+ struct lnet_nid_list *ne;
+
+ if (lpni->lpni_pref_nnids == 0)
+ return false;
+ if (lpni->lpni_pref_nnids == 1)
+ return lpni->lpni_pref.nid == nid;
+ list_for_each_entry(ne, &lpni->lpni_pref.nids, nl_list) {
+ if (ne->nl_nid == nid)
+ return true;
+ }
+ return false;
+}
+
+/*
+ * Set a single ni as preferred, provided no preferred ni is already
+ * defined. Only to be used for non-multi-rail peer_ni.
+ */
+int
+lnet_peer_ni_set_non_mr_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid)
+{
+ int rc = 0;
+
+ spin_lock(&lpni->lpni_lock);
+ if (nid == LNET_NID_ANY) {
+ rc = -EINVAL;
+ } else if (lpni->lpni_pref_nnids > 0) {
+ rc = -EPERM;
+ } else if (lpni->lpni_pref_nnids == 0) {
+ lpni->lpni_pref.nid = nid;
+ lpni->lpni_pref_nnids = 1;
+ lpni->lpni_state |= LNET_PEER_NI_NON_MR_PREF;
+ }
+ spin_unlock(&lpni->lpni_lock);
+
+ CDEBUG(D_NET, "peer %s nid %s: %d\n",
+ libcfs_nid2str(lpni->lpni_nid), libcfs_nid2str(nid), rc);
+ return rc;
+}
+
+/*
+ * Clear the preferred NID from a non-multi-rail peer_ni, provided
+ * this preference was set by lnet_peer_ni_set_non_mr_pref_nid().
+ */
+int
+lnet_peer_ni_clr_non_mr_pref_nid(struct lnet_peer_ni *lpni)
+{
+ int rc = 0;
+
+ spin_lock(&lpni->lpni_lock);
+ if (lpni->lpni_state & LNET_PEER_NI_NON_MR_PREF) {
+ lpni->lpni_pref_nnids = 0;
+ lpni->lpni_state &= ~LNET_PEER_NI_NON_MR_PREF;
+ } else if (lpni->lpni_pref_nnids == 0) {
+ rc = -ENOENT;
+ } else {
+ rc = -EPERM;
+ }
+ spin_unlock(&lpni->lpni_lock);
+
+ CDEBUG(D_NET, "peer %s: %d\n",
+ libcfs_nid2str(lpni->lpni_nid), rc);
+ return rc;
+}
+
+void
+lnet_peer_ni_set_selection_priority(struct lnet_peer_ni *lpni, __u32 priority)
+{
+ lpni->lpni_sel_priority = priority;
+}
+
+/*
+ * Clear the preferred NIDs from a non-multi-rail peer.
+ */
+void
+lnet_peer_clr_non_mr_pref_nids(struct lnet_peer *lp)
+{
+ struct lnet_peer_ni *lpni = NULL;
+
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL)
+ lnet_peer_ni_clr_non_mr_pref_nid(lpni);
+}
+
+int
+lnet_peer_add_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid)
+{
+ struct lnet_peer *lp = lpni->lpni_peer_net->lpn_peer;
+ struct lnet_nid_list *ne1 = NULL;
+ struct lnet_nid_list *ne2 = NULL;
+ lnet_nid_t tmp_nid = LNET_NID_ANY;
+ int rc = 0;
+
+ if (nid == LNET_NID_ANY) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (lpni->lpni_pref_nnids == 1 && lpni->lpni_pref.nid == nid) {
+ rc = -EEXIST;
+ goto out;
+ }
+
+ /* A non-MR node may have only one preferred NI per peer_ni */
+ if (lpni->lpni_pref_nnids > 0 &&
+ !(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ rc = -EPERM;
+ goto out;
+ }
+
+ /* add the new preferred nid to the list of preferred nids */
+ if (lpni->lpni_pref_nnids != 0) {
+ size_t alloc_size = sizeof(*ne1);
+
+ if (lpni->lpni_pref_nnids == 1) {
+ tmp_nid = lpni->lpni_pref.nid;
+ INIT_LIST_HEAD(&lpni->lpni_pref.nids);
+ }
+
+ list_for_each_entry(ne1, &lpni->lpni_pref.nids, nl_list) {
+ if (ne1->nl_nid == nid) {
+ rc = -EEXIST;
+ goto out;
+ }
+ }
+
+ LIBCFS_CPT_ALLOC(ne1, lnet_cpt_table(), lpni->lpni_cpt,
+ alloc_size);
+ if (!ne1) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* move the originally stored nid to the list */
+ if (lpni->lpni_pref_nnids == 1) {
+ LIBCFS_CPT_ALLOC(ne2, lnet_cpt_table(),
+ lpni->lpni_cpt, alloc_size);
+ if (!ne2) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ INIT_LIST_HEAD(&ne2->nl_list);
+ ne2->nl_nid = tmp_nid;
+ }
+ ne1->nl_nid = nid;
+ }
+
+ lnet_net_lock(LNET_LOCK_EX);
+ spin_lock(&lpni->lpni_lock);
+ if (lpni->lpni_pref_nnids == 0) {
+ lpni->lpni_pref.nid = nid;
+ } else {
+ if (ne2)
+ list_add_tail(&ne2->nl_list, &lpni->lpni_pref.nids);
+ list_add_tail(&ne1->nl_list, &lpni->lpni_pref.nids);
+ }
+ lpni->lpni_pref_nnids++;
+ lpni->lpni_state &= ~LNET_PEER_NI_NON_MR_PREF;
+ spin_unlock(&lpni->lpni_lock);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+out:
+ if (rc == -EEXIST && (lpni->lpni_state & LNET_PEER_NI_NON_MR_PREF)) {
+ spin_lock(&lpni->lpni_lock);
+ lpni->lpni_state &= ~LNET_PEER_NI_NON_MR_PREF;
+ spin_unlock(&lpni->lpni_lock);
+ }
+ CDEBUG(D_NET, "peer %s nid %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), libcfs_nid2str(nid), rc);
+ return rc;
+}
+
+int
+lnet_peer_del_pref_nid(struct lnet_peer_ni *lpni, lnet_nid_t nid)
+{
+ struct lnet_peer *lp = lpni->lpni_peer_net->lpn_peer;
+ struct lnet_nid_list *ne = NULL;
+ int rc = 0;
+
+ if (lpni->lpni_pref_nnids == 0) {
+ rc = -ENOENT;
+ goto out;
+ }
+
+ if (lpni->lpni_pref_nnids == 1) {
+ if (lpni->lpni_pref.nid != nid) {
+ rc = -ENOENT;
+ goto out;
+ }
+ } else {
+ list_for_each_entry(ne, &lpni->lpni_pref.nids, nl_list) {
+ if (ne->nl_nid == nid)
+ goto remove_nid_entry;
+ }
+ rc = -ENOENT;
+ ne = NULL;
+ goto out;
+ }
+
+remove_nid_entry:
+ lnet_net_lock(LNET_LOCK_EX);
+ spin_lock(&lpni->lpni_lock);
+ if (lpni->lpni_pref_nnids == 1)
+ lpni->lpni_pref.nid = LNET_NID_ANY;
+ else {
+ list_del_init(&ne->nl_list);
+ if (lpni->lpni_pref_nnids == 2) {
+ struct lnet_nid_list *ne, *tmp;
+
+ list_for_each_entry_safe(ne, tmp,
+ &lpni->lpni_pref.nids,
+ nl_list) {
+ lpni->lpni_pref.nid = ne->nl_nid;
+ list_del_init(&ne->nl_list);
+ LIBCFS_FREE(ne, sizeof(*ne));
+ }
+ }
+ }
+ lpni->lpni_pref_nnids--;
+ lpni->lpni_state &= ~LNET_PEER_NI_NON_MR_PREF;
+ spin_unlock(&lpni->lpni_lock);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ if (ne)
+ LIBCFS_FREE(ne, sizeof(*ne));
+out:
+ CDEBUG(D_NET, "peer %s nid %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), libcfs_nid2str(nid), rc);
+ return rc;
+}
+
+void
+lnet_peer_clr_pref_nids(struct lnet_peer_ni *lpni)
+{
+ struct list_head zombies;
+ struct lnet_nid_list *ne;
+ struct lnet_nid_list *tmp;
+
+ INIT_LIST_HEAD(&zombies);
+
+ lnet_net_lock(LNET_LOCK_EX);
+ if (lpni->lpni_pref_nnids == 1)
+ lpni->lpni_pref.nid = LNET_NID_ANY;
+ else if (lpni->lpni_pref_nnids > 1)
+ list_splice_init(&lpni->lpni_pref.nids, &zombies);
+ lpni->lpni_pref_nnids = 0;
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ list_for_each_entry_safe(ne, tmp, &zombies, nl_list) {
+ list_del_init(&ne->nl_list);
+ LIBCFS_FREE(ne, sizeof(*ne));
+ }
+}
+
+lnet_nid_t
+lnet_peer_primary_nid_locked(lnet_nid_t nid)
+{
+ struct lnet_peer_ni *lpni;
+ lnet_nid_t primary_nid = nid;
+
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni) {
+ primary_nid = lpni->lpni_peer_net->lpn_peer->lp_primary_nid;
+ lnet_peer_ni_decref_locked(lpni);
+ }
+
+ return primary_nid;
+}
+
+bool
+lnet_is_discovery_disabled_locked(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ if (lnet_peer_discovery_disabled)
+ return true;
+
+ if (!(lp->lp_state & LNET_PEER_MULTI_RAIL) ||
+ (lp->lp_state & LNET_PEER_NO_DISCOVERY)) {
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Peer Discovery
+ */
+bool
+lnet_is_discovery_disabled(struct lnet_peer *lp)
+{
+ bool rc = false;
+
+ spin_lock(&lp->lp_lock);
+ rc = lnet_is_discovery_disabled_locked(lp);
+ spin_unlock(&lp->lp_lock);
+
+ return rc;
+}
+
+lnet_nid_t
+LNetPrimaryNID(lnet_nid_t nid)
+{
+ struct lnet_peer *lp;
+ struct lnet_peer_ni *lpni;
+ lnet_nid_t primary_nid = nid;
+ int rc = 0;
+ int cpt;
+
+ if (nid == LNET_NID_LO_0)
+ return LNET_NID_LO_0;
+
+ cpt = lnet_net_lock_current();
+ lpni = lnet_nid2peerni_locked(nid, LNET_NID_ANY, cpt);
+ if (IS_ERR(lpni)) {
+ rc = PTR_ERR(lpni);
+ goto out_unlock;
+ }
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ while (!lnet_peer_is_uptodate(lp)) {
+ spin_lock(&lp->lp_lock);
+ /* force a full discovery cycle */
+ lp->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH;
+ spin_unlock(&lp->lp_lock);
+
+ rc = lnet_discover_peer_locked(lpni, cpt, true);
+ if (rc)
+ goto out_decref;
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ /* Only try once if discovery is disabled */
+ if (lnet_is_discovery_disabled(lp))
+ break;
+ }
+ primary_nid = lp->lp_primary_nid;
+out_decref:
+ lnet_peer_ni_decref_locked(lpni);
+out_unlock:
+ lnet_net_unlock(cpt);
+
+ CDEBUG(D_NET, "NID %s primary NID %s rc %d\n", libcfs_nid2str(nid),
+ libcfs_nid2str(primary_nid), rc);
+ return primary_nid;
+}
+EXPORT_SYMBOL(LNetPrimaryNID);
+
+struct lnet_peer_net *
+lnet_peer_get_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;
+}
+
+/*
+ * Attach a peer_ni to a peer_net and peer. This function assumes
+ * peer_ni is not already attached to the peer_net/peer. The peer_ni
+ * may be attached to a different peer, in which case it will be
+ * properly detached first. The whole operation is done atomically.
+ *
+ * This function consumes the reference on lpni and Always returns 0.
+ * This is the last function called from functions that do return an
+ * int, so returning 0 here allows the compiler to do a tail call.
+ */
+static int
+lnet_peer_attach_peer_ni(struct lnet_peer *lp,
+ struct lnet_peer_net *lpn,
+ struct lnet_peer_ni *lpni,
+ unsigned flags)
+{
+ struct lnet_peer_table *ptable;
+ bool new_lpn = false;
+ int rc;
+
+ /* Install the new peer_ni */
+ lnet_net_lock(LNET_LOCK_EX);
+ /* Add peer_ni to global peer table hash, if necessary. */
+ if (list_empty(&lpni->lpni_hashlist)) {
+ int hash = lnet_nid2peerhash(lpni->lpni_nid);
+
+ ptable = the_lnet.ln_peer_tables[lpni->lpni_cpt];
+ list_add_tail(&lpni->lpni_hashlist, &ptable->pt_hash[hash]);
+ ptable->pt_version++;
+ lnet_peer_ni_addref_locked(lpni);
+ }
+
+ /* Detach the peer_ni from an existing peer, if necessary. */
+ if (lpni->lpni_peer_net) {
+ LASSERT(lpni->lpni_peer_net != lpn);
+ LASSERT(lpni->lpni_peer_net->lpn_peer != lp);
+ lnet_peer_detach_peer_ni_locked(lpni);
+ lnet_peer_net_decref_locked(lpni->lpni_peer_net);
+ lpni->lpni_peer_net = NULL;
+ }
+
+ /* Add peer_ni to peer_net */
+ lpni->lpni_peer_net = lpn;
+ list_add_tail(&lpni->lpni_peer_nis, &lpn->lpn_peer_nis);
+ lnet_update_peer_net_healthv(lpni);
+ lnet_peer_net_addref_locked(lpn);
+
+ /* Add peer_net to peer */
+ if (!lpn->lpn_peer) {
+ new_lpn = true;
+ lpn->lpn_peer = lp;
+ list_add_tail(&lpn->lpn_peer_nets, &lp->lp_peer_nets);
+ lnet_peer_addref_locked(lp);
+ }
+
+ /* Add peer to global peer list, if necessary */
+ ptable = the_lnet.ln_peer_tables[lp->lp_cpt];
+ if (list_empty(&lp->lp_peer_list)) {
+ list_add_tail(&lp->lp_peer_list, &ptable->pt_peer_list);
+ ptable->pt_peers++;
+ }
+
+
+ /* Update peer state */
+ spin_lock(&lp->lp_lock);
+ if (flags & LNET_PEER_CONFIGURED) {
+ if (!(lp->lp_state & LNET_PEER_CONFIGURED))
+ lp->lp_state |= LNET_PEER_CONFIGURED;
+ }
+ if (flags & LNET_PEER_MULTI_RAIL) {
+ if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
+ }
+ }
+ spin_unlock(&lp->lp_lock);
+
+ lp->lp_nnis++;
+
+ /* apply UDSPs */
+ if (new_lpn) {
+ rc = lnet_udsp_apply_policies_on_lpn(lpn);
+ if (rc)
+ CERROR("Failed to apply UDSPs on lpn %s\n",
+ libcfs_net2str(lpn->lpn_net_id));
+ }
+ rc = lnet_udsp_apply_policies_on_lpni(lpni);
+ if (rc)
+ CERROR("Failed to apply UDSPs on lpni %s\n",
+ libcfs_nid2str(lpni->lpni_nid));
+
+ CDEBUG(D_NET, "peer %s NID %s flags %#x\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ libcfs_nid2str(lpni->lpni_nid), flags);
+ lnet_peer_ni_decref_locked(lpni);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ return 0;
+}
+
+/*
+ * Create a new peer, with nid as its primary nid.
+ *
+ * Call with the lnet_api_mutex held.
+ */
+static int
+lnet_peer_add(lnet_nid_t nid, unsigned flags)
+{
+ struct lnet_peer *lp;
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
+ int rc = 0;
+
+ LASSERT(nid != LNET_NID_ANY);
+
+ /*
+ * No need for the lnet_net_lock here, because the
+ * lnet_api_mutex is held.
+ */
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni) {
+ /* A peer with this NID already exists. */
+ lp = lpni->lpni_peer_net->lpn_peer;
+ lnet_peer_ni_decref_locked(lpni);
+ /*
+ * This is an error if the peer was configured and the
+ * primary NID differs or an attempt is made to change
+ * the Multi-Rail flag. Otherwise the assumption is
+ * that an existing peer is being modified.
+ */
+ if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ if (lp->lp_primary_nid != nid)
+ rc = -EEXIST;
+ else if ((lp->lp_state ^ flags) & LNET_PEER_MULTI_RAIL)
+ rc = -EPERM;
+ goto out;
+ }
+ /* Delete and recreate as a configured peer. */
+ lnet_peer_del(lp);
+ }
+
+ /* Create peer, peer_net, and peer_ni. */
+ rc = -ENOMEM;
+ lp = lnet_peer_alloc(nid);
+ if (!lp)
+ goto out;
+ lpn = lnet_peer_net_alloc(LNET_NIDNET(nid));
+ if (!lpn)
+ goto out_free_lp;
+ lpni = lnet_peer_ni_alloc(nid);
+ if (!lpni)
+ goto out_free_lpn;
+
+ return lnet_peer_attach_peer_ni(lp, lpn, lpni, flags);
+
+out_free_lpn:
+ LIBCFS_FREE(lpn, sizeof(*lpn));
+out_free_lp:
+ LIBCFS_FREE(lp, sizeof(*lp));
+out:
+ CDEBUG(D_NET, "peer %s NID flags %#x: %d\n",
+ libcfs_nid2str(nid), flags, rc);
+ return rc;
+}
+
+/*
+ * Add a NID to a peer. Call with ln_api_mutex held.
+ *
+ * Error codes:
+ * -EPERM: Non-DLC addition to a DLC-configured peer.
+ * -EEXIST: The NID was configured by DLC for a different peer.
+ * -ENOMEM: Out of memory.
+ * -ENOTUNIQ: Adding a second peer NID on a single network on a
+ * non-multi-rail peer.
+ */
+static int
+lnet_peer_add_nid(struct lnet_peer *lp, lnet_nid_t nid, unsigned flags)
+{
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
+ int rc = 0;
+
+ LASSERT(lp);
+ LASSERT(nid != LNET_NID_ANY);
+
+ /* A configured peer can only be updated through configuration. */
+ if (!(flags & LNET_PEER_CONFIGURED)) {
+ if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ rc = -EPERM;
+ goto out;
+ }
+ }
+
+ /*
+ * The MULTI_RAIL flag can be set but not cleared, because
+ * that would leave the peer struct in an invalid state.
+ */
+ if (flags & LNET_PEER_MULTI_RAIL) {
+ spin_lock(&lp->lp_lock);
+ if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
+ }
+ spin_unlock(&lp->lp_lock);
+ } else if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
+ rc = -EPERM;
+ goto out;
+ }
+
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni) {
+ /*
+ * A peer_ni already exists. This is only a problem if
+ * it is not connected to this peer and was configured
+ * by DLC.
+ */
+ if (lpni->lpni_peer_net->lpn_peer == lp)
+ goto out_free_lpni;
+ if (lnet_peer_ni_is_configured(lpni)) {
+ rc = -EEXIST;
+ goto out_free_lpni;
+ }
+ /* If this is the primary NID, destroy the peer. */
+ if (lnet_peer_ni_is_primary(lpni)) {
+ struct lnet_peer *rtr_lp =
+ lpni->lpni_peer_net->lpn_peer;
+ int rtr_refcount = rtr_lp->lp_rtr_refcount;
+ /*
+ * if we're trying to delete a router it means
+ * we're moving this peer NI to a new peer so must
+ * transfer router properties to the new peer
+ */
+ if (rtr_refcount > 0) {
+ flags |= LNET_PEER_RTR_NI_FORCE_DEL;
+ lnet_rtr_transfer_to_peer(rtr_lp, lp);
+ }
+ lnet_peer_del(lpni->lpni_peer_net->lpn_peer);
+ lnet_peer_ni_decref_locked(lpni);
+ lpni = lnet_peer_ni_alloc(nid);
+ if (!lpni) {
+ rc = -ENOMEM;
+ goto out_free_lpni;
+ }
+ }
+ } else {
+ lpni = lnet_peer_ni_alloc(nid);
+ if (!lpni) {
+ rc = -ENOMEM;
+ goto out_free_lpni;
+ }
+ }
+
+ /*
+ * Get the peer_net. Check that we're not adding a second
+ * peer_ni on a peer_net of a non-multi-rail peer.
+ */
+ lpn = lnet_peer_get_net_locked(lp, LNET_NIDNET(nid));
+ if (!lpn) {
+ lpn = lnet_peer_net_alloc(LNET_NIDNET(nid));
+ if (!lpn) {
+ rc = -ENOMEM;
+ goto out_free_lpni;
+ }
+ } else if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ rc = -ENOTUNIQ;
+ goto out_free_lpni;
+ }
+
+ return lnet_peer_attach_peer_ni(lp, lpn, lpni, flags);
+
+out_free_lpni:
+ lnet_peer_ni_decref_locked(lpni);
+out:
+ CDEBUG(D_NET, "peer %s NID %s flags %#x: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), libcfs_nid2str(nid),
+ flags, rc);
+ return rc;
+}
+
+/*
+ * Update the primary NID of a peer, if possible.
+ *
+ * Call with the lnet_api_mutex held.
+ */
+static int
+lnet_peer_set_primary_nid(struct lnet_peer *lp, lnet_nid_t nid, unsigned flags)
+{
+ lnet_nid_t old = lp->lp_primary_nid;
+ int rc = 0;
+
+ if (lp->lp_primary_nid == nid)
+ goto out;
+ rc = lnet_peer_add_nid(lp, nid, flags);
+ if (rc)
+ goto out;
+ lp->lp_primary_nid = nid;
+out:
+ CDEBUG(D_NET, "peer %s NID %s: %d\n",
+ libcfs_nid2str(old), libcfs_nid2str(nid), rc);
+ return rc;
+}
+
+/*
+ * lpni creation initiated due to traffic either sending or receiving.
+ */
+static int
+lnet_peer_ni_traffic_add(lnet_nid_t nid, lnet_nid_t pref)
+{
+ struct lnet_peer *lp;
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
+ unsigned flags = 0;
+ int rc = 0;
+
+ if (nid == LNET_NID_ANY) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* lnet_net_lock is not needed here because ln_api_lock is held */
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni) {
+ /*
+ * We must have raced with another thread. Since we
+ * know next to nothing about a peer_ni created by
+ * traffic, we just assume everything is ok and
+ * return.
+ */
+ lnet_peer_ni_decref_locked(lpni);
+ goto out;
+ }
+
+ /* Create peer, peer_net, and peer_ni. */
+ rc = -ENOMEM;
+ lp = lnet_peer_alloc(nid);
+ if (!lp)
+ goto out;
+ lpn = lnet_peer_net_alloc(LNET_NIDNET(nid));
+ if (!lpn)
+ goto out_free_lp;
+ lpni = lnet_peer_ni_alloc(nid);
+ if (!lpni)
+ goto out_free_lpn;
+ if (pref != LNET_NID_ANY)
+ lnet_peer_ni_set_non_mr_pref_nid(lpni, pref);
+
+ return lnet_peer_attach_peer_ni(lp, lpn, lpni, flags);
+
+out_free_lpn:
+ LIBCFS_FREE(lpn, sizeof(*lpn));
+out_free_lp:
+ LIBCFS_FREE(lp, sizeof(*lp));
+out:
+ CDEBUG(D_NET, "peer %s: %d\n", libcfs_nid2str(nid), rc);
+ return rc;
+}
+
+/*
+ * Implementation of IOC_LIBCFS_ADD_PEER_NI.
+ *
+ * This API handles the following combinations:
+ * Create a peer with its primary NI if only the prim_nid is provided
+ * Add a NID to a peer identified by the prim_nid. The peer identified
+ * by the prim_nid must already exist.
+ * The peer being created may be non-MR.
+ *
+ * The caller must hold ln_api_mutex. This prevents the peer from
+ * being created/modified/deleted by a different thread.
+ */
+int
+lnet_add_peer_ni(lnet_nid_t prim_nid, lnet_nid_t nid, bool mr)
+{
+ struct lnet_peer *lp = NULL;
+ struct lnet_peer_ni *lpni;
+ unsigned flags;
+
+ /* The prim_nid must always be specified */
+ if (prim_nid == LNET_NID_ANY)
+ return -EINVAL;
+
+ flags = LNET_PEER_CONFIGURED;
+ if (mr)
+ flags |= LNET_PEER_MULTI_RAIL;
+
+ /*
+ * If nid isn't specified, we must create a new peer with
+ * prim_nid as its primary nid.
+ */
+ if (nid == LNET_NID_ANY)
+ return lnet_peer_add(prim_nid, flags);
+
+ /* Look up the prim_nid, which must exist. */
+ lpni = lnet_find_peer_ni_locked(prim_nid);
+ if (!lpni)
+ return -ENOENT;
+ lnet_peer_ni_decref_locked(lpni);
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ /* Peer must have been configured. */
+ if (!(lp->lp_state & LNET_PEER_CONFIGURED)) {
+ CDEBUG(D_NET, "peer %s was not configured\n",
+ libcfs_nid2str(prim_nid));
+ return -ENOENT;
+ }
+
+ /* Primary NID must match */
+ if (lp->lp_primary_nid != prim_nid) {
+ CDEBUG(D_NET, "prim_nid %s is not primary for peer %s\n",
+ libcfs_nid2str(prim_nid),
+ libcfs_nid2str(lp->lp_primary_nid));
+ return -ENODEV;
+ }
+
+ /* Multi-Rail flag must match. */
+ if ((lp->lp_state ^ flags) & LNET_PEER_MULTI_RAIL) {
+ CDEBUG(D_NET, "multi-rail state mismatch for peer %s\n",
+ libcfs_nid2str(prim_nid));
+ return -EPERM;
+ }
+
+ return lnet_peer_add_nid(lp, nid, flags);
+}
+
+/*
+ * Implementation of IOC_LIBCFS_DEL_PEER_NI.
+ *
+ * This API handles the following combinations:
+ * Delete a NI from a peer if both prim_nid and nid are provided.
+ * Delete a peer if only prim_nid is provided.
+ * Delete a peer if its primary nid is provided.
+ *
+ * The caller must hold ln_api_mutex. This prevents the peer from
+ * being modified/deleted by a different thread.
+ */
+int
+lnet_del_peer_ni(lnet_nid_t prim_nid, lnet_nid_t nid)
+{
+ struct lnet_peer *lp;
+ struct lnet_peer_ni *lpni;
+ unsigned flags;
+
+ if (prim_nid == LNET_NID_ANY)
+ return -EINVAL;
+
+ lpni = lnet_find_peer_ni_locked(prim_nid);
+ if (!lpni)
+ return -ENOENT;
+ lnet_peer_ni_decref_locked(lpni);
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ if (prim_nid != lp->lp_primary_nid) {
+ CDEBUG(D_NET, "prim_nid %s is not primary for peer %s\n",
+ libcfs_nid2str(prim_nid),
+ libcfs_nid2str(lp->lp_primary_nid));
+ return -ENODEV;
+ }
+
+ lnet_net_lock(LNET_LOCK_EX);
+ if (lp->lp_rtr_refcount > 0) {
+ lnet_net_unlock(LNET_LOCK_EX);
+ CERROR("%s is a router. Can not be deleted\n",
+ libcfs_nid2str(prim_nid));
+ return -EBUSY;
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ if (nid == LNET_NID_ANY || nid == lp->lp_primary_nid)
+ return lnet_peer_del(lp);
+
+ flags = LNET_PEER_CONFIGURED;
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL)
+ flags |= LNET_PEER_MULTI_RAIL;
+
+ return lnet_peer_del_nid(lp, nid, flags);
+}
+
+void
+lnet_destroy_peer_ni_locked(struct lnet_peer_ni *lpni)
+{
+ struct lnet_peer_table *ptable;
+ struct lnet_peer_net *lpn;
+
+ CDEBUG(D_NET, "%p nid %s\n", lpni, libcfs_nid2str(lpni->lpni_nid));
+
+ LASSERT(atomic_read(&lpni->lpni_refcount) == 0);
+ LASSERT(list_empty(&lpni->lpni_txq));
+ LASSERT(lpni->lpni_txqnob == 0);
+ LASSERT(list_empty(&lpni->lpni_peer_nis));
+ LASSERT(list_empty(&lpni->lpni_on_remote_peer_ni_list));
+
+ lpn = lpni->lpni_peer_net;
+ lpni->lpni_peer_net = NULL;
+ lpni->lpni_net = NULL;
+
+ if (!list_empty(&lpni->lpni_hashlist)) {
+ /* remove the peer ni from the zombie list */
+ ptable = the_lnet.ln_peer_tables[lpni->lpni_cpt];
+ spin_lock(&ptable->pt_zombie_lock);
+ list_del_init(&lpni->lpni_hashlist);
+ ptable->pt_zombies--;
+ spin_unlock(&ptable->pt_zombie_lock);
+ }
+
+ if (lpni->lpni_pref_nnids > 1) {
+ struct lnet_nid_list *ne, *tmp;
+
+ list_for_each_entry_safe(ne, tmp, &lpni->lpni_pref.nids,
+ nl_list) {
+ list_del_init(&ne->nl_list);
+ LIBCFS_FREE(ne, sizeof(*ne));
+ }
+ }
+ LIBCFS_FREE(lpni, sizeof(*lpni));
+
+ if (lpn)
+ lnet_peer_net_decref_locked(lpn);
+}
+
+struct lnet_peer_ni *
+lnet_nid2peerni_ex(lnet_nid_t nid, int cpt)
+{
+ struct lnet_peer_ni *lpni = NULL;
+ int rc;
+
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ return ERR_PTR(-ESHUTDOWN);
+
+ /*
+ * find if a peer_ni already exists.
+ * If so then just return that.
+ */
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni)
+ return lpni;
+
+ lnet_net_unlock(cpt);
+
+ rc = lnet_peer_ni_traffic_add(nid, LNET_NID_ANY);
+ if (rc) {
+ lpni = ERR_PTR(rc);
+ goto out_net_relock;
+ }
+
+ lpni = lnet_find_peer_ni_locked(nid);
+ LASSERT(lpni);
+
+out_net_relock:
+ lnet_net_lock(cpt);
+
+ return lpni;
+}
+
+/*
+ * Get a peer_ni for the given nid, create it if necessary. Takes a
+ * hold on the peer_ni.
+ */
+struct lnet_peer_ni *
+lnet_nid2peerni_locked(lnet_nid_t nid, lnet_nid_t pref, int cpt)
+{
+ struct lnet_peer_ni *lpni = NULL;
+ int rc;
+
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ return ERR_PTR(-ESHUTDOWN);
+
+ /*
+ * find if a peer_ni already exists.
+ * If so then just return that.
+ */
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni)
+ return lpni;
+
+ /*
+ * Slow path:
+ * use the lnet_api_mutex to serialize the creation of the peer_ni
+ * and the creation/deletion of the local ni/net. When a local ni is
+ * created, if there exists a set of peer_nis on that network,
+ * they need to be traversed and updated. When a local NI is
+ * deleted, which could result in a network being deleted, then
+ * all peer nis on that network need to be removed as well.
+ *
+ * Creation through traffic should also be serialized with
+ * creation through DLC.
+ */
+ lnet_net_unlock(cpt);
+ mutex_lock(&the_lnet.ln_api_mutex);
+ /*
+ * Shutdown is only set under the ln_api_lock, so a single
+ * check here is sufficent.
+ */
+ if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ lpni = ERR_PTR(-ESHUTDOWN);
+ goto out_mutex_unlock;
+ }
+
+ rc = lnet_peer_ni_traffic_add(nid, pref);
+ if (rc) {
+ lpni = ERR_PTR(rc);
+ goto out_mutex_unlock;
+ }
+
+ lpni = lnet_find_peer_ni_locked(nid);
+ LASSERT(lpni);
+
+out_mutex_unlock:
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ lnet_net_lock(cpt);
+
+ /* Lock has been dropped, check again for shutdown. */
+ if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ if (!IS_ERR(lpni))
+ lnet_peer_ni_decref_locked(lpni);
+ lpni = ERR_PTR(-ESHUTDOWN);
+ }
+
+ return lpni;
+}
+
+bool
+lnet_peer_gw_discovery(struct lnet_peer *lp)
+{
+ bool rc = false;
+
+ spin_lock(&lp->lp_lock);
+ if (lp->lp_state & LNET_PEER_RTR_DISCOVERY)
+ rc = true;
+ spin_unlock(&lp->lp_lock);
+
+ return rc;
+}
+
+bool
+lnet_peer_is_uptodate(struct lnet_peer *lp)
+{
+ bool rc;
+
+ spin_lock(&lp->lp_lock);
+ rc = lnet_peer_is_uptodate_locked(lp);
+ spin_unlock(&lp->lp_lock);
+ return rc;
+}
+
+/*
+ * Is a peer uptodate from the point of view of discovery?
+ *
+ * If it is currently being processed, obviously not.
+ * A forced Ping or Push is also handled by the discovery thread.
+ *
+ * Otherwise look at whether the peer needs rediscovering.
+ */
+bool
+lnet_peer_is_uptodate_locked(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ bool rc;
+
+ if (lp->lp_state & (LNET_PEER_DISCOVERING |
+ LNET_PEER_FORCE_PING |
+ LNET_PEER_FORCE_PUSH)) {
+ rc = false;
+ } else if (lp->lp_state & LNET_PEER_REDISCOVER) {
+ rc = false;
+ } else if (lnet_peer_needs_push(lp)) {
+ rc = false;
+ } else if (lp->lp_state & LNET_PEER_DISCOVERED) {
+ if (lp->lp_state & LNET_PEER_NIDS_UPTODATE)
+ rc = true;
+ else
+ rc = false;
+ } else {
+ rc = false;
+ }
+
+ return rc;
+}
+
+/*
+ * Queue a peer for the attention of the discovery thread. Call with
+ * lnet_net_lock/EX held. Returns 0 if the peer was queued, and
+ * -EALREADY if the peer was already queued.
+ */
+static int lnet_peer_queue_for_discovery(struct lnet_peer *lp)
+{
+ int rc;
+
+ spin_lock(&lp->lp_lock);
+ if (!(lp->lp_state & LNET_PEER_DISCOVERING))
+ lp->lp_state |= LNET_PEER_DISCOVERING;
+ spin_unlock(&lp->lp_lock);
+ if (list_empty(&lp->lp_dc_list)) {
+ lnet_peer_addref_locked(lp);
+ list_add_tail(&lp->lp_dc_list, &the_lnet.ln_dc_request);
+ wake_up(&the_lnet.ln_dc_waitq);
+ rc = 0;
+ } else {
+ rc = -EALREADY;
+ }
+
+ CDEBUG(D_NET, "Queue peer %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+
+ return rc;
+}
+
+/*
+ * Discovery of a peer is complete. Wake all waiters on the peer.
+ * Call with lnet_net_lock/EX held.
+ */
+static void lnet_peer_discovery_complete(struct lnet_peer *lp)
+{
+ struct lnet_msg *msg, *tmp;
+ int rc = 0;
+ LIST_HEAD(pending_msgs);
+
+ CDEBUG(D_NET, "Discovery complete. Dequeue peer %s\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+
+ list_del_init(&lp->lp_dc_list);
+ spin_lock(&lp->lp_lock);
+ list_splice_init(&lp->lp_dc_pendq, &pending_msgs);
+ spin_unlock(&lp->lp_lock);
+ wake_up_all(&lp->lp_dc_waitq);
+
+ if (lp->lp_rtr_refcount > 0)
+ lnet_router_discovery_complete(lp);
+
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ /* iterate through all pending messages and send them again */
+ list_for_each_entry_safe(msg, tmp, &pending_msgs, msg_list) {
+ list_del_init(&msg->msg_list);
+ if (lp->lp_dc_error) {
+ lnet_finalize(msg, lp->lp_dc_error);
+ continue;
+ }
+
+ CDEBUG(D_NET, "sending pending message %s to target %s\n",
+ lnet_msgtyp2str(msg->msg_type),
+ libcfs_id2str(msg->msg_target));
+ rc = lnet_send(msg->msg_src_nid_param, msg,
+ msg->msg_rtr_nid_param);
+ if (rc < 0) {
+ CNETERR("Error sending %s to %s: %d\n",
+ lnet_msgtyp2str(msg->msg_type),
+ libcfs_id2str(msg->msg_target), rc);
+ lnet_finalize(msg, rc);
+ }
+ }
+ lnet_net_lock(LNET_LOCK_EX);
+ lnet_peer_decref_locked(lp);
+}
+
+/*
+ * Handle inbound push.
+ * Like any event handler, called with lnet_res_lock/CPT held.
+ */
+void lnet_peer_push_event(struct lnet_event *ev)
+{
+ struct lnet_ping_buffer *pbuf;
+ struct lnet_peer *lp;
+
+ pbuf = LNET_PING_INFO_TO_BUFFER(ev->md_start + ev->offset);
+
+ /* lnet_find_peer() adds a refcount */
+ lp = lnet_find_peer(ev->source.nid);
+ if (!lp) {
+ CDEBUG(D_NET, "Push Put from unknown %s (source %s). Ignoring...\n",
+ libcfs_nid2str(ev->initiator.nid),
+ libcfs_nid2str(ev->source.nid));
+ pbuf->pb_needs_post = true;
+ return;
+ }
+
+ /* Ensure peer state remains consistent while we modify it. */
+ spin_lock(&lp->lp_lock);
+
+ /*
+ * If some kind of error happened the contents of the message
+ * cannot be used. Clear the NIDS_UPTODATE and set the
+ * FORCE_PING flag to trigger a ping.
+ */
+ if (ev->status) {
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ CDEBUG(D_NET, "Push Put error %d from %s (source %s)\n",
+ ev->status,
+ libcfs_nid2str(lp->lp_primary_nid),
+ libcfs_nid2str(ev->source.nid));
+ goto out;
+ }
+
+ /*
+ * A push with invalid or corrupted info. Clear the UPTODATE
+ * flag to trigger a ping.
+ */
+ if (lnet_ping_info_validate(&pbuf->pb_info)) {
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ CDEBUG(D_NET, "Corrupted Push from %s\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ goto out;
+ }
+
+ /*
+ * Make sure we'll allocate the correct size ping buffer when
+ * pinging the peer.
+ */
+ if (lp->lp_data_nnis < pbuf->pb_info.pi_nnis)
+ lp->lp_data_nnis = pbuf->pb_info.pi_nnis;
+
+ /*
+ * A non-Multi-Rail peer is not supposed to be capable of
+ * sending a push.
+ */
+ if (!(pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL)) {
+ CERROR("Push from non-Multi-Rail peer %s dropped\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ goto out;
+ }
+
+ /*
+ * The peer may have discovery disabled at its end. Set
+ * NO_DISCOVERY as appropriate.
+ */
+ if (!(pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY)) {
+ CDEBUG(D_NET, "Peer %s has discovery disabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ /*
+ * Mark the peer for deletion if we already know about it
+ * and it's going from discovery set to no discovery set
+ */
+ if (!(lp->lp_state & (LNET_PEER_NO_DISCOVERY |
+ LNET_PEER_DISCOVERING)) &&
+ lp->lp_state & LNET_PEER_DISCOVERED) {
+ CDEBUG(D_NET, "Marking %s:0x%x for deletion\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ lp->lp_state);
+ lp->lp_state |= LNET_PEER_MARK_DELETION;
+ }
+ lp->lp_state |= LNET_PEER_NO_DISCOVERY;
+ } else if (lp->lp_state & LNET_PEER_NO_DISCOVERY) {
+ CDEBUG(D_NET, "Peer %s has discovery enabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
+ }
+
+ /*
+ * Update the MULTI_RAIL flag based on the push. If the peer
+ * was configured with DLC then the setting should match what
+ * DLC put in.
+ * NB: We verified above that the MR feature bit is set in pi_features
+ */
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
+ CDEBUG(D_NET, "peer %s(%p) is MR\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ CWARN("Push says %s is Multi-Rail, DLC says not\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ } else if (lnet_peer_discovery_disabled) {
+ CDEBUG(D_NET, "peer %s(%p) not MR: DD disabled locally\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else if (lp->lp_state & LNET_PEER_NO_DISCOVERY) {
+ CDEBUG(D_NET, "peer %s(%p) not MR: DD disabled remotely\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else {
+ CDEBUG(D_NET, "peer %s(%p) is MR capable\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
+ }
+
+ /*
+ * Check for truncation of the Put message. Clear the
+ * NIDS_UPTODATE flag and set FORCE_PING to trigger a ping,
+ * and tell discovery to allocate a bigger buffer.
+ */
+ if (ev->mlength < ev->rlength) {
+ if (the_lnet.ln_push_target_nnis < pbuf->pb_info.pi_nnis)
+ the_lnet.ln_push_target_nnis = pbuf->pb_info.pi_nnis;
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ CDEBUG(D_NET, "Truncated Push from %s (%d nids)\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ pbuf->pb_info.pi_nnis);
+ goto out;
+ }
+
+ /* always assume new data */
+ lp->lp_peer_seqno = LNET_PING_BUFFER_SEQNO(pbuf);
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+
+ /*
+ * If there is data present that hasn't been processed yet,
+ * we'll replace it if the Put contained newer data and it
+ * fits. We're racing with a Ping or earlier Push in this
+ * case.
+ */
+ if (lp->lp_state & LNET_PEER_DATA_PRESENT) {
+ if (LNET_PING_BUFFER_SEQNO(pbuf) >
+ LNET_PING_BUFFER_SEQNO(lp->lp_data) &&
+ pbuf->pb_info.pi_nnis <= lp->lp_data->pb_nnis) {
+ memcpy(&lp->lp_data->pb_info, &pbuf->pb_info,
+ LNET_PING_INFO_SIZE(pbuf->pb_info.pi_nnis));
+ CDEBUG(D_NET, "Ping/Push race from %s: %u vs %u\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ LNET_PING_BUFFER_SEQNO(pbuf),
+ LNET_PING_BUFFER_SEQNO(lp->lp_data));
+ }
+ goto out;
+ }
+
+ /*
+ * Allocate a buffer to copy the data. On a failure we drop
+ * the Push and set FORCE_PING to force the discovery
+ * thread to fix the problem by pinging the peer.
+ */
+ lp->lp_data = lnet_ping_buffer_alloc(lp->lp_data_nnis, GFP_ATOMIC);
+ if (!lp->lp_data) {
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ CDEBUG(D_NET, "Cannot allocate Push buffer for %s %u\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ LNET_PING_BUFFER_SEQNO(pbuf));
+ goto out;
+ }
+
+ /* Success */
+ memcpy(&lp->lp_data->pb_info, &pbuf->pb_info,
+ LNET_PING_INFO_SIZE(pbuf->pb_info.pi_nnis));
+ lp->lp_state |= LNET_PEER_DATA_PRESENT;
+ CDEBUG(D_NET, "Received Push %s %u\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ LNET_PING_BUFFER_SEQNO(pbuf));
+
+out:
+ /* We've processed this buffer. It can be reposted */
+ pbuf->pb_needs_post = true;
+
+ /*
+ * Queue the peer for discovery if not done, force it on the request
+ * queue and wake the discovery thread if the peer was already queued,
+ * because its status changed.
+ */
+ spin_unlock(&lp->lp_lock);
+ lnet_net_lock(LNET_LOCK_EX);
+ if (!lnet_peer_is_uptodate(lp) && lnet_peer_queue_for_discovery(lp)) {
+ list_move(&lp->lp_dc_list, &the_lnet.ln_dc_request);
+ wake_up(&the_lnet.ln_dc_waitq);
+ }
+ /* Drop refcount from lookup */
+ lnet_peer_decref_locked(lp);
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
+/*
+ * Clear the discovery error state, unless we're already discovering
+ * this peer, in which case the error is current.
+ */
+static void lnet_peer_clear_discovery_error(struct lnet_peer *lp)
+{
+ spin_lock(&lp->lp_lock);
+ if (!(lp->lp_state & LNET_PEER_DISCOVERING))
+ lp->lp_dc_error = 0;
+ spin_unlock(&lp->lp_lock);
+}
+
+/*
+ * Peer discovery slow path. The ln_api_mutex is held on entry, and
+ * dropped/retaken within this function. An lnet_peer_ni is passed in
+ * because discovery could tear down an lnet_peer.
+ */
+int
+lnet_discover_peer_locked(struct lnet_peer_ni *lpni, int cpt, bool block)
+{
+ DEFINE_WAIT(wait);
+ struct lnet_peer *lp;
+ int rc = 0;
+ int count = 0;
+
+again:
+ lnet_net_unlock(cpt);
+ lnet_net_lock(LNET_LOCK_EX);
+ lp = lpni->lpni_peer_net->lpn_peer;
+ lnet_peer_clear_discovery_error(lp);
+
+ /*
+ * We're willing to be interrupted. The lpni can become a
+ * zombie if we race with DLC, so we must check for that.
+ */
+ for (;;) {
+ /* Keep lp alive when the lnet_net_lock is unlocked */
+ lnet_peer_addref_locked(lp);
+ prepare_to_wait(&lp->lp_dc_waitq, &wait, TASK_INTERRUPTIBLE);
+ if (signal_pending(current))
+ break;
+ if (the_lnet.ln_dc_state != LNET_DC_STATE_RUNNING)
+ break;
+ /*
+ * Don't repeat discovery if discovery is disabled. This is
+ * done to ensure we can use discovery as a standard ping as
+ * well for backwards compatibility with routers which do not
+ * have discovery or have discovery disabled
+ */
+ if (lnet_is_discovery_disabled(lp) && count > 0)
+ break;
+ if (lp->lp_dc_error)
+ break;
+ if (lnet_peer_is_uptodate(lp))
+ break;
+ lnet_peer_queue_for_discovery(lp);
+ count++;
+ CDEBUG(D_NET, "Discovery attempt # %d\n", count);
+
+ /*
+ * If caller requested a non-blocking operation then
+ * return immediately. Once discovery is complete any
+ * pending messages that were stopped due to discovery
+ * will be transmitted.
+ */
+ if (!block)
+ break;
+
+ lnet_net_unlock(LNET_LOCK_EX);
+ schedule();
+ finish_wait(&lp->lp_dc_waitq, &wait);
+ lnet_net_lock(LNET_LOCK_EX);
+ lnet_peer_decref_locked(lp);
+ /* Peer may have changed */
+ lp = lpni->lpni_peer_net->lpn_peer;
+ }
+ finish_wait(&lp->lp_dc_waitq, &wait);
+
+ lnet_net_unlock(LNET_LOCK_EX);
+ lnet_net_lock(cpt);
+ lnet_peer_decref_locked(lp);
+ /*
+ * The peer may have changed, so re-check and rediscover if that turns
+ * out to have been the case. The reference count on lp ensured that
+ * even if it was unlinked from lpni the memory could not be recycled.
+ * Thus the check below is sufficient to determine whether the peer
+ * changed. If the peer changed, then lp must not be dereferenced.
+ */
+ if (lp != lpni->lpni_peer_net->lpn_peer)
+ goto again;
+
+ if (signal_pending(current))
+ rc = -EINTR;
+ else if (the_lnet.ln_dc_state != LNET_DC_STATE_RUNNING)
+ rc = -ESHUTDOWN;
+ else if (lp->lp_dc_error)
+ rc = lp->lp_dc_error;
+ else if (!block)
+ CDEBUG(D_NET, "non-blocking discovery\n");
+ else if (!lnet_peer_is_uptodate(lp) && !lnet_is_discovery_disabled(lp))
+ goto again;
+
+ CDEBUG(D_NET, "peer %s NID %s: %d. %s\n",
+ (lp ? libcfs_nid2str(lp->lp_primary_nid) : "(none)"),
+ libcfs_nid2str(lpni->lpni_nid), rc,
+ (!block) ? "pending discovery" : "discovery complete");
+
+ return rc;
+}
+
+/* Handle an incoming ack for a push. */
+static void
+lnet_discovery_event_ack(struct lnet_peer *lp, struct lnet_event *ev)
+{
+ struct lnet_ping_buffer *pbuf;
+
+ pbuf = LNET_PING_INFO_TO_BUFFER(ev->md_start);
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~LNET_PEER_PUSH_SENT;
+ lp->lp_push_error = ev->status;
+ if (ev->status)
+ lp->lp_state |= LNET_PEER_PUSH_FAILED;
+ else
+ lp->lp_node_seqno = LNET_PING_BUFFER_SEQNO(pbuf);
+ spin_unlock(&lp->lp_lock);
+
+ CDEBUG(D_NET, "peer %s ev->status %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), ev->status);
+}
+
+/* Handle a Reply message. This is the reply to a Ping message. */
+static void
+lnet_discovery_event_reply(struct lnet_peer *lp, struct lnet_event *ev)
+{
+ struct lnet_ping_buffer *pbuf;
+ int rc;
+
+ spin_lock(&lp->lp_lock);
+
+ lp->lp_disc_src_nid = ev->target.nid;
+
+ /*
+ * If some kind of error happened the contents of message
+ * cannot be used. Set PING_FAILED to trigger a retry.
+ */
+ if (ev->status) {
+ lp->lp_state |= LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = ev->status;
+ CDEBUG(D_NET, "Ping Reply error %d from %s (source %s)\n",
+ ev->status,
+ libcfs_nid2str(lp->lp_primary_nid),
+ libcfs_nid2str(ev->source.nid));
+ goto out;
+ }
+
+ pbuf = LNET_PING_INFO_TO_BUFFER(ev->md_start);
+ if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC))
+ lnet_swap_pinginfo(pbuf);
+
+ /*
+ * A reply with invalid or corrupted info. Set PING_FAILED to
+ * trigger a retry.
+ */
+ rc = lnet_ping_info_validate(&pbuf->pb_info);
+ if (rc) {
+ lp->lp_state |= LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = 0;
+ CDEBUG(D_NET, "Corrupted Ping Reply from %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+ goto out;
+ }
+
+
+ /*
+ * The peer may have discovery disabled at its end. Set
+ * NO_DISCOVERY as appropriate.
+ */
+ if ((pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY) &&
+ !lnet_peer_discovery_disabled) {
+ CDEBUG(D_NET, "Peer %s has discovery enabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
+ } else {
+ CDEBUG(D_NET, "Peer %s has discovery disabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state |= LNET_PEER_NO_DISCOVERY;
+ }
+
+ /*
+ * Update the MULTI_RAIL flag based on the reply. If the peer
+ * was configured with DLC then the setting should match what
+ * DLC put in.
+ */
+ if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL) {
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
+ CDEBUG(D_NET, "peer %s(%p) is MR\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ CWARN("Reply says %s is Multi-Rail, DLC says not\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ } else if (lnet_peer_discovery_disabled) {
+ CDEBUG(D_NET,
+ "peer %s(%p) not MR: DD disabled locally\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else if (lp->lp_state & LNET_PEER_NO_DISCOVERY) {
+ CDEBUG(D_NET,
+ "peer %s(%p) not MR: DD disabled remotely\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else {
+ CDEBUG(D_NET, "peer %s(%p) is MR capable\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
+ }
+ } else if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
+ if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ CWARN("DLC says %s is Multi-Rail, Reply says not\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ } else {
+ CERROR("Multi-Rail state vanished from %s\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state &= ~LNET_PEER_MULTI_RAIL;
+ }
+ }
+
+ /*
+ * Make sure we'll allocate the correct size ping buffer when
+ * pinging the peer.
+ */
+ if (lp->lp_data_nnis < pbuf->pb_info.pi_nnis)
+ lp->lp_data_nnis = pbuf->pb_info.pi_nnis;
+
+ /*
+ * Check for truncation of the Reply. Clear PING_SENT and set
+ * PING_FAILED to trigger a retry.
+ */
+ if (pbuf->pb_nnis < pbuf->pb_info.pi_nnis) {
+ if (the_lnet.ln_push_target_nnis < pbuf->pb_info.pi_nnis)
+ the_lnet.ln_push_target_nnis = pbuf->pb_info.pi_nnis;
+ lp->lp_state |= LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = 0;
+ CDEBUG(D_NET, "Truncated Reply from %s (%d nids)\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ pbuf->pb_info.pi_nnis);
+ goto out;
+ }
+
+ /*
+ * Check the sequence numbers in the reply. These are only
+ * available if the reply came from a Multi-Rail peer.
+ */
+ if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL &&
+ pbuf->pb_info.pi_nnis > 1 &&
+ lp->lp_primary_nid == pbuf->pb_info.pi_ni[1].ns_nid) {
+ if (LNET_PING_BUFFER_SEQNO(pbuf) < lp->lp_peer_seqno)
+ CDEBUG(D_NET, "peer %s: seq# got %u have %u. peer rebooted?\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ LNET_PING_BUFFER_SEQNO(pbuf),
+ lp->lp_peer_seqno);
+
+ lp->lp_peer_seqno = LNET_PING_BUFFER_SEQNO(pbuf);
+ }
+
+ /* We're happy with the state of the data in the buffer. */
+ CDEBUG(D_NET, "peer %s data present %u. state = 0x%x\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp->lp_peer_seqno, lp->lp_state);
+ if (lp->lp_state & LNET_PEER_DATA_PRESENT)
+ lnet_ping_buffer_decref(lp->lp_data);
+ else
+ lp->lp_state |= LNET_PEER_DATA_PRESENT;
+ lnet_ping_buffer_addref(pbuf);
+ lp->lp_data = pbuf;
+out:
+ lp->lp_state &= ~LNET_PEER_PING_SENT;
+ spin_unlock(&lp->lp_lock);
+
+ lnet_net_lock(LNET_LOCK_EX);
+ /*
+ * If this peer is a gateway, call the routing callback to
+ * handle the ping reply
+ */
+ if (lp->lp_rtr_refcount > 0)
+ lnet_router_discovery_ping_reply(lp);
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
+/*
+ * Send event handling. Only matters for error cases, where we clean
+ * up state on the peer and peer_ni that would otherwise be updated in
+ * the REPLY event handler for a successful Ping, and the ACK event
+ * handler for a successful Push.
+ */
+static int
+lnet_discovery_event_send(struct lnet_peer *lp, struct lnet_event *ev)
+{
+ int rc = 0;
+
+ if (!ev->status)
+ goto out;
+
+ spin_lock(&lp->lp_lock);
+ if (ev->msg_type == LNET_MSG_GET) {
+ lp->lp_state &= ~LNET_PEER_PING_SENT;
+ lp->lp_state |= LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = ev->status;
+ } else { /* ev->msg_type == LNET_MSG_PUT */
+ lp->lp_state &= ~LNET_PEER_PUSH_SENT;
+ lp->lp_state |= LNET_PEER_PUSH_FAILED;
+ lp->lp_push_error = ev->status;
+ }
+ spin_unlock(&lp->lp_lock);
+ rc = LNET_REDISCOVER_PEER;
+out:
+ CDEBUG(D_NET, "%s Send to %s: %d\n",
+ (ev->msg_type == LNET_MSG_GET ? "Ping" : "Push"),
+ libcfs_nid2str(ev->target.nid), rc);
+ return rc;
+}
+
+/*
+ * Unlink event handling. This event is only seen if a call to
+ * LNetMDUnlink() caused the event to be unlinked. If this call was
+ * made after the event was set up in LNetGet() or LNetPut() then we
+ * assume the Ping or Push timed out.
+ */
+static void
+lnet_discovery_event_unlink(struct lnet_peer *lp, struct lnet_event *ev)
+{
+ spin_lock(&lp->lp_lock);
+ /* We've passed through LNetGet() */
+ if (lp->lp_state & LNET_PEER_PING_SENT) {
+ lp->lp_state &= ~LNET_PEER_PING_SENT;
+ lp->lp_state |= LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = -ETIMEDOUT;
+ CDEBUG(D_NET, "Ping Unlink for message to peer %s\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ }
+ /* We've passed through LNetPut() */
+ if (lp->lp_state & LNET_PEER_PUSH_SENT) {
+ lp->lp_state &= ~LNET_PEER_PUSH_SENT;
+ lp->lp_state |= LNET_PEER_PUSH_FAILED;
+ lp->lp_push_error = -ETIMEDOUT;
+ CDEBUG(D_NET, "Push Unlink for message to peer %s\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ }
+ spin_unlock(&lp->lp_lock);
+}
+
+/*
+ * Event handler for the discovery EQ.
+ *
+ * Called with lnet_res_lock(cpt) held. The cpt is the
+ * lnet_cpt_of_cookie() of the md handle cookie.
+ */
+static void lnet_discovery_event_handler(struct lnet_event *event)
+{
+ struct lnet_peer *lp = event->md_user_ptr;
+ struct lnet_ping_buffer *pbuf;
+ int rc;
+
+ /* discovery needs to take another look */
+ rc = LNET_REDISCOVER_PEER;
+
+ CDEBUG(D_NET, "Received event: %d\n", event->type);
+
+ switch (event->type) {
+ case LNET_EVENT_ACK:
+ lnet_discovery_event_ack(lp, event);
+ break;
+ case LNET_EVENT_REPLY:
+ lnet_discovery_event_reply(lp, event);
+ break;
+ case LNET_EVENT_SEND:
+ /* Only send failure triggers a retry. */
+ rc = lnet_discovery_event_send(lp, event);
+ break;
+ case LNET_EVENT_UNLINK:
+ /* LNetMDUnlink() was called */
+ lnet_discovery_event_unlink(lp, event);
+ break;
+ default:
+ /* Invalid events. */
+ LBUG();
+ }
+ lnet_net_lock(LNET_LOCK_EX);
+ if (event->unlinked) {
+ pbuf = LNET_PING_INFO_TO_BUFFER(event->md_start);
+ lnet_ping_buffer_decref(pbuf);
+ lnet_peer_decref_locked(lp);
+ }
+
+ /* put peer back at end of request queue, if discovery not already
+ * done */
+ if (rc == LNET_REDISCOVER_PEER && !lnet_peer_is_uptodate(lp)) {
+ list_move_tail(&lp->lp_dc_list, &the_lnet.ln_dc_request);
+ wake_up(&the_lnet.ln_dc_waitq);
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
+/*
+ * Build a peer from incoming data.
+ *
+ * The NIDs in the incoming data are supposed to be structured as follows:
+ * - loopback
+ * - primary NID
+ * - other NIDs in same net
+ * - NIDs in second net
+ * - NIDs in third net
+ * - ...
+ * This due to the way the list of NIDs in the data is created.
+ *
+ * Note that this function will mark the peer uptodate unless an
+ * ENOMEM is encontered. All other errors are due to a conflict
+ * between the DLC configuration and what discovery sees. We treat DLC
+ * as binding, and therefore set the NIDS_UPTODATE flag to prevent the
+ * peer from becoming stuck in discovery.
+ */
+static int lnet_peer_merge_data(struct lnet_peer *lp,
+ struct lnet_ping_buffer *pbuf)
+{
+ struct lnet_peer_ni *lpni;
+ lnet_nid_t *curnis = NULL;
+ struct lnet_ni_status *addnis = NULL;
+ lnet_nid_t *delnis = NULL;
+ unsigned flags;
+ int ncurnis;
+ int naddnis;
+ int ndelnis;
+ int nnis = 0;
+ int i;
+ int j;
+ int rc;
+
+ flags = LNET_PEER_DISCOVERED;
+ if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL)
+ flags |= LNET_PEER_MULTI_RAIL;