Merge branch 'for-5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "This includes Roman's cgroup2 freezer implementation.

  It's a separate machanism from cgroup1 freezer. Instead of blocking
  user tasks in arbitrary uninterruptible sleeps, the new implementation
  extends jobctl stop - frozen tasks are trapped in jobctl stop until
  thawed and can be killed and ptraced. Lots of thanks to Oleg for
  sheperding the effort.

  Other than that, there are a few trivial changes"

* 'for-5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: never call do_group_exit() with task->frozen bit set
  kernel: cgroup: fix misuse of %x
  cgroup: get rid of cgroup_freezer_frozen_exit()
  cgroup: prevent spurious transition into non-frozen state
  cgroup: Remove unused cgrp variable
  cgroup: document cgroup v2 freezer interface
  cgroup: add tracing points for cgroup v2 freezer
  cgroup: make TRACE_CGROUP_PATH irq-safe
  kselftests: cgroup: add freezer controller self-tests
  kselftests: cgroup: don't fail on cg_kill_all() error in cg_destroy()
  cgroup: cgroup v2 freezer
  cgroup: protect cgroup->nr_(dying_)descendants by css_set_lock
  cgroup: implement __cgroup_task_count() helper
  cgroup: rename freezer.c into legacy_freezer.c
  cgroup: remove extra cgroup_migrate_finish() call

Documentation/admin-guide/cgroup-v2.rst

@@ -864,6 +864,8 @@ All cgroup core files are prefixed with "cgroup."
 	  populated
 		1 if the cgroup or its descendants contains any live
 		processes; otherwise, 0.
+	  frozen
+		1 if the cgroup is frozen; otherwise, 0.
 
   cgroup.max.descendants
 	A read-write single value files.  The default is "max".
@@ -897,6 +899,31 @@ All cgroup core files are prefixed with "cgroup."
 		A dying cgroup can consume system resources not exceeding
 		limits, which were active at the moment of cgroup deletion.
 
+  cgroup.freeze
+	A read-write single value file which exists on non-root cgroups.
+	Allowed values are "0" and "1". The default is "0".
+
+	Writing "1" to the file causes freezing of the cgroup and all
+	descendant cgroups. This means that all belonging processes will
+	be stopped and will not run until the cgroup will be explicitly
+	unfrozen. Freezing of the cgroup may take some time; when this action
+	is completed, the "frozen" value in the cgroup.events control file
+	will be updated to "1" and the corresponding notification will be
+	issued.
+
+	A cgroup can be frozen either by its own settings, or by settings
+	of any ancestor cgroups. If any of ancestor cgroups is frozen, the
+	cgroup will remain frozen.
+
+	Processes in the frozen cgroup can be killed by a fatal signal.
+	They also can enter and leave a frozen cgroup: either by an explicit
+	move by a user, or if freezing of the cgroup races with fork().
+	If a process is moved to a frozen cgroup, it stops. If a process is
+	moved out of a frozen cgroup, it becomes running.
+
+	Frozen status of a cgroup doesn't affect any cgroup tree operations:
+	it's possible to delete a frozen (and empty) cgroup, as well as
+	create new sub-cgroups.
 
 Controllers
 ===========

include/linux/cgroup-defs.h

@@ -65,6 +65,12 @@ enum {
 	 * specified at mount time and thus is implemented here.
 	 */
 	CGRP_CPUSET_CLONE_CHILDREN,
+
+	/* Control group has to be frozen. */
+	CGRP_FREEZE,
+
+	/* Cgroup is frozen. */
+	CGRP_FROZEN,
 };
 
 /* cgroup_root->flags */
@@ -317,6 +323,25 @@ struct cgroup_rstat_cpu {
 	struct cgroup *updated_next;		/* NULL iff not on the list */
 };
 
+struct cgroup_freezer_state {
+	/* Should the cgroup and its descendants be frozen. */
+	bool freeze;
+
+	/* Should the cgroup actually be frozen? */
+	int e_freeze;
+
+	/* Fields below are protected by css_set_lock */
+
+	/* Number of frozen descendant cgroups */
+	int nr_frozen_descendants;
+
+	/*
+	 * Number of tasks, which are counted as frozen:
+	 * frozen, SIGSTOPped, and PTRACEd.
+	 */
+	int nr_frozen_tasks;
+};
+
 struct cgroup {
 	/* self css with NULL ->ss, points back to this cgroup */
 	struct cgroup_subsys_state self;
@@ -349,6 +374,11 @@ struct cgroup {
 	 * Dying cgroups are cgroups which were deleted by a user,
 	 * but are still existing because someone else is holding a reference.
 	 * max_descendants is a maximum allowed number of descent cgroups.
+	 *
+	 * nr_descendants and nr_dying_descendants are protected
+	 * by cgroup_mutex and css_set_lock. It's fine to read them holding
+	 * any of cgroup_mutex and css_set_lock; for writing both locks
+	 * should be held.
 	 */
 	int nr_descendants;
 	int nr_dying_descendants;
@@ -448,6 +478,9 @@ struct cgroup {
 	/* If there is block congestion on this cgroup. */
 	atomic_t congestion_count;
 
+	/* Used to store internal freezer state */
+	struct cgroup_freezer_state freezer;
+
 	/* ids of the ancestors at each level including self */
 	int ancestor_ids[];
 };

include/linux/cgroup.h

@@ -881,4 +881,47 @@ static inline void put_cgroup_ns(struct cgroup_namespace *ns)
 		free_cgroup_ns(ns);
 }
 
+#ifdef CONFIG_CGROUPS
+
+void cgroup_enter_frozen(void);
+void cgroup_leave_frozen(bool always_leave);
+void cgroup_update_frozen(struct cgroup *cgrp);
+void cgroup_freeze(struct cgroup *cgrp, bool freeze);
+void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src,
+				 struct cgroup *dst);
+
+static inline bool cgroup_task_freeze(struct task_struct *task)
+{
+	bool ret;
+
+	if (task->flags & PF_KTHREAD)
+		return false;
+
+	rcu_read_lock();
+	ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static inline bool cgroup_task_frozen(struct task_struct *task)
+{
+	return task->frozen;
+}
+
+#else /* !CONFIG_CGROUPS */
+
+static inline void cgroup_enter_frozen(void) { }
+static inline void cgroup_leave_frozen(bool always_leave) { }
+static inline bool cgroup_task_freeze(struct task_struct *task)
+{
+	return false;
+}
+static inline bool cgroup_task_frozen(struct task_struct *task)
+{
+	return false;
+}
+
+#endif /* !CONFIG_CGROUPS */
+
 #endif /* _LINUX_CGROUP_H */

include/linux/sched.h

@@ -726,6 +726,8 @@ struct task_struct {
 #ifdef CONFIG_CGROUPS
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
+	/* task is frozen/stopped (used by the cgroup freezer) */
+	unsigned			frozen:1;
 #endif
 #ifdef CONFIG_BLK_CGROUP
 	/* to be used once the psi infrastructure lands upstream. */

include/linux/sched/jobctl.h

@@ -18,6 +18,7 @@ struct task_struct;
 #define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
+#define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -26,6 +27,7 @@ struct task_struct;
 #define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
+#define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)

include/trace/events/cgroup.h

@@ -103,6 +103,20 @@ DEFINE_EVENT(cgroup, cgroup_rename,
 	TP_ARGS(cgrp, path)
 );
 
+DEFINE_EVENT(cgroup, cgroup_freeze,
+
+	TP_PROTO(struct cgroup *cgrp, const char *path),
+
+	TP_ARGS(cgrp, path)
+);
+
+DEFINE_EVENT(cgroup, cgroup_unfreeze,
+
+	TP_PROTO(struct cgroup *cgrp, const char *path),
+
+	TP_ARGS(cgrp, path)
+);
+
 DECLARE_EVENT_CLASS(cgroup_migrate,
 
 	TP_PROTO(struct cgroup *dst_cgrp, const char *path,
@@ -149,6 +163,47 @@ DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks,
 	TP_ARGS(dst_cgrp, path, task, threadgroup)
 );
 
+DECLARE_EVENT_CLASS(cgroup_event,
+
+	TP_PROTO(struct cgroup *cgrp, const char *path, int val),
+
+	TP_ARGS(cgrp, path, val),
+
+	TP_STRUCT__entry(
+		__field(	int,		root			)
+		__field(	int,		id			)
+		__field(	int,		level			)
+		__string(	path,		path			)
+		__field(	int,		val			)
+	),
+
+	TP_fast_assign(
+		__entry->root = cgrp->root->hierarchy_id;
+		__entry->id = cgrp->id;
+		__entry->level = cgrp->level;
+		__assign_str(path, path);
+		__entry->val = val;
+	),
+
+	TP_printk("root=%d id=%d level=%d path=%s val=%d",
+		  __entry->root, __entry->id, __entry->level, __get_str(path),
+		  __entry->val)
+);
+
+DEFINE_EVENT(cgroup_event, cgroup_notify_populated,
+
+	TP_PROTO(struct cgroup *cgrp, const char *path, int val),
+
+	TP_ARGS(cgrp, path, val)
+);
+
+DEFINE_EVENT(cgroup_event, cgroup_notify_frozen,
+
+	TP_PROTO(struct cgroup *cgrp, const char *path, int val),
+
+	TP_ARGS(cgrp, path, val)
+);
+
 #endif /* _TRACE_CGROUP_H */
 
 /* This part must be outside protection */

kernel/cgroup/Makefile

 # SPDX-License-Identifier: GPL-2.0
-obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o
+obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o freezer.o
 
-obj-$(CONFIG_CGROUP_FREEZER) += freezer.o
+obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
 obj-$(CONFIG_CGROUP_PIDS) += pids.o
 obj-$(CONFIG_CGROUP_RDMA) += rdma.o
 obj-$(CONFIG_CPUSETS) += cpuset.o

kernel/cgroup/cgroup-internal.h

@@ -28,12 +28,15 @@ extern void __init enable_debug_cgroup(void);
 #define TRACE_CGROUP_PATH(type, cgrp, ...)				\
 	do {								\
 		if (trace_cgroup_##type##_enabled()) {			\
-			spin_lock(&trace_cgroup_path_lock);		\
+			unsigned long flags;				\
+			spin_lock_irqsave(&trace_cgroup_path_lock,	\
+					  flags);			\
 			cgroup_path(cgrp, trace_cgroup_path,		\
 				    TRACE_CGROUP_PATH_LEN);		\
 			trace_cgroup_##type(cgrp, trace_cgroup_path,	\
 					    ##__VA_ARGS__);		\
-			spin_unlock(&trace_cgroup_path_lock);		\
+			spin_unlock_irqrestore(&trace_cgroup_path_lock, \
+					       flags);			\
 		}							\
 	} while (0)
 
@@ -240,6 +243,7 @@ int cgroup_rmdir(struct kernfs_node *kn);
 int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 		     struct kernfs_root *kf_root);
 
+int __cgroup_task_count(const struct cgroup *cgrp);
 int cgroup_task_count(const struct cgroup *cgrp);
 
 /*

kernel/cgroup/cgroup-v1.c

@@ -342,22 +342,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
 	return l;
 }
 
-/**
- * cgroup_task_count - count the number of tasks in a cgroup.
- * @cgrp: the cgroup in question
- */
-int cgroup_task_count(const struct cgroup *cgrp)
-{
-	int count = 0;
-	struct cgrp_cset_link *link;
-
-	spin_lock_irq(&css_set_lock);
-	list_for_each_entry(link, &cgrp->cset_links, cset_link)
-		count += link->cset->nr_tasks;
-	spin_unlock_irq(&css_set_lock);
-	return count;
-}
-
 /*
  * Load a cgroup's pidarray with either procs' tgids or tasks' pids
  */

kernel/cgroup/cgroup.c

@@ -593,6 +593,39 @@ static void cgroup_get_live(struct cgroup *cgrp)
 	css_get(&cgrp->self);
 }
 
+/**
+ * __cgroup_task_count - count the number of tasks in a cgroup. The caller
+ * is responsible for taking the css_set_lock.
+ * @cgrp: the cgroup in question
+ */
+int __cgroup_task_count(const struct cgroup *cgrp)
+{
+	int count = 0;
+	struct cgrp_cset_link *link;
+
+	lockdep_assert_held(&css_set_lock);
+
+	list_for_each_entry(link, &cgrp->cset_links, cset_link)
+		count += link->cset->nr_tasks;
+
+	return count;
+}
+
+/**
+ * cgroup_task_count - count the number of tasks in a cgroup.
+ * @cgrp: the cgroup in question
+ */
+int cgroup_task_count(const struct cgroup *cgrp)
+{
+	int count;
+
+	spin_lock_irq(&css_set_lock);
+	count = __cgroup_task_count(cgrp);
+	spin_unlock_irq(&css_set_lock);
+
+	return count;
+}
+
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
 	struct cgroup *cgrp = of->kn->parent->priv;
@@ -783,6 +816,8 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
 			break;
 
 		cgroup1_check_for_release(cgrp);
+		TRACE_CGROUP_PATH(notify_populated, cgrp,
+				  cgroup_is_populated(cgrp));
 		cgroup_file_notify(&cgrp->events_file);
 
 		child = cgrp;
@@ -2402,8 +2437,15 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 			get_css_set(to_cset);
 			to_cset->nr_tasks++;
 			css_set_move_task(task, from_cset, to_cset, true);
-			put_css_set_locked(from_cset);
 			from_cset->nr_tasks--;
+			/*
+			 * If the source or destination cgroup is frozen,
+			 * the task might require to change its state.
+			 */
+			cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp,
+						    to_cset->dfl_cgrp);
+			put_css_set_locked(from_cset);
+
 		}
 	}
 	spin_unlock_irq(&css_set_lock);
@@ -2602,7 +2644,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 		dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp);
 		if (!dst_cset)
-			goto err;
+			return -ENOMEM;
 
 		WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
 
@@ -2634,9 +2676,6 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 	}
 
 	return 0;
-err:
-	cgroup_migrate_finish(mgctx);
-	return -ENOMEM;
 }
 
 /**
@@ -3447,8 +3486,11 @@ static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of,
 
 static int cgroup_events_show(struct seq_file *seq, void *v)
 {
-	seq_printf(seq, "populated %d\n",
-		   cgroup_is_populated(seq_css(seq)->cgroup));
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp));
+	seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags));
+
 	return 0;
 }
 
@@ -3510,6 +3552,40 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 }
 #endif
 
+static int cgroup_freeze_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	seq_printf(seq, "%d\n", cgrp->freezer.freeze);
+
+	return 0;
+}
+
+static ssize_t cgroup_freeze_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	struct cgroup *cgrp;
+	ssize_t ret;
+	int freeze;
+
+	ret = kstrtoint(strstrip(buf), 0, &freeze);
+	if (ret)
+		return ret;
+
+	if (freeze < 0 || freeze > 1)
+		return -ERANGE;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENOENT;
+
+	cgroup_freeze(cgrp, freeze);
+
+	cgroup_kn_unlock(of->kn);
+
+	return nbytes;
+}
+
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of->kn->priv;
@@ -4653,6 +4729,12 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cgroup.stat",
 		.seq_show = cgroup_stat_show,
 	},
+	{
+		.name = "cgroup.freeze",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_freeze_show,
+		.write = cgroup_freeze_write,
+	},
 	{
 		.name = "cpu.stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -4781,9 +4863,11 @@ static void css_release_work_fn(struct work_struct *work)
 		if (cgroup_on_dfl(cgrp))
 			cgroup_rstat_flush(cgrp);
 
+		spin_lock_irq(&css_set_lock);
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
 		     tcgrp = cgroup_parent(tcgrp))
 			tcgrp->nr_dying_descendants--;
+		spin_unlock_irq(&css_set_lock);
 
 		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
 		cgrp->id = -1;
@@ -5001,12 +5085,31 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	if (ret)
 		goto out_psi_free;
 
+	/*
+	 * New cgroup inherits effective freeze counter, and
+	 * if the parent has to be frozen, the child has too.
+	 */
+	cgrp->freezer.e_freeze = parent->freezer.e_freeze;
+	if (cgrp->freezer.e_freeze)
+		set_bit(CGRP_FROZEN, &cgrp->flags);
+
+	spin_lock_irq(&css_set_lock);
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
 
-		if (tcgrp != cgrp)
+		if (tcgrp != cgrp) {
 			tcgrp->nr_descendants++;
+
+			/*
+			 * If the new cgroup is frozen, all ancestor cgroups
+			 * get a new frozen descendant, but their state can't
+			 * change because of this.
+			 */
+			if (cgrp->freezer.e_freeze)
+				tcgrp->freezer.nr_frozen_descendants++;
+		}
 	}
+	spin_unlock_irq(&css_set_lock);
 
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -5291,10 +5394,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	if (parent && cgroup_is_threaded(cgrp))
 		parent->nr_threaded_children--;
 
+	spin_lock_irq(&css_set_lock);
 	for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		tcgrp->nr_descendants--;
 		tcgrp->nr_dying_descendants++;
+		/*
+		 * If the dying cgroup is frozen, decrease frozen descendants
+		 * counters of ancestor cgroups.
+		 */
+		if (test_bit(CGRP_FROZEN, &cgrp->flags))
+			tcgrp->freezer.nr_frozen_descendants--;
 	}
+	spin_unlock_irq(&css_set_lock);
 
 	cgroup1_check_for_release(parent);
 
@@ -5746,6 +5857,26 @@ void cgroup_post_fork(struct task_struct *child)
 			cset->nr_tasks++;
 			css_set_move_task(child, NULL, cset, false);
 		}
+
+		/*
+		 * If the cgroup has to be frozen, the new task has too.
+		 * Let's set the JOBCTL_TRAP_FREEZE jobctl bit to get
+		 * the task into the frozen state.
+		 */
+		if (unlikely(cgroup_task_freeze(child))) {
+			spin_lock(&child->sighand->siglock);
+			WARN_ON_ONCE(child->frozen);
+			child->jobctl |= JOBCTL_TRAP_FREEZE;
+			spin_unlock(&child->sighand->siglock);
+
+			/*
+			 * Calling cgroup_update_frozen() isn't required here,
+			 * because it will be called anyway a bit later
+			 * from do_freezer_trap(). So we avoid cgroup's
+			 * transient switch from the frozen state and back.
+			 */
+		}
+
 		spin_unlock_irq(&css_set_lock);
 	}
 
@@ -5794,6 +5925,11 @@ void cgroup_exit(struct task_struct *tsk)
 		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
 		cset->nr_tasks--;
+
+		WARN_ON_ONCE(cgroup_task_frozen(tsk));
+		if (unlikely(cgroup_task_freeze(tsk)))
+			cgroup_update_frozen(task_dfl_cgroup(tsk));
+
 		spin_unlock_irq(&css_set_lock);
 	} else {
 		get_css_set(cset);

kernel/cgroup/debug.c

@@ -64,8 +64,8 @@ static int current_css_set_read(struct seq_file *seq, void *v)
 		css = cset->subsys[ss->id];
 		if (!css)
 			continue;
-		seq_printf(seq, "%2d: %-4s\t- %lx[%d]\n", ss->id, ss->name,
-			  (unsigned long)css, css->id);
+		seq_printf(seq, "%2d: %-4s\t- %p[%d]\n", ss->id, ss->name,
+			  css, css->id);
 	}
 	rcu_read_unlock();
 	spin_unlock_irq(&css_set_lock);
@@ -224,8 +224,8 @@ static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
 		if (css->parent)
 			snprintf(pbuf, sizeof(pbuf) - 1, " P=%d",
 				 css->parent->id);
-		seq_printf(seq, "%2d: %-4s\t- %lx[%d] %d%s\n", ss->id, ss->name,
-			  (unsigned long)css, css->id,
+		seq_printf(seq, "%2d: %-4s\t- %p[%d] %d%s\n", ss->id, ss->name,
+			  css, css->id,
 			  atomic_read(&css->online_cnt), pbuf);
 	}
 

kernel/fork.c

@@ -1225,7 +1225,9 @@ static int wait_for_vfork_done(struct task_struct *child,
 	int killed;
 
 	freezer_do_not_count();
+	cgroup_enter_frozen();
 	killed = wait_for_completion_killable(vfork);
+	cgroup_leave_frozen(false);
 	freezer_count();
 
 	if (killed) {

kernel/signal.c

@@ -43,6 +43,7 @@
 #include <linux/compiler.h>
 #include <linux/posix-timers.h>
 #include <linux/livepatch.h>
+#include <linux/cgroup.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/signal.h>
@@ -146,9 +147,10 @@ static inline bool has_pending_signals(sigset_t *signal, sigset_t *blocked)
 
 static bool recalc_sigpending_tsk(struct task_struct *t)
 {
-	if ((t->jobctl & JOBCTL_PENDING_MASK) ||
+	if ((t->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) ||
 	    PENDING(&t->pending, &t->blocked) ||
-	    PENDING(&t->signal->shared_pending, &t->blocked)) {
+	    PENDING(&t->signal->shared_pending, &t->blocked) ||
+	    cgroup_task_frozen(t)) {
 		set_tsk_thread_flag(t, TIF_SIGPENDING);
 		return true;
 	}
@@ -2108,6 +2110,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 		preempt_disable();
 		read_unlock(&tasklist_lock);
 		preempt_enable_no_resched();
+		cgroup_enter_frozen();
 		freezable_schedule();
 	} else {
 		/*
@@ -2286,6 +2289,7 @@ static bool do_signal_stop(int signr)
 		}
 
 		/* Now we don't run again until woken by SIGCONT or SIGKILL */
+		cgroup_enter_frozen();
 		freezable_schedule();
 		return true;
 	} else {
@@ -2332,6 +2336,43 @@ static void do_jobctl_trap(void)
 	}
 }
 
+/**
+ * do_freezer_trap - handle the freezer jobctl trap
+ *
+ * Puts the task into frozen state, if only the task is not about to quit.
+ * In this case it drops JOBCTL_TRAP_FREEZE.
+ *
+ * CONTEXT:
+ * Must be called with @current->sighand->siglock held,
+ * which is always released before returning.
+ */
+static void do_freezer_trap(void)
+	__releases(&current->sighand->siglock)
+{
+	/*
+	 * If there are other trap bits pending except JOBCTL_TRAP_FREEZE,
+	 * let's make another loop to give it a chance to be handled.
+	 * In any case, we'll return back.
+	 */
+	if ((current->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) !=
+	     JOBCTL_TRAP_FREEZE) {
+		spin_unlock_irq(&current->sighand->siglock);
+		return;
+	}
+
+	/*
+	 * Now we're sure that there is no pending fatal signal and no
+	 * pending traps. Clear TIF_SIGPENDING to not get out of schedule()
+	 * immediately (if there is a non-fatal signal pending), and
+	 * put the task into sleep.
+	 */
+	__set_current_state(TASK_INTERRUPTIBLE);
+	clear_thread_flag(TIF_SIGPENDING);
+	spin_unlock_irq(&current->sighand->siglock);
+	cgroup_enter_frozen();
+	freezable_schedule();
+}
+
 static int ptrace_signal(int signr, kernel_siginfo_t *info)
 {
 	/*
@@ -2452,9 +2493,24 @@ bool get_signal(struct ksignal *ksig)
 		    do_signal_stop(0))
 			goto relock;
 
-		if (unlikely(current->jobctl & JOBCTL_TRAP_MASK)) {
+		if (unlikely(current->jobctl &
+			     (JOBCTL_TRAP_MASK | JOBCTL_TRAP_FREEZE))) {
+			if (current->jobctl & JOBCTL_TRAP_MASK) {
 				do_jobctl_trap();
 				spin_unlock_irq(&sighand->siglock);
+			} else if (current->jobctl & JOBCTL_TRAP_FREEZE)
+				do_freezer_trap();
+
+			goto relock;
+		}
+
+		/*
+		 * If the task is leaving the frozen state, let's update
+		 * cgroup counters and reset the frozen bit.
+		 */
+		if (unlikely(cgroup_task_frozen(current))) {
+			spin_unlock_irq(&sighand->siglock);
+			cgroup_leave_frozen(false);
 			goto relock;
 		}
 
@@ -2550,6 +2606,8 @@ bool get_signal(struct ksignal *ksig)
 
 	fatal:
 		spin_unlock_irq(&sighand->siglock);
+		if (unlikely(cgroup_task_frozen(current)))
+			cgroup_leave_frozen(true);
 
 		/*
 		 * Anything else is fatal, maybe with a core dump.

tools/testing/selftests/cgroup/.gitignore

 test_memcontrol
 test_core
+test_freezer

tools/testing/selftests/cgroup/Makefile

@@ -5,8 +5,10 @@ all:
 
 TEST_GEN_PROGS = test_memcontrol
 TEST_GEN_PROGS += test_core
+TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
 $(OUTPUT)/test_memcontrol: cgroup_util.c
 $(OUTPUT)/test_core: cgroup_util.c
+$(OUTPUT)/test_freezer: cgroup_util.c

tools/testing/selftests/cgroup/cgroup_util.c

@@ -74,6 +74,16 @@ char *cg_name_indexed(const char *root, const char *name, int index)
 	return ret;
 }
 
+char *cg_control(const char *cgroup, const char *control)
+{
+	size_t len = strlen(cgroup) + strlen(control) + 2;
+	char *ret = malloc(len);
+
+	snprintf(ret, len, "%s/%s", cgroup, control);
+
+	return ret;
+}
+
 int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
 {
 	char path[PATH_MAX];
@@ -196,7 +206,32 @@ int cg_create(const char *cgroup)
 	return mkdir(cgroup, 0644);
 }
 
-static int cg_killall(const char *cgroup)
+int cg_wait_for_proc_count(const char *cgroup, int count)
+{
+	char buf[10 * PAGE_SIZE] = {0};
+	int attempts;
+	char *ptr;
+
+	for (attempts = 10; attempts >= 0; attempts--) {
+		int nr = 0;
+
+		if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
+			break;
+
+		for (ptr = buf; *ptr; ptr++)
+			if (*ptr == '\n')
+				nr++;
+
+		if (nr >= count)
+			return 0;
+
+		usleep(100000);
+	}
+
+	return -1;
+}
+
+int cg_killall(const char *cgroup)
 {
 	char buf[PAGE_SIZE];
 	char *ptr = buf;
@@ -227,9 +262,7 @@ int cg_destroy(const char *cgroup)
 retry:
 	ret = rmdir(cgroup);
 	if (ret && errno == EBUSY) {
-		ret = cg_killall(cgroup);
-		if (ret)
-			return ret;
+		cg_killall(cgroup);
 		usleep(100);
 		goto retry;
 	}
@@ -240,6 +273,14 @@ int cg_destroy(const char *cgroup)
 	return ret;
 }
 
+int cg_enter(const char *cgroup, int pid)
+{
+	char pidbuf[64];
+
+	snprintf(pidbuf, sizeof(pidbuf), "%d", pid);
+	return cg_write(cgroup, "cgroup.procs", pidbuf);
+}
+
 int cg_enter_current(const char *cgroup)
 {
 	char pidbuf[64];
@@ -369,3 +410,12 @@ int set_oom_adj_score(int pid, int score)
 	close(fd);
 	return 0;
 }
+
+char proc_read_text(int pid, const char *item, char *buf, size_t size)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
+
+	return read_text(path, buf, size);
+}

tools/testing/selftests/cgroup/cgroup_util.h

@@ -18,6 +18,7 @@ static inline int values_close(long a, long b, int err)
 extern int cg_find_unified_root(char *root, size_t len);
 extern char *cg_name(const char *root, const char *name);
 extern char *cg_name_indexed(const char *root, const char *name, int index);
+extern char *cg_control(const char *cgroup, const char *control);
 extern int cg_create(const char *cgroup);
 extern int cg_destroy(const char *cgroup);
 extern int cg_read(const char *cgroup, const char *control,
@@ -32,6 +33,7 @@ extern int cg_write(const char *cgroup, const char *control, char *buf);
 extern int cg_run(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
 		  void *arg);
+extern int cg_enter(const char *cgroup, int pid);
 extern int cg_enter_current(const char *cgroup);
 extern int cg_run_nowait(const char *cgroup,
 			 int (*fn)(const char *cgroup, void *arg),
@@ -41,3 +43,6 @@ extern int alloc_pagecache(int fd, size_t size);
 extern int alloc_anon(const char *cgroup, void *arg);
 extern int is_swap_enabled(void);
 extern int set_oom_adj_score(int pid, int score);
+extern int cg_wait_for_proc_count(const char *cgroup, int count);
+extern int cg_killall(const char *cgroup);
+extern char proc_read_text(int pid, const char *item, char *buf, size_t size);