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

17 files changed, 215 insertions, 146 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9b58d70b0e7d..4f52c3d50ebe 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -148,11 +148,16 @@ static int br_set_tx_csum(struct net_device *dev, u32 data)
 }
 
 static struct ethtool_ops br_ethtool_ops = {
-	.get_drvinfo = br_getinfo,
-	.get_link = ethtool_op_get_link,
-	.set_sg = br_set_sg,
-	.set_tx_csum = br_set_tx_csum,
-	.set_tso = br_set_tso,
+	.get_drvinfo    = br_getinfo,
+	.get_link	= ethtool_op_get_link,
+	.get_tx_csum	= ethtool_op_get_tx_csum,
+	.set_tx_csum 	= br_set_tx_csum,
+	.get_sg		= ethtool_op_get_sg,
+	.set_sg		= br_set_sg,
+	.get_tso	= ethtool_op_get_tso,
+	.set_tso	= br_set_tso,
+	.get_ufo	= ethtool_op_get_ufo,
+	.get_flags	= ethtool_op_get_flags,
 };
 
 void br_dev_setup(struct net_device *dev)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index dd61dcad6019..52f577a0f544 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -339,6 +339,93 @@ fault:
 	return -EFAULT;
 }
 
+/**
+ *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying to
+ *	@from: io vector to copy to
+ *	@len: amount of data to copy to buffer from iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is modified during the copy.
+ */
+int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
+				 struct iovec *from, int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_fromiovec(skb->data + offset, from, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = frag->page;
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_fromiovec(vaddr + frag->page_offset +
+					       offset - start, from, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	if (skb_shinfo(skb)->frag_list) {
+		struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+		for (; list; list = list->next) {
+			int end;
+
+			WARN_ON(start > offset + len);
+
+			end = start + list->len;
+			if ((copy = end - offset) > 0) {
+				if (copy > len)
+					copy = len;
+				if (skb_copy_datagram_from_iovec(list,
+								 offset - start,
+								 from, copy))
+					goto fault;
+				if ((len -= copy) == 0)
+					return 0;
+				offset += copy;
+			}
+			start = end;
+		}
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
+
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      u8 __user *to, int len,
 				      __wsum *csump)
diff --git a/net/core/dev.c b/net/core/dev.c
index 600bb23c4c2e..8d133802372b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1339,19 +1339,23 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 }
 
 
-void __netif_schedule(struct Qdisc *q)
+static inline void __netif_reschedule(struct Qdisc *q)
 {
-	if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) {
-		struct softnet_data *sd;
-		unsigned long flags;
+	struct softnet_data *sd;
+	unsigned long flags;
 
-		local_irq_save(flags);
-		sd = &__get_cpu_var(softnet_data);
-		q->next_sched = sd->output_queue;
-		sd->output_queue = q;
-		raise_softirq_irqoff(NET_TX_SOFTIRQ);
-		local_irq_restore(flags);
-	}
+	local_irq_save(flags);
+	sd = &__get_cpu_var(softnet_data);
+	q->next_sched = sd->output_queue;
+	sd->output_queue = q;
+	raise_softirq_irqoff(NET_TX_SOFTIRQ);
+	local_irq_restore(flags);
+}
+
+void __netif_schedule(struct Qdisc *q)
+{
+	if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
+		__netif_reschedule(q);
 }
 EXPORT_SYMBOL(__netif_schedule);
 
@@ -1800,9 +1804,13 @@ gso:
 
 		spin_lock(root_lock);
 
-		rc = qdisc_enqueue_root(skb, q);
-		qdisc_run(q);
-
+		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+			kfree_skb(skb);
+			rc = NET_XMIT_DROP;
+		} else {
+			rc = qdisc_enqueue_root(skb, q);
+			qdisc_run(q);
+		}
 		spin_unlock(root_lock);
 
 		goto out;
@@ -1974,15 +1982,15 @@ static void net_tx_action(struct softirq_action *h)
 
 			head = head->next_sched;
 
-			smp_mb__before_clear_bit();
-			clear_bit(__QDISC_STATE_SCHED, &q->state);
-
 			root_lock = qdisc_lock(q);
 			if (spin_trylock(root_lock)) {
+				smp_mb__before_clear_bit();
+				clear_bit(__QDISC_STATE_SCHED,
+					  &q->state);
 				qdisc_run(q);
 				spin_unlock(root_lock);
 			} else {
-				__netif_schedule(q);
+				__netif_reschedule(q);
 			}
 		}
 	}
@@ -2084,7 +2092,8 @@ static int ing_filter(struct sk_buff *skb)
 	q = rxq->qdisc;
 	if (q != &noop_qdisc) {
 		spin_lock(qdisc_lock(q));
-		result = qdisc_enqueue_root(skb, q);
+		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+			result = qdisc_enqueue_root(skb, q);
 		spin_unlock(qdisc_lock(q));
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 84640172d65d..ca1ccdf1ef76 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2256,14 +2256,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 			segs = nskb;
 		tail = nskb;
 
-		nskb->dev = skb->dev;
-		skb_copy_queue_mapping(nskb, skb);
-		nskb->priority = skb->priority;
-		nskb->protocol = skb->protocol;
-		nskb->vlan_tci = skb->vlan_tci;
-		nskb->dst = dst_clone(skb->dst);
-		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
-		nskb->pkt_type = skb->pkt_type;
+		__copy_skb_header(nskb, skb);
 		nskb->mac_len = skb->mac_len;
 
 		skb_reserve(nskb, headroom);
@@ -2274,6 +2267,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 		skb_copy_from_linear_data(skb, skb_put(nskb, doffset),
 					  doffset);
 		if (!sg) {
+			nskb->ip_summed = CHECKSUM_NONE;
 			nskb->csum = skb_copy_and_csum_bits(skb, offset,
 							    skb_put(nskb, len),
 							    len, 0);
@@ -2283,8 +2277,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 		frag = skb_shinfo(nskb)->frags;
 		k = 0;
 
-		nskb->ip_summed = CHECKSUM_PARTIAL;
-		nskb->csum = skb->csum;
 		skb_copy_from_linear_data_offset(skb, offset,
 						 skb_put(nskb, hsize), hsize);
 
diff --git a/net/dccp/input.c b/net/dccp/input.c
index df2f110df94a..803933ab396d 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -411,12 +411,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk,
 		struct dccp_sock *dp = dccp_sk(sk);
 		long tstamp = dccp_timestamp();
 
-		/* Stop the REQUEST timer */
-		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
-		WARN_ON(sk->sk_send_head == NULL);
-		__kfree_skb(sk->sk_send_head);
-		sk->sk_send_head = NULL;
-
 		if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
 			       dp->dccps_awl, dp->dccps_awh)) {
 			dccp_pr_debug("invalid ackno: S.AWL=%llu, "
@@ -441,6 +435,12 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk,
 				    DCCP_ACKVEC_STATE_RECEIVED))
 			goto out_invalid_packet; /* FIXME: change error code */
 
+		/* Stop the REQUEST timer */
+		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
+		WARN_ON(sk->sk_send_head == NULL);
+		kfree_skb(sk->sk_send_head);
+		sk->sk_send_head = NULL;
+
 		dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
 		dccp_update_gsr(sk, dp->dccps_isr);
 		/*
diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c
index 49587a497229..462a22c97877 100644
--- a/net/ipv4/netfilter/ipt_addrtype.c
+++ b/net/ipv4/netfilter/ipt_addrtype.c
@@ -70,7 +70,7 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct net_device *in,
 		       (info->flags & IPT_ADDRTYPE_INVERT_SOURCE);
 	if (ret && info->dest)
 		ret &= match_type(dev, iph->daddr, info->dest) ^
-		       (info->flags & IPT_ADDRTYPE_INVERT_DEST);
+		       !!(info->flags & IPT_ADDRTYPE_INVERT_DEST);
 	return ret;
 }
 
diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c
index 91537f11273f..6c4f11f51446 100644
--- a/net/ipv4/netfilter/nf_nat_proto_common.c
+++ b/net/ipv4/netfilter/nf_nat_proto_common.c
@@ -73,9 +73,13 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 		range_size = ntohs(range->max.all) - min + 1;
 	}
 
-	off = *rover;
 	if (range->flags & IP_NAT_RANGE_PROTO_RANDOM)
-		off = net_random();
+		off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip,
+						 maniptype == IP_NAT_MANIP_SRC
+						 ? tuple->dst.u.all
+						 : tuple->src.u.all);
+	else
+		off = *rover;
 
 	for (i = 0; i < range_size; i++, off++) {
 		*portptr = htons(min + off % range_size);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 741cfcd96f88..4e5eac301f91 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -911,7 +911,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		} else {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
-				src_info.ipi6_ifindex = np->mcast_oif;
+				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if;
 				ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr);
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
@@ -921,7 +921,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			}
 			if (np->rxopt.bits.rxoinfo) {
 				struct in6_pktinfo src_info;
-				src_info.ipi6_ifindex = np->mcast_oif;
+				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if;
 				ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr);
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e1d11c9b6729..1e97fb9fb34b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2103,6 +2103,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 			rcu_read_unlock();
 			return;
 		}
+		/* update new sta with its last rx activity */
+		sta->last_rx = jiffies;
 	}
 
 	/*
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 105a616c5c78..a8752031adcb 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -968,7 +968,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[])
 		/* need to zero data of old helper */
 		memset(&help->help, 0, sizeof(help->help));
 	} else {
-		help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
+		help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 		if (help == NULL)
 			return -ENOMEM;
 	}
@@ -1136,16 +1136,33 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 	ct->timeout.expires = jiffies + ct->timeout.expires * HZ;
 	ct->status |= IPS_CONFIRMED;
 
+	rcu_read_lock();
+	helper = __nf_ct_helper_find(rtuple);
+	if (helper) {
+		help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+		if (help == NULL) {
+			rcu_read_unlock();
+			err = -ENOMEM;
+			goto err;
+		}
+		/* not in hash table yet so not strictly necessary */
+		rcu_assign_pointer(help->helper, helper);
+	}
+
 	if (cda[CTA_STATUS]) {
 		err = ctnetlink_change_status(ct, cda);
-		if (err < 0)
+		if (err < 0) {
+			rcu_read_unlock();
 			goto err;
+		}
 	}
 
 	if (cda[CTA_PROTOINFO]) {
 		err = ctnetlink_change_protoinfo(ct, cda);
-		if (err < 0)
+		if (err < 0) {
+			rcu_read_unlock();
 			goto err;
+		}
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_KERNEL);
@@ -1155,19 +1172,6 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 		ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
 #endif
 
-	rcu_read_lock();
-	helper = __nf_ct_helper_find(rtuple);
-	if (helper) {
-		help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
-		if (help == NULL) {
-			rcu_read_unlock();
-			err = -ENOMEM;
-			goto err;
-		}
-		/* not in hash table yet so not strictly necessary */
-		rcu_assign_pointer(help->helper, helper);
-	}
-
 	/* setup master conntrack: this is a confirmed expectation */
 	if (master_ct) {
 		__set_bit(IPS_EXPECTED_BIT, &ct->status);
diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c
index d2d45655cd1a..35a9994e2339 100644
--- a/net/rfkill/rfkill.c
+++ b/net/rfkill/rfkill.c
@@ -150,6 +150,8 @@ static void update_rfkill_state(struct rfkill *rfkill)
  * calls and handling all the red tape such as issuing notifications
  * if the call is successful.
  *
+ * Suspended devices are not touched at all, and -EAGAIN is returned.
+ *
  * Note that the @force parameter cannot override a (possibly cached)
  * state of RFKILL_STATE_HARD_BLOCKED.  Any device making use of
  * RFKILL_STATE_HARD_BLOCKED implements either get_state() or
@@ -168,6 +170,9 @@ static int rfkill_toggle_radio(struct rfkill *rfkill,
 	int retval = 0;
 	enum rfkill_state oldstate, newstate;
 
+	if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP))
+		return -EBUSY;
+
 	oldstate = rfkill->state;
 
 	if (rfkill->get_state && !force &&
@@ -214,7 +219,7 @@ static int rfkill_toggle_radio(struct rfkill *rfkill,
  *
  * This function toggles the state of all switches of given type,
  * unless a specific switch is claimed by userspace (in which case,
- * that switch is left alone).
+ * that switch is left alone) or suspended.
  */
 void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state)
 {
@@ -239,8 +244,8 @@ EXPORT_SYMBOL(rfkill_switch_all);
 /**
  * rfkill_epo - emergency power off all transmitters
  *
- * This kicks all rfkill devices to RFKILL_STATE_SOFT_BLOCKED, ignoring
- * everything in its path but rfkill_mutex and rfkill->mutex.
+ * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED,
+ * ignoring everything in its path but rfkill_mutex and rfkill->mutex.
  */
 void rfkill_epo(void)
 {
@@ -458,13 +463,14 @@ static int rfkill_resume(struct device *dev)
 	if (dev->power.power_state.event != PM_EVENT_ON) {
 		mutex_lock(&rfkill->mutex);
 
+		dev->power.power_state.event = PM_EVENT_ON;
+
 		/* restore radio state AND notify everybody */
 		rfkill_toggle_radio(rfkill, rfkill->state, 1);
 
 		mutex_unlock(&rfkill->mutex);
 	}
 
-	dev->power.power_state = PMSG_ON;
 	return 0;
 }
 #else
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c25465e5607a..9372ec41ce84 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -27,6 +27,7 @@
 #include <linux/kmod.h>
 #include <linux/list.h>
 #include <linux/hrtimer.h>
+#include <linux/lockdep.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -426,7 +427,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 
 	wd->qdisc->flags &= ~TCQ_F_THROTTLED;
 	smp_wmb();
-	__netif_schedule(wd->qdisc);
+	__netif_schedule(qdisc_root(wd->qdisc));
 
 	return HRTIMER_NORESTART;
 }
@@ -637,11 +638,8 @@ static void notify_and_destroy(struct sk_buff *skb, struct nlmsghdr *n, u32 clid
 	if (new || old)
 		qdisc_notify(skb, n, clid, old, new);
 
-	if (old) {
-		spin_lock_bh(&old->q.lock);
+	if (old)
 		qdisc_destroy(old);
-		spin_unlock_bh(&old->q.lock);
-	}
 }
 
 /* Graft qdisc "new" to class "classid" of qdisc "parent" or
@@ -707,6 +705,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 	return err;
 }
 
+/* lockdep annotation is needed for ingress; egress gets it only for name */
+static struct lock_class_key qdisc_tx_lock;
+static struct lock_class_key qdisc_rx_lock;
+
 /*
    Allocate and initialize new qdisc.
 
@@ -767,6 +769,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 	if (handle == TC_H_INGRESS) {
 		sch->flags |= TCQ_F_INGRESS;
 		handle = TC_H_MAKE(TC_H_INGRESS, 0);
+		lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock);
 	} else {
 		if (handle == 0) {
 			handle = qdisc_alloc_handle(dev);
@@ -774,6 +777,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 			if (handle == 0)
 				goto err_out3;
 		}
+		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 	}
 
 	sch->handle = handle;
@@ -1084,20 +1088,13 @@ create_n_graft:
 	}
 
 graft:
-	if (1) {
-		spinlock_t *root_lock;
-
-		err = qdisc_graft(dev, p, skb, n, clid, q, NULL);
-		if (err) {
-			if (q) {
-				root_lock = qdisc_root_lock(q);
-				spin_lock_bh(root_lock);
-				qdisc_destroy(q);
-				spin_unlock_bh(root_lock);
-			}
-			return err;
-		}
+	err = qdisc_graft(dev, p, skb, n, clid, q, NULL);
+	if (err) {
+		if (q)
+			qdisc_destroy(q);
+		return err;
 	}
+
 	return 0;
 }
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 4e261ce62f48..47ef492c4ff4 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -654,7 +654,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer)
 	}
 
 	sch->flags &= ~TCQ_F_THROTTLED;
-	__netif_schedule(sch);
+	__netif_schedule(qdisc_root(sch));
 	return HRTIMER_NORESTART;
 }
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 468574682caa..c3ed4d44fc14 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -518,14 +518,17 @@ void qdisc_reset(struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-/* this is the rcu callback function to clean up a qdisc when there
- * are no further references to it */
-
-static void __qdisc_destroy(struct rcu_head *head)
+void qdisc_destroy(struct Qdisc *qdisc)
 {
-	struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu);
 	const struct Qdisc_ops  *ops = qdisc->ops;
 
+	if (qdisc->flags & TCQ_F_BUILTIN ||
+	    !atomic_dec_and_test(&qdisc->refcnt))
+		return;
+
+	if (qdisc->parent)
+		list_del(&qdisc->list);
+
 #ifdef CONFIG_NET_SCHED
 	qdisc_put_stab(qdisc->stab);
 #endif
@@ -542,20 +545,6 @@ static void __qdisc_destroy(struct rcu_head *head)
 
 	kfree((char *) qdisc - qdisc->padded);
 }
-
-/* Under qdisc_lock(qdisc) and BH! */
-
-void qdisc_destroy(struct Qdisc *qdisc)
-{
-	if (qdisc->flags & TCQ_F_BUILTIN ||
-	    !atomic_dec_and_test(&qdisc->refcnt))
-		return;
-
-	if (qdisc->parent)
-		list_del(&qdisc->list);
-
-	call_rcu(&qdisc->q_rcu, __qdisc_destroy);
-}
 EXPORT_SYMBOL(qdisc_destroy);
 
 static bool dev_all_qdisc_sleeping_noop(struct net_device *dev)
@@ -597,6 +586,9 @@ static void transition_one_qdisc(struct net_device *dev,
 	struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping;
 	int *need_watchdog_p = _need_watchdog;
 
+	if (!(new_qdisc->flags & TCQ_F_BUILTIN))
+		clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
+
 	rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
 	if (need_watchdog_p && new_qdisc != &noqueue_qdisc)
 		*need_watchdog_p = 1;
@@ -640,6 +632,9 @@ static void dev_deactivate_queue(struct net_device *dev,
 	if (qdisc) {
 		spin_lock_bh(qdisc_lock(qdisc));
 
+		if (!(qdisc->flags & TCQ_F_BUILTIN))
+			set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
+
 		dev_queue->qdisc = qdisc_default;
 		qdisc_reset(qdisc);
 
@@ -647,7 +642,7 @@ static void dev_deactivate_queue(struct net_device *dev,
 	}
 }
 
-static bool some_qdisc_is_busy(struct net_device *dev, int lock)
+static bool some_qdisc_is_busy(struct net_device *dev)
 {
 	unsigned int i;
 
@@ -661,14 +656,12 @@ static bool some_qdisc_is_busy(struct net_device *dev, int lock)
 		q = dev_queue->qdisc_sleeping;
 		root_lock = qdisc_lock(q);
 
-		if (lock)
-			spin_lock_bh(root_lock);
+		spin_lock_bh(root_lock);
 
 		val = (test_bit(__QDISC_STATE_RUNNING, &q->state) ||
 		       test_bit(__QDISC_STATE_SCHED, &q->state));
 
-		if (lock)
-			spin_unlock_bh(root_lock);
+		spin_unlock_bh(root_lock);
 
 		if (val)
 			return true;
@@ -678,8 +671,6 @@ static bool some_qdisc_is_busy(struct net_device *dev, int lock)
 
 void dev_deactivate(struct net_device *dev)
 {
-	bool running;
-
 	netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc);
 	dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc);
 
@@ -689,25 +680,8 @@ void dev_deactivate(struct net_device *dev)
 	synchronize_rcu();
 
 	/* Wait for outstanding qdisc_run calls. */
-	do {
-		while (some_qdisc_is_busy(dev, 0))
-			yield();
-
-		/*
-		 * Double-check inside queue lock to ensure that all effects
-		 * of the queue run are visible when we return.
-		 */
-		running = some_qdisc_is_busy(dev, 1);
-
-		/*
-		 * The running flag should never be set at this point because
-		 * we've already set dev->qdisc to noop_qdisc *inside* the same
-		 * pair of spin locks.  That is, if any qdisc_run starts after
-		 * our initial test it should see the noop_qdisc and then
-		 * clear the RUNNING bit before dropping the queue lock.  So
-		 * if it is set here then we've found a bug.
-		 */
-	} while (WARN_ON_ONCE(running));
+	while (some_qdisc_is_busy(dev))
+		yield();
 }
 
 static void dev_init_scheduler_queue(struct net_device *dev,
@@ -736,14 +710,10 @@ static void shutdown_scheduler_queue(struct net_device *dev,
 	struct Qdisc *qdisc_default = _qdisc_default;
 
 	if (qdisc) {
-		spinlock_t *root_lock = qdisc_lock(qdisc);
-
 		dev_queue->qdisc = qdisc_default;
 		dev_queue->qdisc_sleeping = qdisc_default;
 
-		spin_lock_bh(root_lock);
 		qdisc_destroy(qdisc);
-		spin_unlock_bh(root_lock);
 	}
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 6febd245e62b..0df0df202ed0 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -577,7 +577,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			sch->qstats.drops++;
 			cl->qstats.drops++;
 		}
-		return NET_XMIT_DROP;
+		return ret;
 	} else {
 		cl->bstats.packets +=
 			skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
@@ -623,7 +623,7 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
 			sch->qstats.drops++;
 			cl->qstats.drops++;
 		}
-		return NET_XMIT_DROP;
+		return ret;
 	} else
 		htb_activate(q, cl);
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index eac197610edf..a6697c686c7f 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -113,11 +113,11 @@ prio_requeue(struct sk_buff *skb, struct Qdisc* sch)
 	if ((ret = qdisc->ops->requeue(skb, qdisc)) == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		sch->qstats.requeues++;
-		return 0;
+		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
 		sch->qstats.drops++;
-	return NET_XMIT_DROP;
+	return ret;
 }
 
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 7d3b7ff3bf07..94c61598b86a 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -123,15 +123,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	int ret;
 
-	if (qdisc_pkt_len(skb) > q->max_size) {
-		sch->qstats.drops++;
-#ifdef CONFIG_NET_CLS_ACT
-		if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
-#endif
-			kfree_skb(skb);
-
-		return NET_XMIT_DROP;
-	}
+	if (qdisc_pkt_len(skb) > q->max_size)
+		return qdisc_reshape_fail(skb, sch);
 
 	ret = qdisc_enqueue(skb, q->qdisc);
 	if (ret != 0) {