Merge commit 'v2.6.28-rc1' into sched/urgent

7 files changed, 29 insertions, 16 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index b043eda60b04..1a9dd66511fc 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -663,7 +663,7 @@ out:
 void arp_xmit(struct sk_buff *skb)
 {
         /* Send it off, maybe filter it using firewalling first.  */
-        NF_HOOK(NF_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
+        NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
 }
 
 /*
@@ -928,7 +928,7 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
 
         memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 
-        return NF_HOOK(NF_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
+        return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
 
 freeskb:
         kfree_skb(skb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5154e729cf16..56fce3ab6c55 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -613,9 +613,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
         if (colon)
                 *colon = 0;
 
-#ifdef CONFIG_KMOD
         dev_load(net, ifr.ifr_name);
-#endif
 
         switch (cmd) {
         case SIOCGIFADDR:       /* Get interface address */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 89cb047ab314..564230dabcb8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -53,11 +53,9 @@ static DEFINE_MUTEX(inet_diag_table_mutex);
 
 static const struct inet_diag_handler *inet_diag_lock_handler(int type)
 {
-#ifdef CONFIG_KMOD
         if (!inet_diag_table[type])
                 request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
                                NETLINK_INET_DIAG, type);
-#endif
 
         mutex_lock(&inet_diag_table_mutex);
         if (!inet_diag_table[type])
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index ffeaffc3fffe..8303e4b406c0 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -742,6 +742,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx,
                         *obj = kmalloc(sizeof(struct snmp_object) + len,
                                        GFP_ATOMIC);
                         if (*obj == NULL) {
+                                kfree(p);
                                 kfree(id);
                                 if (net_ratelimit())
                                         printk("OOM in bsalg (%d)\n", __LINE__);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 942be04e7955..2ea6dcc3e2cc 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1109,7 +1109,12 @@ restart:
                 printk("\n");
         }
 #endif
-        rt_hash_table[hash].chain = rt;
+        /*
+         * Since lookup is lockfree, we must make sure
+         * previous writes to rt are comitted to memory
+         * before making rt visible to other CPUS.
+         */
+        rcu_assign_pointer(rt_hash_table[hash].chain, rt);
         spin_unlock_bh(rt_hash_lock_addr(hash));
         *rp = rt;
         return 0;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 6a250828b767..4ec5b4e97c4e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -115,7 +115,7 @@ int tcp_set_default_congestion_control(const char *name)
 
         spin_lock(&tcp_cong_list_lock);
         ca = tcp_ca_find(name);
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         if (!ca && capable(CAP_SYS_MODULE)) {
                 spin_unlock(&tcp_cong_list_lock);
 
@@ -244,7 +244,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
         if (ca == icsk->icsk_ca_ops)
                 goto out;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         /* not found attempt to autoload module */
         if (!ca && capable(CAP_SYS_MODULE)) {
                 rcu_read_unlock();
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 990a58493235..e4c5ac9fe89b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -362,6 +362,17 @@ struct tcp_out_options {
         __u32 tsval, tsecr;     /* need to include OPTION_TS */
 };
 
+/* Beware: Something in the Internet is very sensitive to the ordering of
+ * TCP options, we learned this through the hard way, so be careful here.
+ * Luckily we can at least blame others for their non-compliance but from
+ * inter-operatibility perspective it seems that we're somewhat stuck with
+ * the ordering which we have been using if we want to keep working with
+ * those broken things (not that it currently hurts anybody as there isn't
+ * particular reason why the ordering would need to be changed).
+ *
+ * At least SACK_PERM as the first option is known to lead to a disaster
+ * (but it may well be that other scenarios fail similarly).
+ */
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                               const struct tcp_out_options *opts,
                               __u8 **md5_hash) {
@@ -376,6 +387,12 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                 *md5_hash = NULL;
         }
 
+        if (unlikely(opts->mss)) {
+                *ptr++ = htonl((TCPOPT_MSS << 24) |
+                               (TCPOLEN_MSS << 16) |
+                               opts->mss);
+        }
+
         if (likely(OPTION_TS & opts->options)) {
                 if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
                         *ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
@@ -392,12 +409,6 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                 *ptr++ = htonl(opts->tsecr);
         }
 
-        if (unlikely(opts->mss)) {
-                *ptr++ = htonl((TCPOPT_MSS << 24) |
-                               (TCPOLEN_MSS << 16) |
-                               opts->mss);
-        }
-
         if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
                      !(OPTION_TS & opts->options))) {
                 *ptr++ = htonl((TCPOPT_NOP << 24) |
@@ -432,7 +443,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
                 if (tp->rx_opt.dsack) {
                         tp->rx_opt.dsack = 0;
-                        tp->rx_opt.eff_sacks--;
+                        tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks;
                 }
         }
 }