Improves minimum RTT probing, adds packet pacing and refactors the code.

Adds minimum RTT probing.
2026-07-13 16:20:23 +02:00 · 2026-06-12 14:01:25 +02:00
3 changed files with 462 additions and 255 deletions
@@ -19,6 +19,15 @@ Note: This change is not persistent, the module will not be loaded at boot.
 sudo modprobe tcp_roccet
 sudo sysctl net.ipv4.tcp_congestion_control=roccet
 ```
+### Versions
+
+- latest on master branch
+    - Improved min RTT probing
+    - Packet pacing
+    - Code refactor
+
+- release-2026-06-12-v1
+    - Adds minimum RTT probing

 ## Build from source

@@ -86,4 +95,4 @@ To see the trace output use
 To remove the module again, use 
 `sudo rmmod roccet_kprobe` 

-_See more info at_ https://docs.kernel.org/trace/kprobes.html and https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
+_See more info at_ https://docs.kernel.org/trace/kprobes.html and https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
@@ -14,7 +14,8 @@
 * CUBIC's window growth function and adds, based on RTT
 * and ACK rate, congestion events.
 *
- * A peer-reviewed paper on TCP ROCCET will be presented at the WONS 2026 conference.
+ * A peer-reviewed paper on TCP ROCCET will be presented
+ * at the WONS 2026 conference.
 * A draft of the paper is available here:
 *		https://arxiv.org/abs/2510.25281
 *
@@ -45,12 +46,12 @@
 */

 #include "tcp_roccet.h"
-#include "linux/printk.h"
 #include <linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/math64.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <net/tcp.h>

 /* Scale factor beta calculation (max_cwnd = snd_cwnd * beta) */
@@ -63,35 +64,18 @@
 */
 #define ROCCET_ALPHA_TIMES_100 20

-/* The amount of seconds ROCCET stores a minRTT.
- * Enable "calculate_min_rtt" first.
- */
-#define ROCCET_RTT_LOOKBACK_S 10
+/* min RTT probe period in seconds */
+#define ROCCET_NEXT_MIN_RTT_PROBE 5000

 /* Parameters that are specific to the ROCCET-Algorithm */
-static int sr_rtt_upper_bound __read_mostly = 100;
+static uint sr_rtt_upper_bound __read_mostly = 100;
 static int ack_rate_diff_ss __read_mostly = 10;
-static int ack_rate_diff_ca __read_mostly = 200;
-static bool calculate_min_rtt __read_mostly;
-static bool ignore_loss __read_mostly;
-static int roccet_min_rtt_interpolation_factor __read_mostly = 70;

-module_param(sr_rtt_upper_bound, int, 0644);
+module_param(sr_rtt_upper_bound, uint, 0644);
 MODULE_PARM_DESC(sr_rtt_upper_bound, "ROCCET's upper bound for srRTT.");
 module_param(ack_rate_diff_ss, int, 0644);
 MODULE_PARM_DESC(ack_rate_diff_ss,
 		 "ROCCET's threshold to exit slow start if ACK-rate defer by given amount of segments.");
-module_param(ack_rate_diff_ca, int, 0644);
-MODULE_PARM_DESC(ack_rate_diff_ca,
-		 "ROCCET's threshold for ack-rate and cum_cwnd, in percantage of the current cwnd.");
-module_param(calculate_min_rtt, bool, 0644);
-MODULE_PARM_DESC(calculate_min_rtt,
-		 "Calculate min RTT if no lower RTT occurs after 10 sec.");
-module_param(ignore_loss, bool, 0644);
-MODULE_PARM_DESC(ignore_loss, "Ignore loss as a congestion event.");
-module_param(roccet_min_rtt_interpolation_factor, int, 0644);
-MODULE_PARM_DESC(roccet_min_rtt_interpolation_factor,
-		 "ROCCET factor for interpolating the current RTT with the last minRTT (minRTT = (factor * currRTT + (100-factor) * minRTT) / 100)");

 static int fast_convergence __read_mostly = 1;
 static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */
@@ -116,92 +100,207 @@ MODULE_PARM_DESC(bic_scale,
 module_param(tcp_friendliness, int, 0644);
 MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness");

-static inline void roccettcp_reset(struct roccettcp *ca)
+static __always_inline void roccettcp_reset(struct roccettcp *ca)
 {
-	memset(ca, 0, offsetof(struct roccettcp, curr_rtt));
-	ca->bw_limit.sum_cwnd = 1;
-	ca->bw_limit.sum_acked = 1;
-	ca->bw_limit.next_check = 0;
-	ca->curr_min_rtt_timed.rtt = ~0U;
-	ca->curr_min_rtt_timed.time = ~0U;
+	memset(ca, 0, sizeof(struct roccettcp));
+	ca->next_srrtt_check = 0;
+	ca->curr_min_rtt = ~0U;
 	ca->last_rtt = 0;
 	ca->ece_received = false;
+
+	ca->roccet_last_event_time_us = 0;
+	ca->ack_rate.last_rate = 0;
+	/* Initialize to current time to avoid overflow in ack rate calculation */
+	ca->ack_rate.last_rate_time = jiffies_to_usecs(tcp_jiffies32);
+	ca->ack_rate.curr_rate = 0;
+	ca->ack_rate.cnt = 0;
+
+    /* Start state is LAUNCH */
+    ca->state = LAUNCH;
 }

-static inline void update_min_rtt(struct sock *sk)
+/* Return true if ROCCET is in min RTT probing.
+ */
+static __always_inline bool is_in_min_rtt_probing(struct roccettcp *ca, u32 now)
+{
+	if (ca->probe_min_rtt_until == 0)
+		return false;
+	return before(now, ca->probe_min_rtt_until);
+}
+
+static __always_inline void update_min_rtt(struct sock *sk)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);
-	u32 now = jiffies_to_usecs(tcp_jiffies32);
-
-	if (now - ca->curr_min_rtt_timed.time >
-		    ROCCET_RTT_LOOKBACK_S * USEC_PER_SEC &&
-	    calculate_min_rtt) {
-		u32 new_min_rtt = max(ca->curr_rtt, 1);
-		u32 old_min_rtt = ca->curr_min_rtt_timed.rtt;
-
-		u32 interpolated_min_rtt =
-			(new_min_rtt * roccet_min_rtt_interpolation_factor +
-			 old_min_rtt *
-				 (100 - roccet_min_rtt_interpolation_factor)) /
-			100;
-
-		ca->curr_min_rtt_timed.rtt = interpolated_min_rtt;
-		ca->curr_min_rtt_timed.time = now;
-	}

 	/* Check if new lower min RTT was found. If so, set it directly */
-	if (ca->curr_rtt < ca->curr_min_rtt_timed.rtt) {
-		ca->curr_min_rtt_timed.rtt = max(ca->curr_rtt, 1);
-		ca->curr_min_rtt_timed.time = now;
+	if (ca->curr_rtt < ca->curr_min_rtt) {
+		ca->curr_min_rtt = max(ca->curr_rtt, 1);
+		/* Probe for the min RTT in ROCCET_NEXT_MIN_RTT_PROBE seconds
+		 * if no other update occurs.
+		 */
+		ca->next_min_rtt_probe = jiffies_to_usecs(tcp_jiffies32) +
+					ROCCET_NEXT_MIN_RTT_PROBE * USEC_PER_MSEC;
 	}
 }

 /* Return difference between last and current ack rate.
 */
-static inline int get_ack_rate_diff(struct roccettcp *ca)
+static __always_inline s32 get_ack_rate_diff(struct roccettcp *ca)
 {
-	return ca->ack_rate.last_rate - ca->ack_rate.curr_rate;
+	if (ca->ack_rate.curr_rate < ca->ack_rate.last_rate)
+		return 0;
+	return (s32)(ca->ack_rate.curr_rate - ca->ack_rate.last_rate);
 }

 /* Update ack rate sampled by 100ms.
 */
-static inline void update_ack_rate(struct sock *sk)
+static __always_inline void update_ack_rate(struct sock *sk, u32 acked, u32 now)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);
-	u32 now = jiffies_to_usecs(tcp_jiffies32);
-	u32 interval = USEC_PER_MSEC * 100;
+	s32 interval = USEC_PER_MSEC * 100;

-	if ((u32)(now - ca->ack_rate.last_rate_time) >= interval) {
-		ca->ack_rate.last_rate_time = now;
-		ca->ack_rate.last_rate = ca->ack_rate.curr_rate;
-		ca->ack_rate.curr_rate = ca->ack_rate.cnt;
-		ca->ack_rate.cnt = 0;
+	s32 time_delta = (s32)(ca->ack_rate.last_rate_time - now);
+	const s32 idle_threshold = USEC_PER_SEC * 2;
+
+	// Check if the time has arrived in the new interval
+	if (time_delta < -interval) {
+		// Check if the connection was idle for X seconds (e.g. no ACK for X seconds)
+		if (time_delta < -idle_threshold) {
+			// Reset ack counting as if a new connection was created
+			ca->ack_rate.last_rate = 0;
+			ca->ack_rate.last_rate_time = jiffies_to_usecs(tcp_jiffies32);
+			ca->ack_rate.curr_rate = 0;
+			ca->ack_rate.cnt = 0;
+		} else {
+			ca->ack_rate.last_rate_time = now;
+			ca->ack_rate.last_rate = ca->ack_rate.curr_rate;
+			ca->ack_rate.curr_rate = ca->ack_rate.cnt;
+			ca->ack_rate.cnt = acked; // start counting for the new interval
+		}
 	} else {
-		ca->ack_rate.cnt += 1;
+		ca->ack_rate.cnt += acked;
 	}
 }

 /* Compute srRTT.
 */
-static inline void update_srrtt(struct sock *sk)
+static __always_inline void update_srrtt(struct sock *sk)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);

-	if (ca->curr_min_rtt_timed.rtt == 0)
-		return;
+	/* Avoid integer overflow in the calculation below.
+	 * This could occur in cases where we have not yet
+	 * received an RTT sample. In these cases, set the
+	 * rtt to a safe value.
+	 */
+	if (ca->curr_rtt < ca->curr_min_rtt) {
+		ca->curr_rtt = max(ca->curr_rtt, 1);
+		ca->curr_min_rtt = ca->curr_rtt;
+	}
+
+	/* Avoid division by zero */
+	if (ca->curr_min_rtt == 0) {
+		ca->curr_min_rtt = max(ca->curr_min_rtt, 1);
+		return; // skip srRTT update
+	}

 	/* Calculate the new rRTT (Scaled by 100).
-	 * 100 * ((sRTT - sRTT_min) / sRTT_min)
+	 * 100 * ((sRTT - sRTT_min) / sRTT_min).
+	 *
+	 * curr_min_rtt_timed.rtt is always <= than curr_rtt,
+	 * since this is the minimum of the rtt.
+	 *
+	 * 0 is a valid value for rrtt.
 	 */
-	u32 rrtt = (100 * (ca->curr_rtt - ca->curr_min_rtt_timed.rtt)) /
-		   ca->curr_min_rtt_timed.rtt;
+	u32 rrtt = div_u64(100 * (u64)(ca->curr_rtt - ca->curr_min_rtt),
+			     ca->curr_min_rtt);

 	// (1 - alpha) * srRTT + alpha * rRTT
 	ca->curr_srrtt = ((100 - ROCCET_ALPHA_TIMES_100) * ca->curr_srrtt +
 			  ROCCET_ALPHA_TIMES_100 * rrtt) / 100;
 }

-__bpf_kfunc static void roccettcp_init(struct sock *sk)
+/* Do a ROCCET congestion event.
+ */
+static __always_inline void roccet_congestion_event(struct sock *sk, u32 now)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct roccettcp *ca = inet_csk_ca(sk);
+
+	ca->epoch_start = 0;
+	ca->roccet_last_event_time_us = now;
+	ca->cnt = 100 * tcp_snd_cwnd(tp);
+	ca->last_max_cwnd = tcp_snd_cwnd(tp);
+	tcp_snd_cwnd_set(tp, min(tp->snd_cwnd_clamp,
+				 max((tcp_snd_cwnd(tp) * beta) /
+				      BICTCP_BETA_SCALE, 2U)));
+	tp->snd_ssthresh = tcp_snd_cwnd(tp);
+}
+
+/* Do minimum RTT probing.
+ */
+static __always_inline void roccet_min_rtt_probe(struct sock *sk, u32 now)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct roccettcp *ca = inet_csk_ca(sk);
+    u32 interval, probe_cwnd;
+
+    /* Do nothing if we are probing */
+    if (before(now, ca->probe_min_rtt_until) && ca->probe_min_rtt_until > 0)
+		return;
+
+    /* Start of min RTT probing*/
+    if(ca->probe_min_rtt_until == 0){
+        /* Probe 1*RTT or at least 200ms */
+        interval = max(200 * USEC_PER_MSEC, ca->curr_rtt);
+
+        /* This is to handle deep shared buffers with loss-based
+         * congestion control like CUBIC. If the the cwnd is not limited
+         * by the application but falsely detected (see ROCCET paper),
+         * we have to empty the pipe more.
+         * If the limit detection is correct this will cause no harm
+         * to the tcp flow because the cwnd is not fully utilized and
+         * we set the cwnd to its previous value after probing.
+         */
+        probe_cwnd = max(tcp_snd_cwnd(tp) / 2, TCP_INIT_CWND);
+        if (!tcp_is_cwnd_limited(sk))
+            probe_cwnd = max(tcp_snd_cwnd(tp) / 3, TCP_INIT_CWND);
+
+        ca->probe_min_rtt_until = now + interval;
+        ca->cwnd_before_min_rtt_probe = tcp_snd_cwnd(tp);
+
+        /* Half the cwnd to drain the buffer for probing.
+         * Set the ssthresh to the probing cwnd otherwise
+         * the TCP state machine is in slow start.
+         */
+        tcp_snd_cwnd_set(tp, probe_cwnd);
+        tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp);
+
+        /* Reset current min RTT to allow probing for
+         * a new lower and higher minimum RTT.
+         */
+        ca->curr_min_rtt = ~0U;
+
+        /* Refill the pipe after probing.
+         * To this end we need the previous cwnd over the
+         * the probing interval.
+         */
+        ca->refill_until = ca->probe_min_rtt_until + interval;
+    }else if(before(now, ca->refill_until)){
+        /* Reset cwnd and refill the pipe. */
+        if(ca->state != RTT_PROBE_REFILL){
+            tcp_snd_cwnd_set(tp, ca->cwnd_before_min_rtt_probe);
+            tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp);
+            ca->state = RTT_PROBE_REFILL;
+        }
+    }else{
+        /* End min RTT probing phase. */
+        ca->probe_min_rtt_until = 0;
+        ca->state = ORBITER;
+    }
+}
+
+static void roccettcp_init(struct sock *sk)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);

@@ -210,34 +309,25 @@ __bpf_kfunc static void roccettcp_init(struct sock *sk)
 	if (initial_ssthresh)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;

-	/* Initial roccet parameters */
-	ca->roccet_last_event_time_us = 0;
-	ca->curr_min_rtt = ~0U;
-	ca->ack_rate.last_rate = 0;
-	ca->ack_rate.last_rate_time = 0;
-	ca->ack_rate.curr_rate = 0;
-	ca->ack_rate.cnt = 0;
+    cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED);
+	//WRITE_ONCE(sk->sk_pacing_rate, 0);
 }

-__bpf_kfunc static void roccettcp_cwnd_event(struct sock *sk,
-					     enum tcp_ca_event event)
+static void roccettcp_cwnd_event_tx_start(struct sock *sk)
 {
-	if (event == CA_EVENT_TX_START) {
-		struct roccettcp *ca = inet_csk_ca(sk);
-		u32 now = tcp_jiffies32;
-		s32 delta;
+	struct roccettcp *ca = inet_csk_ca(sk);
+	u32 now = tcp_jiffies32;
+	s32 delta;

-		delta = now - tcp_sk(sk)->lsndtime;
+	delta = now - tcp_sk(sk)->lsndtime;

-		/* We were application limited (idle) for a while.
-		 * Shift epoch_start to keep cwnd growth to cubic curve.
-		 */
-		if (ca->epoch_start && delta > 0) {
-			ca->epoch_start += delta;
-			if (after(ca->epoch_start, now))
-				ca->epoch_start = now;
-		}
-		return;
+	/* We were application limited (idle) for a while.
+	 * Shift epoch_start to keep cwnd growth to cubic curve.
+	 */
+	if (ca->epoch_start && delta > 0) {
+		ca->epoch_start += delta;
+		if (after(ca->epoch_start, now))
+			ca->epoch_start = now;
 	}
 }

@@ -289,7 +379,8 @@ static u32 cubic_root(u64 a)

 /* Compute congestion window to use.
 */
-static inline void bictcp_update(struct roccettcp *ca, u32 cwnd, u32 acked)
+static __always_inline void bictcp_update(struct roccettcp *ca, u32 cwnd,
+					  u32 acked)
 {
 	u32 delta, bic_target, max_cnt;
 	u64 offs, t;
@@ -398,136 +489,165 @@ tcp_friendliness:
 	ca->cnt = max(ca->cnt, 2U);
 }

-__bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack,
-					     u32 acked)
+static void roccettcp_cong_avoid(struct sock *sk, u32 ack,
+				 u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct roccettcp *ca = inet_csk_ca(sk);

 	u32 now = jiffies_to_usecs(tcp_jiffies32);
-	u32 bw_limit_detect = 0;
+	bool evaluate_srrtt = false;
 	u32 roccet_xj;
 	u32 jitter;

-	if (ca->last_rtt > ca->curr_rtt)
-		jitter = ca->last_rtt - ca->curr_rtt;
-	else
-		jitter = ca->curr_rtt - ca->last_rtt;
-
-	/* Update roccet parameters */
-	update_ack_rate(sk);
-	update_min_rtt(sk);
-	update_srrtt(sk);
-
-	/* ROCCET drain.
-	 * Do not increase the cwnd for 100ms after a roccet congestion event
-	 */
-	if (now - ca->roccet_last_event_time_us <= 100 * USEC_PER_MSEC)
-		return;
-
-	/* LAUNCH: Detect an exit point for tcp slow start
+    if(ca->state == LAUNCH){
+    /* LAUNCH: Detect an exit point for tcp slow start
 	 * in networks with large buffers of multiple BDP
 	 * Like in cellular networks (5G, ...).
 	 * Or exit LAUNCH if cwnd is too large for application layer
-	 * data rate.
+	 * data rate (tcp cwnd validation).
 	 */
+        if ((ca->curr_srrtt > sr_rtt_upper_bound &&
+            get_ack_rate_diff(ca) <= ack_rate_diff_ss) ||
+            !tcp_is_cwnd_limited(sk)) {
+            ca->epoch_start = 0;

-	if ((tcp_in_slow_start(tp) && ca->curr_srrtt > sr_rtt_upper_bound &&
-	     get_ack_rate_diff(ca) >= ack_rate_diff_ss) ||
-	    (!tcp_is_cwnd_limited(sk) && tcp_in_slow_start(tp))) {
-		ca->epoch_start = 0;
+            /* Handle initial slow start. Here occur most bufferbloat */
+            if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) {
+                tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp) / 2;
+                /* since this is the initial slow start,
+                * the min cwnd won't be 1, so the window
+                * can't be set to 0 by accident.
+                * Halfing the cwnd will undo the previous step
+                * of slow start. Which is fine since the pipe
+                * is already full.
+                */
+                tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp) / 2,
+                            TCP_INIT_CWND));
+            } else {
+                tcp_sk(sk)->snd_ssthresh =
+                    tcp_snd_cwnd(tp) - (tcp_snd_cwnd(tp) / 3);
+                tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) -
+                                (tcp_snd_cwnd(tp) / 3));
+            }
+            ca->roccet_last_event_time_us = now;
+            return;
+        }

-		/* Handle initial slow start. Here we observe the most problems */
-		if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) {
-			tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp) / 2;
-			tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) / 2);
-		} else {
-			tcp_sk(sk)->snd_ssthresh =
-				tcp_snd_cwnd(tp) - (tcp_snd_cwnd(tp) / 3);
-			tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) -
-						     (tcp_snd_cwnd(tp) / 3));
-		}
-		ca->roccet_last_event_time_us = now;
-		return;
-	}
+        acked = tcp_slow_start(tp, acked);
+        if (!acked)
+            return;

-	if (tcp_in_slow_start(tp)) {
-		acked = tcp_slow_start(tp, acked);
-		if (!acked)
-			return;
-	}
-
-	if (ca->bw_limit.next_check == 0)
-		ca->bw_limit.next_check = now + 5 * ca->curr_rtt;
-
-	ca->bw_limit.sum_cwnd += tcp_snd_cwnd(tp);
-	ca->bw_limit.sum_acked += acked;
-
-	if (ca->bw_limit.next_check < now) {
-		/* We send more data as we got acked in the last 5 RTTs */
-		if ((ca->bw_limit.sum_cwnd * 100) / ca->bw_limit.sum_acked >=
-		    ack_rate_diff_ca)
-			bw_limit_detect = 1;
-
-		/* reset struct and set next end of period */
-		ca->bw_limit.sum_cwnd = 1;
-
-		/* set to 1 to avoid division by zero */
-		ca->bw_limit.sum_acked = 1;
-		ca->bw_limit.next_check = now + 5 * ca->curr_rtt;
-	}
-
-	/* Respects the jitter of the connection and add it on top of the upper bound
-	 * for the srRTT
+    }else if(ca->state == ORBITER){
+    /* ORBITER: Increase the cwnd by using the CUBIC
+     * cwnd growth function, if no roccet congestion
+     * event is detechted.
 	 */
-	roccet_xj = ((jitter * 100) / ca->curr_min_rtt_timed.rtt) +
-		    sr_rtt_upper_bound;
-	if (roccet_xj < sr_rtt_upper_bound)
-		roccet_xj = sr_rtt_upper_bound;
+        /* Calculate jitter */
+        if ((s32)(ca->curr_rtt - ca->last_rtt) < 0)
+            jitter = ca->last_rtt - ca->curr_rtt;
+        else
+            jitter = ca->curr_rtt - ca->last_rtt;

-	if (ca->curr_srrtt > roccet_xj && (bw_limit_detect || ca->ece_received)) {
-		if (ca->ece_received)
-			ca->ece_received = false;
-		ca->epoch_start = 0;
-		ca->roccet_last_event_time_us = now;
-		ca->cnt = 100 * tcp_snd_cwnd(tp);
+        if (ca->next_srrtt_check == 0)
+            ca->next_srrtt_check = now + 5 * ca->curr_rtt;

-		/* Set Wmax if cwnd is larger than the old Wmax */
-		if (tcp_snd_cwnd(tp) > ca->last_max_cwnd)
-			ca->last_max_cwnd = tcp_snd_cwnd(tp);
+        /* Check if it's time to evaluate the srRTT */
+        if ((s32)(ca->next_srrtt_check - now) < 0) {
+            evaluate_srrtt = true;

-		tcp_snd_cwnd_set(tp, min(tp->snd_cwnd_clamp,
-					 max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U)));
-		tp->snd_ssthresh = tcp_snd_cwnd(tp);
-		return;
-	}
+            /* reset struct and set next end of period */
+            ca->next_srrtt_check = now + 5 * ca->curr_rtt;
+        }

-	/* Terminates this function if cwnd is not fully utilized.
-	 * In mobile networks like 5G, this termination causes the cwnd to be frozen at
-	 * an excessively high value. This is because slow start or HyStart massively
-	 * exceed the available bandwidth and leave the cwnd at an excessively high
-	 * value. The cwnd cannot therefore be fully utilized because it is limited by
-	 * the connection capacity.
-	 */
-	if (!tcp_is_cwnd_limited(sk))
-		return;
+        /* Respects the jitter of the connection and add it on top of
+        * the upper bound for the srRTT.
+        */
+        roccet_xj = div_u64((u64)jitter * 100, ca->curr_min_rtt) +
+                sr_rtt_upper_bound;
+        if (roccet_xj < sr_rtt_upper_bound)
+            roccet_xj = sr_rtt_upper_bound;

-	bictcp_update(ca, tcp_snd_cwnd(tp), acked);
-	tcp_cong_avoid_ai(tp, max(1, ca->cnt), acked);
+        /* The srRTT exceeds the upper bound if bufferbloat happens.
+        * Here, we want to reduce the cwnd and drain the buffer.
+        */
+        if (ca->curr_srrtt > roccet_xj && evaluate_srrtt) {
+            roccet_congestion_event(sk, now);
+            return;
+        }
+
+        /* Terminates this function if cwnd is not fully utilized.
+        * In mobile networks like 5G, this termination causes the cwnd to be
+        * frozen at an excessively high value. This is because slow start or
+        * HyStart massively exceed the available bandwidth and leave the cwnd
+        * at an excessively high value. The cwnd cannot therefore be fully
+        * utilized because it is limited by the connection capacity.
+        */
+        if (!tcp_is_cwnd_limited(sk))
+            return;
+
+        bictcp_update(ca, tcp_snd_cwnd(tp), acked);
+        tcp_cong_avoid_ai(tp, max(1, ca->cnt), acked);
+    }
 }

-__bpf_kfunc static u32 roccettcp_recalc_ssthresh(struct sock *sk)
+static u32 roccettcp_recalc_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct roccettcp *ca = inet_csk_ca(sk);
+	u32 cwnd;

-	if (ignore_loss)
+    /* If a loss/ECN occurs in the refill pahse of min RTT probing
+     * we reduce the cwnd and abort the refill.
+     */
+    if (ca->state == RTT_PROBE_REFILL)
+        ca->state = ORBITER;
+
+    /* If ROCCET is in min RTT probing and a loss/ECN occurs,
+     * we use the cwnd before the probing interval to
+     * calculate the cwnd reduction and continue probing.
+     * After min RTT probing the cwnd is set to the reduced
+     * value. During min RTT probing it is very likely that
+     * congestion was caused by the cwnd value before min
+     * RTT probing.
+     */
+    if (ca->state == RTT_PROBE){
+        /* Handle ECN as cubic congestion event in min
+            * RTT probe.
+            */
+        ca->ece_received = false;
+
+        ca->epoch_start = 0; /* end of epoch */
+
+        /* Wmax and fast convergence */
+        if (cwnd < ca->last_max_cwnd && fast_convergence)
+            ca->last_max_cwnd =
+                (cwnd * (BICTCP_BETA_SCALE + beta)) /
+                (2 * BICTCP_BETA_SCALE);
+        else
+            ca->last_max_cwnd = cwnd;
+
+        cwnd = ca->cwnd_before_min_rtt_probe;
+        ca->cwnd_before_min_rtt_probe = max((cwnd * beta) / BICTCP_BETA_SCALE, 2U);
+        return cwnd;
+    }
+
+	/* Handle ECN as ROCCET congestion event. */
+	if (ca->ece_received) {
+		ca->ece_received = false;
+		roccet_congestion_event(sk, jiffies_to_usecs(tcp_jiffies32));
 		return tcp_snd_cwnd(tp);
+	}

-	/* Don't exit slow start if loss occurs. */
+	/* On loss in slow start enter congestion avoidance
+	 * without a cwnd reduction. Additional slow start
+	 * exit conditions with a cwnd reduction are handled
+	 * in roccettcp_cong_avoid.
+	 */
 	if (tcp_in_slow_start(tp))
 		return tcp_snd_cwnd(tp);

+	/*CUBIC congestion event*/
 	ca->epoch_start = 0; /* end of epoch */

 	/* Wmax and fast convergence */
@@ -541,16 +661,22 @@ __bpf_kfunc static u32 roccettcp_recalc_ssthresh(struct sock *sk)
 	return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U);
 }

-__bpf_kfunc static void roccettcp_state(struct sock *sk, u8 new_state)
+static void roccettcp_state(struct sock *sk, u8 new_state)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);
+    struct tcp_sock *tp = tcp_sk(sk);

-	if (new_state == TCP_CA_Loss)
+	if (new_state == TCP_CA_Loss){
 		roccettcp_reset(ca);
+    }
+    else if(new_state == TCP_CA_Recovery){
+        tcp_sk(sk)->snd_ssthresh = roccettcp_recalc_ssthresh(sk);
+        tcp_snd_cwnd_set(tp, tcp_sk(sk)->snd_ssthresh);
+    }
 }

-__bpf_kfunc static void roccettcp_acked(struct sock *sk,
-					const struct ack_sample *sample)
+static void roccettcp_acked(struct sock *sk,
+			    const struct ack_sample *sample)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);

@@ -568,7 +694,7 @@ __bpf_kfunc static void roccettcp_acked(struct sock *sk,
 		delay = 1;

 	/* first time call or link delay decreases */
-	if (ca->delay_min == 0 || ca->delay_min > delay)
+	if (ca->delay_min == 0 || (s32)(delay - ca->delay_min) < 0)
 		ca->delay_min = delay;

 	/* Get valid sample for roccet */
@@ -578,54 +704,124 @@ __bpf_kfunc static void roccettcp_acked(struct sock *sk,
 	}
 }

-__bpf_kfunc static void roccet_in_ack_event(struct sock *sk, u32 flags)
+static void roccet_in_ack_event(struct sock *sk, u32 flags)
 {
 	struct roccettcp *ca = inet_csk_ca(sk);

 	/* Handle ECE bit.
-	 * Processing of ECE events is done in roccettcp_cong_avoid()
+	 * Processing of ECE events is done in roccettcp_recalc_ssthresh()
 	 */
 	if (flags & CA_ACK_ECE)
 		ca->ece_received = true;
 }

+__bpf_kfunc static void roccet_control(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) {
+    struct tcp_sock *tp = tcp_sk(sk);
+	struct roccettcp *ca = inet_csk_ca(sk);
+
+	u32 now = jiffies_to_usecs(tcp_jiffies32);
+    u64 rate;
+
+    /* Update roccet parameters */
+	update_ack_rate(sk, rs->acked_sacked, now);
+	update_min_rtt(sk);
+	update_srrtt(sk);
+
+    /* Update roccet state */
+    if(tcp_in_slow_start(tp)){
+        ca->state = LAUNCH;
+    }else if((s32) now - ca->roccet_last_event_time_us <= 100 * USEC_PER_MSEC){
+        ca->state = DRAIN;
+    }
+    else if(after(now, ca->next_min_rtt_probe) || ca->state == RTT_PROBE || ca->state == RTT_PROBE_REFILL){
+        if(ca->state != RTT_PROBE_REFILL)
+            ca->state = RTT_PROBE;
+        roccet_min_rtt_probe(sk, now);
+    }
+    else{
+        ca->state = ORBITER;
+    }
+
+    /* If nothing was fully acked do not increase the cwnd */
+    if (!rs->acked_sacked)
+            return;
+
+    /* Increase the cwnd.
+     * Loss recovery is handled in roccettcp_state()
+     */
+    roccettcp_cong_avoid(sk, ack, rs->acked_sacked);
+
+    /* Adjust pacing rate. The code here is similar to the
+     * pacing rate adjustemnts in tcp_input.c tcp_cong_control().
+     * In LAUNCH (slow start) we want a pacing of 200% and
+     * in ORBITER (congestion avoidance) we adjust the pacing
+     * to 100% and do not use the sysctl_tcp_pacing_ca_ratio.
+     */
+
+    /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+	rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3);
+
+	/* current rate is (cwnd * mss) / srtt
+	 * In Slow Start [1], set sk_pacing_rate to 200 % the current rate.
+	 * In Congestion Avoidance phase, set it to 120 % the current rate.
+	 *
+	 * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh)
+	 *	 If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching
+	 *	 end of slow start and should slow down.
+	 */
+	if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
+		rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
+	else
+		/* Pacing rate of 100% (instead of ipv4.sysctl_tcp_pacing_ca_ratio) */
+        rate *= 100;
+
+	rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
+
+	if (likely(tp->srtt_us))
+		do_div(rate, tp->srtt_us);
+
+	/* WRITE_ONCE() is needed because sch_fq fetches sk_pacing_rate
+	 * without any lock. We want to make sure compiler wont store
+	 * intermediate values in this location.
+	 */
+	WRITE_ONCE(sk->sk_pacing_rate,
+		   min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)));
+}
+
 static struct tcp_congestion_ops roccet_tcp __read_mostly = {
-	.init = roccettcp_init,
-	.ssthresh = roccettcp_recalc_ssthresh,
-	.cong_avoid = roccettcp_cong_avoid,
-	.set_state = roccettcp_state,
-	.undo_cwnd = tcp_reno_undo_cwnd,
-	.cwnd_event = roccettcp_cwnd_event,
-	.pkts_acked = roccettcp_acked,
-	.in_ack_event   = roccet_in_ack_event,
-	.owner = THIS_MODULE,
-	.name = "roccet",
-};
-
-BTF_KFUNCS_START(tcp_roccet_check_kfunc_ids)
-BTF_ID_FLAGS(func, roccettcp_init)
-BTF_ID_FLAGS(func, roccettcp_recalc_ssthresh)
-BTF_ID_FLAGS(func, roccettcp_cong_avoid)
-BTF_ID_FLAGS(func, roccettcp_state)
-BTF_ID_FLAGS(func, roccettcp_cwnd_event)
-BTF_ID_FLAGS(func, roccettcp_acked)
-BTF_KFUNCS_END(tcp_roccet_check_kfunc_ids)
-
-static const struct btf_kfunc_id_set tcp_roccet_kfunc_set = {
-	.owner = THIS_MODULE,
-	.set = &tcp_roccet_check_kfunc_ids,
+    .init = roccettcp_init,
+    .ssthresh = roccettcp_recalc_ssthresh,
+    .set_state = roccettcp_state,
+    .undo_cwnd = tcp_reno_undo_cwnd,
+    .cwnd_event_tx_start = roccettcp_cwnd_event_tx_start,
+    .pkts_acked = roccettcp_acked,
+    .in_ack_event   = roccet_in_ack_event,
+    .cong_control	= roccet_control,
+    .owner = THIS_MODULE,
+    .name = "roccet",
 };

 static int __init roccettcp_register(void)
 {
-	int ret;
-
 	BUILD_BUG_ON(sizeof(struct roccettcp) > ICSK_CA_PRIV_SIZE);

+	/*
+	 * Validate parameters to avoid division by zero errors.
+	 */
+	if (beta <= 0 || beta >= BICTCP_BETA_SCALE) {
+		pr_err("roccet: beta must be between 0 and %d\n",
+		       BICTCP_BETA_SCALE);
+		return -EINVAL;
+	}
+
+	if (bic_scale <= 0) {
+		pr_err("roccet: bic_scale must be positive\n");
+		return -EINVAL;
+	}
+
 	/* 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);

@@ -650,10 +846,6 @@ static int __init roccettcp_register(void)
 	/* divide by bic_scale and by constant Srtt (100ms) */
 	do_div(cube_factor, bic_scale * 10);

-	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
-					&tcp_roccet_kfunc_set);
-	if (ret < 0)
-		return ret;
 	return tcp_register_congestion_control(&roccet_tcp);
 }

@@ -668,4 +860,3 @@ module_exit(roccettcp_unregister);
 MODULE_AUTHOR("Lukas Prause, Tim Füchsel");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ROCCET TCP");
-MODULE_VERSION("1.0");
@@ -7,25 +7,26 @@

 #include <linux/math64.h>

+/* State in which roccet currently opperates */
+enum roccet_state {
+  LAUNCH,
+  ORBITER,
+  RTT_PROBE,
+  RTT_PROBE_REFILL,
+  DRAIN
+};
+
+/* TCP ROCCET helper type, storing data related to ack counting */
 struct ack_rate {
-	u16 last_rate;	/* Last ACK-rate */
+	u32 last_rate;	/* Last ACK-rate */
 	u32 last_rate_time;	/* Timestamp of the last ACK-rate */
-	u16 curr_rate;	/* Current ACK-rate */
-	u16 cnt;	/* Used for counting acks */
+	u32 curr_rate;	/* Current ACK-rate */
+	u32 cnt;	/* Used for counting acks */
 };

-struct bandwidth_limit_detect {
-	u32 sum_cwnd;	/* sum of cwnd during time interval */
-	u32 sum_acked;	/* sum of received acks during time interval */
-	u32 next_check;	/* end/upper bound of time interval */
-};
-
-struct timed_rtt {
-	u32 time;	/* Time of recording */
-	u32 rtt;	/* Measured RTT */
-};
-
-/* Based on the BICTCP struct with additions specific for the ROCCET-Algorithm */
+/* TCP ROCCET struct based on the original BICTCP struct with
+ * additions specific to the ROCCET-Algorithm.
+ */
 struct roccettcp {
 	u32 cnt;		/* increase cwnd by 1 after ACKs */
 	u32 last_max_cwnd;	/* last maximum snd_cwnd */
@@ -39,18 +40,24 @@ struct roccettcp {
 	u32 epoch_start;	/* beginning of an epoch */
 	u32 ack_cnt;		/* number of acks */
 	u32 tcp_cwnd;		/* estimated tcp cwnd */
-	u32 curr_rtt;		/* the minimum rtt of current round */
+	u32 curr_rtt;		/* last sample rtt of current round */

-	u32 roccet_last_event_time_us;	/* The last time ROCCET was triggered */
+	u32 roccet_last_event_time_us;	/* The last time ROCCET was
+					 * triggered
+					 */
 	bool ece_received;	/* Set to true if an ECE bit was received */
-	u32 curr_min_rtt;		/* The current observed minRTT */
-	struct timed_rtt curr_min_rtt_timed;	/* The current observed minRTT with
-						 * the timestamp when it was observed
-						 */
-	u32 curr_srrtt;			/* The srRTT calculated based on the latest ACK */
+	u32 curr_min_rtt;	/* The current observed minRTT */
+	u32 next_min_rtt_probe; /* Next time to probe the minRTT */
+	u32 probe_min_rtt_until;	/* End of minRTT probing period */
+	u32 refill_until;       /* End of pipe refill after minRTT probe */
+	u32 cwnd_before_min_rtt_probe;	/* cwnd before min RTT probeing */
+	u32 curr_srrtt;		/* srRTT calculated based on the latest ACK */
+	u32 next_srrtt_check;	/* Next check for srRTT */
 	struct ack_rate ack_rate;	/* The last and the current ACK rate */
-	struct bandwidth_limit_detect bw_limit;
-	u32 last_rtt;			/* Used for jitter calculation */
+	u32 last_rtt;			/* sample rtt of previous round.
+					 * Used for jitter calculation
+					 */
+    enum roccet_state state; /* State in which roccet currently opperates */
 };

 #endif /* __TCP_ROCCET_H */
Author	SHA1	Message	Date
Lukas Prause	35aa714256	Improves minimum RTT probing, adds packet pacing and refactors the code.	2026-07-13 16:20:23 +02:00
Lukas Prause	52cb1fe1f1	Adds minimum RTT probing.	2026-06-12 14:01:25 +02:00