cgroup: fix cgroup_sk_alloc() for sk_clone_lock()

[ Upstream commit ad0f75e5f57ccbceec13274e1e242f2b5a6397ed ]

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: Daniël 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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1619a3213af5d2ef5863c4c8a1fda991c807506e..8428a4cb2c05ffd18d9b1183817b6e61500291ec 100644 (file)
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -587,7 +587,8 @@ struct sock_cgroup_data {
        union {
 #ifdef __LITTLE_ENDIAN
                struct {
-                       u8      is_data;
+                       u8      is_data : 1;
+                       u8      no_refcnt : 1;
                        u8      padding;
                        u16     prioidx;
                        u32     classid;
@@ -597,7 +598,8 @@ struct sock_cgroup_data {
                        u32     classid;
                        u16     prioidx;
                        u8      padding;
-                       u8      is_data;
+                       u8      no_refcnt : 1;
+                       u8      is_data : 1;
                } __packed;
 #endif
                u64             val;

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8be03520995cd899a82f8c694327d7ee0cb7d6e8..75fbf932db50fabd3e6521cd965d9591d2f79ef9 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -657,6 +657,7 @@ 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)
@@ -670,7 +671,7 @@ 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;
@@ -682,6 +683,7 @@ 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 */

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2d7a4fc42a88c2465bca3f30997d0c59c4b528a7..f047c73189f36bc8910970a94ea8d0aabfac6adb 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -6326,12 +6326,8 @@ 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) {
-               cgroup_get(sock_cgroup_ptr(skcd));
+       if (cgroup_sk_alloc_disabled) {
+               skcd->no_refcnt = 1;
                return;
        }
 
@@ -6355,8 +6351,24 @@ 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));
+       }
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
+       if (skcd->no_refcnt)
+               return;
+
        cgroup_put(sock_cgroup_ptr(skcd));
 }
 

diff --git a/net/core/sock.c b/net/core/sock.c
index dac9365151df958e79df78bf8084dac84170577f..3be209f7496540e2cbb723bbb296f6ce2a0c9c1e 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1533,7 +1533,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                newsk->sk_userlocks     = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
                sock_reset_flag(newsk, SOCK_DONE);
-               cgroup_sk_alloc(&newsk->sk_cgrp_data);
+               cgroup_sk_clone(&newsk->sk_cgrp_data);
                skb_queue_head_init(&newsk->sk_error_queue);
 
                filter = rcu_dereference_protected(newsk->sk_filter, 1);