Merge branch 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "cgroup file type addition / removal is updated so that file types are
  added and removed instead of individual files so that dynamic file
  type addition / removal can be implemented by cgroup and used by
  controllers.  blkio controller changes which will come through block
  tree are dependent on this.  Other changes include res_counter cleanup
  and disallowing kthread / PF_THREAD_BOUND threads to be attached to
  non-root cgroups.

  There's a reported bug with the file type addition / removal handling
  which can lead to oops on cgroup umount.  The issue is being looked
  into.  It shouldn't cause problems for most setups and isn't a
  security concern."

Fix up trivial conflict in Documentation/feature-removal-schedule.txt

* 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  res_counter: Account max_usage when calling res_counter_charge_nofail()
  res_counter: Merge res_counter_charge and res_counter_charge_nofail
  cgroups: disallow attaching kthreadd or PF_THREAD_BOUND threads
  cgroup: remove cgroup_subsys->populate()
  cgroup: get rid of populate for memcg
  cgroup: pass struct mem_cgroup instead of struct cgroup to socket memcg
  cgroup: make css->refcnt clearing on cgroup removal optional
  cgroup: use negative bias on css->refcnt to block css_tryget()
  cgroup: implement cgroup_rm_cftypes()
  cgroup: introduce struct cfent
  cgroup: relocate __d_cgrp() and __d_cft()
  cgroup: remove cgroup_add_file[s]()
  cgroup: convert memcg controller to the new cftype interface
  memcg: always create memsw files if CONFIG_CGROUP_MEM_RES_CTLR_SWAP
  cgroup: convert all non-memcg controllers to the new cftype interface
  cgroup: relocate cftype and cgroup_subsys definitions in controllers
  cgroup: merge cft_release_agent cftype array into the base files array
  cgroup: implement cgroup_add_cftypes() and friends
  cgroup: build list of all cgroups under a given cgroupfs_root
  cgroup: move cgroup_clear_directory() call out of cgroup_populate_dir()
  ...

4 files changed, 64 insertions, 35 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5a85b3415c1b..d3f5fba2c159 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 */
@@ -175,6 +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 */
@@ -191,6 +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
@@ -275,11 +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;
@@ -295,6 +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,
@@ -373,6 +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);
@@ -382,21 +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);
 
@@ -461,7 +472,6 @@ struct cgroup_subsys {
 	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);
 
@@ -474,6 +484,18 @@ 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;
 
@@ -500,6 +522,13 @@ struct cgroup_subsys {
 	struct idr idr;
 	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;
 };
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index da81af086eaf..fb201896a8b0 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -116,7 +116,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
  */
 
 int __must_check res_counter_charge_locked(struct res_counter *counter,
-		unsigned long val);
+					   unsigned long val, bool force);
 int __must_check res_counter_charge(struct res_counter *counter,
 		unsigned long val, struct res_counter **limit_fail_at);
 int __must_check res_counter_charge_nofail(struct res_counter *counter,
diff --git a/include/net/sock.h b/include/net/sock.h
index da931555e000..d89f0582b6b6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -70,16 +70,16 @@
 struct cgroup;
 struct cgroup_subsys;
 #ifdef CONFIG_NET
-int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp);
+int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg);
 #else
 static inline
-int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return 0;
 }
 static inline
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp)
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 {
 }
 #endif
@@ -914,9 +914,9 @@ struct proto {
 	 * This function has to setup any files the protocol want to
 	 * appear in the kmem cgroup filesystem.
 	 */
-	int			(*init_cgroup)(struct cgroup *cgrp,
+	int			(*init_cgroup)(struct mem_cgroup *memcg,
 					       struct cgroup_subsys *ss);
-	void			(*destroy_cgroup)(struct cgroup *cgrp);
+	void			(*destroy_cgroup)(struct mem_cgroup *memcg);
 	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
 #endif
 };
diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
index 48410ff25c9e..7df18bc43a97 100644
--- a/include/net/tcp_memcontrol.h
+++ b/include/net/tcp_memcontrol.h
@@ -12,8 +12,8 @@ struct tcp_memcontrol {
 };
 
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
-int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
-void tcp_destroy_cgroup(struct cgroup *cgrp);
+int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
+void tcp_destroy_cgroup(struct mem_cgroup *memcg);
 unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
 void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
 #endif /* _TCP_MEMCG_H */