diff options
Diffstat (limited to 'include/linux/kernfs.h')
| -rw-r--r-- | include/linux/kernfs.h | 271 |
1 files changed, 178 insertions, 93 deletions
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5b36b1287a5a..b5a5f32fdfd1 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -1,13 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * kernfs.h - pseudo filesystem decoupled from vfs locking - * - * This file is released under the GPLv2. */ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H -#include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> @@ -15,28 +13,94 @@ #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/types.h> #include <linux/uidgid.h> #include <linux/wait.h> +#include <linux/rwsem.h> +#include <linux/cache.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; +struct vm_operations_struct; struct super_block; struct file_system_type; +struct poll_table_struct; +struct fs_context; +struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; +/* + * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash + * table of locks. + * Having a small hash table would impact scalability, since + * more and more kernfs_node objects will end up using same lock + * and having a very large hash table would waste memory. + * + * At the moment size of hash table of locks is being set based on + * the number of CPUs as follows: + * + * NR_CPU NR_KERNFS_LOCK_BITS NR_KERNFS_LOCKS + * 1 1 2 + * 2-3 2 4 + * 4-7 4 16 + * 8-15 6 64 + * 16-31 8 256 + * 32 and more 10 1024 + * + * The above relation between NR_CPU and number of locks is based + * on some internal experimentation which involved booting qemu + * with different values of smp, performing some sysfs operations + * on all CPUs and observing how increase in number of locks impacts + * completion time of these sysfs operations on each CPU. + */ +#ifdef CONFIG_SMP +#define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32))) +#else +#define NR_KERNFS_LOCK_BITS 1 +#endif + +#define NR_KERNFS_LOCKS (1 << NR_KERNFS_LOCK_BITS) + +/* + * There's one kernfs_open_file for each open file and one kernfs_open_node + * for each kernfs_node with one or more open files. + * + * filp->private_data points to seq_file whose ->private points to + * kernfs_open_file. + * + * kernfs_open_files are chained at kernfs_open_node->files, which is + * protected by kernfs_global_locks.open_file_mutex[i]. + * + * To reduce possible contention in sysfs access, arising due to single + * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node + * object address as hash keys to get the index of these locks. + * + * Hashed mutexes are safe to use here because operations using these don't + * rely on global exclusion. + * + * In future we intend to replace other global locks with hashed ones as well. + * kernfs_global_locks acts as a holder for all such hash tables. + */ +struct kernfs_global_locks { + struct mutex open_file_mutex[NR_KERNFS_LOCKS]; +}; + enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, KERNFS_LINK = 0x0004, }; -#define KERNFS_TYPE_MASK 0x000f -#define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK +#define KERNFS_TYPE_MASK 0x000f +#define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK +#define KERNFS_MAX_USER_XATTRS 128 +#define KERNFS_USER_XATTR_SIZE_LIMIT (128 << 10) enum kernfs_node_flag { KERNFS_ACTIVATED = 0x0010, @@ -44,10 +108,12 @@ enum kernfs_node_flag { KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, + KERNFS_HIDDEN = 0x0200, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, + KERNFS_REMOVING = 0x4000, }; /* @flags for kernfs_create_root() */ @@ -61,7 +127,7 @@ enum kernfs_root_flag { KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, /* - * For regular flies, if the opener has CAP_DAC_OVERRIDE, open(2) + * For regular files, if the opener has CAP_DAC_OVERRIDE, open(2) * succeeds regardless of the RW permissions. sysfs had an extra * layer of enforcement where open(2) fails with -EACCES regardless * of CAP_DAC_OVERRIDE if the permission doesn't have the @@ -76,6 +142,16 @@ enum kernfs_root_flag { * fhandle to access nodes of the fs. */ KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, + + /* + * 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 */ @@ -89,6 +165,11 @@ struct kernfs_elem_dir { * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; + /* + * Monotonic revision counter, used to identify if a directory + * node has changed during negative dentry revalidation. + */ + unsigned long rev; }; struct kernfs_elem_symlink { @@ -97,32 +178,17 @@ struct kernfs_elem_symlink { struct kernfs_elem_attr { const struct kernfs_ops *ops; - struct kernfs_open_node *open; + struct kernfs_open_node __rcu *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; -/* represent a kernfs node */ -union kernfs_node_id { - struct { - /* - * blktrace will export this struct as a simplified 'struct - * fid' (which is a big data struction), so userspace can use - * it to find kernfs node. The layout must match the first two - * fields of 'struct fid' exactly. - */ - u32 ino; - u32 generation; - }; - u64 id; -}; - /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are * private to kernfs and shouldn't be accessed directly by kernfs users. * - * As long as s_count reference is held, the kernfs_node itself is + * As long as count reference is held, the kernfs_node itself is * accessible. Dereferencing elem or any other outer entity requires * active reference. */ @@ -138,25 +204,32 @@ 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; + const char __rcu *name; struct rb_node rb; const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ + unsigned short flags; + umode_t mode; + union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; - void *priv; + /* + * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, + * the low 32bits are ino and upper generation. + */ + u64 id; - union kernfs_node_id id; - unsigned short flags; - umode_t mode; + void *priv; struct kernfs_iattrs *iattr; + + struct rcu_head rcu; }; /* @@ -167,7 +240,6 @@ struct kernfs_node { * kernfs_node parameter. */ 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, @@ -179,21 +251,7 @@ struct kernfs_syscall_ops { struct kernfs_root *root); }; -struct kernfs_root { - /* published fields */ - struct kernfs_node *kn; - unsigned int flags; /* KERNFS_ROOT_* flags */ - - /* private fields, do not use outside kernfs proper */ - struct idr ino_idr; - u32 next_generation; - struct kernfs_syscall_ops *syscall_ops; - - /* list of kernfs_super_info of this root, protected by kernfs_mutex */ - struct list_head supers; - - wait_queue_head_t deactivate_waitq; -}; +struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ @@ -261,11 +319,23 @@ struct kernfs_ops { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); + __poll_t (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); + loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence); +}; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif +/* + * The kernfs superblock creation/mount parameter context. + */ +struct kernfs_fs_context { + struct kernfs_root *root; /* Root of the hierarchy being mounted */ + void *ns_tag; /* Namespace tag of the mount (or NULL) */ + unsigned long magic; /* File system specific magic number */ + + /* The following are set/used by kernfs_mount() */ + bool new_sb_created; /* Set to T if we allocated a new sb */ }; #ifdef CONFIG_KERNFS @@ -275,6 +345,34 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) return kn->flags & KERNFS_TYPE_MASK; } +static inline ino_t kernfs_id_ino(u64 id) +{ + /* id is ino if ino_t is 64bit; otherwise, low 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return id; + else + return (u32)id; +} + +static inline u32 kernfs_id_gen(u64 id) +{ + /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return 1; + else + return id >> 32; +} + +static inline ino_t kernfs_ino(struct kernfs_node *kn) +{ + return kernfs_id_ino(kn->id); +} + +static inline ino_t kernfs_gen(struct kernfs_node *kn) +{ + return kernfs_id_gen(kn->id); +} + /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty @@ -302,7 +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); @@ -323,6 +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, @@ -341,6 +440,7 @@ 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_show(struct kernfs_node *kn, bool show); 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); @@ -350,19 +450,24 @@ 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); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); +int kernfs_xattr_get(struct kernfs_node *kn, const char *name, + void *value, size_t size); +int kernfs_xattr_set(struct kernfs_node *kn, const char *name, + const void *value, size_t size, int flags); + const void *kernfs_super_ns(struct super_block *sb); -struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, unsigned long magic, - bool *new_sb_created, const void *ns); +int kernfs_get_tree(struct fs_context *fc); +void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); -struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns); void kernfs_init(void); -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id); +struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, + u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) @@ -415,6 +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, @@ -454,16 +561,27 @@ static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } +static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt) +{ return -ENOSYS; } + static inline void kernfs_notify(struct kernfs_node *kn) { } +static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, + void *value, size_t size) +{ return -ENOSYS; } + +static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, + const void *value, size_t size, int flags) +{ return -ENOSYS; } + static inline const void *kernfs_super_ns(struct super_block *sb) { return NULL; } -static inline struct dentry * -kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, unsigned long magic, - bool *new_sb_created, const void *ns) -{ return ERR_PTR(-ENOSYS); } +static inline int kernfs_get_tree(struct fs_context *fc) +{ return -ENOSYS; } + +static inline void kernfs_free_fs_context(struct fs_context *fc) { } static inline void kernfs_kill_sb(struct super_block *sb) { } @@ -509,30 +627,6 @@ kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, priv, NULL); } -static inline struct kernfs_node * -kernfs_create_file_ns(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 = NULL; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - key = (struct lock_class_key *)&ops->lockdep_key; -#endif - return __kernfs_create_file(parent, name, mode, uid, gid, - size, ops, priv, ns, key); -} - -static inline struct kernfs_node * -kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, - loff_t size, const struct kernfs_ops *ops, void *priv) -{ - return kernfs_create_file_ns(parent, name, mode, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - size, ops, priv, NULL); -} - static inline int kernfs_remove_by_name(struct kernfs_node *parent, const char *name) { @@ -546,13 +640,4 @@ static inline int kernfs_rename(struct kernfs_node *kn, 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, unsigned long magic, - bool *new_sb_created) -{ - return kernfs_mount_ns(fs_type, flags, root, - magic, new_sb_created, NULL); -} - #endif /* __LINUX_KERNFS_H */ |