net: fix IP early demux races

[ Upstream commit 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 ]

David Wilder reported crashes caused by dst reuse.

<quote David>
  I am seeing a crash on a distro V4.2.3 kernel caused by a double
  release of a dst_entry.  In ipv4_dst_destroy() the call to
  list_empty() finds a poisoned next pointer, indicating the dst_entry
  has already been removed from the list and freed. The crash occurs
  18 to 24 hours into a run of a network stress exerciser.
</quote>

Thanks to his detailed report and analysis, we were able to understand
the core issue.

IP early demux can associate a dst to skb, after a lookup in TCP/UDP
sockets.

When socket cache is not properly set, we want to store into
sk->sk_dst_cache the dst for future IP early demux lookups,
by acquiring a stable refcount on the dst.

Problem is this acquisition is simply using an atomic_inc(),
which works well, unless the dst was queued for destruction from
dst_release() noticing dst refcount went to zero, if DST_NOCACHE
was set on dst.

We need to make sure current refcount is not zero before incrementing
it, or risk double free as David reported.

This patch, being a stable candidate, adds two new helpers, and use
them only from IP early demux problematic paths.

It might be possible to merge in net-next skb_dst_force() and
skb_dst_force_safe(), but I prefer having the smallest patch for stable
kernels : Maybe some skb_dst_force() callers do not expect skb->dst
can suddenly be cleared.

Can probably be backported back to linux-3.6 kernels

Reported-by: David J. Wilder <dwilder@us.ibm.com>
Tested-by: David J. Wilder <dwilder@us.ibm.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/include/net/dst.h b/include/net/dst.h
index 30cd2f9cd1dd8fa5d3b41347e83ed005bf423fdf..d30afbdc1a5945e9ccc2abae6c24f8c8212b2d93 100644 (file)
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -306,6 +306,39 @@ static inline void skb_dst_force(struct sk_buff *skb)
        }
 }
 
+/**
+ * dst_hold_safe - Take a reference on a dst if possible
+ * @dst: pointer to dst entry
+ *
+ * This helper returns false if it could not safely
+ * take a reference on a dst.
+ */
+static inline bool dst_hold_safe(struct dst_entry *dst)
+{
+       if (dst->flags & DST_NOCACHE)
+               return atomic_inc_not_zero(&dst->__refcnt);
+       dst_hold(dst);
+       return true;
+}
+
+/**
+ * skb_dst_force_safe - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ */
+static inline void skb_dst_force_safe(struct sk_buff *skb)
+{
+       if (skb_dst_is_noref(skb)) {
+               struct dst_entry *dst = skb_dst(skb);
+
+               if (!dst_hold_safe(dst))
+                       dst = NULL;
+
+               skb->_skb_refdst = (unsigned long)dst;
+       }
+}
+
 
 /**
  *     __skb_tunnel_rx - prepare skb for rx reinsert

diff --git a/include/net/sock.h b/include/net/sock.h
index 41d98f1d0459ce1d53e82b032eae7c8ecdf2c082..6ed6df149bce16598f9b6be06f2c7674de62efa5 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -760,7 +760,7 @@ extern void sk_stream_write_space(struct sock *sk);
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
        /* dont let skb dst not refcounted, we are going to leave rcu lock */
-       skb_dst_force(skb);
+       skb_dst_force_safe(skb);
 
        if (!sk->sk_backlog.tail)
                sk->sk_backlog.head = skb;

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 624ceca7ffd1a83214f18a902e2cceaebd7733ef..09451a2cbd6a672e2f56424c32d8feb63839f325 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1905,7 +1905,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
            skb_queue_len(&tp->ucopy.prequeue) == 0)
                return false;
 
-       skb_dst_force(skb);
+       skb_dst_force_safe(skb);
        __skb_queue_tail(&tp->ucopy.prequeue, skb);
        tp->ucopy.memory += skb->truesize;
        if (tp->ucopy.memory > sk->sk_rcvbuf) {
@@ -2098,9 +2098,10 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
        struct dst_entry *dst = skb_dst(skb);
 
-       dst_hold(dst);
-       sk->sk_rx_dst = dst;
-       inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+       if (dst_hold_safe(dst)) {
+               sk->sk_rx_dst = dst;
+               inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+       }
 }
 EXPORT_SYMBOL(inet_sk_rx_dst_set);
 

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 65c310d6e92a40b02f1af025b966791c5916b652..90004c6e3bff715fd44fa1ce18bacdf8fa9545a3 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -97,11 +97,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
        struct dst_entry *dst = skb_dst(skb);
        const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-       dst_hold(dst);
-       sk->sk_rx_dst = dst;
-       inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-       if (rt->rt6i_node)
-               inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+       if (dst_hold_safe(dst)) {
+               sk->sk_rx_dst = dst;
+               inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+               if (rt->rt6i_node)
+                       inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+       }
 }
 
 static void tcp_v6_hash(struct sock *sk)