mm: numa: add paranoid check around pte_protnone_numa

[cascardo/linux.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index d63849b..f7886ab 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
        pmd = pmd_offset(pud, start);
        pud_clear(pud);
        pmd_free_tlb(tlb, pmd, start);
+       mm_dec_nr_pmds(tlb->mm);
 }
 
 static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -3012,14 +3013,17 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
        bool migrated = false;
        int flags = 0;
 
+       /* A PROT_NONE fault should not end up here */
+       BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
+
        /*
        * The "pte" at this point cannot be used safely without
        * validation through pte_unmap_same(). It's of NUMA type but
        * the pfn may be screwed if the read is non atomic.
        *
-       * ptep_modify_prot_start is not called as this is clearing
-       * the _PAGE_NUMA bit and it is not really expected that there
-       * would be concurrent hardware modifications to the PTE.
+       * We can safely just do a "set_pte_at()", because the old
+       * page table entry is not accessible, so there would be no
+       * concurrent hardware modifications to the PTE.
        */
        ptl = pte_lockptr(mm, pmd);
        spin_lock(ptl);
@@ -3028,7 +3032,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                goto out;
        }
 
-       pte = pte_mknonnuma(pte);
+       /* Make it present again */
+       pte = pte_modify(pte, vma->vm_page_prot);
+       pte = pte_mkyoung(pte);
        set_pte_at(mm, addr, ptep, pte);
        update_mmu_cache(vma, addr, ptep);
 
@@ -3037,7 +3043,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                pte_unmap_unlock(ptep, ptl);
                return 0;
        }
-       BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
        /*
         * Avoid grouping on DSO/COW pages in specific and RO pages
@@ -3123,7 +3128,7 @@ static int handle_pte_fault(struct mm_struct *mm,
                                        pte, pmd, flags, entry);
        }
 
-       if (pte_numa(entry))
+       if (pte_protnone(entry))
                return do_numa_page(mm, vma, address, entry, pte, pmd);
 
        ptl = pte_lockptr(mm, pmd);
@@ -3201,7 +3206,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                        if (pmd_trans_splitting(orig_pmd))
                                return 0;
 
-                       if (pmd_numa(orig_pmd))
+                       if (pmd_protnone(orig_pmd))
                                return do_huge_pmd_numa_page(mm, vma, address,
                                                             orig_pmd, pmd);
 
@@ -3322,15 +3327,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 
        spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_4LEVEL_HACK
-       if (pud_present(*pud))          /* Another has populated it */
-               pmd_free(mm, new);
-       else
+       if (!pud_present(*pud)) {
+               mm_inc_nr_pmds(mm);
                pud_populate(mm, pud, new);
-#else
-       if (pgd_present(*pud))          /* Another has populated it */
+       } else  /* Another has populated it */
                pmd_free(mm, new);
-       else
+#else
+       if (!pgd_present(*pud)) {
+               mm_inc_nr_pmds(mm);
                pgd_populate(mm, pud, new);
+       } else /* Another has populated it */
+               pmd_free(mm, new);
 #endif /* __ARCH_HAS_4LEVEL_HACK */
        spin_unlock(&mm->page_table_lock);
        return 0;