summaryrefslogtreecommitdiffstats
path: root/lib/raid6/neon.uc
blob: b7c68030da4fd94d5e6bf3efca157127288e9f9a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
/* -----------------------------------------------------------------------
 *
 *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
 *
 *   Copyright (C) 2012 Rob Herring
 *   Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
 *
 *   Based on altivec.uc:
 *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
 *
 *   This program is free software; you can redistribute it and/or modify
 *   it under the terms of the GNU General Public License as published by
 *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
 *   Boston MA 02111-1307, USA; either version 2 of the License, or
 *   (at your option) any later version; incorporated herein by reference.
 *
 * ----------------------------------------------------------------------- */

/*
 * neon$#.c
 *
 * $#-way unrolled NEON intrinsics math RAID-6 instruction set
 *
 * This file is postprocessed using unroll.awk
 */

#include <arm_neon.h>

typedef uint8x16_t unative_t;

#define NSIZE	sizeof(unative_t)

/*
 * The SHLBYTE() operation shifts each byte left by 1, *not*
 * rolling over into the next byte
 */
static inline unative_t SHLBYTE(unative_t v)
{
	return vshlq_n_u8(v, 1);
}

/*
 * The MASK() operation returns 0xFF in any byte for which the high
 * bit is 1, 0x00 for any byte for which the high bit is 0.
 */
static inline unative_t MASK(unative_t v)
{
	return (unative_t)vshrq_n_s8((int8x16_t)v, 7);
}

static inline unative_t PMUL(unative_t v, unative_t u)
{
	return (unative_t)vmulq_p8((poly8x16_t)v, (poly8x16_t)u);
}

void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
{
	uint8_t **dptr = (uint8_t **)ptrs;
	uint8_t *p, *q;
	int d, z, z0;

	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
	const unative_t x1d = vdupq_n_u8(0x1d);

	z0 = disks - 3;		/* Highest data disk */
	p = dptr[z0+1];		/* XOR parity */
	q = dptr[z0+2];		/* RS syndrome */

	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
		wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
		for ( z = z0-1 ; z >= 0 ; z-- ) {
			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
			wp$$ = veorq_u8(wp$$, wd$$);
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			w1$$ = veorq_u8(w1$$, w2$$);
			wq$$ = veorq_u8(w1$$, wd$$);
		}
		vst1q_u8(&p[d+NSIZE*$$], wp$$);
		vst1q_u8(&q[d+NSIZE*$$], wq$$);
	}
}

void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
				    unsigned long bytes, void **ptrs)
{
	uint8_t **dptr = (uint8_t **)ptrs;
	uint8_t *p, *q;
	int d, z, z0;

	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
	const unative_t x1d = vdupq_n_u8(0x1d);

	z0 = stop;		/* P/Q right side optimization */
	p = dptr[disks-2];	/* XOR parity */
	q = dptr[disks-1];	/* RS syndrome */

	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
		wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
		wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$);

		/* P/Q data pages */
		for ( z = z0-1 ; z >= start ; z-- ) {
			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
			wp$$ = veorq_u8(wp$$, wd$$);
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			w1$$ = veorq_u8(w1$$, w2$$);
			wq$$ = veorq_u8(w1$$, wd$$);
		}
		/* P/Q left side optimization */
		for ( z = start-1 ; z >= 3 ; z -= 4 ) {
			w2$$ = vshrq_n_u8(wq$$, 4);
			w1$$ = vshlq_n_u8(wq$$, 4);

			w2$$ = PMUL(w2$$, x1d);
			wq$$ = veorq_u8(w1$$, w2$$);
		}

		switch (z) {
		case 2:
			w2$$ = vshrq_n_u8(wq$$, 5);
			w1$$ = vshlq_n_u8(wq$$, 3);

			w2$$ = PMUL(w2$$, x1d);
			wq$$ = veorq_u8(w1$$, w2$$);
			break;
		case 1:
			w2$$ = vshrq_n_u8(wq$$, 6);
			w1$$ = vshlq_n_u8(wq$$, 2);

			w2$$ = PMUL(w2$$, x1d);
			wq$$ = veorq_u8(w1$$, w2$$);
			break;
		case 0:
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			wq$$ = veorq_u8(w1$$, w2$$);
		}
		w1$$ = vld1q_u8(&q[d+NSIZE*$$]);
		wq$$ = veorq_u8(wq$$, w1$$);

		vst1q_u8(&p[d+NSIZE*$$], wp$$);
		vst1q_u8(&q[d+NSIZE*$$], wq$$);
	}
}