Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking updates from David Miller:
 "More bug fixes, nothing gets past these guys"

 1) More kernel info leaks found by Mathias Krause, this time in the
    IPSEC configuration layers.

 2) When IPSEC policies change, we do not properly make sure that cached
    routes (which could now be stale) throughout the system will be
    revalidated.  Fix this by generalizing the generation count
    invalidation scheme used by ipv4.  From Nicolas Dichtel.

 3) When repairing TCP sockets, we need to allow to restore not just the
    send window scale, but the receive one too.  Extend the existing
    interface to achieve this in a backwards compatible way.  From
    Andrey Vagin.

 4) A fix for FCOE scatter gather feature validation erroneously caused
    scatter gather to be disabled for things like AOE too.  From Ed L
    Cashin.

 5) Several cases of mishandling of error pointers, from Mathias Krause,
    Wei Yongjun, and Devendra Naga.

 6) Fix gianfar build, from Richard Cochran.

 7) CAP_NET_* failures should return -EPERM not -EACCES, from Zhao
    Hongjiang.

 8) Hardware reset fix in janz-ican3 CAN driver, from Ira W Snyder.

 9) Fix oops during rmmod in ti_hecc CAN driver, from Marc Kleine-Budde.

10) The removal of the conditional compilation of the clk support code
    in the stmmac driver broke things.  This is because the interfaces
    used are the ones that don't also perform the enable/disable of the
    clk.  Fix from Stefan Roese.

11) The QFQ packet scheduler can record out of range virtual start
    times, resulting later in misbehavior and even crashes.  Fix from
    Paolo Valente.

12) If MSG_WAITALL is used with IOAT DMA under TCP, we can wedge the
    receiver when the advertised receive window goes to zero.  Detect
    this case and force the processing of the IOAT DMA queue when it
    happens to avoid getting stuck.  Fix from Michal Kubecek.

13) batman-adv assumes that test_bit() returns only 0 or 1, but this is
    not true for x86 (which returns -1 or 0, via the 'sbb' instruction).
    Fix from Linus Lussing.

14) Fix small packet corruption in e1000, from Tushar Dave.

15) make_blackhole() in the IPSEC policy code can do one read unlock too
    many, fix from Li RongQing.

16) The new tcp_try_coalesce() code introduced a bug in TCP URG
    handling, fix from Eric Dumazet.

17) Fix memory leak in __netif_receive_skb() when doing zerocopy and
    when hit an OOM condition.  From Michael S Tsirkin.

18) netxen blindly deferences pdev->bus->self, which is not guarenteed
    to be non-NULL.  Fix from Nikolay Aleksandrov.

19) Fix a performance regression caused by mistakes in ipv6 checksum
    validation in the bnx2x driver, fix from Michal Schmidt.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (45 commits)
  net/stmmac: Use clk_prepare_enable and clk_disable_unprepare
  net: change return values from -EACCES to -EPERM
  net/irda: sh_sir: fix return value check in sh_sir_set_baudrate()
  stmmac: fix return value check in stmmac_open_ext_timer()
  gianfar: fix phc index build failure
  ipv6: fix return value check in fib6_add()
  bnx2x: remove false warning regarding interrupt number
  can: ti_hecc: fix oops during rmmod
  can: janz-ican3: fix support for older hardware revisions
  net: do not disable sg for packets requiring no checksum
  aoe: assert AoE packets marked as requiring no checksum
  at91ether: return PTR_ERR if call to clk_get fails
  xfrm_user: don't copy esn replay window twice for new states
  xfrm_user: ensure user supplied esn replay window is valid
  xfrm_user: fix info leak in copy_to_user_tmpl()
  xfrm_user: fix info leak in copy_to_user_policy()
  xfrm_user: fix info leak in copy_to_user_state()
  xfrm_user: fix info leak in copy_to_user_auth()
  net: qmi_wwan: adding Huawei E367, ZTE MF683 and Pantech P4200
  tcp: restore rcv_wscale in a repair mode (v2)
  ...

8 files changed, 45 insertions, 66 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 77e87aff419a..47800459e4cb 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1225,7 +1225,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event,
 	switch (event) {
 	case NETDEV_CHANGEADDR:
 		neigh_changeaddr(&arp_tbl, dev);
-		rt_cache_flush(dev_net(dev), 0);
+		rt_cache_flush(dev_net(dev));
 		break;
 	default:
 		break;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 44bf82e3aef7..e12fad773852 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -725,7 +725,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 		break;
 
 	case SIOCSIFFLAGS:
-		ret = -EACCES;
+		ret = -EPERM;
 		if (!capable(CAP_NET_ADMIN))
 			goto out;
 		break;
@@ -733,7 +733,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSIFBRDADDR:	/* Set the broadcast address */
 	case SIOCSIFDSTADDR:	/* Set the destination address */
 	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
-		ret = -EACCES;
+		ret = -EPERM;
 		if (!capable(CAP_NET_ADMIN))
 			goto out;
 		ret = -EINVAL;
@@ -1503,7 +1503,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 		if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 ||
 		    i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
 			if ((new_value == 0) && (old_value != 0))
-				rt_cache_flush(net, 0);
+				rt_cache_flush(net);
 	}
 
 	return ret;
@@ -1537,7 +1537,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
 				dev_disable_lro(idev->dev);
 			}
 			rtnl_unlock();
-			rt_cache_flush(net, 0);
+			rt_cache_flush(net);
 		}
 	}
 
@@ -1554,7 +1554,7 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write,
 	struct net *net = ctl->extra2;
 
 	if (write && *valp != val)
-		rt_cache_flush(net, 0);
+		rt_cache_flush(net);
 
 	return ret;
 }
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c43ae3fba792..8e2b475da9fa 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -148,7 +148,7 @@ static void fib_flush(struct net *net)
 	}
 
 	if (flushed)
-		rt_cache_flush(net, -1);
+		rt_cache_flush(net);
 }
 
 /*
@@ -999,11 +999,11 @@ static void nl_fib_lookup_exit(struct net *net)
 	net->ipv4.fibnl = NULL;
 }
 
-static void fib_disable_ip(struct net_device *dev, int force, int delay)
+static void fib_disable_ip(struct net_device *dev, int force)
 {
 	if (fib_sync_down_dev(dev, force))
 		fib_flush(dev_net(dev));
-	rt_cache_flush(dev_net(dev), delay);
+	rt_cache_flush(dev_net(dev));
 	arp_ifdown(dev);
 }
 
@@ -1020,7 +1020,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 		fib_sync_up(dev);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
-		rt_cache_flush(dev_net(dev), -1);
+		rt_cache_flush(dev_net(dev));
 		break;
 	case NETDEV_DOWN:
 		fib_del_ifaddr(ifa, NULL);
@@ -1029,9 +1029,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			/* Last address was deleted from this interface.
 			 * Disable IP.
 			 */
-			fib_disable_ip(dev, 1, 0);
+			fib_disable_ip(dev, 1);
 		} else {
-			rt_cache_flush(dev_net(dev), -1);
+			rt_cache_flush(dev_net(dev));
 		}
 		break;
 	}
@@ -1045,7 +1045,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	struct net *net = dev_net(dev);
 
 	if (event == NETDEV_UNREGISTER) {
-		fib_disable_ip(dev, 2, -1);
+		fib_disable_ip(dev, 2);
 		rt_flush_dev(dev);
 		return NOTIFY_DONE;
 	}
@@ -1062,14 +1062,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 		fib_sync_up(dev);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
-		rt_cache_flush(dev_net(dev), -1);
+		rt_cache_flush(dev_net(dev));
 		break;
 	case NETDEV_DOWN:
-		fib_disable_ip(dev, 0, 0);
+		fib_disable_ip(dev, 0);
 		break;
 	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGE:
-		rt_cache_flush(dev_net(dev), 0);
+		rt_cache_flush(dev_net(dev));
 		break;
 	case NETDEV_UNREGISTER_BATCH:
 		break;
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index a83d74e498d2..274309d3aded 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -259,7 +259,7 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
 
 static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
 {
-	rt_cache_flush(ops->fro_net, -1);
+	rt_cache_flush(ops->fro_net);
 }
 
 static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 57bd978483e1..d1b93595b4a7 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1286,7 +1286,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 
 			fib_release_info(fi_drop);
 			if (state & FA_S_ACCESSED)
-				rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
+				rt_cache_flush(cfg->fc_nlinfo.nl_net);
 			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
 				tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE);
 
@@ -1333,7 +1333,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	list_add_tail_rcu(&new_fa->fa_list,
 			  (fa ? &fa->fa_list : fa_head));
 
-	rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
+	rt_cache_flush(cfg->fc_nlinfo.nl_net);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 succeeded:
@@ -1708,7 +1708,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 		trie_leaf_remove(t, l);
 
 	if (fa->fa_state & FA_S_ACCESSED)
-		rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
+		rt_cache_flush(cfg->fc_nlinfo.nl_net);
 
 	fib_release_info(fa->fa_info);
 	alias_free_mem_rcu(fa);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 82cf2a722b23..fd9af60397b5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -202,11 +202,6 @@ EXPORT_SYMBOL(ip_tos2prio);
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
 #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
 
-static inline int rt_genid(struct net *net)
-{
-	return atomic_read(&net->ipv4.rt_genid);
-}
-
 #ifdef CONFIG_PROC_FS
 static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
 {
@@ -447,27 +442,9 @@ static inline bool rt_is_expired(const struct rtable *rth)
 	return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
 }
 
-/*
- * Perturbation of rt_genid by a small quantity [1..256]
- * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
- * many times (2^24) without giving recent rt_genid.
- * Jenkins hash is strong enough that litle changes of rt_genid are OK.
- */
-static void rt_cache_invalidate(struct net *net)
+void rt_cache_flush(struct net *net)
 {
-	unsigned char shuffle;
-
-	get_random_bytes(&shuffle, sizeof(shuffle));
-	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
-}
-
-/*
- * delay < 0  : invalidate cache (fast : entries will be deleted later)
- * delay >= 0 : invalidate & flush cache (can be long)
- */
-void rt_cache_flush(struct net *net, int delay)
-{
-	rt_cache_invalidate(net);
+	rt_genid_bump(net);
 }
 
 static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
@@ -2345,7 +2322,7 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 
 void ip_rt_multicast_event(struct in_device *in_dev)
 {
-	rt_cache_flush(dev_net(in_dev->dev), 0);
+	rt_cache_flush(dev_net(in_dev->dev));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -2354,16 +2331,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
 					size_t *lenp, loff_t *ppos)
 {
 	if (write) {
-		int flush_delay;
-		ctl_table ctl;
-		struct net *net;
-
-		memcpy(&ctl, __ctl, sizeof(ctl));
-		ctl.data = &flush_delay;
-		proc_dointvec(&ctl, write, buffer, lenp, ppos);
-
-		net = (struct net *)__ctl->extra1;
-		rt_cache_flush(net, flush_delay);
+		rt_cache_flush((struct net *)__ctl->extra1);
 		return 0;
 	}
 
@@ -2533,8 +2501,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
 
 static __net_init int rt_genid_init(struct net *net)
 {
-	get_random_bytes(&net->ipv4.rt_genid,
-			 sizeof(net->ipv4.rt_genid));
+	atomic_set(&net->rt_genid, 0);
 	get_random_bytes(&net->ipv4.dev_addr_genid,
 			 sizeof(net->ipv4.dev_addr_genid));
 	return 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2109ff4a1daf..5f6419341821 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1762,8 +1762,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 #ifdef CONFIG_NET_DMA
-		if (tp->ucopy.dma_chan)
-			dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+		if (tp->ucopy.dma_chan) {
+			if (tp->rcv_wnd == 0 &&
+			    !skb_queue_empty(&sk->sk_async_wait_queue)) {
+				tcp_service_net_dma(sk, true);
+				tcp_cleanup_rbuf(sk, copied);
+			} else
+				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+		}
 #endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
@@ -2325,10 +2331,17 @@ static int tcp_repair_options_est(struct tcp_sock *tp,
 			tp->rx_opt.mss_clamp = opt.opt_val;
 			break;
 		case TCPOPT_WINDOW:
-			if (opt.opt_val > 14)
-				return -EFBIG;
+			{
+				u16 snd_wscale = opt.opt_val & 0xFFFF;
+				u16 rcv_wscale = opt.opt_val >> 16;
+
+				if (snd_wscale > 14 || rcv_wscale > 14)
+					return -EFBIG;
 
-			tp->rx_opt.snd_wscale = opt.opt_val;
+				tp->rx_opt.snd_wscale = snd_wscale;
+				tp->rx_opt.rcv_wscale = rcv_wscale;
+				tp->rx_opt.wscale_ok = 1;
+			}
 			break;
 		case TCPOPT_SACK_PERM:
 			if (opt.opt_val != 0)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6e38c6c23caa..d377f4854cb8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4661,7 +4661,7 @@ queue_and_out:
 
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
-		else if (!sock_flag(sk, SOCK_DEAD))
+		if (!sock_flag(sk, SOCK_DEAD))
 			sk->sk_data_ready(sk, 0);
 		return;
 	}
@@ -5556,8 +5556,7 @@ no_ack:
 #endif
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			else
-				sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk, 0);
 			return 0;
 		}
 	}