mm: hugetlb: fix a race between freeing and dissolving the page

commit 7ffddd499ba6122b1a07828f023d1d67629aa017 upstream

There is a race condition between __free_huge_page()
and dissolve_free_huge_page().

  CPU0:                         CPU1:

  // page_count(page) == 1
  put_page(page)
    __free_huge_page(page)
                                dissolve_free_huge_page(page)
                                  spin_lock(&hugetlb_lock)
                                  // PageHuge(page) && !page_count(page)
                                  update_and_free_page(page)
                                  // page is freed to the buddy
                                  spin_unlock(&hugetlb_lock)
      spin_lock(&hugetlb_lock)
      clear_page_huge_active(page)
      enqueue_huge_page(page)
      // It is wrong, the page is already freed
      spin_unlock(&hugetlb_lock)

The race window is between put_page() and dissolve_free_huge_page().

We should make sure that the page is already on the free list when it is
dissolved.

As a result __free_huge_page would corrupt page(s) already in the buddy
allocator.

Link: https://lkml.kernel.org/r/20210115124942.46403-4-songmuchun@bytedance.com
Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[sudip: adjust context]
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 39 insertions, 0 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c3ecac8aeb3..13a4f3fe2d91 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -66,6 +66,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+static inline bool PageHugeFreed(struct page *head)
+{
+	return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, 0);
+}
+
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 
@@ -841,6 +856,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
+	SetPageHugeFreed(page);
 }
 
 static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
@@ -858,6 +874,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 		return NULL;
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
+	ClearPageHugeFreed(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
 	return page;
@@ -1266,6 +1283,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
+	ClearPageHugeFreed(page);
 	spin_unlock(&hugetlb_lock);
 	put_page(page); /* free it into the hugepage allocator */
 }
@@ -1424,11 +1442,32 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  */
 static void dissolve_free_huge_page(struct page *page)
 {
+retry:
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
 		struct page *head = compound_head(page);
 		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
+
+		/*
+		 * We should make sure that the page is already on the free list
+		 * when it is dissolved.
+		 */
+		if (unlikely(!PageHugeFreed(head))) {
+			spin_unlock(&hugetlb_lock);
+			cond_resched();
+
+			/*
+			 * Theoretically, we should return -EBUSY when we
+			 * encounter this race. In fact, we have a chance
+			 * to successfully dissolve the page if we do a
+			 * retry. Because the race window is quite small.
+			 * If we seize this opportunity, it is an optimization
+			 * for increasing the success rate of dissolving page.
+			 */
+			goto retry;
+		}
+
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;