1 files changed, 78 insertions, 13 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4c842adf14e0..1eedc7003380 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/jhash.h>
 #include <linux/numa.h>
+#include <linux/llist.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -1255,7 +1256,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
 	page[2].mapping = NULL;
 }
 
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
 {
 	/*
 	 * Can't pass hstate in here because it is called from the
@@ -1318,6 +1319,54 @@ void free_huge_page(struct page *page)
 	spin_unlock(&hugetlb_lock);
 }
 
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		__free_huge_page(page);
+	}
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+	/*
+	 * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+	 */
+	if (!in_task()) {
+		/*
+		 * Only call schedule_work() if hpage_freelist is previously
+		 * empty. Otherwise, schedule_work() had been called but the
+		 * workfn hasn't retrieved the list yet.
+		 */
+		if (llist_add((struct llist_node *)&page->mapping,
+			      &hpage_freelist))
+			schedule_work(&free_hpage_work);
+		return;
+	}
+
+	__free_huge_page(page);
+}
+
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
@@ -2964,6 +3013,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void __user *buffer, size_t *length, loff_t *ppos)
@@ -2975,9 +3040,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3021,9 +3085,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -4879,8 +4942,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pud_t *pud, pud_entry;
+	pmd_t *pmd, pmd_entry;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -4890,17 +4953,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pud_entry = READ_ONCE(*pud);
+	if (sz != PUD_SIZE && pud_none(pud_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
+	if (pud_huge(pud_entry) || !pud_present(pud_entry))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, addr);
-	if (sz != PMD_SIZE && pmd_none(*pmd))
+	pmd_entry = READ_ONCE(*pmd);
+	if (sz != PMD_SIZE && pmd_none(pmd_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
+	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
 		return (pte_t *)pmd;
 
 	return NULL;