 6ebbf2ce43
			
		
	
	
	6ebbf2ce43
	
	
	
		
			
			ARMv6 and greater introduced a new instruction ("bx") which can be used
to return from function calls.  Recent CPUs perform better when the
"bx lr" instruction is used rather than the "mov pc, lr" instruction,
and this sequence is strongly recommended to be used by the ARM
architecture manual (section A.4.1.1).
We provide a new macro "ret" with all its variants for the condition
code which will resolve to the appropriate instruction.
Rather than doing this piecemeal, and miss some instances, change all
the "mov pc" instances to use the new macro, with the exception of
the "movs" instruction and the kprobes code.  This allows us to detect
the "mov pc, lr" case and fix it up - and also gives us the possibility
of deploying this for other registers depending on the CPU selection.
Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S
Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood
Tested-by: Shawn Guo <shawn.guo@freescale.com>
Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385
Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M
Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
		
	
			
		
			
				
	
	
		
			206 lines
		
	
	
	
		
			4.7 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
			
		
		
	
	
			206 lines
		
	
	
	
		
			4.7 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
| /*
 | |
|  *  linux/arch/arm/mm/cache-v4wt.S
 | |
|  *
 | |
|  *  Copyright (C) 1997-2002 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.
 | |
|  *
 | |
|  *  ARMv4 write through cache operations support.
 | |
|  *
 | |
|  *  We assume that the write buffer is not enabled.
 | |
|  */
 | |
| #include <linux/linkage.h>
 | |
| #include <linux/init.h>
 | |
| #include <asm/assembler.h>
 | |
| #include <asm/page.h>
 | |
| #include "proc-macros.S"
 | |
| 
 | |
| /*
 | |
|  * The size of one data cache line.
 | |
|  */
 | |
| #define CACHE_DLINESIZE	32
 | |
| 
 | |
| /*
 | |
|  * The number of data cache segments.
 | |
|  */
 | |
| #define CACHE_DSEGMENTS	8
 | |
| 
 | |
| /*
 | |
|  * The number of lines in a cache segment.
 | |
|  */
 | |
| #define CACHE_DENTRIES	64
 | |
| 
 | |
| /*
 | |
|  * This is the size at which it becomes more efficient to
 | |
|  * clean the whole cache, rather than using the individual
 | |
|  * cache line maintenance instructions.
 | |
|  *
 | |
|  * *** This needs benchmarking
 | |
|  */
 | |
| #define CACHE_DLIMIT	16384
 | |
| 
 | |
| /*
 | |
|  *	flush_icache_all()
 | |
|  *
 | |
|  *	Unconditionally clean and invalidate the entire icache.
 | |
|  */
 | |
| ENTRY(v4wt_flush_icache_all)
 | |
| 	mov	r0, #0
 | |
| 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 | |
| 	ret	lr
 | |
| ENDPROC(v4wt_flush_icache_all)
 | |
| 
 | |
| /*
 | |
|  *	flush_user_cache_all()
 | |
|  *
 | |
|  *	Invalidate all cache entries in a particular address
 | |
|  *	space.
 | |
|  */
 | |
| ENTRY(v4wt_flush_user_cache_all)
 | |
| 	/* FALLTHROUGH */
 | |
| /*
 | |
|  *	flush_kern_cache_all()
 | |
|  *
 | |
|  *	Clean and invalidate the entire cache.
 | |
|  */
 | |
| ENTRY(v4wt_flush_kern_cache_all)
 | |
| 	mov	r2, #VM_EXEC
 | |
| 	mov	ip, #0
 | |
| __flush_whole_cache:
 | |
| 	tst	r2, #VM_EXEC
 | |
| 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 | |
| 	mcr	p15, 0, ip, c7, c6, 0		@ invalidate D cache
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	flush_user_cache_range(start, end, flags)
 | |
|  *
 | |
|  *	Clean and invalidate a range of cache entries in the specified
 | |
|  *	address space.
 | |
|  *
 | |
|  *	- start - start address (inclusive, page aligned)
 | |
|  *	- end	- end address (exclusive, page aligned)
 | |
|  *	- flags	- vma_area_struct flags describing address space
 | |
|  */
 | |
| ENTRY(v4wt_flush_user_cache_range)
 | |
| 	sub	r3, r1, r0			@ calculate total size
 | |
| 	cmp	r3, #CACHE_DLIMIT
 | |
| 	bhs	__flush_whole_cache
 | |
| 
 | |
| 1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
 | |
| 	tst	r2, #VM_EXEC
 | |
| 	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate I entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	coherent_kern_range(start, end)
 | |
|  *
 | |
|  *	Ensure coherency between the Icache and the Dcache in the
 | |
|  *	region described by start.  If you have non-snooping
 | |
|  *	Harvard caches, you need to implement this function.
 | |
|  *
 | |
|  *	- start  - virtual start address
 | |
|  *	- end	 - virtual end address
 | |
|  */
 | |
| ENTRY(v4wt_coherent_kern_range)
 | |
| 	/* FALLTRHOUGH */
 | |
| 
 | |
| /*
 | |
|  *	coherent_user_range(start, end)
 | |
|  *
 | |
|  *	Ensure coherency between the Icache and the Dcache in the
 | |
|  *	region described by start.  If you have non-snooping
 | |
|  *	Harvard caches, you need to implement this function.
 | |
|  *
 | |
|  *	- start  - virtual start address
 | |
|  *	- end	 - virtual end address
 | |
|  */
 | |
| ENTRY(v4wt_coherent_user_range)
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 1:	mcr	p15, 0, r0, c7, c5, 1		@ invalidate I entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mov	r0, #0
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	flush_kern_dcache_area(void *addr, size_t size)
 | |
|  *
 | |
|  *	Ensure no D cache aliasing occurs, either with itself or
 | |
|  *	the I cache
 | |
|  *
 | |
|  *	- addr	- kernel address
 | |
|  *	- size	- region size
 | |
|  */
 | |
| ENTRY(v4wt_flush_kern_dcache_area)
 | |
| 	mov	r2, #0
 | |
| 	mcr	p15, 0, r2, c7, c5, 0		@ invalidate I cache
 | |
| 	add	r1, r0, r1
 | |
| 	/* fallthrough */
 | |
| 
 | |
| /*
 | |
|  *	dma_inv_range(start, end)
 | |
|  *
 | |
|  *	Invalidate (discard) the specified virtual address range.
 | |
|  *	May not write back any entries.  If 'start' or 'end'
 | |
|  *	are not cache line aligned, those lines must be written
 | |
|  *	back.
 | |
|  *
 | |
|  *	- start  - virtual start address
 | |
|  *	- end	 - virtual end address
 | |
|  */
 | |
| v4wt_dma_inv_range:
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	dma_flush_range(start, end)
 | |
|  *
 | |
|  *	Clean and invalidate the specified virtual address range.
 | |
|  *
 | |
|  *	- start  - virtual start address
 | |
|  *	- end	 - virtual end address
 | |
|  */
 | |
| 	.globl	v4wt_dma_flush_range
 | |
| 	.equ	v4wt_dma_flush_range, v4wt_dma_inv_range
 | |
| 
 | |
| /*
 | |
|  *	dma_unmap_area(start, size, dir)
 | |
|  *	- start	- kernel virtual start address
 | |
|  *	- size	- size of region
 | |
|  *	- dir	- DMA direction
 | |
|  */
 | |
| ENTRY(v4wt_dma_unmap_area)
 | |
| 	add	r1, r1, r0
 | |
| 	teq	r2, #DMA_TO_DEVICE
 | |
| 	bne	v4wt_dma_inv_range
 | |
| 	/* FALLTHROUGH */
 | |
| 
 | |
| /*
 | |
|  *	dma_map_area(start, size, dir)
 | |
|  *	- start	- kernel virtual start address
 | |
|  *	- size	- size of region
 | |
|  *	- dir	- DMA direction
 | |
|  */
 | |
| ENTRY(v4wt_dma_map_area)
 | |
| 	ret	lr
 | |
| ENDPROC(v4wt_dma_unmap_area)
 | |
| ENDPROC(v4wt_dma_map_area)
 | |
| 
 | |
| 	.globl	v4wt_flush_kern_cache_louis
 | |
| 	.equ	v4wt_flush_kern_cache_louis, v4wt_flush_kern_cache_all
 | |
| 
 | |
| 	__INITDATA
 | |
| 
 | |
| 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 | |
| 	define_cache_functions v4wt
 |