X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Flnet%2Fapi-ni.c;h=c08e929842b0b85d7a3961cb1ab4dad2dd1ae584;hp=8d318cd0d6aeca3e0a9db168b166326f9d9e16dd;hb=8cb7ccf54e2d34010bea9a71fe0eff708545ab78;hpb=362e52efec1a6f6fd43b16ccd555b714a30642da diff --git a/lnet/lnet/api-ni.c b/lnet/lnet/api-ni.c index 8d318cd..c08e929 100644 --- a/lnet/lnet/api-ni.c +++ b/lnet/lnet/api-ni.c @@ -23,7 +23,7 @@ * 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/ @@ -31,14 +31,25 @@ */ #define DEBUG_SUBSYSTEM S_LNET + +#include #include #include +#include +#include #include #define D_LNI D_CONSOLE -lnet_t 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 = ""; @@ -62,22 +73,440 @@ module_param(use_tcp_bonding, int, 0444); MODULE_PARM_DESC(use_tcp_bonding, "Set to 1 to use socklnd bonding. 0 to use Multi-Rail"); -static __u32 lnet_numa_range = 0; -module_param(lnet_numa_range, int, 0444); +unsigned int lnet_numa_range = 0; +module_param(lnet_numa_range, uint, 0444); 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); +#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, 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, + ¶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, 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, + ¶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."); + +unsigned lnet_transaction_timeout = 50; +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."); + +unsigned lnet_retry_count = 0; +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"); + + +unsigned lnet_lnd_timeout = LNET_LND_DEFAULT_TIMEOUT; + +/* * This sequence number keeps track of how many times DLC was used to - * update the configuration. It is incremented on any DLC update and - * checked when sending a message to determine if there is a need to - * re-run the selection algorithm to handle configuration change. - * Look at lnet_select_pathway() for more details on its usage. + * update the local NIs. It is incremented when a NI is added or + * removed and checked when sending a message to determine if there is + * a need to re-run the selection algorithm. See lnet_select_pathway() + * for more details on its usage. */ static atomic_t lnet_dlc_seq_no = ATOMIC_INIT(0); -static int lnet_ping(lnet_process_id_t id, signed long timeout, - lnet_process_id_t __user *ids, int n_ids); +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 (the_lnet.ln_state != LNET_STATE_RUNNING) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + 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; + } + + *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); + + if (the_lnet.ln_state != LNET_STATE_RUNNING) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + *interval = value; + + mutex_unlock(&the_lnet.ln_api_mutex); + + return 0; +} + +static int +discovery_set(const char *val, cfs_kernel_param_arg_t *kp) +{ + int rc; + unsigned *discovery = (unsigned *)kp->arg; + unsigned long value; + struct lnet_ping_buffer *pbuf; + + rc = kstrtoul(val, 0, &value); + if (rc) { + CERROR("Invalid module parameter value for 'lnet_peer_discovery_disabled'\n"); + return rc; + } + + 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; +} + +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 (the_lnet.ln_state != LNET_STATE_RUNNING) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + 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; + if (lnet_retry_count == 0) + lnet_lnd_timeout = value; + else + lnet_lnd_timeout = value / lnet_retry_count; + + 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 (the_lnet.ln_state != LNET_STATE_RUNNING) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + 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; + } + + if (value == *retry_count) { + mutex_unlock(&the_lnet.ln_api_mutex); + return 0; + } + + *retry_count = value; + + if (value == 0) + lnet_lnd_timeout = lnet_transaction_timeout; + else + lnet_lnd_timeout = lnet_transaction_timeout / value; + + mutex_unlock(&the_lnet.ln_api_mutex); + + return 0; +} + +static int +intf_max_set(const char *val, cfs_kernel_param_arg_t *kp) +{ + int value, rc; + + rc = kstrtoint(val, 0, &value); + if (rc) { + CERROR("Invalid module parameter value for 'lnet_interfaces_max'\n"); + return rc; + } + + if (value < LNET_INTERFACES_MIN) { + CWARN("max interfaces provided are too small, setting to %d\n", + LNET_INTERFACES_MAX_DEFAULT); + value = LNET_INTERFACES_MAX_DEFAULT; + } + + *(int *)kp->arg = value; + + return 0; +} static char * lnet_get_routes(void) @@ -112,10 +541,10 @@ static void lnet_init_locks(void) { 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); - mutex_init(&the_lnet.ln_api_mutex); } static void @@ -133,7 +562,7 @@ lnet_descriptor_setup(void) /* create specific kmem_cache for MEs and small MDs (i.e., originally * allocated in kmem_cache). */ - lnet_mes_cachep = kmem_cache_create("lnet_MEs", sizeof(lnet_me_t), + lnet_mes_cachep = kmem_cache_create("lnet_MEs", sizeof(struct lnet_me), 0, 0, NULL); if (!lnet_mes_cachep) return -ENOMEM; @@ -259,83 +688,120 @@ static void lnet_assert_wire_constants(void) CLASSERT((int)offsetof(struct lnet_handle_wire, wh_object_cookie) == 8); CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) == 8); - /* Checks for struct lnet_magicversion_t */ - CLASSERT((int)sizeof(lnet_magicversion_t) == 8); - CLASSERT((int)offsetof(lnet_magicversion_t, magic) == 0); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->magic) == 4); - CLASSERT((int)offsetof(lnet_magicversion_t, version_major) == 4); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->version_major) == 2); - CLASSERT((int)offsetof(lnet_magicversion_t, version_minor) == 6); - CLASSERT((int)sizeof(((lnet_magicversion_t *)0)->version_minor) == 2); - - /* Checks for struct lnet_hdr_t */ - CLASSERT((int)sizeof(lnet_hdr_t) == 72); - CLASSERT((int)offsetof(lnet_hdr_t, dest_nid) == 0); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->dest_nid) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, src_nid) == 8); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->src_nid) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, dest_pid) == 16); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->dest_pid) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, src_pid) == 20); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->src_pid) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, type) == 24); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->type) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, payload_length) == 28); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->payload_length) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg) == 40); + /* 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); + + /* 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); /* Ack */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.dst_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.dst_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.ack.mlength) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.ack.mlength) == 4); + 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); /* Put */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.ack_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.ack_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.hdr_data) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.hdr_data) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.ptl_index) == 64); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.ptl_index) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.put.offset) == 68); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.put.offset) == 4); + 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); /* Get */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.return_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.return_wmd) == 16); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.match_bits) == 48); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.match_bits) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.ptl_index) == 56); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.ptl_index) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.src_offset) == 60); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.src_offset) == 4); - CLASSERT((int)offsetof(lnet_hdr_t, msg.get.sink_length) == 64); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.get.sink_length) == 4); + 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); /* Reply */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.reply.dst_wmd) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.reply.dst_wmd) == 16); + CLASSERT((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) == 32); + CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) == 16); /* Hello */ - CLASSERT((int)offsetof(lnet_hdr_t, msg.hello.incarnation) == 32); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.hello.incarnation) == 8); - CLASSERT((int)offsetof(lnet_hdr_t, msg.hello.type) == 40); - CLASSERT((int)sizeof(((lnet_hdr_t *)0)->msg.hello.type) == 4); + 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); + + /* 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); + + /* 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); + + /* 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); + + /* 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); } -static lnd_t *lnet_find_lnd_by_type(__u32 type) +static struct lnet_lnd *lnet_find_lnd_by_type(__u32 type) { - lnd_t *lnd; + struct lnet_lnd *lnd; struct list_head *tmp; /* holding lnd mutex */ list_for_each(tmp, &the_lnet.ln_lnds) { - lnd = list_entry(tmp, lnd_t, lnd_list); + lnd = list_entry(tmp, struct lnet_lnd, lnd_list); if (lnd->lnd_type == type) return lnd; @@ -343,8 +809,15 @@ static lnd_t *lnet_find_lnd_by_type(__u32 type) return NULL; } +unsigned int +lnet_get_lnd_timeout(void) +{ + return lnet_lnd_timeout; +} +EXPORT_SYMBOL(lnet_get_lnd_timeout); + void -lnet_register_lnd (lnd_t *lnd) +lnet_register_lnd(struct lnet_lnd *lnd) { mutex_lock(&the_lnet.ln_lnd_mutex); @@ -361,7 +834,7 @@ lnet_register_lnd (lnd_t *lnd) EXPORT_SYMBOL(lnet_register_lnd); void -lnet_unregister_lnd (lnd_t *lnd) +lnet_unregister_lnd(struct lnet_lnd *lnd) { mutex_lock(&the_lnet.ln_lnd_mutex); @@ -376,28 +849,70 @@ lnet_unregister_lnd (lnd_t *lnd) EXPORT_SYMBOL(lnet_unregister_lnd); void -lnet_counters_get(lnet_counters_t *counters) +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) { - lnet_counters_t *ctr; + 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); } @@ -406,13 +921,13 @@ EXPORT_SYMBOL(lnet_counters_get); void lnet_counters_reset(void) { - lnet_counters_t *counters; + struct lnet_counters *counters; int i; lnet_net_lock(LNET_LOCK_EX); cfs_percpt_for_each(counters, i, the_lnet.ln_counters) - memset(counters, 0, sizeof(lnet_counters_t)); + memset(counters, 0, sizeof(struct lnet_counters)); lnet_net_unlock(LNET_LOCK_EX); } @@ -445,10 +960,10 @@ lnet_res_container_cleanup(struct lnet_res_container *rec) list_del_init(e); if (rec->rec_type == LNET_COOKIE_TYPE_EQ) { - lnet_eq_free(list_entry(e, lnet_eq_t, eq_list)); + lnet_eq_free(list_entry(e, struct lnet_eq, eq_list)); } else if (rec->rec_type == LNET_COOKIE_TYPE_MD) { - lnet_md_free(list_entry(e, lnet_libmd_t, md_list)); + lnet_md_free(list_entry(e, struct lnet_libmd, md_list)); } else { /* NB: Active MEs should be attached on portals */ LBUG(); @@ -544,12 +1059,12 @@ lnet_res_containers_create(int type) return recs; } -lnet_libhandle_t * +struct lnet_libhandle * lnet_res_lh_lookup(struct lnet_res_container *rec, __u64 cookie) { /* ALWAYS called with lnet_res_lock held */ struct list_head *head; - lnet_libhandle_t *lh; + struct lnet_libhandle *lh; unsigned int hash; if ((cookie & LNET_COOKIE_MASK) != rec->rec_type) @@ -567,7 +1082,8 @@ lnet_res_lh_lookup(struct lnet_res_container *rec, __u64 cookie) } void -lnet_res_lh_initialize(struct lnet_res_container *rec, lnet_libhandle_t *lh) +lnet_res_lh_initialize(struct lnet_res_container *rec, + struct lnet_libhandle *lh) { /* ALWAYS called with lnet_res_lock held */ unsigned int ibits = LNET_COOKIE_TYPE_BITS + LNET_CPT_BITS; @@ -603,12 +1119,17 @@ lnet_prepare(lnet_pid_t requested_pid) the_lnet.ln_pid = requested_pid; INIT_LIST_HEAD(&the_lnet.ln_test_peers); - INIT_LIST_HEAD(&the_lnet.ln_peers); INIT_LIST_HEAD(&the_lnet.ln_remote_peer_ni_list); INIT_LIST_HEAD(&the_lnet.ln_nets); 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_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(); if (rc != 0) @@ -625,7 +1146,7 @@ lnet_prepare(lnet_pid_t requested_pid) the_lnet.ln_interface_cookie = ktime_get_real_ns(); the_lnet.ln_counters = cfs_percpt_alloc(lnet_cpt_table(), - sizeof(lnet_counters_t)); + sizeof(struct lnet_counters)); if (the_lnet.ln_counters == NULL) { CERROR("Failed to allocate counters for LNet\n"); rc = -ENOMEM; @@ -716,7 +1237,7 @@ lnet_unprepare (void) return 0; } -lnet_ni_t * +struct lnet_ni * lnet_net2ni_locked(__u32 net_id, int cpt) { struct lnet_ni *ni; @@ -735,10 +1256,10 @@ lnet_net2ni_locked(__u32 net_id, int cpt) return NULL; } -lnet_ni_t * +struct lnet_ni * lnet_net2ni_addref(__u32 net) { - lnet_ni_t *ni; + struct lnet_ni *ni; lnet_net_lock(0); ni = lnet_net2ni_locked(net, 0); @@ -853,17 +1374,7 @@ lnet_islocalnet(__u32 net_id) return local; } -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) - return true; - - return false; -} - -lnet_ni_t * +struct lnet_ni * lnet_nid2ni_locked(lnet_nid_t nid, int cpt) { struct lnet_net *net; @@ -881,10 +1392,10 @@ lnet_nid2ni_locked(lnet_nid_t nid, int cpt) return NULL; } -lnet_ni_t * +struct lnet_ni * lnet_nid2ni_addref(lnet_nid_t nid) { - lnet_ni_t *ni; + struct lnet_ni *ni; lnet_net_lock(0); ni = lnet_nid2ni_locked(nid, 0); @@ -930,25 +1441,45 @@ lnet_count_acceptor_nets(void) return count; } -static struct lnet_ping_info * -lnet_ping_info_create(int num_ni) +struct lnet_ping_buffer * +lnet_ping_buffer_alloc(int nnis, gfp_t gfp) { - struct lnet_ping_info *ping_info; - unsigned int infosz; + struct lnet_ping_buffer *pbuf; - infosz = offsetof(struct lnet_ping_info, pi_ni[num_ni]); - LIBCFS_ALLOC(ping_info, infosz); - if (ping_info == NULL) { - CERROR("Can't allocate ping info[%d]\n", num_ni); + LIBCFS_ALLOC_GFP(pbuf, LNET_PING_BUFFER_SIZE(nnis), gfp); + if (pbuf) { + pbuf->pb_nnis = nnis; + atomic_set(&pbuf->pb_refcnt, 1); + } + + return pbuf; +} + +void +lnet_ping_buffer_free(struct lnet_ping_buffer *pbuf) +{ + LASSERT(lnet_ping_buffer_numref(pbuf) == 0); + LIBCFS_FREE(pbuf, LNET_PING_BUFFER_SIZE(pbuf->pb_nnis)); +} + +static struct lnet_ping_buffer * +lnet_ping_target_create(int nnis) +{ + struct lnet_ping_buffer *pbuf; + + pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS); + if (pbuf == NULL) { + CERROR("Can't allocate ping source [%d]\n", nnis); return NULL; } - ping_info->pi_nnis = num_ni; - ping_info->pi_pid = the_lnet.ln_pid; - ping_info->pi_magic = LNET_PROTO_PING_MAGIC; - ping_info->pi_features = LNET_PING_FEAT_NI_STATUS; + 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 | LNET_PING_FEAT_MULTI_RAIL; - return ping_info; + return pbuf; } static inline int @@ -994,16 +1525,25 @@ lnet_get_ni_count(void) return count; } -static inline void -lnet_ping_info_free(struct lnet_ping_info *pinfo) +int +lnet_ping_info_validate(struct lnet_ping_info *pinfo) { - LIBCFS_FREE(pinfo, - offsetof(struct lnet_ping_info, - pi_ni[pinfo->pi_nnis])); + if (!pinfo) + return -EINVAL; + if (pinfo->pi_magic != LNET_PROTO_PING_MAGIC) + return -EPROTO; + if (!(pinfo->pi_features & LNET_PING_FEAT_NI_STATUS)) + return -EPROTO; + /* 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) + return -EPROTO; + return 0; } static void -lnet_ping_info_destroy(void) +lnet_ping_target_destroy(void) { struct lnet_net *net; struct lnet_ni *ni; @@ -1018,97 +1558,105 @@ lnet_ping_info_destroy(void) } } - lnet_ping_info_free(the_lnet.ln_ping_info); - the_lnet.ln_ping_info = NULL; + lnet_ping_buffer_decref(the_lnet.ln_ping_target); + the_lnet.ln_ping_target = NULL; lnet_net_unlock(LNET_LOCK_EX); } static void -lnet_ping_event_handler(lnet_event_t *event) +lnet_ping_target_event_handler(struct lnet_event *event) { - struct lnet_ping_info *pinfo = event->md.user_ptr; + struct lnet_ping_buffer *pbuf = event->md.user_ptr; if (event->unlinked) - pinfo->pi_features = LNET_PING_FEAT_INVAL; + lnet_ping_buffer_decref(pbuf); } static int -lnet_ping_info_setup(struct lnet_ping_info **ppinfo, lnet_handle_md_t *md_handle, - int ni_count, bool set_eq) +lnet_ping_target_setup(struct lnet_ping_buffer **ppbuf, + struct lnet_handle_md *ping_mdh, + int ni_count, bool set_eq) { - lnet_handle_me_t me_handle; - lnet_process_id_t id = {LNET_NID_ANY, LNET_PID_ANY}; - lnet_md_t md = {NULL}; - int rc, rc2; + struct lnet_process_id id = { + .nid = LNET_NID_ANY, + .pid = LNET_PID_ANY + }; + struct lnet_handle_me me_handle; + struct lnet_md md = { NULL }; + int rc, rc2; if (set_eq) { - rc = LNetEQAlloc(0, lnet_ping_event_handler, + rc = LNetEQAlloc(0, lnet_ping_target_event_handler, &the_lnet.ln_ping_target_eq); if (rc != 0) { - CERROR("Can't allocate ping EQ: %d\n", rc); + CERROR("Can't allocate ping buffer EQ: %d\n", rc); return rc; } } - *ppinfo = lnet_ping_info_create(ni_count); - if (*ppinfo == NULL) { + *ppbuf = lnet_ping_target_create(ni_count); + if (*ppbuf == NULL) { rc = -ENOMEM; - goto failed_0; + goto fail_free_eq; } + /* Ping target ME/MD */ rc = LNetMEAttach(LNET_RESERVED_PORTAL, id, LNET_PROTO_PING_MATCHBITS, 0, LNET_UNLINK, LNET_INS_AFTER, &me_handle); if (rc != 0) { - CERROR("Can't create ping ME: %d\n", rc); - goto failed_1; + CERROR("Can't create ping target ME: %d\n", rc); + goto fail_decref_ping_buffer; } /* initialize md content */ - md.start = *ppinfo; - md.length = offsetof(struct lnet_ping_info, - pi_ni[(*ppinfo)->pi_nnis]); + md.start = &(*ppbuf)->pb_info; + md.length = LNET_PING_INFO_SIZE((*ppbuf)->pb_nnis); md.threshold = LNET_MD_THRESH_INF; md.max_size = 0; md.options = LNET_MD_OP_GET | LNET_MD_TRUNCATE | LNET_MD_MANAGE_REMOTE; - md.user_ptr = NULL; md.eq_handle = the_lnet.ln_ping_target_eq; - md.user_ptr = *ppinfo; + md.user_ptr = *ppbuf; - rc = LNetMDAttach(me_handle, md, LNET_RETAIN, md_handle); + rc = LNetMDAttach(me_handle, md, LNET_RETAIN, ping_mdh); if (rc != 0) { - CERROR("Can't attach ping MD: %d\n", rc); - goto failed_2; + CERROR("Can't attach ping target MD: %d\n", rc); + goto fail_unlink_ping_me; } + lnet_ping_buffer_addref(*ppbuf); return 0; -failed_2: +fail_unlink_ping_me: rc2 = LNetMEUnlink(me_handle); LASSERT(rc2 == 0); -failed_1: - lnet_ping_info_free(*ppinfo); - *ppinfo = NULL; -failed_0: - if (set_eq) - LNetEQFree(the_lnet.ln_ping_target_eq); +fail_decref_ping_buffer: + LASSERT(lnet_ping_buffer_numref(*ppbuf) == 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; } static void -lnet_ping_md_unlink(struct lnet_ping_info *pinfo, lnet_handle_md_t *md_handle) +lnet_ping_md_unlink(struct lnet_ping_buffer *pbuf, + struct lnet_handle_md *ping_mdh) { sigset_t blocked = cfs_block_allsigs(); - LNetMDUnlink(*md_handle); - LNetInvalidateHandle(md_handle); + LNetMDUnlink(*ping_mdh); + LNetInvalidateMDHandle(ping_mdh); - /* NB md could be busy; this just starts the unlink */ - while (pinfo->pi_features != LNET_PING_FEAT_INVAL) { - CDEBUG(D_NET, "Still waiting for ping MD to unlink\n"); + /* 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)); } @@ -1117,62 +1665,84 @@ lnet_ping_md_unlink(struct lnet_ping_info *pinfo, lnet_handle_md_t *md_handle) } static void -lnet_ping_info_install_locked(struct lnet_ping_info *ping_info) +lnet_ping_target_install_locked(struct lnet_ping_buffer *pbuf) { - int i; struct lnet_ni *ni; struct lnet_net *net; struct lnet_ni_status *ns; + int i; + int rc; i = 0; list_for_each_entry(net, &the_lnet.ln_nets, net_list) { list_for_each_entry(ni, &net->net_ni_list, ni_netlist) { - LASSERT(i < ping_info->pi_nnis); + LASSERT(i < pbuf->pb_nnis); - ns = &ping_info->pi_ni[i]; + ns = &pbuf->pb_info.pi_ni[i]; ns->ns_nid = ni->ni_nid; lnet_ni_lock(ni); ns->ns_status = (ni->ni_status != NULL) ? - ni->ni_status->ns_status : + ni->ni_status->ns_status : LNET_NI_STATUS_UP; ni->ni_status = ns; lnet_ni_unlock(ni); i++; } - } + /* + * We (ab)use the ns_status of the loopback interface to + * transmit the sequence number. The first interface listed + * must be the loopback interface. + */ + rc = lnet_ping_info_validate(&pbuf->pb_info); + if (rc) { + LCONSOLE_EMERG("Invalid ping target: %d\n", rc); + LBUG(); + } + LNET_PING_BUFFER_SEQNO(pbuf) = + atomic_inc_return(&the_lnet.ln_ping_target_seqno); } static void -lnet_ping_target_update(struct lnet_ping_info *pinfo, lnet_handle_md_t md_handle) +lnet_ping_target_update(struct lnet_ping_buffer *pbuf, + struct lnet_handle_md ping_mdh) { - struct lnet_ping_info *old_pinfo = NULL; - lnet_handle_md_t old_md; + struct lnet_ping_buffer *old_pbuf = NULL; + struct lnet_handle_md old_ping_md; /* switch the NIs to point to the new ping info created */ lnet_net_lock(LNET_LOCK_EX); if (!the_lnet.ln_routing) - pinfo->pi_features |= LNET_PING_FEAT_RTE_DISABLED; - lnet_ping_info_install_locked(pinfo); + 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); + LASSERT(!(pbuf->pb_info.pi_features & ~LNET_PING_FEAT_BITS)); - if (the_lnet.ln_ping_info != NULL) { - old_pinfo = the_lnet.ln_ping_info; - old_md = the_lnet.ln_ping_target_md; + lnet_ping_target_install_locked(pbuf); + + if (the_lnet.ln_ping_target) { + old_pbuf = the_lnet.ln_ping_target; + old_ping_md = the_lnet.ln_ping_target_md; } - the_lnet.ln_ping_target_md = md_handle; - the_lnet.ln_ping_info = pinfo; + the_lnet.ln_ping_target_md = ping_mdh; + the_lnet.ln_ping_target = pbuf; lnet_net_unlock(LNET_LOCK_EX); - if (old_pinfo != NULL) { - /* unlink the old ping info */ - lnet_ping_md_unlink(old_pinfo, &old_md); - lnet_ping_info_free(old_pinfo); + if (old_pbuf) { + /* unlink and free the old ping info */ + lnet_ping_md_unlink(old_pbuf, &old_ping_md); + lnet_ping_buffer_decref(old_pbuf); } + + lnet_push_update_to_peers(0); } static void @@ -1180,21 +1750,164 @@ lnet_ping_target_fini(void) { int rc; - lnet_ping_md_unlink(the_lnet.ln_ping_info, + lnet_ping_md_unlink(the_lnet.ln_ping_target, &the_lnet.ln_ping_target_md); rc = LNetEQFree(the_lnet.ln_ping_target_eq); LASSERT(rc == 0); - lnet_ping_info_destroy(); + lnet_ping_target_destroy(); } -static int -lnet_ni_tq_credits(lnet_ni_t *ni) +/* Resize the push target. */ +int lnet_push_target_resize(void) { - int credits; + 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; + int rc; - LASSERT(ni->ni_ncpts >= 1); + if (nnis <= 0) { + rc = -EINVAL; + goto fail_return; + } +again: + pbuf = lnet_ping_buffer_alloc(nnis, GFP_NOFS); + if (!pbuf) { + rc = -ENOMEM; + goto fail_return; + } + + rc = LNetMEAttach(LNET_RESERVED_PORTAL, id, + LNET_PROTO_PING_MATCHBITS, 0, + LNET_UNLINK, LNET_INS_AFTER, + &meh); + if (rc) { + CERROR("Can't create push target ME: %d\n", rc); + goto fail_decref_pbuf; + } + + /* initialize md content */ + md.start = &pbuf->pb_info; + md.length = LNET_PING_INFO_SIZE(nnis); + md.threshold = LNET_MD_THRESH_INF; + md.max_size = 0; + md.options = LNET_MD_OP_PUT | LNET_MD_TRUNCATE | + LNET_MD_MANAGE_REMOTE; + md.user_ptr = pbuf; + md.eq_handle = the_lnet.ln_push_target_eq; + + rc = LNetMDAttach(meh, md, LNET_RETAIN, &mdh); + if (rc) { + CERROR("Can't attach push MD: %d\n", rc); + goto fail_unlink_meh; + } + lnet_ping_buffer_addref(pbuf); + + 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); + lnet_ping_buffer_decref(old_pbuf); + } + + if (nnis < the_lnet.ln_push_target_nnis) + goto again; + + CDEBUG(D_NET, "nnis %d success\n", nnis); + + return 0; + +fail_unlink_meh: + LNetMEUnlink(meh); +fail_decref_pbuf: + lnet_ping_buffer_decref(pbuf); +fail_return: + CDEBUG(D_NET, "nnis %d error %d\n", nnis, rc); + return rc; +} + +static void lnet_push_target_event_handler(struct lnet_event *ev) +{ + struct lnet_ping_buffer *pbuf = ev->md.user_ptr; + + 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); +} + +/* Initialize the push target. */ +static int lnet_push_target_init(void) +{ + int rc; + + if (the_lnet.ln_push_target) + return -EALREADY; + + rc = LNetEQAlloc(0, lnet_push_target_event_handler, + &the_lnet.ln_push_target_eq); + if (rc) { + CERROR("Can't allocated push target EQ: %d\n", rc); + return rc; + } + + /* 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) { + LNetEQFree(the_lnet.ln_push_target_eq); + LNetInvalidateEQHandle(&the_lnet.ln_push_target_eq); + } + + 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. */ + while (lnet_ping_buffer_numref(the_lnet.ln_push_target) > 1) { + CDEBUG(D_NET, "Still waiting for ping data MD to unlink\n"); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(cfs_time_seconds(1)); + } + + lnet_ping_buffer_decref(the_lnet.ln_push_target); + the_lnet.ln_push_target = NULL; + the_lnet.ln_push_target_nnis = 0; + + LNetEQFree(the_lnet.ln_push_target_eq); + LNetInvalidateEQHandle(&the_lnet.ln_push_target_eq); +} + +static int +lnet_ni_tq_credits(struct lnet_ni *ni) +{ + int credits; + + LASSERT(ni->ni_ncpts >= 1); if (ni->ni_ncpts == 1) return ni->ni_net->net_tunables.lct_max_tx_credits; @@ -1207,13 +1920,8 @@ lnet_ni_tq_credits(lnet_ni_t *ni) } static void -lnet_ni_unlink_locked(lnet_ni_t *ni) +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); @@ -1225,7 +1933,7 @@ lnet_clear_zombies_nis_locked(struct lnet_net *net) { int i; int islo; - lnet_ni_t *ni; + struct lnet_ni *ni; struct list_head *zombie_list = &net->net_ni_zombie; /* @@ -1238,7 +1946,7 @@ lnet_clear_zombies_nis_locked(struct lnet_net *net) int j; ni = list_entry(zombie_list->next, - lnet_ni_t, ni_netlist); + struct lnet_ni, ni_netlist); list_del_init(&ni->ni_netlist); /* the ni should be in deleting state. If it's not it's * a bug */ @@ -1290,8 +1998,11 @@ lnet_shutdown_lndni(struct lnet_ni *ni) 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); /* clear messages for this NI on the lazy portal */ @@ -1316,7 +2027,7 @@ lnet_shutdown_lndnet(struct lnet_net *net) while (!list_empty(&net->net_ni_list)) { ni = list_entry(net->net_ni_list.next, - lnet_ni_t, ni_netlist); + struct lnet_ni, ni_netlist); lnet_net_unlock(LNET_LOCK_EX); lnet_shutdown_lndni(ni); lnet_net_lock(LNET_LOCK_EX); @@ -1343,15 +2054,19 @@ static void lnet_shutdown_lndnets(void) { struct lnet_net *net; + struct list_head resend; + struct lnet_msg *msg, *tmp; + + INIT_LIST_HEAD(&resend); /* NB called holding the global mutex */ /* All quiet on the API front */ - LASSERT(!the_lnet.ln_shutdown); + LASSERT(the_lnet.ln_state == LNET_STATE_RUNNING); LASSERT(the_lnet.ln_refcount == 0); lnet_net_lock(LNET_LOCK_EX); - the_lnet.ln_shutdown = 1; /* flag shutdown */ + the_lnet.ln_state = LNET_STATE_STOPPING; while (!list_empty(&the_lnet.ln_nets)) { /* @@ -1378,8 +2093,18 @@ lnet_shutdown_lndnets(void) 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_shutdown = 0; + the_lnet.ln_state = LNET_STATE_SHUTDOWN; lnet_net_unlock(LNET_LOCK_EX); } @@ -1411,7 +2136,9 @@ lnet_startup_lndni(struct lnet_ni *ni, struct lnet_lnd_tunables *tun) 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) { @@ -1446,6 +2173,7 @@ lnet_startup_lndni(struct lnet_ni *ni, struct lnet_lnd_tunables *tun) 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), @@ -1463,13 +2191,13 @@ failed0: static int lnet_startup_lndnet(struct lnet_net *net, struct lnet_lnd_tunables *tun) { - struct lnet_ni *ni; - struct lnet_net *net_l = NULL; + 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; - lnd_t *lnd; + struct lnet_lnd *lnd; int peer_timeout = net->net_tunables.lct_peer_timeout; int maxtxcredits = @@ -1489,15 +2217,6 @@ lnet_startup_lndnet(struct lnet_net *net, struct lnet_lnd_tunables *tun) 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)); - - if (lnd_type == CIBLND || lnd_type == OPENIBLND || - lnd_type == IIBLND || lnd_type == VIBLND) { - CERROR("LND %s obsoleted\n", libcfs_lnd2str(lnd_type)); - rc = -EINVAL; - goto failed0; - } - mutex_lock(&the_lnet.ln_lnd_mutex); lnd = lnet_find_lnd_by_type(lnd_type); @@ -1657,6 +2376,15 @@ lnet_startup_lndnets(struct list_head *netlist) int rc; int ni_count = 0; + /* + * Change to running state before bringing up the LNDs. This + * allows lnet_shutdown_lndnets() to assert that we've passed + * through here. + */ + lnet_net_lock(LNET_LOCK_EX); + the_lnet.ln_state = LNET_STATE_RUNNING; + lnet_net_unlock(LNET_LOCK_EX); + while (!list_empty(netlist)) { net = list_entry(netlist->next, struct lnet_net, net_list); list_del_init(&net->net_list); @@ -1692,8 +2420,6 @@ int lnet_lib_init(void) 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); @@ -1717,10 +2443,11 @@ int lnet_lib_init(void) } the_lnet.ln_refcount = 0; - LNetInvalidateHandle(&the_lnet.ln_rc_eqh); + 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_msg_resend); INIT_LIST_HEAD(&the_lnet.ln_rcd_deathrow); /* The hash table size is the number of bits it takes to express the set @@ -1752,7 +2479,7 @@ void lnet_lib_exit(void) while (!list_empty(&the_lnet.ln_lnds)) lnet_unregister_lnd(list_entry(the_lnet.ln_lnds.next, - lnd_t, lnd_list)); + struct lnet_lnd, lnd_list)); lnet_destroy_locks(); } @@ -1777,8 +2504,8 @@ LNetNIInit(lnet_pid_t requested_pid) int im_a_router = 0; int rc; int ni_count; - struct lnet_ping_info *pinfo; - lnet_handle_md_t md_handle; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; struct list_head net_head; struct lnet_net *net; @@ -1853,23 +2580,35 @@ LNetNIInit(lnet_pid_t requested_pid) the_lnet.ln_refcount = 1; /* Now I may use my own API functions... */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, ni_count, true); + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, ni_count, true); if (rc != 0) goto err_acceptor_stop; - lnet_ping_target_update(pinfo, md_handle); + 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_monitor_thr; + + rc = lnet_peer_discovery_start(); + if (rc != 0) + goto err_destroy_push_target; + lnet_fault_init(); - lnet_proc_init(); + lnet_router_debugfs_init(); mutex_unlock(&the_lnet.ln_api_mutex); return 0; +err_destroy_push_target: + lnet_push_target_fini(); +err_stop_monitor_thr: + lnet_monitor_thr_stop(); err_stop_ping: lnet_ping_target_fini(); err_acceptor_stop: @@ -1918,8 +2657,10 @@ LNetNIFini() lnet_fault_fini(); - lnet_proc_fini(); - lnet_router_checker_stop(); + lnet_router_debugfs_fini(); + lnet_peer_discovery_stop(); + lnet_push_target_fini(); + lnet_monitor_thr_stop(); lnet_ping_target_fini(); /* Teardown fns that use my own API functions BEFORE here */ @@ -1936,17 +2677,6 @@ LNetNIFini() } EXPORT_SYMBOL(LNetNIFini); - -static int lnet_handle_dbg_task(struct lnet_ioctl_dbg *dbg, - struct lnet_dbg_task_info *dbg_info) -{ - switch (dbg->dbg_task) { - case LNET_DBG_INCR_DLC_SEQ: - lnet_incr_dlc_seq(); - } - - return 0; -} /** * Grabs the ni data from the ni structure and fills the out * parameters @@ -1978,15 +2708,22 @@ lnet_fill_ni_info(struct lnet_ni *ni, struct lnet_ioctl_config_ni *cfg_ni, } cfg_ni->lic_nid = ni->ni_nid; - cfg_ni->lic_status = ni->ni_status->ns_status; + if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND) + cfg_ni->lic_status = LNET_NI_STATUS_UP; + else + cfg_ni->lic_status = ni->ni_status->ns_status; cfg_ni->lic_tcp_bonding = use_tcp_bonding; - cfg_ni->lic_dev_cpt = ni->dev_cpt; + cfg_ni->lic_dev_cpt = ni->ni_dev_cpt; memcpy(&tun->lt_cmn, &ni->ni_net->net_tunables, sizeof(tun->lt_cmn)); if (stats) { - stats->send_count = atomic_read(&ni->ni_stats.send_count); - stats->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); } /* @@ -2063,7 +2800,10 @@ lnet_fill_ni_info_legacy(struct lnet_ni *ni, config->cfg_config_u.cfg_net.net_peer_rtr_credits = ni->ni_net->net_tunables.lct_peer_rtr_credits; - net_config->ni_status = ni->ni_status->ns_status; + if (LNET_NETTYP(LNET_NIDNET(ni->ni_nid)) == LOLND) + net_config->ni_status = LNET_NI_STATUS_UP; + else + net_config->ni_status = ni->ni_status->ns_status; if (ni->ni_cpts) { int num_cpts = min(ni->ni_ncpts, LNET_MAX_SHOW_NUM_CPT); @@ -2121,10 +2861,17 @@ lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev) 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); @@ -2146,6 +2893,8 @@ lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev) /* 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); @@ -2153,6 +2902,9 @@ lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev) 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); @@ -2210,15 +2962,37 @@ lnet_get_ni_config(struct lnet_ioctl_config_ni *cfg_ni, 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) { - struct lnet_net *netl = NULL; __u32 net_id; - lnet_ping_info_t *pinfo; - lnet_handle_md_t md_handle; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; int rc; - lnet_remotenet_t *rnet; + struct lnet_remotenet *rnet; int net_ni_count; int num_acceptor_nets; @@ -2232,13 +3006,13 @@ static int lnet_add_net_common(struct lnet_net *net, if (rnet) { CERROR("Adding net %s will invalidate routing configuration\n", libcfs_net2str(net->net_id)); - rc = -EUSERS; - goto failed1; + lnet_net_free(net); + return -EUSERS; } /* * make sure you calculate the correct number of slots in the ping - * info. Since the ping info is a flattened list of all the NIs, + * buffer. Since the ping info is a flattened list of all the NIs, * we should allocate enough slots to accomodate the number of NIs * which will be added. * @@ -2247,11 +3021,13 @@ static int lnet_add_net_common(struct lnet_net *net, */ net_ni_count = lnet_get_net_ni_count_pre(net); - rc = lnet_ping_info_setup(&pinfo, &md_handle, - net_ni_count + lnet_get_ni_count(), - false); - if (rc < 0) - goto failed1; + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + net_ni_count + lnet_get_ni_count(), + false); + if (rc < 0) { + lnet_net_free(net); + return rc; + } if (tun) memcpy(&net->net_tunables, @@ -2275,18 +3051,16 @@ static int lnet_add_net_common(struct lnet_net *net, goto failed; lnet_net_lock(LNET_LOCK_EX); - netl = lnet_get_net_locked(net_id); + net = lnet_get_net_locked(net_id); lnet_net_unlock(LNET_LOCK_EX); - LASSERT(netl); + LASSERT(net); /* * Start the acceptor thread if this is the first network * being added that requires the thread. */ - if (netl->net_lnd->lnd_accept && - num_acceptor_nets == 0) - { + if (net->net_lnd->lnd_accept && num_acceptor_nets == 0) { rc = lnet_acceptor_start(); if (rc < 0) { /* shutdown the net that we just started */ @@ -2297,18 +3071,16 @@ static int lnet_add_net_common(struct lnet_net *net, } lnet_net_lock(LNET_LOCK_EX); - lnet_peer_net_added(netl); + lnet_peer_net_added(net); lnet_net_unlock(LNET_LOCK_EX); - lnet_ping_target_update(pinfo, md_handle); + lnet_ping_target_update(pbuf, ping_mdh); return 0; failed: - lnet_ping_md_unlink(pinfo, &md_handle); - lnet_ping_info_free(pinfo); -failed1: - lnet_net_free(net); + lnet_ping_md_unlink(pbuf, &ping_mdh); + lnet_ping_buffer_decref(pbuf); return rc; } @@ -2355,8 +3127,8 @@ int lnet_dyn_add_ni(struct lnet_ioctl_config_ni *conf) struct lnet_net *net; struct lnet_ni *ni; struct lnet_ioctl_config_lnd_tunables *tun = NULL; - int rc; - __u32 net_id; + int rc, i; + __u32 net_id, lnd_type; /* get the tunables if they are available */ if (conf->lic_cfg_hdr.ioc_len >= @@ -2370,11 +3142,22 @@ int lnet_dyn_add_ni(struct lnet_ioctl_config_ni *conf) 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) return -ENOMEM; + for (i = 0; i < conf->lic_ncpts; i++) { + if (conf->lic_cpts[i] >= LNET_CPT_NUMBER) + return -EINVAL; + } + ni = lnet_ni_alloc_w_cpt_array(net, conf->lic_cpts, conf->lic_ncpts, conf->lic_ni_intf[0]); if (!ni) @@ -2394,8 +3177,8 @@ int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf) struct lnet_net *net; struct lnet_ni *ni; __u32 net_id = LNET_NIDNET(conf->lic_nid); - lnet_ping_info_t *pinfo; - lnet_handle_md_t md_handle; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; int rc; int net_count; __u32 addr; @@ -2413,7 +3196,7 @@ int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf) CERROR("net %s not found\n", libcfs_net2str(net_id)); rc = -ENOENT; - goto net_unlock; + goto unlock_net; } addr = LNET_NIDADDR(conf->lic_nid); @@ -2424,28 +3207,28 @@ int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf) lnet_net_unlock(0); /* create and link a new ping info, before removing the old one */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, lnet_get_ni_count() - net_count, false); if (rc != 0) - goto out; + goto unlock_api_mutex; lnet_shutdown_lndnet(net); if (lnet_count_acceptor_nets() == 0) lnet_acceptor_stop(); - lnet_ping_target_update(pinfo, md_handle); + lnet_ping_target_update(pbuf, ping_mdh); - goto out; + goto unlock_api_mutex; } ni = lnet_nid2ni_locked(conf->lic_nid, 0); if (!ni) { - CERROR("nid %s not found \n", + CERROR("nid %s not found\n", libcfs_nid2str(conf->lic_nid)); rc = -ENOENT; - goto net_unlock; + goto unlock_net; } net_count = lnet_get_net_ni_count_locked(net); @@ -2453,27 +3236,27 @@ int lnet_dyn_del_ni(struct lnet_ioctl_config_ni *conf) lnet_net_unlock(0); /* create and link a new ping info, before removing the old one */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, lnet_get_ni_count() - 1, false); if (rc != 0) - goto out; + goto unlock_api_mutex; lnet_shutdown_lndni(ni); if (lnet_count_acceptor_nets() == 0) lnet_acceptor_stop(); - lnet_ping_target_update(pinfo, md_handle); + lnet_ping_target_update(pbuf, ping_mdh); /* check if the net is empty and remove it if it is */ if (net_count == 1) lnet_shutdown_lndnet(net); - goto out; + goto unlock_api_mutex; -net_unlock: +unlock_net: lnet_net_unlock(0); -out: +unlock_api_mutex: mutex_unlock(&the_lnet.ln_api_mutex); return rc; @@ -2505,7 +3288,7 @@ lnet_dyn_add_net(struct lnet_ioctl_config_data *conf) if (rc > 1) { rc = -EINVAL; /* only add one network per call */ - goto failed; + goto out_unlock_clean; } net = list_entry(net_head.next, struct lnet_net, net_list); @@ -2513,7 +3296,7 @@ lnet_dyn_add_net(struct lnet_ioctl_config_data *conf) LASSERT(lnet_net_unique(net->net_id, &the_lnet.ln_nets, NULL)); - memset(&tun, sizeof(tun), 0); + memset(&tun, 0, sizeof(tun)); tun.lt_cmn.lct_peer_timeout = conf->cfg_config_u.cfg_net.net_peer_timeout; @@ -2525,14 +3308,11 @@ lnet_dyn_add_net(struct lnet_ioctl_config_data *conf) conf->cfg_config_u.cfg_net.net_max_tx_credits; rc = lnet_add_net_common(net, &tun); - if (rc != 0) - goto failed; - return 0; - -failed: +out_unlock_clean: mutex_unlock(&the_lnet.ln_api_mutex); while (!list_empty(&net_head)) { + /* net_head list is empty in success case */ net = list_entry(net_head.next, struct lnet_net, net_list); list_del_init(&net->net_list); lnet_net_free(net); @@ -2544,8 +3324,8 @@ int lnet_dyn_del_net(__u32 net_id) { struct lnet_net *net; - struct lnet_ping_info *pinfo; - lnet_handle_md_t md_handle; + struct lnet_ping_buffer *pbuf; + struct lnet_handle_md ping_mdh; int rc; int net_ni_count; @@ -2559,6 +3339,7 @@ lnet_dyn_del_net(__u32 net_id) net = lnet_get_net_locked(net_id); if (net == NULL) { + lnet_net_unlock(0); rc = -EINVAL; goto out; } @@ -2568,8 +3349,8 @@ lnet_dyn_del_net(__u32 net_id) lnet_net_unlock(0); /* create and link a new ping info, before removing the old one */ - rc = lnet_ping_info_setup(&pinfo, &md_handle, - lnet_get_ni_count() - net_ni_count, false); + rc = lnet_ping_target_setup(&pbuf, &ping_mdh, + lnet_get_ni_count() - net_ni_count, false); if (rc != 0) goto out; @@ -2578,7 +3359,7 @@ lnet_dyn_del_net(__u32 net_id) if (lnet_count_acceptor_nets() == 0) lnet_acceptor_stop(); - lnet_ping_target_update(pinfo, md_handle); + lnet_ping_target_update(pbuf, ping_mdh); out: mutex_unlock(&the_lnet.ln_api_mutex); @@ -2596,9 +3377,100 @@ __u32 lnet_get_dlc_seq_locked(void) return atomic_read(&lnet_dlc_seq_no); } -inline __u32 lnet_get_numa_range(void) +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) { - return lnet_numa_range; + 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; } /** @@ -2610,8 +3482,8 @@ LNetCtl(unsigned int cmd, void *arg) { struct libcfs_ioctl_data *data = arg; struct lnet_ioctl_config_data *config; - lnet_process_id_t id = {0}; - lnet_ni_t *ni; + struct lnet_process_id id = {0}; + struct lnet_ni *ni; int rc; BUILD_BUG_ON(sizeof(struct lnet_ioctl_net_config) + @@ -2682,9 +3554,10 @@ LNetCtl(unsigned int cmd, void *arg) __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 *) @@ -2701,6 +3574,19 @@ LNetCtl(unsigned int cmd, void *arg) 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); @@ -2761,22 +3647,22 @@ LNetCtl(unsigned int cmd, void *arg) return rc; case IOC_LIBCFS_SET_NUMA_RANGE: { - struct lnet_ioctl_numa_range *numa; + struct lnet_ioctl_set_value *numa; numa = arg; - if (numa->nr_hdr.ioc_len != sizeof(*numa)) + if (numa->sv_hdr.ioc_len != sizeof(*numa)) return -EINVAL; - mutex_lock(&the_lnet.ln_api_mutex); - lnet_numa_range = numa->nr_range; - mutex_unlock(&the_lnet.ln_api_mutex); + lnet_net_lock(LNET_LOCK_EX); + lnet_numa_range = numa->sv_value; + lnet_net_unlock(LNET_LOCK_EX); return 0; } case IOC_LIBCFS_GET_NUMA_RANGE: { - struct lnet_ioctl_numa_range *numa; + struct lnet_ioctl_set_value *numa; numa = arg; - if (numa->nr_hdr.ioc_len != sizeof(*numa)) + if (numa->sv_hdr.ioc_len != sizeof(*numa)) return -EINVAL; - numa->nr_range = lnet_numa_range; + numa->sv_value = lnet_numa_range; return 0; } @@ -2797,6 +3683,33 @@ LNetCtl(unsigned int cmd, void *arg) 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; @@ -2804,10 +3717,9 @@ LNetCtl(unsigned int cmd, void *arg) return -EINVAL; mutex_lock(&the_lnet.ln_api_mutex); - lnet_incr_dlc_seq(); - rc = lnet_add_peer_ni_to_peer(cfg->prcfg_key_nid, - cfg->prcfg_cfg_nid, - cfg->prcfg_mr); + rc = lnet_add_peer_ni(cfg->prcfg_prim_nid, + cfg->prcfg_cfg_nid, + cfg->prcfg_mr); mutex_unlock(&the_lnet.ln_api_mutex); return rc; } @@ -2819,9 +3731,8 @@ LNetCtl(unsigned int cmd, void *arg) return -EINVAL; mutex_lock(&the_lnet.ln_api_mutex); - lnet_incr_dlc_seq(); - rc = lnet_del_peer_ni_from_peer(cfg->prcfg_key_nid, - cfg->prcfg_cfg_nid); + rc = lnet_del_peer_ni(cfg->prcfg_prim_nid, + cfg->prcfg_cfg_nid); mutex_unlock(&the_lnet.ln_api_mutex); return rc; } @@ -2842,7 +3753,7 @@ LNetCtl(unsigned int cmd, void *arg) &peer_info->pr_lnd_u.pr_peer_credits.cr_ni_peer_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_rtr_credits, - &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_min_rtr_credits, + &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_min_tx_credits, &peer_info->pr_lnd_u.pr_peer_credits.cr_peer_tx_qnob); mutex_unlock(&the_lnet.ln_api_mutex); return rc; @@ -2850,34 +3761,64 @@ LNetCtl(unsigned int cmd, void *arg) case IOC_LIBCFS_GET_PEER_NI: { struct lnet_ioctl_peer_cfg *cfg = arg; - struct lnet_peer_ni_credit_info *lpni_cri; - struct lnet_ioctl_element_stats *lpni_stats; - size_t total = sizeof(*cfg) + sizeof(*lpni_cri) + - sizeof(*lpni_stats); - if (cfg->prcfg_hdr.ioc_len < total) + if (cfg->prcfg_hdr.ioc_len < sizeof(*cfg)) return -EINVAL; - lpni_cri = (struct lnet_peer_ni_credit_info*) cfg->prcfg_bulk; - lpni_stats = (struct lnet_ioctl_element_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_idx, &cfg->prcfg_key_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]; + /* 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: @@ -2903,35 +3844,75 @@ LNetCtl(unsigned int cmd, void *arg) 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(lnet_process_id_t)); + data->ioc_plen1 / sizeof(struct lnet_process_id)); + if (rc < 0) return rc; + data->ioc_count = rc; return 0; } - case IOC_LIBCFS_DBG: { - struct lnet_ioctl_dbg *dbg = arg; - struct lnet_dbg_task_info *dbg_info; - size_t total = sizeof(*dbg) + sizeof(*dbg_info); + case IOC_LIBCFS_PING_PEER: { + struct lnet_ioctl_ping_data *ping = arg; + struct lnet_peer *lp; + signed long timeout; - if (dbg->dbg_hdr.ioc_len < total) - return -EINVAL; + /* 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; + + 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; - dbg_info = (struct lnet_dbg_task_info*) dbg->dbg_bulk; + rc = lnet_discover(discover->ping_id, discover->op_param, + discover->ping_buf, + discover->ping_count); + if (rc < 0) + return rc; - return lnet_handle_dbg_task(dbg, dbg_info); + 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: @@ -2951,25 +3932,54 @@ LNetCtl(unsigned int cmd, void *arg) } EXPORT_SYMBOL(LNetCtl); -void LNetDebugPeer(lnet_process_id_t id) +void LNetDebugPeer(struct lnet_process_id id) { lnet_debug_peer(id.nid); } EXPORT_SYMBOL(LNetDebugPeer); /** - * Retrieve the lnet_process_id_t ID of LNet interface at \a index. Note that - * all interfaces share a same PID, as requested by LNetNIInit(). + * Determine if the specified peer \a nid is on the local node. + * + * \param nid peer nid to check + * + * \retval true If peer NID is on the local node. + * \retval false If peer NID is not on the local node. + */ +bool LNetIsPeerLocal(lnet_nid_t nid) +{ + struct lnet_net *net; + struct lnet_ni *ni; + int cpt; + + cpt = lnet_net_lock_current(); + 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) { + lnet_net_unlock(cpt); + return true; + } + } + } + lnet_net_unlock(cpt); + + return false; +} +EXPORT_SYMBOL(LNetIsPeerLocal); + +/** + * Retrieve the struct lnet_process_id ID of LNet interface at \a index. + * Note that all interfaces share a same PID, as requested by LNetNIInit(). * * \param index Index of the interface to look up. * \param id On successful return, this location will hold the - * lnet_process_id_t ID of the interface. + * struct lnet_process_id ID of the interface. * * \retval 0 If an interface exists at \a index. * \retval -ENOENT If no interface has been found. */ int -LNetGetId(unsigned int index, lnet_process_id_t *id) +LNetGetId(unsigned int index, struct lnet_process_id *id) { struct lnet_ni *ni; struct lnet_net *net; @@ -2997,61 +4007,54 @@ LNetGetId(unsigned int index, lnet_process_id_t *id) } EXPORT_SYMBOL(LNetGetId); -/** - * Print a string representation of handle \a h into buffer \a str of - * \a len bytes. - */ -void -LNetSnprintHandle(char *str, int len, lnet_handle_any_t h) -{ - snprintf(str, len, "%#llx", h.cookie); -} -EXPORT_SYMBOL(LNetSnprintHandle); - -static int lnet_ping(lnet_process_id_t id, signed long timeout, - lnet_process_id_t __user *ids, int n_ids) +static int lnet_ping(struct lnet_process_id id, signed long timeout, + struct lnet_process_id __user *ids, int n_ids) { - lnet_handle_eq_t eqh; - lnet_handle_md_t mdh; - lnet_event_t event; - lnet_md_t md = { NULL }; - int which; - int unlinked = 0; - int replied = 0; + 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); - int infosz; - struct lnet_ping_info *info; - lnet_process_id_t tmpid; - int i; - int nob; - int rc; - int rc2; - sigset_t blocked; - - infosz = offsetof(struct lnet_ping_info, pi_ni[n_ids]); + 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 > 20 || 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; - LIBCFS_ALLOC(info, infosz); - if (info == NULL) + pbuf = lnet_ping_buffer_alloc(n_ids, GFP_NOFS); + 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 out_0; + goto fail_ping_buffer_decref; } /* initialize md content */ - md.start = info; - md.length = infosz; - md.threshold = 2; /*GET/REPLY*/ + md.start = &pbuf->pb_info; + md.length = LNET_PING_INFO_SIZE(n_ids); + md.threshold = 2; /* GET/REPLY */ md.max_size = 0; md.options = LNET_MD_TRUNCATE; md.user_ptr = NULL; @@ -3060,16 +4063,15 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, rc = LNetMDBind(md, LNET_UNLINK, &mdh); if (rc != 0) { CERROR("Can't bind MD: %d\n", rc); - goto out_1; + goto fail_free_eq; } 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! */ - rc2 = LNetMDUnlink(mdh); LASSERT(rc2 == 0); @@ -3117,7 +4119,6 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, replied = 1; rc = event.mlength; } - } while (rc2 <= 0 || !event.unlinked); if (!replied) { @@ -3125,68 +4126,170 @@ static int lnet_ping(lnet_process_id_t id, signed long timeout, CWARN("%s: Unexpected rc >= 0 but no reply!\n", libcfs_id2str(id)); rc = -EIO; - goto out_1; + goto fail_free_eq; } nob = rc; - LASSERT(nob >= 0 && nob <= infosz); + 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 out_1; + goto fail_free_eq; } - if (info->pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) { - lnet_swap_pinginfo(info); - } else if (info->pi_magic != LNET_PROTO_PING_MAGIC) { + if (pbuf->pb_info.pi_magic == __swab32(LNET_PROTO_PING_MAGIC)) { + lnet_swap_pinginfo(pbuf); + } else if (pbuf->pb_info.pi_magic != LNET_PROTO_PING_MAGIC) { CERROR("%s: Unexpected magic %08x\n", - libcfs_id2str(id), info->pi_magic); - goto out_1; + libcfs_id2str(id), pbuf->pb_info.pi_magic); + goto fail_free_eq; } - if ((info->pi_features & LNET_PING_FEAT_NI_STATUS) == 0) { + 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), info->pi_features); - goto out_1; + libcfs_id2str(id), pbuf->pb_info.pi_features); + goto fail_free_eq; } - if (nob < offsetof(struct lnet_ping_info, pi_ni[0])) { - CERROR("%s: Short reply %d(%d min)\n", libcfs_id2str(id), - nob, (int)offsetof(struct lnet_ping_info, pi_ni[0])); - goto out_1; + if (nob < LNET_PING_INFO_SIZE(0)) { + CERROR("%s: Short reply %d(%d min)\n", + libcfs_id2str(id), + nob, (int)LNET_PING_INFO_SIZE(0)); + goto fail_free_eq; } - if (info->pi_nnis < n_ids) - n_ids = info->pi_nnis; + if (pbuf->pb_info.pi_nnis < n_ids) + n_ids = pbuf->pb_info.pi_nnis; - if (nob < offsetof(struct lnet_ping_info, pi_ni[n_ids])) { - CERROR("%s: Short reply %d(%d expected)\n", libcfs_id2str(id), - nob, (int)offsetof(struct lnet_ping_info, pi_ni[n_ids])); - goto out_1; + if (nob < LNET_PING_INFO_SIZE(n_ids)) { + 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++) { - tmpid.pid = info->pi_pid; - tmpid.nid = info->pi_ni[i].ns_nid; + 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 out_1; + goto fail_free_eq; } - rc = info->pi_nnis; + rc = pbuf->pb_info.pi_nnis; - out_1: + fail_free_eq: rc2 = LNetEQFree(eqh); if (rc2 != 0) CERROR("rc2 %d\n", rc2); LASSERT(rc2 == 0); - out_0: - LIBCFS_FREE(info, infosz); + 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; + int max_intf = lnet_interfaces_max; + size_t buf_size; + + 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 max_intf + * then only fill it up to max_intf + */ + if (n_ids > max_intf) + n_ids = max_intf; + + buf_size = n_ids * sizeof(*buf); + + LIBCFS_ALLOC(buf, buf_size); + 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); + + LIBCFS_FREE(buf, buf_size); + + 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);