[PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing

[PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing

[chia-yu.chang]

From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>

Today, congestion control algorithms influence TSO sizing through the
min_tso_segs() callback, which provides the minimum number of segments
used by tcp_tso_autosize(). However, Prague congestion control requires
finer control and needs to determine the final TSO segment count
directly rather than only providing a minimum bound.
 
This patch introduces TCP_CONG_EXACT_TSO_SEGS flag and extends
tcp_congestion_ops with an alternative tso_segs() callback. When the
flag is set, the congestion control algorithm supplies the final TSO
segment count directly and bypasses tcp_tso_autosize(). Otherwise, the
existing min_tso_segs() callback continues to provide the minimum
segment count used by tcp_tso_autosize().

This preserves the existing behavior of current congestion control
algorithms without introducing additional callbacks while enabling
future algorithms to implement custom TSO sizing policies.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
 include/net/tcp.h     | 16 +++++++++++++---
 net/ipv4/tcp_output.c | 17 +++++++++++++----
 2 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2c5b889530b5..82cd82a19ff9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1283,9 +1283,11 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CONG_ECT_1_NEGOTIATION	BIT(3)
 /* Cannot fallback to RFC3168 during AccECN negotiation */
 #define TCP_CONG_NO_FALLBACK_RFC3168	BIT(4)
+/* Congestion cotnrol provides the exact TSO segment numbers  */
+#define TCP_CONG_EXACT_TSO_SEGS		BIT(5)
 #define TCP_CONG_MASK  (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
 			TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \
-			TCP_CONG_NO_FALLBACK_RFC3168)
+			TCP_CONG_NO_FALLBACK_RFC3168 | TCP_CONG_EXACT_TSO_SEGS)
 
 union tcp_cc_info;
 
@@ -1361,8 +1363,16 @@ struct tcp_congestion_ops {
 	/* hook for packet ack accounting (optional) */
 	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
 
-	/* override sysctl_tcp_min_tso_segs (optional) */
-	u32 (*min_tso_segs)(struct sock *sk);
+	union {
+		/* Used when TCP_CONG_EXACT_TSO_SEGS is not set,
+		 * override sysctl_tcp_min_tso_segs (optional)
+		 */
+		u32 (*min_tso_segs)(struct sock *sk);
+		/* Used when TCP_CONG_EXACT_TSO_SEGS is set,
+		 * override tcp_tso_autosize (optional)
+		 */
+		u32 (*tso_segs)(struct sock *sk, u32 mss_now);
+	};
 
 	/* new value of cwnd after loss (required) */
 	u32  (*undo_cwnd)(struct sock *sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d7c1444b5e30..0de27a87c39e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2278,11 +2278,20 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	u32 min_tso, tso_segs;
 
-	min_tso = ca_ops->min_tso_segs ?
-			ca_ops->min_tso_segs(sk) :
-			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+	min_tso = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+
+	if (ca_ops->flags & TCP_CONG_EXACT_TSO_SEGS) {
+		if (WARN_ON_ONCE(!ca_ops->tso_segs))
+			tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
+		else
+			tso_segs = ca_ops->tso_segs(sk, mss_now);
+	} else {
+		if (ca_ops->min_tso_segs)
+			min_tso = ca_ops->min_tso_segs(sk);
+
+		tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
+	}
 
-	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
 }
 
-- 
2.34.1

RE: [PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing

[Chia-Yu Chang (Nokia)]

> -----Original Message-----
> From: Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com> 
> Sent: Sunday, July 26, 2026 9:38 PM
> To: horms@kernel.org; dsahern@kernel.org; bpf@vger.kernel.org; netdev@vger.kernel.org; pabeni@redhat.com; jhs@mojatatu.com; kuba@kernel.org; stephen@networkplumber.org; davem@davemloft.net; edumazet@google.com; andrew+netdev@lunn.ch; donald.hunter@gmail.com; kuniyu@google.com; ij@kernel.org; ncardwell@google.com; Koen De Schepper (Nokia) <koen.de_schepper@nokia-bell-labs.com>; g.white@cablelabs.com; ingemar.s.johansson@ericsson.com; mirja.kuehlewind@ericsson.com; cheshire@apple.com; rs.ietf@gmx.at; Jason_Livingood@comcast.com; vidhi_goel@apple.com
> Cc: Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com>
> Subject: [PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing
> 
> From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
> 
> Today, congestion control algorithms influence TSO sizing through the
> min_tso_segs() callback, which provides the minimum number of segments used by tcp_tso_autosize(). However, Prague congestion control requires finer control and needs to determine the final TSO segment count directly rather than only providing a minimum bound.
>  
> This patch introduces TCP_CONG_EXACT_TSO_SEGS flag and extends tcp_congestion_ops with an alternative tso_segs() callback. When the flag is set, the congestion control algorithm supplies the final TSO segment count directly and bypasses tcp_tso_autosize(). Otherwise, the existing min_tso_segs() callback continues to provide the minimum segment count used by tcp_tso_autosize().
> 
> This preserves the existing behavior of current congestion control algorithms without introducing additional callbacks while enabling future algorithms to implement custom TSO sizing policies.
> 
> Signed-off-by: Ilpo Järvinen <ij@kernel.org>
> Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
> ---
>  include/net/tcp.h     | 16 +++++++++++++---
>  net/ipv4/tcp_output.c | 17 +++++++++++++----
>  2 files changed, 26 insertions(+), 7 deletions(-)
> 
> diff --git a/include/net/tcp.h b/include/net/tcp.h index 2c5b889530b5..82cd82a19ff9 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -1283,9 +1283,11 @@ enum tcp_ca_ack_event_flags {
>  #define TCP_CONG_ECT_1_NEGOTIATION	BIT(3)
>  /* Cannot fallback to RFC3168 during AccECN negotiation */
>  #define TCP_CONG_NO_FALLBACK_RFC3168	BIT(4)
> +/* Congestion cotnrol provides the exact TSO segment numbers  */
> +#define TCP_CONG_EXACT_TSO_SEGS		BIT(5)
>  #define TCP_CONG_MASK  (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
>  			TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \
> -			TCP_CONG_NO_FALLBACK_RFC3168)
> +			TCP_CONG_NO_FALLBACK_RFC3168 | TCP_CONG_EXACT_TSO_SEGS)
>  
>  union tcp_cc_info;
>  
> @@ -1361,8 +1363,16 @@ struct tcp_congestion_ops {
>  	/* hook for packet ack accounting (optional) */
>  	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
>  
> -	/* override sysctl_tcp_min_tso_segs (optional) */
> -	u32 (*min_tso_segs)(struct sock *sk);
> +	union {
> +		/* Used when TCP_CONG_EXACT_TSO_SEGS is not set,
> +		 * override sysctl_tcp_min_tso_segs (optional)
> +		 */
> +		u32 (*min_tso_segs)(struct sock *sk);
> +		/* Used when TCP_CONG_EXACT_TSO_SEGS is set,
> +		 * override tcp_tso_autosize (optional)
> +		 */
> +		u32 (*tso_segs)(struct sock *sk, u32 mss_now);
> +	};
>  
>  	/* new value of cwnd after loss (required) */
>  	u32  (*undo_cwnd)(struct sock *sk);
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d7c1444b5e30..0de27a87c39e 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2278,11 +2278,20 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
>  	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
>  	u32 min_tso, tso_segs;
>  
> -	min_tso = ca_ops->min_tso_segs ?
> -			ca_ops->min_tso_segs(sk) :
> -			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
> +	min_tso = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
> +
> +	if (ca_ops->flags & TCP_CONG_EXACT_TSO_SEGS) {
> +		if (WARN_ON_ONCE(!ca_ops->tso_segs))
> +			tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
> +		else
> +			tso_segs = ca_ops->tso_segs(sk, mss_now);
> +	} else {
> +		if (ca_ops->min_tso_segs)
> +			min_tso = ca_ops->min_tso_segs(sk);
> +
> +		tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
> +	}
>  
> -	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
>  	return min_t(u32, tso_segs, sk->sk_gso_max_segs);  }

Hello,

I see this commit is marked as Changes Requested; however, I do not see any request yet.

Could anyone let me know which specific request it is?

This commit updated our previously submitted v3 https://lore.kernel.org/all/20260630120145.286497-1-chia-yu.chang@nokia-bell-labs.com/ to have no impact on BPF.

Thanks!
Chia-Yu

Re: [PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing

[Jakub Kicinski]

On Mon, 27 Jul 2026 08:02:00 +0000 Chia-Yu Chang (Nokia) wrote:
> I see this commit is marked as Changes Requested; however, I do not see any request yet.
> 
> Could anyone let me know which specific request it is?
> 
> This commit updated our previously submitted v3 https://lore.kernel.org/all/20260630120145.286497-1-chia-yu.chang@nokia-bell-labs.com/ to have no impact on BPF.

The BPF CI has failed with your patch applied, that's why it was
auto-ejected. You need to fix up the BPF selftests to use the new
callback.

Re: [PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing

[Emil Tsalapatis]

On Mon Jul 27, 2026 at 4:02 AM EDT, Chia-Yu Chang (Nokia) wrote:
>> -----Original Message-----
>> From: Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com> 
>> Sent: Sunday, July 26, 2026 9:38 PM
>> To: horms@kernel.org; dsahern@kernel.org; bpf@vger.kernel.org; netdev@vger.kernel.org; pabeni@redhat.com; jhs@mojatatu.com; kuba@kernel.org; stephen@networkplumber.org; davem@davemloft.net; edumazet@google.com; andrew+netdev@lunn.ch; donald.hunter@gmail.com; kuniyu@google.com; ij@kernel.org; ncardwell@google.com; Koen De Schepper (Nokia) <koen.de_schepper@nokia-bell-labs.com>; g.white@cablelabs.com; ingemar.s.johansson@ericsson.com; mirja.kuehlewind@ericsson.com; cheshire@apple.com; rs.ietf@gmx.at; Jason_Livingood@comcast.com; vidhi_goel@apple.com
>> Cc: Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com>
>> Subject: [PATCH v4 net-next 1/1] tcp: allow congestion controls to override TSO autosizing
>> 
>> From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
>> 

Hi Chia-Yu,

Sorry for the late reply. From the BPF side we had a discussion and
concluded that going ahead with the original change to the struct_ops
without adding a union is fine. AFAIU this is the main delta between v3
and v4, in which case we can go ahead with v3.

>> Today, congestion control algorithms influence TSO sizing through the
>> min_tso_segs() callback, which provides the minimum number of segments used by tcp_tso_autosize(). However, Prague congestion control requires finer control and needs to determine the final TSO segment count directly rather than only providing a minimum bound.
>>  
>> This patch introduces TCP_CONG_EXACT_TSO_SEGS flag and extends tcp_congestion_ops with an alternative tso_segs() callback. When the flag is set, the congestion control algorithm supplies the final TSO segment count directly and bypasses tcp_tso_autosize(). Otherwise, the existing min_tso_segs() callback continues to provide the minimum segment count used by tcp_tso_autosize().
>> 
>> This preserves the existing behavior of current congestion control algorithms without introducing additional callbacks while enabling future algorithms to implement custom TSO sizing policies.
>> 
>> Signed-off-by: Ilpo Järvinen <ij@kernel.org>
>> Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
>> ---
>>  include/net/tcp.h     | 16 +++++++++++++---
>>  net/ipv4/tcp_output.c | 17 +++++++++++++----
>>  2 files changed, 26 insertions(+), 7 deletions(-)
>> 
>> diff --git a/include/net/tcp.h b/include/net/tcp.h index 2c5b889530b5..82cd82a19ff9 100644
>> --- a/include/net/tcp.h
>> +++ b/include/net/tcp.h
>> @@ -1283,9 +1283,11 @@ enum tcp_ca_ack_event_flags {
>>  #define TCP_CONG_ECT_1_NEGOTIATION	BIT(3)
>>  /* Cannot fallback to RFC3168 during AccECN negotiation */
>>  #define TCP_CONG_NO_FALLBACK_RFC3168	BIT(4)
>> +/* Congestion cotnrol provides the exact TSO segment numbers  */
>> +#define TCP_CONG_EXACT_TSO_SEGS		BIT(5)
>>  #define TCP_CONG_MASK  (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
>>  			TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \
>> -			TCP_CONG_NO_FALLBACK_RFC3168)
>> +			TCP_CONG_NO_FALLBACK_RFC3168 | TCP_CONG_EXACT_TSO_SEGS)
>>  
>>  union tcp_cc_info;
>>  
>> @@ -1361,8 +1363,16 @@ struct tcp_congestion_ops {
>>  	/* hook for packet ack accounting (optional) */
>>  	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
>>  
>> -	/* override sysctl_tcp_min_tso_segs (optional) */
>> -	u32 (*min_tso_segs)(struct sock *sk);
>> +	union {
>> +		/* Used when TCP_CONG_EXACT_TSO_SEGS is not set,
>> +		 * override sysctl_tcp_min_tso_segs (optional)
>> +		 */
>> +		u32 (*min_tso_segs)(struct sock *sk);
>> +		/* Used when TCP_CONG_EXACT_TSO_SEGS is set,
>> +		 * override tcp_tso_autosize (optional)
>> +		 */
>> +		u32 (*tso_segs)(struct sock *sk, u32 mss_now);
>> +	};
>>  
>>  	/* new value of cwnd after loss (required) */
>>  	u32  (*undo_cwnd)(struct sock *sk);
>> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d7c1444b5e30..0de27a87c39e 100644
>> --- a/net/ipv4/tcp_output.c
>> +++ b/net/ipv4/tcp_output.c
>> @@ -2278,11 +2278,20 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
>>  	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
>>  	u32 min_tso, tso_segs;
>>  
>> -	min_tso = ca_ops->min_tso_segs ?
>> -			ca_ops->min_tso_segs(sk) :
>> -			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
>> +	min_tso = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
>> +
>> +	if (ca_ops->flags & TCP_CONG_EXACT_TSO_SEGS) {
>> +		if (WARN_ON_ONCE(!ca_ops->tso_segs))
>> +			tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
>> +		else
>> +			tso_segs = ca_ops->tso_segs(sk, mss_now);
>> +	} else {
>> +		if (ca_ops->min_tso_segs)
>> +			min_tso = ca_ops->min_tso_segs(sk);
>> +
>> +		tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
>> +	}
>>  
>> -	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
>>  	return min_t(u32, tso_segs, sk->sk_gso_max_segs);  }
>
> Hello,
>
> I see this commit is marked as Changes Requested; however, I do not see any request yet.
>
> Could anyone let me know which specific request it is?
>
> This commit updated our previously submitted v3 https://lore.kernel.org/all/20260630120145.286497-1-chia-yu.chang@nokia-bell-labs.com/ to have no impact on BPF.

>
> Thanks!
> Chia-Yu