1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) 2012 Intel Corporation
4 * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
5 */
6
7#include <arm_neon.h>
8
9#ifdef CONFIG_ARM
10/*
11 * AArch32 does not provide this intrinsic natively because it does not
12 * implement the underlying instruction. AArch32 only provides a 64-bit
13 * wide vtbl.8 instruction, so use that instead.
14 */
15static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
16{
17	union {
18		uint8x16_t	val;
19		uint8x8x2_t	pair;
20	} __a = { a };
21
22	return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
23			   vtbl2_u8(__a.pair, vget_high_u8(b)));
24}
25#endif
26
27void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
28			      uint8_t *dq, const uint8_t *pbmul,
29			      const uint8_t *qmul)
30{
31	uint8x16_t pm0 = vld1q_u8(pbmul);
32	uint8x16_t pm1 = vld1q_u8(pbmul + 16);
33	uint8x16_t qm0 = vld1q_u8(qmul);
34	uint8x16_t qm1 = vld1q_u8(qmul + 16);
35	uint8x16_t x0f = vdupq_n_u8(0x0f);
36
37	/*
38	 * while ( bytes-- ) {
39	 *	uint8_t px, qx, db;
40	 *
41	 *	px    = *p ^ *dp;
42	 *	qx    = qmul[*q ^ *dq];
43	 *	*dq++ = db = pbmul[px] ^ qx;
44	 *	*dp++ = db ^ px;
45	 *	p++; q++;
46	 * }
47	 */
48
49	while (bytes) {
50		uint8x16_t vx, vy, px, qx, db;
51
52		px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
53		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
54
55		vy = vshrq_n_u8(vx, 4);
56		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
57		vy = vqtbl1q_u8(qm1, vy);
58		qx = veorq_u8(vx, vy);
59
60		vy = vshrq_n_u8(px, 4);
61		vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
62		vy = vqtbl1q_u8(pm1, vy);
63		vx = veorq_u8(vx, vy);
64		db = veorq_u8(vx, qx);
65
66		vst1q_u8(dq, db);
67		vst1q_u8(dp, veorq_u8(db, px));
68
69		bytes -= 16;
70		p += 16;
71		q += 16;
72		dp += 16;
73		dq += 16;
74	}
75}
76
77void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
78			      const uint8_t *qmul)
79{
80	uint8x16_t qm0 = vld1q_u8(qmul);
81	uint8x16_t qm1 = vld1q_u8(qmul + 16);
82	uint8x16_t x0f = vdupq_n_u8(0x0f);
83
84	/*
85	 * while (bytes--) {
86	 *	*p++ ^= *dq = qmul[*q ^ *dq];
87	 *	q++; dq++;
88	 * }
89	 */
90
91	while (bytes) {
92		uint8x16_t vx, vy;
93
94		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
95
96		vy = vshrq_n_u8(vx, 4);
97		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
98		vy = vqtbl1q_u8(qm1, vy);
99		vx = veorq_u8(vx, vy);
100		vy = veorq_u8(vx, vld1q_u8(p));
101
102		vst1q_u8(dq, vx);
103		vst1q_u8(p, vy);
104
105		bytes -= 16;
106		p += 16;
107		q += 16;
108		dq += 16;
109	}
110}
111