da30e0ac0f
The current implementation of the v7_coherent_*_range function assumes that the D and I cache lines have the same size, which is incorrect architecturally. This patch adds the icache_line_size macro which reads the CTR register. The main loop in v7_coherent_*_range is split in two independent loops or the D and I caches. This also has the performance advantage that the DSB is moved outside the main loop. Reported-by: Kevin Sapp <ksapp@quicinc.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
339 lines
8.5 KiB
ArmAsm
339 lines
8.5 KiB
ArmAsm
/*
|
|
* linux/arch/arm/mm/cache-v7.S
|
|
*
|
|
* Copyright (C) 2001 Deep Blue Solutions Ltd.
|
|
* Copyright (C) 2005 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 is the "shell" of the ARMv7 processor support.
|
|
*/
|
|
#include <linux/linkage.h>
|
|
#include <linux/init.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/unwind.h>
|
|
|
|
#include "proc-macros.S"
|
|
|
|
/*
|
|
* v7_flush_icache_all()
|
|
*
|
|
* Flush the whole I-cache.
|
|
*
|
|
* Registers:
|
|
* r0 - set to 0
|
|
*/
|
|
ENTRY(v7_flush_icache_all)
|
|
mov r0, #0
|
|
ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable
|
|
ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate
|
|
mov pc, lr
|
|
ENDPROC(v7_flush_icache_all)
|
|
|
|
/*
|
|
* v7_flush_dcache_all()
|
|
*
|
|
* Flush the whole D-cache.
|
|
*
|
|
* Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
|
|
*
|
|
* - mm - mm_struct describing address space
|
|
*/
|
|
ENTRY(v7_flush_dcache_all)
|
|
dmb @ ensure ordering with previous memory accesses
|
|
mrc p15, 1, r0, c0, c0, 1 @ read clidr
|
|
ands r3, r0, #0x7000000 @ extract loc from clidr
|
|
mov r3, r3, lsr #23 @ left align loc bit field
|
|
beq finished @ if loc is 0, then no need to clean
|
|
mov r10, #0 @ start clean at cache level 0
|
|
loop1:
|
|
add r2, r10, r10, lsr #1 @ work out 3x current cache level
|
|
mov r1, r0, lsr r2 @ extract cache type bits from clidr
|
|
and r1, r1, #7 @ mask of the bits for current cache only
|
|
cmp r1, #2 @ see what cache we have at this level
|
|
blt skip @ skip if no cache, or just i-cache
|
|
mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr
|
|
isb @ isb to sych the new cssr&csidr
|
|
mrc p15, 1, r1, c0, c0, 0 @ read the new csidr
|
|
and r2, r1, #7 @ extract the length of the cache lines
|
|
add r2, r2, #4 @ add 4 (line length offset)
|
|
ldr r4, =0x3ff
|
|
ands r4, r4, r1, lsr #3 @ find maximum number on the way size
|
|
clz r5, r4 @ find bit position of way size increment
|
|
ldr r7, =0x7fff
|
|
ands r7, r7, r1, lsr #13 @ extract max number of the index size
|
|
loop2:
|
|
mov r9, r4 @ create working copy of max way size
|
|
loop3:
|
|
ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11
|
|
THUMB( lsl r6, r9, r5 )
|
|
THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11
|
|
ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11
|
|
THUMB( lsl r6, r7, r2 )
|
|
THUMB( orr r11, r11, r6 ) @ factor index number into r11
|
|
mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way
|
|
subs r9, r9, #1 @ decrement the way
|
|
bge loop3
|
|
subs r7, r7, #1 @ decrement the index
|
|
bge loop2
|
|
skip:
|
|
add r10, r10, #2 @ increment cache number
|
|
cmp r3, r10
|
|
bgt loop1
|
|
finished:
|
|
mov r10, #0 @ swith back to cache level 0
|
|
mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr
|
|
dsb
|
|
isb
|
|
mov pc, lr
|
|
ENDPROC(v7_flush_dcache_all)
|
|
|
|
/*
|
|
* v7_flush_cache_all()
|
|
*
|
|
* Flush the entire cache system.
|
|
* The data cache flush is now achieved using atomic clean / invalidates
|
|
* working outwards from L1 cache. This is done using Set/Way based cache
|
|
* maintainance instructions.
|
|
* The instruction cache can still be invalidated back to the point of
|
|
* unification in a single instruction.
|
|
*
|
|
*/
|
|
ENTRY(v7_flush_kern_cache_all)
|
|
ARM( stmfd sp!, {r4-r5, r7, r9-r11, lr} )
|
|
THUMB( stmfd sp!, {r4-r7, r9-r11, lr} )
|
|
bl v7_flush_dcache_all
|
|
mov r0, #0
|
|
ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable
|
|
ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate
|
|
ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} )
|
|
THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} )
|
|
mov pc, lr
|
|
ENDPROC(v7_flush_kern_cache_all)
|
|
|
|
/*
|
|
* v7_flush_cache_all()
|
|
*
|
|
* Flush all TLB entries in a particular address space
|
|
*
|
|
* - mm - mm_struct describing address space
|
|
*/
|
|
ENTRY(v7_flush_user_cache_all)
|
|
/*FALLTHROUGH*/
|
|
|
|
/*
|
|
* v7_flush_cache_range(start, end, flags)
|
|
*
|
|
* Flush a range of TLB entries in the specified address space.
|
|
*
|
|
* - start - start address (may not be aligned)
|
|
* - end - end address (exclusive, may not be aligned)
|
|
* - flags - vm_area_struct flags describing address space
|
|
*
|
|
* It is assumed that:
|
|
* - we have a VIPT cache.
|
|
*/
|
|
ENTRY(v7_flush_user_cache_range)
|
|
mov pc, lr
|
|
ENDPROC(v7_flush_user_cache_all)
|
|
ENDPROC(v7_flush_user_cache_range)
|
|
|
|
/*
|
|
* v7_coherent_kern_range(start,end)
|
|
*
|
|
* Ensure that the I and D caches are coherent within specified
|
|
* region. This is typically used when code has been written to
|
|
* a memory region, and will be executed.
|
|
*
|
|
* - start - virtual start address of region
|
|
* - end - virtual end address of region
|
|
*
|
|
* It is assumed that:
|
|
* - the Icache does not read data from the write buffer
|
|
*/
|
|
ENTRY(v7_coherent_kern_range)
|
|
/* FALLTHROUGH */
|
|
|
|
/*
|
|
* v7_coherent_user_range(start,end)
|
|
*
|
|
* Ensure that the I and D caches are coherent within specified
|
|
* region. This is typically used when code has been written to
|
|
* a memory region, and will be executed.
|
|
*
|
|
* - start - virtual start address of region
|
|
* - end - virtual end address of region
|
|
*
|
|
* It is assumed that:
|
|
* - the Icache does not read data from the write buffer
|
|
*/
|
|
ENTRY(v7_coherent_user_range)
|
|
UNWIND(.fnstart )
|
|
dcache_line_size r2, r3
|
|
sub r3, r2, #1
|
|
bic r12, r0, r3
|
|
1:
|
|
USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification
|
|
add r12, r12, r2
|
|
cmp r12, r1
|
|
blo 1b
|
|
dsb
|
|
icache_line_size r2, r3
|
|
sub r3, r2, #1
|
|
bic r12, r0, r3
|
|
2:
|
|
USER( mcr p15, 0, r12, c7, c5, 1 ) @ invalidate I line
|
|
add r12, r12, r2
|
|
cmp r12, r1
|
|
blo 2b
|
|
3:
|
|
mov r0, #0
|
|
ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable
|
|
ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB
|
|
dsb
|
|
isb
|
|
mov pc, lr
|
|
|
|
/*
|
|
* Fault handling for the cache operation above. If the virtual address in r0
|
|
* isn't mapped, just try the next page.
|
|
*/
|
|
9001:
|
|
mov r12, r12, lsr #12
|
|
mov r12, r12, lsl #12
|
|
add r12, r12, #4096
|
|
b 3b
|
|
UNWIND(.fnend )
|
|
ENDPROC(v7_coherent_kern_range)
|
|
ENDPROC(v7_coherent_user_range)
|
|
|
|
/*
|
|
* v7_flush_kern_dcache_area(void *addr, size_t size)
|
|
*
|
|
* Ensure that the data held in the page kaddr is written back
|
|
* to the page in question.
|
|
*
|
|
* - addr - kernel address
|
|
* - size - region size
|
|
*/
|
|
ENTRY(v7_flush_kern_dcache_area)
|
|
dcache_line_size r2, r3
|
|
add r1, r0, r1
|
|
1:
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line / unified line
|
|
add r0, r0, r2
|
|
cmp r0, r1
|
|
blo 1b
|
|
dsb
|
|
mov pc, lr
|
|
ENDPROC(v7_flush_kern_dcache_area)
|
|
|
|
/*
|
|
* v7_dma_inv_range(start,end)
|
|
*
|
|
* Invalidate the data cache within the specified region; we will
|
|
* be performing a DMA operation in this region and we want to
|
|
* purge old data in the cache.
|
|
*
|
|
* - start - virtual start address of region
|
|
* - end - virtual end address of region
|
|
*/
|
|
v7_dma_inv_range:
|
|
dcache_line_size r2, r3
|
|
sub r3, r2, #1
|
|
tst r0, r3
|
|
bic r0, r0, r3
|
|
mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line
|
|
|
|
tst r1, r3
|
|
bic r1, r1, r3
|
|
mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D / U line
|
|
1:
|
|
mcr p15, 0, r0, c7, c6, 1 @ invalidate D / U line
|
|
add r0, r0, r2
|
|
cmp r0, r1
|
|
blo 1b
|
|
dsb
|
|
mov pc, lr
|
|
ENDPROC(v7_dma_inv_range)
|
|
|
|
/*
|
|
* v7_dma_clean_range(start,end)
|
|
* - start - virtual start address of region
|
|
* - end - virtual end address of region
|
|
*/
|
|
v7_dma_clean_range:
|
|
dcache_line_size r2, r3
|
|
sub r3, r2, #1
|
|
bic r0, r0, r3
|
|
1:
|
|
mcr p15, 0, r0, c7, c10, 1 @ clean D / U line
|
|
add r0, r0, r2
|
|
cmp r0, r1
|
|
blo 1b
|
|
dsb
|
|
mov pc, lr
|
|
ENDPROC(v7_dma_clean_range)
|
|
|
|
/*
|
|
* v7_dma_flush_range(start,end)
|
|
* - start - virtual start address of region
|
|
* - end - virtual end address of region
|
|
*/
|
|
ENTRY(v7_dma_flush_range)
|
|
dcache_line_size r2, r3
|
|
sub r3, r2, #1
|
|
bic r0, r0, r3
|
|
1:
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line
|
|
add r0, r0, r2
|
|
cmp r0, r1
|
|
blo 1b
|
|
dsb
|
|
mov pc, lr
|
|
ENDPROC(v7_dma_flush_range)
|
|
|
|
/*
|
|
* dma_map_area(start, size, dir)
|
|
* - start - kernel virtual start address
|
|
* - size - size of region
|
|
* - dir - DMA direction
|
|
*/
|
|
ENTRY(v7_dma_map_area)
|
|
add r1, r1, r0
|
|
teq r2, #DMA_FROM_DEVICE
|
|
beq v7_dma_inv_range
|
|
b v7_dma_clean_range
|
|
ENDPROC(v7_dma_map_area)
|
|
|
|
/*
|
|
* dma_unmap_area(start, size, dir)
|
|
* - start - kernel virtual start address
|
|
* - size - size of region
|
|
* - dir - DMA direction
|
|
*/
|
|
ENTRY(v7_dma_unmap_area)
|
|
add r1, r1, r0
|
|
teq r2, #DMA_TO_DEVICE
|
|
bne v7_dma_inv_range
|
|
mov pc, lr
|
|
ENDPROC(v7_dma_unmap_area)
|
|
|
|
__INITDATA
|
|
|
|
.type v7_cache_fns, #object
|
|
ENTRY(v7_cache_fns)
|
|
.long v7_flush_icache_all
|
|
.long v7_flush_kern_cache_all
|
|
.long v7_flush_user_cache_all
|
|
.long v7_flush_user_cache_range
|
|
.long v7_coherent_kern_range
|
|
.long v7_coherent_user_range
|
|
.long v7_flush_kern_dcache_area
|
|
.long v7_dma_map_area
|
|
.long v7_dma_unmap_area
|
|
.long v7_dma_flush_range
|
|
.size v7_cache_fns, . - v7_cache_fns
|