Free Electrons

Embedded Linux Experts

/*
 * TCP CUBIC: Binary Increase Congestion control for TCP v2.1
 *
 * This is from the implementation of CUBIC TCP in
 * Injong Rhee, Lisong Xu.
 *  "CUBIC: A New TCP-Friendly High-Speed TCP Variant
 *  in PFLDnet 2005
 * Available from:
 *  http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
 *
 * Unless CUBIC is enabled and congestion window is large
 * this behaves the same as the original Reno.
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <net/tcp.h>
#include <asm/div64.h>

#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
					 * max_cwnd = snd_cwnd * beta
					 */
#define BICTCP_B		4	 /*
					  * In binary search,
					  * go to point (max+min)/N
					  */
#define	BICTCP_HZ		10	/* BIC HZ 2^10 = 1024 */

static int fast_convergence __read_mostly = 1;
static int max_increment __read_mostly = 16;
static int beta __read_mostly = 819;	/* = 819/1024 (BICTCP_BETA_SCALE) */
static int initial_ssthresh __read_mostly;
static int bic_scale __read_mostly = 41;
static int tcp_friendliness __read_mostly = 1;

static u32 cube_rtt_scale __read_mostly;
static u32 beta_scale __read_mostly;
static u64 cube_factor __read_mostly;

/* Note parameters that are used for precomputing scale factors are read-only */
module_param(fast_convergence, int, 0644);
MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence");
module_param(max_increment, int, 0644);
MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search");
module_param(beta, int, 0444);
MODULE_PARM_DESC(beta, "beta for multiplicative increase");
module_param(initial_ssthresh, int, 0644);
MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
module_param(bic_scale, int, 0444);
MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)");
module_param(tcp_friendliness, int, 0644);
MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness");

/* BIC TCP Parameters */
struct bictcp {
	u32	cnt;		/* increase cwnd by 1 after ACKs */
	u32 	last_max_cwnd;	/* last maximum snd_cwnd */
	u32	loss_cwnd;	/* congestion window at last loss */
	u32	last_cwnd;	/* the last snd_cwnd */
	u32	last_time;	/* time when updated last_cwnd */
	u32	bic_origin_point;/* origin point of bic function */
	u32	bic_K;		/* time to origin point from the beginning of the current epoch */
	u32	delay_min;	/* min delay */
	u32	epoch_start;	/* beginning of an epoch */
	u32	ack_cnt;	/* number of acks */
	u32	tcp_cwnd;	/* estimated tcp cwnd */
#define ACK_RATIO_SHIFT	4
	u32	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
};

static inline void bictcp_reset(struct bictcp *ca)
{
	ca->cnt = 0;
	ca->last_max_cwnd = 0;
	ca->loss_cwnd = 0;
	ca->last_cwnd = 0;
	ca->last_time = 0;
	ca->bic_origin_point = 0;
	ca->bic_K = 0;
	ca->delay_min = 0;
	ca->epoch_start = 0;
	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
	ca->ack_cnt = 0;
	ca->tcp_cwnd = 0;
}

static void bictcp_init(struct sock *sk)
{
	bictcp_reset(inet_csk_ca(sk));
	if (initial_ssthresh)
		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
}

/* calculate the cubic root of x using a table lookup followed by one
 * Newton-Raphson iteration.
 * Avg err ~= 0.195%
 */
static u32 cubic_root(u64 a)
{
	u32 x, b, shift;
	/*
	 * cbrt(x) MSB values for x MSB values in [0..63].
	 * Precomputed then refined by hand - Willy Tarreau
	 *
	 * For x in [0..63],
	 *   v = cbrt(x << 18) - 1
	 *   cbrt(x) = (v[x] + 10) >> 6
	 */
	static const u8 v[] = {
		/* 0x00 */    0,   54,   54,   54,  118,  118,  118,  118,
		/* 0x08 */  123,  129,  134,  138,  143,  147,  151,  156,
		/* 0x10 */  157,  161,  164,  168,  170,  173,  176,  179,
		/* 0x18 */  181,  185,  187,  190,  192,  194,  197,  199,
		/* 0x20 */  200,  202,  204,  206,  209,  211,  213,  215,
		/* 0x28 */  217,  219,  221,  222,  224,  225,  227,  229,
		/* 0x30 */  231,  232,  234,  236,  237,  239,  240,  242,
		/* 0x38 */  244,  245,  246,  248,  250,  251,  252,  254,
	};

	b = fls64(a);
	if (b < 7) {
		/* a in [0..63] */
		return ((u32)v[(u32)a] + 35) >> 6;
	}

	b = ((b * 84) >> 8) - 1;
	shift = (a >> (b * 3));

	x = ((u32)(((u32)v[shift] + 10) << b)) >> 6;

	/*
	 * Newton-Raphson iteration
	 *                         2
	 * x    = ( 2 * x  +  a / x  ) / 3
	 *  k+1          k         k
	 */
	x = (2 * x + (u32)div64_64(a, (u64)x * (u64)(x - 1)));
	x = ((x * 341) >> 10);
	return x;
}

/*
 * Compute congestion window to use.
 */
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
	u64 offs;
	u32 delta, t, bic_target, min_cnt, max_cnt;

	ca->ack_cnt++;	/* count the number of ACKs */

	if (ca->last_cwnd == cwnd &&
	    (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
		return;

	ca->last_cwnd = cwnd;
	ca->last_time = tcp_time_stamp;

	if (ca->epoch_start == 0) {
		ca->epoch_start = tcp_time_stamp;	/* record the beginning of an epoch */
		ca->ack_cnt = 1;			/* start counting */
		ca->tcp_cwnd = cwnd;			/* syn with cubic */

		if (ca->last_max_cwnd <= cwnd) {
			ca->bic_K = 0;
			ca->bic_origin_point = cwnd;
		} else {
			/* Compute new K based on
			 * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ)
			 */
			ca->bic_K = cubic_root(cube_factor
					       * (ca->last_max_cwnd - cwnd));
			ca->bic_origin_point = ca->last_max_cwnd;
		}
	}

	/* cubic function - calc*/
	/* calculate c * time^3 / rtt,
	 *  while considering overflow in calculation of time^3
	 * (so time^3 is done by using 64 bit)
	 * and without the support of division of 64bit numbers
	 * (so all divisions are done by using 32 bit)
	 *  also NOTE the unit of those veriables
	 *	  time  = (t - K) / 2^bictcp_HZ
	 *	  c = bic_scale >> 10
	 * rtt  = (srtt >> 3) / HZ
	 * !!! The following code does not have overflow problems,
	 * if the cwnd < 1 million packets !!!
	 */

	/* change the unit from HZ to bictcp_HZ */
	t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
	     << BICTCP_HZ) / HZ;

	if (t < ca->bic_K)		/* t - K */
		offs = ca->bic_K - t;
	else
		offs = t - ca->bic_K;

	/* c/rtt * (t-K)^3 */
	delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
	if (t < ca->bic_K)                                	/* below origin*/
		bic_target = ca->bic_origin_point - delta;
	else                                                	/* above origin*/
		bic_target = ca->bic_origin_point + delta;

	/* cubic function - calc bictcp_cnt*/
	if (bic_target > cwnd) {
		ca->cnt = cwnd / (bic_target - cwnd);
	} else {
		ca->cnt = 100 * cwnd;              /* very small increment*/
	}

	if (ca->delay_min > 0) {
		/* max increment = Smax * rtt / 0.1  */
		min_cnt = (cwnd * HZ * 8)/(10 * max_increment * ca->delay_min);

		/* use concave growth when the target is above the origin */
		if (ca->cnt < min_cnt && t >= ca->bic_K)
			ca->cnt = min_cnt;
	}

	/* slow start and low utilization  */
	if (ca->loss_cwnd == 0)		/* could be aggressive in slow start */
		ca->cnt = 50;

	/* TCP Friendly */
	if (tcp_friendliness) {
		u32 scale = beta_scale;
		delta = (cwnd * scale) >> 3;
		while (ca->ack_cnt > delta) {		/* update tcp cwnd */
			ca->ack_cnt -= delta;
			ca->tcp_cwnd++;
		}

		if (ca->tcp_cwnd > cwnd){	/* if bic is slower than tcp */
			delta = ca->tcp_cwnd - cwnd;
			max_cnt = cwnd / delta;
			if (ca->cnt > max_cnt)
				ca->cnt = max_cnt;
		}
	}

	ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
	if (ca->cnt == 0)			/* cannot be zero */
		ca->cnt = 1;
}

static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct bictcp *ca = inet_csk_ca(sk);

	if (!tcp_is_cwnd_limited(sk, in_flight))
		return;

	if (tp->snd_cwnd <= tp->snd_ssthresh)
		tcp_slow_start(tp);
	else {
		bictcp_update(ca, tp->snd_cwnd);

		/* In dangerous area, increase slowly.
		 * In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd
		 */
		if (tp->snd_cwnd_cnt >= ca->cnt) {
			if (tp->snd_cwnd < tp->snd_cwnd_clamp)
				tp->snd_cwnd++;
			tp->snd_cwnd_cnt = 0;
		} else
			tp->snd_cwnd_cnt++;
	}

}

static u32 bictcp_recalc_ssthresh(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct bictcp *ca = inet_csk_ca(sk);

	ca->epoch_start = 0;	/* end of epoch */

	/* Wmax and fast convergence */
	if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
		ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
			/ (2 * BICTCP_BETA_SCALE);
	else
		ca->last_max_cwnd = tp->snd_cwnd;

	ca->loss_cwnd = tp->snd_cwnd;

	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
}

static u32 bictcp_undo_cwnd(struct sock *sk)
{
	struct bictcp *ca = inet_csk_ca(sk);

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

static void bictcp_state(struct sock *sk, u8 new_state)
{
	if (new_state == TCP_CA_Loss)
		bictcp_reset(inet_csk_ca(sk));
}

/* Track delayed acknowledgment ratio using sliding window
 * ratio = (15*ratio + sample) / 16
 */
static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct bictcp *ca = inet_csk_ca(sk);
	u32 delay;

	if (icsk->icsk_ca_state == TCP_CA_Open) {
		cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
		ca->delayed_ack += cnt;
	}

	/* Some calls are for duplicates without timetamps */
	if (rtt_us < 0)
		return;

	/* Discard delay samples right after fast recovery */
	if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
		return;

	delay = usecs_to_jiffies(rtt_us) << 3;
	if (delay == 0)
		delay = 1;

	/* first time call or link delay decreases */
	if (ca->delay_min == 0 || ca->delay_min > delay)
		ca->delay_min = delay;
}

static struct tcp_congestion_ops cubictcp = {
	.init		= bictcp_init,
	.ssthresh	= bictcp_recalc_ssthresh,
	.cong_avoid	= bictcp_cong_avoid,
	.set_state	= bictcp_state,
	.undo_cwnd	= bictcp_undo_cwnd,
	.pkts_acked     = bictcp_acked,
	.owner		= THIS_MODULE,
	.name		= "cubic",
};

static int __init cubictcp_register(void)
{
	BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE);

	/* Precompute a bunch of the scaling factors that are used per-packet
	 * based on SRTT of 100ms
	 */

	beta_scale = 8*(BICTCP_BETA_SCALE+beta)/ 3 / (BICTCP_BETA_SCALE - beta);

	cube_rtt_scale = (bic_scale * 10);	/* 1024*c/rtt */

	/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
	 *  so K = cubic_root( (wmax-cwnd)*rtt/c )
	 * the unit of K is bictcp_HZ=2^10, not HZ
	 *
	 *  c = bic_scale >> 10
	 *  rtt = 100ms
	 *
	 * the following code has been designed and tested for
	 * cwnd < 1 million packets
	 * RTT < 100 seconds
	 * HZ < 1,000,00  (corresponding to 10 nano-second)
	 */

	/* 1/c * 2^2*bictcp_HZ * srtt */
	cube_factor = 1ull << (10+3*BICTCP_HZ); /* 2^40 */

	/* divide by bic_scale and by constant Srtt (100ms) */
	do_div(cube_factor, bic_scale * 10);

	return tcp_register_congestion_control(&cubictcp);
}

static void __exit cubictcp_unregister(void)
{
	tcp_unregister_congestion_control(&cubictcp);
}

module_init(cubictcp_register);
module_exit(cubictcp_unregister);

MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CUBIC TCP");
MODULE_VERSION("2.1");