# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.


# vs0 - vs15              : buffer for xor
# vs32 - vs47 (v0 - v15)  : 4 "converted" states
# vs48 - vs51 (v16 - v19) : original state
# vs52 - vs55 (v20 - v23) : "converted" constants
# vs56 (v24)              : "converted" counter
# vs57 (v25)              : increment for "converted" counter
# vs60 - vs63 (v28 - v31) : constants for rotate left or vpermxor

#define r0	0
#define sp	1
#define r2	2
#define rSIZE	3
#define rDST	4
#define rSRC	5
#define rKEY	6
#define rNONCE	7
#define rCNTR	8
#define r9	9
#define r10	10
#define r11	11
#define r12	12
#define r13	13
#define r14	14
#define r15	15
#define r16	16
#define r17	17
#define r18	18
#define r19	19
#define r20	20
#define r21	21
#define r22	22
#define r23	23
#define r24	24
#define r25	25
#define r26	26
#define r27	27
#define r28	28
#define r29	29
#define r30	30
#define r31	31

#define v0	0
#define v1	1
#define v2	2
#define v3	3
#define v4	4
#define v5	5
#define v6	6
#define v7	7
#define v8	8
#define v9	9
#define v10	10
#define v11	11
#define v12	12
#define v13	13
#define v14	14
#define v15	15
#define v16	16
#define v17	17
#define v18	18
#define v19	19
#define v20	20
#define v21	21
#define v22	22
#define v23	23
#define v24	24
#define v25	25
#define v26	26
#define v27	27
#define v28	28
#define v29	29
#define v30	30
#define v31	31

#define vs0	0
#define vs1	1
#define vs2	2
#define vs3	3
#define vs4	4
#define vs5	5
#define vs6	6
#define vs7	7
#define vs8	8
#define vs9	9
#define vs10	10
#define vs11	11
#define vs12	12
#define vs13	13
#define vs14	14
#define vs15	15
#define vs16	16
#define vs17	17
#define vs18	18
#define vs19	19
#define vs20	20
#define vs21	21
#define vs22	22
#define vs23	23
#define vs24	24
#define vs25	25
#define vs26	26
#define vs27	27
#define vs28	28
#define vs29	29
#define vs30	30
#define vs31	31
#define vs32	32
#define vs33	33
#define vs34	34
#define vs35	35
#define vs36	36
#define vs37	37
#define vs38	38
#define vs39	39
#define vs40	40
#define vs41	41
#define vs42	42
#define vs43	43
#define vs44	44
#define vs45	45
#define vs46	46
#define vs47	47
#define vs48	48
#define vs49	49
#define vs50	50
#define vs51	51
#define vs52	52
#define vs53	53
#define vs54	54
#define vs55	55
#define vs56	56
#define vs57	57
#define vs58	58
#define vs59	59
#define vs60	60
#define vs61	61
#define vs62	62
#define vs63	63

.abiversion 2
.section ".data"
.align 5
lblock:	.skip 256
cnts0:	.long 0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
cnts1:	.long 0x61707865, 0x61707865, 0x61707865, 0x61707865
cnts2:	.long 0x3320646e, 0x3320646e, 0x3320646e, 0x3320646e
cnts3:	.long 0x79622d32, 0x79622d32, 0x79622d32, 0x79622d32
cnts4:	.long 0x6b206574, 0x6b206574, 0x6b206574, 0x6b206574
st4:	.long 0, 0, 0, 0
cntr:	.long 0, 0, 0, 0
incr:	.long 4, 4, 4, 4
rotl1:	.long 0x22330011, 0x66774455, 0xAABB8899, 0xEEFFCCDD
rotl2:	.long 12, 12, 12, 12
rotl3:	.long 0x11223300, 0x55667744, 0x99AABB88, 0xDDEEFFCC
rotl4:	.long 7, 7, 7, 7

.section ".text"
.align 5
.globl chacha20vsx
.type chacha20vsx, @function
chacha20vsx:
	# prologue
	addis	2, r12, .TOC.-chacha20vsx@ha
	addi	2, 2, .TOC.-chacha20vsx@l
	.localentry	chacha20vsx, .-chacha20vsx
	std	r14, -8(sp)
	std	r15, -16(sp)
	std	r16, -24(sp)
	std	r17, -32(sp)
	std	r18, -40(sp)
	std	r19, -48(sp)
	std	r20, -56(sp)
	std	r21, -64(sp)
	std	r22, -72(sp)
	std	r23, -80(sp)
	std	r24, -88(sp)
	std	r25, -96(sp)
	std	r26, -104(sp)
	std	r27, -112(sp)
	std	r28, -120(sp)
	std	r29, -128(sp)
	std	r30, -136(sp)
	std	r31, -144(sp)

	addi	r14, sp, -160

	li	r16, -16
	li	r17, -32
	li	r18, -48
	li	r19, -64
	li	r20, -80
	li	r21, -96
	li	r22, -112
	li	r23, -128
	li	r24, -144
	li	r25, -160
	li	r26, -176
	li	r27, -192
	li	r28, -208

	# save f14, f15
	stxvw4x	vs14, 0, r14
	stxvw4x	vs15, r16, r14

	# save v20 - v31
	stxvw4x	vs52, r17, r14
	stxvw4x	vs53, r18, r14
	stxvw4x	vs54, r19, r14
	stxvw4x	vs55, r20, r14
	stxvw4x	vs56, r21, r14
	stxvw4x	vs57, r22, r14
	stxvw4x	vs58, r23, r14
	stxvw4x	vs59, r24, r14
	stxvw4x	vs60, r25, r14
	stxvw4x	vs61, r26, r14
	stxvw4x	vs62, r27, r14
	stxvw4x	vs63, r28, r14

	# offset in src/dst
	li	r17, 16
	li	r18, 32
	li	r19, 48
	li	r20, 64
	li	r21, 80
	li	r22, 96
	li	r23, 112
	li	r24, 128
	li	r25, 144
	li	r26, 160
	li	r27, 176
	li	r28, 192
	li	r29, 208
	li	r30, 224
	li	r31, 240

	# load const's address
	addis	r14, 2, cnts0@toc@ha
	addi	r14, r14, cnts0@toc@l

	# save nonce to st4
	lwz	r15, 0(rNONCE)
	stw	r15, 84(r14)
	lwz	r15, 4(rNONCE)
	stw	r15, 88(r14)
	lwz	r15, 8(rNONCE)
	stw	r15, 92(r14)

	# load state to vectors
	lxvw4x	vs48, 0, r14
	lxvw4x	vs49, 0, rKEY
	lxvw4x	vs50, r17, rKEY
	lxvw4x	vs51, r21, r14

	# load consts for x4 rounds
	lxvw4x	vs52, r17, r14
	lxvw4x	vs53, r18, r14
	lxvw4x	vs54, r19, r14
	lxvw4x	vs55, r20, r14

	# counter
	stw	rCNTR, 96(r14)
	addi	rCNTR, rCNTR, 1
	stw	rCNTR, 100(r14)
	addi	rCNTR, rCNTR, 1
	stw	rCNTR, 104(r14)
	addi	rCNTR, rCNTR, 1
	stw	rCNTR, 108(r14)
	lxvw4x	vs56, r22, r14

	# load increment
	lxvw4x	vs57, r23, r14

	# load rotl to vectors
	lxvw4x	vs60, r24, r14
	lxvw4x	vs61, r25, r14
	lxvw4x	vs62, r26, r14
	lxvw4x	vs63, r27, r14

	# counter for loop = size/256
	li	r15, 256
	divdu.	r16, rSIZE, r15
	beq	lastblock
	mtctr	r16

mainloop:
	# init 16 vectors (4 states x4)
	vor	v0, v20, v20
	vor	v1, v21, v21
	vor	v2, v22, v22
	vor	v3, v23, v23
	vspltw	v4, v17, v0
	vspltw	v5, v17, v1
	vspltw	v6, v17, v2
	vspltw	v7, v17, v3
	vspltw	v8, v18, v0
	vspltw	v9, v18, v1
	vspltw	v10, v18, v2
	vspltw	v11, v18, v3
	vor	v12, v24, v24
	vspltw	v13, v19, v1
	vspltw	v14, v19, v2
	vspltw	v15, v19, v3

.macro _plus a b_y b_x
	vadduwm	\a,   \a,   \b_y*4+(\b_x)%4
	vadduwm	\a+1, \a+1, \b_y*4+(\b_x+1)%4
	vadduwm	\a+2, \a+2, \b_y*4+(\b_x+2)%4
	vadduwm	\a+3, \a+3, \b_y*4+(\b_x+3)%4
.endm

.macro _xor a b_y b_x
	vxor	\a,   \a,   \b_y*4+(\b_x)%4
	vxor	\a+1, \a+1, \b_y*4+(\b_x+1)%4
	vxor	\a+2, \a+2, \b_y*4+(\b_x+2)%4
	vxor	\a+3, \a+3, \b_y*4+(\b_x+3)%4
.endm

.macro _rotl a b
	vrlw	\a,   \a,   \b
	vrlw	\a+1, \a+1, \b
	vrlw	\a+2, \a+2, \b
	vrlw	\a+3, \a+3, \b
.endm

.macro _pxor a b_y b_x c
	vpermxor	\a,   \a,   \b_y*4+(\b_x)%4,   \c
	vpermxor	\a+1, \a+1, \b_y*4+(\b_x+1)%4, \c
	vpermxor	\a+2, \a+2, \b_y*4+(\b_x+2)%4, \c
	vpermxor	\a+3, \a+3, \b_y*4+(\b_x+3)%4, \c
.endm

#  00  01  02  03
#  04  05  06  07
#  08  09  10  11
#  12  13  14  15
.macro doubleround
	# column round
	_plus	v0,  v1, v0       # a+=b
	_pxor	v12, v0, v0, v28  # d^=a; d<<<=16
	_plus	v8,  v3, v0       # c+=d
	_xor	v4,  v2, v0       # b^=c
	_rotl	v4,  v29          # b<<<=12
	_plus	v0,  v1, v0       # a+=b
	_pxor	v12, v0, v0, v30  # d^=a; d<<<=8
	_plus	v8,  v3, v0       # c+=d
	_xor	v4,  v2, v0       # b^=c
	_rotl	v4,  v31          # b<<<=7

	# diagonal round
	_plus	v0,  v1, v1       # a+=b
	_pxor	v12, v0, v1, v28  # d^=a; d<<<=16
	_plus	v8,  v3, v1       # c+=d
	_xor	v4,  v2, v1       # b^=c
	_rotl	v4,  v29          # b<<<=12
	_plus	v0,  v1, v1       # a+=b
	_pxor	v12, v0, v1, v30  # d^=a; d<<<=8
	_plus	v8,  v3, v1       # c+=d
	_xor	v4,  v2, v1       # b^=c
	_rotl	v4,  v31          # b<<<=7
.endm

	doubleround # 1
	doubleround # 2
	doubleround # 3
	doubleround # 4
	doubleround # 5
	doubleround # 6
	doubleround # 7
	doubleround # 8
	doubleround # 9
	doubleround # 10

	# counter += original counter
	vadduwm	v12, v12, v24

.macro convert a
	vmrgew	26, 0+\a, 1+\a
	vmrgew	27, 2+\a, 3+\a
	vmrgow	0+\a, 0+\a, 1+\a
	vmrgow	2+\a, 2+\a, 3+\a
	xxmrghd	33+\a, 32+\a, 34+\a
	xxmrgld	35+\a, 32+\a, 34+\a
	xxmrghd	32+\a, 58, 59
	xxmrgld	34+\a, 58, 59
.endm

	convert 0
	convert 4
	convert 8
	convert 12

.macro addition a
	vadduwm	0+\a, 0+\a, 16
	vadduwm	4+\a, 4+\a, 17
	vadduwm	8+\a, 8+\a, 18
	vadduwm	12+\a, 12+\a, 19
.endm

	addition 0
	addition 1
	addition 2
	addition 3

	# load text/cipher
	lxvw4x	vs0, 0, rSRC
	lxvw4x	vs1, r17, rSRC
	lxvw4x	vs2, r18, rSRC
	lxvw4x	vs3, r19, rSRC
	lxvw4x	vs4, r20, rSRC
	lxvw4x	vs5, r21, rSRC
	lxvw4x	vs6, r22, rSRC
	lxvw4x	vs7, r23, rSRC
	lxvw4x	vs8, r24, rSRC
	lxvw4x	vs9, r25, rSRC
	lxvw4x	vs10, r26, rSRC
	lxvw4x	vs11, r27, rSRC
	lxvw4x	vs12, r28, rSRC
	lxvw4x	vs13, r29, rSRC
	lxvw4x	vs14, r30, rSRC
	lxvw4x	vs15, r31, rSRC
	# xor (encrypt/decrypt)
	xxlxor	vs0, vs0, vs32
	xxlxor	vs1, vs1, vs36
	xxlxor	vs2, vs2, vs40
	xxlxor	vs3, vs3, vs44
	xxlxor	vs4, vs4, vs33
	xxlxor	vs5, vs5, vs37
	xxlxor	vs6, vs6, vs41
	xxlxor	vs7, vs7, vs45
	xxlxor	vs8, vs8, vs34
	xxlxor	vs9, vs9, vs38
	xxlxor	vs10, vs10, vs42
	xxlxor	vs11, vs11, vs46
	xxlxor	vs12, vs12, vs35
	xxlxor	vs13, vs13, vs39
	xxlxor	vs14, vs14, vs43
	xxlxor	vs15, vs15, vs47
	# store cipher/text
	stxvw4x	vs0, 0, rDST
	stxvw4x	vs1, r17, rDST
	stxvw4x	vs2, r18, rDST
	stxvw4x	vs3, r19, rDST
	stxvw4x	vs4, r20, rDST
	stxvw4x	vs5, r21, rDST
	stxvw4x	vs6, r22, rDST
	stxvw4x	vs7, r23, rDST
	stxvw4x	vs8, r24, rDST
	stxvw4x	vs9, r25, rDST
	stxvw4x	vs10, r26, rDST
	stxvw4x	vs11, r27, rDST
	stxvw4x	vs12, r28, rDST
	stxvw4x	vs13, r29, rDST
	stxvw4x	vs14, r30, rDST
	stxvw4x	vs15, r31, rDST

	# src/dst increment
	addi	rSRC, rSRC, 256
	addi	rDST, rDST, 256

	# counter increment
	vadduwm	v24, v24, v25

	bdnz	mainloop

lastblock:
	# reminder
	mulld	r16, r16, r15
	subf.	r16, r16, rSIZE

	# check reminder
	beq	exitsub

	addi	r14, r14, -256
	# last block x4
	# init 16 vectors (4 states x4)
	vor	v0, v20, v20
	vor	v1, v21, v21
	vor	v2, v22, v22
	vor	v3, v23, v23
	vspltw	v4, v17, v0
	vspltw	v5, v17, v1
	vspltw	v6, v17, v2
	vspltw	v7, v17, v3
	vspltw	v8, v18, v0
	vspltw	v9, v18, v1
	vspltw	v10, v18, v2
	vspltw	v11, v18, v3
	vor	v12, v24, v24
	vspltw	v13, v19, v1
	vspltw	v14, v19, v2
	vspltw	v15, v19, v3

	doubleround # 1
	doubleround # 2
	doubleround # 3
	doubleround # 4
	doubleround # 5
	doubleround # 6
	doubleround # 7
	doubleround # 8
	doubleround # 9
	doubleround # 10

	vadduwm	v12, v12, v24

	convert 0
	convert 4
	convert 8
	convert 12

	addition 0
	addition 1
	addition 2
	addition 3

	# store vectors
	stxvw4x	vs32, 0, r14
	stxvw4x	vs36, r17, r14
	stxvw4x	vs40, r18, r14
	stxvw4x	vs44, r19, r14
	stxvw4x	vs33, r20, r14
	stxvw4x	vs37, r21, r14
	stxvw4x	vs41, r22, r14
	stxvw4x	vs45, r23, r14
	stxvw4x	vs34, r24, r14
	stxvw4x	vs38, r25, r14
	stxvw4x	vs42, r26, r14
	stxvw4x	vs46, r27, r14
	stxvw4x	vs35, r28, r14
	stxvw4x	vs39, r29, r14
	stxvw4x	vs43, r30, r14
	stxvw4x	vs47, r31, r14

	mtctr	r16
	addi	rSIZE, r14, -1
	addi	rSRC, rSRC, -1
	addi	rDST, rDST, -1
xorlast:
	lbzu	r15, 1(rSIZE)
	lbzu	r16, 1(rSRC)
	xor	r15, r15, r16
	stbu	r15, 1(rDST)
	bdnz	xorlast

	# zeroing last block
	xxlxor	vs0, vs0, vs0
	stxvw4x	vs0, 0, r14
	stxvw4x	vs0, r17, r14
	stxvw4x	vs0, r18, r14
	stxvw4x	vs0, r19, r14
	stxvw4x	vs0, r20, r14
	stxvw4x	vs0, r21, r14
	stxvw4x	vs0, r22, r14
	stxvw4x	vs0, r23, r14
	stxvw4x	vs0, r24, r14
	stxvw4x	vs0, r25, r14
	stxvw4x	vs0, r26, r14
	stxvw4x	vs0, r27, r14
	stxvw4x	vs0, r28, r14
	stxvw4x	vs0, r29, r14
	stxvw4x	vs0, r30, r14
	stxvw4x	vs0, r31, r14

exitsub:
	# zeroing volatile registers
	xxlxor	vs0, vs0, vs0
	xxlxor	vs1, vs1, vs1
	xxlxor	vs2, vs2, vs2
	xxlxor	vs3, vs3, vs3
	xxlxor	vs4, vs4, vs4
	xxlxor	vs5, vs5, vs5
	xxlxor	vs6, vs6, vs6
	xxlxor	vs7, vs7, vs7
	xxlxor	vs8, vs8, vs8
	xxlxor	vs9, vs9, vs9
	xxlxor	vs10, vs10, vs10
	xxlxor	vs11, vs11, vs11
	xxlxor	vs12, vs12, vs12
	xxlxor	vs13, vs13, vs13

	xxlxor	vs32, vs32, vs32
	xxlxor	vs33, vs33, vs33
	xxlxor	vs34, vs34, vs34
	xxlxor	vs35, vs35, vs35
	xxlxor	vs36, vs36, vs36
	xxlxor	vs37, vs37, vs37
	xxlxor	vs38, vs38, vs38
	xxlxor	vs39, vs39, vs39
	xxlxor	vs40, vs40, vs40
	xxlxor	vs41, vs41, vs41
	xxlxor	vs42, vs42, vs42
	xxlxor	vs43, vs43, vs43
	xxlxor	vs44, vs44, vs44
	xxlxor	vs45, vs45, vs45
	xxlxor	vs46, vs46, vs46
	xxlxor	vs47, vs47, vs47
	xxlxor	vs48, vs48, vs48
	xxlxor	vs49, vs49, vs49
	xxlxor	vs50, vs50, vs50
	xxlxor	vs51, vs51, vs51

	li	rSIZE, 0
	li	rDST, 0
	li	rSRC, 0
	li	rKEY, 0
	li	rNONCE, 0
	li	rCNTR, 0

	# epilogue
	addi	r14, sp, -160

	li	r16, -16
	li	r17, -32
	li	r18, -48
	li	r19, -64
	li	r20, -80
	li	r21, -96
	li	r22, -112
	li	r23, -128
	li	r24, -144
	li	r25, -160
	li	r26, -176
	li	r27, -192
	li	r28, -208

	# load f14, f15
	lxvw4x	vs14, 0, r14
	lxvw4x	vs15, r16, r14

	# load v20 - v31
	lxvw4x	vs52, r17, r14
	lxvw4x	vs53, r18, r14
	lxvw4x	vs54, r19, r14
	lxvw4x	vs55, r20, r14
	lxvw4x	vs56, r21, r14
	lxvw4x	vs57, r22, r14
	lxvw4x	vs58, r23, r14
	lxvw4x	vs59, r24, r14
	lxvw4x	vs60, r25, r14
	lxvw4x	vs61, r26, r14
	lxvw4x	vs62, r27, r14
	lxvw4x	vs63, r28, r14

	ld	r14, -8(sp)
	ld	r15, -16(sp)
	ld	r16, -24(sp)
	ld	r17, -32(sp)
	ld	r18, -40(sp)
	ld	r19, -48(sp)
	ld	r20, -56(sp)
	ld	r21, -64(sp)
	ld	r22, -72(sp)
	ld	r23, -80(sp)
	ld	r24, -88(sp)
	ld	r25, -96(sp)
	ld	r26, -104(sp)
	ld	r27, -112(sp)
	ld	r28, -120(sp)
	ld	r29, -128(sp)
	ld	r30, -136(sp)
	ld	r31, -144(sp)

	blr