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

Pull networking changes from David Miller:
 "Most importantly this should cure the ipv4-mapped ipv6 socket TCP
  crashes some people were seeing, otherwise:

   1) Fix e1000e autonegotiation handling regression, from Tushar Dave.

   2) Fix TX data corruption race on e1000e down, also from Tushar Dave.

   3) Fix bfin_sir IRDA driver build, from Sonic Zhang.

   4) AF_PACKET mmap() tests a flag in the TX ring shared between
      userspace and the kernel for an internal consistency check.  It
      really shouldn't do this to validate the kernel's own behavior
      because the user can corrupt it to be any value at all.  From
      Daniel Borkmann.

   5) Fix TCP metrics leak on netns dismantle, from Eric Dumazet.

   6) Orphan the anonymous TCP socket from the SKB in
      ip_send_unicast_reply() so that the rest of the stack needn't see
      it.  Otherwise we get selinux problems of all sorts, from Eric
      Dumazet.

      This is the best way to fix this since the socket is just a place
      holder for sending packets in a context where we have no real
      socket at all.

   7) Fix TUN detach crashes, from Stanislav Kinsbursky.

   8) dev_set_alias() leaks memory on krealloc() failure, from Alexey
      Khoroshilov.

   9) FIB trie must use call_rcu() not call_rcu_bh(), because this code
      is not universally invoked from software interrupts.  From Eric
      Dumazet.

  10) PPTP looks up ipv4 routes with the wrong network namespace, fix
      from Gao Feng."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (33 commits)
  bnx2x: Fix compiler warnings
  af_packet: remove BUG statement in tpacket_destruct_skb
  macvtap: rcu_dereference outside read-lock section
  codel: refine one condition to avoid a nul rec_inv_sqrt
  ixgbe: add missing braces
  ipv4: fix ip_send_skb()
  net: tcp: ipv6_mapped needs sk_rx_dst_set method
  ipv4: tcp: unicast_sock should not land outside of TCP stack
  bnx2x: Fix recovery flow cleanup during probe
  bnx2x: fix unload previous driver flow when flr-capable
  tun: don't zeroize sock->file on detach
  igb: Fix register defines for all non-82575 hardware
  e1000e: fix panic while dumping packets on Tx hang with IOMMU
  igb: fix panic while dumping packets on Tx hang with IOMMU
  tcp: must free metrics at net dismantle
  net/stmmac: mark probe function as __devinit
  lpc_eth: remove obsolete ifdefs
  net/core: Fix potential memory leak in dev_set_alias()
  cdc-phonet: Don't leak in usbpn_open
  batman-adv: Fix mem leak in the batadv_tt_local_event() function
  ...

14 files changed, 112 insertions, 38 deletions

diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index a438f4b582fc..99dd8f75b3ff 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -197,6 +197,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
 del:
 		list_del(&entry->list);
 		kfree(entry);
+		kfree(tt_change_node);
 		event_removed = true;
 		goto unlock;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index f91abf800161..a39354ee1432 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1055,6 +1055,8 @@ rollback:
  */
 int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
+	char *new_ifalias;
+
 	ASSERT_RTNL();
 
 	if (len >= IFALIASZ)
@@ -1068,9 +1070,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 		return 0;
 	}
 
-	dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
-	if (!dev->ifalias)
+	new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+	if (!new_ifalias)
 		return -ENOMEM;
+	dev->ifalias = new_ifalias;
 
 	strlcpy(dev->ifalias, alias, len+1);
 	return len;
diff --git a/net/core/dst.c b/net/core/dst.c
index 069d51d29414..56d63612e1e4 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -149,7 +149,15 @@ int dst_discard(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard);
 
-const u32 dst_default_metrics[RTAX_MAX];
+const u32 dst_default_metrics[RTAX_MAX + 1] = {
+	/* This initializer is needed to force linker to place this variable
+	 * into const section. Otherwise it might end into bss section.
+	 * We really want to avoid false sharing on this variable, and catch
+	 * any writes on it.
+	 */
+	[RTAX_MAX] = 0xdeadbeef,
+};
+
 
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 		int initial_ref, int initial_obsolete, unsigned short flags)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index f0cdb30921c0..57bd978483e1 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -367,7 +367,7 @@ static void __leaf_free_rcu(struct rcu_head *head)
 
 static inline void free_leaf(struct leaf *l)
 {
-	call_rcu_bh(&l->rcu, __leaf_free_rcu);
+	call_rcu(&l->rcu, __leaf_free_rcu);
 }
 
 static inline void free_leaf_info(struct leaf_info *leaf)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 76dde25fb9a0..147ccc3e93db 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1366,9 +1366,8 @@ out:
 	return skb;
 }
 
-int ip_send_skb(struct sk_buff *skb)
+int ip_send_skb(struct net *net, struct sk_buff *skb)
 {
-	struct net *net = sock_net(skb->sk);
 	int err;
 
 	err = ip_local_out(skb);
@@ -1391,7 +1390,7 @@ int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
 		return 0;
 
 	/* Netfilter gets whole the not fragmented skb. */
-	return ip_send_skb(skb);
+	return ip_send_skb(sock_net(sk), skb);
 }
 
 /*
@@ -1536,6 +1535,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
+		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 272241f16fcb..767823764016 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1869,7 +1869,7 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
 	.twsk_destructor= tcp_twsk_destructor,
 };
 
-static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
@@ -1877,6 +1877,7 @@ static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	sk->sk_rx_dst = dst;
 	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 }
+EXPORT_SYMBOL(inet_sk_rx_dst_set);
 
 const struct inet_connection_sock_af_ops ipv4_specific = {
 	.queue_xmit	   = ip_queue_xmit,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 2288a6399e1e..0abe67bb4d3a 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -731,6 +731,18 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 
 static void __net_exit tcp_net_metrics_exit(struct net *net)
 {
+	unsigned int i;
+
+	for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) {
+		struct tcp_metrics_block *tm, *next;
+
+		tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1);
+		while (tm) {
+			next = rcu_dereference_protected(tm->tcpm_next, 1);
+			kfree(tm);
+			tm = next;
+		}
+	}
 	kfree(net->ipv4.tcp_metrics_hash);
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b4c3582a991f..6f6d1aca3c3d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -758,7 +758,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 		uh->check = CSUM_MANGLED_0;
 
 send:
-	err = ip_send_skb(skb);
+	err = ip_send_skb(sock_net(sk), skb);
 	if (err) {
 		if (err == -ENOBUFS && !inet->recverr) {
 			UDP_INC_STATS_USER(sock_net(sk),
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a439e9a4c01..bb9ce2b2f377 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1777,6 +1777,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.queue_xmit	   = ip_queue_xmit,
 	.send_check	   = tcp_v4_send_check,
 	.rebuild_header	   = inet_sk_rebuild_header,
+	.sk_rx_dst_set	   = inet_sk_rx_dst_set,
 	.conn_request	   = tcp_v6_conn_request,
 	.syn_recv_sock	   = tcp_v6_syn_recv_sock,
 	.net_header_len	   = sizeof(struct iphdr),
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ceaca7c134a0..8ac890a1a4c0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1079,7 +1079,7 @@ static void *packet_current_rx_frame(struct packet_sock *po,
 	default:
 		WARN(1, "TPACKET version not supported\n");
 		BUG();
-		return 0;
+		return NULL;
 	}
 }
 
@@ -1936,7 +1936,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 	if (likely(po->tx_ring.pg_vec)) {
 		ph = skb_shinfo(skb)->destructor_arg;
-		BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING);
 		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
 		atomic_dec(&po->tx_ring.pending);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 9af01f3df18c..e4723d31fdd5 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -203,6 +203,34 @@ out:
 	return index;
 }
 
+/* Length of the next packet (0 if the queue is empty). */
+static unsigned int qdisc_peek_len(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	skb = sch->ops->peek(sch);
+	return skb ? qdisc_pkt_len(skb) : 0;
+}
+
+static void qfq_deactivate_class(struct qfq_sched *, struct qfq_class *);
+static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl,
+			       unsigned int len);
+
+static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl,
+				    u32 lmax, u32 inv_w, int delta_w)
+{
+	int i;
+
+	/* update qfq-specific data */
+	cl->lmax = lmax;
+	cl->inv_w = inv_w;
+	i = qfq_calc_index(cl->inv_w, cl->lmax);
+
+	cl->grp = &q->groups[i];
+
+	q->wsum += delta_w;
+}
+
 static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 			    struct nlattr **tca, unsigned long *arg)
 {
@@ -250,6 +278,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		lmax = 1UL << QFQ_MTU_SHIFT;
 
 	if (cl != NULL) {
+		bool need_reactivation = false;
+
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
@@ -258,12 +288,29 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 				return err;
 		}
 
-		if (inv_w != cl->inv_w) {
-			sch_tree_lock(sch);
-			q->wsum += delta_w;
-			cl->inv_w = inv_w;
-			sch_tree_unlock(sch);
+		if (lmax == cl->lmax && inv_w == cl->inv_w)
+			return 0; /* nothing to update */
+
+		i = qfq_calc_index(inv_w, lmax);
+		sch_tree_lock(sch);
+		if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
+			/*
+			 * shift cl->F back, to not charge the
+			 * class for the not-yet-served head
+			 * packet
+			 */
+			cl->F = cl->S;
+			/* remove class from its slot in the old group */
+			qfq_deactivate_class(q, cl);
+			need_reactivation = true;
 		}
+
+		qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
+
+		if (need_reactivation) /* activate in new group */
+			qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+		sch_tree_unlock(sch);
+
 		return 0;
 	}
 
@@ -273,11 +320,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	cl->refcnt = 1;
 	cl->common.classid = classid;
-	cl->lmax = lmax;
-	cl->inv_w = inv_w;
-	i = qfq_calc_index(cl->inv_w, cl->lmax);
 
-	cl->grp = &q->groups[i];
+	qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
 
 	cl->qdisc = qdisc_create_dflt(sch->dev_queue,
 				      &pfifo_qdisc_ops, classid);
@@ -294,7 +338,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 			return err;
 		}
 	}
-	q->wsum += weight;
 
 	sch_tree_lock(sch);
 	qdisc_class_hash_insert(&q->clhash, &cl->common);
@@ -711,15 +754,6 @@ static void qfq_update_eligible(struct qfq_sched *q, u64 old_V)
 	}
 }
 
-/* What is length of next packet in queue (0 if queue is empty) */
-static unsigned int qdisc_peek_len(struct Qdisc *sch)
-{
-	struct sk_buff *skb;
-
-	skb = sch->ops->peek(sch);
-	return skb ? qdisc_pkt_len(skb) : 0;
-}
-
 /*
  * Updates the class, returns true if also the group needs to be updated.
  */
@@ -843,11 +877,8 @@ static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl)
 static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
-	struct qfq_group *grp;
 	struct qfq_class *cl;
 	int err;
-	u64 roundedS;
-	int s;
 
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -876,11 +907,25 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 
 	/* If reach this point, queue q was idle */
-	grp = cl->grp;
+	qfq_activate_class(q, cl, qdisc_pkt_len(skb));
+
+	return err;
+}
+
+/*
+ * Handle class switch from idle to backlogged.
+ */
+static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl,
+			       unsigned int pkt_len)
+{
+	struct qfq_group *grp = cl->grp;
+	u64 roundedS;
+	int s;
+
 	qfq_update_start(q, cl);
 
 	/* compute new finish time and rounded start. */
-	cl->F = cl->S + (u64)qdisc_pkt_len(skb) * cl->inv_w;
+	cl->F = cl->S + (u64)pkt_len * cl->inv_w;
 	roundedS = qfq_round_down(cl->S, grp->slot_shift);
 
 	/*
@@ -917,8 +962,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 skip_update:
 	qfq_slot_insert(grp, cl, roundedS);
-
-	return err;
 }
 
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 31b40cc4a9c3..dcd64d5b07aa 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -952,6 +952,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		 */
 		synchronize_rcu();
 		INIT_LIST_HEAD(&wdev->list);
+		/*
+		 * Ensure that all events have been processed and
+		 * freed.
+		 */
+		cfg80211_process_wdev_events(wdev);
 		break;
 	case NETDEV_PRE_UP:
 		if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)))
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 5206c6844fd7..bc7430b54771 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -426,6 +426,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			  struct net_device *dev, enum nl80211_iftype ntype,
 			  u32 *flags, struct vif_params *params);
 void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev);
+void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 
 int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 struct wireless_dev *wdev,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 26f8cd30f712..994e2f0cc7a8 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -735,7 +735,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev)
 	wdev->connect_keys = NULL;
 }
 
-static void cfg80211_process_wdev_events(struct wireless_dev *wdev)
+void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 {
 	struct cfg80211_event *ev;
 	unsigned long flags;