Adding upstream version 4.19.249.upstream/4.19.249

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

27 files changed, 10323 insertions, 0 deletions

diff --git a/net/smc/Kconfig b/net/smc/Kconfig
new file mode 100644
index 000000000..c717ef089
--- /dev/null
+++ b/net/smc/Kconfig
@@ -0,0 +1,20 @@
+config SMC
+	tristate "SMC socket protocol family"
+	depends on INET && INFINIBAND
+	---help---
+	  SMC-R provides a "sockets over RDMA" solution making use of
+	  RDMA over Converged Ethernet (RoCE) technology to upgrade
+	  AF_INET TCP connections transparently.
+	  The Linux implementation of the SMC-R solution is designed as
+	  a separate socket family SMC.
+
+	  Select this option if you want to run SMC socket applications
+
+config SMC_DIAG
+	tristate "SMC: socket monitoring interface"
+	depends on SMC
+	---help---
+	  Support for SMC socket monitoring interface used by tools such as
+	  smcss.
+
+	  if unsure, say Y.
diff --git a/net/smc/Makefile b/net/smc/Makefile
new file mode 100644
index 000000000..4df96b4b8
--- /dev/null
+++ b/net/smc/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_SMC)	+= smc.o
+obj-$(CONFIG_SMC_DIAG)	+= smc_diag.o
+smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
new file mode 100644
index 000000000..4c904ab29
--- /dev/null
+++ b/net/smc/af_smc.c
@@ -0,0 +1,2027 @@
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  AF_SMC protocol family socket handler keeping the AF_INET sock address type
+ *  applies to SOCK_STREAM sockets only
+ *  offers an alternative communication option for TCP-protocol sockets
+ *  applicable with RoCE-cards only
+ *
+ *  Initial restrictions:
+ *    - support for alternate links postponed
+ *
+ *  Copyright IBM Corp. 2016, 2018
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ *              based on prototype from Frank Blaschka
+ */
+
+#define KMSG_COMPONENT "smc"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/workqueue.h>
+#include <linux/in.h>
+#include <linux/sched/signal.h>
+#include <linux/if_vlan.h>
+
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/smc.h>
+#include <asm/ioctls.h>
+
+#include "smc.h"
+#include "smc_clc.h"
+#include "smc_llc.h"
+#include "smc_cdc.h"
+#include "smc_core.h"
+#include "smc_ib.h"
+#include "smc_ism.h"
+#include "smc_pnet.h"
+#include "smc_tx.h"
+#include "smc_rx.h"
+#include "smc_close.h"
+
+static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
+						 * creation
+						 */
+
+static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
+
+static void smc_set_keepalive(struct sock *sk, int val)
+{
+	struct smc_sock *smc = smc_sk(sk);
+
+	smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val);
+}
+
+static struct smc_hashinfo smc_v4_hashinfo = {
+	.lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock),
+};
+
+static struct smc_hashinfo smc_v6_hashinfo = {
+	.lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock),
+};
+
+int smc_hash_sk(struct sock *sk)
+{
+	struct smc_hashinfo *h = sk->sk_prot->h.smc_hash;
+	struct hlist_head *head;
+
+	head = &h->ht;
+
+	write_lock_bh(&h->lock);
+	sk_add_node(sk, head);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+	write_unlock_bh(&h->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(smc_hash_sk);
+
+void smc_unhash_sk(struct sock *sk)
+{
+	struct smc_hashinfo *h = sk->sk_prot->h.smc_hash;
+
+	write_lock_bh(&h->lock);
+	if (sk_del_node_init(sk))
+		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	write_unlock_bh(&h->lock);
+}
+EXPORT_SYMBOL_GPL(smc_unhash_sk);
+
+struct proto smc_proto = {
+	.name		= "SMC",
+	.owner		= THIS_MODULE,
+	.keepalive	= smc_set_keepalive,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.obj_size	= sizeof(struct smc_sock),
+	.h.smc_hash	= &smc_v4_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+};
+EXPORT_SYMBOL_GPL(smc_proto);
+
+struct proto smc_proto6 = {
+	.name		= "SMC6",
+	.owner		= THIS_MODULE,
+	.keepalive	= smc_set_keepalive,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.obj_size	= sizeof(struct smc_sock),
+	.h.smc_hash	= &smc_v6_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+};
+EXPORT_SYMBOL_GPL(smc_proto6);
+
+static int smc_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = 0;
+
+	if (!sk)
+		goto out;
+
+	smc = smc_sk(sk);
+
+	/* cleanup for a dangling non-blocking connect */
+	flush_work(&smc->connect_work);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+
+	if (sk->sk_state == SMC_LISTEN)
+		/* smc_close_non_accepted() is called and acquires
+		 * sock lock for child sockets again
+		 */
+		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+	else
+		lock_sock(sk);
+
+	if (!smc->use_fallback) {
+		rc = smc_close_active(smc);
+		sock_set_flag(sk, SOCK_DEAD);
+		sk->sk_shutdown |= SHUTDOWN_MASK;
+	}
+
+	sk->sk_prot->unhash(sk);
+
+	if (smc->clcsock) {
+		if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
+			/* wake up clcsock accept */
+			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+		}
+		mutex_lock(&smc->clcsock_release_lock);
+		sock_release(smc->clcsock);
+		smc->clcsock = NULL;
+		mutex_unlock(&smc->clcsock_release_lock);
+	}
+	if (smc->use_fallback) {
+		if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+			sock_put(sk); /* passive closing */
+		sk->sk_state = SMC_CLOSED;
+		sk->sk_state_change(sk);
+	}
+
+	/* detach socket */
+	sock_orphan(sk);
+	sock->sk = NULL;
+	if (!smc->use_fallback && sk->sk_state == SMC_CLOSED)
+		smc_conn_free(&smc->conn);
+	release_sock(sk);
+
+	sock_put(sk); /* final sock_put */
+out:
+	return rc;
+}
+
+static void smc_destruct(struct sock *sk)
+{
+	if (sk->sk_state != SMC_CLOSED)
+		return;
+	if (!sock_flag(sk, SOCK_DEAD))
+		return;
+
+	sk_refcnt_debug_dec(sk);
+}
+
+static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
+				   int protocol)
+{
+	struct smc_sock *smc;
+	struct proto *prot;
+	struct sock *sk;
+
+	prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto;
+	sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0);
+	if (!sk)
+		return NULL;
+
+	sock_init_data(sock, sk); /* sets sk_refcnt to 1 */
+	sk->sk_state = SMC_INIT;
+	sk->sk_destruct = smc_destruct;
+	sk->sk_protocol = protocol;
+	smc = smc_sk(sk);
+	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+	INIT_WORK(&smc->connect_work, smc_connect_work);
+	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
+	INIT_LIST_HEAD(&smc->accept_q);
+	spin_lock_init(&smc->accept_q_lock);
+	spin_lock_init(&smc->conn.send_lock);
+	sk->sk_prot->hash(sk);
+	sk_refcnt_debug_inc(sk);
+	mutex_init(&smc->clcsock_release_lock);
+
+	return sk;
+}
+
+static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
+		    int addr_len)
+{
+	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc;
+
+	smc = smc_sk(sk);
+
+	/* replicate tests from inet_bind(), to be safe wrt. future changes */
+	rc = -EINVAL;
+	if (addr_len < sizeof(struct sockaddr_in))
+		goto out;
+
+	rc = -EAFNOSUPPORT;
+	if (addr->sin_family != AF_INET &&
+	    addr->sin_family != AF_INET6 &&
+	    addr->sin_family != AF_UNSPEC)
+		goto out;
+	/* accept AF_UNSPEC (mapped to AF_INET) only if s_addr is INADDR_ANY */
+	if (addr->sin_family == AF_UNSPEC &&
+	    addr->sin_addr.s_addr != htonl(INADDR_ANY))
+		goto out;
+
+	lock_sock(sk);
+
+	/* Check if socket is already active */
+	rc = -EINVAL;
+	if (sk->sk_state != SMC_INIT)
+		goto out_rel;
+
+	smc->clcsock->sk->sk_reuse = sk->sk_reuse;
+	rc = kernel_bind(smc->clcsock, uaddr, addr_len);
+
+out_rel:
+	release_sock(sk);
+out:
+	return rc;
+}
+
+static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
+				   unsigned long mask)
+{
+	/* options we don't get control via setsockopt for */
+	nsk->sk_type = osk->sk_type;
+	nsk->sk_sndbuf = osk->sk_sndbuf;
+	nsk->sk_rcvbuf = osk->sk_rcvbuf;
+	nsk->sk_sndtimeo = osk->sk_sndtimeo;
+	nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
+	nsk->sk_mark = osk->sk_mark;
+	nsk->sk_priority = osk->sk_priority;
+	nsk->sk_rcvlowat = osk->sk_rcvlowat;
+	nsk->sk_bound_dev_if = osk->sk_bound_dev_if;
+	nsk->sk_err = osk->sk_err;
+
+	nsk->sk_flags &= ~mask;
+	nsk->sk_flags |= osk->sk_flags & mask;
+}
+
+#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
+			     (1UL << SOCK_KEEPOPEN) | \
+			     (1UL << SOCK_LINGER) | \
+			     (1UL << SOCK_BROADCAST) | \
+			     (1UL << SOCK_TIMESTAMP) | \
+			     (1UL << SOCK_DBG) | \
+			     (1UL << SOCK_RCVTSTAMP) | \
+			     (1UL << SOCK_RCVTSTAMPNS) | \
+			     (1UL << SOCK_LOCALROUTE) | \
+			     (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
+			     (1UL << SOCK_RXQ_OVFL) | \
+			     (1UL << SOCK_WIFI_STATUS) | \
+			     (1UL << SOCK_NOFCS) | \
+			     (1UL << SOCK_FILTER_LOCKED))
+/* copy only relevant settings and flags of SOL_SOCKET level from smc to
+ * clc socket (since smc is not called for these options from net/core)
+ */
+static void smc_copy_sock_settings_to_clc(struct smc_sock *smc)
+{
+	smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC);
+}
+
+#define SK_FLAGS_CLC_TO_SMC ((1UL << SOCK_URGINLINE) | \
+			     (1UL << SOCK_KEEPOPEN) | \
+			     (1UL << SOCK_LINGER) | \
+			     (1UL << SOCK_DBG))
+/* copy only settings and flags relevant for smc from clc to smc socket */
+static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
+{
+	smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
+}
+
+/* register a new rmb, optionally send confirm_rkey msg to register with peer */
+static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc,
+		       bool conf_rkey)
+{
+	/* register memory region for new rmb */
+	if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+		rmb_desc->regerr = 1;
+		return -EFAULT;
+	}
+	if (!conf_rkey)
+		return 0;
+	/* exchange confirm_rkey msg with peer */
+	if (smc_llc_do_confirm_rkey(link, rmb_desc)) {
+		rmb_desc->regerr = 1;
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static int smc_clnt_conf_first_link(struct smc_sock *smc)
+{
+	struct net *net = sock_net(smc->clcsock->sk);
+	struct smc_link_group *lgr = smc->conn.lgr;
+	struct smc_link *link;
+	int rest;
+	int rc;
+
+	link = &lgr->lnk[SMC_SINGLE_LINK];
+	/* receive CONFIRM LINK request from server over RoCE fabric */
+	rest = wait_for_completion_interruptible_timeout(
+		&link->llc_confirm,
+		SMC_LLC_WAIT_FIRST_TIME);
+	if (rest <= 0) {
+		struct smc_clc_msg_decline dclc;
+
+		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+				      SMC_CLC_DECLINE);
+		return rc;
+	}
+
+	if (link->llc_confirm_rc)
+		return SMC_CLC_DECL_RMBE_EC;
+
+	rc = smc_ib_modify_qp_rts(link);
+	if (rc)
+		return SMC_CLC_DECL_ERR_RDYLNK;
+
+	smc_wr_remember_qp_attr(link);
+
+	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
+		return SMC_CLC_DECL_ERR_REGRMB;
+
+	/* send CONFIRM LINK response over RoCE fabric */
+	rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP);
+	if (rc < 0)
+		return SMC_CLC_DECL_TIMEOUT_CL;
+
+	/* receive ADD LINK request from server over RoCE fabric */
+	rest = wait_for_completion_interruptible_timeout(&link->llc_add,
+							 SMC_LLC_WAIT_TIME);
+	if (rest <= 0) {
+		struct smc_clc_msg_decline dclc;
+
+		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+				      SMC_CLC_DECLINE);
+		return rc;
+	}
+
+	/* send add link reject message, only one link supported for now */
+	rc = smc_llc_send_add_link(link,
+				   link->smcibdev->mac[link->ibport - 1],
+				   link->gid, SMC_LLC_RESP);
+	if (rc < 0)
+		return SMC_CLC_DECL_TIMEOUT_AL;
+
+	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
+
+	return 0;
+}
+
+static void smcr_conn_save_peer_info(struct smc_sock *smc,
+				     struct smc_clc_msg_accept_confirm *clc)
+{
+	int bufsize = smc_uncompress_bufsize(clc->rmbe_size);
+
+	smc->conn.peer_rmbe_idx = clc->rmbe_idx;
+	smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token);
+	smc->conn.peer_rmbe_size = bufsize;
+	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
+	smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
+}
+
+static void smcd_conn_save_peer_info(struct smc_sock *smc,
+				     struct smc_clc_msg_accept_confirm *clc)
+{
+	int bufsize = smc_uncompress_bufsize(clc->dmbe_size);
+
+	smc->conn.peer_rmbe_idx = clc->dmbe_idx;
+	smc->conn.peer_token = clc->token;
+	/* msg header takes up space in the buffer */
+	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
+	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
+	smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx;
+}
+
+static void smc_conn_save_peer_info(struct smc_sock *smc,
+				    struct smc_clc_msg_accept_confirm *clc)
+{
+	if (smc->conn.lgr->is_smcd)
+		smcd_conn_save_peer_info(smc, clc);
+	else
+		smcr_conn_save_peer_info(smc, clc);
+}
+
+static void smc_link_save_peer_info(struct smc_link *link,
+				    struct smc_clc_msg_accept_confirm *clc)
+{
+	link->peer_qpn = ntoh24(clc->qpn);
+	memcpy(link->peer_gid, clc->lcl.gid, SMC_GID_SIZE);
+	memcpy(link->peer_mac, clc->lcl.mac, sizeof(link->peer_mac));
+	link->peer_psn = ntoh24(clc->psn);
+	link->peer_mtu = clc->qp_mtu;
+}
+
+/* fall back during connect */
+static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
+{
+	smc->use_fallback = true;
+	smc->fallback_rsn = reason_code;
+	smc_copy_sock_settings_to_clc(smc);
+	if (smc->sk.sk_state == SMC_INIT)
+		smc->sk.sk_state = SMC_ACTIVE;
+	return 0;
+}
+
+/* decline and fall back during connect */
+static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
+{
+	int rc;
+
+	if (reason_code < 0) { /* error, fallback is not possible */
+		if (smc->sk.sk_state == SMC_INIT)
+			sock_put(&smc->sk); /* passive closing */
+		return reason_code;
+	}
+	if (reason_code != SMC_CLC_DECL_PEERDECL) {
+		rc = smc_clc_send_decline(smc, reason_code);
+		if (rc < 0) {
+			if (smc->sk.sk_state == SMC_INIT)
+				sock_put(&smc->sk); /* passive closing */
+			return rc;
+		}
+	}
+	return smc_connect_fallback(smc, reason_code);
+}
+
+/* abort connecting */
+static int smc_connect_abort(struct smc_sock *smc, int reason_code,
+			     int local_contact)
+{
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_lgr_forget(smc->conn.lgr);
+	mutex_unlock(&smc_create_lgr_pending);
+	smc_conn_free(&smc->conn);
+	return reason_code;
+}
+
+/* check if there is a rdma device available for this connection. */
+/* called for connect and listen */
+static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
+			  u8 *ibport, unsigned short vlan_id, u8 gid[])
+{
+	int reason_code = 0;
+
+	/* PNET table look up: search active ib_device and port
+	 * within same PNETID that also contains the ethernet device
+	 * used for the internal TCP socket
+	 */
+	smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
+				    gid);
+	if (!(*ibdev))
+		reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
+
+	return reason_code;
+}
+
+/* check if there is an ISM device available for this connection. */
+/* called for connect and listen */
+static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+{
+	/* Find ISM device with same PNETID as connecting interface  */
+	smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
+	if (!(*ismdev))
+		return SMC_CLC_DECL_CNFERR; /* configuration error */
+	return 0;
+}
+
+/* Check for VLAN ID and register it on ISM device just for CLC handshake */
+static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
+				      struct smcd_dev *ismdev,
+				      unsigned short vlan_id)
+{
+	if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
+		return SMC_CLC_DECL_CNFERR;
+	return 0;
+}
+
+/* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is
+ * used, the VLAN ID will be registered again during the connection setup.
+ */
+static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
+					struct smcd_dev *ismdev,
+					unsigned short vlan_id)
+{
+	if (!is_smcd)
+		return 0;
+	if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+		return SMC_CLC_DECL_CNFERR;
+	return 0;
+}
+
+/* CLC handshake during connect */
+static int smc_connect_clc(struct smc_sock *smc, int smc_type,
+			   struct smc_clc_msg_accept_confirm *aclc,
+			   struct smc_ib_device *ibdev, u8 ibport,
+			   u8 gid[], struct smcd_dev *ismdev)
+{
+	int rc = 0;
+
+	/* do inband token exchange */
+	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
+	if (rc)
+		return rc;
+	/* receive SMC Accept CLC message */
+	return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT);
+}
+
+/* setup for RDMA connection of client */
+static int smc_connect_rdma(struct smc_sock *smc,
+			    struct smc_clc_msg_accept_confirm *aclc,
+			    struct smc_ib_device *ibdev, u8 ibport)
+{
+	int local_contact = SMC_FIRST_CONTACT;
+	struct smc_link *link;
+	int reason_code = 0;
+
+	mutex_lock(&smc_create_lgr_pending);
+	local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
+					ibport, &aclc->lcl, NULL, 0);
+	if (local_contact < 0) {
+		if (local_contact == -ENOMEM)
+			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
+		else if (local_contact == -ENOLINK)
+			reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
+		else
+			reason_code = SMC_CLC_DECL_INTERR; /* other error */
+		return smc_connect_abort(smc, reason_code, 0);
+	}
+	link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK];
+
+	smc_conn_save_peer_info(smc, aclc);
+
+	/* create send buffer and rmb */
+	if (smc_buf_create(smc, false))
+		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_link_save_peer_info(link, aclc);
+
+	if (smc_rmb_rtoken_handling(&smc->conn, aclc))
+		return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
+					 local_contact);
+
+	smc_close_init(smc);
+	smc_rx_init(smc);
+
+	if (local_contact == SMC_FIRST_CONTACT) {
+		if (smc_ib_ready_link(link))
+			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
+						 local_contact);
+	} else {
+		if (!smc->conn.rmb_desc->reused &&
+		    smc_reg_rmb(link, smc->conn.rmb_desc, true))
+			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
+						 local_contact);
+	}
+	smc_rmb_sync_sg_for_device(&smc->conn);
+
+	reason_code = smc_clc_send_confirm(smc);
+	if (reason_code)
+		return smc_connect_abort(smc, reason_code, local_contact);
+
+	smc_tx_init(smc);
+
+	if (local_contact == SMC_FIRST_CONTACT) {
+		/* QP confirmation over RoCE fabric */
+		reason_code = smc_clnt_conf_first_link(smc);
+		if (reason_code)
+			return smc_connect_abort(smc, reason_code,
+						 local_contact);
+	}
+	mutex_unlock(&smc_create_lgr_pending);
+
+	smc_copy_sock_settings_to_clc(smc);
+	if (smc->sk.sk_state == SMC_INIT)
+		smc->sk.sk_state = SMC_ACTIVE;
+
+	return 0;
+}
+
+/* setup for ISM connection of client */
+static int smc_connect_ism(struct smc_sock *smc,
+			   struct smc_clc_msg_accept_confirm *aclc,
+			   struct smcd_dev *ismdev)
+{
+	int local_contact = SMC_FIRST_CONTACT;
+	int rc = 0;
+
+	mutex_lock(&smc_create_lgr_pending);
+	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
+					NULL, ismdev, aclc->gid);
+	if (local_contact < 0)
+		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
+
+	/* Create send and receive buffers */
+	if (smc_buf_create(smc, true))
+		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+
+	smc_conn_save_peer_info(smc, aclc);
+	smc_close_init(smc);
+	smc_rx_init(smc);
+	smc_tx_init(smc);
+
+	rc = smc_clc_send_confirm(smc);
+	if (rc)
+		return smc_connect_abort(smc, rc, local_contact);
+	mutex_unlock(&smc_create_lgr_pending);
+
+	smc_copy_sock_settings_to_clc(smc);
+	if (smc->sk.sk_state == SMC_INIT)
+		smc->sk.sk_state = SMC_ACTIVE;
+
+	return 0;
+}
+
+/* perform steps before actually connecting */
+static int __smc_connect(struct smc_sock *smc)
+{
+	bool ism_supported = false, rdma_supported = false;
+	struct smc_clc_msg_accept_confirm aclc;
+	struct smc_ib_device *ibdev;
+	struct smcd_dev *ismdev;
+	u8 gid[SMC_GID_SIZE];
+	unsigned short vlan;
+	int smc_type;
+	int rc = 0;
+	u8 ibport;
+
+	sock_hold(&smc->sk); /* sock put in passive closing */
+
+	if (smc->use_fallback)
+		return smc_connect_fallback(smc, smc->fallback_rsn);
+
+	/* if peer has not signalled SMC-capability, fall back */
+	if (!tcp_sk(smc->clcsock->sk)->syn_smc)
+		return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
+
+	/* IPSec connections opt out of SMC-R optimizations */
+	if (using_ipsec(smc))
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
+
+	/* check for VLAN ID */
+	if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+
+	/* check if there is an ism device available */
+	if (!smc_check_ism(smc, &ismdev) &&
+	    !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+		/* ISM is supported for this connection */
+		ism_supported = true;
+		smc_type = SMC_TYPE_D;
+	}
+
+	/* check if there is a rdma device available */
+	if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
+		/* RDMA is supported for this connection */
+		rdma_supported = true;
+		if (ism_supported)
+			smc_type = SMC_TYPE_B; /* both */
+		else
+			smc_type = SMC_TYPE_R; /* only RDMA */
+	}
+
+	/* if neither ISM nor RDMA are supported, fallback */
+	if (!rdma_supported && !ism_supported)
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
+
+	/* perform CLC handshake */
+	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
+	if (rc) {
+		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+		return smc_connect_decline_fallback(smc, rc);
+	}
+
+	/* depending on previous steps, connect using rdma or ism */
+	if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
+		rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
+		rc = smc_connect_ism(smc, &aclc, ismdev);
+	else
+		rc = SMC_CLC_DECL_MODEUNSUPP;
+	if (rc) {
+		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+		return smc_connect_decline_fallback(smc, rc);
+	}
+
+	smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+	return 0;
+}
+
+static void smc_connect_work(struct work_struct *work)
+{
+	struct smc_sock *smc = container_of(work, struct smc_sock,
+					    connect_work);
+	int rc;
+
+	lock_sock(&smc->sk);
+	rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+			    smc->connect_info->alen, smc->connect_info->flags);
+	if (smc->clcsock->sk->sk_err) {
+		smc->sk.sk_err = smc->clcsock->sk->sk_err;
+		goto out;
+	}
+	if (rc < 0) {
+		smc->sk.sk_err = -rc;
+		goto out;
+	}
+
+	rc = __smc_connect(smc);
+	if (rc < 0)
+		smc->sk.sk_err = -rc;
+
+out:
+	if (smc->sk.sk_err)
+		smc->sk.sk_state_change(&smc->sk);
+	else
+		smc->sk.sk_write_space(&smc->sk);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+	release_sock(&smc->sk);
+}
+
+static int smc_connect(struct socket *sock, struct sockaddr *addr,
+		       int alen, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = -EINVAL;
+
+	smc = smc_sk(sk);
+
+	/* separate smc parameter checking to be safe */
+	if (alen < sizeof(addr->sa_family))
+		goto out_err;
+	if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6)
+		goto out_err;
+
+	lock_sock(sk);
+	switch (sk->sk_state) {
+	default:
+		goto out;
+	case SMC_ACTIVE:
+		rc = -EISCONN;
+		goto out;
+	case SMC_INIT:
+		rc = 0;
+		break;
+	}
+
+	smc_copy_sock_settings_to_clc(smc);
+	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+	if (flags & O_NONBLOCK) {
+		if (smc->connect_info) {
+			rc = -EALREADY;
+			goto out;
+		}
+		smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+		if (!smc->connect_info) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		smc->connect_info->alen = alen;
+		smc->connect_info->flags = flags ^ O_NONBLOCK;
+		memcpy(&smc->connect_info->addr, addr, alen);
+		schedule_work(&smc->connect_work);
+		rc = -EINPROGRESS;
+	} else {
+		rc = kernel_connect(smc->clcsock, addr, alen, flags);
+		if (rc)
+			goto out;
+
+		rc = __smc_connect(smc);
+		if (rc < 0)
+			goto out;
+		else
+			rc = 0; /* success cases including fallback */
+	}
+
+out:
+	release_sock(sk);
+out_err:
+	return rc;
+}
+
+static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
+{
+	struct socket *new_clcsock = NULL;
+	struct sock *lsk = &lsmc->sk;
+	struct sock *new_sk;
+	int rc = -EINVAL;
+
+	release_sock(lsk);
+	new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol);
+	if (!new_sk) {
+		rc = -ENOMEM;
+		lsk->sk_err = ENOMEM;
+		*new_smc = NULL;
+		lock_sock(lsk);
+		goto out;
+	}
+	*new_smc = smc_sk(new_sk);
+
+	mutex_lock(&lsmc->clcsock_release_lock);
+	if (lsmc->clcsock)
+		rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+	mutex_unlock(&lsmc->clcsock_release_lock);
+	lock_sock(lsk);
+	if  (rc < 0)
+		lsk->sk_err = -rc;
+	if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+		new_sk->sk_prot->unhash(new_sk);
+		if (new_clcsock)
+			sock_release(new_clcsock);
+		new_sk->sk_state = SMC_CLOSED;
+		sock_set_flag(new_sk, SOCK_DEAD);
+		sock_put(new_sk); /* final */
+		*new_smc = NULL;
+		goto out;
+	}
+
+	(*new_smc)->clcsock = new_clcsock;
+out:
+	return rc;
+}
+
+/* add a just created sock to the accept queue of the listen sock as
+ * candidate for a following socket accept call from user space
+ */
+static void smc_accept_enqueue(struct sock *parent, struct sock *sk)
+{
+	struct smc_sock *par = smc_sk(parent);
+
+	sock_hold(sk); /* sock_put in smc_accept_unlink () */
+	spin_lock(&par->accept_q_lock);
+	list_add_tail(&smc_sk(sk)->accept_q, &par->accept_q);
+	spin_unlock(&par->accept_q_lock);
+	sk_acceptq_added(parent);
+}
+
+/* remove a socket from the accept queue of its parental listening socket */
+static void smc_accept_unlink(struct sock *sk)
+{
+	struct smc_sock *par = smc_sk(sk)->listen_smc;
+
+	spin_lock(&par->accept_q_lock);
+	list_del_init(&smc_sk(sk)->accept_q);
+	spin_unlock(&par->accept_q_lock);
+	sk_acceptq_removed(&smc_sk(sk)->listen_smc->sk);
+	sock_put(sk); /* sock_hold in smc_accept_enqueue */
+}
+
+/* remove a sock from the accept queue to bind it to a new socket created
+ * for a socket accept call from user space
+ */
+struct sock *smc_accept_dequeue(struct sock *parent,
+				struct socket *new_sock)
+{
+	struct smc_sock *isk, *n;
+	struct sock *new_sk;
+
+	list_for_each_entry_safe(isk, n, &smc_sk(parent)->accept_q, accept_q) {
+		new_sk = (struct sock *)isk;
+
+		smc_accept_unlink(new_sk);
+		if (new_sk->sk_state == SMC_CLOSED) {
+			new_sk->sk_prot->unhash(new_sk);
+			if (isk->clcsock) {
+				sock_release(isk->clcsock);
+				isk->clcsock = NULL;
+			}
+			sock_put(new_sk); /* final */
+			continue;
+		}
+		if (new_sock)
+			sock_graft(new_sk, new_sock);
+		return new_sk;
+	}
+	return NULL;
+}
+
+/* clean up for a created but never accepted sock */
+void smc_close_non_accepted(struct sock *sk)
+{
+	struct smc_sock *smc = smc_sk(sk);
+
+	lock_sock(sk);
+	if (!sk->sk_lingertime)
+		/* wait for peer closing */
+		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
+	if (!smc->use_fallback) {
+		smc_close_active(smc);
+		sock_set_flag(sk, SOCK_DEAD);
+		sk->sk_shutdown |= SHUTDOWN_MASK;
+	}
+	sk->sk_prot->unhash(sk);
+	if (smc->clcsock) {
+		struct socket *tcp;
+
+		tcp = smc->clcsock;
+		smc->clcsock = NULL;
+		sock_release(tcp);
+	}
+	if (smc->use_fallback) {
+		sock_put(sk); /* passive closing */
+		sk->sk_state = SMC_CLOSED;
+	} else {
+		if (sk->sk_state == SMC_CLOSED)
+			smc_conn_free(&smc->conn);
+	}
+	release_sock(sk);
+	sock_put(sk); /* final sock_put */
+}
+
+static int smc_serv_conf_first_link(struct smc_sock *smc)
+{
+	struct net *net = sock_net(smc->clcsock->sk);
+	struct smc_link_group *lgr = smc->conn.lgr;
+	struct smc_link *link;
+	int rest;
+	int rc;
+
+	link = &lgr->lnk[SMC_SINGLE_LINK];
+
+	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
+		return SMC_CLC_DECL_ERR_REGRMB;
+
+	/* send CONFIRM LINK request to client over the RoCE fabric */
+	rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ);
+	if (rc < 0)
+		return SMC_CLC_DECL_TIMEOUT_CL;
+
+	/* receive CONFIRM LINK response from client over the RoCE fabric */
+	rest = wait_for_completion_interruptible_timeout(
+		&link->llc_confirm_resp,
+		SMC_LLC_WAIT_FIRST_TIME);
+	if (rest <= 0) {
+		struct smc_clc_msg_decline dclc;
+
+		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+				      SMC_CLC_DECLINE);
+		return rc;
+	}
+
+	if (link->llc_confirm_resp_rc)
+		return SMC_CLC_DECL_RMBE_EC;
+
+	/* send ADD LINK request to client over the RoCE fabric */
+	rc = smc_llc_send_add_link(link,
+				   link->smcibdev->mac[link->ibport - 1],
+				   link->gid, SMC_LLC_REQ);
+	if (rc < 0)
+		return SMC_CLC_DECL_TIMEOUT_AL;
+
+	/* receive ADD LINK response from client over the RoCE fabric */
+	rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp,
+							 SMC_LLC_WAIT_TIME);
+	if (rest <= 0) {
+		struct smc_clc_msg_decline dclc;
+
+		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+				      SMC_CLC_DECLINE);
+		return rc;
+	}
+
+	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
+
+	return 0;
+}
+
+/* listen worker: finish */
+static void smc_listen_out(struct smc_sock *new_smc)
+{
+	struct smc_sock *lsmc = new_smc->listen_smc;
+	struct sock *newsmcsk = &new_smc->sk;
+
+	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
+	if (lsmc->sk.sk_state == SMC_LISTEN) {
+		smc_accept_enqueue(&lsmc->sk, newsmcsk);
+	} else { /* no longer listening */
+		smc_close_non_accepted(newsmcsk);
+	}
+	release_sock(&lsmc->sk);
+
+	/* Wake up accept */
+	lsmc->sk.sk_data_ready(&lsmc->sk);
+	sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
+}
+
+/* listen worker: finish in state connected */
+static void smc_listen_out_connected(struct smc_sock *new_smc)
+{
+	struct sock *newsmcsk = &new_smc->sk;
+
+	sk_refcnt_debug_inc(newsmcsk);
+	if (newsmcsk->sk_state == SMC_INIT)
+		newsmcsk->sk_state = SMC_ACTIVE;
+
+	smc_listen_out(new_smc);
+}
+
+/* listen worker: finish in error state */
+static void smc_listen_out_err(struct smc_sock *new_smc)
+{
+	struct sock *newsmcsk = &new_smc->sk;
+
+	if (newsmcsk->sk_state == SMC_INIT)
+		sock_put(&new_smc->sk); /* passive closing */
+	newsmcsk->sk_state = SMC_CLOSED;
+	smc_conn_free(&new_smc->conn);
+
+	smc_listen_out(new_smc);
+}
+
+/* listen worker: decline and fall back if possible */
+static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
+			       int local_contact)
+{
+	/* RDMA setup failed, switch back to TCP */
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_lgr_forget(new_smc->conn.lgr);
+	if (reason_code < 0) { /* error, no fallback possible */
+		smc_listen_out_err(new_smc);
+		return;
+	}
+	smc_conn_free(&new_smc->conn);
+	new_smc->use_fallback = true;
+	new_smc->fallback_rsn = reason_code;
+	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
+		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
+			smc_listen_out_err(new_smc);
+			return;
+		}
+	}
+	smc_listen_out_connected(new_smc);
+}
+
+/* listen worker: check prefixes */
+static int smc_listen_rdma_check(struct smc_sock *new_smc,
+				 struct smc_clc_msg_proposal *pclc)
+{
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct socket *newclcsock = new_smc->clcsock;
+
+	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (smc_clc_prfx_match(newclcsock, pclc_prfx))
+		return SMC_CLC_DECL_CNFERR;
+
+	return 0;
+}
+
+/* listen worker: initialize connection and buffers */
+static int smc_listen_rdma_init(struct smc_sock *new_smc,
+				struct smc_clc_msg_proposal *pclc,
+				struct smc_ib_device *ibdev, u8 ibport,
+				int *local_contact)
+{
+	/* allocate connection / link group */
+	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
+					 &pclc->lcl, NULL, 0);
+	if (*local_contact < 0) {
+		if (*local_contact == -ENOMEM)
+			return SMC_CLC_DECL_MEM;/* insufficient memory*/
+		return SMC_CLC_DECL_INTERR; /* other error */
+	}
+
+	/* create send buffer and rmb */
+	if (smc_buf_create(new_smc, false))
+		return SMC_CLC_DECL_MEM;
+
+	return 0;
+}
+
+/* listen worker: initialize connection and buffers for SMC-D */
+static int smc_listen_ism_init(struct smc_sock *new_smc,
+			       struct smc_clc_msg_proposal *pclc,
+			       struct smcd_dev *ismdev,
+			       int *local_contact)
+{
+	struct smc_clc_msg_smcd *pclc_smcd;
+
+	pclc_smcd = smc_get_clc_msg_smcd(pclc);
+	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
+					 ismdev, pclc_smcd->gid);
+	if (*local_contact < 0) {
+		if (*local_contact == -ENOMEM)
+			return SMC_CLC_DECL_MEM;/* insufficient memory*/
+		return SMC_CLC_DECL_INTERR; /* other error */
+	}
+
+	/* Check if peer can be reached via ISM device */
+	if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
+			    new_smc->conn.lgr->vlan_id,
+			    new_smc->conn.lgr->smcd)) {
+		if (*local_contact == SMC_FIRST_CONTACT)
+			smc_lgr_forget(new_smc->conn.lgr);
+		smc_conn_free(&new_smc->conn);
+		return SMC_CLC_DECL_CNFERR;
+	}
+
+	/* Create send and receive buffers */
+	if (smc_buf_create(new_smc, true)) {
+		if (*local_contact == SMC_FIRST_CONTACT)
+			smc_lgr_forget(new_smc->conn.lgr);
+		smc_conn_free(&new_smc->conn);
+		return SMC_CLC_DECL_MEM;
+	}
+
+	return 0;
+}
+
+/* listen worker: register buffers */
+static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
+{
+	struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
+
+	if (local_contact != SMC_FIRST_CONTACT) {
+		if (!new_smc->conn.rmb_desc->reused) {
+			if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
+				return SMC_CLC_DECL_ERR_REGRMB;
+		}
+	}
+	smc_rmb_sync_sg_for_device(&new_smc->conn);
+
+	return 0;
+}
+
+/* listen worker: finish RDMA setup */
+static int smc_listen_rdma_finish(struct smc_sock *new_smc,
+				  struct smc_clc_msg_accept_confirm *cclc,
+				  int local_contact)
+{
+	struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
+	int reason_code = 0;
+
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_link_save_peer_info(link, cclc);
+
+	if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) {
+		reason_code = SMC_CLC_DECL_ERR_RTOK;
+		goto decline;
+	}
+
+	if (local_contact == SMC_FIRST_CONTACT) {
+		if (smc_ib_ready_link(link)) {
+			reason_code = SMC_CLC_DECL_ERR_RDYLNK;
+			goto decline;
+		}
+		/* QP confirmation over RoCE fabric */
+		reason_code = smc_serv_conf_first_link(new_smc);
+		if (reason_code)
+			goto decline;
+	}
+	return 0;
+
+decline:
+	mutex_unlock(&smc_create_lgr_pending);
+	smc_listen_decline(new_smc, reason_code, local_contact);
+	return reason_code;
+}
+
+/* setup for RDMA connection of server */
+static void smc_listen_work(struct work_struct *work)
+{
+	struct smc_sock *new_smc = container_of(work, struct smc_sock,
+						smc_listen_work);
+	struct socket *newclcsock = new_smc->clcsock;
+	struct smc_clc_msg_accept_confirm cclc;
+	struct smc_clc_msg_proposal *pclc;
+	struct smc_ib_device *ibdev;
+	bool ism_supported = false;
+	struct smcd_dev *ismdev;
+	u8 buf[SMC_CLC_MAX_LEN];
+	int local_contact = 0;
+	unsigned short vlan;
+	int reason_code = 0;
+	int rc = 0;
+	u8 ibport;
+
+	if (new_smc->use_fallback) {
+		smc_listen_out_connected(new_smc);
+		return;
+	}
+
+	/* check if peer is smc capable */
+	if (!tcp_sk(newclcsock->sk)->syn_smc) {
+		new_smc->use_fallback = true;
+		new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
+		smc_listen_out_connected(new_smc);
+		return;
+	}
+
+	/* do inband token exchange -
+	 * wait for and receive SMC Proposal CLC message
+	 */
+	pclc = (struct smc_clc_msg_proposal *)&buf;
+	reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+				       SMC_CLC_PROPOSAL);
+	if (reason_code) {
+		smc_listen_decline(new_smc, reason_code, 0);
+		return;
+	}
+
+	/* IPSec connections opt out of SMC-R optimizations */
+	if (using_ipsec(new_smc)) {
+		smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0);
+		return;
+	}
+
+	mutex_lock(&smc_create_lgr_pending);
+	smc_close_init(new_smc);
+	smc_rx_init(new_smc);
+	smc_tx_init(new_smc);
+
+	/* check if ISM is available */
+	if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
+	    !smc_check_ism(new_smc, &ismdev) &&
+	    !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
+		ism_supported = true;
+	}
+
+	/* check if RDMA is available */
+	if (!ism_supported &&
+	    ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
+	     smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
+	     smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
+	     smc_listen_rdma_check(new_smc, pclc) ||
+	     smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
+				  &local_contact) ||
+	     smc_listen_rdma_reg(new_smc, local_contact))) {
+		/* SMC not supported, decline */
+		mutex_unlock(&smc_create_lgr_pending);
+		smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
+				   local_contact);
+		return;
+	}
+
+	/* send SMC Accept CLC message */
+	rc = smc_clc_send_accept(new_smc, local_contact);
+	if (rc) {
+		mutex_unlock(&smc_create_lgr_pending);
+		smc_listen_decline(new_smc, rc, local_contact);
+		return;
+	}
+
+	/* receive SMC Confirm CLC message */
+	reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+				       SMC_CLC_CONFIRM);
+	if (reason_code) {
+		mutex_unlock(&smc_create_lgr_pending);
+		smc_listen_decline(new_smc, reason_code, local_contact);
+		return;
+	}
+
+	/* finish worker */
+	if (!ism_supported) {
+		if (smc_listen_rdma_finish(new_smc, &cclc, local_contact))
+			return;
+	}
+	smc_conn_save_peer_info(new_smc, &cclc);
+	mutex_unlock(&smc_create_lgr_pending);
+	smc_listen_out_connected(new_smc);
+}
+
+static void smc_tcp_listen_work(struct work_struct *work)
+{
+	struct smc_sock *lsmc = container_of(work, struct smc_sock,
+					     tcp_listen_work);
+	struct sock *lsk = &lsmc->sk;
+	struct smc_sock *new_smc;
+	int rc = 0;
+
+	lock_sock(lsk);
+	while (lsk->sk_state == SMC_LISTEN) {
+		rc = smc_clcsock_accept(lsmc, &new_smc);
+		if (rc)
+			goto out;
+		if (!new_smc)
+			continue;
+
+		new_smc->listen_smc = lsmc;
+		new_smc->use_fallback = lsmc->use_fallback;
+		new_smc->fallback_rsn = lsmc->fallback_rsn;
+		sock_hold(lsk); /* sock_put in smc_listen_work */
+		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
+		smc_copy_sock_settings_to_smc(new_smc);
+		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
+		sock_hold(&new_smc->sk); /* sock_put in passive closing */
+		if (!schedule_work(&new_smc->smc_listen_work))
+			sock_put(&new_smc->sk);
+	}
+
+out:
+	release_sock(lsk);
+	sock_put(&lsmc->sk); /* sock_hold in smc_listen */
+}
+
+static int smc_listen(struct socket *sock, int backlog)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc;
+
+	smc = smc_sk(sk);
+	lock_sock(sk);
+
+	rc = -EINVAL;
+	if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+		goto out;
+
+	rc = 0;
+	if (sk->sk_state == SMC_LISTEN) {
+		sk->sk_max_ack_backlog = backlog;
+		goto out;
+	}
+	/* some socket options are handled in core, so we could not apply
+	 * them to the clc socket -- copy smc socket options to clc socket
+	 */
+	smc_copy_sock_settings_to_clc(smc);
+	if (!smc->use_fallback)
+		tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+
+	rc = kernel_listen(smc->clcsock, backlog);
+	if (rc)
+		goto out;
+	sk->sk_max_ack_backlog = backlog;
+	sk->sk_ack_backlog = 0;
+	sk->sk_state = SMC_LISTEN;
+	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+	sock_hold(sk); /* sock_hold in tcp_listen_worker */
+	if (!schedule_work(&smc->tcp_listen_work))
+		sock_put(sk);
+
+out:
+	release_sock(sk);
+	return rc;
+}
+
+static int smc_accept(struct socket *sock, struct socket *new_sock,
+		      int flags, bool kern)
+{
+	struct sock *sk = sock->sk, *nsk;
+	DECLARE_WAITQUEUE(wait, current);
+	struct smc_sock *lsmc;
+	long timeo;
+	int rc = 0;
+
+	lsmc = smc_sk(sk);
+	sock_hold(sk); /* sock_put below */
+	lock_sock(sk);
+
+	if (lsmc->sk.sk_state != SMC_LISTEN) {
+		rc = -EINVAL;
+		release_sock(sk);
+		goto out;
+	}
+
+	/* Wait for an incoming connection */
+	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+	add_wait_queue_exclusive(sk_sleep(sk), &wait);
+	while (!(nsk = smc_accept_dequeue(sk, new_sock))) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!timeo) {
+			rc = -EAGAIN;
+			break;
+		}
+		release_sock(sk);
+		timeo = schedule_timeout(timeo);
+		/* wakeup by sk_data_ready in smc_listen_work() */
+		sched_annotate_sleep();
+		lock_sock(sk);
+		if (signal_pending(current)) {
+			rc = sock_intr_errno(timeo);
+			break;
+		}
+	}
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	if (!rc)
+		rc = sock_error(nsk);
+	release_sock(sk);
+	if (rc)
+		goto out;
+
+	if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) {
+		/* wait till data arrives on the socket */
+		timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept *
+								MSEC_PER_SEC);
+		if (smc_sk(nsk)->use_fallback) {
+			struct sock *clcsk = smc_sk(nsk)->clcsock->sk;
+
+			lock_sock(clcsk);
+			if (skb_queue_empty(&clcsk->sk_receive_queue))
+				sk_wait_data(clcsk, &timeo, NULL);
+			release_sock(clcsk);
+		} else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) {
+			lock_sock(nsk);
+			smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available);
+			release_sock(nsk);
+		}
+	}
+
+out:
+	sock_put(sk); /* sock_hold above */
+	return rc;
+}
+
+static int smc_getname(struct socket *sock, struct sockaddr *addr,
+		       int peer)
+{
+	struct smc_sock *smc;
+
+	if (peer && (sock->sk->sk_state != SMC_ACTIVE) &&
+	    (sock->sk->sk_state != SMC_APPCLOSEWAIT1))
+		return -ENOTCONN;
+
+	smc = smc_sk(sock->sk);
+
+	return smc->clcsock->ops->getname(smc->clcsock, addr, peer);
+}
+
+static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = -EPIPE;
+
+	smc = smc_sk(sk);
+	lock_sock(sk);
+	if ((sk->sk_state != SMC_ACTIVE) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_INIT))
+		goto out;
+
+	if (msg->msg_flags & MSG_FASTOPEN) {
+		if (sk->sk_state == SMC_INIT) {
+			smc->use_fallback = true;
+			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
+		} else {
+			rc = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (smc->use_fallback)
+		rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
+	else
+		rc = smc_tx_sendmsg(smc, msg, len);
+out:
+	release_sock(sk);
+	return rc;
+}
+
+static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		       int flags)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = -ENOTCONN;
+
+	smc = smc_sk(sk);
+	lock_sock(sk);
+	if ((sk->sk_state == SMC_INIT) ||
+	    (sk->sk_state == SMC_LISTEN) ||
+	    (sk->sk_state == SMC_CLOSED))
+		goto out;
+
+	if (sk->sk_state == SMC_PEERFINCLOSEWAIT) {
+		rc = 0;
+		goto out;
+	}
+
+	if (smc->use_fallback) {
+		rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags);
+	} else {
+		msg->msg_namelen = 0;
+		rc = smc_rx_recvmsg(smc, msg, NULL, len, flags);
+	}
+
+out:
+	release_sock(sk);
+	return rc;
+}
+
+static __poll_t smc_accept_poll(struct sock *parent)
+{
+	struct smc_sock *isk = smc_sk(parent);
+	__poll_t mask = 0;
+
+	spin_lock(&isk->accept_q_lock);
+	if (!list_empty(&isk->accept_q))
+		mask = EPOLLIN | EPOLLRDNORM;
+	spin_unlock(&isk->accept_q_lock);
+
+	return mask;
+}
+
+static __poll_t smc_poll(struct file *file, struct socket *sock,
+			     poll_table *wait)
+{
+	struct sock *sk = sock->sk;
+	__poll_t mask = 0;
+	struct smc_sock *smc;
+
+	if (!sk)
+		return EPOLLNVAL;
+
+	smc = smc_sk(sock->sk);
+	if (smc->use_fallback) {
+		/* delegate to CLC child sock */
+		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
+		sk->sk_err = smc->clcsock->sk->sk_err;
+		if (sk->sk_err)
+			mask |= EPOLLERR;
+	} else {
+		if (sk->sk_state != SMC_CLOSED)
+			sock_poll_wait(file, sock, wait);
+		if (sk->sk_err)
+			mask |= EPOLLERR;
+		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
+		    (sk->sk_state == SMC_CLOSED))
+			mask |= EPOLLHUP;
+		if (sk->sk_state == SMC_LISTEN) {
+			/* woken up by sk_data_ready in smc_listen_work() */
+			mask = smc_accept_poll(sk);
+		} else {
+			if (atomic_read(&smc->conn.sndbuf_space) ||
+			    sk->sk_shutdown & SEND_SHUTDOWN) {
+				mask |= EPOLLOUT | EPOLLWRNORM;
+			} else {
+				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			}
+			if (atomic_read(&smc->conn.bytes_to_rcv))
+				mask |= EPOLLIN | EPOLLRDNORM;
+			if (sk->sk_shutdown & RCV_SHUTDOWN)
+				mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+			if (sk->sk_state == SMC_APPCLOSEWAIT1)
+				mask |= EPOLLIN;
+			if (smc->conn.urg_state == SMC_URG_VALID)
+				mask |= EPOLLPRI;
+		}
+	}
+
+	return mask;
+}
+
+static int smc_shutdown(struct socket *sock, int how)
+{
+	struct sock *sk = sock->sk;
+	bool do_shutdown = true;
+	struct smc_sock *smc;
+	int rc = -EINVAL;
+	int old_state;
+	int rc1 = 0;
+
+	smc = smc_sk(sk);
+
+	if ((how < SHUT_RD) || (how > SHUT_RDWR))
+		return rc;
+
+	lock_sock(sk);
+
+	rc = -ENOTCONN;
+	if ((sk->sk_state != SMC_ACTIVE) &&
+	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT2) &&
+	    (sk->sk_state != SMC_APPFINCLOSEWAIT))
+		goto out;
+	if (smc->use_fallback) {
+		rc = kernel_sock_shutdown(smc->clcsock, how);
+		sk->sk_shutdown = smc->clcsock->sk->sk_shutdown;
+		if (sk->sk_shutdown == SHUTDOWN_MASK)
+			sk->sk_state = SMC_CLOSED;
+		goto out;
+	}
+	switch (how) {
+	case SHUT_RDWR:		/* shutdown in both directions */
+		old_state = sk->sk_state;
+		rc = smc_close_active(smc);
+		if (old_state == SMC_ACTIVE &&
+		    sk->sk_state == SMC_PEERCLOSEWAIT1)
+			do_shutdown = false;
+		break;
+	case SHUT_WR:
+		rc = smc_close_shutdown_write(smc);
+		break;
+	case SHUT_RD:
+		rc = 0;
+		/* nothing more to do because peer is not involved */
+		break;
+	}
+	if (do_shutdown && smc->clcsock)
+		rc1 = kernel_sock_shutdown(smc->clcsock, how);
+	/* map sock_shutdown_cmd constants to sk_shutdown value range */
+	sk->sk_shutdown |= how + 1;
+
+out:
+	release_sock(sk);
+	return rc ? rc : rc1;
+}
+
+static int smc_setsockopt(struct socket *sock, int level, int optname,
+			  char __user *optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int val, rc;
+
+	if (level == SOL_TCP && optname == TCP_ULP)
+		return -EOPNOTSUPP;
+
+	smc = smc_sk(sk);
+
+	/* generic setsockopts reaching us here always apply to the
+	 * CLC socket
+	 */
+	rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
+					   optval, optlen);
+	if (smc->clcsock->sk->sk_err) {
+		sk->sk_err = smc->clcsock->sk->sk_err;
+		sk->sk_error_report(sk);
+	}
+	if (rc)
+		return rc;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
+
+	lock_sock(sk);
+	switch (optname) {
+	case TCP_FASTOPEN:
+	case TCP_FASTOPEN_CONNECT:
+	case TCP_FASTOPEN_KEY:
+	case TCP_FASTOPEN_NO_COOKIE:
+		/* option not supported by SMC */
+		if (sk->sk_state == SMC_INIT) {
+			smc->use_fallback = true;
+			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
+		} else {
+			if (!smc->use_fallback)
+				rc = -EINVAL;
+		}
+		break;
+	case TCP_NODELAY:
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
+			if (val && !smc->use_fallback)
+				mod_delayed_work(system_wq, &smc->conn.tx_work,
+						 0);
+		}
+		break;
+	case TCP_CORK:
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
+			if (!val && !smc->use_fallback)
+				mod_delayed_work(system_wq, &smc->conn.tx_work,
+						 0);
+		}
+		break;
+	case TCP_DEFER_ACCEPT:
+		smc->sockopt_defer_accept = val;
+		break;
+	default:
+		break;
+	}
+	release_sock(sk);
+
+	return rc;
+}
+
+static int smc_getsockopt(struct socket *sock, int level, int optname,
+			  char __user *optval, int __user *optlen)
+{
+	struct smc_sock *smc;
+
+	smc = smc_sk(sock->sk);
+	/* socket options apply to the CLC socket */
+	return smc->clcsock->ops->getsockopt(smc->clcsock, level, optname,
+					     optval, optlen);
+}
+
+static int smc_ioctl(struct socket *sock, unsigned int cmd,
+		     unsigned long arg)
+{
+	union smc_host_cursor cons, urg;
+	struct smc_connection *conn;
+	struct smc_sock *smc;
+	int answ;
+
+	smc = smc_sk(sock->sk);
+	conn = &smc->conn;
+	lock_sock(&smc->sk);
+	if (smc->use_fallback) {
+		if (!smc->clcsock) {
+			release_sock(&smc->sk);
+			return -EBADF;
+		}
+		answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		release_sock(&smc->sk);
+		return answ;
+	}
+	switch (cmd) {
+	case SIOCINQ: /* same as FIONREAD */
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
+			return -EINVAL;
+		}
+		if (smc->sk.sk_state == SMC_INIT ||
+		    smc->sk.sk_state == SMC_CLOSED)
+			answ = 0;
+		else
+			answ = atomic_read(&smc->conn.bytes_to_rcv);
+		break;
+	case SIOCOUTQ:
+		/* output queue size (not send + not acked) */
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
+			return -EINVAL;
+		}
+		if (smc->sk.sk_state == SMC_INIT ||
+		    smc->sk.sk_state == SMC_CLOSED)
+			answ = 0;
+		else
+			answ = smc->conn.sndbuf_desc->len -
+					atomic_read(&smc->conn.sndbuf_space);
+		break;
+	case SIOCOUTQNSD:
+		/* output queue size (not send only) */
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
+			return -EINVAL;
+		}
+		if (smc->sk.sk_state == SMC_INIT ||
+		    smc->sk.sk_state == SMC_CLOSED)
+			answ = 0;
+		else
+			answ = smc_tx_prepared_sends(&smc->conn);
+		break;
+	case SIOCATMARK:
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
+			return -EINVAL;
+		}
+		if (smc->sk.sk_state == SMC_INIT ||
+		    smc->sk.sk_state == SMC_CLOSED) {
+			answ = 0;
+		} else {
+			smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+			smc_curs_copy(&urg, &conn->urg_curs, conn);
+			answ = smc_curs_diff(conn->rmb_desc->len,
+					     &cons, &urg) == 1;
+		}
+		break;
+	default:
+		release_sock(&smc->sk);
+		return -ENOIOCTLCMD;
+	}
+	release_sock(&smc->sk);
+
+	return put_user(answ, (int __user *)arg);
+}
+
+static ssize_t smc_sendpage(struct socket *sock, struct page *page,
+			    int offset, size_t size, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = -EPIPE;
+
+	smc = smc_sk(sk);
+	lock_sock(sk);
+	if (sk->sk_state != SMC_ACTIVE) {
+		release_sock(sk);
+		goto out;
+	}
+	release_sock(sk);
+	if (smc->use_fallback)
+		rc = kernel_sendpage(smc->clcsock, page, offset,
+				     size, flags);
+	else
+		rc = sock_no_sendpage(sock, page, offset, size, flags);
+
+out:
+	return rc;
+}
+
+/* Map the affected portions of the rmbe into an spd, note the number of bytes
+ * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor
+ * updates till whenever a respective page has been fully processed.
+ * Note that subsequent recv() calls have to wait till all splice() processing
+ * completed.
+ */
+static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
+			       struct pipe_inode_info *pipe, size_t len,
+			       unsigned int flags)
+{
+	struct sock *sk = sock->sk;
+	struct smc_sock *smc;
+	int rc = -ENOTCONN;
+
+	smc = smc_sk(sk);
+	lock_sock(sk);
+
+	if (sk->sk_state == SMC_INIT ||
+	    sk->sk_state == SMC_LISTEN ||
+	    sk->sk_state == SMC_CLOSED)
+		goto out;
+
+	if (sk->sk_state == SMC_PEERFINCLOSEWAIT) {
+		rc = 0;
+		goto out;
+	}
+
+	if (smc->use_fallback) {
+		rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos,
+						    pipe, len, flags);
+	} else {
+		if (*ppos) {
+			rc = -ESPIPE;
+			goto out;
+		}
+		if (flags & SPLICE_F_NONBLOCK)
+			flags = MSG_DONTWAIT;
+		else
+			flags = 0;
+		rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags);
+	}
+out:
+	release_sock(sk);
+
+	return rc;
+}
+
+/* must look like tcp */
+static const struct proto_ops smc_sock_ops = {
+	.family		= PF_SMC,
+	.owner		= THIS_MODULE,
+	.release	= smc_release,
+	.bind		= smc_bind,
+	.connect	= smc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= smc_accept,
+	.getname	= smc_getname,
+	.poll		= smc_poll,
+	.ioctl		= smc_ioctl,
+	.listen		= smc_listen,
+	.shutdown	= smc_shutdown,
+	.setsockopt	= smc_setsockopt,
+	.getsockopt	= smc_getsockopt,
+	.sendmsg	= smc_sendmsg,
+	.recvmsg	= smc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.sendpage	= smc_sendpage,
+	.splice_read	= smc_splice_read,
+};
+
+static int smc_create(struct net *net, struct socket *sock, int protocol,
+		      int kern)
+{
+	int family = (protocol == SMCPROTO_SMC6) ? PF_INET6 : PF_INET;
+	struct smc_sock *smc;
+	struct sock *sk;
+	int rc;
+
+	rc = -ESOCKTNOSUPPORT;
+	if (sock->type != SOCK_STREAM)
+		goto out;
+
+	rc = -EPROTONOSUPPORT;
+	if (protocol != SMCPROTO_SMC && protocol != SMCPROTO_SMC6)
+		goto out;
+
+	rc = -ENOBUFS;
+	sock->ops = &smc_sock_ops;
+	sk = smc_sock_alloc(net, sock, protocol);
+	if (!sk)
+		goto out;
+
+	/* create internal TCP socket for CLC handshake and fallback */
+	smc = smc_sk(sk);
+	smc->use_fallback = false; /* assume rdma capability first */
+	smc->fallback_rsn = 0;
+	rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
+			      &smc->clcsock);
+	if (rc) {
+		sk_common_release(sk);
+		goto out;
+	}
+	smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE);
+	smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE);
+
+out:
+	return rc;
+}
+
+static const struct net_proto_family smc_sock_family_ops = {
+	.family	= PF_SMC,
+	.owner	= THIS_MODULE,
+	.create	= smc_create,
+};
+
+static int __init smc_init(void)
+{
+	int rc;
+
+	rc = smc_pnet_init();
+	if (rc)
+		return rc;
+
+	rc = smc_llc_init();
+	if (rc) {
+		pr_err("%s: smc_llc_init fails with %d\n", __func__, rc);
+		goto out_pnet;
+	}
+
+	rc = smc_cdc_init();
+	if (rc) {
+		pr_err("%s: smc_cdc_init fails with %d\n", __func__, rc);
+		goto out_pnet;
+	}
+
+	rc = proto_register(&smc_proto, 1);
+	if (rc) {
+		pr_err("%s: proto_register(v4) fails with %d\n", __func__, rc);
+		goto out_pnet;
+	}
+
+	rc = proto_register(&smc_proto6, 1);
+	if (rc) {
+		pr_err("%s: proto_register(v6) fails with %d\n", __func__, rc);
+		goto out_proto;
+	}
+
+	rc = sock_register(&smc_sock_family_ops);
+	if (rc) {
+		pr_err("%s: sock_register fails with %d\n", __func__, rc);
+		goto out_proto6;
+	}
+	INIT_HLIST_HEAD(&smc_v4_hashinfo.ht);
+	INIT_HLIST_HEAD(&smc_v6_hashinfo.ht);
+
+	rc = smc_ib_register_client();
+	if (rc) {
+		pr_err("%s: ib_register fails with %d\n", __func__, rc);
+		goto out_sock;
+	}
+
+	static_branch_enable(&tcp_have_smc);
+	return 0;
+
+out_sock:
+	sock_unregister(PF_SMC);
+out_proto6:
+	proto_unregister(&smc_proto6);
+out_proto:
+	proto_unregister(&smc_proto);
+out_pnet:
+	smc_pnet_exit();
+	return rc;
+}
+
+static void __exit smc_exit(void)
+{
+	smc_core_exit();
+	static_branch_disable(&tcp_have_smc);
+	smc_ib_unregister_client();
+	sock_unregister(PF_SMC);
+	proto_unregister(&smc_proto6);
+	proto_unregister(&smc_proto);
+	smc_pnet_exit();
+}
+
+module_init(smc_init);
+module_exit(smc_exit);
+
+MODULE_AUTHOR("Ursula Braun <ubraun@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("smc socket address family");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_SMC);
diff --git a/net/smc/smc.h b/net/smc/smc.h
new file mode 100644
index 000000000..adbdf195e
--- /dev/null
+++ b/net/smc/smc.h
@@ -0,0 +1,271 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for the SMC module (socket related)
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+#ifndef __SMC_H
+#define __SMC_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+#include <linux/compiler.h> /* __aligned */
+#include <net/sock.h>
+
+#include "smc_ib.h"
+
+#define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
+#define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
+
+extern struct proto smc_proto;
+extern struct proto smc_proto6;
+
+#ifdef ATOMIC64_INIT
+#define KERNEL_HAS_ATOMIC64
+#endif
+
+enum smc_state {		/* possible states of an SMC socket */
+	SMC_ACTIVE	= 1,
+	SMC_INIT	= 2,
+	SMC_CLOSED	= 7,
+	SMC_LISTEN	= 10,
+	/* normal close */
+	SMC_PEERCLOSEWAIT1	= 20,
+	SMC_PEERCLOSEWAIT2	= 21,
+	SMC_APPFINCLOSEWAIT	= 24,
+	SMC_APPCLOSEWAIT1	= 22,
+	SMC_APPCLOSEWAIT2	= 23,
+	SMC_PEERFINCLOSEWAIT	= 25,
+	/* abnormal close */
+	SMC_PEERABORTWAIT	= 26,
+	SMC_PROCESSABORT	= 27,
+};
+
+struct smc_link_group;
+
+struct smc_wr_rx_hdr {	/* common prefix part of LLC and CDC to demultiplex */
+	u8			type;
+} __aligned(1);
+
+struct smc_cdc_conn_state_flags {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8	peer_done_writing : 1;	/* Sending done indicator */
+	u8	peer_conn_closed : 1;	/* Peer connection closed indicator */
+	u8	peer_conn_abort : 1;	/* Abnormal close indicator */
+	u8	reserved : 5;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8	reserved : 5;
+	u8	peer_conn_abort : 1;
+	u8	peer_conn_closed : 1;
+	u8	peer_done_writing : 1;
+#endif
+};
+
+struct smc_cdc_producer_flags {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8	write_blocked : 1;	/* Writing Blocked, no rx buf space */
+	u8	urg_data_pending : 1;	/* Urgent Data Pending */
+	u8	urg_data_present : 1;	/* Urgent Data Present */
+	u8	cons_curs_upd_req : 1;	/* cursor update requested */
+	u8	failover_validation : 1;/* message replay due to failover */
+	u8	reserved : 3;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8	reserved : 3;
+	u8	failover_validation : 1;
+	u8	cons_curs_upd_req : 1;
+	u8	urg_data_present : 1;
+	u8	urg_data_pending : 1;
+	u8	write_blocked : 1;
+#endif
+};
+
+/* in host byte order */
+union smc_host_cursor {	/* SMC cursor - an offset in an RMBE */
+	struct {
+		u16	reserved;
+		u16	wrap;		/* window wrap sequence number */
+		u32	count;		/* cursor (= offset) part */
+	};
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_t		acurs;	/* for atomic processing */
+#else
+	u64			acurs;	/* for atomic processing */
+#endif
+} __aligned(8);
+
+/* in host byte order, except for flag bitfields in network byte order */
+struct smc_host_cdc_msg {		/* Connection Data Control message */
+	struct smc_wr_rx_hdr		common; /* .type = 0xFE */
+	u8				len;	/* length = 44 */
+	u16				seqno;	/* connection seq # */
+	u32				token;	/* alert_token */
+	union smc_host_cursor		prod;		/* producer cursor */
+	union smc_host_cursor		cons;		/* consumer cursor,
+							 * piggy backed "ack"
+							 */
+	struct smc_cdc_producer_flags	prod_flags;	/* conn. tx/rx status */
+	struct smc_cdc_conn_state_flags	conn_state_flags; /* peer conn. status*/
+	u8				reserved[18];
+} __aligned(8);
+
+enum smc_urg_state {
+	SMC_URG_VALID	= 1,			/* data present */
+	SMC_URG_NOTYET	= 2,			/* data pending */
+	SMC_URG_READ	= 3,			/* data was already read */
+};
+
+struct smc_connection {
+	struct rb_node		alert_node;
+	struct smc_link_group	*lgr;		/* link group of connection */
+	u32			alert_token_local; /* unique conn. id */
+	u8			peer_rmbe_idx;	/* from tcp handshake */
+	int			peer_rmbe_size;	/* size of peer rx buffer */
+	atomic_t		peer_rmbe_space;/* remaining free bytes in peer
+						 * rmbe
+						 */
+	int			rtoken_idx;	/* idx to peer RMB rkey/addr */
+
+	struct smc_buf_desc	*sndbuf_desc;	/* send buffer descriptor */
+	struct smc_buf_desc	*rmb_desc;	/* RMBE descriptor */
+	int			rmbe_size_short;/* compressed notation */
+	int			rmbe_update_limit;
+						/* lower limit for consumer
+						 * cursor update
+						 */
+
+	struct smc_host_cdc_msg	local_tx_ctrl;	/* host byte order staging
+						 * buffer for CDC msg send
+						 * .prod cf. TCP snd_nxt
+						 * .cons cf. TCP sends ack
+						 */
+	union smc_host_cursor	tx_curs_prep;	/* tx - prepared data
+						 * snd_max..wmem_alloc
+						 */
+	union smc_host_cursor	tx_curs_sent;	/* tx - sent data
+						 * snd_nxt ?
+						 */
+	union smc_host_cursor	tx_curs_fin;	/* tx - confirmed by peer
+						 * snd-wnd-begin ?
+						 */
+	atomic_t		sndbuf_space;	/* remaining space in sndbuf */
+	u16			tx_cdc_seq;	/* sequence # for CDC send */
+	spinlock_t		send_lock;	/* protect wr_sends */
+	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
+	u32			tx_off;		/* base offset in peer rmb */
+
+	struct smc_host_cdc_msg	local_rx_ctrl;	/* filled during event_handl.
+						 * .prod cf. TCP rcv_nxt
+						 * .cons cf. TCP snd_una
+						 */
+	union smc_host_cursor	rx_curs_confirmed; /* confirmed to peer
+						    * source of snd_una ?
+						    */
+	union smc_host_cursor	urg_curs;	/* points at urgent byte */
+	enum smc_urg_state	urg_state;
+	bool			urg_tx_pend;	/* urgent data staged */
+	bool			urg_rx_skip_pend;
+						/* indicate urgent oob data
+						 * read, but previous regular
+						 * data still pending
+						 */
+	char			urg_rx_byte;	/* urgent byte */
+	atomic_t		bytes_to_rcv;	/* arrived data,
+						 * not yet received
+						 */
+	atomic_t		splice_pending;	/* number of spliced bytes
+						 * pending processing
+						 */
+#ifndef KERNEL_HAS_ATOMIC64
+	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_connect_info {
+	int			flags;
+	int			alen;
+	struct sockaddr		addr;
+};
+
+struct smc_sock {				/* smc sock container */
+	struct sock		sk;
+	struct socket		*clcsock;	/* internal tcp socket */
+	struct smc_connection	conn;		/* smc connection */
+	struct smc_sock		*listen_smc;	/* listen parent */
+	struct smc_connect_info *connect_info;	/* connect address & flags */
+	struct work_struct	connect_work;	/* handle non-blocking connect*/
+	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
+	struct work_struct	smc_listen_work;/* prepare new accept socket */
+	struct list_head	accept_q;	/* sockets to be accepted */
+	spinlock_t		accept_q_lock;	/* protects accept_q */
+	bool			use_fallback;	/* fallback to tcp */
+	int			fallback_rsn;	/* reason for fallback */
+	u32			peer_diagnosis; /* decline reason from peer */
+	int			sockopt_defer_accept;
+						/* sockopt TCP_DEFER_ACCEPT
+						 * value
+						 */
+	u8			wait_close_tx_prepared : 1;
+						/* shutdown wr or close
+						 * started, waiting for unsent
+						 * data to be sent
+						 */
+	struct mutex            clcsock_release_lock;
+						/* protects clcsock of a listen
+						 * socket
+						 * */
+};
+
+static inline struct smc_sock *smc_sk(const struct sock *sk)
+{
+	return (struct smc_sock *)sk;
+}
+
+#define SMC_SYSTEMID_LEN		8
+
+extern u8	local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */
+
+/* convert an u32 value into network byte order, store it into a 3 byte field */
+static inline void hton24(u8 *net, u32 host)
+{
+	__be32 t;
+
+	t = cpu_to_be32(host);
+	memcpy(net, ((u8 *)&t) + 1, 3);
+}
+
+/* convert a received 3 byte field into host byte order*/
+static inline u32 ntoh24(u8 *net)
+{
+	__be32 t = 0;
+
+	memcpy(((u8 *)&t) + 1, net, 3);
+	return be32_to_cpu(t);
+}
+
+#ifdef CONFIG_XFRM
+static inline bool using_ipsec(struct smc_sock *smc)
+{
+	return (smc->clcsock->sk->sk_policy[0] ||
+		smc->clcsock->sk->sk_policy[1]) ? true : false;
+}
+#else
+static inline bool using_ipsec(struct smc_sock *smc)
+{
+	return false;
+}
+#endif
+
+struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock);
+void smc_close_non_accepted(struct sock *sk);
+
+#endif	/* __SMC_H */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
new file mode 100644
index 000000000..333e43534
--- /dev/null
+++ b/net/smc/smc_cdc.c
@@ -0,0 +1,407 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Connection Data Control (CDC)
+ * handles flow control
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/spinlock.h>
+
+#include "smc.h"
+#include "smc_wr.h"
+#include "smc_cdc.h"
+#include "smc_tx.h"
+#include "smc_rx.h"
+#include "smc_close.h"
+
+/********************************** send *************************************/
+
+struct smc_cdc_tx_pend {
+	struct smc_connection	*conn;		/* socket connection */
+	union smc_host_cursor	cursor;	/* tx sndbuf cursor sent */
+	union smc_host_cursor	p_cursor;	/* rx RMBE cursor produced */
+	u16			ctrl_seq;	/* conn. tx sequence # */
+};
+
+/* handler for send/transmission completion of a CDC msg */
+static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
+			       struct smc_link *link,
+			       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 (!conn)
+		/* already dismissed */
+		return;
+
+	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,
+				     &cdcpend->conn->tx_curs_fin,
+				     &cdcpend->cursor);
+		/* sndbuf_space is decreased in smc_sendmsg */
+		smp_mb__before_atomic();
+		atomic_add(diff, &cdcpend->conn->sndbuf_space);
+		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+		smp_mb__after_atomic();
+		smc_curs_copy(&conn->tx_curs_fin, &cdcpend->cursor, conn);
+	}
+	smc_tx_sndbuf_nonfull(smc);
+	bh_unlock_sock(&smc->sk);
+}
+
+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];
+	int rc;
+
+	rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
+				     (struct smc_wr_tx_pend_priv **)pend);
+	if (!conn->alert_token_local)
+		/* abnormal termination */
+		rc = -EPIPE;
+	return rc;
+}
+
+static inline void smc_cdc_add_pending_send(struct smc_connection *conn,
+					    struct smc_cdc_tx_pend *pend)
+{
+	BUILD_BUG_ON_MSG(
+		sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE,
+		"must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)");
+	BUILD_BUG_ON_MSG(
+		sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE,
+		"must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()");
+	BUILD_BUG_ON_MSG(
+		sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE,
+		"must increase SMC_WR_TX_PEND_PRIV_SIZE to at least sizeof(struct smc_cdc_tx_pend)");
+	pend->conn = conn;
+	pend->cursor = conn->tx_curs_sent;
+	pend->p_cursor = conn->local_tx_ctrl.prod;
+	pend->ctrl_seq = conn->tx_cdc_seq;
+}
+
+int smc_cdc_msg_send(struct smc_connection *conn,
+		     struct smc_wr_buf *wr_buf,
+		     struct smc_cdc_tx_pend *pend)
+{
+	union smc_host_cursor cfed;
+	struct smc_link *link;
+	int rc;
+
+	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
+	smc_cdc_add_pending_send(conn, pend);
+
+	conn->tx_cdc_seq++;
+	conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
+	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
+	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
+	if (!rc)
+		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
+
+	return rc;
+}
+
+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;
+	int rc;
+
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+	if (rc)
+		return rc;
+
+	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)
+{
+	struct smc_connection *conn = (struct smc_connection *)data;
+	struct smc_cdc_tx_pend *cdc_pend =
+		(struct smc_cdc_tx_pend *)tx_pend;
+
+	return cdc_pend->conn == conn;
+}
+
+static void smc_cdc_tx_dismisser(struct smc_wr_tx_pend_priv *tx_pend)
+{
+	struct smc_cdc_tx_pend *cdc_pend =
+		(struct smc_cdc_tx_pend *)tx_pend;
+
+	cdc_pend->conn = NULL;
+}
+
+void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
+{
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
+	smc_wr_tx_dismiss_slots(link, SMC_CDC_MSG_TYPE,
+				smc_cdc_tx_filter, smc_cdc_tx_dismisser,
+				(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)
+{
+	return (s16)(seq1 - seq2) < 0;
+}
+
+static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
+					    int *diff_prod)
+{
+	struct smc_connection *conn = &smc->conn;
+	char *base;
+
+	/* new data included urgent business */
+	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 + conn->rx_off;
+	if (conn->urg_curs.count)
+		conn->urg_rx_byte = *(base + conn->urg_curs.count - 1);
+	else
+		conn->urg_rx_byte = *(base + conn->rmb_desc->len - 1);
+	sk_send_sigurg(&smc->sk);
+}
+
+static void smc_cdc_msg_recv_action(struct smc_sock *smc,
+				    struct smc_cdc_msg *cdc)
+{
+	union smc_host_cursor cons_old, prod_old;
+	struct smc_connection *conn = &smc->conn;
+	int diff_cons, diff_prod;
+
+	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,
+				  &conn->local_rx_ctrl.cons);
+	if (diff_cons) {
+		/* peer_rmbe_space is decreased during data transfer with RDMA
+		 * write
+		 */
+		smp_mb__before_atomic();
+		atomic_add(diff_cons, &conn->peer_rmbe_space);
+		/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
+		smp_mb__after_atomic();
+	}
+
+	diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
+				  &conn->local_rx_ctrl.prod);
+	if (diff_prod) {
+		if (conn->local_rx_ctrl.prod_flags.urg_data_present)
+			smc_cdc_handle_urg_data_arrival(smc, &diff_prod);
+		/* bytes_to_rcv is decreased in smc_recvmsg */
+		smp_mb__before_atomic();
+		atomic_add(diff_prod, &conn->bytes_to_rcv);
+		/* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
+		smp_mb__after_atomic();
+		smc->sk.sk_data_ready(&smc->sk);
+	} else {
+		if (conn->local_rx_ctrl.prod_flags.write_blocked ||
+		    conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
+		    conn->local_rx_ctrl.prod_flags.urg_data_pending) {
+			if (conn->local_rx_ctrl.prod_flags.urg_data_pending)
+				conn->urg_state = SMC_URG_NOTYET;
+			/* force immediate tx of current consumer cursor, but
+			 * under send_lock to guarantee arrival in seqno-order
+			 */
+			if (smc->sk.sk_state != SMC_INIT)
+				smc_tx_sndbuf_nonempty(conn);
+		}
+	}
+
+	/* piggy backed tx info */
+	/* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */
+	if (diff_cons && smc_tx_prepared_sends(conn)) {
+		smc_tx_sndbuf_nonempty(conn);
+		/* trigger socket release if connection closed */
+		smc_close_wake_tx_prepared(smc);
+	}
+	if (diff_cons && conn->urg_tx_pend &&
+	    atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) {
+		/* urg data confirmed by peer, indicate we're ready for more */
+		conn->urg_tx_pend = false;
+		smc->sk.sk_write_space(&smc->sk);
+	}
+
+	if (conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) {
+		smc->sk.sk_err = ECONNRESET;
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+	}
+	if (smc_cdc_rxed_any_close_or_senddone(conn)) {
+		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);
+		sock_hold(&smc->sk); /* sock_put in close_work */
+		if (!schedule_work(&conn->close_work))
+			sock_put(&smc->sk);
+	}
+}
+
+/* called under tasklet context */
+static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
+{
+	sock_hold(&smc->sk);
+	bh_lock_sock(&smc->sk);
+	smc_cdc_msg_recv_action(smc, cdc);
+	bh_unlock_sock(&smc->sk);
+	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)
+{
+	struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
+	struct smc_cdc_msg *cdc = buf;
+	struct smc_connection *conn;
+	struct smc_link_group *lgr;
+	struct smc_sock *smc;
+
+	if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved))
+		return; /* short message */
+	if (cdc->len != SMC_WR_TX_SIZE)
+		return; /* invalid message */
+
+	/* lookup connection */
+	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);
+	if (!conn)
+		return;
+	smc = container_of(conn, struct smc_sock, conn);
+
+	if (!cdc->prod_flags.failover_validation) {
+		if (smc_cdc_before(ntohs(cdc->seqno),
+				   conn->local_rx_ctrl.seqno))
+			/* received seqno is old */
+			return;
+	}
+	smc_cdc_msg_recv(smc, cdc);
+}
+
+static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = {
+	{
+		.handler	= smc_cdc_rx_handler,
+		.type		= SMC_CDC_MSG_TYPE
+	},
+	{
+		.handler	= NULL,
+	}
+};
+
+int __init smc_cdc_init(void)
+{
+	struct smc_wr_rx_handler *handler;
+	int rc = 0;
+
+	for (handler = smc_cdc_rx_handlers; handler->handler; handler++) {
+		INIT_HLIST_NODE(&handler->list);
+		rc = smc_wr_rx_register_handler(handler);
+		if (rc)
+			break;
+	}
+	return rc;
+}
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
new file mode 100644
index 000000000..34d2e1450
--- /dev/null
+++ b/net/smc/smc_cdc.h
@@ -0,0 +1,281 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Connection Data Control (CDC)
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_CDC_H
+#define SMC_CDC_H
+
+#include <linux/kernel.h> /* max_t */
+#include <linux/atomic.h>
+#include <linux/in.h>
+#include <linux/compiler.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_wr.h"
+
+#define	SMC_CDC_MSG_TYPE		0xFE
+
+/* in network byte order */
+union smc_cdc_cursor {		/* SMC cursor */
+	struct {
+		__be16	reserved;
+		__be16	wrap;
+		__be32	count;
+	};
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_t	acurs;		/* for atomic processing */
+#else
+	u64		acurs;		/* for atomic processing */
+#endif
+} __aligned(8);
+
+/* in network byte order */
+struct smc_cdc_msg {
+	struct smc_wr_rx_hdr		common; /* .type = 0xFE */
+	u8				len;	/* 44 */
+	__be16				seqno;
+	__be32				token;
+	union smc_cdc_cursor		prod;
+	union smc_cdc_cursor		cons;	/* piggy backed "ack" */
+	struct smc_cdc_producer_flags	prod_flags;
+	struct smc_cdc_conn_state_flags	conn_state_flags;
+	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 ||
+	       conn->local_rx_ctrl.conn_state_flags.peer_conn_closed;
+}
+
+static inline bool smc_cdc_rxed_any_close_or_senddone(
+	struct smc_connection *conn)
+{
+	return smc_cdc_rxed_any_close(conn) ||
+	       conn->local_rx_ctrl.conn_state_flags.peer_done_writing;
+}
+
+static inline void smc_curs_add(int size, union smc_host_cursor *curs,
+				int value)
+{
+	curs->count += value;
+	if (curs->count >= size) {
+		curs->wrap++;
+		curs->count -= size;
+	}
+}
+
+/* SMC cursors are 8 bytes long and require atomic reading and writing */
+static inline u64 smc_curs_read(union smc_host_cursor *curs,
+				struct smc_connection *conn)
+{
+#ifndef KERNEL_HAS_ATOMIC64
+	unsigned long flags;
+	u64 ret;
+
+	spin_lock_irqsave(&conn->acurs_lock, flags);
+	ret = curs->acurs;
+	spin_unlock_irqrestore(&conn->acurs_lock, flags);
+	return ret;
+#else
+	return atomic64_read(&curs->acurs);
+#endif
+}
+
+/* Copy cursor src into tgt */
+static inline void smc_curs_copy(union smc_host_cursor *tgt,
+				 union smc_host_cursor *src,
+				 struct smc_connection *conn)
+{
+#ifndef KERNEL_HAS_ATOMIC64
+	unsigned long flags;
+
+	spin_lock_irqsave(&conn->acurs_lock, flags);
+	tgt->acurs = src->acurs;
+	spin_unlock_irqrestore(&conn->acurs_lock, flags);
+#else
+	atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
+#endif
+}
+
+static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,
+				     union smc_cdc_cursor *src,
+				     struct smc_connection *conn)
+{
+#ifndef KERNEL_HAS_ATOMIC64
+	unsigned long flags;
+
+	spin_lock_irqsave(&conn->acurs_lock, flags);
+	tgt->acurs = src->acurs;
+	spin_unlock_irqrestore(&conn->acurs_lock, flags);
+#else
+	atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
+#endif
+}
+
+/* calculate cursor difference between old and new, where old <= new and
+ * difference cannot exceed size
+ */
+static inline int smc_curs_diff(unsigned int size,
+				union smc_host_cursor *old,
+				union smc_host_cursor *new)
+{
+	if (old->wrap != new->wrap)
+		return max_t(int, 0,
+			     ((size - old->count) + new->count));
+
+	return max_t(int, 0, (new->count - old->count));
+}
+
+/* calculate cursor difference between old and new - returns negative
+ * value in case old > new
+ */
+static inline int smc_curs_comp(unsigned int size,
+				union smc_host_cursor *old,
+				union smc_host_cursor *new)
+{
+	if (old->wrap > new->wrap ||
+	    (old->wrap == new->wrap && old->count > new->count))
+		return -smc_curs_diff(size, new, old);
+	return smc_curs_diff(size, old, new);
+}
+
+/* calculate cursor difference between old and new, where old <= new and
+ * difference may exceed size
+ */
+static inline int smc_curs_diff_large(unsigned int size,
+				      union smc_host_cursor *old,
+				      union smc_host_cursor *new)
+{
+	if (old->wrap < new->wrap)
+		return min_t(int,
+			     (size - old->count) + new->count +
+			     (new->wrap - old->wrap - 1) * size,
+			     size);
+
+	if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */
+		return min_t(int,
+			     (size - old->count) + new->count +
+			     (new->wrap + 0xffff - old->wrap) * size,
+			     size);
+
+	return max_t(int, 0, (new->count - old->count));
+}
+
+static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
+					  union smc_host_cursor *local,
+					  union smc_host_cursor *save,
+					  struct smc_connection *conn)
+{
+	smc_curs_copy(save, local, conn);
+	peer->count = htonl(save->count);
+	peer->wrap = htons(save->wrap);
+	/* peer->reserved = htons(0); must be ensured by caller */
+}
+
+static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer,
+				       struct smc_connection *conn,
+				       union smc_host_cursor *save)
+{
+	struct smc_host_cdc_msg *local = &conn->local_tx_ctrl;
+
+	peer->common.type = local->common.type;
+	peer->len = local->len;
+	peer->seqno = htons(local->seqno);
+	peer->token = htonl(local->token);
+	smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn);
+	smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn);
+	peer->prod_flags = local->prod_flags;
+	peer->conn_state_flags = local->conn_state_flags;
+}
+
+static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
+					  union smc_cdc_cursor *peer,
+					  struct smc_connection *conn)
+{
+	union smc_host_cursor temp, old;
+	union smc_cdc_cursor net;
+
+	smc_curs_copy(&old, local, conn);
+	smc_curs_copy_net(&net, peer, conn);
+	temp.count = ntohl(net.count);
+	temp.wrap = ntohs(net.wrap);
+	if ((old.wrap > temp.wrap) && temp.wrap)
+		return;
+	if ((old.wrap == temp.wrap) &&
+	    (old.count > temp.count))
+		return;
+	smc_curs_copy(local, &temp, 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;
+	local->seqno = ntohs(peer->seqno);
+	local->token = ntohl(peer->token);
+	smc_cdc_cursor_to_host(&local->prod, &peer->prod, conn);
+	smc_cdc_cursor_to_host(&local->cons, &peer->cons, conn);
+	local->prod_flags = peer->prod_flags;
+	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,
+			  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,
+		     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 */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
new file mode 100644
index 000000000..063acfbdc
--- /dev/null
+++ b/net/smc/smc_clc.c
@@ -0,0 +1,604 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  CLC (connection layer control) handshake over initial TCP socket to
+ *  prepare for RDMA traffic
+ *
+ *  Copyright IBM Corp. 2016, 2018
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/in.h>
+#include <linux/inetdevice.h>
+#include <linux/if_ether.h>
+#include <linux/sched/signal.h>
+
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_clc.h"
+#include "smc_ib.h"
+#include "smc_ism.h"
+
+#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
+#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
+
+/* eye catcher "SMCR" EBCDIC for CLC messages */
+static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
+/* eye catcher "SMCD" EBCDIC for CLC messages */
+static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
+
+/* check if received message has a correct header length and contains valid
+ * heading and trailing eyecatchers
+ */
+static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm)
+{
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_msg_proposal *pclc;
+	struct smc_clc_msg_decline *dclc;
+	struct smc_clc_msg_trail *trl;
+
+	if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+	    memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
+		return false;
+	switch (clcm->type) {
+	case SMC_CLC_PROPOSAL:
+		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+		    clcm->path != SMC_TYPE_B)
+			return false;
+		pclc = (struct smc_clc_msg_proposal *)clcm;
+		pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+		if (ntohs(pclc->hdr.length) !=
+			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
+			sizeof(*pclc_prfx) +
+			pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) +
+			sizeof(*trl))
+			return false;
+		trl = (struct smc_clc_msg_trail *)
+			((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl));
+		break;
+	case SMC_CLC_ACCEPT:
+	case SMC_CLC_CONFIRM:
+		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
+			return false;
+		clc = (struct smc_clc_msg_accept_confirm *)clcm;
+		if ((clcm->path == SMC_TYPE_R &&
+		     ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
+		    (clcm->path == SMC_TYPE_D &&
+		     ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
+			return false;
+		trl = (struct smc_clc_msg_trail *)
+			((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
+		break;
+	case SMC_CLC_DECLINE:
+		dclc = (struct smc_clc_msg_decline *)clcm;
+		if (ntohs(dclc->hdr.length) != sizeof(*dclc))
+			return false;
+		trl = &dclc->trl;
+		break;
+	default:
+		return false;
+	}
+	if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+	    memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
+		return false;
+	return true;
+}
+
+/* find ipv4 addr on device and get the prefix len, fill CLC proposal msg */
+static int smc_clc_prfx_set4_rcu(struct dst_entry *dst, __be32 ipv4,
+				 struct smc_clc_msg_proposal_prefix *prop)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dst->dev);
+
+	if (!in_dev)
+		return -ENODEV;
+	for_ifa(in_dev) {
+		if (!inet_ifa_match(ipv4, ifa))
+			continue;
+		prop->prefix_len = inet_mask_len(ifa->ifa_mask);
+		prop->outgoing_subnet = ifa->ifa_address & ifa->ifa_mask;
+		/* prop->ipv6_prefixes_cnt = 0; already done by memset before */
+		return 0;
+	} endfor_ifa(in_dev);
+	return -ENOENT;
+}
+
+/* fill CLC proposal msg with ipv6 prefixes from device */
+static int smc_clc_prfx_set6_rcu(struct dst_entry *dst,
+				 struct smc_clc_msg_proposal_prefix *prop,
+				 struct smc_clc_ipv6_prefix *ipv6_prfx)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_dev *in6_dev = __in6_dev_get(dst->dev);
+	struct inet6_ifaddr *ifa;
+	int cnt = 0;
+
+	if (!in6_dev)
+		return -ENODEV;
+	/* use a maximum of 8 IPv6 prefixes from device */
+	list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
+		if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)
+			continue;
+		ipv6_addr_prefix(&ipv6_prfx[cnt].prefix,
+				 &ifa->addr, ifa->prefix_len);
+		ipv6_prfx[cnt].prefix_len = ifa->prefix_len;
+		cnt++;
+		if (cnt == SMC_CLC_MAX_V6_PREFIX)
+			break;
+	}
+	prop->ipv6_prefixes_cnt = cnt;
+	if (cnt)
+		return 0;
+#endif
+	return -ENOENT;
+}
+
+/* retrieve and set prefixes in CLC proposal msg */
+static int smc_clc_prfx_set(struct socket *clcsock,
+			    struct smc_clc_msg_proposal_prefix *prop,
+			    struct smc_clc_ipv6_prefix *ipv6_prfx)
+{
+	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct sockaddr_storage addrs;
+	struct sockaddr_in6 *addr6;
+	struct sockaddr_in *addr;
+	int rc = -ENOENT;
+
+	memset(prop, 0, sizeof(*prop));
+	if (!dst) {
+		rc = -ENOTCONN;
+		goto out;
+	}
+	if (!dst->dev) {
+		rc = -ENODEV;
+		goto out_rel;
+	}
+	/* get address to which the internal TCP socket is bound */
+	if (kernel_getsockname(clcsock, (struct sockaddr *)&addrs) < 0)
+		goto out_rel;
+	/* analyze IP specific data of net_device belonging to TCP socket */
+	addr6 = (struct sockaddr_in6 *)&addrs;
+	rcu_read_lock();
+	if (addrs.ss_family == PF_INET) {
+		/* IPv4 */
+		addr = (struct sockaddr_in *)&addrs;
+		rc = smc_clc_prfx_set4_rcu(dst, addr->sin_addr.s_addr, prop);
+	} else if (ipv6_addr_v4mapped(&addr6->sin6_addr)) {
+		/* mapped IPv4 address - peer is IPv4 only */
+		rc = smc_clc_prfx_set4_rcu(dst, addr6->sin6_addr.s6_addr32[3],
+					   prop);
+	} else {
+		/* IPv6 */
+		rc = smc_clc_prfx_set6_rcu(dst, prop, ipv6_prfx);
+	}
+	rcu_read_unlock();
+out_rel:
+	dst_release(dst);
+out:
+	return rc;
+}
+
+/* match ipv4 addrs of dev against addr in CLC proposal */
+static int smc_clc_prfx_match4_rcu(struct net_device *dev,
+				   struct smc_clc_msg_proposal_prefix *prop)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+	if (!in_dev)
+		return -ENODEV;
+	for_ifa(in_dev) {
+		if (prop->prefix_len == inet_mask_len(ifa->ifa_mask) &&
+		    inet_ifa_match(prop->outgoing_subnet, ifa))
+			return 0;
+	} endfor_ifa(in_dev);
+
+	return -ENOENT;
+}
+
+/* match ipv6 addrs of dev against addrs in CLC proposal */
+static int smc_clc_prfx_match6_rcu(struct net_device *dev,
+				   struct smc_clc_msg_proposal_prefix *prop)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_dev *in6_dev = __in6_dev_get(dev);
+	struct smc_clc_ipv6_prefix *ipv6_prfx;
+	struct inet6_ifaddr *ifa;
+	int i, max;
+
+	if (!in6_dev)
+		return -ENODEV;
+	/* ipv6 prefix list starts behind smc_clc_msg_proposal_prefix */
+	ipv6_prfx = (struct smc_clc_ipv6_prefix *)((u8 *)prop + sizeof(*prop));
+	max = min_t(u8, prop->ipv6_prefixes_cnt, SMC_CLC_MAX_V6_PREFIX);
+	list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
+		if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)
+			continue;
+		for (i = 0; i < max; i++) {
+			if (ifa->prefix_len == ipv6_prfx[i].prefix_len &&
+			    ipv6_prefix_equal(&ifa->addr, &ipv6_prfx[i].prefix,
+					      ifa->prefix_len))
+				return 0;
+		}
+	}
+#endif
+	return -ENOENT;
+}
+
+/* check if proposed prefixes match one of our device prefixes */
+int smc_clc_prfx_match(struct socket *clcsock,
+		       struct smc_clc_msg_proposal_prefix *prop)
+{
+	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	int rc;
+
+	if (!dst) {
+		rc = -ENOTCONN;
+		goto out;
+	}
+	if (!dst->dev) {
+		rc = -ENODEV;
+		goto out_rel;
+	}
+	rcu_read_lock();
+	if (!prop->ipv6_prefixes_cnt)
+		rc = smc_clc_prfx_match4_rcu(dst->dev, prop);
+	else
+		rc = smc_clc_prfx_match6_rcu(dst->dev, prop);
+	rcu_read_unlock();
+out_rel:
+	dst_release(dst);
+out:
+	return rc;
+}
+
+/* Wait for data on the tcp-socket, analyze received data
+ * Returns:
+ * 0 if success and it was not a decline that we received.
+ * SMC_CLC_DECL_REPLY if decline received for fallback w/o another decl send.
+ * clcsock error, -EINTR, -ECONNRESET, -EPROTO otherwise.
+ */
+int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
+		     u8 expected_type)
+{
+	long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
+	struct sock *clc_sk = smc->clcsock->sk;
+	struct smc_clc_msg_hdr *clcm = buf;
+	struct msghdr msg = {NULL, 0};
+	int reason_code = 0;
+	struct kvec vec = {buf, buflen};
+	int len, datlen;
+	int krflags;
+
+	/* peek the first few bytes to determine length of data to receive
+	 * so we don't consume any subsequent CLC message or payload data
+	 * in the TCP byte stream
+	 */
+	/*
+	 * Caller must make sure that buflen is no less than
+	 * sizeof(struct smc_clc_msg_hdr)
+	 */
+	krflags = MSG_PEEK | MSG_WAITALL;
+	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1,
+			sizeof(struct smc_clc_msg_hdr));
+	len = sock_recvmsg(smc->clcsock, &msg, krflags);
+	if (signal_pending(current)) {
+		reason_code = -EINTR;
+		clc_sk->sk_err = EINTR;
+		smc->sk.sk_err = EINTR;
+		goto out;
+	}
+	if (clc_sk->sk_err) {
+		reason_code = -clc_sk->sk_err;
+		smc->sk.sk_err = clc_sk->sk_err;
+		goto out;
+	}
+	if (!len) { /* peer has performed orderly shutdown */
+		smc->sk.sk_err = ECONNRESET;
+		reason_code = -ECONNRESET;
+		goto out;
+	}
+	if (len < 0) {
+		smc->sk.sk_err = -len;
+		reason_code = len;
+		goto out;
+	}
+	datlen = ntohs(clcm->length);
+	if ((len < sizeof(struct smc_clc_msg_hdr)) ||
+	    (datlen > buflen) ||
+	    (clcm->version != SMC_CLC_V1) ||
+	    (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+	     clcm->path != SMC_TYPE_B) ||
+	    ((clcm->type != SMC_CLC_DECLINE) &&
+	     (clcm->type != expected_type))) {
+		smc->sk.sk_err = EPROTO;
+		reason_code = -EPROTO;
+		goto out;
+	}
+
+	/* receive the complete CLC message */
+	memset(&msg, 0, sizeof(struct msghdr));
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
+	krflags = MSG_WAITALL;
+	len = sock_recvmsg(smc->clcsock, &msg, krflags);
+	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
+		smc->sk.sk_err = EPROTO;
+		reason_code = -EPROTO;
+		goto out;
+	}
+	if (clcm->type == SMC_CLC_DECLINE) {
+		struct smc_clc_msg_decline *dclc;
+
+		dclc = (struct smc_clc_msg_decline *)clcm;
+		reason_code = SMC_CLC_DECL_PEERDECL;
+		smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
+		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
+			smc->conn.lgr->sync_err = 1;
+			smc_lgr_terminate(smc->conn.lgr);
+		}
+	}
+
+out:
+	smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
+	return reason_code;
+}
+
+/* send CLC DECLINE message across internal TCP socket */
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
+{
+	struct smc_clc_msg_decline dclc;
+	struct msghdr msg;
+	struct kvec vec;
+	int len;
+
+	memset(&dclc, 0, sizeof(dclc));
+	memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	dclc.hdr.type = SMC_CLC_DECLINE;
+	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
+	dclc.hdr.version = SMC_CLC_V1;
+	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
+	if (smc->conn.lgr && !smc->conn.lgr->is_smcd)
+		memcpy(dclc.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+	dclc.peer_diagnosis = htonl(peer_diag_info);
+	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &dclc;
+	vec.iov_len = sizeof(struct smc_clc_msg_decline);
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+			     sizeof(struct smc_clc_msg_decline));
+	if (len < sizeof(struct smc_clc_msg_decline))
+		smc->sk.sk_err = EPROTO;
+	if (len < 0)
+		smc->sk.sk_err = -len;
+	return sock_error(&smc->sk);
+}
+
+/* send CLC PROPOSAL message across internal TCP socket */
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+			  struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
+			  struct smcd_dev *ismdev)
+{
+	struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
+	struct smc_clc_msg_proposal_prefix pclc_prfx;
+	struct smc_clc_msg_smcd pclc_smcd;
+	struct smc_clc_msg_proposal pclc;
+	struct smc_clc_msg_trail trl;
+	int len, i, plen, rc;
+	int reason_code = 0;
+	struct kvec vec[5];
+	struct msghdr msg;
+
+	/* retrieve ip prefixes for CLC proposal msg */
+	rc = smc_clc_prfx_set(smc->clcsock, &pclc_prfx, ipv6_prfx);
+	if (rc)
+		return SMC_CLC_DECL_CNFERR; /* configuration error */
+
+	/* send SMC Proposal CLC message */
+	plen = sizeof(pclc) + sizeof(pclc_prfx) +
+	       (pclc_prfx.ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) +
+	       sizeof(trl);
+	memset(&pclc, 0, sizeof(pclc));
+	memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	pclc.hdr.type = SMC_CLC_PROPOSAL;
+	pclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	pclc.hdr.path = smc_type;
+	if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
+		/* add SMC-R specifics */
+		memcpy(pclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
+		memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+		pclc.iparea_offset = htons(0);
+	}
+	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+		/* add SMC-D specifics */
+		memset(&pclc_smcd, 0, sizeof(pclc_smcd));
+		plen += sizeof(pclc_smcd);
+		pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
+		pclc_smcd.gid = ismdev->local_gid;
+	}
+	pclc.hdr.length = htons(plen);
+
+	memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	memset(&msg, 0, sizeof(msg));
+	i = 0;
+	vec[i].iov_base = &pclc;
+	vec[i++].iov_len = sizeof(pclc);
+	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+		vec[i].iov_base = &pclc_smcd;
+		vec[i++].iov_len = sizeof(pclc_smcd);
+	}
+	vec[i].iov_base = &pclc_prfx;
+	vec[i++].iov_len = sizeof(pclc_prfx);
+	if (pclc_prfx.ipv6_prefixes_cnt > 0) {
+		vec[i].iov_base = &ipv6_prfx[0];
+		vec[i++].iov_len = pclc_prfx.ipv6_prefixes_cnt *
+				   sizeof(ipv6_prfx[0]);
+	}
+	vec[i].iov_base = &trl;
+	vec[i++].iov_len = sizeof(trl);
+	/* due to the few bytes needed for clc-handshake this cannot block */
+	len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen);
+	if (len < 0) {
+		smc->sk.sk_err = smc->clcsock->sk->sk_err;
+		reason_code = -smc->sk.sk_err;
+	} else if (len < (int)sizeof(pclc)) {
+		reason_code = -ENETUNREACH;
+		smc->sk.sk_err = -reason_code;
+	}
+
+	return reason_code;
+}
+
+/* send CLC CONFIRM message across internal TCP socket */
+int smc_clc_send_confirm(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct smc_clc_msg_accept_confirm cclc;
+	struct smc_link *link;
+	int reason_code = 0;
+	struct msghdr msg;
+	struct kvec vec;
+	int len;
+
+	/* send SMC Confirm CLC msg */
+	memset(&cclc, 0, sizeof(cclc));
+	cclc.hdr.type = SMC_CLC_CONFIRM;
+	cclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	if (smc->conn.lgr->is_smcd) {
+		/* SMC-D specific settings */
+		memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+		cclc.hdr.path = SMC_TYPE_D;
+		cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		cclc.gid = conn->lgr->smcd->local_gid;
+		cclc.token = conn->rmb_desc->token;
+		cclc.dmbe_size = conn->rmbe_size_short;
+		cclc.dmbe_idx = 0;
+		memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+		memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+	} else {
+		/* SMC-R specific settings */
+		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+		memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+		cclc.hdr.path = SMC_TYPE_R;
+		cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(cclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE);
+		memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+		       ETH_ALEN);
+		hton24(cclc.qpn, link->roce_qp->qp_num);
+		cclc.rmb_rkey =
+			htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+		cclc.rmbe_alert_token = htonl(conn->alert_token_local);
+		cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
+		cclc.rmbe_size = conn->rmbe_size_short;
+		cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+				(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+		hton24(cclc.psn, link->psn_initial);
+		memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &cclc;
+	vec.iov_len = ntohs(cclc.hdr.length);
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+			     ntohs(cclc.hdr.length));
+	if (len < ntohs(cclc.hdr.length)) {
+		if (len >= 0) {
+			reason_code = -ENETUNREACH;
+			smc->sk.sk_err = -reason_code;
+		} else {
+			smc->sk.sk_err = smc->clcsock->sk->sk_err;
+			reason_code = -smc->sk.sk_err;
+		}
+	}
+	return reason_code;
+}
+
+/* send CLC ACCEPT message across internal TCP socket */
+int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
+{
+	struct smc_connection *conn = &new_smc->conn;
+	struct smc_clc_msg_accept_confirm aclc;
+	struct smc_link *link;
+	struct msghdr msg;
+	struct kvec vec;
+	int rc = 0;
+	int len;
+
+	memset(&aclc, 0, sizeof(aclc));
+	aclc.hdr.type = SMC_CLC_ACCEPT;
+	aclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	if (srv_first_contact)
+		aclc.hdr.flag = 1;
+
+	if (new_smc->conn.lgr->is_smcd) {
+		/* SMC-D specific settings */
+		aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+		aclc.hdr.path = SMC_TYPE_D;
+		aclc.gid = conn->lgr->smcd->local_gid;
+		aclc.token = conn->rmb_desc->token;
+		aclc.dmbe_size = conn->rmbe_size_short;
+		aclc.dmbe_idx = 0;
+		memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+		memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+	} else {
+		/* SMC-R specific settings */
+		aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+		aclc.hdr.path = SMC_TYPE_R;
+		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+		memcpy(aclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE);
+		memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
+		       ETH_ALEN);
+		hton24(aclc.qpn, link->roce_qp->qp_num);
+		aclc.rmb_rkey =
+			htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		aclc.rmbe_idx = 1;		/* as long as 1 RMB = 1 RMBE */
+		aclc.rmbe_alert_token = htonl(conn->alert_token_local);
+		aclc.qp_mtu = link->path_mtu;
+		aclc.rmbe_size = conn->rmbe_size_short,
+		aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+				(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+		hton24(aclc.psn, link->psn_initial);
+		memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &aclc;
+	vec.iov_len = ntohs(aclc.hdr.length);
+	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
+			     ntohs(aclc.hdr.length));
+	if (len < ntohs(aclc.hdr.length)) {
+		if (len >= 0)
+			new_smc->sk.sk_err = EPROTO;
+		else
+			new_smc->sk.sk_err = new_smc->clcsock->sk->sk_err;
+		rc = sock_error(&new_smc->sk);
+	}
+
+	return rc;
+}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
new file mode 100644
index 000000000..18da89b68
--- /dev/null
+++ b/net/smc/smc_clc.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  CLC (connection layer control) handshake over initial TCP socket to
+ *  prepare for RDMA traffic
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_CLC_H
+#define _SMC_CLC_H
+
+#include <rdma/ib_verbs.h>
+
+#include "smc.h"
+
+#define SMC_CLC_PROPOSAL	0x01
+#define SMC_CLC_ACCEPT		0x02
+#define SMC_CLC_CONFIRM		0x03
+#define SMC_CLC_DECLINE		0x04
+
+#define SMC_CLC_V1		0x1		/* SMC version                */
+#define SMC_TYPE_R		0		/* SMC-R only		      */
+#define SMC_TYPE_D		1		/* SMC-D only		      */
+#define SMC_TYPE_B		3		/* SMC-R and SMC-D	      */
+#define CLC_WAIT_TIME		(6 * HZ)	/* max. wait time on clcsock  */
+#define SMC_CLC_DECL_MEM	0x01010000  /* insufficient memory resources  */
+#define SMC_CLC_DECL_TIMEOUT_CL	0x02010000  /* timeout w4 QP confirm link     */
+#define SMC_CLC_DECL_TIMEOUT_AL	0x02020000  /* timeout w4 QP add link	      */
+#define SMC_CLC_DECL_CNFERR	0x03000000  /* configuration error            */
+#define SMC_CLC_DECL_PEERNOSMC	0x03010000  /* peer did not indicate SMC      */
+#define SMC_CLC_DECL_IPSEC	0x03020000  /* IPsec usage		      */
+#define SMC_CLC_DECL_NOSMCDEV	0x03030000  /* no SMC device found	      */
+#define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
+#define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
+#define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
+#define SMC_CLC_DECL_SYNCERR	0x04000000  /* synchronization error          */
+#define SMC_CLC_DECL_PEERDECL	0x05000000  /* peer declined during handshake */
+#define SMC_CLC_DECL_INTERR	0x99990000  /* internal error                 */
+#define SMC_CLC_DECL_ERR_RTOK	0x99990001  /*	 rtoken handling failed       */
+#define SMC_CLC_DECL_ERR_RDYLNK	0x99990002  /*	 ib ready link failed	      */
+#define SMC_CLC_DECL_ERR_REGRMB	0x99990003  /*	 reg rmb failed		      */
+
+struct smc_clc_msg_hdr {	/* header1 of clc messages */
+	u8 eyecatcher[4];	/* eye catcher */
+	u8 type;		/* proposal / accept / confirm / decline */
+	__be16 length;
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 version : 4,
+	   flag    : 1,
+	   rsvd	   : 1,
+	   path	   : 2;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 path    : 2,
+	   rsvd    : 1,
+	   flag    : 1,
+	   version : 4;
+#endif
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_clc_msg_trail {	/* trailer of clc messages */
+	u8 eyecatcher[4];
+};
+
+struct smc_clc_msg_local {	/* header2 of clc messages */
+	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* unique system id */
+	u8 gid[16];		/* gid of ib_device port */
+	u8 mac[6];		/* mac of ib_device port */
+};
+
+#define SMC_CLC_MAX_V6_PREFIX	8
+
+/* Struct would be 4 byte aligned, but it is used in an array that is sent
+ * to peers and must conform to RFC7609, hence we need to use packed here.
+ */
+struct smc_clc_ipv6_prefix {
+	struct in6_addr prefix;
+	u8 prefix_len;
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
+	__be32 outgoing_subnet;	/* subnet mask */
+	u8 prefix_len;		/* number of significant bits in mask */
+	u8 reserved[2];
+	u8 ipv6_prefixes_cnt;	/* number of IPv6 prefixes in prefix array */
+} __aligned(4);
+
+struct smc_clc_msg_smcd {	/* SMC-D GID information */
+	u64 gid;		/* ISM GID of requestor */
+	u8 res[32];
+};
+
+struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
+	struct smc_clc_msg_hdr hdr;
+	struct smc_clc_msg_local lcl;
+	__be16 iparea_offset;	/* offset to IP address information area */
+} __aligned(4);
+
+#define SMC_CLC_PROPOSAL_MAX_OFFSET	0x28
+#define SMC_CLC_PROPOSAL_MAX_PREFIX	(SMC_CLC_MAX_V6_PREFIX * \
+					 sizeof(struct smc_clc_ipv6_prefix))
+#define SMC_CLC_MAX_LEN		(sizeof(struct smc_clc_msg_proposal) + \
+				 SMC_CLC_PROPOSAL_MAX_OFFSET + \
+				 sizeof(struct smc_clc_msg_proposal_prefix) + \
+				 SMC_CLC_PROPOSAL_MAX_PREFIX + \
+				 sizeof(struct smc_clc_msg_trail))
+
+struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
+	struct smc_clc_msg_hdr hdr;
+	union {
+		struct { /* SMC-R */
+			struct smc_clc_msg_local lcl;
+			u8 qpn[3];		/* QP number */
+			__be32 rmb_rkey;	/* RMB rkey */
+			u8 rmbe_idx;		/* Index of RMBE in RMB */
+			__be32 rmbe_alert_token;/* unique connection id */
+#if defined(__BIG_ENDIAN_BITFIELD)
+			u8 rmbe_size : 4,	/* buf size (compressed) */
+			   qp_mtu   : 4;	/* QP mtu */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+			u8 qp_mtu   : 4,
+			   rmbe_size : 4;
+#endif
+			u8 reserved;
+			__be64 rmb_dma_addr;	/* RMB virtual address */
+			u8 reserved2;
+			u8 psn[3];		/* packet sequence number */
+			struct smc_clc_msg_trail smcr_trl;
+						/* eye catcher "SMCR" EBCDIC */
+		} __packed;
+		struct { /* SMC-D */
+			u64 gid;		/* Sender GID */
+			u64 token;		/* DMB token */
+			u8 dmbe_idx;		/* DMBE index */
+#if defined(__BIG_ENDIAN_BITFIELD)
+			u8 dmbe_size : 4,	/* buf size (compressed) */
+			   reserved3 : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+			u8 reserved3 : 4,
+			   dmbe_size : 4;
+#endif
+			u16 reserved4;
+			u32 linkid;		/* Link identifier */
+			u32 reserved5[3];
+			struct smc_clc_msg_trail smcd_trl;
+						/* eye catcher "SMCD" EBCDIC */
+		} __packed;
+	};
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_clc_msg_decline {	/* clc decline message */
+	struct smc_clc_msg_hdr hdr;
+	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */
+	__be32 peer_diagnosis;	/* diagnosis information */
+	u8 reserved2[4];
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+} __aligned(4);
+
+/* determine start of the prefix area within the proposal message */
+static inline struct smc_clc_msg_proposal_prefix *
+smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
+{
+	return (struct smc_clc_msg_proposal_prefix *)
+	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
+}
+
+/* get SMC-D info from proposal message */
+static inline struct smc_clc_msg_smcd *
+smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
+{
+	if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
+		return NULL;
+
+	return (struct smc_clc_msg_smcd *)(prop + 1);
+}
+
+struct smcd_dev;
+
+int smc_clc_prfx_match(struct socket *clcsock,
+		       struct smc_clc_msg_proposal_prefix *prop);
+int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
+		     u8 expected_type);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+			  struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
+			  struct smcd_dev *ismdev);
+int smc_clc_send_confirm(struct smc_sock *smc);
+int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
+
+#endif
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
new file mode 100644
index 000000000..092696d73
--- /dev/null
+++ b/net/smc/smc_close.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Socket Closing - normal and abnormal
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/workqueue.h>
+#include <linux/sched/signal.h>
+
+#include <net/sock.h>
+
+#include "smc.h"
+#include "smc_tx.h"
+#include "smc_cdc.h"
+#include "smc_close.h"
+
+#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME	(5 * HZ)
+
+static void smc_close_cleanup_listen(struct sock *parent)
+{
+	struct sock *sk;
+
+	/* Close non-accepted connections */
+	while ((sk = smc_accept_dequeue(parent, NULL)))
+		smc_close_non_accepted(sk);
+}
+
+/* wait for sndbuf data being transmitted */
+static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	struct sock *sk = &smc->sk;
+
+	if (!timeout)
+		return;
+
+	if (!smc_tx_prepared_sends(&smc->conn))
+		return;
+
+	smc->wait_close_tx_prepared = 1;
+	add_wait_queue(sk_sleep(sk), &wait);
+	while (!signal_pending(current) && timeout) {
+		int rc;
+
+		rc = sk_wait_event(sk, &timeout,
+				   !smc_tx_prepared_sends(&smc->conn) ||
+				   (sk->sk_err == ECONNABORTED) ||
+				   (sk->sk_err == ECONNRESET),
+				   &wait);
+		if (rc)
+			break;
+	}
+	remove_wait_queue(sk_sleep(sk), &wait);
+	smc->wait_close_tx_prepared = 0;
+}
+
+void smc_close_wake_tx_prepared(struct smc_sock *smc)
+{
+	if (smc->wait_close_tx_prepared)
+		/* wake up socket closing */
+		smc->sk.sk_state_change(&smc->sk);
+}
+
+static int smc_close_wr(struct smc_connection *conn)
+{
+	conn->local_tx_ctrl.conn_state_flags.peer_done_writing = 1;
+
+	return smc_cdc_get_slot_and_msg_send(conn);
+}
+
+static int smc_close_final(struct smc_connection *conn)
+{
+	if (atomic_read(&conn->bytes_to_rcv))
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+	else
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_closed = 1;
+
+	return smc_cdc_get_slot_and_msg_send(conn);
+}
+
+static int smc_close_abort(struct smc_connection *conn)
+{
+	conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+
+	return smc_cdc_get_slot_and_msg_send(conn);
+}
+
+/* terminate smc socket abnormally - active abort
+ * link group is terminated, i.e. RDMA communication no longer possible
+ */
+static void smc_close_active_abort(struct smc_sock *smc)
+{
+	struct sock *sk = &smc->sk;
+
+	struct smc_cdc_conn_state_flags *txflags =
+		&smc->conn.local_tx_ctrl.conn_state_flags;
+
+	if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) {
+		sk->sk_err = ECONNABORTED;
+		if (smc->clcsock && smc->clcsock->sk) {
+			smc->clcsock->sk->sk_err = ECONNABORTED;
+			smc->clcsock->sk->sk_state_change(smc->clcsock->sk);
+		}
+	}
+	switch (sk->sk_state) {
+	case SMC_ACTIVE:
+		sk->sk_state = SMC_PEERABORTWAIT;
+		release_sock(sk);
+		cancel_delayed_work_sync(&smc->conn.tx_work);
+		lock_sock(sk);
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_APPCLOSEWAIT1:
+	case SMC_APPCLOSEWAIT2:
+		if (!smc_cdc_rxed_any_close(&smc->conn))
+			sk->sk_state = SMC_PEERABORTWAIT;
+		else
+			sk->sk_state = SMC_CLOSED;
+		release_sock(sk);
+		cancel_delayed_work_sync(&smc->conn.tx_work);
+		lock_sock(sk);
+		break;
+	case SMC_PEERCLOSEWAIT1:
+	case SMC_PEERCLOSEWAIT2:
+		if (!txflags->peer_conn_closed) {
+			/* just SHUTDOWN_SEND done */
+			sk->sk_state = SMC_PEERABORTWAIT;
+		} else {
+			sk->sk_state = SMC_CLOSED;
+		}
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_PROCESSABORT:
+	case SMC_APPFINCLOSEWAIT:
+		sk->sk_state = SMC_CLOSED;
+		break;
+	case SMC_PEERFINCLOSEWAIT:
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_INIT:
+	case SMC_PEERABORTWAIT:
+	case SMC_CLOSED:
+		break;
+	}
+
+	sock_set_flag(sk, SOCK_DEAD);
+	sk->sk_state_change(sk);
+}
+
+static inline bool smc_close_sent_any_close(struct smc_connection *conn)
+{
+	return conn->local_tx_ctrl.conn_state_flags.peer_conn_abort ||
+	       conn->local_tx_ctrl.conn_state_flags.peer_conn_closed;
+}
+
+int smc_close_active(struct smc_sock *smc)
+{
+	struct smc_cdc_conn_state_flags *txflags =
+		&smc->conn.local_tx_ctrl.conn_state_flags;
+	struct smc_connection *conn = &smc->conn;
+	struct sock *sk = &smc->sk;
+	int old_state;
+	long timeout;
+	int rc = 0;
+	int rc1 = 0;
+
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
+
+	old_state = sk->sk_state;
+again:
+	switch (sk->sk_state) {
+	case SMC_INIT:
+		sk->sk_state = SMC_CLOSED;
+		break;
+	case SMC_LISTEN:
+		sk->sk_state = SMC_CLOSED;
+		sk->sk_state_change(sk); /* wake up accept */
+		if (smc->clcsock && smc->clcsock->sk) {
+			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+			/* wake up kernel_accept of smc_tcp_listen_worker */
+			smc->clcsock->sk->sk_data_ready(smc->clcsock->sk);
+		}
+		smc_close_cleanup_listen(sk);
+		release_sock(sk);
+		flush_work(&smc->tcp_listen_work);
+		lock_sock(sk);
+		break;
+	case SMC_ACTIVE:
+		smc_close_stream_wait(smc, timeout);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
+		if (sk->sk_state == SMC_ACTIVE) {
+			/* send close request */
+			rc = smc_close_final(conn);
+			if (rc)
+				break;
+			sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+			/* actively shutdown clcsock before peer close it,
+			 * prevent peer from entering TIME_WAIT state.
+			 */
+			if (smc->clcsock && smc->clcsock->sk) {
+				rc1 = kernel_sock_shutdown(smc->clcsock,
+							   SHUT_RDWR);
+				rc = rc ? rc : rc1;
+			}
+		} else {
+			/* peer event has changed the state */
+			goto again;
+		}
+		break;
+	case SMC_APPFINCLOSEWAIT:
+		/* socket already shutdown wr or both (active close) */
+		if (txflags->peer_done_writing &&
+		    !smc_close_sent_any_close(conn)) {
+			/* just shutdown wr done, send close request */
+			rc = smc_close_final(conn);
+			if (rc)
+				break;
+		}
+		sk->sk_state = SMC_CLOSED;
+		break;
+	case SMC_APPCLOSEWAIT1:
+	case SMC_APPCLOSEWAIT2:
+		if (!smc_cdc_rxed_any_close(conn))
+			smc_close_stream_wait(smc, timeout);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
+		if (sk->sk_state != SMC_APPCLOSEWAIT1 &&
+		    sk->sk_state != SMC_APPCLOSEWAIT2)
+			goto again;
+		/* confirm close from peer */
+		rc = smc_close_final(conn);
+		if (rc)
+			break;
+		if (smc_cdc_rxed_any_close(conn)) {
+			/* peer has closed the socket already */
+			sk->sk_state = SMC_CLOSED;
+			sock_put(sk); /* postponed passive closing */
+		} else {
+			/* peer has just issued a shutdown write */
+			sk->sk_state = SMC_PEERFINCLOSEWAIT;
+		}
+		break;
+	case SMC_PEERCLOSEWAIT1:
+	case SMC_PEERCLOSEWAIT2:
+		if (txflags->peer_done_writing &&
+		    !smc_close_sent_any_close(conn)) {
+			/* just shutdown wr done, send close request */
+			rc = smc_close_final(conn);
+			if (rc)
+				break;
+		}
+		/* peer sending PeerConnectionClosed will cause transition */
+		break;
+	case SMC_PEERFINCLOSEWAIT:
+		/* peer sending PeerConnectionClosed will cause transition */
+		break;
+	case SMC_PROCESSABORT:
+		smc_close_abort(conn);
+		sk->sk_state = SMC_CLOSED;
+		break;
+	case SMC_PEERABORTWAIT:
+	case SMC_CLOSED:
+		/* nothing to do, add tracing in future patch */
+		break;
+	}
+
+	if (old_state != sk->sk_state)
+		sk->sk_state_change(sk);
+	return rc;
+}
+
+static void smc_close_passive_abort_received(struct smc_sock *smc)
+{
+	struct smc_cdc_conn_state_flags *txflags =
+		&smc->conn.local_tx_ctrl.conn_state_flags;
+	struct sock *sk = &smc->sk;
+
+	switch (sk->sk_state) {
+	case SMC_INIT:
+	case SMC_ACTIVE:
+	case SMC_APPCLOSEWAIT1:
+		sk->sk_state = SMC_PROCESSABORT;
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_APPFINCLOSEWAIT:
+		sk->sk_state = SMC_PROCESSABORT;
+		break;
+	case SMC_PEERCLOSEWAIT1:
+	case SMC_PEERCLOSEWAIT2:
+		if (txflags->peer_done_writing &&
+		    !smc_close_sent_any_close(&smc->conn))
+			/* just shutdown, but not yet closed locally */
+			sk->sk_state = SMC_PROCESSABORT;
+		else
+			sk->sk_state = SMC_CLOSED;
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_APPCLOSEWAIT2:
+	case SMC_PEERFINCLOSEWAIT:
+		sk->sk_state = SMC_CLOSED;
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_PEERABORTWAIT:
+		sk->sk_state = SMC_CLOSED;
+		break;
+	case SMC_PROCESSABORT:
+	/* nothing to do, add tracing in future patch */
+		break;
+	}
+}
+
+/* Either some kind of closing has been received: peer_conn_closed,
+ * peer_conn_abort, or peer_done_writing
+ * or the link group of the connection terminates abnormally.
+ */
+static void smc_close_passive_work(struct work_struct *work)
+{
+	struct smc_connection *conn = container_of(work,
+						   struct smc_connection,
+						   close_work);
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	struct smc_cdc_conn_state_flags *rxflags;
+	struct sock *sk = &smc->sk;
+	int old_state;
+
+	lock_sock(sk);
+	old_state = sk->sk_state;
+
+	if (!conn->alert_token_local) {
+		/* abnormal termination */
+		smc_close_active_abort(smc);
+		goto wakeup;
+	}
+
+	rxflags = &conn->local_rx_ctrl.conn_state_flags;
+	if (rxflags->peer_conn_abort) {
+		/* peer has not received all data */
+		smc_close_passive_abort_received(smc);
+		release_sock(&smc->sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(&smc->sk);
+		goto wakeup;
+	}
+
+	switch (sk->sk_state) {
+	case SMC_INIT:
+		if (atomic_read(&conn->bytes_to_rcv) ||
+		    (rxflags->peer_done_writing &&
+		     !smc_cdc_rxed_any_close(conn))) {
+			sk->sk_state = SMC_APPCLOSEWAIT1;
+		} else {
+			sk->sk_state = SMC_CLOSED;
+			sock_put(sk); /* passive closing */
+		}
+		break;
+	case SMC_ACTIVE:
+		sk->sk_state = SMC_APPCLOSEWAIT1;
+		/* postpone sock_put() for passive closing to cover
+		 * received SEND_SHUTDOWN as well
+		 */
+		break;
+	case SMC_PEERCLOSEWAIT1:
+		if (rxflags->peer_done_writing)
+			sk->sk_state = SMC_PEERCLOSEWAIT2;
+		/* fall through */
+		/* to check for closing */
+	case SMC_PEERCLOSEWAIT2:
+		if (!smc_cdc_rxed_any_close(conn))
+			break;
+		if (sock_flag(sk, SOCK_DEAD) &&
+		    smc_close_sent_any_close(conn)) {
+			/* smc_release has already been called locally */
+			sk->sk_state = SMC_CLOSED;
+		} else {
+			/* just shutdown, but not yet closed locally */
+			sk->sk_state = SMC_APPFINCLOSEWAIT;
+		}
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_PEERFINCLOSEWAIT:
+		if (smc_cdc_rxed_any_close(conn)) {
+			sk->sk_state = SMC_CLOSED;
+			sock_put(sk); /* passive closing */
+		}
+		break;
+	case SMC_APPCLOSEWAIT1:
+	case SMC_APPCLOSEWAIT2:
+		/* postpone sock_put() for passive closing to cover
+		 * received SEND_SHUTDOWN as well
+		 */
+		break;
+	case SMC_APPFINCLOSEWAIT:
+	case SMC_PEERABORTWAIT:
+	case SMC_PROCESSABORT:
+	case SMC_CLOSED:
+		/* nothing to do, add tracing in future patch */
+		break;
+	}
+
+wakeup:
+	sk->sk_data_ready(sk); /* wakeup blocked rcvbuf consumers */
+	sk->sk_write_space(sk); /* wakeup blocked sndbuf producers */
+
+	if (old_state != sk->sk_state) {
+		sk->sk_state_change(sk);
+		if ((sk->sk_state == SMC_CLOSED) &&
+		    (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket))
+			smc_conn_free(conn);
+	}
+	release_sock(sk);
+	sock_put(sk); /* sock_hold done by schedulers of close_work */
+}
+
+int smc_close_shutdown_write(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct sock *sk = &smc->sk;
+	int old_state;
+	long timeout;
+	int rc = 0;
+
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
+
+	old_state = sk->sk_state;
+again:
+	switch (sk->sk_state) {
+	case SMC_ACTIVE:
+		smc_close_stream_wait(smc, timeout);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
+		if (sk->sk_state != SMC_ACTIVE)
+			goto again;
+		/* send close wr request */
+		rc = smc_close_wr(conn);
+		if (rc)
+			break;
+		sk->sk_state = SMC_PEERCLOSEWAIT1;
+		break;
+	case SMC_APPCLOSEWAIT1:
+		/* passive close */
+		if (!smc_cdc_rxed_any_close(conn))
+			smc_close_stream_wait(smc, timeout);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
+		if (sk->sk_state != SMC_APPCLOSEWAIT1)
+			goto again;
+		/* confirm close from peer */
+		rc = smc_close_wr(conn);
+		if (rc)
+			break;
+		sk->sk_state = SMC_APPCLOSEWAIT2;
+		break;
+	case SMC_APPCLOSEWAIT2:
+	case SMC_PEERFINCLOSEWAIT:
+	case SMC_PEERCLOSEWAIT1:
+	case SMC_PEERCLOSEWAIT2:
+	case SMC_APPFINCLOSEWAIT:
+	case SMC_PROCESSABORT:
+	case SMC_PEERABORTWAIT:
+		/* nothing to do, add tracing in future patch */
+		break;
+	}
+
+	if (old_state != sk->sk_state)
+		sk->sk_state_change(sk);
+	return rc;
+}
+
+/* Initialize close properties on connection establishment. */
+void smc_close_init(struct smc_sock *smc)
+{
+	INIT_WORK(&smc->conn.close_work, smc_close_passive_work);
+}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
new file mode 100644
index 000000000..19eb6a211
--- /dev/null
+++ b/net/smc/smc_close.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Socket Closing
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_CLOSE_H
+#define SMC_CLOSE_H
+
+#include <linux/workqueue.h>
+
+#include "smc.h"
+
+#define SMC_MAX_STREAM_WAIT_TIMEOUT		(2 * HZ)
+#define SMC_CLOSE_SOCK_PUT_DELAY		HZ
+
+void smc_close_wake_tx_prepared(struct smc_sock *smc);
+int smc_close_active(struct smc_sock *smc);
+int smc_close_shutdown_write(struct smc_sock *smc);
+void smc_close_init(struct smc_sock *smc);
+
+#endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
new file mode 100644
index 000000000..4d421407d
--- /dev/null
+++ b/net/smc/smc_core.c
@@ -0,0 +1,1034 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Basic Transport Functions exploiting Infiniband API
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/socket.h>
+#include <linux/if_vlan.h>
+#include <linux/random.h>
+#include <linux/workqueue.h>
+#include <net/tcp.h>
+#include <net/sock.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_cache.h>
+
+#include "smc.h"
+#include "smc_clc.h"
+#include "smc_core.h"
+#include "smc_ib.h"
+#include "smc_wr.h"
+#include "smc_llc.h"
+#include "smc_cdc.h"
+#include "smc_close.h"
+#include "smc_ism.h"
+
+#define SMC_LGR_NUM_INCR		256
+#define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT		(SMC_LGR_FREE_DELAY_SERV + 10 * HZ)
+#define SMC_LGR_FREE_DELAY_FAST		(8 * HZ)
+
+static struct smc_lgr_list smc_lgr_list = {	/* established link groups */
+	.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
+	.list = LIST_HEAD_INIT(smc_lgr_list.list),
+	.num = 0,
+};
+
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+			 struct smc_buf_desc *buf_desc);
+
+static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
+{
+	/* client link group creation always follows the server link group
+	 * creation. For client use a somewhat higher removal delay time,
+	 * otherwise there is a risk of out-of-sync link groups.
+	 */
+	mod_delayed_work(system_wq, &lgr->free_work,
+			 (!lgr->is_smcd && lgr->role == SMC_CLNT) ?
+			 SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV);
+}
+
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr)
+{
+	mod_delayed_work(system_wq, &lgr->free_work, SMC_LGR_FREE_DELAY_FAST);
+}
+
+/* Register connection's alert token in our lookup structure.
+ * To use rbtrees we have to implement our own insert core.
+ * Requires @conns_lock
+ * @smc		connection to register
+ * Returns 0 on success, != otherwise.
+ */
+static void smc_lgr_add_alert_token(struct smc_connection *conn)
+{
+	struct rb_node **link, *parent = NULL;
+	u32 token = conn->alert_token_local;
+
+	link = &conn->lgr->conns_all.rb_node;
+	while (*link) {
+		struct smc_connection *cur = rb_entry(*link,
+					struct smc_connection, alert_node);
+
+		parent = *link;
+		if (cur->alert_token_local > token)
+			link = &parent->rb_left;
+		else
+			link = &parent->rb_right;
+	}
+	/* Put the new node there */
+	rb_link_node(&conn->alert_node, parent, link);
+	rb_insert_color(&conn->alert_node, &conn->lgr->conns_all);
+}
+
+/* Register connection in link group by assigning an alert token
+ * registered in a search tree.
+ * Requires @conns_lock
+ * Note that '0' is a reserved value and not assigned.
+ */
+static void smc_lgr_register_conn(struct smc_connection *conn)
+{
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	static atomic_t nexttoken = ATOMIC_INIT(0);
+
+	/* find a new alert_token_local value not yet used by some connection
+	 * in this link group
+	 */
+	sock_hold(&smc->sk); /* sock_put in smc_lgr_unregister_conn() */
+	while (!conn->alert_token_local) {
+		conn->alert_token_local = atomic_inc_return(&nexttoken);
+		if (smc_lgr_find_conn(conn->alert_token_local, conn->lgr))
+			conn->alert_token_local = 0;
+	}
+	smc_lgr_add_alert_token(conn);
+	conn->lgr->conns_num++;
+}
+
+/* Unregister connection and reset the alert token of the given connection<
+ */
+static void __smc_lgr_unregister_conn(struct smc_connection *conn)
+{
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	struct smc_link_group *lgr = conn->lgr;
+
+	rb_erase(&conn->alert_node, &lgr->conns_all);
+	lgr->conns_num--;
+	conn->alert_token_local = 0;
+	conn->lgr = NULL;
+	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
+}
+
+/* Unregister connection from lgr
+ */
+static void smc_lgr_unregister_conn(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!lgr)
+		return;
+	write_lock_bh(&lgr->conns_lock);
+	if (conn->alert_token_local) {
+		__smc_lgr_unregister_conn(conn);
+	}
+	write_unlock_bh(&lgr->conns_lock);
+}
+
+/* Send delete link, either as client to request the initiation
+ * of the DELETE LINK sequence from server; or as server to
+ * initiate the delete processing. See smc_llc_rx_delete_link().
+ */
+static int smc_link_send_delete(struct smc_link *lnk)
+{
+	if (lnk->state == SMC_LNK_ACTIVE &&
+	    !smc_llc_send_delete_link(lnk, SMC_LLC_REQ, true)) {
+		smc_llc_link_deleting(lnk);
+		return 0;
+	}
+	return -ENOTCONN;
+}
+
+static void smc_lgr_free_work(struct work_struct *work)
+{
+	struct smc_link_group *lgr = container_of(to_delayed_work(work),
+						  struct smc_link_group,
+						  free_work);
+	bool conns;
+
+	spin_lock_bh(&smc_lgr_list.lock);
+	if (list_empty(&lgr->list))
+		goto free;
+	read_lock_bh(&lgr->conns_lock);
+	conns = RB_EMPTY_ROOT(&lgr->conns_all);
+	read_unlock_bh(&lgr->conns_lock);
+	if (!conns) { /* number of lgr connections is no longer zero */
+		spin_unlock_bh(&smc_lgr_list.lock);
+		return;
+	}
+	list_del_init(&lgr->list); /* remove from smc_lgr_list */
+free:
+	spin_unlock_bh(&smc_lgr_list.lock);
+
+	if (!lgr->is_smcd && !lgr->terminating)	{
+		/* try to send del link msg, on error free lgr immediately */
+		if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) {
+			/* reschedule in case we never receive a response */
+			smc_lgr_schedule_free_work(lgr);
+			return;
+		}
+	}
+
+	if (!delayed_work_pending(&lgr->free_work)) {
+		struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+		if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
+			smc_llc_link_inactive(lnk);
+		smc_lgr_free(lgr);
+	}
+}
+
+/* create a new SMC link group */
+static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
+			  struct smc_ib_device *smcibdev, u8 ibport,
+			  char *peer_systemid, unsigned short vlan_id,
+			  struct smcd_dev *smcismdev, u64 peer_gid)
+{
+	struct smc_link_group *lgr;
+	struct smc_link *lnk;
+	u8 rndvec[3];
+	int rc = 0;
+	int i;
+
+	if (is_smcd && vlan_id) {
+		rc = smc_ism_get_vlan(smcismdev, vlan_id);
+		if (rc)
+			goto out;
+	}
+
+	lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
+	if (!lgr) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	lgr->is_smcd = is_smcd;
+	lgr->sync_err = 0;
+	lgr->vlan_id = vlan_id;
+	rwlock_init(&lgr->sndbufs_lock);
+	rwlock_init(&lgr->rmbs_lock);
+	rwlock_init(&lgr->conns_lock);
+	for (i = 0; i < SMC_RMBE_SIZES; i++) {
+		INIT_LIST_HEAD(&lgr->sndbufs[i]);
+		INIT_LIST_HEAD(&lgr->rmbs[i]);
+	}
+	smc_lgr_list.num += SMC_LGR_NUM_INCR;
+	memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
+	INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
+	lgr->conns_all = RB_ROOT;
+	if (is_smcd) {
+		/* SMC-D specific settings */
+		lgr->peer_gid = peer_gid;
+		lgr->smcd = smcismdev;
+	} else {
+		/* SMC-R specific settings */
+		lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+		memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+
+		lnk = &lgr->lnk[SMC_SINGLE_LINK];
+		/* initialize link */
+		lnk->state = SMC_LNK_ACTIVATING;
+		lnk->link_id = SMC_SINGLE_LINK;
+		lnk->smcibdev = smcibdev;
+		lnk->ibport = ibport;
+		lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
+		if (!smcibdev->initialized)
+			smc_ib_setup_per_ibdev(smcibdev);
+		get_random_bytes(rndvec, sizeof(rndvec));
+		lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
+			(rndvec[2] << 16);
+		rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
+					  vlan_id, lnk->gid, &lnk->sgid_index);
+		if (rc)
+			goto free_lgr;
+		rc = smc_llc_link_init(lnk);
+		if (rc)
+			goto free_lgr;
+		rc = smc_wr_alloc_link_mem(lnk);
+		if (rc)
+			goto clear_llc_lnk;
+		rc = smc_ib_create_protection_domain(lnk);
+		if (rc)
+			goto free_link_mem;
+		rc = smc_ib_create_queue_pair(lnk);
+		if (rc)
+			goto dealloc_pd;
+		rc = smc_wr_create_link(lnk);
+		if (rc)
+			goto destroy_qp;
+	}
+	smc->conn.lgr = lgr;
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_add(&lgr->list, &smc_lgr_list.list);
+	spin_unlock_bh(&smc_lgr_list.lock);
+	return 0;
+
+destroy_qp:
+	smc_ib_destroy_queue_pair(lnk);
+dealloc_pd:
+	smc_ib_dealloc_protection_domain(lnk);
+free_link_mem:
+	smc_wr_free_link_mem(lnk);
+clear_llc_lnk:
+	smc_llc_link_clear(lnk);
+free_lgr:
+	kfree(lgr);
+out:
+	return rc;
+}
+
+static void smc_buf_unuse(struct smc_connection *conn,
+			  struct smc_link_group *lgr)
+{
+	if (conn->sndbuf_desc)
+		conn->sndbuf_desc->used = 0;
+	if (conn->rmb_desc) {
+		if (!conn->rmb_desc->regerr) {
+			conn->rmb_desc->reused = 1;
+			conn->rmb_desc->used = 0;
+		} else {
+			/* buf registration failed, reuse not possible */
+			write_lock_bh(&lgr->rmbs_lock);
+			list_del(&conn->rmb_desc->list);
+			write_unlock_bh(&lgr->rmbs_lock);
+
+			smc_buf_free(lgr, true, conn->rmb_desc);
+		}
+	}
+}
+
+/* remove a finished connection from its link group */
+void smc_conn_free(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!lgr)
+		return;
+	if (lgr->is_smcd) {
+		smc_ism_unset_conn(conn);
+		tasklet_kill(&conn->rx_tsklet);
+	} else {
+		smc_cdc_tx_dismiss_slots(conn);
+	}
+	smc_buf_unuse(conn, lgr);		/* allow buffer reuse */
+	smc_lgr_unregister_conn(conn);		/* unsets conn->lgr */
+
+	if (!lgr->conns_num)
+		smc_lgr_schedule_free_work(lgr);
+}
+
+static void smc_link_clear(struct smc_link *lnk)
+{
+	lnk->peer_qpn = 0;
+	smc_llc_link_clear(lnk);
+	smc_ib_modify_qp_reset(lnk);
+	smc_wr_free_link(lnk);
+	smc_ib_destroy_queue_pair(lnk);
+	smc_ib_dealloc_protection_domain(lnk);
+	smc_wr_free_link_mem(lnk);
+}
+
+static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
+			  struct smc_buf_desc *buf_desc)
+{
+	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+	if (is_rmb) {
+		if (buf_desc->mr_rx[SMC_SINGLE_LINK])
+			smc_ib_put_memory_region(
+					buf_desc->mr_rx[SMC_SINGLE_LINK]);
+		smc_ib_buf_unmap_sg(lnk->smcibdev, buf_desc,
+				    DMA_FROM_DEVICE);
+	} else {
+		smc_ib_buf_unmap_sg(lnk->smcibdev, buf_desc,
+				    DMA_TO_DEVICE);
+	}
+	sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]);
+	if (buf_desc->pages)
+		__free_pages(buf_desc->pages, buf_desc->order);
+	kfree(buf_desc);
+}
+
+static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb,
+			  struct smc_buf_desc *buf_desc)
+{
+	if (is_dmb) {
+		/* restore original buf len */
+		buf_desc->len += sizeof(struct smcd_cdc_msg);
+		smc_ism_unregister_dmb(lgr->smcd, buf_desc);
+	} else {
+		kfree(buf_desc->cpu_addr);
+	}
+	kfree(buf_desc);
+}
+
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+			 struct smc_buf_desc *buf_desc)
+{
+	if (lgr->is_smcd)
+		smcd_buf_free(lgr, is_rmb, buf_desc);
+	else
+		smcr_buf_free(lgr, is_rmb, buf_desc);
+}
+
+static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
+{
+	struct smc_buf_desc *buf_desc, *bf_desc;
+	struct list_head *buf_list;
+	int i;
+
+	for (i = 0; i < SMC_RMBE_SIZES; i++) {
+		if (is_rmb)
+			buf_list = &lgr->rmbs[i];
+		else
+			buf_list = &lgr->sndbufs[i];
+		list_for_each_entry_safe(buf_desc, bf_desc, buf_list,
+					 list) {
+			list_del(&buf_desc->list);
+			smc_buf_free(lgr, is_rmb, buf_desc);
+		}
+	}
+}
+
+static void smc_lgr_free_bufs(struct smc_link_group *lgr)
+{
+	/* free send buffers */
+	__smc_lgr_free_bufs(lgr, false);
+	/* free rmbs */
+	__smc_lgr_free_bufs(lgr, true);
+}
+
+/* remove a link group */
+void smc_lgr_free(struct smc_link_group *lgr)
+{
+	smc_lgr_free_bufs(lgr);
+	if (lgr->is_smcd)
+		smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
+	else
+		smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
+	kfree(lgr);
+}
+
+void smc_lgr_forget(struct smc_link_group *lgr)
+{
+	spin_lock_bh(&smc_lgr_list.lock);
+	/* do not use this link group for new connections */
+	if (!list_empty(&lgr->list))
+		list_del_init(&lgr->list);
+	spin_unlock_bh(&smc_lgr_list.lock);
+}
+
+/* terminate linkgroup abnormally */
+static void __smc_lgr_terminate(struct smc_link_group *lgr)
+{
+	struct smc_connection *conn;
+	struct smc_sock *smc;
+	struct rb_node *node;
+
+	if (lgr->terminating)
+		return;	/* lgr already terminating */
+	lgr->terminating = 1;
+	if (!list_empty(&lgr->list)) /* forget lgr */
+		list_del_init(&lgr->list);
+	if (!lgr->is_smcd)
+		smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+
+	write_lock_bh(&lgr->conns_lock);
+	node = rb_first(&lgr->conns_all);
+	while (node) {
+		conn = rb_entry(node, struct smc_connection, alert_node);
+		smc = container_of(conn, struct smc_sock, conn);
+		sock_hold(&smc->sk); /* sock_put in close work */
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+		__smc_lgr_unregister_conn(conn);
+		write_unlock_bh(&lgr->conns_lock);
+		if (!schedule_work(&conn->close_work))
+			sock_put(&smc->sk);
+		write_lock_bh(&lgr->conns_lock);
+		node = rb_first(&lgr->conns_all);
+	}
+	write_unlock_bh(&lgr->conns_lock);
+	if (!lgr->is_smcd)
+		wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait);
+	smc_lgr_schedule_free_work(lgr);
+}
+
+void smc_lgr_terminate(struct smc_link_group *lgr)
+{
+	spin_lock_bh(&smc_lgr_list.lock);
+	__smc_lgr_terminate(lgr);
+	spin_unlock_bh(&smc_lgr_list.lock);
+}
+
+/* Called when IB port is terminated */
+void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	struct smc_link_group *lgr, *l;
+
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
+		if (!lgr->is_smcd &&
+		    lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
+		    lgr->lnk[SMC_SINGLE_LINK].ibport == ibport)
+			__smc_lgr_terminate(lgr);
+	}
+	spin_unlock_bh(&smc_lgr_list.lock);
+}
+
+/* Called when SMC-D device is terminated or peer is lost */
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+{
+	struct smc_link_group *lgr, *l;
+	LIST_HEAD(lgr_free_list);
+
+	/* run common cleanup function and build free list */
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
+		if (lgr->is_smcd && lgr->smcd == dev &&
+		    (!peer_gid || lgr->peer_gid == peer_gid) &&
+		    !list_empty(&lgr->list)) {
+			__smc_lgr_terminate(lgr);
+			list_move(&lgr->list, &lgr_free_list);
+		}
+	}
+	spin_unlock_bh(&smc_lgr_list.lock);
+
+	/* cancel the regular free workers and actually free lgrs */
+	list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
+		list_del_init(&lgr->list);
+		cancel_delayed_work_sync(&lgr->free_work);
+		smc_lgr_free(lgr);
+	}
+}
+
+/* Determine vlan of internal TCP socket.
+ * @vlan_id: address to store the determined vlan id into
+ */
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+{
+	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct net_device *ndev;
+	int i, nest_lvl, rc = 0;
+
+	*vlan_id = 0;
+	if (!dst) {
+		rc = -ENOTCONN;
+		goto out;
+	}
+	if (!dst->dev) {
+		rc = -ENODEV;
+		goto out_rel;
+	}
+
+	ndev = dst->dev;
+	if (is_vlan_dev(ndev)) {
+		*vlan_id = vlan_dev_vlan_id(ndev);
+		goto out_rel;
+	}
+
+	rtnl_lock();
+	nest_lvl = dev_get_nest_level(ndev);
+	for (i = 0; i < nest_lvl; i++) {
+		struct list_head *lower = &ndev->adj_list.lower;
+
+		if (list_empty(lower))
+			break;
+		lower = lower->next;
+		ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
+		if (is_vlan_dev(ndev)) {
+			*vlan_id = vlan_dev_vlan_id(ndev);
+			break;
+		}
+	}
+	rtnl_unlock();
+
+out_rel:
+	dst_release(dst);
+out:
+	return rc;
+}
+
+static bool smcr_lgr_match(struct smc_link_group *lgr,
+			   struct smc_clc_msg_local *lcl,
+			   enum smc_lgr_role role)
+{
+	return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
+		       SMC_SYSTEMID_LEN) &&
+		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
+			SMC_GID_SIZE) &&
+		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
+			sizeof(lcl->mac)) &&
+		lgr->role == role;
+}
+
+static bool smcd_lgr_match(struct smc_link_group *lgr,
+			   struct smcd_dev *smcismdev, u64 peer_gid)
+{
+	return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev;
+}
+
+/* create a new SMC connection (and a new link group if necessary) */
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
+		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+		    u64 peer_gid)
+{
+	struct smc_connection *conn = &smc->conn;
+	int local_contact = SMC_FIRST_CONTACT;
+	struct smc_link_group *lgr;
+	unsigned short vlan_id;
+	enum smc_lgr_role role;
+	int rc = 0;
+
+	role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+	rc = smc_vlan_by_tcpsk(smc->clcsock, &vlan_id);
+	if (rc)
+		return rc;
+
+	if ((role == SMC_CLNT) && srv_first_contact)
+		/* create new link group as well */
+		goto create;
+
+	/* determine if an existing link group can be reused */
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
+		write_lock_bh(&lgr->conns_lock);
+		if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
+		     smcr_lgr_match(lgr, lcl, role)) &&
+		    !lgr->sync_err &&
+		    lgr->vlan_id == vlan_id &&
+		    (role == SMC_CLNT ||
+		    (lgr->conns_num < SMC_RMBS_PER_LGR_MAX &&
+		      !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) {
+			/* link group found */
+			local_contact = SMC_REUSE_CONTACT;
+			conn->lgr = lgr;
+			smc_lgr_register_conn(conn); /* add smc conn to lgr */
+			if (delayed_work_pending(&lgr->free_work))
+				cancel_delayed_work(&lgr->free_work);
+			write_unlock_bh(&lgr->conns_lock);
+			break;
+		}
+		write_unlock_bh(&lgr->conns_lock);
+	}
+	spin_unlock_bh(&smc_lgr_list.lock);
+
+	if (role == SMC_CLNT && !srv_first_contact &&
+	    (local_contact == SMC_FIRST_CONTACT)) {
+		/* Server reuses a link group, but Client wants to start
+		 * a new one
+		 * send out_of_sync decline, reason synchr. error
+		 */
+		return -ENOLINK;
+	}
+
+create:
+	if (local_contact == SMC_FIRST_CONTACT) {
+		rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
+				    lcl->id_for_peer, vlan_id, smcd, peer_gid);
+		if (rc)
+			goto out;
+		smc_lgr_register_conn(conn); /* add smc conn to lgr */
+	}
+	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
+
+out:
+	return rc ? rc : local_contact;
+}
+
+/* convert the RMB size into the compressed notation - minimum 16K.
+ * In contrast to plain ilog2, this rounds towards the next power of 2,
+ * so the socket application gets at least its desired sndbuf / rcvbuf size.
+ */
+static u8 smc_compress_bufsize(int size)
+{
+	u8 compressed;
+
+	if (size <= SMC_BUF_MIN_SIZE)
+		return 0;
+
+	size = (size - 1) >> 14;
+	compressed = ilog2(size) + 1;
+	if (compressed >= SMC_RMBE_SIZES)
+		compressed = SMC_RMBE_SIZES - 1;
+	return compressed;
+}
+
+/* convert the RMB size from compressed notation into integer */
+int smc_uncompress_bufsize(u8 compressed)
+{
+	u32 size;
+
+	size = 0x00000001 << (((int)compressed) + 14);
+	return (int)size;
+}
+
+/* try to reuse a sndbuf or rmb description slot for a certain
+ * buffer size; if not available, return NULL
+ */
+static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize,
+					     rwlock_t *lock,
+					     struct list_head *buf_list)
+{
+	struct smc_buf_desc *buf_slot;
+
+	read_lock_bh(lock);
+	list_for_each_entry(buf_slot, buf_list, list) {
+		if (cmpxchg(&buf_slot->used, 0, 1) == 0) {
+			read_unlock_bh(lock);
+			return buf_slot;
+		}
+	}
+	read_unlock_bh(lock);
+	return NULL;
+}
+
+/* one of the conditions for announcing a receiver's current window size is
+ * that it "results in a minimum increase in the window size of 10% of the
+ * receive buffer space" [RFC7609]
+ */
+static inline int smc_rmb_wnd_update_limit(int rmbe_size)
+{
+	return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
+}
+
+static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
+						bool is_rmb, int bufsize)
+{
+	struct smc_buf_desc *buf_desc;
+	struct smc_link *lnk;
+	int rc;
+
+	/* try to alloc a new buffer */
+	buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+	if (!buf_desc)
+		return ERR_PTR(-ENOMEM);
+
+	buf_desc->order = get_order(bufsize);
+	buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN |
+				      __GFP_NOMEMALLOC | __GFP_COMP |
+				      __GFP_NORETRY | __GFP_ZERO,
+				      buf_desc->order);
+	if (!buf_desc->pages) {
+		kfree(buf_desc);
+		return ERR_PTR(-EAGAIN);
+	}
+	buf_desc->cpu_addr = (void *)page_address(buf_desc->pages);
+
+	/* build the sg table from the pages */
+	lnk = &lgr->lnk[SMC_SINGLE_LINK];
+	rc = sg_alloc_table(&buf_desc->sgt[SMC_SINGLE_LINK], 1,
+			    GFP_KERNEL);
+	if (rc) {
+		smc_buf_free(lgr, is_rmb, buf_desc);
+		return ERR_PTR(rc);
+	}
+	sg_set_buf(buf_desc->sgt[SMC_SINGLE_LINK].sgl,
+		   buf_desc->cpu_addr, bufsize);
+
+	/* map sg table to DMA address */
+	rc = smc_ib_buf_map_sg(lnk->smcibdev, buf_desc,
+			       is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	/* SMC protocol depends on mapping to one DMA address only */
+	if (rc != 1)  {
+		smc_buf_free(lgr, is_rmb, buf_desc);
+		return ERR_PTR(-EAGAIN);
+	}
+
+	/* create a new memory region for the RMB */
+	if (is_rmb) {
+		rc = smc_ib_get_memory_region(lnk->roce_pd,
+					      IB_ACCESS_REMOTE_WRITE |
+					      IB_ACCESS_LOCAL_WRITE,
+					      buf_desc);
+		if (rc) {
+			smc_buf_free(lgr, is_rmb, buf_desc);
+			return ERR_PTR(rc);
+		}
+	}
+
+	buf_desc->len = bufsize;
+	return buf_desc;
+}
+
+#define SMCD_DMBE_SIZES		6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
+
+static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
+						bool is_dmb, int bufsize)
+{
+	struct smc_buf_desc *buf_desc;
+	int rc;
+
+	if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES)
+		return ERR_PTR(-EAGAIN);
+
+	/* try to alloc a new DMB */
+	buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+	if (!buf_desc)
+		return ERR_PTR(-ENOMEM);
+	if (is_dmb) {
+		rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
+		if (rc) {
+			kfree(buf_desc);
+			return ERR_PTR(-EAGAIN);
+		}
+		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 |
+					     __GFP_NOMEMALLOC);
+		if (!buf_desc->cpu_addr) {
+			kfree(buf_desc);
+			return ERR_PTR(-EAGAIN);
+		}
+		buf_desc->len = bufsize;
+	}
+	return buf_desc;
+}
+
+static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
+{
+	struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
+	struct smc_connection *conn = &smc->conn;
+	struct smc_link_group *lgr = conn->lgr;
+	struct list_head *buf_list;
+	int bufsize, bufsize_short;
+	int sk_buf_size;
+	rwlock_t *lock;
+
+	if (is_rmb)
+		/* use socket recv buffer size (w/o overhead) as start value */
+		sk_buf_size = smc->sk.sk_rcvbuf / 2;
+	else
+		/* use socket send buffer size (w/o overhead) as start value */
+		sk_buf_size = smc->sk.sk_sndbuf / 2;
+
+	for (bufsize_short = smc_compress_bufsize(sk_buf_size);
+	     bufsize_short >= 0; bufsize_short--) {
+
+		if (is_rmb) {
+			lock = &lgr->rmbs_lock;
+			buf_list = &lgr->rmbs[bufsize_short];
+		} else {
+			lock = &lgr->sndbufs_lock;
+			buf_list = &lgr->sndbufs[bufsize_short];
+		}
+		bufsize = smc_uncompress_bufsize(bufsize_short);
+		if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC)
+			continue;
+
+		/* check for reusable slot in the link group */
+		buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
+		if (buf_desc) {
+			memset(buf_desc->cpu_addr, 0, bufsize);
+			break; /* found reusable slot */
+		}
+
+		if (is_smcd)
+			buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize);
+		else
+			buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize);
+
+		if (PTR_ERR(buf_desc) == -ENOMEM)
+			break;
+		if (IS_ERR(buf_desc))
+			continue;
+
+		buf_desc->used = 1;
+		write_lock_bh(lock);
+		list_add(&buf_desc->list, buf_list);
+		write_unlock_bh(lock);
+		break; /* found */
+	}
+
+	if (IS_ERR(buf_desc))
+		return -ENOMEM;
+
+	if (is_rmb) {
+		conn->rmb_desc = buf_desc;
+		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(buf_desc->len);
+		if (is_smcd)
+			smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
+	} else {
+		conn->sndbuf_desc = buf_desc;
+		smc->sk.sk_sndbuf = bufsize * 2;
+		atomic_set(&conn->sndbuf_space, bufsize);
+	}
+	return 0;
+}
+
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
+	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+			       conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
+	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				  conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
+	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+			       conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
+	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				  conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
+/* create the send and receive buffer for an SMC socket;
+ * receive buffers are called RMBs;
+ * (even though the SMC protocol allows more than one RMB-element per RMB,
+ * the Linux implementation uses just one RMB-element per RMB, i.e. uses an
+ * extra RMB for every connection in a link group
+ */
+int smc_buf_create(struct smc_sock *smc, bool is_smcd)
+{
+	int rc;
+
+	/* create send buffer */
+	rc = __smc_buf_create(smc, is_smcd, false);
+	if (rc)
+		return rc;
+	/* create rmb */
+	rc = __smc_buf_create(smc, is_smcd, true);
+	if (rc)
+		smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
+	return rc;
+}
+
+static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr)
+{
+	int i;
+
+	for_each_clear_bit(i, lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX) {
+		if (!test_and_set_bit(i, lgr->rtokens_used_mask))
+			return i;
+	}
+	return -ENOSPC;
+}
+
+/* add a new rtoken from peer */
+int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey)
+{
+	u64 dma_addr = be64_to_cpu(nw_vaddr);
+	u32 rkey = ntohl(nw_rkey);
+	int i;
+
+	for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
+		if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) &&
+		    (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) &&
+		    test_bit(i, lgr->rtokens_used_mask)) {
+			/* already in list */
+			return i;
+		}
+	}
+	i = smc_rmb_reserve_rtoken_idx(lgr);
+	if (i < 0)
+		return i;
+	lgr->rtokens[i][SMC_SINGLE_LINK].rkey = rkey;
+	lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr = dma_addr;
+	return i;
+}
+
+/* delete an rtoken */
+int smc_rtoken_delete(struct smc_link_group *lgr, __be32 nw_rkey)
+{
+	u32 rkey = ntohl(nw_rkey);
+	int i;
+
+	for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
+		if (lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey &&
+		    test_bit(i, lgr->rtokens_used_mask)) {
+			lgr->rtokens[i][SMC_SINGLE_LINK].rkey = 0;
+			lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr = 0;
+
+			clear_bit(i, lgr->rtokens_used_mask);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+/* save rkey and dma_addr received from peer during clc handshake */
+int smc_rmb_rtoken_handling(struct smc_connection *conn,
+			    struct smc_clc_msg_accept_confirm *clc)
+{
+	conn->rtoken_idx = smc_rtoken_add(conn->lgr, clc->rmb_dma_addr,
+					  clc->rmb_rkey);
+	if (conn->rtoken_idx < 0)
+		return conn->rtoken_idx;
+	return 0;
+}
+
+/* Called (from smc_exit) when module is removed */
+void smc_core_exit(void)
+{
+	struct smc_link_group *lgr, *lg;
+	LIST_HEAD(lgr_freeing_list);
+
+	spin_lock_bh(&smc_lgr_list.lock);
+	if (!list_empty(&smc_lgr_list.list))
+		list_splice_init(&smc_lgr_list.list, &lgr_freeing_list);
+	spin_unlock_bh(&smc_lgr_list.lock);
+	list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
+		list_del_init(&lgr->list);
+		if (!lgr->is_smcd) {
+			struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+			if (lnk->state == SMC_LNK_ACTIVE)
+				smc_llc_send_delete_link(lnk, SMC_LLC_REQ,
+							 false);
+			smc_llc_link_inactive(lnk);
+		}
+		cancel_delayed_work_sync(&lgr->free_work);
+		smc_lgr_free(lgr); /* free link group */
+	}
+}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
new file mode 100644
index 000000000..c15667473
--- /dev/null
+++ b/net/smc/smc_core.h
@@ -0,0 +1,276 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for SMC Connections, Link Groups and Links
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_CORE_H
+#define _SMC_CORE_H
+
+#include <linux/atomic.h>
+#include <rdma/ib_verbs.h>
+
+#include "smc.h"
+#include "smc_ib.h"
+
+#define SMC_RMBS_PER_LGR_MAX	255	/* max. # of RMBs per link group */
+
+struct smc_lgr_list {			/* list of link group definition */
+	struct list_head	list;
+	spinlock_t		lock;	/* protects list of link groups */
+	u32			num;	/* unique link group number */
+};
+
+enum smc_lgr_role {		/* possible roles of a link group */
+	SMC_CLNT,	/* client */
+	SMC_SERV	/* server */
+};
+
+enum smc_link_state {			/* possible states of a link */
+	SMC_LNK_INACTIVE,	/* link is inactive */
+	SMC_LNK_ACTIVATING,	/* link is being activated */
+	SMC_LNK_ACTIVE,		/* link is active */
+	SMC_LNK_DELETING,	/* link is being deleted */
+};
+
+#define SMC_WR_BUF_SIZE		48	/* size of work request buffer */
+
+struct smc_wr_buf {
+	u8	raw[SMC_WR_BUF_SIZE];
+};
+
+#define SMC_WR_REG_MR_WAIT_TIME	(5 * HZ)/* wait time for ib_wr_reg_mr result */
+
+enum smc_wr_reg_state {
+	POSTED,		/* ib_wr_reg_mr request posted */
+	CONFIRMED,	/* ib_wr_reg_mr response: successful */
+	FAILED		/* ib_wr_reg_mr response: failure */
+};
+
+struct smc_link {
+	struct smc_ib_device	*smcibdev;	/* ib-device */
+	u8			ibport;		/* port - values 1 | 2 */
+	struct ib_pd		*roce_pd;	/* IB protection domain,
+						 * unique for every RoCE QP
+						 */
+	struct ib_qp		*roce_qp;	/* IB queue pair */
+	struct ib_qp_attr	qp_attr;	/* IB queue pair attributes */
+
+	struct smc_wr_buf	*wr_tx_bufs;	/* WR send payload buffers */
+	struct ib_send_wr	*wr_tx_ibs;	/* WR send meta data */
+	struct ib_sge		*wr_tx_sges;	/* WR send gather meta data */
+	struct smc_wr_tx_pend	*wr_tx_pends;	/* WR send waiting for CQE */
+	/* above four vectors have wr_tx_cnt elements and use the same index */
+	dma_addr_t		wr_tx_dma_addr;	/* DMA address of wr_tx_bufs */
+	atomic_long_t		wr_tx_id;	/* seq # of last sent WR */
+	unsigned long		*wr_tx_mask;	/* bit mask of used indexes */
+	u32			wr_tx_cnt;	/* number of WR send buffers */
+	wait_queue_head_t	wr_tx_wait;	/* wait for free WR send buf */
+
+	struct smc_wr_buf	*wr_rx_bufs;	/* WR recv payload buffers */
+	struct ib_recv_wr	*wr_rx_ibs;	/* WR recv meta data */
+	struct ib_sge		*wr_rx_sges;	/* WR recv scatter meta data */
+	/* above three vectors have wr_rx_cnt elements and use the same index */
+	dma_addr_t		wr_rx_dma_addr;	/* DMA address of wr_rx_bufs */
+	u64			wr_rx_id;	/* seq # of last recv WR */
+	u32			wr_rx_cnt;	/* number of WR recv buffers */
+	unsigned long		wr_rx_tstamp;	/* jiffies when last buf rx */
+
+	struct ib_reg_wr	wr_reg;		/* WR register memory region */
+	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
+	enum smc_wr_reg_state	wr_reg_state;	/* state of wr_reg request */
+
+	u8			gid[SMC_GID_SIZE];/* gid matching used vlan id*/
+	u8			sgid_index;	/* gid index for vlan id      */
+	u32			peer_qpn;	/* QP number of peer */
+	enum ib_mtu		path_mtu;	/* used mtu */
+	enum ib_mtu		peer_mtu;	/* mtu size of peer */
+	u32			psn_initial;	/* QP tx initial packet seqno */
+	u32			peer_psn;	/* QP rx initial packet seqno */
+	u8			peer_mac[ETH_ALEN];	/* = gid[8:10||13:15] */
+	u8			peer_gid[SMC_GID_SIZE];	/* gid of peer*/
+	u8			link_id;	/* unique # within link group */
+
+	enum smc_link_state	state;		/* state of link */
+	struct workqueue_struct *llc_wq;	/* single thread work queue */
+	struct completion	llc_confirm;	/* wait for rx of conf link */
+	struct completion	llc_confirm_resp; /* wait 4 rx of cnf lnk rsp */
+	int			llc_confirm_rc; /* rc from confirm link msg */
+	int			llc_confirm_resp_rc; /* rc from conf_resp msg */
+	struct completion	llc_add;	/* wait for rx of add link */
+	struct completion	llc_add_resp;	/* wait for rx of add link rsp*/
+	struct delayed_work	llc_testlink_wrk; /* testlink worker */
+	struct completion	llc_testlink_resp; /* wait for rx of testlink */
+	int			llc_testlink_time; /* testlink interval */
+	struct completion	llc_confirm_rkey; /* wait 4 rx of cnf rkey */
+	int			llc_confirm_rkey_rc; /* rc from cnf rkey msg */
+};
+
+/* For now we just allow one parallel link per link group. The SMC protocol
+ * allows more (up to 8).
+ */
+#define SMC_LINKS_PER_LGR_MAX	1
+#define SMC_SINGLE_LINK		0
+
+#define SMC_FIRST_CONTACT	1		/* first contact to a peer */
+#define SMC_REUSE_CONTACT	0		/* follow-on contact to a peer*/
+
+/* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
+struct smc_buf_desc {
+	struct list_head	list;
+	void			*cpu_addr;	/* virtual address of buffer */
+	struct page		*pages;
+	int			len;		/* length of buffer */
+	u32			used;		/* currently used / unused */
+	u8			reused	: 1;	/* new created / reused */
+	u8			regerr	: 1;	/* err during registration */
+	union {
+		struct { /* SMC-R */
+			struct sg_table		sgt[SMC_LINKS_PER_LGR_MAX];
+						/* virtual buffer */
+			struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
+						/* for rmb only: memory region
+						 * incl. rkey provided to peer
+						 */
+			u32			order;	/* allocation order */
+		};
+		struct { /* SMC-D */
+			unsigned short		sba_idx;
+						/* SBA index number */
+			u64			token;
+						/* DMB token number */
+			dma_addr_t		dma_addr;
+						/* DMA address */
+		};
+	};
+};
+
+struct smc_rtoken {				/* address/key of remote RMB */
+	u64			dma_addr;
+	u32			rkey;
+};
+
+#define SMC_LGR_ID_SIZE		4
+#define SMC_BUF_MIN_SIZE	16384	/* minimum size of an RMB */
+#define SMC_RMBE_SIZES		16	/* number of distinct RMBE sizes */
+/* theoretically, the RFC states that largest size would be 512K,
+ * i.e. compressed 5 and thus 6 sizes (0..5), despite
+ * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
+ */
+
+struct smcd_dev;
+
+struct smc_link_group {
+	struct list_head	list;
+	struct rb_root		conns_all;	/* connection tree */
+	rwlock_t		conns_lock;	/* protects conns_all */
+	unsigned int		conns_num;	/* current # of connections */
+	unsigned short		vlan_id;	/* vlan id of link group */
+
+	struct list_head	sndbufs[SMC_RMBE_SIZES];/* tx buffers */
+	rwlock_t		sndbufs_lock;	/* protects tx buffers */
+	struct list_head	rmbs[SMC_RMBE_SIZES];	/* rx buffers */
+	rwlock_t		rmbs_lock;	/* protects rx buffers */
+
+	u8			id[SMC_LGR_ID_SIZE];	/* unique lgr id */
+	struct delayed_work	free_work;	/* delayed freeing of an lgr */
+	u8			sync_err : 1;	/* lgr no longer fits to peer */
+	u8			terminating : 1;/* lgr is terminating */
+
+	bool			is_smcd;	/* SMC-R or SMC-D */
+	union {
+		struct { /* SMC-R */
+			enum smc_lgr_role	role;
+						/* client or server */
+			struct smc_link		lnk[SMC_LINKS_PER_LGR_MAX];
+						/* smc link */
+			char			peer_systemid[SMC_SYSTEMID_LEN];
+						/* unique system_id of peer */
+			struct smc_rtoken	rtokens[SMC_RMBS_PER_LGR_MAX]
+						[SMC_LINKS_PER_LGR_MAX];
+						/* remote addr/key pairs */
+			DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX);
+						/* used rtoken elements */
+		};
+		struct { /* SMC-D */
+			u64			peer_gid;
+						/* Peer GID (remote) */
+			struct smcd_dev		*smcd;
+						/* ISM device for VLAN reg. */
+		};
+	};
+};
+
+/* Find the connection associated with the given alert token in the link group.
+ * To use rbtrees we have to implement our own search core.
+ * Requires @conns_lock
+ * @token	alert token to search for
+ * @lgr		 link group to search in
+ * Returns connection associated with token if found, NULL otherwise.
+ */
+static inline struct smc_connection *smc_lgr_find_conn(
+	u32 token, struct smc_link_group *lgr)
+{
+	struct smc_connection *res = NULL;
+	struct rb_node *node;
+
+	node = lgr->conns_all.rb_node;
+	while (node) {
+		struct smc_connection *cur = rb_entry(node,
+					struct smc_connection, alert_node);
+
+		if (cur->alert_token_local > token) {
+			node = node->rb_left;
+		} else {
+			if (cur->alert_token_local < token) {
+				node = node->rb_right;
+			} else {
+				res = cur;
+				break;
+			}
+		}
+	}
+
+	return res;
+}
+
+struct smc_sock;
+struct smc_clc_msg_accept_confirm;
+struct smc_clc_msg_local;
+
+void smc_lgr_free(struct smc_link_group *lgr);
+void smc_lgr_forget(struct smc_link_group *lgr);
+void smc_lgr_terminate(struct smc_link_group *lgr);
+void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+int smc_buf_create(struct smc_sock *smc, bool is_smcd);
+int smc_uncompress_bufsize(u8 compressed);
+int smc_rmb_rtoken_handling(struct smc_connection *conn,
+			    struct smc_clc_msg_accept_confirm *clc);
+int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey);
+int smc_rtoken_delete(struct smc_link_group *lgr, __be32 nw_rkey);
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
+
+void smc_conn_free(struct smc_connection *conn);
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
+		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+		    u64 peer_gid);
+void smcd_conn_free(struct smc_connection *conn);
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
+void smc_core_exit(void);
+
+static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
+{
+	return container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+}
+#endif
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
new file mode 100644
index 000000000..6c4a7a593
--- /dev/null
+++ b/net/smc/smc_diag.c
@@ -0,0 +1,266 @@
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Monitoring SMC transport protocol sockets
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/sock_diag.h>
+#include <linux/inet_diag.h>
+#include <linux/smc_diag.h>
+#include <net/netlink.h>
+#include <net/smc.h>
+
+#include "smc.h"
+#include "smc_core.h"
+
+static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)
+{
+	sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x",
+		be16_to_cpu(((__be16 *)gid_raw)[0]),
+		be16_to_cpu(((__be16 *)gid_raw)[1]),
+		be16_to_cpu(((__be16 *)gid_raw)[2]),
+		be16_to_cpu(((__be16 *)gid_raw)[3]),
+		be16_to_cpu(((__be16 *)gid_raw)[4]),
+		be16_to_cpu(((__be16 *)gid_raw)[5]),
+		be16_to_cpu(((__be16 *)gid_raw)[6]),
+		be16_to_cpu(((__be16 *)gid_raw)[7]));
+}
+
+static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
+{
+	struct smc_sock *smc = smc_sk(sk);
+
+	memset(r, 0, sizeof(*r));
+	r->diag_family = sk->sk_family;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
+	if (!smc->clcsock)
+		return;
+	r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
+	r->id.idiag_dport = smc->clcsock->sk->sk_dport;
+	r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
+	if (sk->sk_protocol == SMCPROTO_SMC) {
+		r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
+		r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (sk->sk_protocol == SMCPROTO_SMC6) {
+		memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr,
+		       sizeof(smc->clcsock->sk->sk_v6_rcv_saddr));
+		memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr,
+		       sizeof(smc->clcsock->sk->sk_v6_daddr));
+#endif
+	}
+}
+
+static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
+				   struct smc_diag_msg *r,
+				   struct user_namespace *user_ns)
+{
+	if (nla_put_u8(skb, SMC_DIAG_SHUTDOWN, sk->sk_shutdown))
+		return 1;
+
+	r->diag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
+	r->diag_inode = sock_i_ino(sk);
+	return 0;
+}
+
+static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
+			   struct netlink_callback *cb,
+			   const struct smc_diag_req *req,
+			   struct nlattr *bc)
+{
+	struct smc_sock *smc = smc_sk(sk);
+	struct smc_diag_fallback fallback;
+	struct user_namespace *user_ns;
+	struct smc_diag_msg *r;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			cb->nlh->nlmsg_type, sizeof(*r), NLM_F_MULTI);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	r = nlmsg_data(nlh);
+	smc_diag_msg_common_fill(r, sk);
+	r->diag_state = sk->sk_state;
+	if (smc->use_fallback)
+		r->diag_mode = SMC_DIAG_MODE_FALLBACK_TCP;
+	else if (smc->conn.lgr && smc->conn.lgr->is_smcd)
+		r->diag_mode = SMC_DIAG_MODE_SMCD;
+	else
+		r->diag_mode = SMC_DIAG_MODE_SMCR;
+	user_ns = sk_user_ns(NETLINK_CB(cb->skb).sk);
+	if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns))
+		goto errout;
+
+	fallback.reason = smc->fallback_rsn;
+	fallback.peer_diagnosis = smc->peer_diagnosis;
+	if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0)
+		goto errout;
+
+	if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) &&
+	    smc->conn.alert_token_local) {
+		struct smc_connection *conn = &smc->conn;
+		struct smc_diag_conninfo cinfo = {
+			.token = conn->alert_token_local,
+			.sndbuf_size = conn->sndbuf_desc ?
+				conn->sndbuf_desc->len : 0,
+			.rmbe_size = conn->rmb_desc ? conn->rmb_desc->len : 0,
+			.peer_rmbe_size = conn->peer_rmbe_size,
+
+			.rx_prod.wrap = conn->local_rx_ctrl.prod.wrap,
+			.rx_prod.count = conn->local_rx_ctrl.prod.count,
+			.rx_cons.wrap = conn->local_rx_ctrl.cons.wrap,
+			.rx_cons.count = conn->local_rx_ctrl.cons.count,
+
+			.tx_prod.wrap = conn->local_tx_ctrl.prod.wrap,
+			.tx_prod.count = conn->local_tx_ctrl.prod.count,
+			.tx_cons.wrap = conn->local_tx_ctrl.cons.wrap,
+			.tx_cons.count = conn->local_tx_ctrl.cons.count,
+
+			.tx_prod_flags =
+				*(u8 *)&conn->local_tx_ctrl.prod_flags,
+			.tx_conn_state_flags =
+				*(u8 *)&conn->local_tx_ctrl.conn_state_flags,
+			.rx_prod_flags = *(u8 *)&conn->local_rx_ctrl.prod_flags,
+			.rx_conn_state_flags =
+				*(u8 *)&conn->local_rx_ctrl.conn_state_flags,
+
+			.tx_prep.wrap = conn->tx_curs_prep.wrap,
+			.tx_prep.count = conn->tx_curs_prep.count,
+			.tx_sent.wrap = conn->tx_curs_sent.wrap,
+			.tx_sent.count = conn->tx_curs_sent.count,
+			.tx_fin.wrap = conn->tx_curs_fin.wrap,
+			.tx_fin.count = conn->tx_curs_fin.count,
+		};
+
+		if (nla_put(skb, SMC_DIAG_CONNINFO, sizeof(cinfo), &cinfo) < 0)
+			goto errout;
+	}
+
+	if (smc->conn.lgr && !smc->conn.lgr->is_smcd &&
+	    (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
+	    !list_empty(&smc->conn.lgr->list)) {
+		struct smc_diag_lgrinfo linfo = {
+			.role = smc->conn.lgr->role,
+			.lnk[0].ibport = smc->conn.lgr->lnk[0].ibport,
+			.lnk[0].link_id = smc->conn.lgr->lnk[0].link_id,
+		};
+
+		memcpy(linfo.lnk[0].ibname,
+		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
+		       sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
+		smc_gid_be16_convert(linfo.lnk[0].gid,
+				     smc->conn.lgr->lnk[0].gid);
+		smc_gid_be16_convert(linfo.lnk[0].peer_gid,
+				     smc->conn.lgr->lnk[0].peer_gid);
+
+		if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
+			goto errout;
+	}
+	if (smc->conn.lgr && smc->conn.lgr->is_smcd &&
+	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
+	    !list_empty(&smc->conn.lgr->list)) {
+		struct smc_connection *conn = &smc->conn;
+		struct smcd_diag_dmbinfo dinfo;
+
+		memset(&dinfo, 0, sizeof(dinfo));
+
+		dinfo.linkid = *((u32 *)conn->lgr->id);
+		dinfo.peer_gid = conn->lgr->peer_gid;
+		dinfo.my_gid = conn->lgr->smcd->local_gid;
+		dinfo.token = conn->rmb_desc->token;
+		dinfo.peer_token = conn->peer_token;
+
+		if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
+			goto errout;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+errout:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb,
+			       struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *bc = NULL;
+	struct hlist_head *head;
+	struct sock *sk;
+	int rc = 0;
+
+	read_lock(&prot->h.smc_hash->lock);
+	head = &prot->h.smc_hash->ht;
+	if (hlist_empty(head))
+		goto out;
+
+	sk_for_each(sk, head) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		rc = __smc_diag_dump(sk, skb, cb, nlmsg_data(cb->nlh), bc);
+		if (rc)
+			break;
+	}
+
+out:
+	read_unlock(&prot->h.smc_hash->lock);
+	return rc;
+}
+
+static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int rc = 0;
+
+	rc = smc_diag_dump_proto(&smc_proto, skb, cb);
+	if (!rc)
+		rc = smc_diag_dump_proto(&smc_proto6, skb, cb);
+	return rc;
+}
+
+static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	struct net *net = sock_net(skb->sk);
+
+	if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY &&
+	    h->nlmsg_flags & NLM_F_DUMP) {
+		{
+			struct netlink_dump_control c = {
+				.dump = smc_diag_dump,
+				.min_dump_alloc = SKB_WITH_OVERHEAD(32768),
+			};
+			return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+		}
+	}
+	return 0;
+}
+
+static const struct sock_diag_handler smc_diag_handler = {
+	.family = AF_SMC,
+	.dump = smc_diag_handler_dump,
+};
+
+static int __init smc_diag_init(void)
+{
+	return sock_diag_register(&smc_diag_handler);
+}
+
+static void __exit smc_diag_exit(void)
+{
+	sock_diag_unregister(&smc_diag_handler);
+}
+
+module_init(smc_diag_init);
+module_exit(smc_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 43 /* AF_SMC */);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
new file mode 100644
index 000000000..c974d7d9a
--- /dev/null
+++ b/net/smc/smc_ib.c
@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  IB infrastructure:
+ *  Establish SMC-R as an Infiniband Client to be notified about added and
+ *  removed IB devices of type RDMA.
+ *  Determine device and port characteristics for these IB devices.
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/random.h>
+#include <linux/workqueue.h>
+#include <linux/scatterlist.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_cache.h>
+
+#include "smc_pnet.h"
+#include "smc_ib.h"
+#include "smc_core.h"
+#include "smc_wr.h"
+#include "smc.h"
+
+#define SMC_MAX_CQE 32766	/* max. # of completion queue elements */
+
+#define SMC_QP_MIN_RNR_TIMER		5
+#define SMC_QP_TIMEOUT			15 /* 4096 * 2 ** timeout usec */
+#define SMC_QP_RETRY_CNT			7 /* 7: infinite */
+#define SMC_QP_RNR_RETRY			7 /* 7: infinite */
+
+struct smc_ib_devices smc_ib_devices = {	/* smc-registered ib devices */
+	.lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock),
+	.list = LIST_HEAD_INIT(smc_ib_devices.list),
+};
+
+#define SMC_LOCAL_SYSTEMID_RESET	"%%%%%%%"
+
+u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET;	/* unique system
+								 * identifier
+								 */
+
+static int smc_ib_modify_qp_init(struct smc_link *lnk)
+{
+	struct ib_qp_attr qp_attr;
+
+	memset(&qp_attr, 0, sizeof(qp_attr));
+	qp_attr.qp_state = IB_QPS_INIT;
+	qp_attr.pkey_index = 0;
+	qp_attr.port_num = lnk->ibport;
+	qp_attr.qp_access_flags = IB_ACCESS_LOCAL_WRITE
+				| IB_ACCESS_REMOTE_WRITE;
+	return ib_modify_qp(lnk->roce_qp, &qp_attr,
+			    IB_QP_STATE | IB_QP_PKEY_INDEX |
+			    IB_QP_ACCESS_FLAGS | IB_QP_PORT);
+}
+
+static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
+{
+	enum ib_qp_attr_mask qp_attr_mask =
+		IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN |
+		IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER;
+	struct ib_qp_attr qp_attr;
+
+	memset(&qp_attr, 0, sizeof(qp_attr));
+	qp_attr.qp_state = IB_QPS_RTR;
+	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
+	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
+	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
+	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
+	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
+	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
+	       sizeof(lnk->peer_mac));
+	qp_attr.dest_qp_num = lnk->peer_qpn;
+	qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */
+	qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming
+					 * requests
+					 */
+	qp_attr.min_rnr_timer = SMC_QP_MIN_RNR_TIMER;
+
+	return ib_modify_qp(lnk->roce_qp, &qp_attr, qp_attr_mask);
+}
+
+int smc_ib_modify_qp_rts(struct smc_link *lnk)
+{
+	struct ib_qp_attr qp_attr;
+
+	memset(&qp_attr, 0, sizeof(qp_attr));
+	qp_attr.qp_state = IB_QPS_RTS;
+	qp_attr.timeout = SMC_QP_TIMEOUT;	/* local ack timeout */
+	qp_attr.retry_cnt = SMC_QP_RETRY_CNT;	/* retry count */
+	qp_attr.rnr_retry = SMC_QP_RNR_RETRY;	/* RNR retries, 7=infinite */
+	qp_attr.sq_psn = lnk->psn_initial;	/* starting send packet seq # */
+	qp_attr.max_rd_atomic = 1;	/* # of outstanding RDMA reads and
+					 * atomic ops allowed
+					 */
+	return ib_modify_qp(lnk->roce_qp, &qp_attr,
+			    IB_QP_STATE | IB_QP_TIMEOUT | IB_QP_RETRY_CNT |
+			    IB_QP_SQ_PSN | IB_QP_RNR_RETRY |
+			    IB_QP_MAX_QP_RD_ATOMIC);
+}
+
+int smc_ib_modify_qp_reset(struct smc_link *lnk)
+{
+	struct ib_qp_attr qp_attr;
+
+	memset(&qp_attr, 0, sizeof(qp_attr));
+	qp_attr.qp_state = IB_QPS_RESET;
+	return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
+}
+
+int smc_ib_ready_link(struct smc_link *lnk)
+{
+	struct smc_link_group *lgr = smc_get_lgr(lnk);
+	int rc = 0;
+
+	rc = smc_ib_modify_qp_init(lnk);
+	if (rc)
+		goto out;
+
+	rc = smc_ib_modify_qp_rtr(lnk);
+	if (rc)
+		goto out;
+	smc_wr_remember_qp_attr(lnk);
+	rc = ib_req_notify_cq(lnk->smcibdev->roce_cq_recv,
+			      IB_CQ_SOLICITED_MASK);
+	if (rc)
+		goto out;
+	rc = smc_wr_rx_post_init(lnk);
+	if (rc)
+		goto out;
+	smc_wr_remember_qp_attr(lnk);
+
+	if (lgr->role == SMC_SERV) {
+		rc = smc_ib_modify_qp_rts(lnk);
+		if (rc)
+			goto out;
+		smc_wr_remember_qp_attr(lnk);
+	}
+out:
+	return rc;
+}
+
+static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	const struct ib_gid_attr *attr;
+	int rc = 0;
+
+	attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0);
+	if (IS_ERR(attr))
+		return -ENODEV;
+
+	if (attr->ndev)
+		memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr,
+		       ETH_ALEN);
+	else
+		rc = -ENODEV;
+
+	rdma_put_gid_attr(attr);
+	return rc;
+}
+
+/* Create an identifier unique for this instance of SMC-R.
+ * The MAC-address of the first active registered IB device
+ * plus a random 2-byte number is used to create this identifier.
+ * This name is delivered to the peer during connection initialization.
+ */
+static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
+						u8 ibport)
+{
+	memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
+	       sizeof(smcibdev->mac[ibport - 1]));
+	get_random_bytes(&local_systemid[0], 2);
+}
+
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
+}
+
+/* determine the gid for an ib-device port and vlan id */
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
+{
+	const struct ib_gid_attr *attr;
+	int i;
+
+	for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
+		attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i);
+		if (IS_ERR(attr))
+			continue;
+
+		if (attr->ndev &&
+		    ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
+		     (vlan_id && is_vlan_dev(attr->ndev) &&
+		      vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
+		    attr->gid_type == IB_GID_TYPE_ROCE) {
+			if (gid)
+				memcpy(gid, &attr->gid, SMC_GID_SIZE);
+			if (sgid_index)
+				*sgid_index = attr->index;
+			rdma_put_gid_attr(attr);
+			return 0;
+		}
+		rdma_put_gid_attr(attr);
+	}
+	return -ENODEV;
+}
+
+static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	int rc;
+
+	memset(&smcibdev->pattr[ibport - 1], 0,
+	       sizeof(smcibdev->pattr[ibport - 1]));
+	rc = ib_query_port(smcibdev->ibdev, ibport,
+			   &smcibdev->pattr[ibport - 1]);
+	if (rc)
+		goto out;
+	/* the SMC protocol requires specification of the RoCE MAC address */
+	rc = smc_ib_fill_mac(smcibdev, ibport);
+	if (rc)
+		goto out;
+	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
+		     sizeof(local_systemid)) &&
+	    smc_ib_port_active(smcibdev, ibport))
+		/* create unique system identifier */
+		smc_ib_define_local_systemid(smcibdev, ibport);
+out:
+	return rc;
+}
+
+/* process context wrapper for might_sleep smc_ib_remember_port_attr */
+static void smc_ib_port_event_work(struct work_struct *work)
+{
+	struct smc_ib_device *smcibdev = container_of(
+		work, struct smc_ib_device, port_event_work);
+	u8 port_idx;
+
+	for_each_set_bit(port_idx, &smcibdev->port_event_mask, SMC_MAX_PORTS) {
+		smc_ib_remember_port_attr(smcibdev, port_idx + 1);
+		clear_bit(port_idx, &smcibdev->port_event_mask);
+		if (!smc_ib_port_active(smcibdev, port_idx + 1))
+			smc_port_terminate(smcibdev, port_idx + 1);
+	}
+}
+
+/* can be called in IRQ context */
+static void smc_ib_global_event_handler(struct ib_event_handler *handler,
+					struct ib_event *ibevent)
+{
+	struct smc_ib_device *smcibdev;
+	u8 port_idx;
+
+	smcibdev = container_of(handler, struct smc_ib_device, event_handler);
+
+	switch (ibevent->event) {
+	case IB_EVENT_PORT_ERR:
+	case IB_EVENT_DEVICE_FATAL:
+	case IB_EVENT_PORT_ACTIVE:
+		port_idx = ibevent->element.port_num - 1;
+		set_bit(port_idx, &smcibdev->port_event_mask);
+		schedule_work(&smcibdev->port_event_work);
+		break;
+	default:
+		break;
+	}
+}
+
+void smc_ib_dealloc_protection_domain(struct smc_link *lnk)
+{
+	if (lnk->roce_pd)
+		ib_dealloc_pd(lnk->roce_pd);
+	lnk->roce_pd = NULL;
+}
+
+int smc_ib_create_protection_domain(struct smc_link *lnk)
+{
+	int rc;
+
+	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
+	rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
+	if (IS_ERR(lnk->roce_pd))
+		lnk->roce_pd = NULL;
+	return rc;
+}
+
+static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
+{
+	struct smc_ib_device *smcibdev =
+		(struct smc_ib_device *)ibevent->device;
+	u8 port_idx;
+
+	switch (ibevent->event) {
+	case IB_EVENT_DEVICE_FATAL:
+	case IB_EVENT_GID_CHANGE:
+	case IB_EVENT_PORT_ERR:
+	case IB_EVENT_QP_ACCESS_ERR:
+		port_idx = ibevent->element.port_num - 1;
+		set_bit(port_idx, &smcibdev->port_event_mask);
+		schedule_work(&smcibdev->port_event_work);
+		break;
+	default:
+		break;
+	}
+}
+
+void smc_ib_destroy_queue_pair(struct smc_link *lnk)
+{
+	if (lnk->roce_qp)
+		ib_destroy_qp(lnk->roce_qp);
+	lnk->roce_qp = NULL;
+}
+
+/* create a queue pair within the protection domain for a link */
+int smc_ib_create_queue_pair(struct smc_link *lnk)
+{
+	struct ib_qp_init_attr qp_attr = {
+		.event_handler = smc_ib_qp_event_handler,
+		.qp_context = lnk,
+		.send_cq = lnk->smcibdev->roce_cq_send,
+		.recv_cq = lnk->smcibdev->roce_cq_recv,
+		.srq = NULL,
+		.cap = {
+				/* include unsolicited rdma_writes as well,
+				 * there are max. 2 RDMA_WRITE per 1 WR_SEND
+				 */
+			.max_send_wr = SMC_WR_BUF_CNT * 3,
+			.max_recv_wr = SMC_WR_BUF_CNT * 3,
+			.max_send_sge = SMC_IB_MAX_SEND_SGE,
+			.max_recv_sge = 1,
+		},
+		.sq_sig_type = IB_SIGNAL_REQ_WR,
+		.qp_type = IB_QPT_RC,
+	};
+	int rc;
+
+	lnk->roce_qp = ib_create_qp(lnk->roce_pd, &qp_attr);
+	rc = PTR_ERR_OR_ZERO(lnk->roce_qp);
+	if (IS_ERR(lnk->roce_qp))
+		lnk->roce_qp = NULL;
+	else
+		smc_wr_remember_qp_attr(lnk);
+	return rc;
+}
+
+void smc_ib_put_memory_region(struct ib_mr *mr)
+{
+	ib_dereg_mr(mr);
+}
+
+static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot)
+{
+	unsigned int offset = 0;
+	int sg_num;
+
+	/* map the largest prefix of a dma mapped SG list */
+	sg_num = ib_map_mr_sg(buf_slot->mr_rx[SMC_SINGLE_LINK],
+			      buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+			      buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+			      &offset, PAGE_SIZE);
+
+	return sg_num;
+}
+
+/* Allocate a memory region and map the dma mapped SG list of buf_slot */
+int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
+			     struct smc_buf_desc *buf_slot)
+{
+	if (buf_slot->mr_rx[SMC_SINGLE_LINK])
+		return 0; /* already done */
+
+	buf_slot->mr_rx[SMC_SINGLE_LINK] =
+		ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order);
+	if (IS_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK])) {
+		int rc;
+
+		rc = PTR_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK]);
+		buf_slot->mr_rx[SMC_SINGLE_LINK] = NULL;
+		return rc;
+	}
+
+	if (smc_ib_map_mr_sg(buf_slot) != 1)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* synchronize buffer usage for cpu access */
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+			    struct smc_buf_desc *buf_slot,
+			    enum dma_data_direction data_direction)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		ib_dma_sync_single_for_cpu(smcibdev->ibdev,
+					   sg_dma_address(sg),
+					   sg_dma_len(sg),
+					   data_direction);
+	}
+}
+
+/* synchronize buffer usage for device access */
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+			       struct smc_buf_desc *buf_slot,
+			       enum dma_data_direction data_direction)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		ib_dma_sync_single_for_device(smcibdev->ibdev,
+					      sg_dma_address(sg),
+					      sg_dma_len(sg),
+					      data_direction);
+	}
+}
+
+/* Map a new TX or RX buffer SG-table to DMA */
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
+		      struct smc_buf_desc *buf_slot,
+		      enum dma_data_direction data_direction)
+{
+	int mapped_nents;
+
+	mapped_nents = ib_dma_map_sg(smcibdev->ibdev,
+				     buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+				     buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+				     data_direction);
+	if (!mapped_nents)
+		return -ENOMEM;
+
+	return mapped_nents;
+}
+
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+			 struct smc_buf_desc *buf_slot,
+			 enum dma_data_direction data_direction)
+{
+	if (!buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address)
+		return; /* already unmapped */
+
+	ib_dma_unmap_sg(smcibdev->ibdev,
+			buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+			buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+			data_direction);
+	buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
+}
+
+long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
+{
+	struct ib_cq_init_attr cqattr =	{
+		.cqe = SMC_MAX_CQE, .comp_vector = 0 };
+	int cqe_size_order, smc_order;
+	long rc;
+
+	/* the calculated number of cq entries fits to mlx5 cq allocation */
+	cqe_size_order = cache_line_size() == 128 ? 7 : 6;
+	smc_order = MAX_ORDER - cqe_size_order - 1;
+	if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE)
+		cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2;
+	smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev,
+					      smc_wr_tx_cq_handler, NULL,
+					      smcibdev, &cqattr);
+	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send);
+	if (IS_ERR(smcibdev->roce_cq_send)) {
+		smcibdev->roce_cq_send = NULL;
+		return rc;
+	}
+	smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev,
+					      smc_wr_rx_cq_handler, NULL,
+					      smcibdev, &cqattr);
+	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_recv);
+	if (IS_ERR(smcibdev->roce_cq_recv)) {
+		smcibdev->roce_cq_recv = NULL;
+		goto err;
+	}
+	smc_wr_add_dev(smcibdev);
+	smcibdev->initialized = 1;
+	return rc;
+
+err:
+	ib_destroy_cq(smcibdev->roce_cq_send);
+	return rc;
+}
+
+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);
+}
+
+static struct ib_client smc_ib_client;
+
+/* callback function for ib_register_client() */
+static void smc_ib_add_dev(struct ib_device *ibdev)
+{
+	struct smc_ib_device *smcibdev;
+	u8 port_cnt;
+	int i;
+
+	if (ibdev->node_type != RDMA_NODE_IB_CA)
+		return;
+
+	smcibdev = kzalloc(sizeof(*smcibdev), GFP_KERNEL);
+	if (!smcibdev)
+		return;
+
+	smcibdev->ibdev = ibdev;
+	INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work);
+
+	spin_lock(&smc_ib_devices.lock);
+	list_add_tail(&smcibdev->list, &smc_ib_devices.list);
+	spin_unlock(&smc_ib_devices.lock);
+	ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
+	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
+			      smc_ib_global_event_handler);
+	ib_register_event_handler(&smcibdev->event_handler);
+
+	/* trigger reading of the port attributes */
+	port_cnt = smcibdev->ibdev->phys_port_cnt;
+	for (i = 0;
+	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
+	     i++) {
+		set_bit(i, &smcibdev->port_event_mask);
+		/* determine pnetids of the port */
+		smc_pnetid_by_dev_port(ibdev->dev.parent, i,
+				       smcibdev->pnetid[i]);
+	}
+	schedule_work(&smcibdev->port_event_work);
+}
+
+/* callback function for ib_register_client() */
+static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
+{
+	struct smc_ib_device *smcibdev;
+
+	smcibdev = ib_get_client_data(ibdev, &smc_ib_client);
+	if (!smcibdev || smcibdev->ibdev != ibdev)
+		return;
+	ib_set_client_data(ibdev, &smc_ib_client, NULL);
+	spin_lock(&smc_ib_devices.lock);
+	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
+	spin_unlock(&smc_ib_devices.lock);
+	smc_pnet_remove_by_ibdev(smcibdev);
+	smc_ib_cleanup_per_ibdev(smcibdev);
+	ib_unregister_event_handler(&smcibdev->event_handler);
+	cancel_work_sync(&smcibdev->port_event_work);
+	kfree(smcibdev);
+}
+
+static struct ib_client smc_ib_client = {
+	.name	= "smc_ib",
+	.add	= smc_ib_add_dev,
+	.remove = smc_ib_remove_dev,
+};
+
+int __init smc_ib_register_client(void)
+{
+	return ib_register_client(&smc_ib_client);
+}
+
+void smc_ib_unregister_client(void)
+{
+	ib_unregister_client(&smc_ib_client);
+}
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
new file mode 100644
index 000000000..bac7fd65a
--- /dev/null
+++ b/net/smc/smc_ib.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for IB environment
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <Ursula Braun@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_IB_H
+#define _SMC_IB_H
+
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+#include <rdma/ib_verbs.h>
+#include <net/smc.h>
+
+#define SMC_MAX_PORTS			2	/* Max # of ports */
+#define SMC_GID_SIZE			sizeof(union ib_gid)
+
+#define SMC_IB_MAX_SEND_SGE		2
+
+struct smc_ib_devices {			/* list of smc ib devices definition */
+	struct list_head	list;
+	spinlock_t		lock;	/* protects list of smc ib devices */
+};
+
+extern struct smc_ib_devices	smc_ib_devices; /* list of smc ib devices */
+
+struct smc_ib_device {				/* ib-device infos for smc */
+	struct list_head	list;
+	struct ib_device	*ibdev;
+	struct ib_port_attr	pattr[SMC_MAX_PORTS];	/* ib dev. port attrs */
+	struct ib_event_handler	event_handler;	/* global ib_event handler */
+	struct ib_cq		*roce_cq_send;	/* send completion queue */
+	struct ib_cq		*roce_cq_recv;	/* recv completion queue */
+	struct tasklet_struct	send_tasklet;	/* called by send cq handler */
+	struct tasklet_struct	recv_tasklet;	/* called by recv cq handler */
+	char			mac[SMC_MAX_PORTS][ETH_ALEN];
+						/* mac address per port*/
+	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
+						/* pnetid per port */
+	u8			initialized : 1; /* ib dev CQ, evthdl done */
+	struct work_struct	port_event_work;
+	unsigned long		port_event_mask;
+};
+
+struct smc_buf_desc;
+struct smc_link;
+
+int smc_ib_register_client(void) __init;
+void smc_ib_unregister_client(void);
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
+		      struct smc_buf_desc *buf_slot,
+		      enum dma_data_direction data_direction);
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+			 struct smc_buf_desc *buf_slot,
+			 enum dma_data_direction data_direction);
+void smc_ib_dealloc_protection_domain(struct smc_link *lnk);
+int smc_ib_create_protection_domain(struct smc_link *lnk);
+void smc_ib_destroy_queue_pair(struct smc_link *lnk);
+int smc_ib_create_queue_pair(struct smc_link *lnk);
+int smc_ib_ready_link(struct smc_link *lnk);
+int smc_ib_modify_qp_rts(struct smc_link *lnk);
+int smc_ib_modify_qp_reset(struct smc_link *lnk);
+long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
+int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
+			     struct smc_buf_desc *buf_slot);
+void smc_ib_put_memory_region(struct ib_mr *mr);
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+			    struct smc_buf_desc *buf_slot,
+			    enum dma_data_direction data_direction);
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+			       struct smc_buf_desc *buf_slot,
+			       enum dma_data_direction data_direction);
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index);
+#endif
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
new file mode 100644
index 000000000..e36f21ce7
--- /dev/null
+++ b/net/smc/smc_ism.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * Functions for ISM device.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <asm/page.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_ism.h"
+#include "smc_pnet.h"
+
+struct smcd_dev_list smcd_dev_list = {
+	.list = LIST_HEAD_INIT(smcd_dev_list.list),
+	.lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock)
+};
+
+/* Test if an ISM communication is possible. */
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
+{
+	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
+					   vlan_id);
+}
+
+int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
+		  void *data, size_t len)
+{
+	int rc;
+
+	rc = smcd->ops->move_data(smcd, pos->token, pos->index, pos->signal,
+				  pos->offset, data, len);
+
+	return rc < 0 ? rc : 0;
+}
+
+/* Set a connection using this DMBE. */
+void smc_ism_set_conn(struct smc_connection *conn)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+	conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = conn;
+	spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Unset a connection using this DMBE. */
+void smc_ism_unset_conn(struct smc_connection *conn)
+{
+	unsigned long flags;
+
+	if (!conn->rmb_desc)
+		return;
+
+	spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+	conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = NULL;
+	spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Register a VLAN identifier with the ISM device. Use a reference count
+ * and add a VLAN identifier only when the first DMB using this VLAN is
+ * registered.
+ */
+int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+	struct smc_ism_vlanid *new_vlan, *vlan;
+	unsigned long flags;
+	int rc = 0;
+
+	if (!vlanid)			/* No valid vlan id */
+		return -EINVAL;
+
+	/* create new vlan entry, in case we need it */
+	new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL);
+	if (!new_vlan)
+		return -ENOMEM;
+	new_vlan->vlanid = vlanid;
+	refcount_set(&new_vlan->refcnt, 1);
+
+	/* if there is an existing entry, increase count and return */
+	spin_lock_irqsave(&smcd->lock, flags);
+	list_for_each_entry(vlan, &smcd->vlan, list) {
+		if (vlan->vlanid == vlanid) {
+			refcount_inc(&vlan->refcnt);
+			kfree(new_vlan);
+			goto out;
+		}
+	}
+
+	/* no existing entry found.
+	 * add new entry to device; might fail, e.g., if HW limit reached
+	 */
+	if (smcd->ops->add_vlan_id(smcd, vlanid)) {
+		kfree(new_vlan);
+		rc = -EIO;
+		goto out;
+	}
+	list_add_tail(&new_vlan->list, &smcd->vlan);
+out:
+	spin_unlock_irqrestore(&smcd->lock, flags);
+	return rc;
+}
+
+/* Unregister a VLAN identifier with the ISM device. Use a reference count
+ * and remove a VLAN identifier only when the last DMB using this VLAN is
+ * unregistered.
+ */
+int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+	struct smc_ism_vlanid *vlan;
+	unsigned long flags;
+	bool found = false;
+	int rc = 0;
+
+	if (!vlanid)			/* No valid vlan id */
+		return -EINVAL;
+
+	spin_lock_irqsave(&smcd->lock, flags);
+	list_for_each_entry(vlan, &smcd->vlan, list) {
+		if (vlan->vlanid == vlanid) {
+			if (!refcount_dec_and_test(&vlan->refcnt))
+				goto out;
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		rc = -ENOENT;
+		goto out;		/* VLAN id not in table */
+	}
+
+	/* Found and the last reference just gone */
+	if (smcd->ops->del_vlan_id(smcd, vlanid))
+		rc = -EIO;
+	list_del(&vlan->list);
+	kfree(vlan);
+out:
+	spin_unlock_irqrestore(&smcd->lock, flags);
+	return rc;
+}
+
+int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc)
+{
+	struct smcd_dmb dmb;
+
+	memset(&dmb, 0, sizeof(dmb));
+	dmb.dmb_tok = dmb_desc->token;
+	dmb.sba_idx = dmb_desc->sba_idx;
+	dmb.cpu_addr = dmb_desc->cpu_addr;
+	dmb.dma_addr = dmb_desc->dma_addr;
+	dmb.dmb_len = dmb_desc->len;
+	return smcd->ops->unregister_dmb(smcd, &dmb);
+}
+
+int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
+			 struct smc_buf_desc *dmb_desc)
+{
+	struct smcd_dmb dmb;
+	int rc;
+
+	memset(&dmb, 0, sizeof(dmb));
+	dmb.dmb_len = dmb_len;
+	dmb.sba_idx = dmb_desc->sba_idx;
+	dmb.vlan_id = lgr->vlan_id;
+	dmb.rgid = lgr->peer_gid;
+	rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb);
+	if (!rc) {
+		dmb_desc->sba_idx = dmb.sba_idx;
+		dmb_desc->token = dmb.dmb_tok;
+		dmb_desc->cpu_addr = dmb.cpu_addr;
+		dmb_desc->dma_addr = dmb.dma_addr;
+		dmb_desc->len = dmb.dmb_len;
+	}
+	return rc;
+}
+
+struct smc_ism_event_work {
+	struct work_struct work;
+	struct smcd_dev *smcd;
+	struct smcd_event event;
+};
+
+#define ISM_EVENT_REQUEST		0x0001
+#define ISM_EVENT_RESPONSE		0x0002
+#define ISM_EVENT_REQUEST_IR		0x00000001
+#define ISM_EVENT_CODE_TESTLINK		0x83
+
+static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
+{
+	union {
+		u64	info;
+		struct {
+			u32		uid;
+			unsigned short	vlanid;
+			u16		code;
+		};
+	} ev_info;
+
+	switch (wrk->event.code) {
+	case ISM_EVENT_CODE_TESTLINK:	/* Activity timer */
+		ev_info.info = wrk->event.info;
+		if (ev_info.code == ISM_EVENT_REQUEST) {
+			ev_info.code = ISM_EVENT_RESPONSE;
+			wrk->smcd->ops->signal_event(wrk->smcd,
+						     wrk->event.tok,
+						     ISM_EVENT_REQUEST_IR,
+						     ISM_EVENT_CODE_TESTLINK,
+						     ev_info.info);
+			}
+		break;
+	}
+}
+
+/* worker for SMC-D events */
+static void smc_ism_event_work(struct work_struct *work)
+{
+	struct smc_ism_event_work *wrk =
+		container_of(work, struct smc_ism_event_work, work);
+
+	switch (wrk->event.type) {
+	case ISM_EVENT_GID:	/* GID event, token is peer GID */
+		smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+		break;
+	case ISM_EVENT_DMB:
+		break;
+	case ISM_EVENT_SWR:	/* Software defined event */
+		smcd_handle_sw_event(wrk);
+		break;
+	}
+	kfree(wrk);
+}
+
+static void smcd_release(struct device *dev)
+{
+	struct smcd_dev *smcd = container_of(dev, struct smcd_dev, dev);
+
+	kfree(smcd->conn);
+	kfree(smcd);
+}
+
+struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
+				const struct smcd_ops *ops, int max_dmbs)
+{
+	struct smcd_dev *smcd;
+
+	smcd = kzalloc(sizeof(*smcd), GFP_KERNEL);
+	if (!smcd)
+		return NULL;
+	smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *),
+			     GFP_KERNEL);
+	if (!smcd->conn) {
+		kfree(smcd);
+		return NULL;
+	}
+
+	smcd->dev.parent = parent;
+	smcd->dev.release = smcd_release;
+	device_initialize(&smcd->dev);
+	dev_set_name(&smcd->dev, name);
+	smcd->ops = ops;
+	smc_pnetid_by_dev_port(parent, 0, smcd->pnetid);
+
+	spin_lock_init(&smcd->lock);
+	INIT_LIST_HEAD(&smcd->vlan);
+	smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
+						 WQ_MEM_RECLAIM, name);
+	return smcd;
+}
+EXPORT_SYMBOL_GPL(smcd_alloc_dev);
+
+int smcd_register_dev(struct smcd_dev *smcd)
+{
+	spin_lock(&smcd_dev_list.lock);
+	list_add_tail(&smcd->list, &smcd_dev_list.list);
+	spin_unlock(&smcd_dev_list.lock);
+
+	return device_add(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_register_dev);
+
+void smcd_unregister_dev(struct smcd_dev *smcd)
+{
+	spin_lock(&smcd_dev_list.lock);
+	list_del(&smcd->list);
+	spin_unlock(&smcd_dev_list.lock);
+	flush_workqueue(smcd->event_wq);
+	destroy_workqueue(smcd->event_wq);
+	smc_smcd_terminate(smcd, 0);
+
+	device_del(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_unregister_dev);
+
+void smcd_free_dev(struct smcd_dev *smcd)
+{
+	put_device(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_free_dev);
+
+/* SMCD Device event handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer,
+ * - event->type (0 --> DMB, 1 --> GID),
+ * - event->code (event code),
+ * - event->tok (either DMB token when event type 0, or GID when event type 1)
+ * - event->time (time of day)
+ * - event->info (debug info).
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver event handler.
+ */
+void smcd_handle_event(struct smcd_dev *smcd, struct smcd_event *event)
+{
+	struct smc_ism_event_work *wrk;
+
+	/* copy event to event work queue, and let it be handled there */
+	wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+	if (!wrk)
+		return;
+	INIT_WORK(&wrk->work, smc_ism_event_work);
+	wrk->smcd = smcd;
+	wrk->event = *event;
+	queue_work(smcd->event_wq, &wrk->work);
+}
+EXPORT_SYMBOL_GPL(smcd_handle_event);
+
+/* SMCD Device interrupt handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer and DMB number. Find the connection and
+ * schedule the tasklet for this connection.
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver IRQ handler.
+ */
+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);
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
new file mode 100644
index 000000000..aee45b860
--- /dev/null
+++ b/net/smc/smc_ism.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * SMC-D ISM device structure definitions.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef SMCD_ISM_H
+#define SMCD_ISM_H
+
+#include <linux/uio.h>
+
+#include "smc.h"
+
+struct smcd_dev_list {	/* List of SMCD devices */
+	struct list_head list;
+	spinlock_t lock;	/* Protects list of devices */
+};
+
+extern struct smcd_dev_list	smcd_dev_list; /* list of smcd devices */
+
+struct smc_ism_vlanid {			/* VLAN id set on ISM device */
+	struct list_head list;
+	unsigned short vlanid;		/* Vlan id */
+	refcount_t refcnt;		/* Reference count */
+};
+
+struct smc_ism_position {	/* ISM device position to write to */
+	u64 token;		/* Token of DMB */
+	u32 offset;		/* Offset into DMBE */
+	u8 index;		/* Index of DMBE */
+	u8 signal;		/* Generate interrupt on owner side */
+};
+
+struct smcd_dev;
+
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev);
+void smc_ism_set_conn(struct smc_connection *conn);
+void smc_ism_unset_conn(struct smc_connection *conn);
+int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size,
+			 struct smc_buf_desc *dmb_desc);
+int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
+int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
+		  void *data, size_t len);
+#endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
new file mode 100644
index 000000000..9c916c709
--- /dev/null
+++ b/net/smc/smc_llc.c
@@ -0,0 +1,711 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Link Layer Control (LLC)
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Klaus Wacker <Klaus.Wacker@de.ibm.com>
+ *              Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <net/tcp.h>
+#include <rdma/ib_verbs.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_clc.h"
+#include "smc_llc.h"
+
+#define SMC_LLC_DATA_LEN		40
+
+struct smc_llc_hdr {
+	struct smc_wr_rx_hdr common;
+	u8 length;	/* 44 */
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 reserved:4,
+	   add_link_rej_rsn:4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 add_link_rej_rsn:4,
+	   reserved:4;
+#endif
+	u8 flags;
+};
+
+#define SMC_LLC_FLAG_NO_RMBE_EYEC	0x03
+
+struct smc_llc_msg_confirm_link {	/* type 0x01 */
+	struct smc_llc_hdr hd;
+	u8 sender_mac[ETH_ALEN];
+	u8 sender_gid[SMC_GID_SIZE];
+	u8 sender_qp_num[3];
+	u8 link_num;
+	u8 link_uid[SMC_LGR_ID_SIZE];
+	u8 max_links;
+	u8 reserved[9];
+};
+
+#define SMC_LLC_FLAG_ADD_LNK_REJ	0x40
+#define SMC_LLC_REJ_RSN_NO_ALT_PATH	1
+
+#define SMC_LLC_ADD_LNK_MAX_LINKS	2
+
+struct smc_llc_msg_add_link {		/* type 0x02 */
+	struct smc_llc_hdr hd;
+	u8 sender_mac[ETH_ALEN];
+	u8 reserved2[2];
+	u8 sender_gid[SMC_GID_SIZE];
+	u8 sender_qp_num[3];
+	u8 link_num;
+	u8 flags2;	/* QP mtu */
+	u8 initial_psn[3];
+	u8 reserved[8];
+};
+
+#define SMC_LLC_FLAG_DEL_LINK_ALL	0x40
+#define SMC_LLC_FLAG_DEL_LINK_ORDERLY	0x20
+
+struct smc_llc_msg_del_link {		/* type 0x04 */
+	struct smc_llc_hdr hd;
+	u8 link_num;
+	__be32 reason;
+	u8 reserved[35];
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_llc_msg_test_link {		/* type 0x07 */
+	struct smc_llc_hdr hd;
+	u8 user_data[16];
+	u8 reserved[24];
+};
+
+struct smc_rmb_rtoken {
+	union {
+		u8 num_rkeys;	/* first rtoken byte of CONFIRM LINK msg */
+				/* is actually the num of rtokens, first */
+				/* rtoken is always for the current link */
+		u8 link_id;	/* link id of the rtoken */
+	};
+	__be32 rmb_key;
+	__be64 rmb_vaddr;
+} __packed;			/* format defined in RFC7609 */
+
+#define SMC_LLC_RKEYS_PER_MSG	3
+
+struct smc_llc_msg_confirm_rkey {	/* type 0x06 */
+	struct smc_llc_hdr hd;
+	struct smc_rmb_rtoken rtoken[SMC_LLC_RKEYS_PER_MSG];
+	u8 reserved;
+};
+
+struct smc_llc_msg_confirm_rkey_cont {	/* type 0x08 */
+	struct smc_llc_hdr hd;
+	u8 num_rkeys;
+	struct smc_rmb_rtoken rtoken[SMC_LLC_RKEYS_PER_MSG];
+};
+
+#define SMC_LLC_DEL_RKEY_MAX	8
+#define SMC_LLC_FLAG_RKEY_NEG	0x20
+
+struct smc_llc_msg_delete_rkey {	/* type 0x09 */
+	struct smc_llc_hdr hd;
+	u8 num_rkeys;
+	u8 err_mask;
+	u8 reserved[2];
+	__be32 rkey[8];
+	u8 reserved2[4];
+};
+
+union smc_llc_msg {
+	struct smc_llc_msg_confirm_link confirm_link;
+	struct smc_llc_msg_add_link add_link;
+	struct smc_llc_msg_del_link delete_link;
+
+	struct smc_llc_msg_confirm_rkey confirm_rkey;
+	struct smc_llc_msg_confirm_rkey_cont confirm_rkey_cont;
+	struct smc_llc_msg_delete_rkey delete_rkey;
+
+	struct smc_llc_msg_test_link test_link;
+	struct {
+		struct smc_llc_hdr hdr;
+		u8 data[SMC_LLC_DATA_LEN];
+	} raw;
+};
+
+#define SMC_LLC_FLAG_RESP		0x80
+
+/********************************** send *************************************/
+
+struct smc_llc_tx_pend {
+};
+
+/* handler for send/transmission completion of an LLC msg */
+static void smc_llc_tx_handler(struct smc_wr_tx_pend_priv *pend,
+			       struct smc_link *link,
+			       enum ib_wc_status wc_status)
+{
+	/* future work: handle wc_status error for recovery and failover */
+}
+
+/**
+ * smc_llc_add_pending_send() - add LLC control message to pending WQE transmits
+ * @link: Pointer to SMC link used for sending LLC control message.
+ * @wr_buf: Out variable returning pointer to work request payload buffer.
+ * @pend: Out variable returning pointer to private pending WR tracking.
+ *	  It's the context the transmit complete handler will get.
+ *
+ * Reserves and pre-fills an entry for a pending work request send/tx.
+ * Used by mid-level smc_llc_send_msg() to prepare for later actual send/tx.
+ * Can sleep due to smc_get_ctrl_buf (if not in softirq context).
+ *
+ * Return: 0 on success, otherwise an error value.
+ */
+static int smc_llc_add_pending_send(struct smc_link *link,
+				    struct smc_wr_buf **wr_buf,
+				    struct smc_wr_tx_pend_priv **pend)
+{
+	int rc;
+
+	rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend);
+	if (rc < 0)
+		return rc;
+	BUILD_BUG_ON_MSG(
+		sizeof(union smc_llc_msg) > SMC_WR_BUF_SIZE,
+		"must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_llc_msg)");
+	BUILD_BUG_ON_MSG(
+		sizeof(union smc_llc_msg) != SMC_WR_TX_SIZE,
+		"must adapt SMC_WR_TX_SIZE to sizeof(struct smc_llc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()");
+	BUILD_BUG_ON_MSG(
+		sizeof(struct smc_llc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE,
+		"must increase SMC_WR_TX_PEND_PRIV_SIZE to at least sizeof(struct smc_llc_tx_pend)");
+	return 0;
+}
+
+/* high-level API to send LLC confirm link */
+int smc_llc_send_confirm_link(struct smc_link *link,
+			      enum smc_llc_reqresp reqresp)
+{
+	struct smc_link_group *lgr = smc_get_lgr(link);
+	struct smc_llc_msg_confirm_link *confllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	confllc = (struct smc_llc_msg_confirm_link *)wr_buf;
+	memset(confllc, 0, sizeof(*confllc));
+	confllc->hd.common.type = SMC_LLC_CONFIRM_LINK;
+	confllc->hd.length = sizeof(struct smc_llc_msg_confirm_link);
+	confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC;
+	if (reqresp == SMC_LLC_RESP)
+		confllc->hd.flags |= SMC_LLC_FLAG_RESP;
+	memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1],
+	       ETH_ALEN);
+	memcpy(confllc->sender_gid, link->gid, SMC_GID_SIZE);
+	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
+	confllc->link_num = link->link_id;
+	memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE);
+	confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS; /* enforce peer resp. */
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* send LLC confirm rkey request */
+static int smc_llc_send_confirm_rkey(struct smc_link *link,
+				     struct smc_buf_desc *rmb_desc)
+{
+	struct smc_llc_msg_confirm_rkey *rkeyllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf;
+	memset(rkeyllc, 0, sizeof(*rkeyllc));
+	rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY;
+	rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey);
+	rkeyllc->rtoken[0].rmb_key =
+		htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+	rkeyllc->rtoken[0].rmb_vaddr = cpu_to_be64(
+		(u64)sg_dma_address(rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* prepare an add link message */
+static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
+				  struct smc_link *link, u8 mac[], u8 gid[],
+				  enum smc_llc_reqresp reqresp)
+{
+	memset(addllc, 0, sizeof(*addllc));
+	addllc->hd.common.type = SMC_LLC_ADD_LINK;
+	addllc->hd.length = sizeof(struct smc_llc_msg_add_link);
+	if (reqresp == SMC_LLC_RESP) {
+		addllc->hd.flags |= SMC_LLC_FLAG_RESP;
+		/* always reject more links for now */
+		addllc->hd.flags |= SMC_LLC_FLAG_ADD_LNK_REJ;
+		addllc->hd.add_link_rej_rsn = SMC_LLC_REJ_RSN_NO_ALT_PATH;
+	}
+	memcpy(addllc->sender_mac, mac, ETH_ALEN);
+	memcpy(addllc->sender_gid, gid, SMC_GID_SIZE);
+}
+
+/* send ADD LINK request or response */
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
+			  enum smc_llc_reqresp reqresp)
+{
+	struct smc_llc_msg_add_link *addllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	addllc = (struct smc_llc_msg_add_link *)wr_buf;
+	smc_llc_prep_add_link(addllc, link, mac, gid, reqresp);
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* prepare a delete link message */
+static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
+				     struct smc_link *link,
+				     enum smc_llc_reqresp reqresp, bool orderly)
+{
+	memset(delllc, 0, sizeof(*delllc));
+	delllc->hd.common.type = SMC_LLC_DELETE_LINK;
+	delllc->hd.length = sizeof(struct smc_llc_msg_add_link);
+	if (reqresp == SMC_LLC_RESP)
+		delllc->hd.flags |= SMC_LLC_FLAG_RESP;
+	/* DEL_LINK_ALL because only 1 link supported */
+	delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL;
+	if (orderly)
+		delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
+	delllc->link_num = link->link_id;
+}
+
+/* send DELETE LINK request or response */
+int smc_llc_send_delete_link(struct smc_link *link,
+			     enum smc_llc_reqresp reqresp, bool orderly)
+{
+	struct smc_llc_msg_del_link *delllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	delllc = (struct smc_llc_msg_del_link *)wr_buf;
+	smc_llc_prep_delete_link(delllc, link, reqresp, orderly);
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* send LLC test link request */
+static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16])
+{
+	struct smc_llc_msg_test_link *testllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	testllc = (struct smc_llc_msg_test_link *)wr_buf;
+	memset(testllc, 0, sizeof(*testllc));
+	testllc->hd.common.type = SMC_LLC_TEST_LINK;
+	testllc->hd.length = sizeof(struct smc_llc_msg_test_link);
+	memcpy(testllc->user_data, user_data, sizeof(testllc->user_data));
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+struct smc_llc_send_work {
+	struct work_struct work;
+	struct smc_link *link;
+	int llclen;
+	union smc_llc_msg llcbuf;
+};
+
+/* worker that sends a prepared message */
+static void smc_llc_send_message_work(struct work_struct *work)
+{
+	struct smc_llc_send_work *llcwrk = container_of(work,
+						struct smc_llc_send_work, work);
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	if (llcwrk->link->state == SMC_LNK_INACTIVE)
+		goto out;
+	rc = smc_llc_add_pending_send(llcwrk->link, &wr_buf, &pend);
+	if (rc)
+		goto out;
+	memcpy(wr_buf, &llcwrk->llcbuf, llcwrk->llclen);
+	smc_wr_tx_send(llcwrk->link, pend);
+out:
+	kfree(llcwrk);
+}
+
+/* copy llcbuf and schedule an llc send on link */
+static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
+{
+	struct smc_llc_send_work *wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+
+	if (!wrk)
+		return -ENOMEM;
+	INIT_WORK(&wrk->work, smc_llc_send_message_work);
+	wrk->link = link;
+	wrk->llclen = llclen;
+	memcpy(&wrk->llcbuf, llcbuf, llclen);
+	queue_work(link->llc_wq, &wrk->work);
+	return 0;
+}
+
+/********************************* receive ***********************************/
+
+static void smc_llc_rx_confirm_link(struct smc_link *link,
+				    struct smc_llc_msg_confirm_link *llc)
+{
+	struct smc_link_group *lgr = smc_get_lgr(link);
+	int conf_rc;
+
+	/* RMBE eyecatchers are not supported */
+	if (llc->hd.flags & SMC_LLC_FLAG_NO_RMBE_EYEC)
+		conf_rc = 0;
+	else
+		conf_rc = ENOTSUPP;
+
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		if (lgr->role == SMC_SERV &&
+		    link->state == SMC_LNK_ACTIVATING) {
+			link->llc_confirm_resp_rc = conf_rc;
+			complete(&link->llc_confirm_resp);
+		}
+	} else {
+		if (lgr->role == SMC_CLNT &&
+		    link->state == SMC_LNK_ACTIVATING) {
+			link->llc_confirm_rc = conf_rc;
+			link->link_id = llc->link_num;
+			complete(&link->llc_confirm);
+		}
+	}
+}
+
+static void smc_llc_rx_add_link(struct smc_link *link,
+				struct smc_llc_msg_add_link *llc)
+{
+	struct smc_link_group *lgr = smc_get_lgr(link);
+
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		if (link->state == SMC_LNK_ACTIVATING)
+			complete(&link->llc_add_resp);
+	} else {
+		if (link->state == SMC_LNK_ACTIVATING) {
+			complete(&link->llc_add);
+			return;
+		}
+
+		if (lgr->role == SMC_SERV) {
+			smc_llc_prep_add_link(llc, link,
+					link->smcibdev->mac[link->ibport - 1],
+					link->gid, SMC_LLC_REQ);
+
+		} else {
+			smc_llc_prep_add_link(llc, link,
+					link->smcibdev->mac[link->ibport - 1],
+					link->gid, SMC_LLC_RESP);
+		}
+		smc_llc_send_message(link, llc, sizeof(*llc));
+	}
+}
+
+static void smc_llc_rx_delete_link(struct smc_link *link,
+				   struct smc_llc_msg_del_link *llc)
+{
+	struct smc_link_group *lgr = smc_get_lgr(link);
+
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		if (lgr->role == SMC_SERV)
+			smc_lgr_schedule_free_work_fast(lgr);
+	} else {
+		smc_lgr_forget(lgr);
+		smc_llc_link_deleting(link);
+		if (lgr->role == SMC_SERV) {
+			/* client asks to delete this link, send request */
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ, true);
+		} else {
+			/* server requests to delete this link, send response */
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP, true);
+		}
+		smc_llc_send_message(link, llc, sizeof(*llc));
+		smc_lgr_schedule_free_work_fast(lgr);
+	}
+}
+
+static void smc_llc_rx_test_link(struct smc_link *link,
+				 struct smc_llc_msg_test_link *llc)
+{
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		if (link->state == SMC_LNK_ACTIVE)
+			complete(&link->llc_testlink_resp);
+	} else {
+		llc->hd.flags |= SMC_LLC_FLAG_RESP;
+		smc_llc_send_message(link, llc, sizeof(*llc));
+	}
+}
+
+static void smc_llc_rx_confirm_rkey(struct smc_link *link,
+				    struct smc_llc_msg_confirm_rkey *llc)
+{
+	int rc;
+
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		link->llc_confirm_rkey_rc = llc->hd.flags &
+					    SMC_LLC_FLAG_RKEY_NEG;
+		complete(&link->llc_confirm_rkey);
+	} else {
+		rc = smc_rtoken_add(smc_get_lgr(link),
+				    llc->rtoken[0].rmb_vaddr,
+				    llc->rtoken[0].rmb_key);
+
+		/* ignore rtokens for other links, we have only one link */
+
+		llc->hd.flags |= SMC_LLC_FLAG_RESP;
+		if (rc < 0)
+			llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG;
+		smc_llc_send_message(link, llc, sizeof(*llc));
+	}
+}
+
+static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link,
+				      struct smc_llc_msg_confirm_rkey_cont *llc)
+{
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		/* unused as long as we don't send this type of msg */
+	} else {
+		/* ignore rtokens for other links, we have only one link */
+		llc->hd.flags |= SMC_LLC_FLAG_RESP;
+		smc_llc_send_message(link, llc, sizeof(*llc));
+	}
+}
+
+static void smc_llc_rx_delete_rkey(struct smc_link *link,
+				   struct smc_llc_msg_delete_rkey *llc)
+{
+	u8 err_mask = 0;
+	int i, max;
+
+	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
+		/* unused as long as we don't send this type of msg */
+	} else {
+		max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX);
+		for (i = 0; i < max; i++) {
+			if (smc_rtoken_delete(smc_get_lgr(link), llc->rkey[i]))
+				err_mask |= 1 << (SMC_LLC_DEL_RKEY_MAX - 1 - i);
+		}
+
+		if (err_mask) {
+			llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG;
+			llc->err_mask = err_mask;
+		}
+
+		llc->hd.flags |= SMC_LLC_FLAG_RESP;
+		smc_llc_send_message(link, llc, sizeof(*llc));
+	}
+}
+
+static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
+{
+	struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
+	union smc_llc_msg *llc = buf;
+
+	if (wc->byte_len < sizeof(*llc))
+		return; /* short message */
+	if (llc->raw.hdr.length != sizeof(*llc))
+		return; /* invalid message */
+	if (link->state == SMC_LNK_INACTIVE)
+		return; /* link not active, drop msg */
+
+	switch (llc->raw.hdr.common.type) {
+	case SMC_LLC_TEST_LINK:
+		smc_llc_rx_test_link(link, &llc->test_link);
+		break;
+	case SMC_LLC_CONFIRM_LINK:
+		smc_llc_rx_confirm_link(link, &llc->confirm_link);
+		break;
+	case SMC_LLC_ADD_LINK:
+		smc_llc_rx_add_link(link, &llc->add_link);
+		break;
+	case SMC_LLC_DELETE_LINK:
+		smc_llc_rx_delete_link(link, &llc->delete_link);
+		break;
+	case SMC_LLC_CONFIRM_RKEY:
+		smc_llc_rx_confirm_rkey(link, &llc->confirm_rkey);
+		break;
+	case SMC_LLC_CONFIRM_RKEY_CONT:
+		smc_llc_rx_confirm_rkey_cont(link, &llc->confirm_rkey_cont);
+		break;
+	case SMC_LLC_DELETE_RKEY:
+		smc_llc_rx_delete_rkey(link, &llc->delete_rkey);
+		break;
+	}
+}
+
+/***************************** worker, utils *********************************/
+
+static void smc_llc_testlink_work(struct work_struct *work)
+{
+	struct smc_link *link = container_of(to_delayed_work(work),
+					     struct smc_link, llc_testlink_wrk);
+	unsigned long next_interval;
+	unsigned long expire_time;
+	u8 user_data[16] = { 0 };
+	int rc;
+
+	if (link->state != SMC_LNK_ACTIVE)
+		return;		/* don't reschedule worker */
+	expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
+	if (time_is_after_jiffies(expire_time)) {
+		next_interval = expire_time - jiffies;
+		goto out;
+	}
+	reinit_completion(&link->llc_testlink_resp);
+	smc_llc_send_test_link(link, user_data);
+	/* receive TEST LINK response over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0) {
+		smc_lgr_terminate(smc_get_lgr(link));
+		return;
+	}
+	next_interval = link->llc_testlink_time;
+out:
+	queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+			   next_interval);
+}
+
+int smc_llc_link_init(struct smc_link *link)
+{
+	struct smc_link_group *lgr = smc_get_lgr(link);
+	link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM,
+					       *((u32 *)lgr->id),
+					       link->link_id);
+	if (!link->llc_wq)
+		return -ENOMEM;
+	init_completion(&link->llc_confirm);
+	init_completion(&link->llc_confirm_resp);
+	init_completion(&link->llc_add);
+	init_completion(&link->llc_add_resp);
+	init_completion(&link->llc_confirm_rkey);
+	init_completion(&link->llc_testlink_resp);
+	INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
+	return 0;
+}
+
+void smc_llc_link_active(struct smc_link *link, int testlink_time)
+{
+	link->state = SMC_LNK_ACTIVE;
+	if (testlink_time) {
+		link->llc_testlink_time = testlink_time * HZ;
+		queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+				   link->llc_testlink_time);
+	}
+}
+
+void smc_llc_link_deleting(struct smc_link *link)
+{
+	link->state = SMC_LNK_DELETING;
+}
+
+/* called in tasklet context */
+void smc_llc_link_inactive(struct smc_link *link)
+{
+	link->state = SMC_LNK_INACTIVE;
+	cancel_delayed_work(&link->llc_testlink_wrk);
+}
+
+/* called in worker context */
+void smc_llc_link_clear(struct smc_link *link)
+{
+	flush_workqueue(link->llc_wq);
+	destroy_workqueue(link->llc_wq);
+}
+
+/* register a new rtoken at the remote peer */
+int smc_llc_do_confirm_rkey(struct smc_link *link,
+			    struct smc_buf_desc *rmb_desc)
+{
+	int rc;
+
+	reinit_completion(&link->llc_confirm_rkey);
+	smc_llc_send_confirm_rkey(link, rmb_desc);
+	/* receive CONFIRM RKEY response from server over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0 || link->llc_confirm_rkey_rc)
+		return -EFAULT;
+	return 0;
+}
+
+/***************************** init, exit, misc ******************************/
+
+static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_CONFIRM_LINK
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_TEST_LINK
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_ADD_LINK
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_DELETE_LINK
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_CONFIRM_RKEY
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_CONFIRM_RKEY_CONT
+	},
+	{
+		.handler	= smc_llc_rx_handler,
+		.type		= SMC_LLC_DELETE_RKEY
+	},
+	{
+		.handler	= NULL,
+	}
+};
+
+int __init smc_llc_init(void)
+{
+	struct smc_wr_rx_handler *handler;
+	int rc = 0;
+
+	for (handler = smc_llc_rx_handlers; handler->handler; handler++) {
+		INIT_HLIST_NODE(&handler->list);
+		rc = smc_wr_rx_register_handler(handler);
+		if (rc)
+			break;
+	}
+	return rc;
+}
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
new file mode 100644
index 000000000..9e2ff088e
--- /dev/null
+++ b/net/smc/smc_llc.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for LLC (link layer control) message handling
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Klaus Wacker <Klaus.Wacker@de.ibm.com>
+ *              Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_LLC_H
+#define SMC_LLC_H
+
+#include "smc_wr.h"
+
+#define SMC_LLC_FLAG_RESP		0x80
+
+#define SMC_LLC_WAIT_FIRST_TIME		(5 * HZ)
+#define SMC_LLC_WAIT_TIME		(2 * HZ)
+
+enum smc_llc_reqresp {
+	SMC_LLC_REQ,
+	SMC_LLC_RESP
+};
+
+enum smc_llc_msg_type {
+	SMC_LLC_CONFIRM_LINK		= 0x01,
+	SMC_LLC_ADD_LINK		= 0x02,
+	SMC_LLC_DELETE_LINK		= 0x04,
+	SMC_LLC_CONFIRM_RKEY		= 0x06,
+	SMC_LLC_TEST_LINK		= 0x07,
+	SMC_LLC_CONFIRM_RKEY_CONT	= 0x08,
+	SMC_LLC_DELETE_RKEY		= 0x09,
+};
+
+/* transmit */
+int smc_llc_send_confirm_link(struct smc_link *lnk,
+			      enum smc_llc_reqresp reqresp);
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
+			  enum smc_llc_reqresp reqresp);
+int smc_llc_send_delete_link(struct smc_link *link,
+			     enum smc_llc_reqresp reqresp, bool orderly);
+int smc_llc_link_init(struct smc_link *link);
+void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_deleting(struct smc_link *link);
+void smc_llc_link_inactive(struct smc_link *link);
+void smc_llc_link_clear(struct smc_link *link);
+int smc_llc_do_confirm_rkey(struct smc_link *link,
+			    struct smc_buf_desc *rmb_desc);
+int smc_llc_init(void) __init;
+
+#endif /* SMC_LLC_H */
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
new file mode 100644
index 000000000..7cb3e4f07
--- /dev/null
+++ b/net/smc/smc_pnet.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Generic netlink support functions to configure an SMC-R PNET table
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Thomas Richter <tmricht@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/ctype.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/if.h>
+#include <uapi/linux/smc.h>
+
+#include <rdma/ib_verbs.h>
+
+#include "smc_pnet.h"
+#include "smc_ib.h"
+#include "smc_ism.h"
+
+static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
+	[SMC_PNETID_NAME] = {
+		.type = NLA_NUL_STRING,
+		.len = SMC_MAX_PNETID_LEN - 1
+	},
+	[SMC_PNETID_ETHNAME] = {
+		.type = NLA_NUL_STRING,
+		.len = IFNAMSIZ - 1
+	},
+	[SMC_PNETID_IBNAME] = {
+		.type = NLA_NUL_STRING,
+		.len = IB_DEVICE_NAME_MAX - 1
+	},
+	[SMC_PNETID_IBPORT] = { .type = NLA_U8 }
+};
+
+static struct genl_family smc_pnet_nl_family;
+
+/**
+ * struct smc_pnettable - SMC PNET table anchor
+ * @lock: Lock for list action
+ * @pnetlist: List of PNETIDs
+ */
+static struct smc_pnettable {
+	rwlock_t lock;
+	struct list_head pnetlist;
+} smc_pnettable = {
+	.pnetlist = LIST_HEAD_INIT(smc_pnettable.pnetlist),
+	.lock = __RW_LOCK_UNLOCKED(smc_pnettable.lock)
+};
+
+/**
+ * struct smc_pnetentry - pnet identifier name entry
+ * @list: List node.
+ * @pnet_name: Pnet identifier name
+ * @ndev: pointer to network device.
+ * @smcibdev: Pointer to IB device.
+ */
+struct smc_pnetentry {
+	struct list_head list;
+	char pnet_name[SMC_MAX_PNETID_LEN + 1];
+	struct net_device *ndev;
+	struct smc_ib_device *smcibdev;
+	u8 ib_port;
+};
+
+/* Check if two RDMA device entries are identical. Use device name and port
+ * number for comparison.
+ */
+static bool smc_pnet_same_ibname(struct smc_pnetentry *pnetelem, char *ibname,
+				 u8 ibport)
+{
+	return pnetelem->ib_port == ibport &&
+	       !strncmp(pnetelem->smcibdev->ibdev->name, ibname,
+			sizeof(pnetelem->smcibdev->ibdev->name));
+}
+
+/* Find a pnetid in the pnet table.
+ */
+static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name)
+{
+	struct smc_pnetentry *pnetelem, *found_pnetelem = NULL;
+
+	read_lock(&smc_pnettable.lock);
+	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+		if (!strncmp(pnetelem->pnet_name, pnet_name,
+			     sizeof(pnetelem->pnet_name))) {
+			found_pnetelem = pnetelem;
+			break;
+		}
+	}
+	read_unlock(&smc_pnettable.lock);
+	return found_pnetelem;
+}
+
+/* Remove a pnetid from the pnet table.
+ */
+static int smc_pnet_remove_by_pnetid(char *pnet_name)
+{
+	struct smc_pnetentry *pnetelem, *tmp_pe;
+	int rc = -ENOENT;
+
+	write_lock(&smc_pnettable.lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+				 list) {
+		if (!strncmp(pnetelem->pnet_name, pnet_name,
+			     sizeof(pnetelem->pnet_name))) {
+			list_del(&pnetelem->list);
+			dev_put(pnetelem->ndev);
+			kfree(pnetelem);
+			rc = 0;
+			break;
+		}
+	}
+	write_unlock(&smc_pnettable.lock);
+	return rc;
+}
+
+/* Remove a pnet entry mentioning a given network device from the pnet table.
+ */
+static int smc_pnet_remove_by_ndev(struct net_device *ndev)
+{
+	struct smc_pnetentry *pnetelem, *tmp_pe;
+	int rc = -ENOENT;
+
+	write_lock(&smc_pnettable.lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+				 list) {
+		if (pnetelem->ndev == ndev) {
+			list_del(&pnetelem->list);
+			dev_put(pnetelem->ndev);
+			kfree(pnetelem);
+			rc = 0;
+			break;
+		}
+	}
+	write_unlock(&smc_pnettable.lock);
+	return rc;
+}
+
+/* Remove a pnet entry mentioning a given ib device from the pnet table.
+ */
+int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev)
+{
+	struct smc_pnetentry *pnetelem, *tmp_pe;
+	int rc = -ENOENT;
+
+	write_lock(&smc_pnettable.lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+				 list) {
+		if (pnetelem->smcibdev == ibdev) {
+			list_del(&pnetelem->list);
+			dev_put(pnetelem->ndev);
+			kfree(pnetelem);
+			rc = 0;
+			break;
+		}
+	}
+	write_unlock(&smc_pnettable.lock);
+	return rc;
+}
+
+/* Append a pnetid to the end of the pnet table if not already on this list.
+ */
+static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem)
+{
+	struct smc_pnetentry *pnetelem;
+	int rc = -EEXIST;
+
+	write_lock(&smc_pnettable.lock);
+	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+		if (!strncmp(pnetelem->pnet_name, new_pnetelem->pnet_name,
+			     sizeof(new_pnetelem->pnet_name)) ||
+		    !strncmp(pnetelem->ndev->name, new_pnetelem->ndev->name,
+			     sizeof(new_pnetelem->ndev->name)) ||
+		    smc_pnet_same_ibname(pnetelem,
+					 new_pnetelem->smcibdev->ibdev->name,
+					 new_pnetelem->ib_port)) {
+			dev_put(pnetelem->ndev);
+			goto found;
+		}
+	}
+	list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
+	rc = 0;
+found:
+	write_unlock(&smc_pnettable.lock);
+	return rc;
+}
+
+/* The limit for pnetid is 16 characters.
+ * Valid characters should be (single-byte character set) a-z, A-Z, 0-9.
+ * Lower case letters are converted to upper case.
+ * Interior blanks should not be used.
+ */
+static bool smc_pnetid_valid(const char *pnet_name, char *pnetid)
+{
+	char *bf = skip_spaces(pnet_name);
+	size_t len = strlen(bf);
+	char *end = bf + len;
+
+	if (!len)
+		return false;
+	while (--end >= bf && isspace(*end))
+		;
+	if (end - bf >= SMC_MAX_PNETID_LEN)
+		return false;
+	while (bf <= end) {
+		if (!isalnum(*bf))
+			return false;
+		*pnetid++ = islower(*bf) ? toupper(*bf) : *bf;
+		bf++;
+	}
+	*pnetid = '\0';
+	return true;
+}
+
+/* Find an infiniband device by a given name. The device might not exist. */
+static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
+{
+	struct smc_ib_device *ibdev;
+
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		if (!strncmp(ibdev->ibdev->name, ib_name,
+			     sizeof(ibdev->ibdev->name))) {
+			goto out;
+		}
+	}
+	ibdev = NULL;
+out:
+	spin_unlock(&smc_ib_devices.lock);
+	return ibdev;
+}
+
+/* Parse the supplied netlink attributes and fill a pnetentry structure.
+ * For ethernet and infiniband device names verify that the devices exist.
+ */
+static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
+			       struct nlattr *tb[])
+{
+	char *string, *ibname;
+	int rc;
+
+	memset(pnetelem, 0, sizeof(*pnetelem));
+	INIT_LIST_HEAD(&pnetelem->list);
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_NAME])
+		goto error;
+	string = (char *)nla_data(tb[SMC_PNETID_NAME]);
+	if (!smc_pnetid_valid(string, pnetelem->pnet_name))
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_ETHNAME])
+		goto error;
+	rc = -ENOENT;
+	string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+	pnetelem->ndev = dev_get_by_name(net, string);
+	if (!pnetelem->ndev)
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_IBNAME])
+		goto error;
+	rc = -ENOENT;
+	ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+	ibname = strim(ibname);
+	pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+	if (!pnetelem->smcibdev)
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_IBPORT])
+		goto error;
+	pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+	if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
+		goto error;
+
+	return 0;
+
+error:
+	if (pnetelem->ndev)
+		dev_put(pnetelem->ndev);
+	return rc;
+}
+
+/* Convert an smc_pnetentry to a netlink attribute sequence */
+static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem)
+{
+	if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name) ||
+	    nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->ndev->name) ||
+	    nla_put_string(msg, SMC_PNETID_IBNAME,
+			   pnetelem->smcibdev->ibdev->name) ||
+	    nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
+		return -1;
+	return 0;
+}
+
+/* Retrieve one PNETID entry */
+static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct smc_pnetentry *pnetelem;
+	struct sk_buff *msg;
+	void *hdr;
+	int rc;
+
+	if (!info->attrs[SMC_PNETID_NAME])
+		return -EINVAL;
+	pnetelem = smc_pnet_find_pnetid(
+				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
+	if (!pnetelem)
+		return -ENOENT;
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+			  &smc_pnet_nl_family, 0, SMC_PNETID_GET);
+	if (!hdr) {
+		rc = -EMSGSIZE;
+		goto err_out;
+	}
+
+	if (smc_pnet_set_nla(msg, pnetelem)) {
+		rc = -ENOBUFS;
+		goto err_out;
+	}
+
+	genlmsg_end(msg, hdr);
+	return genlmsg_reply(msg, info);
+
+err_out:
+	nlmsg_free(msg);
+	return rc;
+}
+
+static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct smc_pnetentry *pnetelem;
+	int rc;
+
+	pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
+	if (!pnetelem)
+		return -ENOMEM;
+	rc = smc_pnet_fill_entry(net, pnetelem, info->attrs);
+	if (!rc)
+		rc = smc_pnet_enter(pnetelem);
+	if (rc) {
+		kfree(pnetelem);
+		return rc;
+	}
+	return rc;
+}
+
+static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
+{
+	if (!info->attrs[SMC_PNETID_NAME])
+		return -EINVAL;
+	return smc_pnet_remove_by_pnetid(
+				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
+}
+
+static int smc_pnet_dump_start(struct netlink_callback *cb)
+{
+	cb->args[0] = 0;
+	return 0;
+}
+
+static int smc_pnet_dumpinfo(struct sk_buff *skb,
+			     u32 portid, u32 seq, u32 flags,
+			     struct smc_pnetentry *pnetelem)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family,
+			  flags, SMC_PNETID_GET);
+	if (!hdr)
+		return -ENOMEM;
+	if (smc_pnet_set_nla(skb, pnetelem) < 0) {
+		genlmsg_cancel(skb, hdr);
+		return -EMSGSIZE;
+	}
+	genlmsg_end(skb, hdr);
+	return 0;
+}
+
+static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct smc_pnetentry *pnetelem;
+	int idx = 0;
+
+	read_lock(&smc_pnettable.lock);
+	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+		if (idx++ < cb->args[0])
+			continue;
+		if (smc_pnet_dumpinfo(skb, NETLINK_CB(cb->skb).portid,
+				      cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				      pnetelem)) {
+			--idx;
+			break;
+		}
+	}
+	cb->args[0] = idx;
+	read_unlock(&smc_pnettable.lock);
+	return skb->len;
+}
+
+/* Remove and delete all pnetids from pnet table.
+ */
+static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
+{
+	struct smc_pnetentry *pnetelem, *tmp_pe;
+
+	write_lock(&smc_pnettable.lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+				 list) {
+		list_del(&pnetelem->list);
+		dev_put(pnetelem->ndev);
+		kfree(pnetelem);
+	}
+	write_unlock(&smc_pnettable.lock);
+	return 0;
+}
+
+/* SMC_PNETID generic netlink operation definition */
+static const struct genl_ops smc_pnet_ops[] = {
+	{
+		.cmd = SMC_PNETID_GET,
+		.flags = GENL_ADMIN_PERM,
+		.policy = smc_pnet_policy,
+		.doit = smc_pnet_get,
+		.dumpit = smc_pnet_dump,
+		.start = smc_pnet_dump_start
+	},
+	{
+		.cmd = SMC_PNETID_ADD,
+		.flags = GENL_ADMIN_PERM,
+		.policy = smc_pnet_policy,
+		.doit = smc_pnet_add
+	},
+	{
+		.cmd = SMC_PNETID_DEL,
+		.flags = GENL_ADMIN_PERM,
+		.policy = smc_pnet_policy,
+		.doit = smc_pnet_del
+	},
+	{
+		.cmd = SMC_PNETID_FLUSH,
+		.flags = GENL_ADMIN_PERM,
+		.policy = smc_pnet_policy,
+		.doit = smc_pnet_flush
+	}
+};
+
+/* SMC_PNETID family definition */
+static struct genl_family smc_pnet_nl_family __ro_after_init = {
+	.hdrsize = 0,
+	.name = SMCR_GENL_FAMILY_NAME,
+	.version = SMCR_GENL_FAMILY_VERSION,
+	.maxattr = SMC_PNETID_MAX,
+	.netnsok = true,
+	.module = THIS_MODULE,
+	.ops = smc_pnet_ops,
+	.n_ops =  ARRAY_SIZE(smc_pnet_ops)
+};
+
+static int smc_pnet_netdev_event(struct notifier_block *this,
+				 unsigned long event, void *ptr)
+{
+	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_REBOOT:
+	case NETDEV_UNREGISTER:
+		smc_pnet_remove_by_ndev(event_dev);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block smc_netdev_notifier = {
+	.notifier_call = smc_pnet_netdev_event
+};
+
+int __init smc_pnet_init(void)
+{
+	int rc;
+
+	rc = genl_register_family(&smc_pnet_nl_family);
+	if (rc)
+		return rc;
+	rc = register_netdevice_notifier(&smc_netdev_notifier);
+	if (rc)
+		genl_unregister_family(&smc_pnet_nl_family);
+	return rc;
+}
+
+void smc_pnet_exit(void)
+{
+	smc_pnet_flush(NULL, NULL);
+	unregister_netdevice_notifier(&smc_netdev_notifier);
+	genl_unregister_family(&smc_pnet_nl_family);
+}
+
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
+ */
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
+{
+	int i, nest_lvl;
+
+	rtnl_lock();
+	nest_lvl = dev_get_nest_level(ndev);
+	for (i = 0; i < nest_lvl; i++) {
+		struct list_head *lower = &ndev->adj_list.lower;
+
+		if (list_empty(lower))
+			break;
+		lower = lower->next;
+		ndev = netdev_lower_get_next(ndev, &lower);
+	}
+	rtnl_unlock();
+	return ndev;
+}
+
+/* Determine the corresponding IB device port based on the hardware PNETID.
+ * Searching stops at the first matching active IB device port with vlan_id
+ * configured.
+ */
+static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
+					 struct smc_ib_device **smcibdev,
+					 u8 *ibport, unsigned short vlan_id,
+					 u8 gid[])
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smc_ib_device *ibdev;
+	int i;
+
+	ndev = pnet_find_base_ndev(ndev);
+	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				   ndev_pnetid))
+		return; /* pnetid could not be determined */
+
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		for (i = 1; i <= SMC_MAX_PORTS; i++) {
+			if (!rdma_is_port_valid(ibdev->ibdev, i))
+				continue;
+			if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
+				    SMC_MAX_PNETID_LEN) &&
+			    smc_ib_port_active(ibdev, i) &&
+			    !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
+						  NULL))  {
+				*smcibdev = ibdev;
+				*ibport = i;
+				goto out;
+			}
+		}
+	}
+out:
+	spin_unlock(&smc_ib_devices.lock);
+}
+
+static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
+					struct smcd_dev **smcismdev)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smcd_dev *ismdev;
+
+	ndev = pnet_find_base_ndev(ndev);
+	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				   ndev_pnetid))
+		return; /* pnetid could not be determined */
+
+	spin_lock(&smcd_dev_list.lock);
+	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
+		if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) {
+			*smcismdev = ismdev;
+			break;
+		}
+	}
+	spin_unlock(&smcd_dev_list.lock);
+}
+
+/* Lookup of coupled ib_device via SMC pnet table */
+static void smc_pnet_find_roce_by_table(struct net_device *netdev,
+					struct smc_ib_device **smcibdev,
+					u8 *ibport, unsigned short vlan_id,
+					u8 gid[])
+{
+	struct smc_pnetentry *pnetelem;
+
+	read_lock(&smc_pnettable.lock);
+	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+		if (netdev == pnetelem->ndev) {
+			if (smc_ib_port_active(pnetelem->smcibdev,
+					       pnetelem->ib_port) &&
+			    !smc_ib_determine_gid(pnetelem->smcibdev,
+						  pnetelem->ib_port, vlan_id,
+						  gid, NULL)) {
+				*smcibdev = pnetelem->smcibdev;
+				*ibport = pnetelem->ib_port;
+			}
+			break;
+		}
+	}
+	read_unlock(&smc_pnettable.lock);
+}
+
+/* PNET table analysis for a given sock:
+ * determine ib_device and port belonging to used internal TCP socket
+ * ethernet interface.
+ */
+void smc_pnet_find_roce_resource(struct sock *sk,
+				 struct smc_ib_device **smcibdev, u8 *ibport,
+				 unsigned short vlan_id, u8 gid[])
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+
+	*smcibdev = NULL;
+	*ibport = 0;
+
+	if (!dst)
+		goto out;
+	if (!dst->dev)
+		goto out_rel;
+
+	/* if possible, lookup via hardware-defined pnetid */
+	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
+	if (*smcibdev)
+		goto out_rel;
+
+	/* lookup via SMC PNET table */
+	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport, vlan_id, gid);
+
+out_rel:
+	dst_release(dst);
+out:
+	return;
+}
+
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+
+	*smcismdev = NULL;
+	if (!dst)
+		goto out;
+	if (!dst->dev)
+		goto out_rel;
+
+	/* if possible, lookup via hardware-defined pnetid */
+	smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+
+out_rel:
+	dst_release(dst);
+out:
+	return;
+}
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
new file mode 100644
index 000000000..8ff777636
--- /dev/null
+++ b/net/smc/smc_pnet.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  PNET table queries
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Thomas Richter <tmricht@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_PNET_H
+#define _SMC_PNET_H
+
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+#include <asm/pnet.h>
+#endif
+
+struct smc_ib_device;
+struct smcd_dev;
+
+static inline int smc_pnetid_by_dev_port(struct device *dev,
+					 unsigned short port, u8 *pnetid)
+{
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+	return pnet_id_by_dev_port(dev, port, pnetid);
+#else
+	return -ENOENT;
+#endif
+}
+
+int smc_pnet_init(void) __init;
+void smc_pnet_exit(void);
+int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
+void smc_pnet_find_roce_resource(struct sock *sk,
+				 struct smc_ib_device **smcibdev, u8 *ibport,
+				 unsigned short vlan_id, u8 gid[]);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
+
+#endif
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
new file mode 100644
index 000000000..a7a4e3ce2
--- /dev/null
+++ b/net/smc/smc_rx.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Manage RMBE
+ * copy new RMBE data into user space
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/net.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
+
+#include <net/sock.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_cdc.h"
+#include "smc_tx.h" /* smc_tx_consumer_update() */
+#include "smc_rx.h"
+
+/* callback implementation to wakeup consumers blocked with smc_rx_wait().
+ * indirectly called by smc_cdc_msg_recv_action().
+ */
+static void smc_rx_wake_up(struct sock *sk)
+{
+	struct socket_wq *wq;
+
+	/* derived from sock_def_readable() */
+	/* called already in smc_listen_work() */
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (skwq_has_sleeper(wq))
+		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
+						EPOLLRDNORM | EPOLLRDBAND);
+	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+	if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
+	    (sk->sk_state == SMC_CLOSED))
+		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+	rcu_read_unlock();
+}
+
+/* Update consumer cursor
+ *   @conn   connection to update
+ *   @cons   consumer cursor
+ *   @len    number of Bytes consumed
+ *   Returns:
+ *   1 if we should end our receive, 0 otherwise
+ */
+static int smc_rx_update_consumer(struct smc_sock *smc,
+				  union smc_host_cursor cons, size_t len)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct sock *sk = &smc->sk;
+	bool force = false;
+	int diff, rc = 0;
+
+	smc_curs_add(conn->rmb_desc->len, &cons, len);
+
+	/* did we process urgent data? */
+	if (conn->urg_state == SMC_URG_VALID || conn->urg_rx_skip_pend) {
+		diff = smc_curs_comp(conn->rmb_desc->len, &cons,
+				     &conn->urg_curs);
+		if (sock_flag(sk, SOCK_URGINLINE)) {
+			if (diff == 0) {
+				force = true;
+				rc = 1;
+				conn->urg_state = SMC_URG_READ;
+			}
+		} else {
+			if (diff == 1) {
+				/* skip urgent byte */
+				force = true;
+				smc_curs_add(conn->rmb_desc->len, &cons, 1);
+				conn->urg_rx_skip_pend = false;
+			} else if (diff < -1)
+				/* we read past urgent byte */
+				conn->urg_state = SMC_URG_READ;
+		}
+	}
+
+	smc_curs_copy(&conn->local_tx_ctrl.cons, &cons, conn);
+
+	/* send consumer cursor update if required */
+	/* similar to advertising new TCP rcv_wnd if required */
+	smc_tx_consumer_update(conn, force);
+
+	return rc;
+}
+
+static void smc_rx_update_cons(struct smc_sock *smc, size_t len)
+{
+	struct smc_connection *conn = &smc->conn;
+	union smc_host_cursor cons;
+
+	smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+	smc_rx_update_consumer(smc, cons, len);
+}
+
+struct smc_spd_priv {
+	struct smc_sock *smc;
+	size_t		 len;
+};
+
+static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private;
+	struct smc_sock *smc = priv->smc;
+	struct smc_connection *conn;
+	struct sock *sk = &smc->sk;
+
+	if (sk->sk_state == SMC_CLOSED ||
+	    sk->sk_state == SMC_PEERFINCLOSEWAIT ||
+	    sk->sk_state == SMC_APPFINCLOSEWAIT)
+		goto out;
+	conn = &smc->conn;
+	lock_sock(sk);
+	smc_rx_update_cons(smc, priv->len);
+	release_sock(sk);
+	if (atomic_sub_and_test(priv->len, &conn->splice_pending))
+		smc_rx_wake_up(sk);
+out:
+	kfree(priv);
+	put_page(buf->page);
+	sock_put(sk);
+}
+
+static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+				   struct pipe_buffer *buf)
+{
+	return 1;
+}
+
+static const struct pipe_buf_operations smc_pipe_ops = {
+	.can_merge = 0,
+	.confirm = generic_pipe_buf_confirm,
+	.release = smc_rx_pipe_buf_release,
+	.steal = smc_rx_pipe_buf_nosteal,
+	.get = generic_pipe_buf_get
+};
+
+static void smc_rx_spd_release(struct splice_pipe_desc *spd,
+			       unsigned int i)
+{
+	put_page(spd->pages[i]);
+}
+
+static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
+			 struct smc_sock *smc)
+{
+	struct splice_pipe_desc spd;
+	struct partial_page partial;
+	struct smc_spd_priv *priv;
+	int bytes;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->len = len;
+	priv->smc = smc;
+	partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr;
+	partial.len = len;
+	partial.private = (unsigned long)priv;
+
+	spd.nr_pages_max = 1;
+	spd.nr_pages = 1;
+	spd.pages = &smc->conn.rmb_desc->pages;
+	spd.partial = &partial;
+	spd.ops = &smc_pipe_ops;
+	spd.spd_release = smc_rx_spd_release;
+
+	bytes = splice_to_pipe(pipe, &spd);
+	if (bytes > 0) {
+		sock_hold(&smc->sk);
+		get_page(smc->conn.rmb_desc->pages);
+		atomic_add(bytes, &smc->conn.splice_pending);
+	}
+
+	return bytes;
+}
+
+static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn)
+{
+	return atomic_read(&conn->bytes_to_rcv) &&
+	       !atomic_read(&conn->splice_pending);
+}
+
+/* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted
+ *   @smc    smc socket
+ *   @timeo  pointer to max seconds to wait, pointer to value 0 for no timeout
+ *   @fcrit  add'l criterion to evaluate as function pointer
+ * Returns:
+ * 1 if at least 1 byte available in rcvbuf or if socket error/shutdown.
+ * 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted).
+ */
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+		int (*fcrit)(struct smc_connection *conn))
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	struct smc_connection *conn = &smc->conn;
+	struct sock *sk = &smc->sk;
+	int rc;
+
+	if (fcrit(conn))
+		return 1;
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	add_wait_queue(sk_sleep(sk), &wait);
+	rc = sk_wait_event(sk, timeo,
+			   sk->sk_err ||
+			   sk->sk_shutdown & RCV_SHUTDOWN ||
+			   fcrit(conn),
+			   &wait);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	return rc;
+}
+
+static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
+			   int flags)
+{
+	struct smc_connection *conn = &smc->conn;
+	union smc_host_cursor cons;
+	struct sock *sk = &smc->sk;
+	int rc = 0;
+
+	if (sock_flag(sk, SOCK_URGINLINE) ||
+	    !(conn->urg_state == SMC_URG_VALID) ||
+	    conn->urg_state == SMC_URG_READ)
+		return -EINVAL;
+
+	if (conn->urg_state == SMC_URG_VALID) {
+		if (!(flags & MSG_PEEK))
+			smc->conn.urg_state = SMC_URG_READ;
+		msg->msg_flags |= MSG_OOB;
+		if (len > 0) {
+			if (!(flags & MSG_TRUNC))
+				rc = memcpy_to_msg(msg, &conn->urg_rx_byte, 1);
+			len = 1;
+			smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+			if (smc_curs_diff(conn->rmb_desc->len, &cons,
+					  &conn->urg_curs) > 1)
+				conn->urg_rx_skip_pend = true;
+			/* Urgent Byte was already accounted for, but trigger
+			 * skipping the urgent byte in non-inline case
+			 */
+			if (!(flags & MSG_PEEK))
+				smc_rx_update_consumer(smc, cons, 0);
+		} else {
+			msg->msg_flags |= MSG_TRUNC;
+		}
+
+		return rc ? -EFAULT : len;
+	}
+
+	if (sk->sk_state == SMC_CLOSED || sk->sk_shutdown & RCV_SHUTDOWN)
+		return 0;
+
+	return -EAGAIN;
+}
+
+static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+
+	if (smc_rx_data_available(conn))
+		return true;
+	else if (conn->urg_state == SMC_URG_VALID)
+		/* we received a single urgent Byte - skip */
+		smc_rx_update_cons(smc, 0);
+	return false;
+}
+
+/* smc_rx_recvmsg - receive data from RMBE
+ * @msg:	copy data to receive buffer
+ * @pipe:	copy data to pipe if set - indicates splice() call
+ *
+ * rcvbuf consumer: main API called by socket layer.
+ * Called under sk lock.
+ */
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+		   struct pipe_inode_info *pipe, size_t len, int flags)
+{
+	size_t copylen, read_done = 0, read_remaining = len;
+	size_t chunk_len, chunk_off, chunk_len_sum;
+	struct smc_connection *conn = &smc->conn;
+	int (*func)(struct smc_connection *conn);
+	union smc_host_cursor cons;
+	int readable, chunk;
+	char *rcvbuf_base;
+	struct sock *sk;
+	int splbytes;
+	long timeo;
+	int target;		/* Read at least these many bytes */
+	int rc;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return -EINVAL; /* future work for sk.sk_family == AF_SMC */
+
+	sk = &smc->sk;
+	if (sk->sk_state == SMC_LISTEN)
+		return -ENOTCONN;
+	if (flags & MSG_OOB)
+		return smc_rx_recv_urg(smc, msg, len, flags);
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
+
+	/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
+	rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr;
+
+	do { /* while (read_remaining) */
+		if (read_done >= target || (pipe && read_done))
+			break;
+
+		if (smc_rx_recvmsg_data_available(smc))
+			goto copy;
+
+		if (sk->sk_shutdown & RCV_SHUTDOWN ||
+		    conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) {
+			/* smc_cdc_msg_recv_action() could have run after
+			 * above smc_rx_recvmsg_data_available()
+			 */
+			if (smc_rx_recvmsg_data_available(smc))
+				goto copy;
+			break;
+		}
+
+		if (read_done) {
+			if (sk->sk_err ||
+			    sk->sk_state == SMC_CLOSED ||
+			    !timeo ||
+			    signal_pending(current))
+				break;
+		} else {
+			if (sk->sk_err) {
+				read_done = sock_error(sk);
+				break;
+			}
+			if (sk->sk_state == SMC_CLOSED) {
+				if (!sock_flag(sk, SOCK_DONE)) {
+					/* This occurs when user tries to read
+					 * from never connected socket.
+					 */
+					read_done = -ENOTCONN;
+					break;
+				}
+				break;
+			}
+			if (!timeo)
+				return -EAGAIN;
+			if (signal_pending(current)) {
+				read_done = sock_intr_errno(timeo);
+				break;
+			}
+		}
+
+		if (!smc_rx_data_available(conn)) {
+			smc_rx_wait(smc, &timeo, smc_rx_data_available);
+			continue;
+		}
+
+copy:
+		/* initialize variables for 1st iteration of subsequent loop */
+		/* could be just 1 byte, even after waiting on data above */
+		readable = atomic_read(&conn->bytes_to_rcv);
+		splbytes = atomic_read(&conn->splice_pending);
+		if (!readable || (msg && splbytes)) {
+			if (splbytes)
+				func = smc_rx_data_available_and_no_splice_pend;
+			else
+				func = smc_rx_data_available;
+			smc_rx_wait(smc, &timeo, func);
+			continue;
+		}
+
+		smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+		/* subsequent splice() calls pick up where previous left */
+		if (splbytes)
+			smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
+		if (conn->urg_state == SMC_URG_VALID &&
+		    sock_flag(&smc->sk, SOCK_URGINLINE) &&
+		    readable > 1)
+			readable--;	/* always stop at urgent Byte */
+		/* not more than what user space asked for */
+		copylen = min_t(size_t, read_remaining, readable);
+		/* determine chunks where to read from rcvbuf */
+		/* either unwrapped case, or 1st chunk of wrapped case */
+		chunk_len = min_t(size_t, copylen, conn->rmb_desc->len -
+				  cons.count);
+		chunk_len_sum = chunk_len;
+		chunk_off = cons.count;
+		smc_rmb_sync_sg_for_cpu(conn);
+		for (chunk = 0; chunk < 2; chunk++) {
+			if (!(flags & MSG_TRUNC)) {
+				if (msg) {
+					rc = memcpy_to_msg(msg, rcvbuf_base +
+							   chunk_off,
+							   chunk_len);
+				} else {
+					rc = smc_rx_splice(pipe, rcvbuf_base +
+							chunk_off, chunk_len,
+							smc);
+				}
+				if (rc < 0) {
+					if (!read_done)
+						read_done = -EFAULT;
+					smc_rmb_sync_sg_for_device(conn);
+					goto out;
+				}
+			}
+			read_remaining -= chunk_len;
+			read_done += chunk_len;
+
+			if (chunk_len_sum == copylen)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			chunk_len = copylen - chunk_len; /* remainder */
+			chunk_len_sum += chunk_len;
+			chunk_off = 0; /* modulo offset in recv ring buffer */
+		}
+		smc_rmb_sync_sg_for_device(conn);
+
+		/* update cursors */
+		if (!(flags & MSG_PEEK)) {
+			/* increased in recv tasklet smc_cdc_msg_rcv() */
+			smp_mb__before_atomic();
+			atomic_sub(copylen, &conn->bytes_to_rcv);
+			/* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
+			smp_mb__after_atomic();
+			if (msg && smc_rx_update_consumer(smc, cons, copylen))
+				goto out;
+		}
+	} while (read_remaining);
+out:
+	return read_done;
+}
+
+/* Initialize receive properties on connection establishment. NB: not __init! */
+void smc_rx_init(struct smc_sock *smc)
+{
+	smc->sk.sk_data_ready = smc_rx_wake_up;
+	atomic_set(&smc->conn.splice_pending, 0);
+	smc->conn.urg_state = SMC_URG_READ;
+}
diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h
new file mode 100644
index 000000000..db823c97d
--- /dev/null
+++ b/net/smc/smc_rx.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Manage RMBE
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_RX_H
+#define SMC_RX_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+#include "smc.h"
+
+void smc_rx_init(struct smc_sock *smc);
+
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+		   struct pipe_inode_info *pipe, size_t len, int flags);
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+		int (*fcrit)(struct smc_connection *conn));
+static inline int smc_rx_data_available(struct smc_connection *conn)
+{
+	return atomic_read(&conn->bytes_to_rcv);
+}
+
+#endif /* SMC_RX_H */
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
new file mode 100644
index 000000000..62885a278
--- /dev/null
+++ b/net/smc/smc_tx.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Manage send buffer.
+ * Producer:
+ * Copy user space data into send buffer, if send buffer space available.
+ * Consumer:
+ * Trigger RDMA write into RMBE of peer and send CDC, if RMBE space available.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/net.h>
+#include <linux/rcupdate.h>
+#include <linux/workqueue.h>
+#include <linux/sched/signal.h>
+
+#include <net/sock.h>
+#include <net/tcp.h>
+
+#include "smc.h"
+#include "smc_wr.h"
+#include "smc_cdc.h"
+#include "smc_ism.h"
+#include "smc_tx.h"
+
+#define SMC_TX_WORK_DELAY	HZ
+#define SMC_TX_CORK_DELAY	(HZ >> 2)	/* 250 ms */
+
+/***************************** sndbuf producer *******************************/
+
+/* callback implementation for sk.sk_write_space()
+ * to wakeup sndbuf producers that blocked with smc_tx_wait().
+ * called under sk_socket lock.
+ */
+static void smc_tx_write_space(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+	struct smc_sock *smc = smc_sk(sk);
+	struct socket_wq *wq;
+
+	/* similar to sk_stream_write_space */
+	if (atomic_read(&smc->conn.sndbuf_space) && sock) {
+		clear_bit(SOCK_NOSPACE, &sock->flags);
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		if (skwq_has_sleeper(wq))
+			wake_up_interruptible_poll(&wq->wait,
+						   EPOLLOUT | EPOLLWRNORM |
+						   EPOLLWRBAND);
+		if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
+			sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
+		rcu_read_unlock();
+	}
+}
+
+/* Wakeup sndbuf producers that blocked with smc_tx_wait().
+ * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space().
+ */
+void smc_tx_sndbuf_nonfull(struct smc_sock *smc)
+{
+	if (smc->sk.sk_socket &&
+	    test_bit(SOCK_NOSPACE, &smc->sk.sk_socket->flags))
+		smc->sk.sk_write_space(&smc->sk);
+}
+
+/* blocks sndbuf producer until at least one byte of free space available
+ * or urgent Byte was consumed
+ */
+static int smc_tx_wait(struct smc_sock *smc, int flags)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	struct smc_connection *conn = &smc->conn;
+	struct sock *sk = &smc->sk;
+	long timeo;
+	int rc = 0;
+
+	/* similar to sk_stream_wait_memory */
+	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+	add_wait_queue(sk_sleep(sk), &wait);
+	while (1) {
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+		if (sk->sk_err ||
+		    (sk->sk_shutdown & SEND_SHUTDOWN) ||
+		    conn->local_tx_ctrl.conn_state_flags.peer_done_writing) {
+			rc = -EPIPE;
+			break;
+		}
+		if (smc_cdc_rxed_any_close(conn)) {
+			rc = -ECONNRESET;
+			break;
+		}
+		if (!timeo) {
+			/* ensure EPOLLOUT is subsequently generated */
+			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			rc = -EAGAIN;
+			break;
+		}
+		if (signal_pending(current)) {
+			rc = sock_intr_errno(timeo);
+			break;
+		}
+		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+		if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend)
+			break; /* at least 1 byte of free & no urgent data */
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		sk_wait_event(sk, &timeo,
+			      sk->sk_err ||
+			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
+			      smc_cdc_rxed_any_close(conn) ||
+			      (atomic_read(&conn->sndbuf_space) &&
+			       !conn->urg_tx_pend),
+			      &wait);
+	}
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return rc;
+}
+
+static bool smc_tx_is_corked(struct smc_sock *smc)
+{
+	struct tcp_sock *tp = tcp_sk(smc->clcsock->sk);
+
+	return (tp->nonagle & TCP_NAGLE_CORK) ? true : false;
+}
+
+/* sndbuf producer: main API called by socket layer.
+ * called under sock lock.
+ */
+int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
+{
+	size_t copylen, send_done = 0, send_remaining = len;
+	size_t chunk_len, chunk_off, chunk_len_sum;
+	struct smc_connection *conn = &smc->conn;
+	union smc_host_cursor prep;
+	struct sock *sk = &smc->sk;
+	char *sndbuf_base;
+	int tx_cnt_prep;
+	int writespace;
+	int rc, chunk;
+
+	/* This should be in poll */
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
+		rc = -EPIPE;
+		goto out_err;
+	}
+
+	while (msg_data_left(msg)) {
+		if (sk->sk_state == SMC_INIT)
+			return -ENOTCONN;
+		if (smc->sk.sk_shutdown & SEND_SHUTDOWN ||
+		    (smc->sk.sk_err == ECONNABORTED) ||
+		    conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+			return -EPIPE;
+		if (smc_cdc_rxed_any_close(conn))
+			return send_done ?: -ECONNRESET;
+
+		if (msg->msg_flags & MSG_OOB)
+			conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
+
+		if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
+			if (send_done)
+				return send_done;
+			rc = smc_tx_wait(smc, msg->msg_flags);
+			if (rc)
+				goto out_err;
+			continue;
+		}
+
+		/* initialize variables for 1st iteration of subsequent loop */
+		/* could be just 1 byte, even after smc_tx_wait above */
+		writespace = atomic_read(&conn->sndbuf_space);
+		/* not more than what user space asked for */
+		copylen = min_t(size_t, send_remaining, writespace);
+		/* determine start of sndbuf */
+		sndbuf_base = conn->sndbuf_desc->cpu_addr;
+		smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
+		tx_cnt_prep = prep.count;
+		/* determine chunks where to write into sndbuf */
+		/* either unwrapped case, or 1st chunk of wrapped case */
+		chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len -
+				  tx_cnt_prep);
+		chunk_len_sum = chunk_len;
+		chunk_off = tx_cnt_prep;
+		smc_sndbuf_sync_sg_for_cpu(conn);
+		for (chunk = 0; chunk < 2; chunk++) {
+			rc = memcpy_from_msg(sndbuf_base + chunk_off,
+					     msg, chunk_len);
+			if (rc) {
+				smc_sndbuf_sync_sg_for_device(conn);
+				if (send_done)
+					return send_done;
+				goto out_err;
+			}
+			send_done += chunk_len;
+			send_remaining -= chunk_len;
+
+			if (chunk_len_sum == copylen)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			chunk_len = copylen - chunk_len; /* remainder */
+			chunk_len_sum += chunk_len;
+			chunk_off = 0; /* modulo offset in send ring buffer */
+		}
+		smc_sndbuf_sync_sg_for_device(conn);
+		/* update cursors */
+		smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
+		smc_curs_copy(&conn->tx_curs_prep, &prep, conn);
+		/* increased in send tasklet smc_cdc_tx_handler() */
+		smp_mb__before_atomic();
+		atomic_sub(copylen, &conn->sndbuf_space);
+		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+		smp_mb__after_atomic();
+		/* since we just produced more new data into sndbuf,
+		 * trigger sndbuf consumer: RDMA write into peer RMBE and CDC
+		 */
+		if ((msg->msg_flags & MSG_OOB) && !send_remaining)
+			conn->urg_tx_pend = true;
+		if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
+		    (atomic_read(&conn->sndbuf_space) >
+						(conn->sndbuf_desc->len >> 1)))
+			/* for a corked socket defer the RDMA writes if there
+			 * is still sufficient sndbuf_space available
+			 */
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_CORK_DELAY);
+		else
+			smc_tx_sndbuf_nonempty(conn);
+	} /* while (msg_data_left(msg)) */
+
+	return send_done;
+
+out_err:
+	rc = sk_stream_error(sk, msg->msg_flags, rc);
+	/* make sure we wake any epoll edge trigger waiter */
+	if (unlikely(rc == -EAGAIN))
+		sk->sk_write_space(sk);
+	return rc;
+}
+
+/***************************** sndbuf consumer *******************************/
+
+/* sndbuf consumer: actual data transfer of one target chunk with ISM write */
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+		      u32 offset, int signal)
+{
+	struct smc_ism_position pos;
+	int rc;
+
+	memset(&pos, 0, sizeof(pos));
+	pos.token = conn->peer_token;
+	pos.index = conn->peer_rmbe_idx;
+	pos.offset = conn->tx_off + offset;
+	pos.signal = signal;
+	rc = smc_ism_write(conn->lgr->smcd, &pos, data, len);
+	if (rc)
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+	return rc;
+}
+
+/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
+static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
+			     int num_sges, struct ib_sge sges[])
+{
+	struct smc_link_group *lgr = conn->lgr;
+	struct ib_rdma_wr rdma_wr;
+	struct smc_link *link;
+	int rc;
+
+	memset(&rdma_wr, 0, sizeof(rdma_wr));
+	link = &lgr->lnk[SMC_SINGLE_LINK];
+	rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link);
+	rdma_wr.wr.sg_list = sges;
+	rdma_wr.wr.num_sge = num_sges;
+	rdma_wr.wr.opcode = IB_WR_RDMA_WRITE;
+	rdma_wr.remote_addr =
+		lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr +
+		/* RMBE within RMB */
+		conn->tx_off +
+		/* offset within RMBE */
+		peer_rmbe_offset;
+	rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
+	rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL);
+	if (rc) {
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+		smc_lgr_terminate(lgr);
+	}
+	return rc;
+}
+
+/* sndbuf consumer */
+static inline void smc_tx_advance_cursors(struct smc_connection *conn,
+					  union smc_host_cursor *prod,
+					  union smc_host_cursor *sent,
+					  size_t len)
+{
+	smc_curs_add(conn->peer_rmbe_size, prod, len);
+	/* increased in recv tasklet smc_cdc_msg_rcv() */
+	smp_mb__before_atomic();
+	/* data in flight reduces usable snd_wnd */
+	atomic_sub(len, &conn->peer_rmbe_space);
+	/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
+	smp_mb__after_atomic();
+	smc_curs_add(conn->sndbuf_desc->len, sent, len);
+}
+
+/* SMC-R helper for smc_tx_rdma_writes() */
+static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
+			       size_t src_off, size_t src_len,
+			       size_t dst_off, size_t dst_len)
+{
+	dma_addr_t dma_addr =
+		sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+	int src_len_sum = src_len, dst_len_sum = dst_len;
+	struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
+	int sent_count = src_off;
+	int srcchunk, dstchunk;
+	int num_sges;
+	int rc;
+
+	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+		num_sges = 0;
+		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+			sges[srcchunk].addr = dma_addr + src_off;
+			sges[srcchunk].length = src_len;
+			sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+			num_sges++;
+
+			src_off += src_len;
+			if (src_off >= conn->sndbuf_desc->len)
+				src_off -= conn->sndbuf_desc->len;
+						/* modulo in send ring */
+			if (src_len_sum == dst_len)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			src_len = dst_len - src_len; /* remainder */
+			src_len_sum += src_len;
+		}
+		rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+		if (rc)
+			return rc;
+		if (dst_len_sum == len)
+			break; /* either on 1st or 2nd iteration */
+		/* prepare next (== 2nd) iteration */
+		dst_off = 0; /* modulo offset in RMBE ring buffer */
+		dst_len = len - dst_len; /* remainder */
+		dst_len_sum += dst_len;
+		src_len = min_t(int, dst_len, conn->sndbuf_desc->len -
+				sent_count);
+		src_len_sum = src_len;
+	}
+	return 0;
+}
+
+/* SMC-D helper for smc_tx_rdma_writes() */
+static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
+			       size_t src_off, size_t src_len,
+			       size_t dst_off, size_t dst_len)
+{
+	int src_len_sum = src_len, dst_len_sum = dst_len;
+	int srcchunk, dstchunk;
+	int rc;
+
+	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+			void *data = conn->sndbuf_desc->cpu_addr + src_off;
+
+			rc = smcd_tx_ism_write(conn, data, src_len, dst_off +
+					       sizeof(struct smcd_cdc_msg), 0);
+			if (rc)
+				return rc;
+			dst_off += src_len;
+			src_off += src_len;
+			if (src_off >= conn->sndbuf_desc->len)
+				src_off -= conn->sndbuf_desc->len;
+						/* modulo in send ring */
+			if (src_len_sum == dst_len)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			src_len = dst_len - src_len; /* remainder */
+			src_len_sum += src_len;
+		}
+		if (dst_len_sum == len)
+			break; /* either on 1st or 2nd iteration */
+		/* prepare next (== 2nd) iteration */
+		dst_off = 0; /* modulo offset in RMBE ring buffer */
+		dst_len = len - dst_len; /* remainder */
+		dst_len_sum += dst_len;
+		src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off);
+		src_len_sum = src_len;
+	}
+	return 0;
+}
+
+/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
+ * usable snd_wnd as max transmit
+ */
+static int smc_tx_rdma_writes(struct smc_connection *conn)
+{
+	size_t len, src_len, dst_off, dst_len; /* current chunk values */
+	union smc_host_cursor sent, prep, prod, cons;
+	struct smc_cdc_producer_flags *pflags;
+	int to_send, rmbespace;
+	int rc;
+
+	/* source: sndbuf */
+	smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+	smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
+	/* cf. wmem_alloc - (snd_max - snd_una) */
+	to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
+	if (to_send <= 0)
+		return 0;
+
+	/* destination: RMBE */
+	/* cf. snd_wnd */
+	rmbespace = atomic_read(&conn->peer_rmbe_space);
+	if (rmbespace <= 0)
+		return 0;
+	smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn);
+	smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn);
+
+	/* if usable snd_wnd closes ask peer to advertise once it opens again */
+	pflags = &conn->local_tx_ctrl.prod_flags;
+	pflags->write_blocked = (to_send >= rmbespace);
+	/* cf. usable snd_wnd */
+	len = min(to_send, rmbespace);
+
+	/* initialize variables for first iteration of subsequent nested loop */
+	dst_off = prod.count;
+	if (prod.wrap == cons.wrap) {
+		/* the filled destination area is unwrapped,
+		 * hence the available free destination space is wrapped
+		 * and we need 2 destination chunks of sum len; start with 1st
+		 * which is limited by what's available in sndbuf
+		 */
+		dst_len = min_t(size_t,
+				conn->peer_rmbe_size - prod.count, len);
+	} else {
+		/* the filled destination area is wrapped,
+		 * hence the available free destination space is unwrapped
+		 * and we need a single destination chunk of entire len
+		 */
+		dst_len = len;
+	}
+	/* dst_len determines the maximum src_len */
+	if (sent.count + dst_len <= conn->sndbuf_desc->len) {
+		/* unwrapped src case: single chunk of entire dst_len */
+		src_len = dst_len;
+	} else {
+		/* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
+		src_len = conn->sndbuf_desc->len - sent.count;
+	}
+
+	if (conn->lgr->is_smcd)
+		rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len,
+					 dst_off, dst_len);
+	else
+		rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
+					 dst_off, dst_len);
+	if (rc)
+		return rc;
+
+	if (conn->urg_tx_pend && len == to_send)
+		pflags->urg_data_present = 1;
+	smc_tx_advance_cursors(conn, &prod, &sent, len);
+	/* update connection's cursors with advanced local cursors */
+	smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn);
+							/* dst: peer RMBE */
+	smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */
+
+	return 0;
+}
+
+/* Wakeup sndbuf consumers from any context (IRQ or process)
+ * since there is more data to transmit; usable snd_wnd as max transmit
+ */
+static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+	struct smc_cdc_producer_flags *pflags;
+	struct smc_cdc_tx_pend *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+	if (rc < 0) {
+		if (rc == -EBUSY) {
+			struct smc_sock *smc =
+				container_of(conn, struct smc_sock, conn);
+
+			if (smc->sk.sk_err == ECONNABORTED)
+				return sock_error(&smc->sk);
+			rc = 0;
+			if (conn->alert_token_local) /* connection healthy */
+				mod_delayed_work(system_wq, &conn->tx_work,
+						 SMC_TX_WORK_DELAY);
+		}
+		return rc;
+	}
+
+	spin_lock_bh(&conn->send_lock);
+	if (!conn->local_tx_ctrl.prod_flags.urg_data_present) {
+		rc = smc_tx_rdma_writes(conn);
+		if (rc) {
+			smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
+					   (struct smc_wr_tx_pend_priv *)pend);
+			goto out_unlock;
+		}
+	}
+
+	rc = smc_cdc_msg_send(conn, wr_buf, pend);
+	pflags = &conn->local_tx_ctrl.prod_flags;
+	if (!rc && pflags->urg_data_present) {
+		pflags->urg_data_pending = 0;
+		pflags->urg_data_present = 0;
+	}
+
+out_unlock:
+	spin_unlock_bh(&conn->send_lock);
+	return rc;
+}
+
+static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+	struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
+	int rc = 0;
+
+	spin_lock_bh(&conn->send_lock);
+	if (!pflags->urg_data_present)
+		rc = smc_tx_rdma_writes(conn);
+	if (!rc)
+		rc = smcd_cdc_msg_send(conn);
+
+	if (!rc && pflags->urg_data_present) {
+		pflags->urg_data_pending = 0;
+		pflags->urg_data_present = 0;
+	}
+	spin_unlock_bh(&conn->send_lock);
+	return rc;
+}
+
+int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+	int rc;
+
+	if (conn->lgr->is_smcd)
+		rc = smcd_tx_sndbuf_nonempty(conn);
+	else
+		rc = smcr_tx_sndbuf_nonempty(conn);
+
+	return rc;
+}
+
+/* Wakeup sndbuf consumers from process context
+ * since there is more data to transmit
+ */
+void smc_tx_work(struct work_struct *work)
+{
+	struct smc_connection *conn = container_of(to_delayed_work(work),
+						   struct smc_connection,
+						   tx_work);
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	int rc;
+
+	lock_sock(&smc->sk);
+	if (smc->sk.sk_err ||
+	    !conn->alert_token_local ||
+	    conn->local_rx_ctrl.conn_state_flags.peer_conn_abort)
+		goto out;
+
+	rc = smc_tx_sndbuf_nonempty(conn);
+	if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
+	    !atomic_read(&conn->bytes_to_rcv))
+		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
+
+out:
+	release_sock(&smc->sk);
+}
+
+void smc_tx_consumer_update(struct smc_connection *conn, bool force)
+{
+	union smc_host_cursor cfed, cons, prod;
+	int sender_free = conn->rmb_desc->len;
+	int to_confirm;
+
+	smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+	smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn);
+	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+	if (to_confirm > conn->rmbe_update_limit) {
+		smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
+		sender_free = conn->rmb_desc->len -
+			      smc_curs_diff_large(conn->rmb_desc->len,
+						  &cfed, &prod);
+	}
+
+	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
+	    force ||
+	    ((to_confirm > conn->rmbe_update_limit) &&
+	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
+	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
+		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
+		    conn->alert_token_local) { /* connection healthy */
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_WORK_DELAY);
+			return;
+		}
+		smc_curs_copy(&conn->rx_curs_confirmed,
+			      &conn->local_tx_ctrl.cons, conn);
+		conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
+	}
+	if (conn->local_rx_ctrl.prod_flags.write_blocked &&
+	    !atomic_read(&conn->bytes_to_rcv))
+		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
+}
+
+/***************************** send initialize *******************************/
+
+/* Initialize send properties on connection establishment. NB: not __init! */
+void smc_tx_init(struct smc_sock *smc)
+{
+	smc->sk.sk_write_space = smc_tx_write_space;
+}
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
new file mode 100644
index 000000000..07e6ad762
--- /dev/null
+++ b/net/smc/smc_tx.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Manage send buffer
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_TX_H
+#define SMC_TX_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+#include "smc.h"
+#include "smc_cdc.h"
+
+static inline int smc_tx_prepared_sends(struct smc_connection *conn)
+{
+	union smc_host_cursor sent, prep;
+
+	smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+	smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
+	return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
+}
+
+void smc_tx_work(struct work_struct *work);
+void smc_tx_init(struct smc_sock *smc);
+int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
+int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
+void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
+void smc_tx_consumer_update(struct smc_connection *conn, bool force);
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+		      u32 offset, int signal);
+
+#endif /* SMC_TX_H */
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
new file mode 100644
index 000000000..c2694750a
--- /dev/null
+++ b/net/smc/smc_wr.c
@@ -0,0 +1,644 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Work Requests exploiting Infiniband API
+ *
+ * Work requests (WR) of type ib_post_send or ib_post_recv respectively
+ * are submitted to either RC SQ or RC RQ respectively
+ * (reliably connected send/receive queue)
+ * and become work queue entries (WQEs).
+ * While an SQ WR/WQE is pending, we track it until transmission completion.
+ * Through a send or receive completion queue (CQ) respectively,
+ * we get completion queue entries (CQEs) [aka work completions (WCs)].
+ * Since the CQ callback is called from IRQ context, we split work by using
+ * bottom halves implemented by tasklets.
+ *
+ * SMC uses this to exchange LLC (link layer control)
+ * and CDC (connection data control) messages.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Steffen Maier <maier@linux.vnet.ibm.com>
+ */
+
+#include <linux/atomic.h>
+#include <linux/hashtable.h>
+#include <linux/wait.h>
+#include <rdma/ib_verbs.h>
+#include <asm/div64.h>
+
+#include "smc.h"
+#include "smc_wr.h"
+
+#define SMC_WR_MAX_POLL_CQE 10	/* max. # of compl. queue elements in 1 poll */
+
+#define SMC_WR_RX_HASH_BITS 4
+static DEFINE_HASHTABLE(smc_wr_rx_hash, SMC_WR_RX_HASH_BITS);
+static DEFINE_SPINLOCK(smc_wr_rx_hash_lock);
+
+struct smc_wr_tx_pend {	/* control data for a pending send request */
+	u64			wr_id;		/* work request id sent */
+	smc_wr_tx_handler	handler;
+	enum ib_wc_status	wc_status;	/* CQE status */
+	struct smc_link		*link;
+	u32			idx;
+	struct smc_wr_tx_pend_priv priv;
+};
+
+/******************************** send queue *********************************/
+
+/*------------------------------- completion --------------------------------*/
+
+static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
+{
+	u32 i;
+
+	for (i = 0; i < link->wr_tx_cnt; i++) {
+		if (link->wr_tx_pends[i].wr_id == wr_id)
+			return i;
+	}
+	return link->wr_tx_cnt;
+}
+
+static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
+{
+	struct smc_wr_tx_pend pnd_snd;
+	struct smc_link *link;
+	u32 pnd_snd_idx;
+	int i;
+
+	link = wc->qp->qp_context;
+
+	if (wc->opcode == IB_WC_REG_MR) {
+		if (wc->status)
+			link->wr_reg_state = FAILED;
+		else
+			link->wr_reg_state = CONFIRMED;
+		wake_up(&link->wr_reg_wait);
+		return;
+	}
+
+	pnd_snd_idx = smc_wr_tx_find_pending_index(link, wc->wr_id);
+	if (pnd_snd_idx == link->wr_tx_cnt)
+		return;
+	link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status;
+	memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], sizeof(pnd_snd));
+	/* clear the full struct smc_wr_tx_pend including .priv */
+	memset(&link->wr_tx_pends[pnd_snd_idx], 0,
+	       sizeof(link->wr_tx_pends[pnd_snd_idx]));
+	memset(&link->wr_tx_bufs[pnd_snd_idx], 0,
+	       sizeof(link->wr_tx_bufs[pnd_snd_idx]));
+	if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask))
+		return;
+	if (wc->status) {
+		for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
+			/* clear full struct smc_wr_tx_pend including .priv */
+			memset(&link->wr_tx_pends[i], 0,
+			       sizeof(link->wr_tx_pends[i]));
+			memset(&link->wr_tx_bufs[i], 0,
+			       sizeof(link->wr_tx_bufs[i]));
+			clear_bit(i, link->wr_tx_mask);
+		}
+		/* terminate connections of this link group abnormally */
+		smc_lgr_terminate(smc_get_lgr(link));
+	}
+	if (pnd_snd.handler)
+		pnd_snd.handler(&pnd_snd.priv, link, wc->status);
+	wake_up(&link->wr_tx_wait);
+}
+
+static void smc_wr_tx_tasklet_fn(unsigned long data)
+{
+	struct smc_ib_device *dev = (struct smc_ib_device *)data;
+	struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
+	int i = 0, rc;
+	int polled = 0;
+
+again:
+	polled++;
+	do {
+		memset(&wc, 0, sizeof(wc));
+		rc = ib_poll_cq(dev->roce_cq_send, SMC_WR_MAX_POLL_CQE, wc);
+		if (polled == 1) {
+			ib_req_notify_cq(dev->roce_cq_send,
+					 IB_CQ_NEXT_COMP |
+					 IB_CQ_REPORT_MISSED_EVENTS);
+		}
+		if (!rc)
+			break;
+		for (i = 0; i < rc; i++)
+			smc_wr_tx_process_cqe(&wc[i]);
+	} while (rc > 0);
+	if (polled == 1)
+		goto again;
+}
+
+void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
+{
+	struct smc_ib_device *dev = (struct smc_ib_device *)cq_context;
+
+	tasklet_schedule(&dev->send_tasklet);
+}
+
+/*---------------------------- request submission ---------------------------*/
+
+static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
+{
+	*idx = link->wr_tx_cnt;
+	for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) {
+		if (!test_and_set_bit(*idx, link->wr_tx_mask))
+			return 0;
+	}
+	*idx = link->wr_tx_cnt;
+	return -EBUSY;
+}
+
+/**
+ * smc_wr_tx_get_free_slot() - returns buffer for message assembly,
+ *			and sets info for pending transmit tracking
+ * @link:		Pointer to smc_link used to later send the message.
+ * @handler:		Send completion handler function pointer.
+ * @wr_buf:		Out value returns pointer to message buffer.
+ * @wr_pend_priv:	Out value returns pointer serving as handler context.
+ *
+ * Return: 0 on success, or -errno on error.
+ */
+int smc_wr_tx_get_free_slot(struct smc_link *link,
+			    smc_wr_tx_handler handler,
+			    struct smc_wr_buf **wr_buf,
+			    struct smc_wr_tx_pend_priv **wr_pend_priv)
+{
+	struct smc_wr_tx_pend *wr_pend;
+	u32 idx = link->wr_tx_cnt;
+	struct ib_send_wr *wr_ib;
+	u64 wr_id;
+	int rc;
+
+	*wr_buf = NULL;
+	*wr_pend_priv = NULL;
+	if (in_softirq()) {
+		rc = smc_wr_tx_get_free_slot_index(link, &idx);
+		if (rc)
+			return rc;
+	} else {
+		rc = wait_event_timeout(
+			link->wr_tx_wait,
+			link->state == SMC_LNK_INACTIVE ||
+			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
+			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
+		if (!rc) {
+			/* timeout - terminate connections */
+			smc_lgr_terminate(smc_get_lgr(link));
+			return -EPIPE;
+		}
+		if (idx == link->wr_tx_cnt)
+			return -EPIPE;
+	}
+	wr_id = smc_wr_tx_get_next_wr_id(link);
+	wr_pend = &link->wr_tx_pends[idx];
+	wr_pend->wr_id = wr_id;
+	wr_pend->handler = handler;
+	wr_pend->link = link;
+	wr_pend->idx = idx;
+	wr_ib = &link->wr_tx_ibs[idx];
+	wr_ib->wr_id = wr_id;
+	*wr_buf = &link->wr_tx_bufs[idx];
+	*wr_pend_priv = &wr_pend->priv;
+	return 0;
+}
+
+int smc_wr_tx_put_slot(struct smc_link *link,
+		       struct smc_wr_tx_pend_priv *wr_pend_priv)
+{
+	struct smc_wr_tx_pend *pend;
+
+	pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv);
+	if (pend->idx < link->wr_tx_cnt) {
+		u32 idx = pend->idx;
+
+		/* clear the full struct smc_wr_tx_pend including .priv */
+		memset(&link->wr_tx_pends[pend->idx], 0,
+		       sizeof(link->wr_tx_pends[pend->idx]));
+		memset(&link->wr_tx_bufs[pend->idx], 0,
+		       sizeof(link->wr_tx_bufs[pend->idx]));
+		test_and_clear_bit(idx, link->wr_tx_mask);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* Send prepared WR slot via ib_post_send.
+ * @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer
+ */
+int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
+{
+	struct smc_wr_tx_pend *pend;
+	int rc;
+
+	ib_req_notify_cq(link->smcibdev->roce_cq_send,
+			 IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	pend = container_of(priv, struct smc_wr_tx_pend, priv);
+	rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], NULL);
+	if (rc) {
+		smc_wr_tx_put_slot(link, priv);
+		smc_lgr_terminate(smc_get_lgr(link));
+	}
+	return rc;
+}
+
+/* Register a memory region and wait for result. */
+int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
+{
+	int rc;
+
+	ib_req_notify_cq(link->smcibdev->roce_cq_send,
+			 IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	link->wr_reg_state = POSTED;
+	link->wr_reg.wr.wr_id = (u64)(uintptr_t)mr;
+	link->wr_reg.mr = mr;
+	link->wr_reg.key = mr->rkey;
+	rc = ib_post_send(link->roce_qp, &link->wr_reg.wr, NULL);
+	if (rc)
+		return rc;
+
+	rc = wait_event_interruptible_timeout(link->wr_reg_wait,
+					      (link->wr_reg_state != POSTED),
+					      SMC_WR_REG_MR_WAIT_TIME);
+	if (!rc) {
+		/* timeout - terminate connections */
+		smc_lgr_terminate(smc_get_lgr(link));
+		return -EPIPE;
+	}
+	if (rc == -ERESTARTSYS)
+		return -EINTR;
+	switch (link->wr_reg_state) {
+	case CONFIRMED:
+		rc = 0;
+		break;
+	case FAILED:
+		rc = -EIO;
+		break;
+	case POSTED:
+		rc = -EPIPE;
+		break;
+	}
+	return rc;
+}
+
+void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type,
+			     smc_wr_tx_filter filter,
+			     smc_wr_tx_dismisser dismisser,
+			     unsigned long data)
+{
+	struct smc_wr_tx_pend_priv *tx_pend;
+	struct smc_wr_rx_hdr *wr_tx;
+	int i;
+
+	for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
+		wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i];
+		if (wr_tx->type != wr_tx_hdr_type)
+			continue;
+		tx_pend = &link->wr_tx_pends[i].priv;
+		if (filter(tx_pend, data))
+			dismisser(tx_pend);
+	}
+}
+
+/****************************** receive queue ********************************/
+
+int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler)
+{
+	struct smc_wr_rx_handler *h_iter;
+	int rc = 0;
+
+	spin_lock(&smc_wr_rx_hash_lock);
+	hash_for_each_possible(smc_wr_rx_hash, h_iter, list, handler->type) {
+		if (h_iter->type == handler->type) {
+			rc = -EEXIST;
+			goto out_unlock;
+		}
+	}
+	hash_add(smc_wr_rx_hash, &handler->list, handler->type);
+out_unlock:
+	spin_unlock(&smc_wr_rx_hash_lock);
+	return rc;
+}
+
+/* Demultiplex a received work request based on the message type to its handler.
+ * Relies on smc_wr_rx_hash having been completely filled before any IB WRs,
+ * and not being modified any more afterwards so we don't need to lock it.
+ */
+static inline void smc_wr_rx_demultiplex(struct ib_wc *wc)
+{
+	struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
+	struct smc_wr_rx_handler *handler;
+	struct smc_wr_rx_hdr *wr_rx;
+	u64 temp_wr_id;
+	u32 index;
+
+	if (wc->byte_len < sizeof(*wr_rx))
+		return; /* short message */
+	temp_wr_id = wc->wr_id;
+	index = do_div(temp_wr_id, link->wr_rx_cnt);
+	wr_rx = (struct smc_wr_rx_hdr *)&link->wr_rx_bufs[index];
+	hash_for_each_possible(smc_wr_rx_hash, handler, list, wr_rx->type) {
+		if (handler->type == wr_rx->type)
+			handler->handler(wc, wr_rx);
+	}
+}
+
+static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
+{
+	struct smc_link *link;
+	int i;
+
+	for (i = 0; i < num; i++) {
+		link = wc[i].qp->qp_context;
+		if (wc[i].status == IB_WC_SUCCESS) {
+			link->wr_rx_tstamp = jiffies;
+			smc_wr_rx_demultiplex(&wc[i]);
+			smc_wr_rx_post(link); /* refill WR RX */
+		} else {
+			/* handle status errors */
+			switch (wc[i].status) {
+			case IB_WC_RETRY_EXC_ERR:
+			case IB_WC_RNR_RETRY_EXC_ERR:
+			case IB_WC_WR_FLUSH_ERR:
+				/* terminate connections of this link group
+				 * abnormally
+				 */
+				smc_lgr_terminate(smc_get_lgr(link));
+				break;
+			default:
+				smc_wr_rx_post(link); /* refill WR RX */
+				break;
+			}
+		}
+	}
+}
+
+static void smc_wr_rx_tasklet_fn(unsigned long data)
+{
+	struct smc_ib_device *dev = (struct smc_ib_device *)data;
+	struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
+	int polled = 0;
+	int rc;
+
+again:
+	polled++;
+	do {
+		memset(&wc, 0, sizeof(wc));
+		rc = ib_poll_cq(dev->roce_cq_recv, SMC_WR_MAX_POLL_CQE, wc);
+		if (polled == 1) {
+			ib_req_notify_cq(dev->roce_cq_recv,
+					 IB_CQ_SOLICITED_MASK
+					 | IB_CQ_REPORT_MISSED_EVENTS);
+		}
+		if (!rc)
+			break;
+		smc_wr_rx_process_cqes(&wc[0], rc);
+	} while (rc > 0);
+	if (polled == 1)
+		goto again;
+}
+
+void smc_wr_rx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
+{
+	struct smc_ib_device *dev = (struct smc_ib_device *)cq_context;
+
+	tasklet_schedule(&dev->recv_tasklet);
+}
+
+int smc_wr_rx_post_init(struct smc_link *link)
+{
+	u32 i;
+	int rc = 0;
+
+	for (i = 0; i < link->wr_rx_cnt; i++)
+		rc = smc_wr_rx_post(link);
+	return rc;
+}
+
+/***************************** init, exit, misc ******************************/
+
+void smc_wr_remember_qp_attr(struct smc_link *lnk)
+{
+	struct ib_qp_attr *attr = &lnk->qp_attr;
+	struct ib_qp_init_attr init_attr;
+
+	memset(attr, 0, sizeof(*attr));
+	memset(&init_attr, 0, sizeof(init_attr));
+	ib_query_qp(lnk->roce_qp, attr,
+		    IB_QP_STATE |
+		    IB_QP_CUR_STATE |
+		    IB_QP_PKEY_INDEX |
+		    IB_QP_PORT |
+		    IB_QP_QKEY |
+		    IB_QP_AV |
+		    IB_QP_PATH_MTU |
+		    IB_QP_TIMEOUT |
+		    IB_QP_RETRY_CNT |
+		    IB_QP_RNR_RETRY |
+		    IB_QP_RQ_PSN |
+		    IB_QP_ALT_PATH |
+		    IB_QP_MIN_RNR_TIMER |
+		    IB_QP_SQ_PSN |
+		    IB_QP_PATH_MIG_STATE |
+		    IB_QP_CAP |
+		    IB_QP_DEST_QPN,
+		    &init_attr);
+
+	lnk->wr_tx_cnt = min_t(size_t, SMC_WR_BUF_CNT,
+			       lnk->qp_attr.cap.max_send_wr);
+	lnk->wr_rx_cnt = min_t(size_t, SMC_WR_BUF_CNT * 3,
+			       lnk->qp_attr.cap.max_recv_wr);
+}
+
+static void smc_wr_init_sge(struct smc_link *lnk)
+{
+	u32 i;
+
+	for (i = 0; i < lnk->wr_tx_cnt; i++) {
+		lnk->wr_tx_sges[i].addr =
+			lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
+		lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
+		lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
+		lnk->wr_tx_ibs[i].next = NULL;
+		lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i];
+		lnk->wr_tx_ibs[i].num_sge = 1;
+		lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
+		lnk->wr_tx_ibs[i].send_flags =
+			IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+	}
+	for (i = 0; i < lnk->wr_rx_cnt; i++) {
+		lnk->wr_rx_sges[i].addr =
+			lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE;
+		lnk->wr_rx_sges[i].length = SMC_WR_BUF_SIZE;
+		lnk->wr_rx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
+		lnk->wr_rx_ibs[i].next = NULL;
+		lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[i];
+		lnk->wr_rx_ibs[i].num_sge = 1;
+	}
+	lnk->wr_reg.wr.next = NULL;
+	lnk->wr_reg.wr.num_sge = 0;
+	lnk->wr_reg.wr.send_flags = IB_SEND_SIGNALED;
+	lnk->wr_reg.wr.opcode = IB_WR_REG_MR;
+	lnk->wr_reg.access = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE;
+}
+
+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 (!lnk->smcibdev)
+		return;
+	ibdev = lnk->smcibdev->ibdev;
+
+	if (lnk->wr_rx_dma_addr) {
+		ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
+				    SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+				    DMA_FROM_DEVICE);
+		lnk->wr_rx_dma_addr = 0;
+	}
+	if (lnk->wr_tx_dma_addr) {
+		ib_dma_unmap_single(ibdev, lnk->wr_tx_dma_addr,
+				    SMC_WR_BUF_SIZE * lnk->wr_tx_cnt,
+				    DMA_TO_DEVICE);
+		lnk->wr_tx_dma_addr = 0;
+	}
+}
+
+void smc_wr_free_link_mem(struct smc_link *lnk)
+{
+	kfree(lnk->wr_tx_pends);
+	lnk->wr_tx_pends = NULL;
+	kfree(lnk->wr_tx_mask);
+	lnk->wr_tx_mask = NULL;
+	kfree(lnk->wr_tx_sges);
+	lnk->wr_tx_sges = NULL;
+	kfree(lnk->wr_rx_sges);
+	lnk->wr_rx_sges = NULL;
+	kfree(lnk->wr_rx_ibs);
+	lnk->wr_rx_ibs = NULL;
+	kfree(lnk->wr_tx_ibs);
+	lnk->wr_tx_ibs = NULL;
+	kfree(lnk->wr_tx_bufs);
+	lnk->wr_tx_bufs = NULL;
+	kfree(lnk->wr_rx_bufs);
+	lnk->wr_rx_bufs = NULL;
+}
+
+int smc_wr_alloc_link_mem(struct smc_link *link)
+{
+	/* allocate link related memory */
+	link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL);
+	if (!link->wr_tx_bufs)
+		goto no_mem;
+	link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, SMC_WR_BUF_SIZE,
+				   GFP_KERNEL);
+	if (!link->wr_rx_bufs)
+		goto no_mem_wr_tx_bufs;
+	link->wr_tx_ibs = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_ibs[0]),
+				  GFP_KERNEL);
+	if (!link->wr_tx_ibs)
+		goto no_mem_wr_rx_bufs;
+	link->wr_rx_ibs = kcalloc(SMC_WR_BUF_CNT * 3,
+				  sizeof(link->wr_rx_ibs[0]),
+				  GFP_KERNEL);
+	if (!link->wr_rx_ibs)
+		goto no_mem_wr_tx_ibs;
+	link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]),
+				   GFP_KERNEL);
+	if (!link->wr_tx_sges)
+		goto no_mem_wr_rx_ibs;
+	link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
+				   sizeof(link->wr_rx_sges[0]),
+				   GFP_KERNEL);
+	if (!link->wr_rx_sges)
+		goto no_mem_wr_tx_sges;
+	link->wr_tx_mask = kcalloc(BITS_TO_LONGS(SMC_WR_BUF_CNT),
+				   sizeof(*link->wr_tx_mask),
+				   GFP_KERNEL);
+	if (!link->wr_tx_mask)
+		goto no_mem_wr_rx_sges;
+	link->wr_tx_pends = kcalloc(SMC_WR_BUF_CNT,
+				    sizeof(link->wr_tx_pends[0]),
+				    GFP_KERNEL);
+	if (!link->wr_tx_pends)
+		goto no_mem_wr_tx_mask;
+	return 0;
+
+no_mem_wr_tx_mask:
+	kfree(link->wr_tx_mask);
+no_mem_wr_rx_sges:
+	kfree(link->wr_rx_sges);
+no_mem_wr_tx_sges:
+	kfree(link->wr_tx_sges);
+no_mem_wr_rx_ibs:
+	kfree(link->wr_rx_ibs);
+no_mem_wr_tx_ibs:
+	kfree(link->wr_tx_ibs);
+no_mem_wr_rx_bufs:
+	kfree(link->wr_rx_bufs);
+no_mem_wr_tx_bufs:
+	kfree(link->wr_tx_bufs);
+no_mem:
+	return -ENOMEM;
+}
+
+void smc_wr_remove_dev(struct smc_ib_device *smcibdev)
+{
+	tasklet_kill(&smcibdev->recv_tasklet);
+	tasklet_kill(&smcibdev->send_tasklet);
+}
+
+void smc_wr_add_dev(struct smc_ib_device *smcibdev)
+{
+	tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn,
+		     (unsigned long)smcibdev);
+	tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn,
+		     (unsigned long)smcibdev);
+}
+
+int smc_wr_create_link(struct smc_link *lnk)
+{
+	struct ib_device *ibdev = lnk->smcibdev->ibdev;
+	int rc = 0;
+
+	smc_wr_tx_set_wr_id(&lnk->wr_tx_id, 0);
+	lnk->wr_rx_id = 0;
+	lnk->wr_rx_dma_addr = ib_dma_map_single(
+		ibdev, lnk->wr_rx_bufs,	SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+		DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(ibdev, lnk->wr_rx_dma_addr)) {
+		lnk->wr_rx_dma_addr = 0;
+		rc = -EIO;
+		goto out;
+	}
+	lnk->wr_tx_dma_addr = ib_dma_map_single(
+		ibdev, lnk->wr_tx_bufs,	SMC_WR_BUF_SIZE * lnk->wr_tx_cnt,
+		DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(ibdev, lnk->wr_tx_dma_addr)) {
+		rc = -EIO;
+		goto dma_unmap;
+	}
+	smc_wr_init_sge(lnk);
+	memset(lnk->wr_tx_mask, 0,
+	       BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask));
+	init_waitqueue_head(&lnk->wr_tx_wait);
+	init_waitqueue_head(&lnk->wr_reg_wait);
+	return rc;
+
+dma_unmap:
+	ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
+			    SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+			    DMA_FROM_DEVICE);
+	lnk->wr_rx_dma_addr = 0;
+out:
+	return rc;
+}
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
new file mode 100644
index 000000000..1d85bb14f
--- /dev/null
+++ b/net/smc/smc_wr.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Work Requests exploiting Infiniband API
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s):  Steffen Maier <maier@linux.vnet.ibm.com>
+ */
+
+#ifndef SMC_WR_H
+#define SMC_WR_H
+
+#include <linux/atomic.h>
+#include <rdma/ib_verbs.h>
+#include <asm/div64.h>
+
+#include "smc.h"
+#include "smc_core.h"
+
+#define SMC_WR_BUF_CNT 16	/* # of ctrl buffers per link */
+
+#define SMC_WR_TX_WAIT_FREE_SLOT_TIME	(10 * HZ)
+#define SMC_WR_TX_WAIT_PENDING_TIME	(5 * HZ)
+
+#define SMC_WR_TX_SIZE 44 /* actual size of wr_send data (<=SMC_WR_BUF_SIZE) */
+
+#define SMC_WR_TX_PEND_PRIV_SIZE 32
+
+struct smc_wr_tx_pend_priv {
+	u8			priv[SMC_WR_TX_PEND_PRIV_SIZE];
+};
+
+typedef void (*smc_wr_tx_handler)(struct smc_wr_tx_pend_priv *,
+				  struct smc_link *,
+				  enum ib_wc_status);
+
+typedef bool (*smc_wr_tx_filter)(struct smc_wr_tx_pend_priv *,
+				 unsigned long);
+
+typedef void (*smc_wr_tx_dismisser)(struct smc_wr_tx_pend_priv *);
+
+struct smc_wr_rx_handler {
+	struct hlist_node	list;	/* hash table collision resolution */
+	void			(*handler)(struct ib_wc *, void *);
+	u8			type;
+};
+
+/* Only used by RDMA write WRs.
+ * All other WRs (CDC/LLC) use smc_wr_tx_send handling WR_ID implicitly
+ */
+static inline long smc_wr_tx_get_next_wr_id(struct smc_link *link)
+{
+	return atomic_long_inc_return(&link->wr_tx_id);
+}
+
+static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
+{
+	atomic_long_set(wr_tx_id, val);
+}
+
+/* post a new receive work request to fill a completed old work request entry */
+static inline int smc_wr_rx_post(struct smc_link *link)
+{
+	int rc;
+	u64 wr_id, temp_wr_id;
+	u32 index;
+
+	wr_id = ++link->wr_rx_id; /* tasklet context, thus not atomic */
+	temp_wr_id = wr_id;
+	index = do_div(temp_wr_id, link->wr_rx_cnt);
+	link->wr_rx_ibs[index].wr_id = wr_id;
+	rc = ib_post_recv(link->roce_qp, &link->wr_rx_ibs[index], NULL);
+	return rc;
+}
+
+int smc_wr_create_link(struct smc_link *lnk);
+int smc_wr_alloc_link_mem(struct smc_link *lnk);
+void smc_wr_free_link(struct smc_link *lnk);
+void smc_wr_free_link_mem(struct smc_link *lnk);
+void smc_wr_remember_qp_attr(struct smc_link *lnk);
+void smc_wr_remove_dev(struct smc_ib_device *smcibdev);
+void smc_wr_add_dev(struct smc_ib_device *smcibdev);
+
+int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler,
+			    struct smc_wr_buf **wr_buf,
+			    struct smc_wr_tx_pend_priv **wr_pend_priv);
+int smc_wr_tx_put_slot(struct smc_link *link,
+		       struct smc_wr_tx_pend_priv *wr_pend_priv);
+int smc_wr_tx_send(struct smc_link *link,
+		   struct smc_wr_tx_pend_priv *wr_pend_priv);
+void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context);
+void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
+			     smc_wr_tx_filter filter,
+			     smc_wr_tx_dismisser dismisser,
+			     unsigned long data);
+
+int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
+int smc_wr_rx_post_init(struct smc_link *link);
+void smc_wr_rx_cq_handler(struct ib_cq *ib_cq, void *cq_context);
+int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr);
+
+#endif /* SMC_WR_H */