summaryrefslogtreecommitdiff
path: root/kernel/cgroup
diff options
context:
space:
mode:
authorCong Wang <xiyou.wangcong@gmail.com>2020-07-02 11:52:56 -0700
committerDavid S. Miller <davem@davemloft.net>2020-07-07 13:34:11 -0700
commitad0f75e5f57ccbceec13274e1e242f2b5a6397ed (patch)
tree0731a3f8fd336dcc5e7724aa5fac075fb842639c /kernel/cgroup
parentaea23c323d89836bcdcee67e49def997ffca043b (diff)
cgroup: fix cgroup_sk_alloc() for sk_clone_lock()
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. The global variable 'cgroup_sk_alloc_disabled' is used to determine whether to take these reference counts. It is impossible to make the reference counting correct unless we save this bit of information in skcd->val. So, add a new bit there to record whether the socket has already taken the reference counts. This obviously relies on kmalloc() to align cgroup pointers to at least 4 bytes, ARCH_KMALLOC_MINALIGN is certainly larger than that. This bug seems to be introduced since the beginning, commit d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets") tried to fix it but not compeletely. It seems not easy to trigger until the recent commit 090e28b229af ("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged. Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") 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: Daniƫl Sonck <dsonck92@gmail.com> Reported-by: Zhang Qiang <qiang.zhang@windriver.com> Tested-by: Cameron Berkenpas <cam@neo-zeon.de> Tested-by: Peter Geis <pgwipeout@gmail.com> Tested-by: Thomas Lamprecht <t.lamprecht@proxmox.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Zefan Li <lizefan@huawei.com> Cc: Tejun Heo <tj@kernel.org> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/cgroup')
-rw-r--r--kernel/cgroup/cgroup.c31
1 files changed, 19 insertions, 12 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1ea181a58465..dd247747ec14 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6439,18 +6439,8 @@ void cgroup_sk_alloc_disable(void)
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));
+ if (cgroup_sk_alloc_disabled) {
+ skcd->no_refcnt = 1;
return;
}
@@ -6475,10 +6465,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
rcu_read_unlock();
}
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+ if (skcd->val) {
+ if (skcd->no_refcnt)
+ return;
+ /*
+ * 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);
+ if (skcd->no_refcnt)
+ return;
cgroup_bpf_put(cgrp);
cgroup_put(cgrp);
}