diff options
author | Matteo Croce <mcroce@microsoft.com> | 2022-03-30 20:07:14 +0800 |
---|---|---|
committer | Guo Ren <guoren@linux.alibaba.com> | 2022-04-18 21:23:55 +0800 |
commit | e4df2d5e852a7d24df3672ae9951eb79e179be08 (patch) | |
tree | 304debe8a13e6d07a56b7f97ac9eb92d8ddd95d7 /arch/csky/lib | |
parent | cfb24463a53edeb388f3563e166ad7f9591dad3d (diff) | |
download | linux-e4df2d5e852a7d24df3672ae9951eb79e179be08.tar.bz2 |
csky: Add C based string functions
Try to access RAM with the largest bit width possible, but without
doing unaligned accesses.
A further improvement could be to use multiple read and writes as the
assembly version was trying to do.
Tested on a BeagleV Starlight with a SiFive U74 core, where the
improvement is noticeable.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Co-developed-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Diffstat (limited to 'arch/csky/lib')
-rw-r--r-- | arch/csky/lib/Makefile | 3 | ||||
-rw-r--r-- | arch/csky/lib/string.c | 134 |
2 files changed, 137 insertions, 0 deletions
diff --git a/arch/csky/lib/Makefile b/arch/csky/lib/Makefile index 7fbdbb2c4d12..d0ce6e2d7ab2 100644 --- a/arch/csky/lib/Makefile +++ b/arch/csky/lib/Makefile @@ -1,3 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only lib-y := usercopy.o delay.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y) +lib-y += string.o +endif diff --git a/arch/csky/lib/string.c b/arch/csky/lib/string.c new file mode 100644 index 000000000000..d65626fcaeac --- /dev/null +++ b/arch/csky/lib/string.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * String functions optimized for hardware which doesn't + * handle unaligned memory accesses efficiently. + * + * Copyright (C) 2021 Matteo Croce + */ + +#include <linux/types.h> +#include <linux/module.h> + +/* Minimum size for a word copy to be convenient */ +#define BYTES_LONG sizeof(long) +#define WORD_MASK (BYTES_LONG - 1) +#define MIN_THRESHOLD (BYTES_LONG * 2) + +/* convenience union to avoid cast between different pointer types */ +union types { + u8 *as_u8; + unsigned long *as_ulong; + uintptr_t as_uptr; +}; + +union const_types { + const u8 *as_u8; + unsigned long *as_ulong; + uintptr_t as_uptr; +}; + +void *memcpy(void *dest, const void *src, size_t count) +{ + union const_types s = { .as_u8 = src }; + union types d = { .as_u8 = dest }; + int distance = 0; + + if (count < MIN_THRESHOLD) + goto copy_remainder; + + /* Copy a byte at time until destination is aligned. */ + for (; d.as_uptr & WORD_MASK; count--) + *d.as_u8++ = *s.as_u8++; + + distance = s.as_uptr & WORD_MASK; + + if (distance) { + unsigned long last, next; + + /* + * s is distance bytes ahead of d, and d just reached + * the alignment boundary. Move s backward to word align it + * and shift data to compensate for distance, in order to do + * word-by-word copy. + */ + s.as_u8 -= distance; + + next = s.as_ulong[0]; + for (; count >= BYTES_LONG; count -= BYTES_LONG) { + last = next; + next = s.as_ulong[1]; + + d.as_ulong[0] = last >> (distance * 8) | + next << ((BYTES_LONG - distance) * 8); + + d.as_ulong++; + s.as_ulong++; + } + + /* Restore s with the original offset. */ + s.as_u8 += distance; + } else { + /* + * If the source and dest lower bits are the same, do a simple + * 32/64 bit wide copy. + */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *d.as_ulong++ = *s.as_ulong++; + } + +copy_remainder: + while (count--) + *d.as_u8++ = *s.as_u8++; + + return dest; +} +EXPORT_SYMBOL(memcpy); + +/* + * Simply check if the buffer overlaps an call memcpy() in case, + * otherwise do a simple one byte at time backward copy. + */ +void *memmove(void *dest, const void *src, size_t count) +{ + if (dest < src || src + count <= dest) + return memcpy(dest, src, count); + + if (dest > src) { + const char *s = src + count; + char *tmp = dest + count; + + while (count--) + *--tmp = *--s; + } + return dest; +} +EXPORT_SYMBOL(memmove); + +void *memset(void *s, int c, size_t count) +{ + union types dest = { .as_u8 = s }; + + if (count >= MIN_THRESHOLD) { + unsigned long cu = (unsigned long)c; + + /* Compose an ulong with 'c' repeated 4/8 times */ + cu |= cu << 8; + cu |= cu << 16; + /* Suppress warning on 32 bit machines */ + cu |= (cu << 16) << 16; + + for (; count && dest.as_uptr & WORD_MASK; count--) + *dest.as_u8++ = c; + + /* Copy using the largest size allowed */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *dest.as_ulong++ = cu; + } + + /* copy the remainder */ + while (count--) + *dest.as_u8++ = c; + + return s; +} +EXPORT_SYMBOL(memset); |