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

1 /* SPDX-License-Identifier: GPL-2.0-or-later */
5 # Copyright 2023- IBM Corp. All rights reserved
43 #include <asm/asm-offsets.h>
44 #include <asm/asm-compat.h>
81 	stdu 1,-752(1)
83 	SAVE_GPR 14, 112, 1
116 	SAVE_VSX 14, 192, 9
151 	RESTORE_VSX 14, 192, 9
170 	RESTORE_GPR 14, 112, 1
209 	  vpermxor 14, 14, 2, 25
218 	vadduwm 10, 10, 14
226 	vxor 6, 6, 10
257 	  vpermxor 14, 14, 2, 25
266 	vadduwm 10, 10, 14
276 	vxor 6, 6, 10
307 	  vpermxor 14, 14, 3, 25
314 	vadduwm 10, 10, 15
317 	vadduwm 9, 9, 14
322 	vxor 5, 5, 10
357 	  vpermxor 14, 14, 3, 25
364 	vadduwm 10, 10, 15
367 	vadduwm 9, 9, 14
375 	vxor 5, 5, 10
402 	  vpermxor 14, 14, 2, 20
406 	vadduwm 10, 10, 14
410 	vxor 6, 6, 10
422 	  vpermxor 14, 14, 2, 22
426 	vadduwm 10, 10, 14
430 	vxor 6, 6, 10
445 	  vpermxor 14, 14, 3, 20
446 	vadduwm 10, 10, 15
449 	vadduwm 9, 9, 14
450 	vxor 5, 5, 10
465 	  vpermxor 14, 14, 3, 22
466 	vadduwm 10, 10, 15
469 	vadduwm 9, 9, 14
470 	vxor 5, 5, 10
482 	xxmrghw  10, 32+\a0, 32+\a1	# a0, a1, b0, b1
486 	xxpermdi	32+\a0, 10, 11, 0	# a0, a1, a2, a3
487 	xxpermdi	32+\a1, 10, 11, 3	# b0, b1, b2, b3
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
520 	add 16, 14, 4
531 	lxvw4x 10, 26, 9
535 	lxvw4x 14, 30, 9
548 	xxlxor \S+42, \S+42, 10
552 	xxlxor \S+43, \S+43, 14
587 	# r17 - r31 mainly for Write_256 macro.
605 	li 14, 0			# offset to inp and outp
669 	xxspltw  32+10, 18, 2
673 	xxspltw  32+14, 19, 2
708 	TP_4x 8, 9, 10, 11
709 	TP_4x 12, 13, 14, 15
725 	addi	14, 14, 256	# offset +=256
726 	addi	15, 15, -256	# len -=256
734 	TP_4x 16+8, 16+9, 16+10, 16+11
735 	TP_4x 16+12, 16+13, 16+14, 16+15
743 	addi	14, 14, 256	# offset +=256
744 	addi	15, 15, -256	# len +=256
791 	vspltw  10, 18, 2
796 	vspltw  14, 19, 2
808 	TP_4x 8, 9, 10, 11
809 	TP_4x 12, 13, 14, 15
813 	addi	14, 14, 256	# offset += 256
814 	addi	15, 15, -256	# len += 256