hugetlb: add hugetlb demote page support

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_hugetlb_page and prep_compound_gigantic_page for use by
demote code.

[mike.kravetz@oracle.com: v4]
  Link: https://lkml.kernel.org/r/6ca29b8e-527c-d6ec-900e-e6a43e4f8b73@oracle.com

Link: https://lkml.kernel.org/r/20211007181918.136982-6-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Nghia Le <nghialm78@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Author: mjkravetz

mm/hugetlb.c

@@ -1270,7 +1270,7 @@ 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)
 {
@@ -1293,6 +1293,13 @@ static void __destroy_compound_gigantic_page(struct page *page,
 	__ClearPageHead(page);
 }
 
+static void destroy_compound_hugetlb_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)
 {
@@ -1438,6 +1445,12 @@ 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)
 {
@@ -1779,6 +1792,12 @@ 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
@@ -3304,9 +3323,72 @@ 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;
+	int rc = 0;
+
+	target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
+
+	remove_hugetlb_page_for_demote(h, page, false);
+	spin_unlock_irq(&hugetlb_lock);
+
+	rc = alloc_huge_page_vmemmap(h, page);
+	if (rc) {
+		/* 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 rc;
+	}
+
+	/*
+	 * Use destroy_compound_hugetlb_page_for_demote for all huge page
+	 * sizes as it will not ref count pages.
+	 */
+	destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h));
+
+	/*
+	 * Taking target hstate mutex synchronizes with set_max_huge_pages.
+	 * Without the mutex, pages added to target hstate could be marked
+	 * as surplus.
+	 *
+	 * Note that we already hold h->resize_lock.  To prevent deadlock,
+	 * use the convention of always taking larger size hstate mutex first.
+	 */
+	mutex_lock(&target_hstate->resize_lock);
+	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);
+		put_page(page + i);
+	}
+	mutex_unlock(&target_hstate->resize_lock);
+
+	spin_lock_irq(&hugetlb_lock);
+
+	/*
+	 * Not absolutely necessary, but for consistency update max_huge_pages
+	 * based on pool changes for the demoted page.
+	 */
+	h->max_huge_pages--;
+	target_hstate->max_huge_pages += pages_per_huge_page(h);
+
+	return rc;
+}
+
 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);
@@ -3317,9 +3399,15 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 		return -EINVAL;		/* internal error */
 	}
 
-	/*
-	 * 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;
 }
 
@@ -3554,10 +3642,6 @@ static ssize_t demote_store(struct kobject *kobj,
 		/*
 		 * Check for available pages to demote each time thorough the
 		 * loop as demote_pool_huge_page will drop hugetlb_lock.
-		 *
-		 * NOTE: demote_pool_huge_page does not yet drop hugetlb_lock
-		 * but will when full demote functionality is added in a later
-		 * patch.
 		 */
 		if (nid != NUMA_NO_NODE)
 			nr_available = h->free_huge_pages_node[nid];