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#include "neon.h"
9
10#ifdef CONFIG_ARM
11/*
12 * AArch32 does not provide this intrinsic natively because it does not
13 * implement the underlying instruction. AArch32 only provides a 64-bit
14 * wide vtbl.8 instruction, so use that instead.
15 */
16static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
17{
18	union {
19		uint8x16_t	val;
20		uint8x8x2_t	pair;
21	} __a = { a };
22
23	return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
24			   vtbl2_u8(__a.pair, vget_high_u8(b)));
25}
26#endif
27
28void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
29			      uint8_t *dq, const uint8_t *pbmul,
30			      const uint8_t *qmul)
31{
32	uint8x16_t pm0 = vld1q_u8(pbmul);
33	uint8x16_t pm1 = vld1q_u8(pbmul + 16);
34	uint8x16_t qm0 = vld1q_u8(qmul);
35	uint8x16_t qm1 = vld1q_u8(qmul + 16);
36	uint8x16_t x0f = vdupq_n_u8(0x0f);
37
38	/*
39	 * while ( bytes-- ) {
40	 *	uint8_t px, qx, db;
41	 *
42	 *	px    = *p ^ *dp;
43	 *	qx    = qmul[*q ^ *dq];
44	 *	*dq++ = db = pbmul[px] ^ qx;
45	 *	*dp++ = db ^ px;
46	 *	p++; q++;
47	 * }
48	 */
49
50	while (bytes) {
51		uint8x16_t vx, vy, px, qx, db;
52
53		px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
54		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
55
56		vy = vshrq_n_u8(vx, 4);
57		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
58		vy = vqtbl1q_u8(qm1, vy);
59		qx = veorq_u8(vx, vy);
60
61		vy = vshrq_n_u8(px, 4);
62		vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
63		vy = vqtbl1q_u8(pm1, vy);
64		vx = veorq_u8(vx, vy);
65		db = veorq_u8(vx, qx);
66
67		vst1q_u8(dq, db);
68		vst1q_u8(dp, veorq_u8(db, px));
69
70		bytes -= 16;
71		p += 16;
72		q += 16;
73		dp += 16;
74		dq += 16;
75	}
76}
77
78void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
79			      const uint8_t *qmul)
80{
81	uint8x16_t qm0 = vld1q_u8(qmul);
82	uint8x16_t qm1 = vld1q_u8(qmul + 16);
83	uint8x16_t x0f = vdupq_n_u8(0x0f);
84
85	/*
86	 * while (bytes--) {
87	 *	*p++ ^= *dq = qmul[*q ^ *dq];
88	 *	q++; dq++;
89	 * }
90	 */
91
92	while (bytes) {
93		uint8x16_t vx, vy;
94
95		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
96
97		vy = vshrq_n_u8(vx, 4);
98		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
99		vy = vqtbl1q_u8(qm1, vy);
100		vx = veorq_u8(vx, vy);
101		vy = veorq_u8(vx, vld1q_u8(p));
102
103		vst1q_u8(dq, vx);
104		vst1q_u8(p, vy);
105
106		bytes -= 16;
107		p += 16;
108		q += 16;
109		dq += 16;
110	}
111}
112