net/smc: wait for tx completions before link freeing

Make sure all pending work requests are completed before freeing
a link.
Dismiss tx pending slots already when terminating a link group to
exploit termination shortcut in tx completion queue handler.

And kill the completion queue tasklets after destroy of the
completion queues, otherwise there is a time window for another
tasklet schedule of an already killed tasklet.

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

3 files changed, 28 insertions, 3 deletions

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ee44e8244d0c..0755bd4b587c 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -548,6 +548,8 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
 			tasklet_kill(&conn->rx_tsklet);
 		else
 			tasklet_unlock_wait(&conn->rx_tsklet);
+	} else {
+		smc_cdc_tx_dismiss_slots(conn);
 	}
 	smc_lgr_unregister_conn(conn);
 	smc_close_active_abort(smc);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index af05daeb0538..c15dcd08dc74 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -520,9 +520,9 @@ static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev)
 	if (!smcibdev->initialized)
 		return;
 	smcibdev->initialized = 0;
-	smc_wr_remove_dev(smcibdev);
 	ib_destroy_cq(smcibdev->roce_cq_recv);
 	ib_destroy_cq(smcibdev->roce_cq_send);
+	smc_wr_remove_dev(smcibdev);
 }
 
 static struct ib_client smc_ib_client;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 619dd89fbac0..337ee52ad3d3 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -50,6 +50,26 @@ struct smc_wr_tx_pend {	/* control data for a pending send request */
 
 /*------------------------------- completion --------------------------------*/
 
+/* returns true if at least one tx work request is pending on the given link */
+static inline bool smc_wr_is_tx_pend(struct smc_link *link)
+{
+	if (find_first_bit(link->wr_tx_mask, link->wr_tx_cnt) !=
+							link->wr_tx_cnt) {
+		return true;
+	}
+	return false;
+}
+
+/* wait till all pending tx work requests on the given link are completed */
+static inline int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
+{
+	if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
+			       SMC_WR_TX_WAIT_PENDING_TIME))
+		return 0;
+	else /* timeout */
+		return -EPIPE;
+}
+
 static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
 {
 	u32 i;
@@ -229,6 +249,7 @@ int smc_wr_tx_put_slot(struct smc_link *link,
 		memset(&link->wr_tx_bufs[idx], 0,
 		       sizeof(link->wr_tx_bufs[idx]));
 		test_and_clear_bit(idx, link->wr_tx_mask);
+		wake_up(&link->wr_tx_wait);
 		return 1;
 	}
 
@@ -512,8 +533,10 @@ void smc_wr_free_link(struct smc_link *lnk)
 {
 	struct ib_device *ibdev;
 
-	memset(lnk->wr_tx_mask, 0,
-	       BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask));
+	if (smc_wr_tx_wait_no_pending_sends(lnk))
+		memset(lnk->wr_tx_mask, 0,
+		       BITS_TO_LONGS(SMC_WR_BUF_CNT) *
+						sizeof(*lnk->wr_tx_mask));
 
 	if (!lnk->smcibdev)
 		return;