[PATCH v7 09/15] mm/hugetlb: Defer freeing of HugeTLB pages

[Muchun Song <songmuchun@bytedance.com>]

In the subsequent patch, we will allocate the vmemmap pages when free
HugeTLB pages. But update_and_free_page() is called from a non-task
context(and hold hugetlb_lock), so we can defer the actual freeing in
a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         | 96 ++++++++++++++++++++++++++++++++++++++++++++++------
 mm/hugetlb_vmemmap.c |  5 ---
 mm/hugetlb_vmemmap.h | 10 ++++++
 3 files changed, 95 insertions(+), 16 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 93dee37ceb6d..5131ae3d2245 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1220,7 +1220,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	__ClearPageHead(page);
 }
 
-static void free_gigantic_page(struct page *page, unsigned int order)
+static void __free_gigantic_page(struct page *page, unsigned int order)
 {
 	/*
 	 * If the page isn't allocated using the cma allocator,
@@ -1287,20 +1287,100 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 {
 	return NULL;
 }
-static inline void free_gigantic_page(struct page *page, unsigned int order) { }
+static inline void __free_gigantic_page(struct page *page,
+					unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void __free_hugepage(struct hstate *h, struct page *page);
+
+/*
+ * As update_and_free_page() is be called from a non-task context(and hold
+ * hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
+ * use GFP_ATOMIC to allocate a lot of vmemmap pages.
+ *
+ * update_hpage_vmemmap_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 update_hpage_vmemmap_workfn() anyway, it is
+ * reused as the llist_node structure of a lockless linked list of huge
+ * pages to be freed.
+ */
+static LLIST_HEAD(hpage_update_freelist);
+
+static void update_hpage_vmemmap_workfn(struct work_struct *work)
 {
-	int i;
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_update_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		page->mapping = NULL;
+		__free_hugepage(page_hstate(page), page);
 
+		cond_resched();
+	}
+}
+static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
+
+static inline void __update_and_free_page(struct hstate *h, struct page *page)
+{
+	/* No need to allocate vmemmap pages */
+	if (!free_vmemmap_pages_per_hpage(h)) {
+		__free_hugepage(h, page);
+		return;
+	}
+
+	/*
+	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap
+	 * pages.
+	 *
+	 * Only call schedule_work() if hpage_update_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_update_freelist))
+		schedule_work(&hpage_update_work);
+}
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	__free_gigantic_page(page, huge_page_order(h));
+}
+#else
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	/*
+	 * Temporarily drop the hugetlb_lock, because
+	 * we might block in __free_gigantic_page().
+	 */
+	spin_unlock(&hugetlb_lock);
+	__free_gigantic_page(page, huge_page_order(h));
+	spin_lock(&hugetlb_lock);
+}
+#endif
+
+static void update_and_free_page(struct hstate *h, struct page *page)
+{
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
+
+	__update_and_free_page(h, page);
+}
+
+static void __free_hugepage(struct hstate *h, struct page *page)
+{
+	int i;
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
@@ -1312,14 +1392,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
-		/*
-		 * Temporarily drop the hugetlb_lock, because
-		 * we might block in free_gigantic_page().
-		 */
-		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
-		free_gigantic_page(page, huge_page_order(h));
-		spin_lock(&hugetlb_lock);
+		free_gigantic_page(h, page);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 2c997b5de3b6..af42fad1f131 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -124,11 +124,6 @@
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
 })
 
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-{
-	return h->nr_free_vmemmap_pages;
-}
-
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 67113b67495f..293897b9f1d8 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,6 +13,11 @@
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
@@ -21,5 +26,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return 0;
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0