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

Conflicts:
	net/mac80211/main.c

net/ax25/ax25_ds_timer.c

@@ -112,8 +112,8 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 			if (sk) {
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
-				sock_put(sk);
 				bh_unlock_sock(sk);
+				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
 			return;

net/bridge/br_netfilter.c

@@ -162,8 +162,8 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 		if (tmp) {
 			memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
 			atomic_set(&tmp->use, 1);
-			nf_bridge_put(nf_bridge);
 		}
+		nf_bridge_put(nf_bridge);
 		nf_bridge = tmp;
 	}
 	return nf_bridge;
@@ -761,9 +761,11 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
 	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
-	    !skb_is_gso(skb))
+	    !skb_is_gso(skb)) {
+		/* BUG: Should really parse the IP options here. */
+		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 		return ip_fragment(skb, br_dev_queue_push_xmit);
-	else
+	} else
 		return br_dev_queue_push_xmit(skb);
 }
 #else

net/caif/cfrfml.c

@@ -9,7 +9,7 @@
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/unaligned/le_byteshift.h>
+#include <asm/unaligned.h>
 #include <net/caif/caif_layer.h>
 #include <net/caif/cfsrvl.h>
 #include <net/caif/cfpkt.h>

net/core/dev.c

@@ -2056,16 +2056,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
 					struct sk_buff *skb)
 {
 	int queue_index;
-	struct sock *sk = skb->sk;
+	const struct net_device_ops *ops = dev->netdev_ops;
 
-	queue_index = sk_tx_queue_get(sk);
-	if (queue_index < 0) {
-		const struct net_device_ops *ops = dev->netdev_ops;
+	if (ops->ndo_select_queue) {
+		queue_index = ops->ndo_select_queue(dev, skb);
+		queue_index = dev_cap_txqueue(dev, queue_index);
+	} else {
+		struct sock *sk = skb->sk;
+		queue_index = sk_tx_queue_get(sk);
+		if (queue_index < 0) {
 
-		if (ops->ndo_select_queue) {
-			queue_index = ops->ndo_select_queue(dev, skb);
-			queue_index = dev_cap_txqueue(dev, queue_index);
-		} else {
 			queue_index = 0;
 			if (dev->real_num_tx_queues > 1)
 				queue_index = skb_tx_hash(dev, skb);

net/core/gen_estimator.c

@@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	est->last_packets = bstats->packets;
 	est->avpps = rate_est->pps<<10;
 
-	spin_lock(&est_tree_lock);
+	spin_lock_bh(&est_tree_lock);
 	if (!elist[idx].timer.function) {
 		INIT_LIST_HEAD(&elist[idx].list);
 		setup_timer(&elist[idx].timer, est_timer, idx);
@@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 
 	list_add_rcu(&est->list, &elist[idx].list);
 	gen_add_node(est);
-	spin_unlock(&est_tree_lock);
+	spin_unlock_bh(&est_tree_lock);
 
 	return 0;
 }
@@ -270,7 +270,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 {
 	struct gen_estimator *e;
 
-	spin_lock(&est_tree_lock);
+	spin_lock_bh(&est_tree_lock);
 	while ((e = gen_find_node(bstats, rate_est))) {
 		rb_erase(&e->node, &est_root);
 
@@ -281,7 +281,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 		list_del_rcu(&e->list);
 		call_rcu(&e->e_rcu, __gen_kill_estimator);
 	}
-	spin_unlock(&est_tree_lock);
+	spin_unlock_bh(&est_tree_lock);
 }
 EXPORT_SYMBOL(gen_kill_estimator);
 
@@ -320,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
 
 	ASSERT_RTNL();
 
-	spin_lock(&est_tree_lock);
+	spin_lock_bh(&est_tree_lock);
 	res = gen_find_node(bstats, rate_est) != NULL;
-	spin_unlock(&est_tree_lock);
+	spin_unlock_bh(&est_tree_lock);
 
 	return res;
 }

net/core/skbuff.c

@@ -2569,6 +2569,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 		__copy_skb_header(nskb, skb);
 		nskb->mac_len = skb->mac_len;
 
+		/* nskb and skb might have different headroom */
+		if (nskb->ip_summed == CHECKSUM_PARTIAL)
+			nskb->csum_start += skb_headroom(nskb) - headroom;
+
 		skb_reset_mac_header(nskb);
 		skb_set_network_header(nskb, skb->mac_len);
 		nskb->transport_header = (nskb->network_header +
@@ -2699,7 +2703,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		return -E2BIG;
 
 	headroom = skb_headroom(p);
-	nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
+	nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
 	if (unlikely(!nskb))
 		return -ENOMEM;
 

net/ipv4/Kconfig

@@ -46,7 +46,7 @@ config IP_ADVANCED_ROUTER
 	  rp_filter on use:
 
 	  echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter
-	   and
+	   or
 	  echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter
 
 	  Note that some distributions enable it in startup scripts.

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;

net/ipv4/fib_frontend.c

@@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 
 	struct fib_result res;
 	int no_addr, rpf, accept_local;
+	bool dev_match;
 	int ret;
 	struct net *net;
 
@@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 	}
 	*spec_dst = FIB_RES_PREFSRC(res);
 	fib_combine_itag(itag, &res);
+	dev_match = false;
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
+	for (ret = 0; ret < res.fi->fib_nhs; ret++) {
+		struct fib_nh *nh = &res.fi->fib_nh[ret];
+
+		if (nh->nh_dev == dev) {
+			dev_match = true;
+			break;
+		}
+	}
 #else
 	if (FIB_RES_DEV(res) == dev)
+		dev_match = true;
 #endif
-	{
+	if (dev_match) {
 		ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
 		fib_res_put(&res);
 		return ret;

net/ipv4/fib_trie.c

@@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node)
 {
 	struct tnode *ret = node_parent(node);
 
-	return rcu_dereference(ret);
+	return rcu_dereference_check(ret,
+				     rcu_read_lock_held() ||
+				     lockdep_rtnl_is_held());
 }
 
 /* Same as rcu_assign_pointer
@@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c)
 
 static struct leaf *trie_firstleaf(struct trie *t)
 {
-	struct tnode *n = (struct tnode *) rcu_dereference(t->trie);
+	struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie,
+							rcu_read_lock_held() ||
+							lockdep_rtnl_is_held());
 
 	if (!n)
 		return NULL;

net/ipv4/netfilter/arp_tables.c

@@ -1420,6 +1420,9 @@ static int translate_compat_table(const char *name,
 		if (ret != 0)
 			break;
 		++i;
+		if (strcmp(arpt_get_target(iter1)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 	if (ret) {
 		/*

net/ipv4/netfilter/ip_tables.c

@@ -1751,6 +1751,9 @@ translate_compat_table(struct net *net,
 		if (ret != 0)
 			break;
 		++i;
+		if (strcmp(ipt_get_target(iter1)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 	if (ret) {
 		/*

net/ipv4/route.c

@@ -2731,6 +2731,11 @@ slow_output:
 }
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
 
+static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
+
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 }
@@ -2739,7 +2744,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
 	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.destroy		=	ipv4_dst_destroy,
-	.check			=	ipv4_dst_check,
+	.check			=	ipv4_blackhole_dst_check,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
 	.entries		=	ATOMIC_INIT(0),
 };

net/ipv4/tcp.c

@@ -451,7 +451,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 				if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
 					mask |= POLLOUT | POLLWRNORM;
 			}
-		}
+		} else
+			mask |= POLLOUT | POLLWRNORM;
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
@@ -2011,11 +2012,8 @@ adjudge_to_death:
 		}
 	}
 	if (sk->sk_state != TCP_CLOSE) {
-		int orphan_count = percpu_counter_read_positive(
-						sk->sk_prot->orphan_count);
-
 		sk_mem_reclaim(sk);
-		if (tcp_too_many_orphans(sk, orphan_count)) {
+		if (tcp_too_many_orphans(sk, 0)) {
 			if (net_ratelimit())
 				printk(KERN_INFO "TCP: too many of orphaned "
 				       "sockets\n");
@@ -3221,7 +3219,7 @@ void __init tcp_init(void)
 {
 	struct sk_buff *skb = NULL;
 	unsigned long nr_pages, limit;
-	int order, i, max_share;
+	int i, max_share, cnt;
 	unsigned long jiffy = jiffies;
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3270,22 +3268,12 @@ void __init tcp_init(void)
 		INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
 	}
 
-	/* Try to be a bit smarter and adjust defaults depending
-	 * on available memory.
-	 */
-	for (order = 0; ((1 << order) << PAGE_SHIFT) <
-			(tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
-			order++)
-		;
-	if (order >= 4) {
-		tcp_death_row.sysctl_max_tw_buckets = 180000;
-		sysctl_tcp_max_orphans = 4096 << (order - 4);
-		sysctl_max_syn_backlog = 1024;
-	} else if (order < 3) {
-		tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
-		sysctl_tcp_max_orphans >>= (3 - order);
-		sysctl_max_syn_backlog = 128;
-	}
+
+	cnt = tcp_hashinfo.ehash_mask + 1;
+
+	tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
+	sysctl_tcp_max_orphans = cnt / 2;
+	sysctl_max_syn_backlog = max(128, cnt / 256);
 
 	/* Set the pressure threshold to be a fraction of global memory that
 	 * is up to 1/2 at 256 MB, decreasing toward zero with the amount of

net/ipv4/tcp_cong.c

@@ -196,10 +196,10 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
 int tcp_set_allowed_congestion_control(char *val)
 {
 	struct tcp_congestion_ops *ca;
-	char *clone, *name;
+	char *saved_clone, *clone, *name;
 	int ret = 0;
 
-	clone = kstrdup(val, GFP_USER);
+	saved_clone = clone = kstrdup(val, GFP_USER);
 	if (!clone)
 		return -ENOMEM;
 
@@ -226,6 +226,7 @@ int tcp_set_allowed_congestion_control(char *val)
 	}
 out:
 	spin_unlock(&tcp_cong_list_lock);
+	kfree(saved_clone);
 
 	return ret;
 }

net/ipv4/tcp_timer.c

@@ -66,18 +66,18 @@ static void tcp_write_err(struct sock *sk)
 static int tcp_out_of_resources(struct sock *sk, int do_reset)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int orphans = percpu_counter_read_positive(&tcp_orphan_count);
+	int shift = 0;
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
 	if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
-		orphans <<= 1;
+		shift++;
 
 	/* If some dubious ICMP arrived, penalize even more. */
 	if (sk->sk_err_soft)
-		orphans <<= 1;
+		shift++;
 
-	if (tcp_too_many_orphans(sk, orphans)) {
+	if (tcp_too_many_orphans(sk, shift)) {
 		if (net_ratelimit())
 			printk(KERN_INFO "Out of socket memory\n");
 

net/ipv4/udp.c

@@ -1260,6 +1260,49 @@ 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;
@@ -1843,6 +1886,7 @@ 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,

net/ipv6/datagram.c

@@ -105,9 +105,12 @@ 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;
 	}
@@ -181,6 +184,8 @@ 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,

net/ipv6/netfilter/ip6_tables.c

@@ -1766,6 +1766,9 @@ translate_compat_table(struct net *net,
 		if (ret != 0)
 			break;
 		++i;
+		if (strcmp(ip6t_get_target(iter1)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 	if (ret) {
 		/*

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb)
 		kfree_skb(NFCT_FRAG6_CB(skb)->orig);
 }
 
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct sk_buff *skb)
-{
-	atomic_sub(skb->truesize, &nf_init_frags.mem);
-	nf_skb_free(skb);
-	kfree_skb(skb);
-}
-
 /* Destruction primitives. */
 
 static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
@@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 	}
 
 found:
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
+	/* RFC5722, Section 4:
+	 *                                  When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments, including those not yet received) MUST be silently
+	 *   discarded.
 	 */
-	if (prev) {
-		int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;
 
-		if (i > 0) {
-			offset += i;
-			if (end <= offset) {
-				pr_debug("overlap\n");
-				goto err;
-			}
-			if (!pskb_pull(skb, i)) {
-				pr_debug("Can't pull\n");
-				goto err;
-			}
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
+	/* Check for overlap with preceding fragment. */
+	if (prev &&
+	    (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+		goto discard_fq;
 
-	/* Look for overlap with succeeding segments.
-	 * If we can merge fragments, do it.
-	 */
-	while (next && NFCT_FRAG6_CB(next)->offset < end) {
-		/* overlap is 'i' bytes */
-		int i = end - NFCT_FRAG6_CB(next)->offset;
-
-		if (i < next->len) {
-			/* Eat head of the next overlapped fragment
-			 * and leave the loop. The next ones cannot overlap.
-			 */
-			pr_debug("Eat head of the overlapped parts.: %d", i);
-			if (!pskb_pull(next, i))
-				goto err;
-
-			/* next fragment */
-			NFCT_FRAG6_CB(next)->offset += i;
-			fq->q.meat -= i;
-			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-				next->ip_summed = CHECKSUM_NONE;
-			break;
-		} else {
-			struct sk_buff *free_it = next;
-
-			/* Old fragmnet is completely overridden with
-			 * new one drop it.
-			 */
-			next = next->next;
-
-			if (prev)
-				prev->next = next;
-			else
-				fq->q.fragments = next;
-
-			fq->q.meat -= free_it->len;
-			frag_kfree_skb(free_it);
-		}
-	}
+	/* Look for overlap with succeeding segment. */
+	if (next && NFCT_FRAG6_CB(next)->offset < end)
+		goto discard_fq;
 
 	NFCT_FRAG6_CB(skb)->offset = offset;
 
@@ -371,6 +319,8 @@ found:
 	write_unlock(&nf_frags.lock);
 	return 0;
 
+discard_fq:
+	fq_kill(fq);
 err:
 	return -1;
 }