Merge branch 'driver-core-next' into cgroup/for-3.15

Pending kernfs conversion depends on kernfs improvements in
driver-core-next.  Pull it into for-3.15.
Signed-off-by: Tejun Heo <tj@kernel.org>

arch/s390/include/asm/ccwgroup.h

@@ -23,6 +23,7 @@ struct ccwgroup_device {
 	unsigned int count;
 	struct device	dev;
 	struct ccw_device *cdev[0];
+	struct work_struct ungroup_work;
 };
 
 /**

arch/s390/pci/pci_sysfs.c

@@ -48,29 +48,27 @@ static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL);
 
-static void recover_callback(struct device *dev)
+static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct zpci_dev *zdev = get_zdev(pdev);
 	int ret;
 
+	if (!device_remove_file_self(dev, attr))
+		return count;
+
 	pci_stop_and_remove_bus_device(pdev);
 	ret = zpci_disable_device(zdev);
 	if (ret)
-		return;
+		return ret;
 
 	ret = zpci_enable_device(zdev);
 	if (ret)
-		return;
+		return ret;
 
 	pci_rescan_bus(zdev->bus);
-}
-
-static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
-{
-	int rc = device_schedule_callback(dev, recover_callback);
-	return rc ? rc : count;
+	return count;
 }
 static DEVICE_ATTR(recover, S_IWUSR, NULL, store_recover);
 

drivers/base/core.c

@@ -570,6 +570,23 @@ void device_remove_file(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_remove_file);
 
+/**
+ * device_remove_file_self - remove sysfs attribute file from its own method.
+ * @dev: device.
+ * @attr: device attribute descriptor.
+ *
+ * See kernfs_remove_self() for details.
+ */
+bool device_remove_file_self(struct device *dev,
+			     const struct device_attribute *attr)
+{
+	if (dev)
+		return sysfs_remove_file_self(&dev->kobj, &attr->attr);
+	else
+		return false;
+}
+EXPORT_SYMBOL_GPL(device_remove_file_self);
+
 /**
  * device_create_bin_file - create sysfs binary attribute file for device.
  * @dev: device.
@@ -598,39 +615,6 @@ void device_remove_bin_file(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_remove_bin_file);
 
-/**
- * device_schedule_callback_owner - helper to schedule a callback for a device
- * @dev: device.
- * @func: callback function to invoke later.
- * @owner: module owning the callback routine
- *
- * Attribute methods must not unregister themselves or their parent device
- * (which would amount to the same thing).  Attempts to do so will deadlock,
- * since unregistration is mutually exclusive with driver callbacks.
- *
- * Instead methods can call this routine, which will attempt to allocate
- * and schedule a workqueue request to call back @func with @dev as its
- * argument in the workqueue's process context.  @dev will be pinned until
- * @func returns.
- *
- * This routine is usually called via the inline device_schedule_callback(),
- * which automatically sets @owner to THIS_MODULE.
- *
- * Returns 0 if the request was submitted, -ENOMEM if storage could not
- * be allocated, -ENODEV if a reference to @owner isn't available.
- *
- * NOTE: This routine won't work if CONFIG_SYSFS isn't set!  It uses an
- * underlying sysfs routine (since it is intended for use by attribute
- * methods), and if sysfs isn't available you'll get nothing but -ENOSYS.
- */
-int device_schedule_callback_owner(struct device *dev,
-		void (*func)(struct device *), struct module *owner)
-{
-	return sysfs_schedule_callback(&dev->kobj,
-			(void (*)(void *)) func, dev, owner);
-}
-EXPORT_SYMBOL_GPL(device_schedule_callback_owner);
-
 static void klist_children_get(struct klist_node *n)
 {
 	struct device_private *p = to_device_private_parent(n);

drivers/base/dma-buf.c

@@ -251,9 +251,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
  * @dmabuf:	[in]	buffer to attach device to.
  * @dev:	[in]	device to be attached.
  *
- * Returns struct dma_buf_attachment * for this attachment; may return negative
- * error codes.
- *
+ * Returns struct dma_buf_attachment * for this attachment; returns ERR_PTR on
+ * error.
  */
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 					  struct device *dev)
@@ -319,9 +318,8 @@ EXPORT_SYMBOL_GPL(dma_buf_detach);
  * @attach:	[in]	attachment whose scatterlist is to be returned
  * @direction:	[in]	direction of DMA transfer
  *
- * Returns sg_table containing the scatterlist to be returned; may return NULL
- * or ERR_PTR.
- *
+ * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
+ * on error.
  */
 struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 					enum dma_data_direction direction)
@@ -334,6 +332,8 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		return ERR_PTR(-EINVAL);
 
 	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
+	if (!sg_table)
+		sg_table = ERR_PTR(-ENOMEM);
 
 	return sg_table;
 }
@@ -544,6 +544,8 @@ EXPORT_SYMBOL_GPL(dma_buf_mmap);
  * These calls are optional in drivers. The intended use for them
  * is for mapping objects linear in kernel space for high use objects.
  * Please attempt to use kmap/kunmap before thinking about these interfaces.
+ *
+ * Returns NULL on error.
  */
 void *dma_buf_vmap(struct dma_buf *dmabuf)
 {
@@ -566,7 +568,9 @@ void *dma_buf_vmap(struct dma_buf *dmabuf)
 	BUG_ON(dmabuf->vmap_ptr);
 
 	ptr = dmabuf->ops->vmap(dmabuf);
-	if (IS_ERR_OR_NULL(ptr))
+	if (WARN_ON_ONCE(IS_ERR(ptr)))
+		ptr = NULL;
+	if (!ptr)
 		goto out_unlock;
 
 	dmabuf->vmap_ptr = ptr;

drivers/gpu/drm/drm_prime.c

@@ -471,7 +471,7 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev,
 	get_dma_buf(dma_buf);
 
 	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR_OR_NULL(sgt)) {
+	if (IS_ERR(sgt)) {
 		ret = PTR_ERR(sgt);
 		goto fail_detach;
 	}

drivers/gpu/drm/exynos/exynos_drm_dmabuf.c

@@ -224,7 +224,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 	get_dma_buf(dma_buf);
 
 	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR_OR_NULL(sgt)) {
+	if (IS_ERR(sgt)) {
 		ret = PTR_ERR(sgt);
 		goto err_buf_detach;
 	}

drivers/media/v4l2-core/videobuf2-dma-contig.c

@@ -719,7 +719,7 @@ static int vb2_dc_map_dmabuf(void *mem_priv)
 
 	/* get the associated scatterlist for this buffer */
 	sgt = dma_buf_map_attachment(buf->db_attach, buf->dma_dir);
-	if (IS_ERR_OR_NULL(sgt)) {
+	if (IS_ERR(sgt)) {
 		pr_err("Error getting dmabuf scatterlist\n");
 		return -EINVAL;
 	}

drivers/pci/pci-sysfs.c

@@ -351,28 +351,17 @@ static struct device_attribute dev_rescan_attr = __ATTR(rescan,
 							(S_IWUSR|S_IWGRP),
 							NULL, dev_rescan_store);
 
-static void remove_callback(struct device *dev)
-{
-	pci_stop_and_remove_bus_device_locked(to_pci_dev(dev));
-}
-
 static ssize_t
-remove_store(struct device *dev, struct device_attribute *dummy,
+remove_store(struct device *dev, struct device_attribute *attr,
 	     const char *buf, size_t count)
 {
-	int ret = 0;
 	unsigned long val;
 
 	if (kstrtoul(buf, 0, &val) < 0)
 		return -EINVAL;
 
-	/* An attribute cannot be unregistered by one of its own methods,
-	 * so we have to use this roundabout approach.
-	 */
-	if (val)
-		ret = device_schedule_callback(dev, remove_callback);
-	if (ret)
-		count = ret;
+	if (val && device_remove_file_self(dev, attr))
+		pci_stop_and_remove_bus_device_locked(to_pci_dev(dev));
 	return count;
 }
 static struct device_attribute dev_remove_attr = __ATTR(remove,

drivers/s390/block/dcssblk.c

@@ -304,12 +304,6 @@ dcssblk_load_segment(char *name, struct segment_info **seg_info)
 	return rc;
 }
 
-static void dcssblk_unregister_callback(struct device *dev)
-{
-	device_unregister(dev);
-	put_device(dev);
-}
-
 /*
  * device attribute for switching shared/nonshared (exclusive)
  * operation (show + store)
@@ -397,7 +391,13 @@ dcssblk_shared_store(struct device *dev, struct device_attribute *attr, const ch
 	blk_cleanup_queue(dev_info->dcssblk_queue);
 	dev_info->gd->queue = NULL;
 	put_disk(dev_info->gd);
-	rc = device_schedule_callback(dev, dcssblk_unregister_callback);
+	up_write(&dcssblk_devices_sem);
+
+	if (device_remove_file_self(dev, attr)) {
+		device_unregister(dev);
+		put_device(dev);
+	}
+	return rc;
 out:
 	up_write(&dcssblk_devices_sem);
 	return rc;

drivers/s390/cio/ccwgroup.c

@@ -168,14 +168,12 @@ static ssize_t ccwgroup_online_show(struct device *dev,
  * Provide an 'ungroup' attribute so the user can remove group devices no
  * longer needed or accidentially created. Saves memory :)
  */
-static void ccwgroup_ungroup_callback(struct device *dev)
+static void ccwgroup_ungroup(struct ccwgroup_device *gdev)
 {
-	struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
-
 	mutex_lock(&gdev->reg_mutex);
 	if (device_is_registered(&gdev->dev)) {
 		__ccwgroup_remove_symlinks(gdev);
-		device_unregister(dev);
+		device_unregister(&gdev->dev);
 		__ccwgroup_remove_cdev_refs(gdev);
 	}
 	mutex_unlock(&gdev->reg_mutex);
@@ -195,10 +193,9 @@ static ssize_t ccwgroup_ungroup_store(struct device *dev,
 		rc = -EINVAL;
 		goto out;
 	}
-	/* Note that we cannot unregister the device from one of its
-	 * attribute methods, so we have to use this roundabout approach.
-	 */
-	rc = device_schedule_callback(dev, ccwgroup_ungroup_callback);
+
+	if (device_remove_file_self(dev, attr))
+		ccwgroup_ungroup(gdev);
 out:
 	if (rc) {
 		if (rc != -EAGAIN)
@@ -224,6 +221,14 @@ static const struct attribute_group *ccwgroup_attr_groups[] = {
 	NULL,
 };
 
+static void ccwgroup_ungroup_workfn(struct work_struct *work)
+{
+	struct ccwgroup_device *gdev =
+		container_of(work, struct ccwgroup_device, ungroup_work);
+
+	ccwgroup_ungroup(gdev);
+}
+
 static void ccwgroup_release(struct device *dev)
 {
 	kfree(to_ccwgroupdev(dev));
@@ -323,6 +328,7 @@ int ccwgroup_create_dev(struct device *parent, struct ccwgroup_driver *gdrv,
 	atomic_set(&gdev->onoff, 0);
 	mutex_init(&gdev->reg_mutex);
 	mutex_lock(&gdev->reg_mutex);
+	INIT_WORK(&gdev->ungroup_work, ccwgroup_ungroup_workfn);
 	gdev->count = num_devices;
 	gdev->dev.bus = &ccwgroup_bus_type;
 	gdev->dev.parent = parent;
@@ -404,10 +410,10 @@ EXPORT_SYMBOL(ccwgroup_create_dev);
 static int ccwgroup_notifier(struct notifier_block *nb, unsigned long action,
 			     void *data)
 {
-	struct device *dev = data;
+	struct ccwgroup_device *gdev = to_ccwgroupdev(data);
 
 	if (action == BUS_NOTIFY_UNBIND_DRIVER)
-		device_schedule_callback(dev, ccwgroup_ungroup_callback);
+		schedule_work(&gdev->ungroup_work);
 
 	return NOTIFY_OK;
 }

drivers/scsi/scsi_sysfs.c

@@ -649,23 +649,12 @@ store_rescan_field (struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(rescan, S_IWUSR, NULL, store_rescan_field);
 
-static void sdev_store_delete_callback(struct device *dev)
-{
-	scsi_remove_device(to_scsi_device(dev));
-}
-
 static ssize_t
 sdev_store_delete(struct device *dev, struct device_attribute *attr,
 		  const char *buf, size_t count)
 {
-	int rc;
-
-	/* An attribute cannot be unregistered by one of its own methods,
-	 * so we have to use this roundabout approach.
-	 */
-	rc = device_schedule_callback(dev, sdev_store_delete_callback);
-	if (rc)
-		count = rc;
+	if (device_remove_file_self(dev, attr))
+		scsi_remove_device(to_scsi_device(dev));
 	return count;
 };
 static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete);

fs/Kconfig

@@ -96,6 +96,7 @@ endif # BLOCK
 menu "Pseudo filesystems"
 
 source "fs/proc/Kconfig"
+source "fs/kernfs/Kconfig"
 source "fs/sysfs/Kconfig"
 
 config TMPFS

fs/Makefile

@@ -52,7 +52,8 @@ obj-$(CONFIG_FHANDLE)		+= fhandle.o
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
-obj-$(CONFIG_SYSFS)		+= sysfs/ kernfs/
+obj-$(CONFIG_KERNFS)		+= kernfs/
+obj-$(CONFIG_SYSFS)		+= sysfs/
 obj-$(CONFIG_CONFIGFS_FS)	+= configfs/
 obj-y				+= devpts/
 

fs/kernfs/Kconfig

+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+	bool
+	default n

fs/kernfs/file.c

@@ -252,19 +252,9 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
 	struct kernfs_open_file *of = kernfs_of(file);
-	ssize_t len = min_t(size_t, count, PAGE_SIZE);
 	const struct kernfs_ops *ops;
-	char *buf;
-
-	buf = kmalloc(len + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, user_buf, len)) {
-		len = -EFAULT;
-		goto out_free;
-	}
-	buf[len] = '\0';	/* guarantee string termination */
+	char *buf = NULL;
+	ssize_t len;
 
 	/*
 	 * @of->mutex nests outside active ref and is just to ensure that
@@ -273,22 +263,45 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 	mutex_lock(&of->mutex);
 	if (!kernfs_get_active(of->kn)) {
 		mutex_unlock(&of->mutex);
-		len = -ENODEV;
-		goto out_free;
+		return -ENODEV;
 	}
 
 	ops = kernfs_ops(of->kn);
-	if (ops->write)
-		len = ops->write(of, buf, len, *ppos);
-	else
+	if (!ops->write) {
 		len = -EINVAL;
+		goto out_unlock;
+	}
 
+	if (ops->atomic_write_len) {
+		len = count;
+		if (len > ops->atomic_write_len) {
+			len = -E2BIG;
+			goto out_unlock;
+		}
+	} else {
+		len = min_t(size_t, count, PAGE_SIZE);
+	}
+
+	buf = kmalloc(len + 1, GFP_KERNEL);
+	if (!buf) {
+		len = -ENOMEM;
+		goto out_unlock;
+	}
+
+	if (copy_from_user(buf, user_buf, len)) {
+		len = -EFAULT;
+		goto out_unlock;
+	}
+	buf[len] = '\0';	/* guarantee string termination */
+
+	len = ops->write(of, buf, len, *ppos);
+out_unlock:
 	kernfs_put_active(of->kn);
 	mutex_unlock(&of->mutex);
 
 	if (len > 0)
 		*ppos += len;
-out_free:
+
 	kfree(buf);
 	return len;
 }
@@ -820,7 +833,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 bool name_is_static,
 					 struct lock_class_key *key)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 	unsigned flags;
 	int rc;
@@ -855,10 +867,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 	if (ops->mmap)
 		kn->flags |= KERNFS_HAS_MMAP;
 
-	kernfs_addrm_start(&acxt);
-	rc = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	rc = kernfs_add_one(kn);
 	if (rc) {
 		kernfs_put(kn);
 		return ERR_PTR(rc);

fs/kernfs/kernfs-internal.h

@@ -26,7 +26,8 @@ struct kernfs_iattrs {
 	struct simple_xattrs	xattrs;
 };
 
-#define KN_DEACTIVATED_BIAS		INT_MIN
+/* +1 to avoid triggering overflow warning when negating it */
+#define KN_DEACTIVATED_BIAS		(INT_MIN + 1)
 
 /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
 
@@ -44,13 +45,6 @@ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
 	return kn->dir.root;
 }
 
-/*
- * Context structure to be used while adding/removing nodes.
- */
-struct kernfs_addrm_cxt {
-	struct kernfs_node	*removed;
-};
-
 /*
  * mount.c
  */
@@ -100,9 +94,7 @@ extern const struct inode_operations kernfs_dir_iops;
 
 struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
 void kernfs_put_active(struct kernfs_node *kn);
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt);
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn);
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt);
+int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    unsigned flags);

fs/kernfs/mount.c

@@ -19,12 +19,49 @@
 
 struct kmem_cache *kernfs_node_cache;
 
+static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct kernfs_root *root = kernfs_info(sb)->root;
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->remount_fs)
+		return scops->remount_fs(root, flags, data);
+	return 0;
+}
+
+static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
+{
+	struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->show_options)
+		return scops->show_options(sf, root);
+	return 0;
+}
+
 static const struct super_operations kernfs_sops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= kernfs_evict_inode,
+
+	.remount_fs	= kernfs_sop_remount_fs,
+	.show_options	= kernfs_sop_show_options,
 };
 
+/**
+ * kernfs_root_from_sb - determine kernfs_root associated with a super_block
+ * @sb: the super_block in question
+ *
+ * Return the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * %NULL is returned.
+ */
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{
+	if (sb->s_op == &kernfs_sops)
+		return kernfs_info(sb)->root;
+	return NULL;
+}
+
 static int kernfs_fill_super(struct super_block *sb)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);

fs/kernfs/symlink.c

@@ -27,7 +27,6 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       struct kernfs_node *target)
 {
 	struct kernfs_node *kn;
-	struct kernfs_addrm_cxt acxt;
 	int error;
 
 	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
@@ -39,10 +38,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 	kn->symlink.target_kn = target;
 	kernfs_get(target);	/* ref owned by symlink */
 
-	kernfs_addrm_start(&acxt);
-	error = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	error = kernfs_add_one(kn);
 	if (!error)
 		return kn;
 

fs/sysfs/Kconfig

 config SYSFS
 	bool "sysfs file system support" if EXPERT
 	default y
+	select KERNFS
 	help
 	The sysfs filesystem is a virtual filesystem that the kernel uses to
 	export internal kernel objects, their attributes, and their

fs/sysfs/dir.c

@@ -19,39 +19,18 @@
 
 DEFINE_SPINLOCK(sysfs_symlink_target_lock);
 
-/**
- *	sysfs_pathname - return full path to sysfs dirent
- *	@kn: kernfs_node whose path we want
- *	@path: caller allocated buffer of size PATH_MAX
- *
- *	Gives the name "/" to the sysfs_root entry; any path returned
- *	is relative to wherever sysfs is mounted.
- */
-static char *sysfs_pathname(struct kernfs_node *kn, char *path)
-{
-	if (kn->parent) {
-		sysfs_pathname(kn->parent, path);
-		strlcat(path, "/", PATH_MAX);
-	}
-	strlcat(path, kn->name, PATH_MAX);
-	return path;
-}
-
 void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
 {
-	char *path;
+	char *buf, *path = NULL;
 
-	path = kzalloc(PATH_MAX, GFP_KERNEL);
-	if (path) {
-		sysfs_pathname(parent, path);
-		strlcat(path, "/", PATH_MAX);
-		strlcat(path, name, PATH_MAX);
-	}
+	buf = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (buf)
+		path = kernfs_path(parent, buf, PATH_MAX);
 
-	WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n",
-	     path ? path : name);
+	WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s/%s'\n",
+	     path, name);
 
-	kfree(path);
+	kfree(buf);
 }
 
 /**
@@ -122,9 +101,13 @@ void sysfs_remove_dir(struct kobject *kobj)
 int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
 			const void *new_ns)
 {
-	struct kernfs_node *parent = kobj->sd->parent;
+	struct kernfs_node *parent;
+	int ret;
 
-	return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+	parent = kernfs_get_parent(kobj->sd);
+	ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+	kernfs_put(parent);
+	return ret;
 }
 
 int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
@@ -133,7 +116,6 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
 	struct kernfs_node *kn = kobj->sd;
 	struct kernfs_node *new_parent;
 
-	BUG_ON(!kn->parent);
 	new_parent = new_parent_kobj && new_parent_kobj->sd ?
 		new_parent_kobj->sd : sysfs_root_kn;
 

fs/sysfs/file.c

@@ -372,6 +372,29 @@ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
+/**
+ * sysfs_remove_file_self - remove an object attribute from its own method
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ *
+ * See kernfs_remove_self() for details.
+ */
+bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr)
+{
+	struct kernfs_node *parent = kobj->sd;
+	struct kernfs_node *kn;
+	bool ret;
+
+	kn = kernfs_find_and_get(parent, attr->name);
+	if (WARN_ON_ONCE(!kn))
+		return false;
+
+	ret = kernfs_remove_self(kn);
+
+	kernfs_put(kn);
+	return ret;
+}
+
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
 {
 	int i;
@@ -430,95 +453,3 @@ void sysfs_remove_bin_file(struct kobject *kobj,
 	kernfs_remove_by_name(kobj->sd, attr->attr.name);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
-
-struct sysfs_schedule_callback_struct {
-	struct list_head	workq_list;
-	struct kobject		*kobj;
-	void			(*func)(void *);
-	void			*data;
-	struct module		*owner;
-	struct work_struct	work;
-};
-
-static struct workqueue_struct *sysfs_workqueue;
-static DEFINE_MUTEX(sysfs_workq_mutex);
-static LIST_HEAD(sysfs_workq);
-static void sysfs_schedule_callback_work(struct work_struct *work)
-{
-	struct sysfs_schedule_callback_struct *ss = container_of(work,
-			struct sysfs_schedule_callback_struct, work);
-
-	(ss->func)(ss->data);
-	kobject_put(ss->kobj);
-	module_put(ss->owner);
-	mutex_lock(&sysfs_workq_mutex);
-	list_del(&ss->workq_list);
-	mutex_unlock(&sysfs_workq_mutex);
-	kfree(ss);
-}
-
-/**
- * sysfs_schedule_callback - helper to schedule a callback for a kobject
- * @kobj: object we're acting for.
- * @func: callback function to invoke later.
- * @data: argument to pass to @func.
- * @owner: module owning the callback code
- *
- * sysfs attribute methods must not unregister themselves or their parent
- * kobject (which would amount to the same thing).  Attempts to do so will
- * deadlock, since unregistration is mutually exclusive with driver
- * callbacks.
- *
- * Instead methods can call this routine, which will attempt to allocate
- * and schedule a workqueue request to call back @func with @data as its
- * argument in the workqueue's process context.  @kobj will be pinned
- * until @func returns.
- *
- * Returns 0 if the request was submitted, -ENOMEM if storage could not
- * be allocated, -ENODEV if a reference to @owner isn't available,
- * -EAGAIN if a callback has already been scheduled for @kobj.
- */
-int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
-		void *data, struct module *owner)
-{
-	struct sysfs_schedule_callback_struct *ss, *tmp;
-
-	if (!try_module_get(owner))
-		return -ENODEV;
-
-	mutex_lock(&sysfs_workq_mutex);
-	list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list)
-		if (ss->kobj == kobj) {
-			module_put(owner);
-			mutex_unlock(&sysfs_workq_mutex);
-			return -EAGAIN;
-		}
-	mutex_unlock(&sysfs_workq_mutex);
-
-	if (sysfs_workqueue == NULL) {
-		sysfs_workqueue = create_singlethread_workqueue("sysfsd");
-		if (sysfs_workqueue == NULL) {
-			module_put(owner);
-			return -ENOMEM;
-		}
-	}
-
-	ss = kmalloc(sizeof(*ss), GFP_KERNEL);
-	if (!ss) {
-		module_put(owner);
-		return -ENOMEM;
-	}
-	kobject_get(kobj);
-	ss->kobj = kobj;
-	ss->func = func;
-	ss->data = data;
-	ss->owner = owner;
-	INIT_WORK(&ss->work, sysfs_schedule_callback_work);
-	INIT_LIST_HEAD(&ss->workq_list);
-	mutex_lock(&sysfs_workq_mutex);
-	list_add_tail(&ss->workq_list, &sysfs_workq);
-	mutex_unlock(&sysfs_workq_mutex);
-	queue_work(sysfs_workqueue, &ss->work);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(sysfs_schedule_callback);

fs/sysfs/mount.c

@@ -62,7 +62,7 @@ int __init sysfs_init(void)
 {
 	int err;
 
-	sysfs_root = kernfs_create_root(NULL, NULL);
+	sysfs_root = kernfs_create_root(NULL, 0, NULL);
 	if (IS_ERR(sysfs_root))
 		return PTR_ERR(sysfs_root);
 

include/linux/device.h

@@ -560,16 +560,12 @@ extern int device_create_file(struct device *device,
 			      const struct device_attribute *entry);
 extern void device_remove_file(struct device *dev,
 			       const struct device_attribute *attr);
+extern bool device_remove_file_self(struct device *dev,
+				    const struct device_attribute *attr);
 extern int __must_check device_create_bin_file(struct device *dev,
 					const struct bin_attribute *attr);
 extern void device_remove_bin_file(struct device *dev,
 				   const struct bin_attribute *attr);
-extern int device_schedule_callback_owner(struct device *dev,
-		void (*func)(struct device *dev), struct module *owner);
-
-/* This is a macro to avoid include problems with THIS_MODULE */
-#define device_schedule_callback(dev, func)			\
-	device_schedule_callback_owner(dev, func, THIS_MODULE)
 
 /* device resource management */
 typedef void (*dr_release_t)(struct device *dev, void *res);
@@ -929,10 +925,7 @@ extern int device_online(struct device *dev);
 extern struct device *__root_device_register(const char *name,
 					     struct module *owner);
 
-/*
- * This is a macro to avoid include problems with THIS_MODULE,
- * just as per what is done for device_schedule_callback() above.
- */
+/* This is a macro to avoid include problems with THIS_MODULE */
 #define root_device_register(name) \
 	__root_device_register(name, THIS_MODULE)
 

include/linux/kernfs.h

@@ -15,7 +15,7 @@
 #include <linux/lockdep.h>
 #include <linux/rbtree.h>
 #include <linux/atomic.h>
-#include <linux/completion.h>
+#include <linux/wait.h>
 
 struct file;
 struct dentry;
@@ -35,16 +35,22 @@ enum kernfs_node_type {
 };
 
 #define KERNFS_TYPE_MASK	0x000f
-#define KERNFS_ACTIVE_REF	KERNFS_FILE
 #define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
 
 enum kernfs_node_flag {
-	KERNFS_REMOVED		= 0x0010,
+	KERNFS_ACTIVATED	= 0x0010,
 	KERNFS_NS		= 0x0020,
 	KERNFS_HAS_SEQ_SHOW	= 0x0040,
 	KERNFS_HAS_MMAP		= 0x0080,
 	KERNFS_LOCKDEP		= 0x0100,
 	KERNFS_STATIC_NAME	= 0x0200,
+	KERNFS_SUICIDAL		= 0x0400,
+	KERNFS_SUICIDED		= 0x0800,
+};
+
+/* @flags for kernfs_create_root() */
+enum kernfs_root_flag {
+	KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001,
 };
 
 /* type-specific structures for kernfs_node union members */
@@ -85,17 +91,17 @@ struct kernfs_node {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
-	/* the following two fields are published */
+	/*
+	 * Use kernfs_get_parent() and kernfs_name/path() instead of
+	 * accessing the following two fields directly.  If the node is
+	 * never moved to a different parent, it is safe to access the
+	 * parent directly.
+	 */
 	struct kernfs_node	*parent;
 	const char		*name;
 
 	struct rb_node		rb;
 
-	union {
-		struct completion	*completion;
-		struct kernfs_node	*removed_list;
-	} u;
-
 	const void		*ns;	/* namespace tag */
 	unsigned int		hash;	/* ns + name hash */
 	union {
@@ -113,12 +119,16 @@ struct kernfs_node {
 };
 
 /*
- * kernfs_dir_ops may be specified on kernfs_create_root() to support
- * directory manipulation syscalls.  These optional callbacks are invoked
- * on the matching syscalls and can perform any kernfs operations which
- * don't necessarily have to be the exact operation requested.
+ * kernfs_syscall_ops may be specified on kernfs_create_root() to support
+ * syscalls.  These optional callbacks are invoked on the matching syscalls
+ * and can perform any kernfs operations which don't necessarily have to be
+ * the exact operation requested.  An active reference is held for each
+ * kernfs_node parameter.
  */
-struct kernfs_dir_ops {
+struct kernfs_syscall_ops {
+	int (*remount_fs)(struct kernfs_root *root, int *flags, char *data);
+	int (*show_options)(struct seq_file *sf, struct kernfs_root *root);
+
 	int (*mkdir)(struct kernfs_node *parent, const char *name,
 		     umode_t mode);
 	int (*rmdir)(struct kernfs_node *kn);
@@ -129,16 +139,19 @@ struct kernfs_dir_ops {
 struct kernfs_root {
 	/* published fields */
 	struct kernfs_node	*kn;
+	unsigned int		flags;	/* KERNFS_ROOT_* flags */
 
 	/* private fields, do not use outside kernfs proper */
 	struct ida		ino_ida;
-	struct kernfs_dir_ops	*dir_ops;
+	struct kernfs_syscall_ops *syscall_ops;
+	wait_queue_head_t	deactivate_waitq;
 };
 
 struct kernfs_open_file {
 	/* published fields */
 	struct kernfs_node	*kn;
 	struct file		*file;
+	void			*priv;
 
 	/* private fields, do not use outside kernfs proper */
 	struct mutex		mutex;
@@ -171,9 +184,13 @@ struct kernfs_ops {
 			loff_t off);
 
 	/*
-	 * write() is bounced through kernel buffer and a write larger than
-	 * PAGE_SIZE results in partial operation of PAGE_SIZE.
+	 * write() is bounced through kernel buffer.  If atomic_write_len
+	 * is not set, a write larger than PAGE_SIZE results in partial
+	 * operations of PAGE_SIZE chunks.  If atomic_write_len is set,
+	 * writes upto the specified size are executed atomically but
+	 * larger ones are rejected with -E2BIG.
 	 */
+	size_t atomic_write_len;
 	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
 			 loff_t off);
 
@@ -184,7 +201,7 @@ struct kernfs_ops {
 #endif
 };
 
-#ifdef CONFIG_SYSFS
+#ifdef CONFIG_KERNFS
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
 {
@@ -217,13 +234,22 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 	return kn->flags & KERNFS_NS;
 }
 
+int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
+char * __must_check kernfs_path(struct kernfs_node *kn, char *buf,
+				size_t buflen);
+void pr_cont_kernfs_name(struct kernfs_node *kn);
+void pr_cont_kernfs_path(struct kernfs_node *kn);
+struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 					   const char *name, const void *ns);
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
-struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops,
-				       void *priv);
+struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry);
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb);
+
+struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
+				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
 
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
@@ -239,7 +265,11 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
 				       struct kernfs_node *target);
+void kernfs_activate(struct kernfs_node *kn);
 void kernfs_remove(struct kernfs_node *kn);
+void kernfs_break_active_protection(struct kernfs_node *kn);
+void kernfs_unbreak_active_protection(struct kernfs_node *kn);
+bool kernfs_remove_self(struct kernfs_node *kn);
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 			     const void *ns);
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
@@ -254,7 +284,7 @@ void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
 
-#else	/* CONFIG_SYSFS */
+#else	/* CONFIG_KERNFS */
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
 { return 0; }	/* whatever */
@@ -264,6 +294,19 @@ static inline void kernfs_enable_ns(struct kernfs_node *kn) { }
 static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 { return false; }
 
+static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
+{ return -ENOSYS; }
+
+static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf,
+					      size_t buflen)
+{ return NULL; }
+
+static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { }
+static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { }
+
+static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
+{ return NULL; }
+
 static inline struct kernfs_node *
 kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 		       const void *ns)
@@ -272,8 +315,15 @@ kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
 
+static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
+{ return NULL; }
+
+static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{ return NULL; }
+
 static inline struct kernfs_root *
-kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
+		   void *priv)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_destroy_root(struct kernfs_root *root) { }
@@ -295,8 +345,13 @@ kernfs_create_link(struct kernfs_node *parent, const char *name,
 		   struct kernfs_node *target)
 { return ERR_PTR(-ENOSYS); }
 
+static inline void kernfs_activate(struct kernfs_node *kn) { }
+
 static inline void kernfs_remove(struct kernfs_node *kn) { }
 
+static inline bool kernfs_remove_self(struct kernfs_node *kn)
+{ return false; }
+
 static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn,
 					   const char *name, const void *ns)
 { return -ENOSYS; }
@@ -324,7 +379,7 @@ static inline void kernfs_kill_sb(struct super_block *sb) { }
 
 static inline void kernfs_init(void) { }
 
-#endif	/* CONFIG_SYSFS */
+#endif	/* CONFIG_KERNFS */
 
 static inline struct kernfs_node *
 kernfs_find_and_get(struct kernfs_node *kn, const char *name)
@@ -366,6 +421,13 @@ static inline int kernfs_remove_by_name(struct kernfs_node *parent,
 	return kernfs_remove_by_name_ns(parent, name, NULL);
 }
 
+static inline int kernfs_rename(struct kernfs_node *kn,
+				struct kernfs_node *new_parent,
+				const char *new_name)
+{
+	return kernfs_rename_ns(kn, new_parent, new_name, NULL);
+}
+
 static inline struct dentry *
 kernfs_mount(struct file_system_type *fs_type, int flags,
 	     struct kernfs_root *root)

include/linux/sysfs.h

@@ -178,9 +178,6 @@ struct sysfs_ops {
 
 #ifdef CONFIG_SYSFS
 
-int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
-			    void *data, struct module *owner);
-
 int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
 void sysfs_remove_dir(struct kobject *kobj);
 int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
@@ -198,6 +195,7 @@ int __must_check sysfs_chmod_file(struct kobject *kobj,
 				  const struct attribute *attr, umode_t mode);
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 			  const void *ns);
+bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr);
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr);
 
 int __must_check sysfs_create_bin_file(struct kobject *kobj,
@@ -246,14 +244,13 @@ void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
 
 int __must_check sysfs_init(void);
 
-#else /* CONFIG_SYSFS */
-
-static inline int sysfs_schedule_callback(struct kobject *kobj,
-		void (*func)(void *), void *data, struct module *owner)
+static inline void sysfs_enable_ns(struct kernfs_node *kn)
 {
-	return -ENOSYS;
+	return kernfs_enable_ns(kn);
 }
 
+#else /* CONFIG_SYSFS */
+
 static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	return 0;
@@ -301,6 +298,12 @@ static inline void sysfs_remove_file_ns(struct kobject *kobj,
 {
 }
 
+static inline bool sysfs_remove_file_self(struct kobject *kobj,
+					  const struct attribute *attr)
+{
+	return false;
+}
+
 static inline void sysfs_remove_files(struct kobject *kobj,
 				     const struct attribute **attr)
 {
@@ -418,6 +421,10 @@ static inline int __must_check sysfs_init(void)
 	return 0;
 }
 
+static inline void sysfs_enable_ns(struct kernfs_node *kn)
+{
+}
+
 #endif /* CONFIG_SYSFS */
 
 static inline int __must_check sysfs_create_file(struct kobject *kobj,

lib/kobject.c

@@ -94,7 +94,7 @@ static int create_dir(struct kobject *kobj)
 		BUG_ON(ops->type >= KOBJ_NS_TYPES);
 		BUG_ON(!kobj_ns_type_registered(ops->type));
 
-		kernfs_enable_ns(kobj->sd);
+		sysfs_enable_ns(kobj->sd);
 	}
 
 	return 0;