diff options
Diffstat (limited to 'net/smc')
-rw-r--r-- | net/smc/Makefile | 2 | ||||
-rw-r--r-- | net/smc/af_smc.c | 100 | ||||
-rw-r--r-- | net/smc/smc_cdc.c | 6 | ||||
-rw-r--r-- | net/smc/smc_clc.c | 5 | ||||
-rw-r--r-- | net/smc/smc_clc.h | 6 | ||||
-rw-r--r-- | net/smc/smc_core.c | 399 | ||||
-rw-r--r-- | net/smc/smc_core.h | 50 | ||||
-rw-r--r-- | net/smc/smc_diag.c | 23 | ||||
-rw-r--r-- | net/smc/smc_ib.c | 200 | ||||
-rw-r--r-- | net/smc/smc_ib.h | 6 | ||||
-rw-r--r-- | net/smc/smc_ism.c | 99 | ||||
-rw-r--r-- | net/smc/smc_ism.h | 6 | ||||
-rw-r--r-- | net/smc/smc_netlink.c | 85 | ||||
-rw-r--r-- | net/smc/smc_netlink.h | 32 | ||||
-rw-r--r-- | net/smc/smc_pnet.c | 2 | ||||
-rw-r--r-- | net/smc/smc_wr.c | 14 |
16 files changed, 959 insertions, 76 deletions
diff --git a/net/smc/Makefile b/net/smc/Makefile index cb1254541f37..77e54fe42b1c 100644 --- a/net/smc/Makefile +++ b/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 diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5dd4faaf7d6e..47340b3b514f 100644 --- a/net/smc/af_smc.c +++ b/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; @@ -1347,6 +1344,7 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, { struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext; struct smc_clc_v2_extension *pclc_v2_ext; + int rc = SMC_CLC_DECL_PEERNOSMC; ini->smc_type_v1 = pclc->hdr.typev1; ini->smc_type_v2 = pclc->hdr.typev2; @@ -1354,29 +1352,30 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, if (pclc->hdr.version > SMC_V1) ini->smcd_version |= ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0; - if (!smc_ism_v2_capable) { + if (!(ini->smcd_version & SMC_V2)) { + rc = SMC_CLC_DECL_PEERNOSMC; + goto out; + } + if (!smc_ism_is_v2_capable()) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOISM2SUPP; goto out; } pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2EXT; goto out; } pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); - if (!pclc_smcd_v2_ext) + if (!pclc_smcd_v2_ext) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2DEXT; + } out: - if (!ini->smcd_version) { - if (pclc->hdr.typev1 == SMC_TYPE_B || - pclc->hdr.typev2 == SMC_TYPE_B) - return SMC_CLC_DECL_NOSMCDEV; - if (pclc->hdr.typev1 == SMC_TYPE_D || - pclc->hdr.typev2 == SMC_TYPE_D) - return SMC_CLC_DECL_NOSMCDDEV; - return SMC_CLC_DECL_NOSMCRDEV; - } + if (!ini->smcd_version) + return rc; return 0; } @@ -1428,10 +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; } @@ -1474,6 +1470,12 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini, } } +static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini) +{ + if (!ini->rc) + ini->rc = rc; +} + static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) @@ -1484,7 +1486,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, unsigned int matches = 0; u8 smcd_version; u8 *eid = NULL; - int i; + int i, rc; if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2)) goto not_found; @@ -1493,8 +1495,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, 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_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */ + smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini); goto not_found; + } mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) @@ -1526,9 +1530,12 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, ini->smcd_version = SMC_V2; ini->is_smcd = true; ini->ism_selected = i; - if (smc_listen_ism_init(new_smc, ini)) + rc = smc_listen_ism_init(new_smc, ini); + if (rc) { + smc_find_ism_store_rc(rc, ini); /* try next active ISM device */ continue; + } return; /* matching and usable V2 ISM device found */ } /* no V2 ISM device could be initialized */ @@ -1545,19 +1552,23 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, struct smc_init_info *ini) { struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc); + int rc = 0; /* check if ISM V1 is available */ if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid); - if (smc_find_ism_device(new_smc, ini)) + rc = smc_find_ism_device(new_smc, ini); + if (rc) goto not_found; ini->ism_selected = 0; - if (!smc_listen_ism_init(new_smc, ini)) + rc = smc_listen_ism_init(new_smc, ini); + if (!rc) return; /* V1 ISM device found */ not_found: + smc_find_ism_store_rc(rc, ini); ini->ism_dev[0] = NULL; ini->is_smcd = false; } @@ -1614,16 +1625,16 @@ static int smc_listen_find_device(struct smc_sock *new_smc, return 0; if (!(ini->smcd_version & SMC_V1)) - return SMC_CLC_DECL_NOSMCDEV; + return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV; /* check for matching IP prefix and subnet length */ rc = smc_listen_prfx_check(new_smc, pclc); if (rc) - return rc; + return ini->rc ?: rc; /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) - return SMC_CLC_DECL_GETVLANERR; + return ini->rc ?: SMC_CLC_DECL_GETVLANERR; /* check for ISM device matching V1 proposed device */ smc_find_ism_v1_device_serv(new_smc, pclc, ini); @@ -1631,10 +1642,14 @@ static int smc_listen_find_device(struct smc_sock *new_smc, return 0; if (pclc->hdr.typev1 == SMC_TYPE_D) - return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */ + /* skip RDMA and decline */ + return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV; /* check if RDMA is available */ - return smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + smc_find_ism_store_rc(rc, ini); + + return (!rc) ? 0 : ini->rc; } /* listen worker: finish RDMA setup */ @@ -1667,7 +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; @@ -2481,10 +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) @@ -2555,6 +2574,8 @@ out_alloc_hs_wq: destroy_workqueue(smc_hs_wq); out_pnet: smc_pnet_exit(); +out_nl: + smc_nl_exit(); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); @@ -2572,6 +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(); } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index b1ce6ccbfaec..f23f558054a7 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -389,9 +389,9 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc) * Context: * - tasklet context */ -static void smcd_cdc_rx_tsklet(unsigned long data) +static void smcd_cdc_rx_tsklet(struct tasklet_struct *t) { - struct smc_connection *conn = (struct smc_connection *)data; + struct smc_connection *conn = from_tasklet(conn, t, rx_tsklet); struct smcd_cdc_msg *data_cdc; struct smcd_cdc_msg cdc; struct smc_sock *smc; @@ -411,7 +411,7 @@ static void smcd_cdc_rx_tsklet(unsigned long data) */ void smcd_cdc_rx_init(struct smc_connection *conn) { - tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn); + tasklet_setup(&conn->rx_tsklet, smcd_cdc_rx_tsklet); } /***************************** init, exit, misc ******************************/ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 696d89c2dce4..e286dafd6e88 100644 --- a/net/smc/smc_clc.c +++ b/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; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index c579d1d5995a..32d37f7b70f2 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -37,6 +37,11 @@ #define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */ #define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */ #define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */ +#define SMC_CLC_DECL_NOISM2SUPP 0x03030003 /* hardware has no ISMv2 support */ +#define SMC_CLC_DECL_NOV2EXT 0x03030004 /* peer sent no clc v2 extension */ +#define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */ +#define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */ +#define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 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 */ @@ -329,5 +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 diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index af96f813c075..59342b519e34 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -16,6 +16,8 @@ #include <linux/wait.h> #include <linux/reboot.h> #include <linux/mutex.h> +#include <linux/list.h> +#include <linux/smc.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> @@ -30,12 +32,13 @@ #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" +#include "smc_netlink.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) -static struct smc_lgr_list smc_lgr_list = { /* established link groups */ +struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), .list = LIST_HEAD_INIT(smc_lgr_list.list), .num = 0, @@ -63,6 +66,16 @@ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, return &smc_lgr_list.list; } +static void smc_ibdev_cnt_inc(struct smc_link *lnk) +{ + atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); +} + +static void smc_ibdev_cnt_dec(struct smc_link *lnk) +{ + atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); +} + static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group @@ -139,6 +152,7 @@ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) } if (!conn->lnk) return SMC_CLC_DECL_NOACTLINK; + atomic_inc(&conn->lnk->conn_cnt); return 0; } @@ -180,6 +194,8 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn) struct smc_link_group *lgr = conn->lgr; rb_erase(&conn->alert_node, &lgr->conns_all); + if (conn->lnk) + atomic_dec(&conn->lnk->conn_cnt); lgr->conns_num--; conn->alert_token_local = 0; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ @@ -201,6 +217,361 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + char hostname[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_seid[SMC_MAX_EID_LEN + 1]; + struct smcd_dev *smcd_dev; + struct nlattr *attrs; + u8 *seid = NULL; + u8 *host = NULL; + 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_SYS_INFO); + if (!nlh) + goto errmsg; + if (cb_ctx->pos[0]) + goto errout; + attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO); + if (!attrs) + goto errout; + if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) + goto errattr; + smc_clc_get_hostname(&host); + if (host) { + snprintf(hostname, sizeof(hostname), "%s", host); + if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) + goto errattr; + } + mutex_lock(&smcd_dev_list.mutex); + smcd_dev = list_first_entry_or_null(&smcd_dev_list.list, + struct smcd_dev, list); + if (smcd_dev) + smc_ism_get_system_eid(smcd_dev, &seid); + mutex_unlock(&smcd_dev_list.mutex); + if (seid && smc_ism_is_v2_capable()) { + snprintf(smc_seid, sizeof(smc_seid), "%s", seid); + if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) + goto errattr; + } + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + cb_ctx->pos[0] = 1; + return skb->len; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return skb->len; +} + +static int smc_nl_fill_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_target[SMC_MAX_PNETID_LEN + 1]; + struct nlattr *attrs; + + attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); + if (!attrs) + goto errout; + + if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id))) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) + goto errattr; + snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id); + if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_lgr_link(struct smc_link_group *lgr, + struct smc_link *link, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_ibname[IB_DEVICE_NAME_MAX + 1]; + u8 smc_gid_target[41]; + struct nlattr *attrs; + u32 link_uid = 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_LINK_SMCR); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR); + if (!attrs) + goto errout; + + if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT, + atomic_read(&link->conn_cnt))) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx)) + goto errattr; + snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname); + if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname)) + goto errattr; + memcpy(&link_uid, link->link_uid, sizeof(link_uid)); + if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid)) + goto errattr; + memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid)); + if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid)) + goto errattr; + memset(smc_gid_target, 0, sizeof(smc_gid_target)); + smc_gid_be16_convert(smc_gid_target, link->gid); + if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target)) + goto errattr; + memset(smc_gid_target, 0, sizeof(smc_gid_target)); + smc_gid_be16_convert(smc_gid_target, link->peer_gid); + if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target)) + 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 int smc_nl_handle_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + bool list_links) +{ + 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_LGR_SMCR); + if (!nlh) + goto errmsg; + if (smc_nl_fill_lgr(lgr, skb, cb)) + goto errout; + + genlmsg_end(skb, nlh); + if (!list_links) + goto out; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_usable(&lgr->lnk[i])) + continue; + if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb)) + goto errout; + } +out: + return 0; + +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + bool list_links) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_link_group *lgr; + int snum = cb_ctx->pos[0]; + int num = 0; + + spin_lock_bh(&smc_lgr->lock); + list_for_each_entry(lgr, &smc_lgr->list, list) { + if (num < snum) + goto next; + if (smc_nl_handle_lgr(lgr, skb, cb, list_links)) + goto errout; +next: + num++; + } +errout: + spin_unlock_bh(&smc_lgr->lock); + cb_ctx->pos[0] = num; +} + +static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_pnet[SMC_MAX_PNETID_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + struct nlattr *v2_attrs; + struct nlattr *attrs; + 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_LGR_SMCD); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD); + if (!attrs) + goto errout; + + if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, lgr->smcd->local_gid, + SMC_NLA_LGR_D_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid, + SMC_NLA_LGR_D_PAD)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) + goto errattr; + snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid); + if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) + goto errattr; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname); + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid); + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_link_group *lgr; + int snum = cb_ctx->pos[1]; + int rc = 0, num = 0; + + spin_lock_bh(&dev->lgr_lock); + list_for_each_entry(lgr, &dev->lgr_list, list) { + if (!lgr->is_smcd) + continue; + if (num < snum) + goto next; + rc = smc_nl_fill_smcd_lgr(lgr, skb, cb); + if (rc) + goto errout; +next: + num++; + } +errout: + spin_unlock_bh(&dev->lgr_lock); + cb_ctx->pos[1] = num; + return rc; +} + +static int smc_nl_fill_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); + struct smcd_dev *smcd_dev; + int snum = cb_ctx->pos[0]; + int rc = 0, num = 0; + + mutex_lock(&dev_list->mutex); + list_for_each_entry(smcd_dev, &dev_list->list, list) { + if (list_empty(&smcd_dev->lgr_list)) + continue; + if (num < snum) + goto next; + rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb); + if (rc) + goto errout; +next: + num++; + } +errout: + mutex_unlock(&dev_list->mutex); + cb_ctx->pos[0] = num; + return rc; +} + +int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) +{ + bool list_links = false; + + smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); + return skb->len; +} + +int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) +{ + bool list_links = true; + + smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); + return skb->len; +} + +int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb); + return skb->len; +} + void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; @@ -300,6 +671,15 @@ static u8 smcr_next_link_id(struct smc_link_group *lgr) return link_id; } +static void smcr_copy_dev_info_to_link(struct smc_link *link) +{ + struct smc_ib_device *smcibdev = link->smcibdev; + + snprintf(link->ibname, sizeof(link->ibname), "%s", + smcibdev->ibdev->name); + link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1]; +} + int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { @@ -313,7 +693,10 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->link_idx = link_idx; lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; + smc_ibdev_cnt_inc(lnk); + smcr_copy_dev_info_to_link(lnk); lnk->path_mtu = ini->ib_dev->pattr[ini->ib_port - 1].active_mtu; + atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); if (!ini->ib_dev->initialized) { @@ -355,6 +738,7 @@ free_link_mem: clear_llc_lnk: smc_llc_link_clear(lnk, false); out: + smc_ibdev_cnt_dec(lnk); put_device(&ini->ib_dev->ibdev->dev); memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; @@ -526,6 +910,14 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, return rc; } +static void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk) +{ + atomic_dec(&conn->lnk->conn_cnt); + conn->lnk = to_lnk; + atomic_inc(&conn->lnk->conn_cnt); +} + struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err) { @@ -574,7 +966,7 @@ again: smc->sk.sk_state == SMC_PEERABORTWAIT || smc->sk.sk_state == SMC_PROCESSABORT) { spin_lock_bh(&conn->send_lock); - conn->lnk = to_lnk; + smc_switch_link_and_count(conn, to_lnk); spin_unlock_bh(&conn->send_lock); continue; } @@ -588,7 +980,7 @@ again: } /* avoid race with smcr_tx_sndbuf_nonempty() */ spin_lock_bh(&conn->send_lock); - conn->lnk = to_lnk; + smc_switch_link_and_count(conn, to_lnk); rc = smc_switch_cursor(smc, pend, wr_buf); spin_unlock_bh(&conn->send_lock); sock_put(&smc->sk); @@ -737,6 +1129,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log) smc_ib_destroy_queue_pair(lnk); smc_ib_dealloc_protection_domain(lnk); smc_wr_free_link_mem(lnk); + smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index f1e867ce2e63..e8e448771f85 100644 --- a/net/smc/smc_core.h +++ b/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 @@ -301,6 +307,7 @@ struct smc_init_info { u8 first_contact_peer; u8 first_contact_local; unsigned short vlan_id; + u32 rc; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; @@ -362,6 +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; @@ -409,6 +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) { diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f15fca59b4b2..c952986a6aca 100644 --- a/net/smc/smc_diag.c +++ b/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; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index fc766b537ac7..89ea10675a7d 100644 --- a/net/smc/smc_ib.c +++ b/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 @@ out: 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, diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 2ce481187dd0..3085f5180da7 100644 --- a/net/smc/smc_ib.h +++ b/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 diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 6abbdd09a580..524ef64a191a 100644 --- a/net/smc/smc_ism.c +++ b/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; diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 8048e09ddcf8..113efc7352ed 100644 --- a/net/smc/smc_ism.h +++ b/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 diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c new file mode 100644 index 000000000000..140419a19dbf --- /dev/null +++ b/net/smc/smc_netlink.c @@ -0,0 +1,85 @@ +// 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); +} diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h new file mode 100644 index 000000000000..3477265cba6c --- /dev/null +++ b/net/smc/smc_netlink.h @@ -0,0 +1,32 @@ +/* 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 diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index f3c18b991d35..6f6d33edb135 100644 --- a/net/smc/smc_pnet.c +++ b/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); diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 1e23cdd41eb1..cbc73a7e4d59 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -131,9 +131,9 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) wake_up(&link->wr_tx_wait); } -static void smc_wr_tx_tasklet_fn(unsigned long data) +static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t) { - struct smc_ib_device *dev = (struct smc_ib_device *)data; + struct smc_ib_device *dev = from_tasklet(dev, t, send_tasklet); struct ib_wc wc[SMC_WR_MAX_POLL_CQE]; int i = 0, rc; int polled = 0; @@ -435,9 +435,9 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) } } -static void smc_wr_rx_tasklet_fn(unsigned long data) +static void smc_wr_rx_tasklet_fn(struct tasklet_struct *t) { - struct smc_ib_device *dev = (struct smc_ib_device *)data; + struct smc_ib_device *dev = from_tasklet(dev, t, recv_tasklet); struct ib_wc wc[SMC_WR_MAX_POLL_CQE]; int polled = 0; int rc; @@ -698,10 +698,8 @@ void smc_wr_remove_dev(struct smc_ib_device *smcibdev) void smc_wr_add_dev(struct smc_ib_device *smcibdev) { - tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn, - (unsigned long)smcibdev); - tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn, - (unsigned long)smcibdev); + tasklet_setup(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn); + tasklet_setup(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn); } int smc_wr_create_link(struct smc_link *lnk) |