mm/hugetlb: fix getting refcount 0 page in hugetlb_fault()

When running the test which causes the race as shown in the previous patch,
we can hit the BUG "get_page() on refcount 0 page" in hugetlb_fault().

This race happens when pte turns into migration entry just after the first
check of is_hugetlb_entry_migration() in hugetlb_fault() passed with false.
To fix this, we need to check pte_present() again after huge_ptep_get().

This patch also reorders taking ptl and doing pte_page(), because
pte_page() should be done in ptl.  Due to this reordering, we need use
trylock_page() in page != pagecache_page case to respect locking order.

Fixes: 66aebce747ea ("hugetlb: fix race condition in hugetlb_fault()")
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: <stable@vger.kernel.org>	[3.2+]
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 5aca3707450fe0b205641ab8953dd0214f7976d6..385c3a1aced78f7dcd83f97597100816049bd9bc 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3134,6 +3134,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        struct page *pagecache_page = NULL;
        struct hstate *h = hstate_vma(vma);
        struct address_space *mapping;
+       int need_wait_lock = 0;
 
        address &= huge_page_mask(h);
 
@@ -3171,6 +3172,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
        ret = 0;
 
+       /*
+        * entry could be a migration/hwpoison entry at this point, so this
+        * check prevents the kernel from going below assuming that we have
+        * a active hugepage in pagecache. This goto expects the 2nd page fault,
+        * and is_hugetlb_entry_(migration|hwpoisoned) check will properly
+        * handle it.
+        */
+       if (!pte_present(entry))
+               goto out_mutex;
+
        /*
         * If we are going to COW the mapping later, we examine the pending
         * reservations for this page now. This will ensure that any
@@ -3190,30 +3201,31 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                                                                vma, address);
        }
 
+       ptl = huge_pte_lock(h, mm, ptep);
+
+       /* Check for a racing update before calling hugetlb_cow */
+       if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+               goto out_ptl;
+
        /*
         * hugetlb_cow() requires page locks of pte_page(entry) and
         * pagecache_page, so here we need take the former one
         * when page != pagecache_page or !pagecache_page.
-        * Note that locking order is always pagecache_page -> page,
-        * so no worry about deadlock.
         */
        page = pte_page(entry);
-       get_page(page);
        if (page != pagecache_page)
-               lock_page(page);
-
-       ptl = huge_pte_lockptr(h, mm, ptep);
-       spin_lock(ptl);
-       /* Check for a racing update before calling hugetlb_cow */
-       if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-               goto out_ptl;
+               if (!trylock_page(page)) {
+                       need_wait_lock = 1;
+                       goto out_ptl;
+               }
 
+       get_page(page);
 
        if (flags & FAULT_FLAG_WRITE) {
                if (!huge_pte_write(entry)) {
                        ret = hugetlb_cow(mm, vma, address, ptep, entry,
                                        pagecache_page, ptl);
-                       goto out_ptl;
+                       goto out_put_page;
                }
                entry = huge_pte_mkdirty(entry);
        }
@@ -3221,7 +3233,10 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        if (huge_ptep_set_access_flags(vma, address, ptep, entry,
                                                flags & FAULT_FLAG_WRITE))
                update_mmu_cache(vma, address, ptep);
-
+out_put_page:
+       if (page != pagecache_page)
+               unlock_page(page);
+       put_page(page);
 out_ptl:
        spin_unlock(ptl);
 
@@ -3229,12 +3244,17 @@ out_ptl:
                unlock_page(pagecache_page);
                put_page(pagecache_page);
        }
-       if (page != pagecache_page)
-               unlock_page(page);
-       put_page(page);
-
 out_mutex:
        mutex_unlock(&htlb_fault_mutex_table[hash]);
+       /*
+        * Generally it's safe to hold refcount during waiting page lock. But
+        * here we just wait to defer the next page fault to avoid busy loop and
+        * the page is not used after unlocked before returning from the current
+        * page fault. So we are safe from accessing freed page, even if we wait
+        * here without taking refcount.
+        */
+       if (need_wait_lock)
+               wait_on_page_locked(page);
        return ret;
 }