1 files changed, 59 insertions, 11 deletions

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 9d5a97168969..619b3bab3824 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -18,6 +18,7 @@
 #include "smc_tx.h"
 #include "smc_rx.h"
 #include "smc_close.h"
+#include "smc_ism.h"
 
 /********************************** send *************************************/
 
@@ -28,13 +29,15 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 {
 	struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
 	struct smc_connection *conn = cdcpend->conn;
+	struct smc_buf_desc *sndbuf_desc;
 	struct smc_sock *smc;
 	int diff;
 
+	sndbuf_desc = conn->sndbuf_desc;
 	smc = container_of(conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
-	if (!wc_status) {
-		diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
+	if (!wc_status && sndbuf_desc) {
+		diff = smc_curs_diff(sndbuf_desc->len,
 				     &cdcpend->conn->tx_curs_fin,
 				     &cdcpend->cursor);
 		/* sndbuf_space is decreased in smc_sendmsg */
@@ -48,9 +51,19 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 		conn->tx_cdc_seq_fin = cdcpend->ctrl_seq;
 	}
 
-	if (atomic_dec_and_test(&conn->cdc_pend_tx_wr) &&
-	    unlikely(wq_has_sleeper(&conn->cdc_pend_tx_wq)))
-		wake_up(&conn->cdc_pend_tx_wq);
+	if (atomic_dec_and_test(&conn->cdc_pend_tx_wr)) {
+		/* If user owns the sock_lock, mark the connection need sending.
+		 * User context will later try to send when it release sock_lock
+		 * in smc_release_cb()
+		 */
+		if (sock_owned_by_user(&smc->sk))
+			conn->tx_in_release_sock = true;
+		else
+			smc_tx_pending(conn);
+
+		if (unlikely(wq_has_sleeper(&conn->cdc_pend_tx_wq)))
+			wake_up(&conn->cdc_pend_tx_wq);
+	}
 	WARN_ON(atomic_read(&conn->cdc_pend_tx_wr) < 0);
 
 	smc_tx_sndbuf_nonfull(smc);
@@ -72,7 +85,7 @@ int smc_cdc_get_free_slot(struct smc_connection *conn,
 		/* abnormal termination */
 		if (!rc)
 			smc_wr_tx_put_slot(link,
-					   (struct smc_wr_tx_pend_priv *)pend);
+					   (struct smc_wr_tx_pend_priv *)(*pend));
 		rc = -EPIPE;
 	}
 	return rc;
@@ -243,6 +256,14 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
 		return rc;
 	smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn);
 	conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
+
+	if (smc_ism_support_dmb_nocopy(conn->lgr->smcd))
+		/* if local sndbuf shares the same memory region with
+		 * peer DMB, then don't update the tx_curs_fin
+		 * and sndbuf_space until peer has consumed the data.
+		 */
+		return 0;
+
 	/* Calculate transmitted data and increment free send buffer space */
 	diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
 			     &conn->tx_curs_sent);
@@ -254,7 +275,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
 	smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
 
 	smc_tx_sndbuf_nonfull(smc);
-	return rc;
+	return 0;
 }
 
 /********************************* receive ***********************************/
@@ -311,7 +332,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 {
 	union smc_host_cursor cons_old, prod_old;
 	struct smc_connection *conn = &smc->conn;
-	int diff_cons, diff_prod;
+	int diff_cons, diff_prod, diff_tx;
 
 	smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
 	smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
@@ -327,6 +348,29 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		atomic_add(diff_cons, &conn->peer_rmbe_space);
 		/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
 		smp_mb__after_atomic();
+
+		/* if local sndbuf shares the same memory region with
+		 * peer RMB, then update tx_curs_fin and sndbuf_space
+		 * here since peer has already consumed the data.
+		 */
+		if (conn->lgr->is_smcd &&
+		    smc_ism_support_dmb_nocopy(conn->lgr->smcd)) {
+			/* Calculate consumed data and
+			 * increment free send buffer space.
+			 */
+			diff_tx = smc_curs_diff(conn->sndbuf_desc->len,
+						&conn->tx_curs_fin,
+						&conn->local_rx_ctrl.cons);
+			/* increase local sndbuf space and fin_curs */
+			smp_mb__before_atomic();
+			atomic_add(diff_tx, &conn->sndbuf_space);
+			/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+			smp_mb__after_atomic();
+			smc_curs_copy(&conn->tx_curs_fin,
+				      &conn->local_rx_ctrl.cons, conn);
+
+			smc_tx_sndbuf_nonfull(smc);
+		}
 	}
 
 	diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
@@ -350,8 +394,12 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 	/* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */
 	if ((diff_cons && smc_tx_prepared_sends(conn)) ||
 	    conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
-	    conn->local_rx_ctrl.prod_flags.urg_data_pending)
-		smc_tx_sndbuf_nonempty(conn);
+	    conn->local_rx_ctrl.prod_flags.urg_data_pending) {
+		if (!sock_owned_by_user(&smc->sk))
+			smc_tx_pending(conn);
+		else
+			conn->tx_in_release_sock = true;
+	}
 
 	if (diff_cons && conn->urg_tx_pend &&
 	    atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) {
@@ -368,7 +416,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smc->sk.sk_shutdown |= RCV_SHUTDOWN;
 		if (smc->clcsock && smc->clcsock->sk)
 			smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
-		sock_set_flag(&smc->sk, SOCK_DONE);
+		smc_sock_set_flag(&smc->sk, SOCK_DONE);
 		sock_hold(&smc->sk); /* sock_put in close_work */
 		if (!queue_work(smc_close_wq, &conn->close_work))
 			sock_put(&smc->sk);