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()
  ...

Documentation/cgroups/resource_counter.txt

@@ -77,11 +77,11 @@ to work with it.
 	where the charging failed.
 
  d. int res_counter_charge_locked
-			(struct res_counter *rc, unsigned long val)
+			(struct res_counter *rc, unsigned long val, bool force)
 
 	The same as res_counter_charge(), but it must not acquire/release the
 	res_counter->lock internally (it must be called with res_counter->lock
-	held).
+	held). The force parameter indicates whether we can bypass the limit.
 
  e. void res_counter_uncharge[_locked]
 			(struct res_counter *rc, unsigned long val)

Documentation/feature-removal-schedule.txt

@@ -556,3 +556,14 @@ Why:	The V4L2_CID_VCENTER, V4L2_CID_HCENTER controls have been deprecated
 	There are newer controls (V4L2_CID_PAN*, V4L2_CID_TILT*) that provide
 	similar	functionality.
 Who:	Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+
+----------------------------
+
+What:	cgroup option updates via remount
+When:	March 2013
+Why:	Remount currently allows changing bound subsystems and
+	release_agent.  Rebinding is hardly useful as it only works
+	when the hierarchy is empty and release_agent itself should be
+	replaced with conventional fsnotify.
+
+----------------------------

block/blk-cgroup.c

@@ -28,34 +28,12 @@ static LIST_HEAD(blkio_list);
 struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
-static struct cgroup_subsys_state *blkiocg_create(struct cgroup *);
-static int blkiocg_can_attach(struct cgroup *, struct cgroup_taskset *);
-static void blkiocg_attach(struct cgroup *, struct cgroup_taskset *);
-static void blkiocg_destroy(struct cgroup *);
-static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
-
 /* for encoding cft->private value on file */
 #define BLKIOFILE_PRIVATE(x, val)	(((x) << 16) | (val))
 /* What policy owns the file, proportional or throttle */
 #define BLKIOFILE_POLICY(val)		(((val) >> 16) & 0xffff)
 #define BLKIOFILE_ATTR(val)		((val) & 0xffff)
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
-	.create = blkiocg_create,
-	.can_attach = blkiocg_can_attach,
-	.attach = blkiocg_attach,
-	.destroy = blkiocg_destroy,
-	.populate = blkiocg_populate,
-#ifdef CONFIG_BLK_CGROUP
-	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
-	.subsys_id = blkio_subsys_id,
-#endif
-	.use_id = 1,
-	.module = THIS_MODULE,
-};
-EXPORT_SYMBOL_GPL(blkio_subsys);
-
 static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
 					    struct blkio_policy_node *pn)
 {
@@ -1537,14 +1515,9 @@ struct cftype blkio_files[] = {
 		.read_map = blkiocg_file_read_map,
 	},
 #endif
+	{ }	/* terminate */
 };
 
-static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
-{
-	return cgroup_add_files(cgroup, subsys, blkio_files,
-				ARRAY_SIZE(blkio_files));
-}
-
 static void blkiocg_destroy(struct cgroup *cgroup)
 {
 	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
@@ -1658,6 +1631,22 @@ static void blkiocg_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 	}
 }
 
+struct cgroup_subsys blkio_subsys = {
+	.name = "blkio",
+	.create = blkiocg_create,
+	.can_attach = blkiocg_can_attach,
+	.attach = blkiocg_attach,
+	.destroy = blkiocg_destroy,
+#ifdef CONFIG_BLK_CGROUP
+	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
+	.subsys_id = blkio_subsys_id,
+#endif
+	.base_cftypes = blkio_files,
+	.use_id = 1,
+	.module = THIS_MODULE,
+};
+EXPORT_SYMBOL_GPL(blkio_subsys);
+
 void blkio_policy_register(struct blkio_policy_type *blkiop)
 {
 	spin_lock(&blkio_list_lock);

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;
 };

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,

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
 };

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 */

kernel/cgroup_freezer.c

@@ -358,24 +358,19 @@ static int freezer_write(struct cgroup *cgroup,
 static struct cftype files[] = {
 	{
 		.name = "state",
+		.flags = CFTYPE_NOT_ON_ROOT,
 		.read_seq_string = freezer_read,
 		.write_string = freezer_write,
 	},
+	{ }	/* terminate */
 };
 
-static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup)
-{
-	if (!cgroup->parent)
-		return 0;
-	return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files));
-}
-
 struct cgroup_subsys freezer_subsys = {
 	.name		= "freezer",
 	.create		= freezer_create,
 	.destroy	= freezer_destroy,
-	.populate	= freezer_populate,
 	.subsys_id	= freezer_subsys_id,
 	.can_attach	= freezer_can_attach,
 	.fork		= freezer_fork,
+	.base_cftypes	= files,
 };

kernel/cpuset.c

@@ -1765,28 +1765,17 @@ static struct cftype files[] = {
 		.write_u64 = cpuset_write_u64,
 		.private = FILE_SPREAD_SLAB,
 	},
-};
-
-static struct cftype cft_memory_pressure_enabled = {
-	.name = "memory_pressure_enabled",
-	.read_u64 = cpuset_read_u64,
-	.write_u64 = cpuset_write_u64,
-	.private = FILE_MEMORY_PRESSURE_ENABLED,
-};
 
-static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-	int err;
+	{
+		.name = "memory_pressure_enabled",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEMORY_PRESSURE_ENABLED,
+	},
 
-	err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-	if (err)
-		return err;
-	/* memory_pressure_enabled is in root cpuset only */
-	if (!cont->parent)
-		err = cgroup_add_file(cont, ss,
-				      &cft_memory_pressure_enabled);
-	return err;
-}
+	{ }	/* terminate */
+};
 
 /*
  * post_clone() is called during cgroup_create() when the
@@ -1887,9 +1876,9 @@ struct cgroup_subsys cpuset_subsys = {
 	.destroy = cpuset_destroy,
 	.can_attach = cpuset_can_attach,
 	.attach = cpuset_attach,
-	.populate = cpuset_populate,
 	.post_clone = cpuset_post_clone,
 	.subsys_id = cpuset_subsys_id,
+	.base_cftypes = files,
 	.early_init = 1,
 };
 

kernel/res_counter.c

@@ -22,75 +22,70 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 	counter->parent = parent;
 }
 
-int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
+int res_counter_charge_locked(struct res_counter *counter, unsigned long val,
+			      bool force)
 {
+	int ret = 0;
+
 	if (counter->usage + val > counter->limit) {
 		counter->failcnt++;
-		return -ENOMEM;
+		ret = -ENOMEM;
+		if (!force)
+			return ret;
 	}
 
 	counter->usage += val;
 	if (counter->usage > counter->max_usage)
 		counter->max_usage = counter->usage;
-	return 0;
+	return ret;
 }
 
-int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
+static int __res_counter_charge(struct res_counter *counter, unsigned long val,
+				struct res_counter **limit_fail_at, bool force)
 {
-	int ret;
+	int ret, r;
 	unsigned long flags;
 	struct res_counter *c, *u;
 
+	r = ret = 0;
 	*limit_fail_at = NULL;
 	local_irq_save(flags);
 	for (c = counter; c != NULL; c = c->parent) {
 		spin_lock(&c->lock);
-		ret = res_counter_charge_locked(c, val);
+		r = res_counter_charge_locked(c, val, force);
 		spin_unlock(&c->lock);
-		if (ret < 0) {
+		if (r < 0 && !ret) {
+			ret = r;
 			*limit_fail_at = c;
-			goto undo;
+			if (!force)
+				break;
 		}
 	}
-	ret = 0;
-	goto done;
-undo:
-	for (u = counter; u != c; u = u->parent) {
-		spin_lock(&u->lock);
-		res_counter_uncharge_locked(u, val);
-		spin_unlock(&u->lock);
+
+	if (ret < 0 && !force) {
+		for (u = counter; u != c; u = u->parent) {
+			spin_lock(&u->lock);
+			res_counter_uncharge_locked(u, val);
+			spin_unlock(&u->lock);
+		}
 	}
-done:
 	local_irq_restore(flags);
+
 	return ret;
 }
 
+int res_counter_charge(struct res_counter *counter, unsigned long val,
+			struct res_counter **limit_fail_at)
+{
+	return __res_counter_charge(counter, val, limit_fail_at, false);
+}
+
 int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 			      struct res_counter **limit_fail_at)
 {
-	int ret, r;
-	unsigned long flags;
-	struct res_counter *c;
-
-	r = ret = 0;
-	*limit_fail_at = NULL;
-	local_irq_save(flags);
-	for (c = counter; c != NULL; c = c->parent) {
-		spin_lock(&c->lock);
-		r = res_counter_charge_locked(c, val);
-		if (r)
-			c->usage += val;
-		spin_unlock(&c->lock);
-		if (r < 0 && ret == 0) {
-			*limit_fail_at = c;
-			ret = r;
-		}
-	}
-	local_irq_restore(flags);
-
-	return ret;
+	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
+
 void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 {
 	if (WARN_ON(counter->usage < val))

kernel/sched/core.c

@@ -7985,13 +7985,9 @@ static struct cftype cpu_files[] = {
 		.write_u64 = cpu_rt_period_write_uint,
 	},
 #endif
+	{ }	/* terminate */
 };
 
-static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-	return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
-}
-
 struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
 	.create		= cpu_cgroup_create,
@@ -7999,8 +7995,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
-	.populate	= cpu_cgroup_populate,
 	.subsys_id	= cpu_cgroup_subsys_id,
+	.base_cftypes	= cpu_files,
 	.early_init	= 1,
 };
 
@@ -8185,13 +8181,9 @@ static struct cftype files[] = {
 		.name = "stat",
 		.read_map = cpuacct_stats_show,
 	},
+	{ }	/* terminate */
 };
 
-static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
-{
-	return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files));
-}
-
 /*
  * charge this task's execution time to its accounting group.
  *
@@ -8223,7 +8215,7 @@ struct cgroup_subsys cpuacct_subsys = {
 	.name = "cpuacct",
 	.create = cpuacct_create,
 	.destroy = cpuacct_destroy,
-	.populate = cpuacct_populate,
 	.subsys_id = cpuacct_subsys_id,
+	.base_cftypes = files,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */

mm/memcontrol.c

@@ -3873,14 +3873,21 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	return val << PAGE_SHIFT;
 }
 
-static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
+static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
+			       struct file *file, char __user *buf,
+			       size_t nbytes, loff_t *ppos)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	char str[64];
 	u64 val;
-	int type, name;
+	int type, name, len;
 
 	type = MEMFILE_TYPE(cft->private);
 	name = MEMFILE_ATTR(cft->private);
+
+	if (!do_swap_account && type == _MEMSWAP)
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case _MEM:
 		if (name == RES_USAGE)
@@ -3897,7 +3904,9 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 	default:
 		BUG();
 	}
-	return val;
+
+	len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
+	return simple_read_from_buffer(buf, nbytes, ppos, str, len);
 }
 /*
  * The user of this function is...
@@ -3913,6 +3922,10 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 
 	type = MEMFILE_TYPE(cft->private);
 	name = MEMFILE_ATTR(cft->private);
+
+	if (!do_swap_account && type == _MEMSWAP)
+		return -EOPNOTSUPP;
+
 	switch (name) {
 	case RES_LIMIT:
 		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
@@ -3978,12 +3991,15 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
 
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	int type, name;
 
-	memcg = mem_cgroup_from_cont(cont);
 	type = MEMFILE_TYPE(event);
 	name = MEMFILE_ATTR(event);
+
+	if (!do_swap_account && type == _MEMSWAP)
+		return -EOPNOTSUPP;
+
 	switch (name) {
 	case RES_MAX_USAGE:
 		if (type == _MEM)
@@ -4624,29 +4640,22 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
-static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
-	/*
-	 * Part of this would be better living in a separate allocation
-	 * function, leaving us with just the cgroup tree population work.
-	 * We, however, depend on state such as network's proto_list that
-	 * is only initialized after cgroup creation. I found the less
-	 * cumbersome way to deal with it to defer it all to populate time
-	 */
-	return mem_cgroup_sockets_init(cont, ss);
+	return mem_cgroup_sockets_init(memcg, ss);
 };
 
-static void kmem_cgroup_destroy(struct cgroup *cont)
+static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
 {
-	mem_cgroup_sockets_destroy(cont);
+	mem_cgroup_sockets_destroy(memcg);
 }
 #else
-static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return 0;
 }
 
-static void kmem_cgroup_destroy(struct cgroup *cont)
+static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
 {
 }
 #endif
@@ -4655,7 +4664,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 		.register_event = mem_cgroup_usage_register_event,
 		.unregister_event = mem_cgroup_usage_unregister_event,
 	},
@@ -4663,25 +4672,25 @@ static struct cftype mem_cgroup_files[] = {
 		.name = "max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
 		.trigger = mem_cgroup_reset,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
 		.write_string = mem_cgroup_write,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "soft_limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
 		.write_string = mem_cgroup_write,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "failcnt",
 		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
 		.trigger = mem_cgroup_reset,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "stat",
@@ -4721,14 +4730,11 @@ static struct cftype mem_cgroup_files[] = {
 		.mode = S_IRUGO,
 	},
 #endif
-};
-
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
-static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 		.register_event = mem_cgroup_usage_register_event,
 		.unregister_event = mem_cgroup_usage_unregister_event,
 	},
@@ -4736,35 +4742,23 @@ static struct cftype memsw_cgroup_files[] = {
 		.name = "memsw.max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
 		.trigger = mem_cgroup_reset,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "memsw.limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
 		.write_string = mem_cgroup_write,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
 	{
 		.name = "memsw.failcnt",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
 		.trigger = mem_cgroup_reset,
-		.read_u64 = mem_cgroup_read,
+		.read = mem_cgroup_read,
 	},
-};
-
-static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
-{
-	if (!do_swap_account)
-		return 0;
-	return cgroup_add_files(cont, ss, memsw_cgroup_files,
-				ARRAY_SIZE(memsw_cgroup_files));
-};
-#else
-static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
-{
-	return 0;
-}
 #endif
+	{ },	/* terminate */
+};
 
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
@@ -5016,6 +5010,17 @@ mem_cgroup_create(struct cgroup *cont)
 	memcg->move_charge_at_immigrate = 0;
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
+
+	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	if (error) {
+		/*
+		 * We call put now because our (and parent's) refcnts
+		 * are already in place. mem_cgroup_put() will internally
+		 * call __mem_cgroup_free, so return directly
+		 */
+		mem_cgroup_put(memcg);
+		return ERR_PTR(error);
+	}
 	return &memcg->css;
 free_out:
 	__mem_cgroup_free(memcg);
@@ -5033,28 +5038,11 @@ static void mem_cgroup_destroy(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	kmem_cgroup_destroy(cont);
+	kmem_cgroup_destroy(memcg);
 
 	mem_cgroup_put(memcg);
 }
 
-static int mem_cgroup_populate(struct cgroup_subsys *ss,
-				struct cgroup *cont)
-{
-	int ret;
-
-	ret = cgroup_add_files(cont, ss, mem_cgroup_files,
-				ARRAY_SIZE(mem_cgroup_files));
-
-	if (!ret)
-		ret = register_memsw_files(cont, ss);
-
-	if (!ret)
-		ret = register_kmem_files(cont, ss);
-
-	return ret;
-}
-
 #ifdef CONFIG_MMU
 /* Handlers for move charge at task migration. */
 #define PRECHARGE_COUNT_AT_ONCE	256
@@ -5638,12 +5626,13 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.create = mem_cgroup_create,
 	.pre_destroy = mem_cgroup_pre_destroy,
 	.destroy = mem_cgroup_destroy,
-	.populate = mem_cgroup_populate,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
+	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
 	.use_id = 1,
+	.__DEPRECATED_clear_css_refs = true,
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP

net/core/netprio_cgroup.c

@@ -25,21 +25,6 @@
 #include <net/sock.h>
 #include <net/netprio_cgroup.h>
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp);
-static void cgrp_destroy(struct cgroup *cgrp);
-static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp);
-
-struct cgroup_subsys net_prio_subsys = {
-	.name		= "net_prio",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
-	.populate	= cgrp_populate,
-#ifdef CONFIG_NETPRIO_CGROUP
-	.subsys_id	= net_prio_subsys_id,
-#endif
-	.module		= THIS_MODULE
-};
-
 #define PRIOIDX_SZ 128
 
 static unsigned long prioidx_map[PRIOIDX_SZ];
@@ -259,12 +244,19 @@ static struct cftype ss_files[] = {
 		.read_map = read_priomap,
 		.write_string = write_priomap,
 	},
+	{ }	/* terminate */
 };
 
-static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
-{
-	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
-}
+struct cgroup_subsys net_prio_subsys = {
+	.name		= "net_prio",
+	.create		= cgrp_create,
+	.destroy	= cgrp_destroy,
+#ifdef CONFIG_NETPRIO_CGROUP
+	.subsys_id	= net_prio_subsys_id,
+#endif
+	.base_cftypes	= ss_files,
+	.module		= THIS_MODULE
+};
 
 static int netprio_device_event(struct notifier_block *unused,
 				unsigned long event, void *ptr)

net/core/sock.c

@@ -143,7 +143,7 @@ static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
-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)
 {
 	struct proto *proto;
 	int ret = 0;
@@ -151,7 +151,7 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	mutex_lock(&proto_list_mutex);
 	list_for_each_entry(proto, &proto_list, node) {
 		if (proto->init_cgroup) {
-			ret = proto->init_cgroup(cgrp, ss);
+			ret = proto->init_cgroup(memcg, ss);
 			if (ret)
 				goto out;
 		}
@@ -162,19 +162,19 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
 out:
 	list_for_each_entry_continue_reverse(proto, &proto_list, node)
 		if (proto->destroy_cgroup)
-			proto->destroy_cgroup(cgrp);
+			proto->destroy_cgroup(memcg);
 	mutex_unlock(&proto_list_mutex);
 	return ret;
 }
 
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp)
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 {
 	struct proto *proto;
 
 	mutex_lock(&proto_list_mutex);
 	list_for_each_entry_reverse(proto, &proto_list, node)
 		if (proto->destroy_cgroup)
-			proto->destroy_cgroup(cgrp);
+			proto->destroy_cgroup(memcg);
 	mutex_unlock(&proto_list_mutex);
 }
 #endif

net/ipv4/tcp_memcontrol.c

@@ -6,37 +6,6 @@
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
-static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
-static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
-			    const char *buffer);
-static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event);
-
-static struct cftype tcp_files[] = {
-	{
-		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_LIMIT,
-	},
-	{
-		.name = "kmem.tcp.usage_in_bytes",
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_USAGE,
-	},
-	{
-		.name = "kmem.tcp.failcnt",
-		.private = RES_FAILCNT,
-		.trigger = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-	{
-		.name = "kmem.tcp.max_usage_in_bytes",
-		.private = RES_MAX_USAGE,
-		.trigger = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-};
-
 static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
 {
 	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
@@ -49,7 +18,7 @@ static void memcg_tcp_enter_memory_pressure(struct sock *sk)
 }
 EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
 
-int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
 	 * The root cgroup does not use res_counters, but rather,
@@ -59,13 +28,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	struct res_counter *res_parent = NULL;
 	struct cg_proto *cg_proto, *parent_cg;
 	struct tcp_memcontrol *tcp;
-	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 	struct net *net = current->nsproxy->net_ns;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		goto create_files;
+		return 0;
 
 	tcp = tcp_from_cgproto(cg_proto);
 
@@ -88,15 +56,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
 	cg_proto->memcg = memcg;
 
-create_files:
-	return cgroup_add_files(cgrp, ss, tcp_files,
-				ARRAY_SIZE(tcp_files));
+	return 0;
 }
 EXPORT_SYMBOL(tcp_init_cgroup);
 
-void tcp_destroy_cgroup(struct cgroup *cgrp)
+void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct cg_proto *cg_proto;
 	struct tcp_memcontrol *tcp;
 	u64 val;
@@ -270,3 +235,37 @@ void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
 
 	tcp->tcp_prot_mem[idx] = val;
 }
+
+static struct cftype tcp_files[] = {
+	{
+		.name = "kmem.tcp.limit_in_bytes",
+		.write_string = tcp_cgroup_write,
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_LIMIT,
+	},
+	{
+		.name = "kmem.tcp.usage_in_bytes",
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_USAGE,
+	},
+	{
+		.name = "kmem.tcp.failcnt",
+		.private = RES_FAILCNT,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+	{
+		.name = "kmem.tcp.max_usage_in_bytes",
+		.private = RES_MAX_USAGE,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+	{ }	/* terminate */
+};
+
+static int __init tcp_memcontrol_init(void)
+{
+	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files));
+	return 0;
+}
+__initcall(tcp_memcontrol_init);

net/sched/cls_cgroup.c

@@ -22,22 +22,6 @@
 #include <net/sock.h>
 #include <net/cls_cgroup.h>
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp);
-static void cgrp_destroy(struct cgroup *cgrp);
-static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp);
-
-struct cgroup_subsys net_cls_subsys = {
-	.name		= "net_cls",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
-	.populate	= cgrp_populate,
-#ifdef CONFIG_NET_CLS_CGROUP
-	.subsys_id	= net_cls_subsys_id,
-#endif
-	.module		= THIS_MODULE,
-};
-
-
 static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp)
 {
 	return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id),
@@ -86,12 +70,19 @@ static struct cftype ss_files[] = {
 		.read_u64 = read_classid,
 		.write_u64 = write_classid,
 	},
+	{ }	/* terminate */
 };
 
-static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
-{
-	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
-}
+struct cgroup_subsys net_cls_subsys = {
+	.name		= "net_cls",
+	.create		= cgrp_create,
+	.destroy	= cgrp_destroy,
+#ifdef CONFIG_NET_CLS_CGROUP
+	.subsys_id	= net_cls_subsys_id,
+#endif
+	.base_cftypes	= ss_files,
+	.module		= THIS_MODULE,
+};
 
 struct cls_cgroup_head {
 	u32			handle;

security/device_cgroup.c

@@ -447,22 +447,16 @@ static struct cftype dev_cgroup_files[] = {
 		.read_seq_string = devcgroup_seq_read,
 		.private = DEVCG_LIST,
 	},
+	{ }	/* terminate */
 };
 
-static int devcgroup_populate(struct cgroup_subsys *ss,
-				struct cgroup *cgroup)
-{
-	return cgroup_add_files(cgroup, ss, dev_cgroup_files,
-					ARRAY_SIZE(dev_cgroup_files));
-}
-
 struct cgroup_subsys devices_subsys = {
 	.name = "devices",
 	.can_attach = devcgroup_can_attach,
 	.create = devcgroup_create,
 	.destroy = devcgroup_destroy,
-	.populate = devcgroup_populate,
 	.subsys_id = devices_subsys_id,
+	.base_cftypes = dev_cgroup_files,
 };
 
 int __devcgroup_inode_permission(struct inode *inode, int mask)