hugetlb: offload per node attribute registrations

Offload the registration and unregistration of per node hstate sysfs
attributes to a worker thread rather than attempt the
allocation/attachment or detachment/freeing of the attributes in the
context of the memory hotplug handler.

I don't know that this is absolutely required, but the registration can
sleep in allocations and other mem hot plug handlers do it this way.  If
it turns out this is NOT required, we can drop this patch.

N.B.,  Only tested build, boot, libhugetlbfs regression.
       i.e., no memory hotplug testing.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Andi Kleen <andi@firstfloor.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: David Rientjes <rientjes@google.com>
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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 52 insertions, 10 deletions

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 9e218a6..54e5d8e 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -186,11 +186,14 @@ static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL);
 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)
+static inline bool hugetlb_register_node(struct node *node)
 {
 	if (__hugetlb_register_node &&
-			node_state(node->sysdev.id, N_HIGH_MEMORY))
+			node_state(node->sysdev.id, N_HIGH_MEMORY)) {
 		__hugetlb_register_node(node);
+		return true;
+	}
+	return false;
 }
 
 static inline void hugetlb_unregister_node(struct node *node)
@@ -387,10 +390,31 @@ static int link_mem_sections(int nid)
 	return err;
 }
 
+#ifdef CONFIG_HUGETLBFS
 /*
  * Handle per node hstate attribute [un]registration on transistions
  * to/from memoryless state.
  */
+static void node_hugetlb_work(struct work_struct *work)
+{
+	struct node *node = container_of(work, struct node, node_work);
+
+	/*
+	 * We only get here when a node transitions to/from memoryless state.
+	 * We can detect which transition occurred by examining whether the
+	 * node has memory now.  hugetlb_register_node() already check this
+	 * so we try to register the attributes.  If that fails, then the
+	 * node has transitioned to memoryless, try to unregister the
+	 * attributes.
+	 */
+	if (!hugetlb_register_node(node))
+		hugetlb_unregister_node(node);
+}
+
+static void init_node_hugetlb_work(int nid)
+{
+	INIT_WORK(&node_devices[nid].node_work, node_hugetlb_work);
+}
 
 static int node_memory_callback(struct notifier_block *self,
 				unsigned long action, void *arg)
@@ -399,14 +423,16 @@ static int node_memory_callback(struct notifier_block *self,
 	int nid = mnb->status_change_nid;
 
 	switch (action) {
-	case MEM_ONLINE:    /* memory successfully brought online */
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		/*
+		 * offload per node hstate [un]registration to a work thread
+		 * when transitioning to/from memoryless state.
+		 */
 		if (nid != NUMA_NO_NODE)
-			hugetlb_register_node(&node_devices[nid]);
-		break;
-	case MEM_OFFLINE:   /* or offline */
-		if (nid != NUMA_NO_NODE)
-			hugetlb_unregister_node(&node_devices[nid]);
+			schedule_work(&node_devices[nid].node_work);
 		break;
+
 	case MEM_GOING_ONLINE:
 	case MEM_GOING_OFFLINE:
 	case MEM_CANCEL_ONLINE:
@@ -417,15 +443,23 @@ static int node_memory_callback(struct notifier_block *self,
 
 	return NOTIFY_OK;
 }
-#else
+#endif	/* CONFIG_HUGETLBFS */
+#else	/* !CONFIG_MEMORY_HOTPLUG_SPARSE */
+
 static int link_mem_sections(int nid) { return 0; }
+#endif	/* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
+#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
+    !defined(CONFIG_HUGETLBFS)
 static inline int node_memory_callback(struct notifier_block *self,
 				unsigned long action, void *arg)
 {
 	return NOTIFY_OK;
 }
-#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+
+static void init_node_hugetlb_work(int nid) { }
+
+#endif
 
 int register_one_node(int nid)
 {
@@ -449,6 +483,9 @@ int register_one_node(int nid)
 
 		/* link memory sections under this node */
 		error = link_mem_sections(nid);
+
+		/* initialize work queue for memory hot plug */
+		init_node_hugetlb_work(nid);
 	}
 
 	return error;
diff --git a/include/linux/node.h b/include/linux/node.h
index dae1521..06292da 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -21,9 +21,14 @@
 
 #include <linux/sysdev.h>
 #include <linux/cpumask.h>
+#include <linux/workqueue.h>
 
 struct node {
 	struct sys_device	sysdev;
+
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
+	struct work_struct	node_work;
+#endif
 };
 
 struct memory_block;