linux/mm/mprotect.c
Jeremy Fitzhardinge 1ea0704e0d mm: add a ptep_modify_prot transaction abstraction
This patch adds an API for doing read-modify-write updates to a pte's
protection bits which may race against hardware updates to the pte.
After reading the pte, the hardware may asynchonously set the accessed
or dirty bits on a pte, which would be lost when writing back the
modified pte value.

The existing technique to handle this race is to use
ptep_get_and_clear() atomically fetch the old pte value and clear it
in memory.  This has the effect of marking the pte as non-present,
which will prevent the hardware from updating its state.  When the new
value is written back, the pte will be present again, and the hardware
can resume updating the access/dirty flags.

When running in a virtualized environment, pagetable updates are
relatively expensive, since they generally involve some trap into the
hypervisor.  To mitigate the cost of these updates, we tend to batch
them.

However, because of the atomic nature of ptep_get_and_clear(), it is
inherently non-batchable.  This new interface allows batching by
giving the underlying implementation enough information to open a
transaction between the read and write phases:

ptep_modify_prot_start() returns the current pte value, and puts the
  pte entry into a state where either the hardware will not update the
  pte, or if it does, the updates will be preserved on commit.

ptep_modify_prot_commit() writes back the updated pte, makes sure that
  any hardware updates made since ptep_modify_prot_start() are
  preserved.

ptep_modify_prot_start() and _commit() must be exactly paired, and
used while holding the appropriate pte lock.  They do not protect
against other software updates of the pte in any way.

The current implementations of ptep_modify_prot_start and _commit are
functionally unchanged from before: _start() uses ptep_get_and_clear()
fetch the pte and zero the entry, preventing any hardware updates.
_commit() simply writes the new pte value back knowing that the
hardware has not updated the pte in the meantime.

The only current user of this interface is mprotect

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-25 15:15:53 +02:00

319 lines
7.5 KiB
C

/*
* mm/mprotect.c
*
* (C) Copyright 1994 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*
* Address space accounting code <alan@redhat.com>
* (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 <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);
#ifdef CONFIG_MIGRATION
} else if (!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));
}
#endif
}
} 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.
*
* FIXME? We haven't defined a VM_NORESERVE flag, so mprotecting
* a MAP_NORESERVE private mapping to writable will now reserve.
*/
if (newflags & VM_WRITE) {
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED))) {
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;
}
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);
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;
}
asmlinkage long
sys_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 (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM))
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(&current->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(&current->mm->mmap_sem);
return error;
}