kernel_optimize_test/include/asm-arm/assembler.h
Nicolas Pitre 2239aff6ab [ARM] cache align destination pointer when copying memory for some processors
The implementation for memory copy functions on ARM had a (disabled)
provision for aligning the source pointer before loading registers with
data.  Turns out that aligning the _destination_ pointer is much more
useful, as the read side is already sufficiently helped with the use of
preload.

So this changes the definition of the CALGN() macro to target the
destination pointer instead, and turns it on for Feroceon processors
where the gain is very noticeable.

Signed-off-by: Nicolas Pitre <nico@marvell.com>
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>
2008-06-22 22:44:38 +02:00

117 lines
2.6 KiB
C

/*
* linux/include/asm-arm/assembler.h
*
* Copyright (C) 1996-2000 Russell King
*
* 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 file contains arm architecture specific defines
* for the different processors.
*
* Do not include any C declarations in this file - it is included by
* assembler source.
*/
#ifndef __ASSEMBLY__
#error "Only include this from assembly code"
#endif
#include <asm/ptrace.h>
/*
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
#define pull lsr
#define push lsl
#define get_byte_0 lsl #0
#define get_byte_1 lsr #8
#define get_byte_2 lsr #16
#define get_byte_3 lsr #24
#define put_byte_0 lsl #0
#define put_byte_1 lsl #8
#define put_byte_2 lsl #16
#define put_byte_3 lsl #24
#else
#define pull lsl
#define push lsr
#define get_byte_0 lsr #24
#define get_byte_1 lsr #16
#define get_byte_2 lsr #8
#define get_byte_3 lsl #0
#define put_byte_0 lsl #24
#define put_byte_1 lsl #16
#define put_byte_2 lsl #8
#define put_byte_3 lsl #0
#endif
/*
* Data preload for architectures that support it
*/
#if __LINUX_ARM_ARCH__ >= 5
#define PLD(code...) code
#else
#define PLD(code...)
#endif
/*
* This can be used to enable code to cacheline align the destination
* pointer when bulk writing to memory. Experiments on StrongARM and
* XScale didn't show this a worthwhile thing to do when the cache is not
* set to write-allocate (this would need further testing on XScale when WA
* is used).
*
* On Feroceon there is much to gain however, regardless of cache mode.
*/
#ifdef CONFIG_CPU_FEROCEON
#define CALGN(code...) code
#else
#define CALGN(code...)
#endif
/*
* Enable and disable interrupts
*/
#if __LINUX_ARM_ARCH__ >= 6
.macro disable_irq
cpsid i
.endm
.macro enable_irq
cpsie i
.endm
#else
.macro disable_irq
msr cpsr_c, #PSR_I_BIT | SVC_MODE
.endm
.macro enable_irq
msr cpsr_c, #SVC_MODE
.endm
#endif
/*
* Save the current IRQ state and disable IRQs. Note that this macro
* assumes FIQs are enabled, and that the processor is in SVC mode.
*/
.macro save_and_disable_irqs, oldcpsr
mrs \oldcpsr, cpsr
disable_irq
.endm
/*
* Restore interrupt state previously stored in a register. We don't
* guarantee that this will preserve the flags.
*/
.macro restore_irqs, oldcpsr
msr cpsr_c, \oldcpsr
.endm
#define USER(x...) \
9999: x; \
.section __ex_table,"a"; \
.align 3; \
.long 9999b,9001f; \
.previous