diff options
Diffstat (limited to 'include/linux/cgroup.h')
-rw-r--r-- | include/linux/cgroup.h | 371 |
1 files changed, 274 insertions, 97 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7d73905dcba2..297462b9f41a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -19,6 +19,8 @@ #include <linux/idr.h> #include <linux/workqueue.h> #include <linux/xattr.h> +#include <linux/fs.h> +#include <linux/percpu-refcount.h> #ifdef CONFIG_CGROUPS @@ -27,13 +29,10 @@ struct cgroup_subsys; struct inode; struct cgroup; struct css_id; +struct eventfd_ctx; extern int cgroup_init_early(void); extern int cgroup_init(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_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); @@ -42,16 +41,27 @@ extern int cgroupstats_build(struct cgroupstats *stats, extern int cgroup_load_subsys(struct cgroup_subsys *ss); extern void cgroup_unload_subsys(struct cgroup_subsys *ss); -extern const struct file_operations proc_cgroup_operations; +extern int proc_cgroup_show(struct seq_file *, void *); -/* Define the enumeration of all builtin cgroup subsystems */ +/* + * Define the enumeration of all cgroup subsystems. + * + * We define ids for builtin subsystems and then modular ones. + */ #define SUBSYS(_x) _x ## _subsys_id, -#define IS_SUBSYS_ENABLED(option) IS_ENABLED(option) enum cgroup_subsys_id { +#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option) +#include <linux/cgroup_subsys.h> +#undef IS_SUBSYS_ENABLED + CGROUP_BUILTIN_SUBSYS_COUNT, + + __CGROUP_SUBSYS_TEMP_PLACEHOLDER = CGROUP_BUILTIN_SUBSYS_COUNT - 1, + +#define IS_SUBSYS_ENABLED(option) IS_MODULE(option) #include <linux/cgroup_subsys.h> +#undef IS_SUBSYS_ENABLED CGROUP_SUBSYS_COUNT, }; -#undef IS_SUBSYS_ENABLED #undef SUBSYS /* Per-subsystem/per-cgroup state maintained by the system. */ @@ -63,13 +73,8 @@ struct cgroup_subsys_state { */ struct cgroup *cgroup; - /* - * State maintained by the cgroup system to allow subsystems - * to be "busy". Should be accessed via css_get(), - * css_tryget() and css_put(). - */ - - atomic_t refcnt; + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; unsigned long flags; /* ID for this css, if possible */ @@ -85,56 +90,52 @@ enum { CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ }; -/* 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 css; it can be used - * for a reference obtained via: - * - an existing ref-counted reference to the css - * - task->cgroups for a locked task +/** + * css_get - obtain a reference on the specified css + * @css: target css + * + * The caller must already have a reference. */ - static inline void css_get(struct cgroup_subsys_state *css) { /* We don't need to reference count the root state */ if (!(css->flags & CSS_ROOT)) - __css_get(css, 1); + percpu_ref_get(&css->refcnt); } -/* - * 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. +/** + * css_tryget - try to obtain a reference on the specified css + * @css: target css + * + * Obtain a reference on @css if it's alive. The caller naturally needs to + * ensure that @css is accessible but doesn't have to be holding a + * reference on it - IOW, RCU protected access is good enough for this + * function. Returns %true if a reference count was successfully obtained; + * %false otherwise. */ - -extern bool __css_tryget(struct cgroup_subsys_state *css); static inline bool css_tryget(struct cgroup_subsys_state *css) { if (css->flags & CSS_ROOT) return true; - return __css_tryget(css); + return percpu_ref_tryget(&css->refcnt); } -/* - * css_put() should be called to release a reference taken by - * css_get() or css_tryget() +/** + * css_put - put a css reference + * @css: target css + * + * Put a reference obtained via css_get() and css_tryget(). */ - -extern void __css_put(struct cgroup_subsys_state *css); static inline void css_put(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_ROOT)) - __css_put(css); + percpu_ref_put(&css->refcnt); } /* bits in struct cgroup flags field */ enum { /* Control Group is dead */ - CGRP_REMOVED, + CGRP_DEAD, /* * Control Group has previously had a child cgroup or a task, * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) @@ -148,17 +149,18 @@ enum { * specified at mount time and thus is implemented here. */ CGRP_CPUSET_CLONE_CHILDREN, + /* see the comment above CGRP_ROOT_SANE_BEHAVIOR for details */ + CGRP_SANE_BEHAVIOR, +}; + +struct cgroup_name { + struct rcu_head rcu_head; + char name[]; }; 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 - */ - atomic_t count; - int id; /* ida allocated in-hierarchy ID */ /* @@ -172,20 +174,37 @@ struct cgroup { struct cgroup *parent; /* my parent */ struct dentry *dentry; /* cgroup fs entry, RCU protected */ + /* + * Monotonically increasing unique serial number which defines a + * uniform order among all cgroups. It's guaranteed that all + * ->children lists are in the ascending order of ->serial_nr. + * It's used to allow interrupting and resuming iterations. + */ + u64 serial_nr; + + /* + * This is a copy of dentry->d_name, and it's needed because + * we can't use dentry->d_name in cgroup_path(). + * + * You must acquire rcu_read_lock() to access cgrp->name, and + * the only place that can change it is rename(), which is + * protected by parent dir's i_mutex. + * + * Normally you should use cgroup_name() wrapper rather than + * access it directly. + */ + struct cgroup_name __rcu *name; + /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; - struct cgroup *top_cgroup; /* - * List of cg_cgroup_links pointing at css_sets with - * tasks in this cgroup. Protected by css_set_lock + * List of cgrp_cset_links pointing at css_sets with tasks in this + * cgroup. Protected by css_set_lock. */ - struct list_head css_sets; - - struct list_head allcg_node; /* cgroupfs_root->allcg_list */ - struct list_head cft_q_node; /* used during cftype add/rm */ + struct list_head cset_links; /* * Linked list running through all cgroups that can @@ -201,8 +220,10 @@ struct cgroup { struct list_head pidlists; struct mutex pidlist_mutex; - /* For RCU-protected deletion */ + /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; + struct work_struct destroy_work; + atomic_t css_kill_cnt; /* List of events which userspace want to receive */ struct list_head event_list; @@ -212,6 +233,104 @@ struct cgroup { struct simple_xattrs xattrs; }; +#define MAX_CGROUP_ROOT_NAMELEN 64 + +/* cgroupfs_root->flags */ +enum { + /* + * Unfortunately, cgroup core and various controllers are riddled + * with idiosyncrasies and pointless options. The following flag, + * when set, will force sane behavior - some options are forced on, + * others are disallowed, and some controllers will change their + * hierarchical or other behaviors. + * + * The set of behaviors affected by this flag are still being + * determined and developed and the mount option for this flag is + * prefixed with __DEVEL__. The prefix will be dropped once we + * reach the point where all behaviors are compatible with the + * planned unified hierarchy, which will automatically turn on this + * flag. + * + * The followings are the behaviors currently affected this flag. + * + * - Mount options "noprefix" and "clone_children" are disallowed. + * Also, cgroupfs file cgroup.clone_children is not created. + * + * - When mounting an existing superblock, mount options should + * match. + * + * - Remount is disallowed. + * + * - rename(2) is disallowed. + * + * - "tasks" is removed. Everything should be at process + * granularity. Use "cgroup.procs" instead. + * + * - "release_agent" and "notify_on_release" are removed. + * Replacement notification mechanism will be implemented. + * + * - cpuset: tasks will be kept in empty cpusets when hotplug happens + * and take masks of ancestors with non-empty cpus/mems, instead of + * being moved to an ancestor. + * + * - cpuset: a task can be moved into an empty cpuset, and again it + * takes masks of ancestors. + * + * - memcg: use_hierarchy is on by default and the cgroup file for + * the flag is not created. + * + * - blkcg: blk-throttle becomes properly hierarchical. + */ + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), + + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ + + /* mount options live below bit 16 */ + CGRP_ROOT_OPTION_MASK = (1 << 16) - 1, + + CGRP_ROOT_SUBSYS_BOUND = (1 << 16), /* subsystems finished binding */ +}; + +/* + * A cgroupfs_root represents the root of a cgroup hierarchy, and may be + * associated with a superblock to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroupfs_root { + struct super_block *sb; + + /* The bitmask of subsystems attached to this hierarchy */ + unsigned long subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* A list running through the attached subsystems */ + struct list_head subsys_list; + + /* The root cgroup for this hierarchy */ + struct cgroup top_cgroup; + + /* Tracks how many cgroups are currently defined in hierarchy.*/ + int number_of_cgroups; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* Hierarchy-specific flags */ + unsigned long flags; + + /* IDs for cgroups in this hierarchy */ + struct ida cgroup_ida; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + /* * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct @@ -238,11 +357,10 @@ struct css_set { struct list_head tasks; /* - * List of cg_cgroup_link objects on link chains from - * cgroups referenced from this css_set. Protected by - * css_set_lock + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. */ - struct list_head cg_links; + struct list_head cgrp_links; /* * Set of subsystem states, one for each subsystem. This array @@ -275,8 +393,11 @@ struct cgroup_map_cb { */ /* cftype->flags */ -#define CFTYPE_ONLY_ON_ROOT (1U << 0) /* only create on root cg */ -#define CFTYPE_NOT_ON_ROOT (1U << 1) /* don't create on root cg */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cg */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cg */ + CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ +}; #define MAX_CFTYPE_NAME 64 @@ -303,9 +424,6 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; - /* file xattrs */ - struct simple_xattrs xattrs; - int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -325,13 +443,13 @@ struct cftype { * entry. The key/value pairs (and their ordering) should not * change between reboots. */ - int (*read_map)(struct cgroup *cont, struct cftype *cft, + int (*read_map)(struct cgroup *cgrp, 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, + int (*read_seq_string)(struct cgroup *cgrp, struct cftype *cft, struct seq_file *m); ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, @@ -403,18 +521,32 @@ struct cgroup_scanner { void *data; }; +/* + * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This + * function can be called as long as @cgrp is accessible. + */ +static inline bool cgroup_sane_behavior(const struct cgroup *cgrp) +{ + return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR; +} + +/* Caller should hold rcu_read_lock() */ +static inline const char *cgroup_name(const struct cgroup *cgrp) +{ + return rcu_dereference(cgrp->name)->name; +} + int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_is_removed(const struct cgroup *cgrp); +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); +int task_cgroup_path_from_hierarchy(struct task_struct *task, int hierarchy_id, + char *buf, size_t buflen); int cgroup_task_count(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); - /* * Control Group taskset, used to pass around set of tasks to cgroup_subsys * methods. @@ -457,7 +589,6 @@ struct cgroup_subsys { void (*bind)(struct cgroup *root); int subsys_id; - int active; int disabled; int early_init; /* @@ -517,16 +648,60 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state( return cgrp->subsys[subsys_id]; } -/* - * function to get the cgroup_subsys_state which allows for extra - * rcu_dereference_check() conditions, such as locks used during the - * cgroup_subsys::attach() methods. +/** + * task_css_set_check - obtain a task's css_set with extra access conditions + * @task: the task to obtain css_set for + * @__c: extra condition expression to be passed to rcu_dereference_check() + * + * A task's css_set is RCU protected, initialized and exited while holding + * task_lock(), and can only be modified while holding both cgroup_mutex + * and task_lock() while the task is alive. This macro verifies that the + * caller is inside proper critical section and returns @task's css_set. + * + * The caller can also specify additional allowed conditions via @__c, such + * as locks used during the cgroup_subsys::attach() methods. + */ +#ifdef CONFIG_PROVE_RCU +extern struct mutex cgroup_mutex; +#define task_css_set_check(task, __c) \ + rcu_dereference_check((task)->cgroups, \ + lockdep_is_held(&(task)->alloc_lock) || \ + lockdep_is_held(&cgroup_mutex) || (__c)) +#else +#define task_css_set_check(task, __c) \ + rcu_dereference((task)->cgroups) +#endif + +/** + * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds + * @task: the target task + * @subsys_id: the target subsystem ID + * @__c: extra condition expression to be passed to rcu_dereference_check() + * + * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The + * synchronization rules are the same as task_css_set_check(). */ #define task_subsys_state_check(task, subsys_id, __c) \ - rcu_dereference_check(task->cgroups->subsys[subsys_id], \ - lockdep_is_held(&task->alloc_lock) || \ - cgroup_lock_is_held() || (__c)) + task_css_set_check((task), (__c))->subsys[(subsys_id)] +/** + * task_css_set - obtain a task's css_set + * @task: the task to obtain css_set for + * + * See task_css_set_check(). + */ +static inline struct css_set *task_css_set(struct task_struct *task) +{ + return task_css_set_check(task, false); +} + +/** + * task_subsys_state - obtain css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * See task_subsys_state_check(). + */ static inline struct cgroup_subsys_state * task_subsys_state(struct task_struct *task, int subsys_id) { @@ -539,12 +714,14 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } +struct cgroup *cgroup_next_sibling(struct cgroup *pos); + /** * cgroup_for_each_child - iterate through children of a cgroup * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose children to walk + * @cgrp: cgroup whose children to walk * - * Walk @cgroup's children. Must be called under rcu_read_lock(). A child + * Walk @cgrp's children. Must be called under rcu_read_lock(). A child * cgroup which hasn't finished ->css_online() or already has finished * ->css_offline() may show up during traversal and it's each subsystem's * responsibility to verify that each @pos is alive. @@ -552,12 +729,19 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, a cgroup which finished ->css_online() is * guaranteed to be visible in the future iterations. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_child(pos, cgroup) \ - list_for_each_entry_rcu(pos, &(cgroup)->children, sibling) +#define cgroup_for_each_child(pos, cgrp) \ + for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ + struct cgroup, sibling); \ + (pos); (pos) = cgroup_next_sibling((pos))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); +struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); /** * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants @@ -571,7 +755,7 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_offline() is + * iteration, any descendant cgroup which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape @@ -612,6 +796,10 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. */ #define cgroup_for_each_descendant_pre(pos, cgroup) \ for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos); \ @@ -635,7 +823,7 @@ struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { - struct list_head *cg_link; + struct list_head *cset_link; struct list_head *task; }; @@ -659,8 +847,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, struct cgroup_iter *it); 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 *); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works @@ -685,20 +873,12 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); 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); struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); #else /* !CONFIG_CGROUPS */ @@ -706,12 +886,9 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } 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) {} static inline void cgroup_exit(struct task_struct *p, int callbacks) {} -static inline void cgroup_lock(void) {} -static inline void cgroup_unlock(void) {} static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { |