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

…it/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

@@ -1,7 +1,7 @@
 # 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
  */