1 files changed, 209 insertions, 76 deletions

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 1fe5536d404f..985abd7f49a7 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -15,9 +15,13 @@
 #include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/swap.h>
+#include <linux/gfp.h>
+
+static struct sysdev_class_attribute *node_state_attrs[];
 
 static struct sysdev_class node_class = {
         .name = "node",
+        .attrs = node_state_attrs,
 };
 
 
@@ -162,8 +166,11 @@ static ssize_t node_read_distance(struct sys_device * dev,
         int len = 0;
         int i;
 
-        /* buf currently PAGE_SIZE, need ~4 chars per node */
-        BUILD_BUG_ON(MAX_NUMNODES*4 > PAGE_SIZE/2);
+        /*
+         * buf is currently PAGE_SIZE in length and each node needs 4 chars
+         * at the most (distance + space or newline).
+         */
+        BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE);
 
         for_each_online_node(i)
                 len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
@@ -173,6 +180,47 @@ 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 online nodes with
+ * memory.  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 bool hugetlb_register_node(struct node *node)
+{
+        if (__hugetlb_register_node &&
+                        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)
+{
+        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 +244,8 @@ 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 +266,7 @@ void unregister_node(struct node *node)
         sysdev_remove_file(&node->sysdev, &attr_distance);
 
         scan_unevictable_unregister_node(node);
+        hugetlb_unregister_node(node);          /* no-op, if memoryless node */
 
         sysdev_unregister(&node->sysdev);
 }
@@ -227,26 +278,43 @@ struct node node_devices[MAX_NUMNODES];
  */
 int register_cpu_under_node(unsigned int cpu, unsigned int nid)
 {
-        if (node_online(nid)) {
-                struct sys_device *obj = get_cpu_sysdev(cpu);
-                if (!obj)
-                        return 0;
-                return sysfs_create_link(&node_devices[nid].sysdev.kobj,
-                                         &obj->kobj,
-                                         kobject_name(&obj->kobj));
-         }
+        int ret;
+        struct sys_device *obj;
 
-        return 0;
+        if (!node_online(nid))
+                return 0;
+
+        obj = get_cpu_sysdev(cpu);
+        if (!obj)
+                return 0;
+
+        ret = sysfs_create_link(&node_devices[nid].sysdev.kobj,
+                                &obj->kobj,
+                                kobject_name(&obj->kobj));
+        if (ret)
+                return ret;
+
+        return sysfs_create_link(&obj->kobj,
+                                 &node_devices[nid].sysdev.kobj,
+                                 kobject_name(&node_devices[nid].sysdev.kobj));
 }
 
 int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 {
-        if (node_online(nid)) {
-                struct sys_device *obj = get_cpu_sysdev(cpu);
-                if (obj)
-                        sysfs_remove_link(&node_devices[nid].sysdev.kobj,
-                                         kobject_name(&obj->kobj));
-        }
+        struct sys_device *obj;
+
+        if (!node_online(nid))
+                return 0;
+
+        obj = get_cpu_sysdev(cpu);
+        if (!obj)
+                return 0;
+
+        sysfs_remove_link(&node_devices[nid].sysdev.kobj,
+                          kobject_name(&obj->kobj));
+        sysfs_remove_link(&obj->kobj,
+                          kobject_name(&node_devices[nid].sysdev.kobj));
+
         return 0;
 }
 
@@ -268,6 +336,7 @@ static int get_nid_for_pfn(unsigned long pfn)
 /* register memory section under specified node if it spans that node */
 int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 {
+        int ret;
         unsigned long pfn, sect_start_pfn, sect_end_pfn;
 
         if (!mem_blk)
@@ -284,9 +353,15 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
                         continue;
                 if (page_nid != nid)
                         continue;
-                return sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj,
+                ret = sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj,
                                         &mem_blk->sysdev.kobj,
                                         kobject_name(&mem_blk->sysdev.kobj));
+                if (ret)
+                        return ret;
+
+                return sysfs_create_link_nowarn(&mem_blk->sysdev.kobj,
+                                &node_devices[nid].sysdev.kobj,
+                                kobject_name(&node_devices[nid].sysdev.kobj));
         }
         /* mem section does not span the specified node */
         return 0;
@@ -295,12 +370,16 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 /* unregister memory section under all nodes that it spans */
 int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 {
-        nodemask_t unlinked_nodes;
+        NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
         unsigned long pfn, sect_start_pfn, sect_end_pfn;
 
-        if (!mem_blk)
+        if (!mem_blk) {
+                NODEMASK_FREE(unlinked_nodes);
                 return -EFAULT;
-        nodes_clear(unlinked_nodes);
+        }
+        if (!unlinked_nodes)
+                return -ENOMEM;
+        nodes_clear(*unlinked_nodes);
         sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
         sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
         for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
@@ -311,11 +390,14 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
                         continue;
                 if (!node_online(nid))
                         continue;
-                if (node_test_and_set(nid, unlinked_nodes))
+                if (node_test_and_set(nid, *unlinked_nodes))
                         continue;
                 sysfs_remove_link(&node_devices[nid].sysdev.kobj,
                          kobject_name(&mem_blk->sysdev.kobj));
+                sysfs_remove_link(&mem_blk->sysdev.kobj,
+                         kobject_name(&node_devices[nid].sysdev.kobj));
         }
+        NODEMASK_FREE(unlinked_nodes);
         return 0;
 }
 
@@ -345,9 +427,77 @@ static int link_mem_sections(int nid)
         }
         return err;
 }
-#else
+
+#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)
+{
+        struct memory_notify *mnb = arg;
+        int nid = mnb->status_change_nid;
+
+        switch (action) {
+        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)
+                        schedule_work(&node_devices[nid].node_work);
+                break;
+
+        case MEM_GOING_ONLINE:
+        case MEM_GOING_OFFLINE:
+        case MEM_CANCEL_ONLINE:
+        case MEM_CANCEL_OFFLINE:
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+#endif  /* CONFIG_HUGETLBFS */
+#else   /* !CONFIG_MEMORY_HOTPLUG_SPARSE */
+
 static int link_mem_sections(int nid) { return 0; }
-#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+#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;
+}
+
+static void init_node_hugetlb_work(int nid) { }
+
+#endif
 
 int register_one_node(int nid)
 {
@@ -371,6 +521,9 @@ 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;
@@ -398,75 +551,55 @@ static ssize_t print_nodes_state(enum node_states state, char *buf)
         return n;
 }
 
-static ssize_t print_nodes_possible(struct sysdev_class *class, char *buf)
-{
-        return print_nodes_state(N_POSSIBLE, buf);
-}
-
-static ssize_t print_nodes_online(struct sysdev_class *class, char *buf)
-{
-        return print_nodes_state(N_ONLINE, buf);
-}
-
-static ssize_t print_nodes_has_normal_memory(struct sysdev_class *class,
-                                                char *buf)
-{
-        return print_nodes_state(N_NORMAL_MEMORY, buf);
-}
+struct node_attr {
+        struct sysdev_class_attribute attr;
+        enum node_states state;
+};
 
-static ssize_t print_nodes_has_cpu(struct sysdev_class *class, char *buf)
+static ssize_t show_node_state(struct sysdev_class *class,
+                               struct sysdev_class_attribute *attr, char *buf)
 {
-        return print_nodes_state(N_CPU, buf);
+        struct node_attr *na = container_of(attr, struct node_attr, attr);
+        return print_nodes_state(na->state, buf);
 }
 
-static SYSDEV_CLASS_ATTR(possible, 0444, print_nodes_possible, NULL);
-static SYSDEV_CLASS_ATTR(online, 0444, print_nodes_online, NULL);
-static SYSDEV_CLASS_ATTR(has_normal_memory, 0444, print_nodes_has_normal_memory,
-                                                                        NULL);
-static SYSDEV_CLASS_ATTR(has_cpu, 0444, print_nodes_has_cpu, NULL);
+#define _NODE_ATTR(name, state) \
+        { _SYSDEV_CLASS_ATTR(name, 0444, show_node_state, NULL), state }
 
+static struct node_attr node_state_attr[] = {
+        _NODE_ATTR(possible, N_POSSIBLE),
+        _NODE_ATTR(online, N_ONLINE),
+        _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
+        _NODE_ATTR(has_cpu, N_CPU),
 #ifdef CONFIG_HIGHMEM
-static ssize_t print_nodes_has_high_memory(struct sysdev_class *class,
-                                                 char *buf)
-{
-        return print_nodes_state(N_HIGH_MEMORY, buf);
-}
-
-static SYSDEV_CLASS_ATTR(has_high_memory, 0444, print_nodes_has_high_memory,
-                                                                         NULL);
+        _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
 #endif
+};
 
-struct sysdev_class_attribute *node_state_attr[] = {
-        &attr_possible,
-        &attr_online,
-        &attr_has_normal_memory,
+static struct sysdev_class_attribute *node_state_attrs[] = {
+        &node_state_attr[0].attr,
+        &node_state_attr[1].attr,
+        &node_state_attr[2].attr,
+        &node_state_attr[3].attr,
 #ifdef CONFIG_HIGHMEM
-        &attr_has_high_memory,
+        &node_state_attr[4].attr,
 #endif
-        &attr_has_cpu,
+        NULL
 };
 
-static int node_states_init(void)
-{
-        int i;
-        int err = 0;
-
-        for (i = 0;  i < NR_NODE_STATES; i++) {
-                int ret;
-                ret = sysdev_class_create_file(&node_class, node_state_attr[i]);
-                if (!err)
-                        err = ret;
-        }
-        return err;
-}
-
+#define NODE_CALLBACK_PRI       2       /* lower than SLAB */
 static int __init register_node_type(void)
 {
         int ret;
 
+        BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
+        BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);
+
         ret = sysdev_class_register(&node_class);
-        if (!ret)
-                ret = node_states_init();
+        if (!ret) {
+                hotplug_memory_notifier(node_memory_callback,
+                                        NODE_CALLBACK_PRI);
+        }
 
         /*
          * Note:  we're not going to unregister the node class if we fail