netns xfrm: fix "ip xfrm state|policy count" misreport

[safe/jmp/linux-2.6] / mm / mprotect.c

diff --git a/mm/mprotect.c b/mm/mprotect.c
index ecfaa58..8bc969d 100644 (file)
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -4,7 +4,7 @@
  *  (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
  */
 
@@ -21,6 +21,9 @@
 #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>
@@ -47,21 +50,18 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                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_get_and_clear(mm, addr, pte);
+                       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);
-                       set_pte_at(mm, addr, pte, ptent);
-#ifdef CONFIG_MIGRATION
-               } else if (!pte_file(oldpte)) {
+
+                       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)) {
@@ -73,9 +73,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                                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);
@@ -154,13 +152,12 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
        /*
         * 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))) {
+               if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
+                                               VM_SHARED|VM_NORESERVE))) {
                        charged = nrpages;
                        if (security_vm_enough_memory(charged))
                                return -ENOMEM;
@@ -207,10 +204,12 @@ success:
                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;
@@ -220,8 +219,8 @@ 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;
@@ -301,6 +300,7 @@ sys_mprotect(unsigned long start, size_t len, unsigned long prot)
                error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
                if (error)
                        goto out;
+               perf_event_mmap(vma);
                nstart = tmp;
 
                if (nstart < prev->vm_end)