diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index db01b95a47a501d5976c04d66052a8809f026f29..c5d6bb4290ad2d8fa24c279dc71aaef0b0eb46e4 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -18,6 +18,7 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
+#include <linux/wait.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -70,6 +71,8 @@ struct stupid_thread_structure {
 };
 
 static atomic_t probe_count = ATOMIC_INIT(0);
+static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
+
 static int really_probe(void *void_data)
 {
 	struct stupid_thread_structure *data = void_data;
@@ -121,6 +124,7 @@ static int really_probe(void *void_data)
 done:
 	kfree(data);
 	atomic_dec(&probe_count);
+	wake_up(&probe_waitqueue);
 	return ret;
 }
 
@@ -337,6 +341,32 @@ void driver_detach(struct device_driver * drv)
 	}
 }
 
+#ifdef CONFIG_PCI_MULTITHREAD_PROBE
+static int __init wait_for_probes(void)
+{
+	DEFINE_WAIT(wait);
+
+	printk(KERN_INFO "%s: waiting for %d threads\n", __FUNCTION__,
+			atomic_read(&probe_count));
+	if (!atomic_read(&probe_count))
+		return 0;
+	while (atomic_read(&probe_count)) {
+		prepare_to_wait(&probe_waitqueue, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(&probe_count))
+			schedule();
+	}
+	finish_wait(&probe_waitqueue, &wait);
+	return 0;
+}
+
+core_initcall_sync(wait_for_probes);
+postcore_initcall_sync(wait_for_probes);
+arch_initcall_sync(wait_for_probes);
+subsys_initcall_sync(wait_for_probes);
+fs_initcall_sync(wait_for_probes);
+device_initcall_sync(wait_for_probes);
+late_initcall_sync(wait_for_probes);
+#endif
 
 EXPORT_SYMBOL_GPL(device_bind_driver);
 EXPORT_SYMBOL_GPL(device_release_driver);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index e3e83bcaf71047f2f113c76ed50d1abf8b312fa7..9d873163a7ab09dfe605e2a2a49c5176f1b347e9 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -216,10 +216,17 @@
 
 #define INITCALLS							\
   	*(.initcall1.init)						\
+  	*(.initcall1s.init)						\
   	*(.initcall2.init)						\
+  	*(.initcall2s.init)						\
   	*(.initcall3.init)						\
+  	*(.initcall3s.init)						\
   	*(.initcall4.init)						\
+  	*(.initcall4s.init)						\
   	*(.initcall5.init)						\
+  	*(.initcall5s.init)						\
   	*(.initcall6.init)						\
-  	*(.initcall7.init)
+  	*(.initcall6s.init)						\
+  	*(.initcall7.init)						\
+  	*(.initcall7s.init)
 
diff --git a/include/linux/init.h b/include/linux/init.h
index e92b1455d7afd8c908bfc0722be018a09c46c226..ff40ea118e3a7798f2a3a092be3cc238788cbd2c 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -84,19 +84,29 @@ extern void setup_arch(char **);
  * by link order. 
  * For backwards compatibility, initcall() puts the call in 
  * the device init subsection.
+ *
+ * The `id' arg to __define_initcall() is needed so that multiple initcalls
+ * can point at the same handler without causing duplicate-symbol build errors.
  */
 
-#define __define_initcall(level,fn) \
-	static initcall_t __initcall_##fn __attribute_used__ \
+#define __define_initcall(level,fn,id) \
+	static initcall_t __initcall_##fn##id __attribute_used__ \
 	__attribute__((__section__(".initcall" level ".init"))) = fn
 
-#define core_initcall(fn)		__define_initcall("1",fn)
-#define postcore_initcall(fn)		__define_initcall("2",fn)
-#define arch_initcall(fn)		__define_initcall("3",fn)
-#define subsys_initcall(fn)		__define_initcall("4",fn)
-#define fs_initcall(fn)			__define_initcall("5",fn)
-#define device_initcall(fn)		__define_initcall("6",fn)
-#define late_initcall(fn)		__define_initcall("7",fn)
+#define core_initcall(fn)		__define_initcall("1",fn,1)
+#define core_initcall_sync(fn)		__define_initcall("1s",fn,1s)
+#define postcore_initcall(fn)		__define_initcall("2",fn,2)
+#define postcore_initcall_sync(fn)	__define_initcall("2s",fn,2s)
+#define arch_initcall(fn)		__define_initcall("3",fn,3)
+#define arch_initcall_sync(fn)		__define_initcall("3s",fn,3s)
+#define subsys_initcall(fn)		__define_initcall("4",fn,4)
+#define subsys_initcall_sync(fn)	__define_initcall("4s",fn,4s)
+#define fs_initcall(fn)			__define_initcall("5",fn,5)
+#define fs_initcall_sync(fn)		__define_initcall("5s",fn,5s)
+#define device_initcall(fn)		__define_initcall("6",fn,6)
+#define device_initcall_sync(fn)	__define_initcall("6s",fn,6s)
+#define late_initcall(fn)		__define_initcall("7",fn,7)
+#define late_initcall_sync(fn)		__define_initcall("7s",fn,7s)
 
 #define __initcall(fn) device_initcall(fn)