* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2016, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
*/
#define DEBUG_SUBSYSTEM S_LNET
+
+#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/ktime.h>
#include <linux/moduleparam.h>
+#include <linux/uaccess.h>
#include <lnet/lib-lnet.h>
MODULE_PARM_DESC(lnet_numa_range,
"NUMA range to consider during Multi-Rail selection");
+/*
+ * lnet_health_sensitivity determines by how much we decrement the health
+ * value on sending error. The value defaults to 0, which means health
+ * checking is turned off by default.
+ */
+unsigned int lnet_health_sensitivity = 0;
+static int sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp);
+static struct kernel_param_ops param_ops_health_sensitivity = {
+ .set = sensitivity_set,
+ .get = param_get_int,
+};
+#define param_check_health_sensitivity(name, p) \
+ __param_check(name, p, int)
+#ifdef HAVE_KERNEL_PARAM_OPS
+module_param(lnet_health_sensitivity, health_sensitivity, S_IRUGO|S_IWUSR);
+#else
+module_param_call(lnet_health_sensitivity, sensitivity_set, param_get_int,
+ &lnet_health_sensitivity, S_IRUGO|S_IWUSR);
+#endif
+MODULE_PARM_DESC(lnet_health_sensitivity,
+ "Value to decrement the health value by on error");
+
static int lnet_interfaces_max = LNET_INTERFACES_MAX_DEFAULT;
-static int intf_max_set(const char *val, struct kernel_param *kp);
+static int intf_max_set(const char *val, cfs_kernel_param_arg_t *kp);
+
+static struct kernel_param_ops param_ops_interfaces_max = {
+ .set = intf_max_set,
+ .get = param_get_int,
+};
+
+#define param_check_interfaces_max(name, p) \
+ __param_check(name, p, int)
+
+#ifdef HAVE_KERNEL_PARAM_OPS
+module_param(lnet_interfaces_max, interfaces_max, 0644);
+#else
module_param_call(lnet_interfaces_max, intf_max_set, param_get_int,
- &lnet_interfaces_max, S_IRUGO|S_IWUSR);
+ ¶m_ops_interfaces_max, 0644);
+#endif
MODULE_PARM_DESC(lnet_interfaces_max,
"Maximum number of interfaces in a node.");
unsigned lnet_peer_discovery_disabled = 0;
-static int discovery_set(const char *val, struct kernel_param *kp);
+static int discovery_set(const char *val, cfs_kernel_param_arg_t *kp);
+
+static struct kernel_param_ops param_ops_discovery_disabled = {
+ .set = discovery_set,
+ .get = param_get_int,
+};
+
+#define param_check_discovery_disabled(name, p) \
+ __param_check(name, p, int)
+#ifdef HAVE_KERNEL_PARAM_OPS
+module_param(lnet_peer_discovery_disabled, discovery_disabled, 0644);
+#else
module_param_call(lnet_peer_discovery_disabled, discovery_set, param_get_int,
- &lnet_peer_discovery_disabled, S_IRUGO|S_IWUSR);
+ ¶m_ops_discovery_disabled, 0644);
+#endif
MODULE_PARM_DESC(lnet_peer_discovery_disabled,
"Set to 1 to disable peer discovery on this node.");
+unsigned lnet_transaction_timeout = 5;
+module_param(lnet_transaction_timeout, uint, 0444);
+MODULE_PARM_DESC(lnet_transaction_timeout,
+ "Time in seconds to wait for a REPLY or an ACK");
+
+unsigned lnet_retry_count = 0;
+module_param(lnet_retry_count, uint, 0444);
+MODULE_PARM_DESC(lnet_retry_count,
+ "Maximum number of times to retry transmitting a message");
+
+unsigned lnet_lnd_timeout = LNET_LND_DEFAULT_TIMEOUT;
+
/*
* This sequence number keeps track of how many times DLC was used to
* update the local NIs. It is incremented when a NI is added or
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 lnet_discover(struct lnet_process_id id, __u32 force,
+ struct lnet_process_id __user *ids, int n_ids);
+
+static int
+sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned *sensitivity = (unsigned *)kp->arg;
+ unsigned long value;
+
+ rc = kstrtoul(val, 0, &value);
+ if (rc) {
+ CERROR("Invalid module parameter value for 'lnet_health_sensitivity'\n");
+ return rc;
+ }
+
+ /*
+ * 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 (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ if (value == *sensitivity) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ *sensitivity = value;
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return 0;
+}
static int
-discovery_set(const char *val, struct kernel_param *kp)
+discovery_set(const char *val, cfs_kernel_param_arg_t *kp)
{
int rc;
unsigned *discovery = (unsigned *)kp->arg;
}
static int
-intf_max_set(const char *val, struct kernel_param *kp)
+intf_max_set(const char *val, cfs_kernel_param_arg_t *kp)
{
int value, rc;
spin_lock_init(&the_lnet.ln_eq_wait_lock);
spin_lock_init(&the_lnet.ln_msg_resend_lock);
init_waitqueue_head(&the_lnet.ln_eq_waitq);
- init_waitqueue_head(&the_lnet.ln_rc_waitq);
+ init_waitqueue_head(&the_lnet.ln_mt_waitq);
mutex_init(&the_lnet.ln_lnd_mutex);
}
return NULL;
}
+unsigned int
+lnet_get_lnd_timeout(void)
+{
+ return lnet_lnd_timeout;
+}
+EXPORT_SYMBOL(lnet_get_lnd_timeout);
+
void
lnet_register_lnd(struct lnet_lnd *lnd)
{
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_LIST_HEAD(&the_lnet.ln_mt_localNIRecovq);
+ INIT_LIST_HEAD(&the_lnet.ln_mt_peerNIRecovq);
init_waitqueue_head(&the_lnet.ln_dc_waitq);
rc = lnet_descriptor_setup();
bool
lnet_is_ni_healthy_locked(struct lnet_ni *ni)
{
- if (ni->ni_state == LNET_NI_STATE_ACTIVE ||
- ni->ni_state == LNET_NI_STATE_DEGRADED)
+ if (ni->ni_state & LNET_NI_STATE_ACTIVE)
return true;
return false;
/* Resize the push target. */
int lnet_push_target_resize(void)
{
- lnet_process_id_t id = { LNET_NID_ANY, LNET_PID_ANY };
- lnet_md_t md = { NULL };
- lnet_handle_me_t meh;
- lnet_handle_md_t mdh;
- lnet_handle_md_t old_mdh;
+ struct lnet_process_id id = { LNET_NID_ANY, LNET_PID_ANY };
+ struct lnet_md md = { NULL };
+ struct lnet_handle_me meh;
+ struct lnet_handle_md mdh;
+ struct lnet_handle_md old_mdh;
struct lnet_ping_buffer *pbuf;
struct lnet_ping_buffer *old_pbuf;
int nnis = the_lnet.ln_push_target_nnis;
list_del_init(&ni->ni_netlist);
/* the ni should be in deleting state. If it's not it's
* a bug */
- LASSERT(ni->ni_state == LNET_NI_STATE_DELETING);
+ LASSERT(ni->ni_state & LNET_NI_STATE_DELETING);
cfs_percpt_for_each(ref, j, ni->ni_refs) {
if (*ref == 0)
continue;
struct lnet_net *net = ni->ni_net;
lnet_net_lock(LNET_LOCK_EX);
- ni->ni_state = LNET_NI_STATE_DELETING;
+ lnet_ni_lock(ni);
+ ni->ni_state |= LNET_NI_STATE_DELETING;
+ ni->ni_state &= ~LNET_NI_STATE_ACTIVE;
+ lnet_ni_unlock(ni);
lnet_ni_unlink_locked(ni);
lnet_incr_dlc_seq();
lnet_net_unlock(LNET_LOCK_EX);
list_for_each_entry_safe(msg, tmp, &resend, msg_list) {
list_del_init(&msg->msg_list);
+ msg->msg_no_resend = true;
lnet_finalize(msg, -ECANCELED);
}
goto failed0;
}
- ni->ni_state = LNET_NI_STATE_ACTIVE;
+ lnet_ni_lock(ni);
+ ni->ni_state |= LNET_NI_STATE_ACTIVE;
+ ni->ni_state &= ~LNET_NI_STATE_INIT;
+ lnet_ni_unlock(ni);
/* We keep a reference on the loopback net through the loopback NI */
if (net->net_lnd->lnd_type == LOLND) {
atomic_set(&ni->ni_tx_credits,
lnet_ni_tq_credits(ni) * ni->ni_ncpts);
+ atomic_set(&ni->ni_healthv, LNET_MAX_HEALTH_VALUE);
CDEBUG(D_LNI, "Added LNI %s [%d/%d/%d/%d]\n",
libcfs_nid2str(ni->ni_nid),
if (lnet_net_unique(net->net_id, &the_lnet.ln_nets, &net_l)) {
lnd_type = LNET_NETTYP(net->net_id);
- LASSERT(libcfs_isknown_lnd(lnd_type));
-
mutex_lock(&the_lnet.ln_lnd_mutex);
lnd = lnet_find_lnd_by_type(lnd_type);
lnet_ping_target_update(pbuf, ping_mdh);
- rc = lnet_router_checker_start();
+ rc = lnet_monitor_thr_start();
if (rc != 0)
goto err_stop_ping;
rc = lnet_push_target_init();
if (rc != 0)
- goto err_stop_router_checker;
+ goto err_stop_monitor_thr;
rc = lnet_peer_discovery_start();
if (rc != 0)
err_destroy_push_target:
lnet_push_target_fini();
-err_stop_router_checker:
- lnet_router_checker_stop();
+err_stop_monitor_thr:
+ lnet_monitor_thr_stop();
err_stop_ping:
lnet_ping_target_fini();
err_acceptor_stop:
lnet_router_debugfs_init();
lnet_peer_discovery_stop();
lnet_push_target_fini();
- lnet_router_checker_stop();
+ lnet_monitor_thr_stop();
lnet_ping_target_fini();
/* Teardown fns that use my own API functions BEFORE here */
struct lnet_ni *ni;
struct lnet_net *net = mynet;
+ /*
+ * It is possible that the net has been cleaned out while there is
+ * a message being sent. This function accessed the net without
+ * checking if the list is empty
+ */
if (prev == NULL) {
if (net == NULL)
net = list_entry(the_lnet.ln_nets.next, struct lnet_net,
net_list);
+ if (list_empty(&net->net_ni_list))
+ return NULL;
ni = list_entry(net->net_ni_list.next, struct lnet_ni,
ni_netlist);
/* get the next net */
net = list_entry(prev->ni_net->net_list.next, struct lnet_net,
net_list);
+ if (list_empty(&net->net_ni_list))
+ return NULL;
/* get the ni on it */
ni = list_entry(net->net_ni_list.next, struct lnet_ni,
ni_netlist);
return ni;
}
+ if (list_empty(&prev->ni_netlist))
+ return NULL;
+
/* there are more nis left */
ni = list_entry(prev->ni_netlist.next, struct lnet_ni, ni_netlist);
struct lnet_ni *ni;
struct lnet_ioctl_config_lnd_tunables *tun = NULL;
int rc, i;
- __u32 net_id;
+ __u32 net_id, lnd_type;
/* get the tunables if they are available */
if (conf->lic_cfg_hdr.ioc_len >=
tun);
net_id = LNET_NIDNET(conf->lic_nid);
+ lnd_type = LNET_NETTYP(net_id);
+
+ if (!libcfs_isknown_lnd(lnd_type)) {
+ CERROR("No valid net and lnd information provided\n");
+ return -EINVAL;
+ }
net = lnet_net_alloc(net_id, NULL);
if (!net)
mutex_lock(&the_lnet.ln_api_mutex);
rc = lnet_get_peer_list(&cfg->prcfg_count, &cfg->prcfg_size,
- (lnet_process_id_t __user *)cfg->prcfg_bulk);
+ (struct lnet_process_id __user *)cfg->prcfg_bulk);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
}
case IOC_LIBCFS_NOTIFY_ROUTER: {
- unsigned long jiffies_passed;
-
- jiffies_passed = ktime_get_real_seconds() - data->ioc_u64[0];
- jiffies_passed = cfs_time_seconds(jiffies_passed);
+ time64_t deadline = ktime_get_real_seconds() - data->ioc_u64[0];
+ /* The deadline passed in by the user should be some time in
+ * seconds in the future since the UNIX epoch. We have to map
+ * that deadline to the wall clock.
+ */
+ deadline += ktime_get_seconds();
return lnet_notify(NULL, data->ioc_nid, data->ioc_flags,
- jiffies - jiffies_passed);
+ deadline);
}
case IOC_LIBCFS_LNET_DIST:
rc = LNetGet(LNET_NID_ANY, mdh, id,
LNET_RESERVED_PORTAL,
- LNET_PROTO_PING_MATCHBITS, 0);
+ LNET_PROTO_PING_MATCHBITS, 0, false);
if (rc != 0) {
/* Don't CERROR; this could be deliberate! */
}
static int
-lnet_discover(lnet_process_id_t id, __u32 force, lnet_process_id_t __user *ids,
- int n_ids)
+lnet_discover(struct lnet_process_id id, __u32 force,
+ struct lnet_process_id __user *ids, int n_ids)
{
struct lnet_peer_ni *lpni;
struct lnet_peer_ni *p;
struct lnet_peer *lp;
- lnet_process_id_t *buf;
+ struct lnet_process_id *buf;
int cpt;
int i;
int rc;