#include <linux/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
+#include <linux/idr.h>
#ifdef CONFIG_CGROUPS
struct cgroup_subsys;
struct inode;
struct cgroup;
+struct css_id;
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_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 <linux/cgroup_subsys.h>
- 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 {
atomic_t refcnt;
unsigned long flags;
+ /* ID for this css, if possible */
+ struct css_id *id;
};
/* bits in struct cgroup_subsys_state flags field */
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 css; it can be used
* for a reference obtained via:
{
/* 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)
* 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 */
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 {
*/
struct list_head release_list;
- /* pids_mutex protects the fields below */
- struct rw_semaphore pids_mutex;
- /* Array of process ids in the cgroup */
- pid_t *tasks_pids;
- /* How many files are using the current tasks_pids array */
- int pids_use_count;
- /* Length of the current tasks_pids array */
- int pids_length;
+ /*
+ * 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;
};
/*
/*
* 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;
};
/*
*/
char name[MAX_CFTYPE_NAME];
int private;
+ /*
+ * 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
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 {
void (*process_task)(struct task_struct *p,
struct cgroup_scanner *scan);
struct ptr_heap *heap;
+ void *data;
};
/*
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);
-/* Control Group subsystem type. See Documentation/cgroups.txt for details */
+/*
+ * 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/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,
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;
*/
struct cgroupfs_root *root;
struct list_head sibling;
+ /* used when use_id == true */
+ struct idr idr;
+ spinlock_t id_lock;
+
+ /* should be defined only by modular subsystems */
+ struct module *module;
};
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
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,
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; }
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff