[PATCH v8 00/12] syfs: generic deadlock fix with module removal

@@ -44,6 +44,8 @@ static DEFINE_MUTEX(zram_index_mutex);
 static int zram_major;
 static const char *default_compressor = CONFIG_ZRAM_DEF_COMP;
 
+static bool zram_up;
+
 /* Module params (documentation at end) */
 static unsigned int num_devices = 1;
 /*

@@ -1704,6 +1706,7 @@ static void zram_reset_device(struct zram *zram)
 	comp = zram->comp;
 	disksize = zram->disksize;
 	zram->disksize = 0;
+	zram->comp = NULL;
 
 	set_capacity_and_notify(zram->disk, 0);
 	part_stat_set_all(zram->disk->part0, 0);

@@ -1724,9 +1727,18 @@ static ssize_t disksize_store(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 	int err;
 
+	mutex_lock(&zram_index_mutex);
+
+	if (!zram_up) {
+		err = -ENODEV;
+		goto out;
+	}
+
 	disksize = memparse(buf, NULL);
-	if (!disksize)
-		return -EINVAL;
+	if (!disksize) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	down_write(&zram->init_lock);
 	if (init_done(zram)) {

@@ -1754,12 +1766,16 @@ static ssize_t disksize_store(struct device *dev,
 	set_capacity_and_notify(zram->disk, zram->disksize >> SECTOR_SHIFT);
 	up_write(&zram->init_lock);
 
+	mutex_unlock(&zram_index_mutex);
+
 	return len;
 
 out_free_meta:
 	zram_meta_free(zram, disksize);
 out_unlock:
 	up_write(&zram->init_lock);
+out:
+	mutex_unlock(&zram_index_mutex);
 	return err;
 }
 

@@ -1775,8 +1791,17 @@ static ssize_t reset_store(struct device *dev,
 	if (ret)
 		return ret;
 
-	if (!do_reset)
-		return -EINVAL;
+	mutex_lock(&zram_index_mutex);
+
+	if (!zram_up) {
+		len = -ENODEV;
+		goto out;
+	}
+
+	if (!do_reset) {
+		len = -EINVAL;
+		goto out;
+	}
 
 	zram = dev_to_zram(dev);
 	bdev = zram->disk->part0;

@@ -1785,7 +1810,8 @@ static ssize_t reset_store(struct device *dev,
 	/* Do not reset an active device or claimed device */
 	if (bdev->bd_openers || zram->claim) {
 		mutex_unlock(&bdev->bd_disk->open_mutex);
-		return -EBUSY;
+		len = -EBUSY;
+		goto out;
 	}
 
 	/* From now on, anyone can't open /dev/zram[0-9] */

@@ -1800,6 +1826,8 @@ static ssize_t reset_store(struct device *dev,
 	zram->claim = false;
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
+out:
+	mutex_unlock(&zram_index_mutex);
 	return len;
 }
 

@@ -2010,6 +2038,10 @@ static ssize_t hot_add_show(struct class *class,
 	int ret;
 
 	mutex_lock(&zram_index_mutex);
+	if (!zram_up) {
+		mutex_unlock(&zram_index_mutex);
+		return -ENODEV;
+	}
 	ret = zram_add();
 	mutex_unlock(&zram_index_mutex);
 

@@ -2037,6 +2069,11 @@ static ssize_t hot_remove_store(struct class *class,
 
 	mutex_lock(&zram_index_mutex);
 
+	if (!zram_up) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	zram = idr_find(&zram_index_idr, dev_id);
 	if (zram) {
 		ret = zram_remove(zram);

@@ -2046,6 +2083,7 @@ static ssize_t hot_remove_store(struct class *class,
 		ret = -ENODEV;
 	}
 
+out:
 	mutex_unlock(&zram_index_mutex);
 	return ret ? ret : count;
 }

@@ -2072,12 +2110,15 @@ static int zram_remove_cb(int id, void *ptr, void *data)
 
 static void destroy_devices(void)
 {
+	mutex_lock(&zram_index_mutex);
+	zram_up = false;
 	class_unregister(&zram_control_class);
 	idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
 	zram_debugfs_destroy();
 	idr_destroy(&zram_index_idr);
 	unregister_blkdev(zram_major, "zram");
 	cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
+	mutex_unlock(&zram_index_mutex);
 }
 
 static int __init zram_init(void)

@@ -2105,15 +2146,21 @@ static int __init zram_init(void)
 		return -EBUSY;
 	}
 
+	mutex_lock(&zram_index_mutex);
+
 	while (num_devices != 0) {
-		mutex_lock(&zram_index_mutex);
 		ret = zram_add();
-		mutex_unlock(&zram_index_mutex);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&zram_index_mutex);
 			goto out_error;
+		}
 		num_devices--;
 	}
 
+	zram_up = true;
+
+	mutex_unlock(&zram_index_mutex);
+
 	return 0;
 
 out_error:

@@ -60,8 +60,8 @@ ALL_TESTS="$ALL_TESTS 0023:1:1:test_dev_y:block"
 ALL_TESTS="$ALL_TESTS 0024:1:1:test_dev_x:block"
 ALL_TESTS="$ALL_TESTS 0025:1:1:test_dev_y:block"
 ALL_TESTS="$ALL_TESTS 0026:1:1:test_dev_y:block"
-ALL_TESTS="$ALL_TESTS 0027:1:0:test_dev_x:block" # deadlock test
-ALL_TESTS="$ALL_TESTS 0028:1:0:test_dev_x:block" # deadlock test with rntl_lock
+ALL_TESTS="$ALL_TESTS 0027:1:1:test_dev_x:block" # deadlock test
+ALL_TESTS="$ALL_TESTS 0028:1:1:test_dev_x:block" # deadlock test with rntl_lock
 ALL_TESTS="$ALL_TESTS 0029:1:1:test_dev_x:block" # kernfs race removal of store
 ALL_TESTS="$ALL_TESTS 0030:1:1:test_dev_x:block" # kernfs race removal before mutex
 ALL_TESTS="$ALL_TESTS 0031:1:1:test_dev_x:block" # kernfs race removal after mutex

@@ -1902,14 +1902,7 @@ static struct attribute *zram_disk_attrs[] = {
 	NULL,
 };
 
-static const struct attribute_group zram_disk_attr_group = {
-	.attrs = zram_disk_attrs,
-};
-
-static const struct attribute_group *zram_disk_attr_groups[] = {
-	&zram_disk_attr_group,
-	NULL,
-};
+ATTRIBUTE_GROUPS(zram_disk);
 
 /*
  * Allocate and initialize new zram device. the function returns

@@ -1981,7 +1974,7 @@ static int zram_add(void)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
-	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
+	device_add_disk(NULL, zram->disk, zram_disk_groups);
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
 

@@ -609,10 +609,40 @@ void symbol_put_addr(void *addr);
    to handle the error case (which only happens with rmmod --wait). */
 extern void __module_get(struct module *module);
 
-/* This is the Right Way to get a module: if it fails, it's being removed,
- * so pretend it's not there. */
+/**
+ * try_module_get() - yields to module removal and bumps refcnt otherwise
+ * @module: the module we should check for
+ *
+ * This can be used to try to bump the reference count of a module, so to
+ * prevent module removal. The reference count of a module is not allowed
+ * to be incremented if the module is already being removed.
+ *
+ * Care must be taken to ensure the module cannot be removed during the call to
+ * try_module_get(). This can be done by having another entity other than the
+ * module itself increment the module reference count, or through some other
+ * means which guarantees the module could not be removed during an operation.
+ * An example of this later case is using try_module_get() in a sysfs file
+ * which the module created. The sysfs store / read file operations are
+ * gauranteed to exist through the use of kernfs's active reference (see
+ * kernfs_active()). If a sysfs file operation is being run, the module which
+ * created it must still exist as the module is in charge of removing the same
+ * sysfs file being read. Also, a sysfs / kernfs file removal cannot happen
+ * unless the same file is not active.
+ *
+ * One of the real values to try_module_get() is the module_is_live() check
+ * which ensures this the caller of try_module_get() can yield to userspace
+ * module removal requests and fail whatever it was about to process.
+ */
 extern bool try_module_get(struct module *module);
 
+/**
+ * module_put() - release a reference count to a module
+ * @module: the module we should release a reference count for
+ *
+ * If you successfully bump a reference count to a module with try_module_get(),
+ * when you are finished you must call module_put() to release that reference
+ * count.
+ */
 extern void module_put(struct module *module);
 
 #else /*!CONFIG_MODULE_UNLOAD*/

@@ -1,18 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
 /*
  * kmod stress test driver
  *
  * Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or at your option any
- * later version; or, when distributed separately from the Linux kernel or
- * when incorporated into other software packages, subject to the following
- * license:
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of copyleft-next (version 0.3.1 or later) as published
- * at http://copyleft-next.org/.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 

@@ -1,18 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
 /*
  * proc sysctl test driver
  *
  * Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or at your option any
- * later version; or, when distributed separately from the Linux kernel or
- * when incorporated into other software packages, subject to the following
- * license:
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of copyleft-next (version 0.3.1 or later) as published
- * at http://copyleft-next.org/.
  */
 
 /*

@@ -1,18 +1,7 @@
 #!/bin/bash
-#
+# SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
 # Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
 #
-# This program is free software; you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
-# Software Foundation; either version 2 of the License, or at your option any
-# later version; or, when distributed separately from the Linux kernel or
-# when incorporated into other software packages, subject to the following
-# license:
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms of copyleft-next (version 0.3.1 or later) as published
-# at http://copyleft-next.org/.
-
 # This is a stress test script for kmod, the kernel module loader. It uses
 # test_kmod which exposes a series of knobs for the API for us so we can
 # tweak each test in userspace rather than in kernelspace.

@@ -1,16 +1,6 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
 # Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
-# Software Foundation; either version 2 of the License, or at your option any
-# later version; or, when distributed separately from the Linux kernel or
-# when incorporated into other software packages, subject to the following
-# license:
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms of copyleft-next (version 0.3.1 or later) as published
-# at http://copyleft-next.org/.
 
 # This performs a series tests against the proc sysctl interface.
 

@@ -36,8 +36,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 		gid = target->iattr->ia_gid;
 	}
 
-	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, uid, gid,
-			     KERNFS_LINK);
+	kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 

@@ -209,7 +209,7 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
 
 	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
 				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-				  0, rft->kf_ops, rft, NULL, NULL);
+				  0, rft->kf_ops, rft, NULL, NULL, NULL);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 

@@ -2482,7 +2482,7 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
 
 	kn = __kernfs_create_file(parent_kn, name, 0444,
 				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
-				  &kf_mondata_ops, priv, NULL, NULL);
+				  &kf_mondata_ops, priv, NULL, NULL, NULL);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 

@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/hash.h>
+#include <linux/module.h>
 
 #include "kernfs-internal.h"
 

@@ -414,12 +415,29 @@ static bool kernfs_unlink_sibling(struct kernfs_node *kn)
  */
 struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
 {
+	int v;
+
 	if (unlikely(!kn))
 		return NULL;
 
 	if (!atomic_inc_unless_negative(&kn->active))
 		return NULL;
 
+	/*
+	 * If a module created the kernfs_node, the module cannot possibly be
+	 * removed if the above atomic_inc_unless_negative() succeeded. So the
+	 * try_module_get() below is not to protect the lifetime of the module
+	 * as that is already guaranteed. The try_module_get() below is used
+	 * to ensure that we don't deadlock in case a kernfs operation and
+	 * module removal used a shared lock.
+	 */
+	if (!try_module_get(kn->owner)) {
+		v = atomic_dec_return(&kn->active);
+		if (unlikely(v == KN_DEACTIVATED_BIAS))
+			wake_up_all(&kernfs_root(kn)->deactivate_waitq);
+		return NULL;
+	}
+
 	if (kernfs_lockdep(kn))
 		rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
 	return kn;

@@ -442,6 +460,13 @@ void kernfs_put_active(struct kernfs_node *kn)
 	if (kernfs_lockdep(kn))
 		rwsem_release(&kn->dep_map, _RET_IP_);
 	v = atomic_dec_return(&kn->active);
+
+	/*
+	 * We prevent module exit *until* we know for sure all possible
+	 * kernfs ops are done.
+	 */
+	module_put(kn->owner);
+
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
 

@@ -572,7 +597,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     struct kernfs_node *parent,
 					     const char *name, umode_t mode,
 					     kuid_t uid, kgid_t gid,
-					     unsigned flags)
+					     unsigned flags,
+					     struct module *owner)
 {
 	struct kernfs_node *kn;
 	u32 id_highbits;

@@ -607,6 +633,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	kn->name = name;
 	kn->mode = mode;
 	kn->flags = flags;
+	kn->owner = owner;
 
 	if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) {
 		struct iattr iattr = {

@@ -640,12 +667,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    kuid_t uid, kgid_t gid,
-				    unsigned flags)
+				    unsigned flags,
+				    struct module *owner)
 {
 	struct kernfs_node *kn;
 
 	kn = __kernfs_new_node(kernfs_root(parent), parent,
-			       name, mode, uid, gid, flags);
+			       name, mode, uid, gid, flags, owner);
 	if (kn) {
 		kernfs_get(parent);
 		kn->parent = parent;

@@ -927,7 +955,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 
 	kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO,
 			       GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-			       KERNFS_DIR);
+			       KERNFS_DIR, NULL);
 	if (!kn) {
 		idr_destroy(&root->ino_idr);
 		kfree(root);

@@ -969,20 +997,22 @@ void kernfs_destroy_root(struct kernfs_root *root)
  * @gid: gid of the new directory
  * @priv: opaque data associated with the new directory
  * @ns: optional namespace tag of the directory
+ * @owner: if set, the module owner of this directory
  *
  * Returns the created node on success, ERR_PTR() value on failure.
  */
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 kuid_t uid, kgid_t gid,
-					 void *priv, const void *ns)
+					 void *priv, const void *ns,
+					 struct module *owner)
 {
 	struct kernfs_node *kn;
 	int rc;
 
 	/* allocate */
 	kn = kernfs_new_node(parent, name, mode | S_IFDIR,
-			     uid, gid, KERNFS_DIR);
+			     uid, gid, KERNFS_DIR, owner);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 

@@ -1014,7 +1044,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 
 	/* allocate */
 	kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR,
-			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR);
+			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR, NULL);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 

@@ -978,6 +978,7 @@ const struct file_operations kernfs_file_fops = {
  * @priv: private data for the file
  * @ns: optional namespace tag of the file
  * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
+ * @owner: if set, the module owner of the file
  *
  * Returns the created node on success, ERR_PTR() value on error.
  */

@@ -987,7 +988,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 loff_t size,
 					 const struct kernfs_ops *ops,
 					 void *priv, const void *ns,
-					 struct lock_class_key *key)
+					 struct lock_class_key *key,
+					 struct module *owner)
 {
 	struct kernfs_node *kn;
 	unsigned flags;

@@ -996,7 +998,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 	flags = KERNFS_FILE;
 
 	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG,
-			     uid, gid, flags);
+			     uid, gid, flags, owner);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 

@@ -134,7 +134,8 @@ int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    kuid_t uid, kgid_t gid,
-				    unsigned flags);
+				    unsigned flags,
+				    struct module *owner);
 
 /*
  * file.c

@@ -36,7 +36,8 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 		gid = target->iattr->ia_gid;
 	}
 
-	kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK);
+	kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK,
+			     target->owner);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 

@@ -57,7 +57,7 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 	kobject_get_ownership(kobj, &uid, &gid);
 
 	kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid,
-				  kobj, ns);
+				  kobj, ns, NULL);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, kobject_name(kobj));

@@ -292,7 +292,8 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 #endif
 
 	kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid,
-				  PAGE_SIZE, ops, (void *)attr, ns, key);
+				  PAGE_SIZE, ops, (void *)attr, ns, key,
+				  attr->owner);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, attr->name);

@@ -327,7 +328,8 @@ int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
 #endif
 
 	kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid,
-				  battr->size, ops, (void *)attr, ns, key);
+				  battr->size, ops, (void *)attr, ns, key,
+				  attr->owner);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, attr->name);

@@ -135,7 +135,8 @@ static int internal_create_group(struct kobject *kobj, int update,
 		} else {
 			kn = kernfs_create_dir_ns(kobj->sd, grp->name,
 						  S_IRWXU | S_IRUGO | S_IXUGO,
-						  uid, gid, kobj, NULL);
+						  uid, gid, kobj, NULL,
+						  grp->owner);
 			if (IS_ERR(kn)) {
 				if (PTR_ERR(kn) == -EEXIST)
 					sysfs_warn_dup(kobj->sd, grp->name);

@@ -161,6 +161,7 @@ struct kernfs_node {
 	unsigned short		flags;
 	umode_t			mode;
 	struct kernfs_iattrs	*iattr;
+	struct module           *owner;
 };
 
 /*

@@ -370,7 +371,8 @@ void kernfs_destroy_root(struct kernfs_root *root);
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 kuid_t uid, kgid_t gid,
-					 void *priv, const void *ns);
+					 void *priv, const void *ns,
+					 struct module *owner);
 struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 					    const char *name);
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,

@@ -379,7 +381,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 loff_t size,
 					 const struct kernfs_ops *ops,
 					 void *priv, const void *ns,
-					 struct lock_class_key *key);
+					 struct lock_class_key *key,
+					 struct module *owner);
 struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
 				       struct kernfs_node *target);

@@ -472,14 +475,15 @@ static inline void kernfs_destroy_root(struct kernfs_root *root) { }
 static inline struct kernfs_node *
 kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
 		     umode_t mode, kuid_t uid, kgid_t gid,
-		     void *priv, const void *ns)
+		     void *priv, const void *ns, struct module *owner)
 { return ERR_PTR(-ENOSYS); }
 
 static inline struct kernfs_node *
 __kernfs_create_file(struct kernfs_node *parent, const char *name,
 		     umode_t mode, kuid_t uid, kgid_t gid,
 		     loff_t size, const struct kernfs_ops *ops,
-		     void *priv, const void *ns, struct lock_class_key *key)
+		     void *priv, const void *ns, struct lock_class_key *key,
+		     struct module *owner)
 { return ERR_PTR(-ENOSYS); }
 
 static inline struct kernfs_node *

@@ -566,7 +570,7 @@ kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
 {
 	return kernfs_create_dir_ns(parent, name, mode,
 				    GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-				    priv, NULL);
+				    priv, NULL, parent->owner);
 }
 
 static inline int kernfs_remove_by_name(struct kernfs_node *parent,

@@ -30,6 +30,7 @@ enum kobj_ns_type;
 struct attribute {
 	const char		*name;
 	umode_t			mode;
+	struct module           *owner;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	bool			ignore_lockdep:1;
 	struct lock_class_key	*key;

@@ -80,6 +81,7 @@ do {							\
  * @attrs:	Pointer to NULL terminated list of attributes.
  * @bin_attrs:	Pointer to NULL terminated list of binary attributes.
  *		Either attrs or bin_attrs or both must be provided.
+ * @module:	If set, module responsible for this attribute group
  */
 struct attribute_group {
 	const char		*name;

@@ -89,6 +91,7 @@ struct attribute_group {
 						  struct bin_attribute *, int);
 	struct attribute	**attrs;
 	struct bin_attribute	**bin_attrs;
+	struct module           *owner;
 };
 
 /*

@@ -100,38 +103,52 @@ struct attribute_group {
 
 #define __ATTR(_name, _mode, _show, _store) {				\
 	.attr = {.name = __stringify(_name),				\
-		 .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
+		 .mode = VERIFY_OCTAL_PERMISSIONS(_mode),               \
+		 .owner  = THIS_MODULE,                                 \
+	},                                                             \
 	.show	= _show,						\
 	.store	= _store,						\
 }
 
 #define __ATTR_PREALLOC(_name, _mode, _show, _store) {			\
 	.attr = {.name = __stringify(_name),				\
-		 .mode = SYSFS_PREALLOC | VERIFY_OCTAL_PERMISSIONS(_mode) },\
+		 .mode = SYSFS_PREALLOC | VERIFY_OCTAL_PERMISSIONS(_mode),\
+		 .owner  = THIS_MODULE,                                 \
+	},                                                              \
 	.show	= _show,						\
 	.store	= _store,						\
 }
 
 #define __ATTR_RO(_name) {						\
-	.attr	= { .name = __stringify(_name), .mode = 0444 },		\
+	.attr	= { .name = __stringify(_name),                         \
+		    .mode = 0444,					\
+		    .owner  = THIS_MODULE,				\
+		},                                                     \
 	.show	= _name##_show,						\
 }
 
 #define __ATTR_RO_MODE(_name, _mode) {					\
 	.attr	= { .name = __stringify(_name),				\
-		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
+		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode),            \
+		    .owner  = THIS_MODULE,				\
+	},                                                              \
 	.show	= _name##_show,						\
 }
 
 #define __ATTR_RW_MODE(_name, _mode) {					\
 	.attr	= { .name = __stringify(_name),				\
-		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
+		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode),            \
+		    .owner  = THIS_MODULE,                              \
+	},								\
 	.show	= _name##_show,						\
 	.store	= _name##_store,					\
 }
 
 #define __ATTR_WO(_name) {						\
-	.attr	= { .name = __stringify(_name), .mode = 0200 },		\
+	.attr	= { .name = __stringify(_name),                         \
+		    .mode = 0200,					\
+		    .owner  = THIS_MODULE,				\
+	},                                                              \
 	.store	= _name##_store,					\
 }
 

@@ -141,8 +158,11 @@ struct attribute_group {
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) {	\
-	.attr = {.name = __stringify(_name), .mode = _mode,	\
-			.ignore_lockdep = true },		\
+	.attr = {.name = __stringify(_name),                    \
+		 .mode = _mode,					\
+		 .ignore_lockdep = true,                        \
+		 .owner  = THIS_MODULE,                         \
+	},							\
 	.show		= _show,				\
 	.store		= _store,				\
 }

@@ -159,6 +179,7 @@ static const struct attribute_group *_name##_groups[] = {	\
 #define ATTRIBUTE_GROUPS(_name)					\
 static const struct attribute_group _name##_group = {		\
 	.attrs = _name##_attrs,					\
+	.owner = THIS_MODULE,					\
 };								\
 __ATTRIBUTE_GROUPS(_name)
 

@@ -199,20 +220,29 @@ struct bin_attribute {
 
 /* macros to create static binary attributes easier */
 #define __BIN_ATTR(_name, _mode, _read, _write, _size) {		\
-	.attr = { .name = __stringify(_name), .mode = _mode },		\
+	.attr = { .name = __stringify(_name),                           \
+		   .mode = _mode,					\
+		   .owner = THIS_MODULE,				\
+	},								\
 	.read	= _read,						\
 	.write	= _write,						\
 	.size	= _size,						\
 }
 
 #define __BIN_ATTR_RO(_name, _size) {					\
-	.attr	= { .name = __stringify(_name), .mode = 0444 },		\
+	.attr	= { .name = __stringify(_name),                         \
+		    .mode = 0444,					\
+		    .owner = THIS_MODULE,				\
+	},								\
 	.read	= _name##_read,						\
 	.size	= _size,						\
 }
 
 #define __BIN_ATTR_WO(_name, _size) {					\
-	.attr	= { .name = __stringify(_name), .mode = 0200 },		\
+	.attr	= { .name = __stringify(_name),                         \
+		    .mode = 0200,					\
+		    .owner = THIS_MODULE,				\
+	},								\
 	.write	= _name##_write,					\
 	.size	= _size,						\
 }

@@ -3975,7 +3975,7 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 				  cgroup_file_mode(cft),
 				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
 				  0, cft->kf_ops, cft,
-				  NULL, key);
+				  NULL, key, NULL);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 

@@ -56,8 +56,7 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 
 	kobject_get_ownership(kobj, &uid, &gid);
 
-	kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
-				  S_IRWXU | S_IRUGO | S_IXUGO, uid, gid,
+	kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid,
 				  kobj, ns);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)

@@ -0,0 +1,237 @@
+Valid-License-Identifier: copyleft-next-0.3.1
+SPDX-URL: https://spdx.org/licenses/copyleft-next-0.3.1
+Usage-Guide:
+  This license can be used in code, it has been found to be GPLv2 compatible
+  by attorneys at Redhat and SUSE, however to air on the side of caution,
+  it's best to only use it together with a GPL2 compatible license using "OR".
+  To use the copyleft-next-0.3.1 license put the following SPDX tag/value
+  pair into a comment according to the placement guidelines in the
+  licensing rules documentation:
+    SPDX-License-Identifier: GPL-2.0 OR copyleft-next-0.3.1
+    SPDX-License-Identifier: GPL-2.0-only OR copyleft-next 0.3.1
+    SPDX-License-Identifier: GPL-2.0+ OR copyleft-next-0.3.1
+    SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
+License-Text:
+
+=======================================================================
+
+                      copyleft-next 0.3.1 ("this License")
+                            Release date: 2016-04-29
+
+1. License Grants; No Trademark License
+
+   Subject to the terms of this License, I grant You:
+
+   a) A non-exclusive, worldwide, perpetual, royalty-free, irrevocable
+      copyright license, to reproduce, Distribute, prepare derivative works
+      of, publicly perform and publicly display My Work.
+
+   b) A non-exclusive, worldwide, perpetual, royalty-free, irrevocable
+      patent license under Licensed Patents to make, have made, use, sell,
+      offer for sale, and import Covered Works.
+
+   This License does not grant any rights in My name, trademarks, service
+   marks, or logos.
+
+2. Distribution: General Conditions
+
+   You may Distribute Covered Works, provided that You (i) inform
+   recipients how they can obtain a copy of this License; (ii) satisfy the
+   applicable conditions of sections 3 through 6; and (iii) preserve all
+   Legal Notices contained in My Work (to the extent they remain
+   pertinent). "Legal Notices" means copyright notices, license notices,
+   license texts, and author attributions, but does not include logos,
+   other graphical images, trademarks or trademark legends.
+
+3. Conditions for Distributing Derived Works; Outbound GPL Compatibility
+
+   If You Distribute a Derived Work, You must license the entire Derived
+   Work as a whole under this License, with prominent notice of such
+   licensing. This condition may not be avoided through such means as
+   separate Distribution of portions of the Derived Work.
+
+   If the Derived Work includes material licensed under the GPL, You may
+   instead license the Derived Work under the GPL.
+   
+4. Condition Against Further Restrictions; Inbound License Compatibility
+
+   When Distributing a Covered Work, You may not impose further
+   restrictions on the exercise of rights in the Covered Work granted under
+   this License. This condition is not excused merely because such
+   restrictions result from Your compliance with conditions or obligations
+   extrinsic to this License (such as a court order or an agreement with a
+   third party).
+
+   However, You may Distribute a Covered Work incorporating material
+   governed by a license that is both OSI-Approved and FSF-Free as of the
+   release date of this License, provided that compliance with such
+   other license would not conflict with any conditions stated in other
+   sections of this License.
+
+5. Conditions for Distributing Object Code
+
+   You may Distribute an Object Code form of a Covered Work, provided that
+   you accompany the Object Code with a URL through which the Corresponding
+   Source is made available, at no charge, by some standard or customary
+   means of providing network access to source code.
+
+   If you Distribute the Object Code in a physical product or tangible
+   storage medium ("Product"), the Corresponding Source must be available
+   through such URL for two years from the date of Your most recent
+   Distribution of the Object Code in the Product. However, if the Product
+   itself contains or is accompanied by the Corresponding Source (made
+   available in a customarily accessible manner), You need not also comply
+   with the first paragraph of this section.
+
+   Each direct and indirect recipient of the Covered Work from You is an
+   intended third-party beneficiary of this License solely as to this
+   section 5, with the right to enforce its terms.
+
+6. Symmetrical Licensing Condition for Upstream Contributions
+
+   If You Distribute a work to Me specifically for inclusion in or
+   modification of a Covered Work (a "Patch"), and no explicit licensing
+   terms apply to the Patch, You license the Patch under this License, to
+   the extent of Your copyright in the Patch. This condition does not
+   negate the other conditions of this License, if applicable to the Patch.
+
+7. Nullification of Copyleft/Proprietary Dual Licensing
+
+   If I offer to license, for a fee, a Covered Work under terms other than
+   a license that is OSI-Approved or FSF-Free as of the release date of this
+   License or a numbered version of copyleft-next released by the
+   Copyleft-Next Project, then the license I grant You under section 1 is no
+   longer subject to the conditions in sections 3 through 5.
+
+8. Copyleft Sunset
+
+   The conditions in sections 3 through 5 no longer apply once fifteen
+   years have elapsed from the date of My first Distribution of My Work
+   under this License.
+
+9. Pass-Through
+
+   When You Distribute a Covered Work, the recipient automatically receives
+   a license to My Work from Me, subject to the terms of this License.
+
+10. Termination
+
+    Your license grants under section 1 are automatically terminated if You
+
+    a) fail to comply with the conditions of this License, unless You cure
+       such noncompliance within thirty days after becoming aware of it, or
+
+    b) initiate a patent infringement litigation claim (excluding
+       declaratory judgment actions, counterclaims, and cross-claims)
+       alleging that any part of My Work directly or indirectly infringes
+       any patent.
+
+    Termination of Your license grants extends to all copies of Covered
+    Works You subsequently obtain. Termination does not terminate the
+    rights of those who have received copies or rights from You subject to
+    this License.
+
+    To the extent permission to make copies of a Covered Work is necessary
+    merely for running it, such permission is not terminable.
+
+11. Later License Versions
+
+    The Copyleft-Next Project may release new versions of copyleft-next,
+    designated by a distinguishing version number ("Later Versions").
+    Unless I explicitly remove the option of Distributing Covered Works
+    under Later Versions, You may Distribute Covered Works under any Later
+    Version.
+
+** 12. No Warranty                                                       **
+**                                                                       **
+**     My Work is provided "as-is", without warranty. You bear the risk  **
+**     of using it. To the extent permitted by applicable law, each      **
+**     Distributor of My Work excludes the implied warranties of title,  **
+**     merchantability, fitness for a particular purpose and             **
+**     non-infringement.                                                 **
+
+** 13. Limitation of Liability                                           **
+**                                                                       **
+**     To the extent permitted by applicable law, in no event will any   **
+**     Distributor of My Work be liable to You for any damages           **
+**     whatsoever, whether direct, indirect, special, incidental, or     **
+**     consequential damages, whether arising under contract, tort       **
+**     (including negligence), or otherwise, even where the Distributor  **
+**     knew or should have known about the possibility of such damages.  **
+
+14. Severability
+
+    The invalidity or unenforceability of any provision of this License
+    does not affect the validity or enforceability of the remainder of
+    this License. Such provision is to be reformed to the minimum extent
+    necessary to make it valid and enforceable.
+
+15. Definitions
+
+    "Copyleft-Next Project" means the project that maintains the source
+    code repository at <https://github.com/copyleft-next/copyleft-next.git/>
+    as of the release date of this License.
+
+    "Corresponding Source" of a Covered Work in Object Code form means (i)
+    the Source Code form of the Covered Work; (ii) all scripts,
+    instructions and similar information that are reasonably necessary for
+    a skilled developer to generate such Object Code from the Source Code
+    provided under (i); and (iii) a list clearly identifying all Separate
+    Works (other than those provided in compliance with (ii)) that were
+    specifically used in building and (if applicable) installing the
+    Covered Work (for example, a specified proprietary compiler including
+    its version number). Corresponding Source must be machine-readable.
+
+    "Covered Work" means My Work or a Derived Work.
+
+    "Derived Work" means a work of authorship that copies from, modifies,
+    adapts, is based on, is a derivative work of, transforms, translates or
+    contains all or part of My Work, such that copyright permission is
+    required. The following are not Derived Works: (i) Mere Aggregation;
+    (ii) a mere reproduction of My Work; and (iii) if My Work fails to
+    explicitly state an expectation otherwise, a work that merely makes
+    reference to My Work.
+
+    "Distribute" means to distribute, transfer or make a copy available to
+    someone else, such that copyright permission is required.
+
+    "Distributor" means Me and anyone else who Distributes a Covered Work.
+
+    "FSF-Free" means classified as 'free' by the Free Software Foundation.
+
+    "GPL" means a version of the GNU General Public License or the GNU
+    Affero General Public License.
+
+    "I"/"Me"/"My" refers to the individual or legal entity that places My
+    Work under this License. "You"/"Your" refers to the individual or legal
+    entity exercising rights in My Work under this License. A legal entity
+    includes each entity that controls, is controlled by, or is under
+    common control with such legal entity. "Control" means (a) the power to
+    direct the actions of such legal entity, whether by contract or
+    otherwise, or (b) ownership of more than fifty percent of the
+    outstanding shares or beneficial ownership of such legal entity.
+
+    "Licensed Patents" means all patent claims licensable royalty-free by
+    Me, now or in the future, that are necessarily infringed by making,
+    using, or selling My Work, and excludes claims that would be infringed
+    only as a consequence of further modification of My Work.
+
+    "Mere Aggregation" means an aggregation of a Covered Work with a
+    Separate Work.
+
+    "My Work" means the particular work of authorship I license to You
+    under this License.
+
+    "Object Code" means any form of a work that is not Source Code.
+
+    "OSI-Approved" means approved as 'Open Source' by the Open Source
+    Initiative.
+
+    "Separate Work" means a work that is separate from and independent of a
+    particular Covered Work and is not by its nature an extension or
+    enhancement of the Covered Work, and/or a runtime library, standard
+    library or similar component that is used to generate an Object Code
+    form of a Covered Work.
+
+    "Source Code" means the preferred form of a work for making
+    modifications to it.

@@ -28,6 +28,28 @@ Available fault injection capabilities
 
   injects kernel RPC client and server failures.
 
+- fail_kernfs_fop_write_iter
+
+  Allows for failures to be enabled inside kernfs_fop_write_iter(). Enabling
+  this does not immediately enable any errors to occur. You must configure
+  how you want this routine to fail or change behaviour by using the debugfs
+  knobs for it:
+
+  # ls -1 /sys/kernel/debug/kernfs/config_fail_kernfs_fop_write_iter/
+  wait_after_active
+  wait_after_mutex
+  wait_at_start
+  wait_before_mutex
+
+  You can also configure how long to sleep after a wait under
+
+  /sys/kernel/debug/kernfs/sleep_after_wait_ms
+
+  If you enable CONFIG_FAULT_INJECTION_DEBUG_FS the fail_add_disk failure
+  injection parameters are placed under:
+
+  /sys/kernel/debug/kernfs/fail_kernfs_fop_write_iter/
+
 - fail_make_request
 
   injects disk IO errors on devices permitted by setting

@@ -10384,7 +10384,7 @@ M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Tejun Heo <tj@kernel.org>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
-F:	fs/kernfs/
+F:	fs/kernfs/*
 F:	include/linux/kernfs.h
 
 KEXEC

@@ -4,3 +4,4 @@
 #
 
 obj-y		:= mount.o inode.o dir.o file.o symlink.o
+obj-$(CONFIG_FAIL_KERNFS_KNOBS)    += failure-injection.o