3 files changed, 23 insertions, 48 deletions

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/dmem.c b/kernel/cgroup/dmem.c
index fbe34299673d..10b63433f057 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -220,60 +220,32 @@ dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool,
 				 struct dmem_cgroup_pool_state *test_pool)
 {
 	struct page_counter *climit;
-	struct cgroup_subsys_state *css, *next_css;
+	struct cgroup_subsys_state *css;
 	struct dmemcg_state *dmemcg_iter;
-	struct dmem_cgroup_pool_state *pool, *parent_pool;
-	bool found_descendant;
+	struct dmem_cgroup_pool_state *pool, *found_pool;
 
 	climit = &limit_pool->cnt;
 
 	rcu_read_lock();
-	parent_pool = pool = limit_pool;
-	css = &limit_pool->cs->css;
 
-	/*
-	 * This logic is roughly equivalent to css_foreach_descendant_pre,
-	 * except we also track the parent pool to find out which pool we need
-	 * to calculate protection values for.
-	 *
-	 * We can stop the traversal once we find test_pool among the
-	 * descendants since we don't really care about any others.
-	 */
-	while (pool != test_pool) {
-		next_css = css_next_child(NULL, css);
-		if (next_css) {
-			parent_pool = pool;
-		} else {
-			while (css != &limit_pool->cs->css) {
-				next_css = css_next_child(css, css->parent);
-				if (next_css)
-					break;
-				css = css->parent;
-				parent_pool = pool_parent(parent_pool);
-			}
-			/*
-			 * We can only hit this when test_pool is not a
-			 * descendant of limit_pool.
-			 */
-			if (WARN_ON_ONCE(css == &limit_pool->cs->css))
-				break;
-		}
-		css = next_css;
-
-		found_descendant = false;
+	css_for_each_descendant_pre(css, &limit_pool->cs->css) {
 		dmemcg_iter = container_of(css, struct dmemcg_state, css);
+		found_pool = NULL;
 
 		list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) {
-			if (pool_parent(pool) == parent_pool) {
-				found_descendant = true;
+			if (pool->region == limit_pool->region) {
+				found_pool = pool;
 				break;
 			}
 		}
-		if (!found_descendant)
+		if (!found_pool)
 			continue;
 
 		page_counter_calculate_protection(
-			climit, &pool->cnt, true);
+			climit, &found_pool->cnt, true);
+
+		if (found_pool == test_pool)
+			break;
 	}
 	rcu_read_unlock();
 }
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];