1 files changed, 242 insertions, 149 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d8fd8676fc72..638948be4c50 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -19,6 +19,7 @@
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
+#include <linux/xarray.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -36,8 +37,23 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_MISSED,
+	__QDISC_STATE_DRAINING,
 };
 
+enum qdisc_state2_t {
+	/* Only for !TCQ_F_NOLOCK qdisc. Never access it directly.
+	 * Use qdisc_run_begin/end() or qdisc_is_running() instead.
+	 */
+	__QDISC_STATE2_RUNNING,
+};
+
+#define QDISC_STATE_MISSED	BIT(__QDISC_STATE_MISSED)
+#define QDISC_STATE_DRAINING	BIT(__QDISC_STATE_DRAINING)
+
+#define QDISC_STATE_NON_EMPTY	(QDISC_STATE_MISSED | \
+					QDISC_STATE_DRAINING)
+
 struct qdisc_size_table {
 	struct rcu_head		rcu;
 	struct list_head	list;
@@ -89,7 +105,7 @@ struct Qdisc {
 	struct netdev_queue	*dev_queue;
 
 	struct net_rate_estimator __rcu *rate_est;
-	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_basic_sync __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
 	int			pad;
 	refcount_t		refcnt;
@@ -99,20 +115,20 @@ struct Qdisc {
 	 */
 	struct sk_buff_head	gso_skb ____cacheline_aligned_in_smp;
 	struct qdisc_skb_head	q;
-	struct gnet_stats_basic_packed bstats;
-	seqcount_t		running;
+	struct gnet_stats_basic_sync bstats;
 	struct gnet_stats_queue	qstats;
+	int                     owner;
 	unsigned long		state;
+	unsigned long		state2; /* must be written under qdisc spinlock */
 	struct Qdisc            *next_sched;
 	struct sk_buff_head	skb_bad_txq;
 
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 	spinlock_t		seqlock;
 
-	/* for NOLOCK qdisc, true if there are no enqueued skbs */
-	bool			empty;
 	struct rcu_head		rcu;
-
+	netdevice_tracker	dev_tracker;
+	struct lock_class_key	root_lock_key;
 	/* private data */
 	long privdata[] ____cacheline_aligned;
 };
@@ -124,6 +140,13 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
 	refcount_inc(&qdisc->refcnt);
 }
 
+static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN)
+		return true;
+	return refcount_dec_if_one(&qdisc->refcnt);
+}
+
 /* Intended to be used by unlocked users, when concurrent qdisc release is
  * possible.
  */
@@ -137,11 +160,20 @@ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc)
 	return NULL;
 }
 
+/* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc
+ * root_lock section, or provide their own memory barriers -- ordering
+ * against qdisc_run_begin/end() atomic bit operations.
+ */
 static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK)
 		return spin_is_locked(&qdisc->seqlock);
-	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
+	return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2);
+}
+
+static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc)
+{
+	return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY);
 }
 
 static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
@@ -152,32 +184,53 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
 static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 {
 	if (qdisc_is_percpu_stats(qdisc))
-		return READ_ONCE(qdisc->empty);
+		return nolock_qdisc_is_empty(qdisc);
 	return !READ_ONCE(qdisc->q.qlen);
 }
 
+/* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with
+ * the qdisc root lock acquired.
+ */
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
-		if (!spin_trylock(&qdisc->seqlock))
+		if (spin_trylock(&qdisc->seqlock))
+			return true;
+
+		/* No need to insist if the MISSED flag was already set.
+		 * Note that test_and_set_bit() also gives us memory ordering
+		 * guarantees wrt potential earlier enqueue() and below
+		 * spin_trylock(), both of which are necessary to prevent races
+		 */
+		if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state))
 			return false;
-		WRITE_ONCE(qdisc->empty, false);
-	} else if (qdisc_is_running(qdisc)) {
-		return false;
+
+		/* Try to take the lock again to make sure that we will either
+		 * grab it or the CPU that still has it will see MISSED set
+		 * when testing it in qdisc_run_end()
+		 */
+		return spin_trylock(&qdisc->seqlock);
 	}
-	/* Variant of write_seqcount_begin() telling lockdep a trylock
-	 * was attempted.
-	 */
-	raw_write_seqcount_begin(&qdisc->running);
-	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
-	return true;
+	return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2);
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
-	write_seqcount_end(&qdisc->running);
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc->flags & TCQ_F_NOLOCK) {
 		spin_unlock(&qdisc->seqlock);
+
+		/* spin_unlock() only has store-release semantic. The unlock
+		 * and test_bit() ordering is a store-load ordering, so a full
+		 * memory barrier is needed here.
+		 */
+		smp_mb();
+
+		if (unlikely(test_bit(__QDISC_STATE_MISSED,
+				      &qdisc->state)))
+			__netif_schedule(qdisc);
+	} else {
+		__clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2);
+	}
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -187,12 +240,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
 
 static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
 {
-#ifdef CONFIG_BQL
-	/* Non-BQL migrated drivers will return 0, too. */
-	return dql_avail(&txq->dql);
-#else
-	return 0;
-#endif
+	return netdev_queue_dql_avail(txq);
 }
 
 struct Qdisc_class_ops {
@@ -210,7 +258,8 @@ struct Qdisc_class_ops {
 	int			(*change)(struct Qdisc *, u32, u32,
 					struct nlattr **, unsigned long *,
 					struct netlink_ext_ack *);
-	int			(*delete)(struct Qdisc *, unsigned long);
+	int			(*delete)(struct Qdisc *, unsigned long,
+					  struct netlink_ext_ack *);
 	void			(*walk)(struct Qdisc *, struct qdisc_walker * arg);
 
 	/* Filter manipulation */
@@ -257,6 +306,8 @@ struct Qdisc_ops {
 					  struct netlink_ext_ack *extack);
 	void			(*attach)(struct Qdisc *sch);
 	int			(*change_tx_queue_len)(struct Qdisc *, unsigned int);
+	void			(*change_real_num_tx)(struct Qdisc *sch,
+						      unsigned int new_real_tx);
 
 	int			(*dump)(struct Qdisc *, struct sk_buff *);
 	int			(*dump_stats)(struct Qdisc *, struct gnet_dump *);
@@ -271,7 +322,6 @@ struct Qdisc_ops {
 	struct module		*owner;
 };
 
-
 struct tcf_result {
 	union {
 		struct {
@@ -279,12 +329,6 @@ struct tcf_result {
 			u32		classid;
 		};
 		const struct tcf_proto *goto_tp;
-
-		/* used in the skb_tc_reinsert function */
-		struct {
-			bool		ingress;
-			struct gnet_stats_queue *qstats;
-		};
 	};
 };
 
@@ -306,7 +350,7 @@ struct tcf_proto_ops {
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
-					void **, bool, bool,
+					void **, u32,
 					struct netlink_ext_ack *);
 	int			(*delete)(struct tcf_proto *tp, void *arg,
 					  bool *last, bool rtnl_held,
@@ -328,6 +372,12 @@ struct tcf_proto_ops {
 						struct nlattr **tca,
 						struct netlink_ext_ack *extack);
 	void			(*tmplt_destroy)(void *tmplt_priv);
+	void			(*tmplt_reoffload)(struct tcf_chain *chain,
+						   bool add,
+						   flow_setup_cb_t *cb,
+						   void *cb_priv);
+	struct tcf_exts *	(*get_exts)(const struct tcf_proto *tp,
+					    u32 handle);
 
 	/* rtnetlink specific */
 	int			(*dump)(struct net*, struct tcf_proto*, void *,
@@ -374,6 +424,8 @@ struct tcf_proto {
 	 */
 	spinlock_t		lock;
 	bool			deleting;
+	bool			counted;
+	bool			usesw;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
 	struct hlist_node	destroy_ht_node;
@@ -387,7 +439,6 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
-	u16			mru;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
@@ -409,6 +460,7 @@ struct tcf_chain {
 };
 
 struct tcf_block {
+	struct xarray ports; /* datapath accessible */
 	/* Lock protects tcf_block and lifetime-management data of chains
 	 * attached to the block (refcnt, action_refcnt, explicitly_created).
 	 */
@@ -423,6 +475,7 @@ struct tcf_block {
 	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
+	atomic_t useswcnt;
 	atomic_t offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
 	unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */
@@ -435,7 +488,8 @@ struct tcf_block {
 	struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
 };
 
-#ifdef CONFIG_PROVE_LOCKING
+struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index);
+
 static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
 {
 	return lockdep_is_held(&chain->filter_chain_lock);
@@ -445,17 +499,6 @@ static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
 {
 	return lockdep_is_held(&tp->lock);
 }
-#else
-static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain)
-{
-	return true;
-}
-
-static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
-{
-	return true;
-}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
 
 #define tcf_chain_dereference(p, chain)					\
 	rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain))
@@ -471,11 +514,6 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
-static inline int qdisc_qlen_cpu(const struct Qdisc *q)
-{
-	return this_cpu_ptr(q->cpu_qstats)->qlen;
-}
-
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
@@ -520,26 +558,7 @@ static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc)
 
 static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc)
 {
-	return qdisc->dev_queue->qdisc_sleeping;
-}
-
-/* The qdisc root lock is a mechanism by which to top level
- * of a qdisc tree can be locked from any qdisc node in the
- * forest.  This allows changing the configuration of some
- * aspect of the qdisc tree while blocking out asynchronous
- * qdisc access in the packet processing paths.
- *
- * It is only legal to do this when the root will not change
- * on us.  Otherwise we'll potentially lock the wrong qdisc
- * root.  This is enforced by holding the RTNL semaphore, which
- * all users of this lock accessor must do.
- */
-static inline spinlock_t *qdisc_root_lock(const struct Qdisc *qdisc)
-{
-	struct Qdisc *root = qdisc_root(qdisc);
-
-	ASSERT_RTNL();
-	return qdisc_lock(root);
+	return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping);
 }
 
 static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
@@ -550,32 +569,31 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
 	return qdisc_lock(root);
 }
 
-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
-{
-	struct Qdisc *root = qdisc_root_sleeping(qdisc);
-
-	ASSERT_RTNL();
-	return &root->running;
-}
-
 static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc)
 {
 	return qdisc->dev_queue->dev;
 }
 
-static inline void sch_tree_lock(const struct Qdisc *q)
+static inline void sch_tree_lock(struct Qdisc *q)
 {
-	spin_lock_bh(qdisc_root_sleeping_lock(q));
+	if (q->flags & TCQ_F_MQROOT)
+		spin_lock_bh(qdisc_lock(q));
+	else
+		spin_lock_bh(qdisc_root_sleeping_lock(q));
 }
 
-static inline void sch_tree_unlock(const struct Qdisc *q)
+static inline void sch_tree_unlock(struct Qdisc *q)
 {
-	spin_unlock_bh(qdisc_root_sleeping_lock(q));
+	if (q->flags & TCQ_F_MQROOT)
+		spin_unlock_bh(qdisc_lock(q));
+	else
+		spin_unlock_bh(qdisc_root_sleeping_lock(q));
 }
 
 extern struct Qdisc noop_qdisc;
 extern struct Qdisc_ops noop_qdisc_ops;
 extern struct Qdisc_ops pfifo_fast_ops;
+extern const u8 sch_default_prio2band[TC_PRIO_MAX + 1];
 extern struct Qdisc_ops mq_qdisc_ops;
 extern struct Qdisc_ops noqueue_qdisc_ops;
 extern const struct Qdisc_ops *default_qdisc_ops;
@@ -588,6 +606,7 @@ get_default_qdisc_ops(const struct net_device *dev, int ntx)
 
 struct Qdisc_class_common {
 	u32			classid;
+	unsigned int		filter_cnt;
 	struct hlist_node	hnode;
 };
 
@@ -622,6 +641,31 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id)
 	return NULL;
 }
 
+static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl)
+{
+	return cl->filter_cnt > 0;
+}
+
+static inline void qdisc_class_get(struct Qdisc_class_common *cl)
+{
+	unsigned int res;
+
+	if (check_add_overflow(cl->filter_cnt, 1, &res))
+		WARN(1, "Qdisc class overflow");
+
+	cl->filter_cnt = res;
+}
+
+static inline void qdisc_class_put(struct Qdisc_class_common *cl)
+{
+	unsigned int res;
+
+	if (check_sub_overflow(cl->filter_cnt, 1, &res))
+		WARN(1, "Qdisc class underflow");
+
+	cl->filter_cnt = res;
+}
+
 static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid)
 {
 	u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY;
@@ -638,6 +682,8 @@ void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
 void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
 
 int dev_qdisc_change_tx_queue_len(struct net_device *dev);
+void dev_qdisc_change_real_num_tx(struct net_device *dev,
+				  unsigned int new_real_tx);
 void dev_init_scheduler(struct net_device *dev);
 void dev_shutdown(struct net_device *dev);
 void dev_activate(struct net_device *dev);
@@ -646,6 +692,7 @@ void dev_deactivate_many(struct list_head *head);
 struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
+void qdisc_destroy(struct Qdisc *qdisc);
 void qdisc_put(struct Qdisc *qdisc);
 void qdisc_put_unlocked(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len);
@@ -673,6 +720,9 @@ qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
 {
 }
 #endif
+void qdisc_offload_query_caps(struct net_device *dev,
+			      enum tc_setup_type type,
+			      void *caps, size_t caps_len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack);
@@ -686,7 +736,7 @@ int skb_do_redirect(struct sk_buff *);
 
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	return skb->tc_at_ingress;
 #else
 	return false;
@@ -745,12 +795,22 @@ static inline bool qdisc_tx_changing(const struct net_device *dev)
 
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-		if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping)
+
+		if (rcu_access_pointer(txq->qdisc) !=
+		    rcu_access_pointer(txq->qdisc_sleeping))
 			return true;
 	}
 	return false;
 }
 
+/* "noqueue" qdisc identified by not having any enqueue, see noqueue_init() */
+static inline bool qdisc_txq_has_no_queue(const struct netdev_queue *txq)
+{
+	struct Qdisc *qdisc = rcu_access_pointer(txq->qdisc);
+
+	return qdisc->enqueue == NULL;
+}
+
 /* Is the device using the noop qdisc on all queues?  */
 static inline bool qdisc_tx_is_noop(const struct net_device *dev)
 {
@@ -795,18 +855,19 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb,
 static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 				struct sk_buff **to_free)
 {
-	qdisc_calculate_pkt_len(skb, sch);
 	return sch->enqueue(skb, sch, to_free);
 }
 
-static inline void _bstats_update(struct gnet_stats_basic_packed *bstats,
-				  __u64 bytes, __u32 packets)
+static inline void _bstats_update(struct gnet_stats_basic_sync *bstats,
+				  __u64 bytes, __u64 packets)
 {
-	bstats->bytes += bytes;
-	bstats->packets += packets;
+	u64_stats_update_begin(&bstats->syncp);
+	u64_stats_add(&bstats->bytes, bytes);
+	u64_stats_add(&bstats->packets, packets);
+	u64_stats_update_end(&bstats->syncp);
 }
 
-static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
+static inline void bstats_update(struct gnet_stats_basic_sync *bstats,
 				 const struct sk_buff *skb)
 {
 	_bstats_update(bstats,
@@ -814,26 +875,10 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
 		       skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1);
 }
 
-static inline void _bstats_cpu_update(struct gnet_stats_basic_cpu *bstats,
-				      __u64 bytes, __u32 packets)
-{
-	u64_stats_update_begin(&bstats->syncp);
-	_bstats_update(&bstats->bstats, bytes, packets);
-	u64_stats_update_end(&bstats->syncp);
-}
-
-static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats,
-				     const struct sk_buff *skb)
-{
-	u64_stats_update_begin(&bstats->syncp);
-	bstats_update(&bstats->bstats, skb);
-	u64_stats_update_end(&bstats->syncp);
-}
-
 static inline void qdisc_bstats_cpu_update(struct Qdisc *sch,
 					   const struct sk_buff *skb)
 {
-	bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb);
+	bstats_update(this_cpu_ptr(sch->cpu_bstats), skb);
 }
 
 static inline void qdisc_bstats_update(struct Qdisc *sch,
@@ -922,21 +967,12 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch,  __u32 *qlen,
 					     __u32 *backlog)
 {
 	struct gnet_stats_queue qstats = { 0 };
-	__u32 len = qdisc_qlen_sum(sch);
 
-	__gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len);
-	*qlen = qstats.qlen;
+	gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats);
+	*qlen = qstats.qlen + qdisc_qlen(sch);
 	*backlog = qstats.backlog;
 }
 
-static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
-{
-	__u32 qlen, backlog;
-
-	qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
-	qdisc_tree_reduce_backlog(sch, qlen, backlog);
-}
-
 static inline void qdisc_purge_queue(struct Qdisc *sch)
 {
 	__u32 qlen, backlog;
@@ -946,13 +982,6 @@ static inline void qdisc_purge_queue(struct Qdisc *sch)
 	qdisc_tree_reduce_backlog(sch, qlen, backlog);
 }
 
-static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh)
-{
-	qh->head = NULL;
-	qh->tail = NULL;
-	qh->qlen = 0;
-}
-
 static inline void __qdisc_enqueue_tail(struct sk_buff *skb,
 					struct qdisc_skb_head *qh)
 {
@@ -1002,6 +1031,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh)
 	return skb;
 }
 
+static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct)
+{
+	struct sk_buff *skb;
+
+	skb = __skb_dequeue(&sch->gso_skb);
+	if (skb) {
+		sch->q.qlen--;
+		return skb;
+	}
+	if (direct)
+		return __qdisc_dequeue_head(&sch->q);
+	else
+		return sch->dequeue(sch);
+}
+
 static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 {
 	struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
@@ -1014,6 +1058,37 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 	return skb;
 }
 
+struct tc_skb_cb {
+	struct qdisc_skb_cb qdisc_cb;
+	u32 drop_reason;
+
+	u16 zone; /* Only valid if post_ct = true */
+	u16 mru;
+	u8 post_ct:1;
+	u8 post_ct_snat:1;
+	u8 post_ct_dnat:1;
+};
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
+{
+	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
+	return cb;
+}
+
+static inline enum skb_drop_reason
+tcf_get_drop_reason(const struct sk_buff *skb)
+{
+	return tc_skb_cb(skb)->drop_reason;
+}
+
+static inline void tcf_set_drop_reason(const struct sk_buff *skb,
+				       enum skb_drop_reason reason)
+{
+	tc_skb_cb(skb)->drop_reason = reason;
+}
+
 /* Instead of calling kfree_skb() while root qdisc lock is held,
  * queue the skb for future freeing at end of __dev_xmit_skb()
  */
@@ -1143,7 +1218,6 @@ static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh)
 static inline void qdisc_reset_queue(struct Qdisc *sch)
 {
 	__qdisc_reset_queue(&sch->q);
-	sch->qstats.backlog = 0;
 }
 
 static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
@@ -1155,7 +1229,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL)
-		qdisc_tree_flush_backlog(old);
+		qdisc_purge_queue(old);
 	sch_tree_unlock(sch);
 
 	return old;
@@ -1185,6 +1259,14 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
+static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch,
+				    struct sk_buff **to_free,
+				    enum skb_drop_reason reason)
+{
+	tcf_set_drop_reason(skb, reason);
+	return qdisc_drop(skb, sch, to_free);
+}
+
 static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
 				 struct sk_buff **to_free)
 {
@@ -1194,24 +1276,11 @@ static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
-/* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
-   long it will take to send a packet given its size.
- */
-static inline u32 qdisc_l2t(struct qdisc_rate_table* rtab, unsigned int pktlen)
-{
-	int slot = pktlen + rtab->rate.cell_align + rtab->rate.overhead;
-	if (slot < 0)
-		slot = 0;
-	slot >>= rtab->rate.cell_log;
-	if (slot > 255)
-		return rtab->data[255]*(slot >> 8) + rtab->data[slot & 0xFF];
-	return rtab->data[slot];
-}
-
 struct psched_ratecfg {
 	u64	rate_bytes_ps; /* bytes per second */
 	u32	mult;
 	u16	overhead;
+	u16	mpu;
 	u8	linklayer;
 	u8	shift;
 };
@@ -1221,6 +1290,9 @@ static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
 {
 	len += r->overhead;
 
+	if (len < r->mpu)
+		len = r->mpu;
+
 	if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
 		return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
 
@@ -1243,24 +1315,39 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
 	res->rate = min_t(u64, r->rate_bytes_ps, ~0U);
 
 	res->overhead = r->overhead;
+	res->mpu = r->mpu;
 	res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
 }
 
+struct psched_pktrate {
+	u64	rate_pkts_ps; /* packets per second */
+	u32	mult;
+	u8	shift;
+};
+
+static inline u64 psched_pkt2t_ns(const struct psched_pktrate *r,
+				  unsigned int pkt_num)
+{
+	return ((u64)pkt_num * r->mult) >> r->shift;
+}
+
+void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64);
+
 /* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
  * The fast path only needs to access filter list and to update stats
  */
 struct mini_Qdisc {
 	struct tcf_proto *filter_list;
 	struct tcf_block *block;
-	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_basic_sync __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
-	struct rcu_head rcu;
+	unsigned long rcu_state;
 };
 
 static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq,
 						const struct sk_buff *skb)
 {
-	bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb);
+	bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb);
 }
 
 static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq)
@@ -1281,9 +1368,15 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
 				struct tcf_block *block);
 
-static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
+void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx);
+
+int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+
+/* Make sure qdisc is no longer in SCHED state. */
+static inline void qdisc_synchronize(const struct Qdisc *q)
 {
-	return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb);
+	while (test_bit(__QDISC_STATE_SCHED, &q->state))
+		msleep(1);
 }
 
 #endif