linux/lib/raid6/neon.c
Ard Biesheuvel 7d11965ddb lib/raid6: add ARM-NEON accelerated syndrome calculation
Rebased/reworked a patch contributed by Rob Herring that uses
NEON intrinsics to perform the RAID-6 syndrome calculations.
It uses the existing unroll.awk code to generate several
unrolled versions of which the best performing one is selected
at boot time.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Cc: hpa@linux.intel.com
2013-07-08 22:09:18 +01:00

59 lines
1.7 KiB
C

/*
* linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics
*
* Copyright (C) 2013 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 version 2 as
* published by the Free Software Foundation.
*/
#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
/*
* There are 2 reasons these wrappers are kept in a separate compilation unit
* from the actual implementations in neonN.c (generated from neon.uc by
* unroll.awk):
* - the actual implementations use NEON intrinsics, and the GCC support header
* (arm_neon.h) is not fully compatible (type wise) with the kernel;
* - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
* and we have to make sure that we never use *any* NEON/VFP instructions
* outside a kernel_neon_begin()/kernel_neon_end() pair.
*/
#define RAID6_NEON_WRAPPER(_n) \
static void raid6_neon ## _n ## _gen_syndrome(int disks, \
size_t bytes, void **ptrs) \
{ \
void raid6_neon ## _n ## _gen_syndrome_real(int, \
unsigned long, void**); \
kernel_neon_begin(); \
raid6_neon ## _n ## _gen_syndrome_real(disks, \
(unsigned long)bytes, ptrs); \
kernel_neon_end(); \
} \
struct raid6_calls const raid6_neonx ## _n = { \
raid6_neon ## _n ## _gen_syndrome, \
raid6_have_neon, \
"neonx" #_n, \
0 \
}
static int raid6_have_neon(void)
{
return cpu_has_neon();
}
RAID6_NEON_WRAPPER(1);
RAID6_NEON_WRAPPER(2);
RAID6_NEON_WRAPPER(4);
RAID6_NEON_WRAPPER(8);