diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index fecca4223f8ee92adfe4e4824ef6114def00baa2..f178a450ec08e6b56db21736fe9ed438ccf76aa3 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -56,6 +56,7 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
+#include <linux/async.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -5909,6 +5910,54 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 	host->ops = ops;
 }
 
+
+static void async_port_probe(void *data, async_cookie_t cookie)
+{
+	int rc;
+	struct ata_port *ap = data;
+	/* probe */
+	if (ap->ops->error_handler) {
+		struct ata_eh_info *ehi = &ap->link.eh_info;
+		unsigned long flags;
+
+		ata_port_probe(ap);
+
+		/* kick EH for boot probing */
+		spin_lock_irqsave(ap->lock, flags);
+
+		ehi->probe_mask |= ATA_ALL_DEVICES;
+		ehi->action |= ATA_EH_RESET | ATA_EH_LPM;
+		ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET;
+
+		ap->pflags &= ~ATA_PFLAG_INITIALIZING;
+		ap->pflags |= ATA_PFLAG_LOADING;
+		ata_port_schedule_eh(ap);
+
+		spin_unlock_irqrestore(ap->lock, flags);
+
+		/* wait for EH to finish */
+		ata_port_wait_eh(ap);
+	} else {
+		DPRINTK("ata%u: bus probe begin\n", ap->print_id);
+		rc = ata_bus_probe(ap);
+		DPRINTK("ata%u: bus probe end\n", ap->print_id);
+
+		if (rc) {
+			/* FIXME: do something useful here?
+			 * Current libata behavior will
+			 * tear down everything when
+			 * the module is removed
+			 * or the h/w is unplugged.
+			 */
+		}
+	}
+
+	/* in order to keep device order, we need to synchronize at this point */
+	async_synchronize_cookie(cookie);
+
+	ata_scsi_scan_host(ap, 1);
+
+}
 /**
  *	ata_host_register - register initialized ATA host
  *	@host: ATA host to register
@@ -5988,52 +6037,9 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	DPRINTK("probe begin\n");
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
-
-		/* probe */
-		if (ap->ops->error_handler) {
-			struct ata_eh_info *ehi = &ap->link.eh_info;
-			unsigned long flags;
-
-			ata_port_probe(ap);
-
-			/* kick EH for boot probing */
-			spin_lock_irqsave(ap->lock, flags);
-
-			ehi->probe_mask |= ATA_ALL_DEVICES;
-			ehi->action |= ATA_EH_RESET | ATA_EH_LPM;
-			ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET;
-
-			ap->pflags &= ~ATA_PFLAG_INITIALIZING;
-			ap->pflags |= ATA_PFLAG_LOADING;
-			ata_port_schedule_eh(ap);
-
-			spin_unlock_irqrestore(ap->lock, flags);
-
-			/* wait for EH to finish */
-			ata_port_wait_eh(ap);
-		} else {
-			DPRINTK("ata%u: bus probe begin\n", ap->print_id);
-			rc = ata_bus_probe(ap);
-			DPRINTK("ata%u: bus probe end\n", ap->print_id);
-
-			if (rc) {
-				/* FIXME: do something useful here?
-				 * Current libata behavior will
-				 * tear down everything when
-				 * the module is removed
-				 * or the h/w is unplugged.
-				 */
-			}
-		}
-	}
-
-	/* probes are done, now scan each port's disk(s) */
-	DPRINTK("host probe begin\n");
-	for (i = 0; i < host->n_ports; i++) {
-		struct ata_port *ap = host->ports[i];
-
-		ata_scsi_scan_host(ap, 1);
+		async_schedule(async_port_probe, ap);
 	}
+	DPRINTK("probe end\n");
 
 	return 0;
 }
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 18486b51668da7a3591c3112e4eb18ca123a0c8b..17914a346f715e72fec3f7e15dd4310abf11dd12 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -32,6 +32,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/spinlock.h>
+#include <linux/async.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -179,6 +180,8 @@ int scsi_complete_async_scans(void)
 	spin_unlock(&async_scan_lock);
 
 	kfree(data);
+	/* Synchronize async operations globally */
+	async_synchronize_full();
 	return 0;
 }
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 62b28d58e65e0e0c15cf6bcff602708a240b5819..e035c11140104c1db29bdf5fa1f9664e5a9dabb3 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -48,6 +48,7 @@
 #include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/string_helpers.h>
+#include <linux/async.h>
 #include <asm/uaccess.h>
 
 #include <scsi/scsi.h>
@@ -1802,6 +1803,71 @@ static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen)
 	return 0;
 }
 
+/*
+ * The asynchronous part of sd_probe
+ */
+static void sd_probe_async(void *data, async_cookie_t cookie)
+{
+	struct scsi_disk *sdkp = data;
+	struct scsi_device *sdp;
+	struct gendisk *gd;
+	u32 index;
+	struct device *dev;
+
+	sdp = sdkp->device;
+	gd = sdkp->disk;
+	index = sdkp->index;
+	dev = &sdp->sdev_gendev;
+
+	if (!sdp->request_queue->rq_timeout) {
+		if (sdp->type != TYPE_MOD)
+			blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT);
+		else
+			blk_queue_rq_timeout(sdp->request_queue,
+					     SD_MOD_TIMEOUT);
+	}
+
+	device_initialize(&sdkp->dev);
+	sdkp->dev.parent = &sdp->sdev_gendev;
+	sdkp->dev.class = &sd_disk_class;
+	strncpy(sdkp->dev.bus_id, sdp->sdev_gendev.bus_id, BUS_ID_SIZE);
+
+	if (device_add(&sdkp->dev))
+		goto out_free_index;
+
+	get_device(&sdp->sdev_gendev);
+
+	if (index < SD_MAX_DISKS) {
+		gd->major = sd_major((index & 0xf0) >> 4);
+		gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00);
+		gd->minors = SD_MINORS;
+	}
+	gd->fops = &sd_fops;
+	gd->private_data = &sdkp->driver;
+	gd->queue = sdkp->device->request_queue;
+
+	sd_revalidate_disk(gd);
+
+	blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
+
+	gd->driverfs_dev = &sdp->sdev_gendev;
+	gd->flags = GENHD_FL_EXT_DEVT | GENHD_FL_DRIVERFS;
+	if (sdp->removable)
+		gd->flags |= GENHD_FL_REMOVABLE;
+
+	dev_set_drvdata(dev, sdkp);
+	add_disk(gd);
+	sd_dif_config_host(sdkp);
+
+	sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
+		  sdp->removable ? "removable " : "");
+
+	return;
+
+ out_free_index:
+	ida_remove(&sd_index_ida, index);
+}
+
 /**
  *	sd_probe - called during driver initialization and whenever a
  *	new scsi device is attached to the system. It is called once
@@ -1865,48 +1931,7 @@ static int sd_probe(struct device *dev)
 	sdkp->openers = 0;
 	sdkp->previous_state = 1;
 
-	if (!sdp->request_queue->rq_timeout) {
-		if (sdp->type != TYPE_MOD)
-			blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT);
-		else
-			blk_queue_rq_timeout(sdp->request_queue,
-					     SD_MOD_TIMEOUT);
-	}
-
-	device_initialize(&sdkp->dev);
-	sdkp->dev.parent = &sdp->sdev_gendev;
-	sdkp->dev.class = &sd_disk_class;
-	strncpy(sdkp->dev.bus_id, sdp->sdev_gendev.bus_id, BUS_ID_SIZE);
-
-	if (device_add(&sdkp->dev))
-		goto out_free_index;
-
-	get_device(&sdp->sdev_gendev);
-
-	if (index < SD_MAX_DISKS) {
-		gd->major = sd_major((index & 0xf0) >> 4);
-		gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00);
-		gd->minors = SD_MINORS;
-	}
-	gd->fops = &sd_fops;
-	gd->private_data = &sdkp->driver;
-	gd->queue = sdkp->device->request_queue;
-
-	sd_revalidate_disk(gd);
-
-	blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
-
-	gd->driverfs_dev = &sdp->sdev_gendev;
-	gd->flags = GENHD_FL_EXT_DEVT | GENHD_FL_DRIVERFS;
-	if (sdp->removable)
-		gd->flags |= GENHD_FL_REMOVABLE;
-
-	dev_set_drvdata(dev, sdkp);
-	add_disk(gd);
-	sd_dif_config_host(sdkp);
-
-	sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
-		  sdp->removable ? "removable " : "");
+	async_schedule(sd_probe_async, sdkp);
 
 	return 0;
 
diff --git a/fs/inode.c b/fs/inode.c
index 7a6e8c2ff7b16b472b2bc7fd40894cfc3d8d0904..0013ac1af8e75d6178dbcf67a311ea3e4d326ff7 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/inotify.h>
 #include <linux/mount.h>
+#include <linux/async.h>
 
 /*
  * This is needed for the following functions:
@@ -1138,16 +1139,11 @@ EXPORT_SYMBOL(remove_inode_hash);
  * I_FREEING is set so that no-one will take a new reference to the inode while
  * it is being deleted.
  */
-void generic_delete_inode(struct inode *inode)
+static void generic_delete_inode_async(void *data, async_cookie_t cookie)
 {
+	struct inode *inode = data;
 	const struct super_operations *op = inode->i_sb->s_op;
 
-	list_del_init(&inode->i_list);
-	list_del_init(&inode->i_sb_list);
-	inode->i_state |= I_FREEING;
-	inodes_stat.nr_inodes--;
-	spin_unlock(&inode_lock);
-
 	security_inode_delete(inode);
 
 	if (op->delete_inode) {
@@ -1171,6 +1167,16 @@ void generic_delete_inode(struct inode *inode)
 	destroy_inode(inode);
 }
 
+void generic_delete_inode(struct inode *inode)
+{
+	list_del_init(&inode->i_list);
+	list_del_init(&inode->i_sb_list);
+	inode->i_state |= I_FREEING;
+	inodes_stat.nr_inodes--;
+	spin_unlock(&inode_lock);
+	async_schedule_special(generic_delete_inode_async, inode, &inode->i_sb->s_async_list);
+}
+
 EXPORT_SYMBOL(generic_delete_inode);
 
 static void generic_forget_inode(struct inode *inode)
diff --git a/fs/super.c b/fs/super.c
index ddba069d7a99e515f4c6bb16dd61b4b379423a9c..cb20744ec789e1dc83254f3b0912c4b1df12b49f 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -38,6 +38,7 @@
 #include <linux/kobject.h>
 #include <linux/mutex.h>
 #include <linux/file.h>
+#include <linux/async.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -71,6 +72,7 @@ static struct super_block *alloc_super(struct file_system_type *type)
 		INIT_HLIST_HEAD(&s->s_anon);
 		INIT_LIST_HEAD(&s->s_inodes);
 		INIT_LIST_HEAD(&s->s_dentry_lru);
+		INIT_LIST_HEAD(&s->s_async_list);
 		init_rwsem(&s->s_umount);
 		mutex_init(&s->s_lock);
 		lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -289,11 +291,18 @@ void generic_shutdown_super(struct super_block *sb)
 {
 	const struct super_operations *sop = sb->s_op;
 
+
 	if (sb->s_root) {
 		shrink_dcache_for_umount(sb);
 		fsync_super(sb);
 		lock_super(sb);
 		sb->s_flags &= ~MS_ACTIVE;
+
+		/*
+		 * wait for asynchronous fs operations to finish before going further
+		 */
+		async_synchronize_full_special(&sb->s_async_list);
+
 		/* bad name - it should be evict_inodes() */
 		invalidate_inodes(sb);
 		lock_kernel();
@@ -449,6 +458,7 @@ void sync_filesystems(int wait)
 		if (sb->s_flags & MS_RDONLY)
 			continue;
 		sb->s_need_sync_fs = 1;
+		async_synchronize_full_special(&sb->s_async_list);
 	}
 
 restart:
diff --git a/include/linux/async.h b/include/linux/async.h
new file mode 100644
index 0000000000000000000000000000000000000000..c4ecacd0b32771729e68b9b30f766ae55a42a8c6
--- /dev/null
+++ b/include/linux/async.h
@@ -0,0 +1,25 @@
+/*
+ * async.h: Asynchronous function calls for boot performance
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+typedef u64 async_cookie_t;
+typedef void (async_func_ptr) (void *data, async_cookie_t cookie);
+
+extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data);
+extern async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *list);
+extern void async_synchronize_full(void);
+extern void async_synchronize_full_special(struct list_head *list);
+extern void async_synchronize_cookie(async_cookie_t cookie);
+extern void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *list);
+
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d7eba77f666e9558e31061b3a63d7b5d720c4a82..e38a64d71efff910fbc9b6a8ad578a0cd509aea4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1184,6 +1184,11 @@ struct super_block {
 	 * generic_show_options()
 	 */
 	char *s_options;
+
+	/*
+	 * storage for asynchronous operations
+	 */
+	struct list_head s_async_list;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 5efca73b39f908bfbd4844c97c0a3b9dc60d8377..708105e163df8fbbbe69c7fc74a29693d6f3ed58 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/initrd.h>
+#include <linux/async.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
@@ -372,6 +373,7 @@ void __init prepare_namespace(void)
 	/* wait for the known devices to complete their probing */
 	while (driver_probe_done() != 0)
 		msleep(100);
+	async_synchronize_full();
 
 	md_run_setup();
 
diff --git a/init/main.c b/init/main.c
index 05b313283311e56119ad75c63feb83ac6c793f45..844209453c02c2248114972fca3f0fcddbdf513d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -62,6 +62,7 @@
 #include <linux/signal.h>
 #include <linux/idr.h>
 #include <linux/ftrace.h>
+#include <linux/async.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -685,7 +686,7 @@ asmlinkage void __init start_kernel(void)
 	rest_init();
 }
 
-static int initcall_debug;
+int initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
 int do_one_initcall(initcall_t fn)
@@ -786,6 +787,8 @@ static void run_init_process(char *init_filename)
  */
 static noinline int init_post(void)
 {
+	/* need to finish all async __init code before freeing the memory */
+	async_synchronize_full();
 	free_initmem();
 	unlock_kernel();
 	mark_rodata_ro();
diff --git a/kernel/Makefile b/kernel/Makefile
index e1c5bf3365c0a4cdee8e0279f31b3c6742a9c6ef..2921d90ce32fd760000622032f6569b5ab413d71 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o
+	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
+	    async.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
diff --git a/kernel/async.c b/kernel/async.c
new file mode 100644
index 0000000000000000000000000000000000000000..97373380c9e7be42ad7126c6a5d436f7954cc0aa
--- /dev/null
+++ b/kernel/async.c
@@ -0,0 +1,321 @@
+/*
+ * async.c: Asynchronous function calls for boot performance
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+
+/*
+
+Goals and Theory of Operation
+
+The primary goal of this feature is to reduce the kernel boot time,
+by doing various independent hardware delays and discovery operations
+decoupled and not strictly serialized.
+
+More specifically, the asynchronous function call concept allows
+certain operations (primarily during system boot) to happen
+asynchronously, out of order, while these operations still
+have their externally visible parts happen sequentially and in-order.
+(not unlike how out-of-order CPUs retire their instructions in order)
+
+Key to the asynchronous function call implementation is the concept of
+a "sequence cookie" (which, although it has an abstracted type, can be
+thought of as a monotonically incrementing number).
+
+The async core will assign each scheduled event such a sequence cookie and
+pass this to the called functions.
+
+The asynchronously called function should before doing a globally visible
+operation, such as registering device numbers, call the
+async_synchronize_cookie() function and pass in its own cookie. The
+async_synchronize_cookie() function will make sure that all asynchronous
+operations that were scheduled prior to the operation corresponding with the
+cookie have completed.
+
+Subsystem/driver initialization code that scheduled asynchronous probe
+functions, but which shares global resources with other drivers/subsystems
+that do not use the asynchronous call feature, need to do a full
+synchronization with the async_synchronize_full() function, before returning
+from their init function. This is to maintain strict ordering between the
+asynchronous and synchronous parts of the kernel.
+
+*/
+
+#include <linux/async.h>
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kthread.h>
+#include <asm/atomic.h>
+
+static async_cookie_t next_cookie = 1;
+
+#define MAX_THREADS	256
+#define MAX_WORK	32768
+
+static LIST_HEAD(async_pending);
+static LIST_HEAD(async_running);
+static DEFINE_SPINLOCK(async_lock);
+
+struct async_entry {
+	struct list_head list;
+	async_cookie_t   cookie;
+	async_func_ptr	 *func;
+	void             *data;
+	struct list_head *running;
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(async_done);
+static DECLARE_WAIT_QUEUE_HEAD(async_new);
+
+static atomic_t entry_count;
+static atomic_t thread_count;
+
+extern int initcall_debug;
+
+
+/*
+ * MUST be called with the lock held!
+ */
+static async_cookie_t  __lowest_in_progress(struct list_head *running)
+{
+	struct async_entry *entry;
+	if (!list_empty(&async_pending)) {
+		entry = list_first_entry(&async_pending,
+			struct async_entry, list);
+		return entry->cookie;
+	} else if (!list_empty(running)) {
+		entry = list_first_entry(running,
+			struct async_entry, list);
+		return entry->cookie;
+	} else {
+		/* nothing in progress... next_cookie is "infinity" */
+		return next_cookie;
+	}
+
+}
+/*
+ * pick the first pending entry and run it
+ */
+static void run_one_entry(void)
+{
+	unsigned long flags;
+	struct async_entry *entry;
+	ktime_t calltime, delta, rettime;
+
+	/* 1) pick one task from the pending queue */
+
+	spin_lock_irqsave(&async_lock, flags);
+	if (list_empty(&async_pending))
+		goto out;
+	entry = list_first_entry(&async_pending, struct async_entry, list);
+
+	/* 2) move it to the running queue */
+	list_del(&entry->list);
+	list_add_tail(&entry->list, &async_running);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 3) run it (and print duration)*/
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		calltime = ktime_get();
+	}
+	entry->func(entry->data, entry->cookie);
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
+			entry->func, ktime_to_ns(delta) >> 10);
+	}
+
+	/* 4) remove it from the running queue */
+	spin_lock_irqsave(&async_lock, flags);
+	list_del(&entry->list);
+
+	/* 5) free the entry  */
+	kfree(entry);
+	atomic_dec(&entry_count);
+
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 6) wake up any waiters. */
+	wake_up(&async_done);
+	return;
+
+out:
+	spin_unlock_irqrestore(&async_lock, flags);
+}
+
+
+static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	struct async_entry *entry;
+	unsigned long flags;
+	async_cookie_t newcookie;
+	
+
+	/* allow irq-off callers */
+	entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC);
+
+	/*
+	 * If we're out of memory or if there's too much work
+	 * pending already, we execute synchronously.
+	 */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		spin_lock_irqsave(&async_lock, flags);
+		newcookie = next_cookie++;
+		spin_unlock_irqrestore(&async_lock, flags);
+
+		/* low on memory.. run synchronously */
+		ptr(data, newcookie);
+		return newcookie;
+	}
+	entry->func = ptr;
+	entry->data = data;
+	entry->running = running;
+
+	spin_lock_irqsave(&async_lock, flags);
+	newcookie = entry->cookie = next_cookie++;
+	list_add_tail(&entry->list, &async_pending);
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+	wake_up(&async_new);
+	return newcookie;
+}
+
+async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
+{
+	return __async_schedule(ptr, data, &async_pending);
+}
+EXPORT_SYMBOL_GPL(async_schedule);
+
+async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	return __async_schedule(ptr, data, running);
+}
+EXPORT_SYMBOL_GPL(async_schedule_special);
+
+void async_synchronize_full(void)
+{
+	async_synchronize_cookie(next_cookie);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full);
+
+void async_synchronize_full_special(struct list_head *list)
+{
+	async_synchronize_cookie_special(next_cookie, list);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+
+void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+{
+	ktime_t starttime, delta, endtime;
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("async_waiting @ %i\n", task_pid_nr(current));
+		starttime = ktime_get();
+	}
+
+	wait_event(async_done, __lowest_in_progress(running) >= cookie);
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		endtime = ktime_get();
+		delta = ktime_sub(endtime, starttime);
+
+		printk("async_continuing @ %i after %lli usec\n",
+			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+	}
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+
+void async_synchronize_cookie(async_cookie_t cookie)
+{
+	async_synchronize_cookie_special(cookie, &async_running);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie);
+
+
+static int async_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int ret = HZ;
+		set_current_state(TASK_INTERRUPTIBLE);
+		/*
+		 * check the list head without lock.. false positives
+		 * are dealt with inside run_one_entry() while holding
+		 * the lock.
+		 */
+		rmb();
+		if (!list_empty(&async_pending))
+			run_one_entry();
+		else
+			ret = schedule_timeout(HZ);
+
+		if (ret == 0) {
+			/*
+			 * we timed out, this means we as thread are redundant.
+			 * we sign off and die, but we to avoid any races there
+			 * is a last-straw check to see if work snuck in.
+			 */
+			atomic_dec(&thread_count);
+			wmb(); /* manager must see our departure first */
+			if (list_empty(&async_pending))
+				break;
+			/*
+			 * woops work came in between us timing out and us
+			 * signing off; we need to stay alive and keep working.
+			 */
+			atomic_inc(&thread_count);
+		}
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int async_manager_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int tc, ec;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		tc = atomic_read(&thread_count);
+		rmb();
+		ec = atomic_read(&entry_count);
+
+		while (tc < ec && tc < MAX_THREADS) {
+			kthread_run(async_thread, NULL, "async/%i", tc);
+			atomic_inc(&thread_count);
+			tc++;
+		}
+
+		schedule();
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int __init async_init(void)
+{
+	kthread_run(async_manager_thread, NULL, "async/mgr");
+	return 0;
+}
+
+core_initcall(async_init);
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index cc0f7321b8cede4192a4ceb9ffc97311ec9cc7d0..1de9700f416e48e11861e08c42b0ea99216f9e42 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/async.h>
 
 #include "internals.h"
 
@@ -34,6 +35,10 @@ unsigned long probe_irq_on(void)
 	unsigned int status;
 	int i;
 
+	/*
+	 * quiesce the kernel, or at least the asynchronous portion
+	 */
+	async_synchronize_full();
 	mutex_lock(&probing_active);
 	/*
 	 * something may have generated an irq long ago and we want to
diff --git a/kernel/module.c b/kernel/module.c
index 496dcb57b608e0e6c60ebc5a1be002761bdf66a2..c9332c90d5a0dbc56dcd9d1277dcb948817b3c08 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -50,6 +50,7 @@
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
+#include <linux/async.h>
 
 #if 0
 #define DEBUGP printk
@@ -816,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	async_synchronize_full();
 	mutex_lock(&module_mutex);
 	/* Store the name of the last unloaded module for diagnostic purposes */
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));