@@ -79,6 +79,21 @@ 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);
@@ -1028,6 +1043,7 @@ static void enqueue_huge_page(struct hst
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_exact(struct hstate *h, int nid)
@@ -1044,6 +1060,7 @@ static struct page *dequeue_huge_page_no
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;
@@ -1505,6 +1522,7 @@ static void prep_new_huge_page(struct hs
spin_lock(&hugetlb_lock);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
+ ClearPageHugeFreed(page);
spin_unlock(&hugetlb_lock);
}
@@ -1755,6 +1773,7 @@ int dissolve_free_huge_page(struct page
{
int rc = -EBUSY;
+retry:
/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!PageHuge(page))
return 0;
@@ -1771,6 +1790,26 @@ int dissolve_free_huge_page(struct page
int nid = page_to_nid(head);
if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
+
+ /*
+ * 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;
+ }
+
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
The patch titled Subject: mm: hugetlb: fix a race between freeing and dissolving the page has been removed from the -mm tree. Its filename was mm-hugetlb-fix-a-race-between-freeing-and-dissolving-the-page.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Muchun Song <songmuchun@bytedance.com> Subject: mm: hugetlb: fix a race between freeing and dissolving the page 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 windows 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> --- mm/hugetlb.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+)