mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2025-08-17 17:47:28 +00:00
96d81e4766
walk_page_range_novma() is rather confusing - it supports two modes, one used often, the other used only for debugging. The first mode is the common case of traversal of kernel page tables, which is what nearly all callers use this for. Secondly it provides an unusual debugging interface that allows for the traversal of page tables in a userland range of memory even for that memory which is not described by a VMA. It is far from certain that such page tables should even exist, but perhaps this is precisely why it is useful as a debugging mechanism. As a result, this is utilised by ptdump only. Historically, things were reversed - ptdump was the only user, and other parts of the kernel evolved to use the kernel page table walking here. Since we have some complicated and confusing locking rules for the novma case, it makes sense to separate the two usages into their own functions. Doing this also provide self-documentation as to the intent of the caller - are they doing something rather unusual or are they simply doing a standard kernel page table walk? We therefore establish two separate functions - walk_page_range_debug() for this single usage, and walk_kernel_page_table_range() for general kernel page table walking. The walk_page_range_debug() function is currently used to traverse both userland and kernel mappings, so we maintain this and in the case of kernel mappings being traversed, we have walk_page_range_debug() invoke walk_kernel_page_table_range() internally. We additionally make walk_page_range_debug() internal to mm. Link: https://lkml.kernel.org/r/20250605135104.90720-1-lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Acked-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: David Hildenbrand <david@redhat.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Barry Song <baohua@kernel.org> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Jann Horn <jannh@google.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: WANG Xuerui <kernel@xen0n.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
116 lines
2.8 KiB
C
116 lines
2.8 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* OpenRISC Linux
|
|
*
|
|
* Linux architectural port borrowing liberally from similar works of
|
|
* others. All original copyrights apply as per the original source
|
|
* declaration.
|
|
*
|
|
* Modifications for the OpenRISC architecture:
|
|
* Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
|
|
* Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
|
|
*
|
|
* DMA mapping callbacks...
|
|
*/
|
|
|
|
#include <linux/dma-map-ops.h>
|
|
#include <linux/pagewalk.h>
|
|
|
|
#include <asm/cpuinfo.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/spr_defs.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
static int
|
|
page_set_nocache(pte_t *pte, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk)
|
|
{
|
|
pte_val(*pte) |= _PAGE_CI;
|
|
|
|
/*
|
|
* Flush the page out of the TLB so that the new page flags get
|
|
* picked up next time there's an access
|
|
*/
|
|
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
|
|
|
|
/* Flush page out of dcache */
|
|
local_dcache_range_flush(__pa(addr), __pa(next));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct mm_walk_ops set_nocache_walk_ops = {
|
|
.pte_entry = page_set_nocache,
|
|
};
|
|
|
|
static int
|
|
page_clear_nocache(pte_t *pte, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk)
|
|
{
|
|
pte_val(*pte) &= ~_PAGE_CI;
|
|
|
|
/*
|
|
* Flush the page out of the TLB so that the new page flags get
|
|
* picked up next time there's an access
|
|
*/
|
|
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct mm_walk_ops clear_nocache_walk_ops = {
|
|
.pte_entry = page_clear_nocache,
|
|
};
|
|
|
|
void *arch_dma_set_uncached(void *cpu_addr, size_t size)
|
|
{
|
|
unsigned long va = (unsigned long)cpu_addr;
|
|
int error;
|
|
|
|
/*
|
|
* We need to iterate through the pages, clearing the dcache for
|
|
* them and setting the cache-inhibit bit.
|
|
*/
|
|
mmap_write_lock(&init_mm);
|
|
error = walk_kernel_page_table_range(va, va + size,
|
|
&set_nocache_walk_ops, NULL, NULL);
|
|
mmap_write_unlock(&init_mm);
|
|
|
|
if (error)
|
|
return ERR_PTR(error);
|
|
return cpu_addr;
|
|
}
|
|
|
|
void arch_dma_clear_uncached(void *cpu_addr, size_t size)
|
|
{
|
|
unsigned long va = (unsigned long)cpu_addr;
|
|
|
|
mmap_write_lock(&init_mm);
|
|
/* walk_page_range shouldn't be able to fail here */
|
|
WARN_ON(walk_kernel_page_table_range(va, va + size,
|
|
&clear_nocache_walk_ops, NULL, NULL));
|
|
mmap_write_unlock(&init_mm);
|
|
}
|
|
|
|
void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
|
|
enum dma_data_direction dir)
|
|
{
|
|
switch (dir) {
|
|
case DMA_TO_DEVICE:
|
|
/* Flush the dcache for the requested range */
|
|
local_dcache_range_flush(addr, addr + size);
|
|
break;
|
|
case DMA_FROM_DEVICE:
|
|
/* Invalidate the dcache for the requested range */
|
|
local_dcache_range_inv(addr, addr + size);
|
|
break;
|
|
default:
|
|
/*
|
|
* NOTE: If dir == DMA_BIDIRECTIONAL then there's no need to
|
|
* flush nor invalidate the cache here as the area will need
|
|
* to be manually synced anyway.
|
|
*/
|
|
break;
|
|
}
|
|
}
|