Merge branch 'net-smc-add-support-for-generic-netlink-api'

Karsten Graul says:

====================
net/smc: Add support for generic netlink API

Up to version 4 this patch series was using the sock_diag netlink
infrastructure. This version is using the generic netlink API. Generic
netlink API offers a better type safety between kernel and userspace
communication.
Using the generic netlink API the smc module can now provide information
about SMC linkgroups, links and devices (both for SMC-R and SMC-D).

v2: Add missing include to uapi header smc_diag.h.

v3: Apply code style recommendations from review comments.
    Instead of using EXPORTs to allow the smc_diag module to access
    data of the smc module, introduce struct smc_diag_ops and let
    smc_diag access the required data using function pointers.

v4: Address checkpatch.pl warnings. Do not use static inline for
    functions.

v5: Use generic netlink API instead of the sock_diag netlink
    infrastructure.

v6: Integrate more review comments from Jakub.

v7: Use nla_nest_start() with the new family. Use .maxattr=1 in the
    genl family and define one entry for attribute 1 in the policy to
    reject this attritbute for all commands. All other possible attributes
    are rejected because NL_VALIDATE_STRICT is set for the policy
    implicitely, which includes NL_VALIDATE_MAXTYPE.
    Setting policy[0].strict_start_type=1 does not work here because there
    is no valid attribute defined for this family, only plain commands. For
    any type > maxtype (which is .maxattr) validate_nla() would return 0 to
    userspace instead of -EINVAL. What helps here is __nla_validate_parse()
    which checks for type > maxtype and returns -EINVAL when NL_VALIDATE_MAXTYPE
    is set. This requires the one entry for type == .maxattr with
    .type = NLA_REJECT in the nla_policy.
    When a future command wants to allow attributes then it can easily specify a
    dedicated .policy for this new command in the genl_ops array. This dedicated
    policy overlays the global policy specified in the genl_family structure.
====================

Link: https://lore.kernel.org/r/20201201192049.53517-1-kgraul@linux.ibm.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/uapi/linux/smc.h

@@ -33,4 +33,130 @@ enum {				/* SMC PNET Table commands */
 #define SMCR_GENL_FAMILY_NAME		"SMC_PNETID"
 #define SMCR_GENL_FAMILY_VERSION	1
 
+/* gennetlink interface to access non-socket information from SMC module */
+#define SMC_GENL_FAMILY_NAME		"SMC_GEN_NETLINK"
+#define SMC_GENL_FAMILY_VERSION		1
+
+#define SMC_PCI_ID_STR_LEN		16 /* Max length of pci id string */
+
+/* SMC_GENL_FAMILY commands */
+enum {
+	SMC_NETLINK_GET_SYS_INFO = 1,
+	SMC_NETLINK_GET_LGR_SMCR,
+	SMC_NETLINK_GET_LINK_SMCR,
+	SMC_NETLINK_GET_LGR_SMCD,
+	SMC_NETLINK_GET_DEV_SMCD,
+	SMC_NETLINK_GET_DEV_SMCR,
+};
+
+/* SMC_GENL_FAMILY top level attributes */
+enum {
+	SMC_GEN_UNSPEC,
+	SMC_GEN_SYS_INFO,		/* nest */
+	SMC_GEN_LGR_SMCR,		/* nest */
+	SMC_GEN_LINK_SMCR,		/* nest */
+	SMC_GEN_LGR_SMCD,		/* nest */
+	SMC_GEN_DEV_SMCD,		/* nest */
+	SMC_GEN_DEV_SMCR,		/* nest */
+	__SMC_GEN_MAX,
+	SMC_GEN_MAX = __SMC_GEN_MAX - 1
+};
+
+/* SMC_GEN_SYS_INFO attributes */
+enum {
+	SMC_NLA_SYS_UNSPEC,
+	SMC_NLA_SYS_VER,		/* u8 */
+	SMC_NLA_SYS_REL,		/* u8 */
+	SMC_NLA_SYS_IS_ISM_V2,		/* u8 */
+	SMC_NLA_SYS_LOCAL_HOST,		/* string */
+	SMC_NLA_SYS_SEID,		/* string */
+	__SMC_NLA_SYS_MAX,
+	SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1
+};
+
+/* SMC_NLA_LGR_V2 nested attributes */
+enum {
+	SMC_NLA_LGR_V2_VER,		/* u8 */
+	SMC_NLA_LGR_V2_REL,		/* u8 */
+	SMC_NLA_LGR_V2_OS,		/* u8 */
+	SMC_NLA_LGR_V2_NEG_EID,		/* string */
+	SMC_NLA_LGR_V2_PEER_HOST,	/* string */
+};
+
+/* SMC_GEN_LGR_SMCR attributes */
+enum {
+	SMC_NLA_LGR_R_UNSPEC,
+	SMC_NLA_LGR_R_ID,		/* u32 */
+	SMC_NLA_LGR_R_ROLE,		/* u8 */
+	SMC_NLA_LGR_R_TYPE,		/* u8 */
+	SMC_NLA_LGR_R_PNETID,		/* string */
+	SMC_NLA_LGR_R_VLAN_ID,		/* u8 */
+	SMC_NLA_LGR_R_CONNS_NUM,	/* u32 */
+	__SMC_NLA_LGR_R_MAX,
+	SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1
+};
+
+/* SMC_GEN_LINK_SMCR attributes */
+enum {
+	SMC_NLA_LINK_UNSPEC,
+	SMC_NLA_LINK_ID,		/* u8 */
+	SMC_NLA_LINK_IB_DEV,		/* string */
+	SMC_NLA_LINK_IB_PORT,		/* u8 */
+	SMC_NLA_LINK_GID,		/* string */
+	SMC_NLA_LINK_PEER_GID,		/* string */
+	SMC_NLA_LINK_CONN_CNT,		/* u32 */
+	SMC_NLA_LINK_NET_DEV,		/* u32 */
+	SMC_NLA_LINK_UID,		/* u32 */
+	SMC_NLA_LINK_PEER_UID,		/* u32 */
+	SMC_NLA_LINK_STATE,		/* u32 */
+	__SMC_NLA_LINK_MAX,
+	SMC_NLA_LINK_MAX = __SMC_NLA_LINK_MAX - 1
+};
+
+/* SMC_GEN_LGR_SMCD attributes */
+enum {
+	SMC_NLA_LGR_D_UNSPEC,
+	SMC_NLA_LGR_D_ID,		/* u32 */
+	SMC_NLA_LGR_D_GID,		/* u64 */
+	SMC_NLA_LGR_D_PEER_GID,		/* u64 */
+	SMC_NLA_LGR_D_VLAN_ID,		/* u8 */
+	SMC_NLA_LGR_D_CONNS_NUM,	/* u32 */
+	SMC_NLA_LGR_D_PNETID,		/* string */
+	SMC_NLA_LGR_D_CHID,		/* u16 */
+	SMC_NLA_LGR_D_PAD,		/* flag */
+	SMC_NLA_LGR_V2,			/* nest */
+	__SMC_NLA_LGR_D_MAX,
+	SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
+};
+
+/* SMC_NLA_DEV_PORT nested attributes */
+enum {
+	SMC_NLA_DEV_PORT_UNSPEC,
+	SMC_NLA_DEV_PORT_PNET_USR,	/* u8 */
+	SMC_NLA_DEV_PORT_PNETID,	/* string */
+	SMC_NLA_DEV_PORT_NETDEV,	/* u32 */
+	SMC_NLA_DEV_PORT_STATE,		/* u8 */
+	SMC_NLA_DEV_PORT_VALID,		/* u8 */
+	SMC_NLA_DEV_PORT_LNK_CNT,	/* u32 */
+	__SMC_NLA_DEV_PORT_MAX,
+	SMC_NLA_DEV_PORT_MAX = __SMC_NLA_DEV_PORT_MAX - 1
+};
+
+/* SMC_GEN_DEV_SMCD and SMC_GEN_DEV_SMCR attributes */
+enum {
+	SMC_NLA_DEV_UNSPEC,
+	SMC_NLA_DEV_USE_CNT,		/* u32 */
+	SMC_NLA_DEV_IS_CRIT,		/* u8 */
+	SMC_NLA_DEV_PCI_FID,		/* u32 */
+	SMC_NLA_DEV_PCI_CHID,		/* u16 */
+	SMC_NLA_DEV_PCI_VENDOR,		/* u16 */
+	SMC_NLA_DEV_PCI_DEVICE,		/* u16 */
+	SMC_NLA_DEV_PCI_ID,		/* string */
+	SMC_NLA_DEV_PORT,		/* nest */
+	SMC_NLA_DEV_PORT2,		/* nest */
+	SMC_NLA_DEV_IB_NAME,		/* string */
+	__SMC_NLA_DEV_MAX,
+	SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1
+};
+
 #endif /* _UAPI_LINUX_SMC_H */

net/smc/Makefile

@@ -2,4 +2,4 @@
 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
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o

net/smc/af_smc.c

@@ -45,6 +45,7 @@
 #include "smc_ib.h"
 #include "smc_ism.h"
 #include "smc_pnet.h"
+#include "smc_netlink.h"
 #include "smc_tx.h"
 #include "smc_rx.h"
 #include "smc_close.h"
@@ -552,8 +553,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
 	return smc_connect_fallback(smc, reason_code);
 }
 
-/* abort connecting */
-static void smc_connect_abort(struct smc_sock *smc, int local_first)
+static void smc_conn_abort(struct smc_sock *smc, int local_first)
 {
 	if (local_first)
 		smc_lgr_cleanup_early(&smc->conn);
@@ -669,7 +669,7 @@ static int smc_find_proposal_devices(struct smc_sock *smc,
 				ini->smc_type_v1 = SMC_TYPE_N;
 		} /* else RDMA is supported for this connection */
 	}
-	if (smc_ism_v2_capable && smc_find_ism_v2_device_clnt(smc, ini))
+	if (smc_ism_is_v2_capable() && smc_find_ism_v2_device_clnt(smc, ini))
 		ini->smc_type_v2 = SMC_TYPE_N;
 
 	/* if neither ISM nor RDMA are supported, fallback */
@@ -814,7 +814,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	return 0;
 connect_abort:
-	smc_connect_abort(smc, ini->first_contact_local);
+	smc_conn_abort(smc, ini->first_contact_local);
 	mutex_unlock(&smc_client_lgr_pending);
 	smc->connect_nonblock = 0;
 
@@ -893,7 +893,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 
 	return 0;
 connect_abort:
-	smc_connect_abort(smc, ini->first_contact_local);
+	smc_conn_abort(smc, ini->first_contact_local);
 	mutex_unlock(&smc_server_lgr_pending);
 	smc->connect_nonblock = 0;
 
@@ -921,7 +921,7 @@ static int smc_connect_check_aclc(struct smc_init_info *ini,
 /* perform steps before actually connecting */
 static int __smc_connect(struct smc_sock *smc)
 {
-	u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
+	u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
 	struct smc_clc_msg_accept_confirm_v2 *aclc2;
 	struct smc_clc_msg_accept_confirm *aclc;
 	struct smc_init_info *ini = NULL;
@@ -946,9 +946,9 @@ static int __smc_connect(struct smc_sock *smc)
 						    version);
 
 	ini->smcd_version = SMC_V1;
-	ini->smcd_version |= smc_ism_v2_capable ? SMC_V2 : 0;
+	ini->smcd_version |= smc_ism_is_v2_capable() ? SMC_V2 : 0;
 	ini->smc_type_v1 = SMC_TYPE_B;
-	ini->smc_type_v2 = smc_ism_v2_capable ? SMC_TYPE_D : SMC_TYPE_N;
+	ini->smc_type_v2 = smc_ism_is_v2_capable() ? SMC_TYPE_D : SMC_TYPE_N;
 
 	/* get vlan id from IP device */
 	if (smc_vlan_by_tcpsk(smc->clcsock, ini)) {
@@ -1321,10 +1321,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 			       int local_first, u8 version)
 {
 	/* RDMA setup failed, switch back to TCP */
-	if (local_first)
-		smc_lgr_cleanup_early(&new_smc->conn);
-	else
-		smc_conn_free(&new_smc->conn);
+	smc_conn_abort(new_smc, local_first);
 	if (reason_code < 0) { /* error, no fallback possible */
 		smc_listen_out_err(new_smc);
 		return;
@@ -1359,7 +1356,7 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
 		rc = SMC_CLC_DECL_PEERNOSMC;
 		goto out;
 	}
-	if (!smc_ism_v2_capable) {
+	if (!smc_ism_is_v2_capable()) {
 		ini->smcd_version &= ~SMC_V2;
 		rc = SMC_CLC_DECL_NOISM2SUPP;
 		goto out;
@@ -1430,10 +1427,7 @@ static int smc_listen_ism_init(struct smc_sock *new_smc,
 	/* Create send and receive buffers */
 	rc = smc_buf_create(new_smc, true);
 	if (rc) {
-		if (ini->first_contact_local)
-			smc_lgr_cleanup_early(&new_smc->conn);
-		else
-			smc_conn_free(&new_smc->conn);
+		smc_conn_abort(new_smc, ini->first_contact_local);
 		return (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB :
 					 SMC_CLC_DECL_MEM;
 	}
@@ -1688,7 +1682,7 @@ static void smc_listen_work(struct work_struct *work)
 {
 	struct smc_sock *new_smc = container_of(work, struct smc_sock,
 						smc_listen_work);
-	u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
+	u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
 	struct socket *newclcsock = new_smc->clcsock;
 	struct smc_clc_msg_accept_confirm *cclc;
 	struct smc_clc_msg_proposal_area *buf;
@@ -2502,10 +2496,14 @@ static int __init smc_init(void)
 	smc_ism_init();
 	smc_clc_init();
 
-	rc = smc_pnet_init();
+	rc = smc_nl_init();
 	if (rc)
 		goto out_pernet_subsys;
 
+	rc = smc_pnet_init();
+	if (rc)
+		goto out_nl;
+
 	rc = -ENOMEM;
 	smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0);
 	if (!smc_hs_wq)
@@ -2576,6 +2574,8 @@ static int __init smc_init(void)
 	destroy_workqueue(smc_hs_wq);
 out_pnet:
 	smc_pnet_exit();
+out_nl:
+	smc_nl_exit();
 out_pernet_subsys:
 	unregister_pernet_subsys(&smc_net_ops);
 
@@ -2593,6 +2593,7 @@ static void __exit smc_exit(void)
 	proto_unregister(&smc_proto6);
 	proto_unregister(&smc_proto);
 	smc_pnet_exit();
+	smc_nl_exit();
 	unregister_pernet_subsys(&smc_net_ops);
 	rcu_barrier();
 }

net/smc/smc_clc.c

@@ -772,6 +772,11 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 	return len > 0 ? 0 : len;
 }
 
+void smc_clc_get_hostname(u8 **host)
+{
+	*host = &smc_hostname[0];
+}
+
 void __init smc_clc_init(void)
 {
 	struct new_utsname *u;

net/smc/smc_clc.h

@@ -334,5 +334,6 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
 			u8 version);
 void smc_clc_init(void) __init;
+void smc_clc_get_hostname(u8 **host);
 
 #endif

net/smc/smc_core.h

@@ -13,7 +13,10 @@
 #define _SMC_CORE_H
 
 #include <linux/atomic.h>
+#include <linux/smc.h>
+#include <linux/pci.h>
 #include <rdma/ib_verbs.h>
+#include <net/genetlink.h>
 
 #include "smc.h"
 #include "smc_ib.h"
@@ -124,11 +127,14 @@ struct smc_link {
 	u8			link_is_asym;	/* is link asymmetric? */
 	struct smc_link_group	*lgr;		/* parent link group */
 	struct work_struct	link_down_wrk;	/* wrk to bring link down */
+	char			ibname[IB_DEVICE_NAME_MAX]; /* ib device name */
+	int			ndev_ifidx; /* network device ifindex */
 
 	enum smc_link_state	state;		/* state of link */
 	struct delayed_work	llc_testlink_wrk; /* testlink worker */
 	struct completion	llc_testlink_resp; /* wait for rx of testlink */
 	int			llc_testlink_time; /* testlink interval */
+	atomic_t		conn_cnt; /* connections on this link */
 };
 
 /* For now we just allow one parallel link per link group. The SMC protocol
@@ -363,6 +369,45 @@ static inline bool smc_link_active(struct smc_link *lnk)
 	return lnk->state == SMC_LNK_ACTIVE;
 }
 
+static inline 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]));
+}
+
+struct smc_pci_dev {
+	__u32		pci_fid;
+	__u16		pci_pchid;
+	__u16		pci_vendor;
+	__u16		pci_device;
+	__u8		pci_id[SMC_PCI_ID_STR_LEN];
+};
+
+static inline void smc_set_pci_values(struct pci_dev *pci_dev,
+				      struct smc_pci_dev *smc_dev)
+{
+	smc_dev->pci_vendor = pci_dev->vendor;
+	smc_dev->pci_device = pci_dev->device;
+	snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s",
+		 pci_name(pci_dev));
+#if IS_ENABLED(CONFIG_S390)
+	{ /* Set s390 specific PCI information */
+	struct zpci_dev *zdev;
+
+	zdev = to_zpci(pci_dev);
+	smc_dev->pci_fid = zdev->fid;
+	smc_dev->pci_pchid = zdev->pchid;
+	}
+#endif
+}
+
 struct smc_sock;
 struct smc_clc_msg_accept_confirm;
 struct smc_clc_msg_local;
@@ -410,6 +455,10 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
 				  struct smc_link *from_lnk, bool is_dev_err);
 void smcr_link_down_cond(struct smc_link *lnk);
 void smcr_link_down_cond_sched(struct smc_link *lnk);
+int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb);
+int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
 
 static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
 {

net/smc/smc_diag.c

@@ -31,19 +31,6 @@ static struct smc_diag_dump_ctx *smc_dump_context(struct netlink_callback *cb)
 	return (struct smc_diag_dump_ctx *)cb->ctx;
 }
 
-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);
@@ -160,17 +147,17 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    !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,
+			.lnk[0].ibport = smc->conn.lnk->ibport,
+			.lnk[0].link_id = smc->conn.lnk->link_id,
 		};
 
 		memcpy(linfo.lnk[0].ibname,
 		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
-		       sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
+		       sizeof(smc->conn.lnk->smcibdev->ibdev->name));
 		smc_gid_be16_convert(linfo.lnk[0].gid,
-				     smc->conn.lgr->lnk[0].gid);
+				     smc->conn.lnk->gid);
 		smc_gid_be16_convert(linfo.lnk[0].peer_gid,
-				     smc->conn.lgr->lnk[0].peer_gid);
+				     smc->conn.lnk->peer_gid);
 
 		if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
 			goto errout;

net/smc/smc_ib.c

@@ -25,6 +25,7 @@
 #include "smc_core.h"
 #include "smc_wr.h"
 #include "smc.h"
+#include "smc_netlink.h"
 
 #define SMC_MAX_CQE 32766	/* max. # of completion queue elements */
 
@@ -326,6 +327,161 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
 	return rc;
 }
 
+static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr,
+				      struct smc_ib_device *smcibdev)
+{
+	struct smc_link_group *lgr;
+	bool rc = false;
+	int i;
+
+	spin_lock_bh(&smc_lgr->lock);
+	list_for_each_entry(lgr, &smc_lgr->list, list) {
+		if (lgr->is_smcd)
+			continue;
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].state == SMC_LNK_UNUSED ||
+			    lgr->lnk[i].smcibdev != smcibdev)
+				continue;
+			if (lgr->type == SMC_LGR_SINGLE ||
+			    lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) {
+				rc = true;
+				goto out;
+			}
+		}
+	}
+out:
+	spin_unlock_bh(&smc_lgr->lock);
+	return rc;
+}
+
+static int smc_nl_handle_dev_port(struct sk_buff *skb,
+				  struct ib_device *ibdev,
+				  struct smc_ib_device *smcibdev,
+				  int port)
+{
+	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+	struct nlattr *port_attrs;
+	unsigned char port_state;
+	int lnk_count = 0;
+
+	port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port);
+	if (!port_attrs)
+		goto errout;
+
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
+		       smcibdev->pnetid_by_user[port]))
+		goto errattr;
+	snprintf(smc_pnet, sizeof(smc_pnet), "%s",
+		 (char *)&smcibdev->pnetid[port]);
+	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
+			smcibdev->ndev_ifidx[port]))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1))
+		goto errattr;
+	port_state = smc_ib_port_active(smcibdev, port + 1);
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state))
+		goto errattr;
+	lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]);
+	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count))
+		goto errattr;
+	nla_nest_end(skb, port_attrs);
+	return 0;
+errattr:
+	nla_nest_cancel(skb, port_attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev,
+				  struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+	struct smc_pci_dev smc_pci_dev;
+	struct pci_dev *pci_dev;
+	unsigned char is_crit;
+	struct nlattr *attrs;
+	void *nlh;
+	int i;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_DEV_SMCR);
+	if (!nlh)
+		goto errmsg;
+	attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR);
+	if (!attrs)
+		goto errout;
+	is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev);
+	if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit))
+		goto errattr;
+	memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+	pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent);
+	smc_set_pci_values(pci_dev, &smc_pci_dev);
+	if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device))
+		goto errattr;
+	if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id))
+		goto errattr;
+	snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name);
+	if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname))
+		goto errattr;
+	for (i = 1; i <= SMC_MAX_PORTS; i++) {
+		if (!rdma_is_port_valid(smcibdev->ibdev, i))
+			continue;
+		if (smc_nl_handle_dev_port(skb, smcibdev->ibdev,
+					   smcibdev, i - 1))
+			goto errattr;
+	}
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list,
+				 struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct smc_ib_device *smcibdev;
+	int snum = cb_ctx->pos[0];
+	int num = 0;
+
+	mutex_lock(&dev_list->mutex);
+	list_for_each_entry(smcibdev, &dev_list->list, list) {
+		if (num < snum)
+			goto next;
+		if (smc_nl_handle_smcr_dev(smcibdev, skb, cb))
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	mutex_unlock(&dev_list->mutex);
+	cb_ctx->pos[0] = num;
+}
+
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb);
+	return skb->len;
+}
+
 static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
 {
 	struct smc_link *lnk = (struct smc_link *)priv;
@@ -557,6 +713,49 @@ static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev)
 
 static struct ib_client smc_ib_client;
 
+static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port)
+{
+	struct ib_device *ibdev = smcibdev->ibdev;
+	struct net_device *ndev;
+
+	if (!ibdev->ops.get_netdev)
+		return;
+	ndev = ibdev->ops.get_netdev(ibdev, port + 1);
+	if (ndev) {
+		smcibdev->ndev_ifidx[port] = ndev->ifindex;
+		dev_put(ndev);
+	}
+}
+
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event)
+{
+	struct smc_ib_device *smcibdev;
+	struct ib_device *libdev;
+	struct net_device *lndev;
+	u8 port_cnt;
+	int i;
+
+	mutex_lock(&smc_ib_devices.mutex);
+	list_for_each_entry(smcibdev, &smc_ib_devices.list, list) {
+		port_cnt = smcibdev->ibdev->phys_port_cnt;
+		for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) {
+			libdev = smcibdev->ibdev;
+			if (!libdev->ops.get_netdev)
+				continue;
+			lndev = libdev->ops.get_netdev(libdev, i + 1);
+			if (lndev)
+				dev_put(lndev);
+			if (lndev != ndev)
+				continue;
+			if (event == NETDEV_REGISTER)
+				smcibdev->ndev_ifidx[i] = ndev->ifindex;
+			if (event == NETDEV_UNREGISTER)
+				smcibdev->ndev_ifidx[i] = 0;
+		}
+	}
+	mutex_unlock(&smc_ib_devices.mutex);
+}
+
 /* callback function for ib_register_client() */
 static int smc_ib_add_dev(struct ib_device *ibdev)
 {
@@ -596,6 +795,7 @@ static int smc_ib_add_dev(struct ib_device *ibdev)
 		if (smc_pnetid_by_dev_port(ibdev->dev.parent, i,
 					   smcibdev->pnetid[i]))
 			smc_pnetid_by_table_ib(smcibdev, i + 1);
+		smc_copy_netdev_ifindex(smcibdev, i);
 		pr_warn_ratelimited("smc:    ib device %s port %d has pnetid "
 				    "%.16s%s\n",
 				    smcibdev->ibdev->name, i + 1,

net/smc/smc_ib.h

@@ -30,6 +30,7 @@ struct smc_ib_devices {			/* list of smc ib devices definition */
 };
 
 extern struct smc_ib_devices	smc_ib_devices; /* list of smc ib devices */
+extern struct smc_lgr_list smc_lgr_list; /* list of linkgroups */
 
 struct smc_ib_device {				/* ib-device infos for smc */
 	struct list_head	list;
@@ -53,11 +54,15 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	atomic_t		lnk_cnt;	/* number of links on ibdev */
 	wait_queue_head_t	lnks_deleted;	/* wait 4 removal of all links*/
 	struct mutex		mutex;		/* protect dev setup+cleanup */
+	atomic_t		lnk_cnt_by_port[SMC_MAX_PORTS];
+						/* number of links per port */
+	int			ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */
 };
 
 struct smc_buf_desc;
 struct smc_link;
 
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event);
 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);
@@ -87,4 +92,5 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
 int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 			 unsigned short vlan_id, u8 gid[], u8 *sgid_index);
 bool smc_ib_is_valid_local_systemid(void);
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
 #endif

net/smc/smc_ism.c

@@ -15,13 +15,14 @@
 #include "smc_core.h"
 #include "smc_ism.h"
 #include "smc_pnet.h"
+#include "smc_netlink.h"
 
 struct smcd_dev_list smcd_dev_list = {
 	.list = LIST_HEAD_INIT(smcd_dev_list.list),
 	.mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex)
 };
 
-bool smc_ism_v2_capable;
+static bool smc_ism_v2_capable;
 
 /* Test if an ISM communication is possible - same CPC */
 int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
@@ -51,6 +52,12 @@ u16 smc_ism_get_chid(struct smcd_dev *smcd)
 	return smcd->ops->get_chid(smcd);
 }
 
+/* HW supports ISM V2 and thus System EID is defined */
+bool smc_ism_is_v2_capable(void)
+{
+	return smc_ism_v2_capable;
+}
+
 /* Set a connection using this DMBE. */
 void smc_ism_set_conn(struct smc_connection *conn)
 {
@@ -201,6 +208,96 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
 	return rc;
 }
 
+static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
+				  struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+	struct smc_pci_dev smc_pci_dev;
+	struct nlattr *port_attrs;
+	struct nlattr *attrs;
+	int use_cnt = 0;
+	void *nlh;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_DEV_SMCD);
+	if (!nlh)
+		goto errmsg;
+	attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCD);
+	if (!attrs)
+		goto errout;
+	use_cnt = atomic_read(&smcd->lgr_cnt);
+	if (nla_put_u32(skb, SMC_NLA_DEV_USE_CNT, use_cnt))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, use_cnt > 0))
+		goto errattr;
+	memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+	smc_set_pci_values(to_pci_dev(smcd->dev.parent), &smc_pci_dev);
+	if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device))
+		goto errattr;
+	if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id))
+		goto errattr;
+
+	port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT);
+	if (!port_attrs)
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
+		goto errportattr;
+	snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid);
+	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+		goto errportattr;
+
+	nla_nest_end(skb, port_attrs);
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+
+errportattr:
+	nla_nest_cancel(skb, port_attrs);
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	nlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list,
+				 struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	int snum = cb_ctx->pos[0];
+	struct smcd_dev *smcd;
+	int num = 0;
+
+	mutex_lock(&dev_list->mutex);
+	list_for_each_entry(smcd, &dev_list->list, list) {
+		if (num < snum)
+			goto next;
+		if (smc_nl_handle_smcd_dev(smcd, skb, cb))
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	mutex_unlock(&dev_list->mutex);
+	cb_ctx->pos[0] = num;
+}
+
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	smc_nl_prep_smcd_dev(&smcd_dev_list, skb, cb);
+	return skb->len;
+}
+
 struct smc_ism_event_work {
 	struct work_struct work;
 	struct smcd_dev *smcd;

net/smc/smc_ism.h

@@ -10,6 +10,7 @@
 #define SMCD_ISM_H
 
 #include <linux/uio.h>
+#include <linux/types.h>
 #include <linux/mutex.h>
 
 #include "smc.h"
@@ -20,9 +21,6 @@ struct smcd_dev_list {	/* List of SMCD devices */
 };
 
 extern struct smcd_dev_list	smcd_dev_list;	/* list of smcd devices */
-extern bool	smc_ism_v2_capable;	/* HW supports ISM V2 and thus
-					 * System EID is defined
-					 */
 
 struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	struct list_head list;
@@ -52,5 +50,7 @@ int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
 int smc_ism_signal_shutdown(struct smc_link_group *lgr);
 void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
 u16 smc_ism_get_chid(struct smcd_dev *dev);
+bool smc_ism_is_v2_capable(void);
 void smc_ism_init(void);
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
 #endif

net/smc/smc_netlink.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Generic netlink support functions to interact with SMC module
+ *
+ *  Copyright IBM Corp. 2020
+ *
+ *  Author(s):	Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/if.h>
+#include <linux/smc.h>
+
+#include "smc_core.h"
+#include "smc_ism.h"
+#include "smc_ib.h"
+#include "smc_netlink.h"
+
+#define SMC_CMD_MAX_ATTR 1
+
+/* SMC_GENL generic netlink operation definition */
+static const struct genl_ops smc_gen_nl_ops[] = {
+	{
+		.cmd = SMC_NETLINK_GET_SYS_INFO,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smc_nl_get_sys_info,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LGR_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_lgr,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LINK_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_link,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LGR_SMCD,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcd_nl_get_lgr,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_DEV_SMCD,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcd_nl_get_device,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_DEV_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_device,
+	},
+};
+
+static const struct nla_policy smc_gen_nl_policy[2] = {
+	[SMC_CMD_MAX_ATTR]	= { .type = NLA_REJECT, },
+};
+
+/* SMC_GENL family definition */
+struct genl_family smc_gen_nl_family __ro_after_init = {
+	.hdrsize =	0,
+	.name =		SMC_GENL_FAMILY_NAME,
+	.version =	SMC_GENL_FAMILY_VERSION,
+	.maxattr =	SMC_CMD_MAX_ATTR,
+	.policy =	smc_gen_nl_policy,
+	.netnsok =	true,
+	.module =	THIS_MODULE,
+	.ops =		smc_gen_nl_ops,
+	.n_ops =	ARRAY_SIZE(smc_gen_nl_ops)
+};
+
+int __init smc_nl_init(void)
+{
+	return genl_register_family(&smc_gen_nl_family);
+}
+
+void smc_nl_exit(void)
+{
+	genl_unregister_family(&smc_gen_nl_family);
+}

net/smc/smc_netlink.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  SMC Generic netlink operations
+ *
+ *  Copyright IBM Corp. 2020
+ *
+ *  Author(s):	Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#ifndef _SMC_NETLINK_H
+#define _SMC_NETLINK_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+extern struct genl_family smc_gen_nl_family;
+
+struct smc_nl_dmp_ctx {
+	int pos[2];
+};
+
+static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c)
+{
+	return (struct smc_nl_dmp_ctx *)c->ctx;
+}
+
+int smc_nl_init(void) __init;
+void smc_nl_exit(void);
+
+#endif

net/smc/smc_pnet.c

@@ -827,9 +827,11 @@ static int smc_pnet_netdev_event(struct notifier_block *this,
 	case NETDEV_REBOOT:
 	case NETDEV_UNREGISTER:
 		smc_pnet_remove_by_ndev(event_dev);
+		smc_ib_ndev_change(event_dev, event);
 		return NOTIFY_OK;
 	case NETDEV_REGISTER:
 		smc_pnet_add_by_ndev(event_dev);
+		smc_ib_ndev_change(event_dev, event);
 		return NOTIFY_OK;
 	case NETDEV_UP:
 		smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid);