diff --git a/ldso/dynlink.c b/ldso/dynlink.c
index a03f75e..3e52beb 100644
--- a/ldso/dynlink.c
+++ b/ldso/dynlink.c
@@ -67,6 +67,7 @@ struct dso {
 	char constructed;
 	char kernel_mapped;
 	struct dso **deps, *needed_by;
+	size_t next_dep;
 	char *rpath_orig, *rpath;
 	struct tls_module tls;
 	size_t tls_id;
@@ -934,6 +935,7 @@ static struct dso *load_library(const char *name, struct dso *needed_by)
 		if (!ldso.prev) {
 			tail->next = &ldso;
 			ldso.prev = tail;
+			ldso.needed_by = needed_by;
 			tail = ldso.next ? ldso.next : &ldso;
 		}
 		return &ldso;
@@ -1090,9 +1092,12 @@ static void load_deps(struct dso *p)
 				if (runtime) longjmp(*rtld_fail, 1);
 				continue;
 			}
-			if (runtime) {
-				tmp = realloc(*deps, sizeof(*tmp)*(ndeps+2));
-				if (!tmp) longjmp(*rtld_fail, 1);
+			tmp = realloc(*deps, sizeof(*tmp)*(ndeps+2));
+			if (!tmp) {
+				error("Error allocating dependency data for %s: %m",
+					p->name);
+				if (runtime) longjmp(*rtld_fail, 1);
+			} else {
 				tmp[ndeps++] = dep;
 				tmp[ndeps] = 0;
 				*deps = tmp;
@@ -1110,7 +1115,7 @@ static void load_preload(char *s)
 		for (z=s; *z && !isspace(*z) && *z!=':'; z++);
 		tmp = *z;
 		*z = 0;
-		load_library(s, 0);
+		load_library(s, head);
 		*z = tmp;
 	}
 }
@@ -1211,13 +1216,21 @@ void __libc_exit_fini()
 static void do_init_fini(struct dso *p)
 {
 	size_t dyn[DYN_CNT];
-	int need_locking = libc.threads_minus_1;
-	/* Allow recursive calls that arise when a library calls
-	 * dlopen from one of its constructors, but block any
-	 * other threads until all ctors have finished. */
-	if (need_locking) pthread_mutex_lock(&init_fini_lock);
-	for (; p; p=p->prev) {
-		if (p->constructed) continue;
+	pthread_mutex_lock(&init_fini_lock);
+	/* Construct in dependency order without any recursive state. */
+	while (p && !p->constructed) {
+		/* The following loop descends into the first dependency
+		 * that is neither alredy constructed nor pending
+		 * construction due to circular deps, stopping only
+		 * when it reaches a dso with no remaining dependencies
+		 * to descend into. */
+		while (p->deps && p->deps[p->next_dep]) {
+			if (!p->deps[p->next_dep]->constructed &&
+			    !p->deps[p->next_dep]->next_dep)
+				p = p->deps[p->next_dep++];
+			else
+				p->next_dep++;
+		}
 		p->constructed = 1;
 		decode_vec(p->dynv, dyn, DYN_CNT);
 		if (dyn[0] & ((1<<DT_FINI) | (1<<DT_FINI_ARRAY))) {
@@ -1233,17 +1246,19 @@ static void do_init_fini(struct dso *p)
 			size_t *fn = laddr(p, dyn[DT_INIT_ARRAY]);
 			while (n--) ((void (*)(void))*fn++)();
 		}
-		if (!need_locking && libc.threads_minus_1) {
-			need_locking = 1;
-			pthread_mutex_lock(&init_fini_lock);
-		}
-	}
-	if (need_locking) pthread_mutex_unlock(&init_fini_lock);
+		/* Revisit "parent" dso which caused the just-constructed
+		 * dso to be pulled in as a dependency. On the next loop
+		 * iteration we will either descend to construct a sibling
+		 * of the just-constructed dso, or finish constructing the
+		 * parent if no unfinished deps remain. */
+		p = p->needed_by;
+	}
+	pthread_mutex_unlock(&init_fini_lock);
 }
 
 void __libc_start_init(void)
 {
-	do_init_fini(tail);
+	do_init_fini(head);
 }
 
 static void dl_debug_state(void)
@@ -1731,7 +1746,7 @@ end:
 	__release_ptc();
 	if (p) gencnt++;
 	pthread_rwlock_unlock(&lock);
-	if (p) do_init_fini(orig_tail);
+	if (p) do_init_fini(p);
 	pthread_setcancelstate(cs, 0);
 	return p;
 }