X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fcgroup.h;h=8f78073d7caaa278017232112f0d3da05aa0d4c0;hb=3374cd1abd478f767aaedf2c21d109596ff0fe72;hp=028ba3b523b1b8a3a8cdeea0ad745552ae84a8cd;hpb=ffd2d883399cbbb641e55730676ce1ec4845d99d;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 028ba3b..8f78073 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -9,23 +9,27 @@ */ #include -#include #include #include #include #include #include +#include +#include #ifdef CONFIG_CGROUPS struct cgroupfs_root; struct cgroup_subsys; struct inode; +struct cgroup; +struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); -extern void cgroup_init_smp(void); extern void cgroup_lock(void); +extern int cgroup_lock_is_held(void); +extern bool cgroup_lock_live_group(struct cgroup *cgrp); extern void cgroup_unlock(void); extern void cgroup_fork(struct task_struct *p); extern void cgroup_fork_callbacks(struct task_struct *p); @@ -33,67 +37,164 @@ extern void cgroup_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); +extern int cgroup_load_subsys(struct cgroup_subsys *ss); +extern void cgroup_unload_subsys(struct cgroup_subsys *ss); -extern struct file_operations proc_cgroup_operations; +extern const struct file_operations proc_cgroup_operations; -/* Define the enumeration of all cgroup subsystems */ +/* Define the enumeration of all builtin cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, enum cgroup_subsys_id { #include - CGROUP_SUBSYS_COUNT + CGROUP_BUILTIN_SUBSYS_COUNT }; #undef SUBSYS +/* + * This define indicates the maximum number of subsystems that can be loaded + * at once. We limit to this many since cgroupfs_root has subsys_bits to keep + * track of all of them. + */ +#define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long)) /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* The cgroup that this subsystem is attached to. Useful + /* + * The cgroup that this subsystem is attached to. Useful * for subsystems that want to know about the cgroup - * hierarchy structure */ + * hierarchy structure + */ struct cgroup *cgroup; - /* State maintained by the cgroup system to allow - * subsystems to be "busy". Should be accessed via css_get() - * and css_put() */ + /* + * State maintained by the cgroup system to allow subsystems + * to be "busy". Should be accessed via css_get(), + * css_tryget() and and css_put(). + */ atomic_t refcnt; unsigned long flags; + /* ID for this css, if possible */ + struct css_id *id; }; /* bits in struct cgroup_subsys_state flags field */ enum { CSS_ROOT, /* This CSS is the root of the subsystem */ + CSS_REMOVED, /* This CSS is dead */ }; +/* Caller must verify that the css is not for root cgroup */ +static inline void __css_get(struct cgroup_subsys_state *css, int count) +{ + atomic_add(count, &css->refcnt); +} + /* - * Call css_get() to hold a reference on the cgroup; - * + * Call css_get() to hold a reference on the css; it can be used + * for a reference obtained via: + * - an existing ref-counted reference to the css + * - task->cgroups for a locked task */ static inline void css_get(struct cgroup_subsys_state *css) { /* We don't need to reference count the root state */ if (!test_bit(CSS_ROOT, &css->flags)) - atomic_inc(&css->refcnt); + __css_get(css, 1); +} + +static inline bool css_is_removed(struct cgroup_subsys_state *css) +{ + return test_bit(CSS_REMOVED, &css->flags); +} + +/* + * Call css_tryget() to take a reference on a css if your existing + * (known-valid) reference isn't already ref-counted. Returns false if + * the css has been destroyed. + */ + +static inline bool css_tryget(struct cgroup_subsys_state *css) +{ + if (test_bit(CSS_ROOT, &css->flags)) + return true; + while (!atomic_inc_not_zero(&css->refcnt)) { + if (test_bit(CSS_REMOVED, &css->flags)) + return false; + cpu_relax(); + } + return true; } + /* * css_put() should be called to release a reference taken by - * css_get() + * css_get() or css_tryget() */ -extern void __css_put(struct cgroup_subsys_state *css); +extern void __css_put(struct cgroup_subsys_state *css, int count); static inline void css_put(struct cgroup_subsys_state *css) { if (!test_bit(CSS_ROOT, &css->flags)) - __css_put(css); + __css_put(css, 1); } +/* bits in struct cgroup flags field */ +enum { + /* Control Group is dead */ + CGRP_REMOVED, + /* + * Control Group has previously had a child cgroup or a task, + * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) + */ + CGRP_RELEASABLE, + /* Control Group requires release notifications to userspace */ + CGRP_NOTIFY_ON_RELEASE, + /* + * A thread in rmdir() is wating for this cgroup. + */ + CGRP_WAIT_ON_RMDIR, +}; + +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* how many files are using the current array */ + int use_count; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* protects the other fields */ + struct rw_semaphore mutex; +}; + struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - /* count users of this cgroup. >0 means busy, but doesn't - * necessarily indicate the number of tasks in the - * cgroup */ + /* + * count users of this cgroup. >0 means busy, but doesn't + * necessarily indicate the number of tasks in the cgroup + */ atomic_t count; /* @@ -103,8 +204,8 @@ struct cgroup { struct list_head sibling; /* my parent's children */ struct list_head children; /* my children */ - struct cgroup *parent; /* my parent */ - struct dentry *dentry; /* cgroup fs entry */ + struct cgroup *parent; /* my parent */ + struct dentry *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; @@ -124,25 +225,40 @@ struct cgroup { * release_list_lock */ struct list_head release_list; + + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; + + /* List of events which userspace want to recieve */ + struct list_head event_list; + spinlock_t event_list_lock; }; -/* A css_set is a structure holding pointers to a set of +/* + * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire - * cgroup set for a task. + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. */ struct css_set { /* Reference count */ - struct kref ref; + atomic_t refcount; /* - * List running through all cgroup groups. Protected by - * css_set_lock + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock */ - struct list_head list; + struct hlist_node hlist; /* * List running through all tasks using this cgroup @@ -160,19 +276,27 @@ struct css_set { /* * Set of subsystem states, one for each subsystem. This array * is immutable after creation apart from the init_css_set - * during subsystem registration (at boot time). + * during subsystem registration (at boot time) and modular subsystem + * loading/unloading. */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + /* For RCU-protected deletion */ + struct rcu_head rcu_head; }; -/* struct cftype: - * - * The files in the cgroup filesystem mostly have a very simple read/write - * handling, some common function will take care of it. Nevertheless some cases - * (read tasks) are special and therefore I define this structure for every - * kind of file. - * +/* + * cgroup_map_cb is an abstract callback API for reporting map-valued + * control files + */ + +struct cgroup_map_cb { + int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value); + void *state; +}; + +/* + * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_dentry->d_parent->d_fsdata @@ -181,31 +305,100 @@ struct css_set { #define MAX_CFTYPE_NAME 64 struct cftype { - /* By convention, the name should begin with the name of the - * subsystem, followed by a period */ + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period + */ char name[MAX_CFTYPE_NAME]; int private; - int (*open) (struct inode *inode, struct file *file); - ssize_t (*read) (struct cgroup *cgrp, struct cftype *cft, - struct file *file, - char __user *buf, size_t nbytes, loff_t *ppos); /* - * read_uint() is a shortcut for the common case of returning a + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + mode_t mode; + + /* + * If non-zero, defines the maximum length of string that can + * be passed to write_string; defaults to 64 + */ + size_t max_write_len; + + int (*open)(struct inode *inode, struct file *file); + ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos); + /* + * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ - u64 (*read_uint) (struct cgroup *cgrp, struct cftype *cft); - ssize_t (*write) (struct cgroup *cgrp, struct cftype *cft, - struct file *file, - const char __user *buf, size_t nbytes, loff_t *ppos); + u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); + /* + * read_s64() is a signed version of read_u64() + */ + s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); + /* + * read_map() is used for defining a map of key/value + * pairs. It should call cb->fill(cb, key, value) for each + * entry. The key/value pairs (and their ordering) should not + * change between reboots. + */ + int (*read_map)(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb); + /* + * read_seq_string() is used for outputting a simple sequence + * using seqfile. + */ + int (*read_seq_string)(struct cgroup *cont, struct cftype *cft, + struct seq_file *m); + + ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + struct file *file, + const char __user *buf, size_t nbytes, loff_t *ppos); /* - * write_uint() is a shortcut for the common case of accepting + * write_u64() is a shortcut for the common case of accepting * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_uint) (struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); + /* + * write_s64() is a signed version of write_u64() + */ + int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); - int (*release) (struct inode *inode, struct file *file); + /* + * write_string() is passed a nul-terminated kernelspace + * buffer of maximum length determined by max_write_len. + * Returns 0 or -ve error code. + */ + int (*write_string)(struct cgroup *cgrp, struct cftype *cft, + const char *buffer); + /* + * trigger() callback can be used to get some kick from the + * userspace, when the actual string written is not important + * at all. The private field can be used to determine the + * kick type for multiplexing. + */ + int (*trigger)(struct cgroup *cgrp, unsigned int event); + + int (*release)(struct inode *inode, struct file *file); + + /* + * register_event() callback will be used to add new userspace + * waiter for changes related to the cftype. Implement it if + * you want to provide this functionality. Use eventfd_signal() + * on eventfd to send notification to userspace. + */ + int (*register_event)(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd, const char *args); + /* + * unregister_event() callback will be called when userspace + * closes the eventfd or on cgroup removing. + * This callback must be implemented, if you want provide + * notification functionality. + */ + int (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd); }; struct cgroup_scanner { @@ -214,15 +407,20 @@ struct cgroup_scanner { void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); struct ptr_heap *heap; + void *data; }; -/* Add a new file to the given cgroup directory. Should only be - * called by subsystems from within a populate() method */ +/* + * Add a new file to the given cgroup directory. Should only be + * called by subsystems from within a populate() method + */ int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype *cft); -/* Add a set of new files to the given cgroup directory. Should - * only be called by subsystems from within a populate() method */ +/* + * Add a set of new files to the given cgroup directory. Should + * only be called by subsystems from within a populate() method + */ int cgroup_add_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype cft[], @@ -234,38 +432,87 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -/* Return true if the cgroup is a descendant of the current cgroup */ -int cgroup_is_descendant(const struct cgroup *cgrp); +/* Return true if cgrp is a descendant of the task's cgroup */ +int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); + +/* + * When the subsys has to access css and may add permanent refcnt to css, + * it should take care of racy conditions with rmdir(). Following set of + * functions, is for stop/restart rmdir if necessary. + * Because these will call css_get/put, "css" should be alive css. + * + * cgroup_exclude_rmdir(); + * ...do some jobs which may access arbitrary empty cgroup + * cgroup_release_and_wakeup_rmdir(); + * + * When someone removes a cgroup while cgroup_exclude_rmdir() holds it, + * it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up. + */ + +void cgroup_exclude_rmdir(struct cgroup_subsys_state *css); +void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css); -/* Control Group subsystem type. See Documentation/cgroups.txt for details */ +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, struct cgroup *cgrp); - void (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); + int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); - int (*can_attach)(struct cgroup_subsys *ss, - struct cgroup *cgrp, struct task_struct *tsk); + int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup); + void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup); void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *tsk); + struct cgroup *old_cgrp, struct task_struct *tsk, + bool threadgroup); void (*fork)(struct cgroup_subsys *ss, struct task_struct *task); void (*exit)(struct cgroup_subsys *ss, struct task_struct *task); int (*populate)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*bind)(struct cgroup_subsys *ss, struct cgroup *root); + int subsys_id; int active; + int disabled; int early_init; + /* + * True if this subsys uses ID. ID is not available before cgroup_init() + * (not available in early_init time.) + */ + bool use_id; #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; - /* Protected by RCU */ - struct cgroupfs_root *root; + /* + * Protects sibling/children links of cgroups in this + * hierarchy, plus protects which hierarchy (or none) the + * subsystem is a part of (i.e. root/sibling). To avoid + * potential deadlocks, the following operations should not be + * undertaken while holding any hierarchy_mutex: + * + * - allocating memory + * - initiating hotplug events + */ + struct mutex hierarchy_mutex; + struct lock_class_key subsys_key; + /* + * Link to parent, and list entry in parent's children. + * Protected by this->hierarchy_mutex and cgroup_lock() + */ + struct cgroupfs_root *root; struct list_head sibling; + /* used when use_id == true */ + struct idr idr; + spinlock_t id_lock; - void *private; + /* should be defined only by modular subsystems */ + struct module *module; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; @@ -281,7 +528,10 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state( static inline struct cgroup_subsys_state *task_subsys_state( struct task_struct *task, int subsys_id) { - return rcu_dereference(task->cgroups->subsys[subsys_id]); + return rcu_dereference_check(task->cgroups->subsys[subsys_id], + rcu_read_lock_held() || + lockdep_is_held(&task->alloc_lock) || + cgroup_lock_is_held()); } static inline struct cgroup* task_cgroup(struct task_struct *task, @@ -290,7 +540,8 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss); +int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss, + char *nodename); /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { @@ -298,7 +549,8 @@ struct cgroup_iter { struct list_head *task; }; -/* To iterate across the tasks in a cgroup: +/* + * To iterate across the tasks in a cgroup: * * 1) call cgroup_iter_start to intialize an iterator * @@ -307,9 +559,10 @@ struct cgroup_iter { * * 3) call cgroup_iter_end() to destroy the iterator. * - * Or, call cgroup_scan_tasks() to iterate through every task in a cpuset. - * - cgroup_scan_tasks() holds the css_set_lock when calling the test_task() - * callback, but not while calling the process_task() callback. + * Or, call cgroup_scan_tasks() to iterate through every task in a + * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling + * the test_task() callback, but not while calling the process_task() + * callback. */ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); struct task_struct *cgroup_iter_next(struct cgroup *cgrp, @@ -318,11 +571,48 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); +/* + * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works + * if cgroup_subsys.use_id == true. It can be used for looking up and scanning. + * CSS ID is assigned at cgroup allocation (create) automatically + * and removed when subsys calls free_css_id() function. This is because + * the lifetime of cgroup_subsys_state is subsys's matter. + * + * Looking up and scanning function should be called under rcu_read_lock(). + * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls. + * But the css returned by this routine can be "not populated yet" or "being + * destroyed". The caller should check css and cgroup's status. + */ + +/* + * Typically Called at ->destroy(), or somewhere the subsys frees + * cgroup_subsys_state. + */ +void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); + +/* Find a cgroup_subsys_state which has given ID */ + +struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id); + +/* + * Get a cgroup whose id is greater than or equal to id under tree of root. + * Returning a cgroup_subsys_state or NULL. + */ +struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, + struct cgroup_subsys_state *root, int *foundid); + +/* Returns true if root is ancestor of cg */ +bool css_is_ancestor(struct cgroup_subsys_state *cg, + const struct cgroup_subsys_state *root); + +/* Get id and depth of css */ +unsigned short css_id(struct cgroup_subsys_state *css); +unsigned short css_depth(struct cgroup_subsys_state *css); + #else /* !CONFIG_CGROUPS */ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } -static inline void cgroup_init_smp(void) {} static inline void cgroup_fork(struct task_struct *p) {} static inline void cgroup_fork_callbacks(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {}