[ofw] [PATCH] DAPL v2.0: cma: disconnect can block for excessive times waiting for rdma_cm DREP timeout

[Hefty, Sean]

> @@ -636,13 +637,29 @@ dapls_ib_disconnect(IN DAPL_EP * ep_ptr, IN
> DAT_CLOSE_FLAGS close_flags)
> 
>  	/* ABRUPT close, wait for callback and DISCONNECTED state */
>  	if (close_flags == DAT_CLOSE_ABRUPT_FLAG) {
> +		DAPL_EVD *evd = NULL;
> +		DAT_EVENT_NUMBER num = DAT_CONNECTION_EVENT_DISCONNECTED;
> +
>  		dapl_os_lock(&ep_ptr->header.lock);
> -		while (ep_ptr->param.ep_state != DAT_EP_STATE_DISCONNECTED) {
> +		/* limit DREP waiting, other side could be down */
> +		while (--drep_time && ep_ptr->param.ep_state !=
> DAT_EP_STATE_DISCONNECTED) {
>  			dapl_os_unlock(&ep_ptr->header.lock);
>  			dapl_os_sleep_usec(10000);

gak - can't you wait on an event using some timeout interval?

>  			dapl_os_lock(&ep_ptr->header.lock);
>  		}
> +		if (ep_ptr->param.ep_state != DAT_EP_STATE_DISCONNECTED) {
> +			dapl_log(DAPL_DBG_TYPE_WARN,
> +				 " WARNING: disconnect(ep %p, conn %p, id %d) timed
> out\n",
> +				 ep_ptr, conn, (conn ? conn->cm_id : 0));
> +			ep_ptr->param.ep_state = DAT_EP_STATE_DISCONNECTED;
> +			evd = (DAPL_EVD *)ep_ptr->param.connect_evd_handle;
> +		}
>  		dapl_os_unlock(&ep_ptr->header.lock);
> +
> +		if (evd) {
> +			dapl_sp_remove_ep(ep_ptr);
> +			dapls_evd_post_connection_event(evd, num, ep_ptr, 0, 0);
> +		}
>  	}