linux/arch/arm64/mm/pageattr.c
James Morse 5ebe3a44cc arm64: hibernate: Support DEBUG_PAGEALLOC
DEBUG_PAGEALLOC removes the valid bit of page table entries to prevent
any access to unallocated memory. Hibernate uses this as a hint that those
pages don't need to be saved/restored. This patch adds the
kernel_page_present() function it uses.

hibernate.c copies the resume kernel's linear map for use during restore.
Add _copy_pte() to fill-in the holes made by DEBUG_PAGEALLOC in the resume
kernel, so we can restore data the original kernel had at these addresses.

Finally, DEBUG_PAGEALLOC means the linear-map alias of KERNEL_START to
KERNEL_END may have holes in it, so we can't lazily clean this whole
area to the PoC. Only clean the new mmuoff region, and the kernel/kvm
idmaps.

This reverts commit da24eb1f3f.

Reported-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-08-25 18:00:30 +01:00

182 lines
4.7 KiB
C

/*
* Copyright (c) 2014, The Linux Foundation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 and
* only version 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
struct page_change_data {
pgprot_t set_mask;
pgprot_t clear_mask;
};
static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
void *data)
{
struct page_change_data *cdata = data;
pte_t pte = *ptep;
pte = clear_pte_bit(pte, cdata->clear_mask);
pte = set_pte_bit(pte, cdata->set_mask);
set_pte(ptep, pte);
return 0;
}
/*
* This function assumes that the range is mapped with PAGE_SIZE pages.
*/
static int __change_memory_common(unsigned long start, unsigned long size,
pgprot_t set_mask, pgprot_t clear_mask)
{
struct page_change_data data;
int ret;
data.set_mask = set_mask;
data.clear_mask = clear_mask;
ret = apply_to_page_range(&init_mm, start, size, change_page_range,
&data);
flush_tlb_kernel_range(start, start + size);
return ret;
}
static int change_memory_common(unsigned long addr, int numpages,
pgprot_t set_mask, pgprot_t clear_mask)
{
unsigned long start = addr;
unsigned long size = PAGE_SIZE*numpages;
unsigned long end = start + size;
struct vm_struct *area;
if (!PAGE_ALIGNED(addr)) {
start &= PAGE_MASK;
end = start + size;
WARN_ON_ONCE(1);
}
/*
* Kernel VA mappings are always live, and splitting live section
* mappings into page mappings may cause TLB conflicts. This means
* we have to ensure that changing the permission bits of the range
* we are operating on does not result in such splitting.
*
* Let's restrict ourselves to mappings created by vmalloc (or vmap).
* Those are guaranteed to consist entirely of page mappings, and
* splitting is never needed.
*
* So check whether the [addr, addr + size) interval is entirely
* covered by precisely one VM area that has the VM_ALLOC flag set.
*/
area = find_vm_area((void *)addr);
if (!area ||
end > (unsigned long)area->addr + area->size ||
!(area->flags & VM_ALLOC))
return -EINVAL;
if (!numpages)
return 0;
return __change_memory_common(start, size, set_mask, clear_mask);
}
int set_memory_ro(unsigned long addr, int numpages)
{
return change_memory_common(addr, numpages,
__pgprot(PTE_RDONLY),
__pgprot(PTE_WRITE));
}
int set_memory_rw(unsigned long addr, int numpages)
{
return change_memory_common(addr, numpages,
__pgprot(PTE_WRITE),
__pgprot(PTE_RDONLY));
}
int set_memory_nx(unsigned long addr, int numpages)
{
return change_memory_common(addr, numpages,
__pgprot(PTE_PXN),
__pgprot(0));
}
EXPORT_SYMBOL_GPL(set_memory_nx);
int set_memory_x(unsigned long addr, int numpages)
{
return change_memory_common(addr, numpages,
__pgprot(0),
__pgprot(PTE_PXN));
}
EXPORT_SYMBOL_GPL(set_memory_x);
#ifdef CONFIG_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
unsigned long addr = (unsigned long) page_address(page);
if (enable)
__change_memory_common(addr, PAGE_SIZE * numpages,
__pgprot(PTE_VALID),
__pgprot(0));
else
__change_memory_common(addr, PAGE_SIZE * numpages,
__pgprot(0),
__pgprot(PTE_VALID));
}
#ifdef CONFIG_HIBERNATION
/*
* When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
* is used to determine if a linear map page has been marked as not-valid by
* CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
* This is based on kern_addr_valid(), which almost does what we need.
*
* Because this is only called on the kernel linear map, p?d_sect() implies
* p?d_present(). When debug_pagealloc is enabled, sections mappings are
* disabled.
*/
bool kernel_page_present(struct page *page)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long addr = (unsigned long)page_address(page);
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd))
return false;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
return false;
if (pud_sect(*pud))
return true;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return false;
if (pmd_sect(*pmd))
return true;
pte = pte_offset_kernel(pmd, addr);
return pte_valid(*pte);
}
#endif /* CONFIG_HIBERNATION */
#endif /* CONFIG_DEBUG_PAGEALLOC */