[PATCH] mm: pte_offset_map_lock loops

Convert those common loops using page_table_lock on the outside and
pte_offset_map within to use just pte_offset_map_lock within instead.

These all hold mmap_sem (some exclusively, some not), so at no level can a
page table be whipped away from beneath them.  But whereas pte_alloc loops
tested with the "atomic" pmd_present, these loops are testing with pmd_none,
which on i386 PAE tests both lower and upper halves.

That's now unsafe, so add a cast into pmd_none to test only the vital lower
half: we lose a little sensitivity to a corrupt middle directory, but not
enough to worry about.  It appears that i386 and UML were the only
architectures vulnerable in this way, and pgd and pud no problem.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 3 insertions, 4 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 672a76fddd5e..17a2b52b753b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,8 +29,9 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                 unsigned long addr, unsigned long end, pgprot_t newprot)
 {
         pte_t *pte;
+        spinlock_t *ptl;
 
-        pte = pte_offset_map(pmd, addr);
+        pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
         do {
                 if (pte_present(*pte)) {
                         pte_t ptent;
@@ -44,7 +45,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                         lazy_mmu_prot_update(ptent);
                 }
         } while (pte++, addr += PAGE_SIZE, addr != end);
-        pte_unmap(pte - 1);
+        pte_unmap_unlock(pte - 1, ptl);
 }
 
 static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -88,7 +89,6 @@ static void change_protection(struct vm_area_struct *vma,
         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))
@@ -96,7 +96,6 @@ static void change_protection(struct vm_area_struct *vma,
                 change_pud_range(mm, pgd, addr, next, newprot);
         } while (pgd++, addr = next, addr != end);
         flush_tlb_range(vma, start, end);
-        spin_unlock(&mm->page_table_lock);
 }
 
 static int