1 files changed, 396 insertions, 158 deletions

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index edea8cefec6..1af2f73906d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -17,13 +17,14 @@
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/ipv6.h>
 #include <linux/skbuff.h>
 #include <linux/jhash.h>
 #include <linux/slab.h>
-#include <net/ip.h>
+#include <linux/vmalloc.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/flow_keys.h>
+#include <net/red.h>
 
 
 /*	Stochastic Fairness Queuing algorithm.
@@ -66,34 +67,36 @@
 	SFQ is superior for this purpose.
 
 	IMPLEMENTATION:
-	This implementation limits maximal queue length to 128;
-	max mtu to 2^18-1; max 128 flows, number of hash buckets to 1024.
-	The only goal of this restrictions was that all data
-	fit into one 4K page on 32bit arches.
+	This implementation limits :
+	- maximal queue length per flow to 127 packets.
+	- max mtu to 2^18-1;
+	- max 65408 flows,
+	- number of hash buckets to 65536.
 
 	It is easy to increase these values, but not in flight.  */
 
-#define SFQ_DEPTH		128 /* max number of packets per flow */
-#define SFQ_SLOTS		128 /* max number of flows */
-#define SFQ_EMPTY_SLOT		255
-#define SFQ_HASH_DIVISOR	1024
+#define SFQ_MAX_DEPTH		127 /* max number of packets per flow */
+#define SFQ_DEFAULT_FLOWS	128
+#define SFQ_MAX_FLOWS		(0x10000 - SFQ_MAX_DEPTH - 1) /* max number of flows */
+#define SFQ_EMPTY_SLOT		0xffff
+#define SFQ_DEFAULT_HASH_DIVISOR 1024
+
 /* We use 16 bits to store allot, and want to handle packets up to 64K
  * Scale allot by 8 (1<<3) so that no overflow occurs.
  */
 #define SFQ_ALLOT_SHIFT		3
 #define SFQ_ALLOT_SIZE(X)	DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT)
 
-/* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
-typedef unsigned char sfq_index;
+/* This type should contain at least SFQ_MAX_DEPTH + 1 + SFQ_MAX_FLOWS values */
+typedef u16 sfq_index;
 
 /*
  * We dont use pointers to save space.
- * Small indexes [0 ... SFQ_SLOTS - 1] are 'pointers' to slots[] array
- * while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1]
+ * Small indexes [0 ... SFQ_MAX_FLOWS - 1] are 'pointers' to slots[] array
+ * while following values [SFQ_MAX_FLOWS ... SFQ_MAX_FLOWS + SFQ_MAX_DEPTH]
  * are 'pointers' to dep[] array
  */
-struct sfq_head
-{
+struct sfq_head {
 	sfq_index	next;
 	sfq_index	prev;
 };
@@ -102,29 +105,45 @@ struct sfq_slot {
 	struct sk_buff	*skblist_next;
 	struct sk_buff	*skblist_prev;
 	sfq_index	qlen; /* number of skbs in skblist */
-	sfq_index	next; /* next slot in sfq chain */
+	sfq_index	next; /* next slot in sfq RR chain */
 	struct sfq_head dep; /* anchor in dep[] chains */
 	unsigned short	hash; /* hash value (index in ht[]) */
 	short		allot; /* credit for this slot */
+
+	unsigned int    backlog;
+	struct red_vars vars;
 };
 
-struct sfq_sched_data
-{
-/* Parameters */
-	int		perturb_period;
-	unsigned	quantum;	/* Allotment per round: MUST BE >= MTU */
-	int		limit;
+struct sfq_sched_data {
+/* frequently used fields */
+	int		limit;		/* limit of total number of packets in this qdisc */
+	unsigned int	divisor;	/* number of slots in hash table */
+	u8		headdrop;
+	u8		maxdepth;	/* limit of packets per flow */
 
-/* Variables */
-	struct tcf_proto *filter_list;
-	struct timer_list perturb_timer;
 	u32		perturbation;
-	sfq_index	cur_depth;	/* depth of longest slot */
+	u8		cur_depth;	/* depth of longest slot */
+	u8		flags;
 	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
+	struct tcf_proto *filter_list;
+	sfq_index	*ht;		/* Hash table ('divisor' slots) */
+	struct sfq_slot	*slots;		/* Flows table ('maxflows' entries) */
+
+	struct red_parms *red_parms;
+	struct tc_sfqred_stats stats;
 	struct sfq_slot *tail;		/* current slot in round */
-	sfq_index	ht[SFQ_HASH_DIVISOR];	/* Hash table */
-	struct sfq_slot	slots[SFQ_SLOTS];
-	struct sfq_head	dep[SFQ_DEPTH];	/* Linked list of slots, indexed by depth */
+
+	struct sfq_head	dep[SFQ_MAX_DEPTH + 1];
+					/* Linked lists of slots, indexed by depth
+					 * dep[0] : list of unused flows
+					 * dep[1] : list of flows with 1 packet
+					 * dep[X] : list of flows with X packets
+					 */
+
+	unsigned int	maxflows;	/* number of flows in flows array */
+	int		perturb_period;
+	unsigned int	quantum;	/* Allotment per round: MUST BE >= MTU */
+	struct timer_list perturb_timer;
 };
 
 /*
@@ -132,66 +151,35 @@ struct sfq_sched_data
  */
 static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index val)
 {
-	if (val < SFQ_SLOTS)
+	if (val < SFQ_MAX_FLOWS)
 		return &q->slots[val].dep;
-	return &q->dep[val - SFQ_SLOTS];
+	return &q->dep[val - SFQ_MAX_FLOWS];
 }
 
-static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
+/*
+ * In order to be able to quickly rehash our queue when timer changes
+ * q->perturbation, we store flow_keys in skb->cb[]
+ */
+struct sfq_skb_cb {
+       struct flow_keys        keys;
+};
+
+static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb)
 {
-	return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1);
+	qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb));
+	return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data;
 }
 
-static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
+static unsigned int sfq_hash(const struct sfq_sched_data *q,
+			     const struct sk_buff *skb)
 {
-	u32 h, h2;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-	{
-		const struct iphdr *iph;
-		int poff;
-
-		if (!pskb_network_may_pull(skb, sizeof(*iph)))
-			goto err;
-		iph = ip_hdr(skb);
-		h = (__force u32)iph->daddr;
-		h2 = (__force u32)iph->saddr ^ iph->protocol;
-		if (iph->frag_off & htons(IP_MF|IP_OFFSET))
-			break;
-		poff = proto_ports_offset(iph->protocol);
-		if (poff >= 0 &&
-		    pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) {
-			iph = ip_hdr(skb);
-			h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff);
-		}
-		break;
-	}
-	case htons(ETH_P_IPV6):
-	{
-		struct ipv6hdr *iph;
-		int poff;
-
-		if (!pskb_network_may_pull(skb, sizeof(*iph)))
-			goto err;
-		iph = ipv6_hdr(skb);
-		h = (__force u32)iph->daddr.s6_addr32[3];
-		h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr;
-		poff = proto_ports_offset(iph->nexthdr);
-		if (poff >= 0 &&
-		    pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) {
-			iph = ipv6_hdr(skb);
-			h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff);
-		}
-		break;
-	}
-	default:
-err:
-		h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol;
-		h2 = (unsigned long)skb->sk;
-	}
+	const struct flow_keys *keys = &sfq_skb_cb(skb)->keys;
+	unsigned int hash;
 
-	return sfq_fold_hash(q, h, h2);
+	hash = jhash_3words((__force u32)keys->dst,
+			    (__force u32)keys->src ^ keys->ip_proto,
+			    (__force u32)keys->ports, q->perturbation);
+	return hash & (q->divisor - 1);
 }
 
 static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
@@ -203,11 +191,13 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 
 	if (TC_H_MAJ(skb->priority) == sch->handle &&
 	    TC_H_MIN(skb->priority) > 0 &&
-	    TC_H_MIN(skb->priority) <= SFQ_HASH_DIVISOR)
+	    TC_H_MIN(skb->priority) <= q->divisor)
 		return TC_H_MIN(skb->priority);
 
-	if (!q->filter_list)
+	if (!q->filter_list) {
+		skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys);
 		return sfq_hash(q, skb) + 1;
+	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	result = tc_classify(skb, q->filter_list, &res);
@@ -221,35 +211,38 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 			return 0;
 		}
 #endif
-		if (TC_H_MIN(res.classid) <= SFQ_HASH_DIVISOR)
+		if (TC_H_MIN(res.classid) <= q->divisor)
 			return TC_H_MIN(res.classid);
 	}
 	return 0;
 }
 
 /*
- * x : slot number [0 .. SFQ_SLOTS - 1]
+ * x : slot number [0 .. SFQ_MAX_FLOWS - 1]
  */
 static inline void sfq_link(struct sfq_sched_data *q, sfq_index x)
 {
 	sfq_index p, n;
-	int qlen = q->slots[x].qlen;
+	struct sfq_slot *slot = &q->slots[x];
+	int qlen = slot->qlen;
 
-	p = qlen + SFQ_SLOTS;
+	p = qlen + SFQ_MAX_FLOWS;
 	n = q->dep[qlen].next;
 
-	q->slots[x].dep.next = n;
-	q->slots[x].dep.prev = p;
+	slot->dep.next = n;
+	slot->dep.prev = p;
 
 	q->dep[qlen].next = x;		/* sfq_dep_head(q, p)->next = x */
 	sfq_dep_head(q, n)->prev = x;
 }
 
 #define sfq_unlink(q, x, n, p)			\
-	n = q->slots[x].dep.next;		\
-	p = q->slots[x].dep.prev;		\
-	sfq_dep_head(q, p)->next = n;		\
-	sfq_dep_head(q, n)->prev = p
+	do {					\
+		n = q->slots[x].dep.next;	\
+		p = q->slots[x].dep.prev;	\
+		sfq_dep_head(q, p)->next = n;	\
+		sfq_dep_head(q, n)->prev = p;	\
+	} while (0)
 
 
 static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x)
@@ -304,6 +297,7 @@ static inline struct sk_buff *slot_dequeue_head(struct sfq_slot *slot)
 
 static inline void slot_queue_init(struct sfq_slot *slot)
 {
+	memset(slot, 0, sizeof(*slot));
 	slot->skblist_prev = slot->skblist_next = (struct sk_buff *)slot;
 }
 
@@ -334,8 +328,9 @@ static unsigned int sfq_drop(struct Qdisc *sch)
 		x = q->dep[d].next;
 		slot = &q->slots[x];
 drop:
-		skb = slot_dequeue_tail(slot);
+		skb = q->headdrop ? slot_dequeue_head(slot) : slot_dequeue_tail(slot);
 		len = qdisc_pkt_len(skb);
+		slot->backlog -= len;
 		sfq_dec(q, x);
 		kfree_skb(skb);
 		sch->q.qlen--;
@@ -356,14 +351,33 @@ drop:
 	return 0;
 }
 
+/* Is ECN parameter configured */
+static int sfq_prob_mark(const struct sfq_sched_data *q)
+{
+	return q->flags & TC_RED_ECN;
+}
+
+/* Should packets over max threshold just be marked */
+static int sfq_hard_mark(const struct sfq_sched_data *q)
+{
+	return (q->flags & (TC_RED_ECN | TC_RED_HARDDROP)) == TC_RED_ECN;
+}
+
+static int sfq_headdrop(const struct sfq_sched_data *q)
+{
+	return q->headdrop;
+}
+
 static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned int hash;
-	sfq_index x;
+	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
+	struct sk_buff *head;
+	int delta;
 
 	hash = sfq_classify(skb, sch, &ret);
 	if (hash == 0) {
@@ -378,18 +392,80 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	slot = &q->slots[x];
 	if (x == SFQ_EMPTY_SLOT) {
 		x = q->dep[0].next; /* get a free slot */
+		if (x >= SFQ_MAX_FLOWS)
+			return qdisc_drop(skb, sch);
 		q->ht[hash] = x;
 		slot = &q->slots[x];
 		slot->hash = hash;
+		slot->backlog = 0; /* should already be 0 anyway... */
+		red_set_vars(&slot->vars);
+		goto enqueue;
 	}
+	if (q->red_parms) {
+		slot->vars.qavg = red_calc_qavg_no_idle_time(q->red_parms,
+							&slot->vars,
+							slot->backlog);
+		switch (red_action(q->red_parms,
+				   &slot->vars,
+				   slot->vars.qavg)) {
+		case RED_DONT_MARK:
+			break;
 
-	/* If selected queue has length q->limit, do simple tail drop,
-	 * i.e. drop _this_ packet.
-	 */
-	if (slot->qlen >= q->limit)
-		return qdisc_drop(skb, sch);
+		case RED_PROB_MARK:
+			sch->qstats.overlimits++;
+			if (sfq_prob_mark(q)) {
+				/* We know we have at least one packet in queue */
+				if (sfq_headdrop(q) &&
+				    INET_ECN_set_ce(slot->skblist_next)) {
+					q->stats.prob_mark_head++;
+					break;
+				}
+				if (INET_ECN_set_ce(skb)) {
+					q->stats.prob_mark++;
+					break;
+				}
+			}
+			q->stats.prob_drop++;
+			goto congestion_drop;
+
+		case RED_HARD_MARK:
+			sch->qstats.overlimits++;
+			if (sfq_hard_mark(q)) {
+				/* We know we have at least one packet in queue */
+				if (sfq_headdrop(q) &&
+				    INET_ECN_set_ce(slot->skblist_next)) {
+					q->stats.forced_mark_head++;
+					break;
+				}
+				if (INET_ECN_set_ce(skb)) {
+					q->stats.forced_mark++;
+					break;
+				}
+			}
+			q->stats.forced_drop++;
+			goto congestion_drop;
+		}
+	}
 
+	if (slot->qlen >= q->maxdepth) {
+congestion_drop:
+		if (!sfq_headdrop(q))
+			return qdisc_drop(skb, sch);
+
+		/* We know we have at least one packet in queue */
+		head = slot_dequeue_head(slot);
+		delta = qdisc_pkt_len(head) - qdisc_pkt_len(skb);
+		sch->qstats.backlog -= delta;
+		slot->backlog -= delta;
+		qdisc_drop(head, sch);
+
+		slot_queue_add(slot, skb);
+		return NET_XMIT_CN;
+	}
+
+enqueue:
 	sch->qstats.backlog += qdisc_pkt_len(skb);
+	slot->backlog += qdisc_pkt_len(skb);
 	slot_queue_add(slot, skb);
 	sfq_inc(q, x);
 	if (slot->qlen == 1) {		/* The flow is new */
@@ -399,26 +475,28 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			slot->next = q->tail->next;
 			q->tail->next = x;
 		}
+		/* We put this flow at the end of our flow list.
+		 * This might sound unfair for a new flow to wait after old ones,
+		 * but we could endup servicing new flows only, and freeze old ones.
+		 */
 		q->tail = slot;
+		/* We could use a bigger initial quantum for new flows */
 		slot->allot = q->scaled_quantum;
 	}
 	if (++sch->q.qlen <= q->limit)
 		return NET_XMIT_SUCCESS;
 
+	qlen = slot->qlen;
 	sfq_drop(sch);
-	return NET_XMIT_CN;
-}
-
-static struct sk_buff *
-sfq_peek(struct Qdisc *sch)
-{
-	struct sfq_sched_data *q = qdisc_priv(sch);
-
-	/* No active slots */
-	if (q->tail == NULL)
-		return NULL;
+	/* Return Congestion Notification only if we dropped a packet
+	 * from this flow.
+	 */
+	if (qlen != slot->qlen)
+		return NET_XMIT_CN;
 
-	return q->slots[q->tail->next].skblist_next;
+	/* As we dropped a packet, better let upper stack know this */
+	qdisc_tree_decrease_qlen(sch, 1);
+	return NET_XMIT_SUCCESS;
 }
 
 static struct sk_buff *
@@ -446,7 +524,7 @@ next_slot:
 	qdisc_bstats_update(sch, skb);
 	sch->q.qlen--;
 	sch->qstats.backlog -= qdisc_pkt_len(skb);
-
+	slot->backlog -= qdisc_pkt_len(skb);
 	/* Is the slot empty? */
 	if (slot->qlen == 0) {
 		q->ht[slot->hash] = SFQ_EMPTY_SLOT;
@@ -471,12 +549,90 @@ sfq_reset(struct Qdisc *sch)
 		kfree_skb(skb);
 }
 
+/*
+ * When q->perturbation is changed, we rehash all queued skbs
+ * to avoid OOO (Out Of Order) effects.
+ * We dont use sfq_dequeue()/sfq_enqueue() because we dont want to change
+ * counters.
+ */
+static void sfq_rehash(struct Qdisc *sch)
+{
+	struct sfq_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+	int i;
+	struct sfq_slot *slot;
+	struct sk_buff_head list;
+	int dropped = 0;
+
+	__skb_queue_head_init(&list);
+
+	for (i = 0; i < q->maxflows; i++) {
+		slot = &q->slots[i];
+		if (!slot->qlen)
+			continue;
+		while (slot->qlen) {
+			skb = slot_dequeue_head(slot);
+			sfq_dec(q, i);
+			__skb_queue_tail(&list, skb);
+		}
+		slot->backlog = 0;
+		red_set_vars(&slot->vars);
+		q->ht[slot->hash] = SFQ_EMPTY_SLOT;
+	}
+	q->tail = NULL;
+
+	while ((skb = __skb_dequeue(&list)) != NULL) {
+		unsigned int hash = sfq_hash(q, skb);
+		sfq_index x = q->ht[hash];
+
+		slot = &q->slots[x];
+		if (x == SFQ_EMPTY_SLOT) {
+			x = q->dep[0].next; /* get a free slot */
+			if (x >= SFQ_MAX_FLOWS) {
+drop:				sch->qstats.backlog -= qdisc_pkt_len(skb);
+				kfree_skb(skb);
+				dropped++;
+				continue;
+			}
+			q->ht[hash] = x;
+			slot = &q->slots[x];
+			slot->hash = hash;
+		}
+		if (slot->qlen >= q->maxdepth)
+			goto drop;
+		slot_queue_add(slot, skb);
+		if (q->red_parms)
+			slot->vars.qavg = red_calc_qavg(q->red_parms,
+							&slot->vars,
+							slot->backlog);
+		slot->backlog += qdisc_pkt_len(skb);
+		sfq_inc(q, x);
+		if (slot->qlen == 1) {		/* The flow is new */
+			if (q->tail == NULL) {	/* It is the first flow */
+				slot->next = x;
+			} else {
+				slot->next = q->tail->next;
+				q->tail->next = x;
+			}
+			q->tail = slot;
+			slot->allot = q->scaled_quantum;
+		}
+	}
+	sch->q.qlen -= dropped;
+	qdisc_tree_decrease_qlen(sch, dropped);
+}
+
 static void sfq_perturbation(unsigned long arg)
 {
 	struct Qdisc *sch = (struct Qdisc *)arg;
 	struct sfq_sched_data *q = qdisc_priv(sch);
+	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
-	q->perturbation = net_random();
+	spin_lock(root_lock);
+	q->perturbation = prandom_u32();
+	if (!q->filter_list && q->tail)
+		sfq_rehash(sch);
+	spin_unlock(root_lock);
 
 	if (q->perturb_period)
 		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
@@ -486,17 +642,53 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
+	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
 	unsigned int qlen;
+	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
 		return -EINVAL;
-
+	if (opt->nla_len >= nla_attr_size(sizeof(*ctl_v1)))
+		ctl_v1 = nla_data(opt);
+	if (ctl->divisor &&
+	    (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
+		return -EINVAL;
+	if (ctl_v1 && ctl_v1->qth_min) {
+		p = kmalloc(sizeof(*p), GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+	}
 	sch_tree_lock(sch);
-	q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch));
-	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
+	if (ctl->quantum) {
+		q->quantum = ctl->quantum;
+		q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
+	}
 	q->perturb_period = ctl->perturb_period * HZ;
-	if (ctl->limit)
-		q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
+	if (ctl->flows)
+		q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
+	if (ctl->divisor) {
+		q->divisor = ctl->divisor;
+		q->maxflows = min_t(u32, q->maxflows, q->divisor);
+	}
+	if (ctl_v1) {
+		if (ctl_v1->depth)
+			q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
+		if (p) {
+			swap(q->red_parms, p);
+			red_set_parms(q->red_parms,
+				      ctl_v1->qth_min, ctl_v1->qth_max,
+				      ctl_v1->Wlog,
+				      ctl_v1->Plog, ctl_v1->Scell_log,
+				      NULL,
+				      ctl_v1->max_P);
+		}
+		q->flags = ctl_v1->flags;
+		q->headdrop = ctl_v1->headdrop;
+	}
+	if (ctl->limit) {
+		q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows);
+		q->maxflows = min_t(u32, q->maxflows, q->limit);
+	}
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
@@ -506,12 +698,39 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
 		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
-		q->perturbation = net_random();
+		q->perturbation = prandom_u32();
 	}
 	sch_tree_unlock(sch);
+	kfree(p);
 	return 0;
 }
 
+static void *sfq_alloc(size_t sz)
+{
+	void *ptr = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN);
+
+	if (!ptr)
+		ptr = vmalloc(sz);
+	return ptr;
+}
+
+static void sfq_free(void *addr)
+{
+	kvfree(addr);
+}
+
+static void sfq_destroy(struct Qdisc *sch)
+{
+	struct sfq_sched_data *q = qdisc_priv(sch);
+
+	tcf_destroy_chain(&q->filter_list);
+	q->perturb_period = 0;
+	del_timer_sync(&q->perturb_timer);
+	sfq_free(q->ht);
+	sfq_free(q->slots);
+	kfree(q->red_parms);
+}
+
 static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
@@ -521,58 +740,77 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->perturb_timer.data = (unsigned long)sch;
 	init_timer_deferrable(&q->perturb_timer);
 
-	for (i = 0; i < SFQ_HASH_DIVISOR; i++)
-		q->ht[i] = SFQ_EMPTY_SLOT;
-
-	for (i = 0; i < SFQ_DEPTH; i++) {
-		q->dep[i].next = i + SFQ_SLOTS;
-		q->dep[i].prev = i + SFQ_SLOTS;
+	for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) {
+		q->dep[i].next = i + SFQ_MAX_FLOWS;
+		q->dep[i].prev = i + SFQ_MAX_FLOWS;
 	}
 
-	q->limit = SFQ_DEPTH - 1;
+	q->limit = SFQ_MAX_DEPTH;
+	q->maxdepth = SFQ_MAX_DEPTH;
 	q->cur_depth = 0;
 	q->tail = NULL;
-	if (opt == NULL) {
-		q->quantum = psched_mtu(qdisc_dev(sch));
-		q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
-		q->perturb_period = 0;
-		q->perturbation = net_random();
-	} else {
+	q->divisor = SFQ_DEFAULT_HASH_DIVISOR;
+	q->maxflows = SFQ_DEFAULT_FLOWS;
+	q->quantum = psched_mtu(qdisc_dev(sch));
+	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
+	q->perturb_period = 0;
+	q->perturbation = prandom_u32();
+
+	if (opt) {
 		int err = sfq_change(sch, opt);
 		if (err)
 			return err;
 	}
 
-	for (i = 0; i < SFQ_SLOTS; i++) {
+	q->ht = sfq_alloc(sizeof(q->ht[0]) * q->divisor);
+	q->slots = sfq_alloc(sizeof(q->slots[0]) * q->maxflows);
+	if (!q->ht || !q->slots) {
+		sfq_destroy(sch);
+		return -ENOMEM;
+	}
+	for (i = 0; i < q->divisor; i++)
+		q->ht[i] = SFQ_EMPTY_SLOT;
+
+	for (i = 0; i < q->maxflows; i++) {
 		slot_queue_init(&q->slots[i]);
 		sfq_link(q, i);
 	}
+	if (q->limit >= 1)
+		sch->flags |= TCQ_F_CAN_BYPASS;
+	else
+		sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
-static void sfq_destroy(struct Qdisc *sch)
-{
-	struct sfq_sched_data *q = qdisc_priv(sch);
-
-	tcf_destroy_chain(&q->filter_list);
-	q->perturb_period = 0;
-	del_timer_sync(&q->perturb_timer);
-}
-
 static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_sfq_qopt opt;
-
-	opt.quantum = q->quantum;
-	opt.perturb_period = q->perturb_period / HZ;
-
-	opt.limit = q->limit;
-	opt.divisor = SFQ_HASH_DIVISOR;
-	opt.flows = q->limit;
+	struct tc_sfq_qopt_v1 opt;
+	struct red_parms *p = q->red_parms;
+
+	memset(&opt, 0, sizeof(opt));
+	opt.v0.quantum	= q->quantum;
+	opt.v0.perturb_period = q->perturb_period / HZ;
+	opt.v0.limit	= q->limit;
+	opt.v0.divisor	= q->divisor;
+	opt.v0.flows	= q->maxflows;
+	opt.depth	= q->maxdepth;
+	opt.headdrop	= q->headdrop;
+
+	if (p) {
+		opt.qth_min	= p->qth_min >> p->Wlog;
+		opt.qth_max	= p->qth_max >> p->Wlog;
+		opt.Wlog	= p->Wlog;
+		opt.Plog	= p->Plog;
+		opt.Scell_log	= p->Scell_log;
+		opt.max_P	= p->max_P;
+	}
+	memcpy(&opt.stats, &q->stats, sizeof(opt.stats));
+	opt.flags	= q->flags;
 
-	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
+		goto nla_put_failure;
 
 	return skb->len;
 
@@ -594,6 +832,8 @@ static unsigned long sfq_get(struct Qdisc *sch, u32 classid)
 static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
+	/* we cannot bypass queue discipline anymore */
+	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
@@ -624,15 +864,13 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	sfq_index idx = q->ht[cl - 1];
 	struct gnet_stats_queue qs = { 0 };
 	struct tc_sfq_xstats xstats = { 0 };
-	struct sk_buff *skb;
 
 	if (idx != SFQ_EMPTY_SLOT) {
 		const struct sfq_slot *slot = &q->slots[idx];
 
 		xstats.allot = slot->allot << SFQ_ALLOT_SHIFT;
 		qs.qlen = slot->qlen;
-		slot_queue_walk(slot, skb)
-			qs.backlog += qdisc_pkt_len(skb);
+		qs.backlog = slot->backlog;
 	}
 	if (gnet_stats_copy_queue(d, &qs) < 0)
 		return -1;
@@ -647,7 +885,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 	if (arg->stop)
 		return;
 
-	for (i = 0; i < SFQ_HASH_DIVISOR; i++) {
+	for (i = 0; i < q->divisor; i++) {
 		if (q->ht[i] == SFQ_EMPTY_SLOT ||
 		    arg->count < arg->skip) {
 			arg->count++;
@@ -679,7 +917,7 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = {
 	.priv_size	=	sizeof(struct sfq_sched_data),
 	.enqueue	=	sfq_enqueue,
 	.dequeue	=	sfq_dequeue,
-	.peek		=	sfq_peek,
+	.peek		=	qdisc_peek_dequeued,
 	.drop		=	sfq_drop,
 	.init		=	sfq_init,
 	.reset		=	sfq_reset,