net: add limit for socket backlog

We got system OOM while running some UDP netperf testing on the loopback
device. The case is multiple senders sent stream UDP packets to a single
receiver via loopback on local host. Of course, the receiver is not able
to handle all the packets in time. But we surprisingly found that these
packets were not discarded due to the receiver's sk->sk_rcvbuf limit.
Instead, they are kept queuing to sk->sk_backlog and finally ate up all
the memory. We believe this is a secure hole that a none privileged user
can crash the system.

The root cause for this problem is, when the receiver is doing
__release_sock() (i.e. after userspace recv, kernel udp_recvmsg ->
skb_free_datagram_locked -> release_sock), it moves skbs from backlog to
sk_receive_queue with the softirq enabled. In the above case, multiple
busy senders will almost make it an endless loop. The skbs in the
backlog end up eat all the system memory.

The issue is not only for UDP. Any protocols using socket backlog is
potentially affected. The patch adds limit for socket backlog so that
the backlog size cannot be expanded endlessly.

Reported-by: Alex Shi <alex.shi@intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru
Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Vlad Yasevich <vladislav.yasevich@hp.com>
Cc: Sridhar Samudrala <sri@us.ibm.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Allan Stephens <allan.stephens@windriver.com>
Cc: Andrew Hendry <andrew.hendry@gmail.com>
Signed-off-by: Zhu Yi <yi.zhu@intel.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sock.h b/include/net/sock.h
index 6cb1676e409a865f2fb7c21317e2519e1382e847..2516d76f043c5285e68ef78d15e15eece599e0a4 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -253,6 +253,8 @@ struct sock {
        struct {
                struct sk_buff *head;
                struct sk_buff *tail;
+               int len;
+               int limit;
        } sk_backlog;
        wait_queue_head_t       *sk_sleep;
        struct dst_entry        *sk_dst_cache;
@@ -589,7 +591,7 @@ static inline int sk_stream_memory_free(struct sock *sk)
        return sk->sk_wmem_queued < sk->sk_sndbuf;
 }
 
-/* The per-socket spinlock must be held here. */
+/* OOB backlog add */
 static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
        if (!sk->sk_backlog.tail) {
@@ -601,6 +603,17 @@ static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
        skb->next = NULL;
 }
 
+/* The per-socket spinlock must be held here. */
+static inline int sk_add_backlog_limited(struct sock *sk, struct sk_buff *skb)
+{
+       if (sk->sk_backlog.len >= max(sk->sk_backlog.limit, sk->sk_rcvbuf << 1))
+               return -ENOBUFS;
+
+       sk_add_backlog(sk, skb);
+       sk->sk_backlog.len += skb->truesize;
+       return 0;
+}
+
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
        return sk->sk_backlog_rcv(sk, skb);

diff --git a/net/core/sock.c b/net/core/sock.c
index fcd397a762ff37d43846bb19a4db0211d9b88ae7..6e22dc973d23305692182f8b830937b96e2ffbce 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -340,8 +340,12 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
                rc = sk_backlog_rcv(sk, skb);
 
                mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
-       } else
-               sk_add_backlog(sk, skb);
+       } else if (sk_add_backlog_limited(sk, skb)) {
+               bh_unlock_sock(sk);
+               atomic_inc(&sk->sk_drops);
+               goto discard_and_relse;
+       }
+
        bh_unlock_sock(sk);
 out:
        sock_put(sk);
@@ -1139,6 +1143,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
                sock_lock_init(newsk);
                bh_lock_sock(newsk);
                newsk->sk_backlog.head  = newsk->sk_backlog.tail = NULL;
+               newsk->sk_backlog.len = 0;
 
                atomic_set(&newsk->sk_rmem_alloc, 0);
                /*
@@ -1542,6 +1547,12 @@ static void __release_sock(struct sock *sk)
 
                bh_lock_sock(sk);
        } while ((skb = sk->sk_backlog.head) != NULL);
+
+       /*
+        * Doing the zeroing here guarantee we can not loop forever
+        * while a wild producer attempts to flood us.
+        */
+       sk->sk_backlog.len = 0;
 }
 
 /**
@@ -1874,6 +1885,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
        sk->sk_allocation       =       GFP_KERNEL;
        sk->sk_rcvbuf           =       sysctl_rmem_default;
        sk->sk_sndbuf           =       sysctl_wmem_default;
+       sk->sk_backlog.limit    =       sk->sk_rcvbuf << 1;
        sk->sk_state            =       TCP_CLOSE;
        sk_set_socket(sk, sock);