1 files changed, 51 insertions, 7 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0008dee66514..b8ad1ea99586 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 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 */
@@ -220,6 +235,10 @@ struct cgroup {
 
         /* 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;
 };
 
 /*
@@ -257,7 +276,8 @@ 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];
 
@@ -362,6 +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 {
@@ -427,6 +464,8 @@ struct cgroup_subsys {
         void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
         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,
                         bool threadgroup);
@@ -471,6 +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;
@@ -486,7 +528,9 @@ 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() ||
+                                     cgroup_lock_is_held());
 }
 
 static inline struct cgroup* task_cgroup(struct task_struct *task,