.Lk_dsbb:
61.byte	0x60,0x26,0x46,0xf6,0xb0,0xf2,0xd4,0x04,0xd0,0x22,0x64,0x92,0x96,0xb4,0x42,0x00
62.byte	0xf3,0xff,0x0c,0x3e,0x32,0x55,0xaa,0x6b,0xc1,0x94,0x98,0xa6,0xcd,0x59,0x67,0x00
63.Lk_dsbe:
64.byte	0x22,0x42,0x60,0x04,0x64,0xb4,0xf6,0xb0,0x46,0xf2,0x92,0x96,0x26,0xd4,0xd0,0x00
65.byte	0x94,0x67,0xf3,0x6b,0x98,0x59,0x3e,0x32,0x0c,0x55,0xa6,0xcd,0xff,0xaa,0xc1,0x00
66
67
68
69
70.Lk_dksd:
71.byte	0x07,0x40,0xe3,0xa4,0x5a,0x1d,0xbe,0xf9,0xfe,0xb9,0x1a,0x5d,0xa3,0xe4,0x47,0x00
72.byte	0x5f,0xdc,0x69,0xea,0xab,0x28,0x9d,0x1e,0x41,0xc2,0x77,0xf4,0xb5,0x36,0x83,0x00
73.Lk_dksb:
74.byte	0x03,0xd6,0x53,0x86,0x1c,0xc9,0x4c,0x99,0x9a,0x4f,0xca,0x1f,0x85,0x50,0xd5,0x00
75.byte	0xd9,0x93,0x25,0x6f,0x7e,0x34,0x82,0xc8,0x11,0x5b,0xed,0xa7,0xb6,0xfc,0x4a,0x00
76.Lk_dkse:
77.byte	0x53,0x85,0x9a,0x4c,0x99,0x4f,0x50,0x86,0xd5,0x03,0x1c,0xca,0x1f,0xc9,0xd6,0x00
78.byte	0xcd,0x5e,0xf9,0x6a,0x20,0xb3,0x14,0x87,0xa2,0x31,0x96,0x05,0x4f,0xdc,0x7b,0xe8
79.Lk_dks9:
80.byte	0x4a,0xed,0x93,0x34,0x82,0x25,0x5b,0xfc,0xb6,0x11,0x6f,0xc8,0x7e,0xd9,0xa7,0x00
81.byte	0x8b,0xb8,0x9f,0xac,0xe9,0xda,0xfd,0xce,0x45,0x76,0x51,0x62,0x27,0x14,0x33,0x00
82
83.Lk_rcon:
84.byte	0xb6,0xee,0x9d,0xaf,0xb9,0x91,0x83,0x1f,0x81,0x7d,0x7c,0x4d,0x08,0x98,0x2a,0x70
85.Lk_s63:
86.byte	0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b,0x5b
87
88.Lk_opt:
89.byte	0xf7,0x97,0x41,0x21,0xde,0xbe,0x68,0x08,0xff,0x9f,0x49,0x29,0xd6,0xb6,0x60,0x00
90.byte	0xe1,0x0d,0x5d,0xb1,0xb0,0x5c,0x0c,0xe0,0x01,0xed,0xbd,0x51,0x50,0xbc,0xec,0x00
91.Lk_deskew:
92.byte	0x1d,0xfe,0xb9,0x5a,0x5d,0xbe,0xf9,0x1a,0x07,0xe4,0xa3,0x40,0x47,0xa4,0xe3,0x00
93.byte	0x28,0x41,0xc2,0xab,0xf4,0x9d,0x1e,0x77,0x5f,0x36,0xb5,0xdc,0x83,0xea,0x69,0x00
94.align	5
95.Lconsts:
96	mflr	0
97	bcl	20,31,$+4
98	mflr	12
99	addi	12,12,-0x308
100	mtlr	0
101	blr
102.long	0
103.byte	0,12,0x14,0,0,0,0,0
104.byte	86,101,99,116,111,114,32,80,101,114,109,117,116,97,116,105,111,110,32,65,69,83,32,102,111,114,32,65,108,116,105,86,101,99,44,77,105,107,101,32,72,97,109,98,117,114,103,32,40,83,116,97,110,102,111,114,100,32,85,110,105,118,101,114,115,105,116,121,41,0
105.align	2
106.align	6
107
108
109
110
111
112
113.align	4
114_vpaes_encrypt_preheat:
115	mflr	8
116	bl	.Lconsts
117	mtlr	8
118	li	11, 0xc0
119	li	10, 0xd0
120	li	9,  0xe0
121	li	8,  0xf0
122	vxor	7, 7, 7
123	vspltisb	8,4
124	vspltisb	9,0x0f
125	lvx	10, 12, 11
126	li	11, 0x100
127	lvx	11, 12, 10
128	li	10, 0x110
129	lvx	12, 12, 9
130	li	9,  0x120
131	lvx	13, 12, 8
132	li	8,  0x130
133	lvx	14, 12, 11
134	li	11, 0x140
135	lvx	15, 12, 10
136	li	10, 0x150
137	lvx	16, 12, 9
138	lvx	17, 12, 8
139	lvx	18, 12, 11
140	lvx	19, 12, 10
141	blr
142.long	0
143.byte	0,12,0x14,0,0,0,0,0
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159.align	5
160_vpaes_encrypt_core:
161	lwz	8, 240(5)
162	li	9, 16
163	lvx	5, 0, 5
164	li	11, 0x10
165	lvx	6, 9, 5
166	addi	9, 9, 16
167	vperm	5, 6, 5, 31
168	addi	10, 11, 0x40
169	vsrb	1, 0, 8
170	vperm	0, 12, 12, 0
171	vperm	1, 13, 13, 1
172	vxor	0, 0, 5
173	vxor	0, 0, 1
174	mtctr	8
175	b	.Lenc_entry
176
177.align	4
178.Lenc_loop:
179
180	vperm	4, 17, 7, 2
181	lvx	1, 12, 11
182	addi	11, 11, 16
183	vperm	0, 16, 7, 3
184	vxor	4, 4, 5
185	andi.	11, 11, 0x30
186	vperm	5, 19, 7, 2
187	vxor	0, 0, 4
188	vperm	2, 18, 7, 3
189	lvx	4, 12, 10
190	addi	10, 11, 0x40
191	vperm	3, 0, 7, 1
192	vxor	2, 2, 5
193	vperm	0, 0, 7, 4
194	vxor	3, 3, 2
195	vperm	4, 3, 7, 1
196	vxor	0, 0, 3
197	vxor	0, 0, 4
198
199.Lenc_entry:
200
201	vsrb	1, 0, 8
202	vperm	5, 11, 11, 0
203	vxor	0, 0, 1
204	vperm	3, 10, 10, 1
205	vperm	4, 10, 10, 0
206	vand	0, 0, 9
207	vxor	3, 3, 5
208	vxor	4, 4, 5
209	vperm	2, 10, 7, 3
210	vor	5,6,6
211	lvx	6, 9, 5
212	vperm	3, 10, 7, 4
213	addi	9, 9, 16
214	vxor	2, 2, 0
215	vperm	5, 6, 5, 31
216	vxor	3, 3, 1
217	bdnz	.Lenc_loop
218
219
220	addi	10, 11, 0x80
221
222
223	vperm	4, 14, 7, 2
224	lvx	1, 12, 10
225	vperm	0, 15, 7, 3
226	vxor	4, 4, 5
227	vxor	0, 0, 4
228	vperm	0, 0, 7, 1
229	blr
230.long	0
231.byte	0,12,0x14,0,0,0,0,0
232
233.globl	vpaes_encrypt
234.type	vpaes_encrypt,@function
235.align	5
236vpaes_encrypt:
237.localentry	vpaes_encrypt,0
238
239	stdu	1,-256(1)
240	li	10,63
241	li	11,79
242	mflr	6
243	li	7,-1
244	stvx	20,10,1
245	addi	10,10,32
246	stvx	21,11,1
247	addi	11,11,32
248	stvx	22,10,1
249	addi	10,10,32
250	stvx	23,11,1
251	addi	11,11,32
252	stvx	24,10,1
253	addi	10,10,32
254	stvx	25,11,1
255	addi	11,11,32
256	stvx	26,10,1
257	addi	10,10,32
258	stvx	27,11,1
259	addi	11,11,32
260	stvx	28,10,1
261	addi	10,10,32
262	stvx	29,11,1
263	addi	11,11,32
264	stvx	30,10,1
265	stvx	31,11,1
266	stw	7,252(1)
267	li	0, -1
268	std	6,272(1)
269	or	0,0,0
270
271	bl	_vpaes_encrypt_preheat
272
273	lvsr	27, 0, 3
274	lvx	0, 0, 3
275	addi	3, 3, 15
276	lvsl	29, 0, 4
277	lvsr	31, 0, 5
278	lvx	26, 0, 3
279	vperm	0, 26, 0, 27
280
281	bl	_vpaes_encrypt_core
282
283	andi.	8, 4, 15
284	li	9, 16
285	beq	.Lenc_out_aligned
286
287	vperm	0, 0, 0, 29
288	mtctr	9
289.Lenc_out_unaligned:
290	stvebx	0, 0, 4
291	addi	4, 4, 1
292	bdnz	.Lenc_out_unaligned
293	b	.Lenc_done
294
295.align	4
296.Lenc_out_aligned:
297	stvx	0, 0, 4
298.Lenc_done:
299
300	li	10,63
301	li	11,79
302	mtlr	6
303	or	7,7,7
304	lvx	20,10,1
305	addi	10,10,32
306	lvx	21,11,1
307	addi	11,11,32
308	lvx	22,10,1
309	addi	10,10,32
310	lvx	23,11,1
311	addi	11,11,32
312	lvx	24,10,1
313	addi	10,10,32
314	lvx	25,11,1
315	addi	11,11,32
316	lvx	26,10,1
317	addi	10,10,32
318	lvx	27,11,1
319	addi	11,11,32
320	lvx	28,10,1
321	addi	10,10,32
322	lvx	29,11,1
323	addi	11,11,32
324	lvx	30,10,1
325	lvx	31,11,1
326	addi	1,1,256
327	blr
328.long	0
329.byte	0,12,0x04,1,0x80,0,3,0
330.long	0
331.size	vpaes_encrypt,.-vpaes_encrypt
332
333.align	4
334_vpaes_decrypt_preheat:
335	mflr	8
336	bl	.Lconsts
337	mtlr	8
338	li	11, 0xc0
339	li	10, 0xd0
340	li	9,  0x160
341	li	8,  0x170
342	vxor	7, 7, 7
343	vspltisb	8,4
344	vspltisb	9,0x0f
345	lvx	10, 12, 11
346	li	11, 0x180
347	lvx	11, 12, 10
348	li	10, 0x190
349	lvx	12, 12, 9
350	li	9,  0x1a0
351	lvx	13, 12, 8
352	li	8,  0x1b0
353	lvx	14, 12, 11
354	li	11, 0x1c0
355	lvx	15, 12, 10
356	li	10, 0x1d0
357	lvx	16, 12, 9
358	li	9,  0x1e0
359	lvx	17, 12, 8
360	li	8,  0x1f0
361	lvx	18, 12, 11
362	li	11, 0x200
363	lvx	19, 12, 10
364	li	10, 0x210
365	lvx	20, 12, 9
366	lvx	21, 12, 8
367	lvx	22, 12, 11
368	lvx	23, 12, 10
369	blr
370.long	0
371.byte	0,12,0x14,0,0,0,0,0
372
373
374
375
376
377
378.align	4
379_vpaes_decrypt_core:
380	lwz	8, 240(5)
381	li	9, 16
382	lvx	5, 0, 5
383	li	11, 0x30
384	lvx	6, 9, 5
385	addi	9, 9, 16
386	vperm	5, 6, 5, 31
387	vsrb	1, 0, 8
388	vperm	0, 12, 12, 0
389	vperm	1, 13, 13, 1
390	vxor	0, 0, 5
391	vxor	0, 0, 1
392	mtctr	8
393	b	.Ldec_entry
394
395.align	4
396.Ldec_loop:
397
398
399
400	lvx	0, 12, 11
401
402
403	vperm	4, 16, 7, 2
404	subi	11, 11, 16
405	vperm	1, 17, 7, 3
406	andi.	11, 11, 0x30
407	vxor	5, 5, 4
408
409	vxor	5, 5, 1
410
411
412	vperm	4, 18, 7, 2
413	vperm	5, 5, 7, 0
414	vperm	1, 19, 7, 3
415	vxor	5, 5, 4
416
417	vxor	5, 5, 1
418
419
420	vperm	4, 20, 7, 2
421	vperm	5, 5, 7, 0
422	vperm	1, 21, 7, 3
423	vxor	5, 5, 4
424
425	vxor	5, 5, 1
426
427
428	vperm	4, 22, 7, 2
429	vperm	5, 5, 7, 0
430	vperm	1, 23, 7, 3
431	vxor	0, 5, 4
432	vxor	0, 0, 1
433
434.Ldec_entry:
435
436	vsrb	1, 0, 8
437	vperm	2, 11, 11, 0
438	vxor	0, 0, 1
439	vperm	3, 10, 10, 1
440	vperm	4, 10, 10, 0
441	vand	0, 0, 9
442	vxor	3, 3, 2
443	vxor	4, 4, 2
444	vperm	2, 10, 7, 3
445	vor	5,6,6
446	lvx	6, 9, 5
447	vperm	3, 10, 7, 4
448	addi	9, 9, 16
449	vxor	2, 2, 0
450	vperm	5, 6, 5, 31
451	vxor	3, 3, 1
452	bdnz	.Ldec_loop
453
454
455	addi	10, 11, 0x80
456
457	vperm	4, 14, 7, 2
458
459	lvx	2, 12, 10
460	vperm	1, 15, 7, 3
461	vxor	4, 4, 5
462	vxor	0, 1, 4
463	vperm	0, 0, 7, 2
464	blr
465.long	0
466.byte	0,12,0x14,0,0,0,0,0
467
468.globl	vpaes_decrypt
469.type	vpaes_decrypt,@function
470.align	5
471vpaes_decrypt:
472.localentry	vpaes_decrypt,0
473
474	stdu	1,-256(1)
475	li	10,63
476	li	11,79
477	mflr	6
478	li	7,-1
479	stvx	20,10,1
480	addi	10,10,32
481	stvx	21,11,1
482	addi	11,11,32
483	stvx	22,10,1
484	addi	10,10,32
485	stvx	23,11,1
486	addi	11,11,32
487	stvx	24,10,1
488	addi	10,10,32
489	stvx	25,11,1
490	addi	11,11,32
491	stvx	26,10,1
492	addi	10,10,32
493	stvx	27,11,1
494	addi	11,11,32
495	stvx	28,10,1
496	addi	10,10,32
497	stvx	29,11,1
498	addi	11,11,32
499	stvx	30,10,1
500	stvx	31,11,1
501	stw	7,252(1)
502	li	0, -1
503	std	6,272(1)
504	or	0,0,0
505
506	bl	_vpaes_decrypt_preheat
507
508	lvsr	27, 0, 3
509	lvx	0, 0, 3
510	addi	3, 3, 15
511	lvsl	29, 0, 4
512	lvsr	31, 0, 5
513	lvx	26, 0, 3
514	vperm	0, 26, 0, 27
515
516	bl	_vpaes_decrypt_core
517
518	andi.	8, 4, 15
519	li	9, 16
520	beq	.Ldec_out_aligned
521
522	vperm	0, 0, 0, 29
523	mtctr	9
524.Ldec_out_unaligned:
525	stvebx	0, 0, 4
526	addi	4, 4, 1
527	bdnz	.Ldec_out_unaligned
528	b	.Ldec_done
529
530.align	4
531.Ldec_out_aligned:
532	stvx	0, 0, 4
533.Ldec_done:
534
535	li	10,63
536	li	11,79
537	mtlr	6
538	or	7,7,7
539	lvx	20,10,1
540	addi	10,10,32
541	lvx	21,11,1
542	addi	11,11,32
543	lvx	22,10,1
544	addi	10,10,32
545	lvx	23,11,1
546	addi	11,11,32
547	lvx	24,10,1
548	addi	10,10,32
549	lvx	25,11,1
550	addi	11,11,32
551	lvx	26,10,1
552	addi	10,10,32
553	lvx	27,11,1
554	addi	11,11,32
555	lvx	28,10,1
556	addi	10,10,32
557	lvx	29,11,1
558	addi	11,11,32
559	lvx	30,10,1
560	lvx	31,11,1
561	addi	1,1,256
562	blr
563.long	0
564.byte	0,12,0x04,1,0x80,0,3,0
565.long	0
566.size	vpaes_decrypt,.-vpaes_decrypt
567
568.globl	vpaes_cbc_encrypt
569.type	vpaes_cbc_encrypt,@function
570.align	5
571vpaes_cbc_encrypt:
572.localentry	vpaes_cbc_encrypt,0
573
574	cmpldi	5,16
575	.long	0x4dc00020
576
577	stdu	1,-272(1)
578	mflr	0
579	li	10,63
580	li	11,79
581	li	12,-1
582	stvx	20,10,1
583	addi	10,10,32
584	stvx	21,11,1
585	addi	11,11,32
586	stvx	22,10,1
587	addi	10,10,32
588	stvx	23,11,1
589	addi	11,11,32
590	stvx	24,10,1
591	addi	10,10,32
592	stvx	25,11,1
593	addi	11,11,32
594	stvx	26,10,1
595	addi	10,10,32
596	stvx	27,11,1
597	addi	11,11,32
598	stvx	28,10,1
599	addi	10,10,32
600	stvx	29,11,1
601	addi	11,11,32
602	stvx	30,10,1
603	stvx	31,11,1
604	stw	12,252(1)
605	std	30,256(1)
606	std	31,264(1)
607	li	9, -16
608	std	0, 288(1)
609
610	and	30, 5, 9
611	andi.	9, 4, 15
612	mr	5, 6
613	mr	31, 7
614	li	6, -1
615	mcrf	1, 0
616	mr	7, 12
617	or	6,6,6
618
619	lvx	24, 0, 31
620	li	9, 15
621	lvsr	27, 0, 31
622	lvx	25, 9, 31
623	vperm	24, 25, 24, 27
624
625	cmpwi	8, 0
626	neg	8, 3
627	vxor	7, 7, 7
628	lvsr	31, 0, 5
629	lvsl	29, 0, 4
630	lvsl	27, 0, 8
631	vnor	30, 7, 7
632	lvx	26, 0, 3
633	vperm	30, 30, 7, 29
634	addi	3, 3, 15
635
636	beq	.Lcbc_decrypt
637
638	bl	_vpaes_encrypt_preheat
639	li	0, 16
640
641	beq	1, .Lcbc_enc_loop
642
643	vor	0,26,26
644	lvx	26, 0, 3
645	addi	3, 3, 16
646	vperm	0, 26, 0, 27
647	vxor	0, 0, 24
648
649	bl	_vpaes_encrypt_core
650
651	andi.	8, 4, 15
652	vor	24,0,0
653	sub	9, 4, 8
654	vperm	28, 0, 0, 29
655
656.Lcbc_enc_head:
657	stvebx	28, 8, 9
658	cmpwi	8, 15
659	addi	8, 8, 1
660	bne	.Lcbc_enc_head
661
662	sub.	30, 30, 0
663	addi	4, 4, 16
664	beq	.Lcbc_unaligned_done
665
666.Lcbc_enc_loop:
667	vor	0,26,26
668	lvx	26, 0, 3
669	addi	3, 3, 16
670	vperm	0, 26, 0, 27
671	vxor	0, 0, 24
672
673	bl	_vpaes_encrypt_core
674
675	vor	24,0,0
676	sub.	30, 30, 0
677	vperm	0, 0, 0, 29
678	vsel	1, 28, 0, 30
679	vor	28,0,0
680	stvx	1, 0, 4
681	addi	4, 4, 16
682	bne	.Lcbc_enc_loop
683
684	b	.Lcbc_done
685
686.align	5
687.Lcbc_decrypt:
688	bl	_vpaes_decrypt_preheat
689	li	0, 16
690
691	beq	1, .Lcbc_dec_loop
692
693	vor	0,26,26
694	lvx	26, 0, 3
695	addi	3, 3, 16
696	vperm	0, 26, 0, 27
697	vor	25,0,0
698
699	bl	_vpaes_decrypt_core
700
701	andi.	8, 4, 15
702	vxor	0, 0, 24
703	vor	24,25,25
704	sub	9, 4, 8
705	vperm	28, 0, 0, 29
706
707.Lcbc_dec_head:
708	stvebx	28, 8, 9
709	cmpwi	8, 15
710	addi	8, 8, 1
711	bne	.Lcbc_dec_head
712
713	sub.	30, 30, 0
714	addi	4, 4, 16
715	beq	.Lcbc_unaligned_done
716
717.Lcbc_dec_loop:
718	vor	0,26,26
719	lvx	26, 0, 3
720	addi	3, 3, 16
721	vperm	0, 26, 0, 27
722	vor	25,0,0
723
724	bl	_vpaes_decrypt_core
725
726	vxor	0, 0, 24
727	vor	24,25,25
728	sub.	30, 30, 0
729	vperm	0, 0, 0, 29
730	vsel	1, 28, 0, 30
731	vor	28,0,0
732	stvx	1, 0, 4
733	addi	4, 4, 16
734	bne	.Lcbc_dec_loop
735
736.Lcbc_done:
737	beq	1, .Lcbc_write_iv
738
739.Lcbc_unaligned_done:
740	andi.	8, 4, 15
741	sub	4, 4, 8
742	li	9, 0
743.Lcbc_tail:
744	stvebx	28, 9, 4
745	addi	9, 9, 1
746	cmpw	9, 8
747	bne	.Lcbc_tail
748
749.Lcbc_write_iv:
750	neg	8, 31
751	li	10, 4
752	lvsr	29, 0, 8
753	li	11, 8
754	li	12, 12
755	vperm	24, 24, 24, 29
756	stvewx	24, 0, 31
757	stvewx	24, 10, 31
758	stvewx	24, 11, 31
759	stvewx	24, 12, 31
760
761	or	7,7,7
762	li	10,63
763	li	11,79
764	lvx	20,10,1
765	addi	10,10,32
766	lvx	21,11,1
767	addi	11,11,32
768	lvx	22,10,1
769	addi	10,10,32
770	lvx	23,11,1
771	addi	11,11,32
772	lvx	24,10,1
773	addi	10,10,32
774	lvx	25,11,1
775	addi	11,11,32
776	lvx	26,10,1
777	addi	10,10,32
778	lvx	27,11,1
779	addi	11,11,32
780	lvx	28,10,1
781	addi	10,10,32
782	lvx	29,11,1
783	addi	11,11,32
784	lvx	30,10,1
785	lvx	31,11,1
786.Lcbc_abort:
787	ld	0, 288(1)
788	ld	30,256(1)
789	ld	31,264(1)
790	mtlr	0
791	addi	1,1,272
792	blr
793.long	0
794.byte	0,12,0x04,1,0x80,2,6,0
795.long	0
796.size	vpaes_cbc_encrypt,.-vpaes_cbc_encrypt
797
798
799
800
801
802.align	4
803_vpaes_key_preheat:
804	mflr	8
805	bl	.Lconsts
806	mtlr	8
807	li	11, 0xc0
808	li	10, 0xd0
809	li	9,  0xe0
810	li	8,  0xf0
811
812	vspltisb	8,4
813	vxor	9,9,9
814	lvx	10, 12, 11
815	li	11, 0x120
816	lvx	11, 12, 10
817	li	10, 0x130
818	lvx	12, 12, 9
819	li	9, 0x220
820	lvx	13, 12, 8
821	li	8, 0x230
822
823	lvx	14, 12, 11
824	li	11, 0x240
825	lvx	15, 12, 10
826	li	10, 0x250
827
828	lvx	16, 12, 9
829	li	9, 0x260
830	lvx	17, 12, 8
831	li	8, 0x270
832	lvx	18, 12, 11
833	li	11, 0x280
834	lvx	19, 12, 10
835	li	10, 0x290
836	lvx	20, 12, 9
837	li	9, 0x2a0
838	lvx	21, 12, 8
839	li	8, 0x2b0
840	lvx	22, 12, 11
841	lvx	23, 12, 10
842
843	lvx	24, 12, 9
844	lvx	25, 0, 12
845	lvx	26, 12, 8
846	blr
847.long	0
848.byte	0,12,0x14,0,0,0,0,0
849
850.align	4
851_vpaes_schedule_core:
852	mflr	7
853
854	bl	_vpaes_key_preheat
855
856
857	neg	8, 3
858	lvx	0, 0, 3
859	addi	3, 3, 15
860	lvsl	27, 0, 8
861	lvx	6, 0, 3
862	addi	3, 3, 8
863	vperm	0, 6, 0, 27
864
865
866	vor	3,0,0
867	bl	_vpaes_schedule_transform
868	vor	7,0,0
869
870	bne	1, .Lschedule_am_decrypting
871
872
873	li	8, 0x30
874	li	9, 4
875	li	10, 8
876	li	11, 12
877
878	lvsl	29, 0, 5
879	vnor	30, 9, 9
880	vperm	30, 30, 9, 29
881
882
883	vperm	28, 0, 0, 29
884	stvewx	28, 0, 5
885	stvewx	28, 9, 5
886	stvewx	28, 10, 5
887	addi	10, 12, 0x80
888	stvewx	28, 11, 5
889	b	.Lschedule_go
890
891.Lschedule_am_decrypting:
892	srwi	8, 4, 1
893	andi.	8, 8, 32
894	xori	8, 8, 32
895	addi	10, 12, 0x80
896
897	lvx	1, 8, 10
898	li	9, 4
899	li	10, 8
900	li	11, 12
901	vperm	4, 3, 3, 1
902
903	neg	0, 5
904	lvsr	29, 0, 0
905	vnor	30, 9, 9
906	vperm	30, 9, 30, 29
907
908
909	vperm	28, 4, 4, 29
910	stvewx	28, 0, 5
911	stvewx	28, 9, 5
912	stvewx	28, 10, 5
913	addi	10, 12, 0x80
914	stvewx	28, 11, 5
915	addi	5, 5, 15
916	xori	8, 8, 0x30
917
918.Lschedule_go:
919	cmplwi	4, 192
920	bgt	.Lschedule_256
921	beq	.Lschedule_192
922
923
924
925
926
927
928
929
930
931
932.Lschedule_128:
933	li	0, 10
934	mtctr	0
935
936.Loop_schedule_128:
937	bl	_vpaes_schedule_round
938	bdz	.Lschedule_mangle_last
939	bl	_vpaes_schedule_mangle
940	b	.Loop_schedule_128
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957.align	4
958.Lschedule_192:
959	li	0, 4
960	lvx	0, 0, 3
961	vperm	0, 0, 6, 27
962	vsldoi	0, 0, 3, 16-8
963	bl	_vpaes_schedule_transform
964	vsldoi	6, 9, 0, 16-8
965	vsldoi	6, 6, 9, 16-8
966	mtctr	0
967
968.Loop_schedule_192:
969	bl	_vpaes_schedule_round
970	vsldoi	0, 0, 6, 16-8
971	bl	_vpaes_schedule_mangle
972	bl	_vpaes_schedule_192_smear
973	bl	_vpaes_schedule_mangle
974	bl	_vpaes_schedule_round
975	bdz	.Lschedule_mangle_last
976	bl	_vpaes_schedule_mangle
977	bl	_vpaes_schedule_192_smear
978	b	.Loop_schedule_192
979
980
981
982
983
984
985
986
987
988
989
990.align	4
991.Lschedule_256:
992	li	0, 7
993	addi	3, 3, 8
994	lvx	0, 0, 3
995	vperm	0, 0, 6, 27
996	bl	_vpaes_schedule_transform
997	mtctr	0
998
999.Loop_schedule_256:
1000	bl	_vpaes_schedule_mangle
1001	vor	6,0,0
1002
1003
1004	bl	_vpaes_schedule_round
1005	bdz	.Lschedule_mangle_last
1006	bl	_vpaes_schedule_mangle
1007
1008
1009	vspltw	0, 0, 3-3
1010	vor	5,7,7
1011	vor	7,6,6
1012	bl	_vpaes_schedule_low_round
1013	vor	7,5,5
1014
1015	b	.Loop_schedule_256
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026.align	4
1027.Lschedule_mangle_last:
1028
1029	li	11, 0x2e0
1030	li	9,  0x2f0
1031	bne	1, .Lschedule_mangle_last_dec
1032
1033
1034	lvx	1, 8, 10
1035	li	11, 0x2c0
1036	li	9,  0x2d0
1037	vperm	0, 0, 0, 1
1038
1039	lvx	12, 11, 12
1040	lvx	13, 9, 12
1041	addi	5, 5, 16
1042	vxor	0, 0, 26
1043	bl	_vpaes_schedule_transform
1044
1045
1046	vperm	0, 0, 0, 29
1047	li	10, 4
1048	vsel	2, 28, 0, 30
1049	li	11, 8
1050	stvx	2, 0, 5
1051	li	12, 12
1052	stvewx	0, 0, 5
1053	stvewx	0, 10, 5
1054	stvewx	0, 11, 5
1055	stvewx	0, 12, 5
1056	b	.Lschedule_mangle_done
1057
1058.align	4
1059.Lschedule_mangle_last_dec:
1060	lvx	12, 11, 12
1061	lvx	13, 9,  12
1062	addi	5, 5, -16
1063	vxor	0, 0, 26
1064	bl	_vpaes_schedule_transform
1065
1066
1067	addi	9, 5, -15
1068	vperm	0, 0, 0, 29
1069	li	10, 4
1070	vsel	2, 28, 0, 30
1071	li	11, 8
1072	stvx	2, 0, 5
1073	li	12, 12
1074	stvewx	0, 0, 9
1075	stvewx	0, 10, 9
1076	stvewx	0, 11, 9
1077	stvewx	0, 12, 9
1078
1079
1080.Lschedule_mangle_done:
1081	mtlr	7
1082
1083	vxor	0, 0, 0
1084	vxor	1, 1, 1
1085	vxor	2, 2, 2
1086	vxor	3, 3, 3
1087	vxor	4, 4, 4
1088	vxor	5, 5, 5
1089	vxor	6, 6, 6
1090	vxor	7, 7, 7
1091
1092	blr
1093.long	0
1094.byte	0,12,0x14,0,0,0,0,0
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110.align	4
1111_vpaes_schedule_192_smear:
1112	vspltw	0, 7, 3-3
1113	vsldoi	1, 6, 9, 16-12
1114	vsldoi	0, 0, 7, 16-8
1115	vxor	6, 6, 1
1116	vxor	6, 6, 0
1117	vor	0,6,6
1118	vsldoi	6, 9, 6, 16-8
1119	vsldoi	6, 6, 9, 16-8
1120	blr
1121.long	0
1122.byte	0,12,0x14,0,0,0,0,0
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142.align	4
1143_vpaes_schedule_round:
1144
1145
1146	vsldoi	1, 9, 24, 16-15
1147	vsldoi	24, 24, 24, 16-15
1148	vxor	7, 7, 1
1149
1150
1151	vspltw	0, 0, 3-3
1152	vsldoi	0, 0, 0, 16-1
1153
1154
1155
1156
1157_vpaes_schedule_low_round:
1158
1159	vsldoi	1, 7, 9, 16-12
1160	vxor	7, 7, 1
1161	vspltisb	1, 0x0f
1162	vsldoi	4, 7, 9, 16-8
1163
1164
1165	vand	1, 1, 0
1166	vsrb	0, 0, 8
1167	vxor	7, 7, 4
1168	vperm	2, 11, 9, 1
1169	vxor	1, 1, 0
1170	vperm	3, 10, 9, 0
1171	vxor	3, 3, 2
1172	vperm	4, 10, 9, 1
1173	vxor	7, 7, 26
1174	vperm	3, 10, 9, 3
1175	vxor	4, 4, 2
1176	vperm	2, 10, 9, 4
1177	vxor	3, 3, 1
1178	vxor	2, 2, 0
1179	vperm	4, 15, 9, 3
1180	vperm	1, 14, 9, 2
1181	vxor	1, 1, 4
1182
1183
1184	vxor	0, 1, 7
1185	vxor	7, 1, 7
1186	blr
1187.long	0
1188.byte	0,12,0x14,0,0,0,0,0
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199.align	4
1200_vpaes_schedule_transform:
1201
1202	vsrb	2, 0, 8
1203
1204	vperm	0, 12, 12, 0
1205
1206	vperm	2, 13, 13, 2
1207	vxor	0, 0, 2
1208	blr
1209.long	0
1210.byte	0,12,0x14,0,0,0,0,0
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235.align	4
1236_vpaes_schedule_mangle:
1237
1238
1239	bne	1, .Lschedule_mangle_dec
1240
1241
1242	vxor	4, 0, 26
1243	addi	5, 5, 16
1244	vperm	4, 4, 4, 25
1245	vperm	1, 4, 4, 25
1246	vperm	3, 1, 1, 25
1247	vxor	4, 4, 1
1248	lvx	1, 8, 10
1249	vxor	3, 3, 4
1250
1251	vperm	3, 3, 3, 1
1252	addi	8, 8, -16
1253	andi.	8, 8, 0x30
1254
1255
1256	vperm	1, 3, 3, 29
1257	vsel	2, 28, 1, 30
1258	vor	28,1,1
1259	stvx	2, 0, 5
1260	blr
1261
1262.align	4
1263.Lschedule_mangle_dec:
1264
1265
1266	vsrb	1, 0, 8
1267
1268
1269
1270	vperm	2, 16, 16, 0
1271
1272	vperm	3, 17, 17, 1
1273	vxor	3, 3, 2
1274	vperm	3, 3, 9, 25
1275
1276
1277	vperm	2, 18, 18, 0
1278	vxor	2, 2, 3
1279
1280	vperm	3, 19, 19, 1
1281	vxor	3, 3, 2
1282	vperm	3, 3, 9, 25
1283
1284
1285	vperm	2, 20, 20, 0
1286	vxor	2, 2, 3
1287
1288	vperm	3, 21, 21, 1
1289	vxor	3, 3, 2
1290
1291
1292	vperm	2, 22, 22, 0
1293	vperm	3, 3, 9, 25
1294
1295	vperm	4, 23, 23, 1
1296	lvx	1, 8, 10
1297	vxor	2, 2, 3
1298	vxor	3, 4, 2
1299
1300	addi	5, 5, -16
1301
1302	vperm	3, 3, 3, 1
1303	addi	8, 8, -16
1304	andi.	8, 8, 0x30
1305
1306
1307	vperm	1, 3, 3, 29
1308	vsel	2, 28, 1, 30
1309	vor	28,1,1
1310	stvx	2, 0, 5
1311	blr
1312.long	0
1313.byte	0,12,0x14,0,0,0,0,0
1314
1315.globl	vpaes_set_encrypt_key
1316.type	vpaes_set_encrypt_key,@function
1317.align	5
1318vpaes_set_encrypt_key:
1319.localentry	vpaes_set_encrypt_key,0
1320
1321	stdu	1,-256(1)
1322	li	10,63
1323	li	11,79
1324	mflr	0
1325	li	6,-1
1326	stvx	20,10,1
1327	addi	10,10,32
1328	stvx	21,11,1
1329	addi	11,11,32
1330	stvx	22,10,1
1331	addi	10,10,32
1332	stvx	23,11,1
1333	addi	11,11,32
1334	stvx	24,10,1
1335	addi	10,10,32
1336	stvx	25,11,1
1337	addi	11,11,32
1338	stvx	26,10,1
1339	addi	10,10,32
1340	stvx	27,11,1
1341	addi	11,11,32
1342	stvx	28,10,1
1343	addi	10,10,32
1344	stvx	29,11,1
1345	addi	11,11,32
1346	stvx	30,10,1
1347	stvx	31,11,1
1348	stw	6,252(1)
1349	li	7, -1
1350	std	0, 272(1)
1351	or	7,7,7
1352
1353	srwi	9, 4, 5
1354	addi	9, 9, 6
1355	stw	9, 240(5)
1356
1357	cmplw	1,4,4
1358	li	8, 0x30
1359	bl	_vpaes_schedule_core
1360
1361	ld	0, 272(1)
1362	li	10,63
1363	li	11,79
1364	or	6,6,6
1365	mtlr	0
1366	xor	3, 3, 3
1367	lvx	20,10,1
1368	addi	10,10,32
1369	lvx	21,11,1
1370	addi	11,11,32
1371	lvx	22,10,1
1372	addi	10,10,32
1373	lvx	23,11,1
1374	addi	11,11,32
1375	lvx	24,10,1
1376	addi	10,10,32
1377	lvx	25,11,1
1378	addi	11,11,32
1379	lvx	26,10,1
1380	addi	10,10,32
1381	lvx	27,11,1
1382	addi	11,11,32
1383	lvx	28,10,1
1384	addi	10,10,32
1385	lvx	29,11,1
1386	addi	11,11,32
1387	lvx	30,10,1
1388	lvx	31,11,1
1389	addi	1,1,256
1390	blr
1391.long	0
1392.byte	0,12,0x04,1,0x80,0,3,0
1393.long	0
1394.size	vpaes_set_encrypt_key,.-vpaes_set_encrypt_key
1395
1396.globl	vpaes_set_decrypt_key
1397.type	vpaes_set_decrypt_key,@function
1398.align	4
1399vpaes_set_decrypt_key:
1400.localentry	vpaes_set_decrypt_key,0
1401
1402	stdu	1,-256(1)
1403	li	10,63
1404	li	11,79
1405	mflr	0
1406	li	6,-1
1407	stvx	20,10,1
1408	addi	10,10,32
1409	stvx	21,11,1
1410	addi	11,11,32
1411	stvx	22,10,1
1412	addi	10,10,32
1413	stvx	23,11,1
1414	addi	11,11,32
1415	stvx	24,10,1
1416	addi	10,10,32
1417	stvx	25,11,1
1418	addi	11,11,32
1419	stvx	26,10,1
1420	addi	10,10,32
1421	stvx	27,11,1
1422	addi	11,11,32
1423	stvx	28,10,1
1424	addi	10,10,32
1425	stvx	29,11,1
1426	addi	11,11,32
1427	stvx	30,10,1
1428	stvx	31,11,1
1429	stw	6,252(1)
1430	li	7, -1
1431	std	0, 272(1)
1432	or	7,7,7
1433
1434	srwi	9, 4, 5
1435	addi	9, 9, 6
1436	stw	9, 240(5)
1437
1438	slwi	9, 9, 4
1439	add	5, 5, 9
1440
1441	cmplwi	1, 4, 0
1442	srwi	8, 4, 1
1443	andi.	8, 8, 32
1444	xori	8, 8, 32
1445	bl	_vpaes_schedule_core
1446
1447	ld	0,  272(1)
1448	li	10,63
1449	li	11,79
1450	or	6,6,6
1451	mtlr	0
1452	xor	3, 3, 3
1453	lvx	20,10,1
1454	addi	10,10,32
1455	lvx	21,11,1
1456	addi	11,11,32
1457	lvx	22,10,1
1458	addi	10,10,32
1459	lvx	23,11,1
1460	addi	11,11,32
1461	lvx	24,10,1
1462	addi	10,10,32
1463	lvx	25,11,1
1464	addi	11,11,32
1465	lvx	26,10,1
1466	addi	10,10,32
1467	lvx	27,11,1
1468	addi	11,11,32
1469	lvx	28,10,1
1470	addi	10,10,32
1471	lvx	29,11,1
1472	addi	11,11,32
1473	lvx	30,10,1
1474	lvx	31,11,1
1475	addi	1,1,256
1476	blr
1477.long	0
1478.byte	0,12,0x04,1,0x80,0,3,0
1479.long	0
1480.size	vpaes_set_decrypt_key,.-vpaes_set_decrypt_key
1481