From 670805c518547eea0a8d0ca71143d89a65bfc024 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 6 Jun 2017 15:23:51 +0200
Subject: [PATCH 2/4] hugetlb, memory_hotplug: prefer to use reserved pages for
 migration
Git-commit: 4db9b2efe94967be34e3b136a93251a3c1736dd5
Patch-mainline: v4.13-rc1
References: bnc#1042553

new_node_page will try to use the origin's next NUMA node as the
migration destination for hugetlb pages. If such a node doesn't have any
preallocated pool it falls back to __alloc_buddy_huge_page_no_mpol to
allocate a surplus page instead. This is quite subotpimal for any
configuration when hugetlb pages are no distributed to all NUMA nodes
evenly. Say we have a hotplugable node 4 and spare hugetlb pages are
node 0
/sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages:10000
/sys/devices/system/node/node1/hugepages/hugepages-2048kB/nr_hugepages:0
/sys/devices/system/node/node2/hugepages/hugepages-2048kB/nr_hugepages:0
/sys/devices/system/node/node3/hugepages/hugepages-2048kB/nr_hugepages:0
/sys/devices/system/node/node4/hugepages/hugepages-2048kB/nr_hugepages:10000
/sys/devices/system/node/node5/hugepages/hugepages-2048kB/nr_hugepages:0
/sys/devices/system/node/node6/hugepages/hugepages-2048kB/nr_hugepages:0
/sys/devices/system/node/node7/hugepages/hugepages-2048kB/nr_hugepages:0

Now we consume the whole pool on node 4 and try to offline this
node. All the allocated pages should be moved to node0 which has enough
preallocated pages to hold them. With the current implementation
offlining very likely fails because hugetlb allocations during runtime
are much less reliable.

Fix this by reusing the nodemask which excludes migration source and try
to find a first node which has a page in the preallocated pool first and
fall back to __alloc_buddy_huge_page_no_mpol only when the whole pool is
consumed.

Signed-off-by: Michal Hocko <mhocko@suse.com>

---
 include/linux/hugetlb.h |    2 ++
 mm/hugetlb.c            |   27 +++++++++++++++++++++++++++
 mm/memory_hotplug.c     |    9 ++-------
 3 files changed, 31 insertions(+), 7 deletions(-)

--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -333,6 +333,7 @@ struct page *alloc_huge_page(struct vm_a
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
+struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -496,6 +497,7 @@ static inline void hugetlb_count_sub(lon
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
+#define alloc_huge_page_nodemask(h, nmask) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1634,6 +1634,33 @@ struct page *alloc_huge_page_node(struct
 	return page;
 }
 
+struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask)
+{
+	struct page *page = NULL;
+	int node;
+
+	spin_lock(&hugetlb_lock);
+	if (h->free_huge_pages - h->resv_huge_pages > 0) {
+		for_each_node_mask(node, *nmask) {
+			page = dequeue_huge_page_node(h, node);
+			if (page)
+				break;
+		}
+	}
+	spin_unlock(&hugetlb_lock);
+	if (page)
+		return page;
+
+	/* No reservations, try to overcommit */
+	for_each_node_mask(node, *nmask) {
+		page = __alloc_buddy_huge_page_no_mpol(h, node);
+		if (page)
+			return page;
+	}
+
+	return NULL;
+}
+
 /*
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1403,14 +1403,9 @@ static struct page *new_node_page(struct
 	if (nodes_empty(nmask))
 		node_set(nid, nmask);
 
-	/*
-	 * TODO: allocate a destination hugepage from a nearest neighbor node,
-	 * accordance with memory policy of the user process if possible. For
-	 * now as a simple work-around, we use the next node for destination.
-	 */
 	if (PageHuge(page))
-		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					next_node_in(nid, nmask));
+		return alloc_huge_page_nodemask(
+				page_hstate(compound_head(page)), &nmask);
 
 	if (PageHighMem(page)
 	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))