* (C) Copyright 1994 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*
- * Address space accounting code <alan@redhat.com>
+ * 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/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 <linux/perf_event.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)
+ unsigned long addr, unsigned long end, pgprot_t newprot,
+ int dirty_accountable)
{
- pte_t *pte;
+ pte_t *pte, oldpte;
+ spinlock_t *ptl;
- pte = pte_offset_map(pmd, addr);
+ pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ arch_enter_lazy_mmu_mode();
do {
- if (pte_present(*pte)) {
+ oldpte = *pte;
+ if (pte_present(oldpte)) {
pte_t ptent;
- /* Avoid an SMP race with hardware updated dirty/clean
- * bits by wiping the pte and then setting the new pte
- * into place.
+ ptent = ptep_modify_prot_start(mm, addr, pte);
+ ptent = pte_modify(ptent, newprot);
+
+ /*
+ * Avoid taking write faults for pages we know to be
+ * dirty.
*/
- ptent = pte_modify(ptep_get_and_clear(mm, addr, pte), newprot);
- set_pte_at(mm, addr, pte, ptent);
- lazy_mmu_prot_update(ptent);
+ 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);
- pte_unmap(pte - 1);
+ 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)
+ unsigned long addr, unsigned long end, pgprot_t newprot,
+ int dirty_accountable)
{
pmd_t *pmd;
unsigned long next;
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
- change_pte_range(mm, pmd, addr, next, newprot);
+ 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)
+ unsigned long addr, unsigned long end, pgprot_t newprot,
+ int dirty_accountable)
{
pud_t *pud;
unsigned long next;
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
- change_pmd_range(mm, pud, addr, next, newprot);
+ 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)
+ unsigned long addr, unsigned long end, pgprot_t newprot,
+ int dirty_accountable)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
- spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- change_pud_range(mm, pgd, addr, next, newprot);
+ change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
} while (pgd++, addr = next, addr != end);
flush_tlb_range(vma, start, end);
- spin_unlock(&mm->page_table_lock);
}
-static int
+int
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
unsigned long start, unsigned long end, unsigned long newflags)
{
unsigned long oldflags = vma->vm_flags;
long nrpages = (end - start) >> PAGE_SHIFT;
unsigned long charged = 0;
- pgprot_t newprot;
pgoff_t pgoff;
int error;
+ int dirty_accountable = 0;
if (newflags == oldflags) {
*pprev = vma;
/*
* 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.
+ * 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_SHARED|VM_HUGETLB))) {
+ if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
+ VM_SHARED|VM_NORESERVE))) {
charged = nrpages;
if (security_vm_enough_memory(charged))
return -ENOMEM;
}
}
- newprot = protection_map[newflags & 0xf];
-
/*
* First try to merge with previous and/or next vma.
*/
* held in write mode.
*/
vma->vm_flags = newflags;
- vma->vm_page_prot = newprot;
- change_protection(vma, start, end, newprot);
- __vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
- __vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+ 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:
return error;
}
-asmlinkage long
-sys_mprotect(unsigned long start, size_t len, unsigned long prot)
+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;
end = start + len;
if (end <= start)
return -ENOMEM;
- if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM))
+ if (!arch_validate_prot(prot))
return -EINVAL;
reqprot = prot;
/*
* Does the application expect PROT_READ to imply PROT_EXEC:
*/
- if (unlikely((prot & PROT_READ) &&
- (current->personality & READ_IMPLIES_EXEC)))
+ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
prot |= PROT_EXEC;
vm_flags = calc_vm_prot_bits(prot);
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
- if (is_vm_hugetlb_page(vma)) {
- error = -EACCES;
- goto out;
- }
-
newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
- if ((newflags & ~(newflags >> 4)) & 0xf) {
+ /* newflags >> 4 shift VM_MAY% in place of VM_% */
+ if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
error = -EACCES;
goto out;
}
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
if (error)
goto out;
+ perf_event_mmap(vma);
nstart = tmp;
if (nstart < prev->vm_end)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff