@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
void cgroup_sk_alloc_disable(void);
void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
void cgroup_sk_free(struct sock_cgroup_data *skcd);
static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
#else /* CONFIG_CGROUP_DATA */
static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
#endif /* CONFIG_CGROUP_DATA */
@@ -6442,18 +6442,6 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
if (cgroup_sk_alloc_disabled)
return;
- /* Socket clone path */
- if (skcd->val) {
- /*
- * We might be cloning a socket which is left in an empty
- * cgroup and the cgroup might have already been rmdir'd.
- * Don't use cgroup_get_live().
- */
- cgroup_get(sock_cgroup_ptr(skcd));
- cgroup_bpf_get(sock_cgroup_ptr(skcd));
- return;
- }
-
/* Don't associate the sock with unrelated interrupted task's cgroup. */
if (in_interrupt())
return;
@@ -6475,6 +6463,20 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
rcu_read_unlock();
}
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+ /* Socket clone path */
+ if (skcd->val) {
+ /*
+ * We might be cloning a socket which is left in an empty
+ * cgroup and the cgroup might have already been rmdir'd.
+ * Don't use cgroup_get_live().
+ */
+ cgroup_get(sock_cgroup_ptr(skcd));
+ cgroup_bpf_get(sock_cgroup_ptr(skcd));
+ }
+}
+
void cgroup_sk_free(struct sock_cgroup_data *skcd)
{
struct cgroup *cgrp = sock_cgroup_ptr(skcd);
@@ -1925,7 +1925,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
/* sk->sk_memcg will be populated at accept() time */
newsk->sk_memcg = NULL;
- cgroup_sk_alloc(&newsk->sk_cgrp_data);
+ cgroup_sk_clone(&newsk->sk_cgrp_data);
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
When we clone a socket in sk_clone_lock(), its sk_cgrp_data is copied, so the cgroup refcnt must be taken too. And, unlike the sk_alloc() path, sock_update_netprioidx() is not called here. Therefore, it is safe and necessary to grab the cgroup refcnt even when cgroup_sk_alloc is disabled. sk_clone_lock() is in BH context anyway, the in_interrupt() would terminate this function if called there. And for sk_alloc() skcd->val is always zero. So it's safe to factor out the code to make it more readable. Fixes: 090e28b229af92dc5b ("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") Reported-by: Cameron Berkenpas <cam@neo-zeon.de> Reported-by: Peter Geis <pgwipeout@gmail.com> Reported-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com> Reported-by: Daniël Sonck <dsonck92@gmail.com> Tested-by: Cameron Berkenpas <cam@neo-zeon.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Zefan Li <lizefan@huawei.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> --- include/linux/cgroup.h | 2 ++ kernel/cgroup/cgroup.c | 26 ++++++++++++++------------ net/core/sock.c | 2 +- 3 files changed, 17 insertions(+), 13 deletions(-)