Re: [PATCH v5 3/4] tcp: Resend SYN for inbound connections

[David Gibson <david@gibson.dropbear.id.au>]

[-- Attachment #1: Type: text/plain, Size: 6069 bytes --]

On Fri, Oct 17, 2025 at 12:27:42PM +0800, Yumei Huang wrote:
> If a client connects while guest is not connected or ready yet,
> resend SYN instead of just resetting connection after 10 seconds.
> 
> Use the same backoff calculation for the timeout as linux kernel.
> 
> Link: https://bugs.passt.top/show_bug.cgi?id=153
> Signed-off-by: Yumei Huang <yuhuang@redhat.com>
> ---
>  tcp.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++--------
>  tcp.h |  5 +++++
>  2 files changed, 52 insertions(+), 8 deletions(-)
> 
> diff --git a/tcp.c b/tcp.c
> index 2ec4b0c..71e2da0 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -179,9 +179,11 @@
>   *
>   * Timeouts are implemented by means of timerfd timers, set based on flags:
>   *
> - * - SYN_TIMEOUT: if no ACK is received from tap/guest during handshake (flag
> - *   ACK_FROM_TAP_DUE without ESTABLISHED event) within this time, reset the
> - *   connection
> + * - SYN_TIMEOUT_INIT: if no ACK is received from tap/guest during handshake
> + *   (flag ACK_FROM_TAP_DUE without ESTABLISHED event) within this time, resend
> + *   SYN. It's the starting timeout for the first SYN retry. If this persists
> + *   for more than TCP_MAX_RETRIES or (tcp_syn_retries +
> + *   tcp_syn_linear_timeouts) times in a row, reset the connection
>   *
>   * - ACK_TIMEOUT: if no ACK segment was received from tap/guest, after sending
>   *   data (flag ACK_FROM_TAP_DUE with ESTABLISHED event), re-send data from the
> @@ -340,7 +342,7 @@ enum {
>  #define WINDOW_DEFAULT			14600		/* RFC 6928 */
>  
>  #define ACK_INTERVAL			10		/* ms */
> -#define SYN_TIMEOUT			10		/* s */
> +#define SYN_TIMEOUT_INIT		1		/* s */
>  #define ACK_TIMEOUT			2
>  #define FIN_TIMEOUT			60
>  #define ACT_TIMEOUT			7200
> @@ -365,6 +367,9 @@ uint8_t tcp_migrate_rcv_queue		[TCP_MIGRATE_RCV_QUEUE_MAX];
>  
>  #define TCP_MIGRATE_RESTORE_CHUNK_MIN	1024 /* Try smaller when above this */
>  
> +#define TCP_SYN_RETRIES		"/proc/sys/net/ipv4/tcp_syn_retries"
> +#define TCP_SYN_LINEAR_TIMEOUTS	"/proc/sys/net/ipv4/tcp_syn_linear_timeouts"						\
> +
>  /* "Extended" data (not stored in the flow table) for TCP flow migration */
>  static struct tcp_tap_transfer_ext migrate_ext[FLOW_MAX];
>  
> @@ -581,8 +586,13 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
>  	if (conn->flags & ACK_TO_TAP_DUE) {
>  		it.it_value.tv_nsec = (long)ACK_INTERVAL * 1000 * 1000;
>  	} else if (conn->flags & ACK_FROM_TAP_DUE) {
> -		if (!(conn->events & ESTABLISHED))
> -			it.it_value.tv_sec = SYN_TIMEOUT;
> +		if (!(conn->events & ESTABLISHED)) {
> +			if (conn->retries < c->tcp.syn_linear_timeouts)
> +				it.it_value.tv_sec = SYN_TIMEOUT_INIT;
> +			else
> +				it.it_value.tv_sec = SYN_TIMEOUT_INIT <<
> +					(conn->retries - c->tcp.syn_linear_timeouts);
> +		}
>  		else
>  			it.it_value.tv_sec = ACK_TIMEOUT;
>  	} else if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED)) {
> @@ -2409,8 +2419,17 @@ void tcp_timer_handler(const struct ctx *c, union epoll_ref ref)
>  		tcp_timer_ctl(c, conn);
>  	} else if (conn->flags & ACK_FROM_TAP_DUE) {
>  		if (!(conn->events & ESTABLISHED)) {
> -			flow_dbg(conn, "handshake timeout");
> -			tcp_rst(c, conn);
> +			if (conn->retries >= TCP_MAX_RETRIES ||
> +			    conn->retries >= (c->tcp.tcp_syn_retries +
> +					      c->tcp.syn_linear_timeouts)) {
> +				flow_dbg(conn, "handshake timeout");
> +				tcp_rst(c, conn);
> +			} else {
> +				flow_trace(conn, "SYN timeout, retry");
> +				tcp_send_flag(c, conn, SYN);
> +				conn->retries++;
> +				tcp_timer_ctl(c, conn);
> +			}
>  		} else if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED)) {
>  			flow_dbg(conn, "FIN timeout");
>  			tcp_rst(c, conn);
> @@ -2766,6 +2785,24 @@ static socklen_t tcp_probe_tcp_info(void)
>  	return sl;
>  }
>  
> +/**
> + * tcp_syn_params_init() - Get initial syn params for inbound connection

Stefano's comment wasn't 100% clear, but I believe he was suggesting
	s/syn params/SYN parameters/
in the comment here for clarity.

> + * @c:		Execution context
> +*/
> +void tcp_syn_params_init(struct ctx *c)
> +{
> +	intmax_t tcp_syn_retries, syn_linear_timeouts;
> +
> +	tcp_syn_retries = read_file_integer(TCP_SYN_RETRIES, 8);
> +	syn_linear_timeouts = read_file_integer(TCP_SYN_LINEAR_TIMEOUTS, 1);
> +
> +	c->tcp.tcp_syn_retries = MIN(tcp_syn_retries, UINT8_MAX);
> +	c->tcp.syn_linear_timeouts = MIN(syn_linear_timeouts, UINT8_MAX);
> +
> +	debug("TCP SYN parameters: retries=%"PRIu8", linear_timeouts=%"PRIu8,
> +	      c->tcp.tcp_syn_retries, c->tcp.syn_linear_timeouts);
> +}
> +
>  /**
>   * tcp_init() - Get initial sequence, hash secret, initialise per-socket data
>   * @c:		Execution context
> @@ -2776,6 +2813,8 @@ int tcp_init(struct ctx *c)
>  {
>  	ASSERT(!c->no_tcp);
>  
> +	tcp_syn_params_init(c);
> +
>  	tcp_sock_iov_init(c);
>  
>  	memset(init_sock_pool4,		0xff,	sizeof(init_sock_pool4));
> diff --git a/tcp.h b/tcp.h
> index 234a803..bb58324 100644
> --- a/tcp.h
> +++ b/tcp.h
> @@ -59,12 +59,17 @@ union tcp_listen_epoll_ref {
>   * @fwd_out:		Port forwarding configuration for outbound packets
>   * @timer_run:		Timestamp of most recent timer run
>   * @pipe_size:		Size of pipes for spliced connections
> + * @tcp_syn_retries:	Number of times initial SYNs during handshake

Perhaps,

"Number of SYN retries using exponential backoff"

> + * @syn_linear_timeouts: Number of SYN retries using linear backoff timeout
> + * 			  before switching to exponential backoff timeout
>   */
>  struct tcp_ctx {
>  	struct fwd_ports fwd_in;
>  	struct fwd_ports fwd_out;
>  	struct timespec timer_run;
>  	size_t pipe_size;
> +	uint8_t tcp_syn_retries;
> +	uint8_t syn_linear_timeouts;
>  };
>  
>  #endif /* TCP_H */
> -- 
> 2.47.0
> 

-- 
David Gibson (he or they)	| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you, not the other way
				| around.
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]