netfilter: tproxy: do not assign timewait sockets to skb->sk

Assigning a socket in timewait state to skb->sk can trigger
kernel oops, e.g. in nfnetlink_log, which does:

if (skb->sk) {
        read_lock_bh(&skb->sk->sk_callback_lock);
        if (skb->sk->sk_socket && skb->sk->sk_socket->file) ...

in the timewait case, accessing sk->sk_callback_lock and sk->sk_socket
is invalid.

Either all of these spots will need to add a test for sk->sk_state != TCP_TIME_WAIT,
or xt_TPROXY must not assign a timewait socket to skb->sk.

This does the latter.

If a TW socket is found, assign the tproxy nfmark, but skip the skb->sk assignment,
thus mimicking behaviour of a '-m socket .. -j MARK/ACCEPT' re-routing rule.

The 'SYN to TW socket' case is left unchanged -- we try to redirect to the
listener socket.

Cc: Balazs Scheidler <bazsi@balabit.hu>
Cc: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

3 files changed, 43 insertions, 19 deletions

diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index 4d87befb04c..474d621cbc2 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -28,26 +28,23 @@ nf_tproxy_destructor(struct sk_buff *skb)
         skb->destructor = NULL;
 
         if (sk)
-                nf_tproxy_put_sock(sk);
+                sock_put(sk);
 }
 
 /* consumes sk */
-int
+void
 nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
 {
-        bool transparent = (sk->sk_state == TCP_TIME_WAIT) ?
-                                inet_twsk(sk)->tw_transparent :
-                                inet_sk(sk)->transparent;
-
-        if (transparent) {
-                skb_orphan(skb);
-                skb->sk = sk;
-                skb->destructor = nf_tproxy_destructor;
-                return 1;
-        } else
-                nf_tproxy_put_sock(sk);
-
-        return 0;
+        /* assigning tw sockets complicates things; most
+         * skb->sk->X checks would have to test sk->sk_state first */
+        if (sk->sk_state == TCP_TIME_WAIT) {
+                inet_twsk_put(inet_twsk(sk));
+                return;
+        }
+
+        skb_orphan(skb);
+        skb->sk = sk;
+        skb->destructor = nf_tproxy_destructor;
 }
 EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock);
 
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 640678f47a2..dcfd57eb9d0 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -33,6 +33,20 @@
 #include <net/netfilter/nf_tproxy_core.h>
 #include <linux/netfilter/xt_TPROXY.h>
 
+static bool tproxy_sk_is_transparent(struct sock *sk)
+{
+        if (sk->sk_state != TCP_TIME_WAIT) {
+                if (inet_sk(sk)->transparent)
+                        return true;
+                sock_put(sk);
+        } else {
+                if (inet_twsk(sk)->tw_transparent)
+                        return true;
+                inet_twsk_put(inet_twsk(sk));
+        }
+        return false;
+}
+
 static inline __be32
 tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 {
@@ -141,7 +155,7 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
                                            skb->dev, NFT_LOOKUP_LISTENER);
 
         /* NOTE: assign_sock consumes our sk reference */
-        if (sk && nf_tproxy_assign_sock(skb, sk)) {
+        if (sk && tproxy_sk_is_transparent(sk)) {
                 /* This should be in a separate target, but we don't do multiple
                    targets on the same rule yet */
                 skb->mark = (skb->mark & ~mark_mask) ^ mark_value;
@@ -149,6 +163,8 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
                 pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n",
                          iph->protocol, &iph->daddr, ntohs(hp->dest),
                          &laddr, ntohs(lport), skb->mark);
+
+                nf_tproxy_assign_sock(skb, sk);
                 return NF_ACCEPT;
         }
 
@@ -306,7 +322,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
                                            par->in, NFT_LOOKUP_LISTENER);
 
         /* NOTE: assign_sock consumes our sk reference */
-        if (sk && nf_tproxy_assign_sock(skb, sk)) {
+        if (sk && tproxy_sk_is_transparent(sk)) {
                 /* This should be in a separate target, but we don't do multiple
                    targets on the same rule yet */
                 skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;
@@ -314,6 +330,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
                 pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n",
                          tproto, &iph->saddr, ntohs(hp->source),
                          laddr, ntohs(lport), skb->mark);
+
+                nf_tproxy_assign_sock(skb, sk);
                 return NF_ACCEPT;
         }
 
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 00d6ae83830..9cc46356b57 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -35,6 +35,15 @@
 #include <net/netfilter/nf_conntrack.h>
 #endif
 
+static void
+xt_socket_put_sk(struct sock *sk)
+{
+        if (sk->sk_state == TCP_TIME_WAIT)
+                inet_twsk_put(inet_twsk(sk));
+        else
+                sock_put(sk);
+}
+
 static int
 extract_icmp4_fields(const struct sk_buff *skb,
                     u8 *protocol,
@@ -164,7 +173,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
                                        (sk->sk_state == TCP_TIME_WAIT &&
                                         inet_twsk(sk)->tw_transparent));
 
-                nf_tproxy_put_sock(sk);
+                xt_socket_put_sk(sk);
 
                 if (wildcard || !transparent)
                         sk = NULL;
@@ -298,7 +307,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
                                        (sk->sk_state == TCP_TIME_WAIT &&
                                         inet_twsk(sk)->tw_transparent));
 
-                nf_tproxy_put_sock(sk);
+                xt_socket_put_sk(sk);
 
                 if (wildcard || !transparent)
                         sk = NULL;