linux/arch/arm/mm/proc-arm926.S
Linus Walleij 7b749aad1f ARM: 9393/1: mm: Use conditionals for CFI branches
Commit 9385/2 introduced a few branches inside function
prototypes when using CFI in order to deal with the situation
where CFI inserts a few bytes of function information in front
of the symbol.

This is not good for older CPUs where every cycle counts.

Commit 9386/2 alleviated the situation a bit by using aliases
for the cache functions with identical signatures.

This leaves the coherent cache flush functions
*_coherent_kern_range() with these branches to the corresponing
*_coherent_user_range() around, since their return type differ and
they therefore cannot be aliased.

Solve this by a simple ifdef so at least we can use fallthroughs
when compiling without CFI enabled.

Link: https://lore.kernel.org/linux-arm-kernel/Zi+e9M%2Ff5b%2FSto9H@shell.armlinux.org.uk/

Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2024-05-07 10:30:24 +01:00

498 lines
12 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* linux/arch/arm/mm/proc-arm926.S: MMU functions for ARM926EJ-S
*
* Copyright (C) 1999-2001 ARM Limited
* Copyright (C) 2000 Deep Blue Solutions Ltd.
* hacked for non-paged-MM by Hyok S. Choi, 2003.
*
* These are the low level assembler for performing cache and TLB
* functions on the arm926.
*
* CONFIG_CPU_ARM926_CPU_IDLE -> nohlt
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/cfi_types.h>
#include <linux/pgtable.h>
#include <asm/assembler.h>
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include "proc-macros.S"
/*
* This is the maximum size of an area which will be invalidated
* using the single invalidate entry instructions. Anything larger
* than this, and we go for the whole cache.
*
* This value should be chosen such that we choose the cheapest
* alternative.
*/
#define CACHE_DLIMIT 16384
/*
* the cache line size of the I and D cache
*/
#define CACHE_DLINESIZE 32
.text
/*
* cpu_arm926_proc_init()
*/
SYM_TYPED_FUNC_START(cpu_arm926_proc_init)
ret lr
SYM_FUNC_END(cpu_arm926_proc_init)
/*
* cpu_arm926_proc_fin()
*/
SYM_TYPED_FUNC_START(cpu_arm926_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
SYM_FUNC_END(cpu_arm926_proc_fin)
/*
* cpu_arm926_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"
SYM_TYPED_FUNC_START(cpu_arm926_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
SYM_FUNC_END(cpu_arm926_reset)
.popsection
/*
* cpu_arm926_do_idle()
*
* Called with IRQs disabled
*/
.align 10
SYM_TYPED_FUNC_START(cpu_arm926_do_idle)
mov r0, #0
mrc p15, 0, r1, c1, c0, 0 @ Read control register
mcr p15, 0, r0, c7, c10, 4 @ Drain write buffer
bic r2, r1, #1 << 12
mrs r3, cpsr @ Disable FIQs while Icache
orr ip, r3, #PSR_F_BIT @ is disabled
msr cpsr_c, ip
mcr p15, 0, r2, c1, c0, 0 @ Disable I cache
mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt
mcr p15, 0, r1, c1, c0, 0 @ Restore ICache enable
msr cpsr_c, r3 @ Restore FIQ state
ret lr
SYM_FUNC_END(cpu_arm926_do_idle)
/*
* flush_icache_all()
*
* Unconditionally clean and invalidate the entire icache.
*/
SYM_TYPED_FUNC_START(arm926_flush_icache_all)
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
ret lr
SYM_FUNC_END(arm926_flush_icache_all)
/*
* flush_user_cache_all()
*
* Clean and invalidate all cache entries in a particular
* address space.
*/
SYM_FUNC_ALIAS(arm926_flush_user_cache_all, arm926_flush_kern_cache_all)
/*
* flush_kern_cache_all()
*
* Clean and invalidate the entire cache.
*/
SYM_TYPED_FUNC_START(arm926_flush_kern_cache_all)
mov r2, #VM_EXEC
mov ip, #0
__flush_whole_cache:
#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache
#else
1: mrc p15, 0, APSR_nzcv, c7, c14, 3 @ test,clean,invalidate
bne 1b
#endif
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
SYM_FUNC_END(arm926_flush_kern_cache_all)
/*
* 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
*/
SYM_TYPED_FUNC_START(arm926_flush_user_cache_range)
mov ip, #0
sub r3, r1, r0 @ calculate total size
cmp r3, #CACHE_DLIMIT
bgt __flush_whole_cache
1: tst r2, #VM_EXEC
#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
#else
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D entry
mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D entry
mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
#endif
cmp r0, r1
blo 1b
tst r2, #VM_EXEC
mcrne p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
SYM_FUNC_END(arm926_flush_user_cache_range)
/*
* 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
*/
SYM_TYPED_FUNC_START(arm926_coherent_kern_range)
#ifdef CONFIG_CFI_CLANG /* Fallthrough if !CFI */
b arm926_coherent_user_range
#endif
SYM_FUNC_END(arm926_coherent_kern_range)
/*
* 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
*/
SYM_TYPED_FUNC_START(arm926_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
SYM_FUNC_END(arm926_coherent_user_range)
/*
* 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
*/
SYM_TYPED_FUNC_START(arm926_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
SYM_FUNC_END(arm926_flush_kern_dcache_area)
/*
* 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)
*/
arm926_dma_inv_range:
#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
tst 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
#endif
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
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)
*/
arm926_dma_clean_range:
#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
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
#endif
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
*/
SYM_TYPED_FUNC_START(arm926_dma_flush_range)
bic r0, r0, #CACHE_DLINESIZE - 1
1:
#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry
#else
mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
#endif
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
mcr p15, 0, r0, c7, c10, 4 @ drain WB
ret lr
SYM_FUNC_END(arm926_dma_flush_range)
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
SYM_TYPED_FUNC_START(arm926_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm926_dma_clean_range
bcs arm926_dma_inv_range
b arm926_dma_flush_range
SYM_FUNC_END(arm926_dma_map_area)
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
SYM_TYPED_FUNC_START(arm926_dma_unmap_area)
ret lr
SYM_FUNC_END(arm926_dma_unmap_area)
SYM_TYPED_FUNC_START(cpu_arm926_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
mcr p15, 0, r0, c7, c10, 4 @ drain WB
ret lr
SYM_FUNC_END(cpu_arm926_dcache_clean_area)
/* =============================== PageTable ============================== */
/*
* cpu_arm926_switch_mm(pgd)
*
* Set the translation base pointer to be as described by pgd.
*
* pgd: new page tables
*/
.align 5
SYM_TYPED_FUNC_START(cpu_arm926_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'
1: mrc p15, 0, APSR_nzcv, c7, c14, 3 @ test,clean,invalidate
bne 1b
#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
SYM_FUNC_END(cpu_arm926_switch_mm)
/*
* cpu_arm926_set_pte_ext(ptep, pte, ext)
*
* Set a PTE and flush it out
*/
.align 5
SYM_TYPED_FUNC_START(cpu_arm926_set_pte_ext)
#ifdef CONFIG_MMU
armv3_set_pte_ext
mov r0, r0
#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
mcr p15, 0, r0, c7, c10, 1 @ clean D entry
#endif
mcr p15, 0, r0, c7, c10, 4 @ drain WB
#endif
ret lr
SYM_FUNC_END(cpu_arm926_set_pte_ext)
/* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
.globl cpu_arm926_suspend_size
.equ cpu_arm926_suspend_size, 4 * 3
#ifdef CONFIG_ARM_CPU_SUSPEND
SYM_TYPED_FUNC_START(cpu_arm926_do_suspend)
stmfd sp!, {r4 - r6, lr}
mrc p15, 0, r4, c13, c0, 0 @ PID
mrc p15, 0, r5, c3, c0, 0 @ Domain ID
mrc p15, 0, r6, c1, c0, 0 @ Control register
stmia r0, {r4 - r6}
ldmfd sp!, {r4 - r6, pc}
SYM_FUNC_END(cpu_arm926_do_suspend)
SYM_TYPED_FUNC_START(cpu_arm926_do_resume)
mov ip, #0
mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs
mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches
ldmia r0, {r4 - r6}
mcr p15, 0, r4, c13, c0, 0 @ PID
mcr p15, 0, r5, c3, c0, 0 @ Domain ID
mcr p15, 0, r1, c2, c0, 0 @ TTB address
mov r0, r6 @ control register
b cpu_resume_mmu
SYM_FUNC_END(cpu_arm926_do_resume)
#endif
.type __arm926_setup, #function
__arm926_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
#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
mov r0, #4 @ disable write-back on caches explicitly
mcr p15, 7, r0, c15, c0, 0
#endif
adr r5, arm926_crval
ldmia r5, {r5, r6}
mrc p15, 0, r0, c1, c0 @ get control register v4
bic r0, r0, r5
orr r0, r0, r6
#ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
orr r0, r0, #0x4000 @ .1.. .... .... ....
#endif
ret lr
.size __arm926_setup, . - __arm926_setup
/*
* R
* .RVI ZFRS BLDP WCAM
* .011 0001 ..11 0101
*
*/
.type arm926_crval, #object
arm926_crval:
crval clear=0x00007f3f, mmuset=0x00003135, ucset=0x00001134
__INITDATA
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
define_processor_functions arm926, dabort=v5tj_early_abort, pabort=legacy_pabort, suspend=1
.section ".rodata"
string cpu_arch_name, "armv5tej"
string cpu_elf_name, "v5"
string cpu_arm926_name, "ARM926EJ-S"
.align
.section ".proc.info.init", "a"
.type __arm926_proc_info,#object
__arm926_proc_info:
.long 0x41069260 @ ARM926EJ-S (v5TEJ)
.long 0xff0ffff0
.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
initfn __arm926_setup, __arm926_proc_info
.long cpu_arch_name
.long cpu_elf_name
.long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA
.long cpu_arm926_name
.long arm926_processor_functions
.long v4wbi_tlb_fns
.long v4wb_user_fns
.long arm926_cache_fns
.size __arm926_proc_info, . - __arm926_proc_info