The patch titled
badpage: vm_normal_page use print_bad_pte
has been added to the -mm tree. Its filename is
badpage-vm_normal_page-use-print_bad_pte.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: badpage: vm_normal_page use print_bad_pte
From: Hugh Dickins <hugh@xxxxxxxxxxx>
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@xxxxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/internal.h | 1 +
mm/memory.c | 20 ++++++++++----------
mm/page_alloc.c | 4 ++++
3 files changed, 15 insertions(+), 10 deletions(-)
diff -puN mm/internal.h~badpage-vm_normal_page-use-print_bad_pte mm/internal.h
--- a/mm/internal.h~badpage-vm_normal_page-use-print_bad_pte
+++ a/mm/internal.h
@@ -49,6 +49,7 @@ extern void putback_lru_page(struct page
/*
* in mm/page_alloc.c
*/
+extern unsigned long highest_memmap_pfn;
extern void __free_pages_bootmem(struct page *page, unsigned int order);
/*
diff -puN mm/memory.c~badpage-vm_normal_page-use-print_bad_pte mm/memory.c
--- a/mm/memory.c~badpage-vm_normal_page-use-print_bad_pte
+++ a/mm/memory.c
@@ -467,21 +467,18 @@ static inline int is_cow_mapping(unsigne
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_ar
}
}
- 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 -puN mm/page_alloc.c~badpage-vm_normal_page-use-print_bad_pte mm/page_alloc.c
--- a/mm/page_alloc.c~badpage-vm_normal_page-use-print_bad_pte
+++ a/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
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++) {
/*
_
Patches currently in -mm which might be from hugh@xxxxxxxxxxx are
ksym_symbol_len-fixes.patch
linux-next.patch
mm-dont-mark_page_accessed-in-shmem_fault.patch
mm-apply_to_range-call-pte-function-with-lazy-updates.patch
mm-remove-cgroup_mm_owner_callbacks.patch
mm-remove-aop_writepage_activate.patch
mm-remove-gfp_highuser_pagecache.patch
mm-add-setclearpageswapcache-stubs.patch
mm-replace-some-bug_ons-by-vm_bug_ons.patch
mm-add_active_or_unevictable-into-rmap.patch
mm-make-page_lock_anon_vma-static.patch
mm-further-cleanup-page_add_new_anon_rmap.patch
mm-gup-persist-for-write-permission.patch
mm-wp-lock-page-before-deciding-cow.patch
mm-reuse_swap_page-replaces-can_share_swap_page.patch
mm-try_to_free_swap-replaces-remove_exclusive_swap_page.patch
mm-try_to_unuse-check-removing-right-swap.patch
mm-remove-try_to_munlock-from-vmscan.patch
mm-remove-gfp_mask-from-add_to_swap.patch
mm-add-add_to_swap-stub.patch
mm-optimize-get_scan_ratio-for-no-swap.patch
swapfile-swapon-needs-larger-size-type.patch
swapfile-remove-swp_active-mask.patch
swapfile-remove-surplus-whitespace.patch
swapfile-remove-v0-swap-space-message.patch
swapfile-rearrange-scan-and-swap_info.patch
swapfile-swapon-use-discard-trim.patch
swapfile-swap-allocation-use-discard.patch
swapfile-swapon-randomize-if-nonrot.patch
swapfile-swap-allocation-cycle-if-nonrot.patch
swapfile-change-discard-pgoff_t-to-sector_t.patch
swapfile-change-discard-pgoff_t-to-sector_t-fix.patch
swapfile-let-others-seed-random.patch
badpage-simplify-page_alloc-flag-checkclear.patch
badpage-keep-any-bad-page-out-of-circulation.patch
badpage-replace-page_remove_rmap-eeek-and-bug.patch
badpage-vm_normal_page-use-print_bad_pte.patch
badpage-zap-print_bad_pte-on-swap-and-file.patch
badpage-remove-vma-from-page_remove_rmap.patch
badpage-ratelimit-print_bad_pte-and-bad_page.patch
badpage-kern_alert-bug-instead-of-kern_emerg.patch
memcg-handle-swap-caches.patch
memcg-handle-swap-caches-build-fix.patch
memcg-swap-cgroup-for-remembering-usage.patch
memcg-memswap-controller-core.patch
memcg-memswap-controller-core-make-resize-limit-hold-mutex.patch
memcg-memswap-controller-core-swapcache-fixes.patch
prio_tree-debugging-patch.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
