X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Finclude%2Flnet%2Flib-lnet.h;h=176c9a2b3385bbe1c037c045f389242c989ff3c4;hp=6db8a5d763baaaeebac3d315ea21f12d3a5a9673;hb=d123c47a18adbf5665ed63d99c53117b84db9ec8;hpb=257c0debc71ed7c496d55547ad2ee88cd9d546a1 diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h index 6db8a5d..176c9a2 100644 --- a/lnet/include/lnet/lib-lnet.h +++ b/lnet/include/lnet/lib-lnet.h @@ -74,9 +74,10 @@ extern struct lnet the_lnet; /* THE network */ /** exclusive lock */ #define LNET_LOCK_EX CFS_PERCPT_LOCK_EX -/* default timeout */ +/* default timeout and credits */ #define DEFAULT_PEER_TIMEOUT 180 -#define LNET_LND_DEFAULT_TIMEOUT 5 +#define DEFAULT_PEER_CREDITS 8 +#define DEFAULT_CREDITS 256 #ifdef HAVE_KERN_SOCK_GETNAME_2ARGS #define lnet_kernel_getpeername(sock, addr, addrlen) \ @@ -92,11 +93,12 @@ extern struct lnet the_lnet; /* THE network */ /* * kernel 5.3: commit ef11db3310e272d3d8dbe8739e0770820dd20e52 + * kernel 4.18.0-193.el8: * added in_dev_for_each_ifa_rtnl and in_dev_for_each_ifa_rcu * and removed for_ifa and endfor_ifa. * Use the _rntl variant as the current locking is rtnl. */ -#ifdef in_dev_for_each_ifa_rtnl +#ifdef HAVE_IN_DEV_FOR_EACH_IFA_RTNL #define DECLARE_CONST_IN_IFADDR(ifa) const struct in_ifaddr *ifa #define endfor_ifa(in_dev) #else @@ -210,9 +212,66 @@ lnet_net_lock_current(void) extern struct kmem_cache *lnet_mes_cachep; /* MEs kmem_cache */ extern struct kmem_cache *lnet_small_mds_cachep; /* <= LNET_SMALL_MD_SIZE bytes * MDs kmem_cache */ +extern struct kmem_cache *lnet_udsp_cachep; extern struct kmem_cache *lnet_rspt_cachep; extern struct kmem_cache *lnet_msg_cachep; +static inline bool +lnet_ni_set_status_locked(struct lnet_ni *ni, __u32 status) +__must_hold(&ni->ni_lock) +{ + bool update = false; + + if (ni->ni_status && ni->ni_status->ns_status != status) { + CDEBUG(D_NET, "ni %s status changed from %#x to %#x\n", + libcfs_nid2str(ni->ni_nid), + ni->ni_status->ns_status, status); + ni->ni_status->ns_status = status; + update = true; + } + + return update; +} + +static inline bool +lnet_ni_set_status(struct lnet_ni *ni, __u32 status) +{ + bool update; + + lnet_ni_lock(ni); + update = lnet_ni_set_status_locked(ni, status); + lnet_ni_unlock(ni); + + return update; +} + +static inline void lnet_md_wait_handling(struct lnet_libmd *md, int cpt) +{ + wait_queue_head_t *wq = __var_waitqueue(md); +#ifdef HAVE_WAIT_QUEUE_ENTRY + struct wait_bit_queue_entry entry; + wait_queue_entry_t *wqe = &entry.wq_entry; +#else + struct wait_bit_queue entry; + wait_queue_entry_t *wqe = &entry.wait; +#endif + init_wait_var_entry(&entry, md, 0); + prepare_to_wait_event(wq, wqe, TASK_IDLE); + if (md->md_flags & LNET_MD_FLAG_HANDLING) { + /* Race with unlocked call to ->md_handler. + * It is safe to drop the res_lock here as the + * caller has only just claimed it. + */ + lnet_res_unlock(cpt); + schedule(); + /* Cannot check md now, it might be freed. Caller + * must reclaim reference and check. + */ + lnet_res_lock(cpt); + } + finish_wait(wq, wqe); +} + static inline void lnet_md_free(struct lnet_libmd *md) { @@ -375,7 +434,7 @@ lnet_msg_alloc(void) { struct lnet_msg *msg; - msg = kmem_cache_alloc(lnet_msg_cachep, GFP_NOFS | __GFP_ZERO); + msg = kmem_cache_zalloc(lnet_msg_cachep, GFP_NOFS); return (msg); } @@ -392,7 +451,7 @@ lnet_rspt_alloc(int cpt) { struct lnet_rsp_tracker *rspt; - rspt = kmem_cache_alloc(lnet_rspt_cachep, GFP_NOFS | __GFP_ZERO); + rspt = kmem_cache_zalloc(lnet_rspt_cachep, GFP_NOFS); if (rspt) { lnet_net_lock(cpt); the_lnet.ln_counters[cpt]->lct_health.lch_rst_alloc++; @@ -455,11 +514,14 @@ struct lnet_net *lnet_get_net_locked(__u32 net_id); int lnet_lib_init(void); void lnet_lib_exit(void); +extern unsigned int lnet_response_tracking; extern unsigned lnet_transaction_timeout; extern unsigned lnet_retry_count; +extern unsigned int lnet_lnd_timeout; extern unsigned int lnet_numa_range; extern unsigned int lnet_health_sensitivity; extern unsigned int lnet_recovery_interval; +extern unsigned int lnet_recovery_limit; extern unsigned int lnet_peer_discovery_disabled; extern unsigned int lnet_drop_asym_route; extern unsigned int router_sensitivity_percentage; @@ -487,13 +549,21 @@ int lnet_get_rtr_pool_cfg(int idx, struct lnet_ioctl_pool_cfg *pool_cfg); struct lnet_ni *lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev); struct lnet_ni *lnet_get_ni_idx_locked(int idx); +int lnet_get_net_healthv_locked(struct lnet_net *net); extern int libcfs_ioctl_getdata(struct libcfs_ioctl_hdr **hdr_pp, struct libcfs_ioctl_hdr __user *uparam); extern int lnet_get_peer_list(__u32 *countp, __u32 *sizep, struct lnet_process_id __user *ids); extern void lnet_peer_ni_set_healthv(lnet_nid_t nid, int value, bool all); -extern void lnet_peer_ni_add_to_recoveryq_locked(struct lnet_peer_ni *lpni); +extern void lnet_peer_ni_add_to_recoveryq_locked(struct lnet_peer_ni *lpni, + struct list_head *queue, + time64_t now); +extern int lnet_peer_add_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid); +extern void lnet_peer_clr_pref_nids(struct lnet_peer_ni *lpni); +extern int lnet_peer_del_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid); +void lnet_peer_ni_set_selection_priority(struct lnet_peer_ni *lpni, + __u32 priority); void lnet_router_debugfs_init(void); void lnet_router_debugfs_fini(void); @@ -512,6 +582,8 @@ int lnet_dyn_add_ni(struct lnet_ioctl_config_ni *conf); int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf); int lnet_clear_lazy_portal(struct lnet_ni *ni, int portal, char *reason); struct lnet_net *lnet_get_net_locked(__u32 net_id); +void lnet_net_clr_pref_rtrs(struct lnet_net *net); +int lnet_net_add_pref_rtr(struct lnet_net *net, lnet_nid_t gw_nid); int lnet_islocalnid(lnet_nid_t nid); int lnet_islocalnet(__u32 net); @@ -609,6 +681,7 @@ void lnet_set_reply_msg_len(struct lnet_ni *ni, struct lnet_msg *msg, void lnet_detach_rsp_tracker(struct lnet_libmd *md, int cpt); void lnet_clean_zombie_rstqs(void); +bool lnet_md_discarded(struct lnet_libmd *md); void lnet_finalize(struct lnet_msg *msg, int rc); bool lnet_send_error_simulation(struct lnet_msg *msg, enum lnet_msg_hstatus *hstatus); @@ -626,7 +699,6 @@ int lnet_msg_containers_create(void); char *lnet_health_error2str(enum lnet_msg_hstatus hstatus); char *lnet_msgtyp2str(int type); -void lnet_print_hdr(struct lnet_hdr *hdr); int lnet_fail_nid(lnet_nid_t nid, unsigned int threshold); /** \addtogroup lnet_fault_simulation @{ */ @@ -649,14 +721,21 @@ bool lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg); /** @} lnet_fault_simulation */ void lnet_counters_get_common(struct lnet_counters_common *common); -void lnet_counters_get(struct lnet_counters *counters); +int lnet_counters_get(struct lnet_counters *counters); void lnet_counters_reset(void); +static inline void +lnet_ni_set_sel_priority_locked(struct lnet_ni *ni, __u32 priority) +{ + ni->ni_sel_priority = priority; +} -unsigned int lnet_iov_nob(unsigned int niov, struct kvec *iov); -int lnet_extract_iov(int dst_niov, struct kvec *dst, - int src_niov, struct kvec *src, - unsigned int offset, unsigned int len); +static inline void +lnet_net_set_sel_priority_locked(struct lnet_net *net, __u32 priority) +{ + net->net_sel_priority = priority; +} +unsigned int lnet_iov_nob(unsigned int niov, struct kvec *iov); unsigned int lnet_kiov_nob(unsigned int niov, struct bio_vec *iov); int lnet_extract_kiov(int dst_niov, struct bio_vec *dst, int src_niov, struct bio_vec *src, @@ -680,17 +759,6 @@ void lnet_copy_kiov2kiov(unsigned int ndkiov, struct bio_vec *dkiov, unsigned int soffset, unsigned int nob); static inline void -lnet_copy_iov2flat(int dlen, void *dest, unsigned int doffset, - unsigned int nsiov, struct kvec *siov, unsigned int soffset, - unsigned int nob) -{ - struct kvec diov = { .iov_base = dest, .iov_len = dlen }; - - lnet_copy_iov2iov(1, &diov, doffset, - nsiov, siov, soffset, nob); -} - -static inline void lnet_copy_kiov2flat(int dlen, void *dest, unsigned int doffset, unsigned int nsiov, struct bio_vec *skiov, unsigned int soffset, unsigned int nob) @@ -702,16 +770,6 @@ lnet_copy_kiov2flat(int dlen, void *dest, unsigned int doffset, } static inline void -lnet_copy_flat2iov(unsigned int ndiov, struct kvec *diov, unsigned int doffset, - int slen, void *src, unsigned int soffset, - unsigned int nob) -{ - struct kvec siov = { .iov_base = src, .iov_len = slen }; - lnet_copy_iov2iov(ndiov, diov, doffset, - 1, &siov, soffset, nob); -} - -static inline void lnet_copy_flat2kiov(unsigned int ndiov, struct bio_vec *dkiov, unsigned int doffset, int slen, void *src, unsigned int soffset, unsigned int nob) @@ -732,10 +790,10 @@ unsigned int lnet_get_lnd_timeout(void); void lnet_register_lnd(const struct lnet_lnd *lnd); void lnet_unregister_lnd(const struct lnet_lnd *lnd); -struct socket *lnet_connect(lnet_nid_t peer_nid, int interface, __u32 peer_ip, - int peer_port, struct net *ns); +struct socket *lnet_connect(lnet_nid_t peer_nid, int interface, + struct sockaddr *peeraddr, struct net *ns); void lnet_connect_console_error(int rc, lnet_nid_t peer_nid, - __u32 peer_ip, int port); + struct sockaddr *sa); int lnet_count_acceptor_nets(void); int lnet_acceptor_timeout(void); int lnet_acceptor_port(void); @@ -751,9 +809,10 @@ struct lnet_inetdev { }; int lnet_inet_enumerate(struct lnet_inetdev **dev_list, struct net *ns); -int lnet_sock_setbuf(struct socket *socket, int txbufsize, int rxbufsize); -int lnet_sock_getbuf(struct socket *socket, int *txbufsize, int *rxbufsize); -int lnet_sock_getaddr(struct socket *socket, bool remote, __u32 *ip, int *port); +void lnet_sock_setbuf(struct socket *socket, int txbufsize, int rxbufsize); +void lnet_sock_getbuf(struct socket *socket, int *txbufsize, int *rxbufsize); +int lnet_sock_getaddr(struct socket *socket, bool remote, + struct sockaddr_storage *peer); int lnet_sock_write(struct socket *sock, void *buffer, int nob, int timeout); int lnet_sock_read(struct socket *sock, void *buffer, int nob, int timeout); @@ -807,8 +866,7 @@ void lnet_peer_push_event(struct lnet_event *ev); int lnet_parse_ip2nets(const char **networksp, const char *ip2nets); int lnet_parse_routes(const char *route_str, int *im_a_router); -int lnet_parse_networks(struct list_head *nilist, const char *networks, - bool use_tcp_bonding); +int lnet_parse_networks(struct list_head *nilist, const char *networks); bool lnet_net_unique(__u32 net_id, struct list_head *nilist, struct lnet_net **net); bool lnet_ni_unique_net(struct list_head *nilist, char *iface); @@ -832,6 +890,7 @@ struct lnet_peer *lnet_find_peer(lnet_nid_t nid); void lnet_peer_net_added(struct lnet_net *net); lnet_nid_t lnet_peer_primary_nid_locked(lnet_nid_t nid); int lnet_discover_peer_locked(struct lnet_peer_ni *lpni, int cpt, bool block); +void lnet_peer_queue_message(struct lnet_peer *lp, struct lnet_msg *msg); int lnet_peer_discovery_start(void); void lnet_peer_discovery_stop(void); void lnet_push_update_to_peers(int force); @@ -842,6 +901,11 @@ void lnet_debug_peer(lnet_nid_t nid); struct lnet_peer_net *lnet_peer_get_net_locked(struct lnet_peer *peer, __u32 net_id); bool lnet_peer_is_pref_nid_locked(struct lnet_peer_ni *lpni, lnet_nid_t nid); +int lnet_peer_add_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid); +void lnet_peer_clr_pref_nids(struct lnet_peer_ni *lpni); +bool lnet_peer_is_pref_rtr_locked(struct lnet_peer_ni *lpni, lnet_nid_t gw_nid); +void lnet_peer_clr_pref_rtrs(struct lnet_peer_ni *lpni); +int lnet_peer_add_pref_rtr(struct lnet_peer_ni *lpni, lnet_nid_t nid); int lnet_peer_ni_set_non_mr_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid); int lnet_add_peer_ni(lnet_nid_t key_nid, lnet_nid_t nid, bool mr); int lnet_del_peer_ni(lnet_nid_t key_nid, lnet_nid_t nid); @@ -854,6 +918,13 @@ int lnet_get_peer_ni_info(__u32 peer_index, __u64 *nid, __u32 *peer_tx_qnob); int lnet_get_peer_ni_hstats(struct lnet_ioctl_peer_ni_hstats *stats); +static inline void +lnet_peer_net_set_sel_priority_locked(struct lnet_peer_net *lpn, __u32 priority) +{ + lpn->lpn_sel_priority = priority; +} + + static inline struct lnet_peer_net * lnet_find_peer_net_locked(struct lnet_peer *peer, __u32 net_id) { @@ -900,6 +971,8 @@ lnet_peer_needs_push(struct lnet_peer *lp) { if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) return false; + if (lp->lp_state & LNET_PEER_MARK_DELETED) + return false; if (lp->lp_state & LNET_PEER_FORCE_PUSH) return true; if (lp->lp_state & LNET_PEER_NO_DISCOVERY) @@ -912,9 +985,31 @@ lnet_peer_needs_push(struct lnet_peer *lp) return false; } +#define LNET_RECOVERY_INTERVAL_MAX 900 +static inline unsigned int +lnet_get_next_recovery_ping(unsigned int ping_count, time64_t now) +{ + unsigned int interval; + + /* 2^9 = 512, 2^10 = 1024 */ + if (ping_count > 9) + interval = LNET_RECOVERY_INTERVAL_MAX; + else + interval = 1 << ping_count; + + return now + interval; +} + +static inline void +lnet_peer_ni_set_next_ping(struct lnet_peer_ni *lpni, time64_t now) +{ + lpni->lpni_next_ping = + lnet_get_next_recovery_ping(lpni->lpni_ping_count, now); +} + /* - * A peer is alive if it satisfies the following two conditions: - * 1. peer health >= LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage + * A peer NI is alive if it satisfies the following two conditions: + * 1. peer NI health >= LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage * 2. the cached NI status received when we discover the peer is UP */ static inline bool @@ -1000,6 +1095,18 @@ lnet_inc_healthv(atomic_t *healthv, int value) lnet_atomic_add_unless_max(healthv, value, LNET_MAX_HEALTH_VALUE); } +static inline int +lnet_get_list_len(struct list_head *list) +{ + struct list_head *l; + int count = 0; + + list_for_each(l, list) + count++; + + return count; +} + void lnet_incr_stats(struct lnet_element_stats *stats, enum lnet_msg_type msg_type, enum lnet_stats_type stats_type);