/*
 * net/sched/sch_tbf.c	Token Bucket Filter queue.
 *
 *		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, or (at your option) any later version.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *		Dmitry Torokhov <dtor@mail.ru> - allow attaching inner qdiscs -
 *						 original idea by Martin Devera
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>


/*	Simple Token Bucket Filter.
	=======================================

	SOURCE.
	-------

	None.

	Description.
	------------

	A data flow obeys TBF with rate R and depth B, if for any
	time interval t_i...t_f the number of transmitted bits
	does not exceed B + R*(t_f-t_i).

	Packetized version of this definition:
	The sequence of packets of sizes s_i served at moments t_i
	obeys TBF, if for any i<=k:

	s_i+....+s_k <= B + R*(t_k - t_i)

	Algorithm.
	----------

	Let N(t_i) be B/R initially and N(t) grow continuously with time as:

	N(t+delta) = min{B/R, N(t) + delta}

	If the first packet in queue has length S, it may be
	transmitted only at the time t_* when S/R <= N(t_*),
	and in this case N(t) jumps:

	N(t_* + 0) = N(t_* - 0) - S/R.



	Actually, QoS requires two TBF to be applied to a data stream.
	One of them controls steady state burst size, another
	one with rate P (peak rate) and depth M (equal to link MTU)
	limits bursts at a smaller time scale.

	It is easy to see that P>R, and B>M. If P is infinity, this double
	TBF is equivalent to a single one.

	When TBF works in reshaping mode, latency is estimated as:

	lat = max ((L-B)/R, (L-M)/P)


	NOTES.
	------

	If TBF throttles, it starts a watchdog timer, which will wake it up
	when it is ready to transmit.
	Note that the minimal timer resolution is 1/HZ.
	If no new packets arrive during this period,
	or if the device is not awaken by EOI for some previous packet,
	TBF can stop its activity for 1/HZ.


	This means, that with depth B, the maximal rate is

	R_crit = B*HZ

	F.e. for 10Mbit ethernet and HZ=100 the minimal allowed B is ~10Kbytes.

	Note that the peak rate TBF is much more tough: with MTU 1500
	P_crit = 150Kbytes/sec. So, if you need greater peak
	rates, use alpha with HZ=1000 :-)

	With classful TBF, limit is just kept for backwards compatibility.
	It is passed to the default bfifo qdisc - if the inner qdisc is
	changed the limit is not effective anymore.
*/

struct tbf_sched_data {
/* Parameters */
	u32		limit;		/* Maximal length of backlog: bytes */
	u32		max_size;
	s64		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
	s64		mtu;
	struct psched_ratecfg rate;
	struct psched_ratecfg peak;

/* Variables */
	s64	tokens;			/* Current number of B tokens */
	s64	ptokens;		/* Current number of P tokens */
	s64	t_c;			/* Time check-point */
	struct Qdisc	*qdisc;		/* Inner qdisc, default - bfifo queue */
	struct qdisc_watchdog watchdog;	/* Watchdog timer */
};


/* Time to Length, convert time in ns to length in bytes
 * to determinate how many bytes can be sent in given time.
 */
static u64 psched_ns_t2l(const struct psched_ratecfg *r,
			 u64 time_in_ns)
{
	/* The formula is :
	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
	 */
	u64 len = time_in_ns * r->rate_bytes_ps;

	do_div(len, NSEC_PER_SEC);

	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
		do_div(len, 53);
		len = len * 48;
	}

	if (len > r->overhead)
		len -= r->overhead;
	else
		len = 0;

	return len;
}

/*
 * Return length of individual segments of a gso packet,
 * including all headers (MAC, IP, TCP/UDP)
 */
static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
{
	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
	return hdr_len + skb_gso_transport_seglen(skb);
}

/* GSO packet is too big, segment it so that tbf can transmit
 * each segment in time
 */
static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
		       struct sk_buff **to_free)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	struct sk_buff *segs, *nskb;
	netdev_features_t features = netif_skb_features(skb);
	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
	int ret, nb;

	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);

	if (IS_ERR_OR_NULL(segs))
		return qdisc_drop(skb, sch, to_free);

	nb = 0;
	while (segs) {
		nskb = segs->next;
		segs->next = NULL;
		qdisc_skb_cb(segs)->pkt_len = segs->len;
		len += segs->len;
		ret = qdisc_enqueue(segs, q->qdisc, to_free);
		if (ret != NET_XMIT_SUCCESS) {
			if (net_xmit_drop_count(ret))
				qdisc_qstats_drop(sch);
		} else {
			nb++;
		}
		segs = nskb;
	}
	sch->q.qlen += nb;
	if (nb > 1)
		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
	consume_skb(skb);
	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}

static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
		       struct sk_buff **to_free)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	int ret;

	if (qdisc_pkt_len(skb) > q->max_size) {
		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
			return tbf_segment(skb, sch, to_free);
		return qdisc_drop(skb, sch, to_free);
	}
	ret = qdisc_enqueue(skb, q->qdisc, to_free);
	if (ret != NET_XMIT_SUCCESS) {
		if (net_xmit_drop_count(ret))
			qdisc_qstats_drop(sch);