[RFC PATCH 3/3] hugetlb: add hugetlb demote page support

From: Mike Kravetz <mike.kravetz@oracle.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: David Hildenbrand <david@redhat.com>,
	Michal Hocko <mhocko@suse.com>,
	Oscar Salvador <osalvador@suse.de>, Zi Yan <ziy@nvidia.com>,
	David Rientjes <rientjes@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Kravetz <mike.kravetz@oracle.com>
Subject: [RFC PATCH 3/3] hugetlb: add hugetlb demote page support
Date: Mon,  8 Mar 2021 16:18:55 -0800	[thread overview]
Message-ID: <20210309001855.142453-4-mike.kravetz@oracle.com> (raw)
In-Reply-To: <20210309001855.142453-1-mike.kravetz@oracle.com>

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.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 mm/hugetlb.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 58 insertions(+), 3 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0c29b7d0d469..33b0d8778551 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2744,17 +2744,72 @@ 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;
+	bool cma_page = HPageCma(page);
+
+	target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
+
+	ClearHPageFreed(page);
+	list_del(&page->lru);
+	h->free_huge_pages--;
+	h->free_huge_pages_node[nid]--;
+	h->nr_huge_pages--;
+	h->nr_huge_pages_node[nid]--;
+	set_page_refcounted(page);
+	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
+	spin_unlock(&hugetlb_lock);
+
+	/*
+	 * Note for future:
+	 * When support for reducing vmemmap of huge pages is added, we
+	 * will need to allocate vmemmap pages here and could fail.
+	 */
+	destroy_compound_gigantic_page(page, huge_page_order(h));
+
+	for (i = 0; i < pages_per_huge_page(h);
+				i += pages_per_huge_page(target_hstate)) {
+		/*
+		 * Explicitly use prep_compound_gigantic_page if demoting
+		 * a page allocated from CMA so that TAIL_MAPPING is not
+		 * set in tail pages.  The CMA code does not expect this.
+		 */
+		if (cma_page)
+			prep_compound_gigantic_page(page + i,
+							target_hstate->order);
+		else
+			prep_compound_huge_page(page + i, target_hstate->order);
+		prep_new_huge_page(target_hstate, page + i, nid);
+		if (cma_page)
+			SetHPageCma(page + i);
+		put_page(page + i);
+	}
+
+	spin_lock(&hugetlb_lock);
+	return 0;
+}
+
 static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 {
+	int nr_nodes, node;
+	struct page *page;
 	int rc = 0;
 
 	/* If no demote order, free to buddy */
 	if (!h->demote_order)
 		return free_pool_huge_page(h, nodes_allowed, 0);
 
-	/*
-	 * 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;
 }
 
-- 
2.29.2

