kernel_optimize_test/lib/raid6/recov_neon.c
Ard Biesheuvel 6ec4e2514d md/raid6: implement recovery using ARM NEON intrinsics
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>
2017-08-09 18:52:07 +01:00

111 lines
2.7 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 <linux/raid/pq.h>
#ifdef __KERNEL__
#include <asm/neon.h>
#else
#define kernel_neon_begin()
#define kernel_neon_end()
#define cpu_has_neon() (1)
#endif
static int raid6_has_neon(void)
{
return cpu_has_neon();
}
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);
void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
const uint8_t *qmul);
static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
const u8 *pbmul; /* P multiplier table for B data */
const u8 *qmul; /* Q multiplier table (for both) */
p = (u8 *)ptrs[disks - 2];
q = (u8 *)ptrs[disks - 1];
/*
* Compute syndrome with zero for the missing data pages
* Use the dead data pages as temporary storage for
* delta p and delta q
*/
dp = (u8 *)ptrs[faila];
ptrs[faila] = (void *)raid6_empty_zero_page;
ptrs[disks - 2] = dp;
dq = (u8 *)ptrs[failb];
ptrs[failb] = (void *)raid6_empty_zero_page;
ptrs[disks - 1] = dq;
raid6_call.gen_syndrome(disks, bytes, ptrs);
/* Restore pointer table */
ptrs[faila] = dp;
ptrs[failb] = dq;
ptrs[disks - 2] = p;
ptrs[disks - 1] = q;
/* Now, pick the proper data tables */
pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
raid6_gfexp[failb]]];
kernel_neon_begin();
__raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
kernel_neon_end();
}
static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
p = (u8 *)ptrs[disks - 2];
q = (u8 *)ptrs[disks - 1];
/*
* Compute syndrome with zero for the missing data page
* Use the dead data page as temporary storage for delta q
*/
dq = (u8 *)ptrs[faila];
ptrs[faila] = (void *)raid6_empty_zero_page;
ptrs[disks - 1] = dq;
raid6_call.gen_syndrome(disks, bytes, ptrs);
/* Restore pointer table */
ptrs[faila] = dq;
ptrs[disks - 1] = q;
/* Now, pick the proper data tables */
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
kernel_neon_begin();
__raid6_datap_recov_neon(bytes, p, q, dq, qmul);
kernel_neon_end();
}
const struct raid6_recov_calls raid6_recov_neon = {
.data2 = raid6_2data_recov_neon,
.datap = raid6_datap_recov_neon,
.valid = raid6_has_neon,
.name = "neon",
.priority = 10,
};