X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Finclude%2Flnet%2Flib-lnet.h;h=52aeb92f74a3fde9239f6f66e3c87205e702487c;hp=0d3fc995f0b49cdef093ac4d94464b648a1bc5ec;hb=1aae733c16161513b07d7f8cc046299e2de5aad3;hpb=58091af960fed0cc16e2b96e54ee6e2f8791d9c1 diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h index 0d3fc99..52aeb92 100644 --- a/lnet/include/lnet/lib-lnet.h +++ b/lnet/include/lnet/lib-lnet.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/ @@ -37,16 +37,22 @@ #ifndef __LNET_LIB_LNET_H__ #define __LNET_LIB_LNET_H__ +/* LNET has 0xeXXX */ +#define CFS_FAIL_PTLRPC_OST_BULK_CB2 0xe000 + #ifndef __KERNEL__ # error This include is only for kernel use. #endif #include #include -#include #include +#include +#include +#include +#include -extern lnet_t the_lnet; /* THE network */ +extern struct lnet the_lnet; /* THE network */ #if (BITS_PER_LONG == 32) /* 2 CPTs, allowing more CPTs might make us under memory pressure */ @@ -70,16 +76,24 @@ extern lnet_t the_lnet; /* THE network */ /** exclusive lock */ #define LNET_LOCK_EX CFS_PERCPT_LOCK_EX -static inline int lnet_is_route_alive(lnet_route_t *route) -{ - if (!route->lr_gateway->lpni_alive) - return 0; /* gateway is down */ - if ((route->lr_gateway->lpni_ping_feats & - LNET_PING_FEAT_NI_STATUS) == 0) - return 1; /* no NI status, assume it's alive */ - /* has NI status, check # down NIs */ - return route->lr_downis == 0; -} +/* default timeout */ +#define DEFAULT_PEER_TIMEOUT 180 +#define LNET_LND_DEFAULT_TIMEOUT 5 + +#ifdef HAVE_KERN_SOCK_GETNAME_2ARGS +#define lnet_kernel_getpeername(sock, addr, addrlen) \ + kernel_getpeername(sock, addr) +#define lnet_kernel_getsockname(sock, addr, addrlen) \ + kernel_getsockname(sock, addr) +#else +#define lnet_kernel_getpeername(sock, addr, addrlen) \ + kernel_getpeername(sock, addr, addrlen) +#define lnet_kernel_getsockname(sock, addr, addrlen) \ + kernel_getsockname(sock, addr, addrlen) +#endif + +bool lnet_is_route_alive(struct lnet_route *route); +bool lnet_is_gateway_alive(struct lnet_peer *gw); static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh) { @@ -87,14 +101,14 @@ static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh) wh->wh_object_cookie == LNET_WIRE_HANDLE_COOKIE_NONE); } -static inline int lnet_md_exhausted (lnet_libmd_t *md) +static inline int lnet_md_exhausted(struct lnet_libmd *md) { return (md->md_threshold == 0 || ((md->md_options & LNET_MD_MAX_SIZE) != 0 && md->md_offset + md->md_max_size > md->md_length)); } -static inline int lnet_md_unlinkable (lnet_libmd_t *md) +static inline int lnet_md_unlinkable(struct lnet_libmd *md) { /* Should unlink md when its refcount is 0 and either: * - md has been flagged for deletion (by auto unlink or LNetM[DE]Unlink, @@ -178,40 +192,40 @@ lnet_net_lock_current(void) #define MAX_PORTALS 64 -#define LNET_SMALL_MD_SIZE offsetof(lnet_libmd_t, md_iov.iov[1]) +#define LNET_SMALL_MD_SIZE offsetof(struct lnet_libmd, md_iov.iov[1]) 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 */ -static inline lnet_eq_t * +static inline struct lnet_eq * lnet_eq_alloc (void) { - lnet_eq_t *eq; + struct lnet_eq *eq; LIBCFS_ALLOC(eq, sizeof(*eq)); return (eq); } static inline void -lnet_eq_free(lnet_eq_t *eq) +lnet_eq_free(struct lnet_eq *eq) { LIBCFS_FREE(eq, sizeof(*eq)); } -static inline lnet_libmd_t * -lnet_md_alloc (lnet_md_t *umd) +static inline struct lnet_libmd * +lnet_md_alloc(struct lnet_md *umd) { - lnet_libmd_t *md; + struct lnet_libmd *md; unsigned int size; unsigned int niov; if ((umd->options & LNET_MD_KIOV) != 0) { niov = umd->length; - size = offsetof(lnet_libmd_t, md_iov.kiov[niov]); + size = offsetof(struct lnet_libmd, md_iov.kiov[niov]); } else { niov = ((umd->options & LNET_MD_IOVEC) != 0) ? umd->length : 1; - size = offsetof(lnet_libmd_t, md_iov.iov[niov]); + size = offsetof(struct lnet_libmd, md_iov.iov[niov]); } if (size <= LNET_SMALL_MD_SIZE) { @@ -240,14 +254,14 @@ lnet_md_alloc (lnet_md_t *umd) } static inline void -lnet_md_free(lnet_libmd_t *md) +lnet_md_free(struct lnet_libmd *md) { unsigned int size; if ((md->md_options & LNET_MD_KIOV) != 0) - size = offsetof(lnet_libmd_t, md_iov.kiov[md->md_niov]); + size = offsetof(struct lnet_libmd, md_iov.kiov[md->md_niov]); else - size = offsetof(lnet_libmd_t, md_iov.iov[md->md_niov]); + size = offsetof(struct lnet_libmd, md_iov.iov[md->md_niov]); if (size <= LNET_SMALL_MD_SIZE) { CDEBUG(D_MALLOC, "slab-freed 'md' at %p.\n", md); @@ -257,10 +271,10 @@ lnet_md_free(lnet_libmd_t *md) } } -static inline lnet_me_t * +static inline struct lnet_me * lnet_me_alloc (void) { - lnet_me_t *me; + struct lnet_me *me; me = kmem_cache_alloc(lnet_mes_cachep, GFP_NOFS | __GFP_ZERO); @@ -273,18 +287,18 @@ lnet_me_alloc (void) } static inline void -lnet_me_free(lnet_me_t *me) +lnet_me_free(struct lnet_me *me) { CDEBUG(D_MALLOC, "slab-freed 'me' at %p.\n", me); kmem_cache_free(lnet_mes_cachep, me); } -lnet_libhandle_t *lnet_res_lh_lookup(struct lnet_res_container *rec, +struct lnet_libhandle *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); + struct lnet_libhandle *lh); static inline void -lnet_res_lh_invalidate(lnet_libhandle_t *lh) +lnet_res_lh_invalidate(struct lnet_libhandle *lh) { /* ALWAYS called with resource lock held */ /* NB: cookie is still useful, don't reset it */ @@ -292,40 +306,40 @@ lnet_res_lh_invalidate(lnet_libhandle_t *lh) } static inline void -lnet_eq2handle (lnet_handle_eq_t *handle, lnet_eq_t *eq) +lnet_eq2handle(struct lnet_handle_eq *handle, struct lnet_eq *eq) { if (eq == NULL) { - LNetInvalidateHandle(handle); + LNetInvalidateEQHandle(handle); return; } handle->cookie = eq->eq_lh.lh_cookie; } -static inline lnet_eq_t * -lnet_handle2eq(lnet_handle_eq_t *handle) +static inline struct lnet_eq * +lnet_handle2eq(struct lnet_handle_eq *handle) { /* ALWAYS called with resource lock held */ - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; lh = lnet_res_lh_lookup(&the_lnet.ln_eq_container, handle->cookie); if (lh == NULL) return NULL; - return lh_entry(lh, lnet_eq_t, eq_lh); + return lh_entry(lh, struct lnet_eq, eq_lh); } static inline void -lnet_md2handle (lnet_handle_md_t *handle, lnet_libmd_t *md) +lnet_md2handle(struct lnet_handle_md *handle, struct lnet_libmd *md) { handle->cookie = md->md_lh.lh_cookie; } -static inline lnet_libmd_t * -lnet_handle2md(lnet_handle_md_t *handle) +static inline struct lnet_libmd * +lnet_handle2md(struct lnet_handle_md *handle) { /* ALWAYS called with resource lock held */ - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; int cpt; cpt = lnet_cpt_of_cookie(handle->cookie); @@ -334,14 +348,14 @@ lnet_handle2md(lnet_handle_md_t *handle) if (lh == NULL) return NULL; - return lh_entry(lh, lnet_libmd_t, md_lh); + return lh_entry(lh, struct lnet_libmd, md_lh); } -static inline lnet_libmd_t * +static inline struct lnet_libmd * lnet_wire_handle2md(struct lnet_handle_wire *wh) { /* ALWAYS called with resource lock held */ - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; int cpt; if (wh->wh_interface_cookie != the_lnet.ln_interface_cookie) @@ -353,20 +367,20 @@ lnet_wire_handle2md(struct lnet_handle_wire *wh) if (lh == NULL) return NULL; - return lh_entry(lh, lnet_libmd_t, md_lh); + return lh_entry(lh, struct lnet_libmd, md_lh); } static inline void -lnet_me2handle (lnet_handle_me_t *handle, lnet_me_t *me) +lnet_me2handle(struct lnet_handle_me *handle, struct lnet_me *me) { handle->cookie = me->me_lh.lh_cookie; } -static inline lnet_me_t * -lnet_handle2me(lnet_handle_me_t *handle) +static inline struct lnet_me * +lnet_handle2me(struct lnet_handle_me *handle) { /* ALWAYS called with resource lock held */ - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; int cpt; cpt = lnet_cpt_of_cookie(handle->cookie); @@ -375,13 +389,43 @@ lnet_handle2me(lnet_handle_me_t *handle) if (lh == NULL) return NULL; - return lh_entry(lh, lnet_me_t, me_lh); + return lh_entry(lh, struct lnet_me, me_lh); +} + +static inline void +lnet_peer_net_addref_locked(struct lnet_peer_net *lpn) +{ + atomic_inc(&lpn->lpn_refcount); +} + +extern void lnet_destroy_peer_net_locked(struct lnet_peer_net *lpn); + +static inline void +lnet_peer_net_decref_locked(struct lnet_peer_net *lpn) +{ + if (atomic_dec_and_test(&lpn->lpn_refcount)) + lnet_destroy_peer_net_locked(lpn); +} + +static inline void +lnet_peer_addref_locked(struct lnet_peer *lp) +{ + atomic_inc(&lp->lp_refcount); +} + +extern void lnet_destroy_peer_locked(struct lnet_peer *lp); + +static inline void +lnet_peer_decref_locked(struct lnet_peer *lp) +{ + if (atomic_dec_and_test(&lp->lp_refcount)) + lnet_destroy_peer_locked(lp); } static inline void lnet_peer_ni_addref_locked(struct lnet_peer_ni *lp) { - LASSERT (atomic_read(&lp->lpni_refcount) > 0); + LASSERT(atomic_read(&lp->lpni_refcount) > 0); atomic_inc(&lp->lpni_refcount); } @@ -390,20 +434,19 @@ extern void lnet_destroy_peer_ni_locked(struct lnet_peer_ni *lp); static inline void lnet_peer_ni_decref_locked(struct lnet_peer_ni *lp) { - LASSERT (atomic_read(&lp->lpni_refcount) > 0); - atomic_dec(&lp->lpni_refcount); - if (atomic_read(&lp->lpni_refcount) == 0) + LASSERT(atomic_read(&lp->lpni_refcount) > 0); + if (atomic_dec_and_test(&lp->lpni_refcount)) lnet_destroy_peer_ni_locked(lp); } static inline int -lnet_isrouter(struct lnet_peer_ni *lp) +lnet_isrouter(struct lnet_peer_ni *lpni) { - return lp->lpni_rtr_refcount != 0; + return lpni->lpni_peer_net->lpn_peer->lp_rtr_refcount != 0; } static inline void -lnet_ni_addref_locked(lnet_ni_t *ni, int cpt) +lnet_ni_addref_locked(struct lnet_ni *ni, int cpt) { LASSERT(cpt >= 0 && cpt < LNET_CPT_NUMBER); LASSERT(*ni->ni_refs[cpt] >= 0); @@ -412,7 +455,7 @@ lnet_ni_addref_locked(lnet_ni_t *ni, int cpt) } static inline void -lnet_ni_addref(lnet_ni_t *ni) +lnet_ni_addref(struct lnet_ni *ni) { lnet_net_lock(0); lnet_ni_addref_locked(ni, 0); @@ -420,7 +463,7 @@ lnet_ni_addref(lnet_ni_t *ni) } static inline void -lnet_ni_decref_locked(lnet_ni_t *ni, int cpt) +lnet_ni_decref_locked(struct lnet_ni *ni, int cpt) { LASSERT(cpt >= 0 && cpt < LNET_CPT_NUMBER); LASSERT(*ni->ni_refs[cpt] > 0); @@ -429,17 +472,17 @@ lnet_ni_decref_locked(lnet_ni_t *ni, int cpt) } static inline void -lnet_ni_decref(lnet_ni_t *ni) +lnet_ni_decref(struct lnet_ni *ni) { lnet_net_lock(0); lnet_ni_decref_locked(ni, 0); lnet_net_unlock(0); } -static inline lnet_msg_t * +static inline struct lnet_msg * lnet_msg_alloc(void) { - lnet_msg_t *msg; + struct lnet_msg *msg; LIBCFS_ALLOC(msg, sizeof(*msg)); @@ -448,17 +491,30 @@ lnet_msg_alloc(void) } static inline void -lnet_msg_free(lnet_msg_t *msg) +lnet_msg_free(struct lnet_msg *msg) { LASSERT(!msg->msg_onactivelist); + LIBCFS_FREE(msg, sizeof(*msg)); +} - /* Make sure we have no references to an NI. */ - if (msg->msg_txni) - lnet_ni_decref_locked(msg->msg_txni, msg->msg_tx_cpt); - if (msg->msg_rxni) - lnet_ni_decref_locked(msg->msg_rxni, msg->msg_rx_cpt); +static inline struct lnet_rsp_tracker * +lnet_rspt_alloc(int cpt) +{ + struct lnet_rsp_tracker *rspt; + LIBCFS_ALLOC(rspt, sizeof(*rspt)); + lnet_net_lock(cpt); + the_lnet.ln_counters[cpt]->lct_health.lch_rst_alloc++; + lnet_net_unlock(cpt); + return rspt; +} - LIBCFS_FREE(msg, sizeof(*msg)); +static inline void +lnet_rspt_free(struct lnet_rsp_tracker *rspt, int cpt) +{ + LIBCFS_FREE(rspt, sizeof(*rspt)); + lnet_net_lock(cpt); + the_lnet.ln_counters[cpt]->lct_health.lch_rst_alloc--; + lnet_net_unlock(cpt); } void lnet_ni_free(struct lnet_ni *ni); @@ -470,6 +526,9 @@ lnet_net_alloc(__u32 net_type, struct list_head *netlist); struct lnet_ni * lnet_ni_alloc(struct lnet_net *net, struct cfs_expr_list *el, char *iface); +struct lnet_ni * +lnet_ni_alloc_w_cpt_array(struct lnet_net *net, __u32 *cpts, __u32 ncpts, + char *iface); static inline int lnet_nid2peerhash(lnet_nid_t nid) @@ -485,135 +544,144 @@ lnet_net2rnethash(__u32 net) ((1U << the_lnet.ln_remote_nets_hbits) - 1)]; } -extern lnd_t the_lolnd; +extern struct lnet_lnd the_lolnd; extern int avoid_asym_router_failure; extern unsigned int lnet_nid_cpt_hash(lnet_nid_t nid, unsigned int number); extern int lnet_cpt_of_nid_locked(lnet_nid_t nid, struct lnet_ni *ni); extern int lnet_cpt_of_nid(lnet_nid_t nid, struct lnet_ni *ni); -extern lnet_ni_t *lnet_nid2ni_locked(lnet_nid_t nid, int cpt); -extern lnet_ni_t *lnet_nid2ni_addref(lnet_nid_t nid); -extern lnet_ni_t *lnet_net2ni_locked(__u32 net, int cpt); -extern lnet_ni_t *lnet_net2ni(__u32 net); -bool lnet_is_ni_healthy_locked(struct lnet_ni *ni); +extern struct lnet_ni *lnet_nid2ni_locked(lnet_nid_t nid, int cpt); +extern struct lnet_ni *lnet_nid2ni_addref(lnet_nid_t nid); +extern struct lnet_ni *lnet_net2ni_locked(__u32 net, int cpt); +extern struct lnet_ni *lnet_net2ni_addref(__u32 net); +struct lnet_net *lnet_get_net_locked(__u32 net_id); int lnet_lib_init(void); void lnet_lib_exit(void); +extern unsigned lnet_transaction_timeout; +extern unsigned lnet_retry_count; +extern unsigned int lnet_numa_range; +extern unsigned int lnet_health_sensitivity; +extern unsigned int lnet_recovery_interval; +extern unsigned int lnet_peer_discovery_disabled; +extern unsigned int lnet_drop_asym_route; +extern unsigned int router_sensitivity_percentage; +extern int alive_router_check_interval; extern int portal_rotor; -int lnet_notify(lnet_ni_t *ni, lnet_nid_t peer, int alive, cfs_time_t when); +void lnet_mt_event_handler(struct lnet_event *event); + +int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, bool alive, bool reset, + time64_t when); void lnet_notify_locked(struct lnet_peer_ni *lp, int notifylnd, int alive, - cfs_time_t when); + time64_t when); int lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway_nid, - unsigned int priority); -int lnet_check_routes(void); + __u32 priority, __u32 sensitivity); int lnet_del_route(__u32 net, lnet_nid_t gw_nid); void lnet_destroy_routes(void); int lnet_get_route(int idx, __u32 *net, __u32 *hops, - lnet_nid_t *gateway, __u32 *alive, __u32 *priority); + lnet_nid_t *gateway, __u32 *alive, __u32 *priority, + __u32 *sensitivity); 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); -struct libcfs_ioctl_handler { - struct list_head item; - int (*handle_ioctl)(unsigned int cmd, struct libcfs_ioctl_hdr *hdr); -}; - -#define DECLARE_IOCTL_HANDLER(ident, func) \ - static struct libcfs_ioctl_handler ident = { \ - /* .item = */ LIST_HEAD_INIT(ident.item), \ - /* .handle_ioctl = */ func \ - } - -extern int libcfs_register_ioctl(struct libcfs_ioctl_handler *hand); -extern int libcfs_deregister_ioctl(struct libcfs_ioctl_handler *hand); 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); -void lnet_proc_init(void); -void lnet_proc_fini(void); +void lnet_router_debugfs_init(void); +void lnet_router_debugfs_fini(void); int lnet_rtrpools_alloc(int im_a_router); -void lnet_destroy_rtrbuf(lnet_rtrbuf_t *rb, int npages); +void lnet_destroy_rtrbuf(struct lnet_rtrbuf *rb, int npages); int lnet_rtrpools_adjust(int tiny, int small, int large); int lnet_rtrpools_enable(void); void lnet_rtrpools_disable(void); void lnet_rtrpools_free(int keep_pools); -lnet_remotenet_t *lnet_find_rnet_locked(__u32 net); -int lnet_dyn_add_ni(lnet_pid_t requested_pid, - struct lnet_ioctl_config_data *conf); -int lnet_dyn_del_ni(__u32 net); +void lnet_rtr_transfer_to_peer(struct lnet_peer *src, + struct lnet_peer *target); +struct lnet_remotenet *lnet_find_rnet_locked(__u32 net); +int lnet_dyn_add_net(struct lnet_ioctl_config_data *conf); +int lnet_dyn_del_net(__u32 net); +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); int lnet_islocalnid(lnet_nid_t nid); int lnet_islocalnet(__u32 net); +int lnet_islocalnet_locked(__u32 net); -void lnet_msg_attach_md(lnet_msg_t *msg, lnet_libmd_t *md, +void lnet_msg_attach_md(struct lnet_msg *msg, struct lnet_libmd *md, unsigned int offset, unsigned int mlen); -void lnet_msg_detach_md(lnet_msg_t *msg, int status); -void lnet_build_unlink_event(lnet_libmd_t *md, lnet_event_t *ev); -void lnet_build_msg_event(lnet_msg_t *msg, lnet_event_kind_t ev_type); -void lnet_msg_commit(lnet_msg_t *msg, int cpt); -void lnet_msg_decommit(lnet_msg_t *msg, int cpt, int status); - -void lnet_eq_enqueue_event(lnet_eq_t *eq, lnet_event_t *ev); -void lnet_prep_send(lnet_msg_t *msg, int type, lnet_process_id_t target, - unsigned int offset, unsigned int len); -int lnet_send(lnet_nid_t nid, lnet_msg_t *msg, lnet_nid_t rtr_nid); -void lnet_return_tx_credits_locked(lnet_msg_t *msg); -void lnet_return_rx_credits_locked(lnet_msg_t *msg); -void lnet_schedule_blocked_locked(lnet_rtrbufpool_t *rbp); +void lnet_build_unlink_event(struct lnet_libmd *md, struct lnet_event *ev); +void lnet_build_msg_event(struct lnet_msg *msg, enum lnet_event_kind ev_type); +void lnet_msg_commit(struct lnet_msg *msg, int cpt); +void lnet_msg_decommit(struct lnet_msg *msg, int cpt, int status); + +void lnet_eq_enqueue_event(struct lnet_eq *eq, struct lnet_event *ev); +void lnet_prep_send(struct lnet_msg *msg, int type, + struct lnet_process_id target, unsigned int offset, + unsigned int len); +int lnet_send(lnet_nid_t nid, struct lnet_msg *msg, lnet_nid_t rtr_nid); +int lnet_send_ping(lnet_nid_t dest_nid, struct lnet_handle_md *mdh, int nnis, + void *user_ptr, struct lnet_handle_eq eqh, bool recovery); +void lnet_return_tx_credits_locked(struct lnet_msg *msg); +void lnet_return_rx_credits_locked(struct lnet_msg *msg); +void lnet_schedule_blocked_locked(struct lnet_rtrbufpool *rbp); void lnet_drop_routed_msgs_locked(struct list_head *list, int cpt); /* portals functions */ /* portals attributes */ static inline int -lnet_ptl_is_lazy(lnet_portal_t *ptl) +lnet_ptl_is_lazy(struct lnet_portal *ptl) { return !!(ptl->ptl_options & LNET_PTL_LAZY); } static inline int -lnet_ptl_is_unique(lnet_portal_t *ptl) +lnet_ptl_is_unique(struct lnet_portal *ptl) { return !!(ptl->ptl_options & LNET_PTL_MATCH_UNIQUE); } static inline int -lnet_ptl_is_wildcard(lnet_portal_t *ptl) +lnet_ptl_is_wildcard(struct lnet_portal *ptl) { return !!(ptl->ptl_options & LNET_PTL_MATCH_WILDCARD); } static inline void -lnet_ptl_setopt(lnet_portal_t *ptl, int opt) +lnet_ptl_setopt(struct lnet_portal *ptl, int opt) { ptl->ptl_options |= opt; } static inline void -lnet_ptl_unsetopt(lnet_portal_t *ptl, int opt) +lnet_ptl_unsetopt(struct lnet_portal *ptl, int opt) { ptl->ptl_options &= ~opt; } /* match-table functions */ struct list_head *lnet_mt_match_head(struct lnet_match_table *mtable, - lnet_process_id_t id, __u64 mbits); + struct lnet_process_id id, __u64 mbits); struct lnet_match_table *lnet_mt_of_attach(unsigned int index, - lnet_process_id_t id, __u64 mbits, - __u64 ignore_bits, - lnet_ins_pos_t pos); + struct lnet_process_id id, + __u64 mbits, __u64 ignore_bits, + enum lnet_ins_pos pos); int lnet_mt_match_md(struct lnet_match_table *mtable, struct lnet_match_info *info, struct lnet_msg *msg); /* portals match/attach functions */ -void lnet_ptl_attach_md(lnet_me_t *me, lnet_libmd_t *md, +void lnet_ptl_attach_md(struct lnet_me *me, struct lnet_libmd *md, struct list_head *matches, struct list_head *drops); -void lnet_ptl_detach_md(lnet_me_t *me, lnet_libmd_t *md); +void lnet_ptl_detach_md(struct lnet_me *me, struct lnet_libmd *md); int lnet_ptl_match_md(struct lnet_match_info *info, struct lnet_msg *msg); /* initialized and finalize portals */ @@ -621,24 +689,31 @@ int lnet_portals_create(void); void lnet_portals_destroy(void); /* message functions */ -int lnet_parse (lnet_ni_t *ni, lnet_hdr_t *hdr, - lnet_nid_t fromnid, void *private, int rdma_req); -int lnet_parse_local(lnet_ni_t *ni, lnet_msg_t *msg); -int lnet_parse_forward_locked(lnet_ni_t *ni, lnet_msg_t *msg); - -void lnet_recv(lnet_ni_t *ni, void *private, lnet_msg_t *msg, int delayed, - unsigned int offset, unsigned int mlen, unsigned int rlen); -void lnet_ni_recv(lnet_ni_t *ni, void *private, lnet_msg_t *msg, +int lnet_parse(struct lnet_ni *ni, struct lnet_hdr *hdr, + lnet_nid_t fromnid, void *private, int rdma_req); +int lnet_parse_local(struct lnet_ni *ni, struct lnet_msg *msg); +int lnet_parse_forward_locked(struct lnet_ni *ni, struct lnet_msg *msg); + +void lnet_recv(struct lnet_ni *ni, void *private, struct lnet_msg *msg, + int delayed, unsigned int offset, unsigned int mlen, + unsigned int rlen); +void lnet_ni_recv(struct lnet_ni *ni, void *private, struct lnet_msg *msg, int delayed, unsigned int offset, unsigned int mlen, unsigned int rlen); -lnet_msg_t *lnet_create_reply_msg (lnet_ni_t *ni, lnet_msg_t *get_msg); -void lnet_set_reply_msg_len(lnet_ni_t *ni, lnet_msg_t *msg, unsigned int len); +struct lnet_msg *lnet_create_reply_msg(struct lnet_ni *ni, + struct lnet_msg *get_msg); +void lnet_set_reply_msg_len(struct lnet_ni *ni, struct lnet_msg *msg, + unsigned int len); +void lnet_detach_rsp_tracker(struct lnet_libmd *md, int cpt); -void lnet_finalize(lnet_ni_t *ni, lnet_msg_t *msg, int rc); +void lnet_finalize(struct lnet_msg *msg, int rc); +bool lnet_send_error_simulation(struct lnet_msg *msg, + enum lnet_msg_hstatus *hstatus); +void lnet_handle_remote_failure_locked(struct lnet_peer_ni *lpni); -void lnet_drop_message(lnet_ni_t *ni, int cpt, void *private, - unsigned int nob); +void lnet_drop_message(struct lnet_ni *ni, int cpt, void *private, + unsigned int nob, __u32 msg_type); void lnet_drop_delayed_msg_list(struct list_head *head, char *reason); void lnet_recv_delayed_msg_list(struct list_head *head); @@ -647,8 +722,9 @@ void lnet_msg_container_cleanup(struct lnet_msg_container *container); void lnet_msg_containers_destroy(void); int lnet_msg_containers_create(void); -char *lnet_msgtyp2str (int type); -void lnet_print_hdr (lnet_hdr_t * hdr); +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 @{ */ @@ -657,7 +733,8 @@ int lnet_fault_ctl(int cmd, struct libcfs_ioctl_data *data); int lnet_fault_init(void); void lnet_fault_fini(void); -bool lnet_drop_rule_match(lnet_hdr_t *hdr); +bool lnet_drop_rule_match(struct lnet_hdr *hdr, lnet_nid_t local_nid, + enum lnet_msg_hstatus *hstatus); int lnet_delay_rule_add(struct lnet_fault_attr *attr); int lnet_delay_rule_del(lnet_nid_t src, lnet_nid_t dst, bool shutdown); @@ -665,11 +742,12 @@ int lnet_delay_rule_list(int pos, struct lnet_fault_attr *attr, struct lnet_fault_stat *stat); void lnet_delay_rule_reset(void); void lnet_delay_rule_check(void); -bool lnet_delay_rule_match_locked(lnet_hdr_t *hdr, struct lnet_msg *msg); +bool lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg); /** @} lnet_fault_simulation */ -void lnet_counters_get(lnet_counters_t *counters); +void lnet_counters_get_common(struct lnet_counters_common *common); +void lnet_counters_get(struct lnet_counters *counters); void lnet_counters_reset(void); unsigned int lnet_iov_nob(unsigned int niov, struct kvec *iov); @@ -704,7 +782,7 @@ 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}; + struct kvec diov = { .iov_base = dest, .iov_len = dlen }; lnet_copy_iov2iov(1, &diov, doffset, nsiov, siov, soffset, nob); @@ -715,7 +793,7 @@ lnet_copy_kiov2flat(int dlen, void *dest, unsigned int doffset, unsigned int nsiov, lnet_kiov_t *skiov, unsigned int soffset, unsigned int nob) { - struct kvec diov = {/* .iov_base = */ dest, /* .iov_len = */ dlen}; + struct kvec diov = { .iov_base = dest, .iov_len = dlen }; lnet_copy_kiov2iov(1, &diov, doffset, nsiov, skiov, soffset, nob); @@ -726,7 +804,7 @@ 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}; + struct kvec siov = { .iov_base = src, .iov_len = slen }; lnet_copy_iov2iov(ndiov, diov, doffset, 1, &siov, soffset, nob); } @@ -736,18 +814,21 @@ lnet_copy_flat2kiov(unsigned int ndiov, lnet_kiov_t *dkiov, unsigned int doffset, int slen, void *src, unsigned int soffset, unsigned int nob) { - struct kvec siov = {/* .iov_base = */ src, /* .iov_len = */ slen}; + struct kvec siov = { .iov_base = src, .iov_len = slen }; lnet_copy_iov2kiov(ndiov, dkiov, doffset, 1, &siov, soffset, nob); } -void lnet_me_unlink(lnet_me_t *me); +void lnet_me_unlink(struct lnet_me *me); -void lnet_md_unlink(lnet_libmd_t *md); -void lnet_md_deconstruct(lnet_libmd_t *lmd, lnet_md_t *umd); +void lnet_md_unlink(struct lnet_libmd *md); +void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_md *umd); +struct page *lnet_kvaddr_to_page(unsigned long vaddr); +int lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset); -void lnet_register_lnd(lnd_t *lnd); -void lnet_unregister_lnd(lnd_t *lnd); +unsigned int lnet_get_lnd_timeout(void); +void lnet_register_lnd(struct lnet_lnd *lnd); +void lnet_unregister_lnd(struct lnet_lnd *lnd); int lnet_connect(struct socket **sockp, lnet_nid_t peer_nid, __u32 local_ip, __u32 peer_ip, int peer_port); @@ -759,9 +840,6 @@ int lnet_acceptor_port(void); int lnet_acceptor_start(void); void lnet_acceptor_stop(void); -int lnet_ipif_query(char *name, int *up, __u32 *ip, __u32 *mask); -int lnet_ipif_enumerate(char ***names); -void lnet_ipif_free_enumeration(char **names, int n); 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); @@ -776,11 +854,45 @@ int lnet_sock_connect(struct socket **sockp, int *fatal, int lnet_peers_start_down(void); int lnet_peer_buffer_credits(struct lnet_net *net); +void lnet_consolidate_routes_locked(struct lnet_peer *orig_lp, + struct lnet_peer *new_lp); +void lnet_router_discovery_complete(struct lnet_peer *lp); + +int lnet_monitor_thr_start(void); +void lnet_monitor_thr_stop(void); + +bool lnet_router_checker_active(void); +void lnet_check_routers(void); +void lnet_wait_router_start(void); +void lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf); + +int lnet_ping_info_validate(struct lnet_ping_info *pinfo); +struct lnet_ping_buffer *lnet_ping_buffer_alloc(int nnis, gfp_t gfp); +void lnet_ping_buffer_free(struct lnet_ping_buffer *pbuf); + +static inline void lnet_ping_buffer_addref(struct lnet_ping_buffer *pbuf) +{ + atomic_inc(&pbuf->pb_refcnt); +} + +static inline void lnet_ping_buffer_decref(struct lnet_ping_buffer *pbuf) +{ + if (atomic_dec_and_test(&pbuf->pb_refcnt)) + lnet_ping_buffer_free(pbuf); +} -int lnet_router_checker_start(void); -void lnet_router_checker_stop(void); -void lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net); -void lnet_swap_pinginfo(struct lnet_ping_info *info); +static inline int lnet_ping_buffer_numref(struct lnet_ping_buffer *pbuf) +{ + return atomic_read(&pbuf->pb_refcnt); +} + +static inline int lnet_push_target_resize_needed(void) +{ + return the_lnet.ln_push_target->pb_nnis < the_lnet.ln_push_target_nnis; +} + +int lnet_push_target_resize(void); +void lnet_peer_push_event(struct lnet_event *ev); int lnet_parse_ip2nets(char **networksp, char *ip2nets); int lnet_parse_routes(char *route_str, int *im_a_router); @@ -789,26 +901,139 @@ int lnet_parse_networks(struct list_head *nilist, 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); - -int lnet_nid2peerni_locked(struct lnet_peer_ni **lpp, lnet_nid_t nid, int cpt); -struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid, int cpt); -void lnet_peer_tables_cleanup(lnet_ni_t *ni); -void lnet_peer_tables_destroy(void); +void lnet_incr_dlc_seq(void); +__u32 lnet_get_dlc_seq_locked(void); +int lnet_get_net_count(void); + +struct lnet_peer_net *lnet_get_next_peer_net_locked(struct lnet_peer *lp, + __u32 prev_lpn_id); +struct lnet_peer_ni *lnet_get_next_peer_ni_locked(struct lnet_peer *peer, + struct lnet_peer_net *peer_net, + struct lnet_peer_ni *prev); +struct lnet_peer_ni *lnet_nid2peerni_locked(lnet_nid_t nid, lnet_nid_t pref, + int cpt); +struct lnet_peer_ni *lnet_nid2peerni_ex(lnet_nid_t nid, int cpt); +struct lnet_peer_ni *lnet_peer_get_ni_locked(struct lnet_peer *lp, + lnet_nid_t nid); +struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid); +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); +int lnet_peer_discovery_start(void); +void lnet_peer_discovery_stop(void); +void lnet_push_update_to_peers(int force); +void lnet_peer_tables_cleanup(struct lnet_net *net); +void lnet_peer_uninit(void); int lnet_peer_tables_create(void); void lnet_debug_peer(lnet_nid_t nid); -int lnet_get_peer_info(__u32 peer_index, __u64 *nid, - char alivness[LNET_MAX_STR_LEN], - __u32 *cpt_iter, __u32 *refcount, - __u32 *ni_peer_tx_credits, __u32 *peer_tx_credits, - __u32 *peer_rtr_credits, __u32 *peer_min_rtr_credtis, - __u32 *peer_tx_qnob); +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_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); +int lnet_get_peer_info(struct lnet_ioctl_peer_cfg *cfg, void __user *bulk); +int lnet_get_peer_ni_info(__u32 peer_index, __u64 *nid, + char alivness[LNET_MAX_STR_LEN], + __u32 *cpt_iter, __u32 *refcount, + __u32 *ni_peer_tx_credits, __u32 *peer_tx_credits, + __u32 *peer_rtr_credits, __u32 *peer_min_rtr_credtis, + __u32 *peer_tx_qnob); +int lnet_get_peer_ni_hstats(struct lnet_ioctl_peer_ni_hstats *stats); + +static inline struct lnet_peer_net * +lnet_find_peer_net_locked(struct lnet_peer *peer, __u32 net_id) +{ + struct lnet_peer_net *peer_net; + + list_for_each_entry(peer_net, &peer->lp_peer_nets, lpn_peer_nets) { + if (peer_net->lpn_net_id == net_id) + return peer_net; + } + + return NULL; +} + +static inline bool +lnet_peer_is_multi_rail(struct lnet_peer *lp) +{ + if (lp->lp_state & LNET_PEER_MULTI_RAIL) + return true; + return false; +} + +static inline bool +lnet_peer_ni_is_configured(struct lnet_peer_ni *lpni) +{ + if (lpni->lpni_peer_net->lpn_peer->lp_state & LNET_PEER_CONFIGURED) + return true; + return false; +} + +static inline bool +lnet_peer_ni_is_primary(struct lnet_peer_ni *lpni) +{ + return lpni->lpni_nid == lpni->lpni_peer_net->lpn_peer->lp_primary_nid; +} + +bool lnet_peer_is_uptodate(struct lnet_peer *lp); +bool lnet_is_discovery_disabled(struct lnet_peer *lp); +bool lnet_peer_gw_discovery(struct lnet_peer *lp); + +static inline bool +lnet_peer_needs_push(struct lnet_peer *lp) +{ + if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) + return false; + if (lp->lp_state & LNET_PEER_FORCE_PUSH) + return true; + if (lp->lp_state & LNET_PEER_NO_DISCOVERY) + return false; + /* if discovery is not enabled then no need to push */ + if (lnet_peer_discovery_disabled) + return false; + if (lp->lp_node_seqno < atomic_read(&the_lnet.ln_ping_target_seqno)) + return true; + return false; +} + +/* + * A peer is alive if it satisfies the following two conditions: + * 1. peer health >= LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage + * 2. the cached NI status received when we discover the peer is UP + */ +static inline bool +lnet_is_peer_ni_alive(struct lnet_peer_ni *lpni) +{ + bool halive = false; + + halive = (atomic_read(&lpni->lpni_healthv) >= + (LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage / 100)); + + return halive && lpni->lpni_ns_status == LNET_NI_STATUS_UP; +} + +static inline void +lnet_set_healthv(atomic_t *healthv, int value) +{ + atomic_set(healthv, value); +} static inline void -lnet_peer_set_alive(struct lnet_peer_ni *lp) +lnet_inc_healthv(atomic_t *healthv) { - lp->lpni_last_alive = lp->lpni_last_query = cfs_time_current(); - if (!lp->lpni_alive) - lnet_notify_locked(lp, 0, 1, lp->lpni_last_alive); + atomic_add_unless(healthv, 1, LNET_MAX_HEALTH_VALUE); } +void lnet_incr_stats(struct lnet_element_stats *stats, + enum lnet_msg_type msg_type, + enum lnet_stats_type stats_type); + +__u32 lnet_sum_stats(struct lnet_element_stats *stats, + enum lnet_stats_type stats_type); + +void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats, + struct lnet_element_stats *stats); + #endif