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

12 files changed, 95 insertions, 37 deletions

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index c0316e0..c584a0a 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -11,7 +11,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
 	if (netpoll_rx(skb))
 		return NET_RX_DROP;
 
-	if (skb_bond_should_drop(skb))
+	if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master)))
 		goto drop;
 
 	skb->skb_iif = skb->dev->ifindex;
@@ -83,7 +83,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
 {
 	struct sk_buff *p;
 
-	if (skb_bond_should_drop(skb))
+	if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master)))
 		goto drop;
 
 	skb->skb_iif = skb->dev->ifindex;
diff --git a/net/core/dev.c b/net/core/dev.c
index d1f027c..c0e2608 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2622,6 +2622,7 @@ int __netif_receive_skb(struct sk_buff *skb)
 {
 	struct packet_type *ptype, *pt_prev;
 	struct net_device *orig_dev;
+	struct net_device *master;
 	struct net_device *null_or_orig;
 	struct net_device *null_or_bond;
 	int ret = NET_RX_DROP;
@@ -2642,11 +2643,12 @@ int __netif_receive_skb(struct sk_buff *skb)
 
 	null_or_orig = NULL;
 	orig_dev = skb->dev;
-	if (orig_dev->master) {
-		if (skb_bond_should_drop(skb))
+	master = ACCESS_ONCE(orig_dev->master);
+	if (master) {
+		if (skb_bond_should_drop(skb, master))
 			null_or_orig = orig_dev; /* deliver only exact match */
 		else
-			skb->dev = orig_dev->master;
+			skb->dev = master;
 	}
 
 	__get_cpu_var(netdev_rx_stat).total++;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8582e12..0b9d03c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -802,6 +802,9 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	int line;
 	struct mfc_cache *uc, *c, **cp;
 
+	if (mfc->mfcc_parent >= MAXVIFS)
+		return -ENFILE;
+
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
 	for (cp = &net->ipv4.mfc_cache_array[line];
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a770df2..32d3961 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1441,7 +1441,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 					dev_hold(rt->u.dst.dev);
 				if (rt->idev)
 					in_dev_hold(rt->idev);
-				rt->u.dst.obsolete	= 0;
+				rt->u.dst.obsolete	= -1;
 				rt->u.dst.lastuse	= jiffies;
 				rt->u.dst.path		= &rt->u.dst;
 				rt->u.dst.neighbour	= NULL;
@@ -1506,7 +1506,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 	struct dst_entry *ret = dst;
 
 	if (rt) {
-		if (dst->obsolete) {
+		if (dst->obsolete > 0) {
 			ip_rt_put(rt);
 			ret = NULL;
 		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
@@ -1726,7 +1726,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 {
-	return NULL;
+	if (rt_is_expired((struct rtable *)dst))
+		return NULL;
+	return dst;
 }
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1888,7 +1890,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (!rth)
 		goto e_nobufs;
 
-	rth->u.dst.output= ip_rt_bug;
+	rth->u.dst.output = ip_rt_bug;
+	rth->u.dst.obsolete = -1;
 
 	atomic_set(&rth->u.dst.__refcnt, 1);
 	rth->u.dst.flags= DST_HOST;
@@ -2054,6 +2057,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->fl.oif 	= 0;
 	rth->rt_spec_dst= spec_dst;
 
+	rth->u.dst.obsolete = -1;
 	rth->u.dst.input = ip_forward;
 	rth->u.dst.output = ip_output;
 	rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
@@ -2218,6 +2222,7 @@ local_input:
 		goto e_nobufs;
 
 	rth->u.dst.output= ip_rt_bug;
+	rth->u.dst.obsolete = -1;
 	rth->rt_genid = rt_genid(net);
 
 	atomic_set(&rth->u.dst.__refcnt, 1);
@@ -2444,6 +2449,7 @@ static int __mkroute_output(struct rtable **result,
 	rth->rt_spec_dst= fl->fl4_src;
 
 	rth->u.dst.output=ip_output;
+	rth->u.dst.obsolete = -1;
 	rth->rt_genid = rt_genid(dev_net(dev_out));
 
 	RT_CACHE_STAT_INC(out_slow_tot);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5901010..6afb6d8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -429,7 +429,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		if (tp->urg_seq == tp->copied_seq &&
 		    !sock_flag(sk, SOCK_URGINLINE) &&
 		    tp->urg_data)
-			target--;
+			target++;
 
 		/* Potential race condition. If read of tp below will
 		 * escape above sk->sk_state, we can be illegally awaken
@@ -1254,6 +1254,39 @@ static void tcp_prequeue_process(struct sock *sk)
 	tp->ucopy.memory = 0;
 }
 
+#ifdef CONFIG_NET_DMA
+static void tcp_service_net_dma(struct sock *sk, bool wait)
+{
+	dma_cookie_t done, used;
+	dma_cookie_t last_issued;
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (!tp->ucopy.dma_chan)
+		return;
+
+	last_issued = tp->ucopy.dma_cookie;
+	dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+
+	do {
+		if (dma_async_memcpy_complete(tp->ucopy.dma_chan,
+					      last_issued, &done,
+					      &used) == DMA_SUCCESS) {
+			/* Safe to free early-copied skbs now */
+			__skb_queue_purge(&sk->sk_async_wait_queue);
+			break;
+		} else {
+			struct sk_buff *skb;
+			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
+			       (dma_async_is_complete(skb->dma_cookie, done,
+						      used) == DMA_SUCCESS)) {
+				__skb_dequeue(&sk->sk_async_wait_queue);
+				kfree_skb(skb);
+			}
+		}
+	} while (wait);
+}
+#endif
+
 static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1546,6 +1579,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			/* __ Set realtime policy in scheduler __ */
 		}
 
+#ifdef CONFIG_NET_DMA
+		if (tp->ucopy.dma_chan)
+			dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+#endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1554,6 +1591,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			sk_wait_data(sk, &timeo);
 
 #ifdef CONFIG_NET_DMA
+		tcp_service_net_dma(sk, false);  /* Don't block */
 		tp->ucopy.wakeup = 0;
 #endif
 
@@ -1633,6 +1671,9 @@ do_prequeue:
 						copied = -EFAULT;
 					break;
 				}
+
+				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+
 				if ((offset + used) == skb->len)
 					copied_early = 1;
 
@@ -1702,27 +1743,9 @@ skip_copy:
 	}
 
 #ifdef CONFIG_NET_DMA
-	if (tp->ucopy.dma_chan) {
-		dma_cookie_t done, used;
-
-		dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
-
-		while (dma_async_memcpy_complete(tp->ucopy.dma_chan,
-						 tp->ucopy.dma_cookie, &done,
-						 &used) == DMA_IN_PROGRESS) {
-			/* do partial cleanup of sk_async_wait_queue */
-			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
-			       (dma_async_is_complete(skb->dma_cookie, done,
-						      used) == DMA_SUCCESS)) {
-				__skb_dequeue(&sk->sk_async_wait_queue);
-				kfree_skb(skb);
-			}
-		}
+	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
+	tp->ucopy.dma_chan = NULL;
 
-		/* Safe to free early-copied skbs now */
-		__skb_queue_purge(&sk->sk_async_wait_queue);
-		tp->ucopy.dma_chan = NULL;
-	}
 	if (tp->ucopy.pinned_list) {
 		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
 		tp->ucopy.pinned_list = NULL;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 788851c..c096a42 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2511,6 +2511,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
 	int err;
 	unsigned int mss;
 
+	if (packets == 0)
+		return;
+
 	WARN_ON(packets > tp->packets_out);
 	if (tp->lost_skb_hint) {
 		skb = tp->lost_skb_hint;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 70df409..f4df5f9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -370,6 +370,11 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
+	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
+		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+		goto out;
+	}
+
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
 	seq = ntohl(th->seq);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 52e0f74..23e4ac0 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1113,6 +1113,9 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
 	unsigned char ttls[MAXMIFS];
 	int i;
 
+	if (mfc->mf6cc_parent >= MAXMIFS)
+		return -ENFILE;
+
 	memset(ttls, 255, MAXMIFS);
 	for (i = 0; i < MAXMIFS; i++) {
 		if (IF_ISSET(i, &mfc->mf6cc_ifset))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 52cd3ef..7fcb0e5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -879,7 +879,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = (struct rt6_info *) dst;
 
-	if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
 		return dst;
 
 	return NULL;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 2b2af63..569410a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -582,7 +582,9 @@ nla_put_failure:
 nlmsg_failure:
 	kfree_skb(skb);
 errout:
-	nfnetlink_set_err(net, 0, group, -ENOBUFS);
+	if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0)
+		return -ENOBUFS;
+
 	return 0;
 }
 #endif /* CONFIG_NF_CONNTRACK_EVENTS */
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 8eb0cc2..6afa3d5 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -113,9 +113,9 @@ int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid,
 }
 EXPORT_SYMBOL_GPL(nfnetlink_send);
 
-void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error)
+int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error)
 {
-	netlink_set_err(net->nfnl, pid, group, error);
+	return netlink_set_err(net->nfnl, pid, group, error);
 }
 EXPORT_SYMBOL_GPL(nfnetlink_set_err);
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 320d042..acbbae1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1093,6 +1093,7 @@ static inline int do_one_set_err(struct sock *sk,
 				 struct netlink_set_err_data *p)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
+	int ret = 0;
 
 	if (sk == p->exclude_sk)
 		goto out;
@@ -1104,10 +1105,15 @@ static inline int do_one_set_err(struct sock *sk,
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
+	if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) {
+		ret = 1;
+		goto out;
+	}
+
 	sk->sk_err = p->code;
 	sk->sk_error_report(sk);
 out:
-	return 0;
+	return ret;
 }
 
 /**
@@ -1116,12 +1122,16 @@ out:
  * @pid: the PID of a process that we want to skip (if any)
  * @groups: the broadcast group that will notice the error
  * @code: error code, must be negative (as usual in kernelspace)
+ *
+ * This function returns the number of broadcast listeners that have set the
+ * NETLINK_RECV_NO_ENOBUFS socket option.
  */
-void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
+int netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 {
 	struct netlink_set_err_data info;
 	struct hlist_node *node;
 	struct sock *sk;
+	int ret = 0;
 
 	info.exclude_sk = ssk;
 	info.pid = pid;
@@ -1132,9 +1142,10 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 	read_lock(&nl_table_lock);
 
 	sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list)
-		do_one_set_err(sk, &info);
+		ret += do_one_set_err(sk, &info);
 
 	read_unlock(&nl_table_lock);
+	return ret;
 }
 EXPORT_SYMBOL(netlink_set_err);