diff options
authorHugh Dickins <>2014-08-29 15:18:44 -0700
committerLinus Torvalds <>2014-08-29 16:28:16 -0700
commitb38af4721f59d0b564468f623b3e52a638195015 (patch)
parent7ea8574e5fa31f43d8098a028f12ba6a9c9f3530 (diff)
x86,mm: fix pte_special versus pte_numa
Sasha Levin has shown oopses on ffffea0003480048 and ffffea0003480008 at mm/memory.c:1132, running Trinity on different 3.16-rc-next kernels: where zap_pte_range() checks page->mapping to see if PageAnon(page). Those addresses fit struct pages for pfns d2001 and d2000, and in each dump a register or a stack slot showed d2001730 or d2000730: pte flags 0x730 are PCD ACCESSED PROTNONE SPECIAL IOMAP; and Sasha's e820 map has a hole between cfffffff and 100000000, which would need special access. Commit c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") has broken vm_normal_page(): a PROTNONE SPECIAL pte no longer passes the pte_special() test, so zap_pte_range() goes on to try to access a non-existent struct page. Fix this by refining pte_special() (SPECIAL with PRESENT or PROTNONE) to complement pte_numa() (SPECIAL with neither PRESENT nor PROTNONE). A hint that this was a problem was that c46a7c817e66 added pte_numa() test to vm_normal_page(), and moved its is_zero_pfn() test from slow to fast path: This was papering over a pte_special() snag when the zero page was encountered during zap. This patch reverts vm_normal_page() to how it was before, relying on pte_special(). It still appears that this patch may be incomplete: aren't there other places which need to be handling PROTNONE along with PRESENT? For example, pte_mknuma() clears _PAGE_PRESENT and sets _PAGE_NUMA, but on a PROT_NONE area, that would make it pte_special(). This is side-stepped by the fact that NUMA hinting faults skipped PROT_NONE VMAs and there are no grounds where a NUMA hinting fault on a PROT_NONE VMA would be interesting. Fixes: c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") Reported-by: Sasha Levin <> Tested-by: Sasha Levin <> Signed-off-by: Hugh Dickins <> Signed-off-by: Mel Gorman <> Cc: "Kirill A. Shutemov" <> Cc: Peter Zijlstra <> Cc: Rik van Riel <> Cc: Johannes Weiner <> Cc: Cyrill Gorcunov <> Cc: Matthew Wilcox <> Cc: <> [3.16] Signed-off-by: Andrew Morton <> Signed-off-by: Linus Torvalds <>
2 files changed, 10 insertions, 6 deletions
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0ec056012618..aa97a070f09f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -131,8 +131,13 @@ static inline int pte_exec(pte_t pte)
static inline int pte_special(pte_t pte)
- return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
+ /*
+ * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
+ * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
+ */
+ return (pte_flags(pte) & _PAGE_SPECIAL) &&
+ (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
static inline unsigned long pte_pfn(pte_t pte)
diff --git a/mm/memory.c b/mm/memory.c
index ab3537bcfed2..adeac306610f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -751,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn = pte_pfn(pte);
- if (likely(!pte_special(pte) || pte_numa(pte)))
+ if (likely(!pte_special(pte)))
goto check_pfn;
if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
@@ -777,15 +777,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ if (is_zero_pfn(pfn))
+ return NULL;
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
- if (is_zero_pfn(pfn))
- return NULL;
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.