X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Finclude%2Flnet%2Flib-types.h;h=7528c3c6189fceb5903f1284375562b6a32e5a38;hp=588ea0029381fec460b5c9fc167923c4f35acdd3;hb=d54afb86116c0640d7a201571b337042c87a3e40;hpb=76adbed805e71995d521d1a26e1e3d93f3dfd7b7 diff --git a/lnet/include/lnet/lib-types.h b/lnet/include/lnet/lib-types.h index 588ea00..7528c3c 100644 --- a/lnet/include/lnet/lib-types.h +++ b/lnet/include/lnet/lib-types.h @@ -23,7 +23,7 @@ * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2012, 2016, Intel Corporation. + * Copyright (c) 2012, 2017, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -44,36 +44,44 @@ #include #include +#include #include -#include +#include +#include /* Max payload size */ -#ifndef CONFIG_LNET_MAX_PAYLOAD -# error "CONFIG_LNET_MAX_PAYLOAD must be defined in config.h" -#endif +#define LNET_MAX_PAYLOAD LNET_MTU -#define LNET_MAX_PAYLOAD CONFIG_LNET_MAX_PAYLOAD -#if (LNET_MAX_PAYLOAD < LNET_MTU) -# error "LNET_MAX_PAYLOAD too small - error in configure --with-max-payload-mb" -#elif (LNET_MAX_PAYLOAD > (PAGE_SIZE * LNET_MAX_IOV)) -# error "LNET_MAX_PAYLOAD too large - error in configure --with-max-payload-mb" -#endif +#define LNET_MAX_IOV (LNET_MAX_PAYLOAD >> PAGE_SHIFT) + +/* + * This is the maximum health value. + * All local and peer NIs created have their health default to this value. + */ +#define LNET_MAX_HEALTH_VALUE 1000 /* forward refs */ struct lnet_libmd; -typedef struct lnet_msg { +struct lnet_msg { struct list_head msg_activelist; struct list_head msg_list; /* Q for credits/MD */ - lnet_process_id_t msg_target; + struct lnet_process_id msg_target; /* Primary NID of the source. */ lnet_nid_t msg_initiator; /* where is it from, it's only for building event */ lnet_nid_t msg_from; __u32 msg_type; + /* + * hold parameters in case message is with held due + * to discovery + */ + lnet_nid_t msg_src_nid_param; + lnet_nid_t msg_rtr_nid_param; + /* committed for sending */ unsigned int msg_tx_committed:1; /* CPT # this message committed for sending */ @@ -118,46 +126,45 @@ typedef struct lnet_msg { struct kvec *msg_iov; lnet_kiov_t *msg_kiov; - lnet_event_t msg_ev; - lnet_hdr_t msg_hdr; -} lnet_msg_t; - + struct lnet_event msg_ev; + struct lnet_hdr msg_hdr; +}; -typedef struct lnet_libhandle { +struct lnet_libhandle { struct list_head lh_hash_chain; __u64 lh_cookie; -} lnet_libhandle_t; +}; #define lh_entry(ptr, type, member) \ ((type *)((char *)(ptr)-(char *)(&((type *)0)->member))) -typedef struct lnet_eq { +struct lnet_eq { struct list_head eq_list; - lnet_libhandle_t eq_lh; - lnet_seq_t eq_enq_seq; - lnet_seq_t eq_deq_seq; + struct lnet_libhandle eq_lh; + unsigned long eq_enq_seq; + unsigned long eq_deq_seq; unsigned int eq_size; lnet_eq_handler_t eq_callback; - lnet_event_t *eq_events; + struct lnet_event *eq_events; int **eq_refs; /* percpt refcount for EQ */ -} lnet_eq_t; +}; -typedef struct lnet_me { +struct lnet_me { struct list_head me_list; - lnet_libhandle_t me_lh; - lnet_process_id_t me_match_id; + struct lnet_libhandle me_lh; + struct lnet_process_id me_match_id; unsigned int me_portal; unsigned int me_pos; /* hash offset in mt_hash */ __u64 me_match_bits; __u64 me_ignore_bits; - lnet_unlink_t me_unlink; + enum lnet_unlink me_unlink; struct lnet_libmd *me_md; -} lnet_me_t; +}; -typedef struct lnet_libmd { +struct lnet_libmd { struct list_head md_list; - lnet_libhandle_t md_lh; - lnet_me_t *md_me; + struct lnet_libhandle md_lh; + struct lnet_me *md_me; char *md_start; unsigned int md_offset; unsigned int md_length; @@ -168,23 +175,24 @@ typedef struct lnet_libmd { unsigned int md_flags; unsigned int md_niov; /* # frags at end of struct */ void *md_user_ptr; - lnet_eq_t *md_eq; + struct lnet_eq *md_eq; + struct lnet_handle_md md_bulk_handle; union { struct kvec iov[LNET_MAX_IOV]; lnet_kiov_t kiov[LNET_MAX_IOV]; } md_iov; -} lnet_libmd_t; +}; #define LNET_MD_FLAG_ZOMBIE (1 << 0) #define LNET_MD_FLAG_AUTO_UNLINK (1 << 1) #define LNET_MD_FLAG_ABORTED (1 << 2) -typedef struct { +struct lnet_test_peer { /* info about peers we are trying to fail */ struct list_head tp_list; /* ln_test_peers */ lnet_nid_t tp_nid; /* matching nid */ unsigned int tp_threshold; /* # failures to simulate */ -} lnet_test_peer_t; +}; #define LNET_COOKIE_TYPE_MD 1 #define LNET_COOKIE_TYPE_ME 2 @@ -195,8 +203,7 @@ typedef struct { struct lnet_ni; /* forward ref */ struct socket; -typedef struct lnet_lnd -{ +struct lnet_lnd { /* fields managed by portals */ struct list_head lnd_list; /* stash in the LND table */ int lnd_refcount; /* # active instances */ @@ -224,14 +231,15 @@ typedef struct lnet_lnd * and 'private' is the 'private' passed to lnet_parse(). Return * non-zero for immediate failure, otherwise complete later with * lnet_finalize() */ - int (*lnd_send)(struct lnet_ni *ni, void *private, lnet_msg_t *msg); + int (*lnd_send)(struct lnet_ni *ni, void *private, + struct lnet_msg *msg); /* Start receiving 'mlen' bytes of payload data, skipping the following * 'rlen' - 'mlen' bytes. 'private' is the 'private' passed to * lnet_parse(). Return non-zero for immedaite failure, otherwise * complete later with lnet_finalize(). This also gives back a receive * credit if the LND does flow control. */ - int (*lnd_recv)(struct lnet_ni *ni, void *private, lnet_msg_t *msg, + int (*lnd_recv)(struct lnet_ni *ni, void *private, struct lnet_msg *msg, int delayed, unsigned int niov, struct kvec *iov, lnet_kiov_t *kiov, unsigned int offset, unsigned int mlen, unsigned int rlen); @@ -242,24 +250,18 @@ typedef struct lnet_lnd * for success and do NOT give back a receive credit; that has to wait * until lnd_recv() gets called. On failure return < 0 and * release resources; lnd_recv() will not be called. */ - int (*lnd_eager_recv)(struct lnet_ni *ni, void *private, lnet_msg_t *msg, - void **new_privatep); + int (*lnd_eager_recv)(struct lnet_ni *ni, void *private, + struct lnet_msg *msg, void **new_privatep); /* notification of peer health */ void (*lnd_notify)(struct lnet_ni *ni, lnet_nid_t peer, int alive); /* query of peer aliveness */ - void (*lnd_query)(struct lnet_ni *ni, lnet_nid_t peer, cfs_time_t *when); + void (*lnd_query)(struct lnet_ni *ni, lnet_nid_t peer, time64_t *when); /* accept a new connection */ int (*lnd_accept)(struct lnet_ni *ni, struct socket *sock); -} lnd_t; - -typedef struct lnet_ni_status { - lnet_nid_t ns_nid; - __u32 ns_status; - __u32 ns_unused; -} WIRE_ATTR lnet_ni_status_t; +}; struct lnet_tx_queue { int tq_credits; /* # tx credits free */ @@ -292,10 +294,24 @@ enum lnet_ni_state { LNET_NI_STATE_DELETING }; +enum lnet_stats_type { + LNET_STATS_TYPE_SEND = 0, + LNET_STATS_TYPE_RECV, + LNET_STATS_TYPE_DROP +}; + +struct lnet_comm_count { + atomic_t co_get_count; + atomic_t co_put_count; + atomic_t co_reply_count; + atomic_t co_ack_count; + atomic_t co_hello_count; +}; + struct lnet_element_stats { - atomic_t send_count; - atomic_t recv_count; - atomic_t drop_count; + struct lnet_comm_count el_send_stats; + struct lnet_comm_count el_recv_stats; + struct lnet_comm_count el_drop_stats; }; struct lnet_net { @@ -327,7 +343,7 @@ struct lnet_net { bool net_tunables_set; /* procedural interface */ - lnd_t *net_lnd; + struct lnet_lnd *net_lnd; /* list of NIs on this net */ struct list_head net_ni_list; @@ -342,7 +358,7 @@ struct lnet_net { enum lnet_net_state net_state; }; -typedef struct lnet_ni { +struct lnet_ni { /* chain on the lnet_net structure */ struct list_head ni_netlist; @@ -373,13 +389,13 @@ typedef struct lnet_ni { int **ni_refs; /* when I was last alive */ - long ni_last_alive; + time64_t ni_last_alive; /* pointer to parent network */ struct lnet_net *ni_net; /* my health status */ - lnet_ni_status_t *ni_status; + struct lnet_ni_status *ni_status; /* NI FSM */ enum lnet_ni_state ni_state; @@ -400,47 +416,57 @@ typedef struct lnet_ni { __u32 ni_seq; /* + * health value + * initialized to LNET_MAX_HEALTH_VALUE + * Value is decremented every time we fail to send a message over + * this NI because of a NI specific failure. + * Value is incremented if we successfully send a message. + */ + atomic_t ni_healthv; + + /* * equivalent interfaces to use * This is an array because socklnd bonding can still be configured */ - char *ni_interfaces[LNET_MAX_INTERFACES]; + char *ni_interfaces[LNET_INTERFACES_NUM]; struct net *ni_net_ns; /* original net namespace */ -} lnet_ni_t; +}; #define LNET_PROTO_PING_MATCHBITS 0x8000000000000000LL -/* NB: value of these features equal to LNET_PROTO_PING_VERSION_x - * of old LNet, so there shouldn't be any compatibility issue */ -#define LNET_PING_FEAT_INVAL (0) /* no feature */ -#define LNET_PING_FEAT_BASE (1 << 0) /* just a ping */ -#define LNET_PING_FEAT_NI_STATUS (1 << 1) /* return NI status */ -#define LNET_PING_FEAT_RTE_DISABLED (1 << 2) /* Routing enabled */ +/* + * Descriptor of a ping info buffer: keep a separate indicator of the + * size and a reference count. The type is used both as a source and + * sink of data, so we need to keep some information outside of the + * area that may be overwritten by network data. + */ +struct lnet_ping_buffer { + int pb_nnis; + atomic_t pb_refcnt; + struct lnet_ping_info pb_info; +}; -#define LNET_PING_FEAT_MASK (LNET_PING_FEAT_BASE | \ - LNET_PING_FEAT_NI_STATUS) +#define LNET_PING_BUFFER_SIZE(NNIDS) \ + offsetof(struct lnet_ping_buffer, pb_info.pi_ni[NNIDS]) +#define LNET_PING_BUFFER_LONI(PBUF) ((PBUF)->pb_info.pi_ni[0].ns_nid) +#define LNET_PING_BUFFER_SEQNO(PBUF) ((PBUF)->pb_info.pi_ni[0].ns_status) -typedef struct lnet_ping_info { - __u32 pi_magic; - __u32 pi_features; - lnet_pid_t pi_pid; - __u32 pi_nnis; - struct lnet_ni_status pi_ni[0]; -} WIRE_ATTR lnet_ping_info_t; +#define LNET_PING_INFO_TO_BUFFER(PINFO) \ + container_of((PINFO), struct lnet_ping_buffer, pb_info) /* router checker data, per router */ -#define LNET_MAX_RTR_NIS 16 -#define LNET_PINGINFO_SIZE offsetof(struct lnet_ping_info, pi_ni[LNET_MAX_RTR_NIS]) -typedef struct { +struct lnet_rc_data { /* chain on the_lnet.ln_zombie_rcd or ln_deathrow_rcd */ struct list_head rcd_list; - lnet_handle_md_t rcd_mdh; /* ping buffer MD */ + struct lnet_handle_md rcd_mdh; /* ping buffer MD */ struct lnet_peer_ni *rcd_gateway; /* reference to gateway */ - struct lnet_ping_info *rcd_pinginfo; /* ping buffer */ -} lnet_rc_data_t; + struct lnet_ping_buffer *rcd_pingbuffer;/* ping buffer */ + int rcd_nnis; /* desired size of buffer */ +}; struct lnet_peer_ni { - /* chain on peer_net */ - struct list_head lpni_on_peer_net_list; + /* chain on lpn_peer_nis */ + struct list_head lpni_peer_nis; /* chain on remote peer list */ struct list_head lpni_on_remote_peer_ni_list; /* chain on peer hash */ @@ -480,15 +506,15 @@ struct lnet_peer_ni { /* # times router went dead<->alive. Protected with lpni_lock */ int lpni_alive_count; /* time of last aliveness news */ - cfs_time_t lpni_timestamp; + time64_t lpni_timestamp; /* time of last ping attempt */ - cfs_time_t lpni_ping_timestamp; + time64_t lpni_ping_timestamp; /* != 0 if ping reply expected */ - cfs_time_t lpni_ping_deadline; + time64_t lpni_ping_deadline; /* when I was last alive */ - cfs_time_t lpni_last_alive; + time64_t lpni_last_alive; /* when lpni_ni was queried last time */ - cfs_time_t lpni_last_query; + time64_t lpni_last_query; /* network peer is on */ struct lnet_net *lpni_net; /* peer's NID */ @@ -497,6 +523,8 @@ struct lnet_peer_ni { atomic_t lpni_refcount; /* CPT this peer attached on */ int lpni_cpt; + /* state flags -- protected by lpni_lock */ + unsigned lpni_state; /* # refs from lnet_route_t::lr_gateway */ int lpni_rtr_refcount; /* sequence number used to round robin over peer nis within a net */ @@ -509,31 +537,139 @@ struct lnet_peer_ni { unsigned int lpni_ping_feats; /* routes on this peer */ struct list_head lpni_routes; - /* array of preferred local nids */ - lnet_nid_t *lpni_pref_nids; + /* preferred local nids: if only one, use lpni_pref.nid */ + union lpni_pref { + lnet_nid_t nid; + lnet_nid_t *nids; + } lpni_pref; /* number of preferred NIDs in lnpi_pref_nids */ __u32 lpni_pref_nnids; /* router checker state */ - lnet_rc_data_t *lpni_rcd; + struct lnet_rc_data *lpni_rcd; }; +/* Preferred path added due to traffic on non-MR peer_ni */ +#define LNET_PEER_NI_NON_MR_PREF (1 << 0) + struct lnet_peer { - /* chain on global peer list */ - struct list_head lp_on_lnet_peer_list; + /* chain on pt_peer_list */ + struct list_head lp_peer_list; /* list of peer nets */ struct list_head lp_peer_nets; + /* list of messages pending discovery*/ + struct list_head lp_dc_pendq; + /* primary NID of the peer */ lnet_nid_t lp_primary_nid; - /* peer is Multi-Rail enabled peer */ - bool lp_multi_rail; + /* CPT of peer_table */ + int lp_cpt; + + /* number of NIDs on this peer */ + int lp_nnis; + + /* reference count */ + atomic_t lp_refcount; + + /* lock protecting peer state flags */ + spinlock_t lp_lock; + + /* peer state flags */ + unsigned lp_state; + + /* buffer for data pushed by peer */ + struct lnet_ping_buffer *lp_data; + + /* MD handle for ping in progress */ + struct lnet_handle_md lp_ping_mdh; + + /* MD handle for push in progress */ + struct lnet_handle_md lp_push_mdh; + + /* number of NIDs for sizing push data */ + int lp_data_nnis; + + /* NI config sequence number of peer */ + __u32 lp_peer_seqno; + + /* Local NI config sequence number acked by peer */ + __u32 lp_node_seqno; + + /* Local NI config sequence number sent to peer */ + __u32 lp_node_seqno_sent; + + /* Ping error encountered during discovery. */ + int lp_ping_error; + + /* Push error encountered during discovery. */ + int lp_push_error; + + /* Error encountered during discovery. */ + int lp_dc_error; + + /* time it was put on the ln_dc_working queue */ + time64_t lp_last_queued; + + /* link on discovery-related lists */ + struct list_head lp_dc_list; + + /* tasks waiting on discovery of this peer */ + wait_queue_head_t lp_dc_waitq; }; +/* + * The status flags in lp_state. Their semantics have chosen so that + * lp_state can be zero-initialized. + * + * A peer is marked MULTI_RAIL in two cases: it was configured using DLC + * as multi-rail aware, or the LNET_PING_FEAT_MULTI_RAIL bit was set. + * + * A peer is marked NO_DISCOVERY if the LNET_PING_FEAT_DISCOVERY bit was + * NOT set when the peer was pinged by discovery. + */ +#define LNET_PEER_MULTI_RAIL (1 << 0) /* Multi-rail aware */ +#define LNET_PEER_NO_DISCOVERY (1 << 1) /* Peer disabled discovery */ +/* + * A peer is marked CONFIGURED if it was configured by DLC. + * + * In addition, a peer is marked DISCOVERED if it has fully passed + * through Peer Discovery. + * + * When Peer Discovery is disabled, the discovery thread will mark + * peers REDISCOVER to indicate that they should be re-examined if + * discovery is (re)enabled on the node. + * + * A peer that was created as the result of inbound traffic will not + * be marked at all. + */ +#define LNET_PEER_CONFIGURED (1 << 2) /* Configured via DLC */ +#define LNET_PEER_DISCOVERED (1 << 3) /* Peer was discovered */ +#define LNET_PEER_REDISCOVER (1 << 4) /* Discovery was disabled */ +/* + * A peer is marked DISCOVERING when discovery is in progress. + * The other flags below correspond to stages of discovery. + */ +#define LNET_PEER_DISCOVERING (1 << 5) /* Discovering */ +#define LNET_PEER_DATA_PRESENT (1 << 6) /* Remote peer data present */ +#define LNET_PEER_NIDS_UPTODATE (1 << 7) /* Remote peer info uptodate */ +#define LNET_PEER_PING_SENT (1 << 8) /* Waiting for REPLY to Ping */ +#define LNET_PEER_PUSH_SENT (1 << 9) /* Waiting for ACK of Push */ +#define LNET_PEER_PING_FAILED (1 << 10) /* Ping send failure */ +#define LNET_PEER_PUSH_FAILED (1 << 11) /* Push send failure */ +/* + * A ping can be forced as a way to fix up state, or as a manual + * intervention by an admin. + * A push can be forced in circumstances that would normally not + * allow for one to happen. + */ +#define LNET_PEER_FORCE_PING (1 << 12) /* Forced Ping */ +#define LNET_PEER_FORCE_PUSH (1 << 13) /* Forced Push */ + struct lnet_peer_net { - /* chain on peer block */ - struct list_head lpn_on_peer_list; + /* chain on lp_peer_nets */ + struct list_head lpn_peer_nets; /* list of peer_nis on this network */ struct list_head lpn_peer_nis; @@ -543,28 +679,49 @@ struct lnet_peer_net { /* Net ID */ __u32 lpn_net_id; + + /* reference count */ + atomic_t lpn_refcount; }; /* peer hash size */ #define LNET_PEER_HASH_BITS 9 #define LNET_PEER_HASH_SIZE (1 << LNET_PEER_HASH_BITS) -/* peer hash table */ +/* + * peer hash table - one per CPT + * + * protected by lnet_net_lock/EX for update + * pt_version + * pt_number + * pt_hash[...] + * pt_peer_list + * pt_peers + * protected by pt_zombie_lock: + * pt_zombie_list + * pt_zombies + * + * pt_zombie lock nests inside lnet_net_lock + */ struct lnet_peer_table { int pt_version; /* /proc validity stamp */ - atomic_t pt_number; /* # peers extant */ + int pt_number; /* # peers_ni extant */ struct list_head *pt_hash; /* NID->peer hash */ - struct list_head pt_zombie_list; /* zombie peers */ - int pt_zombies; /* # zombie peers */ + struct list_head pt_peer_list; /* peers */ + int pt_peers; /* # peers */ + struct list_head pt_zombie_list; /* zombie peer_ni */ + int pt_zombies; /* # zombie peers_ni */ spinlock_t pt_zombie_lock; /* protect list and count */ }; /* peer aliveness is enabled only on routers for peers in a network where the - * lnet_ni_t::ni_peertimeout has been set to a positive value */ + * struct lnet_ni::ni_peertimeout has been set to a positive value + */ #define lnet_peer_aliveness_enabled(lp) (the_lnet.ln_routing != 0 && \ - (lp)->lpni_net->net_tunables.lct_peer_timeout > 0) + ((lp)->lpni_net) && \ + (lp)->lpni_net->net_tunables.lct_peer_timeout > 0) -typedef struct { +struct lnet_route { struct list_head lr_list; /* chain on net */ struct list_head lr_gwlist; /* chain on gateway */ struct lnet_peer_ni *lr_gateway; /* router node */ @@ -573,27 +730,29 @@ typedef struct { unsigned int lr_downis; /* number of down NIs */ __u32 lr_hops; /* how far I am */ unsigned int lr_priority; /* route priority */ -} lnet_route_t; +}; #define LNET_REMOTE_NETS_HASH_DEFAULT (1U << 7) #define LNET_REMOTE_NETS_HASH_MAX (1U << 16) #define LNET_REMOTE_NETS_HASH_SIZE (1 << the_lnet.ln_remote_nets_hbits) -typedef struct { +struct lnet_remotenet { /* chain on ln_remote_nets_hash */ struct list_head lrn_list; /* routes to me */ struct list_head lrn_routes; /* my net number */ __u32 lrn_net; -} lnet_remotenet_t; +}; /** lnet message has credit and can be submitted to lnd for send/receive */ #define LNET_CREDIT_OK 0 /** lnet message is waiting for credit */ #define LNET_CREDIT_WAIT 1 +/** lnet message is waiting for discovery */ +#define LNET_DC_WAIT 2 -typedef struct { +struct lnet_rtrbufpool { /* my free buffer pool */ struct list_head rbp_bufs; /* messages blocking for a buffer */ @@ -608,17 +767,17 @@ typedef struct { int rbp_credits; /* low water mark */ int rbp_mincredits; -} lnet_rtrbufpool_t; +}; -typedef struct { +struct lnet_rtrbuf { struct list_head rb_list; /* chain on rbp_bufs */ - lnet_rtrbufpool_t *rb_pool; /* owning pool */ + struct lnet_rtrbufpool *rb_pool; /* owning pool */ lnet_kiov_t rb_kiov[0]; /* the buffer space */ -} lnet_rtrbuf_t; +}; #define LNET_PEER_HASHSIZE 503 /* prime! */ -enum { +enum lnet_match_flags { /* Didn't match anything */ LNET_MATCHMD_NONE = (1 << 0), /* Matched OK */ @@ -631,7 +790,7 @@ enum { LNET_MATCHMD_FINISH = (LNET_MATCHMD_OK | LNET_MATCHMD_DROP), }; -/* Options for lnet_portal_t::ptl_options */ +/* Options for struct lnet_portal::ptl_options */ #define LNET_PTL_LAZY (1 << 0) #define LNET_PTL_MATCH_UNIQUE (1 << 1) /* unique match, for RDMA */ #define LNET_PTL_MATCH_WILDCARD (1 << 2) /* wildcard match, request portal */ @@ -639,7 +798,7 @@ enum { /* parameter for matching operations (GET, PUT) */ struct lnet_match_info { __u64 mi_mbits; - lnet_process_id_t mi_id; + struct lnet_process_id mi_id; unsigned int mi_cpt; unsigned int mi_opc; unsigned int mi_portal; @@ -684,7 +843,7 @@ struct lnet_match_table { /* dispatch routed PUT message by hashing source NID for wildcard portals */ #define LNET_PTL_ROTOR_HASH_RT 3 -typedef struct lnet_portal { +struct lnet_portal { spinlock_t ptl_lock; unsigned int ptl_index; /* portal ID, reserved */ /* flags on this portal: lazy, unique... */ @@ -701,7 +860,7 @@ typedef struct lnet_portal { int ptl_mt_nmaps; /* array of active entries' cpu-partition-id */ int ptl_mt_maps[0]; -} lnet_portal_t; +}; #define LNET_LH_HASH_BITS 12 #define LNET_LH_HASH_SIZE (1ULL << LNET_LH_HASH_BITS) @@ -727,13 +886,22 @@ struct lnet_msg_container { void **msc_finalizers; }; +/* Peer Discovery states */ +#define LNET_DC_STATE_SHUTDOWN 0 /* not started */ +#define LNET_DC_STATE_RUNNING 1 /* started up OK */ +#define LNET_DC_STATE_STOPPING 2 /* telling thread to stop */ + /* Router Checker states */ #define LNET_RC_STATE_SHUTDOWN 0 /* not started */ #define LNET_RC_STATE_RUNNING 1 /* started up OK */ #define LNET_RC_STATE_STOPPING 2 /* telling thread to stop */ -typedef struct -{ +/* LNet states */ +#define LNET_STATE_SHUTDOWN 0 /* not started */ +#define LNET_STATE_RUNNING 1 /* started up OK */ +#define LNET_STATE_STOPPING 2 /* telling thread to stop */ + +struct lnet { /* CPU partition table of LNet */ struct cfs_cpt_table *ln_cpt_table; /* number of CPTs in ln_cpt_table */ @@ -745,7 +913,7 @@ typedef struct /* # portals */ int ln_nportals; /* the vector of portals */ - lnet_portal_t **ln_portals; + struct lnet_portal **ln_portals; /* percpt ME containers */ struct lnet_res_container **ln_me_containers; /* percpt MD container */ @@ -762,10 +930,8 @@ typedef struct struct cfs_percpt_lock *ln_net_lock; /* percpt message containers for active/finalizing/freed message */ struct lnet_msg_container **ln_msg_containers; - lnet_counters_t **ln_counters; + struct lnet_counters **ln_counters; struct lnet_peer_table **ln_peer_tables; - /* list of configured or discovered peers */ - struct list_head ln_peers; /* list of peer nis not on a local network */ struct list_head ln_remote_peer_ni_list; /* failure simulation */ @@ -778,6 +944,10 @@ typedef struct struct lnet_ni *ln_loni; /* network zombie list */ struct list_head ln_net_zombie; + /* resend messages list */ + struct list_head ln_msg_resend; + /* spin lock to protect the msg resend list */ + spinlock_t ln_msg_resend_lock; /* remote networks with routes to them */ struct list_head *ln_remote_nets_hash; @@ -788,16 +958,50 @@ typedef struct /* validity stamp */ __u64 ln_routers_version; /* percpt router buffer pools */ - lnet_rtrbufpool_t **ln_rtrpools; + struct lnet_rtrbufpool **ln_rtrpools; + + /* + * Ping target / Push source + * + * The ping target and push source share a single buffer. The + * ln_ping_target is protected against concurrent updates by + * ln_api_mutex. + */ + struct lnet_handle_md ln_ping_target_md; + struct lnet_handle_eq ln_ping_target_eq; + struct lnet_ping_buffer *ln_ping_target; + atomic_t ln_ping_target_seqno; - lnet_handle_md_t ln_ping_target_md; - lnet_handle_eq_t ln_ping_target_eq; - struct lnet_ping_info *ln_ping_info; + /* + * Push Target + * + * ln_push_nnis contains the desired size of the push target. + * The lnet_net_lock is used to handle update races. The old + * buffer may linger a while after it has been unlinked, in + * which case the event handler cleans up. + */ + struct lnet_handle_eq ln_push_target_eq; + struct lnet_handle_md ln_push_target_md; + struct lnet_ping_buffer *ln_push_target; + int ln_push_target_nnis; + + /* discovery event queue handle */ + struct lnet_handle_eq ln_dc_eqh; + /* discovery requests */ + struct list_head ln_dc_request; + /* discovery working list */ + struct list_head ln_dc_working; + /* discovery expired list */ + struct list_head ln_dc_expired; + /* discovery thread wait queue */ + wait_queue_head_t ln_dc_waitq; + /* discovery startup/shutdown state */ + int ln_dc_state; /* router checker startup/shutdown state */ int ln_rc_state; /* router checker's event queue */ - lnet_handle_eq_t ln_rc_eqh; + struct lnet_handle_eq ln_rc_eqh; /* rcd still pending on net */ struct list_head ln_rcd_deathrow; /* rcd ready for free */ @@ -811,8 +1015,8 @@ typedef struct int ln_niinit_self; /* LNetNIInit/LNetNIFini counter */ int ln_refcount; - /* shutdown in progress */ - int ln_shutdown; + /* SHUTDOWN/RUNNING/STOPPING */ + int ln_state; int ln_routing; /* am I a router? */ lnet_pid_t ln_pid; /* requested pid */ @@ -835,6 +1039,6 @@ typedef struct * the list, the router checker will sleep on this queue. when * routes are added the thread will wake up */ wait_queue_head_t ln_rc_waitq; -} lnet_t; +}; #endif