 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>
		
	
			
		
			
				
	
	
		
			458 lines
		
	
	
	
		
			11 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
			
		
		
	
	
			458 lines
		
	
	
	
		
			11 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
| /*
 | |
|  *  linux/arch/arm/mm/proc-arm922.S: MMU functions for ARM922
 | |
|  *
 | |
|  *  Copyright (C) 1999,2000 ARM Limited
 | |
|  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
 | |
|  *  Copyright (C) 2001 Altera Corporation
 | |
|  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
 | |
|  *
 | |
|  * This program is free software; you can redistribute it and/or modify
 | |
|  * it under the terms of the GNU General Public License as published by
 | |
|  * the Free Software Foundation; either version 2 of the License, or
 | |
|  * (at your option) any later version.
 | |
|  *
 | |
|  * 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, write to the Free Software
 | |
|  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 | |
|  *
 | |
|  *
 | |
|  * These are the low level assembler for performing cache and TLB
 | |
|  * functions on the arm922.
 | |
|  *
 | |
|  *  CONFIG_CPU_ARM922_CPU_IDLE -> nohlt
 | |
|  */
 | |
| #include <linux/linkage.h>
 | |
| #include <linux/init.h>
 | |
| #include <asm/assembler.h>
 | |
| #include <asm/hwcap.h>
 | |
| #include <asm/pgtable-hwdef.h>
 | |
| #include <asm/pgtable.h>
 | |
| #include <asm/page.h>
 | |
| #include <asm/ptrace.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	4
 | |
| 
 | |
| /*
 | |
|  * 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.  (I think this should
 | |
|  * be 32768).
 | |
|  */
 | |
| #define CACHE_DLIMIT	8192
 | |
| 
 | |
| 
 | |
| 	.text
 | |
| /*
 | |
|  * cpu_arm922_proc_init()
 | |
|  */
 | |
| ENTRY(cpu_arm922_proc_init)
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  * cpu_arm922_proc_fin()
 | |
|  */
 | |
| ENTRY(cpu_arm922_proc_fin)
 | |
| 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 | |
| 	bic	r0, r0, #0x1000			@ ...i............
 | |
| 	bic	r0, r0, #0x000e			@ ............wca.
 | |
| 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  * cpu_arm922_reset(loc)
 | |
|  *
 | |
|  * Perform a soft reset of the system.  Put the CPU into the
 | |
|  * same state as it would be if it had been reset, and branch
 | |
|  * to what would be the reset vector.
 | |
|  *
 | |
|  * loc: location to jump to for soft reset
 | |
|  */
 | |
| 	.align	5
 | |
| 	.pushsection	.idmap.text, "ax"
 | |
| ENTRY(cpu_arm922_reset)
 | |
| 	mov	ip, #0
 | |
| 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
 | |
| 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
 | |
| #ifdef CONFIG_MMU
 | |
| 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
 | |
| #endif
 | |
| 	mrc	p15, 0, ip, c1, c0, 0		@ ctrl register
 | |
| 	bic	ip, ip, #0x000f			@ ............wcam
 | |
| 	bic	ip, ip, #0x1100			@ ...i...s........
 | |
| 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 | |
| 	ret	r0
 | |
| ENDPROC(cpu_arm922_reset)
 | |
| 	.popsection
 | |
| 
 | |
| /*
 | |
|  * cpu_arm922_do_idle()
 | |
|  */
 | |
| 	.align	5
 | |
| ENTRY(cpu_arm922_do_idle)
 | |
| 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
 | |
| 	ret	lr
 | |
| 
 | |
| 
 | |
| #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
 | |
| 
 | |
| /*
 | |
|  *	flush_icache_all()
 | |
|  *
 | |
|  *	Unconditionally clean and invalidate the entire icache.
 | |
|  */
 | |
| ENTRY(arm922_flush_icache_all)
 | |
| 	mov	r0, #0
 | |
| 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 | |
| 	ret	lr
 | |
| ENDPROC(arm922_flush_icache_all)
 | |
| 
 | |
| /*
 | |
|  *	flush_user_cache_all()
 | |
|  *
 | |
|  *	Clean and invalidate all cache entries in a particular
 | |
|  *	address space.
 | |
|  */
 | |
| ENTRY(arm922_flush_user_cache_all)
 | |
| 	/* FALLTHROUGH */
 | |
| 
 | |
| /*
 | |
|  *	flush_kern_cache_all()
 | |
|  *
 | |
|  *	Clean and invalidate the entire cache.
 | |
|  */
 | |
| ENTRY(arm922_flush_kern_cache_all)
 | |
| 	mov	r2, #VM_EXEC
 | |
| 	mov	ip, #0
 | |
| __flush_whole_cache:
 | |
| 	mov	r1, #(CACHE_DSEGMENTS - 1) << 5	@ 8 segments
 | |
| 1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
 | |
| 2:	mcr	p15, 0, r3, c7, c14, 2		@ clean+invalidate D index
 | |
| 	subs	r3, r3, #1 << 26
 | |
| 	bcs	2b				@ entries 63 to 0
 | |
| 	subs	r1, r1, #1 << 5
 | |
| 	bcs	1b				@ segments 7 to 0
 | |
| 	tst	r2, #VM_EXEC
 | |
| 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 | |
| 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	flush_user_cache_range(start, end, flags)
 | |
|  *
 | |
|  *	Clean and invalidate a range of cache entries in the
 | |
|  *	specified address range.
 | |
|  *
 | |
|  *	- start	- start address (inclusive)
 | |
|  *	- end	- end address (exclusive)
 | |
|  *	- flags	- vm_flags describing address space
 | |
|  */
 | |
| ENTRY(arm922_flush_user_cache_range)
 | |
| 	mov	ip, #0
 | |
| 	sub	r3, r1, r0			@ calculate total size
 | |
| 	cmp	r3, #CACHE_DLIMIT
 | |
| 	bhs	__flush_whole_cache
 | |
| 
 | |
| 1:	mcr	p15, 0, r0, c7, c14, 1		@ clean+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
 | |
| 	tst	r2, #VM_EXEC
 | |
| 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	coherent_kern_range(start, end)
 | |
|  *
 | |
|  *	Ensure coherency between the Icache and the Dcache in the
 | |
|  *	region described by start, end.  If you have non-snooping
 | |
|  *	Harvard caches, you need to implement this function.
 | |
|  *
 | |
|  *	- start	- virtual start address
 | |
|  *	- end	- virtual end address
 | |
|  */
 | |
| ENTRY(arm922_coherent_kern_range)
 | |
| 	/* FALLTHROUGH */
 | |
| 
 | |
| /*
 | |
|  *	coherent_user_range(start, end)
 | |
|  *
 | |
|  *	Ensure coherency between the Icache and the Dcache in the
 | |
|  *	region described by start, end.  If you have non-snooping
 | |
|  *	Harvard caches, you need to implement this function.
 | |
|  *
 | |
|  *	- start	- virtual start address
 | |
|  *	- end	- virtual end address
 | |
|  */
 | |
| ENTRY(arm922_coherent_user_range)
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 | |
| 	mcr	p15, 0, r0, c7, c5, 1		@ invalidate I entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| 	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(arm922_flush_kern_dcache_area)
 | |
| 	add	r1, r0, r1
 | |
| 1:	mcr	p15, 0, r0, c7, c14, 1		@ clean+invalidate D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mov	r0, #0
 | |
| 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	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
 | |
|  *
 | |
|  * (same as v4wb)
 | |
|  */
 | |
| arm922_dma_inv_range:
 | |
| 	tst	r0, #CACHE_DLINESIZE - 1
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 	mcrne	p15, 0, r0, c7, c10, 1		@ clean D entry
 | |
| 	tst	r1, #CACHE_DLINESIZE - 1
 | |
| 	mcrne	p15, 0, r1, c7, c10, 1		@ clean D entry
 | |
| 1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	dma_clean_range(start, end)
 | |
|  *
 | |
|  *	Clean the specified virtual address range.
 | |
|  *
 | |
|  *	- start	- virtual start address
 | |
|  *	- end	- virtual end address
 | |
|  *
 | |
|  * (same as v4wb)
 | |
|  */
 | |
| arm922_dma_clean_range:
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	dma_flush_range(start, end)
 | |
|  *
 | |
|  *	Clean and invalidate the specified virtual address range.
 | |
|  *
 | |
|  *	- start	- virtual start address
 | |
|  *	- end	- virtual end address
 | |
|  */
 | |
| ENTRY(arm922_dma_flush_range)
 | |
| 	bic	r0, r0, #CACHE_DLINESIZE - 1
 | |
| 1:	mcr	p15, 0, r0, c7, c14, 1		@ clean+invalidate D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	cmp	r0, r1
 | |
| 	blo	1b
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  *	dma_map_area(start, size, dir)
 | |
|  *	- start	- kernel virtual start address
 | |
|  *	- size	- size of region
 | |
|  *	- dir	- DMA direction
 | |
|  */
 | |
| ENTRY(arm922_dma_map_area)
 | |
| 	add	r1, r1, r0
 | |
| 	cmp	r2, #DMA_TO_DEVICE
 | |
| 	beq	arm922_dma_clean_range
 | |
| 	bcs	arm922_dma_inv_range
 | |
| 	b	arm922_dma_flush_range
 | |
| ENDPROC(arm922_dma_map_area)
 | |
| 
 | |
| /*
 | |
|  *	dma_unmap_area(start, size, dir)
 | |
|  *	- start	- kernel virtual start address
 | |
|  *	- size	- size of region
 | |
|  *	- dir	- DMA direction
 | |
|  */
 | |
| ENTRY(arm922_dma_unmap_area)
 | |
| 	ret	lr
 | |
| ENDPROC(arm922_dma_unmap_area)
 | |
| 
 | |
| 	.globl	arm922_flush_kern_cache_louis
 | |
| 	.equ	arm922_flush_kern_cache_louis, arm922_flush_kern_cache_all
 | |
| 
 | |
| 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 | |
| 	define_cache_functions arm922
 | |
| #endif
 | |
| 
 | |
| 
 | |
| ENTRY(cpu_arm922_dcache_clean_area)
 | |
| #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
 | |
| 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 | |
| 	add	r0, r0, #CACHE_DLINESIZE
 | |
| 	subs	r1, r1, #CACHE_DLINESIZE
 | |
| 	bhi	1b
 | |
| #endif
 | |
| 	ret	lr
 | |
| 
 | |
| /* =============================== PageTable ============================== */
 | |
| 
 | |
| /*
 | |
|  * cpu_arm922_switch_mm(pgd)
 | |
|  *
 | |
|  * Set the translation base pointer to be as described by pgd.
 | |
|  *
 | |
|  * pgd: new page tables
 | |
|  */
 | |
| 	.align	5
 | |
| ENTRY(cpu_arm922_switch_mm)
 | |
| #ifdef CONFIG_MMU
 | |
| 	mov	ip, #0
 | |
| #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
 | |
| 	mcr	p15, 0, ip, c7, c6, 0		@ invalidate D cache
 | |
| #else
 | |
| @ && 'Clean & Invalidate whole DCache'
 | |
| @ && Re-written to use Index Ops.
 | |
| @ && Uses registers r1, r3 and ip
 | |
| 
 | |
| 	mov	r1, #(CACHE_DSEGMENTS - 1) << 5	@ 4 segments
 | |
| 1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
 | |
| 2:	mcr	p15, 0, r3, c7, c14, 2		@ clean & invalidate D index
 | |
| 	subs	r3, r3, #1 << 26
 | |
| 	bcs	2b				@ entries 63 to 0
 | |
| 	subs	r1, r1, #1 << 5
 | |
| 	bcs	1b				@ segments 7 to 0
 | |
| #endif
 | |
| 	mcr	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 | |
| 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
 | |
| 	mcr	p15, 0, r0, c2, c0, 0		@ load page table pointer
 | |
| 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
 | |
| #endif
 | |
| 	ret	lr
 | |
| 
 | |
| /*
 | |
|  * cpu_arm922_set_pte_ext(ptep, pte, ext)
 | |
|  *
 | |
|  * Set a PTE and flush it out
 | |
|  */
 | |
| 	.align	5
 | |
| ENTRY(cpu_arm922_set_pte_ext)
 | |
| #ifdef CONFIG_MMU
 | |
| 	armv3_set_pte_ext
 | |
| 	mov	r0, r0
 | |
| 	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 | |
| #endif /* CONFIG_MMU */
 | |
| 	ret	lr
 | |
| 
 | |
| 	.type	__arm922_setup, #function
 | |
| __arm922_setup:
 | |
| 	mov	r0, #0
 | |
| 	mcr	p15, 0, r0, c7, c7		@ invalidate I,D caches on v4
 | |
| 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer on v4
 | |
| #ifdef CONFIG_MMU
 | |
| 	mcr	p15, 0, r0, c8, c7		@ invalidate I,D TLBs on v4
 | |
| #endif
 | |
| 	adr	r5, arm922_crval
 | |
| 	ldmia	r5, {r5, r6}
 | |
| 	mrc	p15, 0, r0, c1, c0		@ get control register v4
 | |
| 	bic	r0, r0, r5
 | |
| 	orr	r0, r0, r6
 | |
| 	ret	lr
 | |
| 	.size	__arm922_setup, . - __arm922_setup
 | |
| 
 | |
| 	/*
 | |
| 	 *  R
 | |
| 	 * .RVI ZFRS BLDP WCAM
 | |
| 	 * ..11 0001 ..11 0101
 | |
| 	 * 
 | |
| 	 */
 | |
| 	.type	arm922_crval, #object
 | |
| arm922_crval:
 | |
| 	crval	clear=0x00003f3f, mmuset=0x00003135, ucset=0x00001130
 | |
| 
 | |
| 	__INITDATA
 | |
| 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
 | |
| 	define_processor_functions arm922, dabort=v4t_early_abort, pabort=legacy_pabort
 | |
| 
 | |
| 	.section ".rodata"
 | |
| 
 | |
| 	string	cpu_arch_name, "armv4t"
 | |
| 	string	cpu_elf_name, "v4"
 | |
| 	string	cpu_arm922_name, "ARM922T"
 | |
| 
 | |
| 	.align
 | |
| 
 | |
| 	.section ".proc.info.init", #alloc, #execinstr
 | |
| 
 | |
| 	.type	__arm922_proc_info,#object
 | |
| __arm922_proc_info:
 | |
| 	.long	0x41009220
 | |
| 	.long	0xff00fff0
 | |
| 	.long   PMD_TYPE_SECT | \
 | |
| 		PMD_SECT_BUFFERABLE | \
 | |
| 		PMD_SECT_CACHEABLE | \
 | |
| 		PMD_BIT4 | \
 | |
| 		PMD_SECT_AP_WRITE | \
 | |
| 		PMD_SECT_AP_READ
 | |
| 	.long   PMD_TYPE_SECT | \
 | |
| 		PMD_BIT4 | \
 | |
| 		PMD_SECT_AP_WRITE | \
 | |
| 		PMD_SECT_AP_READ
 | |
| 	b	__arm922_setup
 | |
| 	.long	cpu_arch_name
 | |
| 	.long	cpu_elf_name
 | |
| 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
 | |
| 	.long	cpu_arm922_name
 | |
| 	.long	arm922_processor_functions
 | |
| 	.long	v4wbi_tlb_fns
 | |
| 	.long	v4wb_user_fns
 | |
| #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
 | |
| 	.long	arm922_cache_fns
 | |
| #else
 | |
| 	.long	v4wt_cache_fns
 | |
| #endif
 | |
| 	.size	__arm922_proc_info, . - __arm922_proc_info
 |