5 files changed, 155 insertions, 87 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index be9924f60ec..4fad9db417b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1853,6 +1853,14 @@ gso:
 
 		skb->next = nskb->next;
 		nskb->next = NULL;
+
+		/*
+		 * If device doesnt need nskb->dst, release it right now while
+		 * its hot in this cpu cache
+		 */
+		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+			skb_dst_drop(nskb);
+
 		rc = ops->ndo_start_xmit(nskb, dev);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -1974,6 +1982,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	return rc;
 }
 
+/*
+ * Returns true if either:
+ *	1. skb has frag_list and the device doesn't support FRAGLIST, or
+ *	2. skb is fragmented and the device does not support SG, or if
+ *	   at least one of fragments is in highmem and device does not
+ *	   support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+				      struct net_device *dev)
+{
+	return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+	       (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+					      illegal_highdma(dev, skb)));
+}
+
 /**
  *	dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
@@ -2010,18 +2033,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 	if (netif_needs_gso(dev, skb))
 		goto gso;
 
-	if (skb_has_frags(skb) &&
-	    !(dev->features & NETIF_F_FRAGLIST) &&
-	    __skb_linearize(skb))
-		goto out_kfree_skb;
-
-	/* Fragmented skb is linearized if device does not support SG,
-	 * or if at least one of fragments is in highmem and device
-	 * does not support DMA from it.
-	 */
-	if (skb_shinfo(skb)->nr_frags &&
-	    (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
-	    __skb_linearize(skb))
+	/* Convert a paged skb to linear, if required */
+	if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
 		goto out_kfree_skb;
 
 	/* If packet is not checksummed and device does not support
@@ -2422,6 +2435,7 @@ int netif_receive_skb(struct sk_buff *skb)
 	struct packet_type *ptype, *pt_prev;
 	struct net_device *orig_dev;
 	struct net_device *null_or_orig;
+	struct net_device *null_or_bond;
 	int ret = NET_RX_DROP;
 	__be16 type;
 
@@ -2487,12 +2501,24 @@ ncls:
 	if (!skb)
 		goto out;
 
+	/*
+	 * Make sure frames received on VLAN interfaces stacked on
+	 * bonding interfaces still make their way to any base bonding
+	 * device that may have registered for a specific ptype.  The
+	 * handler may have to adjust skb->dev and orig_dev.
+	 */
+	null_or_bond = NULL;
+	if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
+	    (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
+		null_or_bond = vlan_dev_real_dev(skb->dev);
+	}
+
 	type = skb->protocol;
 	list_for_each_entry_rcu(ptype,
 			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-		if (ptype->type == type &&
-		    (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
-		     ptype->dev == orig_dev)) {
+		if (ptype->type == type && (ptype->dev == null_or_orig ||
+		     ptype->dev == skb->dev || ptype->dev == orig_dev ||
+		     ptype->dev == null_or_bond)) {
 			if (pt_prev)
 				ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = ptype;
@@ -2561,7 +2587,7 @@ out:
 	return netif_receive_skb(skb);
 }
 
-void napi_gro_flush(struct napi_struct *napi)
+static void napi_gro_flush(struct napi_struct *napi)
 {
 	struct sk_buff *skb, *next;
 
@@ -2574,7 +2600,6 @@ void napi_gro_flush(struct napi_struct *napi)
 	napi->gro_count = 0;
 	napi->gro_list = NULL;
 }
-EXPORT_SYMBOL(napi_gro_flush);
 
 enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -3185,7 +3210,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
 	const struct net_device_stats *stats = dev_get_stats(dev);
 
-	seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+	seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
 		   "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
 		   dev->name, stats->rx_bytes, stats->rx_packets,
 		   stats->rx_errors,
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 02a3b2c69c1..9a24377146b 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -708,7 +708,7 @@ static struct notifier_block fib_rules_notifier = {
 	.notifier_call = fib_rules_event,
 };
 
-static int fib_rules_net_init(struct net *net)
+static int __net_init fib_rules_net_init(struct net *net)
 {
 	INIT_LIST_HEAD(&net->rules_ops);
 	spin_lock_init(&net->rules_mod_lock);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 0b4d0d35ef4..7aa69725376 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -407,11 +407,24 @@ static void arp_reply(struct sk_buff *skb)
 	__be32 sip, tip;
 	unsigned char *sha;
 	struct sk_buff *send_skb;
-	struct netpoll *np = NULL;
+	struct netpoll *np, *tmp;
+	unsigned long flags;
+	int hits = 0;
+
+	if (list_empty(&npinfo->rx_np))
+		return;
+
+	/* Before checking the packet, we do some early
+	   inspection whether this is interesting at all */
+	spin_lock_irqsave(&npinfo->rx_lock, flags);
+	list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+		if (np->dev == skb->dev)
+			hits++;
+	}
+	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 
-	if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev)
-		np = npinfo->rx_np;
-	if (!np)
+	/* No netpoll struct is using this dev */
+	if (!hits)
 		return;
 
 	/* No arp on this interface */
@@ -437,77 +450,91 @@ static void arp_reply(struct sk_buff *skb)
 	arp_ptr += skb->dev->addr_len;
 	memcpy(&sip, arp_ptr, 4);
 	arp_ptr += 4;
-	/* if we actually cared about dst hw addr, it would get copied here */
+	/* If we actually cared about dst hw addr,
+	   it would get copied here */
 	arp_ptr += skb->dev->addr_len;
 	memcpy(&tip, arp_ptr, 4);
 
 	/* Should we ignore arp? */
-	if (tip != np->local_ip ||
-	    ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
+	if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
 		return;
 
 	size = arp_hdr_len(skb->dev);
-	send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
-			    LL_RESERVED_SPACE(np->dev));
 
-	if (!send_skb)
-		return;
-
-	skb_reset_network_header(send_skb);
-	arp = (struct arphdr *) skb_put(send_skb, size);
-	send_skb->dev = skb->dev;
-	send_skb->protocol = htons(ETH_P_ARP);
+	spin_lock_irqsave(&npinfo->rx_lock, flags);
+	list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+		if (tip != np->local_ip)
+			continue;
 
-	/* Fill the device header for the ARP frame */
-	if (dev_hard_header(send_skb, skb->dev, ptype,
-			    sha, np->dev->dev_addr,
-			    send_skb->len) < 0) {
-		kfree_skb(send_skb);
-		return;
-	}
+		send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
+				    LL_RESERVED_SPACE(np->dev));
+		if (!send_skb)
+			continue;
 
-	/*
-	 * Fill out the arp protocol part.
-	 *
-	 * we only support ethernet device type,
-	 * which (according to RFC 1390) should always equal 1 (Ethernet).
-	 */
+		skb_reset_network_header(send_skb);
+		arp = (struct arphdr *) skb_put(send_skb, size);
+		send_skb->dev = skb->dev;
+		send_skb->protocol = htons(ETH_P_ARP);
 
-	arp->ar_hrd = htons(np->dev->type);
-	arp->ar_pro = htons(ETH_P_IP);
-	arp->ar_hln = np->dev->addr_len;
-	arp->ar_pln = 4;
-	arp->ar_op = htons(type);
+		/* Fill the device header for the ARP frame */
+		if (dev_hard_header(send_skb, skb->dev, ptype,
+				    sha, np->dev->dev_addr,
+				    send_skb->len) < 0) {
+			kfree_skb(send_skb);
+			continue;
+		}
 
-	arp_ptr=(unsigned char *)(arp + 1);
-	memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
-	arp_ptr += np->dev->addr_len;
-	memcpy(arp_ptr, &tip, 4);
-	arp_ptr += 4;
-	memcpy(arp_ptr, sha, np->dev->addr_len);
-	arp_ptr += np->dev->addr_len;
-	memcpy(arp_ptr, &sip, 4);
+		/*
+		 * Fill out the arp protocol part.
+		 *
+		 * we only support ethernet device type,
+		 * which (according to RFC 1390) should
+		 * always equal 1 (Ethernet).
+		 */
 
-	netpoll_send_skb(np, send_skb);
+		arp->ar_hrd = htons(np->dev->type);
+		arp->ar_pro = htons(ETH_P_IP);
+		arp->ar_hln = np->dev->addr_len;
+		arp->ar_pln = 4;
+		arp->ar_op = htons(type);
+
+		arp_ptr = (unsigned char *)(arp + 1);
+		memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
+		arp_ptr += np->dev->addr_len;
+		memcpy(arp_ptr, &tip, 4);
+		arp_ptr += 4;
+		memcpy(arp_ptr, sha, np->dev->addr_len);
+		arp_ptr += np->dev->addr_len;
+		memcpy(arp_ptr, &sip, 4);
+
+		netpoll_send_skb(np, send_skb);
+
+		/* If there are several rx_hooks for the same address,
+		   we're fine by sending a single reply */
+		break;
+	}
+	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 }
 
 int __netpoll_rx(struct sk_buff *skb)
 {
 	int proto, len, ulen;
+	int hits = 0;
 	struct iphdr *iph;
 	struct udphdr *uh;
-	struct netpoll_info *npi = skb->dev->npinfo;
-	struct netpoll *np = npi->rx_np;
+	struct netpoll_info *npinfo = skb->dev->npinfo;
+	struct netpoll *np, *tmp;
 
-	if (!np)
+	if (list_empty(&npinfo->rx_np))
 		goto out;
+
 	if (skb->dev->type != ARPHRD_ETHER)
 		goto out;
 
 	/* check if netpoll clients need ARP */
 	if (skb->protocol == htons(ETH_P_ARP) &&
 	    atomic_read(&trapped)) {
-		skb_queue_tail(&npi->arp_tx, skb);
+		skb_queue_tail(&npinfo->arp_tx, skb);
 		return 1;
 	}
 
@@ -551,16 +578,23 @@ int __netpoll_rx(struct sk_buff *skb)
 		goto out;
 	if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
 		goto out;
-	if (np->local_ip && np->local_ip != iph->daddr)
-		goto out;
-	if (np->remote_ip && np->remote_ip != iph->saddr)
-		goto out;
-	if (np->local_port && np->local_port != ntohs(uh->dest))
-		goto out;
 
-	np->rx_hook(np, ntohs(uh->source),
-		    (char *)(uh+1),
-		    ulen - sizeof(struct udphdr));
+	list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+		if (np->local_ip && np->local_ip != iph->daddr)
+			continue;
+		if (np->remote_ip && np->remote_ip != iph->saddr)
+			continue;
+		if (np->local_port && np->local_port != ntohs(uh->dest))
+			continue;
+
+		np->rx_hook(np, ntohs(uh->source),
+			       (char *)(uh+1),
+			       ulen - sizeof(struct udphdr));
+		hits++;
+	}
+
+	if (!hits)
+		goto out;
 
 	kfree_skb(skb);
 	return 1;
@@ -684,6 +718,7 @@ int netpoll_setup(struct netpoll *np)
 	struct net_device *ndev = NULL;
 	struct in_device *in_dev;
 	struct netpoll_info *npinfo;
+	struct netpoll *npe, *tmp;
 	unsigned long flags;
 	int err;
 
@@ -704,7 +739,7 @@ int netpoll_setup(struct netpoll *np)
 		}
 
 		npinfo->rx_flags = 0;
-		npinfo->rx_np = NULL;
+		INIT_LIST_HEAD(&npinfo->rx_np);
 
 		spin_lock_init(&npinfo->rx_lock);
 		skb_queue_head_init(&npinfo->arp_tx);
@@ -785,7 +820,7 @@ int netpoll_setup(struct netpoll *np)
 	if (np->rx_hook) {
 		spin_lock_irqsave(&npinfo->rx_lock, flags);
 		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
-		npinfo->rx_np = np;
+		list_add_tail(&np->rx, &npinfo->rx_np);
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 	}
 
@@ -801,9 +836,16 @@ int netpoll_setup(struct netpoll *np)
 	return 0;
 
  release:
-	if (!ndev->npinfo)
+	if (!ndev->npinfo) {
+		spin_lock_irqsave(&npinfo->rx_lock, flags);
+		list_for_each_entry_safe(npe, tmp, &npinfo->rx_np, rx) {
+			npe->dev = NULL;
+		}
+		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+
 		kfree(npinfo);
-	np->dev = NULL;
+	}
+
 	dev_put(ndev);
 	return err;
 }
@@ -823,10 +865,11 @@ void netpoll_cleanup(struct netpoll *np)
 	if (np->dev) {
 		npinfo = np->dev->npinfo;
 		if (npinfo) {
-			if (npinfo->rx_np == np) {
+			if (!list_empty(&npinfo->rx_np)) {
 				spin_lock_irqsave(&npinfo->rx_lock, flags);
-				npinfo->rx_np = NULL;
-				npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
+				list_del(&np->rx);
+				if (list_empty(&npinfo->rx_np))
+					npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
 				spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 			}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 794bcb897ff..62f3878a601 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1386,7 +1386,7 @@ static struct notifier_block rtnetlink_dev_notifier = {
 };
 
 
-static int rtnetlink_net_init(struct net *net)
+static int __net_init rtnetlink_net_init(struct net *net)
 {
 	struct sock *sk;
 	sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX,
@@ -1397,7 +1397,7 @@ static int rtnetlink_net_init(struct net *net)
 	return 0;
 }
 
-static void rtnetlink_net_exit(struct net *net)
+static void __net_exit rtnetlink_net_exit(struct net *net)
 {
 	netlink_kernel_release(net->rtnl);
 	net->rtnl = NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index e1f6f225f01..ceef50bd131 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -741,7 +741,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		struct timeval tm;
 	} v;
 
-	unsigned int lv = sizeof(int);
+	int lv = sizeof(int);
 	int len;
 
 	if (get_user(len, optlen))
@@ -2140,13 +2140,13 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot)
 }
 EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
 
-static int sock_inuse_init_net(struct net *net)
+static int __net_init sock_inuse_init_net(struct net *net)
 {
 	net->core.inuse = alloc_percpu(struct prot_inuse);
 	return net->core.inuse ? 0 : -ENOMEM;
 }
 
-static void sock_inuse_exit_net(struct net *net)
+static void __net_exit sock_inuse_exit_net(struct net *net)
 {
 	free_percpu(net->core.inuse);
 }