diff options
Diffstat (limited to 'include/linux/kernfs.h')
| -rw-r--r-- | include/linux/kernfs.h | 148 |
1 files changed, 94 insertions, 54 deletions
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 89f6a4214a70..b5a5f32fdfd1 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -6,7 +6,6 @@ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H -#include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> @@ -14,14 +13,19 @@ #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; @@ -31,6 +35,62 @@ 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, @@ -48,10 +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() */ @@ -85,6 +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 */ @@ -98,6 +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 { @@ -106,7 +178,7 @@ 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() */ }; @@ -116,7 +188,7 @@ struct kernfs_elem_attr { * 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. */ @@ -132,30 +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; - unsigned short flags; - umode_t mode; + void *priv; struct kernfs_iattrs *iattr; + + struct rcu_head rcu; }; /* @@ -177,22 +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 last_id_lowbits; - u32 id_highbits; - 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 */ @@ -264,10 +323,7 @@ struct kernfs_ops { struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif + loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence); }; /* @@ -344,7 +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); @@ -365,6 +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, @@ -383,6 +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); @@ -462,6 +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, @@ -501,6 +561,10 @@ 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, @@ -563,30 +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) { |