Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 93 insertions, 20 deletions

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 9bde1e4ca288..ed5dcf03fe0b 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -34,14 +34,15 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 			       enum ib_wc_status wc_status)
 {
 	struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
+	struct smc_connection *conn = cdcpend->conn;
 	struct smc_sock *smc;
 	int diff;
 
-	if (!cdcpend->conn)
+	if (!conn)
 		/* already dismissed */
 		return;
 
-	smc = container_of(cdcpend->conn, struct smc_sock, conn);
+	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,
@@ -52,9 +53,7 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 		atomic_add(diff, &cdcpend->conn->sndbuf_space);
 		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 		smp_mb__after_atomic();
-		smc_curs_write(&cdcpend->conn->tx_curs_fin,
-			       smc_curs_read(&cdcpend->cursor, cdcpend->conn),
-			       cdcpend->conn);
+		smc_curs_copy(&conn->tx_curs_fin, &cdcpend->cursor, conn);
 	}
 	smc_tx_sndbuf_nonfull(smc);
 	bh_unlock_sock(&smc->sk);
@@ -110,14 +109,13 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 			    &conn->local_tx_ctrl, conn);
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc)
-		smc_curs_write(&conn->rx_curs_confirmed,
-			       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-			       conn);
+		smc_curs_copy(&conn->rx_curs_confirmed,
+			      &conn->local_tx_ctrl.cons, 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 +128,21 @@ 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 +170,44 @@ 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_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons,
+		      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_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
+
+	smc_tx_sndbuf_nonfull(smc);
+	return rc;
+}
+
 /********************************* receive ***********************************/
 
 static inline bool smc_cdc_before(u16 seq1, u16 seq2)
@@ -171,14 +222,12 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
 	char *base;
 
 	/* new data included urgent business */
-	smc_curs_write(&conn->urg_curs,
-		       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
-		       conn);
+	smc_curs_copy(&conn->urg_curs, &conn->local_rx_ctrl.prod, conn);
 	conn->urg_state = SMC_URG_VALID;
 	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
@@ -193,12 +242,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 	struct smc_connection *conn = &smc->conn;
 	int diff_cons, diff_prod;
 
-	smc_curs_write(&prod_old,
-		       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
-		       conn);
-	smc_curs_write(&cons_old,
-		       smc_curs_read(&conn->local_rx_ctrl.cons, conn),
-		       conn);
+	smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
+	smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
 	smc_cdc_msg_to_host(&conn->local_rx_ctrl, cdc, conn);
 
 	diff_cons = smc_curs_diff(conn->peer_rmbe_size, &cons_old,
@@ -277,6 +322,34 @@ 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)
@@ -293,7 +366,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
 		return; /* invalid message */
 
 	/* lookup connection */
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+	lgr = smc_get_lgr(link);
 	read_lock_bh(&lgr->conns_lock);
 	conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
 	read_unlock_bh(&lgr->conns_lock);