Merge branch 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cgroup.kill is added which implements atomic killing of the whole
   subtree.

   Down the line, this should be able to replace the multiple userland
   implementations of "keep killing till empty".

 - PSI can now be turned off at boot time to avoid overhead for
   configurations which don't care about PSI.

* 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: make per-cgroup pressure stall tracking configurable
  cgroup: Fix kernel-doc
  cgroup: inline cgroup_task_freeze()
  tests/cgroup: test cgroup.kill
  tests/cgroup: move cg_wait_for(), cg_prepare_for_wait()
  tests/cgroup: use cgroup.kill in cg_killall()
  docs/cgroup: add entry for cgroup.kill
  cgroup: introduce cgroup.kill

Documentation/admin-guide/cgroup-v2.rst

@@ -953,6 +953,21 @@ All cgroup core files are prefixed with "cgroup."
 	it's possible to delete a frozen (and empty) cgroup, as well as
 	create new sub-cgroups.
 
+  cgroup.kill
+	A write-only single value file which exists in non-root cgroups.
+	The only allowed value is "1".
+
+	Writing "1" to the file causes the cgroup and all descendant cgroups to
+	be killed. This means that all processes located in the affected cgroup
+	tree will be killed via SIGKILL.
+
+	Killing a cgroup tree will deal with concurrent forks appropriately and
+	is protected against migrations.
+
+	In a threaded cgroup, writing this file fails with EOPNOTSUPP as
+	killing cgroups is a process directed operation, i.e. it affects
+	the whole thread-group.
+
 Controllers
 ===========
 

Documentation/admin-guide/kernel-parameters.txt

@@ -497,16 +497,21 @@
 	ccw_timeout_log	[S390]
 			See Documentation/s390/common_io.rst for details.
 
-	cgroup_disable=	[KNL] Disable a particular controller
-			Format: {name of the controller(s) to disable}
+	cgroup_disable=	[KNL] Disable a particular controller or optional feature
+			Format: {name of the controller(s) or feature(s) to disable}
 			The effects of cgroup_disable=foo are:
 			- foo isn't auto-mounted if you mount all cgroups in
 			  a single hierarchy
 			- foo isn't visible as an individually mountable
 			  subsystem
+			- if foo is an optional feature then the feature is
+			  disabled and corresponding cgroup files are not
+			  created
 			{Currently only "memory" controller deal with this and
 			cut the overhead, others just disable the usage. So
 			only cgroup_disable=memory is actually worthy}
+			Specifying "pressure" disables per-cgroup pressure
+			stall information accounting feature
 
 	cgroup_no_v1=	[KNL] Disable cgroup controllers and named hierarchies in v1
 			Format: { { controller | "all" | "named" }

include/linux/cgroup-defs.h

@@ -71,6 +71,9 @@ enum {
 
 	/* Cgroup is frozen. */
 	CGRP_FROZEN,
+
+	/* Control group has to be killed. */
+	CGRP_KILL,
 };
 
 /* cgroup_root->flags */
@@ -110,6 +113,7 @@ enum {
 	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
 	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
 	CFTYPE_DEBUG		= (1 << 5),	/* create when cgroup_debug */
+	CFTYPE_PRESSURE		= (1 << 6),	/* only if pressure feature is enabled */
 
 	/* internal flags, do not use outside cgroup core proper */
 	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */

include/linux/cgroup.h

@@ -676,6 +676,8 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
 	return &cgrp->psi;
 }
 
+bool cgroup_psi_enabled(void);
+
 static inline void cgroup_init_kthreadd(void)
 {
 	/*
@@ -735,6 +737,11 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
 	return NULL;
 }
 
+static inline bool cgroup_psi_enabled(void)
+{
+	return false;
+}
+
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 					       struct cgroup *ancestor)
 {
@@ -906,20 +913,6 @@ 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;
@@ -929,10 +922,6 @@ static inline bool cgroup_task_frozen(struct task_struct *task)
 
 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;