cgroup: always put cset in cgroup_css_set_put_fork

[ Upstream commit 2bd1103 ]

A successful call to cgroup_css_set_fork() will always have taken
a ref on kargs->cset (regardless of CLONE_INTO_CGROUP), so always
do a corresponding put in cgroup_css_set_put_fork().

Without this, a cset and its contained css structures will be
leaked for some fork failures.  The following script reproduces
the leak for a fork failure due to exceeding pids.max in the
pids controller.  A similar thing can happen if we jump to the
bad_fork_cancel_cgroup label in copy_process().

[ -z "$1" ] && echo "Usage $0 pids-root" && exit 1
PID_ROOT=$1
CGROUP=$PID_ROOT/foo

[ -e $CGROUP ] && rmdir -f $CGROUP
mkdir $CGROUP
echo 5 > $CGROUP/pids.max
echo $$ > $CGROUP/cgroup.procs

fork_bomb()
{
	set -e
	for i in $(seq 10); do
		/bin/sleep 3600 &
	done
}

(fork_bomb) &
wait
echo $$ > $PID_ROOT/cgroup.procs
kill $(cat $CGROUP/cgroup.procs)
rmdir $CGROUP

Fixes: ef2c41c ("clone3: allow spawning processes into cgroups")
Cc: [email protected] # v5.7+
Signed-off-by: John Sperbeck <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>

Author: John Sperbeck

kernel/cgroup/cgroup.c

@@ -6471,19 +6471,18 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	struct cgroup *cgrp = kargs->cgrp;
+	struct css_set *cset = kargs->cset;
+
 	cgroup_threadgroup_change_end(current);
 
-	if (kargs->flags & CLONE_INTO_CGROUP) {
-		struct cgroup *cgrp = kargs->cgrp;
-		struct css_set *cset = kargs->cset;
+	if (cset) {
+		put_css_set(cset);
+		kargs->cset = NULL;
+	}
 
+	if (kargs->flags & CLONE_INTO_CGROUP) {
 		cgroup_unlock();
-
-		if (cset) {
-			put_css_set(cset);
-			kargs->cset = NULL;
-		}
-
 		if (cgrp) {
 			cgroup_put(cgrp);
 			kargs->cgrp = NULL;