soreuseport: fix initialization race

Syzkaller stumbled upon a way to trigger
WARNING: CPU: 1 PID: 13881 at net/core/sock_reuseport.c:41
reuseport_alloc+0x306/0x3b0 net/core/sock_reuseport.c:39

There are two initialization paths for the sock_reuseport structure in a
socket: Through the udp/tcp bind paths of SO_REUSEPORT sockets or through
SO_ATTACH_REUSEPORT_[CE]BPF before bind.  The existing implementation
assumedthat the socket lock protected both of these paths when it actually
only protects the SO_ATTACH_REUSEPORT path.  Syzkaller triggered this
double allocation by running these paths concurrently.

This patch moves the check for double allocation into the reuseport_alloc
function which is protected by a global spin lock.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: c125e80b8868 ("soreuseport: fast reuseport TCP socket selection")
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index eed1ebf..b1e0dbe 100644 (file)
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk)
         * soft irq of receive path or setsockopt from process context
         */
        spin_lock_bh(&reuseport_lock);
-       WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-                                           lockdep_is_held(&reuseport_lock)),
-                 "multiple allocations for the same socket");
+
+       /* Allocation attempts can occur concurrently via the setsockopt path
+        * and the bind/hash path.  Nothing to do when we lose the race.
+        */
+       if (rcu_dereference_protected(sk->sk_reuseport_cb,
+                                     lockdep_is_held(&reuseport_lock)))
+               goto out;
+
        reuse = __reuseport_alloc(INIT_SOCKS);
        if (!reuse) {
                spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk)
        reuse->num_socks = 1;
        rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
+out:
        spin_unlock_bh(&reuseport_lock);
 
        return 0;

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 597bb4c..e7d15fb 100644 (file)
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -456,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
                        return reuseport_add_sock(sk, sk2);
        }
 
-       /* Initial allocation may have already happened via setsockopt */
-       if (!rcu_access_pointer(sk->sk_reuseport_cb))
-               return reuseport_alloc(sk);
-       return 0;
+       return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 806b298..ebfbcca 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
                }
        }
 
-       /* Initial allocation may have already happened via setsockopt */
-       if (!rcu_access_pointer(sk->sk_reuseport_cb))
-               return reuseport_alloc(sk);
-       return 0;
+       return reuseport_alloc(sk);
 }
 
 /**