10 files changed, 566 insertions, 127 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 6bee6af8d8e1..f1290cbd1350 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -56,7 +56,14 @@ static inline int device_is_not_partition(struct device *dev)
  */
 const char *dev_driver_string(const struct device *dev)
 {
-        return dev->driver ? dev->driver->name :
+        struct device_driver *drv;
+
+        /* dev->driver can change to NULL underneath us because of unbinding,
+         * so be careful about accessing it.  dev->bus and dev->class should
+         * never change once they are set, so they don't need special care.
+         */
+        drv = ACCESS_ONCE(dev->driver);
+        return drv ? drv->name :
                         (dev->bus ? dev->bus->name :
                         (dev->class ? dev->class->name : ""));
 }
@@ -987,6 +994,8 @@ done:
         device_remove_class_symlinks(dev);
  SymlinkError:
         if (MAJOR(dev->devt))
+                devtmpfs_delete_node(dev);
+        if (MAJOR(dev->devt))
                 device_remove_sys_dev_entry(dev);
  devtattrError:
         if (MAJOR(dev->devt))
@@ -1728,8 +1737,5 @@ void device_shutdown(void)
                         dev->driver->shutdown(dev);
                 }
         }
-        kobject_put(sysfs_dev_char_kobj);
-        kobject_put(sysfs_dev_block_kobj);
-        kobject_put(dev_kobj);
         async_synchronize_full();
 }
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index e62a4ccea54d..958bd1540c30 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -35,6 +35,7 @@ static ssize_t __ref store_online(struct sys_device *dev, struct sysdev_attribut
         struct cpu *cpu = container_of(dev, struct cpu, sysdev);
         ssize_t ret;
 
+        cpu_hotplug_driver_lock();
         switch (buf[0]) {
         case '0':
                 ret = cpu_down(cpu->sysdev.id);
@@ -49,6 +50,7 @@ static ssize_t __ref store_online(struct sys_device *dev, struct sysdev_attribut
         default:
                 ret = -EINVAL;
         }
+        cpu_hotplug_driver_unlock();
 
         if (ret >= 0)
                 ret = count;
@@ -72,6 +74,38 @@ void unregister_cpu(struct cpu *cpu)
         per_cpu(cpu_sys_devices, logical_cpu) = NULL;
         return;
 }
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static ssize_t cpu_probe_store(struct class *class, const char *buf,
+                               size_t count)
+{
+        return arch_cpu_probe(buf, count);
+}
+
+static ssize_t cpu_release_store(struct class *class, const char *buf,
+                                 size_t count)
+{
+        return arch_cpu_release(buf, count);
+}
+
+static CLASS_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
+static CLASS_ATTR(release, S_IWUSR, NULL, cpu_release_store);
+
+int __init cpu_probe_release_init(void)
+{
+        int rc;
+
+        rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+                               &class_attr_probe.attr);
+        if (!rc)
+                rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+                                       &class_attr_release.attr);
+
+        return rc;
+}
+device_initcall(cpu_probe_release_init);
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
 #else /* ... !CONFIG_HOTPLUG_CPU */
 static inline void register_cpu_control(struct cpu *cpu)
 {
@@ -97,7 +131,7 @@ static ssize_t show_crash_notes(struct sys_device *dev, struct sysdev_attribute
          * boot up and this data does not change there after. Hence this
          * operation should be safe. No locking required.
          */
-        addr = __pa(per_cpu_ptr(crash_notes, cpunum));
+        addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
         rc = sprintf(buf, "%Lx\n", addr);
         return rc;
 }
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 979d159b5cd1..ee95c76bfd3d 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -188,7 +188,7 @@ EXPORT_SYMBOL_GPL(wait_for_device_probe);
  * @dev: device to try to bind to the driver
  *
  * This function returns -ENODEV if the device is not registered,
- * 1 if the device is bound sucessfully and 0 otherwise.
+ * 1 if the device is bound successfully and 0 otherwise.
  *
  * This function must be called with @dev->sem held.  When called for a
  * USB interface, @dev->parent->sem must be held as well.
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index a1cb5afe6801..50375bb8e51d 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -32,6 +32,8 @@ static int dev_mount = 1;
 static int dev_mount;
 #endif
 
+static rwlock_t dirlock;
+
 static int __init mount_param(char *str)
 {
         dev_mount = simple_strtoul(str, NULL, 0);
@@ -74,47 +76,35 @@ static int dev_mkdir(const char *name, mode_t mode)
         dentry = lookup_create(&nd, 1);
         if (!IS_ERR(dentry)) {
                 err = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
+                if (!err)
+                        /* mark as kernel-created inode */
+                        dentry->d_inode->i_private = &dev_mnt;
                 dput(dentry);
         } else {
                 err = PTR_ERR(dentry);
         }
-        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
+        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
         return err;
 }
 
 static int create_path(const char *nodepath)
 {
-        char *path;
-        struct nameidata nd;
-        int err = 0;
-
-        path = kstrdup(nodepath, GFP_KERNEL);
-        if (!path)
-                return -ENOMEM;
-
-        err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
-                              path, LOOKUP_PARENT, &nd);
-        if (err == 0) {
-                struct dentry *dentry;
-
-                /* create directory right away */
-                dentry = lookup_create(&nd, 1);
-                if (!IS_ERR(dentry)) {
-                        err = vfs_mkdir(nd.path.dentry->d_inode,
-                                        dentry, 0755);
-                        dput(dentry);
-                }
-                mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+        int err;
 
-                path_put(&nd.path);
-        } else if (err == -ENOENT) {
+        read_lock(&dirlock);
+        err = dev_mkdir(nodepath, 0755);
+        if (err == -ENOENT) {
+                char *path;
                 char *s;
 
                 /* parent directories do not exist, create them */
+                path = kstrdup(nodepath, GFP_KERNEL);
+                if (!path)
+                        return -ENOMEM;
                 s = path;
-                while (1) {
+                for (;;) {
                         s = strchr(s, '/');
                         if (!s)
                                 break;
@@ -125,9 +115,9 @@ static int create_path(const char *nodepath)
                         s[0] = '/';
                         s++;
                 }
+                kfree(path);
         }
-
-        kfree(path);
+        read_unlock(&dirlock);
         return err;
 }
 
@@ -156,34 +146,40 @@ int devtmpfs_create_node(struct device *dev)
                 mode |= S_IFCHR;
 
         curr_cred = override_creds(&init_cred);
+
         err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
                               nodename, LOOKUP_PARENT, &nd);
         if (err == -ENOENT) {
-                /* create missing parent directories */
                 create_path(nodename);
                 err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
                                       nodename, LOOKUP_PARENT, &nd);
-                if (err)
-                        goto out;
         }
+        if (err)
+                goto out;
 
         dentry = lookup_create(&nd, 0);
         if (!IS_ERR(dentry)) {
-                int umask;
-
-                umask = sys_umask(0000);
                 err = vfs_mknod(nd.path.dentry->d_inode,
                                 dentry, mode, dev->devt);
-                sys_umask(umask);
-                /* mark as kernel created inode */
-                if (!err)
+                if (!err) {
+                        struct iattr newattrs;
+
+                        /* fixup possibly umasked mode */
+                        newattrs.ia_mode = mode;
+                        newattrs.ia_valid = ATTR_MODE;
+                        mutex_lock(&dentry->d_inode->i_mutex);
+                        notify_change(dentry, &newattrs);
+                        mutex_unlock(&dentry->d_inode->i_mutex);
+
+                        /* mark as kernel-created inode */
                         dentry->d_inode->i_private = &dev_mnt;
+                }
                 dput(dentry);
         } else {
                 err = PTR_ERR(dentry);
         }
-        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
+        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
 out:
         kfree(tmp);
@@ -205,16 +201,21 @@ static int dev_rmdir(const char *name)
         mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
         dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
         if (!IS_ERR(dentry)) {
-                if (dentry->d_inode)
-                        err = vfs_rmdir(nd.path.dentry->d_inode, dentry);
-                else
+                if (dentry->d_inode) {
+                        if (dentry->d_inode->i_private == &dev_mnt)
+                                err = vfs_rmdir(nd.path.dentry->d_inode,
+                                                dentry);
+                        else
+                                err = -EPERM;
+                } else {
                         err = -ENOENT;
+                }
                 dput(dentry);
         } else {
                 err = PTR_ERR(dentry);
         }
-        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
+        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
         return err;
 }
@@ -228,7 +229,8 @@ static int delete_path(const char *nodepath)
         if (!path)
                 return -ENOMEM;
 
-        while (1) {
+        write_lock(&dirlock);
+        for (;;) {
                 char *base;
 
                 base = strrchr(path, '/');
@@ -239,6 +241,7 @@ static int delete_path(const char *nodepath)
                 if (err)
                         break;
         }
+        write_unlock(&dirlock);
 
         kfree(path);
         return err;
@@ -322,9 +325,8 @@ out:
  * If configured, or requested by the commandline, devtmpfs will be
  * auto-mounted after the kernel mounted the root filesystem.
  */
-int devtmpfs_mount(const char *mountpoint)
+int devtmpfs_mount(const char *mntdir)
 {
-        struct path path;
         int err;
 
         if (!dev_mount)
@@ -333,15 +335,11 @@ int devtmpfs_mount(const char *mountpoint)
         if (!dev_mnt)
                 return 0;
 
-        err = kern_path(mountpoint, LOOKUP_FOLLOW, &path);
-        if (err)
-                return err;
-        err = do_add_mount(dev_mnt, &path, 0, NULL);
+        err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, NULL);
         if (err)
                 printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
         else
                 printk(KERN_INFO "devtmpfs: mounted\n");
-        path_put(&path);
         return err;
 }
 
@@ -354,6 +352,8 @@ int __init devtmpfs_init(void)
         int err;
         struct vfsmount *mnt;
 
+        rwlock_init(&dirlock);
+
         err = register_filesystem(&dev_fs_type);
         if (err) {
                 printk(KERN_ERR "devtmpfs: unable to register devtmpfs "
@@ -361,7 +361,7 @@ int __init devtmpfs_init(void)
                 return err;
         }
 
-        mnt = kern_mount(&dev_fs_type);
+        mnt = kern_mount_data(&dev_fs_type, "mode=0755");
         if (IS_ERR(mnt)) {
                 err = PTR_ERR(mnt);
                 printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 7376367bcb80..a95024166b66 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -601,12 +601,9 @@ request_firmware_work_func(void *arg)
         }
         ret = _request_firmware(&fw, fw_work->name, fw_work->device,
                 fw_work->uevent);
-        if (ret < 0)
-                fw_work->cont(NULL, fw_work->context);
-        else {
-                fw_work->cont(fw, fw_work->context);
-                release_firmware(fw);
-        }
+
+        fw_work->cont(fw, fw_work->context);
+
         module_put(fw_work->module);
         kfree(fw_work);
         return ret;
@@ -619,6 +616,7 @@ request_firmware_work_func(void *arg)
  *      is non-zero else the firmware copy must be done manually.
  * @name: name of firmware file
  * @device: device for which firmware is being loaded
+ * @gfp: allocation flags
  * @context: will be passed over to @cont, and
  *      @fw may be %NULL if firmware request fails.
  * @cont: function will be called asynchronously when the firmware
@@ -631,12 +629,12 @@ request_firmware_work_func(void *arg)
 int
 request_firmware_nowait(
         struct module *module, int uevent,
-        const char *name, struct device *device, void *context,
+        const char *name, struct device *device, gfp_t gfp, void *context,
         void (*cont)(const struct firmware *fw, void *context))
 {
         struct task_struct *task;
         struct firmware_work *fw_work = kmalloc(sizeof (struct firmware_work),
-                                                GFP_ATOMIC);
+                                                gfp);
 
         if (!fw_work)
                 return -ENOMEM;
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 989429cfed88..d7d77d4a402c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -63,6 +63,20 @@ void unregister_memory_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_memory_notifier);
 
+static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);
+
+int register_memory_isolate_notifier(struct notifier_block *nb)
+{
+        return atomic_notifier_chain_register(&memory_isolate_chain, nb);
+}
+EXPORT_SYMBOL(register_memory_isolate_notifier);
+
+void unregister_memory_isolate_notifier(struct notifier_block *nb)
+{
+        atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
+}
+EXPORT_SYMBOL(unregister_memory_isolate_notifier);
+
 /*
  * register_memory - Setup a sysfs device for a memory block
  */
@@ -157,6 +171,11 @@ int memory_notify(unsigned long val, void *v)
         return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
+int memory_isolate_notify(unsigned long val, void *v)
+{
+        return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
+}
+
 /*
  * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
  * OK to have direct references to sparsemem variables in here.
@@ -341,6 +360,64 @@ static inline int memory_probe_init(void)
 }
 #endif
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Support for offlining pages of memory
+ */
+
+/* Soft offline a page */
+static ssize_t
+store_soft_offline_page(struct class *class, const char *buf, size_t count)
+{
+        int ret;
+        u64 pfn;
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+        if (strict_strtoull(buf, 0, &pfn) < 0)
+                return -EINVAL;
+        pfn >>= PAGE_SHIFT;
+        if (!pfn_valid(pfn))
+                return -ENXIO;
+        ret = soft_offline_page(pfn_to_page(pfn), 0);
+        return ret == 0 ? count : ret;
+}
+
+/* Forcibly offline a page, including killing processes. */
+static ssize_t
+store_hard_offline_page(struct class *class, const char *buf, size_t count)
+{
+        int ret;
+        u64 pfn;
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+        if (strict_strtoull(buf, 0, &pfn) < 0)
+                return -EINVAL;
+        pfn >>= PAGE_SHIFT;
+        ret = __memory_failure(pfn, 0, 0);
+        return ret ? ret : count;
+}
+
+static CLASS_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
+static CLASS_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
+
+static __init int memory_fail_init(void)
+{
+        int err;
+
+        err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
+                                &class_attr_soft_offline_page.attr);
+        if (!err)
+                err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
+                                &class_attr_hard_offline_page.attr);
+        return err;
+}
+#else
+static inline int memory_fail_init(void)
+{
+        return 0;
+}
+#endif
+
 /*
  * Note that phys_device is optional.  It is here to allow for
  * differentiation between which *physical* devices each
@@ -473,6 +550,9 @@ int __init memory_dev_init(void)
         err = memory_probe_init();
         if (!ret)
                 ret = err;
+        err = memory_fail_init();
+        if (!ret)
+                ret = err;
         err = block_size_init();
         if (!ret)
                 ret = err;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 1fe5536d404f..70122791683d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -173,6 +173,47 @@ 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 +237,8 @@ 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 +259,7 @@ 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 +271,43 @@ 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 +329,7 @@ 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 +346,15 @@ 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 +363,16 @@ 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 +383,14 @@ 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 +420,77 @@ 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 +514,9 @@ 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;
@@ -460,13 +606,17 @@ static int node_states_init(void)
         return err;
 }
 
+#define NODE_CALLBACK_PRI       2       /* lower than SLAB */
 static int __init register_node_type(void)
 {
         int ret;
 
         ret = sysdev_class_register(&node_class);
-        if (!ret)
+        if (!ret) {
                 ret = node_states_init();
+                hotplug_memory_notifier(node_memory_callback,
+                                        NODE_CALLBACK_PRI);
+        }
 
         /*
          * Note:  we're not going to unregister the node class if we fail
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 4fa954b07ac4..9d2ee25deaf5 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1000,7 +1000,7 @@ static __initdata LIST_HEAD(early_platform_device_list);
 int __init early_platform_driver_register(struct early_platform_driver *epdrv,
                                           char *buf)
 {
-        unsigned long index;
+        char *tmp;
         int n;
 
         /* Simply add the driver to the end of the global list.
@@ -1019,13 +1019,28 @@ int __init early_platform_driver_register(struct early_platform_driver *epdrv,
         if (buf && !strncmp(buf, epdrv->pdrv->driver.name, n)) {
                 list_move(&epdrv->list, &early_platform_driver_list);
 
-                if (!strcmp(buf, epdrv->pdrv->driver.name))
+                /* Allow passing parameters after device name */
+                if (buf[n] == '\0' || buf[n] == ',')
                         epdrv->requested_id = -1;
-                else if (buf[n] == '.' && strict_strtoul(&buf[n + 1], 10,
-                                                         &index) == 0)
-                        epdrv->requested_id = index;
-                else
-                        epdrv->requested_id = EARLY_PLATFORM_ID_ERROR;
+                else {
+                        epdrv->requested_id = simple_strtoul(&buf[n + 1],
+                                                             &tmp, 10);
+
+                        if (buf[n] != '.' || (tmp == &buf[n + 1])) {
+                                epdrv->requested_id = EARLY_PLATFORM_ID_ERROR;
+                                n = 0;
+                        } else
+                                n += strcspn(&buf[n + 1], ",") + 1;
+                }
+
+                if (buf[n] == ',')
+                        n++;
+
+                if (epdrv->bufsize) {
+                        memcpy(epdrv->buffer, &buf[n],
+                               min_t(int, epdrv->bufsize, strlen(&buf[n]) + 1));
+                        epdrv->buffer[epdrv->bufsize - 1] = '\0';
+                }
         }
 
         return 0;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 8aa2443182d5..48adf80926a0 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -23,8 +23,8 @@
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/resume-trace.h>
-#include <linux/rwsem.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 
 #include "../base.h"
 #include "power.h"
@@ -161,6 +161,32 @@ void device_pm_move_last(struct device *dev)
         list_move_tail(&dev->power.entry, &dpm_list);
 }
 
+static ktime_t initcall_debug_start(struct device *dev)
+{
+        ktime_t calltime = ktime_set(0, 0);
+
+        if (initcall_debug) {
+                pr_info("calling  %s+ @ %i\n",
+                                dev_name(dev), task_pid_nr(current));
+                calltime = ktime_get();
+        }
+
+        return calltime;
+}
+
+static void initcall_debug_report(struct device *dev, ktime_t calltime,
+                                  int error)
+{
+        ktime_t delta, rettime;
+
+        if (initcall_debug) {
+                rettime = ktime_get();
+                delta = ktime_sub(rettime, calltime);
+                pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
+                        error, (unsigned long long)ktime_to_ns(delta) >> 10);
+        }
+}
+
 /**
  * pm_op - Execute the PM operation appropriate for given PM event.
  * @dev: Device to handle.
@@ -172,6 +198,9 @@ static int pm_op(struct device *dev,
                  pm_message_t state)
 {
         int error = 0;
+        ktime_t calltime;
+
+        calltime = initcall_debug_start(dev);
 
         switch (state.event) {
 #ifdef CONFIG_SUSPEND
@@ -219,6 +248,9 @@ static int pm_op(struct device *dev,
         default:
                 error = -EINVAL;
         }
+
+        initcall_debug_report(dev, calltime, error);
+
         return error;
 }
 
@@ -236,6 +268,13 @@ static int pm_noirq_op(struct device *dev,
                         pm_message_t state)
 {
         int error = 0;
+        ktime_t calltime, delta, rettime;
+
+        if (initcall_debug) {
+                pr_info("calling  %s_i+ @ %i\n",
+                                dev_name(dev), task_pid_nr(current));
+                calltime = ktime_get();
+        }
 
         switch (state.event) {
 #ifdef CONFIG_SUSPEND
@@ -283,6 +322,15 @@ static int pm_noirq_op(struct device *dev,
         default:
                 error = -EINVAL;
         }
+
+        if (initcall_debug) {
+                rettime = ktime_get();
+                delta = ktime_sub(rettime, calltime);
+                printk("initcall %s_i+ returned %d after %Ld usecs\n",
+                        dev_name(dev), error,
+                        (unsigned long long)ktime_to_ns(delta) >> 10);
+        }
+
         return error;
 }
 
@@ -324,6 +372,23 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
                 kobject_name(&dev->kobj), pm_verb(state.event), info, error);
 }
 
+static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
+{
+        ktime_t calltime;
+        s64 usecs64;
+        int usecs;
+
+        calltime = ktime_get();
+        usecs64 = ktime_to_ns(ktime_sub(calltime, starttime));
+        do_div(usecs64, NSEC_PER_USEC);
+        usecs = usecs64;
+        if (usecs == 0)
+                usecs = 1;
+        pr_info("PM: %s%s%s of devices complete after %ld.%03ld msecs\n",
+                info ?: "", info ? " " : "", pm_verb(state.event),
+                usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC);
+}
+
 /*------------------------- Resume routines -------------------------*/
 
 /**
@@ -341,14 +406,11 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
         TRACE_DEVICE(dev);
         TRACE_RESUME(0);
 
-        if (!dev->bus)
-                goto End;
-
-        if (dev->bus->pm) {
+        if (dev->bus && dev->bus->pm) {
                 pm_dev_dbg(dev, state, "EARLY ");
                 error = pm_noirq_op(dev, dev->bus->pm, state);
         }
- End:
+
         TRACE_RESUME(error);
         return error;
 }
@@ -363,6 +425,7 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 void dpm_resume_noirq(pm_message_t state)
 {
         struct device *dev;
+        ktime_t starttime = ktime_get();
 
         mutex_lock(&dpm_list_mtx);
         transition_started = false;
@@ -376,11 +439,32 @@ void dpm_resume_noirq(pm_message_t state)
                                 pm_dev_err(dev, state, " early", error);
                 }
         mutex_unlock(&dpm_list_mtx);
+        dpm_show_time(starttime, state, "early");
         resume_device_irqs();
 }
 EXPORT_SYMBOL_GPL(dpm_resume_noirq);
 
 /**
+ * legacy_resume - Execute a legacy (bus or class) resume callback for device.
+ * dev: Device to resume.
+ * cb: Resume callback to execute.
+ */
+static int legacy_resume(struct device *dev, int (*cb)(struct device *dev))
+{
+        int error;
+        ktime_t calltime;
+
+        calltime = initcall_debug_start(dev);
+
+        error = cb(dev);
+        suspend_report_result(cb, error);
+
+        initcall_debug_report(dev, calltime, error);
+
+        return error;
+}
+
+/**
  * device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
@@ -400,7 +484,7 @@ static int device_resume(struct device *dev, pm_message_t state)
                         error = pm_op(dev, dev->bus->pm, state);
                 } else if (dev->bus->resume) {
                         pm_dev_dbg(dev, state, "legacy ");
-                        error = dev->bus->resume(dev);
+                        error = legacy_resume(dev, dev->bus->resume);
                 }
                 if (error)
                         goto End;
@@ -421,7 +505,7 @@ static int device_resume(struct device *dev, pm_message_t state)
                         error = pm_op(dev, dev->class->pm, state);
                 } else if (dev->class->resume) {
                         pm_dev_dbg(dev, state, "legacy class ");
-                        error = dev->class->resume(dev);
+                        error = legacy_resume(dev, dev->class->resume);
                 }
         }
  End:
@@ -441,6 +525,7 @@ static int device_resume(struct device *dev, pm_message_t state)
 static void dpm_resume(pm_message_t state)
 {
         struct list_head list;
+        ktime_t starttime = ktime_get();
 
         INIT_LIST_HEAD(&list);
         mutex_lock(&dpm_list_mtx);
@@ -469,6 +554,7 @@ static void dpm_resume(pm_message_t state)
         }
         list_splice(&list, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
+        dpm_show_time(starttime, state, NULL);
 }
 
 /**
@@ -521,7 +607,7 @@ static void dpm_complete(pm_message_t state)
                         mutex_unlock(&dpm_list_mtx);
 
                         device_complete(dev, state);
-                        pm_runtime_put_noidle(dev);
+                        pm_runtime_put_sync(dev);
 
                         mutex_lock(&dpm_list_mtx);
                 }
@@ -584,10 +670,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
         int error = 0;
 
-        if (!dev->bus)
-                return 0;
-
-        if (dev->bus->pm) {
+        if (dev->bus && dev->bus->pm) {
                 pm_dev_dbg(dev, state, "LATE ");
                 error = pm_noirq_op(dev, dev->bus->pm, state);
         }
@@ -604,6 +687,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 int dpm_suspend_noirq(pm_message_t state)
 {
         struct device *dev;
+        ktime_t starttime = ktime_get();
         int error = 0;
 
         suspend_device_irqs();
@@ -619,11 +703,34 @@ int dpm_suspend_noirq(pm_message_t state)
         mutex_unlock(&dpm_list_mtx);
         if (error)
                 dpm_resume_noirq(resume_event(state));
+        else
+                dpm_show_time(starttime, state, "late");
         return error;
 }
 EXPORT_SYMBOL_GPL(dpm_suspend_noirq);
 
 /**
+ * legacy_suspend - Execute a legacy (bus or class) suspend callback for device.
+ * dev: Device to suspend.
+ * cb: Suspend callback to execute.
+ */
+static int legacy_suspend(struct device *dev, pm_message_t state,
+                          int (*cb)(struct device *dev, pm_message_t state))
+{
+        int error;
+        ktime_t calltime;
+
+        calltime = initcall_debug_start(dev);
+
+        error = cb(dev, state);
+        suspend_report_result(cb, error);
+
+        initcall_debug_report(dev, calltime, error);
+
+        return error;
+}
+
+/**
  * device_suspend - Execute "suspend" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
@@ -640,8 +747,7 @@ static int device_suspend(struct device *dev, pm_message_t state)
                         error = pm_op(dev, dev->class->pm, state);
                 } else if (dev->class->suspend) {
                         pm_dev_dbg(dev, state, "legacy class ");
-                        error = dev->class->suspend(dev, state);
-                        suspend_report_result(dev->class->suspend, error);
+                        error = legacy_suspend(dev, state, dev->class->suspend);
                 }
                 if (error)
                         goto End;
@@ -662,8 +768,7 @@ static int device_suspend(struct device *dev, pm_message_t state)
                         error = pm_op(dev, dev->bus->pm, state);
                 } else if (dev->bus->suspend) {
                         pm_dev_dbg(dev, state, "legacy ");
-                        error = dev->bus->suspend(dev, state);
-                        suspend_report_result(dev->bus->suspend, error);
+                        error = legacy_suspend(dev, state, dev->bus->suspend);
                 }
         }
  End:
@@ -679,6 +784,7 @@ static int device_suspend(struct device *dev, pm_message_t state)
 static int dpm_suspend(pm_message_t state)
 {
         struct list_head list;
+        ktime_t starttime = ktime_get();
         int error = 0;
 
         INIT_LIST_HEAD(&list);
@@ -704,6 +810,8 @@ static int dpm_suspend(pm_message_t state)
         }
         list_splice(&list, dpm_list.prev);
         mutex_unlock(&dpm_list_mtx);
+        if (!error)
+                dpm_show_time(starttime, state, NULL);
         return error;
 }
 
@@ -772,7 +880,7 @@ static int dpm_prepare(pm_message_t state)
                 pm_runtime_get_noresume(dev);
                 if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) {
                         /* Wake-up requested during system sleep transition. */
-                        pm_runtime_put_noidle(dev);
+                        pm_runtime_put_sync(dev);
                         error = -EBUSY;
                 } else {
                         error = device_prepare(dev, state);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 846d89e3d122..f8b044e8aef7 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -85,6 +85,19 @@ static int __pm_runtime_idle(struct device *dev)
                 dev->bus->pm->runtime_idle(dev);
 
                 spin_lock_irq(&dev->power.lock);
+        } else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle) {
+                spin_unlock_irq(&dev->power.lock);
+
+                dev->type->pm->runtime_idle(dev);
+
+                spin_lock_irq(&dev->power.lock);
+        } else if (dev->class && dev->class->pm
+            && dev->class->pm->runtime_idle) {
+                spin_unlock_irq(&dev->power.lock);
+
+                dev->class->pm->runtime_idle(dev);
+
+                spin_lock_irq(&dev->power.lock);
         }
 
         dev->power.idle_notification = false;
@@ -185,6 +198,7 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
         }
 
         dev->power.runtime_status = RPM_SUSPENDING;
+        dev->power.deferred_resume = false;
 
         if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) {
                 spin_unlock_irq(&dev->power.lock);
@@ -193,6 +207,22 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
 
                 spin_lock_irq(&dev->power.lock);
                 dev->power.runtime_error = retval;
+        } else if (dev->type && dev->type->pm
+            && dev->type->pm->runtime_suspend) {
+                spin_unlock_irq(&dev->power.lock);
+
+                retval = dev->type->pm->runtime_suspend(dev);
+
+                spin_lock_irq(&dev->power.lock);
+                dev->power.runtime_error = retval;
+        } else if (dev->class && dev->class->pm
+            && dev->class->pm->runtime_suspend) {
+                spin_unlock_irq(&dev->power.lock);
+
+                retval = dev->class->pm->runtime_suspend(dev);
+
+                spin_lock_irq(&dev->power.lock);
+                dev->power.runtime_error = retval;
         } else {
                 retval = -ENOSYS;
         }
@@ -200,7 +230,6 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
         if (retval) {
                 dev->power.runtime_status = RPM_ACTIVE;
                 pm_runtime_cancel_pending(dev);
-                dev->power.deferred_resume = false;
 
                 if (retval == -EAGAIN || retval == -EBUSY) {
                         notify = true;
@@ -217,7 +246,6 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
         wake_up_all(&dev->power.wait_queue);
 
         if (dev->power.deferred_resume) {
-                dev->power.deferred_resume = false;
                 __pm_runtime_resume(dev, false);
                 retval = -EAGAIN;
                 goto out;
@@ -360,6 +388,22 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
 
                 spin_lock_irq(&dev->power.lock);
                 dev->power.runtime_error = retval;
+        } else if (dev->type && dev->type->pm
+            && dev->type->pm->runtime_resume) {
+                spin_unlock_irq(&dev->power.lock);
+
+                retval = dev->type->pm->runtime_resume(dev);
+
+                spin_lock_irq(&dev->power.lock);
+                dev->power.runtime_error = retval;
+        } else if (dev->class && dev->class->pm
+            && dev->class->pm->runtime_resume) {
+                spin_unlock_irq(&dev->power.lock);
+
+                retval = dev->class->pm->runtime_resume(dev);
+
+                spin_lock_irq(&dev->power.lock);
+                dev->power.runtime_error = retval;
         } else {
                 retval = -ENOSYS;
         }
@@ -626,6 +670,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay)
                 goto out;
 
         dev->power.timer_expires = jiffies + msecs_to_jiffies(delay);
+        if (!dev->power.timer_expires)
+                dev->power.timer_expires = 1;
         mod_timer(&dev->power.suspend_timer, dev->power.timer_expires);
 
  out:
@@ -659,13 +705,17 @@ static int __pm_request_resume(struct device *dev)
 
         pm_runtime_deactivate_timer(dev);
 
+        if (dev->power.runtime_status == RPM_SUSPENDING) {
+                dev->power.deferred_resume = true;
+                return retval;
+        }
         if (dev->power.request_pending) {
                 /* If non-resume request is pending, we can overtake it. */
                 dev->power.request = retval ? RPM_REQ_NONE : RPM_REQ_RESUME;
                 return retval;
-        } else if (retval) {
-                return retval;
         }
+        if (retval)
+                return retval;
 
         dev->power.request = RPM_REQ_RESUME;
         dev->power.request_pending = true;
@@ -696,15 +746,15 @@ EXPORT_SYMBOL_GPL(pm_request_resume);
  * @dev: Device to handle.
  * @sync: If set and the device is suspended, resume it synchronously.
  *
- * Increment the usage count of the device and if it was zero previously,
- * resume it or submit a resume request for it, depending on the value of @sync.
+ * Increment the usage count of the device and resume it or submit a resume
+ * request for it, depending on the value of @sync.
  */
 int __pm_runtime_get(struct device *dev, bool sync)
 {
-        int retval = 1;
+        int retval;
 
-        if (atomic_add_return(1, &dev->power.usage_count) == 1)
-                retval = sync ? pm_runtime_resume(dev) : pm_request_resume(dev);
+        atomic_inc(&dev->power.usage_count);
+        retval = sync ? pm_runtime_resume(dev) : pm_request_resume(dev);
 
         return retval;
 }
@@ -777,7 +827,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
         }
 
         if (parent) {
-                spin_lock(&parent->power.lock);
+                spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);
 
                 /*
                  * It is invalid to put an active child under a parent that is
@@ -786,12 +836,10 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
                  */
                 if (!parent->power.disable_depth
                     && !parent->power.ignore_children
-                    && parent->power.runtime_status != RPM_ACTIVE) {
+                    && parent->power.runtime_status != RPM_ACTIVE)
                         error = -EBUSY;
-                } else {
-                        if (dev->power.runtime_status == RPM_SUSPENDED)
-                                atomic_inc(&parent->power.child_count);
-                }
+                else if (dev->power.runtime_status == RPM_SUSPENDED)
+                        atomic_inc(&parent->power.child_count);
 
                 spin_unlock(&parent->power.lock);