X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fcgroup.h;h=8f78073d7caaa278017232112f0d3da05aa0d4c0;hb=3374cd1abd478f767aaedf2c21d109596ff0fe72;hp=665fa70e4094166c76b85176f0fbb3f5f6fae7c5;hpb=811158b147a503fbdf9773224004ffd32002d1fe;p=safe%2Fjmp%2Flinux-2.6

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 665fa70..8f78073 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -28,6 +28,7 @@ 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);
@@ -36,16 +37,24 @@ 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 <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 {
@@ -75,6 +84,12 @@ enum {
 	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:
@@ -86,7 +101,7 @@ 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)
@@ -117,11 +132,11 @@ static inline bool css_tryget(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 */
@@ -141,6 +156,38 @@ enum {
 	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 */
 
@@ -179,17 +226,19 @@ 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;
 };
 
 /*
@@ -227,9 +276,13 @@ 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;
 };
 
 /*
@@ -329,6 +382,23 @@ struct cftype {
 	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 {
@@ -366,6 +436,23 @@ int cgroup_task_count(const struct cgroup *cgrp);
 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/cgroups.txt for details
  */
@@ -375,10 +462,13 @@ struct cgroup_subsys {
 						  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,
@@ -420,6 +510,9 @@ struct cgroup_subsys {
 	/* 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;
@@ -435,7 +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,