Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:

	net/mac80211/tx.c

7 files changed, 102 insertions, 30 deletions

diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 04578593e100..d2a887fc8d9b 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -556,7 +556,6 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
 
         spin_lock_bh(&nf_nat_lock);
         hlist_del_rcu(&nat->bysource);
-        nat->ct = NULL;
         spin_unlock_bh(&nf_nat_lock);
 }
 
@@ -570,8 +569,8 @@ static void nf_nat_move_storage(void *new, void *old)
                 return;
 
         spin_lock_bh(&nf_nat_lock);
-        hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource);
         new_nat->ct = ct;
+        hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource);
         spin_unlock_bh(&nf_nat_lock);
 }
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 584e6d74e3a9..7135279f3f84 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -52,7 +52,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
                 IP_ECN_clear(top_iph);
 
         top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
-                            0 : XFRM_MODE_SKB_CB(skb)->frag_off;
+                0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
         ip_select_ident(top_iph, dst->child, NULL);
 
         top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 195cb6dd02a0..ce06e791bf43 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1567,7 +1567,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb,
          * make it big enough for everything we may ever need.
          */
 
-        if (head_need > 0 || skb_header_cloned(skb)) {
+        if (head_need > 0 || skb_cloned(skb)) {
                 head_need += IEEE80211_ENCRYPT_HEADROOM;
                 head_need += local->tx_headroom;
                 head_need = max_t(int, 0, head_need);
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index ba1c4915e9eb..3469bc71a385 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -59,12 +59,19 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp)
         if (!*ext)
                 return NULL;
 
+        INIT_RCU_HEAD(&(*ext)->rcu);
         (*ext)->offset[id] = off;
         (*ext)->len = len;
 
         return (void *)(*ext) + off;
 }
 
+static void __nf_ct_ext_free_rcu(struct rcu_head *head)
+{
+        struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu);
+        kfree(ext);
+}
+
 void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 {
         struct nf_ct_ext *new;
@@ -104,7 +111,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
                                         (void *)ct->ext + ct->ext->offset[i]);
                         rcu_read_unlock();
                 }
-                kfree(ct->ext);
+                call_rcu(&ct->ext->rcu, __nf_ct_ext_free_rcu);
                 ct->ext = new;
         }
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 95da1a24aab7..2f83c158934d 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -619,6 +619,7 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = {
 static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
         .name                   = "H.245",
         .me                     = THIS_MODULE,
+        .tuple.src.l3num        = AF_UNSPEC,
         .tuple.dst.protonum     = IPPROTO_UDP,
         .help                   = h245_help,
         .expect_policy          = &h245_exp_policy,
@@ -1765,6 +1766,7 @@ static void __exit nf_conntrack_h323_fini(void)
         nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]);
         nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]);
         nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]);
+        nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
         kfree(h323_buffer);
         pr_debug("nf_ct_h323: fini\n");
 }
@@ -1777,28 +1779,34 @@ static int __init nf_conntrack_h323_init(void)
         h323_buffer = kmalloc(65536, GFP_KERNEL);
         if (!h323_buffer)
                 return -ENOMEM;
-        ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]);
+        ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245);
         if (ret < 0)
                 goto err1;
-        ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]);
+        ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]);
         if (ret < 0)
                 goto err2;
-        ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]);
+        ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]);
         if (ret < 0)
                 goto err3;
-        ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]);
+        ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]);
         if (ret < 0)
                 goto err4;
+        ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]);
+        if (ret < 0)
+                goto err5;
         pr_debug("nf_ct_h323: init success\n");
         return 0;
 
-err4:
+err5:
         nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]);
-err3:
+err4:
         nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]);
-err2:
+err3:
         nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]);
+err2:
+        nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
 err1:
+        kfree(h323_buffer);
         return ret;
 }
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f5aa23c3e886..3e1191cecaf0 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -444,8 +444,11 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                 if (ops->dumpit == NULL)
                         return -EOPNOTSUPP;
 
-                return netlink_dump_start(genl_sock, skb, nlh,
-                                          ops->dumpit, ops->done);
+                genl_unlock();
+                err = netlink_dump_start(genl_sock, skb, nlh,
+                                         ops->dumpit, ops->done);
+                genl_lock();
+                return err;
         }
 
         if (ops->doit == NULL)
@@ -603,9 +606,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
         int chains_to_skip = cb->args[0];
         int fams_to_skip = cb->args[1];
 
-        if (chains_to_skip != 0)
-                genl_lock();
-
         for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
                 if (i < chains_to_skip)
                         continue;
@@ -623,9 +623,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
         }
 
 errout:
-        if (chains_to_skip != 0)
-                genl_unlock();
-
         cb->args[0] = i;
         cb->args[1] = n;
 
@@ -770,7 +767,7 @@ static int __init genl_init(void)
 
         /* we'll bump the group number right afterwards */
         genl_sock = netlink_kernel_create(&init_net, NETLINK_GENERIC, 0,
-                                          genl_rcv, NULL, THIS_MODULE);
+                                          genl_rcv, &genl_mutex, THIS_MODULE);
         if (genl_sock == NULL)
                 panic("GENL: Cannot initialize generic netlink\n");
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 392e80e3268d..b4280490cf6e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -167,6 +167,11 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)
         return (unix_peer(osk) == NULL || unix_our_peer(sk, osk));
 }
 
+static inline int unix_recvq_full(struct sock const *sk)
+{
+        return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
+}
+
 static struct sock *unix_peer_get(struct sock *s)
 {
         struct sock *peer;
@@ -480,6 +485,8 @@ static int unix_socketpair(struct socket *, struct socket *);
 static int unix_accept(struct socket *, struct socket *, int);
 static int unix_getname(struct socket *, struct sockaddr *, int *, int);
 static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
+static unsigned int unix_datagram_poll(struct file *, struct socket *,
+                                       poll_table *);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct kiocb *, struct socket *,
@@ -525,7 +532,7 @@ static const struct proto_ops unix_dgram_ops = {
         .socketpair =   unix_socketpair,
         .accept =       sock_no_accept,
         .getname =      unix_getname,
-        .poll =         datagram_poll,
+        .poll =         unix_datagram_poll,
         .ioctl =        unix_ioctl,
         .listen =       sock_no_listen,
         .shutdown =     unix_shutdown,
@@ -546,7 +553,7 @@ static const struct proto_ops unix_seqpacket_ops = {
         .socketpair =   unix_socketpair,
         .accept =       unix_accept,
         .getname =      unix_getname,
-        .poll =         datagram_poll,
+        .poll =         unix_datagram_poll,
         .ioctl =        unix_ioctl,
         .listen =       unix_listen,
         .shutdown =     unix_shutdown,
@@ -981,8 +988,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo)
 
         sched = !sock_flag(other, SOCK_DEAD) &&
                 !(other->sk_shutdown & RCV_SHUTDOWN) &&
-                (skb_queue_len(&other->sk_receive_queue) >
-                 other->sk_max_ack_backlog);
+                unix_recvq_full(other);
 
         unix_state_unlock(other);
 
@@ -1056,8 +1062,7 @@ restart:
         if (other->sk_state != TCP_LISTEN)
                 goto out_unlock;
 
-        if (skb_queue_len(&other->sk_receive_queue) >
-            other->sk_max_ack_backlog) {
+        if (unix_recvq_full(other)) {
                 err = -EAGAIN;
                 if (!timeo)
                         goto out_unlock;
@@ -1426,9 +1431,7 @@ restart:
                         goto out_unlock;
         }
 
-        if (unix_peer(other) != sk &&
-            (skb_queue_len(&other->sk_receive_queue) >
-             other->sk_max_ack_backlog)) {
+        if (unix_peer(other) != sk && unix_recvq_full(other)) {
                 if (!timeo) {
                         err = -EAGAIN;
                         goto out_unlock;
@@ -1989,6 +1992,64 @@ static unsigned int unix_poll(struct file * file, struct socket *sock, poll_tabl
         return mask;
 }
 
+static unsigned int unix_datagram_poll(struct file *file, struct socket *sock,
+                                       poll_table *wait)
+{
+        struct sock *sk = sock->sk, *peer;
+        unsigned int mask;
+
+        poll_wait(file, sk->sk_sleep, wait);
+
+        peer = unix_peer_get(sk);
+        if (peer) {
+                if (peer != sk) {
+                        /*
+                         * Writability of a connected socket additionally
+                         * depends on the state of the receive queue of the
+                         * peer.
+                         */
+                        poll_wait(file, &unix_sk(peer)->peer_wait, wait);
+                } else {
+                        sock_put(peer);
+                        peer = NULL;
+                }
+        }
+
+        mask = 0;
+
+        /* exceptional events? */
+        if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+                mask |= POLLERR;
+        if (sk->sk_shutdown & RCV_SHUTDOWN)
+                mask |= POLLRDHUP;
+        if (sk->sk_shutdown == SHUTDOWN_MASK)
+                mask |= POLLHUP;
+
+        /* readable? */
+        if (!skb_queue_empty(&sk->sk_receive_queue) ||
+            (sk->sk_shutdown & RCV_SHUTDOWN))
+                mask |= POLLIN | POLLRDNORM;
+
+        /* Connection-based need to check for termination and startup */
+        if (sk->sk_type == SOCK_SEQPACKET) {
+                if (sk->sk_state == TCP_CLOSE)
+                        mask |= POLLHUP;
+                /* connection hasn't started yet? */
+                if (sk->sk_state == TCP_SYN_SENT)
+                        return mask;
+        }
+
+        /* writable? */
+        if (unix_writable(sk) && !(peer && unix_recvq_full(peer)))
+                mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+        else
+                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+        if (peer)
+                sock_put(peer);
+
+        return mask;
+}
 
 #ifdef CONFIG_PROC_FS
 static struct sock *first_unix_socket(int *i)