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 @@ removeseg:
 	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

@@ -0,0 +1,7 @@
+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+	bool
+	default n

fs/kernfs/dir.c

@@ -8,6 +8,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/idr.h>
@@ -18,9 +19,161 @@
 #include "kernfs-internal.h"
 
 DEFINE_MUTEX(kernfs_mutex);
+static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
+static bool kernfs_active(struct kernfs_node *kn)
+{
+	lockdep_assert_held(&kernfs_mutex);
+	return atomic_read(&kn->active) >= 0;
+}
+
+static bool kernfs_lockdep(struct kernfs_node *kn)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	return kn->flags & KERNFS_LOCKDEP;
+#else
+	return false;
+#endif
+}
+
+static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+}
+
+static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
+					      size_t buflen)
+{
+	char *p = buf + buflen;
+	int len;
+
+	*--p = '\0';
+
+	do {
+		len = strlen(kn->name);
+		if (p - buf < len + 1) {
+			buf[0] = '\0';
+			p = NULL;
+			break;
+		}
+		p -= len;
+		memcpy(p, kn->name, len);
+		*--p = '/';
+		kn = kn->parent;
+	} while (kn && kn->parent);
+
+	return p;
+}
+
+/**
+ * kernfs_name - obtain the name of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
+ * similar to strlcpy().  It returns the length of @kn's name and if @buf
+ * isn't long enough, it's filled upto @buflen-1 and nul terminated.
+ *
+ * This function can be called from any context.
+ */
+int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	ret = kernfs_name_locked(kn, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return ret;
+}
+
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes.  The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf.  If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	unsigned long flags;
+	char *p;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	p = kernfs_path_locked(kn, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return p;
+}
+
+/**
+ * pr_cont_kernfs_name - pr_cont name of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_name(struct kernfs_node *kn)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	pr_cont("%s", kernfs_pr_cont_buf);
+
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * pr_cont_kernfs_path - pr_cont path of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_path(struct kernfs_node *kn)
+{
+	unsigned long flags;
+	char *p;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+	p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
+			       sizeof(kernfs_pr_cont_buf));
+	if (p)
+		pr_cont("%s", p);
+	else
+		pr_cont("<name too long>");
+
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * kernfs_get_parent - determine the parent node and pin it
+ * @kn: kernfs_node of interest
+ *
+ * Determines @kn's parent, pins and returns it.  This function can be
+ * called from any context.
+ */
+struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	unsigned long flags;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	parent = kn->parent;
+	kernfs_get(parent);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+
+	return parent;
+}
+
 /**
  *	kernfs_name_hash
  *	@name: Null terminated string to hash
@@ -105,18 +258,24 @@ static int kernfs_link_sibling(struct kernfs_node *kn)
  *	kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree
  *	@kn: kernfs_node of interest
  *
- *	Unlink @kn from its sibling rbtree which starts from
- *	kn->parent->dir.children.
+ *	Try to unlink @kn from its sibling rbtree which starts from
+ *	kn->parent->dir.children.  Returns %true if @kn was actually
+ *	removed, %false if @kn wasn't on the rbtree.
  *
  *	Locking:
  *	mutex_lock(kernfs_mutex)
  */
-static void kernfs_unlink_sibling(struct kernfs_node *kn)
+static bool kernfs_unlink_sibling(struct kernfs_node *kn)
 {
+	if (RB_EMPTY_NODE(&kn->rb))
+		return false;
+
 	if (kernfs_type(kn) == KERNFS_DIR)
 		kn->parent->dir.subdirs--;
 
 	rb_erase(&kn->rb, &kn->parent->dir.children);
+	RB_CLEAR_NODE(&kn->rb);
+	return true;
 }
 
 /**
@@ -137,7 +296,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
 	if (!atomic_inc_unless_negative(&kn->active))
 		return NULL;
 
-	if (kn->flags & KERNFS_LOCKDEP)
+	if (kernfs_lockdep(kn))
 		rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
 	return kn;
 }
@@ -151,55 +310,57 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
  */
 void kernfs_put_active(struct kernfs_node *kn)
 {
+	struct kernfs_root *root = kernfs_root(kn);
 	int v;
 
 	if (unlikely(!kn))
 		return;
 
-	if (kn->flags & KERNFS_LOCKDEP)
+	if (kernfs_lockdep(kn))
 		rwsem_release(&kn->dep_map, 1, _RET_IP_);
 	v = atomic_dec_return(&kn->active);
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
 
-	/*
-	 * atomic_dec_return() is a mb(), we'll always see the updated
-	 * kn->u.completion.
-	 */
-	complete(kn->u.completion);
+	wake_up_all(&root->deactivate_waitq);
 }
 
 /**
- *	kernfs_deactivate - deactivate kernfs_node
- *	@kn: kernfs_node to deactivate
+ * kernfs_drain - drain kernfs_node
+ * @kn: kernfs_node to drain
  *
- *	Deny new active references and drain existing ones.
+ * Drain existing usages and nuke all existing mmaps of @kn.  Mutiple
+ * removers may invoke this function concurrently on @kn and all will
+ * return after draining is complete.
  */
-static void kernfs_deactivate(struct kernfs_node *kn)
+static void kernfs_drain(struct kernfs_node *kn)
+	__releases(&kernfs_mutex) __acquires(&kernfs_mutex)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int v;
+	struct kernfs_root *root = kernfs_root(kn);
 
-	BUG_ON(!(kn->flags & KERNFS_REMOVED));
+	lockdep_assert_held(&kernfs_mutex);
+	WARN_ON_ONCE(kernfs_active(kn));
 
-	if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
-		return;
+	mutex_unlock(&kernfs_mutex);
 
-	kn->u.completion = (void *)&wait;
+	if (kernfs_lockdep(kn)) {
+		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
+		if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
+			lock_contended(&kn->dep_map, _RET_IP_);
+	}
 
-	rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
-	/* atomic_add_return() is a mb(), put_active() will always see
-	 * the updated kn->u.completion.
-	 */
-	v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
+	/* but everyone should wait for draining */
+	wait_event(root->deactivate_waitq,
+		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
 
-	if (v != KN_DEACTIVATED_BIAS) {
-		lock_contended(&kn->dep_map, _RET_IP_);
-		wait_for_completion(&wait);
+	if (kernfs_lockdep(kn)) {
+		lock_acquired(&kn->dep_map, _RET_IP_);
+		rwsem_release(&kn->dep_map, 1, _RET_IP_);
 	}
 
-	lock_acquired(&kn->dep_map, _RET_IP_);
-	rwsem_release(&kn->dep_map, 1, _RET_IP_);
+	kernfs_unmap_bin_file(kn);
+
+	mutex_lock(&kernfs_mutex);
 }
 
 /**
@@ -230,13 +391,15 @@ void kernfs_put(struct kernfs_node *kn)
 		return;
 	root = kernfs_root(kn);
  repeat:
-	/* Moving/renaming is always done while holding reference.
+	/*
+	 * Moving/renaming is always done while holding reference.
 	 * kn->parent won't change beneath us.
 	 */
 	parent = kn->parent;
 
-	WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n",
-	     parent ? parent->name : "", kn->name);
+	WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
+		  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
+		  parent ? parent->name : "", kn->name, atomic_read(&kn->active));
 
 	if (kernfs_type(kn) == KERNFS_LINK)
 		kernfs_put(kn->symlink.target_kn);
@@ -278,8 +441,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 	kn = dentry->d_fsdata;
 	mutex_lock(&kernfs_mutex);
 
-	/* The kernfs node has been deleted */
-	if (kn->flags & KERNFS_REMOVED)
+	/* The kernfs node has been deactivated */
+	if (!kernfs_active(kn))
 		goto out_bad;
 
 	/* The kernfs node has been moved? */
@@ -324,6 +487,24 @@ const struct dentry_operations kernfs_dops = {
 	.d_release	= kernfs_dop_release,
 };
 
+/**
+ * kernfs_node_from_dentry - determine kernfs_node associated with a dentry
+ * @dentry: the dentry in question
+ *
+ * Return the kernfs_node associated with @dentry.  If @dentry is not a
+ * kernfs one, %NULL is returned.
+ *
+ * While the returned kernfs_node will stay accessible as long as @dentry
+ * is accessible, the returned node can be in any state and the caller is
+ * fully responsible for determining what's accessible.
+ */
+struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
+{
+	if (dentry->d_op == &kernfs_dops)
+		return dentry->d_fsdata;
+	return NULL;
+}
+
 static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     const char *name, umode_t mode,
 					     unsigned flags)
@@ -348,11 +529,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	kn->ino = ret;
 
 	atomic_set(&kn->count, 1);
-	atomic_set(&kn->active, 0);
+	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
+	RB_CLEAR_NODE(&kn->rb);
 
 	kn->name = name;
 	kn->mode = mode;
-	kn->flags = flags | KERNFS_REMOVED;
+	kn->flags = flags;
 
 	return kn;
 
@@ -377,70 +559,45 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 	return kn;
 }
 
-/**
- *	kernfs_addrm_start - prepare for kernfs_node add/remove
- *	@acxt: pointer to kernfs_addrm_cxt to be used
- *
- *	This function is called when the caller is about to add or remove
- *	kernfs_node.  This function acquires kernfs_mutex.  @acxt is used
- *	to keep and pass context to other addrm functions.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).  kernfs_mutex is locked on
- *	return.
- */
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt)
-	__acquires(kernfs_mutex)
-{
-	memset(acxt, 0, sizeof(*acxt));
-
-	mutex_lock(&kernfs_mutex);
-}
-
 /**
  *	kernfs_add_one - add kernfs_node to parent without warning
- *	@acxt: addrm context to use
  *	@kn: kernfs_node to be added
  *
  *	The caller must already have initialized @kn->parent.  This
  *	function increments nlink of the parent's inode if @kn is a
  *	directory and link into the children list of the parent.
  *
- *	This function should be called between calls to
- *	kernfs_addrm_start() and kernfs_addrm_finish() and should be passed
- *	the same @acxt as passed to kernfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by kernfs_addrm_start().
- *
  *	RETURNS:
  *	0 on success, -EEXIST if entry with the given name already
  *	exists.
  */
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
+int kernfs_add_one(struct kernfs_node *kn)
 {
 	struct kernfs_node *parent = kn->parent;
-	bool has_ns = kernfs_ns_enabled(parent);
 	struct kernfs_iattrs *ps_iattr;
+	bool has_ns;
 	int ret;
 
-	if (has_ns != (bool)kn->ns) {
-		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
-		     has_ns ? "required" : "invalid", parent->name, kn->name);
-		return -EINVAL;
-	}
+	mutex_lock(&kernfs_mutex);
+
+	ret = -EINVAL;
+	has_ns = kernfs_ns_enabled(parent);
+	if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+		 has_ns ? "required" : "invalid", parent->name, kn->name))
+		goto out_unlock;
 
 	if (kernfs_type(parent) != KERNFS_DIR)
-		return -EINVAL;
+		goto out_unlock;
 
-	if (parent->flags & KERNFS_REMOVED)
-		return -ENOENT;
+	ret = -ENOENT;
+	if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
+		goto out_unlock;
 
 	kn->hash = kernfs_name_hash(kn->name, kn->ns);
 
 	ret = kernfs_link_sibling(kn);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	/* Update timestamps on the parent */
 	ps_iattr = parent->iattr;
@@ -449,82 +606,22 @@ int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
 		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
 	}
 
-	/* Mark the entry added into directory tree */
-	kn->flags &= ~KERNFS_REMOVED;
-
-	return 0;
-}
-
-/**
- *	kernfs_remove_one - remove kernfs_node from parent
- *	@acxt: addrm context to use
- *	@kn: kernfs_node to be removed
- *
- *	Mark @kn removed and drop nlink of parent inode if @kn is a
- *	directory.  @kn is unlinked from the children list.
- *
- *	This function should be called between calls to
- *	kernfs_addrm_start() and kernfs_addrm_finish() and should be
- *	passed the same @acxt as passed to kernfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by kernfs_addrm_start().
- */
-static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt,
-			      struct kernfs_node *kn)
-{
-	struct kernfs_iattrs *ps_iattr;
+	mutex_unlock(&kernfs_mutex);
 
 	/*
-	 * Removal can be called multiple times on the same node.  Only the
-	 * first invocation is effective and puts the base ref.
+	 * Activate the new node unless CREATE_DEACTIVATED is requested.
+	 * If not activated here, the kernfs user is responsible for
+	 * activating the node with kernfs_activate().  A node which hasn't
+	 * been activated is not visible to userland and its removal won't
+	 * trigger deactivation.
 	 */
-	if (kn->flags & KERNFS_REMOVED)
-		return;
-
-	if (kn->parent) {
-		kernfs_unlink_sibling(kn);
-
-		/* Update timestamps on the parent */
-		ps_iattr = kn->parent->iattr;
-		if (ps_iattr) {
-			ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
-			ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
-		}
-	}
-
-	kn->flags |= KERNFS_REMOVED;
-	kn->u.removed_list = acxt->removed;
-	acxt->removed = kn;
-}
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+		kernfs_activate(kn);
+	return 0;
 
-/**
- *	kernfs_addrm_finish - finish up kernfs_node add/remove
- *	@acxt: addrm context to finish up
- *
- *	Finish up kernfs_node add/remove.  Resources acquired by
- *	kernfs_addrm_start() are released and removed kernfs_nodes are
- *	cleaned up.
- *
- *	LOCKING:
- *	kernfs_mutex is released.
- */
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt)
-	__releases(kernfs_mutex)
-{
-	/* release resources acquired by kernfs_addrm_start() */
+out_unlock:
 	mutex_unlock(&kernfs_mutex);
-
-	/* kill removed kernfs_nodes */
-	while (acxt->removed) {
-		struct kernfs_node *kn = acxt->removed;
-
-		acxt->removed = kn->u.removed_list;
-
-		kernfs_deactivate(kn);
-		kernfs_unmap_bin_file(kn);
-		kernfs_put(kn);
-	}
+	return ret;
 }
 
 /**
@@ -595,13 +692,15 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 
 /**
  * kernfs_create_root - create a new kernfs hierarchy
- * @kdops: optional directory syscall operations for the hierarchy
+ * @scops: optional syscall operations for the hierarchy
+ * @flags: KERNFS_ROOT_* flags
  * @priv: opaque data associated with the new directory
  *
  * Returns the root of the new hierarchy on success, ERR_PTR() value on
  * failure.
  */
-struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
+				       unsigned int flags, void *priv)
 {
 	struct kernfs_root *root;
 	struct kernfs_node *kn;
@@ -620,12 +719,16 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	kn->flags &= ~KERNFS_REMOVED;
 	kn->priv = priv;
 	kn->dir.root = root;
 
-	root->dir_ops = kdops;
+	root->syscall_ops = scops;
+	root->flags = flags;
 	root->kn = kn;
+	init_waitqueue_head(&root->deactivate_waitq);
+
+	if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+		kernfs_activate(kn);
 
 	return root;
 }
@@ -656,7 +759,6 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 void *priv, const void *ns)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 	int rc;
 
@@ -670,10 +772,7 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 	kn->priv = priv;
 
 	/* link in */
-	kernfs_addrm_start(&acxt);
-	rc = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	rc = kernfs_add_one(kn);
 	if (!rc)
 		return kn;
 
@@ -699,7 +798,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 	kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
 
 	/* no such entry */
-	if (!kn) {
+	if (!kn || !kernfs_active(kn)) {
 		ret = NULL;
 		goto out_unlock;
 	}
@@ -724,23 +823,37 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
 			    umode_t mode)
 {
 	struct kernfs_node *parent = dir->i_private;
-	struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops;
+	int ret;
 
-	if (!kdops || !kdops->mkdir)
+	if (!scops || !scops->mkdir)
 		return -EPERM;
 
-	return kdops->mkdir(parent, dentry->d_name.name, mode);
+	if (!kernfs_get_active(parent))
+		return -ENODEV;
+
+	ret = scops->mkdir(parent, dentry->d_name.name, mode);
+
+	kernfs_put_active(parent);
+	return ret;
 }
 
 static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct kernfs_node *kn  = dentry->d_fsdata;
-	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
+	int ret;
 
-	if (!kdops || !kdops->rmdir)
+	if (!scops || !scops->rmdir)
 		return -EPERM;
 
-	return kdops->rmdir(kn);
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	ret = scops->rmdir(kn);
+
+	kernfs_put_active(kn);
+	return ret;
 }
 
 static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -748,12 +861,25 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	struct kernfs_node *kn  = old_dentry->d_fsdata;
 	struct kernfs_node *new_parent = new_dir->i_private;
-	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
+	int ret;
 
-	if (!kdops || !kdops->rename)
+	if (!scops || !scops->rename)
 		return -EPERM;
 
-	return kdops->rename(kn, new_parent, new_dentry->d_name.name);
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	if (!kernfs_get_active(new_parent)) {
+		kernfs_put_active(kn);
+		return -ENODEV;
+	}
+
+	ret = scops->rename(kn, new_parent, new_dentry->d_name.name);
+
+	kernfs_put_active(new_parent);
+	kernfs_put_active(kn);
+	return ret;
 }
 
 const struct inode_operations kernfs_dir_iops = {
@@ -826,23 +952,104 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 	return pos->parent;
 }
 
-static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
-			    struct kernfs_node *kn)
+/**
+ * kernfs_activate - activate a node which started deactivated
+ * @kn: kernfs_node whose subtree is to be activated
+ *
+ * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node
+ * needs to be explicitly activated.  A node which hasn't been activated
+ * isn't visible to userland and deactivation is skipped during its
+ * removal.  This is useful to construct atomic init sequences where
+ * creation of multiple nodes should either succeed or fail atomically.
+ *
+ * The caller is responsible for ensuring that this function is not called
+ * after kernfs_remove*() is invoked on @kn.
+ */
+void kernfs_activate(struct kernfs_node *kn)
 {
-	struct kernfs_node *pos, *next;
+	struct kernfs_node *pos;
 
-	if (!kn)
+	mutex_lock(&kernfs_mutex);
+
+	pos = NULL;
+	while ((pos = kernfs_next_descendant_post(pos, kn))) {
+		if (!pos || (pos->flags & KERNFS_ACTIVATED))
+			continue;
+
+		WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
+		WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS);
+
+		atomic_sub(KN_DEACTIVATED_BIAS, &pos->active);
+		pos->flags |= KERNFS_ACTIVATED;
+	}
+
+	mutex_unlock(&kernfs_mutex);
+}
+
+static void __kernfs_remove(struct kernfs_node *kn)
+{
+	struct kernfs_node *pos;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	/*
+	 * Short-circuit if non-root @kn has already finished removal.
+	 * This is for kernfs_remove_self() which plays with active ref
+	 * after removal.
+	 */
+	if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
 		return;
 
 	pr_debug("kernfs %s: removing\n", kn->name);
 
-	next = NULL;
+	/* prevent any new usage under @kn by deactivating all nodes */
+	pos = NULL;
+	while ((pos = kernfs_next_descendant_post(pos, kn)))
+		if (kernfs_active(pos))
+			atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
+
+	/* deactivate and unlink the subtree node-by-node */
 	do {
-		pos = next;
-		next = kernfs_next_descendant_post(pos, kn);
-		if (pos)
-			kernfs_remove_one(acxt, pos);
-	} while (next);
+		pos = kernfs_leftmost_descendant(kn);
+
+		/*
+		 * kernfs_drain() drops kernfs_mutex temporarily and @pos's
+		 * base ref could have been put by someone else by the time
+		 * the function returns.  Make sure it doesn't go away
+		 * underneath us.
+		 */
+		kernfs_get(pos);
+
+		/*
+		 * Drain iff @kn was activated.  This avoids draining and
+		 * its lockdep annotations for nodes which have never been
+		 * activated and allows embedding kernfs_remove() in create
+		 * error paths without worrying about draining.
+		 */
+		if (kn->flags & KERNFS_ACTIVATED)
+			kernfs_drain(pos);
+		else
+			WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
+
+		/*
+		 * kernfs_unlink_sibling() succeeds once per node.  Use it
+		 * to decide who's responsible for cleanups.
+		 */
+		if (!pos->parent || kernfs_unlink_sibling(pos)) {
+			struct kernfs_iattrs *ps_iattr =
+				pos->parent ? pos->parent->iattr : NULL;
+
+			/* update timestamps on the parent */
+			if (ps_iattr) {
+				ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
+				ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
+			}
+
+			kernfs_put(pos);
+		}
+
+		kernfs_put(pos);
+	} while (pos != kn);
 }
 
 /**
@@ -853,11 +1060,140 @@ static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
  */
 void kernfs_remove(struct kernfs_node *kn)
 {
-	struct kernfs_addrm_cxt acxt;
+	mutex_lock(&kernfs_mutex);
+	__kernfs_remove(kn);
+	mutex_unlock(&kernfs_mutex);
+}
 
-	kernfs_addrm_start(&acxt);
-	__kernfs_remove(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
+/**
+ * kernfs_break_active_protection - break out of active protection
+ * @kn: the self kernfs_node
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  Each invocation of
+ * this function must also be matched with an invocation of
+ * kernfs_unbreak_active_protection().
+ *
+ * This function releases the active reference of @kn the caller is
+ * holding.  Once this function is called, @kn may be removed at any point
+ * and the caller is solely responsible for ensuring that the objects it
+ * dereferences are accessible.
+ */
+void kernfs_break_active_protection(struct kernfs_node *kn)
+{
+	/*
+	 * Take out ourself out of the active ref dependency chain.  If
+	 * we're called without an active ref, lockdep will complain.
+	 */
+	kernfs_put_active(kn);
+}
+
+/**
+ * kernfs_unbreak_active_protection - undo kernfs_break_active_protection()
+ * @kn: the self kernfs_node
+ *
+ * If kernfs_break_active_protection() was called, this function must be
+ * invoked before finishing the kernfs operation.  Note that while this
+ * function restores the active reference, it doesn't and can't actually
+ * restore the active protection - @kn may already or be in the process of
+ * being removed.  Once kernfs_break_active_protection() is invoked, that
+ * protection is irreversibly gone for the kernfs operation instance.
+ *
+ * While this function may be called at any point after
+ * kernfs_break_active_protection() is invoked, its most useful location
+ * would be right before the enclosing kernfs operation returns.
+ */
+void kernfs_unbreak_active_protection(struct kernfs_node *kn)
+{
+	/*
+	 * @kn->active could be in any state; however, the increment we do
+	 * here will be undone as soon as the enclosing kernfs operation
+	 * finishes and this temporary bump can't break anything.  If @kn
+	 * is alive, nothing changes.  If @kn is being deactivated, the
+	 * soon-to-follow put will either finish deactivation or restore
+	 * deactivated state.  If @kn is already removed, the temporary
+	 * bump is guaranteed to be gone before @kn is released.
+	 */
+	atomic_inc(&kn->active);
+	if (kernfs_lockdep(kn))
+		rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_);
+}
+
+/**
+ * kernfs_remove_self - remove a kernfs_node from its own method
+ * @kn: the self kernfs_node to remove
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  This can be used to
+ * implement a file operation which deletes itself.
+ *
+ * For example, the "delete" file for a sysfs device directory can be
+ * implemented by invoking kernfs_remove_self() on the "delete" file
+ * itself.  This function breaks the circular dependency of trying to
+ * deactivate self while holding an active ref itself.  It isn't necessary
+ * to modify the usual removal path to use kernfs_remove_self().  The
+ * "delete" implementation can simply invoke kernfs_remove_self() on self
+ * before proceeding with the usual removal path.  kernfs will ignore later
+ * kernfs_remove() on self.
+ *
+ * kernfs_remove_self() can be called multiple times concurrently on the
+ * same kernfs_node.  Only the first one actually performs removal and
+ * returns %true.  All others will wait until the kernfs operation which
+ * won self-removal finishes and return %false.  Note that the losers wait
+ * for the completion of not only the winning kernfs_remove_self() but also
+ * the whole kernfs_ops which won the arbitration.  This can be used to
+ * guarantee, for example, all concurrent writes to a "delete" file to
+ * finish only after the whole operation is complete.
+ */
+bool kernfs_remove_self(struct kernfs_node *kn)
+{
+	bool ret;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_break_active_protection(kn);
+
+	/*
+	 * SUICIDAL is used to arbitrate among competing invocations.  Only
+	 * the first one will actually perform removal.  When the removal
+	 * is complete, SUICIDED is set and the active ref is restored
+	 * while holding kernfs_mutex.  The ones which lost arbitration
+	 * waits for SUICDED && drained which can happen only after the
+	 * enclosing kernfs operation which executed the winning instance
+	 * of kernfs_remove_self() finished.
+	 */
+	if (!(kn->flags & KERNFS_SUICIDAL)) {
+		kn->flags |= KERNFS_SUICIDAL;
+		__kernfs_remove(kn);
+		kn->flags |= KERNFS_SUICIDED;
+		ret = true;
+	} else {
+		wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq;
+		DEFINE_WAIT(wait);
+
+		while (true) {
+			prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE);
+
+			if ((kn->flags & KERNFS_SUICIDED) &&
+			    atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
+				break;
+
+			mutex_unlock(&kernfs_mutex);
+			schedule();
+			mutex_lock(&kernfs_mutex);
+		}
+		finish_wait(waitq, &wait);
+		WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb));
+		ret = false;
+	}
+
+	/*
+	 * This must be done while holding kernfs_mutex; otherwise, waiting
+	 * for SUICIDED && deactivated could finish prematurely.
+	 */
+	kernfs_unbreak_active_protection(kn);
+
+	mutex_unlock(&kernfs_mutex);
+	return ret;
 }
 
 /**
@@ -872,7 +1208,6 @@ void kernfs_remove(struct kernfs_node *kn)
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 			     const void *ns)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 
 	if (!parent) {
@@ -881,13 +1216,13 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 		return -ENOENT;
 	}
 
-	kernfs_addrm_start(&acxt);
+	mutex_lock(&kernfs_mutex);
 
 	kn = kernfs_find_ns(parent, name, ns);
 	if (kn)
-		__kernfs_remove(&acxt, kn);
+		__kernfs_remove(kn);
 
-	kernfs_addrm_finish(&acxt);
+	mutex_unlock(&kernfs_mutex);
 
 	if (kn)
 		return 0;
@@ -905,12 +1240,18 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		     const char *new_name, const void *new_ns)
 {
+	struct kernfs_node *old_parent;
+	const char *old_name = NULL;
 	int error;
 
+	/* can't move or rename root */
+	if (!kn->parent)
+		return -EINVAL;
+
 	mutex_lock(&kernfs_mutex);
 
 	error = -ENOENT;
-	if ((kn->flags | new_parent->flags) & KERNFS_REMOVED)
+	if (!kernfs_active(kn) || !kernfs_active(new_parent))
 		goto out;
 
 	error = 0;
@@ -928,13 +1269,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		new_name = kstrdup(new_name, GFP_KERNEL);
 		if (!new_name)
 			goto out;
-
-		if (kn->flags & KERNFS_STATIC_NAME)
-			kn->flags &= ~KERNFS_STATIC_NAME;
-		else
-			kfree(kn->name);
-
-		kn->name = new_name;
+	} else {
+		new_name = NULL;
 	}
 
 	/*
@@ -942,12 +1278,29 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	 */
 	kernfs_unlink_sibling(kn);
 	kernfs_get(new_parent);
-	kernfs_put(kn->parent);
-	kn->ns = new_ns;
-	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+
+	/* rename_lock protects ->parent and ->name accessors */
+	spin_lock_irq(&kernfs_rename_lock);
+
+	old_parent = kn->parent;
 	kn->parent = new_parent;
+
+	kn->ns = new_ns;
+	if (new_name) {
+		if (!(kn->flags & KERNFS_STATIC_NAME))
+			old_name = kn->name;
+		kn->flags &= ~KERNFS_STATIC_NAME;
+		kn->name = new_name;
+	}
+
+	spin_unlock_irq(&kernfs_rename_lock);
+
+	kn->hash = kernfs_name_hash(new_name, new_ns);
 	kernfs_link_sibling(kn);
 
+	kernfs_put(old_parent);
+	kfree(old_name);
+
 	error = 0;
  out:
 	mutex_unlock(&kernfs_mutex);
@@ -970,7 +1323,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
 	struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
 {
 	if (pos) {
-		int valid = !(pos->flags & KERNFS_REMOVED) &&
+		int valid = kernfs_active(pos) &&
 			pos->parent == parent && hash == pos->hash;
 		kernfs_put(pos);
 		if (!valid)
@@ -989,8 +1342,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
 				break;
 		}
 	}
-	/* Skip over entries in the wrong namespace */
-	while (pos && pos->ns != ns) {
+	/* Skip over entries which are dying/dead or in the wrong namespace */
+	while (pos && (!kernfs_active(pos) || pos->ns != ns)) {
 		struct rb_node *node = rb_next(&pos->rb);
 		if (!node)
 			pos = NULL;
@@ -1004,14 +1357,15 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
 	struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
 {
 	pos = kernfs_dir_pos(ns, parent, ino, pos);
-	if (pos)
+	if (pos) {
 		do {
 			struct rb_node *node = rb_next(&pos->rb);
 			if (!node)
 				pos = NULL;
 			else
 				pos = rb_to_kn(node);
-		} while (pos && pos->ns != ns);
+		} while (pos && (!kernfs_active(pos) || pos->ns != ns));
+	}
 	return pos;
 }
 

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

@@ -1,6 +1,7 @@
 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;