Re: [PATCH v2 2/3] tcp: Resend SYN for inbound connections

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

[-- Attachment #1: Type: text/plain, Size: 8034 bytes --]

On Fri, Oct 10, 2025 at 03:46:59PM +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.
> 
> Signed-off-by: Yumei Huang <yuhuang@redhat.com>
> ---
>  tcp.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
>  tcp.h |  2 ++
>  2 files changed, 89 insertions(+), 8 deletions(-)
> 
> diff --git a/tcp.c b/tcp.c
> index 2ec4b0c..85bbdac 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
> @@ -309,6 +311,7 @@
>  #include "tcp_internal.h"
>  #include "tcp_buf.h"
>  #include "tcp_vu.h"
> +#include "lineread.h"
>  
>  /*
>   * The size of TCP header (including options) is given by doff (Data Offset)
> @@ -340,7 +343,7 @@ 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

As we've discussed in some places, the RFCs largely treat SYN retries
the same as data retransmits.  ACK_TIMEOUT controls the latter.  2s is
a little odd, IIRC the RFC suggests 3, I'm not sure what Linux does by
default.  In any case, I'm wondering if we should use a single define
for the initial value of both timeouts.

>  #define FIN_TIMEOUT			60
>  #define ACT_TIMEOUT			7200
> @@ -365,6 +368,10 @@ 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_SYSCTL		"/proc/sys/net/ipv4/tcp_syn_retries"
> +#define TCP_SYN_LINEAR_TIMEOUTS_SYSCTL						\
> +	"/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 +588,13 @@ 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)) {
> @@ -1961,6 +1973,7 @@ static void tcp_conn_from_sock_finish(const struct ctx *c,
>  	}
>  
>  	tcp_send_flag(c, conn, ACK);
> +	conn->retries = 0;

I know Stefano said you needed to add this, but on a closer
examination I don't think you do.  tcp_tap_handler() calls
tcp_update_seqack_from_tap() if !ESTABLISHED.  That will clear
retrans/retries if the ack number from the guest has advanced.  That
will occur when the guest SYN-ACKs our SYN, which is exactly the point
at which we should clear the retries count.

>  
>  	/* The client might have sent data already, which we didn't
>  	 * dequeue waiting for SYN,ACK from tap -- check now.
> @@ -2409,8 +2422,16 @@ 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 == MIN(TCP_MAX_RETRIES,
> +				(c->tcp.tcp_syn_retries + c->tcp.tcp_syn_retries))) {

Should this be tcp_syn_retries + linear_timeouts?

Also, probably safer to use a >= rather than == - if we somehow send
an extra retry, we don't want to then retry forever.

> +				flow_dbg(conn, "handshake timeout");
> +				tcp_rst(c, conn);
> +			} else {
> +				flow_dbg(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 +2787,62 @@ static socklen_t tcp_probe_tcp_info(void)
>  	return sl;
>  }
>  
> +/**
> + * get_tcp_syn_param() - Read SYN parameters from /proc/sys
> + * @path: Path to the sysctl file
> + * @fallback: Default value if file can't be read
> + *
> + * Return: Parameter value, fallback on failure
> +*/
> +int get_tcp_syn_param(const char *path, int fallback)

I wonder if it might be worth making a new function in util.c to read
a file containing a single number.

> +{
> +	char *line, *end;
> +	struct lineread lr;
> +	long value;
> +	ssize_t len;
> +	int fd;
> +
> +	fd = open(path, O_RDONLY | O_CLOEXEC);
> +	if (fd < 0) {
> +		debug("Unable to open %s", path);
> +		return fallback;
> +	}
> +
> +	lineread_init(&lr, fd);
> +	len = lineread_get(&lr, &line);
> +	close(fd);
> +
> +	if (len < 0) {
> +		debug("Unable to read %s", path);
> +		return fallback;
> +	}
> +
> +	errno = 0;
> +	value = strtol(line, &end, 10);
> +	if (*end && *end != '\n') {
> +		debug("Invalid format in %s", path);
> +		return fallback;
> +	}
> +	if (errno || value < 0 || value > INT_MAX) {
> +		debug("Invalid value in %s: %ld", path, value);
> +		return fallback;
> +	}
> +	return (int)value;

You return an (int) here, but store the value into a uint8_t in the
caller.  That will cause unexpected results if the value you read is
greater than 255.  Somewhere you need to check for this and clamp the
value.  I'd suggest the function actually reading /proc return a long
long (for reuseability), then clamp it in the caller.

> +}
> +
> +/**
> + * tcp_syn_params_init() - Get initial syn params for inbound connection
> + * @c:		Execution context
> +*/
> +void tcp_syn_params_init(struct ctx *c)
> +{
> +	c->tcp.tcp_syn_retries = get_tcp_syn_param(TCP_SYN_RETRIES_SYSCTL, 8);
> +	c->tcp.syn_linear_timeouts =
> +		get_tcp_syn_param(TCP_SYN_LINEAR_TIMEOUTS_SYSCTL, 1);
> +	debug("TCP SYN parameters: retries=%d, linear_timeouts=%d",
> +		  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 +2853,8 @@ 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..df699a4 100644
> --- a/tcp.h
> +++ b/tcp.h
> @@ -65,6 +65,8 @@ struct tcp_ctx {
>  	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 --]