X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Flnet%2Fapi-ni.c;h=63eeacae7cf311be91662ae5f1456df65e045fee;hp=270629dde17ece76ffbce1a1526c3848b62c821c;hb=ed052504713d1db49531454a87055b2ee54399f0;hpb=2be59ff6bffdbaece48d35cd678bc9ee28ddf4f3 diff --git a/lnet/lnet/api-ni.c b/lnet/lnet/api-ni.c index 270629d..63eeaca 100644 --- a/lnet/lnet/api-ni.c +++ b/lnet/lnet/api-ni.c @@ -33,12 +33,20 @@ #define DEBUG_SUBSYSTEM S_LNET #include #include +#include #include #define D_LNI D_CONSOLE -lnet_t the_lnet; /* THE state of the network */ +/* + * initialize ln_api_mutex statically, since it needs to be used in + * discovery_set callback. That module parameter callback can be called + * before module init completes. The mutex needs to be ready for use then. + */ +struct lnet the_lnet = { + .ln_api_mutex = __MUTEX_INITIALIZER(the_lnet.ln_api_mutex), +}; /* THE state of the network */ EXPORT_SYMBOL(the_lnet); static char *ip2nets = ""; @@ -57,8 +65,116 @@ static int rnet_htable_size = LNET_REMOTE_NETS_HASH_DEFAULT; module_param(rnet_htable_size, int, 0444); MODULE_PARM_DESC(rnet_htable_size, "size of remote network hash table"); -static int lnet_ping(lnet_process_id_t id, signed long timeout, - lnet_process_id_t __user *ids, int n_ids); +static int use_tcp_bonding = false; +module_param(use_tcp_bonding, int, 0444); +MODULE_PARM_DESC(use_tcp_bonding, + "Set to 1 to use socklnd bonding. 0 to use Multi-Rail"); + +unsigned int lnet_numa_range = 0; +module_param(lnet_numa_range, uint, 0444); +MODULE_PARM_DESC(lnet_numa_range, + "NUMA range to consider during Multi-Rail selection"); + +static int lnet_interfaces_max = LNET_INTERFACES_MAX_DEFAULT; +static int intf_max_set(const char *val, struct kernel_param *kp); +module_param_call(lnet_interfaces_max, intf_max_set, param_get_int, + &lnet_interfaces_max, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(lnet_interfaces_max, + "Maximum number of interfaces in a node."); + +unsigned lnet_peer_discovery_disabled = 0; +static int discovery_set(const char *val, struct kernel_param *kp); +module_param_call(lnet_peer_discovery_disabled, discovery_set, param_get_int, + &lnet_peer_discovery_disabled, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(lnet_peer_discovery_disabled, + "Set to 1 to disable peer discovery on this node."); + +/* + * This sequence number keeps track of how many times DLC was used to + * update the local NIs. It is incremented when a NI is added or + * removed and checked when sending a message to determine if there is + * a need to re-run the selection algorithm. See lnet_select_pathway() + * for more details on its usage. + */ +static atomic_t lnet_dlc_seq_no = ATOMIC_INIT(0); + +static int lnet_ping(struct lnet_process_id id, signed long timeout, + struct lnet_process_id __user *ids, int n_ids); + +static int lnet_discover(lnet_process_id_t id, __u32 force, + lnet_process_id_t __user *ids, int n_ids); + +static int +discovery_set(const char *val, struct kernel_param *kp) +{ + int rc; + unsigned *discovery = (unsigned *)kp->arg; + unsigned long value; + struct lnet_ping_buffer *pbuf; + + rc = kstrtoul(val, 0, &value); + if (rc) { + CERROR("Invalid module parameter value for 'lnet_peer_discovery_disabled'\n"); + return rc; + } + + value = (value) ? 1 : 0; + + /* + * The purpose of locking the api_mutex here is to ensure that + * the correct value ends up stored properly. + */ + mutex_lock(&the_lnet.ln_api_mutex); + + if (value == *discovery) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + *discovery = value; + + if (the_lnet.ln_state != LNET_STATE_RUNNING) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + /* tell peers that discovery setting has changed */ + lnet_net_lock(LNET_LOCK_EX); + pbuf = the_lnet.ln_ping_target; + if (value) + pbuf->pb_info.pi_features &= ~LNET_PING_FEAT_DISCOVERY; + else + pbuf->pb_info.pi_features |= LNET_PING_FEAT_DISCOVERY; + lnet_net_unlock(LNET_LOCK_EX); + + lnet_push_update_to_peers(1); + + mutex_unlock(&the_lnet.ln_api_mutex); + + return 0; +} + +static int +intf_max_set(const char *val, struct kernel_param *kp) +{ + int value, rc; + + rc = kstrtoint(val, 0, &value); + if (rc) { + CERROR("Invalid module parameter value for 'lnet_interfaces_max'\n"); + return rc; + } + + if (value < LNET_INTERFACES_MIN) { + CWARN("max interfaces provided are too small, setting to %d\n", + LNET_INTERFACES_MIN); + value = LNET_INTERFACES_MIN; + } + + *(int *)kp->arg = value; + + return 0; +} static char * lnet_get_routes(void) @@ -96,7 +212,6 @@ lnet_init_locks(void) init_waitqueue_head(&the_lnet.ln_eq_waitq); init_waitqueue_head(&the_lnet.ln_rc_waitq); mutex_init(&the_lnet.ln_lnd_mutex); - mutex_init(&the_lnet.ln_api_mutex); } static void @@ -114,7 +229,7 @@ lnet_descriptor_setup(void) /* create specific kmem_cache for MEs and small MDs (i.e., originally * allocated in kmem_cache). */ - lnet_mes_cachep = kmem_cache_create("lnet_MEs", sizeof(lnet_me_t), + lnet_mes_cachep = kmem_cache_create("lnet_MEs", sizeof(struct lnet_me), 0, 0, NULL); if (!lnet_mes_cachep) return -ENOMEM; @@ -240,83 +355,120 @@ static void lnet_assert_wire_constants(void) CLASSERT((int)offsetof(struct lnet_handle_wire, wh_object_cookie) == 8); CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) == 8); - /* Checks for struct lnet_magicversion_t */ - CLASSERT((int)sizeof(lnet_magicversion_t) == 8); - CLASSERT((int)offsetof(lnet_magicversion_t, magic) == 0); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->magic) == 4); - CLASSERT((int)offsetof(lnet_magicversion_t, version_major) == 4); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->version_major) == 2); - CLASSERT((int)offsetof(lnet_magicversion_t, version_minor) == 6); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->version_minor) == 2); - - /* Checks for struct lnet_hdr_t */ - CLASSERT((int)sizeof(lnet_hdr_t) == 72); - CLASSERT((int)offsetof(lnet_hdr_t, dest_nid) == 0); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->dest_nid) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, src_nid) == 8); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->src_nid) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, dest_pid) == 16); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->dest_pid) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, src_pid) == 20); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->src_pid) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, type) == 24); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->type) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, payload_length) == 28); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->payload_length) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg) == 40); + /* Checks for struct struct lnet_magicversion */ + CLASSERT((int)sizeof(struct lnet_magicversion) == 8); + CLASSERT((int)offsetof(struct lnet_magicversion, magic) == 0); + CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->magic) == 4); + CLASSERT((int)offsetof(struct lnet_magicversion, version_major) == 4); + CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_major) == 2); + CLASSERT((int)offsetof(struct lnet_magicversion, version_minor) == 6); + CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_minor) == 2); + + /* Checks for struct struct lnet_hdr */ + CLASSERT((int)sizeof(struct lnet_hdr) == 72); + CLASSERT((int)offsetof(struct lnet_hdr, dest_nid) == 0); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_nid) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, src_nid) == 8); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_nid) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, dest_pid) == 16); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_pid) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, src_pid) == 20); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_pid) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, type) == 24); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->type) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, payload_length) == 28); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->payload_length) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg) == 40); /* Ack */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.dst_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.dst_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.mlength) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.mlength) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.dst_wmd) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.dst_wmd) == 16); + CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.match_bits) == 48); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.match_bits) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.mlength) == 56); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.mlength) == 4); /* Put */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.ack_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.ack_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.hdr_data) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.hdr_data) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.ptl_index) == 64); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.ptl_index) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.offset) == 68); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.offset) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ack_wmd) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ack_wmd) == 16); + CLASSERT((int)offsetof(struct lnet_hdr, msg.put.match_bits) == 48); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.match_bits) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, msg.put.hdr_data) == 56); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.hdr_data) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ptl_index) == 64); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ptl_index) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.put.offset) == 68); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.offset) == 4); /* Get */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.return_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.return_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.ptl_index) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.ptl_index) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.src_offset) == 60); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.src_offset) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.sink_length) == 64); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.sink_length) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.get.return_wmd) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.return_wmd) == 16); + CLASSERT((int)offsetof(struct lnet_hdr, msg.get.match_bits) == 48); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.match_bits) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, msg.get.ptl_index) == 56); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.ptl_index) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.get.src_offset) == 60); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.src_offset) == 4); + CLASSERT((int)offsetof(struct lnet_hdr, msg.get.sink_length) == 64); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.sink_length) == 4); /* Reply */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.reply.dst_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.reply.dst_wmd) == 16); + CLASSERT((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) == 16); /* Hello */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.hello.incarnation) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.hello.incarnation) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.hello.type) == 40); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.hello.type) == 4); -} - -static lnd_t *lnet_find_lnd_by_type(__u32 type) -{ - lnd_t *lnd; + CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.incarnation) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.incarnation) == 8); + CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.type) == 40); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.type) == 4); + + /* Checks for struct lnet_ni_status and related constants */ + CLASSERT(LNET_NI_STATUS_INVALID == 0x00000000); + CLASSERT(LNET_NI_STATUS_UP == 0x15aac0de); + CLASSERT(LNET_NI_STATUS_DOWN == 0xdeadface); + + /* Checks for struct lnet_ni_status */ + CLASSERT((int)sizeof(struct lnet_ni_status) == 16); + CLASSERT((int)offsetof(struct lnet_ni_status, ns_nid) == 0); + CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_nid) == 8); + CLASSERT((int)offsetof(struct lnet_ni_status, ns_status) == 8); + CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_status) == 4); + CLASSERT((int)offsetof(struct lnet_ni_status, ns_unused) == 12); + CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_unused) == 4); + + /* Checks for struct lnet_ping_info and related constants */ + CLASSERT(LNET_PROTO_PING_MAGIC == 0x70696E67); + CLASSERT(LNET_PING_FEAT_INVAL == 0); + CLASSERT(LNET_PING_FEAT_BASE == 1); + CLASSERT(LNET_PING_FEAT_NI_STATUS == 2); + CLASSERT(LNET_PING_FEAT_RTE_DISABLED == 4); + CLASSERT(LNET_PING_FEAT_MULTI_RAIL == 8); + CLASSERT(LNET_PING_FEAT_DISCOVERY == 16); + CLASSERT(LNET_PING_FEAT_BITS == 31); + + /* Checks for struct lnet_ping_info */ + CLASSERT((int)sizeof(struct lnet_ping_info) == 16); + CLASSERT((int)offsetof(struct lnet_ping_info, pi_magic) == 0); + CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_magic) == 4); + CLASSERT((int)offsetof(struct lnet_ping_info, pi_features) == 4); + CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_features) == 4); + CLASSERT((int)offsetof(struct lnet_ping_info, pi_pid) == 8); + CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_pid) == 4); + CLASSERT((int)offsetof(struct lnet_ping_info, pi_nnis) == 12); + CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_nnis) == 4); + CLASSERT((int)offsetof(struct lnet_ping_info, pi_ni) == 16); + CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_ni) == 0); +} + +static struct lnet_lnd *lnet_find_lnd_by_type(__u32 type) +{ + struct lnet_lnd *lnd; struct list_head *tmp; /* holding lnd mutex */ list_for_each(tmp, &the_lnet.ln_lnds) { - lnd = list_entry(tmp, lnd_t, lnd_list); + lnd = list_entry(tmp, struct lnet_lnd, lnd_list); if (lnd->lnd_type == type) return lnd; @@ -325,7 +477,7 @@ static lnd_t *lnet_find_lnd_by_type(__u32 type) } void -lnet_register_lnd (lnd_t *lnd) +lnet_register_lnd(struct lnet_lnd *lnd) { mutex_lock(&the_lnet.ln_lnd_mutex); @@ -342,7 +494,7 @@ lnet_register_lnd (lnd_t *lnd) EXPORT_SYMBOL(lnet_register_lnd); void -lnet_unregister_lnd (lnd_t *lnd) +lnet_unregister_lnd(struct lnet_lnd *lnd) { mutex_lock(&the_lnet.ln_lnd_mutex); @@ -357,9 +509,9 @@ lnet_unregister_lnd (lnd_t *lnd) EXPORT_SYMBOL(lnet_unregister_lnd); void -lnet_counters_get(lnet_counters_t *counters) +lnet_counters_get(struct lnet_counters *counters) { - lnet_counters_t *ctr; + struct lnet_counters *ctr; int i; memset(counters, 0, sizeof(*counters)); @@ -387,13 +539,13 @@ EXPORT_SYMBOL(lnet_counters_get); void lnet_counters_reset(void) { - lnet_counters_t *counters; + struct lnet_counters *counters; int i; lnet_net_lock(LNET_LOCK_EX); cfs_percpt_for_each(counters, i, the_lnet.ln_counters) - memset(counters, 0, sizeof(lnet_counters_t)); + memset(counters, 0, sizeof(struct lnet_counters)); lnet_net_unlock(LNET_LOCK_EX); } @@ -426,10 +578,10 @@ lnet_res_container_cleanup(struct lnet_res_container *rec) list_del_init(e); if (rec->rec_type == LNET_COOKIE_TYPE_EQ) { - lnet_eq_free(list_entry(e, lnet_eq_t, eq_list)); + lnet_eq_free(list_entry(e, struct lnet_eq, eq_list)); } else if (rec->rec_type == LNET_COOKIE_TYPE_MD) { - lnet_md_free(list_entry(e, lnet_libmd_t, md_list)); + lnet_md_free(list_entry(e, struct lnet_libmd, md_list)); } else { /* NB: Active MEs should be attached on portals */ LBUG(); @@ -525,12 +677,12 @@ lnet_res_containers_create(int type) return recs; } -lnet_libhandle_t * +struct lnet_libhandle * lnet_res_lh_lookup(struct lnet_res_container *rec, __u64 cookie) { /* ALWAYS called with lnet_res_lock held */ struct list_head *head; - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; unsigned int hash; if ((cookie & LNET_COOKIE_MASK) != rec->rec_type) @@ -548,7 +700,8 @@ lnet_res_lh_lookup(struct lnet_res_container *rec, __u64 cookie) } void -lnet_res_lh_initialize(struct lnet_res_container *rec, lnet_libhandle_t *lh) +lnet_res_lh_initialize(struct lnet_res_container *rec, + struct lnet_libhandle *lh) { /* ALWAYS called with lnet_res_lock held */ unsigned int ibits = LNET_COOKIE_TYPE_BITS + LNET_CPT_BITS; @@ -584,12 +737,15 @@ lnet_prepare(lnet_pid_t requested_pid) the_lnet.ln_pid = requested_pid; INIT_LIST_HEAD(&the_lnet.ln_test_peers); - INIT_LIST_HEAD(&the_lnet.ln_nis); - INIT_LIST_HEAD(&the_lnet.ln_nis_cpt); - INIT_LIST_HEAD(&the_lnet.ln_nis_zombie); + INIT_LIST_HEAD(&the_lnet.ln_remote_peer_ni_list); + INIT_LIST_HEAD(&the_lnet.ln_nets); INIT_LIST_HEAD(&the_lnet.ln_routers); INIT_LIST_HEAD(&the_lnet.ln_drop_rules); INIT_LIST_HEAD(&the_lnet.ln_delay_rules); + INIT_LIST_HEAD(&the_lnet.ln_dc_request); + INIT_LIST_HEAD(&the_lnet.ln_dc_working); + INIT_LIST_HEAD(&the_lnet.ln_dc_expired); + init_waitqueue_head(&the_lnet.ln_dc_waitq); rc = lnet_descriptor_setup(); if (rc != 0) @@ -606,7 +762,7 @@ lnet_prepare(lnet_pid_t requested_pid) the_lnet.ln_interface_cookie = ktime_get_real_ns(); the_lnet.ln_counters = cfs_percpt_alloc(lnet_cpt_table(), - sizeof(lnet_counters_t)); + sizeof(struct lnet_counters)); if (the_lnet.ln_counters == NULL) { CERROR("Failed to allocate counters for LNet\n"); rc = -ENOMEM; @@ -667,9 +823,7 @@ lnet_unprepare (void) LASSERT(the_lnet.ln_refcount == 0); LASSERT(list_empty(&the_lnet.ln_test_peers)); - LASSERT(list_empty(&the_lnet.ln_nis)); - LASSERT(list_empty(&the_lnet.ln_nis_cpt)); - LASSERT(list_empty(&the_lnet.ln_nis_zombie)); + LASSERT(list_empty(&the_lnet.ln_nets)); lnet_portals_destroy(); @@ -686,7 +840,7 @@ lnet_unprepare (void) lnet_res_container_cleanup(&the_lnet.ln_eq_container); lnet_msg_containers_destroy(); - lnet_peer_tables_destroy(); + lnet_peer_uninit(); lnet_rtrpools_free(0); if (the_lnet.ln_counters != NULL) { @@ -699,19 +853,18 @@ lnet_unprepare (void) return 0; } -lnet_ni_t * -lnet_net2ni_locked(__u32 net, int cpt) +struct lnet_ni * +lnet_net2ni_locked(__u32 net_id, int cpt) { - struct list_head *tmp; - lnet_ni_t *ni; + struct lnet_ni *ni; + struct lnet_net *net; LASSERT(cpt != LNET_LOCK_EX); - list_for_each(tmp, &the_lnet.ln_nis) { - ni = list_entry(tmp, lnet_ni_t, ni_list); - - if (LNET_NIDNET(ni->ni_nid) == net) { - lnet_ni_addref_locked(ni, cpt); + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + if (net->net_id == net_id) { + ni = list_entry(net->net_ni_list.next, struct lnet_ni, + ni_netlist); return ni; } } @@ -719,20 +872,35 @@ lnet_net2ni_locked(__u32 net, int cpt) return NULL; } -lnet_ni_t * -lnet_net2ni(__u32 net) +struct lnet_ni * +lnet_net2ni_addref(__u32 net) { - lnet_ni_t *ni; + struct lnet_ni *ni; lnet_net_lock(0); ni = lnet_net2ni_locked(net, 0); + if (ni) + lnet_ni_addref_locked(ni, 0); lnet_net_unlock(0); return ni; } -EXPORT_SYMBOL(lnet_net2ni); +EXPORT_SYMBOL(lnet_net2ni_addref); + +struct lnet_net * +lnet_get_net_locked(__u32 net_id) +{ + struct lnet_net *net; + + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + if (net->net_id == net_id) + return net; + } + + return NULL; +} -static unsigned int +unsigned int lnet_nid_cpt_hash(lnet_nid_t nid, unsigned int number) { __u64 key = nid; @@ -752,31 +920,41 @@ lnet_nid_cpt_hash(lnet_nid_t nid, unsigned int number) } int -lnet_cpt_of_nid_locked(lnet_nid_t nid) +lnet_cpt_of_nid_locked(lnet_nid_t nid, struct lnet_ni *ni) { - struct lnet_ni *ni; + struct lnet_net *net; /* must called with hold of lnet_net_lock */ if (LNET_CPT_NUMBER == 1) return 0; /* the only one */ - /* take lnet_net_lock(any) would be OK */ - if (!list_empty(&the_lnet.ln_nis_cpt)) { - list_for_each_entry(ni, &the_lnet.ln_nis_cpt, ni_cptlist) { - if (LNET_NIDNET(ni->ni_nid) != LNET_NIDNET(nid)) - continue; + /* + * If NI is provided then use the CPT identified in the NI cpt + * list if one exists. If one doesn't exist, then that NI is + * associated with all CPTs and it follows that the net it belongs + * to is implicitly associated with all CPTs, so just hash the nid + * and return that. + */ + if (ni != NULL) { + if (ni->ni_cpts != NULL) + return ni->ni_cpts[lnet_nid_cpt_hash(nid, + ni->ni_ncpts)]; + else + return lnet_nid_cpt_hash(nid, LNET_CPT_NUMBER); + } - LASSERT(ni->ni_cpts != NULL); - return ni->ni_cpts[lnet_nid_cpt_hash - (nid, ni->ni_ncpts)]; - } + /* no NI provided so look at the net */ + net = lnet_get_net_locked(LNET_NIDNET(nid)); + + if (net != NULL && net->net_cpts != NULL) { + return net->net_cpts[lnet_nid_cpt_hash(nid, net->net_ncpts)]; } return lnet_nid_cpt_hash(nid, LNET_CPT_NUMBER); } int -lnet_cpt_of_nid(lnet_nid_t nid) +lnet_cpt_of_nid(lnet_nid_t nid, struct lnet_ni *ni) { int cpt; int cpt2; @@ -784,11 +962,10 @@ lnet_cpt_of_nid(lnet_nid_t nid) if (LNET_CPT_NUMBER == 1) return 0; /* the only one */ - if (list_empty(&the_lnet.ln_nis_cpt)) - return lnet_nid_cpt_hash(nid, LNET_CPT_NUMBER); - cpt = lnet_net_lock_current(); - cpt2 = lnet_cpt_of_nid_locked(nid); + + cpt2 = lnet_cpt_of_nid_locked(nid, ni); + lnet_net_unlock(cpt); return cpt2; @@ -796,42 +973,66 @@ lnet_cpt_of_nid(lnet_nid_t nid) EXPORT_SYMBOL(lnet_cpt_of_nid); int -lnet_islocalnet(__u32 net) +lnet_islocalnet(__u32 net_id) { - struct lnet_ni *ni; + struct lnet_net *net; int cpt; + bool local; cpt = lnet_net_lock_current(); - ni = lnet_net2ni_locked(net, cpt); - if (ni != NULL) - lnet_ni_decref_locked(ni, cpt); + net = lnet_get_net_locked(net_id); + + local = net != NULL; lnet_net_unlock(cpt); - return ni != NULL; + return local; +} + +bool +lnet_is_ni_healthy_locked(struct lnet_ni *ni) +{ + if (ni->ni_state == LNET_NI_STATE_ACTIVE || + ni->ni_state == LNET_NI_STATE_DEGRADED) + return true; + + return false; } -lnet_ni_t * +struct lnet_ni * lnet_nid2ni_locked(lnet_nid_t nid, int cpt) { + struct lnet_net *net; struct lnet_ni *ni; - struct list_head *tmp; LASSERT(cpt != LNET_LOCK_EX); - list_for_each(tmp, &the_lnet.ln_nis) { - ni = list_entry(tmp, lnet_ni_t, ni_list); - - if (ni->ni_nid == nid) { - lnet_ni_addref_locked(ni, cpt); - return ni; + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + if (ni->ni_nid == nid) + return ni; } } return NULL; } +struct lnet_ni * +lnet_nid2ni_addref(lnet_nid_t nid) +{ + struct lnet_ni *ni; + + lnet_net_lock(0); + ni = lnet_nid2ni_locked(nid, 0); + if (ni) + lnet_ni_addref_locked(ni, 0); + lnet_net_unlock(0); + + return ni; +} +EXPORT_SYMBOL(lnet_nid2ni_addref); + int lnet_islocalnid(lnet_nid_t nid) { @@ -840,27 +1041,24 @@ lnet_islocalnid(lnet_nid_t nid) cpt = lnet_net_lock_current(); ni = lnet_nid2ni_locked(nid, cpt); - if (ni != NULL) - lnet_ni_decref_locked(ni, cpt); lnet_net_unlock(cpt); return ni != NULL; } int -lnet_count_acceptor_nis (void) +lnet_count_acceptor_nets(void) { /* Return the # of NIs that need the acceptor. */ int count = 0; - struct list_head *tmp; - struct lnet_ni *ni; + struct lnet_net *net; int cpt; cpt = lnet_net_lock_current(); - list_for_each(tmp, &the_lnet.ln_nis) { - ni = list_entry(tmp, lnet_ni_t, ni_list); - - if (ni->ni_lnd->lnd_accept != NULL) + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + /* all socklnd type networks should have the acceptor + * thread started */ + if (net->net_lnd->lnd_accept != NULL) count++; } @@ -869,155 +1067,222 @@ lnet_count_acceptor_nis (void) return count; } -static struct lnet_ping_info * -lnet_ping_info_create(int num_ni) +struct lnet_ping_buffer * +lnet_ping_buffer_alloc(int nnis, gfp_t gfp) +{ + struct lnet_ping_buffer *pbuf; + + LIBCFS_ALLOC_GFP(pbuf, LNET_PING_BUFFER_SIZE(nnis), gfp); + if (pbuf) { + pbuf->pb_nnis = nnis; + atomic_set(&pbuf->pb_refcnt, 1); + } + + return pbuf; +} + +void +lnet_ping_buffer_free(struct lnet_ping_buffer *pbuf) +{ + LASSERT(lnet_ping_buffer_numref(pbuf) == 0); + LIBCFS_FREE(pbuf, LNET_PING_BUFFER_SIZE(pbuf->pb_nnis)); +} + +static struct lnet_ping_buffer * +lnet_ping_target_create(int nnis) { - struct lnet_ping_info *ping_info; - unsigned int infosz; + struct lnet_ping_buffer *pbuf; - infosz = offsetof(struct lnet_ping_info, pi_ni[num_ni]); - LIBCFS_ALLOC(ping_info, infosz); - if (ping_info == NULL) { - CERROR("Can't allocate ping info[%d]\n", num_ni); + pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS); + if (pbuf == NULL) { + CERROR("Can't allocate ping source [%d]\n", nnis); return NULL; } - ping_info->pi_nnis = num_ni; - ping_info->pi_pid = the_lnet.ln_pid; - ping_info->pi_magic = LNET_PROTO_PING_MAGIC; - ping_info->pi_features = LNET_PING_FEAT_NI_STATUS; + pbuf->pb_info.pi_nnis = nnis; + pbuf->pb_info.pi_pid = the_lnet.ln_pid; + pbuf->pb_info.pi_magic = LNET_PROTO_PING_MAGIC; + pbuf->pb_info.pi_features = + LNET_PING_FEAT_NI_STATUS | LNET_PING_FEAT_MULTI_RAIL; + + return pbuf; +} + +static inline int +lnet_get_net_ni_count_locked(struct lnet_net *net) +{ + struct lnet_ni *ni; + int count = 0; + + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) + count++; + + return count; +} + +static inline int +lnet_get_net_ni_count_pre(struct lnet_net *net) +{ + struct lnet_ni *ni; + int count = 0; + + list_for_each_entry(ni, &net->net_ni_added, ni_netlist) + count++; - return ping_info; + return count; } static inline int lnet_get_ni_count(void) { - struct lnet_ni *ni; - int count = 0; + struct lnet_ni *ni; + struct lnet_net *net; + int count = 0; lnet_net_lock(0); - list_for_each_entry(ni, &the_lnet.ln_nis, ni_list) - count++; + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) + count++; + } lnet_net_unlock(0); return count; } -static inline void -lnet_ping_info_free(struct lnet_ping_info *pinfo) +int +lnet_ping_info_validate(struct lnet_ping_info *pinfo) { - LIBCFS_FREE(pinfo, - offsetof(struct lnet_ping_info, - pi_ni[pinfo->pi_nnis])); + if (!pinfo) + return -EINVAL; + if (pinfo->pi_magic != LNET_PROTO_PING_MAGIC) + return -EPROTO; + if (!(pinfo->pi_features & LNET_PING_FEAT_NI_STATUS)) + return -EPROTO; + /* Loopback is guaranteed to be present */ + if (pinfo->pi_nnis < 1 || pinfo->pi_nnis > lnet_interfaces_max) + return -ERANGE; + if (LNET_NETTYP(LNET_NIDNET(LNET_PING_INFO_LONI(pinfo))) != LOLND) + return -EPROTO; + return 0; } static void -lnet_ping_info_destroy(void) +lnet_ping_target_destroy(void) { + struct lnet_net *net; struct lnet_ni *ni; lnet_net_lock(LNET_LOCK_EX); - list_for_each_entry(ni, &the_lnet.ln_nis, ni_list) { - lnet_ni_lock(ni); - ni->ni_status = NULL; - lnet_ni_unlock(ni); + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + lnet_ni_lock(ni); + ni->ni_status = NULL; + lnet_ni_unlock(ni); + } } - lnet_ping_info_free(the_lnet.ln_ping_info); - the_lnet.ln_ping_info = NULL; + lnet_ping_buffer_decref(the_lnet.ln_ping_target); + the_lnet.ln_ping_target = NULL; lnet_net_unlock(LNET_LOCK_EX); } static void -lnet_ping_event_handler(lnet_event_t *event) +lnet_ping_target_event_handler(struct lnet_event *event) { - struct lnet_ping_info *pinfo = event->md.user_ptr; + struct lnet_ping_buffer *pbuf = event->md.user_ptr; if (event->unlinked) - pinfo->pi_features = LNET_PING_FEAT_INVAL; + lnet_ping_buffer_decref(pbuf); } static int -lnet_ping_info_setup(struct lnet_ping_info **ppinfo, lnet_handle_md_t *md_handle, - int ni_count, bool set_eq) -{ - lnet_handle_me_t me_handle; - lnet_process_id_t id = {LNET_NID_ANY, LNET_PID_ANY}; - lnet_md_t md = {NULL}; - int rc, rc2; +lnet_ping_target_setup(struct lnet_ping_buffer **ppbuf, + struct lnet_handle_md *ping_mdh, + int ni_count, bool set_eq) +{ + struct lnet_process_id id = { + .nid = LNET_NID_ANY, + .pid = LNET_PID_ANY + }; + struct lnet_handle_me me_handle; + struct lnet_md md = { NULL }; + int rc, rc2; if (set_eq) { - rc = LNetEQAlloc(0, lnet_ping_event_handler, + rc = LNetEQAlloc(0, lnet_ping_target_event_handler, &the_lnet.ln_ping_target_eq); if (rc != 0) { - CERROR("Can't allocate ping EQ: %d\n", rc); + CERROR("Can't allocate ping buffer EQ: %d\n", rc); return rc; } } - *ppinfo = lnet_ping_info_create(ni_count); - if (*ppinfo == NULL) { + *ppbuf = lnet_ping_target_create(ni_count); + if (*ppbuf == NULL) { rc = -ENOMEM; - goto failed_0; + goto fail_free_eq; } + /* Ping target ME/MD */ rc = LNetMEAttach(LNET_RESERVED_PORTAL, id, LNET_PROTO_PING_MATCHBITS, 0, LNET_UNLINK, LNET_INS_AFTER, &me_handle); if (rc != 0) { - CERROR("Can't create ping ME: %d\n", rc); - goto failed_1; + CERROR("Can't create ping target ME: %d\n", rc); + goto fail_decref_ping_buffer; } /* initialize md content */ - md.start = *ppinfo; - md.length = offsetof(struct lnet_ping_info, - pi_ni[(*ppinfo)->pi_nnis]); + md.start = &(*ppbuf)->pb_info; + md.length = LNET_PING_INFO_SIZE((*ppbuf)->pb_nnis); md.threshold = LNET_MD_THRESH_INF; md.max_size = 0; md.options = LNET_MD_OP_GET | LNET_MD_TRUNCATE | LNET_MD_MANAGE_REMOTE; - md.user_ptr = NULL; md.eq_handle = the_lnet.ln_ping_target_eq; - md.user_ptr = *ppinfo; + md.user_ptr = *ppbuf; - rc = LNetMDAttach(me_handle, md, LNET_RETAIN, md_handle); + rc = LNetMDAttach(me_handle, md, LNET_RETAIN, ping_mdh); if (rc != 0) { - CERROR("Can't attach ping MD: %d\n", rc); - goto failed_2; + CERROR("Can't attach ping target MD: %d\n", rc); + goto fail_unlink_ping_me; } + lnet_ping_buffer_addref(*ppbuf); return 0; -failed_2: +fail_unlink_ping_me: rc2 = LNetMEUnlink(me_handle); LASSERT(rc2 == 0); -failed_1: - lnet_ping_info_free(*ppinfo); - *ppinfo = NULL; -failed_0: - if (set_eq) - LNetEQFree(the_lnet.ln_ping_target_eq); +fail_decref_ping_buffer: + LASSERT(lnet_ping_buffer_numref(*ppbuf) == 1); + lnet_ping_buffer_decref(*ppbuf); + *ppbuf = NULL; +fail_free_eq: + if (set_eq) { + rc2 = LNetEQFree(the_lnet.ln_ping_target_eq); + LASSERT(rc2 == 0); + } return rc; } static void -lnet_ping_md_unlink(struct lnet_ping_info *pinfo, lnet_handle_md_t *md_handle) +lnet_ping_md_unlink(struct lnet_ping_buffer *pbuf, + struct lnet_handle_md *ping_mdh) { sigset_t blocked = cfs_block_allsigs(); - LNetMDUnlink(*md_handle); - LNetInvalidateHandle(md_handle); + LNetMDUnlink(*ping_mdh); + LNetInvalidateMDHandle(ping_mdh); - /* NB md could be busy; this just starts the unlink */ - while (pinfo->pi_features != LNET_PING_FEAT_INVAL) { - CDEBUG(D_NET, "Still waiting for ping MD to unlink\n"); + /* NB the MD could be busy; this just starts the unlink */ + while (lnet_ping_buffer_numref(pbuf) > 1) { + CDEBUG(D_NET, "Still waiting for ping data MD to unlink\n"); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(cfs_time_seconds(1)); } @@ -1026,57 +1291,84 @@ lnet_ping_md_unlink(struct lnet_ping_info *pinfo, lnet_handle_md_t *md_handle) } static void -lnet_ping_info_install_locked(struct lnet_ping_info *ping_info) +lnet_ping_target_install_locked(struct lnet_ping_buffer *pbuf) { - int i; - lnet_ni_t *ni; + struct lnet_ni *ni; + struct lnet_net *net; struct lnet_ni_status *ns; + int i; + int rc; i = 0; - list_for_each_entry(ni, &the_lnet.ln_nis, ni_list) { - LASSERT(i < ping_info->pi_nnis); + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + LASSERT(i < pbuf->pb_nnis); - ns = &ping_info->pi_ni[i]; + ns = &pbuf->pb_info.pi_ni[i]; - ns->ns_nid = ni->ni_nid; + ns->ns_nid = ni->ni_nid; - lnet_ni_lock(ni); - ns->ns_status = (ni->ni_status != NULL) ? - ni->ni_status->ns_status : LNET_NI_STATUS_UP; - ni->ni_status = ns; - lnet_ni_unlock(ni); + lnet_ni_lock(ni); + ns->ns_status = (ni->ni_status != NULL) ? + ni->ni_status->ns_status : + LNET_NI_STATUS_UP; + ni->ni_status = ns; + lnet_ni_unlock(ni); - i++; + i++; + } + } + /* + * We (ab)use the ns_status of the loopback interface to + * transmit the sequence number. The first interface listed + * must be the loopback interface. + */ + rc = lnet_ping_info_validate(&pbuf->pb_info); + if (rc) { + LCONSOLE_EMERG("Invalid ping target: %d\n", rc); + LBUG(); } + LNET_PING_BUFFER_SEQNO(pbuf) = + atomic_inc_return(&the_lnet.ln_ping_target_seqno); } static void -lnet_ping_target_update(struct lnet_ping_info *pinfo, lnet_handle_md_t md_handle) +lnet_ping_target_update(struct lnet_ping_buffer *pbuf, + struct lnet_handle_md ping_mdh) { - struct lnet_ping_info *old_pinfo = NULL; - lnet_handle_md_t old_md; + struct lnet_ping_buffer *old_pbuf = NULL; + struct lnet_handle_md old_ping_md; /* switch the NIs to point to the new ping info created */ lnet_net_lock(LNET_LOCK_EX); if (!the_lnet.ln_routing) - pinfo->pi_features |= LNET_PING_FEAT_RTE_DISABLED; - lnet_ping_info_install_locked(pinfo); + pbuf->pb_info.pi_features |= LNET_PING_FEAT_RTE_DISABLED; + if (!lnet_peer_discovery_disabled) + pbuf->pb_info.pi_features |= LNET_PING_FEAT_DISCOVERY; + + /* Ensure only known feature bits have been set. */ + LASSERT(pbuf->pb_info.pi_features & LNET_PING_FEAT_BITS); + LASSERT(!(pbuf->pb_info.pi_features & ~LNET_PING_FEAT_BITS)); - if (the_lnet.ln_ping_info != NULL) { - old_pinfo = the_lnet.ln_ping_info; - old_md = the_lnet.ln_ping_target_md; + lnet_ping_target_install_locked(pbuf); + + if (the_lnet.ln_ping_target) { + old_pbuf = the_lnet.ln_ping_target; + old_ping_md = the_lnet.ln_ping_target_md; } - the_lnet.ln_ping_target_md = md_handle; - the_lnet.ln_ping_info = pinfo; + the_lnet.ln_ping_target_md = ping_mdh; + the_lnet.ln_ping_target = pbuf; lnet_net_unlock(LNET_LOCK_EX); - if (old_pinfo != NULL) { - /* unlink the old ping info */ - lnet_ping_md_unlink(old_pinfo, &old_md); - lnet_ping_info_free(old_pinfo); + if (old_pbuf) { + /* unlink and free the old ping info */ + lnet_ping_md_unlink(old_pbuf, &old_ping_md); + lnet_ping_buffer_decref(old_pbuf); } + + lnet_push_update_to_peers(0); } static void @@ -1084,34 +1376,177 @@ lnet_ping_target_fini(void) { int rc; - lnet_ping_md_unlink(the_lnet.ln_ping_info, + lnet_ping_md_unlink(the_lnet.ln_ping_target, &the_lnet.ln_ping_target_md); rc = LNetEQFree(the_lnet.ln_ping_target_eq); LASSERT(rc == 0); - lnet_ping_info_destroy(); + lnet_ping_target_destroy(); +} + +/* Resize the push target. */ +int lnet_push_target_resize(void) +{ + lnet_process_id_t id = { LNET_NID_ANY, LNET_PID_ANY }; + lnet_md_t md = { NULL }; + lnet_handle_me_t meh; + lnet_handle_md_t mdh; + lnet_handle_md_t old_mdh; + struct lnet_ping_buffer *pbuf; + struct lnet_ping_buffer *old_pbuf; + int nnis = the_lnet.ln_push_target_nnis; + int rc; + + if (nnis <= 0) { + rc = -EINVAL; + goto fail_return; + } +again: + pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS); + if (!pbuf) { + rc = -ENOMEM; + goto fail_return; + } + + rc = LNetMEAttach(LNET_RESERVED_PORTAL, id, + LNET_PROTO_PING_MATCHBITS, 0, + LNET_UNLINK, LNET_INS_AFTER, + &meh); + if (rc) { + CERROR("Can't create push target ME: %d\n", rc); + goto fail_decref_pbuf; + } + + /* initialize md content */ + md.start = &pbuf->pb_info; + md.length = LNET_PING_INFO_SIZE(nnis); + md.threshold = LNET_MD_THRESH_INF; + md.max_size = 0; + md.options = LNET_MD_OP_PUT | LNET_MD_TRUNCATE | + LNET_MD_MANAGE_REMOTE; + md.user_ptr = pbuf; + md.eq_handle = the_lnet.ln_push_target_eq; + + rc = LNetMDAttach(meh, md, LNET_RETAIN, &mdh); + if (rc) { + CERROR("Can't attach push MD: %d\n", rc); + goto fail_unlink_meh; + } + lnet_ping_buffer_addref(pbuf); + + lnet_net_lock(LNET_LOCK_EX); + old_pbuf = the_lnet.ln_push_target; + old_mdh = the_lnet.ln_push_target_md; + the_lnet.ln_push_target = pbuf; + the_lnet.ln_push_target_md = mdh; + lnet_net_unlock(LNET_LOCK_EX); + + if (old_pbuf) { + LNetMDUnlink(old_mdh); + lnet_ping_buffer_decref(old_pbuf); + } + + if (nnis < the_lnet.ln_push_target_nnis) + goto again; + + CDEBUG(D_NET, "nnis %d success\n", nnis); + + return 0; + +fail_unlink_meh: + LNetMEUnlink(meh); +fail_decref_pbuf: + lnet_ping_buffer_decref(pbuf); +fail_return: + CDEBUG(D_NET, "nnis %d error %d\n", nnis, rc); + return rc; +} + +static void lnet_push_target_event_handler(struct lnet_event *ev) +{ + struct lnet_ping_buffer *pbuf = ev->md.user_ptr; + + if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) + lnet_swap_pinginfo(pbuf); + + lnet_peer_push_event(ev); + if (ev->unlinked) + lnet_ping_buffer_decref(pbuf); +} + +/* Initialize the push target. */ +static int lnet_push_target_init(void) +{ + int rc; + + if (the_lnet.ln_push_target) + return -EALREADY; + + rc = LNetEQAlloc(0, lnet_push_target_event_handler, + &the_lnet.ln_push_target_eq); + if (rc) { + CERROR("Can't allocated push target EQ: %d\n", rc); + return rc; + } + + /* Start at the required minimum, we'll enlarge if required. */ + the_lnet.ln_push_target_nnis = LNET_INTERFACES_MIN; + + rc = lnet_push_target_resize(); + + if (rc) { + LNetEQFree(the_lnet.ln_push_target_eq); + LNetInvalidateEQHandle(&the_lnet.ln_push_target_eq); + } + + return rc; +} + +/* Clean up the push target. */ +static void lnet_push_target_fini(void) +{ + if (!the_lnet.ln_push_target) + return; + + /* Unlink and invalidate to prevent new references. */ + LNetMDUnlink(the_lnet.ln_push_target_md); + LNetInvalidateMDHandle(&the_lnet.ln_push_target_md); + + /* Wait for the unlink to complete. */ + while (lnet_ping_buffer_numref(the_lnet.ln_push_target) > 1) { + CDEBUG(D_NET, "Still waiting for ping data MD to unlink\n"); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(cfs_time_seconds(1)); + } + + lnet_ping_buffer_decref(the_lnet.ln_push_target); + the_lnet.ln_push_target = NULL; + the_lnet.ln_push_target_nnis = 0; + + LNetEQFree(the_lnet.ln_push_target_eq); + LNetInvalidateEQHandle(&the_lnet.ln_push_target_eq); } static int -lnet_ni_tq_credits(lnet_ni_t *ni) +lnet_ni_tq_credits(struct lnet_ni *ni) { int credits; LASSERT(ni->ni_ncpts >= 1); if (ni->ni_ncpts == 1) - return ni->ni_maxtxcredits; + return ni->ni_net->net_tunables.lct_max_tx_credits; - credits = ni->ni_maxtxcredits / ni->ni_ncpts; - credits = max(credits, 8 * ni->ni_peertxcredits); - credits = min(credits, ni->ni_maxtxcredits); + credits = ni->ni_net->net_tunables.lct_max_tx_credits / ni->ni_ncpts; + credits = max(credits, 8 * ni->ni_net->net_tunables.lct_peer_tx_credits); + credits = min(credits, ni->ni_net->net_tunables.lct_max_tx_credits); return credits; } static void -lnet_ni_unlink_locked(lnet_ni_t *ni) +lnet_ni_unlink_locked(struct lnet_ni *ni) { if (!list_empty(&ni->ni_cptlist)) { list_del_init(&ni->ni_cptlist); @@ -1119,37 +1554,43 @@ lnet_ni_unlink_locked(lnet_ni_t *ni) } /* move it to zombie list and nobody can find it anymore */ - LASSERT(!list_empty(&ni->ni_list)); - list_move(&ni->ni_list, &the_lnet.ln_nis_zombie); - lnet_ni_decref_locked(ni, 0); /* drop ln_nis' ref */ + LASSERT(!list_empty(&ni->ni_netlist)); + list_move(&ni->ni_netlist, &ni->ni_net->net_ni_zombie); + lnet_ni_decref_locked(ni, 0); } static void -lnet_clear_zombies_nis_locked(void) +lnet_clear_zombies_nis_locked(struct lnet_net *net) { int i; int islo; - lnet_ni_t *ni; + struct lnet_ni *ni; + struct list_head *zombie_list = &net->net_ni_zombie; - /* Now wait for the NI's I just nuked to show up on ln_zombie_nis - * and shut them down in guaranteed thread context */ + /* + * Now wait for the NIs I just nuked to show up on the zombie + * list and shut them down in guaranteed thread context + */ i = 2; - while (!list_empty(&the_lnet.ln_nis_zombie)) { + while (!list_empty(zombie_list)) { int *ref; int j; - ni = list_entry(the_lnet.ln_nis_zombie.next, - lnet_ni_t, ni_list); - list_del_init(&ni->ni_list); + ni = list_entry(zombie_list->next, + struct lnet_ni, ni_netlist); + list_del_init(&ni->ni_netlist); + /* the ni should be in deleting state. If it's not it's + * a bug */ + LASSERT(ni->ni_state == LNET_NI_STATE_DELETING); cfs_percpt_for_each(ref, j, ni->ni_refs) { if (*ref == 0) continue; /* still busy, add it back to zombie list */ - list_add(&ni->ni_list, &the_lnet.ln_nis_zombie); + list_add(&ni->ni_netlist, zombie_list); break; } - if (!list_empty(&ni->ni_list)) { + if (!list_empty(&ni->ni_netlist)) { lnet_net_unlock(LNET_LOCK_EX); ++i; if ((i & (-i)) == i) { @@ -1163,16 +1604,12 @@ lnet_clear_zombies_nis_locked(void) continue; } - ni->ni_lnd->lnd_refcount--; lnet_net_unlock(LNET_LOCK_EX); - islo = ni->ni_lnd->lnd_type == LOLND; + islo = ni->ni_net->net_lnd->lnd_type == LOLND; LASSERT(!in_interrupt()); - (ni->ni_lnd->lnd_shutdown)(ni); - - /* can't deref lnd anymore now; it might have unregistered - * itself... */ + (net->net_lnd->lnd_shutdown)(ni); if (!islo) CDEBUG(D_LNI, "Removed LNI %s\n", @@ -1184,212 +1621,155 @@ lnet_clear_zombies_nis_locked(void) } } -static void -lnet_shutdown_lndnis(void) -{ - int i; - lnet_ni_t *ni; - - /* NB called holding the global mutex */ - - /* All quiet on the API front */ - LASSERT(!the_lnet.ln_shutdown); - LASSERT(the_lnet.ln_refcount == 0); - LASSERT(list_empty(&the_lnet.ln_nis_zombie)); - - lnet_net_lock(LNET_LOCK_EX); - the_lnet.ln_shutdown = 1; /* flag shutdown */ - - /* Unlink NIs from the global table */ - while (!list_empty(&the_lnet.ln_nis)) { - ni = list_entry(the_lnet.ln_nis.next, - lnet_ni_t, ni_list); - lnet_ni_unlink_locked(ni); - } - - /* Drop the cached loopback NI. */ - if (the_lnet.ln_loni != NULL) { - lnet_ni_decref_locked(the_lnet.ln_loni, 0); - the_lnet.ln_loni = NULL; - } - - lnet_net_unlock(LNET_LOCK_EX); - - /* Clear lazy portals and drop delayed messages which hold refs - * on their lnet_msg_t::msg_rxpeer */ - for (i = 0; i < the_lnet.ln_nportals; i++) - LNetClearLazyPortal(i); - - /* Clear the peer table and wait for all peers to go (they hold refs on - * their NIs) */ - lnet_peer_tables_cleanup(NULL); - - lnet_net_lock(LNET_LOCK_EX); - - lnet_clear_zombies_nis_locked(); - the_lnet.ln_shutdown = 0; - lnet_net_unlock(LNET_LOCK_EX); -} - /* shutdown down the NI and release refcount */ static void lnet_shutdown_lndni(struct lnet_ni *ni) { int i; + struct lnet_net *net = ni->ni_net; lnet_net_lock(LNET_LOCK_EX); + ni->ni_state = LNET_NI_STATE_DELETING; lnet_ni_unlink_locked(ni); + lnet_incr_dlc_seq(); lnet_net_unlock(LNET_LOCK_EX); /* clear messages for this NI on the lazy portal */ for (i = 0; i < the_lnet.ln_nportals; i++) lnet_clear_lazy_portal(ni, i, "Shutting down NI"); - /* Do peer table cleanup for this ni */ - lnet_peer_tables_cleanup(ni); - lnet_net_lock(LNET_LOCK_EX); - lnet_clear_zombies_nis_locked(); + lnet_clear_zombies_nis_locked(net); lnet_net_unlock(LNET_LOCK_EX); } -static int -lnet_startup_lndni(struct lnet_ni *ni, struct lnet_ioctl_config_data *conf) +static void +lnet_shutdown_lndnet(struct lnet_net *net) { - struct lnet_ioctl_config_lnd_tunables *lnd_tunables = NULL; - int rc = -EINVAL; - __u32 lnd_type; - lnd_t *lnd; - struct lnet_tx_queue *tq; - int i; + struct lnet_ni *ni; - lnd_type = LNET_NETTYP(LNET_NIDNET(ni->ni_nid)); + lnet_net_lock(LNET_LOCK_EX); - LASSERT(libcfs_isknown_lnd(lnd_type)); + net->net_state = LNET_NET_STATE_DELETING; - if (lnd_type == CIBLND || lnd_type == OPENIBLND || - lnd_type == IIBLND || lnd_type == VIBLND) { - CERROR("LND %s obsoleted\n", libcfs_lnd2str(lnd_type)); - goto failed0; + list_del_init(&net->net_list); + + while (!list_empty(&net->net_ni_list)) { + ni = list_entry(net->net_ni_list.next, + struct lnet_ni, ni_netlist); + lnet_net_unlock(LNET_LOCK_EX); + lnet_shutdown_lndni(ni); + lnet_net_lock(LNET_LOCK_EX); } - /* Make sure this new NI is unique. */ + lnet_net_unlock(LNET_LOCK_EX); + + /* Do peer table cleanup for this net */ + lnet_peer_tables_cleanup(net); + lnet_net_lock(LNET_LOCK_EX); - rc = lnet_net_unique(LNET_NIDNET(ni->ni_nid), &the_lnet.ln_nis); + /* + * decrement ref count on lnd only when the entire network goes + * away + */ + net->net_lnd->lnd_refcount--; + lnet_net_unlock(LNET_LOCK_EX); - if (!rc) { - if (lnd_type == LOLND) { - lnet_ni_free(ni); - return 0; - } + lnet_net_free(net); +} - CERROR("Net %s is not unique\n", - libcfs_net2str(LNET_NIDNET(ni->ni_nid))); +static void +lnet_shutdown_lndnets(void) +{ + struct lnet_net *net; - rc = -EEXIST; - goto failed0; - } + /* NB called holding the global mutex */ - mutex_lock(&the_lnet.ln_lnd_mutex); - lnd = lnet_find_lnd_by_type(lnd_type); + /* All quiet on the API front */ + LASSERT(the_lnet.ln_state == LNET_STATE_RUNNING); + LASSERT(the_lnet.ln_refcount == 0); - if (lnd == NULL) { - mutex_unlock(&the_lnet.ln_lnd_mutex); - rc = request_module("%s", libcfs_lnd2modname(lnd_type)); - mutex_lock(&the_lnet.ln_lnd_mutex); + lnet_net_lock(LNET_LOCK_EX); + the_lnet.ln_state = LNET_STATE_STOPPING; - lnd = lnet_find_lnd_by_type(lnd_type); - if (lnd == NULL) { - mutex_unlock(&the_lnet.ln_lnd_mutex); - CERROR("Can't load LND %s, module %s, rc=%d\n", - libcfs_lnd2str(lnd_type), - libcfs_lnd2modname(lnd_type), rc); -#ifndef HAVE_MODULE_LOADING_SUPPORT - LCONSOLE_ERROR_MSG(0x104, "Your kernel must be " - "compiled with kernel module " - "loading support."); -#endif - rc = -EINVAL; - goto failed0; - } + while (!list_empty(&the_lnet.ln_nets)) { + /* + * move the nets to the zombie list to avoid them being + * picked up for new work. LONET is also included in the + * Nets that will be moved to the zombie list + */ + net = list_entry(the_lnet.ln_nets.next, + struct lnet_net, net_list); + list_move(&net->net_list, &the_lnet.ln_net_zombie); } - lnet_net_lock(LNET_LOCK_EX); - lnd->lnd_refcount++; + /* Drop the cached loopback Net. */ + if (the_lnet.ln_loni != NULL) { + lnet_ni_decref_locked(the_lnet.ln_loni, 0); + the_lnet.ln_loni = NULL; + } lnet_net_unlock(LNET_LOCK_EX); - ni->ni_lnd = lnd; + /* iterate through the net zombie list and delete each net */ + while (!list_empty(&the_lnet.ln_net_zombie)) { + net = list_entry(the_lnet.ln_net_zombie.next, + struct lnet_net, net_list); + lnet_shutdown_lndnet(net); + } - if (conf && conf->cfg_hdr.ioc_len > sizeof(*conf)) - lnd_tunables = (struct lnet_ioctl_config_lnd_tunables *)conf->cfg_bulk; + lnet_net_lock(LNET_LOCK_EX); + the_lnet.ln_state = LNET_STATE_SHUTDOWN; + lnet_net_unlock(LNET_LOCK_EX); +} - if (lnd_tunables != NULL) { - LIBCFS_ALLOC(ni->ni_lnd_tunables, - sizeof(*ni->ni_lnd_tunables)); - if (ni->ni_lnd_tunables == NULL) { - mutex_unlock(&the_lnet.ln_lnd_mutex); - rc = -ENOMEM; - goto failed0; - } - memcpy(ni->ni_lnd_tunables, lnd_tunables, - sizeof(*ni->ni_lnd_tunables)); - } +static int +lnet_startup_lndni(struct lnet_ni *ni, struct lnet_lnd_tunables *tun) +{ + int rc = -EINVAL; + struct lnet_tx_queue *tq; + int i; + struct lnet_net *net = ni->ni_net; + + mutex_lock(&the_lnet.ln_lnd_mutex); - /* If given some LND tunable parameters, parse those now to - * override the values in the NI structure. */ - if (conf) { - if (conf->cfg_config_u.cfg_net.net_peer_rtr_credits >= 0) - ni->ni_peerrtrcredits = - conf->cfg_config_u.cfg_net.net_peer_rtr_credits; - if (conf->cfg_config_u.cfg_net.net_peer_timeout >= 0) - ni->ni_peertimeout = - conf->cfg_config_u.cfg_net.net_peer_timeout; - if (conf->cfg_config_u.cfg_net.net_peer_tx_credits >= 0) - ni->ni_peertxcredits = - conf->cfg_config_u.cfg_net.net_peer_tx_credits; - if (conf->cfg_config_u.cfg_net.net_max_tx_credits >= 0) - ni->ni_maxtxcredits = - conf->cfg_config_u.cfg_net.net_max_tx_credits; + if (tun) { + memcpy(&ni->ni_lnd_tunables, tun, sizeof(*tun)); + ni->ni_lnd_tunables_set = true; } - rc = (lnd->lnd_startup)(ni); + rc = (net->net_lnd->lnd_startup)(ni); mutex_unlock(&the_lnet.ln_lnd_mutex); if (rc != 0) { LCONSOLE_ERROR_MSG(0x105, "Error %d starting up LNI %s\n", - rc, libcfs_lnd2str(lnd->lnd_type)); + rc, libcfs_lnd2str(net->net_lnd->lnd_type)); lnet_net_lock(LNET_LOCK_EX); - lnd->lnd_refcount--; + net->net_lnd->lnd_refcount--; lnet_net_unlock(LNET_LOCK_EX); goto failed0; } - LASSERT(ni->ni_peertimeout <= 0 || lnd->lnd_query != NULL); + ni->ni_state = LNET_NI_STATE_ACTIVE; - lnet_net_lock(LNET_LOCK_EX); - /* refcount for ln_nis */ - lnet_ni_addref_locked(ni, 0); - list_add_tail(&ni->ni_list, &the_lnet.ln_nis); - if (ni->ni_cpts != NULL) { - lnet_ni_addref_locked(ni, 0); - list_add_tail(&ni->ni_cptlist, &the_lnet.ln_nis_cpt); - } - - lnet_net_unlock(LNET_LOCK_EX); - - if (lnd->lnd_type == LOLND) { + /* We keep a reference on the loopback net through the loopback NI */ + if (net->net_lnd->lnd_type == LOLND) { lnet_ni_addref(ni); LASSERT(the_lnet.ln_loni == NULL); the_lnet.ln_loni = ni; + ni->ni_net->net_tunables.lct_peer_tx_credits = 0; + ni->ni_net->net_tunables.lct_peer_rtr_credits = 0; + ni->ni_net->net_tunables.lct_max_tx_credits = 0; + ni->ni_net->net_tunables.lct_peer_timeout = 0; return 0; } - if (ni->ni_peertxcredits == 0 || ni->ni_maxtxcredits == 0) { + if (ni->ni_net->net_tunables.lct_peer_tx_credits == 0 || + ni->ni_net->net_tunables.lct_max_tx_credits == 0) { LCONSOLE_ERROR_MSG(0x107, "LNI %s has no %scredits\n", - libcfs_lnd2str(lnd->lnd_type), - ni->ni_peertxcredits == 0 ? + libcfs_lnd2str(net->net_lnd->lnd_type), + ni->ni_net->net_tunables.lct_peer_tx_credits == 0 ? "" : "per-peer "); /* shutdown the NI since if we get here then it must've already * been started @@ -1404,10 +1784,15 @@ lnet_startup_lndni(struct lnet_ni *ni, struct lnet_ioctl_config_data *conf) tq->tq_credits = lnet_ni_tq_credits(ni); } + atomic_set(&ni->ni_tx_credits, + lnet_ni_tq_credits(ni) * ni->ni_ncpts); + CDEBUG(D_LNI, "Added LNI %s [%d/%d/%d/%d]\n", - libcfs_nid2str(ni->ni_nid), ni->ni_peertxcredits, + libcfs_nid2str(ni->ni_nid), + ni->ni_net->net_tunables.lct_peer_tx_credits, lnet_ni_tq_credits(ni) * LNET_CPT_NUMBER, - ni->ni_peerrtrcredits, ni->ni_peertimeout); + ni->ni_net->net_tunables.lct_peer_rtr_credits, + ni->ni_net->net_tunables.lct_peer_timeout); return 0; failed0: @@ -1416,26 +1801,219 @@ failed0: } static int -lnet_startup_lndnis(struct list_head *nilist) +lnet_startup_lndnet(struct lnet_net *net, struct lnet_lnd_tunables *tun) { - struct lnet_ni *ni; + struct lnet_ni *ni; + struct lnet_net *net_l = NULL; + struct list_head local_ni_list; int rc; int ni_count = 0; + __u32 lnd_type; + struct lnet_lnd *lnd; + int peer_timeout = + net->net_tunables.lct_peer_timeout; + int maxtxcredits = + net->net_tunables.lct_max_tx_credits; + int peerrtrcredits = + net->net_tunables.lct_peer_rtr_credits; + + INIT_LIST_HEAD(&local_ni_list); + + /* + * make sure that this net is unique. If it isn't then + * we are adding interfaces to an already existing network, and + * 'net' is just a convenient way to pass in the list. + * if it is unique we need to find the LND and load it if + * necessary. + */ + if (lnet_net_unique(net->net_id, &the_lnet.ln_nets, &net_l)) { + lnd_type = LNET_NETTYP(net->net_id); + + LASSERT(libcfs_isknown_lnd(lnd_type)); + + mutex_lock(&the_lnet.ln_lnd_mutex); + lnd = lnet_find_lnd_by_type(lnd_type); + + if (lnd == NULL) { + mutex_unlock(&the_lnet.ln_lnd_mutex); + rc = request_module("%s", libcfs_lnd2modname(lnd_type)); + mutex_lock(&the_lnet.ln_lnd_mutex); + + lnd = lnet_find_lnd_by_type(lnd_type); + if (lnd == NULL) { + mutex_unlock(&the_lnet.ln_lnd_mutex); + CERROR("Can't load LND %s, module %s, rc=%d\n", + libcfs_lnd2str(lnd_type), + libcfs_lnd2modname(lnd_type), rc); +#ifndef HAVE_MODULE_LOADING_SUPPORT + LCONSOLE_ERROR_MSG(0x104, "Your kernel must be " + "compiled with kernel module " + "loading support."); +#endif + rc = -EINVAL; + goto failed0; + } + } + + lnet_net_lock(LNET_LOCK_EX); + lnd->lnd_refcount++; + lnet_net_unlock(LNET_LOCK_EX); - while (!list_empty(nilist)) { - ni = list_entry(nilist->next, lnet_ni_t, ni_list); - list_del(&ni->ni_list); - rc = lnet_startup_lndni(ni, NULL); + net->net_lnd = lnd; + + mutex_unlock(&the_lnet.ln_lnd_mutex); + + net_l = net; + } + + /* + * net_l: if the network being added is unique then net_l + * will point to that network + * if the network being added is not unique then + * net_l points to the existing network. + * + * When we enter the loop below, we'll pick NIs off he + * network beign added and start them up, then add them to + * a local ni list. Once we've successfully started all + * the NIs then we join the local NI list (of started up + * networks) with the net_l->net_ni_list, which should + * point to the correct network to add the new ni list to + * + * If any of the new NIs fail to start up, then we want to + * iterate through the local ni list, which should include + * any NIs which were successfully started up, and shut + * them down. + * + * After than we want to delete the network being added, + * to avoid a memory leak. + */ + + /* + * When a network uses TCP bonding then all its interfaces + * must be specified when the network is first defined: the + * TCP bonding code doesn't allow for interfaces to be added + * or removed. + */ + if (net_l != net && net_l != NULL && use_tcp_bonding && + LNET_NETTYP(net_l->net_id) == SOCKLND) { + rc = -EINVAL; + goto failed0; + } + + while (!list_empty(&net->net_ni_added)) { + ni = list_entry(net->net_ni_added.next, struct lnet_ni, + ni_netlist); + list_del_init(&ni->ni_netlist); + + /* make sure that the the NI we're about to start + * up is actually unique. if it's not fail. */ + if (!lnet_ni_unique_net(&net_l->net_ni_list, + ni->ni_interfaces[0])) { + rc = -EINVAL; + goto failed1; + } + + /* adjust the pointer the parent network, just in case it + * the net is a duplicate */ + ni->ni_net = net_l; + + rc = lnet_startup_lndni(ni, tun); + + LASSERT(ni->ni_net->net_tunables.lct_peer_timeout <= 0 || + ni->ni_net->net_lnd->lnd_query != NULL); if (rc < 0) - goto failed; + goto failed1; + + lnet_ni_addref(ni); + list_add_tail(&ni->ni_netlist, &local_ni_list); ni_count++; } + lnet_net_lock(LNET_LOCK_EX); + list_splice_tail(&local_ni_list, &net_l->net_ni_list); + lnet_incr_dlc_seq(); + lnet_net_unlock(LNET_LOCK_EX); + + /* if the network is not unique then we don't want to keep + * it around after we're done. Free it. Otherwise add that + * net to the global the_lnet.ln_nets */ + if (net_l != net && net_l != NULL) { + /* + * TODO - note. currently the tunables can not be updated + * once added + */ + lnet_net_free(net); + } else { + net->net_state = LNET_NET_STATE_ACTIVE; + /* + * restore tunables after it has been overwitten by the + * lnd + */ + if (peer_timeout != -1) + net->net_tunables.lct_peer_timeout = peer_timeout; + if (maxtxcredits != -1) + net->net_tunables.lct_max_tx_credits = maxtxcredits; + if (peerrtrcredits != -1) + net->net_tunables.lct_peer_rtr_credits = peerrtrcredits; + + lnet_net_lock(LNET_LOCK_EX); + list_add_tail(&net->net_list, &the_lnet.ln_nets); + lnet_net_unlock(LNET_LOCK_EX); + } + + return ni_count; + +failed1: + /* + * shutdown the new NIs that are being started up + * free the NET being started + */ + while (!list_empty(&local_ni_list)) { + ni = list_entry(local_ni_list.next, struct lnet_ni, + ni_netlist); + + lnet_shutdown_lndni(ni); + } + +failed0: + lnet_net_free(net); + + return rc; +} + +static int +lnet_startup_lndnets(struct list_head *netlist) +{ + struct lnet_net *net; + int rc; + int ni_count = 0; + + /* + * Change to running state before bringing up the LNDs. This + * allows lnet_shutdown_lndnets() to assert that we've passed + * through here. + */ + lnet_net_lock(LNET_LOCK_EX); + the_lnet.ln_state = LNET_STATE_RUNNING; + lnet_net_unlock(LNET_LOCK_EX); + + while (!list_empty(netlist)) { + net = list_entry(netlist->next, struct lnet_net, net_list); + list_del_init(&net->net_list); + + rc = lnet_startup_lndnet(net, NULL); + + if (rc < 0) + goto failed; + + ni_count += rc; + } + return ni_count; failed: - lnet_shutdown_lndnis(); + lnet_shutdown_lndnets(); return rc; } @@ -1456,8 +2034,6 @@ int lnet_lib_init(void) lnet_assert_wire_constants(); - memset(&the_lnet, 0, sizeof(the_lnet)); - /* refer to global cfs_cpt_table for now */ the_lnet.ln_cpt_table = cfs_cpt_table; the_lnet.ln_cpt_number = cfs_cpt_number(cfs_cpt_table); @@ -1481,8 +2057,9 @@ int lnet_lib_init(void) } the_lnet.ln_refcount = 0; - LNetInvalidateHandle(&the_lnet.ln_rc_eqh); + LNetInvalidateEQHandle(&the_lnet.ln_rc_eqh); INIT_LIST_HEAD(&the_lnet.ln_lnds); + INIT_LIST_HEAD(&the_lnet.ln_net_zombie); INIT_LIST_HEAD(&the_lnet.ln_rcd_zombie); INIT_LIST_HEAD(&the_lnet.ln_rcd_deathrow); @@ -1515,7 +2092,7 @@ void lnet_lib_exit(void) while (!list_empty(&the_lnet.ln_lnds)) lnet_unregister_lnd(list_entry(the_lnet.ln_lnds.next, - lnd_t, lnd_list)); + struct lnet_lnd, lnd_list)); lnet_destroy_locks(); } @@ -1540,9 +2117,10 @@ LNetNIInit(lnet_pid_t requested_pid) int im_a_router = 0; int rc; int ni_count; - struct lnet_ping_info *pinfo; - lnet_handle_md_t md_handle; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; struct list_head net_head; + struct lnet_net *net; INIT_LIST_HEAD(&net_head); @@ -1562,8 +2140,15 @@ LNetNIInit(lnet_pid_t requested_pid) return rc; } - /* Add in the loopback network */ - if (lnet_ni_alloc(LNET_MKNET(LOLND, 0), NULL, &net_head) == NULL) { + /* create a network for Loopback network */ + net = lnet_net_alloc(LNET_MKNET(LOLND, 0), &net_head); + if (net == NULL) { + rc = -ENOMEM; + goto err_empty_list; + } + + /* Add in the loopback NI */ + if (lnet_ni_alloc(net, NULL, NULL) == NULL) { rc = -ENOMEM; goto err_empty_list; } @@ -1575,13 +2160,13 @@ LNetNIInit(lnet_pid_t requested_pid) * in this case. On cleanup in case of failure only clean up * routes if it has been loaded */ if (!the_lnet.ln_nis_from_mod_params) { - rc = lnet_parse_networks(&net_head, - lnet_get_networks()); + rc = lnet_parse_networks(&net_head, lnet_get_networks(), + use_tcp_bonding); if (rc < 0) goto err_empty_list; } - ni_count = lnet_startup_lndnis(&net_head); + ni_count = lnet_startup_lndnets(&net_head); if (ni_count < 0) { rc = ni_count; goto err_empty_list; @@ -1608,16 +2193,24 @@ LNetNIInit(lnet_pid_t requested_pid) the_lnet.ln_refcount = 1; /* Now I may use my own API functions... */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, ni_count, true); + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, ni_count, true); if (rc != 0) goto err_acceptor_stop; - lnet_ping_target_update(pinfo, md_handle); + lnet_ping_target_update(pbuf, ping_mdh); rc = lnet_router_checker_start(); if (rc != 0) goto err_stop_ping; + rc = lnet_push_target_init(); + if (rc != 0) + goto err_stop_router_checker; + + rc = lnet_peer_discovery_start(); + if (rc != 0) + goto err_destroy_push_target; + lnet_fault_init(); lnet_proc_init(); @@ -1625,6 +2218,10 @@ LNetNIInit(lnet_pid_t requested_pid) return 0; +err_destroy_push_target: + lnet_push_target_fini(); +err_stop_router_checker: + lnet_router_checker_stop(); err_stop_ping: lnet_ping_target_fini(); err_acceptor_stop: @@ -1634,17 +2231,17 @@ err_destroy_routes: if (!the_lnet.ln_nis_from_mod_params) lnet_destroy_routes(); err_shutdown_lndnis: - lnet_shutdown_lndnis(); + lnet_shutdown_lndnets(); err_empty_list: lnet_unprepare(); LASSERT(rc < 0); mutex_unlock(&the_lnet.ln_api_mutex); while (!list_empty(&net_head)) { - struct lnet_ni *ni; + struct lnet_net *net; - ni = list_entry(net_head.next, struct lnet_ni, ni_list); - list_del_init(&ni->ni_list); - lnet_ni_free(ni); + net = list_entry(net_head.next, struct lnet_net, net_list); + list_del_init(&net->net_list); + lnet_net_free(net); } return rc; } @@ -1674,6 +2271,8 @@ LNetNIFini() lnet_fault_fini(); lnet_proc_fini(); + lnet_peer_discovery_stop(); + lnet_push_target_fini(); lnet_router_checker_stop(); lnet_ping_target_fini(); @@ -1682,7 +2281,7 @@ LNetNIFini() lnet_acceptor_stop(); lnet_destroy_routes(); - lnet_shutdown_lndnis(); + lnet_shutdown_lndnets(); lnet_unprepare(); } @@ -1696,16 +2295,89 @@ EXPORT_SYMBOL(LNetNIFini); * parameters * * \param[in] ni network interface structure - * \param[out] cpt_count the number of cpts the ni is on - * \param[out] nid Network Interface ID - * \param[out] peer_timeout NI peer timeout - * \param[out] peer_tx_crdits NI peer transmit credits - * \param[out] peer_rtr_credits NI peer router credits - * \param[out] max_tx_credits NI max transmit credit - * \param[out] net_config Network configuration + * \param[out] cfg_ni NI config information + * \param[out] tun network and LND tunables + */ +static void +lnet_fill_ni_info(struct lnet_ni *ni, struct lnet_ioctl_config_ni *cfg_ni, + struct lnet_ioctl_config_lnd_tunables *tun, + struct lnet_ioctl_element_stats *stats, + __u32 tun_size) +{ + size_t min_size = 0; + int i; + + if (!ni || !cfg_ni || !tun) + return; + + if (ni->ni_interfaces[0] != NULL) { + for (i = 0; i < ARRAY_SIZE(ni->ni_interfaces); i++) { + if (ni->ni_interfaces[i] != NULL) { + strncpy(cfg_ni->lic_ni_intf[i], + ni->ni_interfaces[i], + sizeof(cfg_ni->lic_ni_intf[i])); + } + } + } + + cfg_ni->lic_nid = ni->ni_nid; + if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND) + cfg_ni->lic_status = LNET_NI_STATUS_UP; + else + cfg_ni->lic_status = ni->ni_status->ns_status; + cfg_ni->lic_tcp_bonding = use_tcp_bonding; + cfg_ni->lic_dev_cpt = ni->ni_dev_cpt; + + memcpy(&tun->lt_cmn, &ni->ni_net->net_tunables, sizeof(tun->lt_cmn)); + + if (stats) { + stats->iel_send_count = lnet_sum_stats(&ni->ni_stats, + LNET_STATS_TYPE_SEND); + stats->iel_recv_count = lnet_sum_stats(&ni->ni_stats, + LNET_STATS_TYPE_RECV); + stats->iel_drop_count = lnet_sum_stats(&ni->ni_stats, + LNET_STATS_TYPE_DROP); + } + + /* + * tun->lt_tun will always be present, but in order to be + * backwards compatible, we need to deal with the cases when + * tun->lt_tun is smaller than what the kernel has, because it + * comes from an older version of a userspace program, then we'll + * need to copy as much information as we have available space. + */ + min_size = tun_size - sizeof(tun->lt_cmn); + memcpy(&tun->lt_tun, &ni->ni_lnd_tunables, min_size); + + /* copy over the cpts */ + if (ni->ni_ncpts == LNET_CPT_NUMBER && + ni->ni_cpts == NULL) { + for (i = 0; i < ni->ni_ncpts; i++) + cfg_ni->lic_cpts[i] = i; + } else { + for (i = 0; + ni->ni_cpts != NULL && i < ni->ni_ncpts && + i < LNET_MAX_SHOW_NUM_CPT; + i++) + cfg_ni->lic_cpts[i] = ni->ni_cpts[i]; + } + cfg_ni->lic_ncpts = ni->ni_ncpts; +} + +/** + * NOTE: This is a legacy function left in the code to be backwards + * compatible with older userspace programs. It should eventually be + * removed. + * + * Grabs the ni data from the ni structure and fills the out + * parameters + * + * \param[in] ni network interface structure + * \param[out] config config information */ static void -lnet_fill_ni_info(struct lnet_ni *ni, struct lnet_ioctl_config_data *config) +lnet_fill_ni_info_legacy(struct lnet_ni *ni, + struct lnet_ioctl_config_data *config) { struct lnet_ioctl_net_config *net_config; struct lnet_ioctl_config_lnd_tunables *lnd_cfg = NULL; @@ -1732,199 +2404,574 @@ lnet_fill_ni_info(struct lnet_ni *ni, struct lnet_ioctl_config_data *config) } config->cfg_nid = ni->ni_nid; - config->cfg_config_u.cfg_net.net_peer_timeout = ni->ni_peertimeout; - config->cfg_config_u.cfg_net.net_max_tx_credits = ni->ni_maxtxcredits; - config->cfg_config_u.cfg_net.net_peer_tx_credits = ni->ni_peertxcredits; - config->cfg_config_u.cfg_net.net_peer_rtr_credits = ni->ni_peerrtrcredits; - - net_config->ni_status = ni->ni_status->ns_status; + config->cfg_config_u.cfg_net.net_peer_timeout = + ni->ni_net->net_tunables.lct_peer_timeout; + config->cfg_config_u.cfg_net.net_max_tx_credits = + ni->ni_net->net_tunables.lct_max_tx_credits; + config->cfg_config_u.cfg_net.net_peer_tx_credits = + ni->ni_net->net_tunables.lct_peer_tx_credits; + config->cfg_config_u.cfg_net.net_peer_rtr_credits = + ni->ni_net->net_tunables.lct_peer_rtr_credits; + + if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND) + net_config->ni_status = LNET_NI_STATUS_UP; + else + net_config->ni_status = ni->ni_status->ns_status; if (ni->ni_cpts) { int num_cpts = min(ni->ni_ncpts, LNET_MAX_SHOW_NUM_CPT); - for (i = 0; i < num_cpts; i++) - net_config->ni_cpts[i] = ni->ni_cpts[i]; + for (i = 0; i < num_cpts; i++) + net_config->ni_cpts[i] = ni->ni_cpts[i]; + + config->cfg_ncpts = num_cpts; + } + + /* + * See if user land tools sent in a newer and larger version + * of struct lnet_tunables than what the kernel uses. + */ + min_size = sizeof(*config) + sizeof(*net_config); + + if (config->cfg_hdr.ioc_len > min_size) + tunable_size = config->cfg_hdr.ioc_len - min_size; + + /* Don't copy too much data to user space */ + min_size = min(tunable_size, sizeof(ni->ni_lnd_tunables)); + lnd_cfg = (struct lnet_ioctl_config_lnd_tunables *)net_config->cfg_bulk; + + if (lnd_cfg && min_size) { + memcpy(&lnd_cfg->lt_tun, &ni->ni_lnd_tunables, min_size); + config->cfg_config_u.cfg_net.net_interface_count = 1; + + /* Tell user land that kernel side has less data */ + if (tunable_size > sizeof(ni->ni_lnd_tunables)) { + min_size = tunable_size - sizeof(ni->ni_lnd_tunables); + config->cfg_hdr.ioc_len -= min_size; + } + } +} + +struct lnet_ni * +lnet_get_ni_idx_locked(int idx) +{ + struct lnet_ni *ni; + struct lnet_net *net; + + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + if (idx-- == 0) + return ni; + } + } + + return NULL; +} + +struct lnet_ni * +lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev) +{ + struct lnet_ni *ni; + struct lnet_net *net = mynet; + + if (prev == NULL) { + if (net == NULL) + net = list_entry(the_lnet.ln_nets.next, struct lnet_net, + net_list); + ni = list_entry(net->net_ni_list.next, struct lnet_ni, + ni_netlist); + + return ni; + } + + if (prev->ni_netlist.next == &prev->ni_net->net_ni_list) { + /* if you reached the end of the ni list and the net is + * specified, then there are no more nis in that net */ + if (net != NULL) + return NULL; + + /* we reached the end of this net ni list. move to the + * next net */ + if (prev->ni_net->net_list.next == &the_lnet.ln_nets) + /* no more nets and no more NIs. */ + return NULL; + + /* get the next net */ + net = list_entry(prev->ni_net->net_list.next, struct lnet_net, + net_list); + /* get the ni on it */ + ni = list_entry(net->net_ni_list.next, struct lnet_ni, + ni_netlist); + + return ni; + } + + /* there are more nis left */ + ni = list_entry(prev->ni_netlist.next, struct lnet_ni, ni_netlist); + + return ni; +} + +int +lnet_get_net_config(struct lnet_ioctl_config_data *config) +{ + struct lnet_ni *ni; + int cpt; + int rc = -ENOENT; + int idx = config->cfg_count; + + cpt = lnet_net_lock_current(); + + ni = lnet_get_ni_idx_locked(idx); + + if (ni != NULL) { + rc = 0; + lnet_ni_lock(ni); + lnet_fill_ni_info_legacy(ni, config); + lnet_ni_unlock(ni); + } + + lnet_net_unlock(cpt); + return rc; +} + +int +lnet_get_ni_config(struct lnet_ioctl_config_ni *cfg_ni, + struct lnet_ioctl_config_lnd_tunables *tun, + struct lnet_ioctl_element_stats *stats, + __u32 tun_size) +{ + struct lnet_ni *ni; + int cpt; + int rc = -ENOENT; + + if (!cfg_ni || !tun || !stats) + return -EINVAL; + + cpt = lnet_net_lock_current(); + + ni = lnet_get_ni_idx_locked(cfg_ni->lic_idx); + + if (ni) { + rc = 0; + lnet_ni_lock(ni); + lnet_fill_ni_info(ni, cfg_ni, tun, stats, tun_size); + lnet_ni_unlock(ni); + } + + lnet_net_unlock(cpt); + return rc; +} + +int lnet_get_ni_stats(struct lnet_ioctl_element_msg_stats *msg_stats) +{ + struct lnet_ni *ni; + int cpt; + int rc = -ENOENT; + + if (!msg_stats) + return -EINVAL; + + cpt = lnet_net_lock_current(); + + ni = lnet_get_ni_idx_locked(msg_stats->im_idx); + + if (ni) { + lnet_usr_translate_stats(msg_stats, &ni->ni_stats); + rc = 0; + } + + lnet_net_unlock(cpt); + + return rc; +} + +static int lnet_add_net_common(struct lnet_net *net, + struct lnet_ioctl_config_lnd_tunables *tun) +{ + __u32 net_id; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; + int rc; + struct lnet_remotenet *rnet; + int net_ni_count; + int num_acceptor_nets; + + lnet_net_lock(LNET_LOCK_EX); + rnet = lnet_find_rnet_locked(net->net_id); + lnet_net_unlock(LNET_LOCK_EX); + /* + * make sure that the net added doesn't invalidate the current + * configuration LNet is keeping + */ + if (rnet) { + CERROR("Adding net %s will invalidate routing configuration\n", + libcfs_net2str(net->net_id)); + lnet_net_free(net); + return -EUSERS; + } + + /* + * make sure you calculate the correct number of slots in the ping + * buffer. Since the ping info is a flattened list of all the NIs, + * we should allocate enough slots to accomodate the number of NIs + * which will be added. + * + * since ni hasn't been configured yet, use + * lnet_get_net_ni_count_pre() which checks the net_ni_added list + */ + net_ni_count = lnet_get_net_ni_count_pre(net); + + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + net_ni_count + lnet_get_ni_count(), + false); + if (rc < 0) { + lnet_net_free(net); + return rc; + } + + if (tun) + memcpy(&net->net_tunables, + &tun->lt_cmn, sizeof(net->net_tunables)); + else + memset(&net->net_tunables, -1, sizeof(net->net_tunables)); + + /* + * before starting this network get a count of the current TCP + * networks which require the acceptor thread running. If that + * count is == 0 before we start up this network, then we'd want to + * start up the acceptor thread after starting up this network + */ + num_acceptor_nets = lnet_count_acceptor_nets(); + + net_id = net->net_id; + + rc = lnet_startup_lndnet(net, + (tun) ? &tun->lt_tun : NULL); + if (rc < 0) + goto failed; + + lnet_net_lock(LNET_LOCK_EX); + net = lnet_get_net_locked(net_id); + lnet_net_unlock(LNET_LOCK_EX); + + LASSERT(net); + + /* + * Start the acceptor thread if this is the first network + * being added that requires the thread. + */ + if (net->net_lnd->lnd_accept && num_acceptor_nets == 0) { + rc = lnet_acceptor_start(); + if (rc < 0) { + /* shutdown the net that we just started */ + CERROR("Failed to start up acceptor thread\n"); + lnet_shutdown_lndnet(net); + goto failed; + } + } + + lnet_net_lock(LNET_LOCK_EX); + lnet_peer_net_added(net); + lnet_net_unlock(LNET_LOCK_EX); + + lnet_ping_target_update(pbuf, ping_mdh); + + return 0; + +failed: + lnet_ping_md_unlink(pbuf, &ping_mdh); + lnet_ping_buffer_decref(pbuf); + return rc; +} + +static int lnet_handle_legacy_ip2nets(char *ip2nets, + struct lnet_ioctl_config_lnd_tunables *tun) +{ + struct lnet_net *net; + char *nets; + int rc; + struct list_head net_head; + + INIT_LIST_HEAD(&net_head); + + rc = lnet_parse_ip2nets(&nets, ip2nets); + if (rc < 0) + return rc; + + rc = lnet_parse_networks(&net_head, nets, use_tcp_bonding); + if (rc < 0) + return rc; + + mutex_lock(&the_lnet.ln_api_mutex); + while (!list_empty(&net_head)) { + net = list_entry(net_head.next, struct lnet_net, net_list); + list_del_init(&net->net_list); + rc = lnet_add_net_common(net, tun); + if (rc < 0) + goto out; + } + +out: + mutex_unlock(&the_lnet.ln_api_mutex); + + while (!list_empty(&net_head)) { + net = list_entry(net_head.next, struct lnet_net, net_list); + list_del_init(&net->net_list); + lnet_net_free(net); + } + return rc; +} + +int lnet_dyn_add_ni(struct lnet_ioctl_config_ni *conf) +{ + struct lnet_net *net; + struct lnet_ni *ni; + struct lnet_ioctl_config_lnd_tunables *tun = NULL; + int rc, i; + __u32 net_id; + + /* get the tunables if they are available */ + if (conf->lic_cfg_hdr.ioc_len >= + sizeof(*conf) + sizeof(*tun)) + tun = (struct lnet_ioctl_config_lnd_tunables *) + conf->lic_bulk; + + /* handle legacy ip2nets from DLC */ + if (conf->lic_legacy_ip2nets[0] != '\0') + return lnet_handle_legacy_ip2nets(conf->lic_legacy_ip2nets, + tun); + + net_id = LNET_NIDNET(conf->lic_nid); + + net = lnet_net_alloc(net_id, NULL); + if (!net) + return -ENOMEM; + + for (i = 0; i < conf->lic_ncpts; i++) { + if (conf->lic_cpts[i] >= LNET_CPT_NUMBER) + return -EINVAL; + } + + ni = lnet_ni_alloc_w_cpt_array(net, conf->lic_cpts, conf->lic_ncpts, + conf->lic_ni_intf[0]); + if (!ni) + return -ENOMEM; + + mutex_lock(&the_lnet.ln_api_mutex); + + rc = lnet_add_net_common(net, tun); + + mutex_unlock(&the_lnet.ln_api_mutex); + + return rc; +} + +int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf) +{ + struct lnet_net *net; + struct lnet_ni *ni; + __u32 net_id = LNET_NIDNET(conf->lic_nid); + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; + int rc; + int net_count; + __u32 addr; + + /* don't allow userspace to shutdown the LOLND */ + if (LNET_NETTYP(net_id) == LOLND) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + + lnet_net_lock(0); + + net = lnet_get_net_locked(net_id); + if (!net) { + CERROR("net %s not found\n", + libcfs_net2str(net_id)); + rc = -ENOENT; + goto unlock_net; + } + + addr = LNET_NIDADDR(conf->lic_nid); + if (addr == 0) { + /* remove the entire net */ + net_count = lnet_get_net_ni_count_locked(net); + + lnet_net_unlock(0); + + /* create and link a new ping info, before removing the old one */ + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + lnet_get_ni_count() - net_count, + false); + if (rc != 0) + goto unlock_api_mutex; + + lnet_shutdown_lndnet(net); + + if (lnet_count_acceptor_nets() == 0) + lnet_acceptor_stop(); + + lnet_ping_target_update(pbuf, ping_mdh); - config->cfg_ncpts = num_cpts; + goto unlock_api_mutex; } - /* - * See if user land tools sent in a newer and larger version - * of struct lnet_tunables than what the kernel uses. - */ - min_size = sizeof(*config) + sizeof(*net_config); + ni = lnet_nid2ni_locked(conf->lic_nid, 0); + if (!ni) { + CERROR("nid %s not found\n", + libcfs_nid2str(conf->lic_nid)); + rc = -ENOENT; + goto unlock_net; + } - if (config->cfg_hdr.ioc_len > min_size) - tunable_size = config->cfg_hdr.ioc_len - min_size; + net_count = lnet_get_net_ni_count_locked(net); - /* Don't copy to much data to user space */ - min_size = min(tunable_size, sizeof(*ni->ni_lnd_tunables)); - lnd_cfg = (struct lnet_ioctl_config_lnd_tunables *)net_config->cfg_bulk; + lnet_net_unlock(0); - if (ni->ni_lnd_tunables && lnd_cfg && min_size) { - memcpy(lnd_cfg, ni->ni_lnd_tunables, min_size); - config->cfg_config_u.cfg_net.net_interface_count = 1; + /* create and link a new ping info, before removing the old one */ + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + lnet_get_ni_count() - 1, false); + if (rc != 0) + goto unlock_api_mutex; - /* Tell user land that kernel side has less data */ - if (tunable_size > sizeof(*ni->ni_lnd_tunables)) { - min_size = tunable_size - sizeof(ni->ni_lnd_tunables); - config->cfg_hdr.ioc_len -= min_size; - } - } -} + lnet_shutdown_lndni(ni); -static int -lnet_get_net_config(struct lnet_ioctl_config_data *config) -{ - struct lnet_ni *ni; - struct list_head *tmp; - int idx = config->cfg_count; - int rc = -ENOENT; - int cpt, i = 0; + if (lnet_count_acceptor_nets() == 0) + lnet_acceptor_stop(); - if (unlikely(!config->cfg_bulk)) - return -EINVAL; + lnet_ping_target_update(pbuf, ping_mdh); - cpt = lnet_net_lock_current(); + /* check if the net is empty and remove it if it is */ + if (net_count == 1) + lnet_shutdown_lndnet(net); - list_for_each(tmp, &the_lnet.ln_nis) { - if (i++ != idx) - continue; + goto unlock_api_mutex; - ni = list_entry(tmp, lnet_ni_t, ni_list); - lnet_ni_lock(ni); - lnet_fill_ni_info(ni, config); - lnet_ni_unlock(ni); - rc = 0; - break; - } +unlock_net: + lnet_net_unlock(0); +unlock_api_mutex: + mutex_unlock(&the_lnet.ln_api_mutex); - lnet_net_unlock(cpt); return rc; } +/* + * lnet_dyn_add_net and lnet_dyn_del_net are now deprecated. + * They are only expected to be called for unique networks. + * That can be as a result of older DLC library + * calls. Multi-Rail DLC and beyond no longer uses these APIs. + */ int -lnet_dyn_add_ni(lnet_pid_t requested_pid, struct lnet_ioctl_config_data *conf) +lnet_dyn_add_net(struct lnet_ioctl_config_data *conf) { - char *nets = conf->cfg_config_u.cfg_net.net_intf; - struct lnet_ping_info *pinfo; - lnet_handle_md_t md_handle; - struct lnet_ni *ni; + struct lnet_net *net; struct list_head net_head; int rc; - lnet_remotenet_t *rnet; + struct lnet_ioctl_config_lnd_tunables tun; + char *nets = conf->cfg_config_u.cfg_net.net_intf; INIT_LIST_HEAD(&net_head); - /* Create a ni structure for the network string */ - rc = lnet_parse_networks(&net_head, nets); + /* Create a net/ni structures for the network string */ + rc = lnet_parse_networks(&net_head, nets, use_tcp_bonding); if (rc <= 0) return rc == 0 ? -EINVAL : rc; mutex_lock(&the_lnet.ln_api_mutex); if (rc > 1) { - rc = -EINVAL; /* only add one interface per call */ - goto failed0; - } - - ni = list_entry(net_head.next, struct lnet_ni, ni_list); - - lnet_net_lock(LNET_LOCK_EX); - rnet = lnet_find_net_locked(LNET_NIDNET(ni->ni_nid)); - lnet_net_unlock(LNET_LOCK_EX); - /* make sure that the net added doesn't invalidate the current - * configuration LNet is keeping */ - if (rnet != NULL) { - CERROR("Adding net %s will invalidate routing configuration\n", - nets); - rc = -EUSERS; - goto failed0; + rc = -EINVAL; /* only add one network per call */ + goto out_unlock_clean; } - rc = lnet_ping_info_setup(&pinfo, &md_handle, 1 + lnet_get_ni_count(), - false); - if (rc != 0) - goto failed0; - - list_del_init(&ni->ni_list); + net = list_entry(net_head.next, struct lnet_net, net_list); + list_del_init(&net->net_list); - rc = lnet_startup_lndni(ni, conf); - if (rc != 0) - goto failed1; + LASSERT(lnet_net_unique(net->net_id, &the_lnet.ln_nets, NULL)); - if (ni->ni_lnd->lnd_accept != NULL) { - rc = lnet_acceptor_start(); - if (rc < 0) { - /* shutdown the ni that we just started */ - CERROR("Failed to start up acceptor thread\n"); - lnet_shutdown_lndni(ni); - goto failed1; - } - } + memset(&tun, 0, sizeof(tun)); - lnet_ping_target_update(pinfo, md_handle); - mutex_unlock(&the_lnet.ln_api_mutex); + tun.lt_cmn.lct_peer_timeout = + conf->cfg_config_u.cfg_net.net_peer_timeout; + tun.lt_cmn.lct_peer_tx_credits = + conf->cfg_config_u.cfg_net.net_peer_tx_credits; + tun.lt_cmn.lct_peer_rtr_credits = + conf->cfg_config_u.cfg_net.net_peer_rtr_credits; + tun.lt_cmn.lct_max_tx_credits = + conf->cfg_config_u.cfg_net.net_max_tx_credits; - return 0; + rc = lnet_add_net_common(net, &tun); -failed1: - lnet_ping_md_unlink(pinfo, &md_handle); - lnet_ping_info_free(pinfo); -failed0: +out_unlock_clean: mutex_unlock(&the_lnet.ln_api_mutex); while (!list_empty(&net_head)) { - ni = list_entry(net_head.next, struct lnet_ni, ni_list); - list_del_init(&ni->ni_list); - lnet_ni_free(ni); + /* net_head list is empty in success case */ + net = list_entry(net_head.next, struct lnet_net, net_list); + list_del_init(&net->net_list); + lnet_net_free(net); } return rc; } int -lnet_dyn_del_ni(__u32 net) +lnet_dyn_del_net(__u32 net_id) { - lnet_ni_t *ni; - struct lnet_ping_info *pinfo; - lnet_handle_md_t md_handle; + struct lnet_net *net; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; int rc; + int net_ni_count; /* don't allow userspace to shutdown the LOLND */ - if (LNET_NETTYP(net) == LOLND) + if (LNET_NETTYP(net_id) == LOLND) return -EINVAL; mutex_lock(&the_lnet.ln_api_mutex); - /* create and link a new ping info, before removing the old one */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, - lnet_get_ni_count() - 1, false); - if (rc != 0) - goto out; - ni = lnet_net2ni(net); - if (ni == NULL) { + lnet_net_lock(0); + + net = lnet_get_net_locked(net_id); + if (net == NULL) { + lnet_net_unlock(0); rc = -EINVAL; - goto failed; + goto out; } - /* decrement the reference counter taken by lnet_net2ni() */ - lnet_ni_decref_locked(ni, 0); + net_ni_count = lnet_get_net_ni_count_locked(net); - lnet_shutdown_lndni(ni); + lnet_net_unlock(0); + + /* create and link a new ping info, before removing the old one */ + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + lnet_get_ni_count() - net_ni_count, false); + if (rc != 0) + goto out; + + lnet_shutdown_lndnet(net); - if (lnet_count_acceptor_nis() == 0) + if (lnet_count_acceptor_nets() == 0) lnet_acceptor_stop(); - lnet_ping_target_update(pinfo, md_handle); - goto out; -failed: - lnet_ping_md_unlink(pinfo, &md_handle); - lnet_ping_info_free(pinfo); + lnet_ping_target_update(pbuf, ping_mdh); + out: mutex_unlock(&the_lnet.ln_api_mutex); return rc; } +void lnet_incr_dlc_seq(void) +{ + atomic_inc(&lnet_dlc_seq_no); +} + +__u32 lnet_get_dlc_seq_locked(void) +{ + return atomic_read(&lnet_dlc_seq_no); +} + /** * LNet ioctl handler. * @@ -1934,8 +2981,8 @@ LNetCtl(unsigned int cmd, void *arg) { struct libcfs_ioctl_data *data = arg; struct lnet_ioctl_config_data *config; - lnet_process_id_t id = {0}; - lnet_ni_t *ni; + struct lnet_process_id id = {0}; + struct lnet_ni *ni; int rc; BUILD_BUG_ON(sizeof(struct lnet_ioctl_net_config) + @@ -1988,13 +3035,56 @@ LNetCtl(unsigned int cmd, void *arg) if (config->cfg_hdr.ioc_len < sizeof(*config)) return -EINVAL; - return lnet_get_route(config->cfg_count, - &config->cfg_net, - &config->cfg_config_u.cfg_route.rtr_hop, - &config->cfg_nid, - &config->cfg_config_u.cfg_route.rtr_flags, - &config->cfg_config_u.cfg_route. + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_route(config->cfg_count, + &config->cfg_net, + &config->cfg_config_u.cfg_route.rtr_hop, + &config->cfg_nid, + &config->cfg_config_u.cfg_route.rtr_flags, + &config->cfg_config_u.cfg_route. rtr_priority); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + + case IOC_LIBCFS_GET_LOCAL_NI: { + struct lnet_ioctl_config_ni *cfg_ni; + struct lnet_ioctl_config_lnd_tunables *tun = NULL; + struct lnet_ioctl_element_stats *stats; + __u32 tun_size; + + cfg_ni = arg; + + /* get the tunables if they are available */ + if (cfg_ni->lic_cfg_hdr.ioc_len < + sizeof(*cfg_ni) + sizeof(*stats) + sizeof(*tun)) + return -EINVAL; + + stats = (struct lnet_ioctl_element_stats *) + cfg_ni->lic_bulk; + tun = (struct lnet_ioctl_config_lnd_tunables *) + (cfg_ni->lic_bulk + sizeof(*stats)); + + tun_size = cfg_ni->lic_cfg_hdr.ioc_len - sizeof(*cfg_ni) - + sizeof(*stats); + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_ni_config(cfg_ni, tun, stats, tun_size); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + } + + case IOC_LIBCFS_GET_LOCAL_NI_MSG_STATS: { + struct lnet_ioctl_element_msg_stats *msg_stats = arg; + + if (msg_stats->im_hdr.ioc_len != sizeof(*msg_stats)) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_ni_stats(msg_stats); + mutex_unlock(&the_lnet.ln_api_mutex); + + return rc; + } case IOC_LIBCFS_GET_NET: { size_t total = sizeof(*config) + @@ -2004,7 +3094,10 @@ LNetCtl(unsigned int cmd, void *arg) if (config->cfg_hdr.ioc_len < total) return -EINVAL; - return lnet_get_net_config(config); + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_net_config(config); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; } case IOC_LIBCFS_GET_LNET_STATS: @@ -2014,7 +3107,9 @@ LNetCtl(unsigned int cmd, void *arg) if (lnet_stats->st_hdr.ioc_len < sizeof(*lnet_stats)) return -EINVAL; + mutex_lock(&the_lnet.ln_api_mutex); lnet_counters_get(&lnet_stats->st_cntrs); + mutex_unlock(&the_lnet.ln_api_mutex); return 0; } @@ -2050,6 +3145,26 @@ LNetCtl(unsigned int cmd, void *arg) mutex_unlock(&the_lnet.ln_api_mutex); return rc; + case IOC_LIBCFS_SET_NUMA_RANGE: { + struct lnet_ioctl_set_value *numa; + numa = arg; + if (numa->sv_hdr.ioc_len != sizeof(*numa)) + return -EINVAL; + lnet_net_lock(LNET_LOCK_EX); + lnet_numa_range = numa->sv_value; + lnet_net_unlock(LNET_LOCK_EX); + return 0; + } + + case IOC_LIBCFS_GET_NUMA_RANGE: { + struct lnet_ioctl_set_value *numa; + numa = arg; + if (numa->sv_hdr.ioc_len != sizeof(*numa)) + return -EINVAL; + numa->sv_value = lnet_numa_range; + return 0; + } + case IOC_LIBCFS_GET_BUF: { struct lnet_ioctl_pool_cfg *pool_cfg; size_t total = sizeof(*config) + sizeof(*pool_cfg); @@ -2060,7 +3175,38 @@ LNetCtl(unsigned int cmd, void *arg) return -EINVAL; pool_cfg = (struct lnet_ioctl_pool_cfg *)config->cfg_bulk; - return lnet_get_rtr_pool_cfg(config->cfg_count, pool_cfg); + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_rtr_pool_cfg(config->cfg_count, pool_cfg); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + } + + case IOC_LIBCFS_ADD_PEER_NI: { + struct lnet_ioctl_peer_cfg *cfg = arg; + + if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg)) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_add_peer_ni(cfg->prcfg_prim_nid, + cfg->prcfg_cfg_nid, + cfg->prcfg_mr); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + } + + case IOC_LIBCFS_DEL_PEER_NI: { + struct lnet_ioctl_peer_cfg *cfg = arg; + + if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg)) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_del_peer_ni(cfg->prcfg_prim_nid, + cfg->prcfg_cfg_nid); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; } case IOC_LIBCFS_GET_PEER_INFO: { @@ -2069,7 +3215,8 @@ LNetCtl(unsigned int cmd, void *arg) if (peer_info->pr_hdr.ioc_len < sizeof(*peer_info)) return -EINVAL; - return lnet_get_peer_info( + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_peer_ni_info( peer_info->pr_count, &peer_info->pr_nid, peer_info->pr_lnd_u.pr_peer_credits.cr_aliveness, @@ -2078,8 +3225,40 @@ LNetCtl(unsigned int cmd, void *arg) &peer_info->pr_lnd_u.pr_peer_credits.cr_ni_peer_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_rtr_credits, - &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_min_rtr_credits, + &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_min_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_tx_qnob); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + } + + case IOC_LIBCFS_GET_PEER_NI: { + struct lnet_ioctl_peer_cfg *cfg = arg; + + if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg)) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_peer_info(&cfg->prcfg_prim_nid, + &cfg->prcfg_cfg_nid, + &cfg->prcfg_count, + &cfg->prcfg_mr, + &cfg->prcfg_size, + (void __user *)cfg->prcfg_bulk); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; + } + + case IOC_LIBCFS_GET_PEER_LIST: { + struct lnet_ioctl_peer_cfg *cfg = arg; + + if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg)) + return -EINVAL; + + mutex_lock(&the_lnet.ln_api_mutex); + rc = lnet_get_peer_list(&cfg->prcfg_count, &cfg->prcfg_size, + (lnet_process_id_t __user *)cfg->prcfg_bulk); + mutex_unlock(&the_lnet.ln_api_mutex); + return rc; } case IOC_LIBCFS_NOTIFY_ROUTER: { @@ -2115,32 +3294,78 @@ LNetCtl(unsigned int cmd, void *arg) id.nid = data->ioc_nid; id.pid = data->ioc_u32[0]; - /* Don't block longer than 2 minutes */ - if (data->ioc_u32[1] > 120 * MSEC_PER_SEC) - return -EINVAL; - - /* If timestamp is negative then disable timeout */ - if ((s32)data->ioc_u32[1] < 0) - timeout = MAX_SCHEDULE_TIMEOUT; + /* If timeout is negative then set default of 3 minutes */ + if (((s32)data->ioc_u32[1] <= 0) || + data->ioc_u32[1] > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC)) + timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC); else timeout = msecs_to_jiffies(data->ioc_u32[1]); rc = lnet_ping(id, timeout, data->ioc_pbuf1, - data->ioc_plen1 / sizeof(lnet_process_id_t)); + data->ioc_plen1 / sizeof(struct lnet_process_id)); + if (rc < 0) return rc; + data->ioc_count = rc; return 0; } + + case IOC_LIBCFS_PING_PEER: { + struct lnet_ioctl_ping_data *ping = arg; + struct lnet_peer *lp; + signed long timeout; + + /* If timeout is negative then set default of 3 minutes */ + if (((s32)ping->op_param) <= 0 || + ping->op_param > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC)) + timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC); + else + timeout = msecs_to_jiffies(ping->op_param); + + rc = lnet_ping(ping->ping_id, timeout, + ping->ping_buf, + ping->ping_count); + if (rc < 0) + return rc; + + lp = lnet_find_peer(ping->ping_id.nid); + if (lp) { + ping->ping_id.nid = lp->lp_primary_nid; + ping->mr_info = lnet_peer_is_multi_rail(lp); + } + ping->ping_count = rc; + return 0; + } + + case IOC_LIBCFS_DISCOVER: { + struct lnet_ioctl_ping_data *discover = arg; + struct lnet_peer *lp; + + rc = lnet_discover(discover->ping_id, discover->op_param, + discover->ping_buf, + discover->ping_count); + if (rc < 0) + return rc; + lp = lnet_find_peer(discover->ping_id.nid); + if (lp) { + discover->ping_id.nid = lp->lp_primary_nid; + discover->mr_info = lnet_peer_is_multi_rail(lp); + } + + discover->ping_count = rc; + return 0; + } + default: - ni = lnet_net2ni(data->ioc_net); + ni = lnet_net2ni_addref(data->ioc_net); if (ni == NULL) return -EINVAL; - if (ni->ni_lnd->lnd_ctl == NULL) + if (ni->ni_net->net_lnd->lnd_ctl == NULL) rc = -EINVAL; else - rc = ni->ni_lnd->lnd_ctl(ni, cmd, arg); + rc = ni->ni_net->net_lnd->lnd_ctl(ni, cmd, arg); lnet_ni_decref(ni); return rc; @@ -2149,28 +3374,57 @@ LNetCtl(unsigned int cmd, void *arg) } EXPORT_SYMBOL(LNetCtl); -void LNetDebugPeer(lnet_process_id_t id) +void LNetDebugPeer(struct lnet_process_id id) { lnet_debug_peer(id.nid); } EXPORT_SYMBOL(LNetDebugPeer); /** - * Retrieve the lnet_process_id_t ID of LNet interface at \a index. Note that - * all interfaces share a same PID, as requested by LNetNIInit(). + * Determine if the specified peer \a nid is on the local node. + * + * \param nid peer nid to check + * + * \retval true If peer NID is on the local node. + * \retval false If peer NID is not on the local node. + */ +bool LNetIsPeerLocal(lnet_nid_t nid) +{ + struct lnet_net *net; + struct lnet_ni *ni; + int cpt; + + cpt = lnet_net_lock_current(); + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + if (ni->ni_nid == nid) { + lnet_net_unlock(cpt); + return true; + } + } + } + lnet_net_unlock(cpt); + + return false; +} +EXPORT_SYMBOL(LNetIsPeerLocal); + +/** + * Retrieve the struct lnet_process_id ID of LNet interface at \a index. + * Note that all interfaces share a same PID, as requested by LNetNIInit(). * * \param index Index of the interface to look up. * \param id On successful return, this location will hold the - * lnet_process_id_t ID of the interface. + * struct lnet_process_id ID of the interface. * * \retval 0 If an interface exists at \a index. * \retval -ENOENT If no interface has been found. */ int -LNetGetId(unsigned int index, lnet_process_id_t *id) +LNetGetId(unsigned int index, struct lnet_process_id *id) { struct lnet_ni *ni; - struct list_head *tmp; + struct lnet_net *net; int cpt; int rc = -ENOENT; @@ -2178,16 +3432,16 @@ LNetGetId(unsigned int index, lnet_process_id_t *id) cpt = lnet_net_lock_current(); - list_for_each(tmp, &the_lnet.ln_nis) { - if (index-- != 0) - continue; - - ni = list_entry(tmp, lnet_ni_t, ni_list); + list_for_each_entry(net, &the_lnet.ln_nets, net_list) { + list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { + if (index-- != 0) + continue; - id->nid = ni->ni_nid; - id->pid = the_lnet.ln_pid; - rc = 0; - break; + id->nid = ni->ni_nid; + id->pid = the_lnet.ln_pid; + rc = 0; + break; + } } lnet_net_unlock(cpt); @@ -2195,61 +3449,47 @@ LNetGetId(unsigned int index, lnet_process_id_t *id) } EXPORT_SYMBOL(LNetGetId); -/** - * Print a string representation of handle \a h into buffer \a str of - * \a len bytes. - */ -void -LNetSnprintHandle(char *str, int len, lnet_handle_any_t h) -{ - snprintf(str, len, "%#llx", h.cookie); -} -EXPORT_SYMBOL(LNetSnprintHandle); - -static int lnet_ping(lnet_process_id_t id, signed long timeout, - lnet_process_id_t __user *ids, int n_ids) +static int lnet_ping(struct lnet_process_id id, signed long timeout, + struct lnet_process_id __user *ids, int n_ids) { - lnet_handle_eq_t eqh; - lnet_handle_md_t mdh; - lnet_event_t event; - lnet_md_t md = { NULL }; - int which; - int unlinked = 0; - int replied = 0; + struct lnet_handle_eq eqh; + struct lnet_handle_md mdh; + struct lnet_event event; + struct lnet_md md = { NULL }; + int which; + int unlinked = 0; + int replied = 0; const signed long a_long_time = msecs_to_jiffies(60 * MSEC_PER_SEC); - int infosz; - struct lnet_ping_info *info; - lnet_process_id_t tmpid; - int i; - int nob; - int rc; - int rc2; - sigset_t blocked; - - infosz = offsetof(struct lnet_ping_info, pi_ni[n_ids]); + struct lnet_ping_buffer *pbuf; + struct lnet_process_id tmpid; + int i; + int nob; + int rc; + int rc2; + sigset_t blocked; /* n_ids limit is arbitrary */ - if (n_ids <= 0 || n_ids > 20 || id.nid == LNET_NID_ANY) + if (n_ids <= 0 || n_ids > lnet_interfaces_max || id.nid == LNET_NID_ANY) return -EINVAL; if (id.pid == LNET_PID_ANY) id.pid = LNET_PID_LUSTRE; - LIBCFS_ALLOC(info, infosz); - if (info == NULL) + pbuf = lnet_ping_buffer_alloc(n_ids, GFP_NOFS); + if (!pbuf) return -ENOMEM; /* NB 2 events max (including any unlink event) */ rc = LNetEQAlloc(2, LNET_EQ_HANDLER_NONE, &eqh); if (rc != 0) { CERROR("Can't allocate EQ: %d\n", rc); - goto out_0; + goto fail_ping_buffer_decref; } /* initialize md content */ - md.start = info; - md.length = infosz; - md.threshold = 2; /*GET/REPLY*/ + md.start = &pbuf->pb_info; + md.length = LNET_PING_INFO_SIZE(n_ids); + md.threshold = 2; /* GET/REPLY */ md.max_size = 0; md.options = LNET_MD_TRUNCATE; md.user_ptr = NULL; @@ -2258,7 +3498,7 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, rc = LNetMDBind(md, LNET_UNLINK, &mdh); if (rc != 0) { CERROR("Can't bind MD: %d\n", rc); - goto out_1; + goto fail_free_eq; } rc = LNetGet(LNET_NID_ANY, mdh, id, @@ -2267,7 +3507,6 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, if (rc != 0) { /* Don't CERROR; this could be deliberate! */ - rc2 = LNetMDUnlink(mdh); LASSERT(rc2 == 0); @@ -2315,7 +3554,6 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, replied = 1; rc = event.mlength; } - } while (rc2 <= 0 || !event.unlinked); if (!replied) { @@ -2323,68 +3561,146 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, CWARN("%s: Unexpected rc >= 0 but no reply!\n", libcfs_id2str(id)); rc = -EIO; - goto out_1; + goto fail_free_eq; } nob = rc; - LASSERT(nob >= 0 && nob <= infosz); + LASSERT(nob >= 0 && nob <= LNET_PING_INFO_SIZE(n_ids)); - rc = -EPROTO; /* if I can't parse... */ + rc = -EPROTO; /* if I can't parse... */ if (nob < 8) { - /* can't check magic/version */ CERROR("%s: ping info too short %d\n", libcfs_id2str(id), nob); - goto out_1; + goto fail_free_eq; } - if (info->pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) { - lnet_swap_pinginfo(info); - } else if (info->pi_magic != LNET_PROTO_PING_MAGIC) { + if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) { + lnet_swap_pinginfo(pbuf); + } else if (pbuf->pb_info.pi_magic != LNET_PROTO_PING_MAGIC) { CERROR("%s: Unexpected magic %08x\n", - libcfs_id2str(id), info->pi_magic); - goto out_1; + libcfs_id2str(id), pbuf->pb_info.pi_magic); + goto fail_free_eq; } - if ((info->pi_features & LNET_PING_FEAT_NI_STATUS) == 0) { + if ((pbuf->pb_info.pi_features & LNET_PING_FEAT_NI_STATUS) == 0) { CERROR("%s: ping w/o NI status: 0x%x\n", - libcfs_id2str(id), info->pi_features); - goto out_1; + libcfs_id2str(id), pbuf->pb_info.pi_features); + goto fail_free_eq; } - if (nob < offsetof(struct lnet_ping_info, pi_ni[0])) { - CERROR("%s: Short reply %d(%d min)\n", libcfs_id2str(id), - nob, (int)offsetof(struct lnet_ping_info, pi_ni[0])); - goto out_1; + if (nob < LNET_PING_INFO_SIZE(0)) { + CERROR("%s: Short reply %d(%d min)\n", + libcfs_id2str(id), + nob, (int)LNET_PING_INFO_SIZE(0)); + goto fail_free_eq; } - if (info->pi_nnis < n_ids) - n_ids = info->pi_nnis; + if (pbuf->pb_info.pi_nnis < n_ids) + n_ids = pbuf->pb_info.pi_nnis; - if (nob < offsetof(struct lnet_ping_info, pi_ni[n_ids])) { - CERROR("%s: Short reply %d(%d expected)\n", libcfs_id2str(id), - nob, (int)offsetof(struct lnet_ping_info, pi_ni[n_ids])); - goto out_1; + if (nob < LNET_PING_INFO_SIZE(n_ids)) { + CERROR("%s: Short reply %d(%d expected)\n", + libcfs_id2str(id), + nob, (int)LNET_PING_INFO_SIZE(n_ids)); + goto fail_free_eq; } - rc = -EFAULT; /* If I SEGV... */ + rc = -EFAULT; /* if I segv in copy_to_user()... */ memset(&tmpid, 0, sizeof(tmpid)); for (i = 0; i < n_ids; i++) { - tmpid.pid = info->pi_pid; - tmpid.nid = info->pi_ni[i].ns_nid; + tmpid.pid = pbuf->pb_info.pi_pid; + tmpid.nid = pbuf->pb_info.pi_ni[i].ns_nid; if (copy_to_user(&ids[i], &tmpid, sizeof(tmpid))) - goto out_1; + goto fail_free_eq; } - rc = info->pi_nnis; + rc = pbuf->pb_info.pi_nnis; - out_1: + fail_free_eq: rc2 = LNetEQFree(eqh); if (rc2 != 0) CERROR("rc2 %d\n", rc2); LASSERT(rc2 == 0); - out_0: - LIBCFS_FREE(info, infosz); + fail_ping_buffer_decref: + lnet_ping_buffer_decref(pbuf); + return rc; +} + +static int +lnet_discover(lnet_process_id_t id, __u32 force, lnet_process_id_t __user *ids, + int n_ids) +{ + struct lnet_peer_ni *lpni; + struct lnet_peer_ni *p; + struct lnet_peer *lp; + lnet_process_id_t *buf; + int cpt; + int i; + int rc; + int max_intf = lnet_interfaces_max; + + if (n_ids <= 0 || + id.nid == LNET_NID_ANY || + n_ids > max_intf) + return -EINVAL; + + if (id.pid == LNET_PID_ANY) + id.pid = LNET_PID_LUSTRE; + + LIBCFS_ALLOC(buf, n_ids * sizeof(*buf)); + if (!buf) + return -ENOMEM; + + cpt = lnet_net_lock_current(); + lpni = lnet_nid2peerni_locked(id.nid, LNET_NID_ANY, cpt); + if (IS_ERR(lpni)) { + rc = PTR_ERR(lpni); + goto out; + } + + /* + * Clearing the NIDS_UPTODATE flag ensures the peer will + * be discovered, provided discovery has not been disabled. + */ + lp = lpni->lpni_peer_net->lpn_peer; + spin_lock(&lp->lp_lock); + lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE; + /* If the force flag is set, force a PING and PUSH as well. */ + if (force) + lp->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH; + spin_unlock(&lp->lp_lock); + rc = lnet_discover_peer_locked(lpni, cpt, true); + if (rc) + goto out_decref; + + /* Peer may have changed. */ + lp = lpni->lpni_peer_net->lpn_peer; + if (lp->lp_nnis < n_ids) + n_ids = lp->lp_nnis; + + i = 0; + p = NULL; + while ((p = lnet_get_next_peer_ni_locked(lp, NULL, p)) != NULL) { + buf[i].pid = id.pid; + buf[i].nid = p->lpni_nid; + if (++i >= n_ids) + break; + } + + lnet_net_unlock(cpt); + + rc = -EFAULT; + if (copy_to_user(ids, buf, n_ids * sizeof(*buf))) + goto out_relock; + rc = n_ids; +out_relock: + lnet_net_lock(cpt); +out_decref: + lnet_peer_ni_decref_locked(lpni); +out: + lnet_net_unlock(cpt); + return rc; }