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

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (183 commits)
  [TG3]: Update version to 3.78.
  [TG3]: Add missing NVRAM strapping.
  [TG3]: Enable auto MDI.
  [TG3]: Fix the polarity bit.
  [TG3]: Fix irq_sync race condition.
  [NET_SCHED]: ematch: module autoloading
  [TCP]: tcp probe wraparound handling and other changes
  [RTNETLINK]: rtnl_link: allow specifying initial device address
  [RTNETLINK]: rtnl_link API simplification
  [VLAN]: Fix MAC address handling
  [ETH]: Validate address in eth_mac_addr
  [NET]: Fix races in net_rx_action vs netpoll.
  [AF_UNIX]: Rewrite garbage collector, fixes race.
  [NETFILTER]: {ip, nf}_conntrack_sctp: fix remotely triggerable NULL ptr dereference (CVE-2007-2876)
  [NET]: Make all initialized struct seq_operations const.
  [UDP]: Fix length check.
  [IPV6]: Remove unneeded pointer idev from addrconf_cleanup().
  [DECNET]: Another unnecessary net/tcp.h inclusion in net/dn.h
  [IPV6]: Make IPV6_{RECV,2292}RTHDR boolean options.
  [IPV6]: Do not send RH0 anymore.
  ...

Fixed up trivial conflict in Documentation/feature-removal-schedule.txt
manually.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

39 files changed, 327 insertions, 571 deletions

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 475df8449be9..b4662888bdbd 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -111,6 +111,17 @@ config NET_SCH_PRIO
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_prio.
 
+config NET_SCH_RR
+	tristate "Multi Band Round Robin Queuing (RR)"
+	select NET_SCH_PRIO
+	---help---
+	  Say Y here if you want to use an n-band round robin packet
+	  scheduler.
+
+	  The module uses sch_prio for its framework and is aliased as
+	  sch_rr, so it will load sch_prio, although it is referred
+	  to using sch_rr.
+
 config NET_SCH_RED
 	tristate "Random Early Detection (RED)"
 	---help---
@@ -275,7 +286,6 @@ config CLS_U32_MARK
 config NET_CLS_RSVP
 	tristate "IPv4 Resource Reservation Protocol (RSVP)"
 	select NET_CLS
-	select NET_ESTIMATOR
 	---help---
 	  The Resource Reservation Protocol (RSVP) permits end systems to
 	  request a minimum and maximum data flow rate for a connection; this
@@ -290,7 +300,6 @@ config NET_CLS_RSVP
 config NET_CLS_RSVP6
 	tristate "IPv6 Resource Reservation Protocol (RSVP6)"
 	select NET_CLS
-	select NET_ESTIMATOR
 	---help---
 	  The Resource Reservation Protocol (RSVP) permits end systems to
 	  request a minimum and maximum data flow rate for a connection; this
@@ -382,7 +391,6 @@ config NET_EMATCH_TEXT
 
 config NET_CLS_ACT
 	bool "Actions"
-	select NET_ESTIMATOR
 	---help---
 	  Say Y here if you want to use traffic control actions. Actions
 	  get attached to classifiers and are invoked after a successful
@@ -465,7 +473,6 @@ config NET_ACT_SIMP
 config NET_CLS_POLICE
 	bool "Traffic Policing (obsolete)"
 	depends on NET_CLS_ACT!=y
-	select NET_ESTIMATOR
 	---help---
 	  Say Y here if you want to do traffic policing, i.e. strict
 	  bandwidth limiting. This option is obsoleted by the traffic
@@ -480,14 +487,6 @@ config NET_CLS_IND
 	  classification based on the incoming device. This option is
 	  likely to disappear in favour of the metadata ematch.
 
-config NET_ESTIMATOR
-	bool "Rate estimator"
-	---help---
-	  Say Y here to allow using rate estimators to estimate the current
-	  rate-of-flow for network devices, queues, etc. This module is
-	  automatically selected if needed but can be selected manually for
-	  statistical purposes.
-
 endif # NET_SCHED
 
 endmenu
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 711dd26c95c3..feef366cad5d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -11,23 +11,13 @@
  *
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
-#include <net/sock.h>
 #include <net/sch_generic.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
@@ -42,10 +32,8 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 			write_lock_bh(hinfo->lock);
 			*p1p = p->tcfc_next;
 			write_unlock_bh(hinfo->lock);
-#ifdef CONFIG_NET_ESTIMATOR
 			gen_kill_estimator(&p->tcfc_bstats,
 					   &p->tcfc_rate_est);
-#endif
 			kfree(p);
 			return;
 		}
@@ -232,15 +220,12 @@ struct tcf_common *tcf_hash_create(u32 index, struct rtattr *est, struct tc_acti
 		p->tcfc_bindcnt = 1;
 
 	spin_lock_init(&p->tcfc_lock);
-	p->tcfc_stats_lock = &p->tcfc_lock;
 	p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo);
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
-#ifdef CONFIG_NET_ESTIMATOR
 	if (est)
 		gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est,
-				  p->tcfc_stats_lock, est);
-#endif
+				  &p->tcfc_lock, est);
 	a->priv = (void *) p;
 	return p;
 }
@@ -599,12 +584,12 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (compat_mode) {
 		if (a->type == TCA_OLD_COMPAT)
 			err = gnet_stats_start_copy_compat(skb, 0,
-				TCA_STATS, TCA_XSTATS, h->tcf_stats_lock, &d);
+				TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d);
 		else
 			return 0;
 	} else
 		err = gnet_stats_start_copy(skb, TCA_ACT_STATS,
-			h->tcf_stats_lock, &d);
+					    &h->tcf_lock, &d);
 
 	if (err < 0)
 		goto errout;
@@ -614,9 +599,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 			goto errout;
 
 	if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 ||
-#ifdef CONFIG_NET_ESTIMATOR
 	    gnet_stats_copy_rate_est(&d, &h->tcf_rate_est) < 0 ||
-#endif
 	    gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0)
 		goto errout;
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 7517f3791541..a9631e426d91 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -10,26 +10,15 @@
  *
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <linux/tc_act/tc_gact.h>
 #include <net/tc_act/tc_gact.h>
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 00b05f422d45..6b407ece953c 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -11,27 +11,15 @@
  * Copyright:	Jamal Hadi Salim (2002-4)
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/kmod.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <linux/tc_act/tc_ipt.h>
 #include <net/tc_act/tc_ipt.h>
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index de21c92faaa2..579578944ae7 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -12,31 +12,19 @@
  *
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <linux/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_mirred.h>
 
-#include <linux/etherdevice.h>
 #include <linux/if_arp.h>
 
 #define MIRRED_TAB_MASK     7
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 6f8684b5617e..b46fab5fb323 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -9,26 +9,15 @@
  * Authors:	Jamal Hadi Salim (2002-4)
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <linux/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_pedit.h>
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 616f465f407e..d20403890877 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -10,25 +10,15 @@
  * 		J Hadi Salim (action changes)
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/module.h>
 #include <linux/rtnetlink.h>
 #include <linux/init.h>
-#include <net/sock.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 
@@ -118,10 +108,8 @@ void tcf_police_destroy(struct tcf_police *p)
 			write_lock_bh(&police_lock);
 			*p1p = p->tcf_next;
 			write_unlock_bh(&police_lock);
-#ifdef CONFIG_NET_ESTIMATOR
 			gen_kill_estimator(&p->tcf_bstats,
 					   &p->tcf_rate_est);
-#endif
 			if (p->tcfp_R_tab)
 				qdisc_put_rtab(p->tcfp_R_tab);
 			if (p->tcfp_P_tab)
@@ -185,7 +173,6 @@ static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est,
 	ret = ACT_P_CREATED;
 	police->tcf_refcnt = 1;
 	spin_lock_init(&police->tcf_lock);
-	police->tcf_stats_lock = &police->tcf_lock;
 	if (bind)
 		police->tcf_bindcnt = 1;
 override:
@@ -227,15 +214,13 @@ override:
 		police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu);
 	police->tcf_action = parm->action;
 
-#ifdef CONFIG_NET_ESTIMATOR
 	if (tb[TCA_POLICE_AVRATE-1])
 		police->tcfp_ewma_rate =
 			*(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]);
 	if (est)
 		gen_replace_estimator(&police->tcf_bstats,
 				      &police->tcf_rate_est,
-				      police->tcf_stats_lock, est);
-#endif
+				      &police->tcf_lock, est);
 
 	spin_unlock_bh(&police->tcf_lock);
 	if (ret != ACT_P_CREATED)
@@ -281,14 +266,12 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a,
 	police->tcf_bstats.bytes += skb->len;
 	police->tcf_bstats.packets++;
 
-#ifdef CONFIG_NET_ESTIMATOR
 	if (police->tcfp_ewma_rate &&
 	    police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
 		police->tcf_qstats.overlimits++;
 		spin_unlock(&police->tcf_lock);
 		return police->tcf_action;
 	}
-#endif
 
 	if (skb->len <= police->tcfp_mtu) {
 		if (police->tcfp_R_tab == NULL) {
@@ -348,10 +331,8 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	if (police->tcfp_result)
 		RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int),
 			&police->tcfp_result);
-#ifdef CONFIG_NET_ESTIMATOR
 	if (police->tcfp_ewma_rate)
 		RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate);
-#endif
 	return skb->len;
 
 rtattr_failure:
@@ -458,7 +439,6 @@ struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est)
 
 	police->tcf_refcnt = 1;
 	spin_lock_init(&police->tcf_lock);
-	police->tcf_stats_lock = &police->tcf_lock;
 	if (parm->rate.rate) {
 		police->tcfp_R_tab =
 			qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE-1]);
@@ -477,14 +457,12 @@ struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est)
 			goto failure;
 		police->tcfp_result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]);
 	}
-#ifdef CONFIG_NET_ESTIMATOR
 	if (tb[TCA_POLICE_AVRATE-1]) {
 		if (RTA_PAYLOAD(tb[TCA_POLICE_AVRATE-1]) != sizeof(u32))
 			goto failure;
 		police->tcfp_ewma_rate =
 			*(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]);
 	}
-#endif
 	police->tcfp_toks = police->tcfp_burst = parm->burst;
 	police->tcfp_mtu = parm->mtu;
 	if (police->tcfp_mtu == 0) {
@@ -498,11 +476,9 @@ struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est)
 	police->tcf_index = parm->index ? parm->index :
 		tcf_police_new_index();
 	police->tcf_action = parm->action;
-#ifdef CONFIG_NET_ESTIMATOR
 	if (est)
 		gen_new_estimator(&police->tcf_bstats, &police->tcf_rate_est,
-				  police->tcf_stats_lock, est);
-#endif
+				  &police->tcf_lock, est);
 	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
 	write_lock_bh(&police_lock);
 	police->tcf_next = tcf_police_ht[h];
@@ -528,14 +504,12 @@ int tcf_police(struct sk_buff *skb, struct tcf_police *police)
 	police->tcf_bstats.bytes += skb->len;
 	police->tcf_bstats.packets++;
 
-#ifdef CONFIG_NET_ESTIMATOR
 	if (police->tcfp_ewma_rate &&
 	    police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
 		police->tcf_qstats.overlimits++;
 		spin_unlock(&police->tcf_lock);
 		return police->tcf_action;
 	}
-#endif
 	if (skb->len <= police->tcfp_mtu) {
 		if (police->tcfp_R_tab == NULL) {
 			spin_unlock(&police->tcf_lock);
@@ -591,10 +565,8 @@ int tcf_police_dump(struct sk_buff *skb, struct tcf_police *police)
 	if (police->tcfp_result)
 		RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int),
 			&police->tcfp_result);
-#ifdef CONFIG_NET_ESTIMATOR
 	if (police->tcfp_ewma_rate)
 		RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate);
-#endif
 	return skb->len;
 
 rtattr_failure:
@@ -607,14 +579,12 @@ int tcf_police_dump_stats(struct sk_buff *skb, struct tcf_police *police)
 	struct gnet_dump d;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS,
-					 TCA_XSTATS, police->tcf_stats_lock,
+					 TCA_XSTATS, &police->tcf_lock,
 					 &d) < 0)
 		goto errout;
 
 	if (gnet_stats_copy_basic(&d, &police->tcf_bstats) < 0 ||
-#ifdef CONFIG_NET_ESTIMATOR
 	    gnet_stats_copy_rate_est(&d, &police->tcf_rate_est) < 0 ||
-#endif
 	    gnet_stats_copy_queue(&d, &police->tcf_qstats) < 0)
 		goto errout;
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 36e1edad5990..fb84ef33d14f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ebf94edf0478..36b72aab1bde 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -14,26 +14,16 @@
  *
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/netlink.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index c885412d79d5..8dbcf2771a46 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -13,7 +13,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index bbec4a0d4dcb..8adbd6a37d14 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -19,29 +19,12 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <linux/netfilter.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index cc941d0ee3a5..0a8409c1d28a 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -10,28 +10,14 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 
diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c
index 0a683c07c648..cbb5e0d600f3 100644
--- a/net/sched/cls_rsvp.c
+++ b/net/sched/cls_rsvp.c
@@ -10,27 +10,12 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/ip.h>
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c
index 93b6abed57db..dd08aea2aee5 100644
--- a/net/sched/cls_rsvp6.c
+++ b/net/sched/cls_rsvp6.c
@@ -10,28 +10,12 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
 #include <linux/ipv6.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 #include <net/netlink.h>
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 47ac0c556429..2314820a080a 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -9,12 +9,9 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/errno.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
-#include <net/route.h>
 
 
 /*
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index c7a347bd6d70..77961e2314dc 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -30,30 +30,14 @@
  *	nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro>
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
 #include <linux/rtnetlink.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index 8d6dacd81900..cc49c932641d 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -98,3 +98,4 @@ MODULE_LICENSE("GPL");
 module_init(init_em_cmp);
 module_exit(exit_em_cmp);
 
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_CMP);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 60acf8cdb27b..650f09c8bd6a 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -848,3 +848,5 @@ MODULE_LICENSE("GPL");
 
 module_init(init_em_meta);
 module_exit(exit_em_meta);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_META);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index b4b36efce292..370a1b2ea317 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -76,3 +76,5 @@ MODULE_LICENSE("GPL");
 
 module_init(init_em_nbyte);
 module_exit(exit_em_nbyte);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_NBYTE);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index e8f46169449d..d5cd86efb7d0 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -150,3 +150,5 @@ MODULE_LICENSE("GPL");
 
 module_init(init_em_text);
 module_exit(exit_em_text);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_TEXT);
diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c
index 0a2a7fe08de3..112796e4a7c4 100644
--- a/net/sched/em_u32.c
+++ b/net/sched/em_u32.c
@@ -60,3 +60,5 @@ MODULE_LICENSE("GPL");
 
 module_init(init_em_u32);
 module_exit(exit_em_u32);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_U32);
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 63146d339d81..f3a104e323bd 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -84,9 +84,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/mm.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 #include <net/pkt_cls.h>
@@ -224,6 +222,19 @@ static int tcf_em_validate(struct tcf_proto *tp,
 
 		if (em->ops == NULL) {
 			err = -ENOENT;
+#ifdef CONFIG_KMOD
+			__rtnl_unlock();
+			request_module("ematch-kind-%u", em_hdr->kind);
+			rtnl_lock();
+			em->ops = tcf_em_lookup(em_hdr->kind);
+			if (em->ops) {
+				/* We dropped the RTNL mutex in order to
+				 * perform the module load. Tell the caller
+				 * to replay the request. */
+				module_put(em->ops->owner);
+				err = -EAGAIN;
+			}
+#endif
 			goto errout;
 		}
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bec600af03ca..d92ea26982c5 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -19,30 +19,18 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
-#include <linux/bitops.h>
 #include <linux/hrtimer.h>
 
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 
-#include <asm/processor.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-
 static int qdisc_notify(struct sk_buff *oskb, struct nlmsghdr *n, u32 clid,
 			struct Qdisc *old, struct Qdisc *new);
 static int tclass_notify(struct sk_buff *oskb, struct nlmsghdr *n,
@@ -515,7 +503,6 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp)
 	sch->handle = handle;
 
 	if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS-1])) == 0) {
-#ifdef CONFIG_NET_ESTIMATOR
 		if (tca[TCA_RATE-1]) {
 			err = gen_new_estimator(&sch->bstats, &sch->rate_est,
 						sch->stats_lock,
@@ -531,7 +518,6 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp)
 				goto err_out3;
 			}
 		}
-#endif
 		qdisc_lock_tree(dev);
 		list_add_tail(&sch->list, &dev->qdisc_list);
 		qdisc_unlock_tree(dev);
@@ -559,11 +545,9 @@ static int qdisc_change(struct Qdisc *sch, struct rtattr **tca)
 		if (err)
 			return err;
 	}
-#ifdef CONFIG_NET_ESTIMATOR
 	if (tca[TCA_RATE-1])
 		gen_replace_estimator(&sch->bstats, &sch->rate_est,
 			sch->stats_lock, tca[TCA_RATE-1]);
-#endif
 	return 0;
 }
 
@@ -839,9 +823,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		goto rtattr_failure;
 
 	if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
-#ifdef CONFIG_NET_ESTIMATOR
 	    gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 ||
-#endif
 	    gnet_stats_copy_queue(&d, &q->qstats) < 0)
 		goto rtattr_failure;
 
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index d1c383fca82c..54b92d22796c 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -8,15 +8,12 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/skbuff.h>
-#include <linux/interrupt.h>
 #include <linux/atmdev.h>
 #include <linux/atmclip.h>
-#include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/file.h> /* for fput */
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
-#include <net/sock.h>
 
 
 extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */
@@ -71,7 +68,6 @@ struct atm_flow_data {
 	int			ref;		/* reference count */
 	struct gnet_stats_basic	bstats;
 	struct gnet_stats_queue	qstats;
-	spinlock_t		*stats_lock;
 	struct atm_flow_data	*next;
 	struct atm_flow_data	*excess;	/* flow for excess traffic;
 						   NULL to set CLP instead */
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index cb0c456aa349..f914fc43a124 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index ee2d5967d109..b184c3545145 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -11,28 +11,12 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/pkt_sched.h>
 
 
@@ -148,7 +132,6 @@ struct cbq_class
 	struct gnet_stats_basic bstats;
 	struct gnet_stats_queue qstats;
 	struct gnet_stats_rate_est rate_est;
-	spinlock_t		*stats_lock;
 	struct tc_cbq_xstats	xstats;
 
 	struct tcf_proto	*filter_list;
@@ -1442,7 +1425,6 @@ static int cbq_init(struct Qdisc *sch, struct rtattr *opt)
 	q->link.ewma_log = TC_CBQ_DEF_EWMA;
 	q->link.avpkt = q->link.allot/2;
 	q->link.minidle = -0x7FFFFFFF;
-	q->link.stats_lock = &sch->dev->queue_lock;
 
 	qdisc_watchdog_init(&q->watchdog, sch);
 	hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
@@ -1653,9 +1635,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 		cl->xstats.undertime = cl->undertime - q->now;
 
 	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
-#ifdef CONFIG_NET_ESTIMATOR
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-#endif
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
 
@@ -1726,9 +1706,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
 	tcf_destroy_chain(cl->filter_list);
 	qdisc_destroy(cl->q);
 	qdisc_put_rtab(cl->R_tab);
-#ifdef CONFIG_NET_ESTIMATOR
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
-#endif
 	if (cl != &q->link)
 		kfree(cl);
 }
@@ -1873,11 +1851,10 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t
 
 		sch_tree_unlock(sch);
 
-#ifdef CONFIG_NET_ESTIMATOR
 		if (tca[TCA_RATE-1])
 			gen_replace_estimator(&cl->bstats, &cl->rate_est,
-				cl->stats_lock, tca[TCA_RATE-1]);
-#endif
+					      &sch->dev->queue_lock,
+					      tca[TCA_RATE-1]);
 		return 0;
 	}
 
@@ -1935,7 +1912,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t
 	cl->allot = parent->allot;
 	cl->quantum = cl->allot;
 	cl->weight = cl->R_tab->rate.rate;
-	cl->stats_lock = &sch->dev->queue_lock;
 
 	sch_tree_lock(sch);
 	cbq_link_class(cl);
@@ -1963,11 +1939,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t
 		cbq_set_fopt(cl, RTA_DATA(tb[TCA_CBQ_FOPT-1]));
 	sch_tree_unlock(sch);
 
-#ifdef CONFIG_NET_ESTIMATOR
 	if (tca[TCA_RATE-1])
 		gen_new_estimator(&cl->bstats, &cl->rate_est,
-			cl->stats_lock, tca[TCA_RATE-1]);
-#endif
+				  &sch->dev->queue_lock, tca[TCA_RATE-1]);
 
 	*arg = (unsigned long)cl;
 	return 0;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 3c6fd181263f..4d2c233a8611 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -9,7 +9,6 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/skbuff.h>
-#include <linux/netdevice.h> /* for pkt_sched */
 #include <linux/rtnetlink.h>
 #include <net/pkt_sched.h>
 #include <net/dsfield.h>
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index c2689f4ba8de..c264308f17c1 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -13,7 +13,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index f4d34480a093..c81649cf0b9e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -11,27 +11,19 @@
  *              - Ingress support
  */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/init.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 
 /* Main transmission queue. */
@@ -59,122 +51,143 @@ void qdisc_unlock_tree(struct net_device *dev)
 	spin_unlock_bh(&dev->queue_lock);
 }
 
-/*
-   dev->queue_lock serializes queue accesses for this device
-   AND dev->qdisc pointer itself.
+static inline int qdisc_qlen(struct Qdisc *q)
+{
+	return q->q.qlen;
+}
 
-   netif_tx_lock serializes accesses to device driver.
+static inline int dev_requeue_skb(struct sk_buff *skb, struct net_device *dev,
+				  struct Qdisc *q)
+{
+	if (unlikely(skb->next))
+		dev->gso_skb = skb;
+	else
+		q->ops->requeue(skb, q);
 
-   dev->queue_lock and netif_tx_lock are mutually exclusive,
-   if one is grabbed, another must be free.
- */
+	netif_schedule(dev);
+	return 0;
+}
 
+static inline struct sk_buff *dev_dequeue_skb(struct net_device *dev,
+					      struct Qdisc *q)
+{
+	struct sk_buff *skb;
 
-/* Kick device.
+	if ((skb = dev->gso_skb))
+		dev->gso_skb = NULL;
+	else
+		skb = q->dequeue(q);
 
-   Returns:  0  - queue is empty or throttled.
-	    >0  - queue is not empty.
+	return skb;
+}
 
-   NOTE: Called under dev->queue_lock with locally disabled BH.
-*/
+static inline int handle_dev_cpu_collision(struct sk_buff *skb,
+					   struct net_device *dev,
+					   struct Qdisc *q)
+{
+	int ret;
 
+	if (unlikely(dev->xmit_lock_owner == smp_processor_id())) {
+		/*
+		 * Same CPU holding the lock. It may be a transient
+		 * configuration error, when hard_start_xmit() recurses. We
+		 * detect it by checking xmit owner and drop the packet when
+		 * deadloop is detected. Return OK to try the next skb.
+		 */
+		kfree_skb(skb);
+		if (net_ratelimit())
+			printk(KERN_WARNING "Dead loop on netdevice %s, "
+			       "fix it urgently!\n", dev->name);
+		ret = qdisc_qlen(q);
+	} else {
+		/*
+		 * Another cpu is holding lock, requeue & delay xmits for
+		 * some time.
+		 */
+		__get_cpu_var(netdev_rx_stat).cpu_collision++;
+		ret = dev_requeue_skb(skb, dev, q);
+	}
+
+	return ret;
+}
+
+/*
+ * NOTE: Called under dev->queue_lock with locally disabled BH.
+ *
+ * __LINK_STATE_QDISC_RUNNING guarantees only one CPU can process this
+ * device at a time. dev->queue_lock serializes queue accesses for
+ * this device AND dev->qdisc pointer itself.
+ *
+ *  netif_tx_lock serializes accesses to device driver.
+ *
+ *  dev->queue_lock and netif_tx_lock are mutually exclusive,
+ *  if one is grabbed, another must be free.
+ *
+ * Note, that this procedure can be called by a watchdog timer
+ *
+ * Returns to the caller:
+ *				0  - queue is empty or throttled.
+ *				>0 - queue is not empty.
+ *
+ */
 static inline int qdisc_restart(struct net_device *dev)
 {
 	struct Qdisc *q = dev->qdisc;
 	struct sk_buff *skb;
+	unsigned lockless;
+	int ret;
 
 	/* Dequeue packet */
-	if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) {
-		unsigned nolock = (dev->features & NETIF_F_LLTX);
+	if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL))
+		return 0;
+
+	/*
+	 * When the driver has LLTX set, it does its own locking in
+	 * start_xmit. These checks are worth it because even uncongested
+	 * locks can be quite expensive. The driver can do a trylock, as
+	 * is being done here; in case of lock contention it should return
+	 * NETDEV_TX_LOCKED and the packet will be requeued.
+	 */
+	lockless = (dev->features & NETIF_F_LLTX);
 
-		dev->gso_skb = NULL;
+	if (!lockless && !netif_tx_trylock(dev)) {
+		/* Another CPU grabbed the driver tx lock */
+		return handle_dev_cpu_collision(skb, dev, q);
+	}
 
-		/*
-		 * When the driver has LLTX set it does its own locking
-		 * in start_xmit. No need to add additional overhead by
-		 * locking again. These checks are worth it because
-		 * even uncongested locks can be quite expensive.
-		 * The driver can do trylock like here too, in case
-		 * of lock congestion it should return -1 and the packet
-		 * will be requeued.
-		 */
-		if (!nolock) {
-			if (!netif_tx_trylock(dev)) {
-			collision:
-				/* So, someone grabbed the driver. */
-
-				/* It may be transient configuration error,
-				   when hard_start_xmit() recurses. We detect
-				   it by checking xmit owner and drop the
-				   packet when deadloop is detected.
-				*/
-				if (dev->xmit_lock_owner == smp_processor_id()) {
-					kfree_skb(skb);
-					if (net_ratelimit())
-						printk(KERN_DEBUG "Dead loop on netdevice %s, fix it urgently!\n", dev->name);
-					goto out;
-				}
-				__get_cpu_var(netdev_rx_stat).cpu_collision++;
-				goto requeue;
-			}
-		}
+	/* And release queue */
+	spin_unlock(&dev->queue_lock);
 
-		{
-			/* And release queue */
-			spin_unlock(&dev->queue_lock);
-
-			if (!netif_queue_stopped(dev)) {
-				int ret;
-
-				ret = dev_hard_start_xmit(skb, dev);
-				if (ret == NETDEV_TX_OK) {
-					if (!nolock) {
-						netif_tx_unlock(dev);
-					}
-					spin_lock(&dev->queue_lock);
-					q = dev->qdisc;
-					goto out;
-				}
-				if (ret == NETDEV_TX_LOCKED && nolock) {
-					spin_lock(&dev->queue_lock);
-					q = dev->qdisc;
-					goto collision;
-				}
-			}
+	ret = dev_hard_start_xmit(skb, dev);
 
-			/* NETDEV_TX_BUSY - we need to requeue */
-			/* Release the driver */
-			if (!nolock) {
-				netif_tx_unlock(dev);
-			}
-			spin_lock(&dev->queue_lock);
-			q = dev->qdisc;
-		}
+	if (!lockless)
+		netif_tx_unlock(dev);
 
-		/* Device kicked us out :(
-		   This is possible in three cases:
+	spin_lock(&dev->queue_lock);
+	q = dev->qdisc;
 
-		   0. driver is locked
-		   1. fastroute is enabled
-		   2. device cannot determine busy state
-		      before start of transmission (f.e. dialout)
-		   3. device is buggy (ppp)
-		 */
+	switch (ret) {
+	case NETDEV_TX_OK:
+		/* Driver sent out skb successfully */
+		ret = qdisc_qlen(q);
+		break;
 
-requeue:
-		if (unlikely(q == &noop_qdisc))
-			kfree_skb(skb);
-		else if (skb->next)
-			dev->gso_skb = skb;
-		else
-			q->ops->requeue(skb, q);
-		netif_schedule(dev);
+	case NETDEV_TX_LOCKED:
+		/* Driver try lock failed */
+		ret = handle_dev_cpu_collision(skb, dev, q);
+		break;
+
+	default:
+		/* Driver returned NETDEV_TX_BUSY - requeue skb */
+		if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit()))
+			printk(KERN_WARNING "BUG %s code %d qlen %d\n",
+			       dev->name, ret, q->q.qlen);
+
+		ret = dev_requeue_skb(skb, dev, q);
+		break;
 	}
-	return 0;
 
-out:
-	BUG_ON((int) q->q.qlen < 0);
-	return q->q.qlen;
+	return ret;
 }
 
 void __qdisc_run(struct net_device *dev)
@@ -493,9 +506,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 		return;
 
 	list_del(&qdisc->list);
-#ifdef CONFIG_NET_ESTIMATOR
 	gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
-#endif
 	if (ops->reset)
 		ops->reset(qdisc);
 	if (ops->destroy)
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index fa1b4fe7a5fd..3cc6dda02e2e 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -21,7 +21,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 #include <net/red.h>
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 9d124c4ee3a7..874452c41a01 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -53,7 +53,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/jiffies.h>
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -62,13 +61,11 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/init.h>
-#include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
-#include <asm/system.h>
 #include <asm/div64.h>
 
 /*
@@ -122,7 +119,6 @@ struct hfsc_class
 	struct gnet_stats_basic bstats;
 	struct gnet_stats_queue qstats;
 	struct gnet_stats_rate_est rate_est;
-	spinlock_t	*stats_lock;
 	unsigned int	level;		/* class level in hierarchy */
 	struct tcf_proto *filter_list;	/* filter list */
 	unsigned int	filter_cnt;	/* filter count */
@@ -1054,11 +1050,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		}
 		sch_tree_unlock(sch);
 
-#ifdef CONFIG_NET_ESTIMATOR
 		if (tca[TCA_RATE-1])
 			gen_replace_estimator(&cl->bstats, &cl->rate_est,
-				cl->stats_lock, tca[TCA_RATE-1]);
-#endif
+					      &sch->dev->queue_lock,
+					      tca[TCA_RATE-1]);
 		return 0;
 	}
 
@@ -1098,7 +1093,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	cl->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, classid);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
-	cl->stats_lock = &sch->dev->queue_lock;
 	INIT_LIST_HEAD(&cl->children);
 	cl->vt_tree = RB_ROOT;
 	cl->cf_tree = RB_ROOT;
@@ -1112,11 +1106,9 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	cl->cl_pcvtoff = parent->cl_cvtoff;
 	sch_tree_unlock(sch);
 
-#ifdef CONFIG_NET_ESTIMATOR
 	if (tca[TCA_RATE-1])
 		gen_new_estimator(&cl->bstats, &cl->rate_est,
-			cl->stats_lock, tca[TCA_RATE-1]);
-#endif
+				  &sch->dev->queue_lock, tca[TCA_RATE-1]);
 	*arg = (unsigned long)cl;
 	return 0;
 }
@@ -1128,9 +1120,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
 
 	tcf_destroy_chain(cl->filter_list);
 	qdisc_destroy(cl->qdisc);
-#ifdef CONFIG_NET_ESTIMATOR
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
-#endif
 	if (cl != &q->root)
 		kfree(cl);
 }
@@ -1384,9 +1374,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.rtwork  = cl->cl_cumul;
 
 	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
-#ifdef CONFIG_NET_ESTIMATOR
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-#endif
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
 
@@ -1448,8 +1436,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct rtattr *opt)
 		return -EINVAL;
 	qopt = RTA_DATA(opt);
 
-	sch->stats_lock = &sch->dev->queue_lock;
-
 	q->defcls = qopt->defcls;
 	for (i = 0; i < HFSC_HSIZE; i++)
 		INIT_LIST_HEAD(&q->clhash[i]);
@@ -1464,7 +1450,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct rtattr *opt)
 					  sch->handle);
 	if (q->root.qdisc == NULL)
 		q->root.qdisc = &noop_qdisc;
-	q->root.stats_lock = &sch->dev->queue_lock;
 	INIT_LIST_HEAD(&q->root.children);
 	q->root.vt_tree = RB_ROOT;
 	q->root.cf_tree = RB_ROOT;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 035788c5b7f8..b417a95df322 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -28,32 +28,16 @@
  * $Id: sch_htb.c,v 1.25 2003/12/07 11:08:25 devik Exp devik $
  */
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
 #include <linux/list.h>
 #include <linux/compiler.h>
+#include <linux/rbtree.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
-#include <linux/rbtree.h>
 
 /* HTB algorithm.
     Author: devik@cdi.cz
@@ -69,8 +53,6 @@
 */
 
 #define HTB_HSIZE 16		/* classid hash size */
-#define HTB_EWMAC 2		/* rate average over HTB_EWMAC*HTB_HSIZE sec */
-#define HTB_RATECM 1		/* whether to use rate computer */
 #define HTB_HYSTERESIS 1	/* whether to use mode hysteresis for speedup */
 #define HTB_VER 0x30011		/* major must be matched with number suplied by TC as version */
 
@@ -95,12 +77,6 @@ struct htb_class {
 	struct tc_htb_xstats xstats;	/* our special stats */
 	int refcnt;		/* usage count of this class */
 
-#ifdef HTB_RATECM
-	/* rate measurement counters */
-	unsigned long rate_bytes, sum_bytes;
-	unsigned long rate_packets, sum_packets;
-#endif
-
 	/* topology */
 	int level;		/* our level (see above) */
 	struct htb_class *parent;	/* parent class */
@@ -153,15 +129,12 @@ struct htb_class {
 				/* of un.leaf originals should be done. */
 };
 
-/* TODO: maybe compute rate when size is too large .. or drop ? */
 static inline long L2T(struct htb_class *cl, struct qdisc_rate_table *rate,
 			   int size)
 {
 	int slot = size >> rate->rate.cell_log;
-	if (slot > 255) {
-		cl->xstats.giants++;
-		slot = 255;
-	}
+	if (slot > 255)
+		return (rate->data[255]*(slot >> 8) + rate->data[slot & 0xFF]);
 	return rate->data[slot];
 }
 
@@ -194,10 +167,6 @@ struct htb_sched {
 	int rate2quantum;	/* quant = rate / rate2quantum */
 	psched_time_t now;	/* cached dequeue time */
 	struct qdisc_watchdog watchdog;
-#ifdef HTB_RATECM
-	struct timer_list rttim;	/* rate computer timer */
-	int recmp_bucket;	/* which hash bucket to recompute next */
-#endif
 
 	/* non shaped skbs; let them go directly thru */
 	struct sk_buff_head direct_queue;
@@ -634,13 +603,14 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		cl->qstats.drops++;
 		return NET_XMIT_DROP;
 	} else {
-		cl->bstats.packets++;
+		cl->bstats.packets +=
+			skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
 		cl->bstats.bytes += skb->len;
 		htb_activate(q, cl);
 	}
 
 	sch->q.qlen++;
-	sch->bstats.packets++;
+	sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
 	sch->bstats.bytes += skb->len;
 	return NET_XMIT_SUCCESS;
 }
@@ -677,34 +647,6 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
 	return NET_XMIT_SUCCESS;
 }
 
-#ifdef HTB_RATECM
-#define RT_GEN(D,R) R+=D-(R/HTB_EWMAC);D=0
-static void htb_rate_timer(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	struct htb_sched *q = qdisc_priv(sch);
-	struct hlist_node *p;
-	struct htb_class *cl;
-
-
-	/* lock queue so that we can muck with it */
-	spin_lock_bh(&sch->dev->queue_lock);
-
-	q->rttim.expires = jiffies + HZ;
-	add_timer(&q->rttim);
-
-	/* scan and recompute one bucket at time */
-	if (++q->recmp_bucket >= HTB_HSIZE)
-		q->recmp_bucket = 0;
-
-	hlist_for_each_entry(cl,p, q->hash + q->recmp_bucket, hlist) {
-		RT_GEN(cl->sum_bytes, cl->rate_bytes);
-		RT_GEN(cl->sum_packets, cl->rate_packets);
-	}
-	spin_unlock_bh(&sch->dev->queue_lock);
-}
-#endif
-
 /**
  * htb_charge_class - charges amount "bytes" to leaf and ancestors
  *
@@ -717,8 +659,9 @@ static void htb_rate_timer(unsigned long arg)
  * In such case we remove class from event queue first.
  */
 static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
-			     int level, int bytes)
+			     int level, struct sk_buff *skb)
 {
+	int bytes = skb->len;
 	long toks, diff;
 	enum htb_cmode old_mode;
 
@@ -750,16 +693,12 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
 			if (cl->cmode != HTB_CAN_SEND)
 				htb_add_to_wait_tree(q, cl, diff);
 		}
-#ifdef HTB_RATECM
-		/* update rate counters */
-		cl->sum_bytes += bytes;
-		cl->sum_packets++;
-#endif
 
 		/* update byte stats except for leaves which are already updated */
 		if (cl->level) {
 			cl->bstats.bytes += bytes;
-			cl->bstats.packets++;
+			cl->bstats.packets += skb_is_gso(skb)?
+					skb_shinfo(skb)->gso_segs:1;
 		}
 		cl = cl->parent;
 	}
@@ -943,7 +882,7 @@ next:
 		   gives us slightly better performance */
 		if (!cl->un.leaf.q->q.qlen)
 			htb_deactivate(q, cl);
-		htb_charge_class(q, cl, level, skb->len);
+		htb_charge_class(q, cl, level, skb);
 	}
 	return skb;
 }
@@ -1095,13 +1034,6 @@ static int htb_init(struct Qdisc *sch, struct rtattr *opt)
 	if (q->direct_qlen < 2)	/* some devices have zero tx_queue_len */
 		q->direct_qlen = 2;
 
-#ifdef HTB_RATECM
-	init_timer(&q->rttim);
-	q->rttim.function = htb_rate_timer;
-	q->rttim.data = (unsigned long)sch;
-	q->rttim.expires = jiffies + HZ;
-	add_timer(&q->rttim);
-#endif
 	if ((q->rate2quantum = gopt->rate2quantum) < 1)
 		q->rate2quantum = 1;
 	q->defcls = gopt->defcls;
@@ -1175,11 +1107,6 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
 
-#ifdef HTB_RATECM
-	cl->rate_est.bps = cl->rate_bytes / (HTB_EWMAC * HTB_HSIZE);
-	cl->rate_est.pps = cl->rate_packets / (HTB_EWMAC * HTB_HSIZE);
-#endif
-
 	if (!cl->level && cl->un.leaf.q)
 		cl->qstats.qlen = cl->un.leaf.q->q.qlen;
 	cl->xstats.tokens = cl->tokens;
@@ -1277,6 +1204,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
 		BUG_TRAP(cl->un.leaf.q);
 		qdisc_destroy(cl->un.leaf.q);
 	}
+	gen_kill_estimator(&cl->bstats, &cl->rate_est);
 	qdisc_put_rtab(cl->rate);
 	qdisc_put_rtab(cl->ceil);
 
@@ -1305,9 +1233,6 @@ static void htb_destroy(struct Qdisc *sch)
 	struct htb_sched *q = qdisc_priv(sch);
 
 	qdisc_watchdog_cancel(&q->watchdog);
-#ifdef HTB_RATECM
-	del_timer_sync(&q->rttim);
-#endif
 	/* This line used to be after htb_destroy_class call below
 	   and surprisingly it worked in 2.4. But it must precede it
 	   because filter need its target class alive to be able to call
@@ -1403,6 +1328,20 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	if (!cl) {		/* new class */
 		struct Qdisc *new_q;
 		int prio;
+		struct {
+			struct rtattr		rta;
+			struct gnet_estimator	opt;
+		} est = {
+			.rta = {
+				.rta_len	= RTA_LENGTH(sizeof(est.opt)),
+				.rta_type	= TCA_RATE,
+			},
+			.opt = {
+				/* 4s interval, 16s averaging constant */
+				.interval	= 2,
+				.ewma_log	= 2,
+			},
+		};
 
 		/* check for valid classid */
 		if (!classid || TC_H_MAJ(classid ^ sch->handle)
@@ -1418,6 +1357,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL)
 			goto failure;
 
+		gen_new_estimator(&cl->bstats, &cl->rate_est,
+				  &sch->dev->queue_lock,
+				  tca[TCA_RATE-1] ? : &est.rta);
 		cl->refcnt = 1;
 		INIT_LIST_HEAD(&cl->sibling);
 		INIT_HLIST_NODE(&cl->hlist);
@@ -1469,8 +1411,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		hlist_add_head(&cl->hlist, q->hash + htb_hash(classid));
 		list_add_tail(&cl->sibling,
 			      parent ? &parent->children : &q->root);
-	} else
+	} else {
+		if (tca[TCA_RATE-1])
+			gen_replace_estimator(&cl->bstats, &cl->rate_est,
+					      &sch->dev->queue_lock,
+					      tca[TCA_RATE-1]);
 		sch_tree_lock(sch);
+	}
 
 	/* it used to be a nasty bug here, we have to check that node
 	   is really leaf before changing cl->un.leaf ! */
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index f8b9f1cdf738..cd0aab6a2a7c 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -9,21 +9,14 @@
 
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/list.h>
 #include <linux/skbuff.h>
-#include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter.h>
-#include <linux/smp.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
-#include <asm/byteorder.h>
-#include <asm/uaccess.h>
-#include <linux/kmod.h>
-#include <linux/stat.h>
-#include <linux/interrupt.h>
-#include <linux/list.h>
 
 
 #undef DEBUG_INGRESS
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5d9d8bc9cc3a..9e5e87e81f00 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -14,11 +14,9 @@
  */
 
 #include <linux/module.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 6d7542c26e47..2d8c08493d6e 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -12,37 +12,23 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/pkt_sched.h>
 
 
 struct prio_sched_data
 {
 	int bands;
+	int curband; /* for round-robin */
 	struct tcf_proto *filter_list;
 	u8  prio2band[TC_PRIO_MAX+1];
 	struct Qdisc *queues[TCQ_PRIO_BANDS];
+	int mq;
 };
 
 
@@ -70,14 +56,17 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 #endif
 			if (TC_H_MAJ(band))
 				band = 0;
-			return q->queues[q->prio2band[band&TC_PRIO_MAX]];
+			band = q->prio2band[band&TC_PRIO_MAX];
+			goto out;
 		}
 		band = res.classid;
 	}
 	band = TC_H_MIN(band) - 1;
 	if (band >= q->bands)
-		return q->queues[q->prio2band[0]];
-
+		band = q->prio2band[0];
+out:
+	if (q->mq)
+		skb_set_queue_mapping(skb, band);
 	return q->queues[band];
 }
 
@@ -144,17 +133,58 @@ prio_dequeue(struct Qdisc* sch)
 	struct Qdisc *qdisc;
 
 	for (prio = 0; prio < q->bands; prio++) {
-		qdisc = q->queues[prio];
-		skb = qdisc->dequeue(qdisc);
-		if (skb) {
-			sch->q.qlen--;
-			return skb;
+		/* Check if the target subqueue is available before
+		 * pulling an skb.  This way we avoid excessive requeues
+		 * for slower queues.
+		 */
+		if (!netif_subqueue_stopped(sch->dev, (q->mq ? prio : 0))) {
+			qdisc = q->queues[prio];
+			skb = qdisc->dequeue(qdisc);
+			if (skb) {
+				sch->q.qlen--;
+				return skb;
+			}
 		}
 	}
 	return NULL;
 
 }
 
+static struct sk_buff *rr_dequeue(struct Qdisc* sch)
+{
+	struct sk_buff *skb;
+	struct prio_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc;
+	int bandcount;
+
+	/* Only take one pass through the queues.  If nothing is available,
+	 * return nothing.
+	 */
+	for (bandcount = 0; bandcount < q->bands; bandcount++) {
+		/* Check if the target subqueue is available before
+		 * pulling an skb.  This way we avoid excessive requeues
+		 * for slower queues.  If the queue is stopped, try the
+		 * next queue.
+		 */
+		if (!netif_subqueue_stopped(sch->dev,
+					    (q->mq ? q->curband : 0))) {
+			qdisc = q->queues[q->curband];
+			skb = qdisc->dequeue(qdisc);
+			if (skb) {
+				sch->q.qlen--;
+				q->curband++;
+				if (q->curband >= q->bands)
+					q->curband = 0;
+				return skb;
+			}
+		}
+		q->curband++;
+		if (q->curband >= q->bands)
+			q->curband = 0;
+	}
+	return NULL;
+}
+
 static unsigned int prio_drop(struct Qdisc* sch)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
@@ -198,21 +228,41 @@ prio_destroy(struct Qdisc* sch)
 static int prio_tune(struct Qdisc *sch, struct rtattr *opt)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
-	struct tc_prio_qopt *qopt = RTA_DATA(opt);
+	struct tc_prio_qopt *qopt;
+	struct rtattr *tb[TCA_PRIO_MAX];
 	int i;
 
-	if (opt->rta_len < RTA_LENGTH(sizeof(*qopt)))
+	if (rtattr_parse_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
+				       sizeof(*qopt)))
 		return -EINVAL;
-	if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2)
+	q->bands = qopt->bands;
+	/* If we're multiqueue, make sure the number of incoming bands
+	 * matches the number of queues on the device we're associating with.
+	 * If the number of bands requested is zero, then set q->bands to
+	 * dev->egress_subqueue_count.
+	 */
+	q->mq = RTA_GET_FLAG(tb[TCA_PRIO_MQ - 1]);
+	if (q->mq) {
+		if (sch->handle != TC_H_ROOT)
+			return -EINVAL;
+		if (netif_is_multiqueue(sch->dev)) {
+			if (q->bands == 0)
+				q->bands = sch->dev->egress_subqueue_count;
+			else if (q->bands != sch->dev->egress_subqueue_count)
+				return -EINVAL;
+		} else
+			return -EOPNOTSUPP;
+	}
+
+	if (q->bands > TCQ_PRIO_BANDS || q->bands < 2)
 		return -EINVAL;
 
 	for (i=0; i<=TC_PRIO_MAX; i++) {
-		if (qopt->priomap[i] >= qopt->bands)
+		if (qopt->priomap[i] >= q->bands)
 			return -EINVAL;
 	}
 
 	sch_tree_lock(sch);
-	q->bands = qopt->bands;
 	memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
 	for (i=q->bands; i<TCQ_PRIO_BANDS; i++) {
@@ -268,11 +318,17 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
+	struct rtattr *nest;
 	struct tc_prio_qopt opt;
 
 	opt.bands = q->bands;
 	memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1);
-	RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+
+	nest = RTA_NEST_COMPAT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+	if (q->mq)
+		RTA_PUT_FLAG(skb, TCA_PRIO_MQ);
+	RTA_NEST_COMPAT_END(skb, nest);
+
 	return skb->len;
 
 rtattr_failure:
@@ -443,17 +499,44 @@ static struct Qdisc_ops prio_qdisc_ops = {
 	.owner		=	THIS_MODULE,
 };
 
+static struct Qdisc_ops rr_qdisc_ops = {
+	.next		=	NULL,
+	.cl_ops		=	&prio_class_ops,
+	.id		=	"rr",
+	.priv_size	=	sizeof(struct prio_sched_data),
+	.enqueue	=	prio_enqueue,
+	.dequeue	=	rr_dequeue,
+	.requeue	=	prio_requeue,
+	.drop		=	prio_drop,
+	.init		=	prio_init,
+	.reset		=	prio_reset,
+	.destroy	=	prio_destroy,
+	.change		=	prio_tune,
+	.dump		=	prio_dump,
+	.owner		=	THIS_MODULE,
+};
+
 static int __init prio_module_init(void)
 {
-	return register_qdisc(&prio_qdisc_ops);
+	int err;
+
+	err = register_qdisc(&prio_qdisc_ops);
+	if (err < 0)
+		return err;
+	err = register_qdisc(&rr_qdisc_ops);
+	if (err < 0)
+		unregister_qdisc(&prio_qdisc_ops);
+	return err;
 }
 
 static void __exit prio_module_exit(void)
 {
 	unregister_qdisc(&prio_qdisc_ops);
+	unregister_qdisc(&rr_qdisc_ops);
 }
 
 module_init(prio_module_init)
 module_exit(prio_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("sch_rr");
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 00db53eb8159..9b95fefb70f4 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 96dfdf78d32c..957957309859 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -10,31 +10,17 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
 #include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
 #include <linux/init.h>
-#include <net/ip.h>
-#include <net/netlink.h>
 #include <linux/ipv6.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/ip.h>
+#include <net/netlink.h>
 #include <net/pkt_sched.h>
 
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 53862953baaf..22e431dace54 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -13,29 +13,12 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/jiffies.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/pkt_sched.h>
 
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index f05ad9a30b4c..0968184ea6be 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -9,30 +9,17 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
 #include <linux/errno.h>
-#include <linux/interrupt.h>
 #include <linux/if_arp.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
 #include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
 #include <linux/init.h>
-#include <net/ip.h>
-#include <net/route.h>
 #include <linux/skbuff.h>
 #include <linux/moduleparam.h>
-#include <net/sock.h>
+#include <net/dst.h>
+#include <net/neighbour.h>
 #include <net/pkt_sched.h>
 
 /*
@@ -225,7 +212,6 @@ static int teql_qdisc_init(struct Qdisc *sch, struct rtattr *opt)
 	return 0;
 }
 
-/* "teql*" netdevice routines */
 
 static int
 __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev)
@@ -277,6 +263,7 @@ static int teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
 	int busy;
 	int nores;
 	int len = skb->len;
+	int subq = skb->queue_mapping;
 	struct sk_buff *skb_res = NULL;
 
 	start = master->slaves;
@@ -293,7 +280,9 @@ restart:
 
 		if (slave->qdisc_sleeping != q)
 			continue;
-		if (netif_queue_stopped(slave) || ! netif_running(slave)) {
+		if (netif_queue_stopped(slave) ||
+		    netif_subqueue_stopped(slave, subq) ||
+		    !netif_running(slave)) {
 			busy = 1;
 			continue;
 		}
@@ -302,6 +291,7 @@ restart:
 		case 0:
 			if (netif_tx_trylock(slave)) {
 				if (!netif_queue_stopped(slave) &&
+				    !netif_subqueue_stopped(slave, subq) &&
 				    slave->hard_start_xmit(skb, slave) == 0) {
 					netif_tx_unlock(slave);
 					master->slaves = NEXT_SLAVE(q);