Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-android

16 files changed, 216 insertions, 36 deletions

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 990afab2be1b..c76a4388a5d7 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -340,7 +340,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 		int count = nr_pages;
 		while (nr_pages) {
 			s = rest_of_page(data);
-			pages[index++] = kmap_to_page(data);
+			if (is_vmalloc_addr(data))
+				pages[index++] = vmalloc_to_page(data);
+			else
+				pages[index++] = kmap_to_page(data);
 			data += s;
 			nr_pages--;
 		}
diff --git a/net/can/af_can.c b/net/can/af_can.c
index c4e50852c9f4..f59859a3f562 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
 #include <linux/skbuff.h>
 #include <linux/can.h>
 #include <linux/can/core.h>
+#include <linux/can/skb.h>
 #include <linux/ratelimit.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -290,7 +291,7 @@ int can_send(struct sk_buff *skb, int loop)
 				return -ENOMEM;
 			}
 
-			newskb->sk = skb->sk;
+			can_skb_set_owner(newskb, skb->sk);
 			newskb->ip_summed = CHECKSUM_UNNECESSARY;
 			newskb->pkt_type = PACKET_BROADCAST;
 		}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8f113e6ff327..35cf02d92766 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op)
 
 	/* send with loopback */
 	skb->dev = dev;
-	skb->sk = op->sk;
+	can_skb_set_owner(skb, op->sk);
 	can_send(skb, 1);
 
 	/* update statistics */
@@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	skb->dev = dev;
-	skb->sk  = sk;
+	can_skb_set_owner(skb, sk);
 	err = can_send(skb, 1); /* send with loopback */
 	dev_put(dev);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 1283c8442e99..a0e55ffc03c9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2374,7 +2374,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
 	int i;
@@ -2454,46 +2454,51 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-	__be16 protocol, netdev_features_t features)
+					    __be16 protocol,
+					    const struct net_device *dev,
+					    netdev_features_t features)
 {
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(skb->dev, skb)) {
+	} else if (illegal_highdma(dev, skb)) {
 		features &= ~NETIF_F_SG;
 	}
 
 	return features;
 }
 
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev)
 {
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = skb->dev->features;
+	netdev_features_t features = dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	}
 
-	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
 					       NETIF_F_HW_VLAN_STAG_TX);
 
 	if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) {
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	} else {
 		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
 				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_STAG_TX;
-		return harmonize_features(skb, protocol, features);
+		return harmonize_features(skb, protocol, dev, features);
 	}
+
+	return harmonize_features(skb, protocol, dev, features);
 }
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
 
 /*
  * Returns true if either:
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 0e9131195eb0..55e08e2de3a1 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -720,6 +720,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event,
 			attach_rules(&ops->rules_list, dev);
 		break;
 
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
+		break;
+
 	case NETDEV_UNREGISTER:
 		list_for_each_entry(ops, &net->rules_ops, list)
 			detach_rules(&ops->rules_list, dev);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 27f33f25cda8..433a1051d323 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -948,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 {
 	char *cur=opt, *delim;
 	int ipv6;
+	bool ipversion_set = false;
 
 	if (*cur != '@') {
 		if ((delim = strchr(cur, '@')) == NULL)
@@ -960,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	cur++;
 
 	if (*cur != '/') {
+		ipversion_set = true;
 		if ((delim = strchr(cur, '/')) == NULL)
 			goto parse_failed;
 		*delim = 0;
@@ -1002,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
 	if (ipv6 < 0)
 		goto parse_failed;
-	else if (np->ipv6 != (bool)ipv6)
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
 		goto parse_failed;
 	else
 		np->ipv6 = (bool)ipv6;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 20ee14d0a8a9..79143b7af7e5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -47,6 +47,8 @@
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/netdevice.h>
 #ifdef CONFIG_NET_CLS_ACT
 #include <net/pkt_sched.h>
@@ -3471,3 +3473,26 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	return true;
 }
 EXPORT_SYMBOL(skb_try_coalesce);
+
+/**
+ * skb_gso_transport_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_transport_seglen is used to determine the real size of the
+ * individual segments, including Layer4 headers (TCP/UDP).
+ *
+ * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
+ */
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	unsigned int hdr_len;
+
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		hdr_len = tcp_hdrlen(skb);
+	else
+		hdr_len = sizeof(struct udphdr);
+	return hdr_len + shinfo->gso_size;
+}
+EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
diff --git a/net/core/sock.c b/net/core/sock.c
index 50a345e5a26f..3ba527074f7f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1814,7 +1814,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 		gfp_t gfp = sk->sk_allocation;
 
 		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN;
+			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
 		pfrag->page = alloc_pages(gfp, order);
 		if (likely(pfrag->page)) {
 			pfrag->offset = 0;
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 31b127e8086b..ca118e8cb141 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -1173,7 +1173,27 @@ static struct header_ops lowpan_header_ops = {
 	.create	= lowpan_header_create,
 };
 
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+	dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	return 0;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
+	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_set_mac_address	= lowpan_set_address,
 };
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e392355afe22..b151e0ac7f27 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1439,7 +1439,8 @@ static size_t inet_nlmsg_size(void)
 	       + nla_total_size(4) /* IFA_ADDRESS */
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
-	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
+	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+	       + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
 }
 
 static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b7aebf..98d7e53d2afd 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+	       !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+	unsigned int mtu;
+
+	if (skb->local_df || !skb_is_gso(skb))
+		return false;
+
+	mtu = dst_mtu(skb_dst(skb));
+
+	/* if seglen > mtu, do software segmentation for IP fragmentation on
+	 * output.  DF bit cannot be set since ip_forward would have sent
+	 * icmp error.
+	 */
+	return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	features = netif_skb_dev_features(skb, dst->dev);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = dst_output(segs);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	if (ip_gso_exceeds_dst_mtu(skb))
+		return ip_forward_finish_gso(skb);
+
 	return dst_output(skb);
 }
 
@@ -88,8 +156,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(dst_mtu(&rt->dst)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6c6ab14da41..1a362f375e67 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1544,6 +1544,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
@@ -1645,8 +1646,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (err != 0)
 		goto no_route;
 
-	RT_CACHE_STAT_INC(in_slow_tot);
-
 	if (res.type == RTN_BROADCAST)
 		goto brd_input;
 
@@ -1715,6 +1714,7 @@ local_input:
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5560abfe6d30..d2df17940e07 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -686,7 +686,8 @@ static void tcp_tsq_handler(struct sock *sk)
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
  * One tasklest per cpu tries to send more skbs.
@@ -1875,7 +1876,15 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 * We abuse smp_mb__after_clear_bit() because
+			 * there is no smp_mb__after_set_bit() yet
+			 */
+			smp_mb__after_clear_bit();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
 
 		limit = mss_now;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b98b8e06739e..98a262b759ae 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -345,6 +345,20 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 	return dst_output(skb);
 }
 
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -467,8 +481,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 79bc251042ba..8554e5eebaeb 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -71,6 +71,7 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -1384,11 +1385,19 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk,
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+	sctp_assoc_t	assoc_id;
+	s32		addr_num;
+	compat_uptr_t	addrs;		/* struct sockaddr * */
+};
+#endif
+
 SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len,
 					char __user *optval,
 					int __user *optlen)
@@ -1397,16 +1406,30 @@ SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len,
 	sctp_assoc_t assoc_id = 0;
 	int err = 0;
 
-	if (len < sizeof(param))
-		return -EINVAL;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		struct compat_sctp_getaddrs_old param32;
 
-	if (copy_from_user(&param, optval, sizeof(param)))
-		return -EFAULT;
+		if (len < sizeof(param32))
+			return -EINVAL;
+		if (copy_from_user(&param32, optval, sizeof(param32)))
+			return -EFAULT;
 
-	err = __sctp_setsockopt_connectx(sk,
-			(struct sockaddr __user *)param.addrs,
-			param.addr_num, &assoc_id);
+		param.assoc_id = param32.assoc_id;
+		param.addr_num = param32.addr_num;
+		param.addrs = compat_ptr(param32.addrs);
+	} else
+#endif
+	{
+		if (len < sizeof(param))
+			return -EINVAL;
+		if (copy_from_user(&param, optval, sizeof(param)))
+			return -EFAULT;
+	}
 
+	err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+					 param.addrs, param.addr_num,
+					 &assoc_id);
 	if (err == 0 || err == -EINPROGRESS) {
 		if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
 			return -EFAULT;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 8a0e04d0928a..fc47165dc254 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -502,6 +502,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -519,7 +520,7 @@ static int xs_nospace(struct rpc_task *task)
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -529,6 +530,9 @@ static int xs_nospace(struct rpc_task *task)
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }