Merge commit 'linus/master' into merge-linus

Conflicts:

	arch/x86/kvm/i8254.c

net/sched/Kconfig

@@ -106,6 +106,15 @@ config NET_SCH_PRIO
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_prio.
 
+config NET_SCH_MULTIQ
+	tristate "Hardware Multiqueue-aware Multi Band Queuing (MULTIQ)"
+	---help---
+	  Say Y here if you want to use an n-band queue packet scheduler
+	  to support devices that have multiple hardware transmit queues.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_multiq.
+
 config NET_SCH_RED
 	tristate "Random Early Detection (RED)"
 	---help---
@@ -476,6 +485,17 @@ config NET_ACT_SIMP
 	  To compile this code as a module, choose M here: the
 	  module will be called simple.
 
+config NET_ACT_SKBEDIT
+        tristate "SKB Editing"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to change skb priority or queue_mapping settings.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called skbedit.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW

net/sched/Makefile

@@ -14,6 +14,7 @@ obj-$(CONFIG_NET_ACT_IPT)	+= act_ipt.o
 obj-$(CONFIG_NET_ACT_NAT)	+= act_nat.o
 obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
+obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
@@ -26,6 +27,7 @@ obj-$(CONFIG_NET_SCH_SFQ)	+= sch_sfq.o
 obj-$(CONFIG_NET_SCH_TBF)	+= sch_tbf.o
 obj-$(CONFIG_NET_SCH_TEQL)	+= sch_teql.o
 obj-$(CONFIG_NET_SCH_PRIO)	+= sch_prio.o
+obj-$(CONFIG_NET_SCH_MULTIQ)	+= sch_multiq.o
 obj-$(CONFIG_NET_SCH_ATM)	+= sch_atm.o
 obj-$(CONFIG_NET_SCH_NETEM)	+= sch_netem.o
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o

net/sched/act_ipt.c

@@ -40,6 +40,7 @@ static struct tcf_hashinfo ipt_hash_info = {
 
 static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook)
 {
+	struct xt_tgchk_param par;
 	struct xt_target *target;
 	int ret = 0;
 
@@ -49,29 +50,30 @@ static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int
 		return -ENOENT;
 
 	t->u.kernel.target = target;
+	par.table     = table;
+	par.entryinfo = NULL;
+	par.target    = target;
+	par.targinfo  = t->data;
+	par.hook_mask = hook;
+	par.family    = NFPROTO_IPV4;
 
-	ret = xt_check_target(target, AF_INET, t->u.target_size - sizeof(*t),
-			      table, hook, 0, 0);
-	if (ret) {
+	ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
+	if (ret < 0) {
 		module_put(t->u.kernel.target->me);
 		return ret;
 	}
-	if (t->u.kernel.target->checkentry
-	    && !t->u.kernel.target->checkentry(table, NULL,
-					       t->u.kernel.target, t->data,
-					       hook)) {
-		module_put(t->u.kernel.target->me);
-		ret = -EINVAL;
-	}
-
-	return ret;
+	return 0;
 }
 
 static void ipt_destroy_target(struct ipt_entry_target *t)
 {
-	if (t->u.kernel.target->destroy)
-		t->u.kernel.target->destroy(t->u.kernel.target, t->data);
-	module_put(t->u.kernel.target->me);
+	struct xt_tgdtor_param par = {
+		.target   = t->u.kernel.target,
+		.targinfo = t->data,
+	};
+	if (par.target->destroy != NULL)
+		par.target->destroy(&par);
+	module_put(par.target->me);
 }
 
 static int tcf_ipt_release(struct tcf_ipt *ipt, int bind)
@@ -196,6 +198,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a,
 {
 	int ret = 0, result = 0;
 	struct tcf_ipt *ipt = a->priv;
+	struct xt_target_param par;
 
 	if (skb_cloned(skb)) {
 		if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
@@ -211,10 +214,13 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a,
 	/* yes, we have to worry about both in and out dev
 	 worry later - danger - this API seems to have changed
 	 from earlier kernels */
-	ret = ipt->tcfi_t->u.kernel.target->target(skb, skb->dev, NULL,
-						   ipt->tcfi_hook,
-						   ipt->tcfi_t->u.kernel.target,
-						   ipt->tcfi_t->data);
+	par.in       = skb->dev;
+	par.out      = NULL;
+	par.hooknum  = ipt->tcfi_hook;
+	par.target   = ipt->tcfi_t->u.kernel.target;
+	par.targinfo = ipt->tcfi_t->data;
+	ret = par.target->target(skb, &par);
+
 	switch (ret) {
 	case NF_ACCEPT:
 		result = TC_ACT_OK;

net/sched/act_skbedit.c

@@ -0,0 +1,203 @@
+/*
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Alexander Duyck <alexander.h.duyck@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_skbedit.h>
+
+#define SKBEDIT_TAB_MASK     15
+static struct tcf_common *tcf_skbedit_ht[SKBEDIT_TAB_MASK + 1];
+static u32 skbedit_idx_gen;
+static DEFINE_RWLOCK(skbedit_lock);
+
+static struct tcf_hashinfo skbedit_hash_info = {
+	.htab	=	tcf_skbedit_ht,
+	.hmask	=	SKBEDIT_TAB_MASK,
+	.lock	=	&skbedit_lock,
+};
+
+static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a,
+		       struct tcf_result *res)
+{
+	struct tcf_skbedit *d = a->priv;
+
+	spin_lock(&d->tcf_lock);
+	d->tcf_tm.lastuse = jiffies;
+	d->tcf_bstats.bytes += qdisc_pkt_len(skb);
+	d->tcf_bstats.packets++;
+
+	if (d->flags & SKBEDIT_F_PRIORITY)
+		skb->priority = d->priority;
+	if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
+	    skb->dev->real_num_tx_queues > d->queue_mapping)
+		skb_set_queue_mapping(skb, d->queue_mapping);
+
+	spin_unlock(&d->tcf_lock);
+	return d->tcf_action;
+}
+
+static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
+	[TCA_SKBEDIT_PARMS]		= { .len = sizeof(struct tc_skbedit) },
+	[TCA_SKBEDIT_PRIORITY]		= { .len = sizeof(u32) },
+	[TCA_SKBEDIT_QUEUE_MAPPING]	= { .len = sizeof(u16) },
+};
+
+static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est,
+			 struct tc_action *a, int ovr, int bind)
+{
+	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
+	struct tc_skbedit *parm;
+	struct tcf_skbedit *d;
+	struct tcf_common *pc;
+	u32 flags = 0, *priority = NULL;
+	u16 *queue_mapping = NULL;
+	int ret = 0, err;
+
+	if (nla == NULL)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_SKBEDIT_PARMS] == NULL)
+		return -EINVAL;
+
+	if (tb[TCA_SKBEDIT_PRIORITY] != NULL) {
+		flags |= SKBEDIT_F_PRIORITY;
+		priority = nla_data(tb[TCA_SKBEDIT_PRIORITY]);
+	}
+
+	if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
+		flags |= SKBEDIT_F_QUEUE_MAPPING;
+		queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
+	}
+	if (!flags)
+		return -EINVAL;
+
+	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
+
+	pc = tcf_hash_check(parm->index, a, bind, &skbedit_hash_info);
+	if (!pc) {
+		pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind,
+				     &skbedit_idx_gen, &skbedit_hash_info);
+		if (unlikely(!pc))
+			return -ENOMEM;
+
+		d = to_skbedit(pc);
+		ret = ACT_P_CREATED;
+	} else {
+		d = to_skbedit(pc);
+		if (!ovr) {
+			tcf_hash_release(pc, bind, &skbedit_hash_info);
+			return -EEXIST;
+		}
+	}
+
+	spin_lock_bh(&d->tcf_lock);
+
+	d->flags = flags;
+	if (flags & SKBEDIT_F_PRIORITY)
+		d->priority = *priority;
+	if (flags & SKBEDIT_F_QUEUE_MAPPING)
+		d->queue_mapping = *queue_mapping;
+	d->tcf_action = parm->action;
+
+	spin_unlock_bh(&d->tcf_lock);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(pc, &skbedit_hash_info);
+	return ret;
+}
+
+static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind)
+{
+	struct tcf_skbedit *d = a->priv;
+
+	if (d)
+		return tcf_hash_release(&d->common, bind, &skbedit_hash_info);
+	return 0;
+}
+
+static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
+				int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_skbedit *d = a->priv;
+	struct tc_skbedit opt;
+	struct tcf_t t;
+
+	opt.index = d->tcf_index;
+	opt.refcnt = d->tcf_refcnt - ref;
+	opt.bindcnt = d->tcf_bindcnt - bind;
+	opt.action = d->tcf_action;
+	NLA_PUT(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt);
+	if (d->flags & SKBEDIT_F_PRIORITY)
+		NLA_PUT(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority),
+			&d->priority);
+	if (d->flags & SKBEDIT_F_QUEUE_MAPPING)
+		NLA_PUT(skb, TCA_SKBEDIT_QUEUE_MAPPING,
+			sizeof(d->queue_mapping), &d->queue_mapping);
+	t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(d->tcf_tm.expires);
+	NLA_PUT(skb, TCA_SKBEDIT_TM, sizeof(t), &t);
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct tc_action_ops act_skbedit_ops = {
+	.kind		=	"skbedit",
+	.hinfo		=	&skbedit_hash_info,
+	.type		=	TCA_ACT_SKBEDIT,
+	.capab		=	TCA_CAP_NONE,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_skbedit,
+	.dump		=	tcf_skbedit_dump,
+	.cleanup	=	tcf_skbedit_cleanup,
+	.init		=	tcf_skbedit_init,
+	.walk		=	tcf_generic_walker,
+};
+
+MODULE_AUTHOR("Alexander Duyck, <[email protected]>");
+MODULE_DESCRIPTION("SKB Editing");
+MODULE_LICENSE("GPL");
+
+static int __init skbedit_init_module(void)
+{
+	return tcf_register_action(&act_skbedit_ops);
+}
+
+static void __exit skbedit_cleanup_module(void)
+{
+	tcf_unregister_action(&act_skbedit_ops);
+}
+
+module_init(skbedit_init_module);
+module_exit(skbedit_cleanup_module);

net/sched/cls_flow.c

@@ -67,9 +67,9 @@ static inline u32 addr_fold(void *addr)
 static u32 flow_get_src(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		return ntohl(ip_hdr(skb)->saddr);
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		return ntohl(ipv6_hdr(skb)->saddr.s6_addr32[3]);
 	default:
 		return addr_fold(skb->sk);
@@ -79,9 +79,9 @@ static u32 flow_get_src(const struct sk_buff *skb)
 static u32 flow_get_dst(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		return ntohl(ip_hdr(skb)->daddr);
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		return ntohl(ipv6_hdr(skb)->daddr.s6_addr32[3]);
 	default:
 		return addr_fold(skb->dst) ^ (__force u16)skb->protocol;
@@ -91,9 +91,9 @@ static u32 flow_get_dst(const struct sk_buff *skb)
 static u32 flow_get_proto(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		return ip_hdr(skb)->protocol;
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		return ipv6_hdr(skb)->nexthdr;
 	default:
 		return 0;
@@ -120,7 +120,7 @@ static u32 flow_get_proto_src(const struct sk_buff *skb)
 	u32 res = 0;
 
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP): {
+	case htons(ETH_P_IP): {
 		struct iphdr *iph = ip_hdr(skb);
 
 		if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) &&
@@ -128,7 +128,7 @@ static u32 flow_get_proto_src(const struct sk_buff *skb)
 			res = ntohs(*(__be16 *)((void *)iph + iph->ihl * 4));
 		break;
 	}
-	case __constant_htons(ETH_P_IPV6): {
+	case htons(ETH_P_IPV6): {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		if (has_ports(iph->nexthdr))
@@ -147,7 +147,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb)
 	u32 res = 0;
 
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP): {
+	case htons(ETH_P_IP): {
 		struct iphdr *iph = ip_hdr(skb);
 
 		if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) &&
@@ -155,7 +155,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb)
 			res = ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + 2));
 		break;
 	}
-	case __constant_htons(ETH_P_IPV6): {
+	case htons(ETH_P_IPV6): {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		if (has_ports(iph->nexthdr))
@@ -213,9 +213,9 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 static u32 flow_get_nfct_src(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		return ntohl(CTTUPLE(skb, src.u3.ip6[3]));
 	}
 fallback:
@@ -225,9 +225,9 @@ fallback:
 static u32 flow_get_nfct_dst(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		return ntohl(CTTUPLE(skb, dst.u3.ip6[3]));
 	}
 fallback:

net/sched/em_cmp.c

@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/tc_ematch/tc_em_cmp.h>
+#include <asm/unaligned.h>
 #include <net/pkt_cls.h>
 
 static inline int cmp_needs_transformation(struct tcf_em_cmp *cmp)
@@ -37,8 +38,7 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em,
 			break;
 
 		case TCF_EM_ALIGN_U16:
-			val = *ptr << 8;
-			val |= *(ptr+1);
+			val = get_unaligned_be16(ptr);
 
 			if (cmp_needs_transformation(cmp))
 				val = be16_to_cpu(val);
@@ -47,10 +47,7 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em,
 		case TCF_EM_ALIGN_U32:
 			/* Worth checking boundries? The branching seems
 			 * to get worse. Visit again. */
-			val = *ptr << 24;
-			val |= *(ptr+1) << 16;
-			val |= *(ptr+2) << 8;
-			val |= *(ptr+3);
+			val = get_unaligned_be32(ptr);
 
 			if (cmp_needs_transformation(cmp))
 				val = be32_to_cpu(val);

net/sched/sch_dsmark.c

@@ -202,7 +202,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	if (p->set_tc_index) {
 		switch (skb->protocol) {
-		case __constant_htons(ETH_P_IP):
+		case htons(ETH_P_IP):
 			if (skb_cow_head(skb, sizeof(struct iphdr)))
 				goto drop;
 
@@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 				& ~INET_ECN_MASK;
 			break;
 
-		case __constant_htons(ETH_P_IPV6):
+		case htons(ETH_P_IPV6):
 			if (skb_cow_head(skb, sizeof(struct ipv6hdr)))
 				goto drop;
 
@@ -289,11 +289,11 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mask[index],
 				    p->value[index]);
 			break;
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 		ipv6_change_dsfield(ipv6_hdr(skb), p->mask[index],
 				    p->value[index]);
 			break;

net/sched/sch_generic.c

@@ -44,23 +44,30 @@ static inline int qdisc_qlen(struct Qdisc *q)
 
 static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	if (unlikely(skb->next))
-		q->gso_skb = skb;
-	else
-		q->ops->requeue(skb, q);
-
+	q->gso_skb = skb;
+	q->qstats.requeues++;
 	__netif_schedule(q);
+
 	return 0;
 }
 
 static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = q->gso_skb;
 
-	if ((skb = q->gso_skb))
-		q->gso_skb = NULL;
-	else
+	if (unlikely(skb)) {
+		struct net_device *dev = qdisc_dev(q);
+		struct netdev_queue *txq;
+
+		/* check the reason of requeuing without tx lock first */
+		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+		if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq))
+			q->gso_skb = NULL;
+		else
+			skb = NULL;
+	} else {
 		skb = q->dequeue(q);
+	}
 
 	return skb;
 }
@@ -215,10 +222,9 @@ static void dev_watchdog(unsigned long arg)
 			    time_after(jiffies, (dev->trans_start +
 						 dev->watchdog_timeo))) {
 				char drivername[64];
-				printk(KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n",
+				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n",
 				       dev->name, netdev_drivername(dev, drivername, 64));
 				dev->tx_timeout(dev);
-				WARN_ON_ONCE(1);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
 				       round_jiffies(jiffies +
@@ -328,6 +334,7 @@ struct Qdisc noop_qdisc = {
 	.flags		=	TCQ_F_BUILTIN,
 	.ops		=	&noop_qdisc_ops,
 	.list		=	LIST_HEAD_INIT(noop_qdisc.list),
+	.requeue.lock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.dev_queue	=	&noop_netdev_queue,
 };
@@ -353,6 +360,7 @@ static struct Qdisc noqueue_qdisc = {
 	.flags		=	TCQ_F_BUILTIN,
 	.ops		=	&noqueue_qdisc_ops,
 	.list		=	LIST_HEAD_INIT(noqueue_qdisc.list),
+	.requeue.lock	=	__SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
 	.dev_queue	=	&noqueue_netdev_queue,
 };
@@ -473,6 +481,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	sch->padded = (char *) sch - (char *) p;
 
 	INIT_LIST_HEAD(&sch->list);
+	skb_queue_head_init(&sch->requeue);
 	skb_queue_head_init(&sch->q);
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
@@ -541,6 +550,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 	dev_put(qdisc_dev(qdisc));
 
 	kfree_skb(qdisc->gso_skb);
+	__skb_queue_purge(&qdisc->requeue);
 
 	kfree((char *) qdisc - qdisc->padded);
 }

net/sched/sch_multiq.c

@@ -0,0 +1,477 @@
+/*
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Alexander Duyck <alexander.h.duyck@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+
+struct multiq_sched_data {
+	u16 bands;
+	u16 max_bands;
+	u16 curband;
+	struct tcf_proto *filter_list;
+	struct Qdisc **queues;
+};
+
+
+static struct Qdisc *
+multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	u32 band;
+	struct tcf_result res;
+	int err;
+
+	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+	err = tc_classify(skb, q->filter_list, &res);
+#ifdef CONFIG_NET_CLS_ACT
+	switch (err) {
+	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
+		*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+	case TC_ACT_SHOT:
+		return NULL;
+	}
+#endif
+	band = skb_get_queue_mapping(skb);
+
+	if (band >= q->bands)
+		return q->queues[0];
+
+	return q->queues[band];
+}
+
+static int
+multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct Qdisc *qdisc;
+	int ret;
+
+	qdisc = multiq_classify(skb, sch, &ret);
+#ifdef CONFIG_NET_CLS_ACT
+	if (qdisc == NULL) {
+
+		if (ret & __NET_XMIT_BYPASS)
+			sch->qstats.drops++;
+		kfree_skb(skb);
+		return ret;
+	}
+#endif
+
+	ret = qdisc_enqueue(skb, qdisc);
+	if (ret == NET_XMIT_SUCCESS) {
+		sch->bstats.bytes += qdisc_pkt_len(skb);
+		sch->bstats.packets++;
+		sch->q.qlen++;
+		return NET_XMIT_SUCCESS;
+	}
+	if (net_xmit_drop_count(ret))
+		sch->qstats.drops++;
+	return ret;
+}
+
+
+static int
+multiq_requeue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct Qdisc *qdisc;
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	int ret;
+
+	qdisc = multiq_classify(skb, sch, &ret);
+#ifdef CONFIG_NET_CLS_ACT
+	if (qdisc == NULL) {
+		if (ret & __NET_XMIT_BYPASS)
+			sch->qstats.drops++;
+		kfree_skb(skb);
+		return ret;
+	}
+#endif
+
+	ret = qdisc->ops->requeue(skb, qdisc);
+	if (ret == NET_XMIT_SUCCESS) {
+		sch->q.qlen++;
+		sch->qstats.requeues++;
+		if (q->curband)
+			q->curband--;
+		else
+			q->curband = q->bands - 1;
+		return NET_XMIT_SUCCESS;
+	}
+	if (net_xmit_drop_count(ret))
+		sch->qstats.drops++;
+	return ret;
+}
+
+
+static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc;
+	struct sk_buff *skb;
+	int band;
+
+	for (band = 0; band < q->bands; band++) {
+		/* cycle through bands to ensure fairness */
+		q->curband++;
+		if (q->curband >= q->bands)
+			q->curband = 0;
+
+		/* Check that target subqueue is available before
+		 * pulling an skb to avoid excessive requeues
+		 */
+		if (!__netif_subqueue_stopped(qdisc_dev(sch), q->curband)) {
+			qdisc = q->queues[q->curband];
+			skb = qdisc->dequeue(qdisc);
+			if (skb) {
+				sch->q.qlen--;
+				return skb;
+			}
+		}
+	}
+	return NULL;
+
+}
+
+static unsigned int multiq_drop(struct Qdisc *sch)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	int band;
+	unsigned int len;
+	struct Qdisc *qdisc;
+
+	for (band = q->bands-1; band >= 0; band--) {
+		qdisc = q->queues[band];
+		if (qdisc->ops->drop) {
+			len = qdisc->ops->drop(qdisc);
+			if (len != 0) {
+				sch->q.qlen--;
+				return len;
+			}
+		}
+	}
+	return 0;
+}
+
+
+static void
+multiq_reset(struct Qdisc *sch)
+{
+	u16 band;
+	struct multiq_sched_data *q = qdisc_priv(sch);
+
+	for (band = 0; band < q->bands; band++)
+		qdisc_reset(q->queues[band]);
+	sch->q.qlen = 0;
+	q->curband = 0;
+}
+
+static void
+multiq_destroy(struct Qdisc *sch)
+{
+	int band;
+	struct multiq_sched_data *q = qdisc_priv(sch);
+
+	tcf_destroy_chain(&q->filter_list);
+	for (band = 0; band < q->bands; band++)
+		qdisc_destroy(q->queues[band]);
+
+	kfree(q->queues);
+}
+
+static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	struct tc_multiq_qopt *qopt;
+	int i;
+
+	if (!netif_is_multiqueue(qdisc_dev(sch)))
+		return -EINVAL;
+	if (nla_len(opt) < sizeof(*qopt))
+		return -EINVAL;
+
+	qopt = nla_data(opt);
+
+	qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
+
+	sch_tree_lock(sch);
+	q->bands = qopt->bands;
+	for (i = q->bands; i < q->max_bands; i++) {
+		if (q->queues[i] != &noop_qdisc) {
+			struct Qdisc *child = xchg(&q->queues[i], &noop_qdisc);
+			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_destroy(child);
+		}
+	}
+
+	sch_tree_unlock(sch);
+
+	for (i = 0; i < q->bands; i++) {
+		if (q->queues[i] == &noop_qdisc) {
+			struct Qdisc *child;
+			child = qdisc_create_dflt(qdisc_dev(sch),
+						  sch->dev_queue,
+						  &pfifo_qdisc_ops,
+						  TC_H_MAKE(sch->handle,
+							    i + 1));
+			if (child) {
+				sch_tree_lock(sch);
+				child = xchg(&q->queues[i], child);
+
+				if (child != &noop_qdisc) {
+					qdisc_tree_decrease_qlen(child,
+								 child->q.qlen);
+					qdisc_destroy(child);
+				}
+				sch_tree_unlock(sch);
+			}
+		}
+	}
+	return 0;
+}
+
+static int multiq_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	int i, err;
+
+	q->queues = NULL;
+
+	if (opt == NULL)
+		return -EINVAL;
+
+	q->max_bands = qdisc_dev(sch)->num_tx_queues;
+
+	q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL);
+	if (!q->queues)
+		return -ENOBUFS;
+	for (i = 0; i < q->max_bands; i++)
+		q->queues[i] = &noop_qdisc;
+
+	err = multiq_tune(sch,opt);
+
+	if (err)
+		kfree(q->queues);
+
+	return err;
+}
+
+static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tc_multiq_qopt opt;
+
+	opt.bands = q->bands;
+	opt.max_bands = q->max_bands;
+
+	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		      struct Qdisc **old)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	unsigned long band = arg - 1;
+
+	if (band >= q->bands)
+		return -EINVAL;
+
+	if (new == NULL)
+		new = &noop_qdisc;
+
+	sch_tree_lock(sch);
+	*old = q->queues[band];
+	q->queues[band] = new;
+	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
+	qdisc_reset(*old);
+	sch_tree_unlock(sch);
+
+	return 0;
+}
+
+static struct Qdisc *
+multiq_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	unsigned long band = arg - 1;
+
+	if (band >= q->bands)
+		return NULL;
+
+	return q->queues[band];
+}
+
+static unsigned long multiq_get(struct Qdisc *sch, u32 classid)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	unsigned long band = TC_H_MIN(classid);
+
+	if (band - 1 >= q->bands)
+		return 0;
+	return band;
+}
+
+static unsigned long multiq_bind(struct Qdisc *sch, unsigned long parent,
+				 u32 classid)
+{
+	return multiq_get(sch, classid);
+}
+
+
+static void multiq_put(struct Qdisc *q, unsigned long cl)
+{
+	return;
+}
+
+static int multiq_change(struct Qdisc *sch, u32 handle, u32 parent,
+			 struct nlattr **tca, unsigned long *arg)
+{
+	unsigned long cl = *arg;
+	struct multiq_sched_data *q = qdisc_priv(sch);
+
+	if (cl - 1 > q->bands)
+		return -ENOENT;
+	return 0;
+}
+
+static int multiq_delete(struct Qdisc *sch, unsigned long cl)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	if (cl - 1 > q->bands)
+		return -ENOENT;
+	return 0;
+}
+
+
+static int multiq_dump_class(struct Qdisc *sch, unsigned long cl,
+			     struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+
+	if (cl - 1 > q->bands)
+		return -ENOENT;
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	if (q->queues[cl-1])
+		tcm->tcm_info = q->queues[cl-1]->handle;
+	return 0;
+}
+
+static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				 struct gnet_dump *d)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *cl_q;
+
+	cl_q = q->queues[cl - 1];
+	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
+		return -1;
+
+	return 0;
+}
+
+static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+	int band;
+
+	if (arg->stop)
+		return;
+
+	for (band = 0; band < q->bands; band++) {
+		if (arg->count < arg->skip) {
+			arg->count++;
+			continue;
+		}
+		if (arg->fn(sch, band+1, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+		arg->count++;
+	}
+}
+
+static struct tcf_proto **multiq_find_tcf(struct Qdisc *sch, unsigned long cl)
+{
+	struct multiq_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return &q->filter_list;
+}
+
+static const struct Qdisc_class_ops multiq_class_ops = {
+	.graft		=	multiq_graft,
+	.leaf		=	multiq_leaf,
+	.get		=	multiq_get,
+	.put		=	multiq_put,
+	.change		=	multiq_change,
+	.delete		=	multiq_delete,
+	.walk		=	multiq_walk,
+	.tcf_chain	=	multiq_find_tcf,
+	.bind_tcf	=	multiq_bind,
+	.unbind_tcf	=	multiq_put,
+	.dump		=	multiq_dump_class,
+	.dump_stats	=	multiq_dump_class_stats,
+};
+
+static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
+	.next		=	NULL,
+	.cl_ops		=	&multiq_class_ops,
+	.id		=	"multiq",
+	.priv_size	=	sizeof(struct multiq_sched_data),
+	.enqueue	=	multiq_enqueue,
+	.dequeue	=	multiq_dequeue,
+	.requeue	=	multiq_requeue,
+	.drop		=	multiq_drop,
+	.init		=	multiq_init,
+	.reset		=	multiq_reset,
+	.destroy	=	multiq_destroy,
+	.change		=	multiq_tune,
+	.dump		=	multiq_dump,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init multiq_module_init(void)
+{
+	return register_qdisc(&multiq_qdisc_ops);
+}
+
+static void __exit multiq_module_exit(void)
+{
+	unregister_qdisc(&multiq_qdisc_ops);
+}
+
+module_init(multiq_module_init)
+module_exit(multiq_module_exit)
+
+MODULE_LICENSE("GPL");

net/sched/sch_netem.c

@@ -388,6 +388,20 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_CORRUPT]	= { .len = sizeof(struct tc_netem_corrupt) },
 };
 
+static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		      const struct nla_policy *policy, int len)
+{
+	int nested_len = nla_len(nla) - NLA_ALIGN(len);
+
+	if (nested_len < 0)
+		return -EINVAL;
+	if (nested_len >= nla_attr_size(0))
+		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
+				 nested_len, policy);
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+	return 0;
+}
+
 /* Parse netlink message to set options */
 static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 {
@@ -399,8 +413,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	ret = nla_parse_nested_compat(tb, TCA_NETEM_MAX, opt, netem_policy,
-				      qopt, sizeof(*qopt));
+	qopt = nla_data(opt);
+	ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt));
 	if (ret < 0)
 		return ret;
 

net/sched/sch_prio.c

@@ -254,16 +254,12 @@ 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 nlattr *nest;
 	struct tc_prio_qopt opt;
 
 	opt.bands = q->bands;
 	memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1);
 
-	nest = nla_nest_compat_start(skb, TCA_OPTIONS, sizeof(opt), &opt);
-	if (nest == NULL)
-		goto nla_put_failure;
-	nla_nest_compat_end(skb, nest);
+	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
 
 	return skb->len;
 

net/sched/sch_sfq.c

@@ -119,7 +119,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
 	u32 h, h2;
 
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 	{
 		const struct iphdr *iph = ip_hdr(skb);
 		h = iph->daddr;
@@ -134,7 +134,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
 			h2 ^= *(((u32*)iph) + iph->ihl);
 		break;
 	}
-	case __constant_htons(ETH_P_IPV6):
+	case htons(ETH_P_IPV6):
 	{
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 		h = iph->daddr.s6_addr32[3];