Re: [PATCH v4 3/4] tcp: Resend SYN for inbound connections

On Thu, 16 Oct 2025 10:34:22 +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 --- tcp.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++-------- tcp.h | 2 ++ 2 files changed, 49 insertions(+), 8 deletions(-)

diff --git a/tcp.c b/tcp.c index 2ec4b0c..3003333 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 +367,10 @@ 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"

It's quite obvious those are names of sysctl entries, I think we can drop the _SYSCTL suffix and keep this shorter without losing any information/indication.

+ /* "Extended" data (not stored in the flow table) for TCP flow migration */ static struct tcp_tap_transfer_ext migrate_ext[FLOW_MAX];

@@ -581,8 +587,13 @@ 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 +2420,16 @@ 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.syn_linear_timeouts))) {

That doesn't seem to match the sysctl documentation for tcp_syn_retries, which should be the *total* number of retries, not excluding the ones with "linear timeouts". This is pretty hard to read, by the way. It could be: if (conn->retries >= TCP_MAX_RETRIES || conn->retries >= ...) {

+ 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

SYN, parameters

+ * @c: Execution context +*/ +void tcp_syn_params_init(struct ctx *c) +{ + long tcp_syn_retries, syn_linear_timeouts; + + tcp_syn_retries = read_file_integer(TCP_SYN_RETRIES_SYSCTL, 8); + syn_linear_timeouts = read_file_integer(TCP_SYN_LINEAR_TIMEOUTS_SYSCTL, 1); + + c->tcp.tcp_syn_retries = (uint8_t)MIN(tcp_syn_retries, UINT8_MAX); + c->tcp.syn_linear_timeouts = (uint8_t)MIN(syn_linear_timeouts, UINT8_MAX);

I don't think you need those casts, MIN(..., UINT8_MAX) already guarantees that the number is <= UINT8_MAX, and in any case the cast won't fix anything here.

+ + 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..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;

These should be added to the documentation for struct tcp_ctx, above.

};

#endif /* TCP_H */

-- Stefano