From 633488947ef66b194377411322dc9e12aab79b65 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 13 Feb 2025 15:50:22 +0100 Subject: kernfs: Use RCU to access kernfs_node::parent. kernfs_rename_lock is used to obtain stable kernfs_node::{name|parent} pointer. This is a preparation to access kernfs_node::parent under RCU and ensure that the pointer remains stable under the RCU lifetime guarantees. For a complete path, as it is done in kernfs_path_from_node(), the kernfs_rename_lock is still required in order to obtain a stable parent relationship while computing the relevant node depth. This must not change while the nodes are inspected in order to build the path. If the kernfs user never moves the nodes (changes the parent) then the kernfs_rename_lock is not required and the RCU guarantees are sufficient. This "restriction" can be set with KERNFS_ROOT_INVARIANT_PARENT. Otherwise the lock is required. Rename kernfs_node::parent to kernfs_node::__parent to denote the RCU access and use RCU accessor while accessing the node. Make cgroup use KERNFS_ROOT_INVARIANT_PARENT since the parent here can not change. Acked-by: Tejun Heo Cc: Yonghong Song Signed-off-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20250213145023.2820193-6-bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 87c79d076d6d..5dda9a268e44 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -147,6 +147,11 @@ enum kernfs_root_flag { * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, + + /* + * Renames must not change the parent node. + */ + KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ @@ -199,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - struct kernfs_node *parent; const char *name; + struct kernfs_node __rcu *__parent; struct rb_node rb; @@ -416,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); +unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, @@ -514,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } +static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, -- cgit v1.2.3 From 741c10b096bc4dd79cd9f215b6ef173bb953e75c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 13 Feb 2025 15:50:23 +0100 Subject: kernfs: Use RCU to access kernfs_node::name. Using RCU lifetime rules to access kernfs_node::name can avoid the trouble with kernfs_rename_lock in kernfs_name() and kernfs_path_from_node() if the fs was created with KERNFS_ROOT_INVARIANT_PARENT. This is usefull as it allows to implement kernfs_path_from_node() only with RCU protection and avoiding kernfs_rename_lock. The lock is only required if the __parent node can be changed and the function requires an unchanged hierarchy while it iterates from the node to its parent. The change is needed to allow the lookup of the node's path (kernfs_path_from_node()) from context which runs always with disabled preemption and or interrutps even on PREEMPT_RT. The problem is that kernfs_rename_lock becomes a sleeping lock on PREEMPT_RT. I went through all ::name users and added the required access for the lookup with a few extensions: - rdtgroup_pseudo_lock_create() drops all locks and then uses the name later on. resctrl supports rename with different parents. Here I made a temporal copy of the name while it is used outside of the lock. - kernfs_rename_ns() accepts NULL as new_parent. This simplifies sysfs_move_dir_ns() where it can set NULL in order to reuse the current name. - kernfs_rename_ns() is only using kernfs_rename_lock if the parents are different. All users use either kernfs_rwsem (for stable path view) or just RCU for the lookup. The ::name uses always RCU free. Use RCU lifetime guarantees to access kernfs_node::name. Suggested-by: Tejun Heo Acked-by: Tejun Heo Reported-by: syzbot+6ea37e2e6ffccf41a7e6@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/67251dc6.050a0220.529b6.015e.GAE@google.com/ Reported-by: Hillf Danton Closes: https://lore.kernel.org/20241102001224.2789-1-hdanton@sina.com Signed-off-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20250213145023.2820193-7-bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5dda9a268e44..b5a5f32fdfd1 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -204,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - const char *name; struct kernfs_node __rcu *__parent; + const char __rcu *name; struct rb_node rb; @@ -400,7 +400,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); -int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, +int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); -- cgit v1.2.3 From 8fd74a31eaf3def0d57264ada57fc981902aeadf Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Sat, 8 Feb 2025 22:15:26 +0800 Subject: driver core: class: Remove needless return in void API class_remove_file() Remove return since both class_remove_file() and class_remove_file_ns() are void functions. Signed-off-by: Zijun Hu Link: https://lore.kernel.org/r/20250208-cls_rmv_return-v1-1-091b37945aac@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 45ee3a634999..65880e60c720 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -193,7 +193,7 @@ static inline int __must_check class_create_file(const struct class *class, static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { - return class_remove_file_ns(class, attr, NULL); + class_remove_file_ns(class, attr, NULL); } /* Simple class attribute that is just a static string */ -- cgit v1.2.3 From a44073c28bc6d4118891d61e31c9fa9dc4333dc0 Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Sat, 8 Feb 2025 23:18:39 +0800 Subject: driver core: Remove needless return in void API device_remove_group() Remove return since both device_remove_group() and device_remove_groups() are void functions. Fixes: e323b2dddc1c ("driver core: add device_{add|remove}_group() helpers") Signed-off-by: Zijun Hu Link: https://lore.kernel.org/r/20250208-fix_device_remove_group-v1-1-8a5b0ac0ce5c@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 80a5b3268986..605b60254f6d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1268,7 +1268,7 @@ static inline void device_remove_group(struct device *dev, { const struct attribute_group *groups[] = { grp, NULL }; - return device_remove_groups(dev, groups); + device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, -- cgit v1.2.3