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
200 	vadduwm 2, 2, 6
209 	  vpermxor 14, 14, 2, 25
218 	vadduwm 10, 10, 14
226 	vxor 6, 6, 10
237 	vrlw 6, 6, 25
246 	vadduwm 2, 2, 6
257 	  vpermxor 14, 14, 2, 25
266 	vadduwm 10, 10, 14
276 	vxor 6, 6, 10
284 	vrlw 6, 6, 28
296 	vadduwm 1, 1, 6
307 	  vpermxor 14, 14, 3, 25
317 	vadduwm 9, 9, 14
323 	vxor 6, 6, 11
334 	vrlw 6, 6, 25
344 	vadduwm 1, 1, 6
357 	  vpermxor 14, 14, 3, 25
367 	vadduwm 9, 9, 14
376 	vxor 6, 6, 11
384 	vrlw 6, 6, 28
398 	vadduwm 2, 2, 6
402 	  vpermxor 14, 14, 2, 20
406 	vadduwm 10, 10, 14
410 	vxor 6, 6, 10
414 	vrlw 6, 6, 21
418 	vadduwm 2, 2, 6
422 	  vpermxor 14, 14, 2, 22
426 	vadduwm 10, 10, 14
430 	vxor 6, 6, 10
434 	vrlw 6, 6, 23
439 	vadduwm 1, 1, 6
445 	  vpermxor 14, 14, 3, 20
449 	vadduwm 9, 9, 14
451 	vxor 6, 6, 11
455 	vrlw 6, 6, 21
459 	vadduwm 1, 1, 6
465 	  vpermxor 14, 14, 3, 22
469 	vadduwm 9, 9, 14
471 	vxor 6, 6, 11
475 	vrlw 6, 6, 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
520 	add 16, 14, 4
527 	lxvw4x 6, 22, 9
535 	lxvw4x 14, 30, 9
544 	xxlxor \S+41, \S+41, 6
552 	xxlxor \S+43, \S+43, 14
582 	cmpdi	6, 0
587 	# r17 - r31 mainly for Write_256 macro.
604 	mr 15, 6			# len
605 	li 14, 0			# offset to inp and outp
654 	cmpdi	6, 512
665 	xxspltw  32+6, 17, 2
673 	xxspltw  32+14, 19, 2
707 	TP_4x 4, 5, 6, 7
709 	TP_4x 12, 13, 14, 15
725 	addi	14, 14, 256	# offset +=256
726 	addi	15, 15, -256	# len -=256
733 	TP_4x 16+4, 16+5, 16+6, 16+7
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
787 	vspltw  6, 17, 2
796 	vspltw  14, 19, 2
807 	TP_4x 4, 5, 6, 7
809 	TP_4x 12, 13, 14, 15
813 	addi	14, 14, 256	# offset += 256
814 	addi	15, 15, -256	# len += 256