1 files changed, 119 insertions, 48 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a7f887d91d89..bacdd971615e 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -378,8 +378,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_state = SMC_INIT;
 	sk->sk_destruct = smc_destruct;
 	sk->sk_protocol = protocol;
-	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem));
-	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem));
+	WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem));
+	WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem));
 	smc = smc_sk(sk);
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
 	INIT_WORK(&smc->connect_work, smc_connect_work);
@@ -436,24 +436,9 @@ 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;
-}
+/* 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)
+ */
 
 #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
 			     (1UL << SOCK_KEEPOPEN) | \
@@ -470,9 +455,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
 			     (1UL << SOCK_NOFCS) | \
 			     (1UL << SOCK_FILTER_LOCKED) | \
 			     (1UL << SOCK_TSTAMP_NEW))
-/* 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)
- */
+
+/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */
+static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk,
+				     unsigned long mask)
+{
+	struct net *nnet = sock_net(nsk);
+
+	nsk->sk_userlocks = osk->sk_userlocks;
+	if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) {
+		nsk->sk_sndbuf = osk->sk_sndbuf;
+	} else {
+		if (mask == SK_FLAGS_SMC_TO_CLC)
+			WRITE_ONCE(nsk->sk_sndbuf,
+				   READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1]));
+		else
+			WRITE_ONCE(nsk->sk_sndbuf,
+				   2 * READ_ONCE(nnet->smc.sysctl_wmem));
+	}
+	if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) {
+		nsk->sk_rcvbuf = osk->sk_rcvbuf;
+	} else {
+		if (mask == SK_FLAGS_SMC_TO_CLC)
+			WRITE_ONCE(nsk->sk_rcvbuf,
+				   READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1]));
+		else
+			WRITE_ONCE(nsk->sk_rcvbuf,
+				   2 * READ_ONCE(nnet->smc.sysctl_rmem));
+	}
+}
+
+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_sndtimeo = osk->sk_sndtimeo;
+	nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
+	nsk->sk_mark = READ_ONCE(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;
+
+	smc_adjust_sock_bufsizes(nsk, osk, mask);
+}
+
 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);
@@ -610,20 +641,22 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	/* optional 2nd link, receive ADD LINK request from server */
-	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
-			      SMC_LLC_ADD_LINK);
-	if (!qentry) {
-		struct smc_clc_msg_decline dclc;
-
-		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
-		if (rc == -EAGAIN)
-			rc = 0; /* no DECLINE received, go with one link */
-		return rc;
+	if (link->lgr->max_links > 1) {
+		/* optional 2nd link, receive ADD LINK request from server */
+		qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+				      SMC_LLC_ADD_LINK);
+		if (!qentry) {
+			struct smc_clc_msg_decline dclc;
+
+			rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+					      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+			if (rc == -EAGAIN)
+				rc = 0; /* no DECLINE received, go with one link */
+			return rc;
+		}
+		smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
+		smc_llc_cli_add_link(link, qentry);
 	}
-	smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
-	smc_llc_cli_add_link(link, qentry);
 	return 0;
 }
 
@@ -1113,7 +1146,7 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 
 #define SMC_CLC_MAX_ACCEPT_LEN \
 	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
-	 sizeof(struct smc_clc_first_contact_ext) + \
+	 sizeof(struct smc_clc_first_contact_ext_v2x) + \
 	 sizeof(struct smc_clc_msg_trail))
 
 /* CLC handshake during connect */
@@ -1167,8 +1200,8 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
 		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 	struct smc_clc_first_contact_ext *fce =
-		(struct smc_clc_first_contact_ext *)
-			(((u8 *)clc_v2) + sizeof(*clc_v2));
+		smc_get_clc_first_contact_ext(clc_v2, false);
+	int rc;
 
 	if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
 		return 0;
@@ -1187,6 +1220,12 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 			return SMC_CLC_DECL_NOINDIRECT;
 		}
 	}
+
+	ini->release_nr = fce->release;
+	rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+	if (rc)
+		return rc;
+
 	return 0;
 }
 
@@ -1205,6 +1244,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN);
 	memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE);
 	memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN);
+	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
 
 	reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini);
 	if (reason_code)
@@ -1355,6 +1396,16 @@ static int smc_connect_ism(struct smc_sock *smc,
 		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
 			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 
+		if (ini->first_contact_peer) {
+			struct smc_clc_first_contact_ext *fce =
+				smc_get_clc_first_contact_ext(aclc_v2, true);
+
+			ini->release_nr = fce->release;
+			rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+			if (rc)
+				return rc;
+		}
+
 		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
 		if (rc)
 			return rc;
@@ -1389,7 +1440,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 	}
 
 	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
-				  aclc->hdr.version, eid, NULL);
+				  aclc->hdr.version, eid, ini);
 	if (rc)
 		goto connect_abort;
 	mutex_unlock(&smc_server_lgr_pending);
@@ -1789,7 +1840,7 @@ void smc_close_non_accepted(struct sock *sk)
 	lock_sock(sk);
 	if (!sk->sk_lingertime)
 		/* wait for peer closing */
-		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
+		WRITE_ONCE(sk->sk_lingertime, SMC_MAX_STREAM_WAIT_TIMEOUT);
 	__smc_release(smc);
 	release_sock(sk);
 	sock_put(sk); /* sock_hold above */
@@ -1839,10 +1890,12 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	down_write(&link->lgr->llc_conf_mutex);
-	/* initial contact - try to establish second link */
-	smc_llc_srv_add_link(link, NULL);
-	up_write(&link->lgr->llc_conf_mutex);
+	if (link->lgr->max_links > 1) {
+		down_write(&link->lgr->llc_conf_mutex);
+		/* initial contact - try to establish second link */
+		smc_llc_srv_add_link(link, NULL);
+		up_write(&link->lgr->llc_conf_mutex);
+	}
 	return 0;
 }
 
@@ -1965,6 +2018,10 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
 		}
 	}
 
+	ini->release_nr = pclc_v2_ext->hdr.flag.release;
+	if (pclc_v2_ext->hdr.flag.release > SMC_RELEASE)
+		ini->release_nr = SMC_RELEASE;
+
 out:
 	if (!ini->smcd_version && !ini->smcr_version)
 		return rc;
@@ -2399,6 +2456,10 @@ static void smc_listen_work(struct work_struct *work)
 	if (rc)
 		goto out_decl;
 
+	rc = smc_clc_srv_v2x_features_validate(pclc, ini);
+	if (rc)
+		goto out_decl;
+
 	mutex_lock(&smc_server_lgr_pending);
 	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
@@ -2412,7 +2473,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* send SMC Accept CLC message */
 	accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version;
 	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,
-				 accept_version, ini->negotiated_eid);
+				 accept_version, ini->negotiated_eid, ini);
 	if (rc)
 		goto out_unlock;
 
@@ -2431,6 +2492,18 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_decl;
 	}
 
+	rc = smc_clc_v2x_features_confirm_check(cclc, ini);
+	if (rc) {
+		if (!ini->is_smcd)
+			goto out_unlock;
+		goto out_decl;
+	}
+
+	/* fce smc release version is needed in smc_listen_rdma_finish,
+	 * so save fce info here.
+	 */
+	smc_conn_save_peer_info_fce(new_smc, cclc);
+
 	/* finish worker */
 	if (!ini->is_smcd) {
 		rc = smc_listen_rdma_finish(new_smc, cclc,
@@ -2479,8 +2552,6 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		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 (!queue_work(smc_hs_wq, &new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);