X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Finclude%2Flnet%2Flib-lnet.h;h=fba7de07478956e73d77755c1222de56dfb992bc;hp=602bf46a2bda22ea55890fb00bbe2e639a5a8941;hb=7b54fc7b1615f23a1ad9da84ba8e289de1f22d70;hpb=6612e57a233fa22af00173366e1121b68bb5524e diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h index 602bf46..fba7de0 100644 --- a/lnet/include/lnet/lib-lnet.h +++ b/lnet/include/lnet/lib-lnet.h @@ -27,7 +27,6 @@ */ /* * This file is part of Lustre, http://www.lustre.org/ - * Lustre is a trademark of Sun Microsystems, Inc. * * lnet/include/lnet/lib-lnet.h * @@ -74,9 +73,13 @@ 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 + +/* default number of connections per peer */ +#define DEFAULT_CONNS_PER_PEER 0 #ifdef HAVE_KERN_SOCK_GETNAME_2ARGS #define lnet_kernel_getpeername(sock, addr, addrlen) \ @@ -90,6 +93,33 @@ extern struct lnet the_lnet; /* THE network */ kernel_getsockname(sock, addr, addrlen) #endif +/* + * 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 HAVE_IN_DEV_FOR_EACH_IFA_RTNL +#define DECLARE_CONST_IN_IFADDR(ifa) const struct in_ifaddr *ifa +#define endfor_ifa(in_dev) +#else +#define DECLARE_CONST_IN_IFADDR(ifa) +#define in_dev_for_each_ifa_rtnl(ifa, in_dev) for_ifa((in_dev)) +#define in_dev_for_each_ifa_rcu(ifa, in_dev) for_ifa((in_dev)) +#endif + +#ifndef fallthrough +# if defined(__GNUC__) && __GNUC__ >= 7 +# define fallthrough __attribute__((fallthrough)) /* fallthrough */ +# else +# define fallthrough do {} while (0) /* fallthrough */ +# endif +#endif + +int choose_ipv4_src(__u32 *ret, + int interface, __u32 dst_ipaddr, struct net *ns); + bool lnet_is_route_alive(struct lnet_route *route); bool lnet_is_gateway_alive(struct lnet_peer *gw); @@ -183,74 +213,87 @@ lnet_net_lock_current(void) #define lnet_ptl_lock(ptl) spin_lock(&(ptl)->ptl_lock) #define lnet_ptl_unlock(ptl) spin_unlock(&(ptl)->ptl_lock) -#define lnet_eq_wait_lock() spin_lock(&the_lnet.ln_eq_wait_lock) -#define lnet_eq_wait_unlock() spin_unlock(&the_lnet.ln_eq_wait_lock) #define lnet_ni_lock(ni) spin_lock(&(ni)->ni_lock) #define lnet_ni_unlock(ni) spin_unlock(&(ni)->ni_lock) #define MAX_PORTALS 64 -#define LNET_SMALL_MD_SIZE offsetof(struct lnet_libmd, md_iov.iov[1]) +#define LNET_SMALL_MD_SIZE offsetof(struct lnet_libmd, md_kiov[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 */ +extern struct kmem_cache *lnet_udsp_cachep; extern struct kmem_cache *lnet_rspt_cachep; extern struct kmem_cache *lnet_msg_cachep; -static inline struct lnet_eq * -lnet_eq_alloc (void) +static inline bool +lnet_ni_set_status_locked(struct lnet_ni *ni, __u32 status) +__must_hold(&ni->ni_lock) { - struct lnet_eq *eq; + 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_nidstr(&ni->ni_nid), + ni->ni_status->ns_status, status); + ni->ni_status->ns_status = status; + update = true; + } - LIBCFS_ALLOC(eq, sizeof(*eq)); - return (eq); + return update; } -static inline void -lnet_eq_free(struct lnet_eq *eq) +static inline unsigned int +lnet_ni_get_status_locked(struct lnet_ni *ni) +__must_hold(&ni->ni_lock) { - LIBCFS_FREE(eq, sizeof(*eq)); + if (nid_is_lo0(&ni->ni_nid)) + return LNET_NI_STATUS_UP; + else if (atomic_read(&ni->ni_fatal_error_on)) + return LNET_NI_STATUS_DOWN; + else if (ni->ni_status) + return ni->ni_status->ns_status; + else + return LNET_NI_STATUS_UP; } -static inline struct lnet_libmd * -lnet_md_alloc(struct lnet_md *umd) +static inline bool +lnet_ni_set_status(struct lnet_ni *ni, __u32 status) { - struct lnet_libmd *md; - unsigned int size; - unsigned int niov; + bool update; - if ((umd->options & LNET_MD_KIOV) != 0) { - niov = umd->length; - size = offsetof(struct lnet_libmd, md_iov.kiov[niov]); - } else { - niov = ((umd->options & LNET_MD_IOVEC) != 0) ? - umd->length : 1; - size = offsetof(struct lnet_libmd, md_iov.iov[niov]); - } + lnet_ni_lock(ni); + update = lnet_ni_set_status_locked(ni, status); + lnet_ni_unlock(ni); - if (size <= LNET_SMALL_MD_SIZE) { - md = kmem_cache_alloc(lnet_small_mds_cachep, - GFP_NOFS | __GFP_ZERO); - if (md) { - CDEBUG(D_MALLOC, "slab-alloced 'md' of size %u at " - "%p.\n", size, md); - } else { - CDEBUG(D_MALLOC, "failed to allocate 'md' of size %u\n", - size); - return NULL; - } - } else { - LIBCFS_ALLOC(md, size); - } + return update; +} - if (md != NULL) { - /* Set here in case of early free */ - md->md_options = umd->options; - md->md_niov = niov; - INIT_LIST_HEAD(&md->md_list); +static inline void lnet_md_wait_handling(struct lnet_libmd *md, int cpt) +{ + wait_queue_head_t *wq = __var_waitqueue(md); +#if defined(HAVE_WAIT_BIT_QUEUE_ENTRY) || !defined(HAVE_WAIT_VAR_EVENT) + 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); } - - return md; + finish_wait(wq, wqe); } static inline void @@ -260,10 +303,7 @@ lnet_md_free(struct lnet_libmd *md) LASSERTF(md->md_rspt_ptr == NULL, "md %p rsp %p\n", md, md->md_rspt_ptr); - if ((md->md_options & LNET_MD_KIOV) != 0) - size = offsetof(struct lnet_libmd, md_iov.kiov[md->md_niov]); - else - size = offsetof(struct lnet_libmd, md_iov.iov[md->md_niov]); + size = offsetof(struct lnet_libmd, md_kiov[md->md_niov]); if (size <= LNET_SMALL_MD_SIZE) { CDEBUG(D_MALLOC, "slab-freed 'md' at %p.\n", md); @@ -359,18 +399,15 @@ lnet_peer_decref_locked(struct lnet_peer *lp) static inline void lnet_peer_ni_addref_locked(struct lnet_peer_ni *lp) { - LASSERT(atomic_read(&lp->lpni_refcount) > 0); - atomic_inc(&lp->lpni_refcount); + kref_get(&lp->lpni_kref); } -extern void lnet_destroy_peer_ni_locked(struct lnet_peer_ni *lp); +extern void lnet_destroy_peer_ni_locked(struct kref *ref); static inline void lnet_peer_ni_decref_locked(struct lnet_peer_ni *lp) { - LASSERT(atomic_read(&lp->lpni_refcount) > 0); - if (atomic_dec_and_test(&lp->lpni_refcount)) - lnet_destroy_peer_ni_locked(lp); + kref_put(&lp->lpni_kref, lnet_destroy_peer_ni_locked); } static inline int @@ -418,7 +455,7 @@ 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); } @@ -435,7 +472,7 @@ 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++; @@ -470,9 +507,14 @@ 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) +lnet_nid2peerhash(struct lnet_nid *nid) { - return hash_long(nid, LNET_PEER_HASH_BITS); + u32 h = 0; + int i; + + for (i = 0; i < 4; i++) + h = hash_32(nid->nid_addr[i]^h, 32); + return hash_32(LNET_NID_NET(nid) ^ h, LNET_PEER_HASH_BITS); } static inline struct list_head * @@ -483,28 +525,93 @@ lnet_net2rnethash(__u32 net) ((1U << the_lnet.ln_remote_nets_hbits) - 1)]; } +static inline void lnet_hdr_from_nid4(struct lnet_hdr *hdr, + const struct lnet_hdr_nid4 *vhdr) +{ + const struct _lnet_hdr_nid4 *hdr_nid4 = (void *)vhdr; + + lnet_nid4_to_nid(le64_to_cpu(hdr_nid4->dest_nid), &hdr->dest_nid); + lnet_nid4_to_nid(le64_to_cpu(hdr_nid4->src_nid), &hdr->src_nid); + hdr->dest_pid = le32_to_cpu(hdr_nid4->dest_pid); + hdr->src_pid = le32_to_cpu(hdr_nid4->src_pid); + hdr->type = le32_to_cpu(hdr_nid4->type); + hdr->payload_length = le32_to_cpu(hdr_nid4->payload_length); + + hdr->msg = hdr_nid4->msg; +} + +static inline void lnet_hdr_to_nid4(const struct lnet_hdr *hdr, + struct lnet_hdr_nid4 *vhdr) +{ + struct _lnet_hdr_nid4 *hdr_nid4 = (void *)vhdr; + + hdr_nid4->dest_nid = cpu_to_le64(lnet_nid_to_nid4(&hdr->dest_nid)); + hdr_nid4->src_nid = cpu_to_le64(lnet_nid_to_nid4(&hdr->src_nid)); + hdr_nid4->dest_pid = cpu_to_le32(hdr->dest_pid); + hdr_nid4->src_pid = cpu_to_le32(hdr->src_pid); + hdr_nid4->type = cpu_to_le32(hdr->type); + hdr_nid4->payload_length = cpu_to_le32(hdr->payload_length); + + hdr_nid4->msg = hdr->msg; +} + +static inline void lnet_hdr_from_nid16(struct lnet_hdr *hdr, + const struct lnet_hdr_nid16 *vhdr) +{ + const struct lnet_hdr *hdr16 = (void *)vhdr; + + hdr->dest_nid = hdr16->dest_nid; + hdr->src_nid = hdr16->src_nid; + hdr->dest_pid = le32_to_cpu(hdr16->dest_pid); + hdr->src_pid = le32_to_cpu(hdr16->src_pid); + hdr->type = le32_to_cpu(hdr16->type); + hdr->payload_length = le32_to_cpu(hdr16->payload_length); +} + +static inline void lnet_hdr_to_nid16(const struct lnet_hdr *hdr, + struct lnet_hdr_nid16 *vhdr) +{ + struct lnet_hdr *hdr16 = (void *)vhdr; + + hdr16->dest_nid = hdr->dest_nid; + hdr16->src_nid = hdr->src_nid; + hdr16->dest_pid = cpu_to_le32(hdr->dest_pid); + hdr16->src_pid = cpu_to_le32(hdr->src_pid); + hdr16->type = cpu_to_le32(hdr->type); + hdr16->payload_length = cpu_to_le32(hdr->payload_length); +} + extern const 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 unsigned int lnet_nid_cpt_hash(struct lnet_nid *nid, + unsigned int number); +extern int lnet_cpt_of_nid_locked(struct lnet_nid *nid, struct lnet_ni *ni); extern int lnet_cpt_of_nid(lnet_nid_t nid, struct lnet_ni *ni); +extern int lnet_nid2cpt(struct lnet_nid *nid, struct lnet_ni *ni); extern struct lnet_ni *lnet_nid2ni_locked(lnet_nid_t nid, int cpt); +extern struct lnet_ni *lnet_nid_to_ni_locked(struct lnet_nid *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); +extern struct lnet_ni *lnet_nid_to_ni_addref(struct lnet_nid *nid); 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 lnet_max_recovery_ping_interval; +extern unsigned int lnet_max_recovery_ping_count; extern unsigned int router_sensitivity_percentage; extern int alive_router_check_interval; extern int live_router_check_interval; @@ -517,9 +624,11 @@ 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, time64_t when); -int lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway_nid, +int lnet_add_route(__u32 net, __u32 hops, struct lnet_nid *gateway, __u32 priority, __u32 sensitivity); -int lnet_del_route(__u32 net, lnet_nid_t gw_nid); +int lnet_del_route(__u32 net, struct lnet_nid *gw_nid); +void lnet_move_route(struct lnet_route *route, struct lnet_peer *lp, + struct list_head *rt_list); void lnet_destroy_routes(void); int lnet_get_route(int idx, __u32 *net, __u32 *hops, lnet_nid_t *gateway, __u32 *alive, __u32 *priority, @@ -528,13 +637,26 @@ 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, + struct lnet_nid *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, + struct lnet_nid *nid); +void lnet_peer_ni_set_selection_priority(struct lnet_peer_ni *lpni, + __u32 priority); +extern void lnet_ni_add_to_recoveryq_locked(struct lnet_ni *ni, + struct list_head *queue, + time64_t now); void lnet_router_debugfs_init(void); void lnet_router_debugfs_fini(void); @@ -553,8 +675,10 @@ 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, struct lnet_nid *gw_nid); -int lnet_islocalnid(lnet_nid_t nid); +int lnet_islocalnid(struct lnet_nid *nid); int lnet_islocalnet(__u32 net); int lnet_islocalnet_locked(__u32 net); @@ -565,13 +689,14 @@ 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, + struct lnet_processid *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_eq *eq, bool recovery); +int lnet_send(struct lnet_nid *nid, struct lnet_msg *msg, + struct lnet_nid *rtr_nid); +int lnet_send_ping(struct lnet_nid *dest_nid, struct lnet_handle_md *mdh, + int nnis, void *user_ptr, lnet_handler_t handler, + 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); @@ -613,9 +738,9 @@ lnet_ptl_unsetopt(struct lnet_portal *ptl, int opt) /* match-table functions */ struct list_head *lnet_mt_match_head(struct lnet_match_table *mtable, - struct lnet_process_id id, __u64 mbits); + struct lnet_processid *id, __u64 mbits); struct lnet_match_table *lnet_mt_of_attach(unsigned int index, - struct lnet_process_id id, + struct lnet_processid *id, __u64 mbits, __u64 ignore_bits, enum lnet_ins_pos pos); int lnet_mt_match_md(struct lnet_match_table *mtable, @@ -633,7 +758,7 @@ void lnet_portals_destroy(void); /* message functions */ int lnet_parse(struct lnet_ni *ni, struct lnet_hdr *hdr, - lnet_nid_t fromnid, void *private, int rdma_req); + struct lnet_nid *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); @@ -643,6 +768,7 @@ void lnet_recv(struct lnet_ni *ni, void *private, struct lnet_msg *msg, 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); +void lnet_ni_send(struct lnet_ni *ni, struct lnet_msg *msg); struct lnet_msg *lnet_create_reply_msg(struct lnet_ni *ni, struct lnet_msg *get_msg); @@ -651,6 +777,7 @@ 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); @@ -668,7 +795,6 @@ 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 @{ */ @@ -677,7 +803,7 @@ 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(struct lnet_hdr *hdr, lnet_nid_t local_nid, +bool lnet_drop_rule_match(struct lnet_hdr *hdr, struct lnet_nid *local_nid, enum lnet_msg_hstatus *hstatus); int lnet_delay_rule_add(struct lnet_fault_attr *attr); @@ -691,50 +817,46 @@ 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; +} + +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); -int lnet_extract_iov(int dst_niov, struct kvec *dst, - int src_niov, struct kvec *src, +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, unsigned int offset, unsigned int len); -unsigned int lnet_kiov_nob (unsigned int niov, lnet_kiov_t *iov); -int lnet_extract_kiov(int dst_niov, lnet_kiov_t *dst, - int src_niov, lnet_kiov_t *src, - unsigned int offset, unsigned int len); - void lnet_copy_iov2iov(unsigned int ndiov, struct kvec *diov, unsigned int doffset, unsigned int nsiov, struct kvec *siov, unsigned int soffset, unsigned int nob); void lnet_copy_kiov2iov(unsigned int niov, struct kvec *iov, unsigned int iovoffset, - unsigned int nkiov, lnet_kiov_t *kiov, + unsigned int nkiov, struct bio_vec *kiov, unsigned int kiovoffset, unsigned int nob); -void lnet_copy_iov2kiov(unsigned int nkiov, lnet_kiov_t *kiov, +void lnet_copy_iov2kiov(unsigned int nkiov, struct bio_vec *kiov, unsigned int kiovoffset, unsigned int niov, struct kvec *iov, unsigned int iovoffset, unsigned int nob); -void lnet_copy_kiov2kiov(unsigned int ndkiov, lnet_kiov_t *dkiov, +void lnet_copy_kiov2kiov(unsigned int ndkiov, struct bio_vec *dkiov, unsigned int doffset, - unsigned int nskiov, lnet_kiov_t *skiov, + unsigned int nskiov, struct bio_vec *skiov, 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, lnet_kiov_t *skiov, + unsigned int nsiov, struct bio_vec *skiov, unsigned int soffset, unsigned int nob) { struct kvec diov = { .iov_base = dest, .iov_len = dlen }; @@ -744,17 +866,7 @@ 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, lnet_kiov_t *dkiov, +lnet_copy_flat2kiov(unsigned int ndiov, struct bio_vec *dkiov, unsigned int doffset, int slen, void *src, unsigned int soffset, unsigned int nob) { @@ -766,18 +878,19 @@ lnet_copy_flat2kiov(unsigned int ndiov, lnet_kiov_t *dkiov, void lnet_me_unlink(struct lnet_me *me); void lnet_md_unlink(struct lnet_libmd *md); -void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_md *umd); +void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_event *ev); struct page *lnet_kvaddr_to_page(unsigned long vaddr); +struct page *lnet_get_first_page(struct lnet_libmd *md, unsigned int offset); int lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset); 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); -int lnet_connect(struct socket **sockp, lnet_nid_t peer_nid, - __u32 local_ip, __u32 peer_ip, int peer_port, struct net *ns); -void lnet_connect_console_error(int rc, lnet_nid_t peer_nid, - __u32 peer_ip, int port); +struct socket *lnet_connect(struct lnet_nid *peer_nid, int interface, + struct sockaddr *peeraddr, struct net *ns); +void lnet_connect_console_error(int rc, struct lnet_nid *peer_nid, + struct sockaddr *sa); int lnet_count_acceptor_nets(void); int lnet_acceptor_timeout(void); int lnet_acceptor_port(void); @@ -793,17 +906,18 @@ 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); -int lnet_sock_listen(struct socket **sockp, __u32 ip, int port, int backlog, - struct net *ns); -int lnet_sock_connect(struct socket **sockp, int *fatal, - __u32 local_ip, int local_port, - __u32 peer_ip, int peer_port, struct net *ns); +struct socket *lnet_sock_listen(int port, int backlog, + struct net *ns); +struct socket *lnet_sock_connect(int interface, int local_port, + struct sockaddr *peeraddr, + struct net *ns); int lnet_peers_start_down(void); int lnet_peer_buffer_credits(struct lnet_net *net); @@ -831,8 +945,10 @@ static inline void lnet_ping_buffer_addref(struct lnet_ping_buffer *pbuf) static inline void lnet_ping_buffer_decref(struct lnet_ping_buffer *pbuf) { - if (atomic_dec_and_test(&pbuf->pb_refcnt)) + if (atomic_dec_and_test(&pbuf->pb_refcnt)) { + wake_up_var(&pbuf->pb_refcnt); lnet_ping_buffer_free(pbuf); + } } static inline int lnet_push_target_resize_needed(void) @@ -845,17 +961,14 @@ int lnet_push_target_post(struct lnet_ping_buffer *pbuf, struct lnet_handle_md *mdh); 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); -int lnet_parse_networks(struct list_head *nilist, char *networks, - bool use_tcp_bonding); +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 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); void lnet_incr_dlc_seq(void); __u32 lnet_get_dlc_seq_locked(void); -int lnet_get_net_count(void); -extern unsigned int lnet_current_net_count; struct lnet_peer_net *lnet_get_next_peer_net_locked(struct lnet_peer *lp, __u32 prev_lpn_id); @@ -864,14 +977,23 @@ struct lnet_peer_ni *lnet_get_next_peer_ni_locked(struct lnet_peer *peer, 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_peerni_by_nid_locked(struct lnet_nid *nid, + struct lnet_nid *pref, + int cpt); +struct lnet_peer_ni *lnet_nid2peerni_ex(struct lnet_nid *nid); struct lnet_peer_ni *lnet_peer_get_ni_locked(struct lnet_peer *lp, lnet_nid_t nid); +struct lnet_peer_ni *lnet_peer_ni_get_locked(struct lnet_peer *lp, + struct lnet_nid *nid); struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid); -struct lnet_peer *lnet_find_peer(lnet_nid_t nid); +struct lnet_peer_ni *lnet_peer_ni_find_locked(struct lnet_nid *nid); +struct lnet_peer *lnet_find_peer4(lnet_nid_t nid); +struct lnet_peer *lnet_find_peer(struct lnet_nid *nid); void lnet_peer_net_added(struct lnet_net *net); -lnet_nid_t lnet_peer_primary_nid_locked(lnet_nid_t nid); +void lnet_peer_primary_nid_locked(struct lnet_nid *nid, + struct lnet_nid *result); 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); @@ -881,9 +1003,17 @@ int lnet_peer_tables_create(void); 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_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); +bool lnet_peer_is_pref_nid_locked(struct lnet_peer_ni *lpni, + struct lnet_nid *nid); +int lnet_peer_add_pref_nid(struct lnet_peer_ni *lpni, struct lnet_nid *nid); +void lnet_peer_clr_pref_nids(struct lnet_peer_ni *lpni); +bool lnet_peer_is_pref_rtr_locked(struct lnet_peer_ni *lpni, + struct lnet_nid *gw_nid); +void lnet_peer_clr_pref_rtrs(struct lnet_peer_ni *lpni); +int lnet_peer_add_pref_rtr(struct lnet_peer_ni *lpni, struct lnet_nid *nid); +int lnet_peer_ni_set_non_mr_pref_nid(struct lnet_peer_ni *lpni, + struct lnet_nid *nid); +int lnet_add_peer_ni(lnet_nid_t key_nid, lnet_nid_t nid, bool mr, bool temp); 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, @@ -894,6 +1024,13 @@ 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) { @@ -926,7 +1063,8 @@ lnet_peer_ni_is_configured(struct lnet_peer_ni *lpni) 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; + return nid_same(&lpni->lpni_nid, + &lpni->lpni_peer_net->lpn_peer->lp_primary_nid); } bool lnet_peer_is_uptodate(struct lnet_peer *lp); @@ -940,6 +1078,8 @@ 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) @@ -952,9 +1092,36 @@ lnet_peer_needs_push(struct lnet_peer *lp) return false; } +static inline unsigned int +lnet_get_next_recovery_ping(unsigned int ping_count, time64_t now) +{ + unsigned int interval; + + /* lnet_max_recovery_interval <= 2^lnet_max_recovery_ping_count */ + if (ping_count > lnet_max_recovery_ping_count) + interval = lnet_max_recovery_ping_interval; + 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); +} + +static inline void +lnet_ni_set_next_ping(struct lnet_ni *ni, time64_t now) +{ + ni->ni_next_ping = lnet_get_next_recovery_ping(ni->ni_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 @@ -994,18 +1161,62 @@ lnet_set_lpni_healthv_locked(struct lnet_peer_ni *lpni, int value) lnet_update_peer_net_healthv(lpni); } +static inline bool +lnet_atomic_add_unless_max(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + bool mod = false; + int old; + int m; + + if (c == u) + return mod; + + for (;;) { + if (c + a >= u) + m = u; + else + m = c + a; + old = atomic_cmpxchg(v, c, m); + + if (old == u) + break; + + if (old == c) { + mod = true; + break; + } + c = old; + } + + return mod; +} + static inline void -lnet_inc_lpni_healthv_locked(struct lnet_peer_ni *lpni) +lnet_inc_lpni_healthv_locked(struct lnet_peer_ni *lpni, int value) { /* only adjust the net health if the lpni health value changed */ - if (atomic_add_unless(&lpni->lpni_healthv, 1, LNET_MAX_HEALTH_VALUE)) + if (lnet_atomic_add_unless_max(&lpni->lpni_healthv, value, + LNET_MAX_HEALTH_VALUE)) lnet_update_peer_net_healthv(lpni); } static inline void -lnet_inc_healthv(atomic_t *healthv) +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) { - atomic_add_unless(healthv, 1, LNET_MAX_HEALTH_VALUE); + struct list_head *l; + int count = 0; + + list_for_each(l, list) + count++; + + return count; } void lnet_incr_stats(struct lnet_element_stats *stats, @@ -1018,4 +1229,16 @@ __u32 lnet_sum_stats(struct lnet_element_stats *stats, void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats, struct lnet_element_stats *stats); +static inline void +lnet_set_route_aliveness(struct lnet_route *route, bool alive) +{ + bool old = atomic_xchg(&route->lr_alive, alive); + + if (old != alive) + CERROR("route to %s through %s has gone from %s to %s\n", + libcfs_net2str(route->lr_net), + libcfs_nidstr(&route->lr_gateway->lp_primary_nid), + old ? "up" : "down", + alive ? "up" : "down"); +} #endif