From 99c0db26797edb39cf83c8c5f8972067f5426b4e Mon Sep 17 00:00:00 2001
From: Jarek Poplawski <jarkao2@gmail.com>
Date: Fri, 31 Oct 2008 00:45:27 -0700
Subject: pkt_sched: sch_generic: Add generic qdisc->ops->peek()
 implementation.

With feedback from Patrick McHardy.

Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'net/sched/sch_generic.c')

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 93cd30ce650..318c9f656e8 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -320,6 +320,7 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = {
 	.priv_size	=	0,
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
+	.peek		=	noop_dequeue,
 	.requeue	=	noop_requeue,
 	.owner		=	THIS_MODULE,
 };
@@ -346,6 +347,7 @@ static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
 	.priv_size	=	0,
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
+	.peek		=	noop_dequeue,
 	.requeue	=	noop_requeue,
 	.owner		=	THIS_MODULE,
 };
@@ -411,6 +413,19 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc)
 	return NULL;
 }
 
+static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc)
+{
+	int prio;
+	struct sk_buff_head *list = qdisc_priv(qdisc);
+
+	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
+		if (!skb_queue_empty(list + prio))
+			return skb_peek(list + prio);
+	}
+
+	return NULL;
+}
+
 static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
 {
 	qdisc->q.qlen++;
@@ -457,6 +472,7 @@ static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.priv_size	=	PFIFO_FAST_BANDS * sizeof(struct sk_buff_head),
 	.enqueue	=	pfifo_fast_enqueue,
 	.dequeue	=	pfifo_fast_dequeue,
+	.peek		=	pfifo_fast_peek,
 	.requeue	=	pfifo_fast_requeue,
 	.init		=	pfifo_fast_init,
 	.reset		=	pfifo_fast_reset,
-- 
cgit v1.2.3-70-g09d2


From 67305ebc992abf2121fb2149fd8a707cd7cfcbd2 Mon Sep 17 00:00:00 2001
From: Jarek Poplawski <jarkao2@gmail.com>
Date: Mon, 3 Nov 2008 02:52:50 -0800
Subject: pkt_sched: sch_generic: Kfree gso_skb in qdisc_reset()

Since gso_skb is re-used for qdisc_peek_dequeued(), and this skb is
counted in the qdisc->q.qlen, it has to be kfreed during qdisc_reset()
when qlen is zeroed.

With help from David S. Miller <davem@davemloft.net>

Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'net/sched/sch_generic.c')

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 318c9f656e8..1192da22983 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -542,6 +542,9 @@ void qdisc_reset(struct Qdisc *qdisc)
 
 	if (ops->reset)
 		ops->reset(qdisc);
+
+	kfree_skb(qdisc->gso_skb);
+	qdisc->gso_skb = NULL;
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-- 
cgit v1.2.3-70-g09d2


From f30ab418a1d3c5a8b83493e7d70d6876a74aa0ce Mon Sep 17 00:00:00 2001
From: Jarek Poplawski <jarkao2@gmail.com>
Date: Thu, 13 Nov 2008 22:56:30 -0800
Subject: pkt_sched: Remove qdisc->ops->requeue() etc.

After implementing qdisc->ops->peek() and changing sch_netem into
classless qdisc there are no more qdisc->ops->requeue() users. This
patch removes this method with its wrappers (qdisc_requeue()), and
also unused qdisc->requeue structure. There are a few minor fixes of
warnings (htb_enqueue()) and comments btw.

The idea to kill ->requeue() and a similar patch were first developed
by David S. Miller.

Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 17 -------------
 net/sched/sch_api.c       |  7 ------
 net/sched/sch_atm.c       | 20 +--------------
 net/sched/sch_cbq.c       | 35 --------------------------
 net/sched/sch_dsmark.c    | 21 ----------------
 net/sched/sch_fifo.c      |  2 --
 net/sched/sch_generic.c   | 23 -----------------
 net/sched/sch_gred.c      | 21 ----------------
 net/sched/sch_hfsc.c      | 19 --------------
 net/sched/sch_htb.c       | 44 +--------------------------------
 net/sched/sch_multiq.c    | 39 ++---------------------------
 net/sched/sch_netem.c     | 16 ------------
 net/sched/sch_prio.c      | 28 ---------------------
 net/sched/sch_red.c       | 18 --------------
 net/sched/sch_sfq.c       | 63 -----------------------------------------------
 net/sched/sch_tbf.c       | 14 -----------
 net/sched/sch_teql.c      | 11 ---------
 17 files changed, 4 insertions(+), 394 deletions(-)

(limited to 'net/sched/sch_generic.c')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 64ae1ba9f55..f8c47429044 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -53,7 +53,6 @@ struct Qdisc
 	atomic_t		refcnt;
 	unsigned long		state;
 	struct sk_buff		*gso_skb;
-	struct sk_buff_head	requeue;
 	struct sk_buff_head	q;
 	struct netdev_queue	*dev_queue;
 	struct Qdisc		*next_sched;
@@ -112,7 +111,6 @@ struct Qdisc_ops
 	int 			(*enqueue)(struct sk_buff *, struct Qdisc *);
 	struct sk_buff *	(*dequeue)(struct Qdisc *);
 	struct sk_buff *	(*peek)(struct Qdisc *);
-	int 			(*requeue)(struct sk_buff *, struct Qdisc *);
 	unsigned int		(*drop)(struct Qdisc *);
 
 	int			(*init)(struct Qdisc *, struct nlattr *arg);
@@ -467,21 +465,6 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 	return skb;
 }
 
-static inline int __qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch,
-				  struct sk_buff_head *list)
-{
-	__skb_queue_head(list, skb);
-	sch->qstats.backlog += qdisc_pkt_len(skb);
-	sch->qstats.requeues++;
-
-	return NET_XMIT_SUCCESS;
-}
-
-static inline int qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	return __qdisc_requeue(skb, sch, &sch->q);
-}
-
 static inline void __qdisc_reset_queue(struct Qdisc *sch,
 				       struct sk_buff_head *list)
 {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e5646614e88..5bcef13408c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -97,11 +97,6 @@ static int tclass_notify(struct sk_buff *oskb, struct nlmsghdr *n,
 
    Auxiliary routines:
 
-   ---requeue
-
-   requeues once dequeued packet. It is used for non-standard or
-   just buggy devices, which can defer output even if netif_queue_stopped()=0.
-
    ---peek
 
    like dequeue but without removing a packet from the queue
@@ -151,8 +146,6 @@ int register_qdisc(struct Qdisc_ops *qops)
 
 	if (qops->enqueue == NULL)
 		qops->enqueue = noop_qdisc_ops.enqueue;
-	if (qops->requeue == NULL)
-		qops->requeue = noop_qdisc_ops.requeue;
 	if (qops->peek == NULL) {
 		if (qops->dequeue == NULL) {
 			qops->peek = noop_qdisc_ops.peek;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 6eb9a650b63..ca90f6e59ae 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -62,7 +62,7 @@ struct atm_qdisc_data {
 	struct atm_flow_data	link;		/* unclassified skbs go here */
 	struct atm_flow_data	*flows;		/* NB: "link" is also on this
 						   list */
-	struct tasklet_struct	task;		/* requeue tasklet */
+	struct tasklet_struct	task;		/* dequeue tasklet */
 };
 
 /* ------------------------- Class/flow operations ------------------------- */
@@ -534,23 +534,6 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch)
 	return p->link.q->ops->peek(p->link.q);
 }
 
-static int atm_tc_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct atm_qdisc_data *p = qdisc_priv(sch);
-	int ret;
-
-	pr_debug("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
-	ret = p->link.q->ops->requeue(skb, p->link.q);
-	if (!ret) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
-	} else if (net_xmit_drop_count(ret)) {
-		sch->qstats.drops++;
-		p->link.qstats.drops++;
-	}
-	return ret;
-}
-
 static unsigned int atm_tc_drop(struct Qdisc *sch)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
@@ -707,7 +690,6 @@ static struct Qdisc_ops atm_qdisc_ops __read_mostly = {
 	.enqueue	= atm_tc_enqueue,
 	.dequeue	= atm_tc_dequeue,
 	.peek		= atm_tc_peek,
-	.requeue	= atm_tc_requeue,
 	.drop		= atm_tc_drop,
 	.init		= atm_tc_init,
 	.reset		= atm_tc_reset,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 63efa70abbe..a99e37e9e6f 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -405,40 +405,6 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return ret;
 }
 
-static int
-cbq_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl;
-	int ret;
-
-	if ((cl = q->tx_class) == NULL) {
-		kfree_skb(skb);
-		sch->qstats.drops++;
-		return NET_XMIT_CN;
-	}
-	q->tx_class = NULL;
-
-	cbq_mark_toplevel(q, cl);
-
-#ifdef CONFIG_NET_CLS_ACT
-	q->rx_class = cl;
-	cl->q->__parent = sch;
-#endif
-	if ((ret = cl->q->ops->requeue(skb, cl->q)) == 0) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
-		if (!cl->next_alive)
-			cbq_activate_class(cl);
-		return 0;
-	}
-	if (net_xmit_drop_count(ret)) {
-		sch->qstats.drops++;
-		cl->qstats.drops++;
-	}
-	return ret;
-}
-
 /* Overlimit actions */
 
 /* TC_CBQ_OVL_CLASSIC: (default) penalize leaf class by adding offtime */
@@ -2067,7 +2033,6 @@ static struct Qdisc_ops cbq_qdisc_ops __read_mostly = {
 	.enqueue	=	cbq_enqueue,
 	.dequeue	=	cbq_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.requeue	=	cbq_requeue,
 	.drop		=	cbq_drop,
 	.init		=	cbq_init,
 	.reset		=	cbq_reset,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 3e491479ea8..3f9427a4b75 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -322,26 +322,6 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch)
 	return p->q->ops->peek(p->q);
 }
 
-static int dsmark_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct dsmark_qdisc_data *p = qdisc_priv(sch);
-	int err;
-
-	pr_debug("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
-
-	err = p->q->ops->requeue(skb, p->q);
-	if (err != NET_XMIT_SUCCESS) {
-		if (net_xmit_drop_count(err))
-			sch->qstats.drops++;
-		return err;
-	}
-
-	sch->q.qlen++;
-	sch->qstats.requeues++;
-
-	return NET_XMIT_SUCCESS;
-}
-
 static unsigned int dsmark_drop(struct Qdisc *sch)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
@@ -506,7 +486,6 @@ static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = {
 	.enqueue	=	dsmark_enqueue,
 	.dequeue	=	dsmark_dequeue,
 	.peek		=	dsmark_peek,
-	.requeue	=	dsmark_requeue,
 	.drop		=	dsmark_drop,
 	.init		=	dsmark_init,
 	.reset		=	dsmark_reset,
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 8825e8806f4..92cfc9d7e3b 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -84,7 +84,6 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
 	.enqueue	=	pfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.requeue	=	qdisc_requeue,
 	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
@@ -100,7 +99,6 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
 	.enqueue	=	bfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.requeue	=	qdisc_requeue,
 	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 1192da22983..80c8f3dbbea 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -306,22 +306,12 @@ static struct sk_buff *noop_dequeue(struct Qdisc * qdisc)
 	return NULL;
 }
 
-static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
-{
-	if (net_ratelimit())
-		printk(KERN_DEBUG "%s deferred output. It is buggy.\n",
-		       skb->dev->name);
-	kfree_skb(skb);
-	return NET_XMIT_CN;
-}
-
 struct Qdisc_ops noop_qdisc_ops __read_mostly = {
 	.id		=	"noop",
 	.priv_size	=	0,
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
 	.peek		=	noop_dequeue,
-	.requeue	=	noop_requeue,
 	.owner		=	THIS_MODULE,
 };
 
@@ -336,7 +326,6 @@ 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,
 };
@@ -348,7 +337,6 @@ static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
 	.peek		=	noop_dequeue,
-	.requeue	=	noop_requeue,
 	.owner		=	THIS_MODULE,
 };
 
@@ -364,7 +352,6 @@ 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,
 };
@@ -426,12 +413,6 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc)
 	return NULL;
 }
 
-static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
-{
-	qdisc->q.qlen++;
-	return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc));
-}
-
 static void pfifo_fast_reset(struct Qdisc* qdisc)
 {
 	int prio;
@@ -473,7 +454,6 @@ static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.enqueue	=	pfifo_fast_enqueue,
 	.dequeue	=	pfifo_fast_dequeue,
 	.peek		=	pfifo_fast_peek,
-	.requeue	=	pfifo_fast_requeue,
 	.init		=	pfifo_fast_init,
 	.reset		=	pfifo_fast_reset,
 	.dump		=	pfifo_fast_dump,
@@ -499,7 +479,6 @@ 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;
@@ -571,8 +550,6 @@ 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);
 }
 EXPORT_SYMBOL(qdisc_destroy);
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index cb20ee3b9fc..40408d595c0 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -240,26 +240,6 @@ congestion_drop:
 	return NET_XMIT_CN;
 }
 
-static int gred_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
-	struct gred_sched *t = qdisc_priv(sch);
-	struct gred_sched_data *q;
-	u16 dp = tc_index_to_dp(skb);
-
-	if (dp >= t->DPs || (q = t->tab[dp]) == NULL) {
-		if (net_ratelimit())
-			printk(KERN_WARNING "GRED: Unable to relocate VQ 0x%x "
-			       "for requeue, screwing up backlog.\n",
-			       tc_index_to_dp(skb));
-	} else {
-		if (red_is_idling(&q->parms))
-			red_end_of_idle_period(&q->parms);
-		q->backlog += qdisc_pkt_len(skb);
-	}
-
-	return qdisc_requeue(skb, sch);
-}
-
 static struct sk_buff *gred_dequeue(struct Qdisc* sch)
 {
 	struct sk_buff *skb;
@@ -603,7 +583,6 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = {
 	.enqueue	=	gred_enqueue,
 	.dequeue	=	gred_dequeue,
 	.peek		=	qdisc_peek_head,
-	.requeue	=	gred_requeue,
 	.drop		=	gred_drop,
 	.init		=	gred_init,
 	.reset		=	gred_reset,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d90b1652f2a..071c4749a12 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -184,7 +184,6 @@ struct hfsc_sched
 	struct rb_root eligible;		/* eligible tree */
 	struct list_head droplist;		/* active leaf class list (for
 						   dropping) */
-	struct sk_buff_head requeue;		/* requeued packet */
 	struct qdisc_watchdog watchdog;		/* watchdog timer */
 };
 
@@ -1432,7 +1431,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 		return err;
 	q->eligible = RB_ROOT;
 	INIT_LIST_HEAD(&q->droplist);
-	skb_queue_head_init(&q->requeue);
 
 	q->root.cl_common.classid = sch->handle;
 	q->root.refcnt  = 1;
@@ -1517,7 +1515,6 @@ hfsc_reset_qdisc(struct Qdisc *sch)
 		hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode)
 			hfsc_reset_class(cl);
 	}
-	__skb_queue_purge(&q->requeue);
 	q->eligible = RB_ROOT;
 	INIT_LIST_HEAD(&q->droplist);
 	qdisc_watchdog_cancel(&q->watchdog);
@@ -1542,7 +1539,6 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
 			hfsc_destroy_class(sch, cl);
 	}
 	qdisc_class_hash_destroy(&q->clhash);
-	__skb_queue_purge(&q->requeue);
 	qdisc_watchdog_cancel(&q->watchdog);
 }
 
@@ -1609,8 +1605,6 @@ hfsc_dequeue(struct Qdisc *sch)
 
 	if (sch->q.qlen == 0)
 		return NULL;
-	if ((skb = __skb_dequeue(&q->requeue)))
-		goto out;
 
 	cur_time = psched_get_time();
 
@@ -1659,24 +1653,12 @@ hfsc_dequeue(struct Qdisc *sch)
 		set_passive(cl);
 	}
 
- out:
 	sch->flags &= ~TCQ_F_THROTTLED;
 	sch->q.qlen--;
 
 	return skb;
 }
 
-static int
-hfsc_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct hfsc_sched *q = qdisc_priv(sch);
-
-	__skb_queue_head(&q->requeue, skb);
-	sch->q.qlen++;
-	sch->qstats.requeues++;
-	return NET_XMIT_SUCCESS;
-}
-
 static unsigned int
 hfsc_drop(struct Qdisc *sch)
 {
@@ -1728,7 +1710,6 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = {
 	.enqueue	= hfsc_enqueue,
 	.dequeue	= hfsc_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.requeue	= hfsc_requeue,
 	.drop		= hfsc_drop,
 	.cl_ops		= &hfsc_class_ops,
 	.priv_size	= sizeof(struct hfsc_sched),
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 3fda8199713..83f5e69243c 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -551,7 +551,7 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 
 static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
-	int ret;
+	int uninitialized_var(ret);
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = htb_classify(skb, sch, &ret);
 
@@ -591,47 +591,6 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return NET_XMIT_SUCCESS;
 }
 
-/* TODO: requeuing packet charges it to policers again !! */
-static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	int ret;
-	struct htb_sched *q = qdisc_priv(sch);
-	struct htb_class *cl = htb_classify(skb, sch, &ret);
-	struct sk_buff *tskb;
-
-	if (cl == HTB_DIRECT) {
-		/* enqueue to helper queue */
-		if (q->direct_queue.qlen < q->direct_qlen) {
-			__skb_queue_head(&q->direct_queue, skb);
-		} else {
-			__skb_queue_head(&q->direct_queue, skb);
-			tskb = __skb_dequeue_tail(&q->direct_queue);
-			kfree_skb(tskb);
-			sch->qstats.drops++;
-			return NET_XMIT_CN;
-		}
-#ifdef CONFIG_NET_CLS_ACT
-	} else if (!cl) {
-		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
-		kfree_skb(skb);
-		return ret;
-#endif
-	} else if ((ret = cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q)) !=
-		   NET_XMIT_SUCCESS) {
-		if (net_xmit_drop_count(ret)) {
-			sch->qstats.drops++;
-			cl->qstats.drops++;
-		}
-		return ret;
-	} else
-		htb_activate(q, cl);
-
-	sch->q.qlen++;
-	sch->qstats.requeues++;
-	return NET_XMIT_SUCCESS;
-}
-
 /**
  * htb_charge_class - charges amount "bytes" to leaf and ancestors
  *
@@ -1566,7 +1525,6 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
 	.enqueue	=	htb_enqueue,
 	.dequeue	=	htb_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.requeue	=	htb_requeue,
 	.drop		=	htb_drop,
 	.init		=	htb_init,
 	.reset		=	htb_reset,
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 155648d23b7..f645ac55a1a 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -92,40 +92,6 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	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);
@@ -140,7 +106,7 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
 			q->curband = 0;
 
 		/* Check that target subqueue is available before
-		 * pulling an skb to avoid excessive requeues
+		 * pulling an skb to avoid head-of-line blocking.
 		 */
 		if (!__netif_subqueue_stopped(qdisc_dev(sch), q->curband)) {
 			qdisc = q->queues[q->curband];
@@ -170,7 +136,7 @@ static struct sk_buff *multiq_peek(struct Qdisc *sch)
 			curband = 0;
 
 		/* Check that target subqueue is available before
-		 * pulling an skb to avoid excessive requeues
+		 * pulling an skb to avoid head-of-line blocking.
 		 */
 		if (!__netif_subqueue_stopped(qdisc_dev(sch), curband)) {
 			qdisc = q->queues[curband];
@@ -480,7 +446,6 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
 	.enqueue	=	multiq_enqueue,
 	.dequeue	=	multiq_dequeue,
 	.peek		=	multiq_peek,
-	.requeue	=	multiq_requeue,
 	.drop		=	multiq_drop,
 	.init		=	multiq_init,
 	.reset		=	multiq_reset,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index f69698ff88d..3cbc3ff7b5b 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -252,20 +252,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return ret;
 }
 
-/* Requeue packets but don't change time stamp */
-static int netem_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct netem_sched_data *q = qdisc_priv(sch);
-	int ret;
-
-	if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
-	}
-
-	return ret;
-}
-
 static unsigned int netem_drop(struct Qdisc* sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
@@ -531,7 +517,6 @@ static struct Qdisc_ops tfifo_qdisc_ops __read_mostly = {
 	.enqueue	=	tfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.requeue	=	qdisc_requeue,
 	.drop		=	qdisc_queue_drop,
 	.init		=	tfifo_init,
 	.reset		=	qdisc_reset_queue,
@@ -620,7 +605,6 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = {
 	.enqueue	=	netem_enqueue,
 	.dequeue	=	netem_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.requeue	=	netem_requeue,
 	.drop		=	netem_drop,
 	.init		=	netem_init,
 	.reset		=	netem_reset,
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 3651da3e280..ea65a87ec22 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -93,33 +93,6 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return ret;
 }
 
-
-static int
-prio_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
-	struct Qdisc *qdisc;
-	int ret;
-
-	qdisc = prio_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
-
-	if ((ret = qdisc->ops->requeue(skb, qdisc)) == NET_XMIT_SUCCESS) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
-		return NET_XMIT_SUCCESS;
-	}
-	if (net_xmit_drop_count(ret))
-		sch->qstats.drops++;
-	return ret;
-}
-
 static struct sk_buff *prio_peek(struct Qdisc *sch)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
@@ -435,7 +408,6 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
 	.enqueue	=	prio_enqueue,
 	.dequeue	=	prio_dequeue,
 	.peek		=	prio_peek,
-	.requeue	=	prio_requeue,
 	.drop		=	prio_drop,
 	.init		=	prio_init,
 	.reset		=	prio_reset,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 7abc51454c2..6a0371c2264 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -108,23 +108,6 @@ congestion_drop:
 	return NET_XMIT_CN;
 }
 
-static int red_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
-	struct red_sched_data *q = qdisc_priv(sch);
-	struct Qdisc *child = q->qdisc;
-	int ret;
-
-	if (red_is_idling(&q->parms))
-		red_end_of_idle_period(&q->parms);
-
-	ret = child->ops->requeue(skb, child);
-	if (likely(ret == NET_XMIT_SUCCESS)) {
-		sch->qstats.requeues++;
-		sch->q.qlen++;
-	}
-	return ret;
-}
-
 static struct sk_buff * red_dequeue(struct Qdisc* sch)
 {
 	struct sk_buff *skb;
@@ -370,7 +353,6 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = {
 	.enqueue	=	red_enqueue,
 	.dequeue	=	red_dequeue,
 	.peek		=	red_peek,
-	.requeue	=	red_requeue,
 	.drop		=	red_drop,
 	.init		=	red_init,
 	.reset		=	red_reset,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 198b83d42ba..ab8cfee3c9c 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -329,68 +329,6 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return NET_XMIT_CN;
 }
 
-static int
-sfq_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
-	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
-	sfq_index x;
-	int ret;
-
-	hash = sfq_classify(skb, sch, &ret);
-	if (hash == 0) {
-		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
-		kfree_skb(skb);
-		return ret;
-	}
-	hash--;
-
-	x = q->ht[hash];
-	if (x == SFQ_DEPTH) {
-		q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
-		q->hash[x] = hash;
-	}
-
-	sch->qstats.backlog += qdisc_pkt_len(skb);
-	__skb_queue_head(&q->qs[x], skb);
-	/* If selected queue has length q->limit+1, this means that
-	 * all another queues are empty and we do simple tail drop.
-	 * This packet is still requeued at head of queue, tail packet
-	 * is dropped.
-	 */
-	if (q->qs[x].qlen > q->limit) {
-		skb = q->qs[x].prev;
-		__skb_unlink(skb, &q->qs[x]);
-		sch->qstats.drops++;
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
-		kfree_skb(skb);
-		return NET_XMIT_CN;
-	}
-
-	sfq_inc(q, x);
-	if (q->qs[x].qlen == 1) {		/* The flow is new */
-		if (q->tail == SFQ_DEPTH) {	/* It is the first flow */
-			q->tail = x;
-			q->next[x] = x;
-			q->allot[x] = q->quantum;
-		} else {
-			q->next[x] = q->next[q->tail];
-			q->next[q->tail] = x;
-			q->tail = x;
-		}
-	}
-
-	if (++sch->q.qlen <= q->limit) {
-		sch->qstats.requeues++;
-		return 0;
-	}
-
-	sch->qstats.drops++;
-	sfq_drop(sch);
-	return NET_XMIT_CN;
-}
-
 static struct sk_buff *
 sfq_peek(struct Qdisc *sch)
 {
@@ -636,7 +574,6 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = {
 	.enqueue	=	sfq_enqueue,
 	.dequeue	=	sfq_dequeue,
 	.peek		=	sfq_peek,
-	.requeue	=	sfq_requeue,
 	.drop		=	sfq_drop,
 	.init		=	sfq_init,
 	.reset		=	sfq_reset,
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 435076cf620..bb7783d584b 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -139,19 +139,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 	return 0;
 }
 
-static int tbf_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
-	struct tbf_sched_data *q = qdisc_priv(sch);
-	int ret;
-
-	if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
-	}
-
-	return ret;
-}
-
 static unsigned int tbf_drop(struct Qdisc* sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -468,7 +455,6 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
 	.enqueue	=	tbf_enqueue,
 	.dequeue	=	tbf_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.requeue	=	tbf_requeue,
 	.drop		=	tbf_drop,
 	.init		=	tbf_init,
 	.reset		=	tbf_reset,
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index bf03e7fa184..cfc8e7caba6 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -93,16 +93,6 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 	return NET_XMIT_DROP;
 }
 
-static int
-teql_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
-	struct teql_sched_data *q = qdisc_priv(sch);
-
-	__skb_queue_head(&q->q, skb);
-	sch->qstats.requeues++;
-	return 0;
-}
-
 static struct sk_buff *
 teql_dequeue(struct Qdisc* sch)
 {
@@ -441,7 +431,6 @@ static __init void teql_master_setup(struct net_device *dev)
 	ops->enqueue	=	teql_enqueue;
 	ops->dequeue	=	teql_dequeue;
 	ops->peek	=	teql_peek;
-	ops->requeue	=	teql_requeue;
 	ops->init	=	teql_qdisc_init;
 	ops->reset	=	teql_reset;
 	ops->destroy	=	teql_destroy;
-- 
cgit v1.2.3-70-g09d2


From d314774cf2cd5dfeb39a00d37deee65d4c627927 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Wed, 19 Nov 2008 21:32:24 -0800
Subject: netdev: network device operations infrastructure

This patch changes the network device internal API to move adminstrative
operations out of the network device structure and into a separate structure.

This patch involves some hackery to maintain compatablity between the
new and old model, so all 300+ drivers don't have to be changed at once.
For drivers that aren't converted yet, the netdevice_ops virt function list
still resides in the net_device structure. For old protocols, the new
net_device_ops are copied out to the old net_device pointers.

After the transistion is completed the nag message can be changed to
an WARN_ON, and the compatiablity code can be made configurable.

Some function pointers aren't moved:
* destructor can't be in net_device_ops because
  it may need to be referenced after the module is unloaded.
* neighbor setup is manipulated in a couple of places that need special
  consideration
* hard_start_xmit is in the fast path for transmit.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 232 +++++++++++++++++++++++++++++++++-------------
 net/Kconfig               |   3 +
 net/core/dev.c            | 109 +++++++++++++++-------
 net/core/netpoll.c        |   7 +-
 net/core/rtnetlink.c      |   9 +-
 net/sched/sch_generic.c   |   4 +-
 6 files changed, 259 insertions(+), 105 deletions(-)

(limited to 'net/sched/sch_generic.c')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 12d7f4469dc..9060f5f3517 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -451,6 +451,131 @@ struct netdev_queue {
 	struct Qdisc		*qdisc_sleeping;
 } ____cacheline_aligned_in_smp;
 
+
+/*
+ * This structure defines the management hooks for network devices.
+ * The following hooks can bed defined and are optonal (can be null)
+ * unless otherwise noted.
+ *
+ * int (*ndo_init)(struct net_device *dev);
+ *     This function is called once when network device is registered.
+ *     The network device can use this to any late stage initializaton
+ *     or semantic validattion. It can fail with an error code which will
+ *     be propogated back to register_netdev
+ *
+ * void (*ndo_uninit)(struct net_device *dev);
+ *     This function is called when device is unregistered or when registration
+ *     fails. It is not called if init fails.
+ *
+ * int (*ndo_open)(struct net_device *dev);
+ *     This function is called when network device transistions to the up
+ *     state.
+ *
+ * int (*ndo_stop)(struct net_device *dev);
+ *     This function is called when network device transistions to the down
+ *     state.
+ *
+ * void (*ndo_change_rx_flags)(struct net_device *dev, int flags);
+ *	This function is called to allow device receiver to make
+ *	changes to configuration when multicast or promiscious is enabled.
+ *
+ * void (*ndo_set_rx_mode)(struct net_device *dev);
+ *	This function is called device changes address list filtering.
+ *
+ * void (*ndo_set_multicast_list)(struct net_device *dev);
+ *	This function is called when the multicast address list changes.
+ *
+ * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
+ *	This function  is called when the Media Access Control address
+ *	needs to be changed. If not this interface is not defined, the
+ *	mac address can not be changed.
+ *
+ * int (*ndo_validate_addr)(struct net_device *dev);
+ *	Test if Media Access Control address is valid for the device.
+ *
+ * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
+ *	Called when a user request an ioctl which can't be handled by
+ *	the generic interface code. If not defined ioctl's return
+ *	not supported error code.
+ *
+ * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);
+ *	Used to set network devices bus interface parameters. This interface
+ *	is retained for legacy reason, new devices should use the bus
+ *	interface (PCI) for low level management.
+ *
+ * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);
+ *	Called when a user wants to change the Maximum Transfer Unit
+ *	of a device. If not defined, any request to change MTU will
+ *	will return an error.
+ *
+ * void (*ndo_tx_timeout) (struct net_device *dev);
+ *	Callback uses when the transmitter has not made any progress
+ *	for dev->watchdog ticks.
+ *
+ * struct net_device_stats* (*get_stats)(struct net_device *dev);
+ *	Called when a user wants to get the network device usage
+ *	statistics. If not defined, the counters in dev->stats will
+ *	be used.
+ *
+ * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp);
+ *	If device support VLAN receive accleration
+ *	(ie. dev->features & NETIF_F_HW_VLAN_RX), then this function is called
+ *	when vlan groups for the device changes.  Note: grp is NULL
+ *	if no vlan's groups are being used.
+ *
+ * void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
+ *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
+ *	this function is called when a VLAN id is registered.
+ *
+ * void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
+ *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
+ *	this function is called when a VLAN id is unregistered.
+ *
+ * void (*ndo_poll_controller)(struct net_device *dev);
+ */
+struct net_device_ops {
+	int			(*ndo_init)(struct net_device *dev);
+	void			(*ndo_uninit)(struct net_device *dev);
+	int			(*ndo_open)(struct net_device *dev);
+	int			(*ndo_stop)(struct net_device *dev);
+#define HAVE_CHANGE_RX_FLAGS
+	void			(*ndo_change_rx_flags)(struct net_device *dev,
+						       int flags);
+#define HAVE_SET_RX_MODE
+	void			(*ndo_set_rx_mode)(struct net_device *dev);
+#define HAVE_MULTICAST
+	void			(*ndo_set_multicast_list)(struct net_device *dev);
+#define HAVE_SET_MAC_ADDR
+	int			(*ndo_set_mac_address)(struct net_device *dev,
+						       void *addr);
+#define HAVE_VALIDATE_ADDR
+	int			(*ndo_validate_addr)(struct net_device *dev);
+#define HAVE_PRIVATE_IOCTL
+	int			(*ndo_do_ioctl)(struct net_device *dev,
+					        struct ifreq *ifr, int cmd);
+#define HAVE_SET_CONFIG
+	int			(*ndo_set_config)(struct net_device *dev,
+					          struct ifmap *map);
+#define HAVE_CHANGE_MTU
+	int			(*ndo_change_mtu)(struct net_device *dev, int new_mtu);
+
+#define HAVE_TX_TIMEOUT
+	void			(*ndo_tx_timeout) (struct net_device *dev);
+
+	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
+
+	void			(*ndo_vlan_rx_register)(struct net_device *dev,
+						        struct vlan_group *grp);
+	void			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
+						       unsigned short vid);
+	void			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
+						        unsigned short vid);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+#define HAVE_NETDEV_POLL
+	void                    (*ndo_poll_controller)(struct net_device *dev);
+#endif
+};
+
 /*
  *	The DEVICE structure.
  *	Actually, this whole structure is a big mistake.  It mixes I/O
@@ -498,11 +623,6 @@ struct net_device
 #ifdef CONFIG_NETPOLL
 	struct list_head	napi_list;
 #endif
-	
-	/* The device initialization function. Called only once. */
-	int			(*init)(struct net_device *dev);
-
-	/* ------- Fields preinitialized in Space.c finish here ------- */
 
 	/* Net device features */
 	unsigned long		features;
@@ -546,15 +666,13 @@ struct net_device
 	 * for all in netdev_increment_features.
 	 */
 #define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
-				 NETIF_F_SG | NETIF_F_HIGHDMA | \
+				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
 				 NETIF_F_FRAGLIST)
 
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;
 	int			iflink;
 
-
-	struct net_device_stats* (*get_stats)(struct net_device *dev);
 	struct net_device_stats	stats;
 
 #ifdef CONFIG_WIRELESS_EXT
@@ -564,18 +682,13 @@ struct net_device
 	/* Instance data managed by the core of Wireless Extensions. */
 	struct iw_public_data *	wireless_data;
 #endif
+	/* Management operations */
+	const struct net_device_ops *netdev_ops;
 	const struct ethtool_ops *ethtool_ops;
 
 	/* Hardware header description */
 	const struct header_ops *header_ops;
 
-	/*
-	 * This marks the end of the "visible" part of the structure. All
-	 * fields hereafter are internal to the system, and may change at
-	 * will (read: may be cleaned up at will).
-	 */
-
-
 	unsigned int		flags;	/* interface flags (a la BSD)	*/
 	unsigned short		gflags;
         unsigned short          priv_flags; /* Like 'flags' but invisible to userspace. */
@@ -634,7 +747,7 @@ struct net_device
 	unsigned long		last_rx;	/* Time of last Rx	*/
 	/* Interface address info used in eth_type_trans() */
 	unsigned char		dev_addr[MAX_ADDR_LEN];	/* hw address, (before bcast 
-							because most packets are unicast) */
+							   because most packets are unicast) */
 
 	unsigned char		broadcast[MAX_ADDR_LEN];	/* hw bcast add	*/
 
@@ -648,6 +761,10 @@ struct net_device
 	/* Number of TX queues currently active in device  */
 	unsigned int		real_num_tx_queues;
 
+	/* Map buffer to appropriate transmit queue */
+	u16			(*select_queue)(struct net_device *dev,
+						struct sk_buff *skb);
+
 	unsigned long		tx_queue_len;	/* Max frames per queue allowed */
 	spinlock_t		tx_global_lock;
 /*
@@ -662,9 +779,6 @@ struct net_device
 	int			watchdog_timeo; /* used by dev_watchdog() */
 	struct timer_list	watchdog_timer;
 
-/*
- * refcnt is a very hot point, so align it on SMP
- */
 	/* Number of references to this device */
 	atomic_t		refcnt ____cacheline_aligned_in_smp;
 
@@ -683,56 +797,14 @@ struct net_device
 	       NETREG_RELEASED,		/* called free_netdev */
 	} reg_state;
 
-	/* Called after device is detached from network. */
-	void			(*uninit)(struct net_device *dev);
-	/* Called after last user reference disappears. */
-	void			(*destructor)(struct net_device *dev);
+	/* Called from unregister, can be used to call free_netdev */
+	void (*destructor)(struct net_device *dev);
 
-	/* Pointers to interface service routines.	*/
-	int			(*open)(struct net_device *dev);
-	int			(*stop)(struct net_device *dev);
-#define HAVE_NETDEV_POLL
-#define HAVE_CHANGE_RX_FLAGS
-	void			(*change_rx_flags)(struct net_device *dev,
-						   int flags);
-#define HAVE_SET_RX_MODE
-	void			(*set_rx_mode)(struct net_device *dev);
-#define HAVE_MULTICAST			 
-	void			(*set_multicast_list)(struct net_device *dev);
-#define HAVE_SET_MAC_ADDR  		 
-	int			(*set_mac_address)(struct net_device *dev,
-						   void *addr);
-#define HAVE_VALIDATE_ADDR
-	int			(*validate_addr)(struct net_device *dev);
-#define HAVE_PRIVATE_IOCTL
-	int			(*do_ioctl)(struct net_device *dev,
-					    struct ifreq *ifr, int cmd);
-#define HAVE_SET_CONFIG
-	int			(*set_config)(struct net_device *dev,
-					      struct ifmap *map);
-#define HAVE_CHANGE_MTU
-	int			(*change_mtu)(struct net_device *dev, int new_mtu);
+	int (*neigh_setup)(struct net_device *dev, struct neigh_parms *);
 
-#define HAVE_TX_TIMEOUT
-	void			(*tx_timeout) (struct net_device *dev);
-
-	void			(*vlan_rx_register)(struct net_device *dev,
-						    struct vlan_group *grp);
-	void			(*vlan_rx_add_vid)(struct net_device *dev,
-						   unsigned short vid);
-	void			(*vlan_rx_kill_vid)(struct net_device *dev,
-						    unsigned short vid);
-
-	int			(*neigh_setup)(struct net_device *dev, struct neigh_parms *);
 #ifdef CONFIG_NETPOLL
 	struct netpoll_info	*npinfo;
 #endif
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	void                    (*poll_controller)(struct net_device *dev);
-#endif
-
-	u16			(*select_queue)(struct net_device *dev,
-						struct sk_buff *skb);
 
 #ifdef CONFIG_NET_NS
 	/* Network namespace this network device is inside */
@@ -763,6 +835,38 @@ struct net_device
 	/* for setting kernel sock attribute on TCP connection setup */
 #define GSO_MAX_SIZE		65536
 	unsigned int		gso_max_size;
+
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
+	struct {
+		int			(*init)(struct net_device *dev);
+		void			(*uninit)(struct net_device *dev);
+		int			(*open)(struct net_device *dev);
+		int			(*stop)(struct net_device *dev);
+		void			(*change_rx_flags)(struct net_device *dev,
+							   int flags);
+		void			(*set_rx_mode)(struct net_device *dev);
+		void			(*set_multicast_list)(struct net_device *dev);
+		int			(*set_mac_address)(struct net_device *dev,
+							   void *addr);
+		int			(*validate_addr)(struct net_device *dev);
+		int			(*do_ioctl)(struct net_device *dev,
+						    struct ifreq *ifr, int cmd);
+		int			(*set_config)(struct net_device *dev,
+						      struct ifmap *map);
+		int			(*change_mtu)(struct net_device *dev, int new_mtu);
+		void			(*tx_timeout) (struct net_device *dev);
+		struct net_device_stats* (*get_stats)(struct net_device *dev);
+		void			(*vlan_rx_register)(struct net_device *dev,
+							    struct vlan_group *grp);
+		void			(*vlan_rx_add_vid)(struct net_device *dev,
+							   unsigned short vid);
+		void			(*vlan_rx_kill_vid)(struct net_device *dev,
+							    unsigned short vid);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+		void                    (*poll_controller)(struct net_device *dev);
+#endif
+#endif
+	};
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/net/Kconfig b/net/Kconfig
index 8c3d97ca0d9..4e2e40ba8ba 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -32,6 +32,9 @@ config NET_NS
 	  Allow user space to create what appear to be multiple instances
 	  of the network stack.
 
+config COMPAT_NET_DEV_OPS
+       def_bool y
+
 source "net/packet/Kconfig"
 source "net/unix/Kconfig"
 source "net/xfrm/Kconfig"
diff --git a/net/core/dev.c b/net/core/dev.c
index e08c0fcd603..ca14ab407b3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1059,6 +1059,7 @@ void dev_load(struct net *net, const char *name)
  */
 int dev_open(struct net_device *dev)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	int ret = 0;
 
 	ASSERT_RTNL();
@@ -1081,11 +1082,11 @@ int dev_open(struct net_device *dev)
 	 */
 	set_bit(__LINK_STATE_START, &dev->state);
 
-	if (dev->validate_addr)
-		ret = dev->validate_addr(dev);
+	if (ops->ndo_validate_addr)
+		ret = ops->ndo_validate_addr(dev);
 
-	if (!ret && dev->open)
-		ret = dev->open(dev);
+	if (!ret && ops->ndo_open)
+		ret = ops->ndo_open(dev);
 
 	/*
 	 *	If it went open OK then:
@@ -1129,6 +1130,7 @@ int dev_open(struct net_device *dev)
  */
 int dev_close(struct net_device *dev)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	ASSERT_RTNL();
 
 	might_sleep();
@@ -1161,8 +1163,8 @@ int dev_close(struct net_device *dev)
 	 *	We allow it to be called even after a DETACH hot-plug
 	 *	event.
 	 */
-	if (dev->stop)
-		dev->stop(dev);
+	if (ops->ndo_stop)
+		ops->ndo_stop(dev);
 
 	/*
 	 *	Device is now down.
@@ -2930,8 +2932,10 @@ int netdev_set_master(struct net_device *slave, struct net_device *master)
 
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
-	if (dev->flags & IFF_UP && dev->change_rx_flags)
-		dev->change_rx_flags(dev, flags);
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+		ops->ndo_change_rx_flags(dev, flags);
 }
 
 static int __dev_set_promiscuity(struct net_device *dev, int inc)
@@ -3051,6 +3055,8 @@ int dev_set_allmulti(struct net_device *dev, int inc)
  */
 void __dev_set_rx_mode(struct net_device *dev)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
+
 	/* dev_open will call this function so the list will stay sane. */
 	if (!(dev->flags&IFF_UP))
 		return;
@@ -3058,8 +3064,8 @@ void __dev_set_rx_mode(struct net_device *dev)
 	if (!netif_device_present(dev))
 		return;
 
-	if (dev->set_rx_mode)
-		dev->set_rx_mode(dev);
+	if (ops->ndo_set_rx_mode)
+		ops->ndo_set_rx_mode(dev);
 	else {
 		/* Unicast addresses changes may only happen under the rtnl,
 		 * therefore calling __dev_set_promiscuity here is safe.
@@ -3072,8 +3078,8 @@ void __dev_set_rx_mode(struct net_device *dev)
 			dev->uc_promisc = 0;
 		}
 
-		if (dev->set_multicast_list)
-			dev->set_multicast_list(dev);
+		if (ops->ndo_set_multicast_list)
+			ops->ndo_set_multicast_list(dev);
 	}
 }
 
@@ -3432,6 +3438,7 @@ int dev_change_flags(struct net_device *dev, unsigned flags)
  */
 int dev_set_mtu(struct net_device *dev, int new_mtu)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
 
 	if (new_mtu == dev->mtu)
@@ -3445,10 +3452,11 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 		return -ENODEV;
 
 	err = 0;
-	if (dev->change_mtu)
-		err = dev->change_mtu(dev, new_mtu);
+	if (ops->ndo_change_mtu)
+		err = ops->ndo_change_mtu(dev, new_mtu);
 	else
 		dev->mtu = new_mtu;
+
 	if (!err && dev->flags & IFF_UP)
 		call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
 	return err;
@@ -3463,15 +3471,16 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
  */
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
 
-	if (!dev->set_mac_address)
+	if (!ops->ndo_set_mac_address)
 		return -EOPNOTSUPP;
 	if (sa->sa_family != dev->type)
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
-	err = dev->set_mac_address(dev, sa);
+	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 	return err;
@@ -3551,6 +3560,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 {
 	int err;
 	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+	const struct net_device_ops *ops = dev->netdev_ops;
 
 	if (!dev)
 		return -ENODEV;
@@ -3578,15 +3588,15 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 			return 0;
 
 		case SIOCSIFMAP:
-			if (dev->set_config) {
+			if (ops->ndo_set_config) {
 				if (!netif_device_present(dev))
 					return -ENODEV;
-				return dev->set_config(dev, &ifr->ifr_map);
+				return ops->ndo_set_config(dev, &ifr->ifr_map);
 			}
 			return -EOPNOTSUPP;
 
 		case SIOCADDMULTI:
-			if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+			if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
 			    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
 				return -EINVAL;
 			if (!netif_device_present(dev))
@@ -3595,7 +3605,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 					  dev->addr_len, 1);
 
 		case SIOCDELMULTI:
-			if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+			if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
 			    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
 				return -EINVAL;
 			if (!netif_device_present(dev))
@@ -3633,10 +3643,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 			    cmd == SIOCBRDELIF ||
 			    cmd == SIOCWANDEV) {
 				err = -EOPNOTSUPP;
-				if (dev->do_ioctl) {
+				if (ops->ndo_do_ioctl) {
 					if (netif_device_present(dev))
-						err = dev->do_ioctl(dev, ifr,
-								    cmd);
+						err = ops->ndo_do_ioctl(dev, ifr, cmd);
 					else
 						err = -ENODEV;
 				}
@@ -3897,8 +3906,8 @@ static void rollback_registered(struct net_device *dev)
 	 */
 	dev_addr_discard(dev);
 
-	if (dev->uninit)
-		dev->uninit(dev);
+	if (dev->netdev_ops->ndo_uninit)
+		dev->netdev_ops->ndo_uninit(dev);
 
 	/* Notifier chain MUST detach us from master device. */
 	WARN_ON(dev->master);
@@ -3988,7 +3997,7 @@ int register_netdevice(struct net_device *dev)
 	struct hlist_head *head;
 	struct hlist_node *p;
 	int ret;
-	struct net *net;
+	struct net *net = dev_net(dev);
 
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();
@@ -3997,8 +4006,7 @@ int register_netdevice(struct net_device *dev)
 
 	/* When net_device's are persistent, this will be fatal. */
 	BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
-	BUG_ON(!dev_net(dev));
-	net = dev_net(dev);
+	BUG_ON(!net);
 
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
@@ -4006,9 +4014,46 @@ int register_netdevice(struct net_device *dev)
 
 	dev->iflink = -1;
 
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
+	/* Netdevice_ops API compatiability support.
+	 * This is temporary until all network devices are converted.
+	 */
+	if (dev->netdev_ops) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		dev->init = ops->ndo_init;
+		dev->uninit = ops->ndo_uninit;
+		dev->open = ops->ndo_open;
+		dev->change_rx_flags = ops->ndo_change_rx_flags;
+		dev->set_rx_mode = ops->ndo_set_rx_mode;
+		dev->set_multicast_list = ops->ndo_set_multicast_list;
+		dev->set_mac_address = ops->ndo_set_mac_address;
+		dev->validate_addr = ops->ndo_validate_addr;
+		dev->do_ioctl = ops->ndo_do_ioctl;
+		dev->set_config = ops->ndo_set_config;
+		dev->change_mtu = ops->ndo_change_mtu;
+		dev->tx_timeout = ops->ndo_tx_timeout;
+		dev->get_stats = ops->ndo_get_stats;
+		dev->vlan_rx_register = ops->ndo_vlan_rx_register;
+		dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
+		dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+		dev->poll_controller = ops->ndo_poll_controller;
+#endif
+	} else {
+		char drivername[64];
+		pr_info("%s (%s): not using net_device_ops yet\n",
+			dev->name, netdev_drivername(dev, drivername, 64));
+
+		/* This works only because net_device_ops and the
+		   compatiablity structure are the same. */
+		dev->netdev_ops = (void *) &(dev->init);
+	}
+#endif
+
 	/* Init, if this function is available */
-	if (dev->init) {
-		ret = dev->init(dev);
+	if (dev->netdev_ops->ndo_init) {
+		ret = dev->netdev_ops->ndo_init(dev);
 		if (ret) {
 			if (ret > 0)
 				ret = -EIO;
@@ -4086,8 +4131,8 @@ out:
 	return ret;
 
 err_uninit:
-	if (dev->uninit)
-		dev->uninit(dev);
+	if (dev->netdev_ops->ndo_uninit)
+		dev->netdev_ops->ndo_uninit(dev);
 	goto out;
 }
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index fc4e28e23b8..630df603444 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -172,12 +172,13 @@ static void service_arp_queue(struct netpoll_info *npi)
 void netpoll_poll(struct netpoll *np)
 {
 	struct net_device *dev = np->dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
 
-	if (!dev || !netif_running(dev) || !dev->poll_controller)
+	if (!dev || !netif_running(dev) || !ops->ndo_poll_controller)
 		return;
 
 	/* Process pending work on NIC */
-	dev->poll_controller(dev);
+	ops->ndo_poll_controller(dev);
 
 	poll_napi(dev);
 
@@ -694,7 +695,7 @@ int netpoll_setup(struct netpoll *np)
 		atomic_inc(&npinfo->refcnt);
 	}
 
-	if (!ndev->poll_controller) {
+	if (!ndev->netdev_ops->ndo_poll_controller) {
 		printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n",
 		       np->name, np->dev_name);
 		err = -ENOTSUPP;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4dfb6b4d455..6f8e0778e56 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -762,6 +762,7 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	int send_addr_notify = 0;
 	int err;
 
@@ -783,7 +784,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		struct rtnl_link_ifmap *u_map;
 		struct ifmap k_map;
 
-		if (!dev->set_config) {
+		if (!ops->ndo_set_config) {
 			err = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -801,7 +802,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		k_map.dma = (unsigned char) u_map->dma;
 		k_map.port = (unsigned char) u_map->port;
 
-		err = dev->set_config(dev, &k_map);
+		err = ops->ndo_set_config(dev, &k_map);
 		if (err < 0)
 			goto errout;
 
@@ -812,7 +813,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		struct sockaddr *sa;
 		int len;
 
-		if (!dev->set_mac_address) {
+		if (!ops->ndo_set_mac_address) {
 			err = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -831,7 +832,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		sa->sa_family = dev->type;
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		err = dev->set_mac_address(dev, sa);
+		err = ops->ndo_set_mac_address(dev, sa);
 		kfree(sa);
 		if (err)
 			goto errout;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 80c8f3dbbea..95ab55c064f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -224,7 +224,7 @@ static void dev_watchdog(unsigned long arg)
 				char drivername[64];
 				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n",
 				       dev->name, netdev_drivername(dev, drivername, 64));
-				dev->tx_timeout(dev);
+				dev->netdev_ops->ndo_tx_timeout(dev);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
 				       round_jiffies(jiffies +
@@ -239,7 +239,7 @@ static void dev_watchdog(unsigned long arg)
 
 void __netdev_watchdog_up(struct net_device *dev)
 {
-	if (dev->tx_timeout) {
+	if (dev->netdev_ops->ndo_tx_timeout) {
 		if (dev->watchdog_timeo <= 0)
 			dev->watchdog_timeo = 5*HZ;
 		if (!mod_timer(&dev->watchdog_timer,
-- 
cgit v1.2.3-70-g09d2