3de13550a2
The raid6 syndrome functions are generated for different sizes and have no generic prototype, while in the inner functions have a prototype in a header that cannot be included from the correct file. In both cases, the compiler warns about missing prototypes: lib/raid6/recov_neon_inner.c:27:6: warning: no previous prototype for '__raid6_2data_recov_neon' [-Wmissing-prototypes] lib/raid6/recov_neon_inner.c:77:6: warning: no previous prototype for '__raid6_datap_recov_neon' [-Wmissing-prototypes] lib/raid6/neon1.c:56:6: warning: no previous prototype for 'raid6_neon1_gen_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon1.c:86:6: warning: no previous prototype for 'raid6_neon1_xor_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon2.c:56:6: warning: no previous prototype for 'raid6_neon2_gen_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon2.c:97:6: warning: no previous prototype for 'raid6_neon2_xor_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon4.c:56:6: warning: no previous prototype for 'raid6_neon4_gen_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon4.c:119:6: warning: no previous prototype for 'raid6_neon4_xor_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon8.c:56:6: warning: no previous prototype for 'raid6_neon8_gen_syndrome_real' [-Wmissing-prototypes] lib/raid6/neon8.c:163:6: warning: no previous prototype for 'raid6_neon8_xor_syndrome_real' [-Wmissing-prototypes] Add a new header file that contains the prototypes for both to avoid the warnings. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Song Liu <song@kernel.org> Link: https://lore.kernel.org/r/20230517132220.937200-1-arnd@kernel.org
112 lines
2.3 KiB
C
112 lines
2.3 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2012 Intel Corporation
|
|
* Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
|
|
*/
|
|
|
|
#include <arm_neon.h>
|
|
#include "neon.h"
|
|
|
|
#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);
|
|
uint8x16_t x0f = vdupq_n_u8(0x0f);
|
|
|
|
/*
|
|
* 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 = vshrq_n_u8(vx, 4);
|
|
vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
|
|
vy = vqtbl1q_u8(qm1, vy);
|
|
qx = veorq_u8(vx, vy);
|
|
|
|
vy = vshrq_n_u8(px, 4);
|
|
vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
|
|
vy = vqtbl1q_u8(pm1, vy);
|
|
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);
|
|
uint8x16_t x0f = vdupq_n_u8(0x0f);
|
|
|
|
/*
|
|
* 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 = vshrq_n_u8(vx, 4);
|
|
vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
|
|
vy = vqtbl1q_u8(qm1, vy);
|
|
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;
|
|
}
|
|
}
|