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

commit 0f792cf949a0be506c2aa8bfac0605746b146dda upstream.

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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2:
 - Adjust context
 - Error label is named 'out_page_table_lock' not 'out_ptl']
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

1 files changed, 35 insertions, 15 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d2c43a2b24fc..f6a621ba1097 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2798,6 +2798,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *pagecache_page = NULL;
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
+	int need_wait_lock = 0;
 
 	ptep = huge_pte_offset(mm, address);
 	if (ptep) {
@@ -2829,6 +2830,16 @@ 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
 	 * allocations necessary to record that reservation occur outside the
@@ -2847,29 +2858,30 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
+	spin_lock(&mm->page_table_lock);
+	/* Check for a racing update before calling hugetlb_cow */
+	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+		goto out_page_table_lock;
+
 	/*
 	 * 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);
-
-	spin_lock(&mm->page_table_lock);
-	/* Check for a racing update before calling hugetlb_cow */
-	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_page_table_lock;
+		if (!trylock_page(page)) {
+			need_wait_lock = 1;
+			goto out_page_table_lock;
+		}
 
+	get_page(page);
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
 							pagecache_page);
-			goto out_page_table_lock;
+			goto out_put_page;
 		}
 		entry = pte_mkdirty(entry);
 	}
@@ -2877,7 +2889,10 @@ 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_page_table_lock:
 	spin_unlock(&mm->page_table_lock);
 
@@ -2885,13 +2900,18 @@ out_page_table_lock:
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
 	}
-	if (page != pagecache_page)
-		unlock_page(page);
-	put_page(page);
-
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
 
+	/*
+	 * 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;
 }