static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
{
	struct net_device *dev = qdisc_dev(sch);
	unsigned long ntx = cl - 1;

	if (ntx >= dev->num_tx_queues)
		return NULL;
	return netdev_get_tx_queue(dev, ntx);
}

/*
 * NOTE: Called under qdisc_lock(q) with locally disabled BH.
 *
 * __QDISC_STATE_RUNNING guarantees only one CPU can process
 * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
 * this queue.
 *
 *  netif_tx_lock serializes accesses to device driver.
 *
 *  qdisc_lock(q) and netif_tx_lock are mutually exclusive,
 *  if one is grabbed, another must be free.
 *
 * Note, that this procedure can be called by a watchdog timer
 *
 * Returns to the caller:
 *				0  - queue is empty or throttled.
 *				>0 - queue is not empty.
 *
 */
static inline int qdisc_restart(struct Qdisc *q)
{
	struct netdev_queue *txq;
	int ret = NETDEV_TX_BUSY;
	struct net_device *dev;
	spinlock_t *root_lock;
	struct sk_buff *skb;

	/* Dequeue packet */
	//从队列上取下一个要发送的数据包.
	if (unlikely((skb = dequeue_skb(q)) == NULL))
		return 0;

	root_lock = qdisc_lock(q);

	/* And release qdisc */
	spin_unlock(root_lock);

	dev = qdisc_dev(q);
	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));

	HARD_TX_LOCK(dev, txq, smp_processor_id());
	//调用dev_hard_start_xmit吧数据包通过实际的链路发送出去...
	if (!netif_tx_queue_stopped(txq) &&
	    !netif_tx_queue_frozen(txq))
		ret = dev_hard_start_xmit(skb, dev, txq);
	HARD_TX_UNLOCK(dev, txq);

	spin_lock(root_lock);

	switch (ret) {
	case NETDEV_TX_OK:
		/* Driver sent out skb successfully */
		ret = qdisc_qlen(q);
		break;

	case NETDEV_TX_LOCKED:
		/* Driver try lock failed */
		ret = handle_dev_cpu_collision(skb, txq, q);
		break;

	default:
		/* Driver returned NETDEV_TX_BUSY - requeue skb */
		if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit()))
			printk(KERN_WARNING "BUG %s code %d qlen %d\n",
			       dev->name, ret, q->q.qlen);

		ret = dev_requeue_skb(skb, q);
		break;
	}

	if (ret && (netif_tx_queue_stopped(txq) ||
		    netif_tx_queue_frozen(txq)))
		ret = 0;

	return ret;
}

static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc)
{
	struct sk_buff_head *list = prio2list(skb, qdisc);

	if (skb_queue_len(list) < qdisc_dev(qdisc)->tx_queue_len) {
		qdisc->q.qlen++;
		return __qdisc_enqueue_tail(skb, qdisc, list);
	}

	return qdisc_drop(skb, qdisc);
}

static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct fifo_sched_data *q = qdisc_priv(sch);

	if (opt == NULL) {
		u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1;

		if (sch->ops == &bfifo_qdisc_ops)
			limit *= psched_mtu(qdisc_dev(sch));

		q->limit = limit;
	} else {

static void mq_destroy(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	struct mq_sched *priv = qdisc_priv(sch);
	unsigned int ntx;

	if (!priv->qdiscs)
		return;
	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
		qdisc_destroy(priv->qdiscs[ntx]);
	kfree(priv->qdiscs);
}

static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
					    struct tcmsg *tcm)
{
	unsigned int ntx = TC_H_MIN(tcm->tcm_parent);
	struct netdev_queue *dev_queue = mq_queue_get(sch, ntx);

	if (!dev_queue) {
		struct net_device *dev = qdisc_dev(sch);

		return netdev_get_tx_queue(dev, 0);
	}
	return dev_queue;
}

static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
{
	bool bypass;
	bool is_bfifo = sch->ops == &bfifo_qdisc_ops;

	if (opt == NULL) {
		u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1;

		if (is_bfifo)
			limit *= psched_mtu(qdisc_dev(sch));

		sch->limit = limit;
	} else {

static int gred_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct nlattr *tb[TCA_GRED_MAX + 1];
	int err;

	if (opt == NULL)
		return -EINVAL;

	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy);
	if (err < 0)
		return err;

	if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB])
		return -EINVAL;

	if (tb[TCA_GRED_LIMIT])
		sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
	else
		sch->limit = qdisc_dev(sch)->tx_queue_len
		             * psched_mtu(qdisc_dev(sch));

	return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
}

static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
{
	if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
		int band = prio2band[skb->priority & TC_PRIO_MAX];
		struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
		struct sk_buff_head *list = band2list(priv, band);

		priv->bitmap |= (1 << band);
		qdisc->q.qlen++;
		return __qdisc_enqueue_tail(skb, qdisc, list);
	}

	return qdisc_drop(skb, qdisc);
}

static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct sfq_sched_data *q = qdisc_priv(sch);
	int i;

	q->perturb_timer.function = sfq_perturbation;
	q->perturb_timer.data = (unsigned long)sch;
	init_timer_deferrable(&q->perturb_timer);

	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_MAX_DEPTH;
	q->maxdepth = SFQ_MAX_DEPTH;
	q->cur_depth = 0;
	q->tail = NULL;
	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;
	}

	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 int ingress_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct ingress_sched_data *q = qdisc_priv(sch);
	struct net_device *dev = qdisc_dev(sch);
	int err;

	err = tcf_block_get(&q->block, &dev->ingress_cl_list);
	if (err)
		return err;

	net_inc_ingress_queue();
	sch->flags |= TCQ_F_CPUSTATS;

	return 0;
}

static void mqprio_destroy(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	struct mqprio_sched *priv = qdisc_priv(sch);
	unsigned int ntx;

	if (priv->qdiscs) {
		for (ntx = 0;
		     ntx < dev->num_tx_queues && priv->qdiscs[ntx];
		     ntx++)
			qdisc_destroy(priv->qdiscs[ntx]);
		kfree(priv->qdiscs);
	}

	netdev_set_num_tc(dev, 0);
}

static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
			struct netlink_ext_ack *extack)
{
	struct ingress_sched_data *q = qdisc_priv(sch);
	struct net_device *dev = qdisc_dev(sch);

	net_inc_ingress_queue();

	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);

	q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
	q->block_info.chain_head_change = clsact_chain_head_change;
	q->block_info.chain_head_change_priv = &q->miniqp;

	return tcf_block_get_ext(&q->block, sch, &q->block_info, extack);
}

/*
 * NOTE: Called under qdisc_lock(q) with locally disabled BH.
 *
 * __QDISC_STATE_RUNNING guarantees only one CPU can process
 * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
 * this queue.
 *
 *  netif_tx_lock serializes accesses to device driver.
 *
 *  qdisc_lock(q) and netif_tx_lock are mutually exclusive,
 *  if one is grabbed, another must be free.
 *
 * Note, that this procedure can be called by a watchdog timer
 *
 * Returns to the caller:
 *				0  - queue is empty or throttled.
 *				>0 - queue is not empty.
 *
 */
static inline int qdisc_restart(struct Qdisc *q)
{
	struct netdev_queue *txq;
	struct net_device *dev;
	spinlock_t *root_lock;
	struct sk_buff *skb;

	/* Dequeue packet */
	skb = dequeue_skb(q);
	if (unlikely(!skb))
		return 0;
	WARN_ON_ONCE(skb_dst_is_noref(skb));
	root_lock = qdisc_lock(q);
	dev = qdisc_dev(q);
	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));

	return sch_direct_xmit(skb, q, dev, txq, root_lock);
}

/*
 * NOTE: Called under qdisc_lock(q) with locally disabled BH.
 *
 * __QDISC___STATE_RUNNING guarantees only one CPU can process
 * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
 * this queue.
 *
 *  netif_tx_lock serializes accesses to device driver.
 *
 *  qdisc_lock(q) and netif_tx_lock are mutually exclusive,
 *  if one is grabbed, another must be free.
 *
 * Note, that this procedure can be called by a watchdog timer
 *
 * Returns to the caller:
 *				0  - queue is empty or throttled.
 *				>0 - queue is not empty.
 *
 */
static inline int qdisc_restart(struct Qdisc *q, int *packets)
{
	struct netdev_queue *txq;
	struct net_device *dev;
	spinlock_t *root_lock;
	struct sk_buff *skb;
	bool validate;

	/* Dequeue packet */
	skb = dequeue_skb(q, &validate, packets);
	if (unlikely(!skb))
		return 0;

	root_lock = qdisc_lock(q);
	dev = qdisc_dev(q);
	txq = skb_get_tx_queue(dev, skb);

	return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
}

static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
{
	struct sk_buff *skb = q->gso_skb;

	if (unlikely(skb)) {
		struct net_device *dev = qdisc_dev(q);
		struct netdev_queue *txq;

		/* check the reason of requeuing without tx lock first */
		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
		if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq))
			q->gso_skb = NULL;
		else
			skb = NULL;
	} else {
		skb = q->dequeue(q);
	}

	return skb;
}

static void gred_offload(struct Qdisc *sch, enum tc_gred_command command)
{
	struct gred_sched *table = qdisc_priv(sch);
	struct net_device *dev = qdisc_dev(sch);
	struct tc_gred_qopt_offload opt = {
		.command	= command,
		.handle		= sch->handle,
		.parent		= sch->parent,
	};

	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
		return;

	if (command == TC_GRED_REPLACE) {
		unsigned int i;

		opt.set.grio_on = gred_rio_mode(table);
		opt.set.wred_on = gred_wred_mode(table);
		opt.set.dp_cnt = table->DPs;
		opt.set.dp_def = table->def;

		for (i = 0; i < table->DPs; i++) {
			struct gred_sched_data *q = table->tab[i];

			if (!q)
				continue;
			opt.set.tab[i].present = true;
			opt.set.tab[i].limit = q->limit;
			opt.set.tab[i].prio = q->prio;
			opt.set.tab[i].min = q->parms.qth_min >> q->parms.Wlog;
			opt.set.tab[i].max = q->parms.qth_max >> q->parms.Wlog;
			opt.set.tab[i].is_ecn = gred_use_ecn(q);
			opt.set.tab[i].is_harddrop = gred_use_harddrop(q);
			opt.set.tab[i].probability = q->parms.max_P;
			opt.set.tab[i].backlog = &q->backlog;
		}
		opt.set.qstats = &sch->qstats;
	}

	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, &opt);
}

static void mq_attach(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	struct mq_sched *priv = qdisc_priv(sch);
	struct Qdisc *qdisc, *old;
	unsigned int ntx;

	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
		qdisc = priv->qdiscs[ntx];
		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
		if (old)
			qdisc_destroy(old);
#ifdef CONFIG_NET_SCHED
		if (ntx < dev->real_num_tx_queues)
			qdisc_list_add(qdisc);
#endif

	}
	kfree(priv->qdiscs);
	priv->qdiscs = NULL;
}

static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
			   struct tcf_ematch *em)
{
	struct xt_set_info *set = data;
	ip_set_id_t index;
	struct net *net = dev_net(qdisc_dev(tp->q));

	if (data_len != sizeof(*set))
		return -EINVAL;

	index = ip_set_nfnl_get_byindex(net, set->index);
	if (index == IPSET_INVALID_ID)
		return -ENOENT;

	em->datalen = sizeof(*set);
	em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL);
	if (em->data)
		return 0;

	ip_set_nfnl_put(net, index);
	return -ENOMEM;
}

static int mq_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct net_device *dev = qdisc_dev(sch);
	struct mq_sched *priv = qdisc_priv(sch);
	struct netdev_queue *dev_queue;
	struct Qdisc *qdisc;
	unsigned int ntx;

	if (sch->parent != TC_H_ROOT)
		return -EOPNOTSUPP;

	if (!netif_is_multiqueue(dev))
		return -EOPNOTSUPP;

	/* pre-allocate qdiscs, attachment can't fail */
	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
			       GFP_KERNEL);
	if (priv->qdiscs == NULL)
		return -ENOMEM;

	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
		dev_queue = netdev_get_tx_queue(dev, ntx);
		qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
					  TC_H_MAKE(TC_H_MAJ(sch->handle),
						    TC_H_MIN(ntx + 1)));
		if (qdisc == NULL)
			goto err;
		priv->qdiscs[ntx] = qdisc;
		qdisc->flags |= TCQ_F_ONETXQUEUE;
	}

	sch->flags |= TCQ_F_MQROOT;
	return 0;

err:
	mq_destroy(sch);
	return -ENOMEM;
}