badpage: vm_normal_page use print_bad_pte

print_bad_pte() is so far being called only when zap_pte_range() finds
negative page_mapcount, or there's a fault on a pte_file where it does not
belong.  That's weak coverage when we suspect pagetable corruption.

Originally, it was called when vm_normal_page() found an invalid pfn: but
pfn_valid is expensive on some architectures and configurations, so 2.6.24
put that under CONFIG_DEBUG_VM (which doesn't help in the field), then
2.6.26 replaced it by a VM_BUG_ON (likewise).

Reinstate the print_bad_pte() in vm_normal_page(), but use a cheaper test
than pfn_valid(): memmap_init_zone() (used in bootup and hotplug) keep a
__read_mostly note of the highest_memmap_pfn, vm_normal_page() then check
pfn against that.  We could call this pfn_plausible() or pfn_sane(), but I
doubt we'll need it elsewhere: of course it's not reliable, but gives much
stronger pagetable validation on many boxes.

Also use print_bad_pte() when the pte_special bit is found outside a
VM_PFNMAP or VM_MIXEDMAP area, instead of VM_BUG_ON.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/internal.h b/mm/internal.h
index 13333bc2eb68ccb86749beb89df89d82a28b5e80..1981bc9454f388a1325d09e6ef226ff9c78cbf71 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -49,6 +49,7 @@ extern void putback_lru_page(struct page *page);
 /*
  * in mm/page_alloc.c
  */
+extern unsigned long highest_memmap_pfn;
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*

diff --git a/mm/memory.c b/mm/memory.c
index cda04b19f733af3107f7321a9e7d2ccd7ca04588..890095f5f36d2a050b33eb0bf257b21640eff263 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -467,21 +467,18 @@ static inline int is_cow_mapping(unsigned int flags)
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                                pte_t pte)
 {
-       unsigned long pfn;
+       unsigned long pfn = pte_pfn(pte);
 
        if (HAVE_PTE_SPECIAL) {
-               if (likely(!pte_special(pte))) {
-                       VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-                       return pte_page(pte);
-               }
-               VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+               if (likely(!pte_special(pte)))
+                       goto check_pfn;
+               if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
+                       print_bad_pte(vma, addr, pte, NULL);
                return NULL;
        }
 
        /* !HAVE_PTE_SPECIAL case follows: */
 
-       pfn = pte_pfn(pte);
-
        if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
                if (vma->vm_flags & VM_MIXEDMAP) {
                        if (!pfn_valid(pfn))
@@ -497,11 +494,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                }
        }
 
-       VM_BUG_ON(!pfn_valid(pfn));
+check_pfn:
+       if (unlikely(pfn > highest_memmap_pfn)) {
+               print_bad_pte(vma, addr, pte, NULL);
+               return NULL;
+       }
 
        /*
         * NOTE! We still have PageReserved() pages in the page tables.
-        *
         * eg. VDSO mappings can cause them to exist.
         */
 out:

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3acb216e9a782d8ea2e2edbd918131f4b58ba486..755c99a0ac71afa8e21e2683979e4b493ab1ef6b 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@ EXPORT_SYMBOL(node_states);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
+unsigned long highest_memmap_pfn __read_mostly;
 int percpu_pagelist_fraction;
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -2597,6 +2598,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
        unsigned long pfn;
        struct zone *z;
 
+       if (highest_memmap_pfn < end_pfn - 1)
+               highest_memmap_pfn = end_pfn - 1;
+
        z = &NODE_DATA(nid)->node_zones[zone];
        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
                /*