diff options
author | Catalin Marinas <catalin.marinas@arm.com> | 2013-03-21 16:16:43 +0000 |
---|---|---|
committer | Catalin Marinas <catalin.marinas@arm.com> | 2013-03-21 17:39:29 +0000 |
commit | 4a8992271c843cb5bcd3321bf6a02eb251280b1d (patch) | |
tree | 100bdf14109f0d6b6ac559db6f25a337daa4280c /arch/arm64/lib/memcpy.S | |
parent | 792072066d30372772137be9ee2f4d72d77329f9 (diff) | |
download | linux-4a8992271c843cb5bcd3321bf6a02eb251280b1d.tar.bz2 |
arm64: klib: Optimised memory functions
This patch introduces AArch64-specific memory functions (memcpy,
memmove, memchr, memset). These functions are not optimised for any CPU
implementation but can be used as a starting point once hardware is
available.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Diffstat (limited to 'arch/arm64/lib/memcpy.S')
-rw-r--r-- | arch/arm64/lib/memcpy.S | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S new file mode 100644 index 000000000000..27b5003609b6 --- /dev/null +++ b/arch/arm64/lib/memcpy.S @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * Copy a buffer from src to dest (alignment handled by the hardware) + * + * Parameters: + * x0 - dest + * x1 - src + * x2 - n + * Returns: + * x0 - dest + */ +ENTRY(memcpy) + mov x4, x0 + subs x2, x2, #8 + b.mi 2f +1: ldr x3, [x1], #8 + subs x2, x2, #8 + str x3, [x4], #8 + b.pl 1b +2: adds x2, x2, #4 + b.mi 3f + ldr w3, [x1], #4 + sub x2, x2, #4 + str w3, [x4], #4 +3: adds x2, x2, #2 + b.mi 4f + ldrh w3, [x1], #2 + sub x2, x2, #2 + strh w3, [x4], #2 +4: adds x2, x2, #1 + b.mi 5f + ldrb w3, [x1] + strb w3, [x4] +5: ret +ENDPROC(memcpy) |