* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2012, 2014, Intel Corporation.
+ * Copyright (c) 2012, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#define DEBUG_SUBSYSTEM S_LNET
+#include <linux/sched.h>
+#ifdef HAVE_SCHED_HEADERS
+#include <linux/sched/signal.h>
+#endif
+#include <linux/uaccess.h>
+
#include <lnet/lib-lnet.h>
#include <uapi/linux/lnet/lnet-dlc.h>
+/* Value indicating that recovery needs to re-check a peer immediately. */
+#define LNET_REDISCOVER_PEER (1)
+
+static int lnet_peer_queue_for_discovery(struct lnet_peer *lp);
+
static void
lnet_peer_remove_from_remote_list(struct lnet_peer_ni *lpni)
{
return NULL;
INIT_LIST_HEAD(&lpni->lpni_txq);
- INIT_LIST_HEAD(&lpni->lpni_rtrq);
- INIT_LIST_HEAD(&lpni->lpni_routes);
INIT_LIST_HEAD(&lpni->lpni_hashlist);
INIT_LIST_HEAD(&lpni->lpni_peer_nis);
+ INIT_LIST_HEAD(&lpni->lpni_recovery);
INIT_LIST_HEAD(&lpni->lpni_on_remote_peer_ni_list);
+ LNetInvalidateMDHandle(&lpni->lpni_recovery_ping_mdh);
spin_lock_init(&lpni->lpni_lock);
- lpni->lpni_alive = !lnet_peers_start_down(); /* 1 bit!! */
- lpni->lpni_last_alive = cfs_time_current(); /* assumes alive */
+ if (lnet_peers_start_down())
+ lpni->lpni_ns_status = LNET_NI_STATUS_DOWN;
+ else
+ lpni->lpni_ns_status = LNET_NI_STATUS_UP;
lpni->lpni_ping_feats = LNET_PING_FEAT_INVAL;
lpni->lpni_nid = nid;
lpni->lpni_cpt = cpt;
- lnet_set_peer_ni_health_locked(lpni, true);
+ atomic_set(&lpni->lpni_healthv, LNET_MAX_HEALTH_VALUE);
net = lnet_get_net_locked(LNET_NIDNET(nid));
lpni->lpni_net = net;
if (!lp)
return NULL;
+ INIT_LIST_HEAD(&lp->lp_rtrq);
+ INIT_LIST_HEAD(&lp->lp_routes);
INIT_LIST_HEAD(&lp->lp_peer_list);
INIT_LIST_HEAD(&lp->lp_peer_nets);
INIT_LIST_HEAD(&lp->lp_dc_list);
+ INIT_LIST_HEAD(&lp->lp_dc_pendq);
+ INIT_LIST_HEAD(&lp->lp_rtr_list);
init_waitqueue_head(&lp->lp_dc_waitq);
spin_lock_init(&lp->lp_lock);
lp->lp_primary_nid = nid;
+
+ /*
+ * all peers created on a router should have health on
+ * if it's not already on.
+ */
+ if (the_lnet.ln_routing && !lnet_health_sensitivity)
+ lp->lp_health_sensitivity = 1;
+
+ /*
+ * Turn off discovery for loopback peer. If you're creating a peer
+ * for the loopback interface then that was initiated when we
+ * attempted to send a message over the loopback. There is no need
+ * to ever use a different interface when sending messages to
+ * myself.
+ */
+ if (LNET_NETTYP(LNET_NIDNET(nid)) == LOLND)
+ lp->lp_state = LNET_PEER_NO_DISCOVERY;
lp->lp_cpt = lnet_nid_cpt_hash(nid, LNET_CPT_NUMBER);
CDEBUG(D_NET, "%p nid %s\n", lp, libcfs_nid2str(lp->lp_primary_nid));
CDEBUG(D_NET, "%p nid %s\n", lp, libcfs_nid2str(lp->lp_primary_nid));
LASSERT(atomic_read(&lp->lp_refcount) == 0);
+ LASSERT(lp->lp_rtr_refcount == 0);
LASSERT(list_empty(&lp->lp_peer_nets));
LASSERT(list_empty(&lp->lp_peer_list));
+ LASSERT(list_empty(&lp->lp_dc_list));
+
+ if (lp->lp_data)
+ lnet_ping_buffer_decref(lp->lp_data);
+
+ /*
+ * if there are messages still on the pending queue, then make
+ * sure to queue them on the ln_msg_resend list so they can be
+ * resent at a later point if the discovery thread is still
+ * running.
+ * If the discovery thread has stopped, then the wakeup will be a
+ * no-op, and it is expected the lnet_shutdown_lndnets() will
+ * eventually be called, which will traverse this list and
+ * finalize the messages on the list.
+ * We can not resend them now because we're holding the cpt lock.
+ * Releasing the lock can cause an inconsistent state
+ */
+ spin_lock(&the_lnet.ln_msg_resend_lock);
+ spin_lock(&lp->lp_lock);
+ list_splice(&lp->lp_dc_pendq, &the_lnet.ln_msg_resend);
+ spin_unlock(&lp->lp_lock);
+ spin_unlock(&the_lnet.ln_msg_resend_lock);
+ wake_up(&the_lnet.ln_dc_waitq);
LIBCFS_FREE(lp, sizeof(*lp));
}
/* Update peer NID count. */
lp = lpn->lpn_peer;
- ptable = the_lnet.ln_peer_tables[lp->lp_cpt];
lp->lp_nnis--;
- ptable->pt_peer_nnids--;
/*
* If there are no more peer nets, make the peer unfindable
* via the peer_tables.
+ *
+ * Otherwise, if the peer is DISCOVERED, tell discovery to
+ * take another look at it. This is a no-op if discovery for
+ * this peer did the detaching.
*/
if (list_empty(&lp->lp_peer_nets)) {
list_del_init(&lp->lp_peer_list);
+ ptable = the_lnet.ln_peer_tables[lp->lp_cpt];
ptable->pt_peers--;
+ } else if (the_lnet.ln_dc_state != LNET_DC_STATE_RUNNING) {
+ /* Discovery isn't running, nothing to do here. */
+ } else if (lp->lp_state & LNET_PEER_DISCOVERED) {
+ lnet_peer_queue_for_discovery(lp);
+ wake_up(&the_lnet.ln_dc_waitq);
}
CDEBUG(D_NET, "peer %s NID %s\n",
libcfs_nid2str(lp->lp_primary_nid),
/* called with lnet_net_lock LNET_LOCK_EX held */
static int
-lnet_peer_ni_del_locked(struct lnet_peer_ni *lpni)
+lnet_peer_ni_del_locked(struct lnet_peer_ni *lpni, bool force)
{
struct lnet_peer_table *ptable = NULL;
/* don't remove a peer_ni if it's also a gateway */
- if (lpni->lpni_rtr_refcount > 0) {
+ if (lnet_isrouter(lpni) && !force) {
CERROR("Peer NI %s is a gateway. Can not delete it\n",
libcfs_nid2str(lpni->lpni_nid));
return -EBUSY;
/* remove peer ni from the hash list. */
list_del_init(&lpni->lpni_hashlist);
+ /*
+ * indicate the peer is being deleted so the monitor thread can
+ * remove it from the recovery queue.
+ */
+ spin_lock(&lpni->lpni_lock);
+ lpni->lpni_state |= LNET_PEER_NI_DELETING;
+ spin_unlock(&lpni->lpni_lock);
+
/* decrement the ref count on the peer table */
ptable = the_lnet.ln_peer_tables[lpni->lpni_cpt];
LASSERT(ptable->pt_number > 0);
/* remove all peer_nis from the remote peer and the hash list */
list_for_each_entry_safe(lpni, tmp, &the_lnet.ln_remote_peer_ni_list,
lpni_on_remote_peer_ni_list)
- lnet_peer_ni_del_locked(lpni);
+ lnet_peer_ni_del_locked(lpni, false);
lnet_peer_tables_destroy();
lpni = lnet_get_next_peer_ni_locked(peer, NULL, lpni);
while (lpni != NULL) {
lpni2 = lnet_get_next_peer_ni_locked(peer, NULL, lpni);
- rc = lnet_peer_ni_del_locked(lpni);
+ rc = lnet_peer_ni_del_locked(lpni, false);
if (rc != 0)
rc2 = rc;
lpni = lpni2;
struct lnet_peer_ni *lpni;
lnet_nid_t primary_nid = lp->lp_primary_nid;
int rc = 0;
+ bool force = (flags & LNET_PEER_RTR_NI_FORCE_DEL) ? true : false;
if (!(flags & LNET_PEER_CONFIGURED)) {
if (lp->lp_state & LNET_PEER_CONFIGURED) {
* This function only allows deletion of the primary NID if it
* is the only NID.
*/
- if (nid == lp->lp_primary_nid && lp->lp_nnis != 1) {
+ if (nid == lp->lp_primary_nid && lp->lp_nnis != 1 && !force) {
rc = -EBUSY;
goto out;
}
lnet_net_lock(LNET_LOCK_EX);
- lnet_peer_ni_del_locked(lpni);
+
+ if (nid == lp->lp_primary_nid && lp->lp_nnis != 1 && force) {
+ struct lnet_peer_ni *lpni2;
+ /* assign the next peer_ni to be the primary */
+ lpni2 = lnet_get_next_peer_ni_locked(lp, NULL, lpni);
+ LASSERT(lpni2);
+ lp->lp_primary_nid = lpni->lpni_nid;
+ }
+ rc = lnet_peer_ni_del_locked(lpni, force);
+
lnet_net_unlock(LNET_LOCK_EX);
out:
peer = lpni->lpni_peer_net->lpn_peer;
if (peer->lp_primary_nid != lpni->lpni_nid) {
- lnet_peer_ni_del_locked(lpni);
+ lnet_peer_ni_del_locked(lpni, false);
continue;
}
/*
{
struct lnet_peer_ni *lp;
struct lnet_peer_ni *tmp;
- lnet_nid_t lpni_nid;
+ lnet_nid_t gw_nid;
int i;
for (i = 0; i < LNET_PEER_HASH_SIZE; i++) {
if (net != lp->lpni_net)
continue;
- if (lp->lpni_rtr_refcount == 0)
+ if (!lnet_isrouter(lp))
continue;
- lpni_nid = lp->lpni_nid;
+ gw_nid = lp->lpni_peer_net->lpn_peer->lp_primary_nid;
lnet_net_unlock(LNET_LOCK_EX);
- lnet_del_route(LNET_NIDNET(LNET_NID_ANY), lpni_nid);
+ lnet_del_route(LNET_NIDNET(LNET_NID_ANY), gw_nid);
lnet_net_lock(LNET_LOCK_EX);
}
}
void
lnet_peer_tables_cleanup(struct lnet_net *net)
{
- int i;
- struct lnet_peer_table *ptable;
+ int i;
+ struct lnet_peer_table *ptable;
LASSERT(the_lnet.ln_state != LNET_STATE_SHUTDOWN || net != NULL);
/* If just deleting the peers for a NI, get rid of any routes these
}
struct lnet_peer_ni *
-lnet_get_peer_ni_idx_locked(int idx, struct lnet_peer_net **lpn,
- struct lnet_peer **lp)
+lnet_peer_get_ni_locked(struct lnet_peer *lp, lnet_nid_t nid)
{
- struct lnet_peer_table *ptable;
- struct lnet_peer_ni *lpni;
- int lncpt;
- int cpt;
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
- lncpt = cfs_percpt_number(the_lnet.ln_peer_tables);
+ lpn = lnet_peer_get_net_locked(lp, LNET_NIDNET(nid));
+ if (!lpn)
+ return NULL;
- for (cpt = 0; cpt < lncpt; cpt++) {
- ptable = the_lnet.ln_peer_tables[cpt];
- if (ptable->pt_peer_nnids > idx)
- break;
- idx -= ptable->pt_peer_nnids;
+ list_for_each_entry(lpni, &lpn->lpn_peer_nis, lpni_peer_nis) {
+ if (lpni->lpni_nid == nid)
+ return lpni;
}
- if (cpt >= lncpt)
- return NULL;
- list_for_each_entry((*lp), &ptable->pt_peer_list, lp_peer_list) {
- if ((*lp)->lp_nnis <= idx) {
- idx -= (*lp)->lp_nnis;
- continue;
- }
- list_for_each_entry((*lpn), &((*lp)->lp_peer_nets),
- lpn_peer_nets) {
- list_for_each_entry(lpni, &((*lpn)->lpn_peer_nis),
- lpni_peer_nis) {
- if (idx-- == 0)
- return lpni;
- }
+ return NULL;
+}
+
+struct lnet_peer *
+lnet_find_peer(lnet_nid_t nid)
+{
+ struct lnet_peer_ni *lpni;
+ struct lnet_peer *lp = NULL;
+ int cpt;
+
+ cpt = lnet_net_lock_current();
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni) {
+ lp = lpni->lpni_peer_net->lpn_peer;
+ lnet_peer_addref_locked(lp);
+ lnet_peer_ni_decref_locked(lpni);
+ }
+ lnet_net_unlock(cpt);
+
+ return lp;
+}
+
+struct lnet_peer_net *
+lnet_get_next_peer_net_locked(struct lnet_peer *lp, __u32 prev_lpn_id)
+{
+ struct lnet_peer_net *net;
+
+ if (!prev_lpn_id) {
+ /* no net id provided return the first net */
+ net = list_first_entry_or_null(&lp->lp_peer_nets,
+ struct lnet_peer_net,
+ lpn_peer_nets);
+
+ return net;
+ }
+
+ /* find the net after the one provided */
+ list_for_each_entry(net, &lp->lp_peer_nets, lpn_peer_nets) {
+ if (net->lpn_net_id == prev_lpn_id) {
+ /*
+ * if we reached the end of the list loop to the
+ * beginning.
+ */
+ if (net->lpn_peer_nets.next == &lp->lp_peer_nets)
+ return list_first_entry_or_null(&lp->lp_peer_nets,
+ struct lnet_peer_net,
+ lpn_peer_nets);
+ else
+ return list_next_entry(net, lpn_peer_nets);
}
}
return lpni;
}
+/* Call with the ln_api_mutex held */
+int lnet_get_peer_list(u32 *countp, u32 *sizep, struct lnet_process_id __user *ids)
+{
+ struct lnet_process_id id;
+ struct lnet_peer_table *ptable;
+ struct lnet_peer *lp;
+ __u32 count = 0;
+ __u32 size = 0;
+ int lncpt;
+ int cpt;
+ __u32 i;
+ int rc;
+
+ rc = -ESHUTDOWN;
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ goto done;
+
+ lncpt = cfs_percpt_number(the_lnet.ln_peer_tables);
+
+ /*
+ * Count the number of peers, and return E2BIG if the buffer
+ * is too small. We'll also return the desired size.
+ */
+ rc = -E2BIG;
+ for (cpt = 0; cpt < lncpt; cpt++) {
+ ptable = the_lnet.ln_peer_tables[cpt];
+ count += ptable->pt_peers;
+ }
+ size = count * sizeof(*ids);
+ if (size > *sizep)
+ goto done;
+
+ /*
+ * Walk the peer lists and copy out the primary nids.
+ * This is safe because the peer lists are only modified
+ * while the ln_api_mutex is held. So we don't need to
+ * hold the lnet_net_lock as well, and can therefore
+ * directly call copy_to_user().
+ */
+ rc = -EFAULT;
+ memset(&id, 0, sizeof(id));
+ id.pid = LNET_PID_LUSTRE;
+ i = 0;
+ for (cpt = 0; cpt < lncpt; cpt++) {
+ ptable = the_lnet.ln_peer_tables[cpt];
+ list_for_each_entry(lp, &ptable->pt_peer_list, lp_peer_list) {
+ if (i >= count)
+ goto done;
+ id.nid = lp->lp_primary_nid;
+ if (copy_to_user(&ids[i], &id, sizeof(id)))
+ goto done;
+ i++;
+ }
+ }
+ rc = 0;
+done:
+ *countp = count;
+ *sizep = size;
+ return rc;
+}
+
+/*
+ * Start pushes to peers that need to be updated for a configuration
+ * change on this node.
+ */
+void
+lnet_push_update_to_peers(int force)
+{
+ struct lnet_peer_table *ptable;
+ struct lnet_peer *lp;
+ int lncpt;
+ int cpt;
+
+ lnet_net_lock(LNET_LOCK_EX);
+ if (lnet_peer_discovery_disabled)
+ force = 0;
+ lncpt = cfs_percpt_number(the_lnet.ln_peer_tables);
+ for (cpt = 0; cpt < lncpt; cpt++) {
+ ptable = the_lnet.ln_peer_tables[cpt];
+ list_for_each_entry(lp, &ptable->pt_peer_list, lp_peer_list) {
+ if (force) {
+ spin_lock(&lp->lp_lock);
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL)
+ lp->lp_state |= LNET_PEER_FORCE_PUSH;
+ spin_unlock(&lp->lp_lock);
+ }
+ if (lnet_peer_needs_push(lp))
+ lnet_peer_queue_for_discovery(lp);
+ }
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+ wake_up(&the_lnet.ln_dc_waitq);
+}
+
/*
* Test whether a ni is a preferred ni for this peer_ni, e.g, whether
* this is a preferred point-to-point path. Call with lnet_net_lock in
return primary_nid;
}
+bool
+lnet_is_discovery_disabled_locked(struct lnet_peer *lp)
+{
+ 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;
rc = PTR_ERR(lpni);
goto out_unlock;
}
- primary_nid = lpni->lpni_peer_net->lpn_peer->lp_primary_nid;
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ while (!lnet_peer_is_uptodate(lp)) {
+ 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);
spin_unlock(&lp->lp_lock);
lp->lp_nnis++;
- the_lnet.ln_peer_tables[lp->lp_cpt]->pt_peer_nnids++;
lnet_net_unlock(LNET_LOCK_EX);
CDEBUG(D_NET, "peer %s NID %s flags %#x\n",
}
/* 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);
lpni = lnet_peer_ni_alloc(nid);
if (!lpni) {
}
/*
+ * 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
struct lnet_peer *lp;
struct lnet_peer_net *lpn;
struct lnet_peer_ni *lpni;
- unsigned flags = 0;
+ /*
+ * Assume peer is Multi-Rail capable and let discovery find out
+ * otherwise.
+ */
+ unsigned flags = LNET_PEER_MULTI_RAIL;
int rc = 0;
if (nid == LNET_NID_ANY) {
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);
CDEBUG(D_NET, "%p nid %s\n", lpni, libcfs_nid2str(lpni->lpni_nid));
LASSERT(atomic_read(&lpni->lpni_refcount) == 0);
- LASSERT(lpni->lpni_rtr_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;
return lpni;
}
-/*
- * Peer Discovery
- */
+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;
+}
/*
* Is a peer uptodate from the point of view of discovery?
LNET_PEER_FORCE_PUSH)) {
rc = false;
} else if (lp->lp_state & LNET_PEER_REDISCOVER) {
- if (lnet_peer_discovery_disabled)
- rc = true;
- else
- rc = false;
+ 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;
rc = -EALREADY;
}
+ CDEBUG(D_NET, "Queue peer %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+
return rc;
}
*/
static void lnet_peer_discovery_complete(struct lnet_peer *lp)
{
+ struct lnet_msg *msg, *tmp;
+ int rc = 0;
+ struct list_head pending_msgs;
+
+ INIT_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);
}
/*
- * 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.
+ * Handle inbound push.
+ * Like any event handler, called with lnet_res_lock/CPT held.
*/
-int
-lnet_discover_peer_locked(struct lnet_peer_ni *lpni, int cpt)
+void lnet_peer_push_event(struct lnet_event *ev)
{
- DEFINE_WAIT(wait);
+ struct lnet_ping_buffer *pbuf = ev->md.user_ptr;
struct lnet_peer *lp;
- int rc = 0;
-
-again:
- lnet_net_unlock(cpt);
- lnet_net_lock(LNET_LOCK_EX);
- /* We're willing to be interrupted. */
- for (;;) {
- lp = lpni->lpni_peer_net->lpn_peer;
- 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;
- if (lnet_peer_is_uptodate(lp))
- break;
- lnet_peer_queue_for_discovery(lp);
- lnet_peer_addref_locked(lp);
- 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);
- /* Do not use lp beyond this point. */
+ /* 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));
+ return;
}
- finish_wait(&lp->lp_dc_waitq, &wait);
- lnet_net_unlock(LNET_LOCK_EX);
- lnet_net_lock(cpt);
+ /* Ensure peer state remains consistent while we modify it. */
+ spin_lock(&lp->lp_lock);
- if (signal_pending(current))
- rc = -EINTR;
- else if (the_lnet.ln_dc_state != LNET_DC_STATE_RUNNING)
- rc = -ESHUTDOWN;
- else if (!lnet_peer_is_uptodate(lp))
- goto again;
+ /*
+ * 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;
+ }
- return rc;
-}
+ /*
+ * 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;
+ }
+
+ /*
+ * Check the MULTIRAIL flag. Complain if the peer was DLC
+ * configured without it.
+ */
+ if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ if (lp->lp_state & LNET_PEER_CONFIGURED) {
+ CERROR("Push says %s is Multi-Rail, DLC says not\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ } else {
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
+ }
+ }
+
+ /*
+ * 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));
+ 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;
+ }
+
+ /*
+ * 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 (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_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:
+ /*
+ * 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);
+
+ /*
+ * 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;
+ }
+
+
+ /*
+ * Only enable the multi-rail feature on the peer if both sides of
+ * the connection have discovery on
+ */
+ if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL) {
+ CDEBUG(D_NET, "Peer %s has Multi-Rail feature enabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ } else {
+ CDEBUG(D_NET, "Peer %s has Multi-Rail feature disabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state &= ~LNET_PEER_MULTI_RAIL;
+ }
+
+ /*
+ * 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) {
+ /* Everything's fine */
+ } 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 discovery is disabled then we don't want to
+ * update the state of the peer. All we'll do is
+ * update the peer_nis which were reported back in
+ * the initial ping
+ */
+
+ if (!lnet_is_discovery_disabled_locked(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);
+}
+
+/*
+ * 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(lnet_event_t *event)
+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;
+
+ /*
+ * Cache the routing feature for the peer; whether it is enabled
+ * for disabled as reported by the remote peer.
+ */
+ spin_lock(&lp->lp_lock);
+ if (!(pbuf->pb_info.pi_features & LNET_PING_FEAT_RTE_DISABLED))
+ lp->lp_state |= LNET_PEER_ROUTER_ENABLED;
+ else
+ lp->lp_state &= ~LNET_PEER_ROUTER_ENABLED;
+ spin_unlock(&lp->lp_lock);
+
+ nnis = MAX(lp->lp_nnis, pbuf->pb_info.pi_nnis);
+ LIBCFS_ALLOC(curnis, nnis * sizeof(*curnis));
+ LIBCFS_ALLOC(addnis, nnis * sizeof(*addnis));
+ LIBCFS_ALLOC(delnis, nnis * sizeof(*delnis));
+ if (!curnis || !addnis || !delnis) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ ncurnis = 0;
+ naddnis = 0;
+ ndelnis = 0;
+
+ /* Construct the list of NIDs present in peer. */
+ lpni = NULL;
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL)
+ curnis[ncurnis++] = lpni->lpni_nid;
+
+ /*
+ * Check for NIDs in pbuf not present in curnis[].
+ * The loop starts at 1 to skip the loopback NID.
+ */
+ for (i = 1; i < pbuf->pb_info.pi_nnis; i++) {
+ for (j = 0; j < ncurnis; j++)
+ if (pbuf->pb_info.pi_ni[i].ns_nid == curnis[j])
+ break;
+ if (j == ncurnis)
+ addnis[naddnis++] = pbuf->pb_info.pi_ni[i];
+ }
+ /*
+ * Check for NIDs in curnis[] not present in pbuf.
+ * The nested loop starts at 1 to skip the loopback NID.
+ *
+ * But never add the loopback NID to delnis[]: if it is
+ * present in curnis[] then this peer is for this node.
+ */
+ for (i = 0; i < ncurnis; i++) {
+ if (LNET_NETTYP(LNET_NIDNET(curnis[i])) == LOLND)
+ continue;
+ for (j = 1; j < pbuf->pb_info.pi_nnis; j++) {
+ if (curnis[i] == pbuf->pb_info.pi_ni[j].ns_nid) {
+ /*
+ * update the information we cache for the
+ * peer with the latest information we
+ * received
+ */
+ lpni = lnet_find_peer_ni_locked(curnis[i]);
+ if (lpni) {
+ lpni->lpni_ns_status = pbuf->pb_info.pi_ni[j].ns_status;
+ lnet_peer_ni_decref_locked(lpni);
+ }
+ break;
+ }
+ }
+ if (j == pbuf->pb_info.pi_nnis)
+ delnis[ndelnis++] = curnis[i];
+ }
+
+ /*
+ * If we get here and the discovery is disabled then we don't want
+ * to add or delete any NIs. We just updated the ones we have some
+ * information on, and call it a day
+ */
+ rc = 0;
+ if (lnet_is_discovery_disabled(lp))
+ goto out;
+
+ for (i = 0; i < naddnis; i++) {
+ rc = lnet_peer_add_nid(lp, addnis[i].ns_nid, flags);
+ if (rc) {
+ CERROR("Error adding NID %s to peer %s: %d\n",
+ libcfs_nid2str(addnis[i].ns_nid),
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+ if (rc == -ENOMEM)
+ goto out;
+ }
+ lpni = lnet_find_peer_ni_locked(addnis[i].ns_nid);
+ if (lpni) {
+ lpni->lpni_ns_status = addnis[i].ns_status;
+ lnet_peer_ni_decref_locked(lpni);
+ }
+ }
+
+ for (i = 0; i < ndelnis; i++) {
+ /*
+ * for routers it's okay to delete the primary_nid because
+ * the upper layers don't really rely on it. So if we're
+ * being told that the router changed its primary_nid
+ * then it's okay to delete it.
+ */
+ if (lp->lp_rtr_refcount > 0)
+ flags |= LNET_PEER_RTR_NI_FORCE_DEL;
+ rc = lnet_peer_del_nid(lp, delnis[i], flags);
+ if (rc) {
+ CERROR("Error deleting NID %s from peer %s: %d\n",
+ libcfs_nid2str(delnis[i]),
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+ if (rc == -ENOMEM)
+ goto out;
+ }
+ }
+ /*
+ * Errors other than -ENOMEM are due to peers having been
+ * configured with DLC. Ignore these because DLC overrides
+ * Discovery.
+ */
+ rc = 0;
+out:
+ LIBCFS_FREE(curnis, nnis * sizeof(*curnis));
+ LIBCFS_FREE(addnis, nnis * sizeof(*addnis));
+ LIBCFS_FREE(delnis, nnis * sizeof(*delnis));
+ lnet_ping_buffer_decref(pbuf);
+ CDEBUG(D_NET, "peer %s (%p): %d\n", libcfs_nid2str(lp->lp_primary_nid), lp, rc);
+
+ if (rc) {
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ spin_unlock(&lp->lp_lock);
+ }
+ return rc;
+}
+
+/*
+ * The data in pbuf says lp is its primary peer, but the data was
+ * received by a different peer. Try to update lp with the data.
+ */
+static int
+lnet_peer_set_primary_data(struct lnet_peer *lp, struct lnet_ping_buffer *pbuf)
+{
+ struct lnet_handle_md mdh;
+
+ /* Queue lp for discovery, and force it on the request queue. */
+ lnet_net_lock(LNET_LOCK_EX);
+ if (lnet_peer_queue_for_discovery(lp))
+ list_move(&lp->lp_dc_list, &the_lnet.ln_dc_request);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ LNetInvalidateMDHandle(&mdh);
+
+ /*
+ * Decide whether we can move the peer to the DATA_PRESENT state.
+ *
+ * We replace stale data for a multi-rail peer, repair PING_FAILED
+ * status, and preempt FORCE_PING.
+ *
+ * If after that we have DATA_PRESENT, we merge it into this peer.
+ */
+ spin_lock(&lp->lp_lock);
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
+ if (lp->lp_peer_seqno < LNET_PING_BUFFER_SEQNO(pbuf)) {
+ lp->lp_peer_seqno = LNET_PING_BUFFER_SEQNO(pbuf);
+ } else if (lp->lp_state & LNET_PEER_DATA_PRESENT) {
+ lp->lp_state &= ~LNET_PEER_DATA_PRESENT;
+ lnet_ping_buffer_decref(pbuf);
+ pbuf = lp->lp_data;
+ lp->lp_data = NULL;
+ }
+ }
+ if (lp->lp_state & LNET_PEER_DATA_PRESENT) {
+ lnet_ping_buffer_decref(lp->lp_data);
+ lp->lp_data = NULL;
+ lp->lp_state &= ~LNET_PEER_DATA_PRESENT;
+ }
+ if (lp->lp_state & LNET_PEER_PING_FAILED) {
+ mdh = lp->lp_ping_mdh;
+ LNetInvalidateMDHandle(&lp->lp_ping_mdh);
+ lp->lp_state &= ~LNET_PEER_PING_FAILED;
+ lp->lp_ping_error = 0;
+ }
+ if (lp->lp_state & LNET_PEER_FORCE_PING)
+ lp->lp_state &= ~LNET_PEER_FORCE_PING;
+ lp->lp_state |= LNET_PEER_NIDS_UPTODATE;
+ spin_unlock(&lp->lp_lock);
+
+ if (!LNetMDHandleIsInvalid(mdh))
+ LNetMDUnlink(mdh);
+
+ if (pbuf)
+ return lnet_peer_merge_data(lp, pbuf);
+
+ CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+ return 0;
+}
+
+static bool lnet_is_nid_in_ping_info(lnet_nid_t nid, struct lnet_ping_info *pinfo)
+{
+ int i;
+
+ for (i = 0; i < pinfo->pi_nnis; i++) {
+ if (pinfo->pi_ni[i].ns_nid == nid)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Update a peer using the data received.
+ */
+static int lnet_peer_data_present(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ struct lnet_ping_buffer *pbuf;
+ struct lnet_peer_ni *lpni;
+ lnet_nid_t nid = LNET_NID_ANY;
+ unsigned flags;
+ int rc = 0;
+
+ pbuf = lp->lp_data;
+ lp->lp_data = NULL;
+ lp->lp_state &= ~LNET_PEER_DATA_PRESENT;
+ lp->lp_state |= LNET_PEER_NIDS_UPTODATE;
+ spin_unlock(&lp->lp_lock);
+
+ /*
+ * Modifications of peer structures are done while holding the
+ * ln_api_mutex. A global lock is required because we may be
+ * modifying multiple peer structures, and a mutex greatly
+ * simplifies memory management.
+ *
+ * The actual changes to the data structures must also protect
+ * against concurrent lookups, for which the lnet_net_lock in
+ * LNET_LOCK_EX mode is used.
+ */
+ mutex_lock(&the_lnet.ln_api_mutex);
+ if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ rc = -ESHUTDOWN;
+ goto out;
+ }
+
+ /*
+ * If this peer is not on the peer list then it is being torn
+ * down, and our reference count may be all that is keeping it
+ * alive. Don't do any work on it.
+ */
+ if (list_empty(&lp->lp_peer_list))
+ goto out;
+
+ flags = LNET_PEER_DISCOVERED;
+ if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL)
+ flags |= LNET_PEER_MULTI_RAIL;
+
+ /*
+ * Check whether the primary NID in the message matches the
+ * primary NID of the peer. If it does, update the peer, if
+ * it it does not, check whether there is already a peer with
+ * that primary NID. If no such peer exists, try to update
+ * the primary NID of the current peer (allowed if it was
+ * created due to message traffic) and complete the update.
+ * If the peer did exist, hand off the data to it.
+ *
+ * The peer for the loopback interface is a special case: this
+ * is the peer for the local node, and we want to set its
+ * primary NID to the correct value here. Moreover, this peer
+ * can show up with only the loopback NID in the ping buffer.
+ */
+ if (pbuf->pb_info.pi_nnis <= 1)
+ goto out;
+ nid = pbuf->pb_info.pi_ni[1].ns_nid;
+ if (LNET_NETTYP(LNET_NIDNET(lp->lp_primary_nid)) == LOLND) {
+ rc = lnet_peer_set_primary_nid(lp, nid, flags);
+ if (!rc)
+ rc = lnet_peer_merge_data(lp, pbuf);
+ /*
+ * if the primary nid of the peer is present in the ping info returned
+ * from the peer, but it's not the local primary peer we have
+ * cached and discovery is disabled, then we don't want to update
+ * our local peer info, by adding or removing NIDs, we just want
+ * to update the status of the nids that we currently have
+ * recorded in that peer.
+ */
+ } else if (lp->lp_primary_nid == nid ||
+ (lnet_is_nid_in_ping_info(lp->lp_primary_nid, &pbuf->pb_info) &&
+ lnet_is_discovery_disabled(lp))) {
+ rc = lnet_peer_merge_data(lp, pbuf);
+ } else {
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (!lpni) {
+ rc = lnet_peer_set_primary_nid(lp, nid, flags);
+ if (rc) {
+ CERROR("Primary NID error %s versus %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ libcfs_nid2str(nid), rc);
+ } else {
+ rc = lnet_peer_merge_data(lp, pbuf);
+ }
+ } else {
+ struct lnet_peer *new_lp;
+ new_lp = lpni->lpni_peer_net->lpn_peer;
+ /*
+ * if lp has discovery/MR enabled that means new_lp
+ * should have discovery/MR enabled as well, since
+ * it's the same peer, which we're about to merge
+ */
+ if (!(lp->lp_state & LNET_PEER_NO_DISCOVERY))
+ new_lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
+ if (lp->lp_state & LNET_PEER_MULTI_RAIL)
+ new_lp->lp_state |= LNET_PEER_MULTI_RAIL;
+
+ rc = lnet_peer_set_primary_data(new_lp, pbuf);
+ lnet_consolidate_routes_locked(lp, new_lp);
+ lnet_peer_ni_decref_locked(lpni);
+ }
+ }
+out:
+ CDEBUG(D_NET, "peer %s(%p): %d. state = 0x%x\n", libcfs_nid2str(lp->lp_primary_nid), lp, rc,
+ lp->lp_state);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ spin_lock(&lp->lp_lock);
+ /* Tell discovery to re-check the peer immediately. */
+ if (!rc)
+ rc = LNET_REDISCOVER_PEER;
+ return rc;
+}
+
+/*
+ * A ping failed. Clear the PING_FAILED state and set the
+ * FORCE_PING state, to ensure a retry even if discovery is
+ * disabled. This avoids being left with incorrect state.
+ */
+static int lnet_peer_ping_failed(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
{
- wake_up(&the_lnet.ln_dc_waitq);
+ struct lnet_handle_md mdh;
+ int rc;
+
+ mdh = lp->lp_ping_mdh;
+ LNetInvalidateMDHandle(&lp->lp_ping_mdh);
+ lp->lp_state &= ~LNET_PEER_PING_FAILED;
+ lp->lp_state |= LNET_PEER_FORCE_PING;
+ rc = lp->lp_ping_error;
+ lp->lp_ping_error = 0;
+ spin_unlock(&lp->lp_lock);
+
+ if (!LNetMDHandleIsInvalid(mdh))
+ LNetMDUnlink(mdh);
+
+ CDEBUG(D_NET, "peer %s:%d\n",
+ libcfs_nid2str(lp->lp_primary_nid), rc);
+
+ spin_lock(&lp->lp_lock);
+ return rc ? rc : LNET_REDISCOVER_PEER;
+}
+
+/*
+ * Select NID to send a Ping or Push to.
+ */
+static lnet_nid_t lnet_peer_select_nid(struct lnet_peer *lp)
+{
+ struct lnet_peer_ni *lpni;
+
+ /* Look for a direct-connected NID for this peer. */
+ lpni = NULL;
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
+ if (!lnet_get_net_locked(lpni->lpni_peer_net->lpn_net_id))
+ continue;
+ break;
+ }
+ if (lpni)
+ return lpni->lpni_nid;
+
+ /* Look for a routed-connected NID for this peer. */
+ lpni = NULL;
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
+ if (!lnet_find_rnet_locked(lpni->lpni_peer_net->lpn_net_id))
+ continue;
+ break;
+ }
+ if (lpni)
+ return lpni->lpni_nid;
+
+ return LNET_NID_ANY;
+}
+
+/* Active side of ping. */
+static int lnet_peer_send_ping(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ lnet_nid_t pnid;
+ int nnis;
+ int rc;
+ int cpt;
+
+ lp->lp_state |= LNET_PEER_PING_SENT;
+ lp->lp_state &= ~LNET_PEER_FORCE_PING;
+ spin_unlock(&lp->lp_lock);
+
+ cpt = lnet_net_lock_current();
+ /* Refcount for MD. */
+ lnet_peer_addref_locked(lp);
+ pnid = lnet_peer_select_nid(lp);
+ lnet_net_unlock(cpt);
+
+ nnis = MAX(lp->lp_data_nnis, LNET_INTERFACES_MIN);
+
+ rc = lnet_send_ping(pnid, &lp->lp_ping_mdh, nnis, lp,
+ the_lnet.ln_dc_eqh, false);
+
+ /*
+ * if LNetMDBind in lnet_send_ping fails we need to decrement the
+ * refcount on the peer, otherwise LNetMDUnlink will be called
+ * which will eventually do that.
+ */
+ if (rc > 0) {
+ lnet_net_lock(cpt);
+ lnet_peer_decref_locked(lp);
+ lnet_net_unlock(cpt);
+ rc = -rc; /* change the rc to negative value */
+ goto fail_error;
+ } else if (rc < 0) {
+ goto fail_error;
+ }
+
+ CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+
+ spin_lock(&lp->lp_lock);
+ return 0;
+
+fail_error:
+ CDEBUG(D_NET, "peer %s: %d\n", libcfs_nid2str(lp->lp_primary_nid), rc);
+ /*
+ * The errors that get us here are considered hard errors and
+ * cause Discovery to terminate. So we clear PING_SENT, but do
+ * not set either PING_FAILED or FORCE_PING. In fact we need
+ * to clear PING_FAILED, because the unlink event handler will
+ * have set it if we called LNetMDUnlink() above.
+ */
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~(LNET_PEER_PING_SENT | LNET_PEER_PING_FAILED);
+ return rc;
+}
+
+/*
+ * This function exists because you cannot call LNetMDUnlink() from an
+ * event handler.
+ */
+static int lnet_peer_push_failed(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ struct lnet_handle_md mdh;
+ int rc;
+
+ mdh = lp->lp_push_mdh;
+ LNetInvalidateMDHandle(&lp->lp_push_mdh);
+ lp->lp_state &= ~LNET_PEER_PUSH_FAILED;
+ rc = lp->lp_push_error;
+ lp->lp_push_error = 0;
+ spin_unlock(&lp->lp_lock);
+
+ if (!LNetMDHandleIsInvalid(mdh))
+ LNetMDUnlink(mdh);
+
+ CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+ spin_lock(&lp->lp_lock);
+ return rc ? rc : LNET_REDISCOVER_PEER;
+}
+
+/* Active side of push. */
+static int lnet_peer_send_push(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ struct lnet_ping_buffer *pbuf;
+ struct lnet_process_id id;
+ struct lnet_md md;
+ int cpt;
+ int rc;
+
+ /* Don't push to a non-multi-rail peer. */
+ if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
+ lp->lp_state &= ~LNET_PEER_FORCE_PUSH;
+ return 0;
+ }
+
+ lp->lp_state |= LNET_PEER_PUSH_SENT;
+ lp->lp_state &= ~LNET_PEER_FORCE_PUSH;
+ spin_unlock(&lp->lp_lock);
+
+ cpt = lnet_net_lock_current();
+ pbuf = the_lnet.ln_ping_target;
+ lnet_ping_buffer_addref(pbuf);
+ lnet_net_unlock(cpt);
+
+ /* Push source MD */
+ md.start = &pbuf->pb_info;
+ md.length = LNET_PING_INFO_SIZE(pbuf->pb_nnis);
+ md.threshold = 2; /* Put/Ack */
+ md.max_size = 0;
+ md.options = 0;
+ md.eq_handle = the_lnet.ln_dc_eqh;
+ md.user_ptr = lp;
+
+ rc = LNetMDBind(md, LNET_UNLINK, &lp->lp_push_mdh);
+ if (rc) {
+ lnet_ping_buffer_decref(pbuf);
+ CERROR("Can't bind push source MD: %d\n", rc);
+ goto fail_error;
+ }
+ cpt = lnet_net_lock_current();
+ /* Refcount for MD. */
+ lnet_peer_addref_locked(lp);
+ id.pid = LNET_PID_LUSTRE;
+ id.nid = lnet_peer_select_nid(lp);
+ lnet_net_unlock(cpt);
+
+ if (id.nid == LNET_NID_ANY) {
+ rc = -EHOSTUNREACH;
+ goto fail_unlink;
+ }
+
+ rc = LNetPut(LNET_NID_ANY, lp->lp_push_mdh,
+ LNET_ACK_REQ, id, LNET_RESERVED_PORTAL,
+ LNET_PROTO_PING_MATCHBITS, 0, 0);
+
+ if (rc)
+ goto fail_unlink;
+
+ CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+
+ spin_lock(&lp->lp_lock);
+ return 0;
+
+fail_unlink:
+ LNetMDUnlink(lp->lp_push_mdh);
+ LNetInvalidateMDHandle(&lp->lp_push_mdh);
+fail_error:
+ CDEBUG(D_NET, "peer %s(%p): %d\n", libcfs_nid2str(lp->lp_primary_nid), lp, rc);
+ /*
+ * The errors that get us here are considered hard errors and
+ * cause Discovery to terminate. So we clear PUSH_SENT, but do
+ * not set PUSH_FAILED. In fact we need to clear PUSH_FAILED,
+ * because the unlink event handler will have set it if we
+ * called LNetMDUnlink() above.
+ */
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~(LNET_PEER_PUSH_SENT | LNET_PEER_PUSH_FAILED);
+ return rc;
+}
+
+/*
+ * An unrecoverable error was encountered during discovery.
+ * Set error status in peer and abort discovery.
+ */
+static void lnet_peer_discovery_error(struct lnet_peer *lp, int error)
+{
+ CDEBUG(D_NET, "Discovery error %s: %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), error);
+
+ spin_lock(&lp->lp_lock);
+ lp->lp_dc_error = error;
+ lp->lp_state &= ~LNET_PEER_DISCOVERING;
+ lp->lp_state |= LNET_PEER_REDISCOVER;
+ spin_unlock(&lp->lp_lock);
+}
+
+/*
+ * Mark the peer as discovered.
+ */
+static int lnet_peer_discovered(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+ lp->lp_state |= LNET_PEER_DISCOVERED;
+ lp->lp_state &= ~(LNET_PEER_DISCOVERING |
+ LNET_PEER_REDISCOVER);
+
+ CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+
+ return 0;
+}
+
+
+/*
+ * Discovering this peer is taking too long. Cancel any Ping or Push
+ * that discovery is waiting on by unlinking the relevant MDs. The
+ * lnet_discovery_event_handler() will proceed from here and complete
+ * the cleanup.
+ */
+static void lnet_peer_cancel_discovery(struct lnet_peer *lp)
+{
+ struct lnet_handle_md ping_mdh;
+ struct lnet_handle_md push_mdh;
+
+ LNetInvalidateMDHandle(&ping_mdh);
+ LNetInvalidateMDHandle(&push_mdh);
+
+ spin_lock(&lp->lp_lock);
+ if (lp->lp_state & LNET_PEER_PING_SENT) {
+ ping_mdh = lp->lp_ping_mdh;
+ LNetInvalidateMDHandle(&lp->lp_ping_mdh);
+ }
+ if (lp->lp_state & LNET_PEER_PUSH_SENT) {
+ push_mdh = lp->lp_push_mdh;
+ LNetInvalidateMDHandle(&lp->lp_push_mdh);
+ }
+ spin_unlock(&lp->lp_lock);
+
+ if (!LNetMDHandleIsInvalid(ping_mdh))
+ LNetMDUnlink(ping_mdh);
+ if (!LNetMDHandleIsInvalid(push_mdh))
+ LNetMDUnlink(push_mdh);
}
/*
TASK_INTERRUPTIBLE);
if (the_lnet.ln_dc_state == LNET_DC_STATE_STOPPING)
break;
+ if (lnet_push_target_resize_needed())
+ break;
if (!list_empty(&the_lnet.ln_dc_request))
break;
+ if (!list_empty(&the_lnet.ln_msg_resend))
+ break;
lnet_net_unlock(cpt);
- schedule();
+
+ /*
+ * wakeup max every second to check if there are peers that
+ * have been stuck on the working queue for greater than
+ * the peer timeout.
+ */
+ schedule_timeout(cfs_time_seconds(1));
finish_wait(&the_lnet.ln_dc_waitq, &wait);
cpt = lnet_net_lock_current();
}
return rc;
}
+/*
+ * Messages that were pending on a destroyed peer will be put on a global
+ * resend list. The message resend list will be checked by
+ * the discovery thread when it wakes up, and will resend messages. These
+ * messages can still be sendable in the case the lpni which was the initial
+ * cause of the message re-queue was transfered to another peer.
+ *
+ * It is possible that LNet could be shutdown while we're iterating
+ * through the list. lnet_shudown_lndnets() will attempt to access the
+ * resend list, but will have to wait until the spinlock is released, by
+ * which time there shouldn't be any more messages on the resend list.
+ * During shutdown lnet_send() will fail and lnet_finalize() will be called
+ * for the messages so they can be released. The other case is that
+ * lnet_shudown_lndnets() can finalize all the messages before this
+ * function can visit the resend list, in which case this function will be
+ * a no-op.
+ */
+static void lnet_resend_msgs(void)
+{
+ struct lnet_msg *msg, *tmp;
+ struct list_head resend;
+ int rc;
+
+ INIT_LIST_HEAD(&resend);
+
+ spin_lock(&the_lnet.ln_msg_resend_lock);
+ list_splice(&the_lnet.ln_msg_resend, &resend);
+ spin_unlock(&the_lnet.ln_msg_resend_lock);
+
+ list_for_each_entry_safe(msg, tmp, &resend, msg_list) {
+ list_del_init(&msg->msg_list);
+ 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);
+ }
+ }
+}
+
/* The discovery thread. */
static int lnet_peer_discovery(void *arg)
{
struct lnet_peer *lp;
+ int rc;
+
+ wait_for_completion(&the_lnet.ln_started);
CDEBUG(D_NET, "started\n");
cfs_block_allsigs();
if (lnet_peer_discovery_wait_for_work())
break;
+ lnet_resend_msgs();
+
+ if (lnet_push_target_resize_needed())
+ lnet_push_target_resize();
+
lnet_net_lock(LNET_LOCK_EX);
if (the_lnet.ln_dc_state == LNET_DC_STATE_STOPPING)
break;
+
+ /*
+ * Process all incoming discovery work requests. When
+ * discovery must wait on a peer to change state, it
+ * is added to the tail of the ln_dc_working queue. A
+ * timestamp keeps track of when the peer was added,
+ * so we can time out discovery requests that take too
+ * long.
+ */
while (!list_empty(&the_lnet.ln_dc_request)) {
lp = list_first_entry(&the_lnet.ln_dc_request,
struct lnet_peer, lp_dc_list);
list_move(&lp->lp_dc_list, &the_lnet.ln_dc_working);
+ /*
+ * set the time the peer was put on the dc_working
+ * queue. It shouldn't remain on the queue
+ * forever, in case the GET message (for ping)
+ * doesn't get a REPLY or the PUT message (for
+ * push) doesn't get an ACK.
+ */
+ lp->lp_last_queued = ktime_get_real_seconds();
lnet_net_unlock(LNET_LOCK_EX);
- /* Just tag and release for now. */
+ /*
+ * Select an action depending on the state of
+ * the peer and whether discovery is disabled.
+ * The check whether discovery is disabled is
+ * done after the code that handles processing
+ * for arrived data, cleanup for failures, and
+ * forcing a Ping or Push.
+ */
spin_lock(&lp->lp_lock);
- if (lnet_peer_discovery_disabled) {
- lp->lp_state |= LNET_PEER_REDISCOVER;
- lp->lp_state &= ~(LNET_PEER_DISCOVERED |
- LNET_PEER_NIDS_UPTODATE |
- LNET_PEER_DISCOVERING);
- } else {
- lp->lp_state |= (LNET_PEER_DISCOVERED |
- LNET_PEER_NIDS_UPTODATE);
- lp->lp_state &= ~(LNET_PEER_REDISCOVER |
- LNET_PEER_DISCOVERING);
- }
+ CDEBUG(D_NET, "peer %s(%p) state %#x\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp,
+ lp->lp_state);
+ if (lp->lp_state & LNET_PEER_DATA_PRESENT)
+ rc = lnet_peer_data_present(lp);
+ else if (lp->lp_state & LNET_PEER_PING_FAILED)
+ rc = lnet_peer_ping_failed(lp);
+ else if (lp->lp_state & LNET_PEER_PUSH_FAILED)
+ rc = lnet_peer_push_failed(lp);
+ else if (lp->lp_state & LNET_PEER_FORCE_PING)
+ rc = lnet_peer_send_ping(lp);
+ else if (lp->lp_state & LNET_PEER_FORCE_PUSH)
+ rc = lnet_peer_send_push(lp);
+ else if (!(lp->lp_state & LNET_PEER_NIDS_UPTODATE))
+ rc = lnet_peer_send_ping(lp);
+ else if (lnet_peer_needs_push(lp))
+ rc = lnet_peer_send_push(lp);
+ else
+ rc = lnet_peer_discovered(lp);
+ CDEBUG(D_NET, "peer %s(%p) state %#x rc %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp,
+ lp->lp_state, rc);
spin_unlock(&lp->lp_lock);
lnet_net_lock(LNET_LOCK_EX);
+ if (rc == LNET_REDISCOVER_PEER) {
+ list_move(&lp->lp_dc_list,
+ &the_lnet.ln_dc_request);
+ } else if (rc) {
+ lnet_peer_discovery_error(lp, rc);
+ }
if (!(lp->lp_state & LNET_PEER_DISCOVERING))
lnet_peer_discovery_complete(lp);
if (the_lnet.ln_dc_state == LNET_DC_STATE_STOPPING)
break;
}
+
lnet_net_unlock(LNET_LOCK_EX);
}
* size of the thundering herd if there are multiple threads
* waiting on discovery of a single peer.
*/
- LNetEQFree(the_lnet.ln_dc_eqh);
- LNetInvalidateEQHandle(&the_lnet.ln_dc_eqh);
+ /* Queue cleanup 1: stop all pending pings and pushes. */
lnet_net_lock(LNET_LOCK_EX);
- list_for_each_entry(lp, &the_lnet.ln_dc_request, lp_dc_list) {
- spin_lock(&lp->lp_lock);
- lp->lp_state |= LNET_PEER_REDISCOVER;
- lp->lp_state &= ~(LNET_PEER_DISCOVERED |
- LNET_PEER_DISCOVERING |
- LNET_PEER_NIDS_UPTODATE);
- spin_unlock(&lp->lp_lock);
- lnet_peer_discovery_complete(lp);
+ while (!list_empty(&the_lnet.ln_dc_working)) {
+ lp = list_first_entry(&the_lnet.ln_dc_working,
+ struct lnet_peer, lp_dc_list);
+ list_move(&lp->lp_dc_list, &the_lnet.ln_dc_expired);
+ lnet_net_unlock(LNET_LOCK_EX);
+ lnet_peer_cancel_discovery(lp);
+ lnet_net_lock(LNET_LOCK_EX);
}
- list_for_each_entry(lp, &the_lnet.ln_dc_working, lp_dc_list) {
- spin_lock(&lp->lp_lock);
- lp->lp_state |= LNET_PEER_REDISCOVER;
- lp->lp_state &= ~(LNET_PEER_DISCOVERED |
- LNET_PEER_DISCOVERING |
- LNET_PEER_NIDS_UPTODATE);
- spin_unlock(&lp->lp_lock);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ /* Queue cleanup 2: wait for the expired queue to clear. */
+ while (!list_empty(&the_lnet.ln_dc_expired))
+ schedule_timeout(cfs_time_seconds(1));
+
+ /* Queue cleanup 3: clear the request queue. */
+ lnet_net_lock(LNET_LOCK_EX);
+ while (!list_empty(&the_lnet.ln_dc_request)) {
+ lp = list_first_entry(&the_lnet.ln_dc_request,
+ struct lnet_peer, lp_dc_list);
+ lnet_peer_discovery_error(lp, -ESHUTDOWN);
lnet_peer_discovery_complete(lp);
}
lnet_net_unlock(LNET_LOCK_EX);
+ LNetEQFree(the_lnet.ln_dc_eqh);
+ LNetInvalidateEQHandle(&the_lnet.ln_dc_eqh);
+
the_lnet.ln_dc_state = LNET_DC_STATE_SHUTDOWN;
wake_up(&the_lnet.ln_dc_waitq);
if (the_lnet.ln_dc_state != LNET_DC_STATE_SHUTDOWN)
return -EALREADY;
- INIT_LIST_HEAD(&the_lnet.ln_dc_request);
- INIT_LIST_HEAD(&the_lnet.ln_dc_working);
- init_waitqueue_head(&the_lnet.ln_dc_waitq);
-
rc = LNetEQAlloc(0, lnet_discovery_event_handler, &the_lnet.ln_dc_eqh);
if (rc != 0) {
CERROR("Can't allocate discovery EQ: %d\n", rc);
the_lnet.ln_dc_state = LNET_DC_STATE_SHUTDOWN;
}
+ CDEBUG(D_NET, "discovery start: %d\n", rc);
+
return rc;
}
LASSERT(the_lnet.ln_dc_state == LNET_DC_STATE_RUNNING);
the_lnet.ln_dc_state = LNET_DC_STATE_STOPPING;
- wake_up(&the_lnet.ln_dc_waitq);
+
+ /* In the LNetNIInit() path we may be stopping discovery before it
+ * entered its work loop
+ */
+ if (!completion_done(&the_lnet.ln_started))
+ complete(&the_lnet.ln_started);
+ else
+ wake_up(&the_lnet.ln_dc_waitq);
wait_event(the_lnet.ln_dc_waitq,
the_lnet.ln_dc_state == LNET_DC_STATE_SHUTDOWN);
LASSERT(list_empty(&the_lnet.ln_dc_request));
LASSERT(list_empty(&the_lnet.ln_dc_working));
+ LASSERT(list_empty(&the_lnet.ln_dc_expired));
+
+ CDEBUG(D_NET, "discovery stopped\n");
}
/* Debugging */
}
if (lnet_isrouter(lp) || lnet_peer_aliveness_enabled(lp))
- aliveness = lp->lpni_alive ? "up" : "down";
+ aliveness = (lnet_is_peer_ni_alive(lp)) ? "up" : "down";
CDEBUG(D_WARNING, "%-24s %4d %5s %5d %5d %5d %5d %5d %ld\n",
libcfs_nid2str(lp->lpni_nid), atomic_read(&lp->lpni_refcount),
if (lnet_isrouter(lp) ||
lnet_peer_aliveness_enabled(lp))
snprintf(aliveness, LNET_MAX_STR_LEN,
- lp->lpni_alive ? "up" : "down");
+ lnet_is_peer_ni_alive(lp) ? "up" : "down");
*nid = lp->lpni_nid;
*refcount = atomic_read(&lp->lpni_refcount);
}
/* ln_api_mutex is held, which keeps the peer list stable */
-int lnet_get_peer_info(__u32 idx, lnet_nid_t *primary_nid, lnet_nid_t *nid,
- bool *mr,
- struct lnet_peer_ni_credit_info __user *peer_ni_info,
- struct lnet_ioctl_element_stats __user *peer_ni_stats)
+int lnet_get_peer_info(struct lnet_ioctl_peer_cfg *cfg, void __user *bulk)
{
- struct lnet_peer_ni *lpni = NULL;
- struct lnet_peer_net *lpn = NULL;
- struct lnet_peer *lp = NULL;
- struct lnet_peer_ni_credit_info ni_info;
- struct lnet_ioctl_element_stats ni_stats;
+ struct lnet_ioctl_element_stats *lpni_stats;
+ struct lnet_ioctl_element_msg_stats *lpni_msg_stats;
+ struct lnet_ioctl_peer_ni_hstats *lpni_hstats;
+ struct lnet_peer_ni_credit_info *lpni_info;
+ struct lnet_peer_ni *lpni;
+ struct lnet_peer *lp;
+ lnet_nid_t nid;
+ __u32 size;
int rc;
- lpni = lnet_get_peer_ni_idx_locked(idx, &lpn, &lp);
+ lp = lnet_find_peer(cfg->prcfg_prim_nid);
- if (!lpni)
- return -ENOENT;
+ if (!lp) {
+ rc = -ENOENT;
+ goto out;
+ }
- *primary_nid = lp->lp_primary_nid;
- *mr = lnet_peer_is_multi_rail(lp);
- *nid = lpni->lpni_nid;
- snprintf(ni_info.cr_aliveness, LNET_MAX_STR_LEN, "NA");
- if (lnet_isrouter(lpni) ||
- lnet_peer_aliveness_enabled(lpni))
- snprintf(ni_info.cr_aliveness, LNET_MAX_STR_LEN,
- lpni->lpni_alive ? "up" : "down");
-
- ni_info.cr_refcount = atomic_read(&lpni->lpni_refcount);
- ni_info.cr_ni_peer_tx_credits = (lpni->lpni_net != NULL) ?
- lpni->lpni_net->net_tunables.lct_peer_tx_credits : 0;
- ni_info.cr_peer_tx_credits = lpni->lpni_txcredits;
- ni_info.cr_peer_rtr_credits = lpni->lpni_rtrcredits;
- ni_info.cr_peer_min_rtr_credits = lpni->lpni_minrtrcredits;
- ni_info.cr_peer_min_tx_credits = lpni->lpni_mintxcredits;
- ni_info.cr_peer_tx_qnob = lpni->lpni_txqnob;
- ni_info.cr_ncpt = lpni->lpni_cpt;
-
- ni_stats.iel_send_count = atomic_read(&lpni->lpni_stats.send_count);
- ni_stats.iel_recv_count = atomic_read(&lpni->lpni_stats.recv_count);
- ni_stats.iel_drop_count = atomic_read(&lpni->lpni_stats.drop_count);
-
- /* If copy_to_user fails */
- rc = -EFAULT;
- if (copy_to_user(peer_ni_info, &ni_info, sizeof(ni_info)))
- goto copy_failed;
+ size = sizeof(nid) + sizeof(*lpni_info) + sizeof(*lpni_stats)
+ + sizeof(*lpni_msg_stats) + sizeof(*lpni_hstats);
+ size *= lp->lp_nnis;
+ if (size > cfg->prcfg_size) {
+ cfg->prcfg_size = size;
+ rc = -E2BIG;
+ goto out_lp_decref;
+ }
- if (copy_to_user(peer_ni_stats, &ni_stats, sizeof(ni_stats)))
- goto copy_failed;
+ cfg->prcfg_prim_nid = lp->lp_primary_nid;
+ cfg->prcfg_mr = lnet_peer_is_multi_rail(lp);
+ cfg->prcfg_cfg_nid = lp->lp_primary_nid;
+ cfg->prcfg_count = lp->lp_nnis;
+ cfg->prcfg_size = size;
+ cfg->prcfg_state = lp->lp_state;
+ /* Allocate helper buffers. */
+ rc = -ENOMEM;
+ LIBCFS_ALLOC(lpni_info, sizeof(*lpni_info));
+ if (!lpni_info)
+ goto out_lp_decref;
+ LIBCFS_ALLOC(lpni_stats, sizeof(*lpni_stats));
+ if (!lpni_stats)
+ goto out_free_info;
+ LIBCFS_ALLOC(lpni_msg_stats, sizeof(*lpni_msg_stats));
+ if (!lpni_msg_stats)
+ goto out_free_stats;
+ LIBCFS_ALLOC(lpni_hstats, sizeof(*lpni_hstats));
+ if (!lpni_hstats)
+ goto out_free_msg_stats;
+
+
+ lpni = NULL;
+ rc = -EFAULT;
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
+ nid = lpni->lpni_nid;
+ if (copy_to_user(bulk, &nid, sizeof(nid)))
+ goto out_free_hstats;
+ bulk += sizeof(nid);
+
+ memset(lpni_info, 0, sizeof(*lpni_info));
+ snprintf(lpni_info->cr_aliveness, LNET_MAX_STR_LEN, "NA");
+ if (lnet_isrouter(lpni) ||
+ lnet_peer_aliveness_enabled(lpni))
+ snprintf(lpni_info->cr_aliveness, LNET_MAX_STR_LEN,
+ lnet_is_peer_ni_alive(lpni) ? "up" : "down");
+
+ lpni_info->cr_refcount = atomic_read(&lpni->lpni_refcount);
+ lpni_info->cr_ni_peer_tx_credits = (lpni->lpni_net != NULL) ?
+ lpni->lpni_net->net_tunables.lct_peer_tx_credits : 0;
+ lpni_info->cr_peer_tx_credits = lpni->lpni_txcredits;
+ lpni_info->cr_peer_rtr_credits = lpni->lpni_rtrcredits;
+ lpni_info->cr_peer_min_rtr_credits = lpni->lpni_minrtrcredits;
+ lpni_info->cr_peer_min_tx_credits = lpni->lpni_mintxcredits;
+ lpni_info->cr_peer_tx_qnob = lpni->lpni_txqnob;
+ if (copy_to_user(bulk, lpni_info, sizeof(*lpni_info)))
+ goto out_free_hstats;
+ bulk += sizeof(*lpni_info);
+
+ memset(lpni_stats, 0, sizeof(*lpni_stats));
+ lpni_stats->iel_send_count = lnet_sum_stats(&lpni->lpni_stats,
+ LNET_STATS_TYPE_SEND);
+ lpni_stats->iel_recv_count = lnet_sum_stats(&lpni->lpni_stats,
+ LNET_STATS_TYPE_RECV);
+ lpni_stats->iel_drop_count = lnet_sum_stats(&lpni->lpni_stats,
+ LNET_STATS_TYPE_DROP);
+ if (copy_to_user(bulk, lpni_stats, sizeof(*lpni_stats)))
+ goto out_free_hstats;
+ bulk += sizeof(*lpni_stats);
+ lnet_usr_translate_stats(lpni_msg_stats, &lpni->lpni_stats);
+ if (copy_to_user(bulk, lpni_msg_stats, sizeof(*lpni_msg_stats)))
+ goto out_free_hstats;
+ bulk += sizeof(*lpni_msg_stats);
+ lpni_hstats->hlpni_network_timeout =
+ atomic_read(&lpni->lpni_hstats.hlt_network_timeout);
+ lpni_hstats->hlpni_remote_dropped =
+ atomic_read(&lpni->lpni_hstats.hlt_remote_dropped);
+ lpni_hstats->hlpni_remote_timeout =
+ atomic_read(&lpni->lpni_hstats.hlt_remote_timeout);
+ lpni_hstats->hlpni_remote_error =
+ atomic_read(&lpni->lpni_hstats.hlt_remote_error);
+ lpni_hstats->hlpni_health_value =
+ atomic_read(&lpni->lpni_healthv);
+ if (copy_to_user(bulk, lpni_hstats, sizeof(*lpni_hstats)))
+ goto out_free_hstats;
+ bulk += sizeof(*lpni_hstats);
+ }
rc = 0;
-copy_failed:
+out_free_hstats:
+ LIBCFS_FREE(lpni_hstats, sizeof(*lpni_hstats));
+out_free_msg_stats:
+ LIBCFS_FREE(lpni_msg_stats, sizeof(*lpni_msg_stats));
+out_free_stats:
+ LIBCFS_FREE(lpni_stats, sizeof(*lpni_stats));
+out_free_info:
+ LIBCFS_FREE(lpni_info, sizeof(*lpni_info));
+out_lp_decref:
+ lnet_peer_decref_locked(lp);
+out:
return rc;
}
+
+void
+lnet_peer_ni_add_to_recoveryq_locked(struct lnet_peer_ni *lpni)
+{
+ /* the mt could've shutdown and cleaned up the queues */
+ if (the_lnet.ln_mt_state != LNET_MT_STATE_RUNNING)
+ return;
+
+ if (list_empty(&lpni->lpni_recovery) &&
+ atomic_read(&lpni->lpni_healthv) < LNET_MAX_HEALTH_VALUE) {
+ CERROR("lpni %s added to recovery queue. Health = %d\n",
+ libcfs_nid2str(lpni->lpni_nid),
+ atomic_read(&lpni->lpni_healthv));
+ list_add_tail(&lpni->lpni_recovery, &the_lnet.ln_mt_peerNIRecovq);
+ lnet_peer_ni_addref_locked(lpni);
+ }
+}
+
+/* Call with the ln_api_mutex held */
+void
+lnet_peer_ni_set_healthv(lnet_nid_t nid, int value, bool all)
+{
+ struct lnet_peer_table *ptable;
+ struct lnet_peer *lp;
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
+ int lncpt;
+ int cpt;
+
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ return;
+
+ if (!all) {
+ lnet_net_lock(LNET_LOCK_EX);
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (!lpni) {
+ lnet_net_unlock(LNET_LOCK_EX);
+ return;
+ }
+ atomic_set(&lpni->lpni_healthv, value);
+ lnet_peer_ni_add_to_recoveryq_locked(lpni);
+ lnet_peer_ni_decref_locked(lpni);
+ lnet_net_unlock(LNET_LOCK_EX);
+ return;
+ }
+
+ lncpt = cfs_percpt_number(the_lnet.ln_peer_tables);
+
+ /*
+ * Walk all the peers and reset the healhv for each one to the
+ * maximum value.
+ */
+ lnet_net_lock(LNET_LOCK_EX);
+ for (cpt = 0; cpt < lncpt; cpt++) {
+ ptable = the_lnet.ln_peer_tables[cpt];
+ list_for_each_entry(lp, &ptable->pt_peer_list, lp_peer_list) {
+ list_for_each_entry(lpn, &lp->lp_peer_nets, lpn_peer_nets) {
+ list_for_each_entry(lpni, &lpn->lpn_peer_nis,
+ lpni_peer_nis) {
+ atomic_set(&lpni->lpni_healthv, value);
+ lnet_peer_ni_add_to_recoveryq_locked(lpni);
+ }
+ }
+ }
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
git://git.whamcloud.com / fs / lustre-release.git / blobdiff