summaryrefslogtreecommitdiff
path: root/include/linux/cgroup.h
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 /include/linux/cgroup.h
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 'include/linux/cgroup.h')
-rw-r--r--include/linux/cgroup.h4
1 files changed, 3 insertions, 1 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4598e4da6b1b..618838c48313 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -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)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
*/
v = READ_ONCE(skcd->val);
- if (v & 1)
+ if (v & 3)
return &cgrp_dfl_root.cgrp;
return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -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 */