In preparation for constraining huge page allocation and freeing by the

controlling task's numa mempolicy, add a "nodes_allowed" nodemask pointer
to the allocate, free and surplus adjustment functions.  For now, pass
NULL to indicate default behavior--i.e., use node_online_map.  A
subsqeuent patch will derive a non-default mask from the controlling
task's numa mempolicy.

Note that this method of updating the global hstate nr_hugepages under the
constraint of a nodemask simplifies keeping the global state
consistent--especially the number of persistent and surplus pages relative
to reservations and overcommit limits.  There are undoubtedly other ways
to do this, but this works for both interfaces: mempolicy and per node
attributes.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Andi Kleen <andi@firstfloor.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Eric Whitney <eric.whitney@hp.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/hugetlb.c

@@ -622,48 +622,56 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 }
 
 /*
- * common helper function for hstate_next_node_to_{alloc|free}.
- * return next node in node_online_map, wrapping at end.
+ * common helper functions for hstate_next_node_to_{alloc|free}.
+ * We may have allocated or freed a huge page based on a different
+ * nodes_allowed previously, so h->next_node_to_{alloc|free} might
+ * be outside of *nodes_allowed.  Ensure that we use an allowed
+ * node for alloc or free.
  */
-static int next_node_allowed(int nid)
+static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
 {
-	nid = next_node(nid, node_online_map);
+	nid = next_node(nid, *nodes_allowed);
 	if (nid == MAX_NUMNODES)
-		nid = first_node(node_online_map);
+		nid = first_node(*nodes_allowed);
 	VM_BUG_ON(nid >= MAX_NUMNODES);
 
 	return nid;
 }
 
+static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
+{
+	if (!node_isset(nid, *nodes_allowed))
+		nid = next_node_allowed(nid, nodes_allowed);
+	return nid;
+}
+
 /*
- * Use a helper variable to find the next node and then
- * copy it back to next_nid_to_alloc afterwards:
- * otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
- * But we don't need to use a spin_lock here: it really
- * doesn't matter if occasionally a racer chooses the
- * same nid as we do.  Move nid forward in the mask even
- * if we just successfully allocated a hugepage so that
- * the next caller gets hugepages on the next node.
+ * returns the previously saved node ["this node"] from which to
+ * allocate a persistent huge page for the pool and advance the
+ * next node from which to allocate, handling wrap at end of node
+ * mask.
  */
-static int hstate_next_node_to_alloc(struct hstate *h)
+static int hstate_next_node_to_alloc(struct hstate *h,
+					nodemask_t *nodes_allowed)
 {
-	int nid, next_nid;
+	int nid;
+
+	VM_BUG_ON(!nodes_allowed);
+
+	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
+	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);
 
-	nid = h->next_nid_to_alloc;
-	next_nid = next_node_allowed(nid);
-	h->next_nid_to_alloc = next_nid;
 	return nid;
 }
 
-static int alloc_fresh_huge_page(struct hstate *h)
+static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 {
 	struct page *page;
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = hstate_next_node_to_alloc(h);
+	start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
 	next_nid = start_nid;
 
 	do {
@@ -672,7 +680,7 @@ static int alloc_fresh_huge_page(struct hstate *h)
 			ret = 1;
 			break;
 		}
-		next_nid = hstate_next_node_to_alloc(h);
+		next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
 	} while (next_nid != start_nid);
 
 	if (ret)
@@ -684,18 +692,20 @@ static int alloc_fresh_huge_page(struct hstate *h)
 }
 
 /*
- * helper for free_pool_huge_page() - return the next node
- * from which to free a huge page.  Advance the next node id
- * whether or not we find a free huge page to free so that the
- * next attempt to free addresses the next node.
+ * helper for free_pool_huge_page() - return the previously saved
+ * node ["this node"] from which to free a huge page.  Advance the
+ * next node id whether or not we find a free huge page to free so
+ * that the next attempt to free addresses the next node.
  */
-static int hstate_next_node_to_free(struct hstate *h)
+static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 {
-	int nid, next_nid;
+	int nid;
+
+	VM_BUG_ON(!nodes_allowed);
+
+	nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
+	h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
 
-	nid = h->next_nid_to_free;
-	next_nid = next_node_allowed(nid);
-	h->next_nid_to_free = next_nid;
 	return nid;
 }
 
@@ -705,13 +715,14 @@ static int hstate_next_node_to_free(struct hstate *h)
  * balanced over allowed nodes.
  * Called with hugetlb_lock locked.
  */
-static int free_pool_huge_page(struct hstate *h, bool acct_surplus)
+static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
+							 bool acct_surplus)
 {
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = hstate_next_node_to_free(h);
+	start_nid = hstate_next_node_to_free(h, nodes_allowed);
 	next_nid = start_nid;
 
 	do {
@@ -735,7 +746,7 @@ static int free_pool_huge_page(struct hstate *h, bool acct_surplus)
 			ret = 1;
 			break;
 		}
-		next_nid = hstate_next_node_to_free(h);
+		next_nid = hstate_next_node_to_free(h, nodes_allowed);
 	} while (next_nid != start_nid);
 
 	return ret;
@@ -937,7 +948,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * on-line nodes for us and will handle the hstate accounting.
 	 */
 	while (nr_pages--) {
-		if (!free_pool_huge_page(h, 1))
+		if (!free_pool_huge_page(h, &node_online_map, 1))
 			break;
 	}
 }
@@ -1047,7 +1058,8 @@ int __weak alloc_bootmem_huge_page(struct hstate *h)
 		void *addr;
 
 		addr = __alloc_bootmem_node_nopanic(
-				NODE_DATA(hstate_next_node_to_alloc(h)),
+				NODE_DATA(hstate_next_node_to_alloc(h,
+							&node_online_map)),
 				huge_page_size(h), huge_page_size(h), 0);
 
 		if (addr) {
@@ -1102,7 +1114,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		if (h->order >= MAX_ORDER) {
 			if (!alloc_bootmem_huge_page(h))
 				break;
-		} else if (!alloc_fresh_huge_page(h))
+		} else if (!alloc_fresh_huge_page(h, &node_online_map))
 			break;
 	}
 	h->max_huge_pages = i;
@@ -1144,14 +1156,15 @@ static void __init report_hugepages(void)
 }
 
 #ifdef CONFIG_HIGHMEM
-static void try_to_free_low(struct hstate *h, unsigned long count)
+static void try_to_free_low(struct hstate *h, unsigned long count,
+						nodemask_t *nodes_allowed)
 {
 	int i;
 
 	if (h->order >= MAX_ORDER)
 		return;
 
-	for (i = 0; i < MAX_NUMNODES; ++i) {
+	for_each_node_mask(node, nodes_allowed_) {
 		struct page *page, *next;
 		struct list_head *freel = &h->hugepage_freelists[i];
 		list_for_each_entry_safe(page, next, freel, lru) {
@@ -1167,7 +1180,8 @@ static void try_to_free_low(struct hstate *h, unsigned long count)
 	}
 }
 #else
-static inline void try_to_free_low(struct hstate *h, unsigned long count)
+static inline void try_to_free_low(struct hstate *h, unsigned long count,
+						nodemask_t *nodes_allowed)
 {
 }
 #endif
@@ -1177,7 +1191,8 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count)
  * balanced by operating on them in a round-robin fashion.
  * Returns 1 if an adjustment was made.
  */
-static int adjust_pool_surplus(struct hstate *h, int delta)
+static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
+				int delta)
 {
 	int start_nid, next_nid;
 	int ret = 0;
@@ -1185,9 +1200,9 @@ static int adjust_pool_surplus(struct hstate *h, int delta)
 	VM_BUG_ON(delta != -1 && delta != 1);
 
 	if (delta < 0)
-		start_nid = hstate_next_node_to_alloc(h);
+		start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
 	else
-		start_nid = hstate_next_node_to_free(h);
+		start_nid = hstate_next_node_to_free(h, nodes_allowed);
 	next_nid = start_nid;
 
 	do {
@@ -1197,7 +1212,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta)
 			 * To shrink on this node, there must be a surplus page
 			 */
 			if (!h->surplus_huge_pages_node[nid]) {
-				next_nid = hstate_next_node_to_alloc(h);
+				next_nid = hstate_next_node_to_alloc(h,
+								nodes_allowed);
 				continue;
 			}
 		}
@@ -1207,7 +1223,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta)
 			 */
 			if (h->surplus_huge_pages_node[nid] >=
 						h->nr_huge_pages_node[nid]) {
-				next_nid = hstate_next_node_to_free(h);
+				next_nid = hstate_next_node_to_free(h,
+								nodes_allowed);
 				continue;
 			}
 		}
@@ -1222,7 +1239,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta)
 }
 
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
-static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
+static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
+						nodemask_t *nodes_allowed)
 {
 	unsigned long min_count, ret;
 
@@ -1242,7 +1260,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 	 */
 	spin_lock(&hugetlb_lock);
 	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
-		if (!adjust_pool_surplus(h, -1))
+		if (!adjust_pool_surplus(h, nodes_allowed, -1))
 			break;
 	}
 
@@ -1253,7 +1271,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 		 * and reducing the surplus.
 		 */
 		spin_unlock(&hugetlb_lock);
-		ret = alloc_fresh_huge_page(h);
+		ret = alloc_fresh_huge_page(h, nodes_allowed);
 		spin_lock(&hugetlb_lock);
 		if (!ret)
 			goto out;
@@ -1277,13 +1295,13 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 	 */
 	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
 	min_count = max(count, min_count);
-	try_to_free_low(h, min_count);
+	try_to_free_low(h, min_count, nodes_allowed);
 	while (min_count < persistent_huge_pages(h)) {
-		if (!free_pool_huge_page(h, 0))
+		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
 	}
 	while (count < persistent_huge_pages(h)) {
-		if (!adjust_pool_surplus(h, 1))
+		if (!adjust_pool_surplus(h, nodes_allowed, 1))
 			break;
 	}
 out:
@@ -1329,7 +1347,7 @@ static ssize_t nr_hugepages_store(struct kobject *kobj,
 	if (err)
 		return 0;
 
-	h->max_huge_pages = set_max_huge_pages(h, input);
+	h->max_huge_pages = set_max_huge_pages(h, input, &node_online_map);
 
 	return count;
 }
@@ -1571,7 +1589,8 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 	proc_doulongvec_minmax(table, write, buffer, length, ppos);
 
 	if (write)
-		h->max_huge_pages = set_max_huge_pages(h, tmp);
+		h->max_huge_pages = set_max_huge_pages(h, tmp,
+							&node_online_map);
 
 	return 0;
 }