* 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>
+#ifdef HAVE_SCHED_HEADERS
+#include <linux/sched/signal.h>
+#endif
#include <lnet/lib-lnet.h>
#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 = "";
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 100, which means health
+ * interface health is decremented by 100 points every failure.
+ */
+unsigned int lnet_health_sensitivity = 100;
+static int sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
+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)
+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");
+
+/*
+ * lnet_recovery_interval determines how often we should perform recovery
+ * on unhealthy interfaces.
+ */
+unsigned int lnet_recovery_interval = 1;
+static int recovery_interval_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
+static struct kernel_param_ops param_ops_recovery_interval = {
+ .set = recovery_interval_set,
+ .get = param_get_int,
+};
+#define param_check_recovery_interval(name, p) \
+ __param_check(name, p, int)
+module_param(lnet_recovery_interval, recovery_interval, S_IRUGO|S_IWUSR);
+#else
+module_param_call(lnet_recovery_interval, recovery_interval_set, param_get_int,
+ &lnet_recovery_interval, S_IRUGO|S_IWUSR);
+#endif
+MODULE_PARM_DESC(lnet_recovery_interval,
+ "Interval to recover unhealthy interfaces in seconds");
+
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 int lnet_drop_asym_route;
+static int drop_asym_route_set(const char *val, cfs_kernel_param_arg_t *kp);
+
+static struct kernel_param_ops param_ops_drop_asym_route = {
+ .set = drop_asym_route_set,
+ .get = param_get_int,
+};
+
+#define param_check_drop_asym_route(name, p) \
+ __param_check(name, p, int)
+#ifdef HAVE_KERNEL_PARAM_OPS
+module_param(lnet_drop_asym_route, drop_asym_route, 0644);
+#else
+module_param_call(lnet_drop_asym_route, drop_asym_route_set, param_get_int,
+ ¶m_ops_drop_asym_route, 0644);
+#endif
+MODULE_PARM_DESC(lnet_drop_asym_route,
+ "Set to 1 to drop asymmetrical route messages.");
+
+#define LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT 50
+#define LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT 50
+
+unsigned lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
+static int transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
+static struct kernel_param_ops param_ops_transaction_timeout = {
+ .set = transaction_to_set,
+ .get = param_get_int,
+};
+
+#define param_check_transaction_timeout(name, p) \
+ __param_check(name, p, int)
+module_param(lnet_transaction_timeout, transaction_timeout, S_IRUGO|S_IWUSR);
+#else
+module_param_call(lnet_transaction_timeout, transaction_to_set, param_get_int,
+ &lnet_transaction_timeout, S_IRUGO|S_IWUSR);
+#endif
+MODULE_PARM_DESC(lnet_transaction_timeout,
+ "Maximum number of seconds to wait for a peer response.");
+
+#define LNET_RETRY_COUNT_HEALTH_DEFAULT 2
+unsigned lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
+static int retry_count_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
+static struct kernel_param_ops param_ops_retry_count = {
+ .set = retry_count_set,
+ .get = param_get_int,
+};
+
+#define param_check_retry_count(name, p) \
+ __param_check(name, p, int)
+module_param(lnet_retry_count, retry_count, S_IRUGO|S_IWUSR);
+#else
+module_param_call(lnet_retry_count, retry_count_set, param_get_int,
+ &lnet_retry_count, S_IRUGO|S_IWUSR);
+#endif
+MODULE_PARM_DESC(lnet_retry_count,
+ "Maximum number of times to retry transmitting a message");
+
+
+#define LNET_LND_TIMEOUT_DEFAULT ((LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT - 1) / \
+ (LNET_RETRY_COUNT_HEALTH_DEFAULT + 1))
+unsigned int lnet_lnd_timeout = LNET_LND_TIMEOUT_DEFAULT;
+static void lnet_set_lnd_timeout(void)
+{
+ lnet_lnd_timeout = (lnet_transaction_timeout - 1) /
+ (lnet_retry_count + 1);
+}
+
+unsigned int lnet_current_net_count;
+
/*
* 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(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 (value > LNET_MAX_HEALTH_VALUE) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ CERROR("Invalid health value. Maximum: %d value = %lu\n",
+ LNET_MAX_HEALTH_VALUE, value);
+ return -EINVAL;
+ }
+
+ /*
+ * if we're turning on health then use the health timeout
+ * defaults.
+ */
+ if (*sensitivity == 0 && value != 0) {
+ lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
+ lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
+ lnet_set_lnd_timeout();
+ /*
+ * if we're turning off health then use the no health timeout
+ * default.
+ */
+ } else if (*sensitivity != 0 && value == 0) {
+ lnet_transaction_timeout =
+ LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT;
+ lnet_retry_count = 0;
+ lnet_set_lnd_timeout();
+ }
+
+ *sensitivity = value;
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return 0;
+}
+
+static int
+recovery_interval_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned *interval = (unsigned *)kp->arg;
+ unsigned long value;
+
+ rc = kstrtoul(val, 0, &value);
+ if (rc) {
+ CERROR("Invalid module parameter value for 'lnet_recovery_interval'\n");
+ return rc;
+ }
+
+ if (value < 1) {
+ CERROR("lnet_recovery_interval must be at least 1 second\n");
+ return -EINVAL;
+ }
+
+ /*
+ * 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);
+
+ *interval = 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_off = (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_off) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ /*
+ * We still want to set the discovery value even when LNet is not
+ * running. This is the case when LNet is being loaded and we want
+ * the module parameters to take effect. Otherwise if we're
+ * changing the value dynamically, we want to set it after
+ * updating the peers
+ */
+ if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ *discovery_off = value;
+ 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);
+
+ /* only send a push when we're turning off discovery */
+ if (*discovery_off <= 0 && value > 0)
+ lnet_push_update_to_peers(1);
+ *discovery_off = value;
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return 0;
+}
+
+static int
+drop_asym_route_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned int *drop_asym_route = (unsigned int *)kp->arg;
+ unsigned long value;
+
+ rc = kstrtoul(val, 0, &value);
+ if (rc) {
+ CERROR("Invalid module parameter value for "
+ "'lnet_drop_asym_route'\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 (value == *drop_asym_route) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ *drop_asym_route = value;
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return 0;
+}
+
+static int
+transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned *transaction_to = (unsigned *)kp->arg;
+ unsigned long value;
+
+ rc = kstrtoul(val, 0, &value);
+ if (rc) {
+ CERROR("Invalid module parameter value for 'lnet_transaction_timeout'\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 (value < lnet_retry_count || value == 0) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ CERROR("Invalid value for lnet_transaction_timeout (%lu). "
+ "Has to be greater than lnet_retry_count (%u)\n",
+ value, lnet_retry_count);
+ return -EINVAL;
+ }
+
+ if (value == *transaction_to) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
+
+ *transaction_to = value;
+ /* Update the lnet_lnd_timeout now that we've modified the
+ * transaction timeout
+ */
+ lnet_set_lnd_timeout();
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return 0;
+}
+
+static int
+retry_count_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned *retry_count = (unsigned *)kp->arg;
+ unsigned long value;
+
+ rc = kstrtoul(val, 0, &value);
+ if (rc) {
+ CERROR("Invalid module parameter value for 'lnet_retry_count'\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 (lnet_health_sensitivity == 0) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ CERROR("Can not set retry_count when health feature is turned off\n");
+ return -EINVAL;
+ }
+
+ if (value > lnet_transaction_timeout) {
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ CERROR("Invalid value for lnet_retry_count (%lu). "
+ "Has to be smaller than lnet_transaction_timeout (%u)\n",
+ value, lnet_transaction_timeout);
+ return -EINVAL;
+ }
+
+ *retry_count = value;
+
+ /* Update the lnet_lnd_timeout now that we've modified the
+ * retry count
+ */
+ lnet_set_lnd_timeout();
+
+ mutex_unlock(&the_lnet.ln_api_mutex);
return 0;
}
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;
if (value < LNET_INTERFACES_MIN) {
CWARN("max interfaces provided are too small, setting to %d\n",
- LNET_INTERFACES_MIN);
- value = LNET_INTERFACES_MIN;
+ LNET_INTERFACES_MAX_DEFAULT);
+ value = LNET_INTERFACES_MAX_DEFAULT;
}
*(int *)kp->arg = value;
return 0;
}
-static char *
+static const char *
lnet_get_routes(void)
{
return routes;
}
-static char *
+static const char *
lnet_get_networks(void)
{
- char *nets;
- int rc;
+ const char *nets;
+ int rc;
if (*networks != 0 && *ip2nets != 0) {
LCONSOLE_ERROR_MSG(0x101, "Please specify EITHER 'networks' or "
lnet_init_locks(void)
{
spin_lock_init(&the_lnet.ln_eq_wait_lock);
- init_waitqueue_head(&the_lnet.ln_eq_waitq);
- init_waitqueue_head(&the_lnet.ln_rc_waitq);
+ spin_lock_init(&the_lnet.ln_msg_resend_lock);
+ init_completion(&the_lnet.ln_mt_wait_complete);
mutex_init(&the_lnet.ln_lnd_mutex);
- mutex_init(&the_lnet.ln_api_mutex);
-}
-
-static void
-lnet_fini_locks(void)
-{
}
struct kmem_cache *lnet_mes_cachep; /* MEs kmem_cache */
struct kmem_cache *lnet_small_mds_cachep; /* <= LNET_SMALL_MD_SIZE bytes
* MDs kmem_cache */
+struct kmem_cache *lnet_rspt_cachep; /* response tracker cache */
+struct kmem_cache *lnet_msg_cachep;
static int
-lnet_descriptor_setup(void)
+lnet_slab_setup(void)
{
/* create specific kmem_cache for MEs and small MDs (i.e., originally
* allocated in <size-xxx> kmem_cache).
if (!lnet_small_mds_cachep)
return -ENOMEM;
+ lnet_rspt_cachep = kmem_cache_create("lnet_rspt", sizeof(struct lnet_rsp_tracker),
+ 0, 0, NULL);
+ if (!lnet_rspt_cachep)
+ return -ENOMEM;
+
+ lnet_msg_cachep = kmem_cache_create("lnet_msg", sizeof(struct lnet_msg),
+ 0, 0, NULL);
+ if (!lnet_msg_cachep)
+ return -ENOMEM;
+
return 0;
}
static void
-lnet_descriptor_cleanup(void)
+lnet_slab_cleanup(void)
{
+ if (lnet_msg_cachep) {
+ kmem_cache_destroy(lnet_msg_cachep);
+ lnet_msg_cachep = NULL;
+ }
+
+
+ if (lnet_rspt_cachep) {
+ kmem_cache_destroy(lnet_rspt_cachep);
+ lnet_rspt_cachep = NULL;
+ }
if (lnet_small_mds_cachep) {
kmem_cache_destroy(lnet_small_mds_cachep);
LASSERT(the_lnet.ln_remote_nets_hash == NULL);
LASSERT(the_lnet.ln_remote_nets_hbits > 0);
- LIBCFS_ALLOC(hash, LNET_REMOTE_NETS_HASH_SIZE * sizeof(*hash));
+ CFS_ALLOC_PTR_ARRAY(hash, LNET_REMOTE_NETS_HASH_SIZE);
if (hash == NULL) {
CERROR("Failed to create remote nets hash table\n");
return -ENOMEM;
for (i = 0; i < LNET_REMOTE_NETS_HASH_SIZE; i++)
LASSERT(list_empty(&the_lnet.ln_remote_nets_hash[i]));
- LIBCFS_FREE(the_lnet.ln_remote_nets_hash,
- LNET_REMOTE_NETS_HASH_SIZE *
- sizeof(the_lnet.ln_remote_nets_hash[0]));
+ CFS_FREE_PTR_ARRAY(the_lnet.ln_remote_nets_hash,
+ LNET_REMOTE_NETS_HASH_SIZE);
the_lnet.ln_remote_nets_hash = NULL;
}
cfs_percpt_lock_free(the_lnet.ln_net_lock);
the_lnet.ln_net_lock = NULL;
}
-
- lnet_fini_locks();
}
static int
* with gcc version 3.3.3 20040412 (Red Hat Linux 3.3.3-7) */
/* Constants... */
- CLASSERT(LNET_PROTO_TCP_MAGIC == 0xeebc0ded);
- CLASSERT(LNET_PROTO_TCP_VERSION_MAJOR == 1);
- CLASSERT(LNET_PROTO_TCP_VERSION_MINOR == 0);
- CLASSERT(LNET_MSG_ACK == 0);
- CLASSERT(LNET_MSG_PUT == 1);
- CLASSERT(LNET_MSG_GET == 2);
- CLASSERT(LNET_MSG_REPLY == 3);
- CLASSERT(LNET_MSG_HELLO == 4);
+ BUILD_BUG_ON(LNET_PROTO_TCP_MAGIC != 0xeebc0ded);
+ BUILD_BUG_ON(LNET_PROTO_TCP_VERSION_MAJOR != 1);
+ BUILD_BUG_ON(LNET_PROTO_TCP_VERSION_MINOR != 0);
+ BUILD_BUG_ON(LNET_MSG_ACK != 0);
+ BUILD_BUG_ON(LNET_MSG_PUT != 1);
+ BUILD_BUG_ON(LNET_MSG_GET != 2);
+ BUILD_BUG_ON(LNET_MSG_REPLY != 3);
+ BUILD_BUG_ON(LNET_MSG_HELLO != 4);
/* Checks for struct lnet_handle_wire */
- CLASSERT((int)sizeof(struct lnet_handle_wire) == 16);
- CLASSERT((int)offsetof(struct lnet_handle_wire, wh_interface_cookie) == 0);
- CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_interface_cookie) == 8);
- CLASSERT((int)offsetof(struct lnet_handle_wire, wh_object_cookie) == 8);
- CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) == 8);
+ BUILD_BUG_ON((int)sizeof(struct lnet_handle_wire) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_handle_wire,
+ wh_interface_cookie) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_handle_wire *)0)->wh_interface_cookie) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_handle_wire,
+ wh_object_cookie) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) != 8);
/* Checks for struct struct lnet_magicversion */
- CLASSERT((int)sizeof(struct lnet_magicversion) == 8);
- CLASSERT((int)offsetof(struct lnet_magicversion, magic) == 0);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->magic) == 4);
- CLASSERT((int)offsetof(struct lnet_magicversion, version_major) == 4);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_major) == 2);
- CLASSERT((int)offsetof(struct lnet_magicversion, version_minor) == 6);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_minor) == 2);
+ BUILD_BUG_ON((int)sizeof(struct lnet_magicversion) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion, magic) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->magic) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion, version_major) != 4);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->version_major) != 2);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion,
+ version_minor) != 6);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->version_minor) != 2);
/* Checks for struct struct lnet_hdr */
- CLASSERT((int)sizeof(struct lnet_hdr) == 72);
- CLASSERT((int)offsetof(struct lnet_hdr, dest_nid) == 0);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, src_nid) == 8);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, dest_pid) == 16);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, src_pid) == 20);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, type) == 24);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->type) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, payload_length) == 28);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->payload_length) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg) == 40);
+ BUILD_BUG_ON((int)sizeof(struct lnet_hdr) != 72);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, dest_nid) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->dest_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, src_nid) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->src_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, dest_pid) != 16);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->dest_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, src_pid) != 20);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->src_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, type) != 24);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->type) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, payload_length) != 28);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->payload_length) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg) != 40);
/* Ack */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.dst_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.dst_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.mlength) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.mlength) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.dst_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.dst_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.mlength) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.mlength) != 4);
/* Put */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ack_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ack_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.hdr_data) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.hdr_data) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ptl_index) == 64);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ptl_index) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.offset) == 68);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.offset) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.ack_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.ack_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.hdr_data) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.hdr_data) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.ptl_index) != 64);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.ptl_index) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.offset) != 68);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.offset) != 4);
/* Get */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.return_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.return_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.ptl_index) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.ptl_index) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.src_offset) == 60);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.src_offset) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.sink_length) == 64);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.sink_length) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.return_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.return_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.ptl_index) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.ptl_index) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.src_offset) != 60);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.src_offset) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.sink_length) != 64);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.sink_length) != 4);
/* Reply */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) == 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) != 16);
/* Hello */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.incarnation) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.incarnation) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.type) == 40);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.type) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.hello.incarnation) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.hello.incarnation) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.hello.type) != 40);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.hello.type) != 4);
/* Checks for struct lnet_ni_status and related constants */
- CLASSERT(LNET_NI_STATUS_INVALID == 0x00000000);
- CLASSERT(LNET_NI_STATUS_UP == 0x15aac0de);
- CLASSERT(LNET_NI_STATUS_DOWN == 0xdeadface);
+ BUILD_BUG_ON(LNET_NI_STATUS_INVALID != 0x00000000);
+ BUILD_BUG_ON(LNET_NI_STATUS_UP != 0x15aac0de);
+ BUILD_BUG_ON(LNET_NI_STATUS_DOWN != 0xdeadface);
/* Checks for struct lnet_ni_status */
- CLASSERT((int)sizeof(struct lnet_ni_status) == 16);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_nid) == 0);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_status) == 8);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_status) == 4);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_unused) == 12);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_unused) == 4);
+ BUILD_BUG_ON((int)sizeof(struct lnet_ni_status) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_nid) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_status) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_status) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_unused) != 12);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_unused) != 4);
/* Checks for struct lnet_ping_info and related constants */
- CLASSERT(LNET_PROTO_PING_MAGIC == 0x70696E67);
- CLASSERT(LNET_PING_FEAT_INVAL == 0);
- CLASSERT(LNET_PING_FEAT_BASE == 1);
- CLASSERT(LNET_PING_FEAT_NI_STATUS == 2);
- CLASSERT(LNET_PING_FEAT_RTE_DISABLED == 4);
- CLASSERT(LNET_PING_FEAT_MULTI_RAIL == 8);
- CLASSERT(LNET_PING_FEAT_DISCOVERY == 16);
- CLASSERT(LNET_PING_FEAT_BITS == 31);
+ BUILD_BUG_ON(LNET_PROTO_PING_MAGIC != 0x70696E67);
+ BUILD_BUG_ON(LNET_PING_FEAT_INVAL != 0);
+ BUILD_BUG_ON(LNET_PING_FEAT_BASE != 1);
+ BUILD_BUG_ON(LNET_PING_FEAT_NI_STATUS != 2);
+ BUILD_BUG_ON(LNET_PING_FEAT_RTE_DISABLED != 4);
+ BUILD_BUG_ON(LNET_PING_FEAT_MULTI_RAIL != 8);
+ BUILD_BUG_ON(LNET_PING_FEAT_DISCOVERY != 16);
+ BUILD_BUG_ON(LNET_PING_FEAT_BITS != 31);
/* Checks for struct lnet_ping_info */
- CLASSERT((int)sizeof(struct lnet_ping_info) == 16);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_magic) == 0);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_magic) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_features) == 4);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_features) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_pid) == 8);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_nnis) == 12);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_nnis) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_ni) == 16);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_ni) == 0);
+ BUILD_BUG_ON((int)sizeof(struct lnet_ping_info) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_magic) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_magic) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_features) != 4);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_features) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_pid) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_nnis) != 12);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_nnis) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_ni) != 16);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_ni) != 0);
}
-static struct lnet_lnd *lnet_find_lnd_by_type(__u32 type)
+static const struct lnet_lnd *lnet_find_lnd_by_type(__u32 type)
{
- struct lnet_lnd *lnd;
- struct list_head *tmp;
+ const struct lnet_lnd *lnd;
/* holding lnd mutex */
- list_for_each(tmp, &the_lnet.ln_lnds) {
- lnd = list_entry(tmp, struct lnet_lnd, lnd_list);
+ if (type >= NUM_LNDS)
+ return NULL;
+ lnd = the_lnet.ln_lnds[type];
+ LASSERT(!lnd || lnd->lnd_type == type);
- if (lnd->lnd_type == type)
- return lnd;
- }
- return NULL;
+ return lnd;
}
+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)
+lnet_register_lnd(const struct lnet_lnd *lnd)
{
mutex_lock(&the_lnet.ln_lnd_mutex);
LASSERT(libcfs_isknown_lnd(lnd->lnd_type));
LASSERT(lnet_find_lnd_by_type(lnd->lnd_type) == NULL);
- list_add_tail(&lnd->lnd_list, &the_lnet.ln_lnds);
- lnd->lnd_refcount = 0;
+ the_lnet.ln_lnds[lnd->lnd_type] = lnd;
CDEBUG(D_NET, "%s LND registered\n", libcfs_lnd2str(lnd->lnd_type));
EXPORT_SYMBOL(lnet_register_lnd);
void
-lnet_unregister_lnd(struct lnet_lnd *lnd)
+lnet_unregister_lnd(const struct lnet_lnd *lnd)
{
mutex_lock(&the_lnet.ln_lnd_mutex);
LASSERT(lnet_find_lnd_by_type(lnd->lnd_type) == lnd);
- LASSERT(lnd->lnd_refcount == 0);
- list_del(&lnd->lnd_list);
+ the_lnet.ln_lnds[lnd->lnd_type] = NULL;
CDEBUG(D_NET, "%s LND unregistered\n", libcfs_lnd2str(lnd->lnd_type));
mutex_unlock(&the_lnet.ln_lnd_mutex);
EXPORT_SYMBOL(lnet_unregister_lnd);
void
+lnet_counters_get_common(struct lnet_counters_common *common)
+{
+ struct lnet_counters *ctr;
+ int i;
+
+ memset(common, 0, sizeof(*common));
+
+ lnet_net_lock(LNET_LOCK_EX);
+
+ cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
+ common->lcc_msgs_max += ctr->lct_common.lcc_msgs_max;
+ common->lcc_msgs_alloc += ctr->lct_common.lcc_msgs_alloc;
+ common->lcc_errors += ctr->lct_common.lcc_errors;
+ common->lcc_send_count += ctr->lct_common.lcc_send_count;
+ common->lcc_recv_count += ctr->lct_common.lcc_recv_count;
+ common->lcc_route_count += ctr->lct_common.lcc_route_count;
+ common->lcc_drop_count += ctr->lct_common.lcc_drop_count;
+ common->lcc_send_length += ctr->lct_common.lcc_send_length;
+ common->lcc_recv_length += ctr->lct_common.lcc_recv_length;
+ common->lcc_route_length += ctr->lct_common.lcc_route_length;
+ common->lcc_drop_length += ctr->lct_common.lcc_drop_length;
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+EXPORT_SYMBOL(lnet_counters_get_common);
+
+void
lnet_counters_get(struct lnet_counters *counters)
{
struct lnet_counters *ctr;
+ struct lnet_counters_health *health = &counters->lct_health;
int i;
memset(counters, 0, sizeof(*counters));
+ lnet_counters_get_common(&counters->lct_common);
+
lnet_net_lock(LNET_LOCK_EX);
cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
- counters->msgs_max += ctr->msgs_max;
- counters->msgs_alloc += ctr->msgs_alloc;
- counters->errors += ctr->errors;
- counters->send_count += ctr->send_count;
- counters->recv_count += ctr->recv_count;
- counters->route_count += ctr->route_count;
- counters->drop_count += ctr->drop_count;
- counters->send_length += ctr->send_length;
- counters->recv_length += ctr->recv_length;
- counters->route_length += ctr->route_length;
- counters->drop_length += ctr->drop_length;
-
+ health->lch_rst_alloc += ctr->lct_health.lch_rst_alloc;
+ health->lch_resend_count += ctr->lct_health.lch_resend_count;
+ health->lch_response_timeout_count +=
+ ctr->lct_health.lch_response_timeout_count;
+ health->lch_local_interrupt_count +=
+ ctr->lct_health.lch_local_interrupt_count;
+ health->lch_local_dropped_count +=
+ ctr->lct_health.lch_local_dropped_count;
+ health->lch_local_aborted_count +=
+ ctr->lct_health.lch_local_aborted_count;
+ health->lch_local_no_route_count +=
+ ctr->lct_health.lch_local_no_route_count;
+ health->lch_local_timeout_count +=
+ ctr->lct_health.lch_local_timeout_count;
+ health->lch_local_error_count +=
+ ctr->lct_health.lch_local_error_count;
+ health->lch_remote_dropped_count +=
+ ctr->lct_health.lch_remote_dropped_count;
+ health->lch_remote_error_count +=
+ ctr->lct_health.lch_remote_error_count;
+ health->lch_remote_timeout_count +=
+ ctr->lct_health.lch_remote_timeout_count;
+ health->lch_network_timeout_count +=
+ ctr->lct_health.lch_network_timeout_count;
}
lnet_net_unlock(LNET_LOCK_EX);
}
struct list_head *e = rec->rec_active.next;
list_del_init(e);
- if (rec->rec_type == LNET_COOKIE_TYPE_EQ) {
- lnet_eq_free(list_entry(e, struct lnet_eq, eq_list));
-
- } else if (rec->rec_type == LNET_COOKIE_TYPE_MD) {
+ if (rec->rec_type == LNET_COOKIE_TYPE_MD) {
lnet_md_free(list_entry(e, struct lnet_libmd, md_list));
} else { /* NB: Active MEs should be attached on portals */
}
if (rec->rec_lh_hash != NULL) {
- LIBCFS_FREE(rec->rec_lh_hash,
- LNET_LH_HASH_SIZE * sizeof(rec->rec_lh_hash[0]));
+ CFS_FREE_PTR_ARRAY(rec->rec_lh_hash, LNET_LH_HASH_SIZE);
rec->rec_lh_hash = NULL;
}
list_add(&lh->lh_hash_chain, &rec->rec_lh_hash[hash]);
}
+struct list_head **
+lnet_create_array_of_queues(void)
+{
+ struct list_head **qs;
+ struct list_head *q;
+ int i;
+
+ qs = cfs_percpt_alloc(lnet_cpt_table(),
+ sizeof(struct list_head));
+ if (!qs) {
+ CERROR("Failed to allocate queues\n");
+ return NULL;
+ }
+
+ cfs_percpt_for_each(q, i, qs)
+ INIT_LIST_HEAD(q);
+
+ return qs;
+}
+
static int lnet_unprepare(void);
static int
INIT_LIST_HEAD(&the_lnet.ln_routers);
INIT_LIST_HEAD(&the_lnet.ln_drop_rules);
INIT_LIST_HEAD(&the_lnet.ln_delay_rules);
-
- rc = lnet_descriptor_setup();
+ 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);
+ the_lnet.ln_mt_handler = NULL;
+ init_completion(&the_lnet.ln_started);
+
+ rc = lnet_slab_setup();
if (rc != 0)
goto failed;
if (rc != 0)
goto failed;
- recs = lnet_res_containers_create(LNET_COOKIE_TYPE_ME);
- if (recs == NULL) {
- rc = -ENOMEM;
- goto failed;
- }
-
- the_lnet.ln_me_containers = recs;
-
recs = lnet_res_containers_create(LNET_COOKIE_TYPE_MD);
if (recs == NULL) {
rc = -ENOMEM;
goto failed;
}
+ the_lnet.ln_mt_zombie_rstqs = lnet_create_array_of_queues();
+ if (!the_lnet.ln_mt_zombie_rstqs) {
+ rc = -ENOMEM;
+ goto failed;
+ }
+
return 0;
failed:
LASSERT(list_empty(&the_lnet.ln_test_peers));
LASSERT(list_empty(&the_lnet.ln_nets));
+ if (the_lnet.ln_mt_zombie_rstqs) {
+ lnet_clean_zombie_rstqs();
+ the_lnet.ln_mt_zombie_rstqs = NULL;
+ }
+
+ lnet_assert_handler_unused(the_lnet.ln_mt_handler);
+ the_lnet.ln_mt_handler = NULL;
+
lnet_portals_destroy();
if (the_lnet.ln_md_containers != NULL) {
the_lnet.ln_md_containers = NULL;
}
- if (the_lnet.ln_me_containers != NULL) {
- lnet_res_containers_destroy(the_lnet.ln_me_containers);
- the_lnet.ln_me_containers = NULL;
- }
-
lnet_res_container_cleanup(&the_lnet.ln_eq_container);
lnet_msg_containers_destroy();
the_lnet.ln_counters = NULL;
}
lnet_destroy_remote_nets_table();
- lnet_descriptor_cleanup();
+ lnet_slab_cleanup();
return 0;
}
EXPORT_SYMBOL(lnet_cpt_of_nid);
int
-lnet_islocalnet(__u32 net_id)
+lnet_islocalnet_locked(__u32 net_id)
{
struct lnet_net *net;
- int cpt;
- bool local;
-
- cpt = lnet_net_lock_current();
+ bool local;
net = lnet_get_net_locked(net_id);
local = net != NULL;
- lnet_net_unlock(cpt);
-
return local;
}
-bool
-lnet_is_ni_healthy_locked(struct lnet_ni *ni)
+int
+lnet_islocalnet(__u32 net_id)
{
- if (ni->ni_state == LNET_NI_STATE_ACTIVE ||
- ni->ni_state == LNET_NI_STATE_DEGRADED)
- return true;
+ int cpt;
+ bool local;
- return false;
+ cpt = lnet_net_lock_current();
+
+ local = lnet_islocalnet_locked(net_id);
+
+ lnet_net_unlock(cpt);
+
+ return local;
}
struct lnet_ni *
LIBCFS_ALLOC_GFP(pbuf, LNET_PING_BUFFER_SIZE(nnis), gfp);
if (pbuf) {
pbuf->pb_nnis = nnis;
+ pbuf->pb_needs_post = false;
atomic_set(&pbuf->pb_refcnt, 1);
}
void
lnet_ping_buffer_free(struct lnet_ping_buffer *pbuf)
{
- LASSERT(lnet_ping_buffer_numref(pbuf) == 0);
+ LASSERT(atomic_read(&pbuf->pb_refcnt) == 0);
LIBCFS_FREE(pbuf, LNET_PING_BUFFER_SIZE(pbuf->pb_nnis));
}
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;
}
}
int
+lnet_get_net_count(void)
+{
+ struct lnet_net *net;
+ int count = 0;
+
+ lnet_net_lock(0);
+
+ list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
+ count++;
+ }
+
+ lnet_net_unlock(0);
+
+ return count;
+}
+
+void
+lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf)
+{
+ struct lnet_ni_status *stat;
+ int nnis;
+ int i;
+
+ __swab32s(&pbuf->pb_info.pi_magic);
+ __swab32s(&pbuf->pb_info.pi_features);
+ __swab32s(&pbuf->pb_info.pi_pid);
+ __swab32s(&pbuf->pb_info.pi_nnis);
+ nnis = pbuf->pb_info.pi_nnis;
+ if (nnis > pbuf->pb_nnis)
+ nnis = pbuf->pb_nnis;
+ for (i = 0; i < nnis; i++) {
+ stat = &pbuf->pb_info.pi_ni[i];
+ __swab64s(&stat->ns_nid);
+ __swab32s(&stat->ns_status);
+ }
+}
+
+int
lnet_ping_info_validate(struct lnet_ping_info *pinfo)
{
if (!pinfo)
/* Loopback is guaranteed to be present */
if (pinfo->pi_nnis < 1 || pinfo->pi_nnis > lnet_interfaces_max)
return -ERANGE;
- if (LNET_NETTYP(LNET_NIDNET(LNET_PING_INFO_LONI(pinfo))) != LOLND)
+ if (LNET_PING_INFO_LONI(pinfo) != LNET_NID_LO_0)
return -EPROTO;
return 0;
}
static void
lnet_ping_target_event_handler(struct lnet_event *event)
{
- struct lnet_ping_buffer *pbuf = event->md.user_ptr;
+ struct lnet_ping_buffer *pbuf = event->md_user_ptr;
if (event->unlinked)
lnet_ping_buffer_decref(pbuf);
.nid = LNET_NID_ANY,
.pid = LNET_PID_ANY
};
- struct lnet_handle_me me_handle;
+ struct lnet_me *me;
struct lnet_md md = { NULL };
- int rc, rc2;
+ int rc;
- if (set_eq) {
- rc = LNetEQAlloc(0, lnet_ping_target_event_handler,
- &the_lnet.ln_ping_target_eq);
- if (rc != 0) {
- CERROR("Can't allocate ping buffer EQ: %d\n", rc);
- return rc;
- }
- }
+ if (set_eq)
+ the_lnet.ln_ping_target_handler =
+ lnet_ping_target_event_handler;
*ppbuf = lnet_ping_target_create(ni_count);
if (*ppbuf == NULL) {
}
/* Ping target ME/MD */
- rc = LNetMEAttach(LNET_RESERVED_PORTAL, id,
+ me = LNetMEAttach(LNET_RESERVED_PORTAL, id,
LNET_PROTO_PING_MATCHBITS, 0,
- LNET_UNLINK, LNET_INS_AFTER,
- &me_handle);
- if (rc != 0) {
+ LNET_UNLINK, LNET_INS_AFTER);
+ if (IS_ERR(me)) {
+ rc = PTR_ERR(me);
CERROR("Can't create ping target ME: %d\n", rc);
goto fail_decref_ping_buffer;
}
md.max_size = 0;
md.options = LNET_MD_OP_GET | LNET_MD_TRUNCATE |
LNET_MD_MANAGE_REMOTE;
- md.eq_handle = the_lnet.ln_ping_target_eq;
+ md.handler = the_lnet.ln_ping_target_handler;
md.user_ptr = *ppbuf;
- rc = LNetMDAttach(me_handle, md, LNET_RETAIN, ping_mdh);
+ rc = LNetMDAttach(me, &md, LNET_RETAIN, ping_mdh);
if (rc != 0) {
CERROR("Can't attach ping target MD: %d\n", rc);
goto fail_unlink_ping_me;
return 0;
fail_unlink_ping_me:
- rc2 = LNetMEUnlink(me_handle);
- LASSERT(rc2 == 0);
+ LNetMEUnlink(me);
fail_decref_ping_buffer:
- LASSERT(lnet_ping_buffer_numref(*ppbuf) == 1);
+ LASSERT(atomic_read(&(*ppbuf)->pb_refcnt) == 1);
lnet_ping_buffer_decref(*ppbuf);
*ppbuf = NULL;
fail_free_eq:
- if (set_eq) {
- rc2 = LNetEQFree(the_lnet.ln_ping_target_eq);
- LASSERT(rc2 == 0);
- }
return rc;
}
lnet_ping_md_unlink(struct lnet_ping_buffer *pbuf,
struct lnet_handle_md *ping_mdh)
{
- sigset_t blocked = cfs_block_allsigs();
-
LNetMDUnlink(*ping_mdh);
LNetInvalidateMDHandle(ping_mdh);
/* NB the MD could be busy; this just starts the unlink */
- while (lnet_ping_buffer_numref(pbuf) > 1) {
- CDEBUG(D_NET, "Still waiting for ping data MD to unlink\n");
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(cfs_time_seconds(1));
- }
-
- cfs_restore_sigs(blocked);
+ wait_var_event_warning(&pbuf->pb_refcnt,
+ atomic_read(&pbuf->pb_refcnt) <= 1,
+ "Still waiting for ping data MD to unlink\n");
}
static void
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
lnet_ping_target_fini(void)
{
- int rc;
-
lnet_ping_md_unlink(the_lnet.ln_ping_target,
&the_lnet.ln_ping_target_md);
- rc = LNetEQFree(the_lnet.ln_ping_target_eq);
+ lnet_assert_handler_unused(the_lnet.ln_ping_target_handler);
+ lnet_ping_target_destroy();
+}
+
+/* Resize the push target. */
+int lnet_push_target_resize(void)
+{
+ struct lnet_handle_md mdh;
+ struct lnet_handle_md old_mdh;
+ struct lnet_ping_buffer *pbuf;
+ struct lnet_ping_buffer *old_pbuf;
+ int nnis;
+ int rc;
+
+again:
+ nnis = the_lnet.ln_push_target_nnis;
+ if (nnis <= 0) {
+ CDEBUG(D_NET, "Invalid nnis %d\n", nnis);
+ return -EINVAL;
+ }
+
+ /* NB: lnet_ping_buffer_alloc() sets pbuf refcount to 1. That ref is
+ * dropped when we need to resize again (see "old_pbuf" below) or when
+ * LNet is shutdown (see lnet_push_target_fini())
+ */
+ pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS);
+ if (!pbuf) {
+ CDEBUG(D_NET, "Can't allocate pbuf for nnis %d\n", nnis);
+ return -ENOMEM;
+ }
+
+ rc = lnet_push_target_post(pbuf, &mdh);
+ if (rc) {
+ CDEBUG(D_NET, "Failed to post push target: %d\n", rc);
+ lnet_ping_buffer_decref(pbuf);
+ return rc;
+ }
+
+ lnet_net_lock(LNET_LOCK_EX);
+ old_pbuf = the_lnet.ln_push_target;
+ old_mdh = the_lnet.ln_push_target_md;
+ the_lnet.ln_push_target = pbuf;
+ the_lnet.ln_push_target_md = mdh;
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ if (old_pbuf) {
+ LNetMDUnlink(old_mdh);
+ /* Drop ref set by lnet_ping_buffer_alloc() */
+ lnet_ping_buffer_decref(old_pbuf);
+ }
+
+ /* Received another push or reply that requires a larger buffer */
+ if (nnis < the_lnet.ln_push_target_nnis)
+ goto again;
+
+ CDEBUG(D_NET, "nnis %d success\n", nnis);
+ return 0;
+}
+
+int lnet_push_target_post(struct lnet_ping_buffer *pbuf,
+ struct lnet_handle_md *mdhp)
+{
+ struct lnet_process_id id = { LNET_NID_ANY, LNET_PID_ANY };
+ struct lnet_md md = { NULL };
+ struct lnet_me *me;
+ int rc;
+
+ me = LNetMEAttach(LNET_RESERVED_PORTAL, id,
+ LNET_PROTO_PING_MATCHBITS, 0,
+ LNET_UNLINK, LNET_INS_AFTER);
+ if (IS_ERR(me)) {
+ rc = PTR_ERR(me);
+ CERROR("Can't create push target ME: %d\n", rc);
+ return rc;
+ }
+
+ pbuf->pb_needs_post = false;
+
+ /* This reference is dropped by lnet_push_target_event_handler() */
+ lnet_ping_buffer_addref(pbuf);
+
+ /* initialize md content */
+ md.start = &pbuf->pb_info;
+ md.length = LNET_PING_INFO_SIZE(pbuf->pb_nnis);
+ md.threshold = 1;
+ md.max_size = 0;
+ md.options = LNET_MD_OP_PUT | LNET_MD_TRUNCATE;
+ md.user_ptr = pbuf;
+ md.handler = the_lnet.ln_push_target_handler;
+
+ rc = LNetMDAttach(me, &md, LNET_UNLINK, mdhp);
+ if (rc) {
+ CERROR("Can't attach push MD: %d\n", rc);
+ LNetMEUnlink(me);
+ lnet_ping_buffer_decref(pbuf);
+ pbuf->pb_needs_post = true;
+ return rc;
+ }
+
+ CDEBUG(D_NET, "posted push target %p\n", pbuf);
+
+ return 0;
+}
+
+static void lnet_push_target_event_handler(struct lnet_event *ev)
+{
+ struct lnet_ping_buffer *pbuf = ev->md_user_ptr;
+
+ CDEBUG(D_NET, "type %d status %d unlinked %d\n", ev->type, ev->status,
+ ev->unlinked);
+
+ if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC))
+ lnet_swap_pinginfo(pbuf);
+
+ if (ev->type == LNET_EVENT_UNLINK) {
+ /* Drop ref added by lnet_push_target_post() */
+ lnet_ping_buffer_decref(pbuf);
+ return;
+ }
+
+ lnet_peer_push_event(ev);
+ if (ev->unlinked)
+ /* Drop ref added by lnet_push_target_post */
+ lnet_ping_buffer_decref(pbuf);
+}
+
+/* Initialize the push target. */
+static int lnet_push_target_init(void)
+{
+ int rc;
+
+ if (the_lnet.ln_push_target)
+ return -EALREADY;
+
+ the_lnet.ln_push_target_handler =
+ lnet_push_target_event_handler;
+
+ rc = LNetSetLazyPortal(LNET_RESERVED_PORTAL);
LASSERT(rc == 0);
- lnet_ping_target_destroy();
+ /* Start at the required minimum, we'll enlarge if required. */
+ the_lnet.ln_push_target_nnis = LNET_INTERFACES_MIN;
+
+ rc = lnet_push_target_resize();
+
+ if (rc) {
+ LNetClearLazyPortal(LNET_RESERVED_PORTAL);
+ the_lnet.ln_push_target_handler = NULL;
+ }
+
+ return rc;
+}
+
+/* Clean up the push target. */
+static void lnet_push_target_fini(void)
+{
+ if (!the_lnet.ln_push_target)
+ return;
+
+ /* Unlink and invalidate to prevent new references. */
+ LNetMDUnlink(the_lnet.ln_push_target_md);
+ LNetInvalidateMDHandle(&the_lnet.ln_push_target_md);
+
+ /* Wait for the unlink to complete. */
+ wait_var_event_warning(&the_lnet.ln_push_target->pb_refcnt,
+ atomic_read(&the_lnet.ln_push_target->pb_refcnt) <= 1,
+ "Still waiting for ping data MD to unlink\n");
+
+ /* Drop ref set by lnet_ping_buffer_alloc() */
+ lnet_ping_buffer_decref(the_lnet.ln_push_target);
+ the_lnet.ln_push_target = NULL;
+ the_lnet.ln_push_target_nnis = 0;
+
+ LNetClearLazyPortal(LNET_RESERVED_PORTAL);
+ lnet_assert_handler_unused(the_lnet.ln_push_target_handler);
+ the_lnet.ln_push_target_handler = NULL;
}
static int
static void
lnet_ni_unlink_locked(struct lnet_ni *ni)
{
- if (!list_empty(&ni->ni_cptlist)) {
- list_del_init(&ni->ni_cptlist);
- lnet_ni_decref_locked(ni, 0);
- }
-
/* move it to zombie list and nobody can find it anymore */
LASSERT(!list_empty(&ni->ni_netlist));
list_move(&ni->ni_netlist, &ni->ni_net->net_ni_zombie);
"Waiting for zombie LNI %s\n",
libcfs_nid2str(ni->ni_nid));
}
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(cfs_time_seconds(1));
+ schedule_timeout_uninterruptible(cfs_time_seconds(1));
lnet_net_lock(LNET_LOCK_EX);
continue;
}
islo = ni->ni_net->net_lnd->lnd_type == LOLND;
LASSERT(!in_interrupt());
+ /* Holding the mutex makes it safe for lnd_shutdown
+ * to call module_put(). Module unload cannot finish
+ * until lnet_unregister_lnd() completes, and that
+ * requires the mutex.
+ */
+ mutex_lock(&the_lnet.ln_lnd_mutex);
(net->net_lnd->lnd_shutdown)(ni);
+ mutex_unlock(&the_lnet.ln_lnd_mutex);
if (!islo)
CDEBUG(D_LNI, "Removed LNI %s\n",
struct lnet_net *net = ni->ni_net;
lnet_net_lock(LNET_LOCK_EX);
+ lnet_ni_lock(ni);
ni->ni_state = LNET_NI_STATE_DELETING;
+ lnet_ni_unlock(ni);
lnet_ni_unlink_locked(ni);
lnet_incr_dlc_seq();
lnet_net_unlock(LNET_LOCK_EX);
lnet_net_lock(LNET_LOCK_EX);
- net->net_state = LNET_NET_STATE_DELETING;
-
list_del_init(&net->net_list);
while (!list_empty(&net->net_ni_list)) {
/* Do peer table cleanup for this net */
lnet_peer_tables_cleanup(net);
- lnet_net_lock(LNET_LOCK_EX);
- /*
- * decrement ref count on lnd only when the entire network goes
- * away
- */
- net->net_lnd->lnd_refcount--;
-
- lnet_net_unlock(LNET_LOCK_EX);
-
lnet_net_free(net);
}
lnet_shutdown_lndnets(void)
{
struct lnet_net *net;
+ LIST_HEAD(resend);
+ struct lnet_msg *msg, *tmp;
/* NB called holding the global mutex */
lnet_net_lock(LNET_LOCK_EX);
the_lnet.ln_state = LNET_STATE_STOPPING;
- while (!list_empty(&the_lnet.ln_nets)) {
- /*
- * move the nets to the zombie list to avoid them being
- * picked up for new work. LONET is also included in the
- * Nets that will be moved to the zombie list
- */
- net = list_entry(the_lnet.ln_nets.next,
- struct lnet_net, net_list);
- list_move(&net->net_list, &the_lnet.ln_net_zombie);
- }
+ /*
+ * move the nets to the zombie list to avoid them being
+ * picked up for new work. LONET is also included in the
+ * Nets that will be moved to the zombie list
+ */
+ list_splice_init(&the_lnet.ln_nets, &the_lnet.ln_net_zombie);
/* Drop the cached loopback Net. */
if (the_lnet.ln_loni != NULL) {
lnet_shutdown_lndnet(net);
}
+ 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);
+ msg->msg_no_resend = true;
+ lnet_finalize(msg, -ECANCELED);
+ }
+
lnet_net_lock(LNET_LOCK_EX);
the_lnet.ln_state = LNET_STATE_SHUTDOWN;
lnet_net_unlock(LNET_LOCK_EX);
if (rc != 0) {
LCONSOLE_ERROR_MSG(0x105, "Error %d starting up LNI %s\n",
rc, libcfs_lnd2str(net->net_lnd->lnd_type));
- lnet_net_lock(LNET_LOCK_EX);
- net->net_lnd->lnd_refcount--;
- lnet_net_unlock(LNET_LOCK_EX);
goto failed0;
}
+ lnet_ni_lock(ni);
ni->ni_state = LNET_NI_STATE_ACTIVE;
+ 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),
lnet_startup_lndnet(struct lnet_net *net, struct lnet_lnd_tunables *tun)
{
struct lnet_ni *ni;
- struct lnet_net *net_l = NULL;
- struct list_head local_ni_list;
- int rc;
- int ni_count = 0;
- __u32 lnd_type;
- struct lnet_lnd *lnd;
- int peer_timeout =
+ struct lnet_net *net_l = NULL;
+ LIST_HEAD(local_ni_list);
+ int rc;
+ int ni_count = 0;
+ __u32 lnd_type;
+ const struct lnet_lnd *lnd;
+ int peer_timeout =
net->net_tunables.lct_peer_timeout;
- int maxtxcredits =
+ int maxtxcredits =
net->net_tunables.lct_max_tx_credits;
- int peerrtrcredits =
+ int peerrtrcredits =
net->net_tunables.lct_peer_rtr_credits;
- INIT_LIST_HEAD(&local_ni_list);
-
/*
* make sure that this net is unique. If it isn't then
* we are adding interfaces to an already existing network, and
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_net_lock(LNET_LOCK_EX);
- lnd->lnd_refcount++;
- lnet_net_unlock(LNET_LOCK_EX);
-
net->net_lnd = lnd;
mutex_unlock(&the_lnet.ln_lnd_mutex);
* up is actually unique. if it's not fail. */
if (!lnet_ni_unique_net(&net_l->net_ni_list,
ni->ni_interfaces[0])) {
- rc = -EINVAL;
+ rc = -EEXIST;
goto failed1;
}
rc = lnet_startup_lndni(ni, tun);
- LASSERT(ni->ni_net->net_tunables.lct_peer_timeout <= 0 ||
- ni->ni_net->net_lnd->lnd_query != NULL);
-
if (rc < 0)
goto failed1;
*/
lnet_net_free(net);
} else {
- net->net_state = LNET_NET_STATE_ACTIVE;
/*
* restore tunables after it has been overwitten by the
* lnd
lnet_net_unlock(LNET_LOCK_EX);
}
+ /* update net count */
+ lnet_current_net_count = lnet_get_net_count();
+
return ni_count;
failed1:
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);
+ the_lnet.ln_cpt_table = cfs_cpt_tab;
+ the_lnet.ln_cpt_number = cfs_cpt_number(cfs_cpt_tab);
LASSERT(the_lnet.ln_cpt_number > 0);
if (the_lnet.ln_cpt_number > LNET_CPT_MAX) {
}
the_lnet.ln_refcount = 0;
- LNetInvalidateEQHandle(&the_lnet.ln_rc_eqh);
- INIT_LIST_HEAD(&the_lnet.ln_lnds);
INIT_LIST_HEAD(&the_lnet.ln_net_zombie);
- INIT_LIST_HEAD(&the_lnet.ln_rcd_zombie);
- INIT_LIST_HEAD(&the_lnet.ln_rcd_deathrow);
+ INIT_LIST_HEAD(&the_lnet.ln_msg_resend);
/* The hash table size is the number of bits it takes to express the set
* ln_num_routes, minus 1 (better to under estimate than over so we
*
* \pre lnet_lib_init() called with success.
* \pre All LNet users called LNetNIFini() for matching LNetNIInit() calls.
+ *
+ * As this happens at module-unload, all lnds must already be unloaded,
+ * so they must already be unregistered.
*/
void lnet_lib_exit(void)
{
- LASSERT(the_lnet.ln_refcount == 0);
+ int i;
- while (!list_empty(&the_lnet.ln_lnds))
- lnet_unregister_lnd(list_entry(the_lnet.ln_lnds.next,
- struct lnet_lnd, lnd_list));
+ LASSERT(the_lnet.ln_refcount == 0);
+ lnet_unregister_lnd(&the_lolnd);
+ for (i = 0; i < NUM_LNDS; i++)
+ LASSERT(!the_lnet.ln_lnds[i]);
lnet_destroy_locks();
}
int ni_count;
struct lnet_ping_buffer *pbuf;
struct lnet_handle_md ping_mdh;
- struct list_head net_head;
+ LIST_HEAD(net_head);
struct lnet_net *net;
- INIT_LIST_HEAD(&net_head);
-
mutex_lock(&the_lnet.ln_api_mutex);
CDEBUG(D_OTHER, "refs %d\n", the_lnet.ln_refcount);
if (rc != 0)
goto err_shutdown_lndnis;
- rc = lnet_check_routes();
- if (rc != 0)
- goto err_destroy_routes;
-
rc = lnet_rtrpools_alloc(im_a_router);
if (rc != 0)
goto err_destroy_routes;
lnet_ping_target_update(pbuf, ping_mdh);
- rc = lnet_router_checker_start();
+ the_lnet.ln_mt_handler = lnet_mt_event_handler;
+
+ rc = lnet_push_target_init();
if (rc != 0)
goto err_stop_ping;
rc = lnet_peer_discovery_start();
if (rc != 0)
- goto err_stop_router_checker;
+ goto err_destroy_push_target;
+
+ rc = lnet_monitor_thr_start();
+ if (rc != 0)
+ goto err_stop_discovery_thr;
lnet_fault_init();
- lnet_proc_init();
+ lnet_router_debugfs_init();
mutex_unlock(&the_lnet.ln_api_mutex);
+ complete_all(&the_lnet.ln_started);
+
+ /* wait for all routers to start */
+ lnet_wait_router_start();
+
return 0;
-err_stop_router_checker:
- lnet_router_checker_stop();
+err_stop_discovery_thr:
+ lnet_peer_discovery_stop();
+err_destroy_push_target:
+ lnet_push_target_fini();
err_stop_ping:
lnet_ping_target_fini();
err_acceptor_stop:
* \return always 0 for current implementation.
*/
int
-LNetNIFini()
+LNetNIFini(void)
{
mutex_lock(&the_lnet.ln_api_mutex);
lnet_fault_fini();
- lnet_proc_fini();
+ lnet_router_debugfs_fini();
+ lnet_monitor_thr_stop();
lnet_peer_discovery_stop();
- lnet_router_checker_stop();
+ lnet_push_target_fini();
lnet_ping_target_fini();
/* Teardown fns that use my own API functions BEFORE here */
}
cfg_ni->lic_nid = ni->ni_nid;
- if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND)
+ if (ni->ni_nid == LNET_NID_LO_0)
cfg_ni->lic_status = LNET_NI_STATUS_UP;
else
cfg_ni->lic_status = ni->ni_status->ns_status;
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);
}
/*
config->cfg_config_u.cfg_net.net_peer_rtr_credits =
ni->ni_net->net_tunables.lct_peer_rtr_credits;
- if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND)
+ if (ni->ni_nid == LNET_NID_LO_0)
net_config->ni_status = LNET_NI_STATUS_UP;
else
net_config->ni_status = ni->ni_status->ns_status;
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);
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)
{
int rc;
struct lnet_remotenet *rnet;
int net_ni_count;
- int num_acceptor_nets;
lnet_net_lock(LNET_LOCK_EX);
rnet = lnet_find_rnet_locked(net->net_id);
else
memset(&net->net_tunables, -1, sizeof(net->net_tunables));
- /*
- * before starting this network get a count of the current TCP
- * networks which require the acceptor thread running. If that
- * count is == 0 before we start up this network, then we'd want to
- * start up the acceptor thread after starting up this network
- */
- num_acceptor_nets = lnet_count_acceptor_nets();
-
net_id = net->net_id;
rc = lnet_startup_lndnet(net,
* Start the acceptor thread if this is the first network
* being added that requires the thread.
*/
- if (net->net_lnd->lnd_accept && num_acceptor_nets == 0) {
+ if (net->net_lnd->lnd_accept) {
rc = lnet_acceptor_start();
if (rc < 0) {
/* shutdown the net that we just started */
struct lnet_ioctl_config_lnd_tunables *tun)
{
struct lnet_net *net;
- char *nets;
+ const char *nets;
int rc;
- struct list_head net_head;
-
- INIT_LIST_HEAD(&net_head);
+ LIST_HEAD(net_head);
rc = lnet_parse_ip2nets(&nets, ip2nets);
if (rc < 0)
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)
lnet_shutdown_lndnet(net);
- if (lnet_count_acceptor_nets() == 0)
- lnet_acceptor_stop();
+ lnet_acceptor_stop();
lnet_ping_target_update(pbuf, ping_mdh);
lnet_shutdown_lndni(ni);
- if (lnet_count_acceptor_nets() == 0)
- lnet_acceptor_stop();
+ lnet_acceptor_stop();
lnet_ping_target_update(pbuf, ping_mdh);
int
lnet_dyn_add_net(struct lnet_ioctl_config_data *conf)
{
- struct lnet_net *net;
- struct list_head net_head;
- int rc;
+ struct lnet_net *net;
+ LIST_HEAD(net_head);
+ int rc;
struct lnet_ioctl_config_lnd_tunables tun;
- char *nets = conf->cfg_config_u.cfg_net.net_intf;
-
- INIT_LIST_HEAD(&net_head);
+ const char *nets = conf->cfg_config_u.cfg_net.net_intf;
/* Create a net/ni structures for the network string */
rc = lnet_parse_networks(&net_head, nets, use_tcp_bonding);
lnet_shutdown_lndnet(net);
- if (lnet_count_acceptor_nets() == 0)
- lnet_acceptor_stop();
+ lnet_acceptor_stop();
lnet_ping_target_update(pbuf, ping_mdh);
return atomic_read(&lnet_dlc_seq_no);
}
+static void
+lnet_ni_set_healthv(lnet_nid_t nid, int value, bool all)
+{
+ struct lnet_net *net;
+ struct lnet_ni *ni;
+
+ lnet_net_lock(LNET_LOCK_EX);
+ list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
+ list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
+ if (ni->ni_nid == nid || all) {
+ atomic_set(&ni->ni_healthv, value);
+ if (list_empty(&ni->ni_recovery) &&
+ value < LNET_MAX_HEALTH_VALUE) {
+ CERROR("manually adding local NI %s to recovery\n",
+ libcfs_nid2str(ni->ni_nid));
+ list_add_tail(&ni->ni_recovery,
+ &the_lnet.ln_mt_localNIRecovq);
+ lnet_ni_addref_locked(ni, 0);
+ }
+ if (!all) {
+ lnet_net_unlock(LNET_LOCK_EX);
+ return;
+ }
+ }
+ }
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
+static int
+lnet_get_local_ni_hstats(struct lnet_ioctl_local_ni_hstats *stats)
+{
+ int cpt, rc = 0;
+ struct lnet_ni *ni;
+ lnet_nid_t nid = stats->hlni_nid;
+
+ cpt = lnet_net_lock_current();
+ ni = lnet_nid2ni_locked(nid, cpt);
+
+ if (!ni) {
+ rc = -ENOENT;
+ goto unlock;
+ }
+
+ stats->hlni_local_interrupt = atomic_read(&ni->ni_hstats.hlt_local_interrupt);
+ stats->hlni_local_dropped = atomic_read(&ni->ni_hstats.hlt_local_dropped);
+ stats->hlni_local_aborted = atomic_read(&ni->ni_hstats.hlt_local_aborted);
+ stats->hlni_local_no_route = atomic_read(&ni->ni_hstats.hlt_local_no_route);
+ stats->hlni_local_timeout = atomic_read(&ni->ni_hstats.hlt_local_timeout);
+ stats->hlni_local_error = atomic_read(&ni->ni_hstats.hlt_local_error);
+ stats->hlni_health_value = atomic_read(&ni->ni_healthv);
+
+unlock:
+ lnet_net_unlock(cpt);
+
+ return rc;
+}
+
+static int
+lnet_get_local_ni_recovery_list(struct lnet_ioctl_recovery_list *list)
+{
+ struct lnet_ni *ni;
+ int i = 0;
+
+ lnet_net_lock(LNET_LOCK_EX);
+ list_for_each_entry(ni, &the_lnet.ln_mt_localNIRecovq, ni_recovery) {
+ list->rlst_nid_array[i] = ni->ni_nid;
+ i++;
+ if (i >= LNET_MAX_SHOW_NUM_NID)
+ break;
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+ list->rlst_num_nids = i;
+
+ return 0;
+}
+
+static int
+lnet_get_peer_ni_recovery_list(struct lnet_ioctl_recovery_list *list)
+{
+ struct lnet_peer_ni *lpni;
+ int i = 0;
+
+ lnet_net_lock(LNET_LOCK_EX);
+ list_for_each_entry(lpni, &the_lnet.ln_mt_peerNIRecovq, lpni_recovery) {
+ list->rlst_nid_array[i] = lpni->lpni_nid;
+ i++;
+ if (i >= LNET_MAX_SHOW_NUM_NID)
+ break;
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+ list->rlst_num_nids = i;
+
+ return 0;
+}
+
/**
* LNet ioctl handler.
*
case IOC_LIBCFS_FAIL_NID:
return lnet_fail_nid(data->ioc_nid, data->ioc_count);
- case IOC_LIBCFS_ADD_ROUTE:
+ case IOC_LIBCFS_ADD_ROUTE: {
+ /* default router sensitivity to 1 */
+ unsigned int sensitivity = 1;
config = arg;
if (config->cfg_hdr.ioc_len < sizeof(*config))
return -EINVAL;
+ if (config->cfg_config_u.cfg_route.rtr_sensitivity) {
+ sensitivity =
+ config->cfg_config_u.cfg_route.rtr_sensitivity;
+ }
+
mutex_lock(&the_lnet.ln_api_mutex);
rc = lnet_add_route(config->cfg_net,
config->cfg_config_u.cfg_route.rtr_hop,
config->cfg_nid,
config->cfg_config_u.cfg_route.
- rtr_priority);
- if (rc == 0) {
- rc = lnet_check_routes();
- if (rc != 0)
- lnet_del_route(config->cfg_net,
- config->cfg_nid);
- }
+ rtr_priority, sensitivity);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
+ }
case IOC_LIBCFS_DEL_ROUTE:
config = arg;
&config->cfg_nid,
&config->cfg_config_u.cfg_route.rtr_flags,
&config->cfg_config_u.cfg_route.
- rtr_priority);
+ rtr_priority,
+ &config->cfg_config_u.cfg_route.
+ rtr_sensitivity);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
__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);
return rc;
}
+ case IOC_LIBCFS_GET_LOCAL_HSTATS: {
+ struct lnet_ioctl_local_ni_hstats *stats = arg;
+
+ if (stats->hlni_hdr.ioc_len < sizeof(*stats))
+ return -EINVAL;
+
+ mutex_lock(&the_lnet.ln_api_mutex);
+ rc = lnet_get_local_ni_hstats(stats);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ return rc;
+ }
+
+ case IOC_LIBCFS_GET_RECOVERY_QUEUE: {
+ struct lnet_ioctl_recovery_list *list = arg;
+ if (list->rlst_hdr.ioc_len < sizeof(*list))
+ return -EINVAL;
+
+ mutex_lock(&the_lnet.ln_api_mutex);
+ if (list->rlst_type == LNET_HEALTH_TYPE_LOCAL_NI)
+ rc = lnet_get_local_ni_recovery_list(list);
+ else
+ rc = lnet_get_peer_ni_recovery_list(list);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return rc;
+ }
+
case IOC_LIBCFS_ADD_PEER_NI: {
struct lnet_ioctl_peer_cfg *cfg = arg;
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,
+ (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,
+ (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;
+ case IOC_LIBCFS_SET_HEALHV: {
+ struct lnet_ioctl_reset_health_cfg *cfg = arg;
+ int value;
+ if (cfg->rh_hdr.ioc_len < sizeof(*cfg))
+ return -EINVAL;
+ if (cfg->rh_value < 0 ||
+ cfg->rh_value > LNET_MAX_HEALTH_VALUE)
+ value = LNET_MAX_HEALTH_VALUE;
+ else
+ value = cfg->rh_value;
+ CDEBUG(D_NET, "Manually setting healthv to %d for %s:%s. all = %d\n",
+ value, (cfg->rh_type == LNET_HEALTH_TYPE_LOCAL_NI) ?
+ "local" : "peer", libcfs_nid2str(cfg->rh_nid), cfg->rh_all);
+ mutex_lock(&the_lnet.ln_api_mutex);
+ if (cfg->rh_type == LNET_HEALTH_TYPE_LOCAL_NI)
+ lnet_ni_set_healthv(cfg->rh_nid, value,
+ cfg->rh_all);
+ else
+ lnet_peer_ni_set_healthv(cfg->rh_nid, value,
+ cfg->rh_all);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+ return 0;
+ }
- jiffies_passed = ktime_get_real_seconds() - data->ioc_u64[0];
- jiffies_passed = cfs_time_seconds(jiffies_passed);
+ case IOC_LIBCFS_NOTIFY_ROUTER: {
+ time64_t deadline = ktime_get_real_seconds() - data->ioc_u64[0];
- return lnet_notify(NULL, data->ioc_nid, data->ioc_flags,
- jiffies - jiffies_passed);
+ /* 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, false,
+ deadline);
}
case IOC_LIBCFS_LNET_DIST:
return 0;
case IOC_LIBCFS_TESTPROTOCOMPAT:
- lnet_net_lock(LNET_LOCK_EX);
the_lnet.ln_testprotocompat = data->ioc_flags;
- lnet_net_unlock(LNET_LOCK_EX);
return 0;
case IOC_LIBCFS_LNET_FAULT:
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 = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
else
- timeout = msecs_to_jiffies(data->ioc_u32[1]);
+ timeout = nsecs_to_jiffies(data->ioc_u32[1] * NSEC_PER_MSEC);
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 = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
+ else
+ timeout = nsecs_to_jiffies(ping->op_param * NSEC_PER_MSEC);
+
+ rc = lnet_ping(ping->ping_id, timeout,
+ ping->ping_buf,
+ ping->ping_count);
+ if (rc < 0)
+ return rc;
+
+ mutex_lock(&the_lnet.ln_api_mutex);
+ 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);
+ lnet_peer_decref_locked(lp);
+ }
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ 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;
+
+ mutex_lock(&the_lnet.ln_api_mutex);
+ 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);
+ lnet_peer_decref_locked(lp);
+ }
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
+ discover->ping_count = rc;
+ return 0;
+ }
+
default:
ni = lnet_net2ni_addref(data->ioc_net);
if (ni == NULL)
}
EXPORT_SYMBOL(LNetGetId);
+struct ping_data {
+ int rc;
+ int replied;
+ struct lnet_handle_md mdh;
+ struct completion completion;
+};
+
+static void
+lnet_ping_event_handler(struct lnet_event *event)
+{
+ struct ping_data *pd = event->md_user_ptr;
+
+ CDEBUG(D_NET, "ping event (%d %d)%s\n",
+ event->type, event->status,
+ event->unlinked ? " unlinked" : "");
+
+ if (event->status) {
+ if (!pd->rc)
+ pd->rc = event->status;
+ } else if (event->type == LNET_EVENT_REPLY) {
+ pd->replied = 1;
+ pd->rc = event->mlength;
+ }
+ if (event->unlinked)
+ complete(&pd->completion);
+}
+
static int lnet_ping(struct lnet_process_id id, signed long timeout,
struct lnet_process_id __user *ids, int n_ids)
{
- struct lnet_handle_eq eqh;
- struct lnet_handle_md mdh;
- struct lnet_event event;
struct lnet_md md = { NULL };
- int which;
- int unlinked = 0;
- int replied = 0;
- const signed long a_long_time = msecs_to_jiffies(60 * MSEC_PER_SEC);
+ struct ping_data pd = { 0 };
struct lnet_ping_buffer *pbuf;
struct lnet_process_id tmpid;
int i;
int nob;
int rc;
int rc2;
- sigset_t blocked;
/* n_ids limit is arbitrary */
- if (n_ids <= 0 || n_ids > lnet_interfaces_max || id.nid == LNET_NID_ANY)
+ if (n_ids <= 0 || id.nid == LNET_NID_ANY)
return -EINVAL;
+ /*
+ * if the user buffer has more space than the lnet_interfaces_max
+ * then only fill it up to lnet_interfaces_max
+ */
+ if (n_ids > lnet_interfaces_max)
+ n_ids = lnet_interfaces_max;
+
if (id.pid == LNET_PID_ANY)
id.pid = LNET_PID_LUSTRE;
if (!pbuf)
return -ENOMEM;
- /* NB 2 events max (including any unlink event) */
- rc = LNetEQAlloc(2, LNET_EQ_HANDLER_NONE, &eqh);
- if (rc != 0) {
- CERROR("Can't allocate EQ: %d\n", rc);
- goto fail_ping_buffer_decref;
- }
-
/* 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;
- md.eq_handle = eqh;
+ md.user_ptr = &pd;
+ md.handler = lnet_ping_event_handler;
+
+ init_completion(&pd.completion);
- rc = LNetMDBind(md, LNET_UNLINK, &mdh);
+ rc = LNetMDBind(&md, LNET_UNLINK, &pd.mdh);
if (rc != 0) {
CERROR("Can't bind MD: %d\n", rc);
- goto fail_free_eq;
+ goto fail_ping_buffer_decref;
}
- rc = LNetGet(LNET_NID_ANY, mdh, id,
+ rc = LNetGet(LNET_NID_ANY, pd.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! */
-
- rc2 = LNetMDUnlink(mdh);
+ rc2 = LNetMDUnlink(pd.mdh);
LASSERT(rc2 == 0);
/* NB must wait for the UNLINK event below... */
- unlinked = 1;
- timeout = a_long_time;
- }
-
- do {
- /* MUST block for unlink to complete */
- if (unlinked)
- blocked = cfs_block_allsigs();
-
- rc2 = LNetEQPoll(&eqh, 1, timeout, &event, &which);
-
- if (unlinked)
- cfs_restore_sigs(blocked);
-
- CDEBUG(D_NET, "poll %d(%d %d)%s\n", rc2,
- (rc2 <= 0) ? -1 : event.type,
- (rc2 <= 0) ? -1 : event.status,
- (rc2 > 0 && event.unlinked) ? " unlinked" : "");
-
- LASSERT(rc2 != -EOVERFLOW); /* can't miss anything */
-
- if (rc2 <= 0 || event.status != 0) {
- /* timeout or error */
- if (!replied && rc == 0)
- rc = (rc2 < 0) ? rc2 :
- (rc2 == 0) ? -ETIMEDOUT :
- event.status;
-
- if (!unlinked) {
- /* Ensure completion in finite time... */
- LNetMDUnlink(mdh);
- /* No assertion (racing with network) */
- unlinked = 1;
- timeout = a_long_time;
- } else if (rc2 == 0) {
- /* timed out waiting for unlink */
- CWARN("ping %s: late network completion\n",
- libcfs_id2str(id));
- }
- } else if (event.type == LNET_EVENT_REPLY) {
- replied = 1;
- rc = event.mlength;
- }
-
- } while (rc2 <= 0 || !event.unlinked);
+ }
- if (!replied) {
- if (rc >= 0)
- CWARN("%s: Unexpected rc >= 0 but no reply!\n",
- libcfs_id2str(id));
+ if (wait_for_completion_timeout(&pd.completion, timeout) == 0) {
+ /* Ensure completion in finite time... */
+ LNetMDUnlink(pd.mdh);
+ wait_for_completion(&pd.completion);
+ }
+ if (!pd.replied) {
rc = -EIO;
- goto fail_free_eq;
+ goto fail_ping_buffer_decref;
}
- nob = rc;
+ nob = pd.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;
+ goto fail_ping_buffer_decref;
}
if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) {
} else if (pbuf->pb_info.pi_magic != LNET_PROTO_PING_MAGIC) {
CERROR("%s: Unexpected magic %08x\n",
libcfs_id2str(id), pbuf->pb_info.pi_magic);
- goto fail_free_eq;
+ goto fail_ping_buffer_decref;
}
if ((pbuf->pb_info.pi_features & LNET_PING_FEAT_NI_STATUS) == 0) {
CERROR("%s: ping w/o NI status: 0x%x\n",
libcfs_id2str(id), pbuf->pb_info.pi_features);
- goto fail_free_eq;
+ goto fail_ping_buffer_decref;
}
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;
+ goto fail_ping_buffer_decref;
}
if (pbuf->pb_info.pi_nnis < n_ids)
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;
+ goto fail_ping_buffer_decref;
}
- 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++) {
tmpid.pid = pbuf->pb_info.pi_pid;
tmpid.nid = pbuf->pb_info.pi_ni[i].ns_nid;
if (copy_to_user(&ids[i], &tmpid, sizeof(tmpid)))
- goto fail_free_eq;
+ goto fail_ping_buffer_decref;
}
rc = pbuf->pb_info.pi_nnis;
- fail_free_eq:
- rc2 = LNetEQFree(eqh);
- if (rc2 != 0)
- CERROR("rc2 %d\n", rc2);
- LASSERT(rc2 == 0);
-
fail_ping_buffer_decref:
lnet_ping_buffer_decref(pbuf);
return rc;
}
+
+static int
+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;
+ struct lnet_process_id *buf;
+ int cpt;
+ int i;
+ int rc;
+
+ if (n_ids <= 0 ||
+ id.nid == LNET_NID_ANY)
+ return -EINVAL;
+
+ if (id.pid == LNET_PID_ANY)
+ id.pid = LNET_PID_LUSTRE;
+
+ /*
+ * If the user buffer has more space than the lnet_interfaces_max,
+ * then only fill it up to lnet_interfaces_max.
+ */
+ if (n_ids > lnet_interfaces_max)
+ n_ids = lnet_interfaces_max;
+
+ CFS_ALLOC_PTR_ARRAY(buf, n_ids);
+ 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;
+
+ 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;
+ }
+ rc = i;
+
+out_decref:
+ lnet_peer_ni_decref_locked(lpni);
+out:
+ lnet_net_unlock(cpt);
+
+ if (rc >= 0)
+ if (copy_to_user(ids, buf, rc * sizeof(*buf)))
+ rc = -EFAULT;
+ CFS_FREE_PTR_ARRAY(buf, n_ids);
+
+ return rc;
+}
+
+/**
+ * Retrieve peer discovery status.
+ *
+ * \retval 1 if lnet_peer_discovery_disabled is 0
+ * \retval 0 if lnet_peer_discovery_disabled is 1
+ */
+int
+LNetGetPeerDiscoveryStatus(void)
+{
+ return !lnet_peer_discovery_disabled;
+}
+EXPORT_SYMBOL(LNetGetPeerDiscoveryStatus);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff