udp: add rehash on connect()

commit 719f835853a92f6090258114a72ffe41f09155cd upstream

commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation)
added a secondary hash on UDP, hashed on (local addr, local port).

Problem is that following sequence :

fd = socket(...)
connect(fd, &remote, ...)

not only selects remote end point (address and port), but also sets
local address, while UDP stack stored in secondary hash table the socket
while its local address was INADDR_ANY (or ipv6 equivalent)

Sequence is :
 - autobind() : choose a random local port, insert socket in hash tables
              [while local address is INADDR_ANY]
 - connect() : set remote address and port, change local address to IP
              given by a route lookup.

When an incoming UDP frame comes, if more than 10 sockets are found in
primary hash table, we switch to secondary table, and fail to find
socket because its local address changed.

One solution to this problem is to rehash datagram socket if needed.

We add a new rehash(struct socket *) method in "struct proto", and
implement this method for UDP v4 & v6, using a common helper.

This rehashing only takes care of secondary hash table, since primary
hash (based on local port only) is not changed.

Reported-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>

diff --git a/include/net/sock.h b/include/net/sock.h
index d91052888fc0b39a01ab94073bb8a1e071cd99d1..efb5730bd57a4c51775cea96a3373dbabaedfc8c 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -697,6 +697,7 @@ struct proto {
        /* Keeping track of sk's, looking them up, and port selection methods. */
        void                    (*hash)(struct sock *sk);
        void                    (*unhash)(struct sock *sk);
+       void                    (*rehash)(struct sock *sk);
        int                     (*get_port)(struct sock *sk, unsigned short snum);
 
        /* Keeping track of sockets in use */

diff --git a/include/net/udp.h b/include/net/udp.h
index 5348d80b25bb8a0593c9f0a80f42c4a6b2aeebc9..4201dc8724ca2e82756014a13da037f3baf3c2e6 100644 (file)
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -151,6 +151,7 @@ static inline void udp_lib_hash(struct sock *sk)
 }
 
 extern void udp_lib_unhash(struct sock *sk);
+extern void udp_lib_rehash(struct sock *sk, u16 new_hash);
 
 static inline void udp_lib_close(struct sock *sk, long timeout)
 {

diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index fb2465811b48658b6be95d6cfd2498c3f8d41da7..31cafd491dde07b6a9217ed3e64f5db7ca8279df 100644 (file)
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
        }
        if (!inet->inet_saddr)
                inet->inet_saddr = rt->rt_src;  /* Update source address */
-       if (!inet->inet_rcv_saddr)
+       if (!inet->inet_rcv_saddr) {
                inet->inet_rcv_saddr = rt->rt_src;
+               if (sk->sk_prot->rehash)
+                       sk->sk_prot->rehash(sk);
+       }
        inet->inet_daddr = rt->rt_dst;
        inet->inet_dport = usin->sin_port;
        sk->sk_state = TCP_ESTABLISHED;

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c36522a0f1130005f96bd11fc385c42d949c6e80..a4e2deeebeec0c1f33b20b6dc132896aff09d05f 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1256,6 +1256,49 @@ void udp_lib_unhash(struct sock *sk)
 }
 EXPORT_SYMBOL(udp_lib_unhash);
 
+/*
+ * inet_rcv_saddr was changed, we must rehash secondary hash
+ */
+void udp_lib_rehash(struct sock *sk, u16 newhash)
+{
+       if (sk_hashed(sk)) {
+               struct udp_table *udptable = sk->sk_prot->h.udp_table;
+               struct udp_hslot *hslot, *hslot2, *nhslot2;
+
+               hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
+               nhslot2 = udp_hashslot2(udptable, newhash);
+               udp_sk(sk)->udp_portaddr_hash = newhash;
+               if (hslot2 != nhslot2) {
+                       hslot = udp_hashslot(udptable, sock_net(sk),
+                                            udp_sk(sk)->udp_port_hash);
+                       /* we must lock primary chain too */
+                       spin_lock_bh(&hslot->lock);
+
+                       spin_lock(&hslot2->lock);
+                       hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+                       hslot2->count--;
+                       spin_unlock(&hslot2->lock);
+
+                       spin_lock(&nhslot2->lock);
+                       hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+                                                &nhslot2->head);
+                       nhslot2->count++;
+                       spin_unlock(&nhslot2->lock);
+
+                       spin_unlock_bh(&hslot->lock);
+               }
+       }
+}
+EXPORT_SYMBOL(udp_lib_rehash);
+
+static void udp_v4_rehash(struct sock *sk)
+{
+       u16 new_hash = udp4_portaddr_hash(sock_net(sk),
+                                         inet_sk(sk)->inet_rcv_saddr,
+                                         inet_sk(sk)->inet_num);
+       udp_lib_rehash(sk, new_hash);
+}
+
 static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
        int rc = sock_queue_rcv_skb(sk, skb);
@@ -1831,6 +1874,7 @@ struct proto udp_prot = {
        .backlog_rcv       = __udp_queue_rcv_skb,
        .hash              = udp_lib_hash,
        .unhash            = udp_lib_unhash,
+       .rehash            = udp_v4_rehash,
        .get_port          = udp_v4_get_port,
        .memory_allocated  = &udp_memory_allocated,
        .sysctl_mem        = sysctl_udp_mem,

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 61573885e4517abca63a36ae1f30999470ef2a32..fc9db30c9ec0bdaf281d519510b4662d5216bbac 100644 (file)
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -104,9 +104,12 @@ ipv4_connected:
                if (ipv6_addr_any(&np->saddr))
                        ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 
-               if (ipv6_addr_any(&np->rcv_saddr))
+               if (ipv6_addr_any(&np->rcv_saddr)) {
                        ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
                                               &np->rcv_saddr);
+                       if (sk->sk_prot->rehash)
+                               sk->sk_prot->rehash(sk);
+               }
 
                goto out;
        }
@@ -191,6 +194,8 @@ ipv4_connected:
        if (ipv6_addr_any(&np->rcv_saddr)) {
                ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
                inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+               if (sk->sk_prot->rehash)
+                       sk->sk_prot->rehash(sk);
        }
 
        ip6_dst_store(sk, dst,

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 90824852f598d34f4c544392e247a6f93a7bd0b0..be5e5a1a683ec89b77f5ae5ee94b1f7e7890fa95 100644 (file)
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
        return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
 }
 
+static void udp_v6_rehash(struct sock *sk)
+{
+       u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+                                         &inet6_sk(sk)->rcv_saddr,
+                                         inet_sk(sk)->inet_num);
+
+       udp_lib_rehash(sk, new_hash);
+}
+
 static inline int compute_score(struct sock *sk, struct net *net,
                                unsigned short hnum,
                                struct in6_addr *saddr, __be16 sport,
@@ -1430,6 +1439,7 @@ struct proto udpv6_prot = {
        .backlog_rcv       = udpv6_queue_rcv_skb,
        .hash              = udp_lib_hash,
        .unhash            = udp_lib_unhash,
+       .rehash            = udp_v6_rehash,
        .get_port          = udp_v6_get_port,
        .memory_allocated  = &udp_memory_allocated,
        .sysctl_mem        = sysctl_udp_mem,