Commit fa086662 authored by Karsten Graul's avatar Karsten Graul Committed by David S. Miller
Browse files

net/smc: add support for user defined EIDs 



SMC-Dv2 allows users to define EIDs which allows to create separate
name spaces enabling users to cluster their SMC-Dv2 connections.
Add support for user defined EIDs and extent the generic netlink
interface so users can add, remove and dump EIDs.

Signed-off-by: default avatarKarsten Graul <kgraul@linux.ibm.com>
Reviewed-by: default avatarGuvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: default avatarGuvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent f787e3cf

include/uapi/linux/smc.h

+15 −0
Original line number Diff line number Diff line
@@ -38,6 +38,9 @@ enum { /* SMC PNET Table commands */ 
#define SMC_GENL_FAMILY_VERSION		1



#define SMC_PCI_ID_STR_LEN		16 /* Max length of pci id string */

#define SMC_MAX_HOSTNAME_LEN		32 /* Max length of the hostname */

#define SMC_MAX_UEID			4  /* Max number of user EIDs */

#define SMC_MAX_EID_LEN			32 /* Max length of an EID */



/* SMC_GENL_FAMILY commands */

enum {
@@ -49,6 +52,10 @@ enum { 
	SMC_NETLINK_GET_DEV_SMCR,

	SMC_NETLINK_GET_STATS,

	SMC_NETLINK_GET_FBACK_STATS,

	SMC_NETLINK_DUMP_UEID,

	SMC_NETLINK_ADD_UEID,

	SMC_NETLINK_REMOVE_UEID,

	SMC_NETLINK_FLUSH_UEID,

};



/* SMC_GENL_FAMILY top level attributes */
@@ -242,4 +249,12 @@ enum { 
	__SMC_NLA_FBACK_STATS_MAX,

	SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1

};



/* SMC_NETLINK_UEID attributes */

enum {

	SMC_NLA_EID_TABLE_UNSPEC,

	SMC_NLA_EID_TABLE_ENTRY,	/* string */

	__SMC_NLA_EID_TABLE_MAX,

	SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1

};

#endif /* _UAPI_LINUX_SMC_H */

net/smc/af_smc.c

+22 −12
Original line number Diff line number Diff line
@@ -829,7 +829,7 @@ static int smc_connect_rdma(struct smc_sock *smc, 
	smc_rmb_sync_sg_for_device(&smc->conn);



	reason_code = smc_clc_send_confirm(smc, ini->first_contact_local,

					   SMC_V1);

					   SMC_V1, NULL);

	if (reason_code)

		goto connect_abort;
@@ -883,6 +883,7 @@ static int smc_connect_ism(struct smc_sock *smc, 
			   struct smc_clc_msg_accept_confirm *aclc,

			   struct smc_init_info *ini)

{

	u8 *eid = NULL;

	int rc = 0;



	ini->is_smcd = true;
@@ -918,8 +919,15 @@ static int smc_connect_ism(struct smc_sock *smc, 
	smc_rx_init(smc);

	smc_tx_init(smc);



	if (aclc->hdr.version > SMC_V1) {

		struct smc_clc_msg_accept_confirm_v2 *clc_v2 =

			(struct smc_clc_msg_accept_confirm_v2 *)aclc;



		eid = clc_v2->eid;

	}



	rc = smc_clc_send_confirm(smc, ini->first_contact_local,

				  aclc->hdr.version);

				  aclc->hdr.version, eid);

	if (rc)

		goto connect_abort;

	mutex_unlock(&smc_server_lgr_pending);
@@ -1533,9 +1541,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, 
	pclc_smcd = smc_get_clc_msg_smcd(pclc);

	smc_v2_ext = smc_get_clc_v2_ext(pclc);

	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);

	if (!smcd_v2_ext ||

	    !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */

		smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini);

	if (!smcd_v2_ext) {

		smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini);

		goto not_found;

	}
@@ -1555,13 +1562,13 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, 
	}

	mutex_unlock(&smcd_dev_list.mutex);



	if (ini->ism_dev[0]) {

		smc_ism_get_system_eid(ini->ism_dev[0], &eid);

		if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN))

	if (!ini->ism_dev[0])

		goto not_found;

	} else {



	smc_ism_get_system_eid(ini->ism_dev[0], &eid);

	if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext,

			       smcd_v2_ext->system_eid, eid))

		goto not_found;

	}



	/* separate - outside the smcd_dev_list.lock */

	smcd_version = ini->smcd_version;
@@ -1579,6 +1586,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, 
	}

	/* no V2 ISM device could be initialized */

	ini->smcd_version = smcd_version;	/* restore original value */

	ini->negotiated_eid[0] = 0;



not_found:

	ini->smcd_version &= ~SMC_V2;
@@ -1788,7 +1796,8 @@ static void smc_listen_work(struct work_struct *work) 


	/* send SMC Accept CLC message */

	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,

				 ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1);

				 ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1,

				 ini->negotiated_eid);

	if (rc)

		goto out_unlock;
@@ -2662,6 +2671,7 @@ static void __exit smc_exit(void) 
	proto_unregister(&smc_proto);

	smc_pnet_exit();

	smc_nl_exit();

	smc_clc_exit();

	unregister_pernet_subsys(&smc_net_stat_ops);

	unregister_pernet_subsys(&smc_net_ops);

	rcu_barrier();

net/smc/smc.h

+0 −3
Original line number Diff line number Diff line
@@ -29,9 +29,6 @@ 
					 * devices

					 */



#define SMC_MAX_HOSTNAME_LEN	32

#define SMC_MAX_EID_LEN		32



extern struct proto smc_proto;

extern struct proto smc_proto6;

net/smc/smc_clc.c

+250 −13
Original line number Diff line number Diff line
@@ -26,6 +26,7 @@ 
#include "smc_clc.h"

#include "smc_ib.h"

#include "smc_ism.h"

#include "smc_netlink.h"



#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68

#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
@@ -39,6 +40,223 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; 


static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN];



struct smc_clc_eid_table {

	rwlock_t lock;

	struct list_head list;

	u8 ueid_cnt;

	u8 seid_enabled;

};



static struct smc_clc_eid_table smc_clc_eid_table;



struct smc_clc_eid_entry {

	struct list_head list;

	u8 eid[SMC_MAX_EID_LEN];

};



/* The size of a user EID is 32 characters.

 * Valid characters should be (single-byte character set) A-Z, 0-9, '.' and '-'.

 * Blanks should only be used to pad to the expected size.

 * First character must be alphanumeric.

 */

static bool smc_clc_ueid_valid(char *ueid)

{

	char *end = ueid + SMC_MAX_EID_LEN;



	while (--end >= ueid && isspace(*end))

		;

	if (end < ueid)

		return false;

	if (!isalnum(*ueid) || islower(*ueid))

		return false;

	while (ueid <= end) {

		if ((!isalnum(*ueid) || islower(*ueid)) && *ueid != '.' &&

		    *ueid != '-')

			return false;

		ueid++;

	}

	return true;

}



static int smc_clc_ueid_add(char *ueid)

{

	struct smc_clc_eid_entry *new_ueid, *tmp_ueid;

	int rc;



	if (!smc_clc_ueid_valid(ueid))

		return -EINVAL;



	/* add a new ueid entry to the ueid table if there isn't one */

	new_ueid = kzalloc(sizeof(*new_ueid), GFP_KERNEL);

	if (!new_ueid)

		return -ENOMEM;

	memcpy(new_ueid->eid, ueid, SMC_MAX_EID_LEN);



	write_lock(&smc_clc_eid_table.lock);

	if (smc_clc_eid_table.ueid_cnt >= SMC_MAX_UEID) {

		rc = -ERANGE;

		goto err_out;

	}

	list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) {

		if (!memcmp(tmp_ueid->eid, ueid, SMC_MAX_EID_LEN)) {

			rc = -EEXIST;

			goto err_out;

		}

	}

	list_add_tail(&new_ueid->list, &smc_clc_eid_table.list);

	smc_clc_eid_table.ueid_cnt++;

	write_unlock(&smc_clc_eid_table.lock);

	return 0;



err_out:

	write_unlock(&smc_clc_eid_table.lock);

	kfree(new_ueid);

	return rc;

}



int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info)

{

	struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY];

	char *ueid;



	if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1)

		return -EINVAL;

	ueid = (char *)nla_data(nla_ueid);



	return smc_clc_ueid_add(ueid);

}



/* remove one or all ueid entries from the table */

static int smc_clc_ueid_remove(char *ueid)

{

	struct smc_clc_eid_entry *lst_ueid, *tmp_ueid;

	int rc = -ENOENT;



	/* remove table entry */

	write_lock(&smc_clc_eid_table.lock);

	list_for_each_entry_safe(lst_ueid, tmp_ueid, &smc_clc_eid_table.list,

				 list) {

		if (!ueid || !memcmp(lst_ueid->eid, ueid, SMC_MAX_EID_LEN)) {

			list_del(&lst_ueid->list);

			smc_clc_eid_table.ueid_cnt--;

			kfree(lst_ueid);

			rc = 0;

		}

	}

	write_unlock(&smc_clc_eid_table.lock);

	return rc;

}



int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info)

{

	struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY];

	char *ueid;



	if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1)

		return -EINVAL;

	ueid = (char *)nla_data(nla_ueid);



	return smc_clc_ueid_remove(ueid);

}



int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info)

{

	smc_clc_ueid_remove(NULL);

	return 0;

}



static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq,

				u32 flags, char *ueid)

{

	char ueid_str[SMC_MAX_EID_LEN + 1];

	void *hdr;



	hdr = genlmsg_put(skb, portid, seq, &smc_gen_nl_family,

			  flags, SMC_NETLINK_DUMP_UEID);

	if (!hdr)

		return -ENOMEM;

	snprintf(ueid_str, sizeof(ueid_str), "%s", ueid);

	if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) {

		genlmsg_cancel(skb, hdr);

		return -EMSGSIZE;

	}

	genlmsg_end(skb, hdr);

	return 0;

}



static int _smc_nl_ueid_dump(struct sk_buff *skb, u32 portid, u32 seq,

			     int start_idx)

{

	struct smc_clc_eid_entry *lst_ueid;

	int idx = 0;



	read_lock(&smc_clc_eid_table.lock);

	list_for_each_entry(lst_ueid, &smc_clc_eid_table.list, list) {

		if (idx++ < start_idx)

			continue;

		if (smc_nl_ueid_dumpinfo(skb, portid, seq, NLM_F_MULTI,

					 lst_ueid->eid)) {

			--idx;

			break;

		}

	}

	read_unlock(&smc_clc_eid_table.lock);

	return idx;

}



int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb)

{

	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);

	int idx;



	idx = _smc_nl_ueid_dump(skb, NETLINK_CB(cb->skb).portid,

				cb->nlh->nlmsg_seq, cb_ctx->pos[0]);



	cb_ctx->pos[0] = idx;

	return skb->len;

}



static bool _smc_clc_match_ueid(u8 *peer_ueid)

{

	struct smc_clc_eid_entry *tmp_ueid;



	list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) {

		if (!memcmp(tmp_ueid->eid, peer_ueid, SMC_MAX_EID_LEN))

			return true;

	}

	return false;

}



bool smc_clc_match_eid(u8 *negotiated_eid,

		       struct smc_clc_v2_extension *smc_v2_ext,

		       u8 *peer_eid, u8 *local_eid)

{

	bool match = false;

	int i;



	negotiated_eid[0] = 0;

	read_lock(&smc_clc_eid_table.lock);

	if (smc_clc_eid_table.seid_enabled &&

	    smc_v2_ext->hdr.flag.seid &&

	    !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) {

		memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN);

		match = true;

		goto out;

	}



	for (i = 0; i < smc_v2_ext->hdr.eid_cnt; i++) {

		if (_smc_clc_match_ueid(smc_v2_ext->user_eids[i])) {

			memcpy(negotiated_eid, smc_v2_ext->user_eids[i],

			       SMC_MAX_EID_LEN);

			match = true;

			goto out;

		}

	}

out:

	read_unlock(&smc_clc_eid_table.lock);

	return match;

}



/* check arriving CLC proposal */

static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)

{
@@ -550,6 +768,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) 
	if (ini->smc_type_v2 == SMC_TYPE_N) {

		pclc_smcd->v2_ext_offset = 0;

	} else {

		struct smc_clc_eid_entry *ueident;

		u16 v2_ext_offset;

		u8 *eid = NULL;
@@ -560,10 +779,19 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) 
						pclc_prfx->ipv6_prefixes_cnt *

						sizeof(ipv6_prfx[0]);

		pclc_smcd->v2_ext_offset = htons(v2_ext_offset);

		v2_ext->hdr.eid_cnt = 0;



		read_lock(&smc_clc_eid_table.lock);

		v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt;

		plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN;

		i = 0;

		list_for_each_entry(ueident, &smc_clc_eid_table.list, list) {

			memcpy(v2_ext->user_eids[i++], ueident->eid,

			       sizeof(ueident->eid));

		}

		v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled;

		read_unlock(&smc_clc_eid_table.lock);

		v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;

		v2_ext->hdr.flag.release = SMC_RELEASE;

		v2_ext->hdr.flag.seid = 1;

		v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -

				offsetofend(struct smc_clnt_opts_area_hdr,

					    smcd_v2_ext_offset) +
@@ -572,7 +800,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) 
			smc_ism_get_system_eid(ini->ism_dev[0], &eid);

		else

			smc_ism_get_system_eid(ini->ism_dev[1], &eid);

		if (eid)

		if (eid && v2_ext->hdr.flag.seid)

			memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN);

		plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext);

		if (ini->ism_offered_cnt) {
@@ -607,7 +835,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) 
	}

	if (ini->smc_type_v2 != SMC_TYPE_N) {

		vec[i].iov_base = v2_ext;

		vec[i++].iov_len = sizeof(*v2_ext);

		vec[i++].iov_len = sizeof(*v2_ext) +

				   (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN);

		vec[i].iov_base = smcd_v2_ext;

		vec[i++].iov_len = sizeof(*smcd_v2_ext);

		if (ini->ism_offered_cnt) {
@@ -635,7 +864,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) 
/* build and send CLC CONFIRM / ACCEPT message */

static int smc_clc_send_confirm_accept(struct smc_sock *smc,

				       struct smc_clc_msg_accept_confirm_v2 *clc_v2,

				       int first_contact, u8 version)

				       int first_contact, u8 version,

				       u8 *eid)

{

	struct smc_connection *conn = &smc->conn;

	struct smc_clc_msg_accept_confirm *clc;
@@ -663,11 +893,8 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, 
		if (version == SMC_V1) {

			clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);

		} else {

			u8 *eid = NULL;



			clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd));

			smc_ism_get_system_eid(conn->lgr->smcd, &eid);

			if (eid)

			if (eid[0])

				memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN);

			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;

			if (first_contact)
@@ -732,7 +959,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, 


/* send CLC CONFIRM message across internal TCP socket */

int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,

			 u8 version)

			 u8 version, u8 *eid)

{

	struct smc_clc_msg_accept_confirm_v2 cclc_v2;

	int reason_code = 0;
@@ -742,7 +969,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, 
	memset(&cclc_v2, 0, sizeof(cclc_v2));

	cclc_v2.hdr.type = SMC_CLC_CONFIRM;

	len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact,

					  version);

					  version, eid);

	if (len < ntohs(cclc_v2.hdr.length)) {

		if (len >= 0) {

			reason_code = -ENETUNREACH;
@@ -757,7 +984,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, 


/* send CLC ACCEPT message across internal TCP socket */

int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,

			u8 version)

			u8 version, u8 *negotiated_eid)

{

	struct smc_clc_msg_accept_confirm_v2 aclc_v2;

	int len;
@@ -765,7 +992,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, 
	memset(&aclc_v2, 0, sizeof(aclc_v2));

	aclc_v2.hdr.type = SMC_CLC_ACCEPT;

	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,

					  version);

					  version, negotiated_eid);

	if (len < ntohs(aclc_v2.hdr.length))

		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
@@ -785,4 +1012,14 @@ void __init smc_clc_init(void) 
	u = utsname();

	memcpy(smc_hostname, u->nodename,

	       min_t(size_t, strlen(u->nodename), sizeof(smc_hostname)));



	INIT_LIST_HEAD(&smc_clc_eid_table.list);

	rwlock_init(&smc_clc_eid_table.lock);

	smc_clc_eid_table.ueid_cnt = 0;

	smc_clc_eid_table.seid_enabled = 1;

}



void smc_clc_exit(void)

{

	smc_clc_ueid_remove(NULL);

}

net/smc/smc_clc.h

+14 −2
Original line number Diff line number Diff line
@@ -14,8 +14,10 @@ 
#define _SMC_CLC_H



#include <rdma/ib_verbs.h>

#include <linux/smc.h>



#include "smc.h"

#include "smc_netlink.h"



#define SMC_CLC_PROPOSAL	0x01

#define SMC_CLC_ACCEPT		0x02
@@ -158,6 +160,7 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ 
} __aligned(4);



#define SMC_CLC_MAX_V6_PREFIX		8

#define SMC_CLC_MAX_UEID		8



struct smc_clc_msg_proposal_area {

	struct smc_clc_msg_proposal		pclc_base;
@@ -165,6 +168,7 @@ struct smc_clc_msg_proposal_area { 
	struct smc_clc_msg_proposal_prefix	pclc_prfx;

	struct smc_clc_ipv6_prefix	pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX];

	struct smc_clc_v2_extension		pclc_v2_ext;

	u8			user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN];

	struct smc_clc_smcd_v2_extension	pclc_smcd_v2_ext;

	struct smc_clc_smcd_gid_chid		pclc_gidchids[SMC_MAX_ISM_DEVS];

	struct smc_clc_msg_trail		pclc_trl;
@@ -330,10 +334,18 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, 
int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version);

int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini);

int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,

			 u8 version);

			 u8 version, u8 *eid);

int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,

			u8 version);

			u8 version, u8 *negotiated_eid);

void smc_clc_init(void) __init;

void smc_clc_exit(void);

void smc_clc_get_hostname(u8 **host);

bool smc_clc_match_eid(u8 *negotiated_eid,

		       struct smc_clc_v2_extension *smc_v2_ext,

		       u8 *peer_eid, u8 *local_eid);

int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb);

int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info);

int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info);

int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info);



#endif