1 files changed, 586 insertions, 291 deletions

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 82f6016d89ab..32a5f3304046 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * net/sched/sch_netem.c	Network emulator
  *
- * 		This program is free software; you can redistribute it and/or
- * 		modify it under the terms of the GNU General Public License
- * 		as published by the Free Software Foundation; either version
- * 		2 of the License.
- *
  *  		Many of the algorithms and ideas for this came from
  *		NIST Net which is not copyrighted.
  *
@@ -21,10 +17,12 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
+#include <linux/prandom.h>
 #include <linux/rtnetlink.h>
 #include <linux/reciprocal_div.h>
 #include <linux/rbtree.h>
 
+#include <net/gso.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
@@ -68,17 +66,28 @@
 		 Fabio Ludovici <fabio.ludovici at yahoo.it>
 */
 
+struct disttable {
+	u32  size;
+	s16 table[] __counted_by(size);
+};
+
 struct netem_sched_data {
 	/* internal t(ime)fifo qdisc uses t_root and sch->limit */
 	struct rb_root t_root;
 
+	/* a linear queue; reduces rbtree rebalancing when jitter is low */
+	struct sk_buff	*t_head;
+	struct sk_buff	*t_tail;
+
+	u32 t_len;
+
 	/* optional qdisc for classful handling (NULL at netem init) */
 	struct Qdisc	*qdisc;
 
 	struct qdisc_watchdog watchdog;
 
-	psched_tdiff_t latency;
-	psched_tdiff_t jitter;
+	s64 latency;
+	s64 jitter;
 
 	u32 loss;
 	u32 ecn;
@@ -88,10 +97,10 @@ struct netem_sched_data {
 	u32 duplicate;
 	u32 reorder;
 	u32 corrupt;
-	u32 rate;
+	u64 rate;
 	s32 packet_overhead;
 	u32 cell_size;
-	u32 cell_size_reciprocal;
+	struct reciprocal_value cell_size_reciprocal;
 	s32 cell_overhead;
 
 	struct crndstate {
@@ -99,10 +108,12 @@ struct netem_sched_data {
 		u32 rho;
 	} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
 
-	struct disttable {
-		u32  size;
-		s16 table[0];
-	} *delay_dist;
+	struct prng  {
+		u64 seed;
+		struct rnd_state prng_state;
+	} prng;
+
+	struct disttable *delay_dist;
 
 	enum  {
 		CLG_RANDOM,
@@ -110,6 +121,18 @@ struct netem_sched_data {
 		CLG_GILB_ELL,
 	} loss_model;
 
+	enum {
+		TX_IN_GAP_PERIOD = 1,
+		TX_IN_BURST_PERIOD,
+		LOST_IN_GAP_PERIOD,
+		LOST_IN_BURST_PERIOD,
+	} _4_state_model;
+
+	enum {
+		GOOD_STATE = 1,
+		BAD_STATE,
+	} GE_state_model;
+
 	/* Correlated Loss Generation models */
 	struct clgstate {
 		/* state of the Markov chain */
@@ -123,39 +146,27 @@ struct netem_sched_data {
 		u32 a5; /* p23 used only in 4-states */
 	} clg;
 
+	struct tc_netem_slot slot_config;
+	struct slotstate {
+		u64 slot_next;
+		s32 packets_left;
+		s32 bytes_left;
+	} slot;
+
+	struct disttable *slot_dist;
 };
 
 /* Time stamp put into socket buffer control block
  * Only valid when skbs are in our internal t(ime)fifo queue.
+ *
+ * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp,
+ * and skb->next & skb->prev are scratch space for a qdisc,
+ * we save skb->tstamp value in skb->cb[] before destroying it.
  */
 struct netem_skb_cb {
-	psched_time_t	time_to_send;
-	ktime_t		tstamp_save;
+	u64	        time_to_send;
 };
 
-/* Because space in skb->cb[] is tight, netem overloads skb->next/prev/tstamp
- * to hold a rb_node structure.
- *
- * If struct sk_buff layout is changed, the following checks will complain.
- */
-static struct rb_node *netem_rb_node(struct sk_buff *skb)
-{
-	BUILD_BUG_ON(offsetof(struct sk_buff, next) != 0);
-	BUILD_BUG_ON(offsetof(struct sk_buff, prev) !=
-		     offsetof(struct sk_buff, next) + sizeof(skb->next));
-	BUILD_BUG_ON(offsetof(struct sk_buff, tstamp) !=
-		     offsetof(struct sk_buff, prev) + sizeof(skb->prev));
-	BUILD_BUG_ON(sizeof(struct rb_node) > sizeof(skb->next) +
-					      sizeof(skb->prev) +
-					      sizeof(skb->tstamp));
-	return (struct rb_node *)&skb->next;
-}
-
-static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
-{
-	return (struct sk_buff *)rb;
-}
-
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
 {
 	/* we assume we can use skb next/prev/tstamp as storage for rb_node */
@@ -169,22 +180,23 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
 static void init_crandom(struct crndstate *state, unsigned long rho)
 {
 	state->rho = rho;
-	state->last = net_random();
+	state->last = get_random_u32();
 }
 
 /* get_crandom - correlated random number generator
  * Next number depends on last value.
  * rho is scaled to avoid floating point.
  */
-static u32 get_crandom(struct crndstate *state)
+static u32 get_crandom(struct crndstate *state, struct prng *p)
 {
 	u64 value, rho;
 	unsigned long answer;
+	struct rnd_state *s = &p->prng_state;
 
-	if (state->rho == 0)	/* no correlation */
-		return net_random();
+	if (!state || state->rho == 0)	/* no correlation */
+		return prandom_u32_state(s);
 
-	value = net_random();
+	value = prandom_u32_state(s);
 	rho = (u64)state->rho + 1;
 	answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
 	state->last = answer;
@@ -198,51 +210,52 @@ static u32 get_crandom(struct crndstate *state)
 static bool loss_4state(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
-	u32 rnd = net_random();
+	u32 rnd = prandom_u32_state(&q->prng.prng_state);
 
 	/*
 	 * Makes a comparison between rnd and the transition
 	 * probabilities outgoing from the current state, then decides the
 	 * next state and if the next packet has to be transmitted or lost.
 	 * The four states correspond to:
-	 *   1 => successfully transmitted packets within a gap period
-	 *   4 => isolated losses within a gap period
-	 *   3 => lost packets within a burst period
-	 *   2 => successfully transmitted packets within a burst period
+	 *   TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period
+	 *   LOST_IN_GAP_PERIOD => isolated losses within a gap period
+	 *   LOST_IN_BURST_PERIOD => lost packets within a burst period
+	 *   TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period
 	 */
 	switch (clg->state) {
-	case 1:
+	case TX_IN_GAP_PERIOD:
 		if (rnd < clg->a4) {
-			clg->state = 4;
+			clg->state = LOST_IN_GAP_PERIOD;
 			return true;
-		} else if (clg->a4 < rnd && rnd < clg->a1) {
-			clg->state = 3;
+		} else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) {
+			clg->state = LOST_IN_BURST_PERIOD;
 			return true;
-		} else if (clg->a1 < rnd)
-			clg->state = 1;
+		} else if (clg->a1 + clg->a4 < rnd) {
+			clg->state = TX_IN_GAP_PERIOD;
+		}
 
 		break;
-	case 2:
+	case TX_IN_BURST_PERIOD:
 		if (rnd < clg->a5) {
-			clg->state = 3;
+			clg->state = LOST_IN_BURST_PERIOD;
 			return true;
-		} else
-			clg->state = 2;
+		} else {
+			clg->state = TX_IN_BURST_PERIOD;
+		}
 
 		break;
-	case 3:
+	case LOST_IN_BURST_PERIOD:
 		if (rnd < clg->a3)
-			clg->state = 2;
+			clg->state = TX_IN_BURST_PERIOD;
 		else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) {
-			clg->state = 1;
-			return true;
+			clg->state = TX_IN_GAP_PERIOD;
 		} else if (clg->a2 + clg->a3 < rnd) {
-			clg->state = 3;
+			clg->state = LOST_IN_BURST_PERIOD;
 			return true;
 		}
 		break;
-	case 4:
-		clg->state = 1;
+	case LOST_IN_GAP_PERIOD:
+		clg->state = TX_IN_GAP_PERIOD;
 		break;
 	}
 
@@ -262,17 +275,19 @@ static bool loss_4state(struct netem_sched_data *q)
 static bool loss_gilb_ell(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
+	struct rnd_state *s = &q->prng.prng_state;
 
 	switch (clg->state) {
-	case 1:
-		if (net_random() < clg->a1)
-			clg->state = 2;
-		if (net_random() < clg->a4)
+	case GOOD_STATE:
+		if (prandom_u32_state(s) < clg->a1)
+			clg->state = BAD_STATE;
+		if (prandom_u32_state(s) < clg->a4)
 			return true;
-	case 2:
-		if (net_random() < clg->a2)
-			clg->state = 1;
-		if (clg->a3 > net_random())
+		break;
+	case BAD_STATE:
+		if (prandom_u32_state(s) < clg->a2)
+			clg->state = GOOD_STATE;
+		if (prandom_u32_state(s) > clg->a3)
 			return true;
 	}
 
@@ -284,7 +299,7 @@ static bool loss_event(struct netem_sched_data *q)
 	switch (q->loss_model) {
 	case CLG_RANDOM:
 		/* Random packet drop 0 => none, ~0 => all */
-		return q->loss && q->loss >= get_crandom(&q->loss_cor);
+		return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng);
 
 	case CLG_4_STATES:
 		/* 4state loss model algorithm (used also for GI model)
@@ -311,22 +326,23 @@ static bool loss_event(struct netem_sched_data *q)
  * std deviation sigma.  Uses table lookup to approximate the desired
  * distribution, and a uniformly-distributed pseudo-random source.
  */
-static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma,
-				struct crndstate *state,
-				const struct disttable *dist)
+static s64 tabledist(s64 mu, s32 sigma,
+		     struct crndstate *state,
+		     struct prng *prng,
+		     const struct disttable *dist)
 {
-	psched_tdiff_t x;
+	s64 x;
 	long t;
 	u32 rnd;
 
 	if (sigma == 0)
 		return mu;
 
-	rnd = get_crandom(state);
+	rnd = get_crandom(state, prng);
 
 	/* default uniform distribution */
 	if (dist == NULL)
-		return (rnd % (2*sigma)) - sigma + mu;
+		return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
 
 	t = dist->table[rnd % dist->size];
 	x = (sigma % NETEM_DIST_SCALE) * t;
@@ -338,10 +354,8 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma,
 	return  x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu;
 }
 
-static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q)
+static u64 packet_time_ns(u64 len, const struct netem_sched_data *q)
 {
-	u64 ticks;
-
 	len += q->packet_overhead;
 
 	if (q->cell_size) {
@@ -352,86 +366,129 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche
 		len = cells * (q->cell_size + q->cell_overhead);
 	}
 
-	ticks = (u64)len * NSEC_PER_SEC;
+	return div64_u64(len * NSEC_PER_SEC, q->rate);
+}
+
+static void tfifo_reset(struct Qdisc *sch)
+{
+	struct netem_sched_data *q = qdisc_priv(sch);
+	struct rb_node *p = rb_first(&q->t_root);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, &q->t_root);
+		rtnl_kfree_skbs(skb, skb);
+	}
 
-	do_div(ticks, q->rate);
-	return PSCHED_NS2TICKS(ticks);
+	rtnl_kfree_skbs(q->t_head, q->t_tail);
+	q->t_head = NULL;
+	q->t_tail = NULL;
+	q->t_len = 0;
 }
 
 static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
-	psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
-	struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
+	u64 tnext = netem_skb_cb(nskb)->time_to_send;
 
-	while (*p) {
-		struct sk_buff *skb;
-
-		parent = *p;
-		skb = netem_rb_to_skb(parent);
-		if (tnext >= netem_skb_cb(skb)->time_to_send)
-			p = &parent->rb_right;
+	if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) {
+		if (q->t_tail)
+			q->t_tail->next = nskb;
 		else
-			p = &parent->rb_left;
+			q->t_head = nskb;
+		q->t_tail = nskb;
+	} else {
+		struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
+
+		while (*p) {
+			struct sk_buff *skb;
+
+			parent = *p;
+			skb = rb_to_skb(parent);
+			if (tnext >= netem_skb_cb(skb)->time_to_send)
+				p = &parent->rb_right;
+			else
+				p = &parent->rb_left;
+		}
+		rb_link_node(&nskb->rbnode, parent, p);
+		rb_insert_color(&nskb->rbnode, &q->t_root);
 	}
-	rb_link_node(netem_rb_node(nskb), parent, p);
-	rb_insert_color(netem_rb_node(nskb), &q->t_root);
+	q->t_len++;
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch,
+				     struct sk_buff **to_free)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	qdisc_skb_cb(skb)->pkt_segs = 1;
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_drop(skb, sch, to_free);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * 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_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
-	struct sk_buff *skb2;
+	struct sk_buff *skb2 = NULL;
+	struct sk_buff *segs = NULL;
+	unsigned int prev_len = qdisc_pkt_len(skb);
 	int count = 1;
 
+	/* Do not fool qdisc_drop_all() */
+	skb->prev = NULL;
+
 	/* Random duplication */
-	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng))
 		++count;
 
 	/* Drop packet? */
 	if (loss_event(q)) {
 		if (q->ecn && INET_ECN_set_ce(skb))
-			sch->qstats.drops++; /* mark packet */
+			qdisc_qstats_drop(sch); /* mark packet */
 		else
 			--count;
 	}
 	if (count == 0) {
-		sch->qstats.drops++;
-		kfree_skb(skb);
+		qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
 		return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	}
 
 	/* If a delay is expected, orphan the skb. (orphaning usually takes
 	 * place at TX completion time, so _before_ the link transit delay)
-	 * Ideally, this orphaning should be done after the rate limiting
-	 * module, because this breaks TCP Small Queue, and other mechanisms
-	 * based on socket sk_wmem_alloc.
 	 */
-	if (q->latency || q->jitter)
-		skb_orphan(skb);
+	if (q->latency || q->jitter || q->rate)
+		skb_orphan_partial(skb);
 
 	/*
-	 * 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 we need to duplicate packet, then clone it before
+	 * original is modified.
 	 */
-	if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
-		struct Qdisc *rootq = qdisc_root(sch);
-		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
-		q->duplicate = 0;
-
-		qdisc_enqueue_root(skb2, rootq);
-		q->duplicate = dupsave;
-	}
+	if (count > 1)
+		skb2 = skb_clone(skb, GFP_ATOMIC);
 
 	/*
 	 * Randomized packet corruption.
@@ -439,55 +496,110 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * If packet is going to be hardware checksummed, then
 	 * do it now in software before we mangle it.
 	 */
-	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
-		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
-		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) {
+		if (skb_is_gso(skb)) {
+			skb = netem_segment(skb, sch, to_free);
+			if (!skb)
+				goto finish_segs;
+
+			segs = skb->next;
+			skb_mark_not_on_list(skb);
+			qdisc_skb_cb(skb)->pkt_len = skb->len;
+		}
+
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (unlikely(!skb)) {
+			qdisc_qstats_drop(sch);
+			goto finish_segs;
+		}
+		if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		    skb_checksum_help(skb)) {
+			qdisc_drop(skb, sch, to_free);
+			skb = NULL;
+			goto finish_segs;
+		}
+
+		skb->data[get_random_u32_below(skb_headlen(skb))] ^=
+			1<<get_random_u32_below(8);
+	}
 
-		skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
+	if (unlikely(q->t_len >= sch->limit)) {
+		/* re-link segs, so that qdisc_drop_all() frees them all */
+		skb->next = segs;
+		qdisc_drop_all(skb, sch, to_free);
+		if (skb2)
+			__qdisc_drop(skb2, to_free);
+		return NET_XMIT_DROP;
 	}
 
-	if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
-		return qdisc_reshape_fail(skb, sch);
+	/*
+	 * If doing duplication then re-insert at top of the
+	 * qdisc tree, since parent queuer expects that only one
+	 * skb will be queued.
+	 */
+	if (skb2) {
+		struct Qdisc *rootq = qdisc_root_bh(sch);
+		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
+
+		q->duplicate = 0;
+		rootq->enqueue(skb2, rootq, to_free);
+		q->duplicate = dupsave;
+		skb2 = NULL;
+	}
 
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 
 	cb = netem_skb_cb(skb);
 	if (q->gap == 0 ||		/* not doing reordering */
 	    q->counter < q->gap - 1 ||	/* inside last reordering gap */
-	    q->reorder < get_crandom(&q->reorder_cor)) {
-		psched_time_t now;
-		psched_tdiff_t delay;
+	    q->reorder < get_crandom(&q->reorder_cor, &q->prng)) {
+		u64 now;
+		s64 delay;
 
 		delay = tabledist(q->latency, q->jitter,
-				  &q->delay_cor, q->delay_dist);
+				  &q->delay_cor, &q->prng, q->delay_dist);
 
-		now = psched_get_time();
+		now = ktime_get_ns();
 
 		if (q->rate) {
-			struct sk_buff *last;
+			struct netem_skb_cb *last = NULL;
+
+			if (sch->q.tail)
+				last = netem_skb_cb(sch->q.tail);
+			if (q->t_root.rb_node) {
+				struct sk_buff *t_skb;
+				struct netem_skb_cb *t_last;
+
+				t_skb = skb_rb_last(&q->t_root);
+				t_last = netem_skb_cb(t_skb);
+				if (!last ||
+				    t_last->time_to_send > last->time_to_send)
+					last = t_last;
+			}
+			if (q->t_tail) {
+				struct netem_skb_cb *t_last =
+					netem_skb_cb(q->t_tail);
+
+				if (!last ||
+				    t_last->time_to_send > last->time_to_send)
+					last = t_last;
+			}
 
-			if (!skb_queue_empty(&sch->q))
-				last = skb_peek_tail(&sch->q);
-			else
-				last = netem_rb_to_skb(rb_last(&q->t_root));
 			if (last) {
 				/*
 				 * Last packet in queue is reference point (now),
 				 * calculate this time bonus and subtract
 				 * from delay.
 				 */
-				delay -= netem_skb_cb(last)->time_to_send - now;
-				delay = max_t(psched_tdiff_t, 0, delay);
-				now = netem_skb_cb(last)->time_to_send;
+				delay -= last->time_to_send - now;
+				delay = max_t(s64, 0, delay);
+				now = last->time_to_send;
 			}
 
-			delay += packet_len_2_sched_time(skb->len, q);
+			delay += packet_time_ns(qdisc_pkt_len(skb), q);
 		}
 
 		cb->time_to_send = now + delay;
-		cb->tstamp_save = skb->tstamp;
 		++q->counter;
 		tfifo_enqueue(skb, sch);
 	} else {
@@ -495,114 +607,178 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		 * Do re-ordering by putting one out of N packets at the front
 		 * of the queue.
 		 */
-		cb->time_to_send = psched_get_time();
+		cb->time_to_send = ktime_get_ns();
 		q->counter = 0;
 
-		__skb_queue_head(&sch->q, skb);
+		__qdisc_enqueue_head(skb, &sch->q);
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (skb2)
+		__qdisc_drop(skb2, to_free);
+
+	if (segs) {
+		unsigned int len, last_len;
+		int rc, nb;
+
+		len = skb ? skb->len : 0;
+		nb = skb ? 1 : 0;
+
+		while (segs) {
+			skb2 = segs->next;
+			skb_mark_not_on_list(segs);
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch, to_free);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		/* Parent qdiscs accounted for 1 skb of size @prev_len */
+		qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len));
+	} else if (!skb) {
+		return NET_XMIT_DROP;
+	}
 	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int netem_drop(struct Qdisc *sch)
+/* Delay the next round with a new future slot with a
+ * correct number of bytes and packets.
+ */
+
+static void get_slot_next(struct netem_sched_data *q, u64 now)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
-	unsigned int len;
+	s64 next_delay;
 
-	len = qdisc_queue_drop(sch);
+	if (!q->slot_dist)
+		next_delay = q->slot_config.min_delay +
+				(get_random_u32() *
+				 (q->slot_config.max_delay -
+				  q->slot_config.min_delay) >> 32);
+	else
+		next_delay = tabledist(q->slot_config.dist_delay,
+				       (s32)(q->slot_config.dist_jitter),
+				       NULL, &q->prng, q->slot_dist);
 
-	if (!len) {
-		struct rb_node *p = rb_first(&q->t_root);
+	q->slot.slot_next = now + next_delay;
+	q->slot.packets_left = q->slot_config.max_packets;
+	q->slot.bytes_left = q->slot_config.max_bytes;
+}
 
-		if (p) {
-			struct sk_buff *skb = netem_rb_to_skb(p);
+static struct sk_buff *netem_peek(struct netem_sched_data *q)
+{
+	struct sk_buff *skb = skb_rb_first(&q->t_root);
+	u64 t1, t2;
 
-			rb_erase(p, &q->t_root);
-			sch->q.qlen--;
-			skb->next = NULL;
-			skb->prev = NULL;
-			len = qdisc_pkt_len(skb);
-			kfree_skb(skb);
-		}
-	}
-	if (!len && q->qdisc && q->qdisc->ops->drop)
-	    len = q->qdisc->ops->drop(q->qdisc);
-	if (len)
-		sch->qstats.drops++;
+	if (!skb)
+		return q->t_head;
+	if (!q->t_head)
+		return skb;
+
+	t1 = netem_skb_cb(skb)->time_to_send;
+	t2 = netem_skb_cb(q->t_head)->time_to_send;
+	if (t1 < t2)
+		return skb;
+	return q->t_head;
+}
 
-	return len;
+static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb)
+{
+	if (skb == q->t_head) {
+		q->t_head = skb->next;
+		if (!q->t_head)
+			q->t_tail = NULL;
+	} else {
+		rb_erase(&skb->rbnode, &q->t_root);
+	}
 }
 
 static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
-	struct rb_node *p;
-
-	if (qdisc_is_throttled(sch))
-		return NULL;
 
 tfifo_dequeue:
-	skb = __skb_dequeue(&sch->q);
+	skb = __qdisc_dequeue_head(&sch->q);
 	if (skb) {
 deliver:
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
-		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_bstats_update(sch, skb);
 		return skb;
 	}
-	p = rb_first(&q->t_root);
-	if (p) {
-		psched_time_t time_to_send;
-
-		skb = netem_rb_to_skb(p);
+	skb = netem_peek(q);
+	if (skb) {
+		u64 time_to_send;
+		u64 now = ktime_get_ns();
 
 		/* if more time remaining? */
 		time_to_send = netem_skb_cb(skb)->time_to_send;
-		if (time_to_send <= psched_get_time()) {
-			rb_erase(p, &q->t_root);
+		if (q->slot.slot_next && q->slot.slot_next < time_to_send)
+			get_slot_next(q, now);
 
-			sch->q.qlen--;
+		if (time_to_send <= now && q->slot.slot_next <= now) {
+			netem_erase_head(q, skb);
+			q->t_len--;
 			skb->next = NULL;
 			skb->prev = NULL;
-			skb->tstamp = netem_skb_cb(skb)->tstamp_save;
-
-#ifdef CONFIG_NET_CLS_ACT
-			/*
-			 * If it's at ingress let's pretend the delay is
-			 * from the network (tstamp will be updated).
+			/* skb->dev shares skb->rbnode area,
+			 * we need to restore its value.
 			 */
-			if (G_TC_FROM(skb->tc_verd) & AT_INGRESS)
-				skb->tstamp.tv64 = 0;
-#endif
+			skb->dev = qdisc_dev(sch);
+
+			if (q->slot.slot_next) {
+				q->slot.packets_left--;
+				q->slot.bytes_left -= qdisc_pkt_len(skb);
+				if (q->slot.packets_left <= 0 ||
+				    q->slot.bytes_left <= 0)
+					get_slot_next(q, now);
+			}
 
 			if (q->qdisc) {
-				int err = qdisc_enqueue(skb, q->qdisc);
-
-				if (unlikely(err != NET_XMIT_SUCCESS)) {
-					if (net_xmit_drop_count(err)) {
-						sch->qstats.drops++;
-						qdisc_tree_decrease_qlen(sch, 1);
-					}
+				unsigned int pkt_len = qdisc_pkt_len(skb);
+				struct sk_buff *to_free = NULL;
+				int err;
+
+				err = qdisc_enqueue(skb, q->qdisc, &to_free);
+				kfree_skb_list(to_free);
+				if (err != NET_XMIT_SUCCESS) {
+					if (net_xmit_drop_count(err))
+						qdisc_qstats_drop(sch);
+					sch->qstats.backlog -= pkt_len;
+					sch->q.qlen--;
+					qdisc_tree_reduce_backlog(sch, 1, pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
+			sch->q.qlen--;
 			goto deliver;
 		}
 
 		if (q->qdisc) {
 			skb = q->qdisc->ops->dequeue(q->qdisc);
-			if (skb)
+			if (skb) {
+				sch->q.qlen--;
 				goto deliver;
+			}
 		}
-		qdisc_watchdog_schedule(&q->watchdog, time_to_send);
+
+		qdisc_watchdog_schedule_ns(&q->watchdog,
+					   max(time_to_send,
+					       q->slot.slot_next));
 	}
 
 	if (q->qdisc) {
 		skb = q->qdisc->ops->dequeue(q->qdisc);
-		if (skb)
+		if (skb) {
+			sch->q.qlen--;
 			goto deliver;
+		}
 	}
 	return NULL;
 }
@@ -612,6 +788,7 @@ static void netem_reset(struct Qdisc *sch)
 	struct netem_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset_queue(sch);
+	tfifo_reset(sch);
 	if (q->qdisc)
 		qdisc_reset(q->qdisc);
 	qdisc_watchdog_cancel(&q->watchdog);
@@ -619,35 +796,25 @@ static void netem_reset(struct Qdisc *sch)
 
 static void dist_free(struct disttable *d)
 {
-	if (d) {
-		if (is_vmalloc_addr(d))
-			vfree(d);
-		else
-			kfree(d);
-	}
+	kvfree(d);
 }
 
 /*
  * Distribution data is a variable size payload containing
  * signed 16 bit values.
  */
-static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
+
+static int get_dist_table(struct disttable **tbl, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	size_t n = nla_len(attr)/sizeof(__s16);
 	const __s16 *data = nla_data(attr);
-	spinlock_t *root_lock;
 	struct disttable *d;
 	int i;
-	size_t s;
 
-	if (n > NETEM_DIST_MAX)
+	if (!n || n > NETEM_DIST_MAX)
 		return -EINVAL;
 
-	s = sizeof(struct disttable) + n * sizeof(s16);
-	d = kmalloc(s, GFP_KERNEL | __GFP_NOWARN);
-	if (!d)
-		d = vmalloc(s);
+	d = kvmalloc(struct_size(d, table, n), GFP_KERNEL);
 	if (!d)
 		return -ENOMEM;
 
@@ -655,19 +822,34 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
 	for (i = 0; i < n; i++)
 		d->table[i] = data[i];
 
-	root_lock = qdisc_root_sleeping_lock(sch);
-
-	spin_lock_bh(root_lock);
-	swap(q->delay_dist, d);
-	spin_unlock_bh(root_lock);
-
-	dist_free(d);
+	*tbl = d;
 	return 0;
 }
 
-static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
+static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
+{
+	const struct tc_netem_slot *c = nla_data(attr);
+
+	q->slot_config = *c;
+	if (q->slot_config.max_packets == 0)
+		q->slot_config.max_packets = INT_MAX;
+	if (q->slot_config.max_bytes == 0)
+		q->slot_config.max_bytes = INT_MAX;
+
+	/* capping dist_jitter to the range acceptable by tabledist() */
+	q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
+	q->slot.packets_left = q->slot_config.max_packets;
+	q->slot.bytes_left = q->slot_config.max_bytes;
+	if (q->slot_config.min_delay | q->slot_config.max_delay |
+	    q->slot_config.dist_jitter)
+		q->slot.slot_next = ktime_get_ns();
+	else
+		q->slot.slot_next = 0;
+}
+
+static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_corr *c = nla_data(attr);
 
 	init_crandom(&q->delay_cor, c->delay_corr);
@@ -675,47 +857,45 @@ static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
 	init_crandom(&q->dup_cor, c->dup_corr);
 }
 
-static void get_reorder(struct Qdisc *sch, const struct nlattr *attr)
+static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_reorder *r = nla_data(attr);
 
 	q->reorder = r->probability;
 	init_crandom(&q->reorder_cor, r->correlation);
 }
 
-static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
+static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_corrupt *r = nla_data(attr);
 
 	q->corrupt = r->probability;
 	init_crandom(&q->corrupt_cor, r->correlation);
 }
 
-static void get_rate(struct Qdisc *sch, const struct nlattr *attr)
+static void get_rate(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_rate *r = nla_data(attr);
 
 	q->rate = r->rate;
 	q->packet_overhead = r->packet_overhead;
 	q->cell_size = r->cell_size;
+	q->cell_overhead = r->cell_overhead;
 	if (q->cell_size)
 		q->cell_size_reciprocal = reciprocal_value(q->cell_size);
-	q->cell_overhead = r->cell_overhead;
+	else
+		q->cell_size_reciprocal = (struct reciprocal_value) { 0 };
 }
 
-static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
+static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct nlattr *la;
 	int rem;
 
 	nla_for_each_nested(la, attr, rem) {
 		u16 type = nla_type(la);
 
-		switch(type) {
+		switch (type) {
 		case NETEM_LOSS_GI: {
 			const struct tc_netem_gimodel *gi = nla_data(la);
 
@@ -726,7 +906,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
 
 			q->loss_model = CLG_4_STATES;
 
-			q->clg.state = 1;
+			q->clg.state = TX_IN_GAP_PERIOD;
 			q->clg.a1 = gi->p13;
 			q->clg.a2 = gi->p31;
 			q->clg.a3 = gi->p32;
@@ -744,7 +924,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
 			}
 
 			q->loss_model = CLG_GILB_ELL;
-			q->clg.state = 1;
+			q->clg.state = GOOD_STATE;
 			q->clg.a1 = ge->p;
 			q->clg.a2 = ge->r;
 			q->clg.a3 = ge->h;
@@ -768,6 +948,11 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_RATE]	= { .len = sizeof(struct tc_netem_rate) },
 	[TCA_NETEM_LOSS]	= { .type = NLA_NESTED },
 	[TCA_NETEM_ECN]		= { .type = NLA_U32 },
+	[TCA_NETEM_RATE64]	= { .type = NLA_U64 },
+	[TCA_NETEM_LATENCY64]	= { .type = NLA_S64 },
+	[TCA_NETEM_JITTER64]	= { .type = NLA_S64 },
+	[TCA_NETEM_SLOT]	= { .len = sizeof(struct tc_netem_slot) },
+	[TCA_NETEM_PRNG_SEED]	= { .type = NLA_U64 },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -781,37 +966,112 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 	}
 
 	if (nested_len >= nla_attr_size(0))
-		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
-				 nested_len, policy);
+		return nla_parse_deprecated(tb, maxtype,
+					    nla_data(nla) + NLA_ALIGN(len),
+					    nested_len, policy, NULL);
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
 }
 
+static const struct Qdisc_class_ops netem_class_ops;
+
+static int check_netem_in_tree(struct Qdisc *sch, bool duplicates,
+			       struct netlink_ext_ack *extack)
+{
+	struct Qdisc *root, *q;
+	unsigned int i;
+
+	root = qdisc_root_sleeping(sch);
+
+	if (sch != root && root->ops->cl_ops == &netem_class_ops) {
+		if (duplicates ||
+		    ((struct netem_sched_data *)qdisc_priv(root))->duplicate)
+			goto err;
+	}
+
+	if (!qdisc_dev(root))
+		return 0;
+
+	hash_for_each(qdisc_dev(root)->qdisc_hash, i, q, hash) {
+		if (sch != q && q->ops->cl_ops == &netem_class_ops) {
+			if (duplicates ||
+			    ((struct netem_sched_data *)qdisc_priv(q))->duplicate)
+				goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	NL_SET_ERR_MSG(extack,
+		       "netem: cannot mix duplicating netems with other netems in tree");
+	return -EINVAL;
+}
+
 /* Parse netlink message to set options */
-static int netem_change(struct Qdisc *sch, struct nlattr *opt)
+static int netem_change(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_NETEM_MAX + 1];
+	struct disttable *delay_dist = NULL;
+	struct disttable *slot_dist = NULL;
 	struct tc_netem_qopt *qopt;
+	struct clgstate old_clg;
+	int old_loss_model = CLG_RANDOM;
 	int ret;
 
-	if (opt == NULL)
-		return -EINVAL;
-
 	qopt = nla_data(opt);
 	ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt));
 	if (ret < 0)
 		return ret;
 
+	if (tb[TCA_NETEM_DELAY_DIST]) {
+		ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]);
+		if (ret)
+			goto table_free;
+	}
+
+	if (tb[TCA_NETEM_SLOT_DIST]) {
+		ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]);
+		if (ret)
+			goto table_free;
+	}
+
+	sch_tree_lock(sch);
+	/* backup q->clg and q->loss_model */
+	old_clg = q->clg;
+	old_loss_model = q->loss_model;
+
+	if (tb[TCA_NETEM_LOSS]) {
+		ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
+		if (ret) {
+			q->loss_model = old_loss_model;
+			q->clg = old_clg;
+			goto unlock;
+		}
+	} else {
+		q->loss_model = CLG_RANDOM;
+	}
+
+	if (delay_dist)
+		swap(q->delay_dist, delay_dist);
+	if (slot_dist)
+		swap(q->slot_dist, slot_dist);
 	sch->limit = qopt->limit;
 
-	q->latency = qopt->latency;
-	q->jitter = qopt->jitter;
+	q->latency = PSCHED_TICKS2NS(qopt->latency);
+	q->jitter = PSCHED_TICKS2NS(qopt->jitter);
 	q->limit = qopt->limit;
 	q->gap = qopt->gap;
 	q->counter = 0;
 	q->loss = qopt->loss;
+
+	ret = check_netem_in_tree(sch, qopt->duplicate, extack);
+	if (ret)
+		goto unlock;
+
 	q->duplicate = qopt->duplicate;
 
 	/* for compatibility with earlier versions.
@@ -821,45 +1081,64 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 		q->reorder = ~0;
 
 	if (tb[TCA_NETEM_CORR])
-		get_correlation(sch, tb[TCA_NETEM_CORR]);
-
-	if (tb[TCA_NETEM_DELAY_DIST]) {
-		ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
-		if (ret)
-			return ret;
-	}
+		get_correlation(q, tb[TCA_NETEM_CORR]);
 
 	if (tb[TCA_NETEM_REORDER])
-		get_reorder(sch, tb[TCA_NETEM_REORDER]);
+		get_reorder(q, tb[TCA_NETEM_REORDER]);
 
 	if (tb[TCA_NETEM_CORRUPT])
-		get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
+		get_corrupt(q, tb[TCA_NETEM_CORRUPT]);
 
 	if (tb[TCA_NETEM_RATE])
-		get_rate(sch, tb[TCA_NETEM_RATE]);
+		get_rate(q, tb[TCA_NETEM_RATE]);
+
+	if (tb[TCA_NETEM_RATE64])
+		q->rate = max_t(u64, q->rate,
+				nla_get_u64(tb[TCA_NETEM_RATE64]));
+
+	if (tb[TCA_NETEM_LATENCY64])
+		q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]);
+
+	if (tb[TCA_NETEM_JITTER64])
+		q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]);
 
 	if (tb[TCA_NETEM_ECN])
 		q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
 
-	q->loss_model = CLG_RANDOM;
-	if (tb[TCA_NETEM_LOSS])
-		ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
+	if (tb[TCA_NETEM_SLOT])
+		get_slot(q, tb[TCA_NETEM_SLOT]);
+
+	/* capping jitter to the range acceptable by tabledist() */
+	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
+	if (tb[TCA_NETEM_PRNG_SEED])
+		q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]);
+	else
+		q->prng.seed = get_random_u64();
+	prandom_seed_state(&q->prng.prng_state, q->prng.seed);
+
+unlock:
+	sch_tree_unlock(sch);
 
+table_free:
+	dist_free(delay_dist);
+	dist_free(slot_dist);
 	return ret;
 }
 
-static int netem_init(struct Qdisc *sch, struct nlattr *opt)
+static int netem_init(struct Qdisc *sch, struct nlattr *opt,
+		      struct netlink_ext_ack *extack)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	int ret;
 
+	qdisc_watchdog_init(&q->watchdog, sch);
+
 	if (!opt)
 		return -EINVAL;
 
-	qdisc_watchdog_init(&q->watchdog, sch);
-
 	q->loss_model = CLG_RANDOM;
-	ret = netem_change(sch, opt);
+	ret = netem_change(sch, opt, extack);
 	if (ret)
 		pr_info("netem: change failed\n");
 	return ret;
@@ -871,8 +1150,9 @@ static void netem_destroy(struct Qdisc *sch)
 
 	qdisc_watchdog_cancel(&q->watchdog);
 	if (q->qdisc)
-		qdisc_destroy(q->qdisc);
+		qdisc_put(q->qdisc);
 	dist_free(q->delay_dist);
+	dist_free(q->slot_dist);
 }
 
 static int dump_loss_model(const struct netem_sched_data *q,
@@ -880,7 +1160,7 @@ static int dump_loss_model(const struct netem_sched_data *q,
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_NETEM_LOSS);
+	nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -934,9 +1214,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_netem_reorder reorder;
 	struct tc_netem_corrupt corrupt;
 	struct tc_netem_rate rate;
+	struct tc_netem_slot slot;
 
-	qopt.latency = q->latency;
-	qopt.jitter = q->jitter;
+	qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency),
+			     UINT_MAX);
+	qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter),
+			    UINT_MAX);
 	qopt.limit = q->limit;
 	qopt.loss = q->loss;
 	qopt.gap = q->gap;
@@ -944,6 +1227,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
 		goto nla_put_failure;
 
+	if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency))
+		goto nla_put_failure;
+
+	if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter))
+		goto nla_put_failure;
+
 	cor.delay_corr = q->delay_cor.rho;
 	cor.loss_corr = q->loss_cor.rho;
 	cor.dup_corr = q->dup_cor.rho;
@@ -960,7 +1249,14 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt))
 		goto nla_put_failure;
 
-	rate.rate = q->rate;
+	if (q->rate >= (1ULL << 32)) {
+		if (nla_put_u64_64bit(skb, TCA_NETEM_RATE64, q->rate,
+				      TCA_NETEM_PAD))
+			goto nla_put_failure;
+		rate.rate = ~0U;
+	} else {
+		rate.rate = q->rate;
+	}
 	rate.packet_overhead = q->packet_overhead;
 	rate.cell_size = q->cell_size;
 	rate.cell_overhead = q->cell_overhead;
@@ -973,6 +1269,21 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (dump_loss_model(q, skb) != 0)
 		goto nla_put_failure;
 
+	if (q->slot_config.min_delay | q->slot_config.max_delay |
+	    q->slot_config.dist_jitter) {
+		slot = q->slot_config;
+		if (slot.max_packets == INT_MAX)
+			slot.max_packets = 0;
+		if (slot.max_bytes == INT_MAX)
+			slot.max_bytes = 0;
+		if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed,
+			      TCA_NETEM_PAD))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, nla);
 
 nla_put_failure:
@@ -995,19 +1306,11 @@ static int netem_dump_class(struct Qdisc *sch, unsigned long cl,
 }
 
 static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
-		     struct Qdisc **old)
+		     struct Qdisc **old, struct netlink_ext_ack *extack)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
@@ -1017,32 +1320,23 @@ static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg)
 	return q->qdisc;
 }
 
-static unsigned long netem_get(struct Qdisc *sch, u32 classid)
+static unsigned long netem_find(struct Qdisc *sch, u32 classid)
 {
 	return 1;
 }
 
-static void netem_put(struct Qdisc *sch, unsigned long arg)
-{
-}
-
 static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 {
 	if (!walker->stop) {
-		if (walker->count >= walker->skip)
-			if (walker->fn(sch, 1, walker) < 0) {
-				walker->stop = 1;
-				return;
-			}
-		walker->count++;
+		if (!tc_qdisc_stats_dump(sch, 1, walker))
+			return;
 	}
 }
 
 static const struct Qdisc_class_ops netem_class_ops = {
 	.graft		=	netem_graft,
 	.leaf		=	netem_leaf,
-	.get		=	netem_get,
-	.put		=	netem_put,
+	.find		=	netem_find,
 	.walk		=	netem_walk,
 	.dump		=	netem_dump_class,
 };
@@ -1054,7 +1348,6 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = {
 	.enqueue	=	netem_enqueue,
 	.dequeue	=	netem_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	netem_drop,
 	.init		=	netem_init,
 	.reset		=	netem_reset,
 	.destroy	=	netem_destroy,
@@ -1062,6 +1355,7 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = {
 	.dump		=	netem_dump,
 	.owner		=	THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("netem");
 
 
 static int __init netem_module_init(void)
@@ -1076,3 +1370,4 @@ static void __exit netem_module_exit(void)
 module_init(netem_module_init)
 module_exit(netem_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Network characteristics emulator qdisc");