diff options
| author | Cong Wang <xiyou.wangcong@gmail.com> | 2020-07-02 11:52:56 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2020-07-22 09:22:21 +0200 |
| commit | 82fd2138a5ffd7e0d4320cdb669e115ee976a26e (patch) | |
| tree | 1dfab1ea21075f9526a13cb02c2b806c4e64f734 | |
| parent | c38a32e30a33ba1db775f9b14246baddf405eb9d (diff) | |
| download | linux-82fd2138a5ffd7e0d4320cdb669e115ee976a26e.tar.gz | |
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: 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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | include/linux/cgroup-defs.h | 6 | ||||
| -rw-r--r-- | include/linux/cgroup.h | 4 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 29 | ||||
| -rw-r--r-- | net/core/sock.c | 2 |
4 files changed, 26 insertions, 15 deletions
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8d4b92185a09a..26e74349f0003 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -681,7 +681,8 @@ 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; @@ -691,7 +692,8 @@ 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 61ab21c348661..3be0c9e7e150b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -714,6 +714,7 @@ 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) @@ -727,7 +728,7 @@ 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; @@ -739,6 +740,7 @@ 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/cgroup.c b/kernel/cgroup/cgroup.c index 2b3f2ea6a8a33..a2fed8fbd2bde 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5798,17 +5798,8 @@ 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)); + if (cgroup_sk_alloc_disabled) { + skcd->no_refcnt = 1; return; } @@ -5832,8 +5823,24 @@ 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 08ca2ec0ce60a..af1201676abc3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1689,7 +1689,7 @@ 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); |
