summaryrefslogtreecommitdiff
path: root/mm/page_vma_mapped.c
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>2018-01-19 15:49:24 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2018-01-21 17:44:47 -0800
commit0d665e7b109d512b7cae3ccef6e8654714887844 (patch)
treee6ebae5cd32b4f9008d06592a5301937c0be5875 /mm/page_vma_mapped.c
parent0c5b9b5d9adbad4b60491f9ba0d2af38904bb4b9 (diff)
mm, page_vma_mapped: Drop faulty pointer arithmetics in check_pte()
Tetsuo reported random crashes under memory pressure on 32-bit x86 system and tracked down to change that introduced page_vma_mapped_walk(). The root cause of the issue is the faulty pointer math in check_pte(). As ->pte may point to an arbitrary page we have to check that they are belong to the section before doing math. Otherwise it may lead to weird results. It wasn't noticed until now as mem_map[] is virtually contiguous on flatmem or vmemmap sparsemem. Pointer arithmetic just works against all 'struct page' pointers. But with classic sparsemem, it doesn't because each section memap is allocated separately and so consecutive pfns crossing two sections might have struct pages at completely unrelated addresses. Let's restructure code a bit and replace pointer arithmetic with operations on pfns. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-and-tested-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Acked-by: Michal Hocko <mhocko@suse.com> Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_vma_mapped.c')
-rw-r--r--mm/page_vma_mapped.c63
1 files changed, 38 insertions, 25 deletions
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index d22b84310f6d..956015614395 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -30,10 +30,29 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
return true;
}
+/**
+ * check_pte - check if @pvmw->page is mapped at the @pvmw->pte
+ *
+ * page_vma_mapped_walk() found a place where @pvmw->page is *potentially*
+ * mapped. check_pte() has to validate this.
+ *
+ * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary
+ * page.
+ *
+ * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration
+ * entry that points to @pvmw->page or any subpage in case of THP.
+ *
+ * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to
+ * @pvmw->page or any subpage in case of THP.
+ *
+ * Otherwise, return false.
+ *
+ */
static bool check_pte(struct page_vma_mapped_walk *pvmw)
{
+ unsigned long pfn;
+
if (pvmw->flags & PVMW_MIGRATION) {
-#ifdef CONFIG_MIGRATION
swp_entry_t entry;
if (!is_swap_pte(*pvmw->pte))
return false;
@@ -41,37 +60,31 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
if (!is_migration_entry(entry))
return false;
- if (migration_entry_to_page(entry) - pvmw->page >=
- hpage_nr_pages(pvmw->page)) {
- return false;
- }
- if (migration_entry_to_page(entry) < pvmw->page)
- return false;
-#else
- WARN_ON_ONCE(1);
-#endif
- } else {
- if (is_swap_pte(*pvmw->pte)) {
- swp_entry_t entry;
- entry = pte_to_swp_entry(*pvmw->pte);
- if (is_device_private_entry(entry) &&
- device_private_entry_to_page(entry) == pvmw->page)
- return true;
- }
+ pfn = migration_entry_to_pfn(entry);
+ } else if (is_swap_pte(*pvmw->pte)) {
+ swp_entry_t entry;
- if (!pte_present(*pvmw->pte))
+ /* Handle un-addressable ZONE_DEVICE memory */
+ entry = pte_to_swp_entry(*pvmw->pte);
+ if (!is_device_private_entry(entry))
return false;
- /* THP can be referenced by any subpage */
- if (pte_page(*pvmw->pte) - pvmw->page >=
- hpage_nr_pages(pvmw->page)) {
- return false;
- }
- if (pte_page(*pvmw->pte) < pvmw->page)
+ pfn = device_private_entry_to_pfn(entry);
+ } else {
+ if (!pte_present(*pvmw->pte))
return false;
+
+ pfn = pte_pfn(*pvmw->pte);
}
+ if (pfn < page_to_pfn(pvmw->page))
+ return false;
+
+ /* THP can be referenced by any subpage */
+ if (pfn - page_to_pfn(pvmw->page) >= hpage_nr_pages(pvmw->page))
+ return false;
+
return true;
}