af_unix: fix races in sk_peer_pid and sk_peer_cred accesses

commit 35306eb23814444bd4021f8a1c3047d3cb0c8b2b upstream.

Jann Horn reported that SO_PEERCRED and SO_PEERGROUPS implementations
are racy, as af_unix can concurrently change sk_peer_pid and sk_peer_cred.

In order to fix this issue, this patch adds a new spinlock that needs
to be used whenever these fields are read or written.

Jann also pointed out that l2cap_sock_get_peer_pid_cb() is currently
reading sk->sk_peer_pid which makes no sense, as this field
is only possibly set by AF_UNIX sockets.
We will have to clean this in a separate patch.
This could be done by reverting b48596d1dc25 "Bluetooth: L2CAP: Add get_peer_pid callback"
or implementing what was truly expected.

Fixes: 109f6e39fa07 ("af_unix: Allow SO_PEERCRED to work across namespaces.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jann Horn <jannh@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Cc: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
[backport note: 4.4 and 4.9 don't have SO_PEERGROUPS, only SO_PEERCRED]
[backport note: got rid of sk_get_peer_cred(), no users in 4.4/4.9]
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/net/sock.h b/include/net/sock.h
index cf27f3688c39c93e1c3b2681b377417eceabb51b..78c292f15ffc1c8764106c092833b4858113d920 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -420,8 +420,10 @@ struct sock {
        u32                     sk_max_ack_backlog;
        __u32                   sk_priority;
        __u32                   sk_mark;
+       spinlock_t              sk_peer_lock;
        struct pid              *sk_peer_pid;
        const struct cred       *sk_peer_cred;
+
        long                    sk_rcvtimeo;
        long                    sk_sndtimeo;
        struct timer_list       sk_timer;

diff --git a/net/core/sock.c b/net/core/sock.c
index d468ffb5a31c681b1e569413187a16afb34bc7d0..1845a37d9f7e19261006b344859fb32a404c0661 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1011,7 +1011,6 @@ set_rcvbuf:
 }
 EXPORT_SYMBOL(sock_setsockopt);
 
-
 static void cred_to_ucred(struct pid *pid, const struct cred *cred,
                          struct ucred *ucred)
 {
@@ -1171,7 +1170,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
                struct ucred peercred;
                if (len > sizeof(peercred))
                        len = sizeof(peercred);
+
+               spin_lock(&sk->sk_peer_lock);
                cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
+               spin_unlock(&sk->sk_peer_lock);
+
                if (copy_to_user(optval, &peercred, len))
                        return -EFAULT;
                goto lenout;
@@ -1439,9 +1442,10 @@ static void __sk_destruct(struct rcu_head *head)
                sk->sk_frag.page = NULL;
        }
 
-       if (sk->sk_peer_cred)
-               put_cred(sk->sk_peer_cred);
+       /* We do not need to acquire sk->sk_peer_lock, we are the last user. */
+       put_cred(sk->sk_peer_cred);
        put_pid(sk->sk_peer_pid);
+
        if (likely(sk->sk_net_refcnt))
                put_net(sock_net(sk));
        sk_prot_free(sk->sk_prot_creator, sk);
@@ -2490,6 +2494,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
        sk->sk_peer_pid         =       NULL;
        sk->sk_peer_cred        =       NULL;
+       spin_lock_init(&sk->sk_peer_lock);
+
        sk->sk_write_pending    =       0;
        sk->sk_rcvlowat         =       1;
        sk->sk_rcvtimeo         =       MAX_SCHEDULE_TIMEOUT;

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2c643e1919aab217cebc8c2da591ac4cef14deda..e7e012933714f5eb14363dae6f4a9d548e995818 100644 (file)
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -594,20 +594,42 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 static void init_peercred(struct sock *sk)
 {
-       put_pid(sk->sk_peer_pid);
-       if (sk->sk_peer_cred)
-               put_cred(sk->sk_peer_cred);
+       const struct cred *old_cred;
+       struct pid *old_pid;
+
+       spin_lock(&sk->sk_peer_lock);
+       old_pid = sk->sk_peer_pid;
+       old_cred = sk->sk_peer_cred;
        sk->sk_peer_pid  = get_pid(task_tgid(current));
        sk->sk_peer_cred = get_current_cred();
+       spin_unlock(&sk->sk_peer_lock);
+
+       put_pid(old_pid);
+       put_cred(old_cred);
 }
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
 {
-       put_pid(sk->sk_peer_pid);
-       if (sk->sk_peer_cred)
-               put_cred(sk->sk_peer_cred);
+       const struct cred *old_cred;
+       struct pid *old_pid;
+
+       if (sk < peersk) {
+               spin_lock(&sk->sk_peer_lock);
+               spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+       } else {
+               spin_lock(&peersk->sk_peer_lock);
+               spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+       }
+       old_pid = sk->sk_peer_pid;
+       old_cred = sk->sk_peer_cred;
        sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
        sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
+
+       spin_unlock(&sk->sk_peer_lock);
+       spin_unlock(&peersk->sk_peer_lock);
+
+       put_pid(old_pid);
+       put_cred(old_cred);
 }
 
 static int unix_listen(struct socket *sock, int backlog)