1
linux/arch/arm/mm/copypage-v4mc.c
Catalin Marinas c01778001a ARM: 6379/1: Assume new page cache pages have dirty D-cache
There are places in Linux where writes to newly allocated page cache
pages happen without a subsequent call to flush_dcache_page() (several
PIO drivers including USB HCD). This patch changes the meaning of
PG_arch_1 to be PG_dcache_clean and always flush the D-cache for a newly
mapped page in update_mmu_cache().

The patch also sets the PG_arch_1 bit in the DMA cache maintenance
function to avoid additional cache flushing in update_mmu_cache().

Tested-by: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-09-19 12:17:43 +01:00

121 lines
3.6 KiB
C

/*
* linux/arch/arm/lib/copypage-armv4mc.S
*
* Copyright (C) 1995-2005 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 handles the mini data cache, as found on SA11x0 and XScale
* processors. When we copy a user page page, we map it in such a way
* that accesses to this page will not touch the main data cache, but
* will be cached in the mini data cache. This prevents us thrashing
* the main data cache on page faults.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include "mm.h"
/*
* 0xffff8000 to 0xffffffff is reserved for any ARM architecture
* specific hacks for copying pages efficiently.
*/
#define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
L_PTE_MT_MINICACHE)
static DEFINE_SPINLOCK(minicache_lock);
/*
* ARMv4 mini-dcache optimised copy_user_highpage
*
* We flush the destination cache lines just before we write the data into the
* corresponding address. Since the Dcache is read-allocate, this removes the
* Dcache aliasing issue. The writes will be forwarded to the write buffer,
* and merged as appropriate.
*
* Note: We rely on all ARMv4 processors implementing the "invalidate D line"
* instruction. If your processor does not supply this, you have to write your
* own copy_user_highpage that does the right thing.
*/
static void __naked
mc_copy_user_page(void *from, void *to)
{
asm volatile(
"stmfd sp!, {r4, lr} @ 2\n\
mov r4, %2 @ 1\n\
ldmia %0!, {r2, r3, ip, lr} @ 4\n\
1: mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\
stmia %1!, {r2, r3, ip, lr} @ 4\n\
ldmia %0!, {r2, r3, ip, lr} @ 4+1\n\
stmia %1!, {r2, r3, ip, lr} @ 4\n\
ldmia %0!, {r2, r3, ip, lr} @ 4\n\
mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\
stmia %1!, {r2, r3, ip, lr} @ 4\n\
ldmia %0!, {r2, r3, ip, lr} @ 4\n\
subs r4, r4, #1 @ 1\n\
stmia %1!, {r2, r3, ip, lr} @ 4\n\
ldmneia %0!, {r2, r3, ip, lr} @ 4\n\
bne 1b @ 1\n\
ldmfd sp!, {r4, pc} @ 3"
:
: "r" (from), "r" (to), "I" (PAGE_SIZE / 64));
}
void v4_mc_copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
void *kto = kmap_atomic(to, KM_USER1);
if (!test_and_set_bit(PG_dcache_clean, &from->flags))
__flush_dcache_page(page_mapping(from), from);
spin_lock(&minicache_lock);
set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
flush_tlb_kernel_page(0xffff8000);
mc_copy_user_page((void *)0xffff8000, kto);
spin_unlock(&minicache_lock);
kunmap_atomic(kto, KM_USER1);
}
/*
* ARMv4 optimised clear_user_page
*/
void v4_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
{
void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
asm volatile("\
mov r1, %2 @ 1\n\
mov r2, #0 @ 1\n\
mov r3, #0 @ 1\n\
mov ip, #0 @ 1\n\
mov lr, #0 @ 1\n\
1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
stmia %0!, {r2, r3, ip, lr} @ 4\n\
stmia %0!, {r2, r3, ip, lr} @ 4\n\
mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
stmia %0!, {r2, r3, ip, lr} @ 4\n\
stmia %0!, {r2, r3, ip, lr} @ 4\n\
subs r1, r1, #1 @ 1\n\
bne 1b @ 1"
: "=r" (ptr)
: "0" (kaddr), "I" (PAGE_SIZE / 64)
: "r1", "r2", "r3", "ip", "lr");
kunmap_atomic(kaddr, KM_USER0);
}
struct cpu_user_fns v4_mc_user_fns __initdata = {
.cpu_clear_user_highpage = v4_mc_clear_user_highpage,
.cpu_copy_user_highpage = v4_mc_copy_user_highpage,
};