linux/arch/arm/mm/copypage-v4mc.c
Matthew Wilcox (Oracle) 8b5989f333 arm: implement the new page table range API
Add set_ptes(), update_mmu_cache_range(), flush_dcache_folio() and
flush_icache_pages().  Change the PG_dcache_clear flag from being per-page
to per-folio which makes __dma_page_dev_to_cpu() a bit more exciting. 
Also add flush_cache_pages(), even though this isn't used by generic code
(yet?)

[m.szyprowski@samsung.com: fix potential endless loop in __dma_page_dev_to_cpu()]
  Link: https://lkml.kernel.org/r/20230809172737.3574190-1-m.szyprowski@samsung.com
[willy@infradead.org: fix folio conversion in __dma_page_dev_to_cpu()]
  Link: https://lkml.kernel.org/r/20230823191852.1556561-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20230802151406.3735276-10-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-24 16:20:20 -07:00

114 lines
3.3 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/lib/copypage-armv4mc.S
*
* Copyright (C) 1995-2005 Russell King
*
* 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 <linux/pagemap.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include "mm.h"
#define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
L_PTE_MT_MINICACHE)
static DEFINE_RAW_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 mc_copy_user_page(void *from, void *to)
{
int tmp;
asm volatile ("\
.syntax unified\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 %2, %2, #1 @ 1\n\
stmia %1!, {r2, r3, ip, lr} @ 4\n\
ldmiane %0!, {r2, r3, ip, lr} @ 4\n\
bne 1b @ "
: "+&r" (from), "+&r" (to), "=&r" (tmp)
: "2" (PAGE_SIZE / 64)
: "r2", "r3", "ip", "lr");
}
void v4_mc_copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
struct folio *src = page_folio(from);
void *kto = kmap_atomic(to);
if (!test_and_set_bit(PG_dcache_clean, &src->flags))
__flush_dcache_folio(folio_flush_mapping(src), src);
raw_spin_lock(&minicache_lock);
set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
raw_spin_unlock(&minicache_lock);
kunmap_atomic(kto);
}
/*
* ARMv4 optimised clear_user_page
*/
void v4_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
{
void *ptr, *kaddr = kmap_atomic(page);
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);
}
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,
};