kernel_optimize_test/arch/arm64/kernel/io.c
Joonwoo Park 70ddb63a88 arm64: optimize memcpy_{from,to}io() and memset_io()
Optimize memcpy_{from,to}io() and memset_io() by transferring in 64 bit
as much as possible with minimized barrier usage.  This simplest
optimization brings faster throughput compare to current byte-by-byte read
and write with barrier in the loop.  Code's skeleton is taken from the
powerpc.

Link: http://lkml.kernel.org/p/20141020133304.GH23751@e104818-lin.cambridge.arm.com
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Trilok Soni <tsoni@codeaurora.org>
Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-11-06 17:25:27 +00:00

111 lines
2.2 KiB
C

/*
* Based on arch/arm/kernel/io.c
*
* Copyright (C) 2012 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/export.h>
#include <linux/types.h>
#include <linux/io.h>
/*
* Copy data from IO memory space to "real" memory space.
*/
void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
{
while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
!IS_ALIGNED((unsigned long)to, 8))) {
*(u8 *)to = __raw_readb(from);
from++;
to++;
count--;
}
while (count >= 8) {
*(u64 *)to = __raw_readq(from);
from += 8;
to += 8;
count -= 8;
}
while (count) {
*(u8 *)to = __raw_readb(from);
from++;
to++;
count--;
}
}
EXPORT_SYMBOL(__memcpy_fromio);
/*
* Copy data from "real" memory space to IO memory space.
*/
void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
{
while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
!IS_ALIGNED((unsigned long)from, 8))) {
__raw_writeb(*(volatile u8 *)from, to);
from++;
to++;
count--;
}
while (count >= 8) {
__raw_writeq(*(volatile u64 *)from, to);
from += 8;
to += 8;
count -= 8;
}
while (count) {
__raw_writeb(*(volatile u8 *)from, to);
from++;
to++;
count--;
}
}
EXPORT_SYMBOL(__memcpy_toio);
/*
* "memset" on IO memory space.
*/
void __memset_io(volatile void __iomem *dst, int c, size_t count)
{
u64 qc = (u8)c;
qc |= qc << 8;
qc |= qc << 16;
qc |= qc << 32;
while (count && !IS_ALIGNED((unsigned long)dst, 8)) {
__raw_writeb(c, dst);
dst++;
count--;
}
while (count >= 8) {
__raw_writeq(qc, dst);
dst += 8;
count -= 8;
}
while (count) {
__raw_writeb(c, dst);
dst++;
count--;
}
}
EXPORT_SYMBOL(__memset_io);