/* DataCenter TCP (DCTCP) congestion control.
 *
 * http://simula.stanford.edu/~alizade/Site/DCTCP.html
 *
 * This is an implementation of DCTCP over Reno, an enhancement to the
 * TCP congestion control algorithm designed for data centers. DCTCP
 * leverages Explicit Congestion Notification (ECN) in the network to
 * provide multi-bit feedback to the end hosts. DCTCP's goal is to meet
 * the following three data center transport requirements:
 *
 *  - High burst tolerance (incast due to partition/aggregate)
 *  - Low latency (short flows, queries)
 *  - High throughput (continuous data updates, large file transfers)
 *    with commodity shallow buffered switches
 *
 * The algorithm is described in detail in the following two papers:
 *
 * 1) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
 *    Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
 *      "Data Center TCP (DCTCP)", Data Center Networks session
 *      Proc. ACM SIGCOMM, New Delhi, 2010.
 *   http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
 *
 * 2) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
 *      "Analysis of DCTCP: Stability, Convergence, and Fairness"
 *      Proc. ACM SIGMETRICS, San Jose, 2011.
 *   http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
 *
 * Initial prototype from Abdul Kabbani, Masato Yasuda and Mohammad Alizadeh.
 *
 * Authors:
 *
 *	Daniel Borkmann <dborkman@redhat.com>
 *	Florian Westphal <fw@strlen.de>
 *	Glenn Judd <glenn.judd@morganstanley.com>
 *
 * 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.
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <net/tcp.h>
#include <linux/inet_diag.h>

#define DCTCP_MAX_ALPHA	1024U

struct dctcp {
	u32 acked_bytes_ecn;
	u32 acked_bytes_total;
	u32 prior_snd_una;
	u32 prior_rcv_nxt;
	u32 dctcp_alpha;
	u32 next_seq;
	u32 ce_state;
	u32 loss_cwnd;
};

static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
module_param(dctcp_shift_g, uint, 0644);
MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");

static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
module_param(dctcp_alpha_on_init, uint, 0644);
MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");

static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
		 "parameter for clamping alpha on loss");

static struct tcp_congestion_ops dctcp_reno;

static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
{
	ca->next_seq = tp->snd_nxt;

	ca->acked_bytes_ecn = 0;
	ca->acked_bytes_total = 0;
}

static void dctcp_init(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	if ((tp->ecn_flags & TCP_ECN_OK) ||
	    (sk->sk_state == TCP_LISTEN ||
	     sk->sk_state == TCP_CLOSE)) {
		struct dctcp *ca = inet_csk_ca(sk);

		ca->prior_snd_una = tp->snd_una;
		ca->prior_rcv_nxt = tp->rcv_nxt;

		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);

		ca->loss_cwnd = 0;
		ca->ce_state = 0;

		dctcp_reset(tp, ca);
		return;
	}

	/* No ECN support? Fall back to Reno. Also need to clear
	 * ECT from sk since it is set during 3WHS for DCTCP.
	 */
	inet_csk(sk)->icsk_ca_ops = &dctcp_reno;
	INET_ECN_dontxmit(sk);
}

static u32 dctcp_ssthresh(struct sock *sk)
{
	struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	ca->loss_cwnd = tp->snd_cwnd;
	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
}

/* Minimal DCTP CE state machine:
 *
 * S:	0 <- last pkt was non-CE
 *	1 <- last pkt was CE
 */

static void dctcp_ce_state_0_to_1(struct sock *sk)
{
	struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	if (!ca->ce_state) {
		/* State has changed from CE=0 to CE=1, force an immediate
		 * ACK to reflect the new CE state. If an ACK was delayed,
		 * send that first to reflect the prior CE state.
		 */
		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
			__tcp_send_ack(sk, ca->prior_rcv_nxt);
		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
	}

	ca->prior_rcv_nxt = tp->rcv_nxt;
	ca->ce_state = 1;

	tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}

static void dctcp_ce_state_1_to_0(struct sock *sk)
{
	struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	if (ca->ce_state) {
		/* State has changed from CE=1 to CE=0, force an immediate
		 * ACK to reflect the new CE state. If an ACK was delayed,
		 * send that first to reflect the prior CE state.
		 */
		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
			__tcp_send_ack(sk, ca->prior_rcv_nxt);
		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
	}

	ca->prior_rcv_nxt = tp->rcv_nxt;
	ca->ce_state = 0;

	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}

static void dctcp_update_alpha(struct sock *sk, u32 flags)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct dctcp *ca = inet_csk_ca(sk);
	u32 acked_bytes = tp->snd_una - ca->prior_snd_una;

	/* If ack did not advance snd_una, count dupack as MSS size.
	 * If ack did update window, do not count it at all.
	 */
	if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
		acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
	if (acked_bytes) {
		ca->acked_bytes_total += acked_bytes;
		ca->prior_snd_una = tp->snd_una;

		if (flags & CA_ACK_ECE)
			ca->acked_bytes_ecn += acked_bytes;
	}

	/* Expired RTT */
	if (!before(tp->snd_una, ca->next_seq)) {
		u64 bytes_ecn = ca->acked_bytes_ecn;
		u32 alpha = ca->dctcp_alpha;

		/* alpha = (1 - g) * alpha + g * F */

		alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
		if (bytes_ecn) {
			/* If dctcp_shift_g == 1, a 32bit value would overflow
			 * after 8 Mbytes.
			 */
			bytes_ecn <<= (10 - dctcp_shift_g);
			do_div(bytes_ecn, max(1U, ca->acked_bytes_total));

			alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
		}
		/* dctcp_alpha can be read from dctcp_get_info() without
		 * synchro, so we ask compiler to not use dctcp_alpha
		 * as a temporary variable in prior operations.
		 */
		WRITE_ONCE(ca->dctcp_alpha, alpha);
		dctcp_reset(tp, ca);
	}
}

static void dctcp_state(struct sock *sk, u8 new_state)
{
	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
		struct dctcp *ca = inet_csk_ca(sk);

		/* If this extension is enabled, we clamp dctcp_alpha to
		 * max on packet loss; the motivation is that dctcp_alpha
		 * is an indicator to the extend of congestion and packet
		 * loss is an indicator of extreme congestion; setting
		 * this in practice turned out to be beneficial, and
		 * effectively assumes total congestion which reduces the
		 * window by half.
		 */
		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
	}
}

static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
	switch (ev) {
	case CA_EVENT_ECN_IS_CE:
		dctcp_ce_state_0_to_1(sk);
		break;
	case CA_EVENT_ECN_NO_CE:
		dctcp_ce_state_1_to_0(sk);
		break;
	default:
		/* Don't care for the rest. */
		break;
	}
}

static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
			     union tcp_cc_info *info)
{
	const struct dctcp *ca = inet_csk_ca(sk);

	/* Fill it also in case of VEGASINFO due to req struct limits.
	 * We can still correctly retrieve it later.
	 */
	if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
		memset(&info->dctcp, 0, sizeof(info->dctcp));
		if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
			info->dctcp.dctcp_enabled = 1;
			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
			info->dctcp.dctcp_alpha = ca->dctcp_alpha;
			info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
			info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
		}

		*attr = INET_DIAG_DCTCPINFO;
		return sizeof(info->dctcp);
	}
	return 0;
}

static u32 dctcp_cwnd_undo(struct sock *sk)
{
	const struct dctcp *ca = inet_csk_ca(sk);

	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
}

static struct tcp_congestion_ops dctcp __read_mostly = {
	.init		= dctcp_init,
	.in_ack_event   = dctcp_update_alpha,
	.cwnd_event	= dctcp_cwnd_event,
	.ssthresh	= dctcp_ssthresh,
	.cong_avoid	= tcp_reno_cong_avoid,
	.undo_cwnd	= dctcp_cwnd_undo,
	.set_state	= dctcp_state,
	.get_info	= dctcp_get_info,
	.flags		= TCP_CONG_NEEDS_ECN,
	.owner		= THIS_MODULE,
	.name		= "dctcp",
};

static struct tcp_congestion_ops dctcp_reno __read_mostly = {
	.ssthresh	= tcp_reno_ssthresh,
	.cong_avoid	= tcp_reno_cong_avoid,
	.undo_cwnd	= tcp_reno_undo_cwnd,
	.get_info	= dctcp_get_info,
	.owner		= THIS_MODULE,
	.name		= "dctcp-reno",
};

static int __init dctcp_register(void)
{
	BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
	return tcp_register_congestion_control(&dctcp);
}

static void __exit dctcp_unregister(void)
{
	tcp_unregister_congestion_control(&dctcp);
}

module_init(dctcp_register);
module_exit(dctcp_unregister);

MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_AUTHOR("Glenn Judd <glenn.judd@morganstanley.com>");

MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("DataCenter TCP (DCTCP)");