[PATCH v2 4/4] hugetlb: add hugetlb demote page support

[Mike Kravetz]

Demote page functionality will split a huge page into a number of huge
pages of a smaller size.  For example, on x86 a 1GB huge page can be
demoted into 512 2M huge pages.  Demotion is done 'in place' by simply
splitting the huge page.

Added '*_for_demote' wrappers for remove_hugetlb_page,
destroy_compound_gigantic_page and prep_compound_gigantic_page for use
by demote code.

Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 mm/hugetlb.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 75 insertions(+), 4 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2317d411243d..ab7bd0434057 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1260,7 +1260,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
 		nr_nodes--)
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+/* used to demote non-gigantic_huge pages as well */
 static void __destroy_compound_gigantic_page(struct page *page,
 					unsigned int order, bool demote)
 {
@@ -1283,6 +1283,13 @@ static void __destroy_compound_gigantic_page(struct page *page,
 	__ClearPageHead(page);
 }
 
+static void destroy_compound_gigantic_page_for_demote(struct page *page,
+					unsigned int order)
+{
+	__destroy_compound_gigantic_page(page, order, true);
+}
+
+#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
 static void destroy_compound_gigantic_page(struct page *page,
 					unsigned int order)
 {
@@ -1428,6 +1435,12 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page,
 	__remove_hugetlb_page(h, page, adjust_surplus, false);
 }
 
+static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page,
+							bool adjust_surplus)
+{
+	__remove_hugetlb_page(h, page, adjust_surplus, true);
+}
+
 static void add_hugetlb_page(struct hstate *h, struct page *page,
 			     bool adjust_surplus)
 {
@@ -1777,6 +1790,12 @@ static bool prep_compound_gigantic_page(struct page *page, unsigned int order)
 	return __prep_compound_gigantic_page(page, order, false);
 }
 
+static bool prep_compound_gigantic_page_for_demote(struct page *page,
+							unsigned int order)
+{
+	return __prep_compound_gigantic_page(page, order, true);
+}
+
 /*
  * PageHuge() only returns true for hugetlbfs pages, but not for normal or
  * transparent huge pages.  See the PageTransHuge() documentation for more
@@ -3298,9 +3317,55 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	return 0;
 }
 
+static int demote_free_huge_page(struct hstate *h, struct page *page)
+{
+	int i, nid = page_to_nid(page);
+	struct hstate *target_hstate;
+	bool cma_page = HPageCma(page);
+
+	target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
+
+	remove_hugetlb_page_for_demote(h, page, false);
+	spin_unlock_irq(&hugetlb_lock);
+
+	if (alloc_huge_page_vmemmap(h, page)) {
+		/* Allocation of vmemmmap failed, we can not demote page */
+		spin_lock_irq(&hugetlb_lock);
+		set_page_refcounted(page);
+		add_hugetlb_page(h, page, false);
+		return 1;
+	}
+
+	/*
+	 * Use destroy_compound_gigantic_page_for_demote for all huge page
+	 * sizes as it will not ref count pages.
+	 */
+	destroy_compound_gigantic_page_for_demote(page, huge_page_order(h));
+
+	for (i = 0; i < pages_per_huge_page(h);
+				i += pages_per_huge_page(target_hstate)) {
+		if (hstate_is_gigantic(target_hstate))
+			prep_compound_gigantic_page_for_demote(page + i,
+							target_hstate->order);
+		else
+			prep_compound_page(page + i, target_hstate->order);
+		set_page_private(page + i, 0);
+		set_page_refcounted(page + i);
+		prep_new_huge_page(target_hstate, page + i, nid);
+		if (cma_page)
+			SetHPageCma(page + i);
+		put_page(page + i);
+	}
+
+	spin_lock_irq(&hugetlb_lock);
+	return 0;
+}
+
 static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 	__must_hold(&hugetlb_lock)
 {
+	int nr_nodes, node;
+	struct page *page;
 	int rc = 0;
 
 	lockdep_assert_held(&hugetlb_lock);
@@ -3309,9 +3374,15 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 	if (!h->demote_order)
 		return rc;
 
-	/*
-	 * TODO - demote fucntionality will be added in subsequent patch
-	 */
+	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+		if (!list_empty(&h->hugepage_freelists[node])) {
+			page = list_entry(h->hugepage_freelists[node].next,
+					struct page, lru);
+			rc = !demote_free_huge_page(h, page);
+			break;
+		}
+	}
+
 	return rc;
 }
 
-- 
2.31.1