diff options
author | Ingo Molnar <mingo@elte.hu> | 2009-04-29 14:46:59 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2009-04-29 14:47:05 +0200 |
commit | e7fd5d4b3d240f42c30a9e3d20a4689c4d3a795a (patch) | |
tree | 4ba588631dd8189a818a91c9e3976526071178b6 /arch/microblaze/lib/memcpy.c | |
parent | 1130b0296184bc21806225fd06d533515a99d2db (diff) | |
parent | 56a50adda49b2020156616c4eb15353e0f9ad7de (diff) |
Merge branch 'linus' into perfcounters/core
Merge reason: This brach was on -rc1, refresh it to almost-rc4 to pick up
the latest upstream fixes.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/microblaze/lib/memcpy.c')
-rw-r--r-- | arch/microblaze/lib/memcpy.c | 161 |
1 files changed, 161 insertions, 0 deletions
diff --git a/arch/microblaze/lib/memcpy.c b/arch/microblaze/lib/memcpy.c new file mode 100644 index 00000000000..5880119c448 --- /dev/null +++ b/arch/microblaze/lib/memcpy.c @@ -0,0 +1,161 @@ +/* + * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> + * Copyright (C) 2008-2009 PetaLogix + * Copyright (C) 2007 John Williams + * + * Reasonably optimised generic C-code for memcpy on Microblaze + * This is generic C code to do efficient, alignment-aware memcpy. + * + * It is based on demo code originally Copyright 2001 by Intel Corp, taken from + * http://www.embedded.com/showArticle.jhtml?articleID=19205567 + * + * Attempts were made, unsuccesfully, to contact the original + * author of this code (Michael Morrow, Intel). Below is the original + * copyright notice. + * + * This software has been developed by Intel Corporation. + * Intel specifically disclaims all warranties, express or + * implied, and all liability, including consequential and + * other indirect damages, for the use of this program, including + * liability for infringement of any proprietary rights, + * and including the warranties of merchantability and fitness + * for a particular purpose. Intel does not assume any + * responsibility for and errors which may appear in this program + * not any responsibility to update it. + */ + +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/compiler.h> +#include <linux/module.h> + +#include <linux/string.h> +#include <asm/system.h> + +#ifdef __HAVE_ARCH_MEMCPY +void *memcpy(void *v_dst, const void *v_src, __kernel_size_t c) +{ + const char *src = v_src; + char *dst = v_dst; +#ifndef CONFIG_OPT_LIB_FUNCTION + /* Simple, byte oriented memcpy. */ + while (c--) + *dst++ = *src++; + + return v_dst; +#else + /* The following code tries to optimize the copy by using unsigned + * alignment. This will work fine if both source and destination are + * aligned on the same boundary. However, if they are aligned on + * different boundaries shifts will be necessary. This might result in + * bad performance on MicroBlaze systems without a barrel shifter. + */ + const uint32_t *i_src; + uint32_t *i_dst; + + if (c >= 4) { + unsigned value, buf_hold; + + /* Align the dstination to a word boundry. */ + /* This is done in an endian independant manner. */ + switch ((unsigned long)dst & 3) { + case 1: + *dst++ = *src++; + --c; + case 2: + *dst++ = *src++; + --c; + case 3: + *dst++ = *src++; + --c; + } + + i_dst = (void *)dst; + + /* Choose a copy scheme based on the source */ + /* alignment relative to dstination. */ + switch ((unsigned long)src & 3) { + case 0x0: /* Both byte offsets are aligned */ + i_src = (const void *)src; + + for (; c >= 4; c -= 4) + *i_dst++ = *i_src++; + + src = (const void *)i_src; + break; + case 0x1: /* Unaligned - Off by 1 */ + /* Word align the source */ + i_src = (const void *) ((unsigned)src & ~3); + + /* Load the holding buffer */ + buf_hold = *i_src++ << 8; + + for (; c >= 4; c -= 4) { + value = *i_src++; + *i_dst++ = buf_hold | value >> 24; + buf_hold = value << 8; + } + + /* Realign the source */ + src = (const void *)i_src; + src -= 3; + break; + case 0x2: /* Unaligned - Off by 2 */ + /* Word align the source */ + i_src = (const void *) ((unsigned)src & ~3); + + /* Load the holding buffer */ + buf_hold = *i_src++ << 16; + + for (; c >= 4; c -= 4) { + value = *i_src++; + *i_dst++ = buf_hold | value >> 16; + buf_hold = value << 16; + } + + /* Realign the source */ + src = (const void *)i_src; + src -= 2; + break; + case 0x3: /* Unaligned - Off by 3 */ + /* Word align the source */ + i_src = (const void *) ((unsigned)src & ~3); + + /* Load the holding buffer */ + buf_hold = *i_src++ << 24; + + for (; c >= 4; c -= 4) { + value = *i_src++; + *i_dst++ = buf_hold | value >> 8; + buf_hold = value << 24; + } + + /* Realign the source */ + src = (const void *)i_src; + src -= 1; + break; + } + dst = (void *)i_dst; + } + + /* Finish off any remaining bytes */ + /* simple fast copy, ... unless a cache boundry is crossed */ + switch (c) { + case 3: + *dst++ = *src++; + case 2: + *dst++ = *src++; + case 1: + *dst++ = *src++; + } + + return v_dst; +#endif +} +EXPORT_SYMBOL(memcpy); +#endif /* __HAVE_ARCH_MEMCPY */ + +void *cacheable_memcpy(void *d, const void *s, __kernel_size_t c) +{ + return memcpy(d, s, c); +} |