diff options
Diffstat (limited to 'include/linux/cgroup.h')
| -rw-r--r-- | include/linux/cgroup.h | 489 |
1 files changed, 282 insertions, 207 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5047355b9a0f..3561d305b1e0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -20,6 +20,7 @@ #include <linux/workqueue.h> #include <linux/xattr.h> #include <linux/fs.h> +#include <linux/percpu-refcount.h> #ifdef CONFIG_CGROUPS @@ -65,27 +66,25 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* - * The cgroup that this subsystem is attached to. Useful - * for subsystems that want to know about the cgroup - * hierarchy structure - */ + /* the cgroup that this css is attached to */ 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(). - */ + /* the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; - atomic_t refcnt; + /* the parent css */ + struct cgroup_subsys_state *parent; unsigned long flags; /* ID for this css, if possible */ struct css_id __rcu *id; - /* Used to put @cgroup->dentry on the last css_put() */ - struct work_struct dput_work; + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; }; /* bits in struct cgroup_subsys_state flags field */ @@ -94,56 +93,52 @@ 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) @@ -170,12 +165,15 @@ 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 + * idr allocated in-hierarchy ID. + * + * The ID of the root cgroup is always 0, and a new cgroup + * will be assigned with a smallest available ID. */ - atomic_t count; + int id; - int id; /* ida allocated in-hierarchy ID */ + /* the number of attached css's */ + int nr_css; /* * We link our 'sibling' struct into our parent's 'children'. @@ -189,6 +187,14 @@ struct cgroup { 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(). * @@ -202,18 +208,15 @@ struct cgroup { struct cgroup_name __rcu *name; /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; /* - * 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 @@ -229,9 +232,12 @@ struct cgroup { struct list_head pidlists; struct mutex pidlist_mutex; - /* For RCU-protected deletion */ + /* dummy css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state dummy_css; + + /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; - struct work_struct free_work; + struct work_struct destroy_work; /* List of events which userspace want to receive */ struct list_head event_list; @@ -269,18 +275,35 @@ enum { * * - 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. * - * The followings are planned changes. - * - * - release_agent will be disallowed once replacement notification - * mechanism is implemented. + * - 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 */ }; /* @@ -291,18 +314,12 @@ enum { struct cgroupfs_root { struct super_block *sb; - /* - * The bitmask of subsystems intended to be attached to this - * hierarchy - */ + /* The bitmask of subsystems attached to this hierarchy */ unsigned long subsys_mask; /* Unique id for this hierarchy. */ int hierarchy_id; - /* The bitmask of subsystems currently attached to this hierarchy */ - unsigned long actual_subsys_mask; - /* A list running through the attached subsystems */ struct list_head subsys_list; @@ -315,14 +332,11 @@ struct cgroupfs_root { /* A list running through the active hierarchies */ struct list_head root_list; - /* All cgroups on this root, cgroup_mutex protected */ - struct list_head allcg_list; - /* Hierarchy-specific flags */ unsigned long flags; /* IDs for cgroups in this hierarchy */ - struct ida cgroup_ida; + struct idr cgroup_idr; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; @@ -357,11 +371,10 @@ 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 @@ -394,9 +407,12 @@ 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 */ -#define CFTYPE_INSANE (1U << 2) /* don't create if sane_behavior */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ +}; #define MAX_CFTYPE_NAME 64 @@ -423,35 +439,41 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; + /* + * The subsys this file belongs to. Initialized automatically + * during registration. NULL for cgroup core files. + */ + struct cgroup_subsys *ss; + int (*open)(struct inode *inode, struct file *file); - ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*read)(struct cgroup_subsys_state *css, 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_u64)(struct cgroup *cgrp, struct cftype *cft); + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ - s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); + s64 (*read_s64)(struct cgroup_subsys_state *css, 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, + int (*read_map)(struct cgroup_subsys_state *css, 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); + int (*read_seq_string)(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m); - ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos); @@ -460,18 +482,20 @@ struct cftype { * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup_subsys_state *css, 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 (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); /* * 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, + int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer); /* * trigger() callback can be used to get some kick from the @@ -479,7 +503,7 @@ struct cftype { * at all. The private field can be used to determine the * kick type for multiplexing. */ - int (*trigger)(struct cgroup *cgrp, unsigned int event); + int (*trigger)(struct cgroup_subsys_state *css, unsigned int event); int (*release)(struct inode *inode, struct file *file); @@ -489,16 +513,18 @@ struct cftype { * 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); + int (*register_event)(struct cgroup_subsys_state *css, + 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. */ - void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd); + void (*unregister_event)(struct cgroup_subsys_state *css, + struct cftype *cft, + struct eventfd_ctx *eventfd); }; /* @@ -511,15 +537,6 @@ struct cftype_set { struct cftype *cfts; }; -struct cgroup_scanner { - struct cgroup *cg; - int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); - void (*process_task)(struct task_struct *p, - struct cgroup_scanner *scan); - struct ptr_heap *heap; - void *data; -}; - /* * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This * function can be called as long as @cgrp is accessible. @@ -536,12 +553,12 @@ static inline const char *cgroup_name(const struct cgroup *cgrp) } int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(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(struct task_struct *task, char *buf, size_t buflen); int cgroup_task_count(const struct cgroup *cgrp); @@ -552,20 +569,22 @@ int cgroup_task_count(const struct cgroup *cgrp); struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); -struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset); +struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, + int subsys_id); int cgroup_taskset_size(struct cgroup_taskset *tset); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor - * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all + * @skip_css: skip if task's css matches this, %NULL to iterate through all * @tset: taskset to iterate */ -#define cgroup_taskset_for_each(task, skip_cgrp, tset) \ +#define cgroup_taskset_for_each(task, skip_css, tset) \ for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) \ - if (!(skip_cgrp) || \ - cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp)) + if (!(skip_css) || \ + cgroup_taskset_cur_css((tset), \ + (skip_css)->ss->subsys_id) != (skip_css)) /* * Control Group subsystem type. @@ -573,18 +592,22 @@ int cgroup_taskset_size(struct cgroup_taskset *tset); */ struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp); - int (*css_online)(struct cgroup *cgrp); - void (*css_offline)(struct cgroup *cgrp); - void (*css_free)(struct cgroup *cgrp); - - int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, struct task_struct *task); - void (*bind)(struct cgroup *root); + void (*bind)(struct cgroup_subsys_state *root_css); int subsys_id; int disabled; @@ -640,95 +663,153 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS -static inline struct cgroup_subsys_state *cgroup_subsys_state( - struct cgroup *cgrp, int subsys_id) +/** + * css_parent - find the parent css + * @css: the target cgroup_subsys_state + * + * Return the parent css of @css. This function is guaranteed to return + * non-NULL parent as long as @css isn't the root. + */ +static inline +struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { - return cgrp->subsys[subsys_id]; + return css->parent; } -/* - * 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_subsys_state_check(task, subsys_id, __c) \ - rcu_dereference_check((task)->cgroups->subsys[(subsys_id)], \ - lockdep_is_held(&(task)->alloc_lock) || \ - lockdep_is_held(&cgroup_mutex) || (__c)) +#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_subsys_state_check(task, subsys_id, __c) \ - rcu_dereference((task)->cgroups->subsys[(subsys_id)]) +#define task_css_set_check(task, __c) \ + rcu_dereference((task)->cgroups) #endif -static inline struct cgroup_subsys_state * -task_subsys_state(struct task_struct *task, int subsys_id) +/** + * task_css_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_css_check(task, subsys_id, __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_subsys_state_check(task, subsys_id, false); + return task_css_set_check(task, false); } -static inline struct cgroup* task_cgroup(struct task_struct *task, - int subsys_id) +/** + * task_css - obtain css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * See task_css_check(). + */ +static inline struct cgroup_subsys_state *task_css(struct task_struct *task, + int subsys_id) +{ + return task_css_check(task, subsys_id, false); +} + +static inline struct cgroup *task_cgroup(struct task_struct *task, + int subsys_id) { - return task_subsys_state(task, subsys_id)->cgroup; + return task_css(task, subsys_id)->cgroup; } +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); + +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); + /** - * 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 + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Walk @cgroup's children. Must be called under rcu_read_lock(). A child - * cgroup which hasn't finished ->css_online() or already has finished + * Walk @parent's children. Must be called under rcu_read_lock(). A child + * css 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. * * If a subsystem synchronizes against the parent in its ->css_online() and - * before starting iterating, a cgroup which finished ->css_online() is + * before starting iterating, a css 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 css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) + +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); -struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, - struct cgroup *cgroup); -struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos); /** - * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk * - * Walk @cgroup's descendants. Must be called under rcu_read_lock(). A - * descendant cgroup which hasn't finished ->css_online() or already has + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). A + * descendant css 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. * * 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 css 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 * state updates of its ancestors. * - * my_online(@cgrp) + * my_online(@css) * { - * Lock @cgrp->parent and @cgrp; - * Inherit state from @cgrp->parent; + * Lock @css's parent and @css; + * Inherit state from the parent; * Unlock both. * } * - * my_update_state(@cgrp) + * my_update_state(@css) * { - * Lock @cgrp; - * Update @cgrp's state; - * Unlock @cgrp; - * - * cgroup_for_each_descendant_pre(@pos, @cgrp) { + * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos->parent; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } @@ -739,8 +820,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any cgroup after the latest update to its - * parent. + * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. @@ -748,53 +828,50 @@ struct cgroup *cgroup_rightmost_descendant(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); \ - pos = cgroup_next_descendant_pre((pos), (cgroup))) +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) -struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, - struct cgroup *cgroup); +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); /** - * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk * - * Similar to cgroup_for_each_descendant_pre() but performs post-order - * traversal instead. Note that the walk visibility guarantee described in - * pre-order walk doesn't apply the same to post-order walks. + * Similar to css_for_each_descendant_pre() but performs post-order + * traversal instead. @root is included in the iteration and the last + * node to be visited. Note that the walk visibility guarantee described + * in pre-order walk doesn't apply the same to post-order walks. */ -#define cgroup_for_each_descendant_post(pos, cgroup) \ - for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_post((pos), (cgroup))) - -/* A cgroup_iter should be treated as an opaque object */ -struct cgroup_iter { - struct list_head *cg_link; - struct list_head *task; +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) + +/* A css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys_state *origin_css; + struct list_head *cset_link; + struct list_head *task; }; -/* - * To iterate across the tasks in a cgroup: - * - * 1) call cgroup_iter_start to initialize an iterator - * - * 2) call cgroup_iter_next() to retrieve member tasks until it - * returns NULL or until you want to end the iteration - * - * 3) call cgroup_iter_end() to destroy the iterator. - * - * 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, - struct cgroup_iter *it); -void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); -int cgroup_scan_tasks(struct cgroup_scanner *scan); +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); + +int css_scan_tasks(struct cgroup_subsys_state *css, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); + int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); @@ -827,8 +904,8 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg, /* 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); +struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); #else /* !CONFIG_CGROUPS */ @@ -838,8 +915,6 @@ static inline void cgroup_fork(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) { |