hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned entry

There's a race between fork() and hugepage migration, as a result we try
to "dereference" a swap entry as a normal pte, causing kernel panic.
The cause of the problem is that copy_hugetlb_page_range() can't handle
"swap entry" family (migration entry and hwpoisoned entry) so let's fix
it.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: <stable@vger.kernel.org>	[2.6.37+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 226910c..2024bbd 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2520,6 +2520,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
                update_mmu_cache(vma, address, ptep);
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+       swp_entry_t swp;
+
+       if (huge_pte_none(pte) || pte_present(pte))
+               return 0;
+       swp = pte_to_swp_entry(pte);
+       if (non_swap_entry(swp) && is_migration_entry(swp))
+               return 1;
+       else
+               return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+       swp_entry_t swp;
+
+       if (huge_pte_none(pte) || pte_present(pte))
+               return 0;
+       swp = pte_to_swp_entry(pte);
+       if (non_swap_entry(swp) && is_hwpoison_entry(swp))
+               return 1;
+       else
+               return 0;
+}
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                            struct vm_area_struct *vma)
@@ -2559,10 +2584,26 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                dst_ptl = huge_pte_lock(h, dst, dst_pte);
                src_ptl = huge_pte_lockptr(h, src, src_pte);
                spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
-               if (!huge_pte_none(huge_ptep_get(src_pte))) {
+               entry = huge_ptep_get(src_pte);
+               if (huge_pte_none(entry)) { /* skip none entry */
+                       ;
+               } else if (unlikely(is_hugetlb_entry_migration(entry) ||
+                                   is_hugetlb_entry_hwpoisoned(entry))) {
+                       swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+                       if (is_write_migration_entry(swp_entry) && cow) {
+                               /*
+                                * COW mappings require pages in both
+                                * parent and child to be set to read.
+                                */
+                               make_migration_entry_read(&swp_entry);
+                               entry = swp_entry_to_pte(swp_entry);
+                               set_huge_pte_at(src, addr, src_pte, entry);
+                       }
+                       set_huge_pte_at(dst, addr, dst_pte, entry);
+               } else {
                        if (cow)
                                huge_ptep_set_wrprotect(src, addr, src_pte);
-                       entry = huge_ptep_get(src_pte);
                        ptepage = pte_page(entry);
                        get_page(ptepage);
                        page_dup_rmap(ptepage);
@@ -2578,32 +2619,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
        return ret;
 }
 
-static int is_hugetlb_entry_migration(pte_t pte)
-{
-       swp_entry_t swp;
-
-       if (huge_pte_none(pte) || pte_present(pte))
-               return 0;
-       swp = pte_to_swp_entry(pte);
-       if (non_swap_entry(swp) && is_migration_entry(swp))
-               return 1;
-       else
-               return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
-       swp_entry_t swp;
-
-       if (huge_pte_none(pte) || pte_present(pte))
-               return 0;
-       swp = pte_to_swp_entry(pte);
-       if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-               return 1;
-       else
-               return 0;
-}
-
 void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
                            unsigned long start, unsigned long end,
                            struct page *ref_page)