Merge tag 'cgroup-for-6.14-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Fix a race window where a newly forked task could escape cgroup.kill

 - Remove incorrectly included steal time from cpu.stat::usage_usec

 - Minor update in selftest

* tag 'cgroup-for-6.14-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Remove steal time from usage_usec
  selftests/cgroup: use bash in test_cpuset_v1_hp.sh
  cgroup: fix race between fork and cgroup.kill

5 files changed, 17 insertions, 13 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1b20d2d8ef7c..17960a1e858d 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -71,9 +71,6 @@ enum {
 
 	/* Cgroup is frozen. */
 	CGRP_FROZEN,
-
-	/* Control group has to be killed. */
-	CGRP_KILL,
 };
 
 /* cgroup_root->flags */
@@ -461,6 +458,9 @@ struct cgroup {
 
 	int nr_threaded_children;	/* # of live threaded child cgroups */
 
+	/* sequence number for cgroup.kill, serialized by css_set_lock. */
+	unsigned int kill_seq;
+
 	struct kernfs_node *kn;		/* cgroup kernfs entry */
 	struct cgroup_file procs_file;	/* handle for "cgroup.procs" */
 	struct cgroup_file events_file;	/* handle for "cgroup.events" */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 0f2aeb37bbb0..ca1db4b92c32 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -43,6 +43,7 @@ struct kernel_clone_args {
 	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
+	unsigned int kill_seq;
 };
 
 /*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d9061bd55436..afc665b7b1fe 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4013,7 +4013,7 @@ static void __cgroup_kill(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
-	set_bit(CGRP_KILL, &cgrp->flags);
+	cgrp->kill_seq++;
 	spin_unlock_irq(&css_set_lock);
 
 	css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it);
@@ -4029,10 +4029,6 @@ static void __cgroup_kill(struct cgroup *cgrp)
 		send_sig(SIGKILL, task, 0);
 	}
 	css_task_iter_end(&it);
-
-	spin_lock_irq(&css_set_lock);
-	clear_bit(CGRP_KILL, &cgrp->flags);
-	spin_unlock_irq(&css_set_lock);
 }
 
 static void cgroup_kill(struct cgroup *cgrp)
@@ -6488,6 +6484,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	spin_lock_irq(&css_set_lock);
 	cset = task_css_set(current);
 	get_css_set(cset);
+	if (kargs->cgrp)
+		kargs->kill_seq = kargs->cgrp->kill_seq;
+	else
+		kargs->kill_seq = cset->dfl_cgrp->kill_seq;
 	spin_unlock_irq(&css_set_lock);
 
 	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
@@ -6668,6 +6668,7 @@ void cgroup_post_fork(struct task_struct *child,
 		      struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	unsigned int cgrp_kill_seq = 0;
 	unsigned long cgrp_flags = 0;
 	bool kill = false;
 	struct cgroup_subsys *ss;
@@ -6681,10 +6682,13 @@ void cgroup_post_fork(struct task_struct *child,
 
 	/* init tasks are special, only link regular threads */
 	if (likely(child->pid)) {
-		if (kargs->cgrp)
+		if (kargs->cgrp) {
 			cgrp_flags = kargs->cgrp->flags;
-		else
+			cgrp_kill_seq = kargs->cgrp->kill_seq;
+		} else {
 			cgrp_flags = cset->dfl_cgrp->flags;
+			cgrp_kill_seq = cset->dfl_cgrp->kill_seq;
+		}
 
 		WARN_ON_ONCE(!list_empty(&child->cg_list));
 		cset->nr_tasks++;
@@ -6719,7 +6723,7 @@ void cgroup_post_fork(struct task_struct *child,
 		 * child down right after we finished preparing it for
 		 * userspace.
 		 */
-		kill = test_bit(CGRP_KILL, &cgrp_flags);
+		kill = kargs->kill_seq != cgrp_kill_seq;
 	}
 
 	spin_unlock_irq(&css_set_lock);
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 5877974ece92..aac91466279f 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -590,7 +590,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 
 		cputime->sum_exec_runtime += user;
 		cputime->sum_exec_runtime += sys;
-		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
 
 #ifdef CONFIG_SCHED_CORE
 		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
index 3f45512fb512..7406c24be1ac 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # Test the special cpuset v1 hotplug case where a cpuset become empty of