LU-13569 lnet: Introduce lnet_recovery_limit parameter

[fs/lustre-release.git] / lnet / lnet / api-ni.c

diff --git a/lnet/lnet/api-ni.c b/lnet/lnet/api-ni.c
index a7b3f8c..b75a625 100644 (file)
--- a/lnet/lnet/api-ni.c
+++ b/lnet/lnet/api-ni.c
@@ -124,6 +124,11 @@ module_param_call(lnet_recovery_interval, recovery_interval_set, param_get_int,
 MODULE_PARM_DESC(lnet_recovery_interval,
                "Interval to recover unhealthy interfaces in seconds");
 
+unsigned int lnet_recovery_limit;
+module_param(lnet_recovery_limit, uint, 0644);
+MODULE_PARM_DESC(lnet_recovery_limit,
+                "How long to attempt recovery of unhealthy peer interfaces in seconds. Set to 0 to allow indefinite recovery");
+
 static int lnet_interfaces_max = LNET_INTERFACES_MAX_DEFAULT;
 static int intf_max_set(const char *val, cfs_kernel_param_arg_t *kp);
 
@@ -2114,7 +2119,13 @@ lnet_clear_zombies_nis_locked(struct lnet_net *net)
                }
 
                if (!list_empty(&ni->ni_netlist)) {
+                       /* Unlock mutex while waiting to allow other
+                        * threads to read the LNet state and fall through
+                        * to avoid deadlock
+                        */
                        lnet_net_unlock(LNET_LOCK_EX);
+                       mutex_unlock(&the_lnet.ln_api_mutex);
+
                        ++i;
                        if ((i & (-i)) == i) {
                                CDEBUG(D_WARNING,
@@ -2122,6 +2133,8 @@ lnet_clear_zombies_nis_locked(struct lnet_net *net)
                                       libcfs_nid2str(ni->ni_nid));
                        }
                        schedule_timeout_uninterruptible(cfs_time_seconds(1));
+
+                       mutex_lock(&the_lnet.ln_api_mutex);
                        lnet_net_lock(LNET_LOCK_EX);
                        continue;
                }