mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-30 12:49:36 +00:00
![Mel Gorman](/assets/img/avatar_default.png)
When overcommit is disabled, the core VM accounts for pages used by anonymous
shared, private mappings and special mappings. It keeps track of VMAs that
should be accounted for with VM_ACCOUNT and VMAs that never had a reserve
with VM_NORESERVE.
Overcommit for hugetlbfs is much riskier than overcommit for base pages
due to contiguity requirements. It avoids overcommiting on both shared and
private mappings using reservation counters that are checked and updated
during mmap(). This ensures (within limits) that hugepages exist in the
future when faults occurs or it is too easy to applications to be SIGKILLed.
As hugetlbfs makes its own reservations of a different unit to the base page
size, VM_ACCOUNT should never be set. Even if the units were correct, we would
double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may
be set because an application can request no reserves be made for hugetlbfs
at the risk of getting killed later.
With commit fc8744adc8
, VM_NORESERVE and
VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This
breaks the accounting for both the core VM and hugetlbfs, can trigger an
OOM storm when hugepage pools are too small lockups and corrupted counters
otherwise are used. This patch brings hugetlbfs more in line with how the
core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
318 lines
7.6 KiB
C
318 lines
7.6 KiB
C
/*
|
|
* mm/mprotect.c
|
|
*
|
|
* (C) Copyright 1994 Linus Torvalds
|
|
* (C) Copyright 2002 Christoph Hellwig
|
|
*
|
|
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
|
|
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/shm.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/security.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/personality.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/migrate.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#ifndef pgprot_modify
|
|
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
|
|
{
|
|
return newprot;
|
|
}
|
|
#endif
|
|
|
|
static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pte_t *pte, oldpte;
|
|
spinlock_t *ptl;
|
|
|
|
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
|
|
arch_enter_lazy_mmu_mode();
|
|
do {
|
|
oldpte = *pte;
|
|
if (pte_present(oldpte)) {
|
|
pte_t ptent;
|
|
|
|
ptent = ptep_modify_prot_start(mm, addr, pte);
|
|
ptent = pte_modify(ptent, newprot);
|
|
|
|
/*
|
|
* Avoid taking write faults for pages we know to be
|
|
* dirty.
|
|
*/
|
|
if (dirty_accountable && pte_dirty(ptent))
|
|
ptent = pte_mkwrite(ptent);
|
|
|
|
ptep_modify_prot_commit(mm, addr, pte, ptent);
|
|
} else if (PAGE_MIGRATION && !pte_file(oldpte)) {
|
|
swp_entry_t entry = pte_to_swp_entry(oldpte);
|
|
|
|
if (is_write_migration_entry(entry)) {
|
|
/*
|
|
* A protection check is difficult so
|
|
* just be safe and disable write
|
|
*/
|
|
make_migration_entry_read(&entry);
|
|
set_pte_at(mm, addr, pte,
|
|
swp_entry_to_pte(entry));
|
|
}
|
|
}
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
arch_leave_lazy_mmu_mode();
|
|
pte_unmap_unlock(pte - 1, ptl);
|
|
}
|
|
|
|
static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
continue;
|
|
change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);
|
|
} while (pmd++, addr = next, addr != end);
|
|
}
|
|
|
|
static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (pud_none_or_clear_bad(pud))
|
|
continue;
|
|
change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable);
|
|
} while (pud++, addr = next, addr != end);
|
|
}
|
|
|
|
static void change_protection(struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
unsigned long start = addr;
|
|
|
|
BUG_ON(addr >= end);
|
|
pgd = pgd_offset(mm, addr);
|
|
flush_cache_range(vma, addr, end);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
continue;
|
|
change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
|
|
} while (pgd++, addr = next, addr != end);
|
|
flush_tlb_range(vma, start, end);
|
|
}
|
|
|
|
int
|
|
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
|
|
unsigned long start, unsigned long end, unsigned long newflags)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
unsigned long oldflags = vma->vm_flags;
|
|
long nrpages = (end - start) >> PAGE_SHIFT;
|
|
unsigned long charged = 0;
|
|
pgoff_t pgoff;
|
|
int error;
|
|
int dirty_accountable = 0;
|
|
|
|
if (newflags == oldflags) {
|
|
*pprev = vma;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* If we make a private mapping writable we increase our commit;
|
|
* but (without finer accounting) cannot reduce our commit if we
|
|
* make it unwritable again. hugetlb mapping were accounted for
|
|
* even if read-only so there is no need to account for them here
|
|
*/
|
|
if (newflags & VM_WRITE) {
|
|
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
|
|
VM_SHARED|VM_NORESERVE))) {
|
|
charged = nrpages;
|
|
if (security_vm_enough_memory(charged))
|
|
return -ENOMEM;
|
|
newflags |= VM_ACCOUNT;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* First try to merge with previous and/or next vma.
|
|
*/
|
|
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
|
|
*pprev = vma_merge(mm, *pprev, start, end, newflags,
|
|
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
|
|
if (*pprev) {
|
|
vma = *pprev;
|
|
goto success;
|
|
}
|
|
|
|
*pprev = vma;
|
|
|
|
if (start != vma->vm_start) {
|
|
error = split_vma(mm, vma, start, 1);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
if (end != vma->vm_end) {
|
|
error = split_vma(mm, vma, end, 0);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
success:
|
|
/*
|
|
* vm_flags and vm_page_prot are protected by the mmap_sem
|
|
* held in write mode.
|
|
*/
|
|
vma->vm_flags = newflags;
|
|
vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
|
|
vm_get_page_prot(newflags));
|
|
|
|
if (vma_wants_writenotify(vma)) {
|
|
vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
|
|
dirty_accountable = 1;
|
|
}
|
|
|
|
mmu_notifier_invalidate_range_start(mm, start, end);
|
|
if (is_vm_hugetlb_page(vma))
|
|
hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
|
|
else
|
|
change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
|
|
mmu_notifier_invalidate_range_end(mm, start, end);
|
|
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
|
|
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
|
|
return 0;
|
|
|
|
fail:
|
|
vm_unacct_memory(charged);
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
|
|
unsigned long, prot)
|
|
{
|
|
unsigned long vm_flags, nstart, end, tmp, reqprot;
|
|
struct vm_area_struct *vma, *prev;
|
|
int error = -EINVAL;
|
|
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
|
|
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
|
|
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
|
|
return -EINVAL;
|
|
|
|
if (start & ~PAGE_MASK)
|
|
return -EINVAL;
|
|
if (!len)
|
|
return 0;
|
|
len = PAGE_ALIGN(len);
|
|
end = start + len;
|
|
if (end <= start)
|
|
return -ENOMEM;
|
|
if (!arch_validate_prot(prot))
|
|
return -EINVAL;
|
|
|
|
reqprot = prot;
|
|
/*
|
|
* Does the application expect PROT_READ to imply PROT_EXEC:
|
|
*/
|
|
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
|
|
prot |= PROT_EXEC;
|
|
|
|
vm_flags = calc_vm_prot_bits(prot);
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
vma = find_vma_prev(current->mm, start, &prev);
|
|
error = -ENOMEM;
|
|
if (!vma)
|
|
goto out;
|
|
if (unlikely(grows & PROT_GROWSDOWN)) {
|
|
if (vma->vm_start >= end)
|
|
goto out;
|
|
start = vma->vm_start;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto out;
|
|
}
|
|
else {
|
|
if (vma->vm_start > start)
|
|
goto out;
|
|
if (unlikely(grows & PROT_GROWSUP)) {
|
|
end = vma->vm_end;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSUP))
|
|
goto out;
|
|
}
|
|
}
|
|
if (start > vma->vm_start)
|
|
prev = vma;
|
|
|
|
for (nstart = start ; ; ) {
|
|
unsigned long newflags;
|
|
|
|
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
|
|
|
|
newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
|
|
|
|
/* newflags >> 4 shift VM_MAY% in place of VM_% */
|
|
if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
|
|
error = -EACCES;
|
|
goto out;
|
|
}
|
|
|
|
error = security_file_mprotect(vma, reqprot, prot);
|
|
if (error)
|
|
goto out;
|
|
|
|
tmp = vma->vm_end;
|
|
if (tmp > end)
|
|
tmp = end;
|
|
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
|
|
if (error)
|
|
goto out;
|
|
nstart = tmp;
|
|
|
|
if (nstart < prev->vm_end)
|
|
nstart = prev->vm_end;
|
|
if (nstart >= end)
|
|
goto out;
|
|
|
|
vma = prev->vm_next;
|
|
if (!vma || vma->vm_start != nstart) {
|
|
error = -ENOMEM;
|
|
goto out;
|
|
}
|
|
}
|
|
out:
|
|
up_write(¤t->mm->mmap_sem);
|
|
return error;
|
|
}
|