#define D_LNI D_CONSOLE
-struct lnet the_lnet; /* THE state of the network */
+/*
+ * initialize ln_api_mutex statically, since it needs to be used in
+ * discovery_set callback. That module parameter callback can be called
+ * before module init completes. The mutex needs to be ready for use then.
+ */
+struct lnet the_lnet = {
+ .ln_api_mutex = __MUTEX_INITIALIZER(the_lnet.ln_api_mutex),
+}; /* THE state of the network */
EXPORT_SYMBOL(the_lnet);
static char *ip2nets = "";
static int lnet_ping(struct lnet_process_id id, signed long timeout,
struct lnet_process_id __user *ids, int n_ids);
+static int lnet_discover(lnet_process_id_t id, __u32 force,
+ lnet_process_id_t __user *ids, int n_ids);
+
static int
discovery_set(const char *val, struct kernel_param *kp)
{
int rc;
+ unsigned *discovery = (unsigned *)kp->arg;
unsigned long value;
+ struct lnet_ping_buffer *pbuf;
rc = kstrtoul(val, 0, &value);
if (rc) {
return rc;
}
- *(unsigned *)kp->arg = (value) ? 1 : 0;
+ value = (value) ? 1 : 0;
+
+ /*
+ * The purpose of locking the api_mutex here is to ensure that
+ * the correct value ends up stored properly.
+ */
+ mutex_lock(&the_lnet.ln_api_mutex);
+
+ if (value == *discovery) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ *discovery = value;
+
+ if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ /* tell peers that discovery setting has changed */
+ lnet_net_lock(LNET_LOCK_EX);
+ pbuf = the_lnet.ln_ping_target;
+ if (value)
+ pbuf->pb_info.pi_features &= ~LNET_PING_FEAT_DISCOVERY;
+ else
+ pbuf->pb_info.pi_features |= LNET_PING_FEAT_DISCOVERY;
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ lnet_push_update_to_peers(1);
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
return 0;
}
init_waitqueue_head(&the_lnet.ln_eq_waitq);
init_waitqueue_head(&the_lnet.ln_rc_waitq);
mutex_init(&the_lnet.ln_lnd_mutex);
- mutex_init(&the_lnet.ln_api_mutex);
}
static void
INIT_LIST_HEAD(&the_lnet.ln_routers);
INIT_LIST_HEAD(&the_lnet.ln_drop_rules);
INIT_LIST_HEAD(&the_lnet.ln_delay_rules);
+ INIT_LIST_HEAD(&the_lnet.ln_dc_request);
+ INIT_LIST_HEAD(&the_lnet.ln_dc_working);
+ INIT_LIST_HEAD(&the_lnet.ln_dc_expired);
+ init_waitqueue_head(&the_lnet.ln_dc_waitq);
rc = lnet_descriptor_setup();
if (rc != 0)
pbuf->pb_info.pi_nnis = nnis;
pbuf->pb_info.pi_pid = the_lnet.ln_pid;
pbuf->pb_info.pi_magic = LNET_PROTO_PING_MAGIC;
- pbuf->pb_info.pi_features = LNET_PING_FEAT_NI_STATUS;
+ pbuf->pb_info.pi_features =
+ LNET_PING_FEAT_NI_STATUS | LNET_PING_FEAT_MULTI_RAIL;
return pbuf;
}
if (!the_lnet.ln_routing)
pbuf->pb_info.pi_features |= LNET_PING_FEAT_RTE_DISABLED;
+ if (!lnet_peer_discovery_disabled)
+ pbuf->pb_info.pi_features |= LNET_PING_FEAT_DISCOVERY;
/* Ensure only known feature bits have been set. */
LASSERT(pbuf->pb_info.pi_features & LNET_PING_FEAT_BITS);
lnet_ping_md_unlink(old_pbuf, &old_ping_md);
lnet_ping_buffer_decref(old_pbuf);
}
+
+ lnet_push_update_to_peers(0);
}
static void
if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC))
lnet_swap_pinginfo(pbuf);
+ lnet_peer_push_event(ev);
if (ev->unlinked)
lnet_ping_buffer_decref(pbuf);
}
lnet_assert_wire_constants();
- memset(&the_lnet, 0, sizeof(the_lnet));
-
/* refer to global cfs_cpt_table for now */
the_lnet.ln_cpt_table = cfs_cpt_table;
the_lnet.ln_cpt_number = cfs_cpt_number(cfs_cpt_table);
memcpy(&tun->lt_cmn, &ni->ni_net->net_tunables, sizeof(tun->lt_cmn));
if (stats) {
- stats->iel_send_count = atomic_read(&ni->ni_stats.send_count);
- stats->iel_recv_count = atomic_read(&ni->ni_stats.recv_count);
+ stats->iel_send_count = lnet_sum_stats(&ni->ni_stats,
+ LNET_STATS_TYPE_SEND);
+ stats->iel_recv_count = lnet_sum_stats(&ni->ni_stats,
+ LNET_STATS_TYPE_RECV);
+ stats->iel_drop_count = lnet_sum_stats(&ni->ni_stats,
+ LNET_STATS_TYPE_DROP);
}
/*
return rc;
}
+int lnet_get_ni_stats(struct lnet_ioctl_element_msg_stats *msg_stats)
+{
+ struct lnet_ni *ni;
+ int cpt;
+ int rc = -ENOENT;
+
+ if (!msg_stats)
+ return -EINVAL;
+
+ cpt = lnet_net_lock_current();
+
+ ni = lnet_get_ni_idx_locked(msg_stats->im_idx);
+
+ if (ni) {
+ lnet_usr_translate_stats(msg_stats, &ni->ni_stats);
+ rc = 0;
+ }
+
+ lnet_net_unlock(cpt);
+
+ return rc;
+}
+
static int lnet_add_net_common(struct lnet_net *net,
struct lnet_ioctl_config_lnd_tunables *tun)
{
__u32 tun_size;
cfg_ni = arg;
+
/* get the tunables if they are available */
if (cfg_ni->lic_cfg_hdr.ioc_len <
- sizeof(*cfg_ni) + sizeof(*stats)+ sizeof(*tun))
+ sizeof(*cfg_ni) + sizeof(*stats) + sizeof(*tun))
return -EINVAL;
stats = (struct lnet_ioctl_element_stats *)
return rc;
}
+ case IOC_LIBCFS_GET_LOCAL_NI_MSG_STATS: {
+ struct lnet_ioctl_element_msg_stats *msg_stats = arg;
+
+ if (msg_stats->im_hdr.ioc_len != sizeof(*msg_stats))
+ return -EINVAL;
+
+ mutex_lock(&the_lnet.ln_api_mutex);
+ rc = lnet_get_ni_stats(msg_stats);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return rc;
+ }
+
case IOC_LIBCFS_GET_NET: {
size_t total = sizeof(*config) +
sizeof(struct lnet_ioctl_net_config);
case IOC_LIBCFS_GET_PEER_NI: {
struct lnet_ioctl_peer_cfg *cfg = arg;
- struct lnet_peer_ni_credit_info __user *lpni_cri;
- struct lnet_ioctl_element_stats __user *lpni_stats;
- size_t usr_size = sizeof(*lpni_cri) + sizeof(*lpni_stats);
- if ((cfg->prcfg_hdr.ioc_len != sizeof(*cfg)) ||
- (cfg->prcfg_size != usr_size))
+ if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg))
return -EINVAL;
- lpni_cri = cfg->prcfg_bulk;
- lpni_stats = cfg->prcfg_bulk + sizeof(*lpni_cri);
+ mutex_lock(&the_lnet.ln_api_mutex);
+ rc = lnet_get_peer_info(&cfg->prcfg_prim_nid,
+ &cfg->prcfg_cfg_nid,
+ &cfg->prcfg_count,
+ &cfg->prcfg_mr,
+ &cfg->prcfg_size,
+ (void __user *)cfg->prcfg_bulk);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return rc;
+ }
+
+ case IOC_LIBCFS_GET_PEER_LIST: {
+ struct lnet_ioctl_peer_cfg *cfg = arg;
+
+ if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg))
+ return -EINVAL;
mutex_lock(&the_lnet.ln_api_mutex);
- rc = lnet_get_peer_info(cfg->prcfg_count, &cfg->prcfg_prim_nid,
- &cfg->prcfg_cfg_nid, &cfg->prcfg_mr,
- lpni_cri, lpni_stats);
+ rc = lnet_get_peer_list(&cfg->prcfg_count, &cfg->prcfg_size,
+ (lnet_process_id_t __user *)cfg->prcfg_bulk);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
}
id.nid = data->ioc_nid;
id.pid = data->ioc_u32[0];
- /* Don't block longer than 2 minutes */
- if (data->ioc_u32[1] > 120 * MSEC_PER_SEC)
- return -EINVAL;
-
- /* If timestamp is negative then disable timeout */
- if ((s32)data->ioc_u32[1] < 0)
- timeout = MAX_SCHEDULE_TIMEOUT;
+ /* If timeout is negative then set default of 3 minutes */
+ if (((s32)data->ioc_u32[1] <= 0) ||
+ data->ioc_u32[1] > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
+ timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
else
timeout = msecs_to_jiffies(data->ioc_u32[1]);
rc = lnet_ping(id, timeout, data->ioc_pbuf1,
data->ioc_plen1 / sizeof(struct lnet_process_id));
+
if (rc < 0)
return rc;
+
data->ioc_count = rc;
return 0;
}
+ case IOC_LIBCFS_PING_PEER: {
+ struct lnet_ioctl_ping_data *ping = arg;
+ struct lnet_peer *lp;
+ signed long timeout;
+
+ /* If timeout is negative then set default of 3 minutes */
+ if (((s32)ping->op_param) <= 0 ||
+ ping->op_param > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
+ timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
+ else
+ timeout = msecs_to_jiffies(ping->op_param);
+
+ rc = lnet_ping(ping->ping_id, timeout,
+ ping->ping_buf,
+ ping->ping_count);
+ if (rc < 0)
+ return rc;
+
+ lp = lnet_find_peer(ping->ping_id.nid);
+ if (lp) {
+ ping->ping_id.nid = lp->lp_primary_nid;
+ ping->mr_info = lnet_peer_is_multi_rail(lp);
+ }
+ ping->ping_count = rc;
+ return 0;
+ }
+
+ case IOC_LIBCFS_DISCOVER: {
+ struct lnet_ioctl_ping_data *discover = arg;
+ struct lnet_peer *lp;
+
+ rc = lnet_discover(discover->ping_id, discover->op_param,
+ discover->ping_buf,
+ discover->ping_count);
+ if (rc < 0)
+ return rc;
+ lp = lnet_find_peer(discover->ping_id.nid);
+ if (lp) {
+ discover->ping_id.nid = lp->lp_primary_nid;
+ discover->mr_info = lnet_peer_is_multi_rail(lp);
+ }
+
+ discover->ping_count = rc;
+ return 0;
+ }
+
default:
ni = lnet_net2ni_addref(data->ioc_net);
if (ni == NULL)
/* initialize md content */
md.start = &pbuf->pb_info;
md.length = LNET_PING_INFO_SIZE(n_ids);
- md.threshold = 2; /*GET/REPLY*/
+ md.threshold = 2; /* GET/REPLY */
md.max_size = 0;
md.options = LNET_MD_TRUNCATE;
md.user_ptr = NULL;
if (rc != 0) {
/* Don't CERROR; this could be deliberate! */
-
rc2 = LNetMDUnlink(mdh);
LASSERT(rc2 == 0);
replied = 1;
rc = event.mlength;
}
-
} while (rc2 <= 0 || !event.unlinked);
if (!replied) {
nob = rc;
LASSERT(nob >= 0 && nob <= LNET_PING_INFO_SIZE(n_ids));
- rc = -EPROTO; /* if I can't parse... */
+ rc = -EPROTO; /* if I can't parse... */
if (nob < 8) {
- /* can't check magic/version */
CERROR("%s: ping info too short %d\n",
libcfs_id2str(id), nob);
goto fail_free_eq;
}
if (nob < LNET_PING_INFO_SIZE(0)) {
- CERROR("%s: Short reply %d(%d min)\n", libcfs_id2str(id),
+ CERROR("%s: Short reply %d(%d min)\n",
+ libcfs_id2str(id),
nob, (int)LNET_PING_INFO_SIZE(0));
goto fail_free_eq;
}
n_ids = pbuf->pb_info.pi_nnis;
if (nob < LNET_PING_INFO_SIZE(n_ids)) {
- CERROR("%s: Short reply %d(%d expected)\n", libcfs_id2str(id),
+ CERROR("%s: Short reply %d(%d expected)\n",
+ libcfs_id2str(id),
nob, (int)LNET_PING_INFO_SIZE(n_ids));
goto fail_free_eq;
}
- rc = -EFAULT; /* If I SEGV... */
+ rc = -EFAULT; /* if I segv in copy_to_user()... */
memset(&tmpid, 0, sizeof(tmpid));
for (i = 0; i < n_ids; i++) {
lnet_ping_buffer_decref(pbuf);
return rc;
}
+
+static int
+lnet_discover(lnet_process_id_t id, __u32 force, lnet_process_id_t __user *ids,
+ int n_ids)
+{
+ struct lnet_peer_ni *lpni;
+ struct lnet_peer_ni *p;
+ struct lnet_peer *lp;
+ lnet_process_id_t *buf;
+ int cpt;
+ int i;
+ int rc;
+ int max_intf = lnet_interfaces_max;
+
+ if (n_ids <= 0 ||
+ id.nid == LNET_NID_ANY ||
+ n_ids > max_intf)
+ return -EINVAL;
+
+ if (id.pid == LNET_PID_ANY)
+ id.pid = LNET_PID_LUSTRE;
+
+ LIBCFS_ALLOC(buf, n_ids * sizeof(*buf));
+ if (!buf)
+ return -ENOMEM;
+
+ cpt = lnet_net_lock_current();
+ lpni = lnet_nid2peerni_locked(id.nid, LNET_NID_ANY, cpt);
+ if (IS_ERR(lpni)) {
+ rc = PTR_ERR(lpni);
+ goto out;
+ }
+
+ /*
+ * Clearing the NIDS_UPTODATE flag ensures the peer will
+ * be discovered, provided discovery has not been disabled.
+ */
+ lp = lpni->lpni_peer_net->lpn_peer;
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ /* If the force flag is set, force a PING and PUSH as well. */
+ if (force)
+ lp->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH;
+ spin_unlock(&lp->lp_lock);
+ rc = lnet_discover_peer_locked(lpni, cpt, true);
+ if (rc)
+ goto out_decref;
+
+ /* Peer may have changed. */
+ lp = lpni->lpni_peer_net->lpn_peer;
+ if (lp->lp_nnis < n_ids)
+ n_ids = lp->lp_nnis;
+
+ i = 0;
+ p = NULL;
+ while ((p = lnet_get_next_peer_ni_locked(lp, NULL, p)) != NULL) {
+ buf[i].pid = id.pid;
+ buf[i].nid = p->lpni_nid;
+ if (++i >= n_ids)
+ break;
+ }
+
+ lnet_net_unlock(cpt);
+
+ rc = -EFAULT;
+ if (copy_to_user(ids, buf, n_ids * sizeof(*buf)))
+ goto out_relock;
+ rc = n_ids;
+out_relock:
+ lnet_net_lock(cpt);
+out_decref:
+ lnet_peer_ni_decref_locked(lpni);
+out:
+ lnet_net_unlock(cpt);
+
+ return rc;
+}