Merge branch 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "The cgroup core saw several significant updates this cycle:

   - percpu_rwsem for threadgroup locking is reinstated.  This was
     temporarily dropped due to down_write latency issues.  Oleg's
     rework of percpu_rwsem which is scheduled to be merged in this
     merge window resolves the issue.

   - On the v2 hierarchy, when controllers are enabled and disabled, all
     operations are atomic and can fail and revert cleanly.  This allows
     ->can_attach() failure which is necessary for cpu RT slices.

   - Tasks now stay associated with the original cgroups after exit
     until released.  This allows tracking resources held by zombies
     (e.g.  pids) and makes it easy to find out where zombies came from
     on the v2 hierarchy.  The pids controller was broken before these
     changes as zombies escaped the limits; unfortunately, updating this
     behavior required too many invasive changes and I don't think it's
     a good idea to backport them, so the pids controller on 4.3, the
     first version which included the pids controller, will stay broken
     at least until I'm sure about the cgroup core changes.

   - Optimization of a couple common tests using static_key"

* 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (38 commits)
  cgroup: fix race condition around termination check in css_task_iter_next()
  blkcg: don't create "io.stat" on the root cgroup
  cgroup: drop cgroup__DEVEL__legacy_files_on_dfl
  cgroup: replace error handling in cgroup_init() with WARN_ON()s
  cgroup: add cgroup_subsys->free() method and use it to fix pids controller
  cgroup: keep zombies associated with their original cgroups
  cgroup: make css_set_rwsem a spinlock and rename it to css_set_lock
  cgroup: don't hold css_set_rwsem across css task iteration
  cgroup: reorganize css_task_iter functions
  cgroup: factor out css_set_move_task()
  cgroup: keep css_set and task lists in chronological order
  cgroup: make cgroup_destroy_locked() test cgroup_is_populated()
  cgroup: make css_sets pin the associated cgroups
  cgroup: relocate cgroup_[try]get/put()
  cgroup: move check_for_release() invocation
  cgroup: replace cgroup_has_tasks() with cgroup_is_populated()
  cgroup: make cgroup->nr_populated count the number of populated css_sets
  cgroup: remove an unused parameter from cgroup_task_migrate()
  cgroup: fix too early usage of static_branch_disable()
  cgroup: make cgroup_update_dfl_csses() migrate all target processes atomically
  ...

6 files changed, 765 insertions, 633 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2c9eae6ad970..b9d0cce3f9ce 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -45,7 +45,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/rwsem.h>
+#include <linux/percpu-rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
@@ -75,7 +75,7 @@
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
- * css_set_rwsem protects task->cgroups pointer, the list of css_set
+ * css_set_lock protects task->cgroups pointer, the list of css_set
  * objects, and the chain of tasks off each css_set.
  *
  * These locks are exported if CONFIG_PROVE_RCU so that accessors in
@@ -83,12 +83,12 @@
  */
 #ifdef CONFIG_PROVE_RCU
 DEFINE_MUTEX(cgroup_mutex);
-DECLARE_RWSEM(css_set_rwsem);
+DEFINE_SPINLOCK(css_set_lock);
 EXPORT_SYMBOL_GPL(cgroup_mutex);
-EXPORT_SYMBOL_GPL(css_set_rwsem);
+EXPORT_SYMBOL_GPL(css_set_lock);
 #else
 static DEFINE_MUTEX(cgroup_mutex);
-static DECLARE_RWSEM(css_set_rwsem);
+static DEFINE_SPINLOCK(css_set_lock);
 #endif
 
 /*
@@ -103,6 +103,8 @@ static DEFINE_SPINLOCK(cgroup_idr_lock);
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
+struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
+
 #define cgroup_assert_mutex_or_rcu_locked()				\
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			   !lockdep_is_held(&cgroup_mutex),		\
@@ -136,6 +138,27 @@ static const char *cgroup_subsys_name[] = {
 };
 #undef SUBSYS
 
+/* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */
+#define SUBSYS(_x)								\
+	DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key);			\
+	DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key);			\
+	EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key);			\
+	EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key);
+#include <linux/cgroup_subsys.h>
+#undef SUBSYS
+
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key,
+static struct static_key_true *cgroup_subsys_enabled_key[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
+
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key,
+static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
+
 /*
  * The default hierarchy, reserved for the subsystems that are otherwise
  * unattached - it never has more than a single cgroup, and all tasks are
@@ -150,12 +173,6 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root);
  */
 static bool cgrp_dfl_root_visible;
 
-/*
- * Set by the boot param of the same name and makes subsystems with NULL
- * ->dfl_files to use ->legacy_files on the default hierarchy.
- */
-static bool cgroup_legacy_files_on_dfl;
-
 /* some controllers are not supported in the default hierarchy */
 static unsigned long cgrp_dfl_root_inhibit_ss_mask;
 
@@ -183,6 +200,7 @@ static u64 css_serial_nr_next = 1;
  */
 static unsigned long have_fork_callback __read_mostly;
 static unsigned long have_exit_callback __read_mostly;
+static unsigned long have_free_callback __read_mostly;
 
 /* Ditto for the can_fork callback. */
 static unsigned long have_canfork_callback __read_mostly;
@@ -192,14 +210,87 @@ static struct cftype cgroup_legacy_base_files[];
 
 static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned long ss_mask);
+static void css_task_iter_advance(struct css_task_iter *it);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 		      bool visible);
 static void css_release(struct percpu_ref *ref);
 static void kill_css(struct cgroup_subsys_state *css);
-static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
+static int cgroup_addrm_files(struct cgroup_subsys_state *css,
+			      struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
 
+/**
+ * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID
+ * @ssid: subsys ID of interest
+ *
+ * cgroup_subsys_enabled() can only be used with literal subsys names which
+ * is fine for individual subsystems but unsuitable for cgroup core.  This
+ * is slower static_key_enabled() based test indexed by @ssid.
+ */
+static bool cgroup_ssid_enabled(int ssid)
+{
+	return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
+}
+
+/**
+ * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
+ * @cgrp: the cgroup of interest
+ *
+ * The default hierarchy is the v2 interface of cgroup and this function
+ * can be used to test whether a cgroup is on the default hierarchy for
+ * cases where a subsystem should behave differnetly depending on the
+ * interface version.
+ *
+ * The set of behaviors which change on the default hierarchy are still
+ * being determined and the mount option is prefixed with __DEVEL__.
+ *
+ * List of changed behaviors:
+ *
+ * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
+ *   and "name" are disallowed.
+ *
+ * - When mounting an existing superblock, mount options should match.
+ *
+ * - Remount is disallowed.
+ *
+ * - rename(2) is disallowed.
+ *
+ * - "tasks" is removed.  Everything should be at process granularity.  Use
+ *   "cgroup.procs" instead.
+ *
+ * - "cgroup.procs" is not sorted.  pids will be unique unless they got
+ *   recycled inbetween reads.
+ *
+ * - "release_agent" and "notify_on_release" are removed.  Replacement
+ *   notification mechanism will be implemented.
+ *
+ * - "cgroup.clone_children" is removed.
+ *
+ * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
+ *   and its descendants contain no task; otherwise, 1.  The file also
+ *   generates kernfs notification which can be monitored through poll and
+ *   [di]notify when the value of the file changes.
+ *
+ * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
+ *   take masks of ancestors with non-empty cpus/mems, instead of being
+ *   moved to an ancestor.
+ *
+ * - cpuset: a task can be moved into an empty cpuset, and again it takes
+ *   masks of ancestors.
+ *
+ * - memcg: use_hierarchy is on by default and the cgroup file for the flag
+ *   is not created.
+ *
+ * - blkcg: blk-throttle becomes properly hierarchical.
+ *
+ * - debug: disallowed on the default hierarchy.
+ */
+static bool cgroup_on_dfl(const struct cgroup *cgrp)
+{
+	return cgrp->root == &cgrp_dfl_root;
+}
+
 /* IDR wrappers which synchronize using cgroup_idr_lock */
 static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
 			    gfp_t gfp_mask)
@@ -332,6 +423,22 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 	return !(cgrp->self.flags & CSS_ONLINE);
 }
 
+static void cgroup_get(struct cgroup *cgrp)
+{
+	WARN_ON_ONCE(cgroup_is_dead(cgrp));
+	css_get(&cgrp->self);
+}
+
+static bool cgroup_tryget(struct cgroup *cgrp)
+{
+	return css_tryget(&cgrp->self);
+}
+
+static void cgroup_put(struct cgroup *cgrp)
+{
+	css_put(&cgrp->self);
+}
+
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
 	struct cgroup *cgrp = of->kn->parent->priv;
@@ -481,19 +588,31 @@ struct css_set init_css_set = {
 	.mg_tasks		= LIST_HEAD_INIT(init_css_set.mg_tasks),
 	.mg_preload_node	= LIST_HEAD_INIT(init_css_set.mg_preload_node),
 	.mg_node		= LIST_HEAD_INIT(init_css_set.mg_node),
+	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 };
 
 static int css_set_count	= 1;	/* 1 for init_css_set */
 
 /**
+ * css_set_populated - does a css_set contain any tasks?
+ * @cset: target css_set
+ */
+static bool css_set_populated(struct css_set *cset)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks);
+}
+
+/**
  * cgroup_update_populated - updated populated count of a cgroup
  * @cgrp: the target cgroup
  * @populated: inc or dec populated count
  *
- * @cgrp is either getting the first task (css_set) or losing the last.
- * Update @cgrp->populated_cnt accordingly.  The count is propagated
- * towards root so that a given cgroup's populated_cnt is zero iff the
- * cgroup and all its descendants are empty.
+ * One of the css_sets associated with @cgrp is either getting its first
+ * task or losing the last.  Update @cgrp->populated_cnt accordingly.  The
+ * count is propagated towards root so that a given cgroup's populated_cnt
+ * is zero iff the cgroup and all its descendants don't contain any tasks.
  *
  * @cgrp's interface file "cgroup.populated" is zero if
  * @cgrp->populated_cnt is zero and 1 otherwise.  When @cgrp->populated_cnt
@@ -503,7 +622,7 @@ static int css_set_count	= 1;	/* 1 for init_css_set */
  */
 static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
 {
-	lockdep_assert_held(&css_set_rwsem);
+	lockdep_assert_held(&css_set_lock);
 
 	do {
 		bool trigger;
@@ -516,12 +635,93 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
 		if (!trigger)
 			break;
 
-		if (cgrp->populated_kn)
-			kernfs_notify(cgrp->populated_kn);
+		check_for_release(cgrp);
+		cgroup_file_notify(&cgrp->events_file);
+
 		cgrp = cgroup_parent(cgrp);
 	} while (cgrp);
 }
 
+/**
+ * css_set_update_populated - update populated state of a css_set
+ * @cset: target css_set
+ * @populated: whether @cset is populated or depopulated
+ *
+ * @cset is either getting the first task or losing the last.  Update the
+ * ->populated_cnt of all associated cgroups accordingly.
+ */
+static void css_set_update_populated(struct css_set *cset, bool populated)
+{
+	struct cgrp_cset_link *link;
+
+	lockdep_assert_held(&css_set_lock);
+
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
+		cgroup_update_populated(link->cgrp, populated);
+}
+
+/**
+ * css_set_move_task - move a task from one css_set to another
+ * @task: task being moved
+ * @from_cset: css_set @task currently belongs to (may be NULL)
+ * @to_cset: new css_set @task is being moved to (may be NULL)
+ * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks
+ *
+ * Move @task from @from_cset to @to_cset.  If @task didn't belong to any
+ * css_set, @from_cset can be NULL.  If @task is being disassociated
+ * instead of moved, @to_cset can be NULL.
+ *
+ * This function automatically handles populated_cnt updates and
+ * css_task_iter adjustments but the caller is responsible for managing
+ * @from_cset and @to_cset's reference counts.
+ */
+static void css_set_move_task(struct task_struct *task,
+			      struct css_set *from_cset, struct css_set *to_cset,
+			      bool use_mg_tasks)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	if (from_cset) {
+		struct css_task_iter *it, *pos;
+
+		WARN_ON_ONCE(list_empty(&task->cg_list));
+
+		/*
+		 * @task is leaving, advance task iterators which are
+		 * pointing to it so that they can resume at the next
+		 * position.  Advancing an iterator might remove it from
+		 * the list, use safe walk.  See css_task_iter_advance*()
+		 * for details.
+		 */
+		list_for_each_entry_safe(it, pos, &from_cset->task_iters,
+					 iters_node)
+			if (it->task_pos == &task->cg_list)
+				css_task_iter_advance(it);
+
+		list_del_init(&task->cg_list);
+		if (!css_set_populated(from_cset))
+			css_set_update_populated(from_cset, false);
+	} else {
+		WARN_ON_ONCE(!list_empty(&task->cg_list));
+	}
+
+	if (to_cset) {
+		/*
+		 * We are synchronized through cgroup_threadgroup_rwsem
+		 * against PF_EXITING setting such that we can't race
+		 * against cgroup_exit() changing the css_set to
+		 * init_css_set and dropping the old one.
+		 */
+		WARN_ON_ONCE(task->flags & PF_EXITING);
+
+		if (!css_set_populated(to_cset))
+			css_set_update_populated(to_cset, true);
+		rcu_assign_pointer(task->cgroups, to_cset);
+		list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
+							     &to_cset->tasks);
+	}
+}
+
 /*
  * hash table for cgroup groups. This improves the performance to find
  * an existing css_set. This hash doesn't (currently) take into
@@ -549,7 +749,7 @@ static void put_css_set_locked(struct css_set *cset)
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	lockdep_assert_held(&css_set_rwsem);
+	lockdep_assert_held(&css_set_lock);
 
 	if (!atomic_dec_and_test(&cset->refcount))
 		return;
@@ -561,17 +761,10 @@ static void put_css_set_locked(struct css_set *cset)
 	css_set_count--;
 
 	list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) {
-		struct cgroup *cgrp = link->cgrp;
-
 		list_del(&link->cset_link);
 		list_del(&link->cgrp_link);
-
-		/* @cgrp can't go away while we're holding css_set_rwsem */
-		if (list_empty(&cgrp->cset_links)) {
-			cgroup_update_populated(cgrp, false);
-			check_for_release(cgrp);
-		}
-
+		if (cgroup_parent(link->cgrp))
+			cgroup_put(link->cgrp);
 		kfree(link);
 	}
 
@@ -588,9 +781,9 @@ static void put_css_set(struct css_set *cset)
 	if (atomic_add_unless(&cset->refcount, -1, 1))
 		return;
 
-	down_write(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 	put_css_set_locked(cset);
-	up_write(&css_set_rwsem);
+	spin_unlock_bh(&css_set_lock);
 }
 
 /*
@@ -779,15 +972,15 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
 	link->cset = cset;
 	link->cgrp = cgrp;
 
-	if (list_empty(&cgrp->cset_links))
-		cgroup_update_populated(cgrp, true);
-	list_move(&link->cset_link, &cgrp->cset_links);
-
 	/*
-	 * Always add links to the tail of the list so that the list
-	 * is sorted by order of hierarchy creation
+	 * Always add links to the tail of the lists so that the lists are
+	 * in choronological order.
 	 */
+	list_move_tail(&link->cset_link, &cgrp->cset_links);
 	list_add_tail(&link->cgrp_link, &cset->cgrp_links);
+
+	if (cgroup_parent(cgrp))
+		cgroup_get(cgrp);
 }
 
 /**
@@ -813,11 +1006,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
 	/* First see if we already have a cgroup group that matches
 	 * the desired set */
-	down_read(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 	cset = find_existing_css_set(old_cset, cgrp, template);
 	if (cset)
 		get_css_set(cset);
-	up_read(&css_set_rwsem);
+	spin_unlock_bh(&css_set_lock);
 
 	if (cset)
 		return cset;
@@ -838,13 +1031,14 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->mg_tasks);
 	INIT_LIST_HEAD(&cset->mg_preload_node);
 	INIT_LIST_HEAD(&cset->mg_node);
+	INIT_LIST_HEAD(&cset->task_iters);
 	INIT_HLIST_NODE(&cset->hlist);
 
 	/* Copy the set of subsystem state objects generated in
 	 * find_existing_css_set() */
 	memcpy(cset->subsys, template, sizeof(cset->subsys));
 
-	down_write(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 	/* Add reference counts and links from the new css_set. */
 	list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
 		struct cgroup *c = link->cgrp;
@@ -866,53 +1060,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 		list_add_tail(&cset->e_cset_node[ssid],
 			      &cset->subsys[ssid]->cgroup->e_csets[ssid]);
 
-	up_write(&css_set_rwsem);
+	spin_unlock_bh(&css_set_lock);
 
 	return cset;
 }
 
-void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-	down_read(&tsk->signal->group_rwsem);
-}
-
-void cgroup_threadgroup_change_end(struct task_struct *tsk)
-{
-	up_read(&tsk->signal->group_rwsem);
-}
-
-/**
- * threadgroup_lock - lock threadgroup
- * @tsk: member task of the threadgroup to lock
- *
- * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
- * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * change ->group_leader/pid.  This is useful for cases where the threadgroup
- * needs to stay stable across blockable operations.
- *
- * fork and exit explicitly call threadgroup_change_{begin|end}() for
- * synchronization.  While held, no new task will be added to threadgroup
- * and no existing live task will have its PF_EXITING set.
- *
- * de_thread() does threadgroup_change_{begin|end}() when a non-leader
- * sub-thread becomes a new leader.
- */
-static void threadgroup_lock(struct task_struct *tsk)
-{
-	down_write(&tsk->signal->group_rwsem);
-}
-
-/**
- * threadgroup_unlock - unlock threadgroup
- * @tsk: member task of the threadgroup to unlock
- *
- * Reverse threadgroup_lock().
- */
-static inline void threadgroup_unlock(struct task_struct *tsk)
-{
-	up_write(&tsk->signal->group_rwsem);
-}
-
 static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
 	struct cgroup *root_cgrp = kf_root->kn->priv;
@@ -972,14 +1124,15 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	 * Release all the links from cset_links to this hierarchy's
 	 * root cgroup
 	 */
-	down_write(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 
 	list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
 		list_del(&link->cset_link);
 		list_del(&link->cgrp_link);
 		kfree(link);
 	}
-	up_write(&css_set_rwsem);
+
+	spin_unlock_bh(&css_set_lock);
 
 	if (!list_empty(&root->root_list)) {
 		list_del(&root->root_list);
@@ -1001,7 +1154,7 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 	struct cgroup *res = NULL;
 
 	lockdep_assert_held(&cgroup_mutex);
-	lockdep_assert_held(&css_set_rwsem);
+	lockdep_assert_held(&css_set_lock);
 
 	if (cset == &init_css_set) {
 		res = &root->cgrp;
@@ -1024,7 +1177,7 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 
 /*
  * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_rwsem held.
+ * called with cgroup_mutex and css_set_lock held.
  */
 static struct cgroup *task_cgroup_from_root(struct task_struct *task,
 					    struct cgroup_root *root)
@@ -1063,7 +1216,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 static const struct file_operations proc_cgroupstats_operations;
 
@@ -1086,43 +1238,25 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
  * cgroup_file_mode - deduce file mode of a control file
  * @cft: the control file in question
  *
- * returns cft->mode if ->mode is not 0
- * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
- * returns S_IRUGO if it has only a read handler
- * returns S_IWUSR if it has only a write hander
+ * S_IRUGO for read, S_IWUSR for write.
  */
 static umode_t cgroup_file_mode(const struct cftype *cft)
 {
 	umode_t mode = 0;
 
-	if (cft->mode)
-		return cft->mode;
-
 	if (cft->read_u64 || cft->read_s64 || cft->seq_show)
 		mode |= S_IRUGO;
 
-	if (cft->write_u64 || cft->write_s64 || cft->write)
-		mode |= S_IWUSR;
+	if (cft->write_u64 || cft->write_s64 || cft->write) {
+		if (cft->flags & CFTYPE_WORLD_WRITABLE)
+			mode |= S_IWUGO;
+		else
+			mode |= S_IWUSR;
+	}
 
 	return mode;
 }
 
-static void cgroup_get(struct cgroup *cgrp)
-{
-	WARN_ON_ONCE(cgroup_is_dead(cgrp));
-	css_get(&cgrp->self);
-}
-
-static bool cgroup_tryget(struct cgroup *cgrp)
-{
-	return css_tryget(&cgrp->self);
-}
-
-static void cgroup_put(struct cgroup *cgrp)
-{
-	css_put(&cgrp->self);
-}
-
 /**
  * cgroup_calc_child_subsys_mask - calculate child_subsys_mask
  * @cgrp: the target cgroup
@@ -1263,28 +1397,64 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 }
 
 /**
- * cgroup_clear_dir - remove subsys files in a cgroup directory
- * @cgrp: target cgroup
- * @subsys_mask: mask of the subsystem ids whose files should be removed
+ * css_clear_dir - remove subsys files in a cgroup directory
+ * @css: taget css
+ * @cgrp_override: specify if target cgroup is different from css->cgroup
  */
-static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
+static void css_clear_dir(struct cgroup_subsys_state *css,
+			  struct cgroup *cgrp_override)
 {
-	struct cgroup_subsys *ss;
-	int i;
+	struct cgroup *cgrp = cgrp_override ?: css->cgroup;
+	struct cftype *cfts;
 
-	for_each_subsys(ss, i) {
-		struct cftype *cfts;
+	list_for_each_entry(cfts, &css->ss->cfts, node)
+		cgroup_addrm_files(css, cgrp, cfts, false);
+}
 
-		if (!(subsys_mask & (1 << i)))
-			continue;
-		list_for_each_entry(cfts, &ss->cfts, node)
-			cgroup_addrm_files(cgrp, cfts, false);
+/**
+ * css_populate_dir - create subsys files in a cgroup directory
+ * @css: target css
+ * @cgrp_overried: specify if target cgroup is different from css->cgroup
+ *
+ * On failure, no file is added.
+ */
+static int css_populate_dir(struct cgroup_subsys_state *css,
+			    struct cgroup *cgrp_override)
+{
+	struct cgroup *cgrp = cgrp_override ?: css->cgroup;
+	struct cftype *cfts, *failed_cfts;
+	int ret;
+
+	if (!css->ss) {
+		if (cgroup_on_dfl(cgrp))
+			cfts = cgroup_dfl_base_files;
+		else
+			cfts = cgroup_legacy_base_files;
+
+		return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
+	}
+
+	list_for_each_entry(cfts, &css->ss->cfts, node) {
+		ret = cgroup_addrm_files(css, cgrp, cfts, true);
+		if (ret < 0) {
+			failed_cfts = cfts;
+			goto err;
+		}
 	}
+	return 0;
+err:
+	list_for_each_entry(cfts, &css->ss->cfts, node) {
+		if (cfts == failed_cfts)
+			break;
+		cgroup_addrm_files(css, cgrp, cfts, false);
+	}
+	return ret;
 }
 
 static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned long ss_mask)
 {
+	struct cgroup *dcgrp = &dst_root->cgrp;
 	struct cgroup_subsys *ss;
 	unsigned long tmp_ss_mask;
 	int ssid, i, ret;
@@ -1306,10 +1476,13 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 	if (dst_root == &cgrp_dfl_root)
 		tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask;
 
-	ret = cgroup_populate_dir(&dst_root->cgrp, tmp_ss_mask);
-	if (ret) {
-		if (dst_root != &cgrp_dfl_root)
-			return ret;
+	for_each_subsys_which(ss, ssid, &tmp_ss_mask) {
+		struct cgroup *scgrp = &ss->root->cgrp;
+		int tssid;
+
+		ret = css_populate_dir(cgroup_css(scgrp, ss), dcgrp);
+		if (!ret)
+			continue;
 
 		/*
 		 * Rebinding back to the default root is not allowed to
@@ -1317,57 +1490,67 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 		 * be rare.  Moving subsystems back and forth even more so.
 		 * Just warn about it and continue.
 		 */
-		if (cgrp_dfl_root_visible) {
-			pr_warn("failed to create files (%d) while rebinding 0x%lx to default root\n",
-				ret, ss_mask);
-			pr_warn("you may retry by moving them to a different hierarchy and unbinding\n");
+		if (dst_root == &cgrp_dfl_root) {
+			if (cgrp_dfl_root_visible) {
+				pr_warn("failed to create files (%d) while rebinding 0x%lx to default root\n",
+					ret, ss_mask);
+				pr_warn("you may retry by moving them to a different hierarchy and unbinding\n");
+			}
+			continue;
+		}
+
+		for_each_subsys_which(ss, tssid, &tmp_ss_mask) {
+			if (tssid == ssid)
+				break;
+			css_clear_dir(cgroup_css(scgrp, ss), dcgrp);
 		}
+		return ret;
 	}
 
 	/*
 	 * Nothing can fail from this point on.  Remove files for the
 	 * removed subsystems and rebind each subsystem.
 	 */
-	for_each_subsys_which(ss, ssid, &ss_mask)
-		cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
-
 	for_each_subsys_which(ss, ssid, &ss_mask) {
-		struct cgroup_root *src_root;
-		struct cgroup_subsys_state *css;
+		struct cgroup_root *src_root = ss->root;
+		struct cgroup *scgrp = &src_root->cgrp;
+		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
 		struct css_set *cset;
 
-		src_root = ss->root;
-		css = cgroup_css(&src_root->cgrp, ss);
+		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
-		WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss));
+		css_clear_dir(css, NULL);
 
-		RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL);
-		rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css);
+		RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
+		rcu_assign_pointer(dcgrp->subsys[ssid], css);
 		ss->root = dst_root;
-		css->cgroup = &dst_root->cgrp;
+		css->cgroup = dcgrp;
 
-		down_write(&css_set_rwsem);
+		spin_lock_bh(&css_set_lock);
 		hash_for_each(css_set_table, i, cset, hlist)
 			list_move_tail(&cset->e_cset_node[ss->id],
-				       &dst_root->cgrp.e_csets[ss->id]);
-		up_write(&css_set_rwsem);
+				       &dcgrp->e_csets[ss->id]);
+		spin_unlock_bh(&css_set_lock);
 
 		src_root->subsys_mask &= ~(1 << ssid);
-		src_root->cgrp.subtree_control &= ~(1 << ssid);
-		cgroup_refresh_child_subsys_mask(&src_root->cgrp);
+		scgrp->subtree_control &= ~(1 << ssid);
+		cgroup_refresh_child_subsys_mask(scgrp);
 
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
-		if (dst_root != &cgrp_dfl_root) {
-			dst_root->cgrp.subtree_control |= 1 << ssid;
-			cgroup_refresh_child_subsys_mask(&dst_root->cgrp);
+		if (dst_root == &cgrp_dfl_root) {
+			static_branch_enable(cgroup_subsys_on_dfl_key[ssid]);
+		} else {
+			dcgrp->subtree_control |= 1 << ssid;
+			cgroup_refresh_child_subsys_mask(dcgrp);
+			static_branch_disable(cgroup_subsys_on_dfl_key[ssid]);
 		}
 
 		if (ss->bind)
 			ss->bind(css);
 	}
 
-	kernfs_activate(dst_root->cgrp.kn);
+	kernfs_activate(dcgrp->kn);
 	return 0;
 }
 
@@ -1497,7 +1680,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 		for_each_subsys(ss, i) {
 			if (strcmp(token, ss->legacy_name))
 				continue;
-			if (ss->disabled)
+			if (!cgroup_ssid_enabled(i))
 				continue;
 
 			/* Mutually exclusive option 'all' + subsystem name */
@@ -1528,7 +1711,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	 */
 	if (all_ss || (!one_ss && !opts->none && !opts->name))
 		for_each_subsys(ss, i)
-			if (!ss->disabled)
+			if (cgroup_ssid_enabled(i))
 				opts->subsys_mask |= (1 << i);
 
 	/*
@@ -1624,7 +1807,7 @@ static void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 
-	down_write(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 
 	if (use_task_css_set_links)
 		goto out_unlock;
@@ -1654,14 +1837,16 @@ static void cgroup_enable_task_cg_lists(void)
 		if (!(p->flags & PF_EXITING)) {
 			struct css_set *cset = task_css_set(p);
 
-			list_add(&p->cg_list, &cset->tasks);
+			if (!css_set_populated(cset))
+				css_set_update_populated(cset, true);
+			list_add_tail(&p->cg_list, &cset->tasks);
 			get_css_set(cset);
 		}
 		spin_unlock_irq(&p->sighand->siglock);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 out_unlock:
-	up_write(&css_set_rwsem);
+	spin_unlock_bh(&css_set_lock);
 }
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -1671,6 +1856,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 
 	INIT_LIST_HEAD(&cgrp->self.sibling);
 	INIT_LIST_HEAD(&cgrp->self.children);
+	INIT_LIST_HEAD(&cgrp->self.files);
 	INIT_LIST_HEAD(&cgrp->cset_links);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
@@ -1708,7 +1894,6 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
-	struct cftype *base_files;
 	struct css_set *cset;
 	int i, ret;
 
@@ -1725,7 +1910,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 		goto out;
 
 	/*
-	 * We're accessing css_set_count without locking css_set_rwsem here,
+	 * We're accessing css_set_count without locking css_set_lock here,
 	 * but that's OK - it can only be increased by someone holding
 	 * cgroup_lock, and that's us. The worst that can happen is that we
 	 * have some link structures left over
@@ -1747,12 +1932,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	}
 	root_cgrp->kn = root->kf_root->kn;
 
-	if (root == &cgrp_dfl_root)
-		base_files = cgroup_dfl_base_files;
-	else
-		base_files = cgroup_legacy_base_files;
-
-	ret = cgroup_addrm_files(root_cgrp, base_files, true);
+	ret = css_populate_dir(&root_cgrp->self, NULL);
 	if (ret)
 		goto destroy_root;
 
@@ -1772,10 +1952,13 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	 * Link the root cgroup in this hierarchy into all the css_set
 	 * objects.
 	 */
-	down_write(&css_set_rwsem);
-	hash_for_each(css_set_table, i, cset, hlist)
+	spin_lock_bh(&css_set_lock);
+	hash_for_each(css_set_table, i, cset, hlist) {
 		link_css_set(&tmp_links, cset, root_cgrp);
-	up_write(&css_set_rwsem);
+		if (css_set_populated(cset))
+			cgroup_update_populated(root_cgrp, true);
+	}
+	spin_unlock_bh(&css_set_lock);
 
 	BUG_ON(!list_empty(&root_cgrp->self.children));
 	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2008,7 +2191,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 	char *path = NULL;
 
 	mutex_lock(&cgroup_mutex);
-	down_read(&css_set_rwsem);
+	spin_lock_bh(&css_set_lock);
 
 	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
 
@@ -2021,7 +2204,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 			path = buf;
 	}
 
-	up_read(&css_set_rwsem);
+	spin_unlock_bh(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 	return path;
 }
@@ -2049,6 +2232,49 @@ struct cgroup_taskset {
 	struct task_struct	*cur_task;
 };
 
+#define CGROUP_TASKSET_INIT(tset)	(struct cgroup_taskset){	\
+	.src_csets		= LIST_HEAD_INIT(tset.src_csets),	\
+	.dst_csets		= LIST_HEAD_INIT(tset.dst_csets),	\
+	.csets			= &tset.src_csets,			\
+}
+
+/**
+ * cgroup_taskset_add - try to add a migration target task to a taskset
+ * @task: target task
+ * @tset: target taskset
+ *
+ * Add @task, which is a migration target, to @tset.  This function becomes
+ * noop if @task doesn't need to be migrated.  @task's css_set should have
+ * been added as a migration source and @task->cg_list will be moved from
+ * the css_set's tasks list to mg_tasks one.
+ */
+static void cgroup_taskset_add(struct task_struct *task,
+			       struct cgroup_taskset *tset)
+{
+	struct css_set *cset;
+
+	lockdep_assert_held(&css_set_lock);
+
+	/* @task either already exited or can't exit until the end */
+	if (task->flags & PF_EXITING)
+		return;
+
+	/* leave @task alone if post_fork() hasn't linked it yet */
+	if (list_empty(&task->cg_list))
+		return;
+
+	cset = task_css_set(task);
+	if (!cset->mg_src_cgrp)
+		return;
+
+	list_move_tail(&task->cg_list, &cset->mg_tasks);
+	if (list_empty(&cset->mg_node))
+		list_add_tail(&cset->mg_node, &tset->src_csets);
+	if (list_empty(&cset->mg_dst_cset->mg_node))
+		list_move_tail(&cset->mg_dst_cset->mg_node,
+			       &tset->dst_csets);
+}
+
 /**