forked from Qortal/Brooklyn
a94b3d14aa
Changes included (and more): 1. Dynamic RAM merge 2. Real-time page scan and allocation 3. Cache compression 4. Real-time IRQ checks 5. Dynamic I/O allocation for Java heap 6. Java page migration 7. Contiguous memory allocation 8. Idle pages tracking 9. Per CPU RAM usage tracking 10. ARM NEON scalar multiplication library 11. NEON/ARMv8 crypto extensions 12. NEON SHA, Blake, RIPEMD crypto extensions 13. Parallel NEON crypto engine for multi-algo based CPU stress reduction
78 lines
1.9 KiB
C
78 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* arch/arm64/include/asm/xor.h
|
|
*
|
|
* Authors: Jackie Liu <liuyun01@kylinos.cn>
|
|
* Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
|
|
*/
|
|
|
|
#include <linux/hardirq.h>
|
|
#include <asm-generic/xor.h>
|
|
#include <asm/hwcap.h>
|
|
#include <asm/neon.h>
|
|
|
|
#ifdef CONFIG_KERNEL_MODE_NEON
|
|
|
|
extern struct xor_block_template const xor_block_inner_neon;
|
|
|
|
static void
|
|
xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
kernel_neon_begin();
|
|
xor_block_inner_neon.do_2(bytes, p1, p2);
|
|
kernel_neon_end();
|
|
}
|
|
|
|
static void
|
|
xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
kernel_neon_begin();
|
|
xor_block_inner_neon.do_3(bytes, p1, p2, p3);
|
|
kernel_neon_end();
|
|
}
|
|
|
|
static void
|
|
xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
kernel_neon_begin();
|
|
xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
|
|
kernel_neon_end();
|
|
}
|
|
|
|
static void
|
|
xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
kernel_neon_begin();
|
|
xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
|
|
kernel_neon_end();
|
|
}
|
|
|
|
static struct xor_block_template xor_block_arm64 = {
|
|
.name = "arm64_neon",
|
|
.do_2 = xor_neon_2,
|
|
.do_3 = xor_neon_3,
|
|
.do_4 = xor_neon_4,
|
|
.do_5 = xor_neon_5
|
|
};
|
|
#undef XOR_TRY_TEMPLATES
|
|
#define XOR_TRY_TEMPLATES \
|
|
do { \
|
|
xor_speed(&xor_block_8regs); \
|
|
xor_speed(&xor_block_32regs); \
|
|
if (cpu_has_neon()) { \
|
|
xor_speed(&xor_block_arm64);\
|
|
} \
|
|
} while (0)
|
|
|
|
#endif /* ! CONFIG_KERNEL_MODE_NEON */
|