*
* Copyright (c) 2011, 2017, Intel Corporation.
*
- * This file is part of Lustre, https://wiki.hpdd.intel.com/
+ * This file is part of Lustre, https://wiki.whamcloud.com/
*
* Portals is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
*/
#define DEBUG_SUBSYSTEM S_LNET
+
+#include <linux/random.h>
#include <lnet/lib-lnet.h>
#define LNET_NRB_TINY_MIN 512 /* min value for each CPT */
return net->net_tunables.lct_peer_tx_credits;
}
-/* forward ref's */
-static int lnet_router_checker(void *);
-
static int check_routers_before_use;
module_param(check_routers_before_use, int, 0444);
MODULE_PARM_DESC(check_routers_before_use, "Assume routers are down and ping them before use");
spin_lock(&lp->lpni_lock);
lp->lpni_timestamp = when; /* update timestamp */
- lp->lpni_ping_deadline = 0; /* disable ping timeout */
if (lp->lpni_alive_count != 0 && /* got old news */
(!lp->lpni_alive) == (!alive)) { /* new date for old news */
}
static void
-lnet_rtr_addref_locked(struct lnet_peer_ni *lp)
+lnet_rtr_addref_locked(struct lnet_peer *lp)
{
- LASSERT(atomic_read(&lp->lpni_refcount) > 0);
- LASSERT(lp->lpni_rtr_refcount >= 0);
+ LASSERT(lp->lp_rtr_refcount >= 0);
/* lnet_net_lock must be exclusively locked */
- lp->lpni_rtr_refcount++;
- if (lp->lpni_rtr_refcount == 1) {
- struct list_head *pos;
-
- /* a simple insertion sort */
- list_for_each_prev(pos, &the_lnet.ln_routers) {
- struct lnet_peer_ni *rtr;
-
- rtr = list_entry(pos, struct lnet_peer_ni,
- lpni_rtr_list);
- if (rtr->lpni_nid < lp->lpni_nid)
- break;
- }
-
- list_add(&lp->lpni_rtr_list, pos);
+ lp->lp_rtr_refcount++;
+ if (lp->lp_rtr_refcount == 1) {
+ list_add_tail(&lp->lp_rtr_list, &the_lnet.ln_routers);
/* addref for the_lnet.ln_routers */
- lnet_peer_ni_addref_locked(lp);
+ lnet_peer_addref_locked(lp);
the_lnet.ln_routers_version++;
}
}
static void
-lnet_rtr_decref_locked(struct lnet_peer_ni *lp)
+lnet_rtr_decref_locked(struct lnet_peer *lp)
{
- LASSERT(atomic_read(&lp->lpni_refcount) > 0);
- LASSERT(lp->lpni_rtr_refcount > 0);
+ LASSERT(atomic_read(&lp->lp_refcount) > 0);
+ LASSERT(lp->lp_rtr_refcount > 0);
/* lnet_net_lock must be exclusively locked */
- lp->lpni_rtr_refcount--;
- if (lp->lpni_rtr_refcount == 0) {
- LASSERT(list_empty(&lp->lpni_routes));
-
- if (lp->lpni_rcd != NULL) {
- list_add(&lp->lpni_rcd->rcd_list,
- &the_lnet.ln_rcd_deathrow);
- lp->lpni_rcd = NULL;
- }
+ lp->lp_rtr_refcount--;
+ if (lp->lp_rtr_refcount == 0) {
+ LASSERT(list_empty(&lp->lp_routes));
- list_del(&lp->lpni_rtr_list);
+ list_del(&lp->lp_rtr_list);
/* decref for the_lnet.ln_routers */
- lnet_peer_ni_decref_locked(lp);
+ lnet_peer_decref_locked(lp);
the_lnet.ln_routers_version++;
}
}
static void lnet_shuffle_seed(void)
{
static int seeded;
- __u32 lnd_type;
- __u32 seed[2];
- struct timespec64 ts;
struct lnet_ni *ni = NULL;
if (seeded)
return;
- cfs_get_random_bytes(seed, sizeof(seed));
-
/* Nodes with small feet have little entropy
* the NID for this node gives the most entropy in the low bits */
- while ((ni = lnet_get_next_ni_locked(NULL, ni))) {
- lnd_type = LNET_NETTYP(LNET_NIDNET(ni->ni_nid));
-
- if (lnd_type != LOLND)
- seed[0] ^= (LNET_NIDADDR(ni->ni_nid) | lnd_type);
- }
+ while ((ni = lnet_get_next_ni_locked(NULL, ni)))
+ add_device_randomness(&ni->ni_nid, sizeof(ni->ni_nid));
- ktime_get_ts64(&ts);
- cfs_srand(ts.tv_sec ^ seed[0], ts.tv_nsec ^ seed[1]);
seeded = 1;
return;
}
static void
lnet_add_route_to_rnet(struct lnet_remotenet *rnet, struct lnet_route *route)
{
- unsigned int len = 0;
- unsigned int offset = 0;
+ unsigned int len = 0;
+ unsigned int offset = 0;
struct list_head *e;
lnet_shuffle_seed();
- list_for_each(e, &rnet->lrn_routes) {
+ list_for_each(e, &rnet->lrn_routes)
len++;
- }
- /* len+1 positions to add a new entry, also prevents division by 0 */
+ /*
+ * Randomly adding routes to the list is done to ensure that when
+ * different nodes are using the same list of routers, they end up
+ * preferring different routers.
+ */
offset = cfs_rand() % (len + 1);
list_for_each(e, &rnet->lrn_routes) {
if (offset == 0)
offset--;
}
list_add(&route->lr_list, e);
- list_add(&route->lr_gwlist, &route->lr_gateway->lpni_routes);
+ /*
+ * force a router check on the gateway to make sure the route is
+ * alive
+ */
+ route->lr_gateway->lp_rtrcheck_timestamp = 0;
the_lnet.ln_remote_nets_version++;
+
+ /* add the route on the gateway list */
+ list_add(&route->lr_gwlist, &route->lr_gateway->lp_routes);
+
+ /* take a router reference count on the gateway */
lnet_rtr_addref_locked(route->lr_gateway);
}
lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway,
unsigned int priority)
{
- struct list_head *e;
- struct lnet_remotenet *rnet;
- struct lnet_remotenet *rnet2;
- struct lnet_route *route;
- struct lnet_ni *ni;
- struct lnet_peer_ni *lpni;
- int add_route;
- int rc;
-
- CDEBUG(D_NET, "Add route: net %s hops %d priority %u gw %s\n",
+ struct list_head *route_entry;
+ struct lnet_remotenet *rnet;
+ struct lnet_remotenet *rnet2;
+ struct lnet_route *route;
+ struct lnet_peer_ni *lpni;
+ struct lnet_peer *gw;
+ int add_route;
+ int rc;
+
+ CDEBUG(D_NET, "Add route: remote net %s hops %d priority %u gw %s\n",
libcfs_net2str(net), hops, priority, libcfs_nid2str(gateway));
if (gateway == LNET_NID_ANY ||
(hops != LNET_UNDEFINED_HOPS && (hops < 1 || hops > 255)))
return -EINVAL;
- if (lnet_islocalnet(net)) /* it's a local network */
+ /* it's a local network */
+ if (lnet_islocalnet(net))
return -EEXIST;
/* Assume net, route, all new */
INIT_LIST_HEAD(&rnet->lrn_routes);
rnet->lrn_net = net;
- route->lr_hops = hops;
+ /* store the local and remote net that the route represents */
+ route->lr_lnet = LNET_NIDNET(gateway);
route->lr_net = net;
route->lr_priority = priority;
+ route->lr_hops = hops;
lnet_net_lock(LNET_LOCK_EX);
+ /*
+ * lnet_nid2peerni_ex() grabs a ref on the lpni. We will need to
+ * lose that once we're done
+ */
lpni = lnet_nid2peerni_ex(gateway, LNET_LOCK_EX);
if (IS_ERR(lpni)) {
lnet_net_unlock(LNET_LOCK_EX);
LIBCFS_FREE(rnet, sizeof(*rnet));
rc = PTR_ERR(lpni);
- if (rc == -EHOSTUNREACH) /* gateway is not on a local net. */
- return rc; /* ignore the route entry */
CERROR("Error %d creating route %s %d %s\n", rc,
libcfs_net2str(net), hops,
libcfs_nid2str(gateway));
return rc;
}
- route->lr_gateway = lpni;
- LASSERT(the_lnet.ln_state == LNET_STATE_RUNNING);
+
+ LASSERT(lpni->lpni_peer_net && lpni->lpni_peer_net->lpn_peer);
+ gw = lpni->lpni_peer_net->lpn_peer;
+
+ route->lr_gateway = gw;
rnet2 = lnet_find_rnet_locked(net);
if (rnet2 == NULL) {
/* Search for a duplicate route (it's a NOOP if it is) */
add_route = 1;
- list_for_each(e, &rnet2->lrn_routes) {
+ list_for_each(route_entry, &rnet2->lrn_routes) {
struct lnet_route *route2;
- route2 = list_entry(e, struct lnet_route, lr_list);
+ route2 = list_entry(route_entry, struct lnet_route, lr_list);
if (route2->lr_gateway == route->lr_gateway) {
add_route = 0;
break;
}
/* our lookups must be true */
- LASSERT(route2->lr_gateway->lpni_nid != gateway);
+ LASSERT(route2->lr_gateway->lp_primary_nid != gateway);
}
- if (add_route) {
- lnet_peer_ni_addref_locked(route->lr_gateway); /* +1 for notify */
+ /*
+ * It is possible to add multiple routes through the same peer,
+ * but it'll be using a different NID of that peer. When the
+ * gateway is discovered, discovery will consolidate the different
+ * peers into one peer. In this case the discovery code will have
+ * to move the routes from the peer that's being deleted to the
+ * consolidated peer lp_routes list
+ */
+ if (add_route)
lnet_add_route_to_rnet(rnet2, route);
- ni = lnet_get_next_ni_locked(route->lr_gateway->lpni_net, NULL);
- lnet_net_unlock(LNET_LOCK_EX);
-
- /* XXX Assume alive */
- if (ni->ni_net->net_lnd->lnd_notify != NULL)
- (ni->ni_net->net_lnd->lnd_notify)(ni, gateway, 1);
-
- lnet_net_lock(LNET_LOCK_EX);
- }
-
- /* -1 for notify or !add_route */
- lnet_peer_ni_decref_locked(route->lr_gateway);
+ /*
+ * get rid of the reference on the lpni.
+ */
+ lnet_peer_ni_decref_locked(lpni);
lnet_net_unlock(LNET_LOCK_EX);
rc = 0;
if (rnet != rnet2)
LIBCFS_FREE(rnet, sizeof(*rnet));
- /* indicate to startup the router checker if configured */
- wake_up(&the_lnet.ln_rc_waitq);
+ /* kick start the monitor thread to handle the added route */
+ wake_up(&the_lnet.ln_mt_waitq);
return rc;
}
-int
-lnet_check_routes(void)
+static void
+lnet_del_route_from_rnet(lnet_nid_t gw_nid, struct list_head *route_list,
+ struct list_head *zombies)
{
- struct lnet_remotenet *rnet;
- struct lnet_route *route;
- struct lnet_route *route2;
- struct list_head *e1;
- struct list_head *e2;
- int cpt;
- struct list_head *rn_list;
- int i;
-
- cpt = lnet_net_lock_current();
-
- for (i = 0; i < LNET_REMOTE_NETS_HASH_SIZE; i++) {
- rn_list = &the_lnet.ln_remote_nets_hash[i];
- list_for_each(e1, rn_list) {
- rnet = list_entry(e1, struct lnet_remotenet, lrn_list);
-
- route2 = NULL;
- list_for_each(e2, &rnet->lrn_routes) {
- lnet_nid_t nid1;
- lnet_nid_t nid2;
- int net;
-
- route = list_entry(e2, struct lnet_route,
- lr_list);
-
- if (route2 == NULL) {
- route2 = route;
- continue;
- }
-
- if (route->lr_gateway->lpni_net ==
- route2->lr_gateway->lpni_net)
- continue;
-
- nid1 = route->lr_gateway->lpni_nid;
- nid2 = route2->lr_gateway->lpni_nid;
- net = rnet->lrn_net;
+ struct lnet_peer *gateway;
+ struct lnet_route *route;
+ struct lnet_route *tmp;
+
+ list_for_each_entry_safe(route, tmp, route_list, lr_list) {
+ gateway = route->lr_gateway;
+ if (gw_nid != LNET_NID_ANY &&
+ gw_nid != gateway->lp_primary_nid)
+ continue;
- lnet_net_unlock(cpt);
+ /*
+ * move to zombie to delete outside the lock
+ * Note that this function is called with the
+ * ln_api_mutex held as well as the exclusive net
+ * lock. Adding to the remote net list happens
+ * under the same conditions. Same goes for the
+ * gateway router list
+ */
+ list_move(&route->lr_list, zombies);
+ the_lnet.ln_remote_nets_version++;
- CERROR("Routes to %s via %s and %s not "
- "supported\n",
- libcfs_net2str(net),
- libcfs_nid2str(nid1),
- libcfs_nid2str(nid2));
- return -EINVAL;
- }
- }
+ list_del(&route->lr_gwlist);
+ lnet_rtr_decref_locked(gateway);
}
-
- lnet_net_unlock(cpt);
- return 0;
}
int
lnet_del_route(__u32 net, lnet_nid_t gw_nid)
{
- struct lnet_peer_ni *gateway;
- struct lnet_remotenet *rnet;
- struct lnet_route *route;
- struct list_head *e1;
- struct list_head *e2;
- int rc = -ENOENT;
- struct list_head *rn_list;
- int idx = 0;
+ struct list_head rnet_zombies;
+ struct lnet_remotenet *rnet;
+ struct lnet_remotenet *tmp;
+ struct list_head *rn_list;
+ struct lnet_peer_ni *lpni;
+ struct lnet_route *route;
+ struct list_head zombies;
+ struct lnet_peer *lp;
+ int i = 0;
+
+ INIT_LIST_HEAD(&rnet_zombies);
+ INIT_LIST_HEAD(&zombies);
CDEBUG(D_NET, "Del route: net %s : gw %s\n",
libcfs_net2str(net), libcfs_nid2str(gw_nid));
* or a specific route entry actual NIDs) */
lnet_net_lock(LNET_LOCK_EX);
- if (net == LNET_NIDNET(LNET_NID_ANY))
- rn_list = &the_lnet.ln_remote_nets_hash[0];
- else
- rn_list = lnet_net2rnethash(net);
-again:
- list_for_each(e1, rn_list) {
- rnet = list_entry(e1, struct lnet_remotenet, lrn_list);
-
- if (!(net == LNET_NIDNET(LNET_NID_ANY) ||
- net == rnet->lrn_net))
- continue;
-
- list_for_each(e2, &rnet->lrn_routes) {
- route = list_entry(e2, struct lnet_route, lr_list);
+ lpni = lnet_find_peer_ni_locked(gw_nid);
+ if (lpni) {
+ lp = lpni->lpni_peer_net->lpn_peer;
+ LASSERT(lp);
+ gw_nid = lp->lp_primary_nid;
+ lnet_peer_ni_decref_locked(lpni);
+ }
- gateway = route->lr_gateway;
- if (!(gw_nid == LNET_NID_ANY ||
- gw_nid == gateway->lpni_nid))
- continue;
+ if (net != LNET_NIDNET(LNET_NID_ANY)) {
+ rnet = lnet_find_rnet_locked(net);
+ if (!rnet) {
+ lnet_net_unlock(LNET_LOCK_EX);
+ return -ENOENT;
+ }
+ lnet_del_route_from_rnet(gw_nid, &rnet->lrn_routes,
+ &zombies);
+ if (list_empty(&rnet->lrn_routes))
+ list_move(&rnet->lrn_list, &rnet_zombies);
+ goto delete_zombies;
+ }
- list_del(&route->lr_list);
- list_del(&route->lr_gwlist);
- the_lnet.ln_remote_nets_version++;
+ for (i = 0; i < LNET_REMOTE_NETS_HASH_SIZE; i++) {
+ rn_list = &the_lnet.ln_remote_nets_hash[i];
+ list_for_each_entry_safe(rnet, tmp, rn_list, lrn_list) {
+ lnet_del_route_from_rnet(gw_nid, &rnet->lrn_routes,
+ &zombies);
if (list_empty(&rnet->lrn_routes))
- list_del(&rnet->lrn_list);
- else
- rnet = NULL;
-
- lnet_rtr_decref_locked(gateway);
- lnet_peer_ni_decref_locked(gateway);
-
- lnet_net_unlock(LNET_LOCK_EX);
-
- LIBCFS_FREE(route, sizeof(*route));
+ list_move(&rnet->lrn_list, &rnet_zombies);
+ }
+ }
- if (rnet != NULL)
- LIBCFS_FREE(rnet, sizeof(*rnet));
+delete_zombies:
+ lnet_net_unlock(LNET_LOCK_EX);
- rc = 0;
- lnet_net_lock(LNET_LOCK_EX);
- goto again;
- }
+ while (!list_empty(&zombies)) {
+ route = list_first_entry(&zombies, struct lnet_route, lr_list);
+ list_del(&route->lr_list);
+ LIBCFS_FREE(route, sizeof(*route));
}
- if (net == LNET_NIDNET(LNET_NID_ANY) &&
- ++idx < LNET_REMOTE_NETS_HASH_SIZE) {
- rn_list = &the_lnet.ln_remote_nets_hash[idx];
- goto again;
+ while (!list_empty(&rnet_zombies)) {
+ rnet = list_first_entry(&rnet_zombies, struct lnet_remotenet,
+ lrn_list);
+ list_del(&rnet->lrn_list);
+ LIBCFS_FREE(rnet, sizeof(*rnet));
}
- lnet_net_unlock(LNET_LOCK_EX);
- return rc;
+ return 0;
}
void
lnet_del_route(LNET_NIDNET(LNET_NID_ANY), LNET_NID_ANY);
}
-int lnet_get_rtr_pool_cfg(int idx, struct lnet_ioctl_pool_cfg *pool_cfg)
+int lnet_get_rtr_pool_cfg(int cpt, struct lnet_ioctl_pool_cfg *pool_cfg)
{
+ struct lnet_rtrbufpool *rbp;
int i, rc = -ENOENT, j;
if (the_lnet.ln_rtrpools == NULL)
return rc;
- for (i = 0; i < LNET_NRBPOOLS; i++) {
- struct lnet_rtrbufpool *rbp;
- lnet_net_lock(LNET_LOCK_EX);
- cfs_percpt_for_each(rbp, j, the_lnet.ln_rtrpools) {
- if (i++ != idx)
- continue;
+ cfs_percpt_for_each(rbp, i, the_lnet.ln_rtrpools) {
+ if (i != cpt)
+ continue;
- pool_cfg->pl_pools[i].pl_npages = rbp[i].rbp_npages;
- pool_cfg->pl_pools[i].pl_nbuffers = rbp[i].rbp_nbuffers;
- pool_cfg->pl_pools[i].pl_credits = rbp[i].rbp_credits;
- pool_cfg->pl_pools[i].pl_mincredits = rbp[i].rbp_mincredits;
- rc = 0;
- break;
+ lnet_net_lock(i);
+ for (j = 0; j < LNET_NRBPOOLS; j++) {
+ pool_cfg->pl_pools[j].pl_npages = rbp[j].rbp_npages;
+ pool_cfg->pl_pools[j].pl_nbuffers = rbp[j].rbp_nbuffers;
+ pool_cfg->pl_pools[j].pl_credits = rbp[j].rbp_credits;
+ pool_cfg->pl_pools[j].pl_mincredits = rbp[j].rbp_mincredits;
}
- lnet_net_unlock(LNET_LOCK_EX);
+ lnet_net_unlock(i);
+ rc = 0;
+ break;
}
lnet_net_lock(LNET_LOCK_EX);
*net = rnet->lrn_net;
*hops = route->lr_hops;
*priority = route->lr_priority;
- *gateway = route->lr_gateway->lpni_nid;
+ *gateway = route->lr_gateway->lp_primary_nid;
*alive = lnet_is_route_alive(route);
lnet_net_unlock(cpt);
return 0;
}
/**
- * parse router-checker pinginfo, record number of down NIs for remote
- * networks on that router.
+ * TODO: re-implement
*/
static void
lnet_parse_rc_info(struct lnet_rc_data *rcd)
{
- struct lnet_ping_buffer *pbuf = rcd->rcd_pingbuffer;
- struct lnet_peer_ni *gw = rcd->rcd_gateway;
- struct lnet_route *rte;
- int nnis;
-
- if (!gw->lpni_alive || !pbuf)
- return;
-
- /*
- * Protect gw->lpni_ping_feats. This can be set from
- * lnet_notify_locked with different locks being held
- */
- spin_lock(&gw->lpni_lock);
-
- if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC))
- lnet_swap_pinginfo(pbuf);
-
- /* NB always racing with network! */
- if (pbuf->pb_info.pi_magic != LNET_PROTO_PING_MAGIC) {
- CDEBUG(D_NET, "%s: Unexpected magic %08x\n",
- libcfs_nid2str(gw->lpni_nid), pbuf->pb_info.pi_magic);
- gw->lpni_ping_feats = LNET_PING_FEAT_INVAL;
- goto out;
- }
-
- gw->lpni_ping_feats = pbuf->pb_info.pi_features;
-
- /* Without NI status info there's nothing more to do. */
- if ((gw->lpni_ping_feats & LNET_PING_FEAT_NI_STATUS) == 0)
- goto out;
-
- /* Determine the number of NIs for which there is data. */
- nnis = pbuf->pb_info.pi_nnis;
- if (pbuf->pb_nnis < nnis) {
- if (rcd->rcd_nnis < nnis)
- rcd->rcd_nnis = nnis;
- nnis = pbuf->pb_nnis;
- }
-
- list_for_each_entry(rte, &gw->lpni_routes, lr_gwlist) {
- int down = 0;
- int up = 0;
- int i;
-
- /* If routing disabled then the route is down. */
- if ((gw->lpni_ping_feats & LNET_PING_FEAT_RTE_DISABLED) != 0) {
- rte->lr_downis = 1;
- continue;
- }
-
- for (i = 0; i < nnis; i++) {
- struct lnet_ni_status *stat = &pbuf->pb_info.pi_ni[i];
- lnet_nid_t nid = stat->ns_nid;
-
- if (nid == LNET_NID_ANY) {
- CDEBUG(D_NET, "%s: unexpected LNET_NID_ANY\n",
- libcfs_nid2str(gw->lpni_nid));
- gw->lpni_ping_feats = LNET_PING_FEAT_INVAL;
- goto out;
- }
-
- if (LNET_NETTYP(LNET_NIDNET(nid)) == LOLND)
- continue;
-
- if (stat->ns_status == LNET_NI_STATUS_DOWN) {
- down++;
- continue;
- }
-
- if (stat->ns_status == LNET_NI_STATUS_UP) {
- if (LNET_NIDNET(nid) == rte->lr_net) {
- up = 1;
- break;
- }
- continue;
- }
-
- CDEBUG(D_NET, "%s: Unexpected status 0x%x\n",
- libcfs_nid2str(gw->lpni_nid), stat->ns_status);
- gw->lpni_ping_feats = LNET_PING_FEAT_INVAL;
- goto out;
- }
-
- if (up) { /* ignore downed NIs if NI for dest network is up */
- rte->lr_downis = 0;
- continue;
- }
- /* if @down is zero and this route is single-hop, it means
- * we can't find NI for target network */
- if (down == 0 && rte->lr_hops == 1)
- down = 1;
-
- rte->lr_downis = down;
- }
-out:
- spin_unlock(&gw->lpni_lock);
+ rcd = rcd;
}
static void
}
if (event->type == LNET_EVENT_SEND) {
- lp->lpni_ping_notsent = 0;
if (event->status == 0)
goto out;
}
static void
lnet_wait_known_routerstate(void)
{
- struct lnet_peer_ni *rtr;
+ struct lnet_peer *rtr;
struct list_head *entry;
int all_known;
- LASSERT(the_lnet.ln_rc_state == LNET_RC_STATE_RUNNING);
+ LASSERT(the_lnet.ln_mt_state == LNET_MT_STATE_RUNNING);
for (;;) {
int cpt = lnet_net_lock_current();
all_known = 1;
list_for_each(entry, &the_lnet.ln_routers) {
- rtr = list_entry(entry, struct lnet_peer_ni,
- lpni_rtr_list);
+ rtr = list_entry(entry, struct lnet_peer,
+ lp_rtr_list);
- spin_lock(&rtr->lpni_lock);
+ spin_lock(&rtr->lp_lock);
- if (rtr->lpni_alive_count == 0) {
+ if ((rtr->lp_state & LNET_PEER_DISCOVERED) == 0) {
all_known = 0;
- spin_unlock(&rtr->lpni_lock);
+ spin_unlock(&rtr->lp_lock);
break;
}
- spin_unlock(&rtr->lpni_lock);
+ spin_unlock(&rtr->lp_lock);
}
lnet_net_unlock(cpt);
}
}
+/* TODO: reimplement */
void
lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net)
{
struct lnet_route *rte;
+ struct lnet_peer *lp;
- if ((gw->lpni_ping_feats & LNET_PING_FEAT_NI_STATUS) != 0) {
- list_for_each_entry(rte, &gw->lpni_routes, lr_gwlist) {
- if (rte->lr_net == net) {
- rte->lr_downis = 0;
- break;
- }
+ if ((gw->lpni_ping_feats & LNET_PING_FEAT_NI_STATUS) != 0)
+ lp = gw->lpni_peer_net->lpn_peer;
+ else
+ return;
+
+ list_for_each_entry(rte, &lp->lp_routes, lr_gwlist) {
+ if (rte->lr_net == net) {
+ rte->lr_downis = 0;
+ break;
}
}
}
}
}
-static void
-lnet_destroy_rc_data(struct lnet_rc_data *rcd)
-{
- LASSERT(list_empty(&rcd->rcd_list));
- /* detached from network */
- LASSERT(LNetMDHandleIsInvalid(rcd->rcd_mdh));
-
- if (rcd->rcd_gateway != NULL) {
- int cpt = rcd->rcd_gateway->lpni_cpt;
-
- lnet_net_lock(cpt);
- lnet_peer_ni_decref_locked(rcd->rcd_gateway);
- lnet_net_unlock(cpt);
- }
-
- if (rcd->rcd_pingbuffer != NULL)
- lnet_ping_buffer_decref(rcd->rcd_pingbuffer);
-
- LIBCFS_FREE(rcd, sizeof(*rcd));
-}
-
-static struct lnet_rc_data *
-lnet_update_rc_data_locked(struct lnet_peer_ni *gateway)
+int lnet_router_pre_mt_start(void)
{
- struct lnet_handle_md mdh;
- struct lnet_rc_data *rcd;
- struct lnet_ping_buffer *pbuf = NULL;
- int nnis = LNET_INTERFACES_MIN;
int rc;
- int i;
-
- rcd = gateway->lpni_rcd;
- if (rcd) {
- nnis = rcd->rcd_nnis;
- mdh = rcd->rcd_mdh;
- LNetInvalidateMDHandle(&rcd->rcd_mdh);
- pbuf = rcd->rcd_pingbuffer;
- rcd->rcd_pingbuffer = NULL;
- } else {
- LNetInvalidateMDHandle(&mdh);
- }
-
- lnet_net_unlock(gateway->lpni_cpt);
-
- if (rcd) {
- LNetMDUnlink(mdh);
- lnet_ping_buffer_decref(pbuf);
- } else {
- LIBCFS_ALLOC(rcd, sizeof(*rcd));
- if (rcd == NULL)
- goto out;
-
- LNetInvalidateMDHandle(&rcd->rcd_mdh);
- INIT_LIST_HEAD(&rcd->rcd_list);
- rcd->rcd_nnis = nnis;
- }
-
- pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS);
- if (pbuf == NULL)
- goto out;
-
- for (i = 0; i < nnis; i++) {
- pbuf->pb_info.pi_ni[i].ns_nid = LNET_NID_ANY;
- pbuf->pb_info.pi_ni[i].ns_status = LNET_NI_STATUS_INVALID;
- }
- rcd->rcd_pingbuffer = pbuf;
-
- LASSERT(!LNetEQHandleIsInvalid(the_lnet.ln_rc_eqh));
- rc = LNetMDBind((struct lnet_md){.start = &pbuf->pb_info,
- .user_ptr = rcd,
- .length = LNET_PING_INFO_SIZE(nnis),
- .threshold = LNET_MD_THRESH_INF,
- .options = LNET_MD_TRUNCATE,
- .eq_handle = the_lnet.ln_rc_eqh},
- LNET_UNLINK,
- &rcd->rcd_mdh);
- if (rc < 0) {
- CERROR("Can't bind MD: %d\n", rc);
- goto out_ping_buffer_decref;
- }
- LASSERT(rc == 0);
-
- lnet_net_lock(gateway->lpni_cpt);
- /* Check if this is still a router. */
- if (!lnet_isrouter(gateway))
- goto out_unlock;
- /* Check if someone else installed router data. */
- if (gateway->lpni_rcd && gateway->lpni_rcd != rcd)
- goto out_unlock;
-
- /* Install and/or update the router data. */
- if (!gateway->lpni_rcd) {
- lnet_peer_ni_addref_locked(gateway);
- rcd->rcd_gateway = gateway;
- gateway->lpni_rcd = rcd;
- }
- gateway->lpni_ping_notsent = 0;
-
- return rcd;
-
-out_unlock:
- lnet_net_unlock(gateway->lpni_cpt);
- rc = LNetMDUnlink(mdh);
- LASSERT(rc == 0);
-out_ping_buffer_decref:
- lnet_ping_buffer_decref(pbuf);
-out:
- if (rcd && rcd != gateway->lpni_rcd)
- lnet_destroy_rc_data(rcd);
- lnet_net_lock(gateway->lpni_cpt);
- return gateway->lpni_rcd;
-}
-
-static int
-lnet_router_check_interval(struct lnet_peer_ni *rtr)
-{
- int secs;
-
- secs = rtr->lpni_alive ? live_router_check_interval :
- dead_router_check_interval;
- if (secs < 0)
- secs = 0;
-
- return secs;
-}
-
-static void
-lnet_ping_router_locked(struct lnet_peer_ni *rtr)
-{
- struct lnet_rc_data *rcd = NULL;
- time64_t now = ktime_get_seconds();
- time64_t secs;
- struct lnet_ni *ni;
-
- lnet_peer_ni_addref_locked(rtr);
-
- if (rtr->lpni_ping_deadline != 0 && /* ping timed out? */
- now > rtr->lpni_ping_deadline)
- lnet_notify_locked(rtr, 1, 0, now);
-
- /* Run any outstanding notifications */
- ni = lnet_get_next_ni_locked(rtr->lpni_net, NULL);
- lnet_ni_notify_locked(ni, rtr);
-
- if (!lnet_isrouter(rtr) ||
- the_lnet.ln_rc_state != LNET_RC_STATE_RUNNING) {
- /* router table changed or router checker is shutting down */
- lnet_peer_ni_decref_locked(rtr);
- return;
- }
-
- rcd = rtr->lpni_rcd;
- if (!rcd || rcd->rcd_nnis > rcd->rcd_pingbuffer->pb_nnis)
- rcd = lnet_update_rc_data_locked(rtr);
- if (rcd == NULL)
- return;
-
- secs = lnet_router_check_interval(rtr);
-
- CDEBUG(D_NET,
- "rtr %s %lld: deadline %lld ping_notsent %d alive %d "
- "alive_count %d lpni_ping_timestamp %lld\n",
- libcfs_nid2str(rtr->lpni_nid), secs,
- rtr->lpni_ping_deadline, rtr->lpni_ping_notsent,
- rtr->lpni_alive, rtr->lpni_alive_count, rtr->lpni_ping_timestamp);
-
- if (secs != 0 && !rtr->lpni_ping_notsent &&
- now > rtr->lpni_ping_timestamp + secs) {
- int rc;
- struct lnet_process_id id;
- struct lnet_handle_md mdh;
-
- id.nid = rtr->lpni_nid;
- id.pid = LNET_PID_LUSTRE;
- CDEBUG(D_NET, "Check: %s\n", libcfs_id2str(id));
-
- rtr->lpni_ping_notsent = 1;
- rtr->lpni_ping_timestamp = now;
-
- mdh = rcd->rcd_mdh;
-
- if (rtr->lpni_ping_deadline == 0) {
- rtr->lpni_ping_deadline = ktime_get_seconds() +
- router_ping_timeout;
- }
-
- lnet_net_unlock(rtr->lpni_cpt);
-
- rc = LNetGet(LNET_NID_ANY, mdh, id, LNET_RESERVED_PORTAL,
- LNET_PROTO_PING_MATCHBITS, 0);
-
- lnet_net_lock(rtr->lpni_cpt);
- if (rc != 0)
- rtr->lpni_ping_notsent = 0; /* no event pending */
- }
-
- lnet_peer_ni_decref_locked(rtr);
- return;
-}
-
-int
-lnet_router_checker_start(void)
-{
- int rc;
- int eqsz = 0;
- struct task_struct *task;
-
- LASSERT(the_lnet.ln_rc_state == LNET_RC_STATE_SHUTDOWN);
if (check_routers_before_use &&
dead_router_check_interval <= 0) {
return -EINVAL;
}
- sema_init(&the_lnet.ln_rc_signal, 0);
-
rc = LNetEQAlloc(0, lnet_router_checker_event, &the_lnet.ln_rc_eqh);
if (rc != 0) {
- CERROR("Can't allocate EQ(%d): %d\n", eqsz, rc);
+ CERROR("Can't allocate EQ(0): %d\n", rc);
return -ENOMEM;
}
- the_lnet.ln_rc_state = LNET_RC_STATE_RUNNING;
- task = kthread_run(lnet_router_checker, NULL, "router_checker");
- if (IS_ERR(task)) {
- rc = PTR_ERR(task);
- CERROR("Can't start router checker thread: %d\n", rc);
- /* block until event callback signals exit */
- down(&the_lnet.ln_rc_signal);
- rc = LNetEQFree(the_lnet.ln_rc_eqh);
- LASSERT(rc == 0);
- the_lnet.ln_rc_state = LNET_RC_STATE_SHUTDOWN;
- return -ENOMEM;
- }
+ return 0;
+}
+void lnet_router_post_mt_start(void)
+{
if (check_routers_before_use) {
/* Note that a helpful side-effect of pinging all known routers
* at startup is that it makes them drop stale connections they
* may have to a previous instance of me. */
lnet_wait_known_routerstate();
}
-
- return 0;
}
void
-lnet_router_checker_stop (void)
+lnet_router_cleanup(void)
{
int rc;
- if (the_lnet.ln_rc_state == LNET_RC_STATE_SHUTDOWN)
- return;
-
- LASSERT (the_lnet.ln_rc_state == LNET_RC_STATE_RUNNING);
- the_lnet.ln_rc_state = LNET_RC_STATE_STOPPING;
- /* wakeup the RC thread if it's sleeping */
- wake_up(&the_lnet.ln_rc_waitq);
-
- /* block until event callback signals exit */
- down(&the_lnet.ln_rc_signal);
- LASSERT(the_lnet.ln_rc_state == LNET_RC_STATE_SHUTDOWN);
-
rc = LNetEQFree(the_lnet.ln_rc_eqh);
LASSERT(rc == 0);
return;
}
-static void
+void
lnet_prune_rc_data(int wait_unlink)
{
- struct lnet_rc_data *rcd;
- struct lnet_rc_data *tmp;
- struct lnet_peer_ni *lp;
- struct list_head head;
- int i = 2;
-
- if (likely(the_lnet.ln_rc_state == LNET_RC_STATE_RUNNING &&
- list_empty(&the_lnet.ln_rcd_deathrow) &&
- list_empty(&the_lnet.ln_rcd_zombie)))
- return;
-
- INIT_LIST_HEAD(&head);
-
- lnet_net_lock(LNET_LOCK_EX);
-
- if (the_lnet.ln_rc_state != LNET_RC_STATE_RUNNING) {
- /* router checker is stopping, prune all */
- list_for_each_entry(lp, &the_lnet.ln_routers,
- lpni_rtr_list) {
- if (lp->lpni_rcd == NULL)
- continue;
-
- LASSERT(list_empty(&lp->lpni_rcd->rcd_list));
- list_add(&lp->lpni_rcd->rcd_list,
- &the_lnet.ln_rcd_deathrow);
- lp->lpni_rcd = NULL;
- }
- }
-
- /* unlink all RCDs on deathrow list */
- list_splice_init(&the_lnet.ln_rcd_deathrow, &head);
-
- if (!list_empty(&head)) {
- lnet_net_unlock(LNET_LOCK_EX);
-
- list_for_each_entry(rcd, &head, rcd_list)
- LNetMDUnlink(rcd->rcd_mdh);
-
- lnet_net_lock(LNET_LOCK_EX);
- }
-
- list_splice_init(&head, &the_lnet.ln_rcd_zombie);
-
- /* release all zombie RCDs */
- while (!list_empty(&the_lnet.ln_rcd_zombie)) {
- list_for_each_entry_safe(rcd, tmp, &the_lnet.ln_rcd_zombie,
- rcd_list) {
- if (LNetMDHandleIsInvalid(rcd->rcd_mdh))
- list_move(&rcd->rcd_list, &head);
- }
-
- wait_unlink = wait_unlink &&
- !list_empty(&the_lnet.ln_rcd_zombie);
-
- lnet_net_unlock(LNET_LOCK_EX);
-
- while (!list_empty(&head)) {
- rcd = list_entry(head.next,
- struct lnet_rc_data, rcd_list);
- list_del_init(&rcd->rcd_list);
- lnet_destroy_rc_data(rcd);
- }
-
- if (!wait_unlink)
- return;
-
- i++;
- CDEBUG(((i & (-i)) == i) ? D_WARNING : D_NET,
- "Waiting for rc buffers to unlink\n");
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(cfs_time_seconds(1) / 4);
-
- lnet_net_lock(LNET_LOCK_EX);
- }
-
- lnet_net_unlock(LNET_LOCK_EX);
+ wait_unlink = wait_unlink;
}
/*
- * This function is called to check if the RC should block indefinitely.
- * It's called from lnet_router_checker() as well as being passed to
- * wait_event_interruptible() to avoid the lost wake_up problem.
- *
- * When it's called from wait_event_interruptible() it is necessary to
- * also not sleep if the rc state is not running to avoid a deadlock
- * when the system is shutting down
+ * This function is called from the monitor thread to check if there are
+ * any active routers that need to be checked.
*/
-static inline bool
+inline bool
lnet_router_checker_active(void)
{
- if (the_lnet.ln_rc_state != LNET_RC_STATE_RUNNING)
+ if (the_lnet.ln_mt_state != LNET_MT_STATE_RUNNING)
return true;
/* Router Checker thread needs to run when routing is enabled in
if (the_lnet.ln_routing)
return true;
+ /* if there are routers that need to be cleaned up then do so */
+ if (!list_empty(&the_lnet.ln_rcd_deathrow) ||
+ !list_empty(&the_lnet.ln_rcd_zombie))
+ return true;
+
return !list_empty(&the_lnet.ln_routers) &&
(live_router_check_interval > 0 ||
dead_router_check_interval > 0);
}
-static int
-lnet_router_checker(void *arg)
+void
+lnet_check_routers(void)
{
- struct lnet_peer_ni *rtr;
+ struct lnet_peer *rtr;
struct list_head *entry;
+ __u64 version;
+ int cpt;
- cfs_block_allsigs();
-
- while (the_lnet.ln_rc_state == LNET_RC_STATE_RUNNING) {
- __u64 version;
- int cpt;
- int cpt2;
-
- cpt = lnet_net_lock_current();
+ cpt = lnet_net_lock_current();
rescan:
- version = the_lnet.ln_routers_version;
+ version = the_lnet.ln_routers_version;
- list_for_each(entry, &the_lnet.ln_routers) {
- rtr = list_entry(entry, struct lnet_peer_ni,
- lpni_rtr_list);
-
- cpt2 = rtr->lpni_cpt;
- if (cpt != cpt2) {
- lnet_net_unlock(cpt);
- cpt = cpt2;
- lnet_net_lock(cpt);
- /* the routers list has changed */
- if (version != the_lnet.ln_routers_version)
- goto rescan;
- }
+ list_for_each(entry, &the_lnet.ln_routers) {
+ rtr = list_entry(entry, struct lnet_peer,
+ lp_rtr_list);
- lnet_ping_router_locked(rtr);
+ /* TODO use discovery to determine if router is alive */
- /* NB dropped lock */
- if (version != the_lnet.ln_routers_version) {
- /* the routers list has changed */
- goto rescan;
- }
+ /* NB dropped lock */
+ if (version != the_lnet.ln_routers_version) {
+ /* the routers list has changed */
+ goto rescan;
}
-
- if (the_lnet.ln_routing)
- lnet_update_ni_status_locked();
-
- lnet_net_unlock(cpt);
-
- lnet_prune_rc_data(0); /* don't wait for UNLINK */
-
- /* Call schedule_timeout() here always adds 1 to load average
- * because kernel counts # active tasks as nr_running
- * + nr_uninterruptible. */
- /* if there are any routes then wakeup every second. If
- * there are no routes then sleep indefinitely until woken
- * up by a user adding a route */
- if (!lnet_router_checker_active())
- wait_event_interruptible(the_lnet.ln_rc_waitq,
- lnet_router_checker_active());
- else
- wait_event_interruptible_timeout(the_lnet.ln_rc_waitq,
- false,
- cfs_time_seconds(1));
}
- lnet_prune_rc_data(1); /* wait for UNLINK */
+ if (the_lnet.ln_routing)
+ lnet_update_ni_status_locked();
- the_lnet.ln_rc_state = LNET_RC_STATE_SHUTDOWN;
- up(&the_lnet.ln_rc_signal);
- /* The unlink event callback will signal final completion */
- return 0;
+ lnet_net_unlock(cpt);
+
+ lnet_prune_rc_data(0); /* don't wait for UNLINK */
}
void
lnet_net_lock(LNET_LOCK_EX);
the_lnet.ln_routing = 1;
lnet_net_unlock(LNET_LOCK_EX);
+ wake_up(&the_lnet.ln_mt_waitq);
return 0;
failed: