1 files changed, 68 insertions, 84 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e9b602151ca..565c8034e6c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -16,6 +16,7 @@
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
 #include <linux/idr.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -76,12 +77,16 @@ struct cgroup_subsys_state {
 	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;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_ROOT, /* This CSS is the root of the subsystem */
 	CSS_REMOVED, /* This CSS is dead */
+	CSS_CLEAR_CSS_REFS,		/* @ss->__DEPRECATED_clear_css_refs */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -115,16 +120,12 @@ static inline bool css_is_removed(struct cgroup_subsys_state *css)
  * the css has been destroyed.
  */
 
+extern bool __css_tryget(struct cgroup_subsys_state *css);
 static inline bool css_tryget(struct cgroup_subsys_state *css)
 {
 	if (test_bit(CSS_ROOT, &css->flags))
 		return true;
-	while (!atomic_inc_not_zero(&css->refcnt)) {
-		if (test_bit(CSS_REMOVED, &css->flags))
-			return false;
-		cpu_relax();
-	}
-	return true;
+	return __css_tryget(css);
 }
 
 /*
@@ -132,11 +133,11 @@ static inline bool css_tryget(struct cgroup_subsys_state *css)
  * css_get() or css_tryget()
  */
 
-extern void __css_put(struct cgroup_subsys_state *css, int count);
+extern void __css_put(struct cgroup_subsys_state *css);
 static inline void css_put(struct cgroup_subsys_state *css)
 {
 	if (!test_bit(CSS_ROOT, &css->flags))
-		__css_put(css, 1);
+		__css_put(css);
 }
 
 /* bits in struct cgroup flags field */
@@ -160,38 +161,6 @@ enum {
 	CGRP_CLONE_CHILDREN,
 };
 
-/* 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 */
 
@@ -207,6 +176,7 @@ struct cgroup {
 	 */
 	struct list_head sibling;	/* my parent's children */
 	struct list_head children;	/* my children */
+	struct list_head files;		/* my files */
 
 	struct cgroup *parent;		/* my parent */
 	struct dentry __rcu *dentry;	/* cgroup fs entry, RCU protected */
@@ -223,6 +193,9 @@ struct cgroup {
 	 */
 	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 */
+
 	/*
 	 * Linked list running through all cgroups that can
 	 * potentially be reaped by the release agent. Protected by
@@ -307,11 +280,17 @@ struct cgroup_map_cb {
  *	- the 'cftype' of the file is file->f_dentry->d_fsdata
  */
 
-#define MAX_CFTYPE_NAME 64
+/* cftype->flags */
+#define CFTYPE_ONLY_ON_ROOT	(1U << 0)	/* only create on root cg */
+#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create onp root cg */
+
+#define MAX_CFTYPE_NAME		64
+
 struct cftype {
 	/*
 	 * By convention, the name should begin with the name of the
-	 * subsystem, followed by a period
+	 * subsystem, followed by a period.  Zero length string indicates
+	 * end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
 	int private;
@@ -327,6 +306,9 @@ struct cftype {
 	 */
 	size_t max_write_len;
 
+	/* CFTYPE_* flags */
+	unsigned int flags;
+
 	int (*open)(struct inode *inode, struct file *file);
 	ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
 			struct file *file,
@@ -405,6 +387,16 @@ struct cftype {
 			struct eventfd_ctx *eventfd);
 };
 
+/*
+ * cftype_sets describe cftypes belonging to a subsystem and are chained at
+ * cgroup_subsys->cftsets.  Each cftset points to an array of cftypes
+ * terminated by zero length name.
+ */
+struct cftype_set {
+	struct list_head		node;	/* chained at subsys->cftsets */
+	const struct cftype		*cfts;
+};
+
 struct cgroup_scanner {
 	struct cgroup *cg;
 	int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan);
@@ -414,21 +406,8 @@ struct cgroup_scanner {
 	void *data;
 };
 
-/*
- * Add a new file to the given cgroup directory. Should only be
- * called by subsystems from within a populate() method
- */
-int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
-		       const struct cftype *cft);
-
-/*
- * Add a set of new files to the given cgroup directory. Should
- * only be called by subsystems from within a populate() method
- */
-int cgroup_add_files(struct cgroup *cgrp,
-			struct cgroup_subsys *subsys,
-			const struct cftype cft[],
-			int count);
+int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
+int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
 
 int cgroup_is_removed(const struct cgroup *cgrp);
 
@@ -484,23 +463,18 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
  */
 
 struct cgroup_subsys {
-	struct cgroup_subsys_state *(*create)(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 cgroup_taskset *tset);
-	void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
-			      struct cgroup_taskset *tset);
-	void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		       struct cgroup_taskset *tset);
-	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-	void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
-			struct cgroup *old_cgrp, struct task_struct *task);
-	int (*populate)(struct cgroup_subsys *ss,
-			struct cgroup *cgrp);
-	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
-	void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
+	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
+	int (*pre_destroy)(struct cgroup *cgrp);
+	void (*destroy)(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);
+	void (*fork)(struct task_struct *task);
+	void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp,
+		     struct task_struct *task);
+	int (*populate)(struct cgroup_subsys *ss, struct cgroup *cgrp);
+	void (*post_clone)(struct cgroup *cgrp);
+	void (*bind)(struct cgroup *root);
 
 	int subsys_id;
 	int active;
@@ -511,6 +485,18 @@ struct cgroup_subsys {
 	 * (not available in early_init time.)
 	 */
 	bool use_id;
+
+	/*
+	 * If %true, cgroup removal will try to clear css refs by retrying
+	 * ss->pre_destroy() until there's no css ref left.  This behavior
+	 * is strictly for backward compatibility and will be removed as
+	 * soon as the current user (memcg) is updated.
+	 *
+	 * If %false, ss->pre_destroy() can't fail and cgroup removal won't
+	 * wait for css refs to drop to zero before proceeding.
+	 */
+	bool __DEPRECATED_clear_css_refs;
+
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
@@ -535,7 +521,14 @@ struct cgroup_subsys {
 	struct list_head sibling;
 	/* used when use_id == true */
 	struct idr idr;
-	rwlock_t id_lock;
+	spinlock_t id_lock;
+
+	/* list of cftype_sets */
+	struct list_head cftsets;
+
+	/* base cftypes, automatically [de]registered with subsys itself */
+	struct cftype *base_cftypes;
+	struct cftype_set base_cftset;
 
 	/* should be defined only by modular subsystems */
 	struct module *module;
@@ -602,11 +595,6 @@ 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 *);
 
-static inline int cgroup_attach_task_current_cg(struct task_struct *tsk)
-{
-	return cgroup_attach_task_all(current, tsk);
-}
-
 /*
  * 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.
@@ -669,10 +657,6 @@ static inline int cgroup_attach_task_all(struct task_struct *from,
 {
 	return 0;
 }
-static inline int cgroup_attach_task_current_cg(struct task_struct *t)
-{
-	return 0;
-}
 
 #endif /* !CONFIG_CGROUPS */