smc: connection and link group creation

* create smc_connection for SMC-sockets
* determine suitable link group for a connection
* create a new link group if necessary

Signed-off-by: Ursula Braun <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Ursula Braun

net/smc/Makefile

@@ -1,2 +1,2 @@
 obj-$(CONFIG_SMC)	+= smc.o
-smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o
+smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o

net/smc/af_smc.c

@@ -31,9 +31,19 @@
 
 #include "smc.h"
 #include "smc_clc.h"
+#include "smc_core.h"
 #include "smc_ib.h"
 #include "smc_pnet.h"
 
+static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
+						 * creation
+						 */
+
+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),
+};
+
 static void smc_tcp_listen_work(struct work_struct *);
 
 static void smc_set_keepalive(struct sock *sk, int val)
@@ -235,11 +245,31 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
 	return rc;
 }
 
+static void smc_conn_save_peer_info(struct smc_sock *smc,
+				    struct smc_clc_msg_accept_confirm *clc)
+{
+	smc->conn.peer_conn_idx = clc->conn_idx;
+}
+
+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;
+}
+
 /* setup for RDMA connection of client */
 static int smc_connect_rdma(struct smc_sock *smc)
 {
+	struct sockaddr_in *inaddr = (struct sockaddr_in *)smc->addr;
 	struct smc_clc_msg_accept_confirm aclc;
+	int local_contact = SMC_FIRST_CONTACT;
 	struct smc_ib_device *smcibdev;
+	struct smc_link *link;
+	u8 srv_first_contact;
 	int reason_code = 0;
 	int rc = 0;
 	u8 ibport;
@@ -278,26 +308,43 @@ static int smc_connect_rdma(struct smc_sock *smc)
 	if (reason_code > 0)
 		goto decline_rdma;
 
-	/* tbd in follow-on patch: more steps to setup RDMA communcication,
-	 * create connection, link group, link
-	 */
+	srv_first_contact = aclc.hdr.flag;
+	mutex_lock(&smc_create_lgr_pending);
+	local_contact = smc_conn_create(smc, inaddr->sin_addr.s_addr, smcibdev,
+					ibport, &aclc.lcl, srv_first_contact);
+	if (local_contact < 0) {
+		rc = local_contact;
+		if (rc == -ENOMEM)
+			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
+		else if (rc == -ENOLINK)
+			reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
+		goto decline_rdma_unlock;
+	}
+	link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
+	smc_conn_save_peer_info(smc, &aclc);
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_link_save_peer_info(link, &aclc);
 	/* tbd in follow-on patch: more steps to setup RDMA communcication,
 	 * create rmbs, map rmbs, rtoken_handling, modify_qp
 	 */
 
 	rc = smc_clc_send_confirm(smc);
 	if (rc)
-		goto out_err;
+		goto out_err_unlock;
 
 	/* tbd in follow-on patch: llc_confirm */
 
+	mutex_unlock(&smc_create_lgr_pending);
 out_connected:
 	smc_copy_sock_settings_to_clc(smc);
 	smc->sk.sk_state = SMC_ACTIVE;
 
-	return rc;
+	return rc ? rc : local_contact;
 
+decline_rdma_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
+	smc_conn_free(&smc->conn);
 decline_rdma:
 	/* RDMA setup failed, switch back to TCP */
 	smc->use_fallback = true;
@@ -308,6 +355,9 @@ static int smc_connect_rdma(struct smc_sock *smc)
 	}
 	goto out_connected;
 
+out_err_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
+	smc_conn_free(&smc->conn);
 out_err:
 	return rc;
 }
@@ -476,10 +526,12 @@ static void smc_listen_work(struct work_struct *work)
 	struct socket *newclcsock = new_smc->clcsock;
 	struct smc_sock *lsmc = new_smc->listen_smc;
 	struct smc_clc_msg_accept_confirm cclc;
+	int local_contact = SMC_REUSE_CONTACT;
 	struct sock *newsmcsk = &new_smc->sk;
 	struct smc_clc_msg_proposal pclc;
 	struct smc_ib_device *smcibdev;
 	struct sockaddr_in peeraddr;
+	struct smc_link *link;
 	int reason_code = 0;
 	int rc = 0, len;
 	__be32 subnet;
@@ -527,15 +579,30 @@ static void smc_listen_work(struct work_struct *work)
 	/* get address of the peer connected to the internal TCP socket */
 	kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr, &len);
 
-	/* tbd in follow-on patch: more steps to setup RDMA communcication,
-	 * create connection, link_group, link
-	 */
+	/* allocate connection / link group */
+	mutex_lock(&smc_create_lgr_pending);
+	local_contact = smc_conn_create(new_smc, peeraddr.sin_addr.s_addr,
+					smcibdev, ibport, &pclc.lcl, 0);
+	if (local_contact == SMC_REUSE_CONTACT)
+		/* lock no longer needed, free it due to following
+		 * smc_clc_wait_msg() call
+		 */
+		mutex_unlock(&smc_create_lgr_pending);
+	if (local_contact < 0) {
+		rc = local_contact;
+		if (rc == -ENOMEM)
+			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
+		else if (rc == -ENOLINK)
+			reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
+		goto decline_rdma;
+	}
+	link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
 	/* tbd in follow-on patch: more steps to setup RDMA communcication,
 	 * create rmbs, map rmbs
 	 */
 
-	rc = smc_clc_send_accept(new_smc);
+	rc = smc_clc_send_accept(new_smc, local_contact);
 	if (rc)
 		goto out_err;
 
@@ -546,6 +613,9 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_err;
 	if (reason_code > 0)
 		goto decline_rdma;
+	smc_conn_save_peer_info(new_smc, &cclc);
+	if (local_contact == SMC_FIRST_CONTACT)
+		smc_link_save_peer_info(link, &cclc);
 
 	/* tbd in follow-on patch: more steps to setup RDMA communcication,
 	 * rtoken_handling, modify_qp
@@ -555,6 +625,8 @@ static void smc_listen_work(struct work_struct *work)
 	sk_refcnt_debug_inc(newsmcsk);
 	newsmcsk->sk_state = SMC_ACTIVE;
 enqueue:
+	if (local_contact == SMC_FIRST_CONTACT)
+		mutex_unlock(&smc_create_lgr_pending);
 	lock_sock(&lsmc->sk);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
@@ -570,6 +642,7 @@ static void smc_listen_work(struct work_struct *work)
 
 decline_rdma:
 	/* RDMA setup failed, switch back to TCP */
+	smc_conn_free(&new_smc->conn);
 	new_smc->use_fallback = true;
 	if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
 		rc = smc_clc_send_decline(new_smc, reason_code, 0);
@@ -1024,6 +1097,17 @@ static int __init smc_init(void)
 
 static void __exit smc_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);
+		smc_lgr_free(lgr); /* free link group */
+	}
 	smc_ib_unregister_client();
 	sock_unregister(PF_SMC);
 	proto_unregister(&smc_proto);

net/smc/smc.h

@@ -14,6 +14,8 @@
 #include <linux/types.h>
 #include <net/sock.h>
 
+#include "smc_ib.h"
+
 #define SMCPROTO_SMC		0	/* SMC protocol */
 
 #define SMC_MAX_PORTS		2	/* Max # of ports */
@@ -25,9 +27,19 @@ enum smc_state {		/* possible states of an SMC socket */
 	SMC_LISTEN	= 10,
 };
 
+struct smc_link_group;
+
+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_conn_idx;	/* from tcp handshake */
+};
+
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
+	struct smc_connection	conn;		/* smc connection */
 	struct sockaddr		*addr;		/* inet connect address */
 	struct smc_sock		*listen_smc;	/* listen parent */
 	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
@@ -46,6 +58,24 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
 
 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)
 {
@@ -59,7 +89,13 @@ static inline bool using_ipsec(struct smc_sock *smc)
 }
 #endif
 
+struct smc_clc_msg_local;
+
 int smc_netinfo_by_tcpsk(struct socket *clcsock, __be32 *subnet,
 			 u8 *prefix_len);
+void smc_conn_free(struct smc_connection *conn);
+int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr,
+		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_clc_msg_local *lcl, int srv_first_contact);
 
 #endif	/* __SMC_H */

net/smc/smc_clc.c

@@ -14,6 +14,7 @@
 #include <net/tcp.h>
 
 #include "smc.h"
+#include "smc_core.h"
 #include "smc_clc.h"
 #include "smc_ib.h"
 
@@ -89,8 +90,13 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		reason_code = -EPROTO;
 		goto out;
 	}
-	if (clcm->type == SMC_CLC_DECLINE)
+	if (clcm->type == SMC_CLC_DECLINE) {
 		reason_code = SMC_CLC_DECL_REPLY;
+		if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
+			== SMC_CLC_DECL_SYNCERR)
+			smc->conn.lgr->sync_err = true;
+	}
+
 out:
 	return reason_code;
 }
@@ -175,25 +181,34 @@ int smc_clc_send_proposal(struct smc_sock *smc,
 /* 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;
 
+	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 	/* send SMC Confirm CLC msg */
 	memset(&cclc, 0, sizeof(cclc));
 	memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	cclc.hdr.type = SMC_CLC_CONFIRM;
 	cclc.hdr.length = htons(sizeof(cclc));
 	cclc.hdr.version = SMC_CLC_V1;		/* SMC version */
 	memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
-
-	/* tbd in follow-on patch: fill in link-related values */
+	memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+	       SMC_GID_SIZE);
+	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+	       sizeof(link->smcibdev->mac));
 
 	/* tbd in follow-on patch: fill in rmb-related values */
 
+	hton24(cclc.qpn, link->roce_qp->qp_num);
 	cclc.conn_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);
+	hton24(cclc.psn, link->psn_initial);
 
 	memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 
@@ -214,26 +229,37 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 }
 
 /* send CLC ACCEPT message across internal TCP socket */
-int smc_clc_send_accept(struct smc_sock *new_smc)
+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;
 
+	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 	memset(&aclc, 0, sizeof(aclc));
 	memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	aclc.hdr.type = SMC_CLC_ACCEPT;
 	aclc.hdr.length = htons(sizeof(aclc));
 	aclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	if (srv_first_contact)
+		aclc.hdr.flag = 1;
 	memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
-
-	/* tbd in follow-on patch: fill in link-related values */
+	memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+	       SMC_GID_SIZE);
+	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
+	       sizeof(link->smcibdev->mac[link->ibport - 1]));
 
 	/* tbd in follow-on patch: fill in rmb-related values */
 
+	hton24(aclc.qpn, link->roce_qp->qp_num);
 	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
+	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
+	aclc.qp_mtu = link->path_mtu;
+	hton24(aclc.psn, link->psn_initial);
 	memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 
 	memset(&msg, 0, sizeof(msg));

net/smc/smc_clc.h

@@ -109,6 +109,6 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
 int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
 			  u8 ibport);
 int smc_clc_send_confirm(struct smc_sock *smc);
-int smc_clc_send_accept(struct smc_sock *smc);
+int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
 
 #endif