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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 105 insertions, 87 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 6fd44bdb0fc3..903321543838 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -337,50 +337,61 @@ 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, 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)
-{
-	if (!rmb_desc->wr_reg) {
-		/* 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;
-		}
-		rmb_desc->wr_reg = 1;
+/* register the new rmb on all links */
+static int smcr_lgr_reg_rmbs(struct smc_link *link,
+			     struct smc_buf_desc *rmb_desc)
+{
+	struct smc_link_group *lgr = link->lgr;
+	int i, rc = 0;
+
+	rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
+	if (rc)
+		return rc;
+	/* protect against parallel smc_llc_cli_rkey_exchange() and
+	 * parallel smcr_link_reg_rmb()
+	 */
+	mutex_lock(&lgr->llc_conf_mutex);
+	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+		if (lgr->lnk[i].state != SMC_LNK_ACTIVE)
+			continue;
+		rc = smcr_link_reg_rmb(&lgr->lnk[i], rmb_desc);
+		if (rc)
+			goto out;
 	}
-	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;
+	rc = smc_llc_do_confirm_rkey(link, rmb_desc);
+	if (rc) {
+		rc = -EFAULT;
+		goto out;
 	}
-	return 0;
+	rmb_desc->is_conf_rkey = true;
+out:
+	mutex_unlock(&lgr->llc_conf_mutex);
+	smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
+	return rc;
 }
 
-static int smc_clnt_conf_first_link(struct smc_sock *smc)
+static int smcr_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;
+	struct smc_link *link = smc->conn.lnk;
+	struct smc_llc_qentry *qentry;
 	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) {
+	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+			      SMC_LLC_CONFIRM_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);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
-
-	if (link->llc_confirm_rc)
+	smc_llc_save_peer_uid(qentry);
+	rc = smc_llc_eval_conf_link(qentry, SMC_LLC_REQ);
+	smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl);
+	if (rc)
 		return SMC_CLC_DECL_RMBE_EC;
 
 	rc = smc_ib_modify_qp_rts(link);
@@ -389,34 +400,34 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 	smc_wr_remember_qp_attr(link);
 
-	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
+	if (smcr_link_reg_rmb(link, smc->conn.rmb_desc))
 		return SMC_CLC_DECL_ERR_REGRMB;
 
+	/* confirm_rkey is implicit on 1st contact */
+	smc->conn.rmb_desc->is_conf_rkey = true;
+
 	/* 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) {
+	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);
-		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
+		if (rc == -EAGAIN)
+			rc = 0; /* no DECLINE received, go with one link */
+		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);
-
+	smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
+	smc_llc_cli_add_link(link, qentry);
 	return 0;
 }
 
@@ -596,8 +607,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 			    struct smc_clc_msg_accept_confirm *aclc,
 			    struct smc_init_info *ini)
 {
+	int i, reason_code = 0;
 	struct smc_link *link;
-	int reason_code = 0;
 
 	ini->is_smcd = false;
 	ini->ib_lcl = &aclc->lcl;
@@ -610,10 +621,28 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		mutex_unlock(&smc_client_lgr_pending);
 		return reason_code;
 	}
-	link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
 	smc_conn_save_peer_info(smc, aclc);
 
+	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+		link = smc->conn.lnk;
+	} else {
+		/* set link that was assigned by server */
+		link = NULL;
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			struct smc_link *l = &smc->conn.lgr->lnk[i];
+
+			if (l->peer_qpn == ntoh24(aclc->qpn)) {
+				link = l;
+				break;
+			}
+		}
+		if (!link)
+			return smc_connect_abort(smc, SMC_CLC_DECL_NOSRVLINK,
+						 ini->cln_first_contact);
+		smc->conn.lnk = link;
+	}
+
 	/* create send buffer and rmb */
 	if (smc_buf_create(smc, false))
 		return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
@@ -622,7 +651,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	if (ini->cln_first_contact == SMC_FIRST_CONTACT)
 		smc_link_save_peer_info(link, aclc);
 
-	if (smc_rmb_rtoken_handling(&smc->conn, aclc))
+	if (smc_rmb_rtoken_handling(&smc->conn, link, aclc))
 		return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
 					 ini->cln_first_contact);
 
@@ -634,7 +663,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
 						 ini->cln_first_contact);
 	} else {
-		if (smc_reg_rmb(link, smc->conn.rmb_desc, true))
+		if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc))
 			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
 						 ini->cln_first_contact);
 	}
@@ -649,7 +678,9 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
 		/* QP confirmation over RoCE fabric */
-		reason_code = smc_clnt_conf_first_link(smc);
+		smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK);
+		reason_code = smcr_clnt_conf_first_link(smc);
+		smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl);
 		if (reason_code)
 			return smc_connect_abort(smc, reason_code,
 						 ini->cln_first_contact);
@@ -999,17 +1030,13 @@ void smc_close_non_accepted(struct sock *sk)
 	sock_put(sk); /* final sock_put */
 }
 
-static int smc_serv_conf_first_link(struct smc_sock *smc)
+static int smcr_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;
+	struct smc_link *link = smc->conn.lnk;
+	struct smc_llc_qentry *qentry;
 	int rc;
 
-	link = &lgr->lnk[SMC_SINGLE_LINK];
-
-	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
+	if (smcr_link_reg_rmb(link, smc->conn.rmb_desc))
 		return SMC_CLC_DECL_ERR_REGRMB;
 
 	/* send CONFIRM LINK request to client over the RoCE fabric */
@@ -1018,40 +1045,29 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 		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) {
+	qentry = smc_llc_wait(link->lgr, link, SMC_LLC_WAIT_TIME,
+			      SMC_LLC_CONFIRM_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);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
-
-	if (link->llc_confirm_resp_rc)
+	smc_llc_save_peer_uid(qentry);
+	rc = smc_llc_eval_conf_link(qentry, SMC_LLC_RESP);
+	smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl);
+	if (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, CLC_WAIT_TIME_SHORT);
-		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
-	}
+	/* confirm_rkey is implicit on 1st contact */
+	smc->conn.rmb_desc->is_conf_rkey = true;
 
-	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
+	smc_llc_link_active(link);
+	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
+	/* initial contact - try to establish second link */
+	smc_llc_srv_add_link(link);
 	return 0;
 }
 
@@ -1194,10 +1210,10 @@ static int smc_listen_ism_init(struct smc_sock *new_smc,
 /* 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];
+	struct smc_connection *conn = &new_smc->conn;
 
 	if (local_contact != SMC_FIRST_CONTACT) {
-		if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
+		if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc))
 			return SMC_CLC_DECL_ERR_REGRMB;
 	}
 	smc_rmb_sync_sg_for_device(&new_smc->conn);
@@ -1210,13 +1226,13 @@ 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];
+	struct smc_link *link = new_smc->conn.lnk;
 	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)) {
+	if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) {
 		reason_code = SMC_CLC_DECL_ERR_RTOK;
 		goto decline;
 	}
@@ -1227,7 +1243,9 @@ static int smc_listen_rdma_finish(struct smc_sock *new_smc,
 			goto decline;
 		}
 		/* QP confirmation over RoCE fabric */
-		reason_code = smc_serv_conf_first_link(new_smc);
+		smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK);
+		reason_code = smcr_serv_conf_first_link(new_smc);
+		smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl);
 		if (reason_code)
 			goto decline;
 	}