Auto merge with /home/aegl/GIT/linus

6 files changed, 381 insertions, 146 deletions

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index b0941186f867..b22c9beb604d 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -405,7 +405,7 @@ config NET_EMATCH_STACK
 	---help---
 	  Size of the local stack variable used while evaluating the tree of
 	  ematches. Limits the depth of the tree, i.e. the number of
-	  encapsulated precedences. Every level requires 4 bytes of addtional
+	  encapsulated precedences. Every level requires 4 bytes of additional
 	  stack space.
 
 config NET_EMATCH_CMP
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index cafcb084098d..914c85ff8fe6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -881,7 +881,7 @@ static int __init tc_action_init(void)
 		link_p[RTM_GETACTION-RTM_BASE].dumpit = tc_dump_action;
 	}
 
-	printk("TC classifier action (bugs to netdev@oss.sgi.com cc "
+	printk("TC classifier action (bugs to netdev@vger.kernel.org cc "
 	       "hadi@cyberus.ca)\n");
 	return 0;
 }
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 0d2d4415f334..dfb300bb6baa 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -261,6 +261,9 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh,
 	rta = (struct rtattr *) b;
 	RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
 
+	if (f->res.classid)
+		RTA_PUT(skb, TCA_BASIC_CLASSID, sizeof(u32), &f->res.classid);
+
 	if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 ||
 	    tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0)
 		goto rtattr_failure;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index f1eeaf65cee5..48bb23c2a35a 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -32,7 +32,7 @@
  * 	      +-----------+                           +-----------+
  * 	            |                                       |
  * 	            ---> meta_ops[INT][INDEV](...)          |
- *                            |                            |
+ *	                      |                             |
  * 	            -----------                             |
  * 	            V                                       V
  * 	      +-----------+                           +-----------+
@@ -70,6 +70,7 @@
 #include <net/dst.h>
 #include <net/route.h>
 #include <net/pkt_cls.h>
+#include <net/sock.h>
 
 struct meta_obj
 {
@@ -284,6 +285,214 @@ META_COLLECTOR(int_rtiif)
 }
 
 /**************************************************************************
+ * Socket Attributes
+ **************************************************************************/
+
+#define SKIP_NONLOCAL(skb)			\
+	if (unlikely(skb->sk == NULL)) {	\
+		*err = -1;			\
+		return;				\
+	}
+
+META_COLLECTOR(int_sk_family)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_family;
+}
+
+META_COLLECTOR(int_sk_state)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_state;
+}
+
+META_COLLECTOR(int_sk_reuse)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_reuse;
+}
+
+META_COLLECTOR(int_sk_bound_if)
+{
+	SKIP_NONLOCAL(skb);
+	/* No error if bound_dev_if is 0, legal userspace check */
+	dst->value = skb->sk->sk_bound_dev_if;
+}
+
+META_COLLECTOR(var_sk_bound_if)
+{
+	SKIP_NONLOCAL(skb);
+
+	 if (skb->sk->sk_bound_dev_if == 0) {
+		dst->value = (unsigned long) "any";
+		dst->len = 3;
+	 } else  {
+		struct net_device *dev;
+		
+		dev = dev_get_by_index(skb->sk->sk_bound_dev_if);
+		*err = var_dev(dev, dst);
+		if (dev)
+			dev_put(dev);
+	 }
+}
+
+META_COLLECTOR(int_sk_refcnt)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_refcnt);
+}
+
+META_COLLECTOR(int_sk_rcvbuf)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvbuf;
+}
+
+META_COLLECTOR(int_sk_shutdown)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_shutdown;
+}
+
+META_COLLECTOR(int_sk_proto)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_protocol;
+}
+
+META_COLLECTOR(int_sk_type)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_type;
+}
+
+META_COLLECTOR(int_sk_rmem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_rmem_alloc);
+}
+
+META_COLLECTOR(int_sk_wmem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_wmem_alloc);
+}
+
+META_COLLECTOR(int_sk_omem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_omem_alloc);
+}
+
+META_COLLECTOR(int_sk_rcv_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_receive_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_snd_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_write_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_wmem_queued)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_wmem_queued;
+}
+
+META_COLLECTOR(int_sk_fwd_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_forward_alloc;
+}
+
+META_COLLECTOR(int_sk_sndbuf)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndbuf;
+}
+
+META_COLLECTOR(int_sk_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_allocation;
+}
+
+META_COLLECTOR(int_sk_route_caps)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_route_caps;
+}
+
+META_COLLECTOR(int_sk_hashent)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_hashent;
+}
+
+META_COLLECTOR(int_sk_lingertime)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_lingertime / HZ;
+}
+
+META_COLLECTOR(int_sk_err_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_error_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_ack_bl)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_ack_backlog;
+}
+
+META_COLLECTOR(int_sk_max_ack_bl)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_max_ack_backlog;
+}
+
+META_COLLECTOR(int_sk_prio)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_priority;
+}
+
+META_COLLECTOR(int_sk_rcvlowat)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvlowat;
+}
+
+META_COLLECTOR(int_sk_rcvtimeo)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvtimeo / HZ;
+}
+
+META_COLLECTOR(int_sk_sndtimeo)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndtimeo / HZ;
+}
+
+META_COLLECTOR(int_sk_sendmsg_off)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndmsg_off;
+}
+
+META_COLLECTOR(int_sk_write_pend)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_write_pending;
+}
+
+/**************************************************************************
  * Meta value collectors assignment table
  **************************************************************************/
 
@@ -293,41 +502,75 @@ struct meta_ops
 			       struct meta_value *, struct meta_obj *, int *);
 };
 
+#define META_ID(name) TCF_META_ID_##name
+#define META_FUNC(name) { .get = meta_##name }
+
 /* Meta value operations table listing all meta value collectors and
  * assigns them to a type and meta id. */
 static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = {
 	[TCF_META_TYPE_VAR] = {
-		[TCF_META_ID_DEV]	= { .get = meta_var_dev },
-		[TCF_META_ID_INDEV]	= { .get = meta_var_indev },
-		[TCF_META_ID_REALDEV]	= { .get = meta_var_realdev }
+		[META_ID(DEV)]			= META_FUNC(var_dev),
+		[META_ID(INDEV)]		= META_FUNC(var_indev),
+		[META_ID(REALDEV)]		= META_FUNC(var_realdev),
+		[META_ID(SK_BOUND_IF)] 		= META_FUNC(var_sk_bound_if),
 	},
 	[TCF_META_TYPE_INT] = {
-		[TCF_META_ID_RANDOM]	= { .get = meta_int_random },
-		[TCF_META_ID_LOADAVG_0]	= { .get = meta_int_loadavg_0 },
-		[TCF_META_ID_LOADAVG_1]	= { .get = meta_int_loadavg_1 },
-		[TCF_META_ID_LOADAVG_2]	= { .get = meta_int_loadavg_2 },
-		[TCF_META_ID_DEV]	= { .get = meta_int_dev },
-		[TCF_META_ID_INDEV]	= { .get = meta_int_indev },
-		[TCF_META_ID_REALDEV]	= { .get = meta_int_realdev },
-		[TCF_META_ID_PRIORITY]	= { .get = meta_int_priority },
-		[TCF_META_ID_PROTOCOL]	= { .get = meta_int_protocol },
-		[TCF_META_ID_SECURITY]	= { .get = meta_int_security },
-		[TCF_META_ID_PKTTYPE]	= { .get = meta_int_pkttype },
-		[TCF_META_ID_PKTLEN]	= { .get = meta_int_pktlen },
-		[TCF_META_ID_DATALEN]	= { .get = meta_int_datalen },
-		[TCF_META_ID_MACLEN]	= { .get = meta_int_maclen },
+		[META_ID(RANDOM)]		= META_FUNC(int_random),
+		[META_ID(LOADAVG_0)]		= META_FUNC(int_loadavg_0),
+		[META_ID(LOADAVG_1)]		= META_FUNC(int_loadavg_1),
+		[META_ID(LOADAVG_2)]		= META_FUNC(int_loadavg_2),
+		[META_ID(DEV)]			= META_FUNC(int_dev),
+		[META_ID(INDEV)]		= META_FUNC(int_indev),
+		[META_ID(REALDEV)]		= META_FUNC(int_realdev),
+		[META_ID(PRIORITY)]		= META_FUNC(int_priority),
+		[META_ID(PROTOCOL)]		= META_FUNC(int_protocol),
+		[META_ID(SECURITY)]		= META_FUNC(int_security),
+		[META_ID(PKTTYPE)]		= META_FUNC(int_pkttype),
+		[META_ID(PKTLEN)]		= META_FUNC(int_pktlen),
+		[META_ID(DATALEN)]		= META_FUNC(int_datalen),
+		[META_ID(MACLEN)]		= META_FUNC(int_maclen),
 #ifdef CONFIG_NETFILTER
-		[TCF_META_ID_NFMARK]	= { .get = meta_int_nfmark },
+		[META_ID(NFMARK)]		= META_FUNC(int_nfmark),
 #endif
-		[TCF_META_ID_TCINDEX]	= { .get = meta_int_tcindex },
+		[META_ID(TCINDEX)]		= META_FUNC(int_tcindex),
 #ifdef CONFIG_NET_CLS_ACT
-		[TCF_META_ID_TCVERDICT]	= { .get = meta_int_tcverd },
-		[TCF_META_ID_TCCLASSID]	= { .get = meta_int_tcclassid },
+		[META_ID(TCVERDICT)]		= META_FUNC(int_tcverd),
+		[META_ID(TCCLASSID)]		= META_FUNC(int_tcclassid),
 #endif
 #ifdef CONFIG_NET_CLS_ROUTE
-		[TCF_META_ID_RTCLASSID]	= { .get = meta_int_rtclassid },
+		[META_ID(RTCLASSID)]		= META_FUNC(int_rtclassid),
 #endif
-		[TCF_META_ID_RTIIF]	= { .get = meta_int_rtiif }
+		[META_ID(RTIIF)]		= META_FUNC(int_rtiif),
+		[META_ID(SK_FAMILY)]		= META_FUNC(int_sk_family),
+		[META_ID(SK_STATE)]		= META_FUNC(int_sk_state),
+		[META_ID(SK_REUSE)]		= META_FUNC(int_sk_reuse),
+		[META_ID(SK_BOUND_IF)]		= META_FUNC(int_sk_bound_if),
+		[META_ID(SK_REFCNT)]		= META_FUNC(int_sk_refcnt),
+		[META_ID(SK_RCVBUF)]		= META_FUNC(int_sk_rcvbuf),
+		[META_ID(SK_SNDBUF)]		= META_FUNC(int_sk_sndbuf),
+		[META_ID(SK_SHUTDOWN)]		= META_FUNC(int_sk_shutdown),
+		[META_ID(SK_PROTO)]		= META_FUNC(int_sk_proto),
+		[META_ID(SK_TYPE)]		= META_FUNC(int_sk_type),
+		[META_ID(SK_RMEM_ALLOC)]	= META_FUNC(int_sk_rmem_alloc),
+		[META_ID(SK_WMEM_ALLOC)]	= META_FUNC(int_sk_wmem_alloc),
+		[META_ID(SK_OMEM_ALLOC)]	= META_FUNC(int_sk_omem_alloc),
+		[META_ID(SK_WMEM_QUEUED)]	= META_FUNC(int_sk_wmem_queued),
+		[META_ID(SK_RCV_QLEN)]		= META_FUNC(int_sk_rcv_qlen),
+		[META_ID(SK_SND_QLEN)]		= META_FUNC(int_sk_snd_qlen),
+		[META_ID(SK_ERR_QLEN)]		= META_FUNC(int_sk_err_qlen),
+		[META_ID(SK_FORWARD_ALLOCS)]	= META_FUNC(int_sk_fwd_alloc),
+		[META_ID(SK_ALLOCS)]		= META_FUNC(int_sk_alloc),
+		[META_ID(SK_ROUTE_CAPS)]	= META_FUNC(int_sk_route_caps),
+		[META_ID(SK_HASHENT)]		= META_FUNC(int_sk_hashent),
+		[META_ID(SK_LINGERTIME)]	= META_FUNC(int_sk_lingertime),
+		[META_ID(SK_ACK_BACKLOG)]	= META_FUNC(int_sk_ack_bl),
+		[META_ID(SK_MAX_ACK_BACKLOG)]	= META_FUNC(int_sk_max_ack_bl),
+		[META_ID(SK_PRIO)]		= META_FUNC(int_sk_prio),
+		[META_ID(SK_RCVLOWAT)]		= META_FUNC(int_sk_rcvlowat),
+		[META_ID(SK_RCVTIMEO)]		= META_FUNC(int_sk_rcvtimeo),
+		[META_ID(SK_SNDTIMEO)]		= META_FUNC(int_sk_sndtimeo),
+		[META_ID(SK_SENDMSG_OFF)]	= META_FUNC(int_sk_sendmsg_off),
+		[META_ID(SK_WRITE_PENDING)]	= META_FUNC(int_sk_write_pend),
 	}
 };
 
@@ -396,9 +639,9 @@ static int meta_int_compare(struct meta_obj *a, struct meta_obj *b)
 	/* Let gcc optimize it, the unlikely is not really based on
 	 * some numbers but jump free code for mismatches seems
 	 * more logical. */
-	if (unlikely(a == b))
+	if (unlikely(a->value == b->value))
 		return 0;
-	else if (a < b)
+	else if (a->value < b->value)
 		return -1;
 	else
 		return 1;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 8a3db9d95bab..d8bd2a569c7c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -18,7 +18,7 @@
 #include <asm/byteorder.h>
 
 
-#if 1 /* control */
+#if 0 /* control */
 #define DPRINTK(format,args...) printk(KERN_DEBUG format,##args)
 #else
 #define DPRINTK(format,args...)
@@ -73,8 +73,13 @@ static int dsmark_graft(struct Qdisc *sch,unsigned long arg,
 
 	DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n",sch,p,new,
 	    old);
-	if (!new)
-		new = &noop_qdisc;
+
+	if (new == NULL) {
+		new = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
+		if (new == NULL)
+			new = &noop_qdisc;
+	}
+
 	sch_tree_lock(sch);
 	*old = xchg(&p->q,new);
 	if (*old)
@@ -163,14 +168,15 @@ static void dsmark_walk(struct Qdisc *sch,struct qdisc_walker *walker)
 		return;
 	for (i = 0; i < p->indices; i++) {
 		if (p->mask[i] == 0xff && !p->value[i])
-			continue;
+			goto ignore;
 		if (walker->count >= walker->skip) {
 			if (walker->fn(sch, i+1, walker) < 0) {
 				walker->stop = 1;
 				break;
 			}
 		}
-                walker->count++;
+ignore:		
+		walker->count++;
         }
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index e0c9fbe73b15..bb9bf8d5003c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -53,7 +53,6 @@
 
 struct netem_sched_data {
 	struct Qdisc	*qdisc;
-	struct sk_buff_head delayed;
 	struct timer_list timer;
 
 	u32 latency;
@@ -63,11 +62,12 @@ struct netem_sched_data {
 	u32 gap;
 	u32 jitter;
 	u32 duplicate;
+	u32 reorder;
 
 	struct crndstate {
 		unsigned long last;
 		unsigned long rho;
-	} delay_cor, loss_cor, dup_cor;
+	} delay_cor, loss_cor, dup_cor, reorder_cor;
 
 	struct disttable {
 		u32  size;
@@ -137,122 +137,68 @@ static long tabledist(unsigned long mu, long sigma,
 	return  x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu;
 }
 
-/* Put skb in the private delayed queue. */
-static int netem_delay(struct Qdisc *sch, struct sk_buff *skb)
-{
-	struct netem_sched_data *q = qdisc_priv(sch);
-	psched_tdiff_t td;
-	psched_time_t now;
-	
-	PSCHED_GET_TIME(now);
-	td = tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist);
-	
-	/* Always queue at tail to keep packets in order */
-	if (likely(q->delayed.qlen < q->limit)) {
-		struct netem_skb_cb *cb = (struct netem_skb_cb *)skb->cb;
-	
-		PSCHED_TADD2(now, td, cb->time_to_send);
-
-		pr_debug("netem_delay: skb=%p now=%llu tosend=%llu\n", skb, 
-			 now, cb->time_to_send);
-	
-		__skb_queue_tail(&q->delayed, skb);
-		return NET_XMIT_SUCCESS;
-	}
-
-	pr_debug("netem_delay: queue over limit %d\n", q->limit);
-	sch->qstats.overlimits++;
-	kfree_skb(skb);
-	return NET_XMIT_DROP;
-}
-
 /*
- *  Move a packet that is ready to send from the delay holding
- *  list to the underlying qdisc.
+ * Insert one skb into qdisc.
+ * Note: parent depends on return value to account for queue length.
+ * 	NET_XMIT_DROP: queue length didn't change.
+ *      NET_XMIT_SUCCESS: one skb was queued.
  */
-static int netem_run(struct Qdisc *sch)
-{
-	struct netem_sched_data *q = qdisc_priv(sch);
-	struct sk_buff *skb;
-	psched_time_t now;
-
-	PSCHED_GET_TIME(now);
-
-	skb = skb_peek(&q->delayed);
-	if (skb) {
-		const struct netem_skb_cb *cb
-			= (const struct netem_skb_cb *)skb->cb;
-		long delay 
-			= PSCHED_US2JIFFIE(PSCHED_TDIFF(cb->time_to_send, now));
-		pr_debug("netem_run: skb=%p delay=%ld\n", skb, delay);
-
-		/* if more time remaining? */
-		if (delay > 0) {
-			mod_timer(&q->timer, jiffies + delay);
-			return 1;
-		}
-
-		__skb_unlink(skb, &q->delayed);
-		
-		if (q->qdisc->enqueue(skb, q->qdisc)) {
-			sch->q.qlen--;
-			sch->qstats.drops++;
-		} 
-	}
-
-	return 0;
-}
-
 static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
+	struct netem_skb_cb *cb = (struct netem_skb_cb *)skb->cb;
+	struct sk_buff *skb2;
 	int ret;
+	int count = 1;
 
 	pr_debug("netem_enqueue skb=%p\n", skb);
 
+	/* Random duplication */
+	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+		++count;
+
 	/* Random packet drop 0 => none, ~0 => all */
-	if (q->loss && q->loss >= get_crandom(&q->loss_cor)) {
-		pr_debug("netem_enqueue: random loss\n");
+	if (q->loss && q->loss >= get_crandom(&q->loss_cor))
+		--count;
+
+	if (count == 0) {
 		sch->qstats.drops++;
 		kfree_skb(skb);
-		return 0;	/* lie about loss so TCP doesn't know */
+		return NET_XMIT_DROP;
 	}
 
-	/* Random duplication */
-	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_clone(skb, GFP_ATOMIC);
-		if (skb2 && netem_delay(sch, skb2) == NET_XMIT_SUCCESS) {
-			struct Qdisc *qp;
-
-			/* Since one packet can generate two packets in the
-			 * queue, the parent's qlen accounting gets confused,
-			 * so fix it.
-			 */
-			qp = qdisc_lookup(sch->dev, TC_H_MAJ(sch->parent));
-			if (qp)
-				qp->q.qlen++;
-
-			sch->q.qlen++;
-			sch->bstats.bytes += skb2->len;
-			sch->bstats.packets++;
-		} else
-			sch->qstats.drops++;
+	/*
+	 * If we need to duplicate packet, then re-insert at top of the
+	 * qdisc tree, since parent queuer expects that only one
+	 * skb will be queued.
+	 */
+	if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
+		struct Qdisc *rootq = sch->dev->qdisc;
+		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
+		q->duplicate = 0;
+
+		rootq->enqueue(skb2, rootq);
+		q->duplicate = dupsave;
 	}
 
-	/* If doing simple delay then gap == 0 so all packets
-	 * go into the delayed holding queue
-	 * otherwise if doing out of order only "1 out of gap"
-	 * packets will be delayed.
-	 */
-	if (q->counter < q->gap) {
+	if (q->gap == 0 		/* not doing reordering */
+	    || q->counter < q->gap 	/* inside last reordering gap */
+	    || q->reorder < get_crandom(&q->reorder_cor)) {
+		psched_time_t now;
+		PSCHED_GET_TIME(now);
+		PSCHED_TADD2(now, tabledist(q->latency, q->jitter, 
+					    &q->delay_cor, q->delay_dist),
+			     cb->time_to_send);
 		++q->counter;
 		ret = q->qdisc->enqueue(skb, q->qdisc);
 	} else {
+		/* 
+		 * Do re-ordering by putting one out of N packets at the front
+		 * of the queue.
+		 */
+		PSCHED_GET_TIME(cb->time_to_send);
 		q->counter = 0;
-		ret = netem_delay(sch, skb);
-		netem_run(sch);
+		ret = q->qdisc->ops->requeue(skb, q->qdisc);
 	}
 
 	if (likely(ret == NET_XMIT_SUCCESS)) {
@@ -296,22 +242,33 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
-	int pending;
-
-	pending = netem_run(sch);
 
 	skb = q->qdisc->dequeue(q->qdisc);
 	if (skb) {
-		pr_debug("netem_dequeue: return skb=%p\n", skb);
-		sch->q.qlen--;
-		sch->flags &= ~TCQ_F_THROTTLED;
-	}
-	else if (pending) {
-		pr_debug("netem_dequeue: throttling\n");
+		const struct netem_skb_cb *cb
+			= (const struct netem_skb_cb *)skb->cb;
+		psched_time_t now;
+		long delay;
+
+		/* if more time remaining? */
+		PSCHED_GET_TIME(now);
+		delay = PSCHED_US2JIFFIE(PSCHED_TDIFF(cb->time_to_send, now));
+		pr_debug("netem_run: skb=%p delay=%ld\n", skb, delay);
+		if (delay <= 0) {
+			pr_debug("netem_dequeue: return skb=%p\n", skb);
+			sch->q.qlen--;
+			sch->flags &= ~TCQ_F_THROTTLED;
+			return skb;
+		}
+
+		mod_timer(&q->timer, jiffies + delay);
 		sch->flags |= TCQ_F_THROTTLED;
-	} 
 
-	return skb;
+		if (q->qdisc->ops->requeue(skb, q->qdisc) != 0)
+			sch->qstats.drops++;
+	}
+
+	return NULL;
 }
 
 static void netem_watchdog(unsigned long arg)
@@ -328,8 +285,6 @@ static void netem_reset(struct Qdisc *sch)
 	struct netem_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
-	skb_queue_purge(&q->delayed);
-
 	sch->q.qlen = 0;
 	sch->flags &= ~TCQ_F_THROTTLED;
 	del_timer_sync(&q->timer);
@@ -397,6 +352,19 @@ static int get_correlation(struct Qdisc *sch, const struct rtattr *attr)
 	return 0;
 }
 
+static int get_reorder(struct Qdisc *sch, const struct rtattr *attr)
+{
+	struct netem_sched_data *q = qdisc_priv(sch);
+	const struct tc_netem_reorder *r = RTA_DATA(attr);
+
+	if (RTA_PAYLOAD(attr) != sizeof(*r))
+		return -EINVAL;
+
+	q->reorder = r->probability;
+	init_crandom(&q->reorder_cor, r->correlation);
+	return 0;
+}
+
 static int netem_change(struct Qdisc *sch, struct rtattr *opt)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
@@ -417,9 +385,15 @@ static int netem_change(struct Qdisc *sch, struct rtattr *opt)
 	q->jitter = qopt->jitter;
 	q->limit = qopt->limit;
 	q->gap = qopt->gap;
+	q->counter = 0;
 	q->loss = qopt->loss;
 	q->duplicate = qopt->duplicate;
 
+	/* for compatiablity with earlier versions.
+	 * if gap is set, need to assume 100% probablity
+	 */
+	q->reorder = ~0;
+
 	/* Handle nested options after initial queue options.
 	 * Should have put all options in nested format but too late now.
 	 */ 
@@ -441,6 +415,11 @@ static int netem_change(struct Qdisc *sch, struct rtattr *opt)
 			if (ret)
 				return ret;
 		}
+		if (tb[TCA_NETEM_REORDER-1]) {
+			ret = get_reorder(sch, tb[TCA_NETEM_REORDER-1]);
+			if (ret)
+				return ret;
+		}
 	}
 
 
@@ -455,11 +434,9 @@ static int netem_init(struct Qdisc *sch, struct rtattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	skb_queue_head_init(&q->delayed);
 	init_timer(&q->timer);
 	q->timer.function = netem_watchdog;
 	q->timer.data = (unsigned long) sch;
-	q->counter = 0;
 
 	q->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
 	if (!q->qdisc) {
@@ -491,6 +468,7 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct rtattr *rta = (struct rtattr *) b;
 	struct tc_netem_qopt qopt;
 	struct tc_netem_corr cor;
+	struct tc_netem_reorder reorder;
 
 	qopt.latency = q->latency;
 	qopt.jitter = q->jitter;
@@ -504,6 +482,11 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	cor.loss_corr = q->loss_cor.rho;
 	cor.dup_corr = q->dup_cor.rho;
 	RTA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor);
+
+	reorder.probability = q->reorder;
+	reorder.correlation = q->reorder_cor.rho;
+	RTA_PUT(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder);
+
 	rta->rta_len = skb->tail - b;
 
 	return skb->len;