mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 16:55:13 +07:00
6ec4e2514d
Provide a NEON accelerated implementation of the recovery algorithm, which supersedes the default byte-by-byte one. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
118 lines
2.6 KiB
C
118 lines
2.6 KiB
C
/*
|
|
* Copyright (C) 2012 Intel Corporation
|
|
* Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
|
|
*
|
|
* 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; version 2
|
|
* of the License.
|
|
*/
|
|
|
|
#include <arm_neon.h>
|
|
|
|
static const uint8x16_t x0f = {
|
|
0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
|
|
0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
|
|
};
|
|
|
|
#ifdef CONFIG_ARM
|
|
/*
|
|
* AArch32 does not provide this intrinsic natively because it does not
|
|
* implement the underlying instruction. AArch32 only provides a 64-bit
|
|
* wide vtbl.8 instruction, so use that instead.
|
|
*/
|
|
static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
|
|
{
|
|
union {
|
|
uint8x16_t val;
|
|
uint8x8x2_t pair;
|
|
} __a = { a };
|
|
|
|
return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
|
|
vtbl2_u8(__a.pair, vget_high_u8(b)));
|
|
}
|
|
#endif
|
|
|
|
void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
|
|
uint8_t *dq, const uint8_t *pbmul,
|
|
const uint8_t *qmul)
|
|
{
|
|
uint8x16_t pm0 = vld1q_u8(pbmul);
|
|
uint8x16_t pm1 = vld1q_u8(pbmul + 16);
|
|
uint8x16_t qm0 = vld1q_u8(qmul);
|
|
uint8x16_t qm1 = vld1q_u8(qmul + 16);
|
|
|
|
/*
|
|
* while ( bytes-- ) {
|
|
* uint8_t px, qx, db;
|
|
*
|
|
* px = *p ^ *dp;
|
|
* qx = qmul[*q ^ *dq];
|
|
* *dq++ = db = pbmul[px] ^ qx;
|
|
* *dp++ = db ^ px;
|
|
* p++; q++;
|
|
* }
|
|
*/
|
|
|
|
while (bytes) {
|
|
uint8x16_t vx, vy, px, qx, db;
|
|
|
|
px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
|
|
vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
|
|
|
|
vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
|
|
vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
|
|
vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
|
|
qx = veorq_u8(vx, vy);
|
|
|
|
vy = (uint8x16_t)vshrq_n_s16((int16x8_t)px, 4);
|
|
vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
|
|
vy = vqtbl1q_u8(pm1, vandq_u8(vy, x0f));
|
|
vx = veorq_u8(vx, vy);
|
|
db = veorq_u8(vx, qx);
|
|
|
|
vst1q_u8(dq, db);
|
|
vst1q_u8(dp, veorq_u8(db, px));
|
|
|
|
bytes -= 16;
|
|
p += 16;
|
|
q += 16;
|
|
dp += 16;
|
|
dq += 16;
|
|
}
|
|
}
|
|
|
|
void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
|
|
const uint8_t *qmul)
|
|
{
|
|
uint8x16_t qm0 = vld1q_u8(qmul);
|
|
uint8x16_t qm1 = vld1q_u8(qmul + 16);
|
|
|
|
/*
|
|
* while (bytes--) {
|
|
* *p++ ^= *dq = qmul[*q ^ *dq];
|
|
* q++; dq++;
|
|
* }
|
|
*/
|
|
|
|
while (bytes) {
|
|
uint8x16_t vx, vy;
|
|
|
|
vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
|
|
|
|
vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
|
|
vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
|
|
vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
|
|
vx = veorq_u8(vx, vy);
|
|
vy = veorq_u8(vx, vld1q_u8(p));
|
|
|
|
vst1q_u8(dq, vx);
|
|
vst1q_u8(p, vy);
|
|
|
|
bytes -= 16;
|
|
p += 16;
|
|
q += 16;
|
|
dq += 16;
|
|
}
|
|
}
|