tcp: Make SYN ACK RTO tunable by BPF programs with TFO
Subsystems (4)
PATCH 1/1 tcp: Make SYN ACK RTO tunable by BPF programs with TFO
Instead of the hardcoded TCP_TIMEOUT_INIT, this diff calls tcp_timeout_init to initiate req->timeout like the non TFO SYN ACK case.
Tested using the following packetdrill script, on a host with a BPF program that sets the initial connect timeout to 10ms.
../../common/defaults.sh
// Initialize connection
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0 +0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+0 < S 0:0(0) win 32792 <mss 1000,sackOK,FO TFO_COOKIE> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.02 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.04 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 < . 1:1(0) ack 1 win 32792
+0 accept(3, ..., ...) = 4
--- net/ipv4/tcp_fastopen.c | 3 ++- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-)
net/ipv4/tcp_fastopen.c +2 -1
@@ -272,8 +272,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,* The request socket is not added to the ehash * because it's been added to the accept queue directly. */ + req->timeout =tcp_timeout_init (child);inet_csk_reset_xmit_timer (child,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT ,TCP_RTO_MAX ); + req->timeout,TCP_RTO_MAX );refcount_set (&req->rsk_refcnt,2 );
net/ipv4/tcp_timer.c +1 -1
@@ -428,7 +428,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)if (!tp->retrans_stamp) tp->retrans_stamp =tcp_time_stamp (tp);inet_csk_reset_xmit_timer (sk,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT << req->num_timeout,TCP_RTO_MAX ); + req->timeout << req->num_timeout,TCP_RTO_MAX ); }
Signature · 1 line
2.30.2
Quoted 50 lines · Jie Meng
Instead of the hardcoded
TCP_TIMEOUT_INIT, this diff callstcp_timeout_initto initiatereq->timeoutlike the non TFO SYN ACK case.Tested using the following packetdrill script, on a host with a BPF program that sets the initial connect timeout to 10ms.
../../common/defaults.sh// Initialize connection
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3+0
setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4)= 0 +0bind(3, ..., ...)= 0
+0listen(3, 1)= 0+0 < S 0:0(0) win 32792 <mss 1000,sackOK,FO TFO_COOKIE> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.02 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.04 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 < . 1:1(0) ack 1 win 32792 +0 accept(3, ..., ...) = 4Signed-off-by Jie Meng <[email protected]>--- net/ipv4/tcp_fastopen.c | 3 ++- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-)net/ipv4/tcp_fastopen.c +2
-1@@ -272,8 +272,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,* The request socket is not added to the ehash * because it's been added to the accept queue directly. */ + req->timeout =tcp_timeout_init (child);inet_csk_reset_xmit_timer (child,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT ,TCP_RTO_MAX ); + req->timeout,TCP_RTO_MAX );refcount_set (&req->rsk_refcnt,2 );net/ipv4/tcp_timer.c +0
-0
net/ipv4/tcp_timer.c static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
Quoted 9 lines
net/ipv4/tcp_timer.c +1
-2@@ -428,7 +428,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)if (!tp->retrans_stamp) tp->retrans_stamp =tcp_time_stamp (tp);inet_csk_reset_xmit_timer (sk,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT << req->num_timeout,TCP_RTO_MAX ); + req->timeout << req->num_timeout,TCP_RTO_MAX ); } --
Looks good to me. Thanks for the feature!
neal
Yuchung Cheng
Acked-byQuoted 60 lines · Neal Cardwell
Quoted 58 lines · Jie Meng
Instead of the hardcoded
TCP_TIMEOUT_INIT, this diff callstcp_timeout_initto initiatereq->timeoutlike the non TFO SYN ACK case.Tested using the following packetdrill script, on a host with a BPF program that sets the initial connect timeout to 10ms.
../../common/defaults.sh// Initialize connection
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3+0
setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4)= 0 +0bind(3, ..., ...)= 0
+0listen(3, 1)= 0+0 < S 0:0(0) win 32792 <mss 1000,sackOK,FO TFO_COOKIE> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.02 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.04 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 < . 1:1(0) ack 1 win 32792 +0 accept(3, ..., ...) = 4Signed-off-by Jie Meng <[email protected]>--- net/ipv4/tcp_fastopen.c | 3 ++- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-)net/ipv4/tcp_fastopen.c +2
-1@@ -272,8 +272,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,* The request socket is not added to the ehash * because it's been added to the accept queue directly. */ + req->timeout =tcp_timeout_init (child);inet_csk_reset_xmit_timer (child,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT ,TCP_RTO_MAX ); + req->timeout,TCP_RTO_MAX );refcount_set (&req->rsk_refcnt,2 );net/ipv4/tcp_timer.c +1
-1@@ -428,7 +428,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)if (!tp->retrans_stamp) tp->retrans_stamp =tcp_time_stamp (tp);inet_csk_reset_xmit_timer (sk,ICSK_TIME_RETRANS , -TCP_TIMEOUT_INIT << req->num_timeout,TCP_RTO_MAX ); + req->timeout << req->num_timeout,TCP_RTO_MAX ); }
Quoted 5 lines
Quoted 1 line
--
Looks good to me. Thanks for the feature!
Acked-by Neal Cardwell <[email protected]>
Would be great to have a companion patch on SYN timeout as well.
Quoted 2 lines
neal
Quoted 14 lines · Jie Meng
Instead of the hardcoded
TCP_TIMEOUT_INIT, this diff callstcp_timeout_initto initiatereq->timeoutlike the non TFO SYN ACK case.Tested using the following packetdrill script, on a host with a BPF program that sets the initial connect timeout to 10ms.
../../common/defaults.sh// Initialize connection
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3+0
setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4)= 0 +0bind(3, ..., ...)= 0
+0listen(3, 1)= 0
Quoted 8 lines
+0 < S 0:0(0) win 32792 <mss 1000,sackOK,FO TFO_COOKIE> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.02 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.04 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> +.01 < . 1:1(0) ack 1 win 32792 +0 accept(3, ..., ...) = 4
This patch was applied to netdev/net-next.git (master) by David S. Miller <[email protected]>:
Hello:
This patch was applied to netdev/net-next.git (master) by David S. Miller <[email protected]>:
Quoted 9 lines · On Mon, 15 Aug 2022 13:29:00 -0700 you wrote:
Instead of the hardcoded
TCP_TIMEOUT_INIT, this diff callstcp_timeout_initto initiatereq->timeoutlike the non TFO SYN ACK case.Tested using the following packetdrill script, on a host with a BPF program that sets the initial connect timeout to 10ms.
../../common/defaults.sh[...]
Here is the summary with links:
- [net-next] tcp: Make SYN ACK RTO tunable by BPF programs with TFO
https://git.kernel.org/netdev/net-next/c/8ea731d4c2ce
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html