net/smc: provide fallback reason code

Remember the fallback reason code and the peer diagnosis code for
smc sockets, and provide them in smc_diag.c to the netlink interface.
And add more detailed reason codes.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/uapi/linux/smc_diag.h

@@ -43,6 +43,7 @@ enum {
 	SMC_DIAG_LGRINFO,
 	SMC_DIAG_SHUTDOWN,
 	SMC_DIAG_DMBINFO,
+	SMC_DIAG_FALLBACK,
 	__SMC_DIAG_MAX,
 };
 
@@ -92,6 +93,11 @@ struct smc_diag_lgrinfo {
 	__u8				role;
 };
 
+struct smc_diag_fallback {
+	__u32 reason;
+	__u32 peer_diagnosis;
+};
+
 struct smcd_diag_dmbinfo {		/* SMC-D Socket internals */
 	__u32 linkid;			/* Link identifier */
 	__u64 peer_gid;			/* Peer GID */

net/smc/af_smc.c

@@ -344,17 +344,17 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 	rc = smc_ib_modify_qp_rts(link);
 	if (rc)
-		return SMC_CLC_DECL_INTERR;
+		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_INTERR;
+		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_TCL;
+		return SMC_CLC_DECL_TIMEOUT_CL;
 
 	/* receive ADD LINK request from server over RoCE fabric */
 	rest = wait_for_completion_interruptible_timeout(&link->llc_add,
@@ -372,7 +372,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 				   link->smcibdev->mac[link->ibport - 1],
 				   link->gid, SMC_LLC_RESP);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		return SMC_CLC_DECL_TIMEOUT_AL;
 
 	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
 
@@ -424,9 +424,10 @@ static void smc_link_save_peer_info(struct smc_link *link,
 }
 
 /* fall back during connect */
-static int smc_connect_fallback(struct smc_sock *smc)
+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;
@@ -443,7 +444,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
 	}
-	if (reason_code != SMC_CLC_DECL_REPLY) {
+	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)
@@ -451,7 +452,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 			return rc;
 		}
 	}
-	return smc_connect_fallback(smc);
+	return smc_connect_fallback(smc, reason_code);
 }
 
 /* abort connecting */
@@ -568,7 +569,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		smc_link_save_peer_info(link, aclc);
 
 	if (smc_rmb_rtoken_handling(&smc->conn, aclc))
-		return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+		return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
 					 local_contact);
 
 	smc_close_init(smc);
@@ -576,12 +577,12 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	if (local_contact == SMC_FIRST_CONTACT) {
 		if (smc_ib_ready_link(link))
-			return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+			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_INTERR,
+			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
 						 local_contact);
 	}
 	smc_rmb_sync_sg_for_device(&smc->conn);
@@ -659,11 +660,11 @@ static int __smc_connect(struct smc_sock *smc)
 	sock_hold(&smc->sk); /* sock put in passive closing */
 
 	if (smc->use_fallback)
-		return smc_connect_fallback(smc);
+		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);
+		return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
 
 	/* IPSec connections opt out of SMC-R optimizations */
 	if (using_ipsec(smc))
@@ -693,7 +694,7 @@ static int __smc_connect(struct smc_sock *smc)
 
 	/* if neither ISM nor RDMA are supported, fallback */
 	if (!rdma_supported && !ism_supported)
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+		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);
@@ -708,7 +709,7 @@ static int __smc_connect(struct smc_sock *smc)
 	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
 		rc = smc_connect_ism(smc, &aclc, ismdev);
 	else
-		rc = SMC_CLC_DECL_CNFERR;
+		rc = SMC_CLC_DECL_MODEUNSUPP;
 	if (rc) {
 		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
@@ -946,12 +947,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 	link = &lgr->lnk[SMC_SINGLE_LINK];
 
 	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
-		return SMC_CLC_DECL_INTERR;
+		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_TCL;
+		return SMC_CLC_DECL_TIMEOUT_CL;
 
 	/* receive CONFIRM LINK response from client over the RoCE fabric */
 	rest = wait_for_completion_interruptible_timeout(
@@ -973,7 +974,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 				   link->smcibdev->mac[link->ibport - 1],
 				   link->gid, SMC_LLC_REQ);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		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,
@@ -1048,7 +1049,8 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	}
 	smc_conn_free(&new_smc->conn);
 	new_smc->use_fallback = true;
-	if (reason_code && reason_code != SMC_CLC_DECL_REPLY) {
+	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;
@@ -1139,7 +1141,7 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
 	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_INTERR;
+				return SMC_CLC_DECL_ERR_REGRMB;
 		}
 	}
 	smc_rmb_sync_sg_for_device(&new_smc->conn);
@@ -1159,13 +1161,13 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc,
 		smc_link_save_peer_info(link, cclc);
 
 	if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) {
-		reason_code = SMC_CLC_DECL_INTERR;
+		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_INTERR;
+			reason_code = SMC_CLC_DECL_ERR_RDYLNK;
 			goto decline;
 		}
 		/* QP confirmation over RoCE fabric */
@@ -1206,6 +1208,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* 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;
 	}
@@ -1250,7 +1253,8 @@ static void smc_listen_work(struct work_struct *work)
 	     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_CNFERR, local_contact);
+		smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
+				   local_contact);
 		return;
 	}
 
@@ -1297,6 +1301,7 @@ static void smc_tcp_listen_work(struct work_struct *work)
 
 		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);
@@ -1451,6 +1456,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	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;
@@ -1648,6 +1654,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		/* 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;
@@ -1885,6 +1892,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol,
 	/* 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) {

net/smc/smc.h

@@ -208,6 +208,8 @@ struct smc_sock {				/* smc sock container */
 	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

net/smc/smc_clc.c

@@ -334,7 +334,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		goto out;
 	}
 	if (clcm->type == SMC_CLC_DECLINE) {
-		reason_code = SMC_CLC_DECL_REPLY;
+		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);

net/smc/smc_clc.h

@@ -28,15 +28,21 @@
 #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	0x02000000  /* timeout                        */
+#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_IPSEC	0x03030000  /* IPsec usage                    */
+#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_REPLY	0x06000000  /* reply to a received decline    */
+#define SMC_CLC_DECL_PEERDECL	0x05000000  /* peer declined during handshake */
 #define SMC_CLC_DECL_INTERR	0x99990000  /* internal error                 */
-#define SMC_CLC_DECL_TCL	0x02040000  /* timeout w4 QP confirm          */
-#define SMC_CLC_DECL_SEND	0x07000000  /* sending problem                */
-#define SMC_CLC_DECL_RMBE_EC	0x08000000  /* peer has eyecatcher in RMBE    */
+#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 */

net/smc/smc_diag.c

@@ -79,6 +79,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 			   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;
@@ -101,6 +102,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	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;