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=f4868e08a2ec482f19f91f5e0e2e3f5babe5605e;hb=d123c47a18adbf5665ed63d99c53117b84db9ec8;hpb=b01e6fce1c988139b5fe59484c7568362992f37b

diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h
index f4868e0..176c9a2 100644
--- a/lnet/include/lnet/lib-lnet.h
+++ b/lnet/include/lnet/lib-lnet.h
@@ -37,9 +37,10 @@
 #ifndef __LNET_LIB_LNET_H__
 #define __LNET_LIB_LNET_H__
 
-#ifndef __KERNEL__
-# error This include is only for kernel use.
-#endif
+/* LNET has 0xeXXX */
+#define CFS_FAIL_PTLRPC_OST_BULK_CB2	0xe000
+
+#include <linux/netdevice.h>
 
 #include <libcfs/libcfs.h>
 #include <lnet/api.h>
@@ -73,19 +74,44 @@ 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 DEFAULT_PEER_CREDITS    8
+#define DEFAULT_CREDITS         256
+
+#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
 
-static inline int lnet_is_route_alive(struct lnet_route *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;
-}
+/*
+ * 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
+
+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);
 
 static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh)
 {
@@ -177,72 +203,73 @@ 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;
-
-	LIBCFS_ALLOC(eq, sizeof(*eq));
-	return (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_nid2str(ni->ni_nid),
+		       ni->ni_status->ns_status, status);
+		ni->ni_status->ns_status = status;
+		update = true;
+	}
 
-static inline void
-lnet_eq_free(struct lnet_eq *eq)
-{
-	LIBCFS_FREE(eq, sizeof(*eq));
+	return update;
 }
 
-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);
+#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);
 	}
-
-	return md;
+	finish_wait(wq, wqe);
 }
 
 static inline void
@@ -250,10 +277,9 @@ lnet_md_free(struct lnet_libmd *md)
 {
 	unsigned int  size;
 
-	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]);
+	LASSERTF(md->md_rspt_ptr == NULL, "md %p rsp %p\n", md, md->md_rspt_ptr);
+
+	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);
@@ -263,28 +289,6 @@ lnet_md_free(struct lnet_libmd *md)
 	}
 }
 
-static inline struct lnet_me *
-lnet_me_alloc (void)
-{
-	struct lnet_me *me;
-
-	me = kmem_cache_alloc(lnet_mes_cachep, GFP_NOFS | __GFP_ZERO);
-
-	if (me)
-		CDEBUG(D_MALLOC, "slab-alloced 'me' at %p.\n", me);
-	else
-		CDEBUG(D_MALLOC, "failed to allocate 'me'\n");
-
-	return me;
-}
-
-static inline void
-lnet_me_free(struct lnet_me *me)
-{
-	CDEBUG(D_MALLOC, "slab-freed 'me' at %p.\n", me);
-	kmem_cache_free(lnet_mes_cachep, me);
-}
-
 struct lnet_libhandle *lnet_res_lh_lookup(struct lnet_res_container *rec,
 				     __u64 cookie);
 void lnet_res_lh_initialize(struct lnet_res_container *rec,
@@ -298,30 +302,6 @@ lnet_res_lh_invalidate(struct lnet_libhandle *lh)
 }
 
 static inline void
-lnet_eq2handle(struct lnet_handle_eq *handle, struct lnet_eq *eq)
-{
-	if (eq == NULL) {
-		LNetInvalidateEQHandle(handle);
-		return;
-	}
-
-	handle->cookie = eq->eq_lh.lh_cookie;
-}
-
-static inline struct lnet_eq *
-lnet_handle2eq(struct lnet_handle_eq *handle)
-{
-	/* ALWAYS called with resource lock held */
-	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, struct lnet_eq, eq_lh);
-}
-
-static inline void
 lnet_md2handle(struct lnet_handle_md *handle, struct lnet_libmd *md)
 {
 	handle->cookie = md->md_lh.lh_cookie;
@@ -363,28 +343,6 @@ lnet_wire_handle2md(struct lnet_handle_wire *wh)
 }
 
 static inline void
-lnet_me2handle(struct lnet_handle_me *handle, struct lnet_me *me)
-{
-	handle->cookie = me->me_lh.lh_cookie;
-}
-
-static inline struct lnet_me *
-lnet_handle2me(struct lnet_handle_me *handle)
-{
-	/* ALWAYS called with resource lock held */
-	struct lnet_libhandle *lh;
-	int		 cpt;
-
-	cpt = lnet_cpt_of_cookie(handle->cookie);
-	lh = lnet_res_lh_lookup(the_lnet.ln_me_containers[cpt],
-				handle->cookie);
-	if (lh == NULL)
-		return NULL;
-
-	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);
@@ -432,9 +390,9 @@ lnet_peer_ni_decref_locked(struct lnet_peer_ni *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
@@ -476,9 +434,8 @@ lnet_msg_alloc(void)
 {
 	struct lnet_msg *msg;
 
-	LIBCFS_ALLOC(msg, sizeof(*msg));
+	msg = kmem_cache_zalloc(lnet_msg_cachep, GFP_NOFS);
 
-	/* no need to zero, LIBCFS_ALLOC does for us */
 	return (msg);
 }
 
@@ -486,7 +443,33 @@ static inline void
 lnet_msg_free(struct lnet_msg *msg)
 {
 	LASSERT(!msg->msg_onactivelist);
-	LIBCFS_FREE(msg, sizeof(*msg));
+	kmem_cache_free(lnet_msg_cachep, msg);
+}
+
+static inline struct lnet_rsp_tracker *
+lnet_rspt_alloc(int cpt)
+{
+	struct lnet_rsp_tracker *rspt;
+
+	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++;
+		lnet_net_unlock(cpt);
+	}
+	CDEBUG(D_MALLOC, "rspt alloc %p\n", rspt);
+	return rspt;
+}
+
+static inline void
+lnet_rspt_free(struct lnet_rsp_tracker *rspt, int cpt)
+{
+	CDEBUG(D_MALLOC, "rspt free %p\n", rspt);
+
+	kmem_cache_free(lnet_rspt_cachep, 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);
@@ -516,7 +499,7 @@ lnet_net2rnethash(__u32 net)
 		((1U << the_lnet.ln_remote_nets_hbits) - 1)];
 }
 
-extern struct lnet_lnd the_lolnd;
+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);
@@ -526,51 +509,61 @@ 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);
-bool lnet_is_ni_healthy_locked(struct lnet_ni *ni);
 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;
+extern int alive_router_check_interval;
+extern int live_router_check_interval;
+extern int dead_router_check_interval;
 extern int portal_rotor;
 
-int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, int alive,
+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,
 			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_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);
+		   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);
+int lnet_get_net_healthv_locked(struct lnet_net *net);
 
-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,
+						 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);
@@ -580,6 +573,8 @@ 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);
+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);
@@ -587,28 +582,33 @@ 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);
+int lnet_islocalnet_locked(__u32 net);
 
 void lnet_msg_attach_md(struct lnet_msg *msg, struct lnet_libmd *md,
 			unsigned int offset, unsigned int mlen);
-void lnet_msg_detach_md(struct lnet_msg *msg, int status);
 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, 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);
 void lnet_drop_routed_msgs_locked(struct list_head *list, int cpt);
 
+struct list_head **lnet_create_array_of_queues(void);
+
 /* portals functions */
 /* portals attributes */
 static inline int
@@ -678,8 +678,14 @@ 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_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);
+void lnet_handle_remote_failure_locked(struct lnet_peer_ni *lpni);
 
 void lnet_drop_message(struct lnet_ni *ni, int cpt, void *private,
 		       unsigned int nob, __u32 msg_type);
@@ -691,8 +697,8 @@ void lnet_msg_container_cleanup(struct lnet_msg_container *container);
 void lnet_msg_containers_destroy(void);
 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 @{ */
@@ -701,7 +707,8 @@ 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(struct lnet_hdr *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);
@@ -713,50 +720,47 @@ bool lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg);
 
 /** @} lnet_fault_simulation */
 
-void lnet_counters_get(struct lnet_counters *counters);
+void lnet_counters_get_common(struct lnet_counters_common *common);
+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 };
@@ -766,17 +770,7 @@ 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)
 {
@@ -788,51 +782,59 @@ 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);
 int lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset);
 
-void lnet_register_lnd(struct lnet_lnd *lnd);
-void lnet_unregister_lnd(struct lnet_lnd *lnd);
+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 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);
 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);
+struct lnet_inetdev {
+	u32	li_cpt;
+	u32	li_flags;
+	u32	li_ipaddr;
+	u32	li_netmask;
+	char	li_name[IFNAMSIZ];
+};
+
+int lnet_inet_enumerate(struct lnet_inetdev **dev_list, struct net *ns);
+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);
-int lnet_sock_accept(struct socket **newsockp, struct socket *sock);
-int lnet_sock_connect(struct socket **sockp, int *fatal,
-			__u32 local_ip, int local_port,
-			__u32 peer_ip, int peer_port);
+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);
+void lnet_consolidate_routes_locked(struct lnet_peer *orig_lp,
+				    struct lnet_peer *new_lp);
+void lnet_router_discovery_complete(struct lnet_peer *lp);
+void lnet_router_discovery_ping_reply(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);
-int lnet_router_pre_mt_start(void);
-void lnet_router_post_mt_start(void);
-void lnet_prune_rc_data(int wait_unlink);
-void lnet_router_cleanup(void);
-void lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net);
+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);
@@ -846,13 +848,10 @@ 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_ping_buffer_numref(struct lnet_ping_buffer *pbuf)
-{
-	return atomic_read(&pbuf->pb_refcnt);
+	}
 }
 
 static inline int lnet_push_target_resize_needed(void)
@@ -861,29 +860,37 @@ static inline int lnet_push_target_resize_needed(void)
 }
 
 int lnet_push_target_resize(void);
+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);
 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);
+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);
@@ -894,6 +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);
@@ -904,45 +916,14 @@ int lnet_get_peer_ni_info(__u32 peer_index, __u64 *nid,
 			  __u32 *ni_peer_tx_credits, __u32 *peer_tx_credits,
 			  __u32 *peer_rtr_credits, __u32 *peer_min_rtr_credtis,
 			  __u32 *peer_tx_qnob);
-
-static inline bool
-lnet_is_peer_ni_healthy_locked(struct lnet_peer_ni *lpni)
-{
-	return lpni->lpni_healthy;
-}
+int lnet_get_peer_ni_hstats(struct lnet_ioctl_peer_ni_hstats *stats);
 
 static inline void
-lnet_set_peer_ni_health_locked(struct lnet_peer_ni *lpni, bool health)
+lnet_peer_net_set_sel_priority_locked(struct lnet_peer_net *lpn, __u32 priority)
 {
-	lpni->lpni_healthy = health;
+	lpn->lpn_sel_priority = priority;
 }
 
-static inline bool
-lnet_is_peer_net_healthy_locked(struct lnet_peer_net *peer_net)
-{
-	struct lnet_peer_ni *lpni;
-
-	list_for_each_entry(lpni, &peer_net->lpn_peer_nis,
-			    lpni_peer_nis) {
-		if (lnet_is_peer_ni_healthy_locked(lpni))
-			return true;
-	}
-
-	return false;
-}
-
-static inline bool
-lnet_is_peer_healthy_locked(struct lnet_peer *peer)
-{
-	struct lnet_peer_net *peer_net;
-
-	list_for_each_entry(peer_net, &peer->lp_peer_nets, lpn_peer_nets) {
-		if (lnet_is_peer_net_healthy_locked(peer_net))
-			return true;
-	}
-
-	return false;
-}
 
 static inline struct lnet_peer_net *
 lnet_find_peer_net_locked(struct lnet_peer *peer, __u32 net_id)
@@ -957,15 +938,6 @@ lnet_find_peer_net_locked(struct lnet_peer *peer, __u32 net_id)
 	return NULL;
 }
 
-static inline void
-lnet_peer_set_alive(struct lnet_peer_ni *lp)
-{
-	lp->lpni_last_alive = ktime_get_seconds();
-	lp->lpni_last_query = lp->lpni_last_alive;
-	if (!lp->lpni_alive)
-		lnet_notify_locked(lp, 0, 1, lp->lpni_last_alive);
-}
-
 static inline bool
 lnet_peer_is_multi_rail(struct lnet_peer *lp)
 {
@@ -989,21 +961,152 @@ lnet_peer_ni_is_primary(struct lnet_peer_ni *lpni)
 }
 
 bool lnet_peer_is_uptodate(struct lnet_peer *lp);
+bool lnet_peer_is_uptodate_locked(struct lnet_peer *lp);
+bool lnet_is_discovery_disabled(struct lnet_peer *lp);
+bool lnet_is_discovery_disabled_locked(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_MARK_DELETED)
+		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;
 }
 
+#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 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
+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_update_peer_net_healthv(struct lnet_peer_ni *lpni)
+{
+	struct lnet_peer_net *lpn;
+	int best_healthv = 0;
+
+	lpn = lpni->lpni_peer_net;
+
+	list_for_each_entry(lpni, &lpn->lpn_peer_nis, lpni_peer_nis) {
+		int lpni_healthv = atomic_read(&lpni->lpni_healthv);
+		if (best_healthv < lpni_healthv)
+			best_healthv = lpni_healthv;
+	}
+
+	lpn->lpn_healthv = best_healthv;
+}
+
+static inline void
+lnet_set_lpni_healthv_locked(struct lnet_peer_ni *lpni, int value)
+{
+	if (atomic_read(&lpni->lpni_healthv) == value)
+		return;
+	atomic_set(&lpni->lpni_healthv, 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, int value)
+{
+	/* only adjust the net health if the lpni health value changed */
+	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, 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);