powerpc/crypto/chacha-p10le-8x.S

1 /* SPDX-License-Identifier: GPL-2.0-or-later */
5 # Copyright 2023- IBM Corp. All rights reserved
13 # do rounds,  8 quarter rounds
16 # 3.  a += b; d ^= a; d <<<= 8;
21 # row1 = (row1 + row2), row4 = row1 xor row4,  row4 rotate each word by 8
43 #include <asm/asm-offsets.h>
44 #include <asm/asm-compat.h>
81 	stdu 1,-752(1)
199 	vadduwm 1, 1, 5
216 	vadduwm 8, 8, 12
224 	vxor 4, 4, 8
225 	vxor 5, 5, 9
236 	vrlw 5, 5, 25
245 	vadduwm 1, 1, 5
264 	vadduwm 8, 8, 12
274 	vxor 4, 4, 8
275 	vxor 5, 5, 9
283 	vrlw 5, 5, 28
295 	vadduwm 0, 0, 5
316 	vadduwm 8, 8, 13
322 	vxor 5, 5, 10
324 	vxor 7, 7, 8
333 	vrlw 5, 5, 25
343 	vadduwm 0, 0, 5
366 	vadduwm 8, 8, 13
375 	vxor 5, 5, 10
377 	vxor 7, 7, 8
383 	vrlw 5, 5, 28
397 	vadduwm 1, 1, 5
404 	vadduwm 8, 8, 12
408 	vxor 4, 4, 8
409 	vxor 5, 5, 9
413 	vrlw 5, 5, 21
417 	vadduwm 1, 1, 5
424 	vadduwm 8, 8, 12
428 	vxor 4, 4, 8
429 	vxor 5, 5, 9
433 	vrlw 5, 5, 23
438 	vadduwm 0, 0, 5
448 	vadduwm 8, 8, 13
450 	vxor 5, 5, 10
452 	vxor 7, 7, 8
454 	vrlw 5, 5, 21
458 	vadduwm 0, 0, 5
468 	vadduwm 8, 8, 13
470 	vxor 5, 5, 10
472 	vxor 7, 7, 8
474 	vrlw 5, 5, 23
494 	vadduwm \S+0, \S+0, 16-\S
495 	vadduwm \S+4, \S+4, 17-\S
496 	vadduwm \S+8, \S+8, 18-\S
497 	vadduwm \S+12, \S+12, 19-\S
499 	vadduwm \S+1, \S+1, 16-\S
500 	vadduwm \S+5, \S+5, 17-\S
501 	vadduwm \S+9, \S+9, 18-\S
502 	vadduwm \S+13, \S+13, 19-\S
504 	vadduwm \S+2, \S+2, 16-\S
505 	vadduwm \S+6, \S+6, 17-\S
506 	vadduwm \S+10, \S+10, 18-\S
507 	vadduwm \S+14, \S+14, 19-\S
509 	vadduwm	\S+3, \S+3, 16-\S
510 	vadduwm	\S+7, \S+7, 17-\S
511 	vadduwm	\S+11, \S+11, 18-\S
512 	vadduwm	\S+15, \S+15, 19-\S
519 	add 9, 14, 5
526 	lxvw4x 5, 21, 9
529 	lxvw4x 8, 24, 9
543 	xxlxor \S+37, \S+37, 5
546 	xxlxor \S+34, \S+34, 8
581 .align 5
587 	# r17 - r31 mainly for Write_256 macro.
618 	vmrglw	5, 2, 3
619 	vsldoi	30, 4, 5, 8		# vr30 counter, 4 (0, 1, 2, 3)
629 	sradi	8, 7, 1
631 	mtctr 8
640 	vspltisw 26, 8
664 	xxspltw  32+5, 17, 1
667 	xxspltw  32+8, 18, 0
696 .align 5
707 	TP_4x 4, 5, 6, 7
708 	TP_4x 8, 9, 10, 11
726 	addi	15, 15, -256	# len -=256
728 	xxlor	5, 32+31, 32+31
731 	xxlor	32+31, 5, 5
733 	TP_4x 16+4, 16+5, 16+6, 16+7
734 	TP_4x 16+8, 16+9, 16+10, 16+11
744 	addi	15, 15, -256	# len +=256
760 	mtctr 8
776 	sradi	8, 7, 1
777 	mtctr 8
786 	vspltw  5, 17, 1
789 	vspltw  8, 18, 0
799 .align 5
807 	TP_4x 4, 5, 6, 7
808 	TP_4x 8, 9, 10, 11
814 	addi	15, 15, -256	# len += 256
825 	mtctr 8
838 .align 5