net/smc: periodic testlink support

Add periodic LLC testlink support to ensure the link is still active.
The interval time is initialized using the value of
sysctl_tcp_keepalive_time.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/af_smc.c

@@ -294,6 +294,7 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
 
 static int smc_clnt_conf_first_link(struct smc_sock *smc)
 {
+	struct net *net = sock_net(smc->clcsock->sk);
 	struct smc_link_group *lgr = smc->conn.lgr;
 	struct smc_link *link;
 	int rest;
@@ -353,7 +354,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
-	link->state = SMC_LNK_ACTIVE;
+	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
 
 	return 0;
 }
@@ -715,6 +716,7 @@ void smc_close_non_accepted(struct sock *sk)
 
 static int smc_serv_conf_first_link(struct smc_sock *smc)
 {
+	struct net *net = sock_net(smc->clcsock->sk);
 	struct smc_link_group *lgr = smc->conn.lgr;
 	struct smc_link *link;
 	int rest;
@@ -769,7 +771,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 		return rc;
 	}
 
-	link->state = SMC_LNK_ACTIVE;
+	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
 
 	return 0;
 }

net/smc/smc_core.c

@@ -310,6 +310,7 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr)
 /* remove a link group */
 void smc_lgr_free(struct smc_link_group *lgr)
 {
+	smc_llc_link_flush(&lgr->lnk[SMC_SINGLE_LINK]);
 	smc_lgr_free_bufs(lgr);
 	smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
 	kfree(lgr);
@@ -332,6 +333,7 @@ void smc_lgr_terminate(struct smc_link_group *lgr)
 	struct rb_node *node;
 
 	smc_lgr_forget(lgr);
+	smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
 
 	write_lock_bh(&lgr->conns_lock);
 	node = rb_first(&lgr->conns_all);

net/smc/smc_core.h

@@ -79,6 +79,7 @@ struct smc_link {
 	dma_addr_t		wr_rx_dma_addr;	/* DMA address of wr_rx_bufs */
 	u64			wr_rx_id;	/* seq # of last recv WR */
 	u32			wr_rx_cnt;	/* number of WR recv buffers */
+	unsigned long		wr_rx_tstamp;	/* jiffies when last buf rx */
 
 	struct ib_reg_wr	wr_reg;		/* WR register memory region */
 	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
@@ -101,6 +102,9 @@ struct smc_link {
 	int			llc_confirm_resp_rc; /* rc from conf_resp msg */
 	struct completion	llc_add;	/* wait for rx of add link */
 	struct completion	llc_add_resp;	/* wait for rx of add link rsp*/
+	struct delayed_work	llc_testlink_wrk; /* testlink worker */
+	struct completion	llc_testlink_resp; /* wait for rx of testlink */
+	int			llc_testlink_time; /* testlink interval */
 };
 
 /* For now we just allow one parallel link per link group. The SMC protocol

net/smc/smc_llc.c

@@ -397,7 +397,8 @@ static void smc_llc_rx_test_link(struct smc_link *link,
 				 struct smc_llc_msg_test_link *llc)
 {
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
-		/* unused as long as we don't send this type of msg */
+		if (link->state == SMC_LNK_ACTIVE)
+			complete(&link->llc_testlink_resp);
 	} else {
 		smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP);
 	}
@@ -502,6 +503,65 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
 	}
 }
 
+/***************************** worker ****************************************/
+
+static void smc_llc_testlink_work(struct work_struct *work)
+{
+	struct smc_link *link = container_of(to_delayed_work(work),
+					     struct smc_link, llc_testlink_wrk);
+	unsigned long next_interval;
+	struct smc_link_group *lgr;
+	unsigned long expire_time;
+	u8 user_data[16] = { 0 };
+	int rc;
+
+	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+	if (link->state != SMC_LNK_ACTIVE)
+		return;		/* don't reschedule worker */
+	expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
+	if (time_is_after_jiffies(expire_time)) {
+		next_interval = expire_time - jiffies;
+		goto out;
+	}
+	reinit_completion(&link->llc_testlink_resp);
+	smc_llc_send_test_link(link, user_data, SMC_LLC_REQ);
+	/* receive TEST LINK response over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0) {
+		smc_lgr_terminate(lgr);
+		return;
+	}
+	next_interval = link->llc_testlink_time;
+out:
+	schedule_delayed_work(&link->llc_testlink_wrk, next_interval);
+}
+
+void smc_llc_link_active(struct smc_link *link, int testlink_time)
+{
+	init_completion(&link->llc_testlink_resp);
+	INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
+	link->state = SMC_LNK_ACTIVE;
+	if (testlink_time) {
+		link->llc_testlink_time = testlink_time * HZ;
+		schedule_delayed_work(&link->llc_testlink_wrk,
+				      link->llc_testlink_time);
+	}
+}
+
+/* called in tasklet context */
+void smc_llc_link_inactive(struct smc_link *link)
+{
+	link->state = SMC_LNK_INACTIVE;
+	cancel_delayed_work(&link->llc_testlink_wrk);
+}
+
+/* called in worker context */
+void smc_llc_link_flush(struct smc_link *link)
+{
+	cancel_delayed_work_sync(&link->llc_testlink_wrk);
+}
+
 /***************************** init, exit, misc ******************************/
 
 static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {

net/smc/smc_llc.h

@@ -44,6 +44,9 @@ int smc_llc_send_delete_link(struct smc_link *link,
 			     enum smc_llc_reqresp reqresp);
 int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16],
 			   enum smc_llc_reqresp reqresp);
+void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_inactive(struct smc_link *link);
+void smc_llc_link_flush(struct smc_link *link);
 int smc_llc_init(void) __init;
 
 #endif /* SMC_LLC_H */

net/smc/smc_wr.c

@@ -376,6 +376,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 	for (i = 0; i < num; i++) {
 		link = wc[i].qp->qp_context;
 		if (wc[i].status == IB_WC_SUCCESS) {
+			link->wr_rx_tstamp = jiffies;
 			smc_wr_rx_demultiplex(&wc[i]);
 			smc_wr_rx_post(link); /* refill WR RX */
 		} else {