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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

7 files changed, 58 insertions, 41 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 745f145d4c4d..6451c5013e06 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -390,6 +390,12 @@ static int smc_connect_rdma(struct smc_sock *smc)
 	int rc = 0;
 	u8 ibport;
 
+	if (!tcp_sk(smc->clcsock->sk)->syn_smc) {
+		/* peer has not signalled SMC-capability */
+		smc->use_fallback = true;
+		goto out_connected;
+	}
+
 	/* IPSec connections opt out of SMC-R optimizations */
 	if (using_ipsec(smc)) {
 		reason_code = SMC_CLC_DECL_IPSEC;
@@ -555,6 +561,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 	}
 
 	smc_copy_sock_settings_to_clc(smc);
+	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
 	rc = kernel_connect(smc->clcsock, addr, alen, flags);
 	if (rc)
 		goto out;
@@ -759,6 +766,12 @@ static void smc_listen_work(struct work_struct *work)
 	u8 prefix_len;
 	u8 ibport;
 
+	/* check if peer is smc capable */
+	if (!tcp_sk(newclcsock->sk)->syn_smc) {
+		new_smc->use_fallback = true;
+		goto out_connected;
+	}
+
 	/* do inband token exchange -
 	 *wait for and receive SMC Proposal CLC message
 	 */
@@ -808,7 +821,7 @@ static void smc_listen_work(struct work_struct *work)
 		rc = local_contact;
 		if (rc == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 	link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
@@ -816,7 +829,7 @@ static void smc_listen_work(struct work_struct *work)
 	rc = smc_buf_create(new_smc);
 	if (rc) {
 		reason_code = SMC_CLC_DECL_MEM;
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 
 	smc_close_init(new_smc);
@@ -831,7 +844,7 @@ static void smc_listen_work(struct work_struct *work)
 					     buf_desc->mr_rx[SMC_SINGLE_LINK]);
 			if (rc) {
 				reason_code = SMC_CLC_DECL_INTERR;
-				goto decline_rdma;
+				goto decline_rdma_unlock;
 			}
 		}
 	}
@@ -839,15 +852,15 @@ static void smc_listen_work(struct work_struct *work)
 
 	rc = smc_clc_send_accept(new_smc, local_contact);
 	if (rc)
-		goto out_err;
+		goto out_err_unlock;
 
 	/* receive SMC Confirm CLC message */
 	reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
 				       SMC_CLC_CONFIRM);
 	if (reason_code < 0)
-		goto out_err;
+		goto out_err_unlock;
 	if (reason_code > 0)
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	smc_conn_save_peer_info(new_smc, &cclc);
 	if (local_contact == SMC_FIRST_CONTACT)
 		smc_link_save_peer_info(link, &cclc);
@@ -855,34 +868,34 @@ static void smc_listen_work(struct work_struct *work)
 	rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc);
 	if (rc) {
 		reason_code = SMC_CLC_DECL_INTERR;
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 
 	if (local_contact == SMC_FIRST_CONTACT) {
 		rc = smc_ib_ready_link(link);
 		if (rc) {
 			reason_code = SMC_CLC_DECL_INTERR;
-			goto decline_rdma;
+			goto decline_rdma_unlock;
 		}
 		/* QP confirmation over RoCE fabric */
 		reason_code = smc_serv_conf_first_link(new_smc);
 		if (reason_code < 0) {
 			/* peer is not aware of a problem */
 			rc = reason_code;
-			goto out_err;
+			goto out_err_unlock;
 		}
 		if (reason_code > 0)
-			goto decline_rdma;
+			goto decline_rdma_unlock;
 	}
 
 	smc_tx_init(new_smc);
+	mutex_unlock(&smc_create_lgr_pending);
 
 out_connected:
 	sk_refcnt_debug_inc(newsmcsk);
 	if (newsmcsk->sk_state == SMC_INIT)
 		newsmcsk->sk_state = SMC_ACTIVE;
 enqueue:
-	mutex_unlock(&smc_create_lgr_pending);
 	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
@@ -896,6 +909,8 @@ enqueue:
 	sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
 	return;
 
+decline_rdma_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
 decline_rdma:
 	/* RDMA setup failed, switch back to TCP */
 	smc_conn_free(&new_smc->conn);
@@ -907,6 +922,8 @@ decline_rdma:
 	}
 	goto out_connected;
 
+out_err_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
 out_err:
 	newsmcsk->sk_state = SMC_CLOSED;
 	smc_conn_free(&new_smc->conn);
@@ -963,6 +980,7 @@ static int smc_listen(struct socket *sock, int backlog)
 	 * them to the clc socket -- copy smc socket options to clc socket
 	 */
 	smc_copy_sock_settings_to_clc(smc);
+	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
 
 	rc = kernel_listen(smc->clcsock, backlog);
 	if (rc)
@@ -1405,6 +1423,7 @@ static int __init smc_init(void)
 		goto out_sock;
 	}
 
+	static_branch_enable(&tcp_have_smc);
 	return 0;
 
 out_sock:
@@ -1429,6 +1448,7 @@ static void __exit smc_exit(void)
 		list_del_init(&lgr->list);
 		smc_lgr_free(lgr); /* free link group */
 	}
+	static_branch_disable(&tcp_have_smc);
 	smc_ib_unregister_client();
 	sock_unregister(PF_SMC);
 	proto_unregister(&smc_proto);
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 535e72cfc64b..87f7bede6eab 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -63,10 +63,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 	bh_unlock_sock(&smc->sk);
 }
 
-int smc_cdc_get_free_slot(struct smc_link *link,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_cdc_tx_pend **pend)
 {
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
 	return smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
 				       (struct smc_wr_tx_pend_priv **)pend);
 }
@@ -119,8 +121,7 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	struct smc_wr_buf *wr_buf;
 	int rc;
 
-	rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
-				   &pend);
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 	if (rc)
 		return rc;
 
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index bea61dadaf36..149ceda1b088 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -207,7 +207,8 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 
 struct smc_cdc_tx_pend;
 
-int smc_cdc_get_free_slot(struct smc_link *link, struct smc_wr_buf **wr_buf,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
+			  struct smc_wr_buf **wr_buf,
 			  struct smc_cdc_tx_pend **pend);
 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,
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2427a1f3d0d1..48615d2ac4aa 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -361,7 +361,8 @@ static void smc_close_passive_work(struct work_struct *work)
 	case SMC_PEERCLOSEWAIT1:
 		if (rxflags->peer_done_writing)
 			sk->sk_state = SMC_PEERCLOSEWAIT2;
-		/* fall through to check for closing */
+		/* fall through */
+		/* to check for closing */
 	case SMC_PEERCLOSEWAIT2:
 	case SMC_PEERFINCLOSEWAIT:
 		if (!smc_cdc_rxed_any_close(&smc->conn))
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 413e3868fbf3..2578fbd95664 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -381,10 +381,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr)
 		if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
 				 &gattr))
 			continue;
-		if (gattr.ndev &&
-		    (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) {
-			lnk->gid = gid;
-			return 0;
+		if (gattr.ndev) {
+			if (is_vlan_dev(gattr.ndev) &&
+			    vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) {
+				lnk->gid = gid;
+				dev_put(gattr.ndev);
+				return 0;
+			}
+			dev_put(gattr.ndev);
 		}
 	}
 	return -ENODEV;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 9033b8a36fe1..90f1a7f9085c 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -370,26 +370,17 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
 
 static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
 {
-	struct net_device *ndev;
+	struct ib_gid_attr gattr;
 	int rc;
 
 	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
-			  &smcibdev->gid[ibport - 1], NULL);
-	/* the SMC protocol requires specification of the roce MAC address;
-	 * if net_device cannot be determined, it can be derived from gid 0
-	 */
-	ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
-	if (ndev) {
-		memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
-		dev_put(ndev);
-	} else if (!rc) {
-		memcpy(&smcibdev->mac[ibport - 1][0],
-		       &smcibdev->gid[ibport - 1].raw[8], 3);
-		memcpy(&smcibdev->mac[ibport - 1][3],
-		       &smcibdev->gid[ibport - 1].raw[13], 3);
-		smcibdev->mac[ibport - 1][0] &= ~0x02;
-	}
-	return rc;
+			  &smcibdev->gid[ibport - 1], &gattr);
+	if (rc || !gattr.ndev)
+		return -ENODEV;
+
+	memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
+	dev_put(gattr.ndev);
+	return 0;
 }
 
 /* Create an identifier unique for this instance of SMC-R.
@@ -420,6 +411,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 			   &smcibdev->pattr[ibport - 1]);
 	if (rc)
 		goto out;
+	/* the SMC protocol requires specification of the RoCE MAC address */
 	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
 	if (rc)
 		goto out;
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 710ab3fbf607..c48dc2d5fd3a 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -397,8 +397,7 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
 	int rc;
 
 	spin_lock_bh(&conn->send_lock);
-	rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
-				   &pend);
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 	if (rc < 0) {
 		if (rc == -EBUSY) {
 			struct smc_sock *smc =
@@ -467,8 +466,7 @@ void smc_tx_consumer_update(struct smc_connection *conn)
 	    ((to_confirm > conn->rmbe_update_limit) &&
 	     ((to_confirm > (conn->rmbe_size / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
-		rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
-					   &wr_buf, &pend);
+		rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 		if (!rc)
 			rc = smc_cdc_msg_send(conn, wr_buf, pend);
 		if (rc < 0) {