hugetlb: add per node hstate attributes

Add the per huge page size control/query attributes to the per node
sysdevs:

/sys/devices/system/node/node<ID>/hugepages/hugepages-<size>/
	nr_hugepages       - r/w
	free_huge_pages    - r/o
	surplus_huge_pages - r/o

The patch attempts to re-use/share as much of the existing global hstate
attribute initialization and handling, and the "nodes_allowed" constraint
processing as possible.

Calling set_max_huge_pages() with no node indicates a change to global
hstate parameters.  In this case, any non-default task mempolicy will be
used to generate the nodes_allowed mask.  A valid node id indicates an
update to that node's hstate parameters, and the count argument specifies
the target count for the specified node.  From this info, we compute the
target global count for the hstate and construct a nodes_allowed node mask
contain only the specified node.

Setting the node specific nr_hugepages via the per node attribute
effectively ignores any task mempolicy or cpuset constraints.

With this patch:

(me):ls /sys/devices/system/node/node0/hugepages/hugepages-2048kB
./  ../  free_hugepages  nr_hugepages  surplus_hugepages

Starting from:
Node 0 HugePages_Total:     0
Node 0 HugePages_Free:      0
Node 0 HugePages_Surp:      0
Node 1 HugePages_Total:     0
Node 1 HugePages_Free:      0
Node 1 HugePages_Surp:      0
Node 2 HugePages_Total:     0
Node 2 HugePages_Free:      0
Node 2 HugePages_Surp:      0
Node 3 HugePages_Total:     0
Node 3 HugePages_Free:      0
Node 3 HugePages_Surp:      0
vm.nr_hugepages = 0

Allocate 16 persistent huge pages on node 2:
(me):echo 16 >/sys/devices/system/node/node2/hugepages/hugepages-2048kB/nr_hugepages

[Note that this is equivalent to:
	numactl -m 2 hugeadmin --pool-pages-min 2M:+16
]

Yields:
Node 0 HugePages_Total:     0
Node 0 HugePages_Free:      0
Node 0 HugePages_Surp:      0
Node 1 HugePages_Total:     0
Node 1 HugePages_Free:      0
Node 1 HugePages_Surp:      0
Node 2 HugePages_Total:    16
Node 2 HugePages_Free:     16
Node 2 HugePages_Surp:      0
Node 3 HugePages_Total:     0
Node 3 HugePages_Free:      0
Node 3 HugePages_Surp:      0
vm.nr_hugepages = 16

Global controls work as expected--reduce pool to 8 persistent huge pages:
(me):echo 8 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages

Node 0 HugePages_Total:     0
Node 0 HugePages_Free:      0
Node 0 HugePages_Surp:      0
Node 1 HugePages_Total:     0
Node 1 HugePages_Free:      0
Node 1 HugePages_Surp:      0
Node 2 HugePages_Total:     8
Node 2 HugePages_Free:      8
Node 2 HugePages_Surp:      0
Node 3 HugePages_Total:     0
Node 3 HugePages_Free:      0
Node 3 HugePages_Surp:      0

Signed-off-by: Lee Schermerhorn <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Cc: KAMEZAWA Hiroyuki <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Nishanth Aravamudan <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Adam Litke <[email protected]>
Cc: Andy Whitcroft <[email protected]>
Cc: Eric Whitney <[email protected]>
Cc: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Lee Schermerhorn

drivers/base/node.c

@@ -173,6 +173,43 @@ static ssize_t node_read_distance(struct sys_device * dev,
 }
 static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL);
 
+#ifdef CONFIG_HUGETLBFS
+/*
+ * hugetlbfs per node attributes registration interface:
+ * When/if hugetlb[fs] subsystem initializes [sometime after this module],
+ * it will register its per node attributes for all nodes online at that
+ * time.  It will also call register_hugetlbfs_with_node(), below, to
+ * register its attribute registration functions with this node driver.
+ * Once these hooks have been initialized, the node driver will call into
+ * the hugetlb module to [un]register attributes for hot-plugged nodes.
+ */
+static node_registration_func_t __hugetlb_register_node;
+static node_registration_func_t __hugetlb_unregister_node;
+
+static inline void hugetlb_register_node(struct node *node)
+{
+	if (__hugetlb_register_node)
+		__hugetlb_register_node(node);
+}
+
+static inline void hugetlb_unregister_node(struct node *node)
+{
+	if (__hugetlb_unregister_node)
+		__hugetlb_unregister_node(node);
+}
+
+void register_hugetlbfs_with_node(node_registration_func_t doregister,
+				  node_registration_func_t unregister)
+{
+	__hugetlb_register_node   = doregister;
+	__hugetlb_unregister_node = unregister;
+}
+#else
+static inline void hugetlb_register_node(struct node *node) {}
+
+static inline void hugetlb_unregister_node(struct node *node) {}
+#endif
+
 
 /*
  * register_node - Setup a sysfs device for a node.
@@ -196,6 +233,7 @@ int register_node(struct node *node, int num, struct node *parent)
 		sysdev_create_file(&node->sysdev, &attr_distance);
 
 		scan_unevictable_register_node(node);
+		hugetlb_register_node(node);
 	}
 	return error;
 }
@@ -216,6 +254,7 @@ void unregister_node(struct node *node)
 	sysdev_remove_file(&node->sysdev, &attr_distance);
 
 	scan_unevictable_unregister_node(node);
+	hugetlb_unregister_node(node);
 
 	sysdev_unregister(&node->sysdev);
 }

include/linux/node.h

@@ -28,6 +28,7 @@ struct node {
 
 struct memory_block;
 extern struct node node_devices[];
+typedef  void (*node_registration_func_t)(struct node *);
 
 extern int register_node(struct node *, int, struct node *);
 extern void unregister_node(struct node *node);
@@ -39,6 +40,11 @@ extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
 						int nid);
 extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk);
+
+#ifdef CONFIG_HUGETLBFS
+extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
+					 node_registration_func_t unregister);
+#endif
 #else
 static inline int register_one_node(int nid)
 {
@@ -65,6 +71,11 @@ static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 {
 	return 0;
 }
+
+static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
+						node_registration_func_t unreg)
+{
+}
 #endif
 
 #define to_node(sys_device) container_of(sys_device, struct node, sysdev)