mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-13 21:16:53 +07:00
c55191e96c
On arm64, we use block mappings and contiguous hints to map the linear region, to minimize the TLB footprint. However, this means that the entire region is mapped using read/write permissions, which we cannot modify at page granularity without having to take intrusive measures to prevent TLB conflicts. This means the linear aliases of pages belonging to read-only mappings (executable or otherwise) in the vmalloc region are also mapped read/write, and could potentially be abused to modify things like module code, bpf JIT code or other read-only data. So let's fix this, by extending the set_memory_ro/rw routines to take the linear alias into account. The consequence of enabling this is that we can no longer use block mappings or contiguous hints, so in cases where the TLB footprint of the linear region is a bottleneck, performance may be affected. Therefore, allow this feature to be runtime en/disabled, by setting rodata=full (or 'on' to disable just this enhancement, or 'off' to disable read-only mappings for code and r/o data entirely) on the kernel command line. Also, allow the default value to be set via a Kconfig option. Tested-by: Laura Abbott <labbott@redhat.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
209 lines
5.6 KiB
C
209 lines
5.6 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/set_memory.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
struct page_change_data {
|
|
pgprot_t set_mask;
|
|
pgprot_t clear_mask;
|
|
};
|
|
|
|
bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED);
|
|
|
|
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 = READ_ONCE(*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;
|
|
int i;
|
|
|
|
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;
|
|
|
|
/*
|
|
* If we are manipulating read-only permissions, apply the same
|
|
* change to the linear mapping of the pages that back this VM area.
|
|
*/
|
|
if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
|
|
pgprot_val(clear_mask) == PTE_RDONLY)) {
|
|
for (i = 0; i < area->nr_pages; i++) {
|
|
__change_memory_common((u64)page_address(area->pages[i]),
|
|
PAGE_SIZE, set_mask, clear_mask);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Get rid of potentially aliasing lazily unmapped vm areas that may
|
|
* have permissions set that deviate from the ones we are setting here.
|
|
*/
|
|
vm_unmap_aliases();
|
|
|
|
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);
|
|
|
|
int set_memory_valid(unsigned long addr, int numpages, int enable)
|
|
{
|
|
if (enable)
|
|
return __change_memory_common(addr, PAGE_SIZE * numpages,
|
|
__pgprot(PTE_VALID),
|
|
__pgprot(0));
|
|
else
|
|
return __change_memory_common(addr, PAGE_SIZE * numpages,
|
|
__pgprot(0),
|
|
__pgprot(PTE_VALID));
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_PAGEALLOC
|
|
void __kernel_map_pages(struct page *page, int numpages, int enable)
|
|
{
|
|
set_memory_valid((unsigned long)page_address(page), numpages, enable);
|
|
}
|
|
#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 *pgdp;
|
|
pud_t *pudp, pud;
|
|
pmd_t *pmdp, pmd;
|
|
pte_t *ptep;
|
|
unsigned long addr = (unsigned long)page_address(page);
|
|
|
|
pgdp = pgd_offset_k(addr);
|
|
if (pgd_none(READ_ONCE(*pgdp)))
|
|
return false;
|
|
|
|
pudp = pud_offset(pgdp, addr);
|
|
pud = READ_ONCE(*pudp);
|
|
if (pud_none(pud))
|
|
return false;
|
|
if (pud_sect(pud))
|
|
return true;
|
|
|
|
pmdp = pmd_offset(pudp, addr);
|
|
pmd = READ_ONCE(*pmdp);
|
|
if (pmd_none(pmd))
|
|
return false;
|
|
if (pmd_sect(pmd))
|
|
return true;
|
|
|
|
ptep = pte_offset_kernel(pmdp, addr);
|
|
return pte_valid(READ_ONCE(*ptep));
|
|
}
|
|
#endif /* CONFIG_HIBERNATION */
|
|
#endif /* CONFIG_DEBUG_PAGEALLOC */
|