net/smc: add SMC-D support in data transfer

The data transfer and CDC message headers differ in SMC-R and SMC-D.
This patch adds support for the SMC-D data transfer to the existing SMC
code. It consists of the following:

* SMC-D CDC support
* SMC-D tx support
* SMC-D rx support

The CDC header is stored at the beginning of the receive buffer. Thus, a
rx_offset variable is added for the CDC header offset within the buffer
(0 for SMC-R).

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/smc.h

@@ -183,6 +183,11 @@ struct smc_connection {
 	spinlock_t		acurs_lock;	/* protect cursors */
 #endif
 	struct work_struct	close_work;	/* peer sent some closing */
+	struct tasklet_struct	rx_tsklet;	/* Receiver tasklet for SMC-D */
+	u8			rx_off;		/* receive offset:
+						 * 0 for SMC-R, 32 for SMC-D
+						 */
+	u64			peer_token;	/* SMC-D token of peer */
 };
 
 struct smc_sock {				/* smc sock container */

net/smc/smc_cdc.c

@@ -117,7 +117,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	return rc;
 }
 
-int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 {
 	struct smc_cdc_tx_pend *pend;
 	struct smc_wr_buf *wr_buf;
@@ -130,6 +130,21 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	return smc_cdc_msg_send(conn, wr_buf, pend);
 }
 
+int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+{
+	int rc;
+
+	if (conn->lgr->is_smcd) {
+		spin_lock_bh(&conn->send_lock);
+		rc = smcd_cdc_msg_send(conn);
+		spin_unlock_bh(&conn->send_lock);
+	} else {
+		rc = smcr_cdc_get_slot_and_msg_send(conn);
+	}
+
+	return rc;
+}
+
 static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
 			      unsigned long data)
 {
@@ -157,6 +172,45 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
 				(unsigned long)conn);
 }
 
+/* Send a SMC-D CDC header.
+ * This increments the free space available in our send buffer.
+ * Also update the confirmed receive buffer with what was sent to the peer.
+ */
+int smcd_cdc_msg_send(struct smc_connection *conn)
+{
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	struct smcd_cdc_msg cdc;
+	int rc, diff;
+
+	memset(&cdc, 0, sizeof(cdc));
+	cdc.common.type = SMC_CDC_MSG_TYPE;
+	cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap;
+	cdc.prod_count = conn->local_tx_ctrl.prod.count;
+
+	cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap;
+	cdc.cons_count = conn->local_tx_ctrl.cons.count;
+	cdc.prod_flags = conn->local_tx_ctrl.prod_flags;
+	cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
+	rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
+	if (rc)
+		return rc;
+	smc_curs_write(&conn->rx_curs_confirmed,
+		       smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn);
+	/* 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);
+	/* increased by confirmed number of bytes */
+	smp_mb__before_atomic();
+	atomic_add(diff, &conn->sndbuf_space);
+	/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+	smp_mb__after_atomic();
+	smc_curs_write(&conn->tx_curs_fin,
+		       smc_curs_read(&conn->tx_curs_sent, conn), conn);
+
+	smc_tx_sndbuf_nonfull(smc);
+	return rc;
+}
+
 /********************************* receive ***********************************/
 
 static inline bool smc_cdc_before(u16 seq1, u16 seq2)
@@ -178,7 +232,7 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
 	if (!sock_flag(&smc->sk, SOCK_URGINLINE))
 		/* we'll skip the urgent byte, so don't account for it */
 		(*diff_prod)--;
-	base = (char *)conn->rmb_desc->cpu_addr;
+	base = (char *)conn->rmb_desc->cpu_addr + conn->rx_off;
 	if (conn->urg_curs.count)
 		conn->urg_rx_byte = *(base + conn->urg_curs.count - 1);
 	else
@@ -276,6 +330,34 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
 	sock_put(&smc->sk); /* no free sk in softirq-context */
 }
 
+/* Schedule a tasklet for this connection. Triggered from the ISM device IRQ
+ * handler to indicate update in the DMBE.
+ *
+ * Context:
+ * - tasklet context
+ */
+static void smcd_cdc_rx_tsklet(unsigned long data)
+{
+	struct smc_connection *conn = (struct smc_connection *)data;
+	struct smcd_cdc_msg cdc;
+	struct smc_sock *smc;
+
+	if (!conn)
+		return;
+
+	memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc));
+	smc = container_of(conn, struct smc_sock, conn);
+	smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc);
+}
+
+/* Initialize receive tasklet. Called from ISM device IRQ handler to start
+ * receiver side.
+ */
+void smcd_cdc_rx_init(struct smc_connection *conn)
+{
+	tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+}
+
 /***************************** init, exit, misc ******************************/
 
 static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)

net/smc/smc_cdc.h

@@ -50,6 +50,20 @@ struct smc_cdc_msg {
 	u8				reserved[18];
 } __packed;					/* format defined in RFC7609 */
 
+/* CDC message for SMC-D */
+struct smcd_cdc_msg {
+	struct smc_wr_rx_hdr common;	/* Type = 0xFE */
+	u8 res1[7];
+	u16 prod_wrap;
+	u32 prod_count;
+	u8 res2[2];
+	u16 cons_wrap;
+	u32 cons_count;
+	struct smc_cdc_producer_flags	prod_flags;
+	struct smc_cdc_conn_state_flags conn_state_flags;
+	u8 res3[8];
+} __packed;
+
 static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
 {
 	return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort ||
@@ -204,9 +218,9 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
 	smc_curs_write(local, smc_curs_read(&temp, conn), conn);
 }
 
-static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
-				       struct smc_cdc_msg *peer,
-				       struct smc_connection *conn)
+static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+					struct smc_cdc_msg *peer,
+					struct smc_connection *conn)
 {
 	local->common.type = peer->common.type;
 	local->len = peer->len;
@@ -218,6 +232,27 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 	local->conn_state_flags = peer->conn_state_flags;
 }
 
+static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+					struct smcd_cdc_msg *peer)
+{
+	local->prod.wrap = peer->prod_wrap;
+	local->prod.count = peer->prod_count;
+	local->cons.wrap = peer->cons_wrap;
+	local->cons.count = peer->cons_count;
+	local->prod_flags = peer->prod_flags;
+	local->conn_state_flags = peer->conn_state_flags;
+}
+
+static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+				       struct smc_cdc_msg *peer,
+				       struct smc_connection *conn)
+{
+	if (conn->lgr->is_smcd)
+		smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer);
+	else
+		smcr_cdc_msg_to_host(local, peer, conn);
+}
+
 struct smc_cdc_tx_pend;
 
 int smc_cdc_get_free_slot(struct smc_connection *conn,
@@ -227,6 +262,8 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
+int smcd_cdc_msg_send(struct smc_connection *conn);
 int smc_cdc_init(void) __init;
+void smcd_cdc_rx_init(struct smc_connection *conn);
 
 #endif /* SMC_CDC_H */

net/smc/smc_core.c

@@ -281,10 +281,12 @@ void smc_conn_free(struct smc_connection *conn)
 {
 	if (!conn->lgr)
 		return;
-	if (conn->lgr->is_smcd)
+	if (conn->lgr->is_smcd) {
 		smc_ism_unset_conn(conn);
-	else
+		tasklet_kill(&conn->rx_tsklet);
+	} else {
 		smc_cdc_tx_dismiss_slots(conn);
+	}
 	smc_lgr_unregister_conn(conn);
 	smc_buf_unuse(conn);
 }
@@ -324,10 +326,13 @@ static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
 static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb,
 			  struct smc_buf_desc *buf_desc)
 {
-	if (is_dmb)
+	if (is_dmb) {
+		/* restore original buf len */
+		buf_desc->len += sizeof(struct smcd_cdc_msg);
 		smc_ism_unregister_dmb(lgr->smcd, buf_desc);
-	else
+	} else {
 		kfree(buf_desc->cpu_addr);
+	}
 	kfree(buf_desc);
 }
 
@@ -632,6 +637,10 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
 	conn->urg_state = SMC_URG_READ;
+	if (is_smcd) {
+		conn->rx_off = sizeof(struct smcd_cdc_msg);
+		smcd_cdc_rx_init(conn); /* init tasklet for this conn */
+	}
 #ifndef KERNEL_HAS_ATOMIC64
 	spin_lock_init(&conn->acurs_lock);
 #endif
@@ -776,8 +785,9 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
 			kfree(buf_desc);
 			return ERR_PTR(-EAGAIN);
 		}
-		memset(buf_desc->cpu_addr, 0, bufsize);
-		buf_desc->len = bufsize;
+		buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
+		/* CDC header stored in buf. So, pretend it was smaller */
+		buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg);
 	} else {
 		buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL |
 					     __GFP_NOWARN | __GFP_NORETRY |
@@ -854,7 +864,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		conn->rmbe_size_short = bufsize_short;
 		smc->sk.sk_rcvbuf = bufsize * 2;
 		atomic_set(&conn->bytes_to_rcv, 0);
-		conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
+		conn->rmbe_update_limit =
+			smc_rmb_wnd_update_limit(buf_desc->len);
 		if (is_smcd)
 			smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
 	} else {

net/smc/smc_ism.c

@@ -302,5 +302,13 @@ EXPORT_SYMBOL_GPL(smcd_handle_event);
  */
 void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
 {
+	struct smc_connection *conn = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&smcd->lock, flags);
+	conn = smcd->conn[dmbno];
+	if (conn)
+		tasklet_schedule(&conn->rx_tsklet);
+	spin_unlock_irqrestore(&smcd->lock, flags);
 }
 EXPORT_SYMBOL_GPL(smcd_handle_irq);

net/smc/smc_rx.c

@@ -305,7 +305,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
 	/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
-	rcvbuf_base = conn->rmb_desc->cpu_addr;
+	rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr;
 
 	do { /* while (read_remaining) */
 		if (read_done >= target || (pipe && read_done))